diff --git a/3rdParty/README_maintainers.md b/3rdParty/README_maintainers.md
new file mode 100644
index 0000000000..eab216091a
--- /dev/null
+++ b/3rdParty/README_maintainers.md
@@ -0,0 +1,111 @@
+3rd Party components and what to do on update
+=============================================
+
+## asio
+
+https://think-async.com/Asio/
+
+## boost
+
+https://www.boost.org/
+
+(we don't ship the upstream documentation!)
+
+
+## catch
+
+https://github.com/catchorg/Catch2
+
+## cmake
+
+Custom boost locator
+
+## curl
+
+HTTP client library https://curl.haxx.se/
+
+We apply several build system patches to avoid unneccessary recompiles, bugfixes.
+
+
+## date
+
+Forward port of C++20 date/time class
+
+## fakeit
+
+Mocking library. https://github.com/eranpeer/FakeIt
+
+
+## fuerte
+
+Our C++ Client driver capable of velocystream. Maintained at https://github.com/arangodb/fuerte
+
+## iresearch
+
+This contains the iresearch library and its sub-components, ICU is used from V8.
+
+## iresearch.build
+
+This contains statically generated files for the IResearch folder, and replaces them.
+
+## jemalloc
+
+Only used on Linux/Mac, still uses autofoo.
+
+## linenoise-ng
+
+Our maintained fork of linenoise
+https://github.com/arangodb/linenoise-ng
+
+We may want to switch to replxx (uniting our & other forks):
+https://github.com/AmokHuginnsson/replxx
+
+
+## lz4
+
+https://github.com/lz4/lz4
+
+## rocksdb
+
+our branch is maintained at:
+https://github.com/arangodb-helper/rocksdb
+
+Most changes can be ported upstream:
+https://github.com/facebook/rocksdb
+
+On Upgrade:
+- thirdparty.inc needs to be adjusted to use the snappy we specify
+
+## s2geometry
+
+http://s2geometry.io/
+
+## snappy
+
+Compression library
+https://github.com/google/snappy
+
+## snowball
+
+http://snowball.tartarus.org/ stemming for IResearch. We use the latest provided cmake which we maintain.
+
+## V8
+
+Javascript interpreter.
+This is maintained via https://github.com/arangodb-helper/v8
+
+Upstream is: https://chromium.googlesource.com/v8/v8.git
+
+- On upgrade the ICU data file(s) need to be replaced with ICU upstream, 
+  since the V8 copy doesn't contain all locales (known as full-icu, ~25 MB icudt*.dat).
+
+## velocypack
+
+our fast and compact format for serialization and storage
+
+Maintained at:
+https://github.com/arangodb/velocypack/
+
+## zlib
+
+ZLib compression library https://zlib.net/
diff --git a/3rdParty/rocksdb/CMakeLists.txt b/3rdParty/rocksdb/CMakeLists.txt
index df339068aa..5c33be2962 100644
--- a/3rdParty/rocksdb/CMakeLists.txt
+++ b/3rdParty/rocksdb/CMakeLists.txt
@@ -4,7 +4,7 @@ project(rocksdb C CXX)
 
 set(FAIL_ON_WARNINGS OFF CACHE BOOL "do not enable -Werror")
 
-set(ARANGO_ROCKSDB_VERSION "v5.16.X")
+set(ARANGO_ROCKSDB_VERSION "v5.18.X")
 set(ARANGO_ROCKSDB_VERSION "${ARANGO_ROCKSDB_VERSION}" PARENT_SCOPE)
 
 # jemalloc settings
diff --git a/3rdParty/rocksdb/RocksDBConfig.cmake.in b/3rdParty/rocksdb/RocksDBConfig.cmake.in
index 8c4704315b..014b61dc37 120000
--- a/3rdParty/rocksdb/RocksDBConfig.cmake.in
+++ b/3rdParty/rocksdb/RocksDBConfig.cmake.in
@@ -1 +1 @@
-v5.16.X/cmake/RocksDBConfig.cmake.in
\ No newline at end of file
+v5.18.X/cmake/RocksDBConfig.cmake.in
\ No newline at end of file
diff --git a/3rdParty/rocksdb/v5.16.X/db/error_handler.h b/3rdParty/rocksdb/v5.16.X/db/error_handler.h
deleted file mode 100644
index 8a1a411fc8..0000000000
--- a/3rdParty/rocksdb/v5.16.X/db/error_handler.h
+++ /dev/null
@@ -1,52 +0,0 @@
-//  Copyright (c) 2018-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-#pragma once
-
-#include "monitoring/instrumented_mutex.h"
-#include "options/db_options.h"
-#include "rocksdb/listener.h"
-#include "rocksdb/status.h"
-
-namespace rocksdb {
-
-class ErrorHandler {
-  public:
-    ErrorHandler(const ImmutableDBOptions& db_options,
-        InstrumentedMutex* db_mutex)
-      : db_options_(db_options),
-        bg_error_(Status::OK()),
-        db_mutex_(db_mutex)
-      {}
-    ~ErrorHandler() {}
-
-    Status::Severity GetErrorSeverity(BackgroundErrorReason reason,
-        Status::Code code, Status::SubCode subcode);
-
-    Status SetBGError(const Status& bg_err, BackgroundErrorReason reason);
-
-    Status GetBGError()
-    {
-      return bg_error_;
-    }
-
-    void ClearBGError() {
-      bg_error_ = Status::OK();
-    }
-
-    bool IsDBStopped() {
-      return !bg_error_.ok();
-    }
-
-    bool IsBGWorkStopped() {
-      return !bg_error_.ok();
-    }
-
-  private:
-    const ImmutableDBOptions& db_options_;
-    Status bg_error_;
-    InstrumentedMutex* db_mutex_;
-};
-
-}
diff --git a/3rdParty/rocksdb/v5.16.X/db/error_handler_test.cc b/3rdParty/rocksdb/v5.16.X/db/error_handler_test.cc
deleted file mode 100644
index abd5663d8d..0000000000
--- a/3rdParty/rocksdb/v5.16.X/db/error_handler_test.cc
+++ /dev/null
@@ -1,138 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-#include "rocksdb/perf_context.h"
-#include "util/fault_injection_test_env.h"
-#if !defined(ROCKSDB_LITE)
-#include "util/sync_point.h"
-#endif
-
-namespace rocksdb {
-
-class DBErrorHandlingTest : public DBTestBase {
- public:
-  DBErrorHandlingTest() : DBTestBase("/db_error_handling_test") {}
-};
-
-class DBErrorHandlingEnv : public EnvWrapper {
-  public:
-    DBErrorHandlingEnv() : EnvWrapper(Env::Default()),
-      trig_no_space(false), trig_io_error(false) {}
-
-    void SetTrigNoSpace() {trig_no_space = true;}
-    void SetTrigIoError() {trig_io_error = true;}
-  private:
-    bool trig_no_space;
-    bool trig_io_error;
-};
-
-TEST_F(DBErrorHandlingTest, FLushWriteError) {
-  std::unique_ptr<FaultInjectionTestEnv> fault_env(
-      new FaultInjectionTestEnv(Env::Default()));
-  Options options = GetDefaultOptions();
-  options.create_if_missing = true;
-  options.env = fault_env.get();
-  Status s;
-  DestroyAndReopen(options);
-
-  Put(Key(0), "va;");
-  SyncPoint::GetInstance()->SetCallBack(
-      "FlushJob::Start", [&](void *) {
-    fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
-  });
-  SyncPoint::GetInstance()->EnableProcessing();
-  s = Flush();
-  ASSERT_EQ(s.severity(), rocksdb::Status::Severity::kSoftError);
-  fault_env->SetFilesystemActive(true);
-  s = dbfull()->Resume();
-  ASSERT_EQ(s, Status::OK());
-
-  Destroy(options);
-}
-
-TEST_F(DBErrorHandlingTest, CompactionWriteError) {
-  std::unique_ptr<FaultInjectionTestEnv> fault_env(
-      new FaultInjectionTestEnv(Env::Default()));
-  Options options = GetDefaultOptions();
-  options.create_if_missing = true;
-  options.level0_file_num_compaction_trigger = 2;
-  options.env = fault_env.get();
-  Status s;
-  DestroyAndReopen(options);
-
-  Put(Key(0), "va;");
-  Put(Key(2), "va;");
-  s = Flush();
-  ASSERT_EQ(s, Status::OK());
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency(
-      {{"FlushMemTableFinished", "BackgroundCallCompaction:0"}});
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "BackgroundCallCompaction:0", [&](void *) {
-      fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  Put(Key(1), "val");
-  s = Flush();
-  ASSERT_EQ(s, Status::OK());
-
-  s = dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(s.severity(), rocksdb::Status::Severity::kSoftError);
-
-  fault_env->SetFilesystemActive(true);
-  s = dbfull()->Resume();
-  ASSERT_EQ(s, Status::OK());
-  Destroy(options);
-}
-
-TEST_F(DBErrorHandlingTest, CorruptionError) {
-  std::unique_ptr<FaultInjectionTestEnv> fault_env(
-      new FaultInjectionTestEnv(Env::Default()));
-  Options options = GetDefaultOptions();
-  options.create_if_missing = true;
-  options.level0_file_num_compaction_trigger = 2;
-  options.env = fault_env.get();
-  Status s;
-  DestroyAndReopen(options);
-
-  Put(Key(0), "va;");
-  Put(Key(2), "va;");
-  s = Flush();
-  ASSERT_EQ(s, Status::OK());
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency(
-      {{"FlushMemTableFinished", "BackgroundCallCompaction:0"}});
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "BackgroundCallCompaction:0", [&](void *) {
-      fault_env->SetFilesystemActive(false, Status::Corruption("Corruption"));
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  Put(Key(1), "val");
-  s = Flush();
-  ASSERT_EQ(s, Status::OK());
-
-  s = dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(s.severity(), rocksdb::Status::Severity::kUnrecoverableError);
-
-  fault_env->SetFilesystemActive(true);
-  s = dbfull()->Resume();
-  ASSERT_NE(s, Status::OK());
-  Destroy(options);
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
diff --git a/3rdParty/rocksdb/v5.16.X/db/flush_job_test.cc b/3rdParty/rocksdb/v5.16.X/db/flush_job_test.cc
deleted file mode 100644
index 324037478a..0000000000
--- a/3rdParty/rocksdb/v5.16.X/db/flush_job_test.cc
+++ /dev/null
@@ -1,238 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#include <algorithm>
-#include <map>
-#include <string>
-
-#include "db/column_family.h"
-#include "db/flush_job.h"
-#include "db/version_set.h"
-#include "rocksdb/cache.h"
-#include "rocksdb/write_buffer_manager.h"
-#include "table/mock_table.h"
-#include "util/file_reader_writer.h"
-#include "util/string_util.h"
-#include "util/testharness.h"
-#include "util/testutil.h"
-
-namespace rocksdb {
-
-// TODO(icanadi) Mock out everything else:
-// 1. VersionSet
-// 2. Memtable
-class FlushJobTest : public testing::Test {
- public:
-  FlushJobTest()
-      : env_(Env::Default()),
-        dbname_(test::PerThreadDBPath("flush_job_test")),
-        options_(),
-        db_options_(options_),
-        table_cache_(NewLRUCache(50000, 16)),
-        write_buffer_manager_(db_options_.db_write_buffer_size),
-        versions_(new VersionSet(dbname_, &db_options_, env_options_,
-                                 table_cache_.get(), &write_buffer_manager_,
-                                 &write_controller_)),
-        shutting_down_(false),
-        mock_table_factory_(new mock::MockTableFactory()) {
-    EXPECT_OK(env_->CreateDirIfMissing(dbname_));
-    db_options_.db_paths.emplace_back(dbname_,
-                                      std::numeric_limits<uint64_t>::max());
-    db_options_.statistics = rocksdb::CreateDBStatistics();
-    // TODO(icanadi) Remove this once we mock out VersionSet
-    NewDB();
-    std::vector<ColumnFamilyDescriptor> column_families;
-    cf_options_.table_factory = mock_table_factory_;
-    column_families.emplace_back(kDefaultColumnFamilyName, cf_options_);
-
-    EXPECT_OK(versions_->Recover(column_families, false));
-  }
-
-  void NewDB() {
-    VersionEdit new_db;
-    new_db.SetLogNumber(0);
-    new_db.SetNextFile(2);
-    new_db.SetLastSequence(0);
-
-    const std::string manifest = DescriptorFileName(dbname_, 1);
-    unique_ptr<WritableFile> file;
-    Status s = env_->NewWritableFile(
-        manifest, &file, env_->OptimizeForManifestWrite(env_options_));
-    ASSERT_OK(s);
-    unique_ptr<WritableFileWriter> file_writer(
-        new WritableFileWriter(std::move(file), EnvOptions()));
-    {
-      log::Writer log(std::move(file_writer), 0, false);
-      std::string record;
-      new_db.EncodeTo(&record);
-      s = log.AddRecord(record);
-    }
-    ASSERT_OK(s);
-    // Make "CURRENT" file that points to the new manifest file.
-    s = SetCurrentFile(env_, dbname_, 1, nullptr);
-  }
-
-  Env* env_;
-  std::string dbname_;
-  EnvOptions env_options_;
-  Options options_;
-  ImmutableDBOptions db_options_;
-  std::shared_ptr<Cache> table_cache_;
-  WriteController write_controller_;
-  WriteBufferManager write_buffer_manager_;
-  ColumnFamilyOptions cf_options_;
-  std::unique_ptr<VersionSet> versions_;
-  InstrumentedMutex mutex_;
-  std::atomic<bool> shutting_down_;
-  std::shared_ptr<mock::MockTableFactory> mock_table_factory_;
-};
-
-TEST_F(FlushJobTest, Empty) {
-  JobContext job_context(0);
-  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-  EventLogger event_logger(db_options_.info_log.get());
-  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
-  FlushJob flush_job(
-      dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
-      *cfd->GetLatestMutableCFOptions(), env_options_, versions_.get(), &mutex_,
-      &shutting_down_, {}, kMaxSequenceNumber, snapshot_checker, &job_context,
-      nullptr, nullptr, nullptr, kNoCompression, nullptr, &event_logger, false);
-  {
-    InstrumentedMutexLock l(&mutex_);
-    flush_job.PickMemTable();
-    ASSERT_OK(flush_job.Run());
-  }
-  job_context.Clean();
-}
-
-TEST_F(FlushJobTest, NonEmpty) {
-  JobContext job_context(0);
-  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-  auto new_mem = cfd->ConstructNewMemtable(*cfd->GetLatestMutableCFOptions(),
-                                           kMaxSequenceNumber);
-  new_mem->Ref();
-  auto inserted_keys = mock::MakeMockFile();
-  // Test data:
-  //   seqno [    1,    2 ... 8998, 8999, 9000, 9001, 9002 ... 9999 ]
-  //   key   [ 1001, 1002 ... 9998, 9999,    0,    1,    2 ...  999 ]
-  //   range-delete "9995" -> "9999" at seqno 10000
-  for (int i = 1; i < 10000; ++i) {
-    std::string key(ToString((i + 1000) % 10000));
-    std::string value("value" + key);
-    new_mem->Add(SequenceNumber(i), kTypeValue, key, value);
-    if ((i + 1000) % 10000 < 9995) {
-      InternalKey internal_key(key, SequenceNumber(i), kTypeValue);
-      inserted_keys.insert({internal_key.Encode().ToString(), value});
-    }
-  }
-  new_mem->Add(SequenceNumber(10000), kTypeRangeDeletion, "9995", "9999a");
-  InternalKey internal_key("9995", SequenceNumber(10000), kTypeRangeDeletion);
-  inserted_keys.insert({internal_key.Encode().ToString(), "9999a"});
-
-  autovector<MemTable*> to_delete;
-  cfd->imm()->Add(new_mem, &to_delete);
-  for (auto& m : to_delete) {
-    delete m;
-  }
-
-  EventLogger event_logger(db_options_.info_log.get());
-  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
-  FlushJob flush_job(dbname_, versions_->GetColumnFamilySet()->GetDefault(),
-                     db_options_, *cfd->GetLatestMutableCFOptions(),
-                     env_options_, versions_.get(), &mutex_, &shutting_down_,
-                     {}, kMaxSequenceNumber, snapshot_checker, &job_context,
-                     nullptr, nullptr, nullptr, kNoCompression,
-                     db_options_.statistics.get(), &event_logger, true);
-
-  HistogramData hist;
-  FileMetaData file_meta;
-  mutex_.Lock();
-  flush_job.PickMemTable();
-  ASSERT_OK(flush_job.Run(nullptr, &file_meta));
-  mutex_.Unlock();
-  db_options_.statistics->histogramData(FLUSH_TIME, &hist);
-  ASSERT_GT(hist.average, 0.0);
-
-  ASSERT_EQ(ToString(0), file_meta.smallest.user_key().ToString());
-  ASSERT_EQ(
-      "9999a",
-      file_meta.largest.user_key().ToString());  // range tombstone end key
-  ASSERT_EQ(1, file_meta.fd.smallest_seqno);
-  ASSERT_EQ(10000, file_meta.fd.largest_seqno);  // range tombstone seqnum 10000
-  mock_table_factory_->AssertSingleFile(inserted_keys);
-  job_context.Clean();
-}
-
-TEST_F(FlushJobTest, Snapshots) {
-  JobContext job_context(0);
-  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-  auto new_mem = cfd->ConstructNewMemtable(*cfd->GetLatestMutableCFOptions(),
-                                           kMaxSequenceNumber);
-
-  std::vector<SequenceNumber> snapshots;
-  std::set<SequenceNumber> snapshots_set;
-  int keys = 10000;
-  int max_inserts_per_keys = 8;
-
-  Random rnd(301);
-  for (int i = 0; i < keys / 2; ++i) {
-    snapshots.push_back(rnd.Uniform(keys * (max_inserts_per_keys / 2)) + 1);
-    snapshots_set.insert(snapshots.back());
-  }
-  std::sort(snapshots.begin(), snapshots.end());
-
-  new_mem->Ref();
-  SequenceNumber current_seqno = 0;
-  auto inserted_keys = mock::MakeMockFile();
-  for (int i = 1; i < keys; ++i) {
-    std::string key(ToString(i));
-    int insertions = rnd.Uniform(max_inserts_per_keys);
-    for (int j = 0; j < insertions; ++j) {
-      std::string value(test::RandomHumanReadableString(&rnd, 10));
-      auto seqno = ++current_seqno;
-      new_mem->Add(SequenceNumber(seqno), kTypeValue, key, value);
-      // a key is visible only if:
-      // 1. it's the last one written (j == insertions - 1)
-      // 2. there's a snapshot pointing at it
-      bool visible = (j == insertions - 1) ||
-                     (snapshots_set.find(seqno) != snapshots_set.end());
-      if (visible) {
-        InternalKey internal_key(key, seqno, kTypeValue);
-        inserted_keys.insert({internal_key.Encode().ToString(), value});
-      }
-    }
-  }
-
-  autovector<MemTable*> to_delete;
-  cfd->imm()->Add(new_mem, &to_delete);
-  for (auto& m : to_delete) {
-    delete m;
-  }
-
-  EventLogger event_logger(db_options_.info_log.get());
-  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
-  FlushJob flush_job(dbname_, versions_->GetColumnFamilySet()->GetDefault(),
-                     db_options_, *cfd->GetLatestMutableCFOptions(),
-                     env_options_, versions_.get(), &mutex_, &shutting_down_,
-                     snapshots, kMaxSequenceNumber, snapshot_checker,
-                     &job_context, nullptr, nullptr, nullptr, kNoCompression,
-                     db_options_.statistics.get(), &event_logger, true);
-  mutex_.Lock();
-  flush_job.PickMemTable();
-  ASSERT_OK(flush_job.Run());
-  mutex_.Unlock();
-  mock_table_factory_->AssertSingleFile(inserted_keys);
-  HistogramData hist;
-  db_options_.statistics->histogramData(FLUSH_TIME, &hist);
-  ASSERT_GT(hist.average, 0.0);
-  job_context.Clean();
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
diff --git a/3rdParty/rocksdb/v5.16.X/db/memtable_list_test.cc b/3rdParty/rocksdb/v5.16.X/db/memtable_list_test.cc
deleted file mode 100644
index 009a718862..0000000000
--- a/3rdParty/rocksdb/v5.16.X/db/memtable_list_test.cc
+++ /dev/null
@@ -1,615 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#include "db/memtable_list.h"
-#include <algorithm>
-#include <string>
-#include <vector>
-#include "db/merge_context.h"
-#include "db/range_del_aggregator.h"
-#include "db/version_set.h"
-#include "db/write_controller.h"
-#include "rocksdb/db.h"
-#include "rocksdb/status.h"
-#include "rocksdb/write_buffer_manager.h"
-#include "util/string_util.h"
-#include "util/testharness.h"
-#include "util/testutil.h"
-
-namespace rocksdb {
-
-class MemTableListTest : public testing::Test {
- public:
-  std::string dbname;
-  DB* db;
-  Options options;
-
-  MemTableListTest() : db(nullptr) {
-    dbname = test::PerThreadDBPath("memtable_list_test");
-  }
-
-  // Create a test db if not yet created
-  void CreateDB() {
-    if (db == nullptr) {
-      options.create_if_missing = true;
-      DestroyDB(dbname, options);
-      Status s = DB::Open(options, dbname, &db);
-      EXPECT_OK(s);
-    }
-  }
-
-  ~MemTableListTest() {
-    if (db) {
-      delete db;
-      DestroyDB(dbname, options);
-    }
-  }
-
-  // Calls MemTableList::InstallMemtableFlushResults() and sets up all
-  // structures needed to call this function.
-  Status Mock_InstallMemtableFlushResults(
-      MemTableList* list, const MutableCFOptions& mutable_cf_options,
-      const autovector<MemTable*>& m, autovector<MemTable*>* to_delete) {
-    // Create a mock Logger
-    test::NullLogger logger;
-    LogBuffer log_buffer(DEBUG_LEVEL, &logger);
-
-    // Create a mock VersionSet
-    DBOptions db_options;
-    ImmutableDBOptions immutable_db_options(db_options);
-    EnvOptions env_options;
-    shared_ptr<Cache> table_cache(NewLRUCache(50000, 16));
-    WriteBufferManager write_buffer_manager(db_options.db_write_buffer_size);
-    WriteController write_controller(10000000u);
-
-    CreateDB();
-    VersionSet versions(dbname, &immutable_db_options, env_options,
-                        table_cache.get(), &write_buffer_manager,
-                        &write_controller);
-
-    // Create mock default ColumnFamilyData
-    ColumnFamilyOptions cf_options;
-    std::vector<ColumnFamilyDescriptor> column_families;
-    column_families.emplace_back(kDefaultColumnFamilyName, cf_options);
-    EXPECT_OK(versions.Recover(column_families, false));
-
-    auto column_family_set = versions.GetColumnFamilySet();
-    auto cfd = column_family_set->GetColumnFamily(0);
-    EXPECT_TRUE(cfd != nullptr);
-
-    // Create dummy mutex.
-    InstrumentedMutex mutex;
-    InstrumentedMutexLock l(&mutex);
-    LogsWithPrepTracker dummy_prep_tracker;
-    return list->InstallMemtableFlushResults(
-        cfd, mutable_cf_options, m, &dummy_prep_tracker, &versions, &mutex, 1,
-        to_delete, nullptr, &log_buffer);
-  }
-};
-
-TEST_F(MemTableListTest, Empty) {
-  // Create an empty MemTableList and validate basic functions.
-  MemTableList list(1, 0);
-
-  ASSERT_EQ(0, list.NumNotFlushed());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-  ASSERT_FALSE(list.IsFlushPending());
-
-  autovector<MemTable*> mems;
-  list.PickMemtablesToFlush(&mems);
-  ASSERT_EQ(0, mems.size());
-
-  autovector<MemTable*> to_delete;
-  list.current()->Unref(&to_delete);
-  ASSERT_EQ(0, to_delete.size());
-}
-
-TEST_F(MemTableListTest, GetTest) {
-  // Create MemTableList
-  int min_write_buffer_number_to_merge = 2;
-  int max_write_buffer_number_to_maintain = 0;
-  MemTableList list(min_write_buffer_number_to_merge,
-                    max_write_buffer_number_to_maintain);
-
-  SequenceNumber seq = 1;
-  std::string value;
-  Status s;
-  MergeContext merge_context;
-  InternalKeyComparator ikey_cmp(options.comparator);
-  RangeDelAggregator range_del_agg(ikey_cmp, {} /* snapshots */);
-  autovector<MemTable*> to_delete;
-
-  LookupKey lkey("key1", seq);
-  bool found = list.current()->Get(lkey, &value, &s, &merge_context,
-                                   &range_del_agg, ReadOptions());
-  ASSERT_FALSE(found);
-
-  // Create a MemTable
-  InternalKeyComparator cmp(BytewiseComparator());
-  auto factory = std::make_shared<SkipListFactory>();
-  options.memtable_factory = factory;
-  ImmutableCFOptions ioptions(options);
-
-  WriteBufferManager wb(options.db_write_buffer_size);
-  MemTable* mem = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb,
-                               kMaxSequenceNumber, 0 /* column_family_id */);
-  mem->Ref();
-
-  // Write some keys to this memtable.
-  mem->Add(++seq, kTypeDeletion, "key1", "");
-  mem->Add(++seq, kTypeValue, "key2", "value2");
-  mem->Add(++seq, kTypeValue, "key1", "value1");
-  mem->Add(++seq, kTypeValue, "key2", "value2.2");
-
-  // Fetch the newly written keys
-  merge_context.Clear();
-  found = mem->Get(LookupKey("key1", seq), &value, &s, &merge_context,
-                   &range_del_agg, ReadOptions());
-  ASSERT_TRUE(s.ok() && found);
-  ASSERT_EQ(value, "value1");
-
-  merge_context.Clear();
-  found = mem->Get(LookupKey("key1", 2), &value, &s, &merge_context,
-                   &range_del_agg, ReadOptions());
-  // MemTable found out that this key is *not* found (at this sequence#)
-  ASSERT_TRUE(found && s.IsNotFound());
-
-  merge_context.Clear();
-  found = mem->Get(LookupKey("key2", seq), &value, &s, &merge_context,
-                   &range_del_agg, ReadOptions());
-  ASSERT_TRUE(s.ok() && found);
-  ASSERT_EQ(value, "value2.2");
-
-  ASSERT_EQ(4, mem->num_entries());
-  ASSERT_EQ(1, mem->num_deletes());
-
-  // Add memtable to list
-  list.Add(mem, &to_delete);
-
-  SequenceNumber saved_seq = seq;
-
-  // Create another memtable and write some keys to it
-  WriteBufferManager wb2(options.db_write_buffer_size);
-  MemTable* mem2 = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb2,
-                                kMaxSequenceNumber, 0 /* column_family_id */);
-  mem2->Ref();
-
-  mem2->Add(++seq, kTypeDeletion, "key1", "");
-  mem2->Add(++seq, kTypeValue, "key2", "value2.3");
-
-  // Add second memtable to list
-  list.Add(mem2, &to_delete);
-
-  // Fetch keys via MemTableList
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key1", seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_TRUE(found && s.IsNotFound());
-
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key1", saved_seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_TRUE(s.ok() && found);
-  ASSERT_EQ("value1", value);
-
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key2", seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_TRUE(s.ok() && found);
-  ASSERT_EQ(value, "value2.3");
-
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key2", 1), &value, &s, &merge_context,
-                              &range_del_agg, ReadOptions());
-  ASSERT_FALSE(found);
-
-  ASSERT_EQ(2, list.NumNotFlushed());
-
-  list.current()->Unref(&to_delete);
-  for (MemTable* m : to_delete) {
-    delete m;
-  }
-}
-
-TEST_F(MemTableListTest, GetFromHistoryTest) {
-  // Create MemTableList
-  int min_write_buffer_number_to_merge = 2;
-  int max_write_buffer_number_to_maintain = 2;
-  MemTableList list(min_write_buffer_number_to_merge,
-                    max_write_buffer_number_to_maintain);
-
-  SequenceNumber seq = 1;
-  std::string value;
-  Status s;
-  MergeContext merge_context;
-  InternalKeyComparator ikey_cmp(options.comparator);
-  RangeDelAggregator range_del_agg(ikey_cmp, {} /* snapshots */);
-  autovector<MemTable*> to_delete;
-
-  LookupKey lkey("key1", seq);
-  bool found = list.current()->Get(lkey, &value, &s, &merge_context,
-                                   &range_del_agg, ReadOptions());
-  ASSERT_FALSE(found);
-
-  // Create a MemTable
-  InternalKeyComparator cmp(BytewiseComparator());
-  auto factory = std::make_shared<SkipListFactory>();
-  options.memtable_factory = factory;
-  ImmutableCFOptions ioptions(options);
-
-  WriteBufferManager wb(options.db_write_buffer_size);
-  MemTable* mem = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb,
-                               kMaxSequenceNumber, 0 /* column_family_id */);
-  mem->Ref();
-
-  // Write some keys to this memtable.
-  mem->Add(++seq, kTypeDeletion, "key1", "");
-  mem->Add(++seq, kTypeValue, "key2", "value2");
-  mem->Add(++seq, kTypeValue, "key2", "value2.2");
-
-  // Fetch the newly written keys
-  merge_context.Clear();
-  found = mem->Get(LookupKey("key1", seq), &value, &s, &merge_context,
-                   &range_del_agg, ReadOptions());
-  // MemTable found out that this key is *not* found (at this sequence#)
-  ASSERT_TRUE(found && s.IsNotFound());
-
-  merge_context.Clear();
-  found = mem->Get(LookupKey("key2", seq), &value, &s, &merge_context,
-                   &range_del_agg, ReadOptions());
-  ASSERT_TRUE(s.ok() && found);
-  ASSERT_EQ(value, "value2.2");
-
-  // Add memtable to list
-  list.Add(mem, &to_delete);
-  ASSERT_EQ(0, to_delete.size());
-
-  // Fetch keys via MemTableList
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key1", seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_TRUE(found && s.IsNotFound());
-
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key2", seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_TRUE(s.ok() && found);
-  ASSERT_EQ("value2.2", value);
-
-  // Flush this memtable from the list.
-  // (It will then be a part of the memtable history).
-  autovector<MemTable*> to_flush;
-  list.PickMemtablesToFlush(&to_flush);
-  ASSERT_EQ(1, to_flush.size());
-
-  s = Mock_InstallMemtableFlushResults(&list, MutableCFOptions(options),
-                                       to_flush, &to_delete);
-  ASSERT_OK(s);
-  ASSERT_EQ(0, list.NumNotFlushed());
-  ASSERT_EQ(1, list.NumFlushed());
-  ASSERT_EQ(0, to_delete.size());
-
-  // Verify keys are no longer in MemTableList
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key1", seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_FALSE(found);
-
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key2", seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_FALSE(found);
-
-  // Verify keys are present in history
-  merge_context.Clear();
-  found = list.current()->GetFromHistory(LookupKey("key1", seq), &value, &s,
-                                         &merge_context, &range_del_agg,
-                                         ReadOptions());
-  ASSERT_TRUE(found && s.IsNotFound());
-
-  merge_context.Clear();
-  found = list.current()->GetFromHistory(LookupKey("key2", seq), &value, &s,
-                                         &merge_context, &range_del_agg,
-                                         ReadOptions());
-  ASSERT_TRUE(found);
-  ASSERT_EQ("value2.2", value);
-
-  // Create another memtable and write some keys to it
-  WriteBufferManager wb2(options.db_write_buffer_size);
-  MemTable* mem2 = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb2,
-                                kMaxSequenceNumber, 0 /* column_family_id */);
-  mem2->Ref();
-
-  mem2->Add(++seq, kTypeDeletion, "key1", "");
-  mem2->Add(++seq, kTypeValue, "key3", "value3");
-
-  // Add second memtable to list
-  list.Add(mem2, &to_delete);
-  ASSERT_EQ(0, to_delete.size());
-
-  to_flush.clear();
-  list.PickMemtablesToFlush(&to_flush);
-  ASSERT_EQ(1, to_flush.size());
-
-  // Flush second memtable
-  s = Mock_InstallMemtableFlushResults(&list, MutableCFOptions(options),
-                                       to_flush, &to_delete);
-  ASSERT_OK(s);
-  ASSERT_EQ(0, list.NumNotFlushed());
-  ASSERT_EQ(2, list.NumFlushed());
-  ASSERT_EQ(0, to_delete.size());
-
-  // Add a third memtable to push the first memtable out of the history
-  WriteBufferManager wb3(options.db_write_buffer_size);
-  MemTable* mem3 = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb3,
-                                kMaxSequenceNumber, 0 /* column_family_id */);
-  mem3->Ref();
-  list.Add(mem3, &to_delete);
-  ASSERT_EQ(1, list.NumNotFlushed());
-  ASSERT_EQ(1, list.NumFlushed());
-  ASSERT_EQ(1, to_delete.size());
-
-  // Verify keys are no longer in MemTableList
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key1", seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_FALSE(found);
-
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key2", seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_FALSE(found);
-
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key3", seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_FALSE(found);
-
-  // Verify that the second memtable's keys are in the history
-  merge_context.Clear();
-  found = list.current()->GetFromHistory(LookupKey("key1", seq), &value, &s,
-                                         &merge_context, &range_del_agg,
-                                         ReadOptions());
-  ASSERT_TRUE(found && s.IsNotFound());
-
-  merge_context.Clear();
-  found = list.current()->GetFromHistory(LookupKey("key3", seq), &value, &s,
-                                         &merge_context, &range_del_agg,
-                                         ReadOptions());
-  ASSERT_TRUE(found);
-  ASSERT_EQ("value3", value);
-
-  // Verify that key2 from the first memtable is no longer in the history
-  merge_context.Clear();
-  found = list.current()->Get(LookupKey("key2", seq), &value, &s,
-                              &merge_context, &range_del_agg, ReadOptions());
-  ASSERT_FALSE(found);
-
-  // Cleanup
-  list.current()->Unref(&to_delete);
-  ASSERT_EQ(3, to_delete.size());
-  for (MemTable* m : to_delete) {
-    delete m;
-  }
-}
-
-TEST_F(MemTableListTest, FlushPendingTest) {
-  const int num_tables = 5;
-  SequenceNumber seq = 1;
-  Status s;
-
-  auto factory = std::make_shared<SkipListFactory>();
-  options.memtable_factory = factory;
-  ImmutableCFOptions ioptions(options);
-  InternalKeyComparator cmp(BytewiseComparator());
-  WriteBufferManager wb(options.db_write_buffer_size);
-  autovector<MemTable*> to_delete;
-
-  // Create MemTableList
-  int min_write_buffer_number_to_merge = 3;
-  int max_write_buffer_number_to_maintain = 7;
-  MemTableList list(min_write_buffer_number_to_merge,
-                    max_write_buffer_number_to_maintain);
-
-  // Create some MemTables
-  std::vector<MemTable*> tables;
-  MutableCFOptions mutable_cf_options(options);
-  for (int i = 0; i < num_tables; i++) {
-    MemTable* mem = new MemTable(cmp, ioptions, mutable_cf_options, &wb,
-                                 kMaxSequenceNumber, 0 /* column_family_id */);
-    mem->Ref();
-
-    std::string value;
-    MergeContext merge_context;
-
-    mem->Add(++seq, kTypeValue, "key1", ToString(i));
-    mem->Add(++seq, kTypeValue, "keyN" + ToString(i), "valueN");
-    mem->Add(++seq, kTypeValue, "keyX" + ToString(i), "value");
-    mem->Add(++seq, kTypeValue, "keyM" + ToString(i), "valueM");
-    mem->Add(++seq, kTypeDeletion, "keyX" + ToString(i), "");
-
-    tables.push_back(mem);
-  }
-
-  // Nothing to flush
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-  autovector<MemTable*> to_flush;
-  list.PickMemtablesToFlush(&to_flush);
-  ASSERT_EQ(0, to_flush.size());
-
-  // Request a flush even though there is nothing to flush
-  list.FlushRequested();
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Attempt to 'flush' to clear request for flush
-  list.PickMemtablesToFlush(&to_flush);
-  ASSERT_EQ(0, to_flush.size());
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Request a flush again
-  list.FlushRequested();
-  // No flush pending since the list is empty.
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Add 2 tables
-  list.Add(tables[0], &to_delete);
-  list.Add(tables[1], &to_delete);
-  ASSERT_EQ(2, list.NumNotFlushed());
-  ASSERT_EQ(0, to_delete.size());
-
-  // Even though we have less than the minimum to flush, a flush is
-  // pending since we had previously requested a flush and never called
-  // PickMemtablesToFlush() to clear the flush.
-  ASSERT_TRUE(list.IsFlushPending());
-  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Pick tables to flush
-  list.PickMemtablesToFlush(&to_flush);
-  ASSERT_EQ(2, to_flush.size());
-  ASSERT_EQ(2, list.NumNotFlushed());
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Revert flush
-  list.RollbackMemtableFlush(to_flush, 0);
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
-  to_flush.clear();
-
-  // Add another table
-  list.Add(tables[2], &to_delete);
-  // We now have the minimum to flush regardles of whether FlushRequested()
-  // was called.
-  ASSERT_TRUE(list.IsFlushPending());
-  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
-  ASSERT_EQ(0, to_delete.size());
-
-  // Pick tables to flush
-  list.PickMemtablesToFlush(&to_flush);
-  ASSERT_EQ(3, to_flush.size());
-  ASSERT_EQ(3, list.NumNotFlushed());
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Pick tables to flush again
-  autovector<MemTable*> to_flush2;
-  list.PickMemtablesToFlush(&to_flush2);
-  ASSERT_EQ(0, to_flush2.size());
-  ASSERT_EQ(3, list.NumNotFlushed());
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Add another table
-  list.Add(tables[3], &to_delete);
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
-  ASSERT_EQ(0, to_delete.size());
-
-  // Request a flush again
-  list.FlushRequested();
-  ASSERT_TRUE(list.IsFlushPending());
-  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Pick tables to flush again
-  list.PickMemtablesToFlush(&to_flush2);
-  ASSERT_EQ(1, to_flush2.size());
-  ASSERT_EQ(4, list.NumNotFlushed());
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Rollback first pick of tables
-  list.RollbackMemtableFlush(to_flush, 0);
-  ASSERT_TRUE(list.IsFlushPending());
-  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
-  to_flush.clear();
-
-  // Add another tables
-  list.Add(tables[4], &to_delete);
-  ASSERT_EQ(5, list.NumNotFlushed());
-  // We now have the minimum to flush regardles of whether FlushRequested()
-  ASSERT_TRUE(list.IsFlushPending());
-  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
-  ASSERT_EQ(0, to_delete.size());
-
-  // Pick tables to flush
-  list.PickMemtablesToFlush(&to_flush);
-  // Should pick 4 of 5 since 1 table has been picked in to_flush2
-  ASSERT_EQ(4, to_flush.size());
-  ASSERT_EQ(5, list.NumNotFlushed());
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Pick tables to flush again
-  autovector<MemTable*> to_flush3;
-  ASSERT_EQ(0, to_flush3.size());  // nothing not in progress of being flushed
-  ASSERT_EQ(5, list.NumNotFlushed());
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Flush the 4 memtables that were picked in to_flush
-  s = Mock_InstallMemtableFlushResults(&list, MutableCFOptions(options),
-                                       to_flush, &to_delete);
-  ASSERT_OK(s);
-
-  // Note:  now to_flush contains tables[0,1,2,4].  to_flush2 contains
-  // tables[3].
-  // Current implementation will only commit memtables in the order they were
-  // created.  So InstallMemtableFlushResults will install the first 3 tables
-  // in to_flush and stop when it encounters a table not yet flushed.
-  ASSERT_EQ(2, list.NumNotFlushed());
-  int num_in_history = std::min(3, max_write_buffer_number_to_maintain);
-  ASSERT_EQ(num_in_history, list.NumFlushed());
-  ASSERT_EQ(5 - list.NumNotFlushed() - num_in_history, to_delete.size());
-
-  // Request a flush again. Should be nothing to flush
-  list.FlushRequested();
-  ASSERT_FALSE(list.IsFlushPending());
-  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
-
-  // Flush the 1 memtable that was picked in to_flush2
-  s = MemTableListTest::Mock_InstallMemtableFlushResults(
-      &list, MutableCFOptions(options), to_flush2, &to_delete);
-  ASSERT_OK(s);
-
-  // This will actually install 2 tables.  The 1 we told it to flush, and also
-  // tables[4] which has been waiting for tables[3] to commit.
-  ASSERT_EQ(0, list.NumNotFlushed());
-  num_in_history = std::min(5, max_write_buffer_number_to_maintain);
-  ASSERT_EQ(num_in_history, list.NumFlushed());
-  ASSERT_EQ(5 - list.NumNotFlushed() - num_in_history, to_delete.size());
-
-  for (const auto& m : to_delete) {
-    // Refcount should be 0 after calling InstallMemtableFlushResults.
-    // Verify this, by Ref'ing then UnRef'ing:
-    m->Ref();
-    ASSERT_EQ(m, m->Unref());
-    delete m;
-  }
-  to_delete.clear();
-
-  list.current()->Unref(&to_delete);
-  int to_delete_size = std::min(5, max_write_buffer_number_to_maintain);
-  ASSERT_EQ(to_delete_size, to_delete.size());
-
-  for (const auto& m : to_delete) {
-    // Refcount should be 0 after calling InstallMemtableFlushResults.
-    // Verify this, by Ref'ing then UnRef'ing:
-    m->Ref();
-    ASSERT_EQ(m, m->Unref());
-    delete m;
-  }
-  to_delete.clear();
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/table_properties_collectors.h b/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/table_properties_collectors.h
deleted file mode 100644
index 0f8827037b..0000000000
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/table_properties_collectors.h
+++ /dev/null
@@ -1,29 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#pragma once
-#ifndef ROCKSDB_LITE
-#include <memory>
-
-#include "rocksdb/table_properties.h"
-
-namespace rocksdb {
-
-// Creates a factory of a table property collector that marks a SST
-// file as need-compaction when it observe at least "D" deletion
-// entries in any "N" consecutive entires.
-//
-// @param sliding_window_size "N". Note that this number will be
-//     round up to the smallest multiple of 128 that is no less
-//     than the specified size.
-// @param deletion_trigger "D".  Note that even when "N" is changed,
-//     the specified number for "D" will not be changed.
-extern std::shared_ptr<TablePropertiesCollectorFactory>
-    NewCompactOnDeletionCollectorFactory(
-        size_t sliding_window_size,
-        size_t deletion_trigger);
-}  // namespace rocksdb
-
-#endif  // !ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionOptionsFIFO.java b/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionOptionsFIFO.java
deleted file mode 100644
index f795807804..0000000000
--- a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionOptionsFIFO.java
+++ /dev/null
@@ -1,50 +0,0 @@
-// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-package org.rocksdb;
-
-/**
- * Options for FIFO Compaction
- */
-public class CompactionOptionsFIFO extends RocksObject {
-
-  public CompactionOptionsFIFO() {
-    super(newCompactionOptionsFIFO());
-  }
-
-  /**
-   * Once the total sum of table files reaches this, we will delete the oldest
-   * table file
-   *
-   * Default: 1GB
-   *
-   * @param maxTableFilesSize The maximum size of the table files
-   *
-   * @return the reference to the current options.
-   */
-  public CompactionOptionsFIFO setMaxTableFilesSize(
-      final long maxTableFilesSize) {
-    setMaxTableFilesSize(nativeHandle_, maxTableFilesSize);
-    return this;
-  }
-
-  /**
-   * Once the total sum of table files reaches this, we will delete the oldest
-   * table file
-   *
-   * Default: 1GB
-   *
-   * @return max table file size in bytes
-   */
-  public long maxTableFilesSize() {
-    return maxTableFilesSize(nativeHandle_);
-  }
-
-  private native void setMaxTableFilesSize(long handle, long maxTableFilesSize);
-  private native long maxTableFilesSize(long handle);
-
-  private native static long newCompactionOptionsFIFO();
-  @Override protected final native void disposeInternal(final long handle);
-}
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/statistics.cc b/3rdParty/rocksdb/v5.16.X/monitoring/statistics.cc
deleted file mode 100644
index 59ce3d9e0a..0000000000
--- a/3rdParty/rocksdb/v5.16.X/monitoring/statistics.cc
+++ /dev/null
@@ -1,197 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-#include "monitoring/statistics.h"
-
-#ifndef __STDC_FORMAT_MACROS
-#define __STDC_FORMAT_MACROS
-#endif
-
-#include <inttypes.h>
-#include "rocksdb/statistics.h"
-#include "port/likely.h"
-#include <algorithm>
-#include <cstdio>
-
-namespace rocksdb {
-
-std::shared_ptr<Statistics> CreateDBStatistics() {
-  return std::make_shared<StatisticsImpl>(nullptr, false);
-}
-
-StatisticsImpl::StatisticsImpl(std::shared_ptr<Statistics> stats,
-                               bool enable_internal_stats)
-    : stats_(std::move(stats)), enable_internal_stats_(enable_internal_stats) {}
-
-StatisticsImpl::~StatisticsImpl() {}
-
-uint64_t StatisticsImpl::getTickerCount(uint32_t tickerType) const {
-  MutexLock lock(&aggregate_lock_);
-  return getTickerCountLocked(tickerType);
-}
-
-uint64_t StatisticsImpl::getTickerCountLocked(uint32_t tickerType) const {
-  assert(
-    enable_internal_stats_ ?
-      tickerType < INTERNAL_TICKER_ENUM_MAX :
-      tickerType < TICKER_ENUM_MAX);
-  uint64_t res = 0;
-  for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
-    res += per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType];
-  }
-  return res;
-}
-
-void StatisticsImpl::histogramData(uint32_t histogramType,
-                                   HistogramData* const data) const {
-  MutexLock lock(&aggregate_lock_);
-  getHistogramImplLocked(histogramType)->Data(data);
-}
-
-std::unique_ptr<HistogramImpl> StatisticsImpl::getHistogramImplLocked(
-    uint32_t histogramType) const {
-  assert(
-    enable_internal_stats_ ?
-      histogramType < INTERNAL_HISTOGRAM_ENUM_MAX :
-      histogramType < HISTOGRAM_ENUM_MAX);
-  std::unique_ptr<HistogramImpl> res_hist(new HistogramImpl());
-  for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
-    res_hist->Merge(
-        per_core_stats_.AccessAtCore(core_idx)->histograms_[histogramType]);
-  }
-  return res_hist;
-}
-
-std::string StatisticsImpl::getHistogramString(uint32_t histogramType) const {
-  MutexLock lock(&aggregate_lock_);
-  return getHistogramImplLocked(histogramType)->ToString();
-}
-
-void StatisticsImpl::setTickerCount(uint32_t tickerType, uint64_t count) {
-  {
-    MutexLock lock(&aggregate_lock_);
-    setTickerCountLocked(tickerType, count);
-  }
-  if (stats_ && tickerType < TICKER_ENUM_MAX) {
-    stats_->setTickerCount(tickerType, count);
-  }
-}
-
-void StatisticsImpl::setTickerCountLocked(uint32_t tickerType, uint64_t count) {
-  assert(enable_internal_stats_ ? tickerType < INTERNAL_TICKER_ENUM_MAX
-                                : tickerType < TICKER_ENUM_MAX);
-  for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
-    if (core_idx == 0) {
-      per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType] = count;
-    } else {
-      per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType] = 0;
-    }
-  }
-}
-
-uint64_t StatisticsImpl::getAndResetTickerCount(uint32_t tickerType) {
-  uint64_t sum = 0;
-  {
-    MutexLock lock(&aggregate_lock_);
-    assert(enable_internal_stats_ ? tickerType < INTERNAL_TICKER_ENUM_MAX
-                                  : tickerType < TICKER_ENUM_MAX);
-    for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
-      sum +=
-          per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType].exchange(
-              0, std::memory_order_relaxed);
-    }
-  }
-  if (stats_ && tickerType < TICKER_ENUM_MAX) {
-    stats_->setTickerCount(tickerType, 0);
-  }
-  return sum;
-}
-
-void StatisticsImpl::recordTick(uint32_t tickerType, uint64_t count) {
-  assert(
-    enable_internal_stats_ ?
-      tickerType < INTERNAL_TICKER_ENUM_MAX :
-      tickerType < TICKER_ENUM_MAX);
-  per_core_stats_.Access()->tickers_[tickerType].fetch_add(
-      count, std::memory_order_relaxed);
-  if (stats_ && tickerType < TICKER_ENUM_MAX) {
-    stats_->recordTick(tickerType, count);
-  }
-}
-
-void StatisticsImpl::measureTime(uint32_t histogramType, uint64_t value) {
-  assert(
-    enable_internal_stats_ ?
-      histogramType < INTERNAL_HISTOGRAM_ENUM_MAX :
-      histogramType < HISTOGRAM_ENUM_MAX);
-  per_core_stats_.Access()->histograms_[histogramType].Add(value);
-  if (stats_ && histogramType < HISTOGRAM_ENUM_MAX) {
-    stats_->measureTime(histogramType, value);
-  }
-}
-
-Status StatisticsImpl::Reset() {
-  MutexLock lock(&aggregate_lock_);
-  for (uint32_t i = 0; i < TICKER_ENUM_MAX; ++i) {
-    setTickerCountLocked(i, 0);
-  }
-  for (uint32_t i = 0; i < HISTOGRAM_ENUM_MAX; ++i) {
-    for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
-      per_core_stats_.AccessAtCore(core_idx)->histograms_[i].Clear();
-    }
-  }
-  return Status::OK();
-}
-
-namespace {
-
-// a buffer size used for temp string buffers
-const int kTmpStrBufferSize = 200;
-
-} // namespace
-
-std::string StatisticsImpl::ToString() const {
-  MutexLock lock(&aggregate_lock_);
-  std::string res;
-  res.reserve(20000);
-  for (const auto& t : TickersNameMap) {
-    if (t.first < TICKER_ENUM_MAX || enable_internal_stats_) {
-      char buffer[kTmpStrBufferSize];
-      snprintf(buffer, kTmpStrBufferSize, "%s COUNT : %" PRIu64 "\n",
-               t.second.c_str(), getTickerCountLocked(t.first));
-      res.append(buffer);
-    }
-  }
-  for (const auto& h : HistogramsNameMap) {
-    if (h.first < HISTOGRAM_ENUM_MAX || enable_internal_stats_) {
-      char buffer[kTmpStrBufferSize];
-      HistogramData hData;
-      getHistogramImplLocked(h.first)->Data(&hData);
-      // don't handle failures - buffer should always be big enough and arguments
-      // should be provided correctly
-      int ret = snprintf(
-          buffer, kTmpStrBufferSize,
-          "%s P50 : %f P95 : %f P99 : %f P100 : %f COUNT : %" PRIu64 " SUM : %"
-          PRIu64 "\n", h.second.c_str(), hData.median, hData.percentile95,
-          hData.percentile99, hData.max, hData.count, hData.sum);
-      if (ret < 0 || ret >= kTmpStrBufferSize) {
-        assert(false);
-        continue;
-      }
-      res.append(buffer);
-    }
-  }
-  res.shrink_to_fit();
-  return res;
-}
-
-bool StatisticsImpl::HistEnabledForType(uint32_t type) const {
-  if (LIKELY(!enable_internal_stats_)) {
-    return type < HISTOGRAM_ENUM_MAX;
-  }
-  return true;
-}
-
-} // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/util/logging.h b/3rdParty/rocksdb/v5.16.X/util/logging.h
deleted file mode 100644
index 992e0018d7..0000000000
--- a/3rdParty/rocksdb/v5.16.X/util/logging.h
+++ /dev/null
@@ -1,50 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-//
-// Must not be included from any .h files to avoid polluting the namespace
-// with macros.
-
-#pragma once
-#include "port/port.h"
-
-// Helper macros that include information about file name and line number
-#define STRINGIFY(x) #x
-#define TOSTRING(x) STRINGIFY(x)
-#define PREPEND_FILE_LINE(FMT) ("[" __FILE__ ":" TOSTRING(__LINE__) "] " FMT)
-
-// Don't inclide file/line info in HEADER level
-#define ROCKS_LOG_HEADER(LGR, FMT, ...) \
-  rocksdb::Log(InfoLogLevel::HEADER_LEVEL, LGR, FMT, ##__VA_ARGS__)
-
-#define ROCKS_LOG_DEBUG(LGR, FMT, ...)                                 \
-  rocksdb::Log(InfoLogLevel::DEBUG_LEVEL, LGR, PREPEND_FILE_LINE(FMT), \
-               ##__VA_ARGS__)
-
-#define ROCKS_LOG_INFO(LGR, FMT, ...)                                 \
-  rocksdb::Log(InfoLogLevel::INFO_LEVEL, LGR, PREPEND_FILE_LINE(FMT), \
-               ##__VA_ARGS__)
-
-#define ROCKS_LOG_WARN(LGR, FMT, ...)                                 \
-  rocksdb::Log(InfoLogLevel::WARN_LEVEL, LGR, PREPEND_FILE_LINE(FMT), \
-               ##__VA_ARGS__)
-
-#define ROCKS_LOG_ERROR(LGR, FMT, ...)                                 \
-  rocksdb::Log(InfoLogLevel::ERROR_LEVEL, LGR, PREPEND_FILE_LINE(FMT), \
-               ##__VA_ARGS__)
-
-#define ROCKS_LOG_FATAL(LGR, FMT, ...)                                 \
-  rocksdb::Log(InfoLogLevel::FATAL_LEVEL, LGR, PREPEND_FILE_LINE(FMT), \
-               ##__VA_ARGS__)
-
-#define ROCKS_LOG_BUFFER(LOG_BUF, FMT, ...) \
-  rocksdb::LogToBuffer(LOG_BUF, PREPEND_FILE_LINE(FMT), ##__VA_ARGS__)
-
-#define ROCKS_LOG_BUFFER_MAX_SZ(LOG_BUF, MAX_LOG_SIZE, FMT, ...)      \
-  rocksdb::LogToBuffer(LOG_BUF, MAX_LOG_SIZE, PREPEND_FILE_LINE(FMT), \
-                       ##__VA_ARGS__)
diff --git a/3rdParty/rocksdb/v5.16.X/util/sst_file_manager_impl.cc b/3rdParty/rocksdb/v5.16.X/util/sst_file_manager_impl.cc
deleted file mode 100644
index 74164e06ae..0000000000
--- a/3rdParty/rocksdb/v5.16.X/util/sst_file_manager_impl.cc
+++ /dev/null
@@ -1,260 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#include "util/sst_file_manager_impl.h"
-
-#include <vector>
-
-#include "port/port.h"
-#include "rocksdb/env.h"
-#include "rocksdb/sst_file_manager.h"
-#include "util/mutexlock.h"
-#include "util/sync_point.h"
-
-namespace rocksdb {
-
-#ifndef ROCKSDB_LITE
-SstFileManagerImpl::SstFileManagerImpl(Env* env, std::shared_ptr<Logger> logger,
-                                       int64_t rate_bytes_per_sec,
-                                       double max_trash_db_ratio,
-                                       uint64_t bytes_max_delete_chunk)
-    : env_(env),
-      logger_(logger),
-      total_files_size_(0),
-      compaction_buffer_size_(0),
-      cur_compactions_reserved_size_(0),
-      max_allowed_space_(0),
-      delete_scheduler_(env, rate_bytes_per_sec, logger.get(), this,
-                        max_trash_db_ratio, bytes_max_delete_chunk) {}
-
-SstFileManagerImpl::~SstFileManagerImpl() {}
-
-Status SstFileManagerImpl::OnAddFile(const std::string& file_path) {
-  uint64_t file_size;
-  Status s = env_->GetFileSize(file_path, &file_size);
-  if (s.ok()) {
-    MutexLock l(&mu_);
-    OnAddFileImpl(file_path, file_size);
-  }
-  TEST_SYNC_POINT("SstFileManagerImpl::OnAddFile");
-  return s;
-}
-
-Status SstFileManagerImpl::OnDeleteFile(const std::string& file_path) {
-  {
-    MutexLock l(&mu_);
-    OnDeleteFileImpl(file_path);
-  }
-  TEST_SYNC_POINT("SstFileManagerImpl::OnDeleteFile");
-  return Status::OK();
-}
-
-void SstFileManagerImpl::OnCompactionCompletion(Compaction* c) {
-  MutexLock l(&mu_);
-  uint64_t size_added_by_compaction = 0;
-  for (size_t i = 0; i < c->num_input_levels(); i++) {
-    for (size_t j = 0; j < c->num_input_files(i); j++) {
-      FileMetaData* filemeta = c->input(i, j);
-      size_added_by_compaction += filemeta->fd.GetFileSize();
-    }
-  }
-  cur_compactions_reserved_size_ -= size_added_by_compaction;
-}
-
-Status SstFileManagerImpl::OnMoveFile(const std::string& old_path,
-                                      const std::string& new_path,
-                                      uint64_t* file_size) {
-  {
-    MutexLock l(&mu_);
-    if (file_size != nullptr) {
-      *file_size = tracked_files_[old_path];
-    }
-    OnAddFileImpl(new_path, tracked_files_[old_path]);
-    OnDeleteFileImpl(old_path);
-  }
-  TEST_SYNC_POINT("SstFileManagerImpl::OnMoveFile");
-  return Status::OK();
-}
-
-void SstFileManagerImpl::SetMaxAllowedSpaceUsage(uint64_t max_allowed_space) {
-  MutexLock l(&mu_);
-  max_allowed_space_ = max_allowed_space;
-}
-
-void SstFileManagerImpl::SetCompactionBufferSize(
-    uint64_t compaction_buffer_size) {
-  MutexLock l(&mu_);
-  compaction_buffer_size_ = compaction_buffer_size;
-}
-
-bool SstFileManagerImpl::IsMaxAllowedSpaceReached() {
-  MutexLock l(&mu_);
-  if (max_allowed_space_ <= 0) {
-    return false;
-  }
-  return total_files_size_ >= max_allowed_space_;
-}
-
-bool SstFileManagerImpl::IsMaxAllowedSpaceReachedIncludingCompactions() {
-  MutexLock l(&mu_);
-  if (max_allowed_space_ <= 0) {
-    return false;
-  }
-  return total_files_size_ + cur_compactions_reserved_size_ >=
-         max_allowed_space_;
-}
-
-bool SstFileManagerImpl::EnoughRoomForCompaction(
-    const std::vector<CompactionInputFiles>& inputs) {
-  MutexLock l(&mu_);
-  uint64_t size_added_by_compaction = 0;
-  // First check if we even have the space to do the compaction
-  for (size_t i = 0; i < inputs.size(); i++) {
-    for (size_t j = 0; j < inputs[i].size(); j++) {
-      FileMetaData* filemeta = inputs[i][j];
-      size_added_by_compaction += filemeta->fd.GetFileSize();
-    }
-  }
-
-  if (max_allowed_space_ != 0 &&
-      (size_added_by_compaction + cur_compactions_reserved_size_ +
-           total_files_size_ + compaction_buffer_size_ >
-       max_allowed_space_)) {
-    return false;
-  }
-  // Update cur_compactions_reserved_size_ so concurrent compaction
-  // don't max out space
-  cur_compactions_reserved_size_ += size_added_by_compaction;
-  return true;
-}
-
-uint64_t SstFileManagerImpl::GetCompactionsReservedSize() {
-  MutexLock l(&mu_);
-  return cur_compactions_reserved_size_;
-}
-
-uint64_t SstFileManagerImpl::GetTotalSize() {
-  MutexLock l(&mu_);
-  return total_files_size_;
-}
-
-std::unordered_map<std::string, uint64_t>
-SstFileManagerImpl::GetTrackedFiles() {
-  MutexLock l(&mu_);
-  return tracked_files_;
-}
-
-int64_t SstFileManagerImpl::GetDeleteRateBytesPerSecond() {
-  return delete_scheduler_.GetRateBytesPerSecond();
-}
-
-void SstFileManagerImpl::SetDeleteRateBytesPerSecond(int64_t delete_rate) {
-  return delete_scheduler_.SetRateBytesPerSecond(delete_rate);
-}
-
-double SstFileManagerImpl::GetMaxTrashDBRatio() {
-  return delete_scheduler_.GetMaxTrashDBRatio();
-}
-
-void SstFileManagerImpl::SetMaxTrashDBRatio(double r) {
-  return delete_scheduler_.SetMaxTrashDBRatio(r);
-}
-
-uint64_t SstFileManagerImpl::GetTotalTrashSize() {
-  return delete_scheduler_.GetTotalTrashSize();
-}
-
-Status SstFileManagerImpl::ScheduleFileDeletion(
-    const std::string& file_path, const std::string& path_to_sync) {
-  return delete_scheduler_.DeleteFile(file_path, path_to_sync);
-}
-
-void SstFileManagerImpl::WaitForEmptyTrash() {
-  delete_scheduler_.WaitForEmptyTrash();
-}
-
-void SstFileManagerImpl::OnAddFileImpl(const std::string& file_path,
-                                       uint64_t file_size) {
-  auto tracked_file = tracked_files_.find(file_path);
-  if (tracked_file != tracked_files_.end()) {
-    // File was added before, we will just update the size
-    total_files_size_ -= tracked_file->second;
-    total_files_size_ += file_size;
-  } else {
-    total_files_size_ += file_size;
-  }
-  tracked_files_[file_path] = file_size;
-}
-
-void SstFileManagerImpl::OnDeleteFileImpl(const std::string& file_path) {
-  auto tracked_file = tracked_files_.find(file_path);
-  if (tracked_file == tracked_files_.end()) {
-    // File is not tracked
-    return;
-  }
-
-  total_files_size_ -= tracked_file->second;
-  tracked_files_.erase(tracked_file);
-}
-
-SstFileManager* NewSstFileManager(Env* env, std::shared_ptr<Logger> info_log,
-                                  std::string trash_dir,
-                                  int64_t rate_bytes_per_sec,
-                                  bool delete_existing_trash, Status* status,
-                                  double max_trash_db_ratio,
-                                  uint64_t bytes_max_delete_chunk) {
-  SstFileManagerImpl* res =
-      new SstFileManagerImpl(env, info_log, rate_bytes_per_sec,
-                             max_trash_db_ratio, bytes_max_delete_chunk);
-
-  // trash_dir is deprecated and not needed anymore, but if user passed it
-  // we will still remove files in it.
-  Status s;
-  if (delete_existing_trash && trash_dir != "") {
-    std::vector<std::string> files_in_trash;
-    s = env->GetChildren(trash_dir, &files_in_trash);
-    if (s.ok()) {
-      for (const std::string& trash_file : files_in_trash) {
-        if (trash_file == "." || trash_file == "..") {
-          continue;
-        }
-
-        std::string path_in_trash = trash_dir + "/" + trash_file;
-        res->OnAddFile(path_in_trash);
-        Status file_delete =
-            res->ScheduleFileDeletion(path_in_trash, trash_dir);
-        if (s.ok() && !file_delete.ok()) {
-          s = file_delete;
-        }
-      }
-    }
-  }
-
-  if (status) {
-    *status = s;
-  }
-
-  return res;
-}
-
-#else
-
-SstFileManager* NewSstFileManager(Env* /*env*/,
-                                  std::shared_ptr<Logger> /*info_log*/,
-                                  std::string /*trash_dir*/,
-                                  int64_t /*rate_bytes_per_sec*/,
-                                  bool /*delete_existing_trash*/,
-                                  Status* status, double /*max_trash_db_ratio*/,
-                                  uint64_t /*bytes_max_delete_chunk*/) {
-  if (status) {
-    *status =
-        Status::NotSupported("SstFileManager is not supported in ROCKSDB_LITE");
-  }
-  return nullptr;
-}
-
-#endif  // ROCKSDB_LITE
-
-}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/util/xxhash.cc b/3rdParty/rocksdb/v5.16.X/util/xxhash.cc
deleted file mode 100644
index 4bce61a487..0000000000
--- a/3rdParty/rocksdb/v5.16.X/util/xxhash.cc
+++ /dev/null
@@ -1,479 +0,0 @@
-/*
-xxHash - Fast Hash algorithm
-Copyright (C) 2012-2014, Yann Collet.
-BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
-
-Redistribution and use in source and binary forms, with or without
-modification, are permitted provided that the following conditions are
-met:
-
-* Redistributions of source code must retain the above copyright
-notice, this list of conditions and the following disclaimer.
-* Redistributions in binary form must reproduce the above
-copyright notice, this list of conditions and the following disclaimer
-in the documentation and/or other materials provided with the
-distribution.
-
-THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
-"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
-LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
-A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
-OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
-SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
-LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
-DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
-THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
-(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
-OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
-
-You can contact the author at :
-- xxHash source repository : http://code.google.com/p/xxhash/
-*/
-
-
-//**************************************
-// Tuning parameters
-//**************************************
-// Unaligned memory access is automatically enabled for "common" CPU, such as x86.
-// For others CPU, the compiler will be more cautious, and insert extra code to ensure aligned access is respected.
-// If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance.
-// You can also enable this parameter if you know your input data will always be aligned (boundaries of 4, for U32).
-#if defined(__ARM_FEATURE_UNALIGNED) || defined(__i386) || defined(_M_IX86) || defined(__x86_64__) || defined(_M_X64)
-#  define XXH_USE_UNALIGNED_ACCESS 1
-#endif
-
-// XXH_ACCEPT_NULL_INPUT_POINTER :
-// If the input pointer is a null pointer, xxHash default behavior is to trigger a memory access error, since it is a bad pointer.
-// When this option is enabled, xxHash output for null input pointers will be the same as a null-length input.
-// This option has a very small performance cost (only measurable on small inputs).
-// By default, this option is disabled. To enable it, uncomment below define :
-//#define XXH_ACCEPT_NULL_INPUT_POINTER 1
-
-// XXH_FORCE_NATIVE_FORMAT :
-// By default, xxHash library provides endian-independent Hash values, based on little-endian convention.
-// Results are therefore identical for little-endian and big-endian CPU.
-// This comes at a performance cost for big-endian CPU, since some swapping is required to emulate little-endian format.
-// Should endian-independence be of no importance for your application, you may set the #define below to 1.
-// It will improve speed for Big-endian CPU.
-// This option has no impact on Little_Endian CPU.
-#define XXH_FORCE_NATIVE_FORMAT 0
-
-
-//**************************************
-// Compiler Specific Options
-//**************************************
-// Disable some Visual warning messages
-#ifdef _MSC_VER  // Visual Studio
-#  pragma warning(disable : 4127)      // disable: C4127: conditional expression is constant
-#  pragma warning(disable : 4804)      // disable: C4804: 'operation' : unsafe use of type 'bool' in operation (static assert line 313)
-#endif
-
-#ifdef _MSC_VER    // Visual Studio
-#  define FORCE_INLINE static __forceinline
-#else
-#  ifdef __GNUC__
-#    define FORCE_INLINE static inline __attribute__((always_inline))
-#  else
-#    define FORCE_INLINE static inline
-#  endif
-#endif
-
-
-//**************************************
-// Includes & Memory related functions
-//**************************************
-#include "xxhash.h"
-// Modify the local functions below should you wish to use some other memory related routines
-// for malloc(), free()
-#include <stdlib.h>
-FORCE_INLINE void* XXH_malloc(size_t s) { return malloc(s); }
-FORCE_INLINE void  XXH_free  (void* p)  { free(p); }
-// for memcpy()
-#include <string.h>
-FORCE_INLINE void* XXH_memcpy(void* dest, const void* src, size_t size) { return memcpy(dest,src,size); }
-
-
-namespace rocksdb {
-//**************************************
-// Basic Types
-//**************************************
-#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   // C99
-# include <stdint.h>
-  typedef uint8_t  BYTE;
-  typedef uint16_t U16;
-  typedef uint32_t U32;
-  typedef  int32_t S32;
-  typedef uint64_t U64;
-#else
-  typedef unsigned char      BYTE;
-  typedef unsigned short     U16;
-  typedef unsigned int       U32;
-  typedef   signed int       S32;
-  typedef unsigned long long U64;
-#endif
-
-#if defined(__GNUC__)  && !defined(XXH_USE_UNALIGNED_ACCESS)
-#  define _PACKED __attribute__ ((packed))
-#else
-#  define _PACKED
-#endif
-
-#if !defined(XXH_USE_UNALIGNED_ACCESS) && !defined(__GNUC__)
-#  ifdef __IBMC__
-#    pragma pack(1)
-#  else
-#    pragma pack(push, 1)
-#  endif
-#endif
-
-typedef struct _U32_S { U32 v; } _PACKED U32_S;
-
-#if !defined(XXH_USE_UNALIGNED_ACCESS) && !defined(__GNUC__)
-#  pragma pack(pop)
-#endif
-
-#define A32(x) (((U32_S *)(x))->v)
-
-
-//***************************************
-// Compiler-specific Functions and Macros
-//***************************************
-#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
-
-// Note : although _rotl exists for minGW (GCC under windows), performance seems poor
-#if defined(_MSC_VER)
-#  define XXH_rotl32(x,r) _rotl(x,r)
-#else
-#  define XXH_rotl32(x,r) ((x << r) | (x >> (32 - r)))
-#endif
-
-#if defined(_MSC_VER)     // Visual Studio
-#  define XXH_swap32 _byteswap_ulong
-#elif GCC_VERSION >= 403
-#  define XXH_swap32 __builtin_bswap32
-#else
-static inline U32 XXH_swap32 (U32 x) {
-    return  ((x << 24) & 0xff000000 ) |
-        ((x <<  8) & 0x00ff0000 ) |
-        ((x >>  8) & 0x0000ff00 ) |
-        ((x >> 24) & 0x000000ff );}
-#endif
-
-
-//**************************************
-// Constants
-//**************************************
-#define PRIME32_1   2654435761U
-#define PRIME32_2   2246822519U
-#define PRIME32_3   3266489917U
-#define PRIME32_4    668265263U
-#define PRIME32_5    374761393U
-
-
-//**************************************
-// Architecture Macros
-//**************************************
-typedef enum { XXH_bigEndian=0, XXH_littleEndian=1 } XXH_endianess;
-#ifndef XXH_CPU_LITTLE_ENDIAN   // It is possible to define XXH_CPU_LITTLE_ENDIAN externally, for example using a compiler switch
-    static const int one = 1;
-#   define XXH_CPU_LITTLE_ENDIAN   (*(char*)(&one))
-#endif
-
-
-//**************************************
-// Macros
-//**************************************
-#define XXH_STATIC_ASSERT(c)   { enum { XXH_static_assert = 1/(!!(c)) }; }    // use only *after* variable declarations
-
-
-//****************************
-// Memory reads
-//****************************
-typedef enum { XXH_aligned, XXH_unaligned } XXH_alignment;
-
-FORCE_INLINE U32 XXH_readLE32_align(const U32* ptr, XXH_endianess endian, XXH_alignment align)
-{
-    if (align==XXH_unaligned)
-        return endian==XXH_littleEndian ? A32(ptr) : XXH_swap32(A32(ptr));
-    else
-        return endian==XXH_littleEndian ? *ptr : XXH_swap32(*ptr);
-}
-
-FORCE_INLINE U32 XXH_readLE32(const U32* ptr, XXH_endianess endian) { return XXH_readLE32_align(ptr, endian, XXH_unaligned); }
-
-
-//****************************
-// Simple Hash Functions
-//****************************
-FORCE_INLINE U32 XXH32_endian_align(const void* input, int len, U32 seed, XXH_endianess endian, XXH_alignment align)
-{
-    const BYTE* p = (const BYTE*)input;
-    const BYTE* const bEnd = p + len;
-    U32 h32;
-
-#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
-    if (p==NULL) { len=0; p=(const BYTE*)(size_t)16; }
-#endif
-
-    if (len>=16)
-    {
-        const BYTE* const limit = bEnd - 16;
-        U32 v1 = seed + PRIME32_1 + PRIME32_2;
-        U32 v2 = seed + PRIME32_2;
-        U32 v3 = seed + 0;
-        U32 v4 = seed - PRIME32_1;
-
-        do
-        {
-            v1 += XXH_readLE32_align((const U32*)p, endian, align) * PRIME32_2; v1 = XXH_rotl32(v1, 13); v1 *= PRIME32_1; p+=4;
-            v2 += XXH_readLE32_align((const U32*)p, endian, align) * PRIME32_2; v2 = XXH_rotl32(v2, 13); v2 *= PRIME32_1; p+=4;
-            v3 += XXH_readLE32_align((const U32*)p, endian, align) * PRIME32_2; v3 = XXH_rotl32(v3, 13); v3 *= PRIME32_1; p+=4;
-            v4 += XXH_readLE32_align((const U32*)p, endian, align) * PRIME32_2; v4 = XXH_rotl32(v4, 13); v4 *= PRIME32_1; p+=4;
-        } while (p<=limit);
-
-        h32 = XXH_rotl32(v1, 1) + XXH_rotl32(v2, 7) + XXH_rotl32(v3, 12) + XXH_rotl32(v4, 18);
-    }
-    else
-    {
-        h32  = seed + PRIME32_5;
-    }
-
-    h32 += (U32) len;
-
-    while (p<=bEnd-4)
-    {
-        h32 += XXH_readLE32_align((const U32*)p, endian, align) * PRIME32_3;
-        h32  = XXH_rotl32(h32, 17) * PRIME32_4 ;
-        p+=4;
-    }
-
-    while (p<bEnd)
-    {
-        h32 += (*p) * PRIME32_5;
-        h32 = XXH_rotl32(h32, 11) * PRIME32_1 ;
-        p++;
-    }
-
-    h32 ^= h32 >> 15;
-    h32 *= PRIME32_2;
-    h32 ^= h32 >> 13;
-    h32 *= PRIME32_3;
-    h32 ^= h32 >> 16;
-
-    return h32;
-}
-
-
-U32 XXH32(const void* input, int len, U32 seed)
-{
-#if 0
-    // Simple version, good for code maintenance, but unfortunately slow for small inputs
-    void* state = XXH32_init(seed);
-    XXH32_update(state, input, len);
-    return XXH32_digest(state);
-#else
-    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
-
-#  if !defined(XXH_USE_UNALIGNED_ACCESS)
-    if ((((size_t)input) & 3))   // Input is aligned, let's leverage the speed advantage
-    {
-        if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
-            return XXH32_endian_align(input, len, seed, XXH_littleEndian, XXH_aligned);
-        else
-            return XXH32_endian_align(input, len, seed, XXH_bigEndian, XXH_aligned);
-    }
-#  endif
-
-    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
-        return XXH32_endian_align(input, len, seed, XXH_littleEndian, XXH_unaligned);
-    else
-        return XXH32_endian_align(input, len, seed, XXH_bigEndian, XXH_unaligned);
-#endif
-}
-
-
-//****************************
-// Advanced Hash Functions
-//****************************
-
-struct XXH_state32_t
-{
-    U64 total_len;
-    U32 seed;
-    U32 v1;
-    U32 v2;
-    U32 v3;
-    U32 v4;
-    int memsize;
-    char memory[16];
-};
-
-
-int XXH32_sizeofState()
-{
-    XXH_STATIC_ASSERT(XXH32_SIZEOFSTATE >= sizeof(struct XXH_state32_t));   // A compilation error here means XXH32_SIZEOFSTATE is not large enough
-    return sizeof(struct XXH_state32_t);
-}
-
-
-XXH_errorcode XXH32_resetState(void* state_in, U32 seed)
-{
-    struct XXH_state32_t * state = (struct XXH_state32_t *) state_in;
-    state->seed = seed;
-    state->v1 = seed + PRIME32_1 + PRIME32_2;
-    state->v2 = seed + PRIME32_2;
-    state->v3 = seed + 0;
-    state->v4 = seed - PRIME32_1;
-    state->total_len = 0;
-    state->memsize = 0;
-    return XXH_OK;
-}
-
-
-void* XXH32_init (U32 seed)
-{
-    void* state = XXH_malloc (sizeof(struct XXH_state32_t));
-    XXH32_resetState(state, seed);
-    return state;
-}
-
-
-FORCE_INLINE XXH_errorcode XXH32_update_endian (void* state_in, const void* input, int len, XXH_endianess endian)
-{
-    struct XXH_state32_t * state = (struct XXH_state32_t *) state_in;
-    const BYTE* p = (const BYTE*)input;
-    const BYTE* const bEnd = p + len;
-
-#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
-    if (input==NULL) return XXH_ERROR;
-#endif
-
-    state->total_len += len;
-
-    if (state->memsize + len < 16)   // fill in tmp buffer
-    {
-        XXH_memcpy(state->memory + state->memsize, input, len);
-        state->memsize +=  len;
-        return XXH_OK;
-    }
-
-    if (state->memsize)   // some data left from previous update
-    {
-        XXH_memcpy(state->memory + state->memsize, input, 16-state->memsize);
-        {
-            const U32* p32 = (const U32*)state->memory;
-            state->v1 += XXH_readLE32(p32, endian) * PRIME32_2; state->v1 = XXH_rotl32(state->v1, 13); state->v1 *= PRIME32_1; p32++;
-            state->v2 += XXH_readLE32(p32, endian) * PRIME32_2; state->v2 = XXH_rotl32(state->v2, 13); state->v2 *= PRIME32_1; p32++;
-            state->v3 += XXH_readLE32(p32, endian) * PRIME32_2; state->v3 = XXH_rotl32(state->v3, 13); state->v3 *= PRIME32_1; p32++;
-            state->v4 += XXH_readLE32(p32, endian) * PRIME32_2; state->v4 = XXH_rotl32(state->v4, 13); state->v4 *= PRIME32_1; p32++;
-        }
-        p += 16-state->memsize;
-        state->memsize = 0;
-    }
-
-    if (p <= bEnd-16)
-    {
-        const BYTE* const limit = bEnd - 16;
-        U32 v1 = state->v1;
-        U32 v2 = state->v2;
-        U32 v3 = state->v3;
-        U32 v4 = state->v4;
-
-        do
-        {
-            v1 += XXH_readLE32((const U32*)p, endian) * PRIME32_2; v1 = XXH_rotl32(v1, 13); v1 *= PRIME32_1; p+=4;
-            v2 += XXH_readLE32((const U32*)p, endian) * PRIME32_2; v2 = XXH_rotl32(v2, 13); v2 *= PRIME32_1; p+=4;
-            v3 += XXH_readLE32((const U32*)p, endian) * PRIME32_2; v3 = XXH_rotl32(v3, 13); v3 *= PRIME32_1; p+=4;
-            v4 += XXH_readLE32((const U32*)p, endian) * PRIME32_2; v4 = XXH_rotl32(v4, 13); v4 *= PRIME32_1; p+=4;
-        } while (p<=limit);
-
-        state->v1 = v1;
-        state->v2 = v2;
-        state->v3 = v3;
-        state->v4 = v4;
-    }
-
-    if (p < bEnd)
-    {
-        XXH_memcpy(state->memory, p, bEnd-p);
-        state->memsize = (int)(bEnd-p);
-    }
-
-    return XXH_OK;
-}
-
-XXH_errorcode XXH32_update (void* state_in, const void* input, int len)
-{
-    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
-
-    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
-        return XXH32_update_endian(state_in, input, len, XXH_littleEndian);
-    else
-        return XXH32_update_endian(state_in, input, len, XXH_bigEndian);
-}
-
-
-
-FORCE_INLINE U32 XXH32_intermediateDigest_endian (void* state_in, XXH_endianess endian)
-{
-    struct XXH_state32_t * state = (struct XXH_state32_t *) state_in;
-    const BYTE * p = (const BYTE*)state->memory;
-    BYTE* bEnd = (BYTE*)state->memory + state->memsize;
-    U32 h32;
-
-    if (state->total_len >= 16)
-    {
-        h32 = XXH_rotl32(state->v1, 1) + XXH_rotl32(state->v2, 7) + XXH_rotl32(state->v3, 12) + XXH_rotl32(state->v4, 18);
-    }
-    else
-    {
-        h32  = state->seed + PRIME32_5;
-    }
-
-    h32 += (U32) state->total_len;
-
-    while (p<=bEnd-4)
-    {
-        h32 += XXH_readLE32((const U32*)p, endian) * PRIME32_3;
-        h32  = XXH_rotl32(h32, 17) * PRIME32_4;
-        p+=4;
-    }
-
-    while (p<bEnd)
-    {
-        h32 += (*p) * PRIME32_5;
-        h32 = XXH_rotl32(h32, 11) * PRIME32_1;
-        p++;
-    }
-
-    h32 ^= h32 >> 15;
-    h32 *= PRIME32_2;
-    h32 ^= h32 >> 13;
-    h32 *= PRIME32_3;
-    h32 ^= h32 >> 16;
-
-    return h32;
-}
-
-
-U32 XXH32_intermediateDigest (void* state_in)
-{
-    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
-
-    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
-        return XXH32_intermediateDigest_endian(state_in, XXH_littleEndian);
-    else
-        return XXH32_intermediateDigest_endian(state_in, XXH_bigEndian);
-}
-
-
-U32 XXH32_digest (void* state_in)
-{
-    U32 h32 = XXH32_intermediateDigest(state_in);
-
-    XXH_free(state_in);
-
-    return h32;
-}
-
-}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/.clang-format b/3rdParty/rocksdb/v5.18.X/.clang-format
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/.clang-format
rename to 3rdParty/rocksdb/v5.18.X/.clang-format
diff --git a/3rdParty/rocksdb/v5.16.X/.gitignore b/3rdParty/rocksdb/v5.18.X/.gitignore
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/.gitignore
rename to 3rdParty/rocksdb/v5.18.X/.gitignore
diff --git a/3rdParty/rocksdb/v5.16.X/.lgtm.yml b/3rdParty/rocksdb/v5.18.X/.lgtm.yml
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/.lgtm.yml
rename to 3rdParty/rocksdb/v5.18.X/.lgtm.yml
diff --git a/3rdParty/rocksdb/v5.16.X/.travis.yml b/3rdParty/rocksdb/v5.18.X/.travis.yml
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/.travis.yml
rename to 3rdParty/rocksdb/v5.18.X/.travis.yml
diff --git a/3rdParty/rocksdb/v5.16.X/AUTHORS b/3rdParty/rocksdb/v5.18.X/AUTHORS
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/AUTHORS
rename to 3rdParty/rocksdb/v5.18.X/AUTHORS
diff --git a/3rdParty/rocksdb/v5.16.X/CMakeLists.txt b/3rdParty/rocksdb/v5.18.X/CMakeLists.txt
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/CMakeLists.txt
rename to 3rdParty/rocksdb/v5.18.X/CMakeLists.txt
index 456c184ece..49f35ddf7f 100644
--- a/3rdParty/rocksdb/v5.16.X/CMakeLists.txt
+++ b/3rdParty/rocksdb/v5.18.X/CMakeLists.txt
@@ -341,12 +341,18 @@ endif()
 
 # Used to run CI build and tests so we can run faster
 option(OPTDBG "Build optimized debug build with MSVC" OFF)
+option(WITH_RUNTIME_DEBUG "build with debug version of runtime library" ON)
 if(MSVC)
   if(OPTDBG)
     message(STATUS "Debug optimization is enabled")
-    set(CMAKE_CXX_FLAGS_DEBUG "/Oxt /${RUNTIME_LIBRARY}d")
+    set(CMAKE_CXX_FLAGS_DEBUG "/Oxt")
   else()
-    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1 /Gm /${RUNTIME_LIBRARY}d")
+    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1 /Gm")
+  endif()
+  if(WITH_RUNTIME_DEBUG)
+    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /${RUNTIME_LIBRARY}d")
+  else()
+    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /${RUNTIME_LIBRARY}")
   endif()
   set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /Oxt /Zp8 /Gm- /Gy /${RUNTIME_LIBRARY}")
 
@@ -361,7 +367,7 @@ endif()
 option(ROCKSDB_LITE "Build RocksDBLite version" OFF)
 if(ROCKSDB_LITE)
   add_definitions(-DROCKSDB_LITE)
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-exceptions")
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-exceptions -Os")
 endif()
 
 if(CMAKE_SYSTEM_NAME MATCHES "Cygwin")
@@ -466,6 +472,7 @@ set(SOURCES
         db/compaction_iterator.cc
         db/compaction_job.cc
         db/compaction_picker.cc
+        db/compaction_picker_fifo.cc
         db/compaction_picker_universal.cc
         db/convenience.cc
         db/db_filesnapshot.cc
@@ -498,6 +505,8 @@ set(SOURCES
         db/merge_helper.cc
         db/merge_operator.cc
         db/range_del_aggregator.cc
+        db/range_del_aggregator_v2.cc
+        db/range_tombstone_fragmenter.cc
         db/repair.cc
         db/snapshot_impl.cc
         db/table_cache.cc
@@ -571,6 +580,7 @@ set(SOURCES
         table/plain_table_index.cc
         table/plain_table_key_coding.cc
         table/plain_table_reader.cc
+        table/sst_file_reader.cc
         table/sst_file_writer.cc
         table/table_properties.cc
         table/two_level_iterator.cc
@@ -597,6 +607,7 @@ set(SOURCES
         util/filename.cc
         util/filter_policy.cc
         util/hash.cc
+        util/jemalloc_nodump_allocator.cc
         util/log_buffer.cc
         util/murmurhash.cc
         util/random.cc
@@ -617,6 +628,7 @@ set(SOURCES
         utilities/blob_db/blob_compaction_filter.cc
         utilities/blob_db/blob_db.cc
         utilities/blob_db/blob_db_impl.cc
+        utilities/blob_db/blob_db_impl_filesnapshot.cc
         utilities/blob_db/blob_dump_tool.cc
         utilities/blob_db/blob_file.cc
         utilities/blob_db/blob_log_reader.cc
@@ -677,12 +689,10 @@ set(SOURCES
         utilities/write_batch_with_index/write_batch_with_index_internal.cc
         $<TARGET_OBJECTS:build_version>)
 
-if(HAVE_SSE42 AND NOT FORCE_SSE42)
-  if(NOT MSVC)
-set_source_files_properties(
-  util/crc32c.cc
-      PROPERTIES COMPILE_FLAGS "-msse4.2 -mpclmul")
-  endif()
+if(HAVE_SSE42 AND NOT MSVC)
+  set_source_files_properties(
+    util/crc32c.cc
+    PROPERTIES COMPILE_FLAGS "-msse4.2 -mpclmul")
 endif()
 
 if(HAVE_POWER8)
@@ -897,6 +907,9 @@ if(WITH_TESTS)
         db/perf_context_test.cc
         db/plain_table_db_test.cc
         db/prefix_test.cc
+        db/range_del_aggregator_test.cc
+        db/range_del_aggregator_v2_test.cc
+        db/range_tombstone_fragmenter_test.cc
         db/repair_test.cc
         db/table_properties_collector_test.cc
         db/version_builder_test.cc
@@ -925,6 +938,7 @@ if(WITH_TESTS)
         table/data_block_hash_index_test.cc
         table/full_filter_block_test.cc
         table/merger_test.cc
+        table/sst_file_reader_test.cc
         table/table_test.cc
         tools/ldb_cmd_test.cc
         tools/reduce_levels_test.cc
@@ -944,6 +958,7 @@ if(WITH_TESTS)
         util/hash_test.cc
         util/heap_test.cc
         util/rate_limiter_test.cc
+        util/repeatable_thread_test.cc
         util/slice_transform_test.cc
         util/timer_queue_test.cc
         util/thread_list_test.cc
@@ -986,6 +1001,7 @@ if(WITH_TESTS)
   set(BENCHMARKS
     cache/cache_bench.cc
     memtable/memtablerep_bench.cc
+    db/range_del_aggregator_bench.cc
     tools/db_bench.cc
     table/table_reader_bench.cc
     utilities/column_aware_encoding_exp.cc
diff --git a/3rdParty/rocksdb/v5.16.X/CODE_OF_CONDUCT.md b/3rdParty/rocksdb/v5.18.X/CODE_OF_CONDUCT.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/CODE_OF_CONDUCT.md
rename to 3rdParty/rocksdb/v5.18.X/CODE_OF_CONDUCT.md
diff --git a/3rdParty/rocksdb/v5.16.X/CONTRIBUTING.md b/3rdParty/rocksdb/v5.18.X/CONTRIBUTING.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/CONTRIBUTING.md
rename to 3rdParty/rocksdb/v5.18.X/CONTRIBUTING.md
diff --git a/3rdParty/rocksdb/v5.16.X/COPYING b/3rdParty/rocksdb/v5.18.X/COPYING
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/COPYING
rename to 3rdParty/rocksdb/v5.18.X/COPYING
diff --git a/3rdParty/rocksdb/v5.16.X/DEFAULT_OPTIONS_HISTORY.md b/3rdParty/rocksdb/v5.18.X/DEFAULT_OPTIONS_HISTORY.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/DEFAULT_OPTIONS_HISTORY.md
rename to 3rdParty/rocksdb/v5.18.X/DEFAULT_OPTIONS_HISTORY.md
diff --git a/3rdParty/rocksdb/v5.16.X/DUMP_FORMAT.md b/3rdParty/rocksdb/v5.18.X/DUMP_FORMAT.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/DUMP_FORMAT.md
rename to 3rdParty/rocksdb/v5.18.X/DUMP_FORMAT.md
diff --git a/3rdParty/rocksdb/v5.16.X/HISTORY.md b/3rdParty/rocksdb/v5.18.X/HISTORY.md
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/HISTORY.md
rename to 3rdParty/rocksdb/v5.18.X/HISTORY.md
index 1c3378221e..429c891db5 100644
--- a/3rdParty/rocksdb/v5.16.X/HISTORY.md
+++ b/3rdParty/rocksdb/v5.18.X/HISTORY.md
@@ -1,13 +1,73 @@
 # Rocksdb Change Log
 ## Unreleased
-### Public API Change
 ### New Features
+
+### Public API Change
+
 ### Bug Fixes
+* Fix a deadlock caused by compaction and file ingestion waiting for each other in the event of write stalls.
+
+## 5.18.0 (11/30/2018)
+### New Features
+* Introduced `JemallocNodumpAllocator` memory allocator. When being use, block cache will be excluded from core dump.
+* Introduced `PerfContextByLevel` as part of `PerfContext` which allows storing perf context at each level. Also replaced `__thread` with `thread_local` keyword for perf_context. Added per-level perf context for bloom filter and `Get` query.
+* With level_compaction_dynamic_level_bytes = true, level multiplier may be adjusted automatically when Level 0 to 1 compaction is lagged behind.
+* Introduced DB option `atomic_flush`. If true, RocksDB supports flushing multiple column families and atomically committing the result to MANIFEST. Useful when WAL is disabled.
+* Added `num_deletions` and `num_merge_operands` members to `TableProperties`.
+* Added "rocksdb.min-obsolete-sst-number-to-keep" DB property that reports the lower bound on SST file numbers that are being kept from deletion, even if the SSTs are obsolete.
+* Add xxhash64 checksum support
+* Introduced `MemoryAllocator`, which lets the user specify custom memory allocator for block based table.
+* Improved `DeleteRange` to prevent read performance degradation. The feature is no longer marked as experimental.
+
+### Public API Change
+* `DBOptions::use_direct_reads` now affects reads issued by `BackupEngine` on the database's SSTs.
+* `NO_ITERATORS` is divided into two counters `NO_ITERATOR_CREATED` and `NO_ITERATOR_DELETE`. Both of them are only increasing now, just as other counters.
+
+### Bug Fixes
+* Fix corner case where a write group leader blocked due to write stall blocks other writers in queue with WriteOptions::no_slowdown set.
+* Fix in-memory range tombstone truncation to avoid erroneously covering newer keys at a lower level, and include range tombstones in compacted files whose largest key is the range tombstone's start key.
+* Properly set the stop key for a truncated manual CompactRange
+* Fix slow flush/compaction when DB contains many snapshots. The problem became noticeable to us in DBs with 100,000+ snapshots, though it will affect others at different thresholds.
+* Fix the bug that WriteBatchWithIndex's SeekForPrev() doesn't see the entries with the same key.
+* Fix the bug where user comparator was sometimes fed with InternalKey instead of the user key. The bug manifests when during GenerateBottommostFiles.
+* Fix a bug in WritePrepared txns where if the number of old snapshots goes beyond the snapshot cache size (128 default) the rest will not be checked when evicting a commit entry from the commit cache.
+* Fixed Get correctness bug in the presence of range tombstones where merge operands covered by a range tombstone always result in NotFound.
+* Start populating `NO_FILE_CLOSES` ticker statistic, which was always zero previously.
+* The default value of NewBloomFilterPolicy()'s argument use_block_based_builder is changed to false. Note that this new default may cause large temp memory usage when building very large SST files.
+
+## 5.17.0 (10/05/2018)
+### Public API Change
+* `OnTableFileCreated` will now be called for empty files generated during compaction. In that case, `TableFileCreationInfo::file_path` will be "(nil)" and `TableFileCreationInfo::file_size` will be zero.
+* Add `FlushOptions::allow_write_stall`, which controls whether Flush calls start working immediately, even if it causes user writes to stall, or will wait until flush can be performed without causing write stall (similar to `CompactRangeOptions::allow_write_stall`). Note that the default value is false, meaning we add delay to Flush calls until stalling can be avoided when possible. This is behavior change compared to previous RocksDB versions, where Flush calls didn't check if they might cause stall or not.
+* Application using PessimisticTransactionDB is expected to rollback/commit recovered transactions before starting new ones. This assumption is used to skip concurrency control during recovery.
+* Expose column family id to `OnCompactionCompleted`.
+
+### New Features
+* TransactionOptions::skip_concurrency_control allows pessimistic transactions to skip the overhead of concurrency control. Could be used for optimizing certain transactions or during recovery.
+
+### Bug Fixes
+* Avoid creating empty SSTs and subsequently deleting them in certain cases during compaction.
+* Sync CURRENT file contents during checkpoint.
+
+## 5.16.3 (10/1/2018)
+### Bug Fixes
+* Fix crash caused when `CompactFiles` run with `CompactionOptions::compression == CompressionType::kDisableCompressionOption`. Now that setting causes the compression type to be chosen according to the column family-wide compression options.
+
+## 5.16.2 (9/21/2018)
+### Bug Fixes
+* Fix bug in partition filters with format_version=4.
+
+## 5.16.1 (9/17/2018)
+### Bug Fixes
+* Remove trace_analyzer_tool from rocksdb_lib target in TARGETS file.
+* Fix RocksDB Java build and tests.
+* Remove sync point in Block destructor.
 
 ## 5.16.0 (8/21/2018)
 ### Public API Change
-* The merge operands are passed to `MergeOperator::ShouldMerge` in the reversed order relative to how they were merged (passed to FullMerge or FullMergeV2) for performance reasons 
+* The merge operands are passed to `MergeOperator::ShouldMerge` in the reversed order relative to how they were merged (passed to FullMerge or FullMergeV2) for performance reasons
 * GetAllKeyVersions() to take an extra argument of `max_num_ikeys`.
+* Using ZSTD dictionary trainer (i.e., setting `CompressionOptions::zstd_max_train_bytes` to a nonzero value) now requires ZSTD version 1.1.3 or later.
 
 ### New Features
 * Changes the format of index blocks by delta encoding the index values, which are the block handles. This saves the encoding of BlockHandle::offset of the non-head index entries in each restart interval. The feature is backward compatible but not forward compatible. It is disabled by default unless format_version 4 or above is used.
@@ -151,7 +211,8 @@
 * `BackupableDBOptions::max_valid_backups_to_open == 0` now means no backups will be opened during BackupEngine initialization. Previously this condition disabled limiting backups opened.
 * `DBOptions::preserve_deletes` is a new option that allows one to specify that DB should not drop tombstones for regular deletes if they have sequence number larger than what was set by the new API call `DB::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum)`. Disabled by default.
 * API call `DB::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum)` was added, users who wish to preserve deletes are expected to periodically call this function to advance the cutoff seqnum (all deletes made before this seqnum can be dropped by DB). It's user responsibility to figure out how to advance the seqnum in the way so the tombstones are kept for the desired period of time, yet are eventually processed in time and don't eat up too much space.
-* `ReadOptions::iter_start_seqnum` was added; if set to something > 0 user will see 2 changes in iterators behavior 1) only keys written with sequence larger than this parameter would be returned and 2) the `Slice` returned by iter->key() now points to the memory that keep User-oriented representation of the internal key, rather than user key. New struct `FullKey` was added to represent internal keys, along with a new helper function `ParseFullKey(const Slice& internal_key, FullKey* result);`.
+* `ReadOptions::iter_start_seqnum` was added;
+if set to something > 0 user will see 2 changes in iterators behavior 1) only keys written with sequence larger than this parameter would be returned and 2) the `Slice` returned by iter->key() now points to the memory that keep User-oriented representation of the internal key, rather than user key. New struct `FullKey` was added to represent internal keys, along with a new helper function `ParseFullKey(const Slice& internal_key, FullKey* result);`.
 * Deprecate trash_dir param in NewSstFileManager, right now we will rename deleted files to <name>.trash instead of moving them to trash directory
 * Allow setting a custom trash/DB size ratio limit in the SstFileManager, after which files that are to be scheduled for deletion are deleted immediately, regardless of any delete ratelimit.
 * Return an error on write if write_options.sync = true and write_options.disableWAL = true to warn user of inconsistent options. Previously we will not write to WAL and not respecting the sync options in this case.
diff --git a/3rdParty/rocksdb/v5.16.X/INSTALL.md b/3rdParty/rocksdb/v5.18.X/INSTALL.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/INSTALL.md
rename to 3rdParty/rocksdb/v5.18.X/INSTALL.md
diff --git a/3rdParty/rocksdb/v5.16.X/LANGUAGE-BINDINGS.md b/3rdParty/rocksdb/v5.18.X/LANGUAGE-BINDINGS.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/LANGUAGE-BINDINGS.md
rename to 3rdParty/rocksdb/v5.18.X/LANGUAGE-BINDINGS.md
diff --git a/3rdParty/rocksdb/v5.16.X/LICENSE.Apache b/3rdParty/rocksdb/v5.18.X/LICENSE.Apache
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/LICENSE.Apache
rename to 3rdParty/rocksdb/v5.18.X/LICENSE.Apache
diff --git a/3rdParty/rocksdb/v5.16.X/LICENSE.leveldb b/3rdParty/rocksdb/v5.18.X/LICENSE.leveldb
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/LICENSE.leveldb
rename to 3rdParty/rocksdb/v5.18.X/LICENSE.leveldb
diff --git a/3rdParty/rocksdb/v5.16.X/Makefile b/3rdParty/rocksdb/v5.18.X/Makefile
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/Makefile
rename to 3rdParty/rocksdb/v5.18.X/Makefile
index 66d94f655e..d4d563f4d6 100644
--- a/3rdParty/rocksdb/v5.16.X/Makefile
+++ b/3rdParty/rocksdb/v5.18.X/Makefile
@@ -93,19 +93,38 @@ ifeq ($(MAKECMDGOALS),rocksdbjavastaticpublish)
 	DEBUG_LEVEL=0
 endif
 
+# Lite build flag.
+LITE ?= 0
+ifeq ($(LITE), 0)
+ifneq ($(filter -DROCKSDB_LITE,$(OPT)),)
+  # Be backward compatible and support older format where OPT=-DROCKSDB_LITE is
+  # specified instead of LITE=1 on the command line.
+  LITE=1
+endif
+else ifeq ($(LITE), 1)
+ifeq ($(filter -DROCKSDB_LITE,$(OPT)),)
+	OPT += -DROCKSDB_LITE
+endif
+endif
+
+# Figure out optimize level.
+ifneq ($(DEBUG_LEVEL), 2)
+ifeq ($(LITE), 0)
+	OPT += -O2
+else
+	OPT += -Os
+endif
+endif
+
 # compile with -O2 if debug level is not 2
 ifneq ($(DEBUG_LEVEL), 2)
-OPT += -O2 -fno-omit-frame-pointer
+OPT += -fno-omit-frame-pointer
 # Skip for archs that don't support -momit-leaf-frame-pointer
 ifeq (,$(shell $(CXX) -fsyntax-only -momit-leaf-frame-pointer -xc /dev/null 2>&1))
 OPT += -momit-leaf-frame-pointer
 endif
 endif
 
-ifeq (,$(shell $(CXX) -fsyntax-only -faligned-new -xc++ /dev/null 2>&1))
-CXXFLAGS += -faligned-new -DHAVE_ALIGNED_NEW
-endif
-
 ifeq (,$(shell $(CXX) -fsyntax-only -maltivec -xc /dev/null 2>&1))
 CXXFLAGS += -DHAS_ALTIVEC
 CFLAGS += -DHAS_ALTIVEC
@@ -322,7 +341,7 @@ endif
 ifeq ("$(wildcard $(LUA_LIB))", "") # LUA_LIB does not exist
 $(error $(LUA_LIB) does not exist.  Try to specify both LUA_PATH and LUA_LIB manually)
 endif
-LDFLAGS += $(LUA_LIB)
+EXEC_LDFLAGS += $(LUA_LIB)
 
 endif
 
@@ -533,6 +552,10 @@ TESTS = \
 	write_unprepared_transaction_test \
 	db_universal_compaction_test \
 	trace_analyzer_test \
+	repeatable_thread_test \
+	range_tombstone_fragmenter_test \
+	range_del_aggregator_v2_test \
+	sst_file_reader_test \
 
 PARALLEL_TEST = \
 	backupable_db_test \
@@ -582,7 +605,7 @@ TEST_LIBS = \
 	librocksdb_env_basic_test.a
 
 # TODO: add back forward_iterator_bench, after making it build in all environemnts.
-BENCHMARKS = db_bench table_reader_bench cache_bench memtablerep_bench column_aware_encoding_exp persistent_cache_bench
+BENCHMARKS = db_bench table_reader_bench cache_bench memtablerep_bench column_aware_encoding_exp persistent_cache_bench range_del_aggregator_bench
 
 # if user didn't config LIBNAME, set the default
 ifeq ($(LIBNAME),)
@@ -883,6 +906,7 @@ crash_test: whitebox_crash_test blackbox_crash_test
 
 blackbox_crash_test: db_stress
 	python -u tools/db_crashtest.py --simple blackbox $(CRASH_TEST_EXT_ARGS)
+	python -u tools/db_crashtest.py --enable_atomic_flush blackbox $(CRASH_TEST_EXT_ARGS)
 	python -u tools/db_crashtest.py blackbox $(CRASH_TEST_EXT_ARGS)
 
 ifeq ($(CRASH_TEST_KILL_ODD),)
@@ -891,6 +915,8 @@ endif
 
 whitebox_crash_test: db_stress
 	python -u tools/db_crashtest.py --simple whitebox --random_kill_odd \
+      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
+	python -u tools/db_crashtest.py --enable_atomic_flush whitebox  --random_kill_odd \
       $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
 	python -u tools/db_crashtest.py whitebox  --random_kill_odd \
       $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
@@ -1002,8 +1028,10 @@ unity.a: unity.o
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ unity.o
 
+
+TOOLLIBOBJECTS = $(TOOL_LIB_SOURCES:.cc=.o)
 # try compiling db_test with unity
-unity_test: db/db_test.o db/db_test_util.o $(TESTHARNESS) unity.a
+unity_test: db/db_test.o db/db_test_util.o $(TESTHARNESS) $(TOOLLIBOBJECTS) unity.a
 	$(AM_LINK)
 	./unity_test
 
@@ -1548,9 +1576,24 @@ lua_test: utilities/lua/rocks_lua_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTH
 range_del_aggregator_test: db/range_del_aggregator_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+range_del_aggregator_bench: db/range_del_aggregator_bench.o $(LIBOBJECTS) $(TESTUTIL)
+	$(AM_LINK)
+
 blob_db_test: utilities/blob_db/blob_db_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
+repeatable_thread_test: util/repeatable_thread_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+range_tombstone_fragmenter_test: db/range_tombstone_fragmenter_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+range_del_aggregator_v2_test: db/range_del_aggregator_v2_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
+sst_file_reader_test: table/sst_file_reader_test.o $(LIBOBJECTS) $(TESTHARNESS)
+	$(AM_LINK)
+
 #-------------------------------------------------
 # make install related stuff
 INSTALL_PATH ?= /usr/local
@@ -1621,7 +1664,7 @@ ZLIB_SHA256 ?= c3e5e9fdd5004dcb542feda5ee4f0ff0744628baf8ed2dd5d66f8ca1197cb1a1
 ZLIB_DOWNLOAD_BASE ?= http://zlib.net
 BZIP2_VER ?= 1.0.6
 BZIP2_SHA256 ?= a2848f34fcd5d6cf47def00461fcb528a0484d8edef8208d6d2e2909dc61d9cd
-BZIP2_DOWNLOAD_BASE ?= http://www.bzip.org
+BZIP2_DOWNLOAD_BASE ?= https://web.archive.org/web/20180624184835/http://www.bzip.org
 SNAPPY_VER ?= 1.1.4
 SNAPPY_SHA256 ?= 134bfe122fd25599bb807bb8130e7ba6d9bdb851e0b16efcb83ac4f5d0b70057
 SNAPPY_DOWNLOAD_BASE ?= https://github.com/google/snappy/releases/download
@@ -1856,7 +1899,7 @@ $(java_libobjects): jl/%.o: %.cc
 rocksdbjava: $(java_all_libobjects)
 	$(AM_V_GEN)cd java;$(MAKE) javalib;
 	$(AM_V_at)rm -f ./java/target/$(ROCKSDBJNILIB)
-	$(AM_V_at)$(CXX) $(CXXFLAGS) -I./java/. $(JAVA_INCLUDE) -shared -fPIC -o ./java/target/$(ROCKSDBJNILIB) $(JNI_NATIVE_SOURCES) $(java_libobjects) $(JAVA_LDFLAGS) $(COVERAGEFLAGS)
+	$(AM_V_at)$(CXX) $(CXXFLAGS) -I./java/. $(JAVA_INCLUDE) -shared -fPIC -o ./java/target/$(ROCKSDBJNILIB) $(JNI_NATIVE_SOURCES) $(java_all_libobjects) $(JAVA_LDFLAGS) $(COVERAGEFLAGS)
 	$(AM_V_at)cd java;jar -cf target/$(ROCKSDB_JAR) HISTORY*.md
 	$(AM_V_at)cd java/target;jar -uf $(ROCKSDB_JAR) $(ROCKSDBJNILIB)
 	$(AM_V_at)cd java/target/classes;jar -uf ../$(ROCKSDB_JAR) org/rocksdb/*.class org/rocksdb/util/*.class
diff --git a/3rdParty/rocksdb/v5.16.X/README.md b/3rdParty/rocksdb/v5.18.X/README.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/README.md
rename to 3rdParty/rocksdb/v5.18.X/README.md
diff --git a/3rdParty/rocksdb/v5.16.X/ROCKSDB_LITE.md b/3rdParty/rocksdb/v5.18.X/ROCKSDB_LITE.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/ROCKSDB_LITE.md
rename to 3rdParty/rocksdb/v5.18.X/ROCKSDB_LITE.md
diff --git a/3rdParty/rocksdb/v5.16.X/TARGETS b/3rdParty/rocksdb/v5.18.X/TARGETS
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/TARGETS
rename to 3rdParty/rocksdb/v5.18.X/TARGETS
index 483dfb5e8e..246c2efee2 100644
--- a/3rdParty/rocksdb/v5.16.X/TARGETS
+++ b/3rdParty/rocksdb/v5.18.X/TARGETS
@@ -1,3 +1,5 @@
+load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
+
 REPO_PATH = package_name() + "/"
 
 BUCK_BINS = "buck-out/gen/" + REPO_PATH
@@ -65,6 +67,16 @@ is_opt_mode = build_mode.startswith("opt")
 if is_opt_mode:
     rocksdb_compiler_flags.append("-DNDEBUG")
 
+default_allocator = read_config("fbcode", "default_allocator")
+
+sanitizer = read_config("fbcode", "sanitizer")
+
+# Let RocksDB aware of jemalloc existence.
+# Do not enable it if sanitizer presents.
+if is_opt_mode and default_allocator.startswith("jemalloc") and sanitizer == "":
+    rocksdb_compiler_flags.append("-DROCKSDB_JEMALLOC")
+    rocksdb_external_deps.append(("jemalloc", None, "headers"))
+
 cpp_library(
     name = "rocksdb_lib",
     srcs = [
@@ -79,6 +91,7 @@ cpp_library(
         "db/compaction_iterator.cc",
         "db/compaction_job.cc",
         "db/compaction_picker.cc",
+        "db/compaction_picker_fifo.cc",
         "db/compaction_picker_universal.cc",
         "db/convenience.cc",
         "db/db_filesnapshot.cc",
@@ -111,6 +124,8 @@ cpp_library(
         "db/merge_helper.cc",
         "db/merge_operator.cc",
         "db/range_del_aggregator.cc",
+        "db/range_del_aggregator_v2.cc",
+        "db/range_tombstone_fragmenter.cc",
         "db/repair.cc",
         "db/snapshot_impl.cc",
         "db/table_cache.cc",
@@ -188,6 +203,7 @@ cpp_library(
         "table/plain_table_index.cc",
         "table/plain_table_key_coding.cc",
         "table/plain_table_reader.cc",
+        "table/sst_file_reader.cc",
         "table/sst_file_writer.cc",
         "table/table_properties.cc",
         "table/two_level_iterator.cc",
@@ -195,7 +211,6 @@ cpp_library(
         "tools/ldb_cmd.cc",
         "tools/ldb_tool.cc",
         "tools/sst_dump_tool.cc",
-        "tools/trace_analyzer_tool.cc",
         "util/arena.cc",
         "util/auto_roll_logger.cc",
         "util/bloom.cc",
@@ -214,6 +229,7 @@ cpp_library(
         "util/filename.cc",
         "util/filter_policy.cc",
         "util/hash.cc",
+        "util/jemalloc_nodump_allocator.cc",
         "util/log_buffer.cc",
         "util/murmurhash.cc",
         "util/random.cc",
@@ -233,6 +249,7 @@ cpp_library(
         "utilities/blob_db/blob_compaction_filter.cc",
         "utilities/blob_db/blob_db.cc",
         "utilities/blob_db/blob_db_impl.cc",
+        "utilities/blob_db/blob_db_impl_filesnapshot.cc",
         "utilities/blob_db/blob_dump_tool.cc",
         "utilities/blob_db/blob_file.cc",
         "utilities/blob_db/blob_log_format.cc",
@@ -290,7 +307,7 @@ cpp_library(
         "utilities/write_batch_with_index/write_batch_with_index.cc",
         "utilities/write_batch_with_index/write_batch_with_index_internal.cc",
     ],
-    headers = AutoHeaders.RECURSIVE_GLOB,
+    auto_headers = AutoHeaders.RECURSIVE_GLOB,
     arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
     compiler_flags = rocksdb_compiler_flags,
     preprocessor_flags = rocksdb_preprocessor_flags,
@@ -303,6 +320,7 @@ cpp_library(
     srcs = [
         "db/db_test_util.cc",
         "table/mock_table.cc",
+        "tools/trace_analyzer_tool.cc",
         "util/fault_injection_test_env.cc",
         "util/testharness.cc",
         "util/testutil.cc",
@@ -311,7 +329,7 @@ cpp_library(
         "utilities/col_buf_encoder.cc",
         "utilities/column_aware_encoding_util.cc",
     ],
-    headers = AutoHeaders.RECURSIVE_GLOB,
+    auto_headers = AutoHeaders.RECURSIVE_GLOB,
     arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
     compiler_flags = rocksdb_compiler_flags,
     preprocessor_flags = rocksdb_preprocessor_flags,
@@ -323,9 +341,10 @@ cpp_library(
     name = "rocksdb_tools_lib",
     srcs = [
         "tools/db_bench_tool.cc",
+        "tools/trace_analyzer_tool.cc",
         "util/testutil.cc",
     ],
-    headers = AutoHeaders.RECURSIVE_GLOB,
+    auto_headers = AutoHeaders.RECURSIVE_GLOB,
     arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
     compiler_flags = rocksdb_compiler_flags,
     preprocessor_flags = rocksdb_preprocessor_flags,
@@ -336,7 +355,7 @@ cpp_library(
 cpp_library(
     name = "env_basic_test_lib",
     srcs = ["env/env_basic_test.cc"],
-    headers = AutoHeaders.RECURSIVE_GLOB,
+    auto_headers = AutoHeaders.RECURSIVE_GLOB,
     arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
     compiler_flags = rocksdb_compiler_flags,
     preprocessor_flags = rocksdb_preprocessor_flags,
@@ -376,11 +395,6 @@ ROCKS_TESTS = [
         "table/block_based_filter_block_test.cc",
         "serial",
     ],
-    [
-        "data_block_hash_index_test",
-        "table/data_block_hash_index_test.cc",
-        "serial",
-    ],
     [
         "block_test",
         "table/block_test.cc",
@@ -506,6 +520,11 @@ ROCKS_TESTS = [
         "table/cuckoo_table_reader_test.cc",
         "serial",
     ],
+    [
+        "data_block_hash_index_test",
+        "table/data_block_hash_index_test.cc",
+        "serial",
+    ],
     [
         "date_tiered_test",
         "utilities/date_tiered/date_tiered_test.cc",
@@ -916,6 +935,16 @@ ROCKS_TESTS = [
         "db/range_del_aggregator_test.cc",
         "serial",
     ],
+    [
+        "range_del_aggregator_v2_test",
+        "db/range_del_aggregator_v2_test.cc",
+        "serial",
+    ],
+    [
+        "range_tombstone_fragmenter_test",
+        "db/range_tombstone_fragmenter_test.cc",
+        "serial",
+    ],
     [
         "rate_limiter_test",
         "util/rate_limiter_test.cc",
@@ -931,6 +960,11 @@ ROCKS_TESTS = [
         "db/repair_test.cc",
         "serial",
     ],
+    [
+        "repeatable_thread_test",
+        "util/repeatable_thread_test.cc",
+        "serial",
+    ],
     [
         "sim_cache_test",
         "utilities/simulator_cache/sim_cache_test.cc",
@@ -957,8 +991,8 @@ ROCKS_TESTS = [
         "serial",
     ],
     [
-        "trace_analyzer_test",
-        "tools/trace_analyzer_test.cc",
+        "sst_file_reader_test",
+        "table/sst_file_reader_test.cc",
         "serial",
     ],
     [
@@ -996,6 +1030,11 @@ ROCKS_TESTS = [
         "util/timer_queue_test.cc",
         "serial",
     ],
+    [
+        "trace_analyzer_test",
+        "tools/trace_analyzer_test.cc",
+        "serial",
+    ],
     [
         "transaction_test",
         "utilities/transactions/transaction_test.cc",
@@ -1078,19 +1117,19 @@ if not is_opt_mode:
         ttype = "gtest" if test_cfg[2] == "parallel" else "simple"
         test_bin = test_name + "_bin"
 
-        cpp_binary (
-          name = test_bin,
-          srcs = [test_cc],
-          deps = [":rocksdb_test_lib"],
-          preprocessor_flags = rocksdb_preprocessor_flags,
-          arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
-          compiler_flags = rocksdb_compiler_flags,
-          external_deps = rocksdb_external_deps,
+        cpp_binary(
+            name = test_bin,
+            srcs = [test_cc],
+            arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+            compiler_flags = rocksdb_compiler_flags,
+            preprocessor_flags = rocksdb_preprocessor_flags,
+            deps = [":rocksdb_test_lib"],
+            external_deps = rocksdb_external_deps,
         )
 
         custom_unittest(
-          name = test_name,
-          type = ttype,
-          deps = [":" + test_bin],
-          command = [TEST_RUNNER, BUCK_BINS + test_bin]
+            name = test_name,
+            command = [TEST_RUNNER, BUCK_BINS + test_bin],
+            type = ttype,
+            deps = [":" + test_bin],
         )
diff --git a/3rdParty/rocksdb/v5.16.X/USERS.md b/3rdParty/rocksdb/v5.18.X/USERS.md
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/USERS.md
rename to 3rdParty/rocksdb/v5.18.X/USERS.md
index 993cc69d34..a95903f066 100644
--- a/3rdParty/rocksdb/v5.16.X/USERS.md
+++ b/3rdParty/rocksdb/v5.18.X/USERS.md
@@ -12,6 +12,7 @@ At Facebook, we use RocksDB as storage engines in multiple data management servi
 6. LogDevice -- a distributed data store for logs [2]
 
 [1] https://research.facebook.com/publications/realtime-data-processing-at-facebook/
+
 [2] https://code.facebook.com/posts/357056558062811/logdevice-a-distributed-data-store-for-logs/
 
 ## LinkedIn
@@ -88,3 +89,6 @@ LzLabs is using RocksDB as a storage engine in their multi-database distributed
 
 ## ProfaneDB
 [ProfaneDB](https://profanedb.gitlab.io/) is a database for Protocol Buffers, and uses RocksDB for storage. It is accessible via gRPC, and the schema is defined using directly `.proto` files.
+
+## IOTA Foundation
+ [IOTA Foundation](https://www.iota.org/) is using RocksDB in the [IOTA Reference Implementation (IRI)](https://github.com/iotaledger/iri) to store the local state of the Tangle. The Tangle is the first open-source distributed ledger powering the future of the Internet of Things.
\ No newline at end of file
diff --git a/3rdParty/rocksdb/v5.16.X/Vagrantfile b/3rdParty/rocksdb/v5.18.X/Vagrantfile
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/Vagrantfile
rename to 3rdParty/rocksdb/v5.18.X/Vagrantfile
diff --git a/3rdParty/rocksdb/v5.16.X/WINDOWS_PORT.md b/3rdParty/rocksdb/v5.18.X/WINDOWS_PORT.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/WINDOWS_PORT.md
rename to 3rdParty/rocksdb/v5.18.X/WINDOWS_PORT.md
diff --git a/3rdParty/rocksdb/v5.16.X/appveyor.yml b/3rdParty/rocksdb/v5.18.X/appveyor.yml
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/appveyor.yml
rename to 3rdParty/rocksdb/v5.18.X/appveyor.yml
diff --git a/3rdParty/rocksdb/v5.16.X/buckifier/buckify_rocksdb.py b/3rdParty/rocksdb/v5.18.X/buckifier/buckify_rocksdb.py
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/buckifier/buckify_rocksdb.py
rename to 3rdParty/rocksdb/v5.18.X/buckifier/buckify_rocksdb.py
index 38aa0bf18e..96903af682 100644
--- a/3rdParty/rocksdb/v5.16.X/buckifier/buckify_rocksdb.py
+++ b/3rdParty/rocksdb/v5.18.X/buckifier/buckify_rocksdb.py
@@ -109,12 +109,14 @@ def generate_targets(repo_path):
         "rocksdb_test_lib",
         src_mk.get("MOCK_LIB_SOURCES", []) +
         src_mk.get("TEST_LIB_SOURCES", []) +
-        src_mk.get("EXP_LIB_SOURCES", []),
+        src_mk.get("EXP_LIB_SOURCES", []) +
+        src_mk.get("ANALYZER_LIB_SOURCES", []),
         [":rocksdb_lib"])
     # rocksdb_tools_lib
     TARGETS.add_library(
         "rocksdb_tools_lib",
         src_mk.get("BENCH_LIB_SOURCES", []) +
+        src_mk.get("ANALYZER_LIB_SOURCES", []) +
         ["util/testutil.cc"],
         [":rocksdb_lib"])
 
diff --git a/3rdParty/rocksdb/v5.16.X/buckifier/rocks_test_runner.sh b/3rdParty/rocksdb/v5.18.X/buckifier/rocks_test_runner.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/buckifier/rocks_test_runner.sh
rename to 3rdParty/rocksdb/v5.18.X/buckifier/rocks_test_runner.sh
diff --git a/3rdParty/rocksdb/v5.16.X/buckifier/targets_builder.py b/3rdParty/rocksdb/v5.18.X/buckifier/targets_builder.py
similarity index 84%
rename from 3rdParty/rocksdb/v5.16.X/buckifier/targets_builder.py
rename to 3rdParty/rocksdb/v5.18.X/buckifier/targets_builder.py
index 7d700a21f0..3d5822d3cb 100644
--- a/3rdParty/rocksdb/v5.16.X/buckifier/targets_builder.py
+++ b/3rdParty/rocksdb/v5.18.X/buckifier/targets_builder.py
@@ -10,7 +10,7 @@ def pretty_list(lst, indent=8):
 
     if len(lst) == 1:
         return "\"%s\"" % lst[0]
-    
+
     separator = "\",\n%s\"" % (" " * indent)
     res = separator.join(sorted(lst))
     res = "\n" + (" " * indent) + "\"" + res + "\",\n" + (" " * (indent - 4))
@@ -31,13 +31,16 @@ class TARGETSBuilder:
         self.targets_file.close()
 
     def add_library(self, name, srcs, deps=None, headers=None):
+        headers_attr_prefix = ""
         if headers is None:
+            headers_attr_prefix = "auto_"
             headers = "AutoHeaders.RECURSIVE_GLOB"
-        self.targets_file.write(targets_cfg.library_template % (
-            name,
-            pretty_list(srcs),
-            headers,
-            pretty_list(deps)))
+        self.targets_file.write(targets_cfg.library_template.format(
+            name=name,
+            srcs=pretty_list(srcs),
+            headers_attr_prefix=headers_attr_prefix,
+            headers=headers,
+            deps=pretty_list(deps)))
         self.total_lib = self.total_lib + 1
 
     def add_binary(self, name, srcs, deps=None):
diff --git a/3rdParty/rocksdb/v5.16.X/buckifier/targets_cfg.py b/3rdParty/rocksdb/v5.18.X/buckifier/targets_cfg.py
similarity index 71%
rename from 3rdParty/rocksdb/v5.16.X/buckifier/targets_cfg.py
rename to 3rdParty/rocksdb/v5.18.X/buckifier/targets_cfg.py
index 1b426acf0a..5378f697a8 100644
--- a/3rdParty/rocksdb/v5.16.X/buckifier/targets_cfg.py
+++ b/3rdParty/rocksdb/v5.18.X/buckifier/targets_cfg.py
@@ -2,7 +2,9 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-rocksdb_target_header = """REPO_PATH = package_name() + "/"
+rocksdb_target_header = """load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
+
+REPO_PATH = package_name() + "/"
 
 BUCK_BINS = "buck-out/gen/" + REPO_PATH
 
@@ -68,18 +70,28 @@ is_opt_mode = build_mode.startswith("opt")
 # doesn't harm and avoid forgetting to add it.
 if is_opt_mode:
     rocksdb_compiler_flags.append("-DNDEBUG")
+
+default_allocator = read_config("fbcode", "default_allocator")
+
+sanitizer = read_config("fbcode", "sanitizer")
+
+# Let RocksDB aware of jemalloc existence.
+# Do not enable it if sanitizer presents.
+if is_opt_mode and default_allocator.startswith("jemalloc") and sanitizer == "":
+    rocksdb_compiler_flags.append("-DROCKSDB_JEMALLOC")
+    rocksdb_external_deps.append(("jemalloc", None, "headers"))
 """
 
 
 library_template = """
 cpp_library(
-    name = "%s",
-    srcs = [%s],
-    headers = %s,
+    name = "{name}",
+    srcs = [{srcs}],
+    {headers_attr_prefix}headers = {headers},
     arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
     compiler_flags = rocksdb_compiler_flags,
     preprocessor_flags = rocksdb_preprocessor_flags,
-    deps = [%s],
+    deps = [{deps}],
     external_deps = rocksdb_external_deps,
 )
 """
@@ -118,21 +130,20 @@ if not is_opt_mode:
         ttype = "gtest" if test_cfg[2] == "parallel" else "simple"
         test_bin = test_name + "_bin"
 
-        cpp_binary (
-          name = test_bin,
-          srcs = [test_cc],
-          deps = [":rocksdb_test_lib"],
-          preprocessor_flags = rocksdb_preprocessor_flags,
-          arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
-          compiler_flags = rocksdb_compiler_flags,
-          external_deps = rocksdb_external_deps,
+        cpp_binary(
+            name = test_bin,
+            srcs = [test_cc],
+            arch_preprocessor_flags = rocksdb_arch_preprocessor_flags,
+            compiler_flags = rocksdb_compiler_flags,
+            preprocessor_flags = rocksdb_preprocessor_flags,
+            deps = [":rocksdb_test_lib"],
+            external_deps = rocksdb_external_deps,
         )
 
         custom_unittest(
-          name = test_name,
-          type = ttype,
-          deps = [":" + test_bin],
-          command = [TEST_RUNNER, BUCK_BINS + test_bin]
+            name = test_name,
+            command = [TEST_RUNNER, BUCK_BINS + test_bin],
+            type = ttype,
+            deps = [":" + test_bin],
         )
-
 """
diff --git a/3rdParty/rocksdb/v5.16.X/buckifier/util.py b/3rdParty/rocksdb/v5.18.X/buckifier/util.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/buckifier/util.py
rename to 3rdParty/rocksdb/v5.18.X/buckifier/util.py
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/RocksDBCommonHelper.php b/3rdParty/rocksdb/v5.18.X/build_tools/RocksDBCommonHelper.php
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/RocksDBCommonHelper.php
rename to 3rdParty/rocksdb/v5.18.X/build_tools/RocksDBCommonHelper.php
index 9fe770fe95..4f4663cbe9 100644
--- a/3rdParty/rocksdb/v5.16.X/build_tools/RocksDBCommonHelper.php
+++ b/3rdParty/rocksdb/v5.18.X/build_tools/RocksDBCommonHelper.php
@@ -7,12 +7,12 @@
 // Name of the environment variables which need to be set by the entity which
 // triggers continuous runs so that code at the end of the file gets executed
 // and Sandcastle run starts.
-define("ENV_POST_RECEIVE_HOOK", "POST_RECEIVE_HOOK");
-define("ENV_HTTPS_APP_VALUE", "HTTPS_APP_VALUE");
-define("ENV_HTTPS_TOKEN_VALUE", "HTTPS_TOKEN_VALUE");
+const ENV_POST_RECEIVE_HOOK = "POST_RECEIVE_HOOK";
+const ENV_HTTPS_APP_VALUE = "HTTPS_APP_VALUE";
+const ENV_HTTPS_TOKEN_VALUE = "HTTPS_TOKEN_VALUE";
 
-define("PRIMARY_TOKEN_FILE", '/home/krad/.sandcastle');
-define("CONT_RUN_ALIAS", "leveldb");
+const PRIMARY_TOKEN_FILE = '/home/krad/.sandcastle';
+const CONT_RUN_ALIAS = "leveldb";
 
 //////////////////////////////////////////////////////////////////////
 /*  Run tests in sandcastle */
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/amalgamate.py b/3rdParty/rocksdb/v5.18.X/build_tools/amalgamate.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/amalgamate.py
rename to 3rdParty/rocksdb/v5.18.X/build_tools/amalgamate.py
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/build_detect_platform b/3rdParty/rocksdb/v5.18.X/build_tools/build_detect_platform
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/build_detect_platform
rename to 3rdParty/rocksdb/v5.18.X/build_tools/build_detect_platform
index 66039bce5c..f237fa4ee8 100755
--- a/3rdParty/rocksdb/v5.16.X/build_tools/build_detect_platform
+++ b/3rdParty/rocksdb/v5.18.X/build_tools/build_detect_platform
@@ -44,7 +44,7 @@ if test -z "$OUTPUT"; then
 fi
 
 # we depend on C++11
-PLATFORM_CXXFLAGS="-std=c++14"
+PLATFORM_CXXFLAGS="-std=c++11"
 # we currently depend on POSIX platform
 COMMON_FLAGS="-DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX"
 
@@ -474,6 +474,17 @@ EOF
             COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_SCHED_GETCPU_PRESENT"
         fi
     fi
+
+    if ! test $ROCKSDB_DISABLE_ALIGNED_NEW; then
+        # Test whether c++17 aligned-new is supported
+        $CXX $PLATFORM_CXXFLAGS -faligned-new -x c++ - -o /dev/null 2>/dev/null <<EOF
+            struct alignas(1024) t {int a;};
+            int main() {}
+EOF
+        if [ "$?" = 0 ]; then
+            PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS -faligned-new -DHAVE_ALIGNED_NEW"
+        fi
+    fi
 fi
 
 # TODO(tec): Fix -Wshorten-64-to-32 errors on FreeBSD and enable the warning.
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/cont_integration.sh b/3rdParty/rocksdb/v5.18.X/build_tools/cont_integration.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/cont_integration.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/cont_integration.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/dependencies.sh b/3rdParty/rocksdb/v5.18.X/build_tools/dependencies.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/dependencies.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/dependencies.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/dependencies_4.8.1.sh b/3rdParty/rocksdb/v5.18.X/build_tools/dependencies_4.8.1.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/dependencies_4.8.1.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/dependencies_4.8.1.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/dockerbuild.sh b/3rdParty/rocksdb/v5.18.X/build_tools/dockerbuild.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/dockerbuild.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/dockerbuild.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/error_filter.py b/3rdParty/rocksdb/v5.18.X/build_tools/error_filter.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/error_filter.py
rename to 3rdParty/rocksdb/v5.18.X/build_tools/error_filter.py
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/fb_compile_mongo.sh b/3rdParty/rocksdb/v5.18.X/build_tools/fb_compile_mongo.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/fb_compile_mongo.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/fb_compile_mongo.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/fbcode_config.sh b/3rdParty/rocksdb/v5.18.X/build_tools/fbcode_config.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/fbcode_config.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/fbcode_config.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/fbcode_config4.8.1.sh b/3rdParty/rocksdb/v5.18.X/build_tools/fbcode_config4.8.1.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/fbcode_config4.8.1.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/fbcode_config4.8.1.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/format-diff.sh b/3rdParty/rocksdb/v5.18.X/build_tools/format-diff.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/format-diff.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/format-diff.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/gnu_parallel b/3rdParty/rocksdb/v5.18.X/build_tools/gnu_parallel
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/gnu_parallel
rename to 3rdParty/rocksdb/v5.18.X/build_tools/gnu_parallel
index abbf8f1008..1cf164fff0 100755
--- a/3rdParty/rocksdb/v5.16.X/build_tools/gnu_parallel
+++ b/3rdParty/rocksdb/v5.18.X/build_tools/gnu_parallel
@@ -5082,8 +5082,8 @@ sub openoutputfiles {
 	# Set reading FD if using --group (--ungroup does not need)
 	for my $fdno (1,2) {
 	    # Re-open the file for reading
-	    # so fdw can be closed seperately
-	    # and fdr can be seeked seperately (for --line-buffer)
+	    # so fdw can be closed separately
+	    # and fdr can be seeked separately (for --line-buffer)
 	    open(my $fdr,"<", $self->fh($fdno,'name')) ||
 		::die_bug("fdr: Cannot open ".$self->fh($fdno,'name'));
 	    $self->set_fh($fdno,'r',$fdr);
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/make_package.sh b/3rdParty/rocksdb/v5.18.X/build_tools/make_package.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/make_package.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/make_package.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/precommit_checker.py b/3rdParty/rocksdb/v5.18.X/build_tools/precommit_checker.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/precommit_checker.py
rename to 3rdParty/rocksdb/v5.18.X/build_tools/precommit_checker.py
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/regression_build_test.sh b/3rdParty/rocksdb/v5.18.X/build_tools/regression_build_test.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/regression_build_test.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/regression_build_test.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/rocksdb-lego-determinator b/3rdParty/rocksdb/v5.18.X/build_tools/rocksdb-lego-determinator
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/rocksdb-lego-determinator
rename to 3rdParty/rocksdb/v5.18.X/build_tools/rocksdb-lego-determinator
index 1365f7fe9d..90ff38556c 100755
--- a/3rdParty/rocksdb/v5.16.X/build_tools/rocksdb-lego-determinator
+++ b/3rdParty/rocksdb/v5.18.X/build_tools/rocksdb-lego-determinator
@@ -85,7 +85,6 @@ NON_SHM="TMPD=/tmp/rocksdb_test_tmp"
 GCC_481="ROCKSDB_FBCODE_BUILD_WITH_481=1"
 ASAN="COMPILE_WITH_ASAN=1"
 CLANG="USE_CLANG=1"
-LITE="OPT=\"-DROCKSDB_LITE -g\""
 TSAN="COMPILE_WITH_TSAN=1"
 UBSAN="COMPILE_WITH_UBSAN=1"
 TSAN_CRASH='CRASH_TEST_EXT_ARGS="--compression_type=zstd --log2_keys_per_lock=22"'
@@ -345,7 +344,7 @@ LITE_BUILD_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build RocksDB debug version',
-                'shell':'$LITE make J=1 all check || $CONTRUN_NAME=lite $TASK_CREATION_TOOL',
+                'shell':'make J=1 LITE=1 all check || $CONTRUN_NAME=lite $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -663,12 +662,12 @@ run_regression()
 
   # === lite build ===
   make clean
-  OPT=-DROCKSDB_LITE make -j$(nproc) static_lib
+  make LITE=1 -j$(nproc) static_lib
   send_size_to_ods static_lib_lite $(stat --printf="%s" librocksdb.a)
   strip librocksdb.a
   send_size_to_ods static_lib_lite_stripped $(stat --printf="%s" librocksdb.a)
 
-  OPT=-DROCKSDB_LITE make -j$(nproc) shared_lib
+  make LITE=1 -j$(nproc) shared_lib
   send_size_to_ods shared_lib_lite $(stat --printf="%s" `readlink -f librocksdb.so`)
   strip `readlink -f librocksdb.so`
   send_size_to_ods shared_lib_lite_stripped $(stat --printf="%s" `readlink -f librocksdb.so`)
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/run_ci_db_test.ps1 b/3rdParty/rocksdb/v5.18.X/build_tools/run_ci_db_test.ps1
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/run_ci_db_test.ps1
rename to 3rdParty/rocksdb/v5.18.X/build_tools/run_ci_db_test.ps1
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/setup_centos7.sh b/3rdParty/rocksdb/v5.18.X/build_tools/setup_centos7.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/setup_centos7.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/setup_centos7.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/update_dependencies.sh b/3rdParty/rocksdb/v5.18.X/build_tools/update_dependencies.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/update_dependencies.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/update_dependencies.sh
diff --git a/3rdParty/rocksdb/v5.16.X/build_tools/version.sh b/3rdParty/rocksdb/v5.18.X/build_tools/version.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/build_tools/version.sh
rename to 3rdParty/rocksdb/v5.18.X/build_tools/version.sh
diff --git a/3rdParty/rocksdb/v5.16.X/cache/cache_bench.cc b/3rdParty/rocksdb/v5.18.X/cache/cache_bench.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cache/cache_bench.cc
rename to 3rdParty/rocksdb/v5.18.X/cache/cache_bench.cc
diff --git a/3rdParty/rocksdb/v5.16.X/cache/cache_test.cc b/3rdParty/rocksdb/v5.18.X/cache/cache_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/cache/cache_test.cc
rename to 3rdParty/rocksdb/v5.18.X/cache/cache_test.cc
index 55f9cc6bb6..0a63bfd694 100644
--- a/3rdParty/rocksdb/v5.16.X/cache/cache_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/cache/cache_test.cc
@@ -64,8 +64,8 @@ class CacheTest : public testing::TestWithParam<std::string> {
 
   std::vector<int> deleted_keys_;
   std::vector<int> deleted_values_;
-  shared_ptr<Cache> cache_;
-  shared_ptr<Cache> cache2_;
+  std::shared_ptr<Cache> cache_;
+  std::shared_ptr<Cache> cache2_;
 
   CacheTest()
       : cache_(NewCache(kCacheSize, kNumShardBits, false)),
@@ -145,7 +145,7 @@ class CacheTest : public testing::TestWithParam<std::string> {
 CacheTest* CacheTest::current_;
 
 TEST_P(CacheTest, UsageTest) {
-  // cache is shared_ptr and will be automatically cleaned up.
+  // cache is std::shared_ptr and will be automatically cleaned up.
   const uint64_t kCapacity = 100000;
   auto cache = NewCache(kCapacity, 8, false);
 
@@ -173,7 +173,7 @@ TEST_P(CacheTest, UsageTest) {
 }
 
 TEST_P(CacheTest, PinnedUsageTest) {
-  // cache is shared_ptr and will be automatically cleaned up.
+  // cache is std::shared_ptr and will be automatically cleaned up.
   const uint64_t kCapacity = 100000;
   auto cache = NewCache(kCapacity, 8, false);
 
diff --git a/3rdParty/rocksdb/v5.16.X/cache/clock_cache.cc b/3rdParty/rocksdb/v5.18.X/cache/clock_cache.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cache/clock_cache.cc
rename to 3rdParty/rocksdb/v5.18.X/cache/clock_cache.cc
diff --git a/3rdParty/rocksdb/v5.16.X/cache/clock_cache.h b/3rdParty/rocksdb/v5.18.X/cache/clock_cache.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cache/clock_cache.h
rename to 3rdParty/rocksdb/v5.18.X/cache/clock_cache.h
diff --git a/3rdParty/rocksdb/v5.16.X/cache/lru_cache.cc b/3rdParty/rocksdb/v5.18.X/cache/lru_cache.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/cache/lru_cache.cc
rename to 3rdParty/rocksdb/v5.18.X/cache/lru_cache.cc
index d4cbb9a45f..e11ac6ddbb 100644
--- a/3rdParty/rocksdb/v5.16.X/cache/lru_cache.cc
+++ b/3rdParty/rocksdb/v5.18.X/cache/lru_cache.cc
@@ -461,8 +461,10 @@ std::string LRUCacheShard::GetPrintableOptions() const {
 }
 
 LRUCache::LRUCache(size_t capacity, int num_shard_bits,
-                   bool strict_capacity_limit, double high_pri_pool_ratio)
-    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
+                   bool strict_capacity_limit, double high_pri_pool_ratio,
+                   std::shared_ptr<MemoryAllocator> allocator)
+    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit,
+                   std::move(allocator)) {
   num_shards_ = 1 << num_shard_bits;
   shards_ = reinterpret_cast<LRUCacheShard*>(
       port::cacheline_aligned_alloc(sizeof(LRUCacheShard) * num_shards_));
@@ -537,12 +539,14 @@ double LRUCache::GetHighPriPoolRatio() {
 std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts) {
   return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
                      cache_opts.strict_capacity_limit,
-                     cache_opts.high_pri_pool_ratio);
+                     cache_opts.high_pri_pool_ratio,
+                     cache_opts.memory_allocator);
 }
 
-std::shared_ptr<Cache> NewLRUCache(size_t capacity, int num_shard_bits,
-                                   bool strict_capacity_limit,
-                                   double high_pri_pool_ratio) {
+std::shared_ptr<Cache> NewLRUCache(
+    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
+    double high_pri_pool_ratio,
+    std::shared_ptr<MemoryAllocator> memory_allocator) {
   if (num_shard_bits >= 20) {
     return nullptr;  // the cache cannot be sharded into too many fine pieces
   }
@@ -554,7 +558,8 @@ std::shared_ptr<Cache> NewLRUCache(size_t capacity, int num_shard_bits,
     num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
   return std::make_shared<LRUCache>(capacity, num_shard_bits,
-                                    strict_capacity_limit, high_pri_pool_ratio);
+                                    strict_capacity_limit, high_pri_pool_ratio,
+                                    std::move(memory_allocator));
 }
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/cache/lru_cache.h b/3rdParty/rocksdb/v5.18.X/cache/lru_cache.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/cache/lru_cache.h
rename to 3rdParty/rocksdb/v5.18.X/cache/lru_cache.h
index 3c067f0c1e..0194d26a56 100644
--- a/3rdParty/rocksdb/v5.16.X/cache/lru_cache.h
+++ b/3rdParty/rocksdb/v5.18.X/cache/lru_cache.h
@@ -279,7 +279,8 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard : public CacheShard {
 class LRUCache : public ShardedCache {
  public:
   LRUCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-           double high_pri_pool_ratio);
+           double high_pri_pool_ratio,
+           std::shared_ptr<MemoryAllocator> memory_allocator = nullptr);
   virtual ~LRUCache();
   virtual const char* Name() const override { return "LRUCache"; }
   virtual CacheShard* GetShard(int shard) override;
diff --git a/3rdParty/rocksdb/v5.16.X/cache/lru_cache_test.cc b/3rdParty/rocksdb/v5.18.X/cache/lru_cache_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cache/lru_cache_test.cc
rename to 3rdParty/rocksdb/v5.18.X/cache/lru_cache_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/cache/sharded_cache.cc b/3rdParty/rocksdb/v5.18.X/cache/sharded_cache.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/cache/sharded_cache.cc
rename to 3rdParty/rocksdb/v5.18.X/cache/sharded_cache.cc
index 6a0a222821..a48a32185b 100644
--- a/3rdParty/rocksdb/v5.16.X/cache/sharded_cache.cc
+++ b/3rdParty/rocksdb/v5.18.X/cache/sharded_cache.cc
@@ -20,8 +20,10 @@
 namespace rocksdb {
 
 ShardedCache::ShardedCache(size_t capacity, int num_shard_bits,
-                           bool strict_capacity_limit)
-    : num_shard_bits_(num_shard_bits),
+                           bool strict_capacity_limit,
+                           std::shared_ptr<MemoryAllocator> allocator)
+    : Cache(std::move(allocator)),
+      num_shard_bits_(num_shard_bits),
       capacity_(capacity),
       strict_capacity_limit_(strict_capacity_limit),
       last_id_(1) {}
@@ -142,6 +144,9 @@ std::string ShardedCache::GetPrintableOptions() const {
              strict_capacity_limit_);
     ret.append(buffer);
   }
+  snprintf(buffer, kBufferSize, "    memory_allocator : %s\n",
+           memory_allocator() ? memory_allocator()->Name() : "None");
+  ret.append(buffer);
   ret.append(GetShard(0)->GetPrintableOptions());
   return ret;
 }
diff --git a/3rdParty/rocksdb/v5.16.X/cache/sharded_cache.h b/3rdParty/rocksdb/v5.18.X/cache/sharded_cache.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/cache/sharded_cache.h
rename to 3rdParty/rocksdb/v5.18.X/cache/sharded_cache.h
index 4f9dea2ad0..543286b9e8 100644
--- a/3rdParty/rocksdb/v5.16.X/cache/sharded_cache.h
+++ b/3rdParty/rocksdb/v5.18.X/cache/sharded_cache.h
@@ -47,7 +47,8 @@ class CacheShard {
 // Keys are sharded by the highest num_shard_bits bits of hash value.
 class ShardedCache : public Cache {
  public:
-  ShardedCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit);
+  ShardedCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
+               std::shared_ptr<MemoryAllocator> memory_allocator = nullptr);
   virtual ~ShardedCache() = default;
   virtual const char* Name() const override = 0;
   virtual CacheShard* GetShard(int shard) = 0;
diff --git a/3rdParty/rocksdb/v5.16.X/cmake/RocksDBConfig.cmake.in b/3rdParty/rocksdb/v5.18.X/cmake/RocksDBConfig.cmake.in
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cmake/RocksDBConfig.cmake.in
rename to 3rdParty/rocksdb/v5.18.X/cmake/RocksDBConfig.cmake.in
diff --git a/3rdParty/rocksdb/v5.16.X/cmake/modules/FindJeMalloc.cmake b/3rdParty/rocksdb/v5.18.X/cmake/modules/FindJeMalloc.cmake
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cmake/modules/FindJeMalloc.cmake
rename to 3rdParty/rocksdb/v5.18.X/cmake/modules/FindJeMalloc.cmake
diff --git a/3rdParty/rocksdb/v5.16.X/cmake/modules/FindNUMA.cmake b/3rdParty/rocksdb/v5.18.X/cmake/modules/FindNUMA.cmake
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cmake/modules/FindNUMA.cmake
rename to 3rdParty/rocksdb/v5.18.X/cmake/modules/FindNUMA.cmake
diff --git a/3rdParty/rocksdb/v5.16.X/cmake/modules/FindTBB.cmake b/3rdParty/rocksdb/v5.18.X/cmake/modules/FindTBB.cmake
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cmake/modules/FindTBB.cmake
rename to 3rdParty/rocksdb/v5.18.X/cmake/modules/FindTBB.cmake
diff --git a/3rdParty/rocksdb/v5.16.X/cmake/modules/Findbzip2.cmake b/3rdParty/rocksdb/v5.18.X/cmake/modules/Findbzip2.cmake
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cmake/modules/Findbzip2.cmake
rename to 3rdParty/rocksdb/v5.18.X/cmake/modules/Findbzip2.cmake
diff --git a/3rdParty/rocksdb/v5.16.X/cmake/modules/Findlz4.cmake b/3rdParty/rocksdb/v5.18.X/cmake/modules/Findlz4.cmake
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cmake/modules/Findlz4.cmake
rename to 3rdParty/rocksdb/v5.18.X/cmake/modules/Findlz4.cmake
diff --git a/3rdParty/rocksdb/v5.16.X/cmake/modules/Findsnappy.cmake b/3rdParty/rocksdb/v5.18.X/cmake/modules/Findsnappy.cmake
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cmake/modules/Findsnappy.cmake
rename to 3rdParty/rocksdb/v5.18.X/cmake/modules/Findsnappy.cmake
diff --git a/3rdParty/rocksdb/v5.16.X/cmake/modules/Findzlib.cmake b/3rdParty/rocksdb/v5.18.X/cmake/modules/Findzlib.cmake
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cmake/modules/Findzlib.cmake
rename to 3rdParty/rocksdb/v5.18.X/cmake/modules/Findzlib.cmake
diff --git a/3rdParty/rocksdb/v5.16.X/cmake/modules/Findzstd.cmake b/3rdParty/rocksdb/v5.18.X/cmake/modules/Findzstd.cmake
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/cmake/modules/Findzstd.cmake
rename to 3rdParty/rocksdb/v5.18.X/cmake/modules/Findzstd.cmake
diff --git a/3rdParty/rocksdb/v5.16.X/coverage/coverage_test.sh b/3rdParty/rocksdb/v5.18.X/coverage/coverage_test.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/coverage/coverage_test.sh
rename to 3rdParty/rocksdb/v5.18.X/coverage/coverage_test.sh
diff --git a/3rdParty/rocksdb/v5.16.X/coverage/parse_gcov_output.py b/3rdParty/rocksdb/v5.18.X/coverage/parse_gcov_output.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/coverage/parse_gcov_output.py
rename to 3rdParty/rocksdb/v5.18.X/coverage/parse_gcov_output.py
diff --git a/3rdParty/rocksdb/v5.16.X/db/builder.cc b/3rdParty/rocksdb/v5.18.X/db/builder.cc
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/db/builder.cc
rename to 3rdParty/rocksdb/v5.18.X/db/builder.cc
index c592a96472..60067c4251 100644
--- a/3rdParty/rocksdb/v5.16.X/db/builder.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/builder.cc
@@ -18,6 +18,7 @@
 #include "db/event_helpers.h"
 #include "db/internal_stats.h"
 #include "db/merge_helper.h"
+#include "db/range_del_aggregator_v2.h"
 #include "db/table_cache.h"
 #include "db/version_edit.h"
 #include "monitoring/iostats_context_imp.h"
@@ -65,8 +66,9 @@ Status BuildTable(
     const std::string& dbname, Env* env, const ImmutableCFOptions& ioptions,
     const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
     TableCache* table_cache, InternalIterator* iter,
-    std::unique_ptr<InternalIterator> range_del_iter, FileMetaData* meta,
-    const InternalKeyComparator& internal_comparator,
+    std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
+        range_del_iters,
+    FileMetaData* meta, const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
     uint32_t column_family_id, const std::string& column_family_name,
@@ -86,12 +88,10 @@ Status BuildTable(
   Status s;
   meta->fd.file_size = 0;
   iter->SeekToFirst();
-  std::unique_ptr<RangeDelAggregator> range_del_agg(
-      new RangeDelAggregator(internal_comparator, snapshots));
-  s = range_del_agg->AddTombstones(std::move(range_del_iter));
-  if (!s.ok()) {
-    // may be non-ok if a range tombstone key is unparsable
-    return s;
+  std::unique_ptr<CompactionRangeDelAggregatorV2> range_del_agg(
+      new CompactionRangeDelAggregatorV2(&internal_comparator, snapshots));
+  for (auto& range_del_iter : range_del_iters) {
+    range_del_agg->AddTombstones(std::move(range_del_iter));
   }
 
   std::string fname = TableFileName(ioptions.cf_paths, meta->fd.GetNumber(),
@@ -104,9 +104,9 @@ Status BuildTable(
 
   if (iter->Valid() || !range_del_agg->IsEmpty()) {
     TableBuilder* builder;
-    unique_ptr<WritableFileWriter> file_writer;
+    std::unique_ptr<WritableFileWriter> file_writer;
     {
-      unique_ptr<WritableFile> file;
+      std::unique_ptr<WritableFile> file;
 #ifndef NDEBUG
       bool use_direct_writes = env_options.use_direct_writes;
       TEST_SYNC_POINT_CALLBACK("BuildTable:create_file", &use_direct_writes);
@@ -121,8 +121,9 @@ Status BuildTable(
       file->SetIOPriority(io_priority);
       file->SetWriteLifeTimeHint(write_hint);
 
-      file_writer.reset(new WritableFileWriter(std::move(file), env_options,
-                                               ioptions.statistics));
+      file_writer.reset(new WritableFileWriter(std::move(file), fname,
+                                               env_options, ioptions.statistics,
+                                               ioptions.listeners));
       builder = NewTableBuilder(
           ioptions, mutable_cf_options, internal_comparator,
           int_tbl_prop_collector_factories, column_family_id,
@@ -157,8 +158,10 @@ Status BuildTable(
       }
     }
 
-    for (auto it = range_del_agg->NewIterator(); it->Valid(); it->Next()) {
-      auto tombstone = it->Tombstone();
+    auto range_del_it = range_del_agg->NewIterator();
+    for (range_del_it->SeekToFirst(); range_del_it->Valid();
+         range_del_it->Next()) {
+      auto tombstone = range_del_it->Tombstone();
       auto kv = tombstone.Serialize();
       builder->Add(kv.first.Encode(), kv.second);
       meta->UpdateBoundariesForRange(kv.first, tombstone.SerializeEndKey(),
diff --git a/3rdParty/rocksdb/v5.16.X/db/builder.h b/3rdParty/rocksdb/v5.18.X/db/builder.h
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/db/builder.h
rename to 3rdParty/rocksdb/v5.18.X/db/builder.h
index 9995723df5..b81355703b 100644
--- a/3rdParty/rocksdb/v5.16.X/db/builder.h
+++ b/3rdParty/rocksdb/v5.18.X/db/builder.h
@@ -9,6 +9,7 @@
 #include <string>
 #include <utility>
 #include <vector>
+#include "db/range_tombstone_fragmenter.h"
 #include "db/table_properties_collector.h"
 #include "options/cf_options.h"
 #include "rocksdb/comparator.h"
@@ -65,8 +66,9 @@ extern Status BuildTable(
     const std::string& dbname, Env* env, const ImmutableCFOptions& options,
     const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
     TableCache* table_cache, InternalIterator* iter,
-    std::unique_ptr<InternalIterator> range_del_iter, FileMetaData* meta,
-    const InternalKeyComparator& internal_comparator,
+    std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
+        range_del_iters,
+    FileMetaData* meta, const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
     uint32_t column_family_id, const std::string& column_family_name,
diff --git a/3rdParty/rocksdb/v5.16.X/db/c.cc b/3rdParty/rocksdb/v5.18.X/db/c.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/db/c.cc
rename to 3rdParty/rocksdb/v5.18.X/db/c.cc
index f9793ceb03..87e08f8065 100644
--- a/3rdParty/rocksdb/v5.16.X/db/c.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/c.cc
@@ -33,6 +33,7 @@
 #include "rocksdb/utilities/backupable_db.h"
 #include "rocksdb/utilities/checkpoint.h"
 #include "rocksdb/utilities/db_ttl.h"
+#include "rocksdb/utilities/memory_util.h"
 #include "rocksdb/utilities/optimistic_transaction_db.h"
 #include "rocksdb/utilities/transaction.h"
 #include "rocksdb/utilities/transaction_db.h"
@@ -41,6 +42,10 @@
 #include "rocksdb/perf_context.h"
 #include "utilities/merge_operators.h"
 
+#include <vector>
+#include <unordered_set>
+#include <map>
+
 using rocksdb::BytewiseComparator;
 using rocksdb::Cache;
 using rocksdb::ColumnFamilyDescriptor;
@@ -108,8 +113,12 @@ using rocksdb::TransactionLogIterator;
 using rocksdb::BatchResult;
 using rocksdb::PerfLevel;
 using rocksdb::PerfContext;
+using rocksdb::MemoryUtil;
 
 using std::shared_ptr;
+using std::vector;
+using std::unordered_set;
+using std::map;
 
 extern "C" {
 
@@ -142,14 +151,20 @@ struct rocksdb_writablefile_t    { WritableFile*     rep; };
 struct rocksdb_wal_iterator_t { TransactionLogIterator* rep; };
 struct rocksdb_wal_readoptions_t { TransactionLogIterator::ReadOptions rep; };
 struct rocksdb_filelock_t        { FileLock*         rep; };
-struct rocksdb_logger_t          { shared_ptr<Logger>  rep; };
-struct rocksdb_cache_t           { shared_ptr<Cache>   rep; };
+struct rocksdb_logger_t {
+  std::shared_ptr<Logger> rep;
+};
+struct rocksdb_cache_t {
+  std::shared_ptr<Cache> rep;
+};
 struct rocksdb_livefiles_t       { std::vector<LiveFileMetaData> rep; };
 struct rocksdb_column_family_handle_t  { ColumnFamilyHandle* rep; };
 struct rocksdb_envoptions_t      { EnvOptions        rep; };
 struct rocksdb_ingestexternalfileoptions_t  { IngestExternalFileOptions rep; };
 struct rocksdb_sstfilewriter_t   { SstFileWriter*    rep; };
-struct rocksdb_ratelimiter_t     { shared_ptr<RateLimiter>      rep; };
+struct rocksdb_ratelimiter_t {
+  std::shared_ptr<RateLimiter> rep;
+};
 struct rocksdb_perfcontext_t     { PerfContext*      rep; };
 struct rocksdb_pinnableslice_t {
   PinnableSlice rep;
@@ -2402,7 +2417,7 @@ void rocksdb_options_set_bytes_per_sync(
 
 void rocksdb_options_set_writable_file_max_buffer_size(rocksdb_options_t* opt,
                                                        uint64_t v) {
-  opt->rep.writable_file_max_buffer_size = v;
+  opt->rep.writable_file_max_buffer_size = static_cast<size_t>(v);
 }
 
 void rocksdb_options_set_allow_concurrent_memtable_write(rocksdb_options_t* opt,
@@ -2433,11 +2448,13 @@ void rocksdb_options_set_max_write_buffer_number_to_maintain(
   opt->rep.max_write_buffer_number_to_maintain = n;
 }
 
-void rocksdb_options_set_enable_pipelined_write(rocksdb_options_t* opt, unsigned char v) {
+void rocksdb_options_set_enable_pipelined_write(rocksdb_options_t* opt,
+                                                unsigned char v) {
   opt->rep.enable_pipelined_write = v;
 }
 
-void rocksdb_options_set_max_subcompactions(rocksdb_options_t* opt, uint32_t n) {
+void rocksdb_options_set_max_subcompactions(rocksdb_options_t* opt,
+                                            uint32_t n) {
   opt->rep.max_subcompactions = n;
 }
 
@@ -3533,6 +3550,18 @@ const char* rocksdb_livefiles_largestkey(
   return lf->rep[index].largestkey.data();
 }
 
+uint64_t rocksdb_livefiles_entries(
+    const rocksdb_livefiles_t* lf,
+    int index) {
+  return lf->rep[index].num_entries;
+}
+
+uint64_t rocksdb_livefiles_deletions(
+    const rocksdb_livefiles_t* lf,
+    int index) {
+  return lf->rep[index].num_deletions;
+}
+
 extern void rocksdb_livefiles_destroy(
   const rocksdb_livefiles_t* lf) {
   delete lf;
@@ -4099,6 +4128,98 @@ const char* rocksdb_pinnableslice_value(const rocksdb_pinnableslice_t* v,
   *vlen = v->rep.size();
   return v->rep.data();
 }
+
+// container to keep databases and caches in order to use rocksdb::MemoryUtil
+struct rocksdb_memory_consumers_t {
+  std::vector<rocksdb_t*> dbs;
+  std::unordered_set<rocksdb_cache_t*> caches;
+};
+
+// initializes new container of memory consumers
+rocksdb_memory_consumers_t* rocksdb_memory_consumers_create() {
+  return new rocksdb_memory_consumers_t;
+}
+
+// adds datatabase to the container of memory consumers
+void rocksdb_memory_consumers_add_db(rocksdb_memory_consumers_t* consumers,
+                                     rocksdb_t* db) {
+  consumers->dbs.push_back(db);
+}
+
+// adds cache to the container of memory consumers
+void rocksdb_memory_consumers_add_cache(rocksdb_memory_consumers_t* consumers,
+                                        rocksdb_cache_t* cache) {
+  consumers->caches.insert(cache);
+}
+
+// deletes container with memory consumers
+void rocksdb_memory_consumers_destroy(rocksdb_memory_consumers_t* consumers) {
+  delete consumers;
+}
+
+// contains memory usage statistics provided by rocksdb::MemoryUtil
+struct rocksdb_memory_usage_t {
+  uint64_t mem_table_total;
+  uint64_t mem_table_unflushed;
+  uint64_t mem_table_readers_total;
+  uint64_t cache_total;
+};
+
+// estimates amount of memory occupied by consumers (dbs and caches)
+rocksdb_memory_usage_t* rocksdb_approximate_memory_usage_create(
+    rocksdb_memory_consumers_t* consumers, char** errptr) {
+
+  vector<DB*> dbs;
+  for (auto db : consumers->dbs) {
+    dbs.push_back(db->rep);
+  }
+
+  unordered_set<const Cache*> cache_set;
+  for (auto cache : consumers->caches) {
+    cache_set.insert(const_cast<const Cache*>(cache->rep.get()));
+  }
+
+  std::map<rocksdb::MemoryUtil::UsageType, uint64_t> usage_by_type;
+
+  auto status = MemoryUtil::GetApproximateMemoryUsageByType(dbs, cache_set,
+                                                            &usage_by_type);
+  if (SaveError(errptr, status)) {
+    return nullptr;
+  }
+
+  auto result = new rocksdb_memory_usage_t;
+  result->mem_table_total = usage_by_type[MemoryUtil::kMemTableTotal];
+  result->mem_table_unflushed = usage_by_type[MemoryUtil::kMemTableUnFlushed];
+  result->mem_table_readers_total = usage_by_type[MemoryUtil::kTableReadersTotal];
+  result->cache_total = usage_by_type[MemoryUtil::kCacheTotal];
+  return result;
+}
+
+uint64_t rocksdb_approximate_memory_usage_get_mem_table_total(
+    rocksdb_memory_usage_t* memory_usage) {
+  return memory_usage->mem_table_total;
+}
+
+uint64_t rocksdb_approximate_memory_usage_get_mem_table_unflushed(
+    rocksdb_memory_usage_t* memory_usage) {
+  return memory_usage->mem_table_unflushed;
+}
+
+uint64_t rocksdb_approximate_memory_usage_get_mem_table_readers_total(
+    rocksdb_memory_usage_t* memory_usage) {
+  return memory_usage->mem_table_readers_total;
+}
+
+uint64_t rocksdb_approximate_memory_usage_get_cache_total(
+    rocksdb_memory_usage_t* memory_usage) {
+  return memory_usage->cache_total;
+}
+
+// deletes container with memory usage estimates
+void rocksdb_approximate_memory_usage_destroy(rocksdb_memory_usage_t* usage) {
+  delete usage;
+}
+
 }  // end extern "C"
 
 #endif  // !ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.16.X/db/c_test.c b/3rdParty/rocksdb/v5.18.X/db/c_test.c
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/db/c_test.c
rename to 3rdParty/rocksdb/v5.18.X/db/c_test.c
index f8e88b4322..4f1c0da9f0 100644
--- a/3rdParty/rocksdb/v5.16.X/db/c_test.c
+++ b/3rdParty/rocksdb/v5.18.X/db/c_test.c
@@ -19,11 +19,8 @@
 
 // Can not use port/port.h macros as this is a c file
 #ifdef OS_WIN
-
 #include <windows.h>
 
-#define snprintf _snprintf
-
 // Ok for uniqueness
 int geteuid() {
   int result = 0;
@@ -34,6 +31,11 @@ int geteuid() {
   return result;
 }
 
+// VS < 2015
+#if defined(_MSC_VER) && (_MSC_VER < 1900)
+#define snprintf _snprintf
+#endif
+
 #endif
 
 const char* phase = "";
@@ -47,12 +49,19 @@ static void StartPhase(const char* name) {
   fprintf(stderr, "=== Test %s\n", name);
   phase = name;
 }
+#ifdef _MSC_VER
+#pragma warning(push)
+#pragma warning (disable: 4996) // getenv security warning
+#endif
 static const char* GetTempDir(void) {
     const char* ret = getenv("TEST_TMPDIR");
     if (ret == NULL || ret[0] == '\0')
         ret = "/tmp";
     return ret;
 }
+#ifdef _MSC_VER
+#pragma warning(pop)
+#endif
 
 #define CheckNoError(err)                                               \
   if ((err) != NULL) {                                                  \
@@ -643,7 +652,7 @@ int main(int argc, char** argv) {
     rocksdb_sstfilewriter_t* writer =
         rocksdb_sstfilewriter_create(env_opt, io_options);
 
-    unlink(sstfilename);
+    remove(sstfilename);
     rocksdb_sstfilewriter_open(writer, sstfilename, &err);
     CheckNoError(err);
     rocksdb_sstfilewriter_put(writer, "sstk1", 5, "v1", 2, &err);
@@ -664,7 +673,7 @@ int main(int argc, char** argv) {
     CheckGet(db, roptions, "sstk2", "v2");
     CheckGet(db, roptions, "sstk3", "v3");
 
-    unlink(sstfilename);
+    remove(sstfilename);
     rocksdb_sstfilewriter_open(writer, sstfilename, &err);
     CheckNoError(err);
     rocksdb_sstfilewriter_put(writer, "sstk2", 5, "v4", 2, &err);
@@ -1334,6 +1343,47 @@ int main(int argc, char** argv) {
     rocksdb_destroy_db(options, dbname, &err);
   }
 
+  // Check memory usage stats
+  StartPhase("approximate_memory_usage");
+  {
+    // Create database
+    db = rocksdb_open(options, dbname, &err);
+    CheckNoError(err);
+
+    rocksdb_memory_consumers_t* consumers;
+    consumers = rocksdb_memory_consumers_create();
+    rocksdb_memory_consumers_add_db(consumers, db);
+    rocksdb_memory_consumers_add_cache(consumers, cache);
+
+    // take memory usage report before write-read operation
+    rocksdb_memory_usage_t* mu1;
+    mu1 = rocksdb_approximate_memory_usage_create(consumers, &err);
+    CheckNoError(err);
+
+    // Put data (this should affect memtables)
+    rocksdb_put(db, woptions, "memory", 6, "test", 4, &err);
+    CheckNoError(err);
+    CheckGet(db, roptions, "memory", "test");
+
+    // take memory usage report after write-read operation
+    rocksdb_memory_usage_t* mu2;
+    mu2 = rocksdb_approximate_memory_usage_create(consumers, &err);
+    CheckNoError(err);
+
+    // amount of memory used within memtables should grow
+    CheckCondition(rocksdb_approximate_memory_usage_get_mem_table_total(mu2) >=
+                   rocksdb_approximate_memory_usage_get_mem_table_total(mu1));
+    CheckCondition(rocksdb_approximate_memory_usage_get_mem_table_unflushed(mu2) >=
+                   rocksdb_approximate_memory_usage_get_mem_table_unflushed(mu1));
+
+    rocksdb_memory_consumers_destroy(consumers);
+    rocksdb_approximate_memory_usage_destroy(mu1);
+    rocksdb_approximate_memory_usage_destroy(mu2);
+    rocksdb_close(db);
+    rocksdb_destroy_db(options, dbname, &err);
+    CheckNoError(err);
+  }
+
   StartPhase("cuckoo_options");
   {
     rocksdb_cuckoo_table_options_t* cuckoo_options;
@@ -1675,7 +1725,7 @@ int main(int argc, char** argv) {
     db = rocksdb_open(options, dbname, &err);
     CheckNoError(err);
   }
-  
+
   StartPhase("cleanup");
   rocksdb_close(db);
   rocksdb_options_destroy(options);
diff --git a/3rdParty/rocksdb/v5.16.X/db/column_family.cc b/3rdParty/rocksdb/v5.18.X/db/column_family.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/db/column_family.cc
rename to 3rdParty/rocksdb/v5.18.X/db/column_family.cc
index 8ea3d12163..c1a85a341c 100644
--- a/3rdParty/rocksdb/v5.16.X/db/column_family.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/column_family.cc
@@ -20,10 +20,12 @@
 #include <limits>
 
 #include "db/compaction_picker.h"
+#include "db/compaction_picker_fifo.h"
 #include "db/compaction_picker_universal.h"
 #include "db/db_impl.h"
 #include "db/internal_stats.h"
 #include "db/job_context.h"
+#include "db/range_del_aggregator_v2.h"
 #include "db/table_properties_collector.h"
 #include "db/version_set.h"
 #include "db/write_controller.h"
@@ -105,9 +107,6 @@ void GetIntTblPropCollectorFactory(
     int_tbl_prop_collector_factories->emplace_back(
         new UserKeyTablePropertiesCollectorFactory(collector_factories[i]));
   }
-  // Add collector to collect internal key statistics
-  int_tbl_prop_collector_factories->emplace_back(
-      new InternalKeyPropertiesCollectorFactory);
 }
 
 Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
@@ -945,26 +944,16 @@ Status ColumnFamilyData::RangesOverlapWithMemtables(
   super_version->imm->AddIterators(read_opts, &merge_iter_builder);
   ScopedArenaIterator memtable_iter(merge_iter_builder.Finish());
 
-  std::vector<InternalIterator*> memtable_range_del_iters;
+  auto read_seq = super_version->current->version_set()->LastSequence();
+  ReadRangeDelAggregatorV2 range_del_agg(&internal_comparator_, read_seq);
   auto* active_range_del_iter =
-      super_version->mem->NewRangeTombstoneIterator(read_opts);
-  if (active_range_del_iter != nullptr) {
-    memtable_range_del_iters.push_back(active_range_del_iter);
-  }
-  super_version->imm->AddRangeTombstoneIterators(read_opts,
-                                                 &memtable_range_del_iters);
-  RangeDelAggregator range_del_agg(internal_comparator_, {} /* snapshots */,
-                                   false /* collapse_deletions */);
+      super_version->mem->NewRangeTombstoneIterator(read_opts, read_seq);
+  range_del_agg.AddTombstones(
+      std::unique_ptr<FragmentedRangeTombstoneIterator>(active_range_del_iter));
+  super_version->imm->AddRangeTombstoneIterators(read_opts, nullptr /* arena */,
+                                                 &range_del_agg);
+
   Status status;
-  {
-    std::unique_ptr<InternalIterator> memtable_range_del_iter(
-        NewMergingIterator(&internal_comparator_,
-                           memtable_range_del_iters.empty()
-                               ? nullptr
-                               : &memtable_range_del_iters[0],
-                           static_cast<int>(memtable_range_del_iters.size())));
-    status = range_del_agg.AddTombstones(std::move(memtable_range_del_iter));
-  }
   for (size_t i = 0; i < ranges.size() && status.ok() && !*overlap; ++i) {
     auto* vstorage = super_version->current->storage_info();
     auto* ucmp = vstorage->InternalComparator()->user_comparator();
diff --git a/3rdParty/rocksdb/v5.16.X/db/column_family.h b/3rdParty/rocksdb/v5.18.X/db/column_family.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/column_family.h
rename to 3rdParty/rocksdb/v5.18.X/db/column_family.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/column_family_test.cc b/3rdParty/rocksdb/v5.18.X/db/column_family_test.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/db/column_family_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/column_family_test.cc
index 5c2a068b34..07cc5dd131 100644
--- a/3rdParty/rocksdb/v5.16.X/db/column_family_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/column_family_test.cc
@@ -47,7 +47,7 @@ class EnvCounter : public EnvWrapper {
   int GetNumberOfNewWritableFileCalls() {
     return num_new_writable_file_;
   }
-  Status NewWritableFile(const std::string& f, unique_ptr<WritableFile>* r,
+  Status NewWritableFile(const std::string& f, std::unique_ptr<WritableFile>* r,
                          const EnvOptions& soptions) override {
     ++num_new_writable_file_;
     return EnvWrapper::NewWritableFile(f, r, soptions);
@@ -486,9 +486,9 @@ class ColumnFamilyTestBase : public testing::Test {
   void CopyFile(const std::string& source, const std::string& destination,
                 uint64_t size = 0) {
     const EnvOptions soptions;
-    unique_ptr<SequentialFile> srcfile;
+    std::unique_ptr<SequentialFile> srcfile;
     ASSERT_OK(env_->NewSequentialFile(source, &srcfile, soptions));
-    unique_ptr<WritableFile> destfile;
+    std::unique_ptr<WritableFile> destfile;
     ASSERT_OK(env_->NewWritableFile(destination, &destfile, soptions));
 
     if (size == 0) {
@@ -513,6 +513,16 @@ class ColumnFamilyTestBase : public testing::Test {
     return static_cast<int>(files.size());
   }
 
+  void RecalculateWriteStallConditions(ColumnFamilyData* cfd,
+      const MutableCFOptions& mutable_cf_options)  {
+    // add lock to avoid race condition between
+    // `RecalculateWriteStallConditions` which writes to CFStats and
+    // background `DBImpl::DumpStats()` threads which read CFStats
+    dbfull()->TEST_LockMutex();
+    cfd->RecalculateWriteStallConditions(mutable_cf_options);
+    dbfull()-> TEST_UnlockMutex();
+  }
+
   std::vector<ColumnFamilyHandle*> handles_;
   std::vector<std::string> names_;
   std::vector<std::set<std::string>> keys_;
@@ -2500,139 +2510,139 @@ TEST_P(ColumnFamilyTest, WriteStallSingleColumnFamily) {
   mutable_cf_options.disable_auto_compactions = false;
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(50);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(201);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(400);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(500);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(450);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(205);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(202);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(201);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(198);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(399);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(599);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(2001);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(3001);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(390);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(100);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
   vstorage->set_l0_delay_trigger_count(100);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(101);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
   vstorage->set_l0_delay_trigger_count(0);
   vstorage->TEST_set_estimated_compaction_needed_bytes(300);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25, GetDbDelayedWriteRate());
 
   vstorage->set_l0_delay_trigger_count(101);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25 / 1.25, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(200);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25, GetDbDelayedWriteRate());
 
   vstorage->set_l0_delay_trigger_count(0);
   vstorage->TEST_set_estimated_compaction_needed_bytes(0);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
   mutable_cf_options.disable_auto_compactions = true;
   dbfull()->TEST_write_controler().set_delayed_write_rate(kBaseRate);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
   vstorage->set_l0_delay_trigger_count(50);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(0, GetDbDelayedWriteRate());
@@ -2640,7 +2650,7 @@ TEST_P(ColumnFamilyTest, WriteStallSingleColumnFamily) {
 
   vstorage->set_l0_delay_trigger_count(60);
   vstorage->TEST_set_estimated_compaction_needed_bytes(300);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(0, GetDbDelayedWriteRate());
@@ -2649,14 +2659,14 @@ TEST_P(ColumnFamilyTest, WriteStallSingleColumnFamily) {
   mutable_cf_options.disable_auto_compactions = false;
   vstorage->set_l0_delay_trigger_count(70);
   vstorage->TEST_set_estimated_compaction_needed_bytes(500);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
   vstorage->set_l0_delay_trigger_count(71);
   vstorage->TEST_set_estimated_compaction_needed_bytes(501);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
@@ -2681,31 +2691,31 @@ TEST_P(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
   mutable_cf_options.hard_pending_compaction_bytes_limit = 2000;
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(40);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(50);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(300);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(45);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(7);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(9);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(6);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
   // Speed up threshold = min(4 * 2, 4 + (12 - 4)/4) = 6
@@ -2714,15 +2724,15 @@ TEST_P(ColumnFamilyTest, CompactionSpeedupSingleColumnFamily) {
   mutable_cf_options.level0_stop_writes_trigger = 30;
 
   vstorage->set_l0_delay_trigger_count(5);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(7);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(3);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 }
 
@@ -2749,53 +2759,53 @@ TEST_P(ColumnFamilyTest, WriteStallTwoColumnFamilies) {
   mutable_cf_options1.soft_pending_compaction_bytes_limit = 500;
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(50);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
   vstorage1->TEST_set_estimated_compaction_needed_bytes(201);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(!dbfull()->TEST_write_controler().NeedsDelay());
 
   vstorage1->TEST_set_estimated_compaction_needed_bytes(600);
-  cfd1->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(70);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate, GetDbDelayedWriteRate());
 
   vstorage1->TEST_set_estimated_compaction_needed_bytes(800);
-  cfd1->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(300);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25, GetDbDelayedWriteRate());
 
   vstorage1->TEST_set_estimated_compaction_needed_bytes(700);
-  cfd1->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(500);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25 / 1.25, GetDbDelayedWriteRate());
 
   vstorage1->TEST_set_estimated_compaction_needed_bytes(600);
-  cfd1->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_TRUE(!IsDbWriteStopped());
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_EQ(kBaseRate / 1.25, GetDbDelayedWriteRate());
@@ -2828,41 +2838,41 @@ TEST_P(ColumnFamilyTest, CompactionSpeedupTwoColumnFamilies) {
   mutable_cf_options1.level0_slowdown_writes_trigger = 16;
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(40);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(60);
-  cfd1->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage1->TEST_set_estimated_compaction_needed_bytes(30);
-  cfd1->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage1->TEST_set_estimated_compaction_needed_bytes(70);
-  cfd1->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->TEST_set_estimated_compaction_needed_bytes(20);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage1->TEST_set_estimated_compaction_needed_bytes(3);
-  cfd1->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(9);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage1->set_l0_delay_trigger_count(2);
-  cfd1->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd1, mutable_cf_options);
   ASSERT_EQ(6, dbfull()->TEST_BGCompactionsAllowed());
 
   vstorage->set_l0_delay_trigger_count(0);
-  cfd->RecalculateWriteStallConditions(mutable_cf_options);
+  RecalculateWriteStallConditions(cfd, mutable_cf_options);
   ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
 }
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/compact_files_test.cc b/3rdParty/rocksdb/v5.18.X/db/compact_files_test.cc
similarity index 83%
rename from 3rdParty/rocksdb/v5.16.X/db/compact_files_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compact_files_test.cc
index 499d88b3e9..1d7cf78a00 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compact_files_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/compact_files_test.cc
@@ -308,6 +308,55 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
   delete db;
 }
 
+TEST_F(CompactFilesTest, SentinelCompressionType) {
+  if (!Zlib_Supported()) {
+    fprintf(stderr, "zlib compression not supported, skip this test\n");
+    return;
+  }
+  if (!Snappy_Supported()) {
+    fprintf(stderr, "snappy compression not supported, skip this test\n");
+    return;
+  }
+  // Check that passing `CompressionType::kDisableCompressionOption` to
+  // `CompactFiles` causes it to use the column family compression options.
+  for (auto compaction_style :
+       {CompactionStyle::kCompactionStyleLevel,
+        CompactionStyle::kCompactionStyleUniversal,
+        CompactionStyle::kCompactionStyleNone}) {
+    DestroyDB(db_name_, Options());
+    Options options;
+    options.compaction_style = compaction_style;
+    // L0: Snappy, L1: ZSTD, L2: Snappy
+    options.compression_per_level = {CompressionType::kSnappyCompression,
+                                     CompressionType::kZlibCompression,
+                                     CompressionType::kSnappyCompression};
+    options.create_if_missing = true;
+    FlushedFileCollector* collector = new FlushedFileCollector();
+    options.listeners.emplace_back(collector);
+    DB* db = nullptr;
+    ASSERT_OK(DB::Open(options, db_name_, &db));
+
+    db->Put(WriteOptions(), "key", "val");
+    db->Flush(FlushOptions());
+
+    auto l0_files = collector->GetFlushedFiles();
+    ASSERT_EQ(1, l0_files.size());
+
+    // L0->L1 compaction, so output should be ZSTD-compressed
+    CompactionOptions compaction_opts;
+    compaction_opts.compression = CompressionType::kDisableCompressionOption;
+    ASSERT_OK(db->CompactFiles(compaction_opts, l0_files, 1));
+
+    rocksdb::TablePropertiesCollection all_tables_props;
+    ASSERT_OK(db->GetPropertiesOfAllTables(&all_tables_props));
+    for (const auto& name_and_table_props : all_tables_props) {
+      ASSERT_EQ(CompressionTypeToString(CompressionType::kZlibCompression),
+                name_and_table_props.second->compression_name);
+    }
+    delete db;
+  }
+}
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
diff --git a/3rdParty/rocksdb/v5.16.X/db/compacted_db_impl.cc b/3rdParty/rocksdb/v5.18.X/db/compacted_db_impl.cc
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/db/compacted_db_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compacted_db_impl.cc
index 823276c4d1..acdaad4ec2 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compacted_db_impl.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/compacted_db_impl.cc
@@ -25,22 +25,12 @@ CompactedDBImpl::~CompactedDBImpl() {
 }
 
 size_t CompactedDBImpl::FindFile(const Slice& key) {
-  size_t left = 0;
   size_t right = files_.num_files - 1;
-  while (left < right) {
-    size_t mid = (left + right) >> 1;
-    const FdWithKeyRange& f = files_.files[mid];
-    if (user_comparator_->Compare(ExtractUserKey(f.largest_key), key) < 0) {
-      // Key at "mid.largest" is < "target".  Therefore all
-      // files at or before "mid" are uninteresting.
-      left = mid + 1;
-    } else {
-      // Key at "mid.largest" is >= "target".  Therefore all files
-      // after "mid" are uninteresting.
-      right = mid;
-    }
-  }
-  return right;
+  auto cmp = [&](const FdWithKeyRange& f, const Slice& k) -> bool {
+    return user_comparator_->Compare(ExtractUserKey(f.largest_key), k) < 0;
+  };
+  return static_cast<size_t>(std::lower_bound(files_.files,
+                            files_.files + right, key, cmp) - files_.files);
 }
 
 Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
@@ -157,6 +147,7 @@ Status CompactedDBImpl::Open(const Options& options,
   std::unique_ptr<CompactedDBImpl> db(new CompactedDBImpl(db_options, dbname));
   Status s = db->Init(options);
   if (s.ok()) {
+    db->StartTimedTasks();
     ROCKS_LOG_INFO(db->immutable_db_options_.info_log,
                    "Opened the db as fully compacted mode");
     LogFlush(db->immutable_db_options_.info_log);
diff --git a/3rdParty/rocksdb/v5.16.X/db/compacted_db_impl.h b/3rdParty/rocksdb/v5.18.X/db/compacted_db_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/compacted_db_impl.h
rename to 3rdParty/rocksdb/v5.18.X/db/compacted_db_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction.cc b/3rdParty/rocksdb/v5.18.X/db/compaction.cc
similarity index 84%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compaction.cc
index 4ea92d5cc7..dbcd82b75f 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction.cc
@@ -23,6 +23,43 @@
 
 namespace rocksdb {
 
+const uint64_t kRangeTombstoneSentinel =
+    PackSequenceAndType(kMaxSequenceNumber, kTypeRangeDeletion);
+
+int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
+                      const InternalKey& b) {
+  auto c = user_cmp->Compare(a.user_key(), b.user_key());
+  if (c != 0) {
+    return c;
+  }
+  auto a_footer = ExtractInternalKeyFooter(a.Encode());
+  auto b_footer = ExtractInternalKeyFooter(b.Encode());
+  if (a_footer == kRangeTombstoneSentinel) {
+    if (b_footer != kRangeTombstoneSentinel) {
+      return -1;
+    }
+  } else if (b_footer == kRangeTombstoneSentinel) {
+    return 1;
+  }
+  return 0;
+}
+
+int sstableKeyCompare(const Comparator* user_cmp, const InternalKey* a,
+                      const InternalKey& b) {
+  if (a == nullptr) {
+    return -1;
+  }
+  return sstableKeyCompare(user_cmp, *a, b);
+}
+
+int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
+                      const InternalKey* b) {
+  if (b == nullptr) {
+    return -1;
+  }
+  return sstableKeyCompare(user_cmp, a, *b);
+}
+
 uint64_t TotalFileSize(const std::vector<FileMetaData*>& files) {
   uint64_t sum = 0;
   for (size_t i = 0; i < files.size() && files[i]; i++) {
@@ -81,6 +118,49 @@ void Compaction::GetBoundaryKeys(
   }
 }
 
+std::vector<CompactionInputFiles> Compaction::PopulateWithAtomicBoundaries(
+    VersionStorageInfo* vstorage, std::vector<CompactionInputFiles> inputs) {
+  const Comparator* ucmp = vstorage->InternalComparator()->user_comparator();
+  for (size_t i = 0; i < inputs.size(); i++) {
+    if (inputs[i].level == 0 || inputs[i].files.empty()) {
+      continue;
+    }
+    inputs[i].atomic_compaction_unit_boundaries.reserve(inputs[i].files.size());
+    AtomicCompactionUnitBoundary cur_boundary;
+    size_t first_atomic_idx = 0;
+    auto add_unit_boundary = [&](size_t to) {
+      if (first_atomic_idx == to) return;
+      for (size_t k = first_atomic_idx; k < to; k++) {
+        inputs[i].atomic_compaction_unit_boundaries.push_back(cur_boundary);
+      }
+      first_atomic_idx = to;
+    };
+    for (size_t j = 0; j < inputs[i].files.size(); j++) {
+      const auto* f = inputs[i].files[j];
+      if (j == 0) {
+        // First file in a level.
+        cur_boundary.smallest = &f->smallest;
+        cur_boundary.largest = &f->largest;
+      } else if (sstableKeyCompare(ucmp, *cur_boundary.largest, f->smallest) ==
+                 0) {
+        // SSTs overlap but the end key of the previous file was not
+        // artificially extended by a range tombstone. Extend the current
+        // boundary.
+        cur_boundary.largest = &f->largest;
+      } else {
+        // Atomic compaction unit has ended.
+        add_unit_boundary(j);
+        cur_boundary.smallest = &f->smallest;
+        cur_boundary.largest = &f->largest;
+      }
+    }
+    add_unit_boundary(inputs[i].files.size());
+    assert(inputs[i].files.size() ==
+           inputs[i].atomic_compaction_unit_boundaries.size());
+  }
+  return inputs;
+}
+
 // helper function to determine if compaction is creating files at the
 // bottommost level
 bool Compaction::IsBottommostLevel(
@@ -155,7 +235,7 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
       output_compression_(_compression),
       output_compression_opts_(_compression_opts),
       deletion_compaction_(_deletion_compaction),
-      inputs_(std::move(_inputs)),
+      inputs_(PopulateWithAtomicBoundaries(vstorage, std::move(_inputs))),
       grandparents_(std::move(_grandparents)),
       score_(_score),
       bottommost_level_(IsBottommostLevel(output_level_, vstorage, inputs_)),
@@ -331,12 +411,14 @@ const char* Compaction::InputLevelSummary(
     if (!is_first) {
       len +=
           snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len, " + ");
+      len = std::min(len, static_cast<int>(sizeof(scratch->buffer)));
     } else {
       is_first = false;
     }
     len += snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len,
                     "%" ROCKSDB_PRIszt "@%d", input_level.size(),
                     input_level.level);
+    len = std::min(len, static_cast<int>(sizeof(scratch->buffer)));
   }
   snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len,
            " files to L%d", output_level());
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction.h b/3rdParty/rocksdb/v5.18.X/db/compaction.h
similarity index 82%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction.h
rename to 3rdParty/rocksdb/v5.18.X/db/compaction.h
index f1d7877169..2cf737b676 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction.h
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction.h
@@ -15,11 +15,43 @@
 
 namespace rocksdb {
 
+// Utility for comparing sstable boundary keys. Returns -1 if either a or b is
+// null which provides the property that a==null indicates a key that is less
+// than any key and b==null indicates a key that is greater than any key. Note
+// that the comparison is performed primarily on the user-key portion of the
+// key. If the user-keys compare equal, an additional test is made to sort
+// range tombstone sentinel keys before other keys with the same user-key. The
+// result is that 2 user-keys will compare equal if they differ purely on
+// their sequence number and value, but the range tombstone sentinel for that
+// user-key will compare not equal. This is necessary because the range
+// tombstone sentinel key is set as the largest key for an sstable even though
+// that key never appears in the database. We don't want adjacent sstables to
+// be considered overlapping if they are separated by the range tombstone
+// sentinel.
+int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
+                      const InternalKey& b);
+int sstableKeyCompare(const Comparator* user_cmp, const InternalKey* a,
+                      const InternalKey& b);
+int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
+                      const InternalKey* b);
+
+// An AtomicCompactionUnitBoundary represents a range of keys [smallest,
+// largest] that exactly spans one ore more neighbouring SSTs on the same
+// level. Every pair of  SSTs in this range "overlap" (i.e., the largest
+// user key of one file is the smallest user key of the next file). These
+// boundaries are propagated down to RangeDelAggregator during compaction
+// to provide safe truncation boundaries for range tombstones.
+struct AtomicCompactionUnitBoundary {
+  const InternalKey* smallest = nullptr;
+  const InternalKey* largest = nullptr;
+};
+
 // The structure that manages compaction input files associated
 // with the same physical level.
 struct CompactionInputFiles {
   int level;
   std::vector<FileMetaData*> files;
+  std::vector<AtomicCompactionUnitBoundary> atomic_compaction_unit_boundaries;
   inline bool empty() const { return files.empty(); }
   inline size_t size() const { return files.size(); }
   inline void clear() { files.clear(); }
@@ -96,6 +128,12 @@ class Compaction {
     return inputs_[compaction_input_level][i];
   }
 
+  const std::vector<AtomicCompactionUnitBoundary>* boundaries(
+      size_t compaction_input_level) const {
+    assert(compaction_input_level < inputs_.size());
+    return &inputs_[compaction_input_level].atomic_compaction_unit_boundaries;
+  }
+
   // Returns the list of file meta data of the specified compaction
   // input level.
   // REQUIREMENT: "compaction_input_level" must be >= 0 and
@@ -262,6 +300,13 @@ class Compaction {
                               const std::vector<CompactionInputFiles>& inputs,
                               Slice* smallest_key, Slice* largest_key);
 
+  // Get the atomic file boundaries for all files in the compaction. Necessary
+  // in order to avoid the scenario described in
+  // https://github.com/facebook/rocksdb/pull/4432#discussion_r221072219 and plumb
+  // down appropriate key boundaries to RangeDelAggregator during compaction.
+  static std::vector<CompactionInputFiles> PopulateWithAtomicBoundaries(
+      VersionStorageInfo* vstorage, std::vector<CompactionInputFiles> inputs);
+
   // helper function to determine if compaction with inputs and storage is
   // bottommost
   static bool IsBottommostLevel(
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_iteration_stats.h b/3rdParty/rocksdb/v5.18.X/db/compaction_iteration_stats.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_iteration_stats.h
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_iteration_stats.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_iterator.cc b/3rdParty/rocksdb/v5.18.X/db/compaction_iterator.cc
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_iterator.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_iterator.cc
index 7b096ca04a..ad45602cc4 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction_iterator.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_iterator.cc
@@ -18,8 +18,8 @@ CompactionIterator::CompactionIterator(
     SequenceNumber earliest_write_conflict_snapshot,
     const SnapshotChecker* snapshot_checker, Env* env,
     bool report_detailed_time, bool expect_valid_internal_key,
-    RangeDelAggregator* range_del_agg,
-    const Compaction* compaction, const CompactionFilter* compaction_filter,
+    CompactionRangeDelAggregatorV2* range_del_agg, const Compaction* compaction,
+    const CompactionFilter* compaction_filter,
     const std::atomic<bool>* shutting_down,
     const SequenceNumber preserve_deletes_seqnum)
     : CompactionIterator(
@@ -36,7 +36,7 @@ CompactionIterator::CompactionIterator(
     SequenceNumber earliest_write_conflict_snapshot,
     const SnapshotChecker* snapshot_checker, Env* env,
     bool report_detailed_time, bool expect_valid_internal_key,
-    RangeDelAggregator* range_del_agg,
+    CompactionRangeDelAggregatorV2* range_del_agg,
     std::unique_ptr<CompactionProxy> compaction,
     const CompactionFilter* compaction_filter,
     const std::atomic<bool>* shutting_down,
@@ -77,6 +77,12 @@ CompactionIterator::CompactionIterator(
     earliest_snapshot_ = snapshots_->at(0);
     latest_snapshot_ = snapshots_->back();
   }
+#ifndef NDEBUG
+  // findEarliestVisibleSnapshot assumes this ordering.
+  for (size_t i = 1; i < snapshots_->size(); ++i) {
+    assert(snapshots_->at(i - 1) <= snapshots_->at(i));
+  }
+#endif
   if (compaction_filter_ != nullptr) {
     if (compaction_filter_->IgnoreSnapshots()) {
       ignore_snapshots_ = true;
@@ -505,6 +511,31 @@ void CompactionIterator::NextFromInput() {
         ++iter_stats_.num_optimized_del_drop_obsolete;
       }
       input_->Next();
+    } else if ((ikey_.type == kTypeDeletion) && bottommost_level_ &&
+               ikeyNotNeededForIncrementalSnapshot()) {
+      // Handle the case where we have a delete key at the bottom most level
+      // We can skip outputting the key iff there are no subsequent puts for this
+      // key
+      ParsedInternalKey next_ikey;
+      input_->Next();
+      // Skip over all versions of this key that happen to occur in the same snapshot
+      // range as the delete
+      while (input_->Valid() &&
+             ParseInternalKey(input_->key(), &next_ikey) &&
+             cmp_->Equal(ikey_.user_key, next_ikey.user_key) &&
+             (prev_snapshot == 0 || next_ikey.sequence > prev_snapshot ||
+              (snapshot_checker_ != nullptr &&
+               UNLIKELY(!snapshot_checker_->IsInSnapshot(next_ikey.sequence,
+                                                         prev_snapshot))))) {
+        input_->Next();
+      }
+      // If you find you still need to output a row with this key, we need to output the
+      // delete too
+      if (input_->Valid() && ParseInternalKey(input_->key(), &next_ikey) &&
+          cmp_->Equal(ikey_.user_key, next_ikey.user_key)) {
+        valid_ = true;
+        at_next_ = true;
+      }
     } else if (ikey_.type == kTypeMerge) {
       if (!merge_helper_->HasOperator()) {
         status_ = Status::InvalidArgument(
@@ -603,18 +634,23 @@ void CompactionIterator::PrepareOutput() {
 inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
     SequenceNumber in, SequenceNumber* prev_snapshot) {
   assert(snapshots_->size());
-  SequenceNumber prev = kMaxSequenceNumber;
-  for (const auto cur : *snapshots_) {
-    assert(prev == kMaxSequenceNumber || prev <= cur);
-    if (cur >= in && (snapshot_checker_ == nullptr ||
-                      snapshot_checker_->IsInSnapshot(in, cur))) {
-      *prev_snapshot = prev == kMaxSequenceNumber ? 0 : prev;
+  auto snapshots_iter = std::lower_bound(
+      snapshots_->begin(), snapshots_->end(), in);
+  if (snapshots_iter == snapshots_->begin()) {
+    *prev_snapshot = 0;
+  } else {
+    *prev_snapshot = *std::prev(snapshots_iter);
+    assert(*prev_snapshot < in);
+  }
+  for (; snapshots_iter != snapshots_->end(); ++snapshots_iter) {
+    auto cur = *snapshots_iter;
+    assert(in <= cur);
+    if (snapshot_checker_ == nullptr ||
+        snapshot_checker_->IsInSnapshot(in, cur)) {
       return cur;
     }
-    prev = cur;
-    assert(prev < kMaxSequenceNumber);
+    *prev_snapshot = cur;
   }
-  *prev_snapshot = prev;
   return kMaxSequenceNumber;
 }
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_iterator.h b/3rdParty/rocksdb/v5.18.X/db/compaction_iterator.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_iterator.h
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_iterator.h
index 71359169c5..1f6a135b89 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction_iterator.h
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_iterator.h
@@ -13,7 +13,7 @@
 #include "db/compaction_iteration_stats.h"
 #include "db/merge_helper.h"
 #include "db/pinned_iterators_manager.h"
-#include "db/range_del_aggregator.h"
+#include "db/range_del_aggregator_v2.h"
 #include "db/snapshot_checker.h"
 #include "options/cf_options.h"
 #include "rocksdb/compaction_filter.h"
@@ -64,7 +64,7 @@ class CompactionIterator {
                      SequenceNumber earliest_write_conflict_snapshot,
                      const SnapshotChecker* snapshot_checker, Env* env,
                      bool report_detailed_time, bool expect_valid_internal_key,
-                     RangeDelAggregator* range_del_agg,
+                     CompactionRangeDelAggregatorV2* range_del_agg,
                      const Compaction* compaction = nullptr,
                      const CompactionFilter* compaction_filter = nullptr,
                      const std::atomic<bool>* shutting_down = nullptr,
@@ -77,7 +77,7 @@ class CompactionIterator {
                      SequenceNumber earliest_write_conflict_snapshot,
                      const SnapshotChecker* snapshot_checker, Env* env,
                      bool report_detailed_time, bool expect_valid_internal_key,
-                     RangeDelAggregator* range_del_agg,
+                     CompactionRangeDelAggregatorV2* range_del_agg,
                      std::unique_ptr<CompactionProxy> compaction,
                      const CompactionFilter* compaction_filter = nullptr,
                      const std::atomic<bool>* shutting_down = nullptr,
@@ -141,7 +141,7 @@ class CompactionIterator {
   Env* env_;
   bool report_detailed_time_;
   bool expect_valid_internal_key_;
-  RangeDelAggregator* range_del_agg_;
+  CompactionRangeDelAggregatorV2* range_del_agg_;
   std::unique_ptr<CompactionProxy> compaction_;
   const CompactionFilter* compaction_filter_;
   const std::atomic<bool>* shutting_down_;
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_iterator_test.cc b/3rdParty/rocksdb/v5.18.X/db/compaction_iterator_test.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_iterator_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_iterator_test.cc
index aa929f19f5..a81efafaa1 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction_iterator_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_iterator_test.cc
@@ -221,10 +221,16 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
       MergeOperator* merge_op = nullptr, CompactionFilter* filter = nullptr,
       bool bottommost_level = false,
       SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
-    std::unique_ptr<InternalIterator> range_del_iter(
+    std::unique_ptr<InternalIterator> unfragmented_range_del_iter(
         new test::VectorIterator(range_del_ks, range_del_vs));
-    range_del_agg_.reset(new RangeDelAggregator(icmp_, snapshots_));
-    ASSERT_OK(range_del_agg_->AddTombstones(std::move(range_del_iter)));
+    auto tombstone_list = std::make_shared<FragmentedRangeTombstoneList>(
+        std::move(unfragmented_range_del_iter), icmp_);
+    std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter(
+        new FragmentedRangeTombstoneIterator(tombstone_list, icmp_,
+                                             kMaxSequenceNumber));
+    range_del_agg_.reset(
+        new CompactionRangeDelAggregatorV2(&icmp_, snapshots_));
+    range_del_agg_->AddTombstones(std::move(range_del_iter));
 
     std::unique_ptr<CompactionIterator::CompactionProxy> compaction;
     if (filter || bottommost_level) {
@@ -247,9 +253,8 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
     c_iter_.reset(new CompactionIterator(
         iter_.get(), cmp_, merge_helper_.get(), last_sequence, &snapshots_,
         earliest_write_conflict_snapshot, snapshot_checker_.get(),
-        Env::Default(), false /* report_detailed_time */,
-        false, range_del_agg_.get(), std::move(compaction), filter,
-        &shutting_down_));
+        Env::Default(), false /* report_detailed_time */, false,
+        range_del_agg_.get(), std::move(compaction), filter, &shutting_down_));
   }
 
   void AddSnapshot(SequenceNumber snapshot,
@@ -293,7 +298,7 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
   std::unique_ptr<MergeHelper> merge_helper_;
   std::unique_ptr<LoggingForwardVectorIterator> iter_;
   std::unique_ptr<CompactionIterator> c_iter_;
-  std::unique_ptr<RangeDelAggregator> range_del_agg_;
+  std::unique_ptr<CompactionRangeDelAggregatorV2> range_del_agg_;
   std::unique_ptr<SnapshotChecker> snapshot_checker_;
   std::atomic<bool> shutting_down_{false};
   FakeCompaction* compaction_proxy_;
@@ -672,8 +677,12 @@ TEST_P(CompactionIteratorTest, ZeroOutSequenceAtBottomLevel) {
 TEST_P(CompactionIteratorTest, RemoveDeletionAtBottomLevel) {
   AddSnapshot(1);
   RunTest({test::KeyStr("a", 1, kTypeDeletion),
-           test::KeyStr("b", 2, kTypeDeletion)},
-          {"", ""}, {test::KeyStr("b", 2, kTypeDeletion)}, {""},
+           test::KeyStr("b", 3, kTypeDeletion),
+           test::KeyStr("b", 1, kTypeValue)},
+          {"", "", ""},
+          {test::KeyStr("b", 3, kTypeDeletion),
+           test::KeyStr("b", 0, kTypeValue)},
+          {"", ""},
           kMaxSequenceNumber /*last_commited_seq*/, nullptr /*merge_operator*/,
           nullptr /*compaction_filter*/, true /*bottommost_level*/);
 }
@@ -842,13 +851,26 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest,
       {test::KeyStr("a", 1, kTypeDeletion), test::KeyStr("b", 2, kTypeDeletion),
        test::KeyStr("c", 3, kTypeDeletion)},
       {"", "", ""},
-      {test::KeyStr("b", 2, kTypeDeletion),
-       test::KeyStr("c", 3, kTypeDeletion)},
+      {},
       {"", ""}, kMaxSequenceNumber /*last_commited_seq*/,
       nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
       true /*bottommost_level*/);
 }
 
+TEST_F(CompactionIteratorWithSnapshotCheckerTest,
+       NotRemoveDeletionIfValuePresentToEarlierSnapshot) {
+  AddSnapshot(2,1);
+  RunTest(
+      {test::KeyStr("a", 4, kTypeDeletion), test::KeyStr("a", 1, kTypeValue),
+          test::KeyStr("b", 3, kTypeValue)},
+      {"", "", ""},
+      {test::KeyStr("a", 4, kTypeDeletion), test::KeyStr("a", 0, kTypeValue),
+            test::KeyStr("b", 3, kTypeValue)},
+      {"", "", ""}, kMaxSequenceNumber /*last_commited_seq*/,
+      nullptr /*merge_operator*/, nullptr /*compaction_filter*/,
+      true /*bottommost_level*/);
+}
+
 TEST_F(CompactionIteratorWithSnapshotCheckerTest,
        NotRemoveSingleDeletionIfNotVisibleToEarliestSnapshot) {
   AddSnapshot(2, 1);
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_job.cc b/3rdParty/rocksdb/v5.18.X/db/compaction_job.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_job.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_job.cc
index 08a5eab6b4..17be3156bf 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction_job.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_job.cc
@@ -36,6 +36,7 @@
 #include "db/memtable_list.h"
 #include "db/merge_context.h"
 #include "db/merge_helper.h"
+#include "db/range_del_aggregator_v2.h"
 #include "db/version_set.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/perf_context_imp.h"
@@ -200,7 +201,7 @@ struct CompactionJob::SubcompactionState {
     return *this;
   }
 
-  // Because member unique_ptrs do not have these.
+  // Because member std::unique_ptrs do not have these.
   SubcompactionState(const SubcompactionState&) = delete;
 
   SubcompactionState& operator=(const SubcompactionState&) = delete;
@@ -511,7 +512,10 @@ void CompactionJob::GenSubcompactionBoundaries() {
   // size of data covered by keys in that range
   uint64_t sum = 0;
   std::vector<RangeWithSize> ranges;
-  auto* v = cfd->current();
+  // Get input version from CompactionState since it's already referenced
+  // earlier in SetInputVersioCompaction::SetInputVersion and will not change
+  // when db_mutex_ is released below
+  auto* v = compact_->compaction->input_version();
   for (auto it = bounds.begin();;) {
     const Slice a = *it;
     it++;
@@ -521,7 +525,13 @@ void CompactionJob::GenSubcompactionBoundaries() {
     }
 
     const Slice b = *it;
+
+    // ApproximateSize could potentially create table reader iterator to seek
+    // to the index block and may incur I/O cost in the process. Unlock db
+    // mutex to reduce contention
+    db_mutex_->Unlock();
     uint64_t size = versions_->ApproximateSize(v, a, b, start_lvl, out_lvl + 1);
+    db_mutex_->Lock();
     ranges.emplace_back(a, b, size);
     sum += size;
   }
@@ -795,10 +805,13 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
 void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   assert(sub_compact != nullptr);
   ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
-  std::unique_ptr<RangeDelAggregator> range_del_agg(
-      new RangeDelAggregator(cfd->internal_comparator(), existing_snapshots_));
+  CompactionRangeDelAggregatorV2 range_del_agg(&cfd->internal_comparator(),
+                                               existing_snapshots_);
+
+  // Although the v2 aggregator is what the level iterator(s) know about,
+  // the AddTombstones calls will be propagated down to the v1 aggregator.
   std::unique_ptr<InternalIterator> input(versions_->MakeInputIterator(
-      sub_compact->compaction, range_del_agg.get(), env_optiosn_for_read_));
+      sub_compact->compaction, &range_del_agg, env_optiosn_for_read_));
 
   AutoThreadOperationStageUpdater stage_updater(
       ThreadStatus::STAGE_COMPACTION_PROCESS_KV);
@@ -887,7 +900,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       input.get(), cfd->user_comparator(), &merge, versions_->LastSequence(),
       &existing_snapshots_, earliest_write_conflict_snapshot_,
       snapshot_checker_, env_, ShouldReportDetailedTime(env_, stats_), false,
-      range_del_agg.get(), sub_compact->compaction, compaction_filter,
+      &range_del_agg, sub_compact->compaction, compaction_filter,
       shutting_down_, preserve_deletes_seqnum_));
   auto c_iter = sub_compact->c_iter.get();
   c_iter->SeekToFirst();
@@ -1025,9 +1038,9 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
         next_key = &c_iter->key();
       }
       CompactionIterationStats range_del_out_stats;
-      status = FinishCompactionOutputFile(input_status, sub_compact,
-                                          range_del_agg.get(),
-                                          &range_del_out_stats, next_key);
+      status =
+          FinishCompactionOutputFile(input_status, sub_compact, &range_del_agg,
+                                     &range_del_out_stats, next_key);
       RecordDroppedKeys(range_del_out_stats,
                         &sub_compact->compaction_job_stats);
       if (sub_compact->outputs.size() == 1) {
@@ -1077,7 +1090,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   }
 
   if (status.ok() && sub_compact->builder == nullptr &&
-      sub_compact->outputs.size() == 0) {
+      sub_compact->outputs.size() == 0 && !range_del_agg.IsEmpty()) {
     // handle subcompaction containing only range deletions
     status = OpenCompactionOutputFile(sub_compact);
   }
@@ -1086,8 +1099,8 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   // close the output file.
   if (sub_compact->builder != nullptr) {
     CompactionIterationStats range_del_out_stats;
-    Status s = FinishCompactionOutputFile(
-        status, sub_compact, range_del_agg.get(), &range_del_out_stats);
+    Status s = FinishCompactionOutputFile(status, sub_compact, &range_del_agg,
+                                          &range_del_out_stats);
     if (status.ok()) {
       status = s;
     }
@@ -1152,7 +1165,7 @@ void CompactionJob::RecordDroppedKeys(
 
 Status CompactionJob::FinishCompactionOutputFile(
     const Status& input_status, SubcompactionState* sub_compact,
-    RangeDelAggregator* range_del_agg,
+    CompactionRangeDelAggregatorV2* range_del_agg,
     CompactionIterationStats* range_del_out_stats,
     const Slice* next_table_min_key /* = nullptr */) {
   AutoThreadOperationStageUpdater stage_updater(
@@ -1204,18 +1217,38 @@ Status CompactionJob::FinishCompactionOutputFile(
     if (existing_snapshots_.size() > 0) {
       earliest_snapshot = existing_snapshots_[0];
     }
-    auto it = range_del_agg->NewIterator();
+    bool has_overlapping_endpoints;
+    if (upper_bound != nullptr && meta->largest.size() > 0) {
+      has_overlapping_endpoints =
+          ucmp->Compare(meta->largest.user_key(), *upper_bound) == 0;
+    } else {
+      has_overlapping_endpoints = false;
+    }
+
+    auto it = range_del_agg->NewIterator(lower_bound, upper_bound,
+                                         has_overlapping_endpoints);
+    // Position the range tombstone output iterator. There may be tombstone
+    // fragments that are entirely out of range, so make sure that we do not
+    // include those.
     if (lower_bound != nullptr) {
       it->Seek(*lower_bound);
+    } else {
+      it->SeekToFirst();
     }
     for (; it->Valid(); it->Next()) {
       auto tombstone = it->Tombstone();
-      if (upper_bound != nullptr &&
-          ucmp->Compare(*upper_bound, tombstone.start_key_) <= 0) {
-        // Tombstones starting at upper_bound or later only need to be included
-        // in the next table. Break because subsequent tombstones will start
-        // even later.
-        break;
+      if (upper_bound != nullptr) {
+        int cmp = ucmp->Compare(*upper_bound, tombstone.start_key_);
+        if ((has_overlapping_endpoints && cmp < 0) ||
+            (!has_overlapping_endpoints && cmp <= 0)) {
+          // Tombstones starting after upper_bound only need to be included in
+          // the next table. If the current SST ends before upper_bound, i.e.,
+          // `has_overlapping_endpoints == false`, we can also skip over range
+          // tombstones that start exactly at upper_bound. Such range tombstones
+          // will be included in the next file and are not relevant to the point
+          // keys or endpoints of the current file.
+          break;
+        }
       }
 
       if (bottommost_level_ && tombstone.seq_ <= earliest_snapshot) {
@@ -1227,6 +1260,8 @@ Status CompactionJob::FinishCompactionOutputFile(
       }
 
       auto kv = tombstone.Serialize();
+      assert(lower_bound == nullptr ||
+             ucmp->Compare(*lower_bound, kv.second) < 0);
       sub_compact->builder->Add(kv.first.Encode(), kv.second);
       InternalKey smallest_candidate = std::move(kv.first);
       if (lower_bound != nullptr &&
@@ -1308,9 +1343,7 @@ Status CompactionJob::FinishCompactionOutputFile(
     // VersionEdit.
     assert(!sub_compact->outputs.empty());
     sub_compact->outputs.pop_back();
-    sub_compact->builder.reset();
-    sub_compact->current_output_file_size = 0;
-    return s;
+    meta = nullptr;
   }
 
   if (s.ok() && (current_entries > 0 || tp.num_range_deletions > 0)) {
@@ -1432,7 +1465,7 @@ Status CompactionJob::OpenCompactionOutputFile(
       TableFileCreationReason::kCompaction);
 #endif  // !ROCKSDB_LITE
   // Make the output file
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
 #ifndef NDEBUG
   bool syncpoint_arg = env_options_.use_direct_writes;
   TEST_SYNC_POINT_CALLBACK("CompactionJob::OpenCompactionOutputFile",
@@ -1464,8 +1497,11 @@ Status CompactionJob::OpenCompactionOutputFile(
   writable_file->SetWriteLifeTimeHint(write_hint_);
   writable_file->SetPreallocationBlockSize(static_cast<size_t>(
       sub_compact->compaction->OutputFilePreallocationSize()));
-  sub_compact->outfile.reset(new WritableFileWriter(
-      std::move(writable_file), env_options_, db_options_.statistics.get()));
+  const auto& listeners =
+      sub_compact->compaction->immutable_cf_options()->listeners;
+  sub_compact->outfile.reset(
+      new WritableFileWriter(std::move(writable_file), fname, env_options_,
+                             db_options_.statistics.get(), listeners));
 
   // If the Column family flag is to only optimize filters for hits,
   // we can skip creating filters if this is the bottommost_level where
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_job.h b/3rdParty/rocksdb/v5.18.X/db/compaction_job.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_job.h
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_job.h
index a31e8c1423..86d97e1dbf 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction_job.h
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_job.h
@@ -25,12 +25,12 @@
 #include "db/job_context.h"
 #include "db/log_writer.h"
 #include "db/memtable_list.h"
-#include "db/range_del_aggregator.h"
+#include "db/range_del_aggregator_v2.h"
 #include "db/version_edit.h"
 #include "db/write_controller.h"
 #include "db/write_thread.h"
-#include "options/db_options.h"
 #include "options/cf_options.h"
+#include "options/db_options.h"
 #include "port/port.h"
 #include "rocksdb/compaction_filter.h"
 #include "rocksdb/compaction_job_stats.h"
@@ -104,7 +104,7 @@ class CompactionJob {
 
   Status FinishCompactionOutputFile(
       const Status& input_status, SubcompactionState* sub_compact,
-      RangeDelAggregator* range_del_agg,
+      CompactionRangeDelAggregatorV2* range_del_agg,
       CompactionIterationStats* range_del_out_stats,
       const Slice* next_table_min_key = nullptr);
   Status InstallCompactionResults(const MutableCFOptions& mutable_cf_options);
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_job_stats_test.cc b/3rdParty/rocksdb/v5.18.X/db/compaction_job_stats_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_job_stats_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_job_stats_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_job_test.cc b/3rdParty/rocksdb/v5.18.X/db/compaction_job_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_job_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_job_test.cc
index e32b5a078d..c7da191dd4 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction_job_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_job_test.cc
@@ -79,7 +79,7 @@ class CompactionJobTest : public testing::Test {
         shutting_down_(false),
         preserve_deletes_seqnum_(0),
         mock_table_factory_(new mock::MockTableFactory()),
-        error_handler_(db_options_, &mutex_) {
+        error_handler_(nullptr, db_options_, &mutex_) {
     EXPECT_OK(env_->CreateDirIfMissing(dbname_));
     db_options_.db_paths.emplace_back(dbname_,
                                       std::numeric_limits<uint64_t>::max());
@@ -200,12 +200,12 @@ class CompactionJobTest : public testing::Test {
     new_db.SetLastSequence(0);
 
     const std::string manifest = DescriptorFileName(dbname_, 1);
-    unique_ptr<WritableFile> file;
+    std::unique_ptr<WritableFile> file;
     Status s = env_->NewWritableFile(
         manifest, &file, env_->OptimizeForManifestWrite(env_options_));
     ASSERT_OK(s);
-    unique_ptr<WritableFileWriter> file_writer(
-        new WritableFileWriter(std::move(file), env_options_));
+    std::unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(file), manifest, env_options_));
     {
       log::Writer log(std::move(file_writer), 0, false);
       std::string record;
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_picker.cc b/3rdParty/rocksdb/v5.18.X/db/compaction_picker.cc
similarity index 86%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_picker.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_picker.cc
index b8f566afef..6510d4bc0c 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction_picker.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_picker.cc
@@ -18,6 +18,7 @@
 #include <queue>
 #include <string>
 #include <utility>
+#include <vector>
 #include "db/column_family.h"
 #include "monitoring/statistics.h"
 #include "util/filename.h"
@@ -36,6 +37,7 @@ uint64_t TotalCompensatedFileSize(const std::vector<FileMetaData*>& files) {
   }
   return sum;
 }
+}  // anonymous namespace
 
 bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
                            size_t min_files_to_compact,
@@ -49,7 +51,7 @@ bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
   // increasing.
   size_t new_compact_bytes_per_del_file = 0;
   for (span_len = 1; span_len < level_files.size(); ++span_len) {
-    compact_bytes += level_files[span_len]->fd.file_size;
+    compact_bytes += static_cast<size_t>(level_files[span_len]->fd.file_size);
     new_compact_bytes_per_del_file = compact_bytes / span_len;
     if (level_files[span_len]->being_compacted ||
         new_compact_bytes_per_del_file > compact_bytes_per_del_file) {
@@ -69,7 +71,6 @@ bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
   }
   return false;
 }
-}  // anonymous namespace
 
 // Determine compression type, based on user options, level of the output
 // file and whether compression is disabled.
@@ -219,7 +220,8 @@ void CompactionPicker::GetRange(const std::vector<CompactionInputFiles>& inputs,
 
 bool CompactionPicker::ExpandInputsToCleanCut(const std::string& /*cf_name*/,
                                               VersionStorageInfo* vstorage,
-                                              CompactionInputFiles* inputs) {
+                                              CompactionInputFiles* inputs,
+                                              InternalKey** next_smallest) {
   // This isn't good compaction
   assert(!inputs->empty());
 
@@ -242,7 +244,8 @@ bool CompactionPicker::ExpandInputsToCleanCut(const std::string& /*cf_name*/,
     GetRange(*inputs, &smallest, &largest);
     inputs->clear();
     vstorage->GetOverlappingInputs(level, &smallest, &largest, &inputs->files,
-                                   hint_index, &hint_index);
+                                   hint_index, &hint_index, true,
+                                   next_smallest);
   } while (inputs->size() > old_size);
 
   // we started off with inputs non-empty and the previous loop only grew
@@ -315,13 +318,29 @@ Compaction* CompactionPicker::CompactFiles(
   // shouldn't have been released since.
   assert(!FilesRangeOverlapWithCompaction(input_files, output_level));
 
-  auto c =
-      new Compaction(vstorage, ioptions_, mutable_cf_options, input_files,
-                     output_level, compact_options.output_file_size_limit,
-                     mutable_cf_options.max_compaction_bytes, output_path_id,
-                     compact_options.compression, ioptions_.compression_opts,
-                     compact_options.max_subcompactions,
-                     /* grandparents */ {}, true);
+  CompressionType compression_type;
+  if (compact_options.compression == kDisableCompressionOption) {
+    int base_level;
+    if (ioptions_.compaction_style == kCompactionStyleLevel) {
+      base_level = vstorage->base_level();
+    } else {
+      base_level = 1;
+    }
+    compression_type =
+        GetCompressionType(ioptions_, vstorage, mutable_cf_options,
+                           output_level, base_level);
+  } else {
+    // TODO(ajkr): `CompactionOptions` offers configurable `CompressionType`
+    // without configurable `CompressionOptions`, which is inconsistent.
+    compression_type = compact_options.compression;
+  }
+  auto c = new Compaction(
+      vstorage, ioptions_, mutable_cf_options, input_files, output_level,
+      compact_options.output_file_size_limit,
+      mutable_cf_options.max_compaction_bytes, output_path_id, compression_type,
+      GetCompressionOptions(ioptions_, vstorage, output_level),
+      compact_options.max_subcompactions,
+      /* grandparents */ {}, true);
   RegisterCompaction(c);
   return c;
 }
@@ -633,7 +652,6 @@ Compaction* CompactionPicker::CompactRange(
       uint64_t s = inputs[i]->compensated_file_size;
       total += s;
       if (total >= limit) {
-        **compaction_end = inputs[i + 1]->smallest;
         covering_the_whole_range = false;
         inputs.files.resize(i + 1);
         break;
@@ -642,7 +660,10 @@ Compaction* CompactionPicker::CompactRange(
   }
   assert(output_path_id < static_cast<uint32_t>(ioptions_.cf_paths.size()));
 
-  if (ExpandInputsToCleanCut(cf_name, vstorage, &inputs) == false) {
+  InternalKey key_storage;
+  InternalKey* next_smallest = &key_storage;
+  if (ExpandInputsToCleanCut(cf_name, vstorage, &inputs, &next_smallest) ==
+      false) {
     // manual compaction is now multi-threaded, so it can
     // happen that ExpandWhileOverlapping fails
     // we handle it higher in RunManualCompaction
@@ -650,8 +671,10 @@ Compaction* CompactionPicker::CompactRange(
     return nullptr;
   }
 
-  if (covering_the_whole_range) {
+  if (covering_the_whole_range || !next_smallest) {
     *compaction_end = nullptr;
+  } else {
+    **compaction_end = *next_smallest;
   }
 
   CompactionInputFiles output_level_inputs;
@@ -921,8 +944,8 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
   // any currently-existing files.
   for (auto file_num : *input_files) {
     bool found = false;
-    for (auto level_meta : cf_meta.levels) {
-      for (auto file_meta : level_meta.files) {
+    for (const auto& level_meta : cf_meta.levels) {
+      for (const auto& file_meta : level_meta.files) {
         if (file_num == TableFileNameToNumber(file_meta.name)) {
           if (file_meta.being_compacted) {
             return Status::Aborted("Specified compaction input file " +
@@ -1525,217 +1548,4 @@ Compaction* LevelCompactionPicker::PickCompaction(
   return builder.PickCompaction();
 }
 
-#ifndef ROCKSDB_LITE
-bool FIFOCompactionPicker::NeedsCompaction(
-    const VersionStorageInfo* vstorage) const {
-  const int kLevel0 = 0;
-  return vstorage->CompactionScore(kLevel0) >= 1;
-}
-
-namespace {
-uint64_t GetTotalFilesSize(
-    const std::vector<FileMetaData*>& files) {
-  uint64_t total_size = 0;
-  for (const auto& f : files) {
-    total_size += f->fd.file_size;
-  }
-  return total_size;
-}
-}  // anonymous namespace
-
-Compaction* FIFOCompactionPicker::PickTTLCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  assert(mutable_cf_options.compaction_options_fifo.ttl > 0);
-
-  const int kLevel0 = 0;
-  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
-  uint64_t total_size = GetTotalFilesSize(level_files);
-
-  int64_t _current_time;
-  auto status = ioptions_.env->GetCurrentTime(&_current_time);
-  if (!status.ok()) {
-    ROCKS_LOG_BUFFER(log_buffer,
-                     "[%s] FIFO compaction: Couldn't get current time: %s. "
-                     "Not doing compactions based on TTL. ",
-                     cf_name.c_str(), status.ToString().c_str());
-    return nullptr;
-  }
-  const uint64_t current_time = static_cast<uint64_t>(_current_time);
-
-  std::vector<CompactionInputFiles> inputs;
-  inputs.emplace_back();
-  inputs[0].level = 0;
-
-  // avoid underflow
-  if (current_time > mutable_cf_options.compaction_options_fifo.ttl) {
-    for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
-      auto f = *ritr;
-      if (f->fd.table_reader != nullptr &&
-          f->fd.table_reader->GetTableProperties() != nullptr) {
-        auto creation_time =
-            f->fd.table_reader->GetTableProperties()->creation_time;
-        if (creation_time == 0 ||
-            creation_time >= (current_time -
-                              mutable_cf_options.compaction_options_fifo.ttl)) {
-          break;
-        }
-        total_size -= f->compensated_file_size;
-        inputs[0].files.push_back(f);
-      }
-    }
-  }
-
-  // Return a nullptr and proceed to size-based FIFO compaction if:
-  // 1. there are no files older than ttl OR
-  // 2. there are a few files older than ttl, but deleting them will not bring
-  //    the total size to be less than max_table_files_size threshold.
-  if (inputs[0].files.empty() ||
-      total_size >
-          mutable_cf_options.compaction_options_fifo.max_table_files_size) {
-    return nullptr;
-  }
-
-  for (const auto& f : inputs[0].files) {
-    ROCKS_LOG_BUFFER(log_buffer,
-                     "[%s] FIFO compaction: picking file %" PRIu64
-                     " with creation time %" PRIu64 " for deletion",
-                     cf_name.c_str(), f->fd.GetNumber(),
-                     f->fd.table_reader->GetTableProperties()->creation_time);
-  }
-
-  Compaction* c = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
-      kNoCompression, ioptions_.compression_opts, /* max_subcompactions */ 0,
-      {}, /* is manual */ false, vstorage->CompactionScore(0),
-      /* is deletion compaction */ true, CompactionReason::kFIFOTtl);
-  return c;
-}
-
-Compaction* FIFOCompactionPicker::PickSizeCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  const int kLevel0 = 0;
-  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
-  uint64_t total_size = GetTotalFilesSize(level_files);
-
-  if (total_size <=
-          mutable_cf_options.compaction_options_fifo.max_table_files_size ||
-      level_files.size() == 0) {
-    // total size not exceeded
-    if (mutable_cf_options.compaction_options_fifo.allow_compaction &&
-        level_files.size() > 0) {
-      CompactionInputFiles comp_inputs;
-      // try to prevent same files from being compacted multiple times, which
-      // could produce large files that may never TTL-expire. Achieve this by
-      // disallowing compactions with files larger than memtable (inflate its
-      // size by 10% to account for uncompressed L0 files that may have size
-      // slightly greater than memtable size limit).
-      size_t max_compact_bytes_per_del_file =
-          static_cast<size_t>(MultiplyCheckOverflow(
-              static_cast<uint64_t>(mutable_cf_options.write_buffer_size),
-              1.1));
-      if (FindIntraL0Compaction(
-              level_files,
-              mutable_cf_options
-                  .level0_file_num_compaction_trigger /* min_files_to_compact */
-              ,
-              max_compact_bytes_per_del_file, &comp_inputs)) {
-        Compaction* c = new Compaction(
-            vstorage, ioptions_, mutable_cf_options, {comp_inputs}, 0,
-            16 * 1024 * 1024 /* output file size limit */,
-            0 /* max compaction bytes, not applicable */,
-            0 /* output path ID */, mutable_cf_options.compression,
-            ioptions_.compression_opts, 0 /* max_subcompactions */, {},
-            /* is manual */ false, vstorage->CompactionScore(0),
-            /* is deletion compaction */ false,
-            CompactionReason::kFIFOReduceNumFiles);
-        return c;
-      }
-    }
-
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] FIFO compaction: nothing to do. Total size %" PRIu64
-        ", max size %" PRIu64 "\n",
-        cf_name.c_str(), total_size,
-        mutable_cf_options.compaction_options_fifo.max_table_files_size);
-    return nullptr;
-  }
-
-  if (!level0_compactions_in_progress_.empty()) {
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "[%s] FIFO compaction: Already executing compaction. No need "
-        "to run parallel compactions since compactions are very fast",
-        cf_name.c_str());
-    return nullptr;
-  }
-
-  std::vector<CompactionInputFiles> inputs;
-  inputs.emplace_back();
-  inputs[0].level = 0;
-
-  for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
-    auto f = *ritr;
-    total_size -= f->compensated_file_size;
-    inputs[0].files.push_back(f);
-    char tmp_fsize[16];
-    AppendHumanBytes(f->fd.GetFileSize(), tmp_fsize, sizeof(tmp_fsize));
-    ROCKS_LOG_BUFFER(log_buffer,
-                     "[%s] FIFO compaction: picking file %" PRIu64
-                     " with size %s for deletion",
-                     cf_name.c_str(), f->fd.GetNumber(), tmp_fsize);
-    if (total_size <=
-        mutable_cf_options.compaction_options_fifo.max_table_files_size) {
-      break;
-    }
-  }
-
-  Compaction* c = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
-      kNoCompression, ioptions_.compression_opts, /* max_subcompactions */ 0,
-      {}, /* is manual */ false, vstorage->CompactionScore(0),
-      /* is deletion compaction */ true, CompactionReason::kFIFOMaxSize);
-  return c;
-}
-
-Compaction* FIFOCompactionPicker::PickCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
-  assert(vstorage->num_levels() == 1);
-
-  Compaction* c = nullptr;
-  if (mutable_cf_options.compaction_options_fifo.ttl > 0) {
-    c = PickTTLCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
-  }
-  if (c == nullptr) {
-    c = PickSizeCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
-  }
-  RegisterCompaction(c);
-  return c;
-}
-
-Compaction* FIFOCompactionPicker::CompactRange(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, int input_level, int output_level,
-    uint32_t /*output_path_id*/, uint32_t /*max_subcompactions*/,
-    const InternalKey* /*begin*/, const InternalKey* /*end*/,
-    InternalKey** compaction_end, bool* /*manual_conflict*/) {
-#ifdef NDEBUG
-  (void)input_level;
-  (void)output_level;
-#endif
-  assert(input_level == 0);
-  assert(output_level == 0);
-  *compaction_end = nullptr;
-  LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, ioptions_.info_log);
-  Compaction* c =
-      PickCompaction(cf_name, mutable_cf_options, vstorage, &log_buffer);
-  log_buffer.FlushBufferToLog();
-  return c;
-}
-
-#endif  // !ROCKSDB_LITE
-
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_picker.h b/3rdParty/rocksdb/v5.18.X/db/compaction_picker.h
similarity index 87%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_picker.h
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_picker.h
index 5f770039a7..c60d792852 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction_picker.h
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_picker.h
@@ -151,7 +151,8 @@ class CompactionPicker {
   // Will return false if it is impossible to apply this compaction.
   bool ExpandInputsToCleanCut(const std::string& cf_name,
                               VersionStorageInfo* vstorage,
-                              CompactionInputFiles* inputs);
+                              CompactionInputFiles* inputs,
+                              InternalKey** next_smallest = nullptr);
 
   // Returns true if any one of the parent files are being compacted
   bool IsRangeInCompaction(VersionStorageInfo* vstorage,
@@ -234,42 +235,6 @@ class LevelCompactionPicker : public CompactionPicker {
 };
 
 #ifndef ROCKSDB_LITE
-class FIFOCompactionPicker : public CompactionPicker {
- public:
-  FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
-                       const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-
-  virtual Compaction* PickCompaction(const std::string& cf_name,
-                                     const MutableCFOptions& mutable_cf_options,
-                                     VersionStorageInfo* version,
-                                     LogBuffer* log_buffer) override;
-
-  virtual Compaction* CompactRange(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, int input_level, int output_level,
-      uint32_t output_path_id, uint32_t max_subcompactions,
-      const InternalKey* begin, const InternalKey* end,
-      InternalKey** compaction_end, bool* manual_conflict) override;
-
-  // The maximum allowed output level.  Always returns 0.
-  virtual int MaxOutputLevel() const override { return 0; }
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-
- private:
-  Compaction* PickTTLCompaction(const std::string& cf_name,
-                                const MutableCFOptions& mutable_cf_options,
-                                VersionStorageInfo* version,
-                                LogBuffer* log_buffer);
-
-  Compaction* PickSizeCompaction(const std::string& cf_name,
-                                 const MutableCFOptions& mutable_cf_options,
-                                 VersionStorageInfo* version,
-                                 LogBuffer* log_buffer);
-};
-
 class NullCompactionPicker : public CompactionPicker {
  public:
   NullCompactionPicker(const ImmutableCFOptions& ioptions,
@@ -307,6 +272,11 @@ class NullCompactionPicker : public CompactionPicker {
 };
 #endif  // !ROCKSDB_LITE
 
+bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
+                           size_t min_files_to_compact,
+                           uint64_t max_compact_bytes_per_del_file,
+                           CompactionInputFiles* comp_inputs);
+
 CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
                                    const VersionStorageInfo* vstorage,
                                    const MutableCFOptions& mutable_cf_options,
diff --git a/3rdParty/rocksdb/v5.18.X/db/compaction_picker_fifo.cc b/3rdParty/rocksdb/v5.18.X/db/compaction_picker_fifo.cc
new file mode 100644
index 0000000000..fd89b65ebb
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_picker_fifo.cc
@@ -0,0 +1,235 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+
+#include "db/compaction_picker_fifo.h"
+#ifndef ROCKSDB_LITE
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
+#include <string>
+#include <vector>
+#include "db/column_family.h"
+#include "util/log_buffer.h"
+#include "util/string_util.h"
+
+namespace rocksdb {
+namespace {
+uint64_t GetTotalFilesSize(const std::vector<FileMetaData*>& files) {
+  uint64_t total_size = 0;
+  for (const auto& f : files) {
+    total_size += f->fd.file_size;
+  }
+  return total_size;
+}
+}  // anonymous namespace
+
+bool FIFOCompactionPicker::NeedsCompaction(
+    const VersionStorageInfo* vstorage) const {
+  const int kLevel0 = 0;
+  return vstorage->CompactionScore(kLevel0) >= 1;
+}
+
+Compaction* FIFOCompactionPicker::PickTTLCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  assert(mutable_cf_options.compaction_options_fifo.ttl > 0);
+
+  const int kLevel0 = 0;
+  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
+  uint64_t total_size = GetTotalFilesSize(level_files);
+
+  int64_t _current_time;
+  auto status = ioptions_.env->GetCurrentTime(&_current_time);
+  if (!status.ok()) {
+    ROCKS_LOG_BUFFER(log_buffer,
+                     "[%s] FIFO compaction: Couldn't get current time: %s. "
+                     "Not doing compactions based on TTL. ",
+                     cf_name.c_str(), status.ToString().c_str());
+    return nullptr;
+  }
+  const uint64_t current_time = static_cast<uint64_t>(_current_time);
+
+  std::vector<CompactionInputFiles> inputs;
+  inputs.emplace_back();
+  inputs[0].level = 0;
+
+  // avoid underflow
+  if (current_time > mutable_cf_options.compaction_options_fifo.ttl) {
+    for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
+      auto f = *ritr;
+      if (f->fd.table_reader != nullptr &&
+          f->fd.table_reader->GetTableProperties() != nullptr) {
+        auto creation_time =
+            f->fd.table_reader->GetTableProperties()->creation_time;
+        if (creation_time == 0 ||
+            creation_time >= (current_time -
+                              mutable_cf_options.compaction_options_fifo.ttl)) {
+          break;
+        }
+        total_size -= f->compensated_file_size;
+        inputs[0].files.push_back(f);
+      }
+    }
+  }
+
+  // Return a nullptr and proceed to size-based FIFO compaction if:
+  // 1. there are no files older than ttl OR
+  // 2. there are a few files older than ttl, but deleting them will not bring
+  //    the total size to be less than max_table_files_size threshold.
+  if (inputs[0].files.empty() ||
+      total_size >
+          mutable_cf_options.compaction_options_fifo.max_table_files_size) {
+    return nullptr;
+  }
+
+  for (const auto& f : inputs[0].files) {
+    ROCKS_LOG_BUFFER(log_buffer,
+                     "[%s] FIFO compaction: picking file %" PRIu64
+                     " with creation time %" PRIu64 " for deletion",
+                     cf_name.c_str(), f->fd.GetNumber(),
+                     f->fd.table_reader->GetTableProperties()->creation_time);
+  }
+
+  Compaction* c = new Compaction(
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
+      kNoCompression, ioptions_.compression_opts, /* max_subcompactions */ 0,
+      {}, /* is manual */ false, vstorage->CompactionScore(0),
+      /* is deletion compaction */ true, CompactionReason::kFIFOTtl);
+  return c;
+}
+
+Compaction* FIFOCompactionPicker::PickSizeCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  const int kLevel0 = 0;
+  const std::vector<FileMetaData*>& level_files = vstorage->LevelFiles(kLevel0);
+  uint64_t total_size = GetTotalFilesSize(level_files);
+
+  if (total_size <=
+          mutable_cf_options.compaction_options_fifo.max_table_files_size ||
+      level_files.size() == 0) {
+    // total size not exceeded
+    if (mutable_cf_options.compaction_options_fifo.allow_compaction &&
+        level_files.size() > 0) {
+      CompactionInputFiles comp_inputs;
+      // try to prevent same files from being compacted multiple times, which
+      // could produce large files that may never TTL-expire. Achieve this by
+      // disallowing compactions with files larger than memtable (inflate its
+      // size by 10% to account for uncompressed L0 files that may have size
+      // slightly greater than memtable size limit).
+      size_t max_compact_bytes_per_del_file =
+          static_cast<size_t>(MultiplyCheckOverflow(
+              static_cast<uint64_t>(mutable_cf_options.write_buffer_size),
+              1.1));
+      if (FindIntraL0Compaction(
+              level_files,
+              mutable_cf_options
+                  .level0_file_num_compaction_trigger /* min_files_to_compact */
+              ,
+              max_compact_bytes_per_del_file, &comp_inputs)) {
+        Compaction* c = new Compaction(
+            vstorage, ioptions_, mutable_cf_options, {comp_inputs}, 0,
+            16 * 1024 * 1024 /* output file size limit */,
+            0 /* max compaction bytes, not applicable */,
+            0 /* output path ID */, mutable_cf_options.compression,
+            ioptions_.compression_opts, 0 /* max_subcompactions */, {},
+            /* is manual */ false, vstorage->CompactionScore(0),
+            /* is deletion compaction */ false,
+            CompactionReason::kFIFOReduceNumFiles);
+        return c;
+      }
+    }
+
+    ROCKS_LOG_BUFFER(
+        log_buffer,
+        "[%s] FIFO compaction: nothing to do. Total size %" PRIu64
+        ", max size %" PRIu64 "\n",
+        cf_name.c_str(), total_size,
+        mutable_cf_options.compaction_options_fifo.max_table_files_size);
+    return nullptr;
+  }
+
+  if (!level0_compactions_in_progress_.empty()) {
+    ROCKS_LOG_BUFFER(
+        log_buffer,
+        "[%s] FIFO compaction: Already executing compaction. No need "
+        "to run parallel compactions since compactions are very fast",
+        cf_name.c_str());
+    return nullptr;
+  }
+
+  std::vector<CompactionInputFiles> inputs;
+  inputs.emplace_back();
+  inputs[0].level = 0;
+
+  for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
+    auto f = *ritr;
+    total_size -= f->compensated_file_size;
+    inputs[0].files.push_back(f);
+    char tmp_fsize[16];
+    AppendHumanBytes(f->fd.GetFileSize(), tmp_fsize, sizeof(tmp_fsize));
+    ROCKS_LOG_BUFFER(log_buffer,
+                     "[%s] FIFO compaction: picking file %" PRIu64
+                     " with size %s for deletion",
+                     cf_name.c_str(), f->fd.GetNumber(), tmp_fsize);
+    if (total_size <=
+        mutable_cf_options.compaction_options_fifo.max_table_files_size) {
+      break;
+    }
+  }
+
+  Compaction* c = new Compaction(
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
+      kNoCompression, ioptions_.compression_opts, /* max_subcompactions */ 0,
+      {}, /* is manual */ false, vstorage->CompactionScore(0),
+      /* is deletion compaction */ true, CompactionReason::kFIFOMaxSize);
+  return c;
+}
+
+Compaction* FIFOCompactionPicker::PickCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  assert(vstorage->num_levels() == 1);
+
+  Compaction* c = nullptr;
+  if (mutable_cf_options.compaction_options_fifo.ttl > 0) {
+    c = PickTTLCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
+  }
+  if (c == nullptr) {
+    c = PickSizeCompaction(cf_name, mutable_cf_options, vstorage, log_buffer);
+  }
+  RegisterCompaction(c);
+  return c;
+}
+
+Compaction* FIFOCompactionPicker::CompactRange(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, int input_level, int output_level,
+    uint32_t /*output_path_id*/, uint32_t /*max_subcompactions*/,
+    const InternalKey* /*begin*/, const InternalKey* /*end*/,
+    InternalKey** compaction_end, bool* /*manual_conflict*/) {
+#ifdef NDEBUG
+  (void)input_level;
+  (void)output_level;
+#endif
+  assert(input_level == 0);
+  assert(output_level == 0);
+  *compaction_end = nullptr;
+  LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, ioptions_.info_log);
+  Compaction* c =
+      PickCompaction(cf_name, mutable_cf_options, vstorage, &log_buffer);
+  log_buffer.FlushBufferToLog();
+  return c;
+}
+
+}  // namespace rocksdb
+#endif  // !ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.18.X/db/compaction_picker_fifo.h b/3rdParty/rocksdb/v5.18.X/db/compaction_picker_fifo.h
new file mode 100644
index 0000000000..015fd42ddb
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_picker_fifo.h
@@ -0,0 +1,52 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+
+#pragma once
+#ifndef ROCKSDB_LITE
+
+#include "db/compaction_picker.h"
+
+namespace rocksdb {
+class FIFOCompactionPicker : public CompactionPicker {
+ public:
+  FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
+                       const InternalKeyComparator* icmp)
+      : CompactionPicker(ioptions, icmp) {}
+
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* version,
+                                     LogBuffer* log_buffer) override;
+
+  virtual Compaction* CompactRange(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, int input_level, int output_level,
+      uint32_t output_path_id, uint32_t max_subcompactions,
+      const InternalKey* begin, const InternalKey* end,
+      InternalKey** compaction_end, bool* manual_conflict) override;
+
+  // The maximum allowed output level.  Always returns 0.
+  virtual int MaxOutputLevel() const override { return 0; }
+
+  virtual bool NeedsCompaction(
+      const VersionStorageInfo* vstorage) const override;
+
+ private:
+  Compaction* PickTTLCompaction(const std::string& cf_name,
+                                const MutableCFOptions& mutable_cf_options,
+                                VersionStorageInfo* version,
+                                LogBuffer* log_buffer);
+
+  Compaction* PickSizeCompaction(const std::string& cf_name,
+                                 const MutableCFOptions& mutable_cf_options,
+                                 VersionStorageInfo* version,
+                                 LogBuffer* log_buffer);
+};
+}  // namespace rocksdb
+#endif  // !ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_picker_test.cc b/3rdParty/rocksdb/v5.18.X/db/compaction_picker_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_picker_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_picker_test.cc
index 40daf9cecc..1f5c90f487 100644
--- a/3rdParty/rocksdb/v5.16.X/db/compaction_picker_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/compaction_picker_test.cc
@@ -4,10 +4,12 @@
 //  (found in the LICENSE.Apache file in the root directory).
 
 #include "db/compaction_picker.h"
+
 #include <limits>
 #include <string>
 #include <utility>
 #include "db/compaction.h"
+#include "db/compaction_picker_fifo.h"
 #include "db/compaction_picker_universal.h"
 
 #include "util/logging.h"
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_picker_universal.cc b/3rdParty/rocksdb/v5.18.X/db/compaction_picker_universal.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_picker_universal.cc
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_picker_universal.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/compaction_picker_universal.h b/3rdParty/rocksdb/v5.18.X/db/compaction_picker_universal.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/compaction_picker_universal.h
rename to 3rdParty/rocksdb/v5.18.X/db/compaction_picker_universal.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/comparator_db_test.cc b/3rdParty/rocksdb/v5.18.X/db/comparator_db_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/comparator_db_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/comparator_db_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/convenience.cc b/3rdParty/rocksdb/v5.18.X/db/convenience.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/db/convenience.cc
rename to 3rdParty/rocksdb/v5.18.X/db/convenience.cc
index 880b840697..71c237f60c 100644
--- a/3rdParty/rocksdb/v5.16.X/db/convenience.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/convenience.cc
@@ -35,7 +35,7 @@ Status DeleteFilesInRanges(DB* db, ColumnFamilyHandle* column_family,
 Status VerifySstFileChecksum(const Options& options,
                              const EnvOptions& env_options,
                              const std::string& file_path) {
-  unique_ptr<RandomAccessFile> file;
+  std::unique_ptr<RandomAccessFile> file;
   uint64_t file_size;
   InternalKeyComparator internal_comparator(options.comparator);
   ImmutableCFOptions ioptions(options);
@@ -46,7 +46,7 @@ Status VerifySstFileChecksum(const Options& options,
   } else {
     return s;
   }
-  unique_ptr<TableReader> table_reader;
+  std::unique_ptr<TableReader> table_reader;
   std::unique_ptr<RandomAccessFileReader> file_reader(
       new RandomAccessFileReader(std::move(file), file_path));
   const bool kImmortal = true;
diff --git a/3rdParty/rocksdb/v5.16.X/db/corruption_test.cc b/3rdParty/rocksdb/v5.18.X/db/corruption_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/corruption_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/corruption_test.cc
index 9488c07fee..3bee4c6b27 100644
--- a/3rdParty/rocksdb/v5.16.X/db/corruption_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/corruption_test.cc
@@ -37,7 +37,7 @@ class CorruptionTest : public testing::Test {
  public:
   test::ErrorEnv env_;
   std::string dbname_;
-  shared_ptr<Cache> tiny_cache_;
+  std::shared_ptr<Cache> tiny_cache_;
   Options options_;
   DB* db_;
 
@@ -485,7 +485,7 @@ TEST_F(CorruptionTest, FileSystemStateCorrupted) {
     db_ = nullptr;
 
     if (iter == 0) {  // corrupt file size
-      unique_ptr<WritableFile> file;
+      std::unique_ptr<WritableFile> file;
       env_.NewWritableFile(filename, &file, EnvOptions());
       file->Append(Slice("corrupted sst"));
       file.reset();
diff --git a/3rdParty/rocksdb/v5.16.X/db/cuckoo_table_db_test.cc b/3rdParty/rocksdb/v5.18.X/db/cuckoo_table_db_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/cuckoo_table_db_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/cuckoo_table_db_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_basic_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_basic_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/db_basic_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_basic_test.cc
index dc732a7106..1c7e4a5c09 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_basic_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_basic_test.cc
@@ -794,7 +794,7 @@ TEST_F(DBBasicTest, ChecksumTest) {
   BlockBasedTableOptions table_options;
   Options options = CurrentOptions();
   // change when new checksum type added
-  int max_checksum = static_cast<int>(kxxHash);
+  int max_checksum = static_cast<int>(kxxHash64);
   const int kNumPerFile = 2;
 
   // generate one table with each type of checksum
@@ -809,7 +809,7 @@ TEST_F(DBBasicTest, ChecksumTest) {
   }
 
   // verify data with each type of checksum
-  for (int i = 0; i <= kxxHash; ++i) {
+  for (int i = 0; i <= kxxHash64; ++i) {
     table_options.checksum = static_cast<ChecksumType>(i);
     options.table_factory.reset(NewBlockBasedTableFactory(table_options));
     Reopen(options);
@@ -881,7 +881,7 @@ class TestEnv : public EnvWrapper {
     int GetCloseCount() { return close_count; }
 
     virtual Status NewLogger(const std::string& /*fname*/,
-                             shared_ptr<Logger>* result) {
+                             std::shared_ptr<Logger>* result) {
       result->reset(new TestLogger(this));
       return Status::OK();
     }
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_blob_index_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_blob_index_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_blob_index_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_blob_index_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_block_cache_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_block_cache_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/db_block_cache_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_block_cache_test.cc
index ac8c2825e3..0cefef3bb7 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_block_cache_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_block_cache_test.cc
@@ -349,7 +349,7 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
   // 200 bytes are enough to hold the first two blocks
   std::shared_ptr<Cache> cache = NewLRUCache(200, 0, false);
   table_options.block_cache = cache;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(20));
+  table_options.filter_policy.reset(NewBloomFilterPolicy(20, true));
   options.table_factory.reset(new BlockBasedTableFactory(table_options));
   CreateAndReopenWithCF({"pikachu"}, options);
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_bloom_filter_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_bloom_filter_test.cc
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/db/db_bloom_filter_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_bloom_filter_test.cc
index 289b5ec626..2fd5d6dfbe 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_bloom_filter_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_bloom_filter_test.cc
@@ -22,11 +22,12 @@ class DBBloomFilterTest : public DBTestBase {
 
 class DBBloomFilterTestWithParam
     : public DBTestBase,
-      public testing::WithParamInterface<std::tuple<bool, bool>> {
+      public testing::WithParamInterface<std::tuple<bool, bool, uint32_t>> {
   //                             public testing::WithParamInterface<bool> {
  protected:
   bool use_block_based_filter_;
   bool partition_filters_;
+  uint32_t format_version_;
 
  public:
   DBBloomFilterTestWithParam() : DBTestBase("/db_bloom_filter_tests") {}
@@ -36,9 +37,12 @@ class DBBloomFilterTestWithParam
   void SetUp() override {
     use_block_based_filter_ = std::get<0>(GetParam());
     partition_filters_ = std::get<1>(GetParam());
+    format_version_ = std::get<2>(GetParam());
   }
 };
 
+class DBBloomFilterTestDefFormatVersion : public DBBloomFilterTestWithParam {};
+
 class SliceTransformLimitedDomainGeneric : public SliceTransform {
   const char* Name() const override {
     return "SliceTransformLimitedDomainGeneric";
@@ -62,7 +66,7 @@ class SliceTransformLimitedDomainGeneric : public SliceTransform {
 // KeyMayExist can lead to a few false positives, but not false negatives.
 // To make test deterministic, use a much larger number of bits per key-20 than
 // bits in the key, so that false positives are eliminated
-TEST_P(DBBloomFilterTestWithParam, KeyMayExist) {
+TEST_P(DBBloomFilterTestDefFormatVersion, KeyMayExist) {
   do {
     ReadOptions ropts;
     std::string value;
@@ -143,6 +147,7 @@ TEST_F(DBBloomFilterTest, GetFilterByPrefixBloomCustomPrefixExtractor) {
     options.prefix_extractor =
         std::make_shared<SliceTransformLimitedDomainGeneric>();
     options.statistics = rocksdb::CreateDBStatistics();
+    get_perf_context()->EnablePerLevelPerfContext();
     BlockBasedTableOptions bbto;
     bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
     if (partition_filters) {
@@ -167,20 +172,39 @@ TEST_F(DBBloomFilterTest, GetFilterByPrefixBloomCustomPrefixExtractor) {
 
     ASSERT_EQ("foo", Get("barbarbar"));
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+    ASSERT_EQ(
+        0,
+        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
     ASSERT_EQ("foo2", Get("barbarbar2"));
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+    ASSERT_EQ(
+        0,
+        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
     ASSERT_EQ("NOT_FOUND", Get("barbarbar3"));
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 0);
+    ASSERT_EQ(
+        0,
+        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
 
     ASSERT_EQ("NOT_FOUND", Get("barfoofoo"));
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 1);
+    ASSERT_EQ(
+        1,
+        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
 
     ASSERT_EQ("NOT_FOUND", Get("foobarbar"));
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
+    ASSERT_EQ(
+        2,
+        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
 
     ro.total_order_seek = true;
     ASSERT_TRUE(db_->Get(ro, "foobarbar", &value).IsNotFound());
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
+    ASSERT_EQ(
+        2,
+        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    get_perf_context()->Reset();
   }
 }
 
@@ -189,6 +213,7 @@ TEST_F(DBBloomFilterTest, GetFilterByPrefixBloom) {
     Options options = last_options_;
     options.prefix_extractor.reset(NewFixedPrefixTransform(8));
     options.statistics = rocksdb::CreateDBStatistics();
+    get_perf_context()->EnablePerLevelPerfContext();
     BlockBasedTableOptions bbto;
     bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
     if (partition_filters) {
@@ -227,6 +252,10 @@ TEST_F(DBBloomFilterTest, GetFilterByPrefixBloom) {
     ro.total_order_seek = true;
     ASSERT_TRUE(db_->Get(ro, "foobarbar", &value).IsNotFound());
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 2);
+    ASSERT_EQ(
+        2,
+        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+    get_perf_context()->Reset();
   }
 }
 
@@ -235,6 +264,7 @@ TEST_F(DBBloomFilterTest, WholeKeyFilterProp) {
     Options options = last_options_;
     options.prefix_extractor.reset(NewFixedPrefixTransform(3));
     options.statistics = rocksdb::CreateDBStatistics();
+    get_perf_context()->EnablePerLevelPerfContext();
 
     BlockBasedTableOptions bbto;
     bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
@@ -382,6 +412,14 @@ TEST_F(DBBloomFilterTest, WholeKeyFilterProp) {
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
     ASSERT_EQ("bar", Get("barfoo"));
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 12);
+    uint64_t bloom_filter_useful_all_levels = 0;
+    for (auto& kv : (*(get_perf_context()->level_to_perf_context))) {
+      if (kv.second.bloom_filter_useful > 0) {
+        bloom_filter_useful_all_levels += kv.second.bloom_filter_useful;
+      }
+    }
+    ASSERT_EQ(12, bloom_filter_useful_all_levels);
+    get_perf_context()->Reset();
   }
 }
 
@@ -401,6 +439,11 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
       table_options.index_type =
           BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
     }
+    table_options.format_version = format_version_;
+    if (format_version_ >= 4) {
+      // value delta encoding challenged more with index interval > 1
+      table_options.index_block_restart_interval = 8;
+    }
     table_options.metadata_block_size = 32;
     options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
@@ -456,15 +499,34 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
   } while (ChangeCompactOptions());
 }
 
-INSTANTIATE_TEST_CASE_P(DBBloomFilterTestWithParam, DBBloomFilterTestWithParam,
-                        ::testing::Values(std::make_tuple(true, false),
-                                          std::make_tuple(false, true),
-                                          std::make_tuple(false, false)));
+#ifndef ROCKSDB_VALGRIND_RUN
+INSTANTIATE_TEST_CASE_P(
+    FormatDef, DBBloomFilterTestDefFormatVersion,
+    ::testing::Values(std::make_tuple(true, false, test::kDefaultFormatVersion),
+                      std::make_tuple(false, true, test::kDefaultFormatVersion),
+                      std::make_tuple(false, false,
+                                      test::kDefaultFormatVersion)));
+
+INSTANTIATE_TEST_CASE_P(
+    FormatDef, DBBloomFilterTestWithParam,
+    ::testing::Values(std::make_tuple(true, false, test::kDefaultFormatVersion),
+                      std::make_tuple(false, true, test::kDefaultFormatVersion),
+                      std::make_tuple(false, false,
+                                      test::kDefaultFormatVersion)));
+
+INSTANTIATE_TEST_CASE_P(
+    FormatLatest, DBBloomFilterTestWithParam,
+    ::testing::Values(std::make_tuple(true, false, test::kLatestFormatVersion),
+                      std::make_tuple(false, true, test::kLatestFormatVersion),
+                      std::make_tuple(false, false,
+                                      test::kLatestFormatVersion)));
+#endif  // ROCKSDB_VALGRIND_RUN
 
 TEST_F(DBBloomFilterTest, BloomFilterRate) {
   while (ChangeFilterOptions()) {
     Options options = CurrentOptions();
     options.statistics = rocksdb::CreateDBStatistics();
+    get_perf_context()->EnablePerLevelPerfContext();
     CreateAndReopenWithCF({"pikachu"}, options);
 
     const int maxKey = 10000;
@@ -486,6 +548,10 @@ TEST_F(DBBloomFilterTest, BloomFilterRate) {
       ASSERT_EQ("NOT_FOUND", Get(1, Key(i + 33333)));
     }
     ASSERT_GE(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), maxKey * 0.98);
+    ASSERT_GE(
+        (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful,
+        maxKey * 0.98);
+    get_perf_context()->Reset();
   }
 }
 
@@ -831,7 +897,7 @@ TEST_P(BloomStatsTestWithParam, BloomStatsTestWithIter) {
   ASSERT_OK(Put(key1, value1, WriteOptions()));
   ASSERT_OK(Put(key3, value3, WriteOptions()));
 
-  unique_ptr<Iterator> iter(dbfull()->NewIterator(ReadOptions()));
+  std::unique_ptr<Iterator> iter(dbfull()->NewIterator(ReadOptions()));
 
   // check memtable bloom stats
   iter->Seek(key1);
@@ -1007,6 +1073,7 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
   options.table_factory.reset(NewBlockBasedTableFactory(bbto));
   options.optimize_filters_for_hits = true;
   options.statistics = rocksdb::CreateDBStatistics();
+  get_perf_context()->EnablePerLevelPerfContext();
   CreateAndReopenWithCF({"mypikachu"}, options);
 
   int numkeys = 200000;
@@ -1053,6 +1120,14 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
   // no bloom filter. Most keys be checked bloom filters twice.
   ASSERT_GT(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 65000 * 2);
   ASSERT_LT(TestGetTickerCount(options, BLOOM_FILTER_USEFUL), 120000 * 2);
+  uint64_t bloom_filter_useful_all_levels = 0;
+  for (auto& kv : (*(get_perf_context()->level_to_perf_context))) {
+    if (kv.second.bloom_filter_useful > 0) {
+      bloom_filter_useful_all_levels += kv.second.bloom_filter_useful;
+    }
+  }
+  ASSERT_GT(bloom_filter_useful_all_levels, 65000 * 2);
+  ASSERT_LT(bloom_filter_useful_all_levels, 120000 * 2);
 
   for (int i = 0; i < numkeys; i += 2) {
     ASSERT_EQ(Get(1, Key(i)), "val");
@@ -1162,6 +1237,7 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
   ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
   ASSERT_EQ(2 /* index and data block */,
             TestGetTickerCount(options, BLOCK_CACHE_ADD));
+  get_perf_context()->Reset();
 }
 
 int CountIter(std::unique_ptr<Iterator>& iter, const Slice& key) {
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_compaction_filter_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_compaction_filter_test.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/db/db_compaction_filter_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_compaction_filter_test.cc
index 0c906948e6..63d2829d53 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_compaction_filter_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_compaction_filter_test.cc
@@ -340,9 +340,10 @@ TEST_F(DBTestCompactionFilter, CompactionFilter) {
   Arena arena;
   {
     InternalKeyComparator icmp(options.comparator);
-    RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
-    ScopedArenaIterator iter(
-        dbfull()->NewInternalIterator(&arena, &range_del_agg, handles_[1]));
+    ReadRangeDelAggregatorV2 range_del_agg(
+        &icmp, kMaxSequenceNumber /* upper_bound */);
+    ScopedArenaIterator iter(dbfull()->NewInternalIterator(
+        &arena, &range_del_agg, kMaxSequenceNumber, handles_[1]));
     iter->SeekToFirst();
     ASSERT_OK(iter->status());
     while (iter->Valid()) {
@@ -429,9 +430,10 @@ TEST_F(DBTestCompactionFilter, CompactionFilter) {
   count = 0;
   {
     InternalKeyComparator icmp(options.comparator);
-    RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
-    ScopedArenaIterator iter(
-        dbfull()->NewInternalIterator(&arena, &range_del_agg, handles_[1]));
+    ReadRangeDelAggregatorV2 range_del_agg(
+        &icmp, kMaxSequenceNumber /* upper_bound */);
+    ScopedArenaIterator iter(dbfull()->NewInternalIterator(
+        &arena, &range_del_agg, kMaxSequenceNumber, handles_[1]));
     iter->SeekToFirst();
     ASSERT_OK(iter->status());
     while (iter->Valid()) {
@@ -646,9 +648,10 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextManual) {
     int total = 0;
     Arena arena;
     InternalKeyComparator icmp(options.comparator);
-    RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
-    ScopedArenaIterator iter(
-        dbfull()->NewInternalIterator(&arena, &range_del_agg));
+    ReadRangeDelAggregatorV2 range_del_agg(&icmp,
+                                           kMaxSequenceNumber /* snapshots */);
+    ScopedArenaIterator iter(dbfull()->NewInternalIterator(
+        &arena, &range_del_agg, kMaxSequenceNumber));
     iter->SeekToFirst();
     ASSERT_OK(iter->status());
     while (iter->Valid()) {
@@ -848,7 +851,7 @@ TEST_F(DBTestCompactionFilter, SkipUntilWithBloomFilter) {
   DestroyAndReopen(options);
 
   Put("0000000010", "v10");
-  Put("0000000020", "v20"); // skipped
+  Put("0000000020", "v20");  // skipped
   Put("0000000050", "v50");
   Flush();
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_compaction_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_compaction_test.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/db/db_compaction_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_compaction_test.cc
index b28f5a2e51..f20be594e6 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_compaction_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_compaction_test.cc
@@ -8,11 +8,13 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
 #include "db/db_test_util.h"
-#include "port/stack_trace.h"
 #include "port/port.h"
+#include "port/stack_trace.h"
 #include "rocksdb/experimental.h"
 #include "rocksdb/utilities/convenience.h"
+#include "util/fault_injection_test_env.h"
 #include "util/sync_point.h"
+
 namespace rocksdb {
 
 // SYNC_POINT is not supported in released Windows mode.
@@ -116,6 +118,21 @@ private:
   std::vector<std::atomic<int>> compaction_completed_;
 };
 
+class SstStatsCollector : public EventListener {
+ public:
+  SstStatsCollector() : num_ssts_creation_started_(0) {}
+
+  void OnTableFileCreationStarted(
+      const TableFileCreationBriefInfo& /* info */) override {
+    ++num_ssts_creation_started_;
+  }
+
+  int num_ssts_creation_started() { return num_ssts_creation_started_; }
+
+ private:
+  std::atomic<int> num_ssts_creation_started_;
+};
+
 static const int kCDTValueSize = 1000;
 static const int kCDTKeysPerBuffer = 4;
 static const int kCDTNumLevels = 8;
@@ -2462,6 +2479,7 @@ TEST_P(DBCompactionTestWithParam, ManualLevelCompactionOutputPathId) {
 
     // Compaction range overlaps files
     Compact(1, "p1", "p9", 1);
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
     ASSERT_EQ("0,1", FilesPerLevel(1));
     ASSERT_EQ(1, GetSstFileCount(options.db_paths[1].path));
     ASSERT_EQ(0, GetSstFileCount(options.db_paths[0].path));
@@ -2477,6 +2495,7 @@ TEST_P(DBCompactionTestWithParam, ManualLevelCompactionOutputPathId) {
 
     // Compact just the new range
     Compact(1, "b", "f", 1);
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
     ASSERT_EQ("0,2", FilesPerLevel(1));
     ASSERT_EQ(2, GetSstFileCount(options.db_paths[1].path));
     ASSERT_EQ(0, GetSstFileCount(options.db_paths[0].path));
@@ -2493,6 +2512,7 @@ TEST_P(DBCompactionTestWithParam, ManualLevelCompactionOutputPathId) {
     compact_options.target_path_id = 1;
     compact_options.exclusive_manual_compaction = exclusive_manual_compaction_;
     db_->CompactRange(compact_options, handles_[1], nullptr, nullptr);
+    ASSERT_OK(dbfull()->TEST_WaitForCompact());
 
     ASSERT_EQ("0,1", FilesPerLevel(1));
     ASSERT_EQ(1, GetSstFileCount(options.db_paths[1].path));
@@ -2935,6 +2955,12 @@ TEST_F(DBCompactionTest, SuggestCompactRangeNoTwoLevel0Compactions) {
   dbfull()->TEST_WaitForCompact();
 }
 
+static std::string ShortKey(int i) {
+  assert(i < 10000);
+  char buf[100];
+  snprintf(buf, sizeof(buf), "key%04d", i);
+  return std::string(buf);
+}
 
 TEST_P(DBCompactionTestWithParam, ForceBottommostLevelCompaction) {
   int32_t trivial_move = 0;
@@ -2947,10 +2973,28 @@ TEST_P(DBCompactionTestWithParam, ForceBottommostLevelCompaction) {
       [&](void* /*arg*/) { non_trivial_move++; });
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
+  // The key size is guaranteed to be <= 8
+  class ShortKeyComparator : public Comparator {
+    int Compare(const rocksdb::Slice& a,
+                const rocksdb::Slice& b) const override {
+      assert(a.size() <= 8);
+      assert(b.size() <= 8);
+      return BytewiseComparator()->Compare(a, b);
+    }
+    const char* Name() const override { return "ShortKeyComparator"; }
+    void FindShortestSeparator(std::string* start,
+                               const rocksdb::Slice& limit) const override {
+      return BytewiseComparator()->FindShortestSeparator(start, limit);
+    }
+    void FindShortSuccessor(std::string* key) const override {
+      return BytewiseComparator()->FindShortSuccessor(key);
+    }
+  } short_key_cmp;
   Options options = CurrentOptions();
   options.target_file_size_base = 100000000;
   options.write_buffer_size = 100000000;
   options.max_subcompactions = max_subcompactions_;
+  options.comparator = &short_key_cmp;
   DestroyAndReopen(options);
 
   int32_t value_size = 10 * 1024;  // 10 KB
@@ -2960,7 +3004,7 @@ TEST_P(DBCompactionTestWithParam, ForceBottommostLevelCompaction) {
   // File with keys [ 0 => 99 ]
   for (int i = 0; i < 100; i++) {
     values.push_back(RandomString(&rnd, value_size));
-    ASSERT_OK(Put(Key(i), values[i]));
+    ASSERT_OK(Put(ShortKey(i), values[i]));
   }
   ASSERT_OK(Flush());
 
@@ -2977,7 +3021,7 @@ TEST_P(DBCompactionTestWithParam, ForceBottommostLevelCompaction) {
   // File with keys [ 100 => 199 ]
   for (int i = 100; i < 200; i++) {
     values.push_back(RandomString(&rnd, value_size));
-    ASSERT_OK(Put(Key(i), values[i]));
+    ASSERT_OK(Put(ShortKey(i), values[i]));
   }
   ASSERT_OK(Flush());
 
@@ -2995,7 +3039,7 @@ TEST_P(DBCompactionTestWithParam, ForceBottommostLevelCompaction) {
   // File with keys [ 200 => 299 ]
   for (int i = 200; i < 300; i++) {
     values.push_back(RandomString(&rnd, value_size));
-    ASSERT_OK(Put(Key(i), values[i]));
+    ASSERT_OK(Put(ShortKey(i), values[i]));
   }
   ASSERT_OK(Flush());
 
@@ -3013,7 +3057,7 @@ TEST_P(DBCompactionTestWithParam, ForceBottommostLevelCompaction) {
   ASSERT_EQ(non_trivial_move, 0);
 
   for (int i = 0; i < 300; i++) {
-    ASSERT_EQ(Get(Key(i)), values[i]);
+    ASSERT_EQ(Get(ShortKey(i)), values[i]);
   }
 
   rocksdb::SyncPoint::GetInstance()->DisableProcessing();
@@ -3485,12 +3529,13 @@ TEST_F(DBCompactionTest, CompactRangeDelayedByL0FileCount) {
       // ensure the auto compaction doesn't finish until manual compaction has
       // had a chance to be delayed.
       rocksdb::SyncPoint::GetInstance()->LoadDependency(
-          {{"DBImpl::CompactRange:StallWait", "CompactionJob::Run():End"}});
+          {{"DBImpl::WaitUntilFlushWouldNotStallWrites:StallWait",
+            "CompactionJob::Run():End"}});
     } else {
       // ensure the auto-compaction doesn't finish until manual compaction has
       // continued without delay.
       rocksdb::SyncPoint::GetInstance()->LoadDependency(
-          {{"DBImpl::CompactRange:StallWaitDone", "CompactionJob::Run():End"}});
+          {{"DBImpl::FlushMemTable:StallWaitDone", "CompactionJob::Run():End"}});
     }
     rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
@@ -3538,12 +3583,13 @@ TEST_F(DBCompactionTest, CompactRangeDelayedByImmMemTableCount) {
       // ensure the flush doesn't finish until manual compaction has had a
       // chance to be delayed.
       rocksdb::SyncPoint::GetInstance()->LoadDependency(
-          {{"DBImpl::CompactRange:StallWait", "FlushJob::WriteLevel0Table"}});
+          {{"DBImpl::WaitUntilFlushWouldNotStallWrites:StallWait",
+            "FlushJob::WriteLevel0Table"}});
     } else {
       // ensure the flush doesn't finish until manual compaction has continued
       // without delay.
       rocksdb::SyncPoint::GetInstance()->LoadDependency(
-          {{"DBImpl::CompactRange:StallWaitDone",
+          {{"DBImpl::FlushMemTable:StallWaitDone",
             "FlushJob::WriteLevel0Table"}});
     }
     rocksdb::SyncPoint::GetInstance()->EnableProcessing();
@@ -3553,6 +3599,7 @@ TEST_F(DBCompactionTest, CompactRangeDelayedByImmMemTableCount) {
       ASSERT_OK(Put(Key(0), RandomString(&rnd, 1024)));
       FlushOptions flush_opts;
       flush_opts.wait = false;
+      flush_opts.allow_write_stall = true;
       dbfull()->Flush(flush_opts);
     }
 
@@ -3588,7 +3635,7 @@ TEST_F(DBCompactionTest, CompactRangeShutdownWhileDelayed) {
     // The auto-compaction waits until the manual compaction finishes to ensure
     // the signal comes from closing CF/DB, not from compaction making progress.
     rocksdb::SyncPoint::GetInstance()->LoadDependency(
-        {{"DBImpl::CompactRange:StallWait",
+        {{"DBImpl::WaitUntilFlushWouldNotStallWrites:StallWait",
           "DBCompactionTest::CompactRangeShutdownWhileDelayed:PreShutdown"},
          {"DBCompactionTest::CompactRangeShutdownWhileDelayed:PostManual",
           "CompactionJob::Run():End"}});
@@ -3639,18 +3686,21 @@ TEST_F(DBCompactionTest, CompactRangeSkipFlushAfterDelay) {
   // began. So it unblocks CompactRange and precludes its flush. Throughout the
   // test, stall conditions are upheld via high L0 file count.
   rocksdb::SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::CompactRange:StallWait",
+      {{"DBImpl::WaitUntilFlushWouldNotStallWrites:StallWait",
         "DBCompactionTest::CompactRangeSkipFlushAfterDelay:PreFlush"},
        {"DBCompactionTest::CompactRangeSkipFlushAfterDelay:PostFlush",
-        "DBImpl::CompactRange:StallWaitDone"},
-       {"DBImpl::CompactRange:StallWaitDone", "CompactionJob::Run():End"}});
+        "DBImpl::FlushMemTable:StallWaitDone"},
+       {"DBImpl::FlushMemTable:StallWaitDone", "CompactionJob::Run():End"}});
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
+  //used for the delayable flushes
+  FlushOptions flush_opts;
+  flush_opts.allow_write_stall = true;
   for (int i = 0; i < kNumL0FilesLimit - 1; ++i) {
     for (int j = 0; j < 2; ++j) {
       ASSERT_OK(Put(Key(j), RandomString(&rnd, 1024)));
     }
-    Flush();
+    dbfull()->Flush(flush_opts);
   }
   auto manual_compaction_thread = port::Thread([this]() {
     CompactRangeOptions cro;
@@ -3660,7 +3710,7 @@ TEST_F(DBCompactionTest, CompactRangeSkipFlushAfterDelay) {
 
   TEST_SYNC_POINT("DBCompactionTest::CompactRangeSkipFlushAfterDelay:PreFlush");
   Put(ToString(0), RandomString(&rnd, 1024));
-  Flush();
+  dbfull()->Flush(flush_opts);
   Put(ToString(0), RandomString(&rnd, 1024));
   TEST_SYNC_POINT("DBCompactionTest::CompactRangeSkipFlushAfterDelay:PostFlush");
   manual_compaction_thread.join();
@@ -3816,6 +3866,30 @@ TEST_F(DBCompactionTest, CompactFilesOutputRangeConflict) {
   bg_thread.join();
 }
 
+TEST_F(DBCompactionTest, CompactionHasEmptyOutput) {
+  Options options = CurrentOptions();
+  SstStatsCollector* collector = new SstStatsCollector();
+  options.level0_file_num_compaction_trigger = 2;
+  options.listeners.emplace_back(collector);
+  Reopen(options);
+
+  // Make sure the L0 files overlap to prevent trivial move.
+  ASSERT_OK(Put("a", "val"));
+  ASSERT_OK(Put("b", "val"));
+  ASSERT_OK(Flush());
+  ASSERT_OK(Delete("a"));
+  ASSERT_OK(Delete("b"));
+  ASSERT_OK(Flush());
+
+  dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(NumTableFilesAtLevel(0), 0);
+  ASSERT_EQ(NumTableFilesAtLevel(1), 0);
+
+  // Expect one file creation to start for each flush, and zero for compaction
+  // since no keys are written.
+  ASSERT_EQ(2, collector->num_ssts_creation_started());
+}
+
 INSTANTIATE_TEST_CASE_P(DBCompactionTestWithParam, DBCompactionTestWithParam,
                         ::testing::Values(std::make_tuple(1, true),
                                           std::make_tuple(1, false),
@@ -3913,6 +3987,167 @@ INSTANTIATE_TEST_CASE_P(
                       CompactionPri::kOldestSmallestSeqFirst,
                       CompactionPri::kMinOverlappingRatio));
 
+class NoopMergeOperator : public MergeOperator {
+ public:
+  NoopMergeOperator() {}
+
+  virtual bool FullMergeV2(const MergeOperationInput& /*merge_in*/,
+                           MergeOperationOutput* merge_out) const override {
+    std::string val("bar");
+    merge_out->new_value = val;
+    return true;
+  }
+
+  virtual const char* Name() const override { return "Noop"; }
+};
+
+TEST_F(DBCompactionTest, PartialManualCompaction) {
+  Options opts = CurrentOptions();
+  opts.num_levels = 3;
+  opts.level0_file_num_compaction_trigger = 10;
+  opts.compression = kNoCompression;
+  opts.merge_operator.reset(new NoopMergeOperator());
+  opts.target_file_size_base = 10240;
+  DestroyAndReopen(opts);
+
+  Random rnd(301);
+  for (auto i = 0; i < 8; ++i) {
+    for (auto j = 0; j < 10; ++j) {
+      Merge("foo", RandomString(&rnd, 1024));
+    }
+    Flush();
+  }
+
+  MoveFilesToLevel(2);
+
+  std::string prop;
+  EXPECT_TRUE(dbfull()->GetProperty(DB::Properties::kLiveSstFilesSize, &prop));
+  uint64_t max_compaction_bytes = atoi(prop.c_str()) / 2;
+  ASSERT_OK(dbfull()->SetOptions(
+      {{"max_compaction_bytes", std::to_string(max_compaction_bytes)}}));
+
+  CompactRangeOptions cro;
+  cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
+  dbfull()->CompactRange(cro, nullptr, nullptr);
+}
+
+TEST_F(DBCompactionTest, ManualCompactionFailsInReadOnlyMode) {
+  // Regression test for bug where manual compaction hangs forever when the DB
+  // is in read-only mode. Verify it now at least returns, despite failing.
+  const int kNumL0Files = 4;
+  std::unique_ptr<FaultInjectionTestEnv> mock_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  Options opts = CurrentOptions();
+  opts.disable_auto_compactions = true;
+  opts.env = mock_env.get();
+  DestroyAndReopen(opts);
+
+  Random rnd(301);
+  for (int i = 0; i < kNumL0Files; ++i) {
+    // Make sure files are overlapping in key-range to prevent trivial move.
+    Put("key1", RandomString(&rnd, 1024));
+    Put("key2", RandomString(&rnd, 1024));
+    Flush();
+  }
+  ASSERT_EQ(kNumL0Files, NumTableFilesAtLevel(0));
+
+  // Enter read-only mode by failing a write.
+  mock_env->SetFilesystemActive(false);
+  // Make sure this is outside `CompactRange`'s range so that it doesn't fail
+  // early trying to flush memtable.
+  ASSERT_NOK(Put("key3", RandomString(&rnd, 1024)));
+
+  // In the bug scenario, the first manual compaction would fail and forget to
+  // unregister itself, causing the second one to hang forever due to conflict
+  // with a non-running compaction.
+  CompactRangeOptions cro;
+  cro.exclusive_manual_compaction = false;
+  Slice begin_key("key1");
+  Slice end_key("key2");
+  ASSERT_NOK(dbfull()->CompactRange(cro, &begin_key, &end_key));
+  ASSERT_NOK(dbfull()->CompactRange(cro, &begin_key, &end_key));
+
+  // Close before mock_env destruct.
+  Close();
+}
+
+// FixFileIngestionCompactionDeadlock tests and verifies that compaction and
+// file ingestion do not cause deadlock in the event of write stall triggered
+// by number of L0 files reaching level0_stop_writes_trigger.
+TEST_P(DBCompactionTestWithParam, FixFileIngestionCompactionDeadlock) {
+  const int kNumKeysPerFile = 100;
+  // Generate SST files.
+  Options options = CurrentOptions();
+
+  // Generate an external SST file containing a single key, i.e. 99
+  std::string sst_files_dir = dbname_ + "/sst_files/";
+  test::DestroyDir(env_, sst_files_dir);
+  ASSERT_OK(env_->CreateDir(sst_files_dir));
+  SstFileWriter sst_writer(EnvOptions(), options);
+  const std::string sst_file_path = sst_files_dir + "test.sst";
+  ASSERT_OK(sst_writer.Open(sst_file_path));
+  ASSERT_OK(sst_writer.Put(Key(kNumKeysPerFile - 1), "value"));
+  ASSERT_OK(sst_writer.Finish());
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+  SyncPoint::GetInstance()->LoadDependency({
+      {"DBImpl::IngestExternalFile:AfterIncIngestFileCounter",
+       "BackgroundCallCompaction:0"},
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  options.write_buffer_size = 110 << 10;  // 110KB
+  options.level0_file_num_compaction_trigger =
+      options.level0_stop_writes_trigger;
+  options.max_subcompactions = max_subcompactions_;
+  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
+  DestroyAndReopen(options);
+  Random rnd(301);
+
+  // Generate level0_stop_writes_trigger L0 files to trigger write stop
+  for (int i = 0; i != options.level0_file_num_compaction_trigger; ++i) {
+    for (int j = 0; j != kNumKeysPerFile; ++j) {
+      ASSERT_OK(Put(Key(j), RandomString(&rnd, 990)));
+    }
+    if (0 == i) {
+      // When we reach here, the memtables have kNumKeysPerFile keys. Note that
+      // flush is not yet triggered. We need to write an extra key so that the
+      // write path will call PreprocessWrite and flush the previous key-value
+      // pairs to e flushed. After that, there will be the newest key in the
+      // memtable, and a bunch of L0 files. Since there is already one key in
+      // the memtable, then for i = 1, 2, ..., we do not have to write this
+      // extra key to trigger flush.
+      ASSERT_OK(Put("", ""));
+    }
+    dbfull()->TEST_WaitForFlushMemTable();
+    ASSERT_EQ(NumTableFilesAtLevel(0 /*level*/, 0 /*cf*/), i + 1);
+  }
+  // When we reach this point, there will be level0_stop_writes_trigger L0
+  // files and one extra key (99) in memory, which overlaps with the external
+  // SST file. Write stall triggers, and can be cleared only after compaction
+  // reduces the number of L0 files.
+
+  // Compaction will also be triggered since we have reached the threshold for
+  // auto compaction. Note that compaction may begin after the following file
+  // ingestion thread and waits for ingestion to finish.
+
+  // Thread to ingest file with overlapping key range with the current
+  // memtable. Consequently ingestion will trigger a flush. The flush MUST
+  // proceed without waiting for the write stall condition to clear, otherwise
+  // deadlock can happen.
+  port::Thread ingestion_thr([&]() {
+    IngestExternalFileOptions ifo;
+    Status s = db_->IngestExternalFile({sst_file_path}, ifo);
+    ASSERT_OK(s);
+  });
+
+  // More write to trigger write stop
+  ingestion_thr.join();
+  ASSERT_OK(dbfull()->TEST_WaitForCompact());
+  Close();
+}
+
 #endif // !defined(ROCKSDB_LITE)
 }  // namespace rocksdb
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_dynamic_level_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_dynamic_level_test.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/db/db_dynamic_level_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_dynamic_level_test.cc
index 3f33027d1c..8fac82851e 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_dynamic_level_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_dynamic_level_test.cc
@@ -27,7 +27,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase) {
     return;
   }
   // Use InMemoryEnv, or it would be too slow.
-  unique_ptr<Env> env(new MockEnv(env_));
+  std::unique_ptr<Env> env(new MockEnv(env_));
 
   const int kNKeys = 1000;
   int keys[kNKeys];
@@ -125,6 +125,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
   int kMaxKey = 1000000;
 
   Options options = CurrentOptions();
+  options.compression = kNoCompression;
   options.create_if_missing = true;
   options.write_buffer_size = 20480;
   options.max_write_buffer_number = 2;
@@ -167,8 +168,8 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
   ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
   ASSERT_EQ(4U, int_prop);
 
-  // Insert extra about 28K to L0. After they are compacted to L4, base level
-  // should be changed to L3.
+  // Insert extra about 28K to L0. After they are compacted to L4, the base
+  // level should be changed to L3.
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "true"},
   }));
@@ -189,13 +190,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
   ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level2", &str_prop));
   ASSERT_EQ("0", str_prop);
 
-  // Trigger parallel compaction, and the first one would change the base
-  // level.
-  // Hold compaction jobs to make sure
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionJob::Run():Start",
-      [&](void* /*arg*/) { env_->SleepForMicroseconds(100000); });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  // Write even more data while leaving the base level at L3.
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "true"},
   }));
@@ -208,18 +203,12 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
       {"disable_auto_compactions", "false"},
   }));
   Flush();
-  // Wait for 200 milliseconds before proceeding compactions to make sure two
-  // parallel ones are executed.
-  env_->SleepForMicroseconds(200000);
   dbfull()->TEST_WaitForCompact();
   ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
   ASSERT_EQ(3U, int_prop);
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 
-  // Trigger a condition that the compaction changes base level and L0->Lbase
-  // happens at the same time.
-  // We try to make last levels' targets to be 40K, 160K, 640K, add triggers
-  // another compaction from 40K->160K.
+  // Fill up L0, and then run an (auto) L0->Lmax compaction to raise the base
+  // level to 2.
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "true"},
   }));
@@ -229,23 +218,31 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
     ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
                   RandomString(&rnd, 380)));
   }
+
+  // Make sure that the compaction starts before the last bit of data is
+  // flushed, so that the base level isn't raised to L1.
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
+      {"CompactionJob::Run():Start", "DynamicLevelMaxBytesBase2:0"},
+  });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "false"},
   }));
+
+  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:0");
   Flush();
   dbfull()->TEST_WaitForCompact();
   ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
   ASSERT_EQ(2U, int_prop);
-
-  // A manual compaction will trigger the base level to become L2
-  // Keep Writing data until base level changed 2->1. There will be L0->L2
-  // compaction going on at the same time.
   rocksdb::SyncPoint::GetInstance()->DisableProcessing();
   rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 
+  // Write more data until the base level changes to L1. There will be
+  // a manual compaction going on at the same time.
   rocksdb::SyncPoint::GetInstance()->LoadDependency({
-      {"CompactionJob::Run():Start", "DynamicLevelMaxBytesBase2:0"},
-      {"DynamicLevelMaxBytesBase2:1", "CompactionJob::Run():End"},
+      {"CompactionJob::Run():Start", "DynamicLevelMaxBytesBase2:1"},
+      {"DynamicLevelMaxBytesBase2:2", "CompactionJob::Run():End"},
       {"DynamicLevelMaxBytesBase2:compact_range_finish",
        "FlushJob::WriteLevel0Table"},
   });
@@ -257,12 +254,12 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
     TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:compact_range_finish");
   });
 
-  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:0");
+  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:1");
   for (int i = 0; i < 2; i++) {
     ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
                   RandomString(&rnd, 380)));
   }
-  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:1");
+  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:2");
 
   Flush();
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_encryption_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_encryption_test.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/db_encryption_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_encryption_test.cc
index 38eee56459..46ba411b6f 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_encryption_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_encryption_test.cc
@@ -40,7 +40,7 @@ TEST_F(DBEncryptionTest, CheckEncrypted) {
       continue;
     }
     auto filePath = dbname_ + "/" + *it;
-    unique_ptr<SequentialFile> seqFile;
+    std::unique_ptr<SequentialFile> seqFile;
     auto envOptions = EnvOptions(CurrentOptions());
     status = defaultEnv->NewSequentialFile(filePath, &seqFile, envOptions);
     ASSERT_OK(status);
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_filesnapshot.cc b/3rdParty/rocksdb/v5.18.X/db/db_filesnapshot.cc
similarity index 78%
rename from 3rdParty/rocksdb/v5.16.X/db/db_filesnapshot.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_filesnapshot.cc
index 010f9fbe8f..ace0befb6d 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_filesnapshot.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_filesnapshot.cc
@@ -44,7 +44,7 @@ Status DBImpl::EnableFileDeletions(bool force) {
   // Job id == 0 means that this is not our background process, but rather
   // user thread
   JobContext job_context(0);
-  bool should_purge_files = false;
+  bool file_deletion_enabled = false;
   {
     InstrumentedMutexLock l(&mutex_);
     if (force) {
@@ -54,19 +54,18 @@ Status DBImpl::EnableFileDeletions(bool force) {
       --disable_delete_obsolete_files_;
     }
     if (disable_delete_obsolete_files_ == 0)  {
-      ROCKS_LOG_INFO(immutable_db_options_.info_log, "File Deletions Enabled");
-      should_purge_files = true;
+      file_deletion_enabled = true;
       FindObsoleteFiles(&job_context, true);
       bg_cv_.SignalAll();
-    } else {
-      ROCKS_LOG_WARN(
-          immutable_db_options_.info_log,
-          "File Deletions Enable, but not really enabled. Counter: %d",
-          disable_delete_obsolete_files_);
     }
   }
-  if (should_purge_files)  {
+  if (file_deletion_enabled) {
+    ROCKS_LOG_INFO(immutable_db_options_.info_log, "File Deletions Enabled");
     PurgeObsoleteFiles(job_context);
+  } else {
+    ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                   "File Deletions Enable, but not really enabled. Counter: %d",
+                   disable_delete_obsolete_files_);
   }
   job_context.Clean();
   LogFlush(immutable_db_options_.info_log);
@@ -87,19 +86,28 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
   if (flush_memtable) {
     // flush all dirty data to disk.
     Status status;
-    for (auto cfd : *versions_->GetColumnFamilySet()) {
-      if (cfd->IsDropped()) {
-        continue;
-      }
-      cfd->Ref();
+    if (immutable_db_options_.atomic_flush) {
+      autovector<ColumnFamilyData*> cfds;
+      SelectColumnFamiliesForAtomicFlush(&cfds);
       mutex_.Unlock();
-      status = FlushMemTable(cfd, FlushOptions(), FlushReason::kGetLiveFiles);
-      TEST_SYNC_POINT("DBImpl::GetLiveFiles:1");
-      TEST_SYNC_POINT("DBImpl::GetLiveFiles:2");
+      status = AtomicFlushMemTables(cfds, FlushOptions(),
+                                    FlushReason::kGetLiveFiles);
       mutex_.Lock();
-      cfd->Unref();
-      if (!status.ok()) {
-        break;
+    } else {
+      for (auto cfd : *versions_->GetColumnFamilySet()) {
+        if (cfd->IsDropped()) {
+          continue;
+        }
+        cfd->Ref();
+        mutex_.Unlock();
+        status = FlushMemTable(cfd, FlushOptions(), FlushReason::kGetLiveFiles);
+        TEST_SYNC_POINT("DBImpl::GetLiveFiles:1");
+        TEST_SYNC_POINT("DBImpl::GetLiveFiles:2");
+        mutex_.Lock();
+        cfd->Unref();
+        if (!status.ok()) {
+          break;
+        }
       }
     }
     versions_->GetColumnFamilySet()->FreeDeadColumnFamilies();
@@ -126,7 +134,7 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
 
   // create names of the live files. The names are not absolute
   // paths, instead they are relative to dbname_;
-  for (auto live_file : live) {
+  for (const auto& live_file : live) {
     ret.push_back(MakeTableFileName("", live_file.GetNumber()));
   }
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_flush_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_flush_test.cc
similarity index 51%
rename from 3rdParty/rocksdb/v5.16.X/db/db_flush_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_flush_test.cc
index a9c5a19a3d..e9ae980b91 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_flush_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_flush_test.cc
@@ -25,6 +25,12 @@ class DBFlushDirectIOTest : public DBFlushTest,
   DBFlushDirectIOTest() : DBFlushTest() {}
 };
 
+class DBAtomicFlushTest : public DBFlushTest,
+                          public ::testing::WithParamInterface<bool> {
+ public:
+  DBAtomicFlushTest() : DBFlushTest() {}
+};
+
 // We had issue when two background threads trying to flush at the same time,
 // only one of them get committed. The test verifies the issue is fixed.
 TEST_F(DBFlushTest, FlushWhileWritingManifest) {
@@ -35,11 +41,12 @@ TEST_F(DBFlushTest, FlushWhileWritingManifest) {
   Reopen(options);
   FlushOptions no_wait;
   no_wait.wait = false;
+  no_wait.allow_write_stall=true;
 
   SyncPoint::GetInstance()->LoadDependency(
       {{"VersionSet::LogAndApply:WriteManifest",
         "DBFlushTest::FlushWhileWritingManifest:1"},
-       {"MemTableList::InstallMemtableFlushResults:InProgress",
+       {"MemTableList::TryInstallMemtableFlushResults:InProgress",
         "VersionSet::LogAndApply:WriteManifestDone"}});
   SyncPoint::GetInstance()->EnableProcessing();
 
@@ -55,7 +62,6 @@ TEST_F(DBFlushTest, FlushWhileWritingManifest) {
 #endif  // ROCKSDB_LITE
 }
 
-#ifndef TRAVIS
 // Disable this test temporarily on Travis as it fails intermittently.
 // Github issue: #4151
 TEST_F(DBFlushTest, SyncFail) {
@@ -66,11 +72,15 @@ TEST_F(DBFlushTest, SyncFail) {
   options.env = fault_injection_env.get();
 
   SyncPoint::GetInstance()->LoadDependency(
-      {{"DBFlushTest::SyncFail:1", "DBImpl::SyncClosedLogs:Start"},
+      {{"DBFlushTest::SyncFail:GetVersionRefCount:1",
+        "DBImpl::FlushMemTableToOutputFile:BeforePickMemtables"},
+       {"DBImpl::FlushMemTableToOutputFile:AfterPickMemtables",
+        "DBFlushTest::SyncFail:GetVersionRefCount:2"},
+       {"DBFlushTest::SyncFail:1", "DBImpl::SyncClosedLogs:Start"},
        {"DBImpl::SyncClosedLogs:Failed", "DBFlushTest::SyncFail:2"}});
   SyncPoint::GetInstance()->EnableProcessing();
 
-  Reopen(options);
+  CreateAndReopenWithCF({"pikachu"}, options);
   Put("key", "value");
   auto* cfd =
       reinterpret_cast<ColumnFamilyHandleImpl*>(db_->DefaultColumnFamily())
@@ -81,6 +91,10 @@ TEST_F(DBFlushTest, SyncFail) {
   // Flush installs a new super-version. Get the ref count after that.
   auto current_before = cfd->current();
   int refs_before = cfd->current()->TEST_refs();
+  TEST_SYNC_POINT("DBFlushTest::SyncFail:GetVersionRefCount:1");
+  TEST_SYNC_POINT("DBFlushTest::SyncFail:GetVersionRefCount:2");
+  int refs_after_picking_memtables = cfd->current()->TEST_refs();
+  ASSERT_EQ(refs_before + 1, refs_after_picking_memtables);
   fault_injection_env->SetFilesystemActive(false);
   TEST_SYNC_POINT("DBFlushTest::SyncFail:1");
   TEST_SYNC_POINT("DBFlushTest::SyncFail:2");
@@ -95,7 +109,30 @@ TEST_F(DBFlushTest, SyncFail) {
   ASSERT_EQ(refs_before, cfd->current()->TEST_refs());
   Destroy(options);
 }
-#endif  // TRAVIS
+
+TEST_F(DBFlushTest, SyncSkip) {
+  Options options = CurrentOptions();
+
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"DBFlushTest::SyncSkip:1", "DBImpl::SyncClosedLogs:Skip"},
+       {"DBImpl::SyncClosedLogs:Skip", "DBFlushTest::SyncSkip:2"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  Reopen(options);
+  Put("key", "value");
+
+  FlushOptions flush_options;
+  flush_options.wait = false;
+  ASSERT_OK(dbfull()->Flush(flush_options));
+
+  TEST_SYNC_POINT("DBFlushTest::SyncSkip:1");
+  TEST_SYNC_POINT("DBFlushTest::SyncSkip:2");
+
+  // Now the background job will do the flush; wait for it.
+  dbfull()->TEST_WaitForFlushMemTable();
+
+  Destroy(options);
+}
 
 TEST_F(DBFlushTest, FlushInLowPriThreadPool) {
   // Verify setting an empty high-pri (flush) thread pool causes flushes to be
@@ -213,9 +250,168 @@ TEST_F(DBFlushTest, FlushError) {
   ASSERT_NE(s, Status::OK());
 }
 
+TEST_F(DBFlushTest, ManualFlushFailsInReadOnlyMode) {
+  // Regression test for bug where manual flush hangs forever when the DB
+  // is in read-only mode. Verify it now at least returns, despite failing.
+  Options options;
+  std::unique_ptr<FaultInjectionTestEnv> fault_injection_env(
+      new FaultInjectionTestEnv(env_));
+  options.env = fault_injection_env.get();
+  options.max_write_buffer_number = 2;
+  Reopen(options);
+
+  // Trigger a first flush but don't let it run
+  ASSERT_OK(db_->PauseBackgroundWork());
+  ASSERT_OK(Put("key1", "value1"));
+  FlushOptions flush_opts;
+  flush_opts.wait = false;
+  ASSERT_OK(db_->Flush(flush_opts));
+
+  // Write a key to the second memtable so we have something to flush later
+  // after the DB is in read-only mode.
+  ASSERT_OK(Put("key2", "value2"));
+
+  // Let the first flush continue, hit an error, and put the DB in read-only
+  // mode.
+  fault_injection_env->SetFilesystemActive(false);
+  ASSERT_OK(db_->ContinueBackgroundWork());
+  dbfull()->TEST_WaitForFlushMemTable();
+#ifndef ROCKSDB_LITE
+  uint64_t num_bg_errors;
+  ASSERT_TRUE(db_->GetIntProperty(DB::Properties::kBackgroundErrors,
+                                  &num_bg_errors));
+  ASSERT_GT(num_bg_errors, 0);
+#endif  // ROCKSDB_LITE
+
+  // In the bug scenario, triggering another flush would cause the second flush
+  // to hang forever. After the fix we expect it to return an error.
+  ASSERT_NOK(db_->Flush(FlushOptions()));
+
+  Close();
+}
+
+TEST_P(DBAtomicFlushTest, ManualAtomicFlush) {
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.atomic_flush = GetParam();
+  options.write_buffer_size = (static_cast<size_t>(64) << 20);
+
+  CreateAndReopenWithCF({"pikachu", "eevee"}, options);
+  size_t num_cfs = handles_.size();
+  ASSERT_EQ(3, num_cfs);
+  WriteOptions wopts;
+  wopts.disableWAL = true;
+  for (size_t i = 0; i != num_cfs; ++i) {
+    ASSERT_OK(Put(static_cast<int>(i) /*cf*/, "key", "value", wopts));
+  }
+  std::vector<int> cf_ids;
+  for (size_t i = 0; i != num_cfs; ++i) {
+    cf_ids.emplace_back(static_cast<int>(i));
+  }
+  ASSERT_OK(Flush(cf_ids));
+  for (size_t i = 0; i != num_cfs; ++i) {
+    auto cfh = static_cast<ColumnFamilyHandleImpl*>(handles_[i]);
+    ASSERT_EQ(0, cfh->cfd()->imm()->NumNotFlushed());
+    ASSERT_TRUE(cfh->cfd()->mem()->IsEmpty());
+  }
+}
+
+TEST_P(DBAtomicFlushTest, AtomicFlushTriggeredByMemTableFull) {
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.atomic_flush = GetParam();
+  // 4KB so that we can easily trigger auto flush.
+  options.write_buffer_size = 4096;
+
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::BackgroundCallFlush:FlushFinish:0",
+        "DBAtomicFlushTest::AtomicFlushTriggeredByMemTableFull:BeforeCheck"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  CreateAndReopenWithCF({"pikachu", "eevee"}, options);
+  size_t num_cfs = handles_.size();
+  ASSERT_EQ(3, num_cfs);
+  WriteOptions wopts;
+  wopts.disableWAL = true;
+  for (size_t i = 0; i != num_cfs; ++i) {
+    ASSERT_OK(Put(static_cast<int>(i) /*cf*/, "key", "value", wopts));
+  }
+  // Keep writing to one of them column families to trigger auto flush.
+  for (int i = 0; i != 4000; ++i) {
+    ASSERT_OK(Put(static_cast<int>(num_cfs) - 1 /*cf*/,
+                  "key" + std::to_string(i), "value" + std::to_string(i),
+                  wopts));
+  }
+
+  TEST_SYNC_POINT(
+      "DBAtomicFlushTest::AtomicFlushTriggeredByMemTableFull:BeforeCheck");
+  if (options.atomic_flush) {
+    for (size_t i = 0; i != num_cfs - 1; ++i) {
+      auto cfh = static_cast<ColumnFamilyHandleImpl*>(handles_[i]);
+      ASSERT_EQ(0, cfh->cfd()->imm()->NumNotFlushed());
+      ASSERT_TRUE(cfh->cfd()->mem()->IsEmpty());
+    }
+  } else {
+    for (size_t i = 0; i != num_cfs - 1; ++i) {
+      auto cfh = static_cast<ColumnFamilyHandleImpl*>(handles_[i]);
+      ASSERT_EQ(0, cfh->cfd()->imm()->NumNotFlushed());
+      ASSERT_FALSE(cfh->cfd()->mem()->IsEmpty());
+    }
+  }
+  SyncPoint::GetInstance()->DisableProcessing();
+}
+
+TEST_P(DBAtomicFlushTest, AtomicFlushRollbackSomeJobs) {
+  bool atomic_flush = GetParam();
+  if (!atomic_flush) {
+    return;
+  }
+  std::unique_ptr<FaultInjectionTestEnv> fault_injection_env(
+      new FaultInjectionTestEnv(env_));
+  Options options = CurrentOptions();
+  options.create_if_missing = true;
+  options.atomic_flush = atomic_flush;
+  options.env = fault_injection_env.get();
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"DBImpl::AtomicFlushMemTablesToOutputFiles:SomeFlushJobsComplete:1",
+        "DBAtomicFlushTest::AtomicFlushRollbackSomeJobs:1"},
+       {"DBAtomicFlushTest::AtomicFlushRollbackSomeJobs:2",
+        "DBImpl::AtomicFlushMemTablesToOutputFiles:SomeFlushJobsComplete:2"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  CreateAndReopenWithCF({"pikachu", "eevee"}, options);
+  size_t num_cfs = handles_.size();
+  ASSERT_EQ(3, num_cfs);
+  WriteOptions wopts;
+  wopts.disableWAL = true;
+  for (size_t i = 0; i != num_cfs; ++i) {
+    int cf_id = static_cast<int>(i);
+    ASSERT_OK(Put(cf_id, "key", "value", wopts));
+  }
+  FlushOptions flush_opts;
+  flush_opts.wait = false;
+  ASSERT_OK(dbfull()->Flush(flush_opts, handles_));
+  TEST_SYNC_POINT("DBAtomicFlushTest::AtomicFlushRollbackSomeJobs:1");
+  fault_injection_env->SetFilesystemActive(false);
+  TEST_SYNC_POINT("DBAtomicFlushTest::AtomicFlushRollbackSomeJobs:2");
+  for (auto* cfh : handles_) {
+    dbfull()->TEST_WaitForFlushMemTable(cfh);
+  }
+  for (size_t i = 0; i != num_cfs; ++i) {
+    auto cfh = static_cast<ColumnFamilyHandleImpl*>(handles_[i]);
+    ASSERT_EQ(1, cfh->cfd()->imm()->NumNotFlushed());
+    ASSERT_TRUE(cfh->cfd()->mem()->IsEmpty());
+  }
+  fault_injection_env->SetFilesystemActive(true);
+  Destroy(options);
+}
+
 INSTANTIATE_TEST_CASE_P(DBFlushDirectIOTest, DBFlushDirectIOTest,
                         testing::Bool());
 
+INSTANTIATE_TEST_CASE_P(DBAtomicFlushTest, DBAtomicFlushTest, testing::Bool());
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_impl.cc b/3rdParty/rocksdb/v5.18.X/db/db_impl.cc
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/db/db_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_impl.cc
index 7e4c0471b2..e22ce20a43 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_impl.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_impl.cc
@@ -46,6 +46,7 @@
 #include "db/merge_context.h"
 #include "db/merge_helper.h"
 #include "db/range_del_aggregator.h"
+#include "db/range_tombstone_fragmenter.h"
 #include "db/table_cache.h"
 #include "db/table_properties_collector.h"
 #include "db/transaction_log_impl.h"
@@ -215,9 +216,12 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
       // requires a custom gc for compaction, we use that to set use_custom_gc_
       // as well.
       use_custom_gc_(seq_per_batch),
+      shutdown_initiated_(false),
+      own_sfm_(options.sst_file_manager == nullptr),
       preserve_deletes_(options.preserve_deletes),
       closed_(false),
-      error_handler_(immutable_db_options_, &mutex_) {
+      error_handler_(this, immutable_db_options_, &mutex_),
+      atomic_flush_commit_in_progress_(false) {
   // !batch_per_trx_ implies seq_per_batch_ because it is only unset for
   // WriteUnprepared, which should use seq_per_batch_.
   assert(batch_per_txn_ || seq_per_batch_);
@@ -259,16 +263,85 @@ Status DBImpl::Resume() {
     return Status::OK();
   }
 
-  Status s = error_handler_.GetBGError();
-  if (s.severity() > Status::Severity::kHardError) {
+  if (error_handler_.IsRecoveryInProgress()) {
+    // Don't allow a mix of manual and automatic recovery
+    return Status::Busy();
+  }
+
+  mutex_.Unlock();
+  Status s = error_handler_.RecoverFromBGError(true);
+  mutex_.Lock();
+  return s;
+}
+
+// This function implements the guts of recovery from a background error. It
+// is eventually called for both manual as well as automatic recovery. It does
+// the following -
+// 1. Wait for currently scheduled background flush/compaction to exit, in
+//    order to inadvertently causing an error and thinking recovery failed
+// 2. Flush memtables if there's any data for all the CFs. This may result
+//    another error, which will be saved by error_handler_ and reported later
+//    as the recovery status
+// 3. Find and delete any obsolete files
+// 4. Schedule compactions if needed for all the CFs. This is needed as the
+//    flush in the prior step might have been a no-op for some CFs, which
+//    means a new super version wouldn't have been installed
+Status DBImpl::ResumeImpl() {
+  mutex_.AssertHeld();
+  WaitForBackgroundWork();
+
+  Status bg_error = error_handler_.GetBGError();
+  Status s;
+  if (shutdown_initiated_) {
+    // Returning shutdown status to SFM during auto recovery will cause it
+    // to abort the recovery and allow the shutdown to progress
+    s = Status::ShutdownInProgress();
+  }
+  if (s.ok() && bg_error.severity() > Status::Severity::kHardError) {
     ROCKS_LOG_INFO(immutable_db_options_.info_log,
         "DB resume requested but failed due to Fatal/Unrecoverable error");
-    return s;
+    s = bg_error;
+  }
+
+  // We cannot guarantee consistency of the WAL. So force flush Memtables of
+  // all the column families
+  if (s.ok()) {
+    FlushOptions flush_opts;
+    // We allow flush to stall write since we are trying to resume from error.
+    flush_opts.allow_write_stall = true;
+    if (immutable_db_options_.atomic_flush) {
+      autovector<ColumnFamilyData*> cfds;
+      SelectColumnFamiliesForAtomicFlush(&cfds);
+      mutex_.Unlock();
+      s = AtomicFlushMemTables(cfds, flush_opts, FlushReason::kErrorRecovery);
+      mutex_.Lock();
+    } else {
+      for (auto cfd : *versions_->GetColumnFamilySet()) {
+        if (cfd->IsDropped()) {
+          continue;
+        }
+        cfd->Ref();
+        mutex_.Unlock();
+        s = FlushMemTable(cfd, flush_opts, FlushReason::kErrorRecovery);
+        mutex_.Lock();
+        cfd->Unref();
+        if (!s.ok()) {
+          break;
+        }
+      }
+    }
+    if (!s.ok()) {
+      ROCKS_LOG_INFO(immutable_db_options_.info_log,
+                     "DB resume requested but failed due to Flush failure [%s]",
+                     s.ToString().c_str());
+    }
   }
 
   JobContext job_context(0);
   FindObsoleteFiles(&job_context, true);
-  error_handler_.ClearBGError();
+  if (s.ok()) {
+    s = error_handler_.ClearBGError();
+  }
   mutex_.Unlock();
 
   job_context.manifest_file_number = 1;
@@ -277,32 +350,72 @@ Status DBImpl::Resume() {
   }
   job_context.Clean();
 
-  ROCKS_LOG_INFO(immutable_db_options_.info_log, "Successfully resumed DB");
+  if (s.ok()) {
+    ROCKS_LOG_INFO(immutable_db_options_.info_log, "Successfully resumed DB");
+  }
   mutex_.Lock();
-  MaybeScheduleFlushOrCompaction();
+  // Check for shutdown again before scheduling further compactions,
+  // since we released and re-acquired the lock above
+  if (shutdown_initiated_) {
+    s = Status::ShutdownInProgress();
+  }
+  if (s.ok()) {
+    for (auto cfd : *versions_->GetColumnFamilySet()) {
+      SchedulePendingCompaction(cfd);
+    }
+    MaybeScheduleFlushOrCompaction();
+  }
+
+  // Wake up any waiters - in this case, it could be the shutdown thread
+  bg_cv_.SignalAll();
 
   // No need to check BGError again. If something happened, event listener would be
   // notified and the operation causing it would have failed
-  return Status::OK();
+  return s;
+}
+
+void DBImpl::WaitForBackgroundWork() {
+  // Wait for background work to finish
+  while (bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
+         bg_flush_scheduled_) {
+    bg_cv_.Wait();
+  }
 }
 
 // Will lock the mutex_,  will wait for completion if wait is true
 void DBImpl::CancelAllBackgroundWork(bool wait) {
-  InstrumentedMutexLock l(&mutex_);
 
   ROCKS_LOG_INFO(immutable_db_options_.info_log,
                  "Shutdown: canceling all background work");
 
+  InstrumentedMutexLock l(&mutex_);
+  // To avoid deadlock, `thread_dump_stats_->cancel()` needs to be called
+  // before grabbing db mutex because the actual worker function
+  // `DBImpl::DumpStats()` also holds db mutex
+  if (thread_dump_stats_ != nullptr) {
+    mutex_.Unlock();
+    thread_dump_stats_->cancel();
+    mutex_.Lock();
+    thread_dump_stats_.reset();
+  }
   if (!shutting_down_.load(std::memory_order_acquire) &&
       has_unpersisted_data_.load(std::memory_order_relaxed) &&
       !mutable_db_options_.avoid_flush_during_shutdown) {
-    for (auto cfd : *versions_->GetColumnFamilySet()) {
-      if (!cfd->IsDropped() && cfd->initialized() && !cfd->mem()->IsEmpty()) {
-        cfd->Ref();
-        mutex_.Unlock();
-        FlushMemTable(cfd, FlushOptions(), FlushReason::kShutDown);
-        mutex_.Lock();
-        cfd->Unref();
+    if (immutable_db_options_.atomic_flush) {
+      autovector<ColumnFamilyData*> cfds;
+      SelectColumnFamiliesForAtomicFlush(&cfds);
+      mutex_.Unlock();
+      AtomicFlushMemTables(cfds, FlushOptions(), FlushReason::kShutDown);
+      mutex_.Lock();
+    } else {
+      for (auto cfd : *versions_->GetColumnFamilySet()) {
+        if (!cfd->IsDropped() && cfd->initialized() && !cfd->mem()->IsEmpty()) {
+          cfd->Ref();
+          mutex_.Unlock();
+          FlushMemTable(cfd, FlushOptions(), FlushReason::kShutDown);
+          mutex_.Lock();
+          cfd->Unref();
+        }
       }
     }
     versions_->GetColumnFamilySet()->FreeDeadColumnFamilies();
@@ -313,14 +426,20 @@ void DBImpl::CancelAllBackgroundWork(bool wait) {
   if (!wait) {
     return;
   }
-  // Wait for background work to finish
-  while (bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
-         bg_flush_scheduled_) {
-    bg_cv_.Wait();
-  }
+  WaitForBackgroundWork();
 }
 
 Status DBImpl::CloseHelper() {
+  // Guarantee that there is no background error recovery in progress before
+  // continuing with the shutdown
+  mutex_.Lock();
+  shutdown_initiated_ = true;
+  error_handler_.CancelErrorRecovery();
+  while (error_handler_.IsRecoveryInProgress()) {
+    bg_cv_.Wait();
+  }
+  mutex_.Unlock();
+
   // CancelAllBackgroundWork called with false means we just set the shutdown
   // marker. After this we do a variant of the waiting and unschedule work
   // (to consider: moving all the waiting into CancelAllBackgroundWork(true))
@@ -338,7 +457,8 @@ Status DBImpl::CloseHelper() {
   // Wait for background work to finish
   while (bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
          bg_flush_scheduled_ || bg_purge_scheduled_ ||
-         pending_purge_obsolete_files_) {
+         pending_purge_obsolete_files_ ||
+         error_handler_.IsRecoveryInProgress()) {
     TEST_SYNC_POINT("DBImpl::~DBImpl:WaitJob");
     bg_cv_.Wait();
   }
@@ -348,9 +468,12 @@ Status DBImpl::CloseHelper() {
   flush_scheduler_.Clear();
 
   while (!flush_queue_.empty()) {
-    auto cfd = PopFirstFromFlushQueue();
-    if (cfd->Unref()) {
-      delete cfd;
+    const FlushRequest& flush_req = PopFirstFromFlushQueue();
+    for (const auto& iter : flush_req) {
+      ColumnFamilyData* cfd = iter.first;
+      if (cfd->Unref()) {
+        delete cfd;
+      }
     }
   }
   while (!compaction_queue_.empty()) {
@@ -440,6 +563,17 @@ Status DBImpl::CloseHelper() {
   ROCKS_LOG_INFO(immutable_db_options_.info_log, "Shutdown complete");
   LogFlush(immutable_db_options_.info_log);
 
+#ifndef ROCKSDB_LITE
+  // If the sst_file_manager was allocated by us during DB::Open(), ccall
+  // Close() on it before closing the info_log. Otherwise, background thread
+  // in SstFileManagerImpl might try to log something
+  if (immutable_db_options_.sst_file_manager && own_sfm_) {
+    auto sfm = static_cast<SstFileManagerImpl*>(
+        immutable_db_options_.sst_file_manager.get());
+    sfm->Close();
+  }
+#endif // ROCKSDB_LITE
+
   if (immutable_db_options_.info_log && own_info_log_) {
     Status s = immutable_db_options_.info_log->Close();
     if (ret.ok()) {
@@ -485,66 +619,68 @@ void DBImpl::PrintStatistics() {
   }
 }
 
-void DBImpl::MaybeDumpStats() {
-  mutex_.Lock();
-  unsigned int stats_dump_period_sec =
-      mutable_db_options_.stats_dump_period_sec;
-  mutex_.Unlock();
-  if (stats_dump_period_sec == 0) return;
-
-  const uint64_t now_micros = env_->NowMicros();
-
-  if (last_stats_dump_time_microsec_ + stats_dump_period_sec * 1000000 <=
-      now_micros) {
-    // Multiple threads could race in here simultaneously.
-    // However, the last one will update last_stats_dump_time_microsec_
-    // atomically. We could see more than one dump during one dump
-    // period in rare cases.
-    last_stats_dump_time_microsec_ = now_micros;
+void DBImpl::StartTimedTasks() {
+  unsigned int stats_dump_period_sec = 0;
+  {
+    InstrumentedMutexLock l(&mutex_);
+    stats_dump_period_sec = mutable_db_options_.stats_dump_period_sec;
+    if (stats_dump_period_sec > 0) {
+      if (!thread_dump_stats_) {
+        thread_dump_stats_.reset(new rocksdb::RepeatableThread(
+            [this]() { DBImpl::DumpStats(); }, "dump_st", env_,
+            stats_dump_period_sec * 1000000));
+      }
+    }
+  }
+}
 
+void DBImpl::DumpStats() {
+  TEST_SYNC_POINT("DBImpl::DumpStats:1");
 #ifndef ROCKSDB_LITE
-    const DBPropertyInfo* cf_property_info =
-        GetPropertyInfo(DB::Properties::kCFStats);
-    assert(cf_property_info != nullptr);
-    const DBPropertyInfo* db_property_info =
-        GetPropertyInfo(DB::Properties::kDBStats);
-    assert(db_property_info != nullptr);
+  const DBPropertyInfo* cf_property_info =
+      GetPropertyInfo(DB::Properties::kCFStats);
+  assert(cf_property_info != nullptr);
+  const DBPropertyInfo* db_property_info =
+      GetPropertyInfo(DB::Properties::kDBStats);
+  assert(db_property_info != nullptr);
 
-    std::string stats;
-    {
-      InstrumentedMutexLock l(&mutex_);
-      default_cf_internal_stats_->GetStringProperty(
-          *db_property_info, DB::Properties::kDBStats, &stats);
-      for (auto cfd : *versions_->GetColumnFamilySet()) {
-        if (cfd->initialized()) {
-          cfd->internal_stats()->GetStringProperty(
-              *cf_property_info, DB::Properties::kCFStatsNoFileHistogram,
-              &stats);
-        }
-      }
-      for (auto cfd : *versions_->GetColumnFamilySet()) {
-        if (cfd->initialized()) {
-          cfd->internal_stats()->GetStringProperty(
-              *cf_property_info, DB::Properties::kCFFileHistogram, &stats);
-        }
+  std::string stats;
+  if (shutdown_initiated_) {
+    return;
+  }
+  {
+    InstrumentedMutexLock l(&mutex_);
+    default_cf_internal_stats_->GetStringProperty(
+        *db_property_info, DB::Properties::kDBStats, &stats);
+    for (auto cfd : *versions_->GetColumnFamilySet()) {
+      if (cfd->initialized()) {
+        cfd->internal_stats()->GetStringProperty(
+            *cf_property_info, DB::Properties::kCFStatsNoFileHistogram, &stats);
       }
     }
-    ROCKS_LOG_WARN(immutable_db_options_.info_log,
-                   "------- DUMPING STATS -------");
-    ROCKS_LOG_WARN(immutable_db_options_.info_log, "%s", stats.c_str());
-    if (immutable_db_options_.dump_malloc_stats) {
-      stats.clear();
-      DumpMallocStats(&stats);
-      if (!stats.empty()) {
-        ROCKS_LOG_WARN(immutable_db_options_.info_log,
-                       "------- Malloc STATS -------");
-        ROCKS_LOG_WARN(immutable_db_options_.info_log, "%s", stats.c_str());
+    for (auto cfd : *versions_->GetColumnFamilySet()) {
+      if (cfd->initialized()) {
+        cfd->internal_stats()->GetStringProperty(
+            *cf_property_info, DB::Properties::kCFFileHistogram, &stats);
       }
     }
+  }
+  TEST_SYNC_POINT("DBImpl::DumpStats:2");
+  ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                 "------- DUMPING STATS -------");
+  ROCKS_LOG_WARN(immutable_db_options_.info_log, "%s", stats.c_str());
+  if (immutable_db_options_.dump_malloc_stats) {
+    stats.clear();
+    DumpMallocStats(&stats);
+    if (!stats.empty()) {
+      ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                     "------- Malloc STATS -------");
+      ROCKS_LOG_WARN(immutable_db_options_.info_log, "%s", stats.c_str());
+    }
+  }
 #endif  // !ROCKSDB_LITE
 
-    PrintStatistics();
-  }
+  PrintStatistics();
 }
 
 void DBImpl::ScheduleBgLogWriterClose(JobContext* job_context) {
@@ -595,7 +731,6 @@ Status DBImpl::SetOptions(
   MutableCFOptions new_options;
   Status s;
   Status persist_options_status;
-  WriteThread::Writer w;
   SuperVersionContext sv_context(/* create_superversion */ true);
   {
     InstrumentedMutexLock l(&mutex_);
@@ -657,7 +792,6 @@ Status DBImpl::SetDBOptions(
   Status s;
   Status persist_options_status;
   bool wal_changed = false;
-  WriteThread::Writer w;
   WriteContext write_context;
   {
     InstrumentedMutexLock l(&mutex_);
@@ -670,7 +804,22 @@ Status DBImpl::SetDBOptions(
             new_options.max_background_compactions, Env::Priority::LOW);
         MaybeScheduleFlushOrCompaction();
       }
-
+      if (new_options.stats_dump_period_sec !=
+          mutable_db_options_.stats_dump_period_sec) {
+          if (thread_dump_stats_) {
+            mutex_.Unlock();
+            thread_dump_stats_->cancel();
+            mutex_.Lock();
+          }
+          if (new_options.stats_dump_period_sec > 0) {
+            thread_dump_stats_.reset(new rocksdb::RepeatableThread(
+                [this]() { DBImpl::DumpStats(); }, "dump_st", env_,
+                new_options.stats_dump_period_sec * 1000000));
+          }
+          else {
+            thread_dump_stats_.reset();
+          }
+      }
       write_controller_.set_max_delayed_write_rate(
           new_options.delayed_write_rate);
       table_cache_.get()->SetCapacity(new_options.max_open_files == -1
@@ -691,6 +840,7 @@ Status DBImpl::SetDBOptions(
           env_options_for_compaction_, immutable_db_options_);
       env_options_for_compaction_.compaction_readahead_size =
           mutable_db_options_.compaction_readahead_size;
+      WriteThread::Writer w;
       write_thread_.EnterUnbatched(&w, &mutex_);
       if (total_log_size_ > GetMaxTotalWalSize() || wal_changed) {
         Status purge_wal_status = SwitchWAL(&write_context);
@@ -883,7 +1033,7 @@ bool DBImpl::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum) {
 }
 
 InternalIterator* DBImpl::NewInternalIterator(
-    Arena* arena, RangeDelAggregator* range_del_agg,
+    Arena* arena, RangeDelAggregatorV2* range_del_agg, SequenceNumber sequence,
     ColumnFamilyHandle* column_family) {
   ColumnFamilyData* cfd;
   if (column_family == nullptr) {
@@ -897,8 +1047,8 @@ InternalIterator* DBImpl::NewInternalIterator(
   SuperVersion* super_version = cfd->GetSuperVersion()->Ref();
   mutex_.Unlock();
   ReadOptions roptions;
-  return NewInternalIterator(roptions, cfd, super_version, arena,
-                             range_del_agg);
+  return NewInternalIterator(roptions, cfd, super_version, arena, range_del_agg,
+                             sequence);
 }
 
 void DBImpl::SchedulePurge() {
@@ -1003,7 +1153,7 @@ static void CleanupIteratorState(void* arg1, void* /*arg2*/) {
 InternalIterator* DBImpl::NewInternalIterator(
     const ReadOptions& read_options, ColumnFamilyData* cfd,
     SuperVersion* super_version, Arena* arena,
-    RangeDelAggregator* range_del_agg) {
+    RangeDelAggregatorV2* range_del_agg, SequenceNumber sequence) {
   InternalIterator* internal_iter;
   assert(arena != nullptr);
   assert(range_del_agg != nullptr);
@@ -1015,12 +1165,12 @@ InternalIterator* DBImpl::NewInternalIterator(
   // Collect iterator for mutable mem
   merge_iter_builder.AddIterator(
       super_version->mem->NewIterator(read_options, arena));
-  std::unique_ptr<InternalIterator> range_del_iter;
+  std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter;
   Status s;
   if (!read_options.ignore_range_deletions) {
     range_del_iter.reset(
-        super_version->mem->NewRangeTombstoneIterator(read_options));
-    s = range_del_agg->AddTombstones(std::move(range_del_iter));
+        super_version->mem->NewRangeTombstoneIterator(read_options, sequence));
+    range_del_agg->AddTombstones(std::move(range_del_iter));
   }
   // Collect all needed child iterators for immutable memtables
   if (s.ok()) {
@@ -1121,7 +1271,7 @@ Status DBImpl::GetImpl(const ReadOptions& read_options,
 
   // Prepare to store a list of merge operations if merge occurs.
   MergeContext merge_context;
-  RangeDelAggregator range_del_agg(cfd->internal_comparator(), snapshot);
+  SequenceNumber max_covering_tombstone_seq = 0;
 
   Status s;
   // First look in the memtable, then in the immutable memtable (if any).
@@ -1135,13 +1285,14 @@ Status DBImpl::GetImpl(const ReadOptions& read_options,
   bool done = false;
   if (!skip_memtable) {
     if (sv->mem->Get(lkey, pinnable_val->GetSelf(), &s, &merge_context,
-                     &range_del_agg, read_options, callback, is_blob_index)) {
+                     &max_covering_tombstone_seq, read_options, callback,
+                     is_blob_index)) {
       done = true;
       pinnable_val->PinSelf();
       RecordTick(stats_, MEMTABLE_HIT);
     } else if ((s.ok() || s.IsMergeInProgress()) &&
                sv->imm->Get(lkey, pinnable_val->GetSelf(), &s, &merge_context,
-                            &range_del_agg, read_options, callback,
+                            &max_covering_tombstone_seq, read_options, callback,
                             is_blob_index)) {
       done = true;
       pinnable_val->PinSelf();
@@ -1155,8 +1306,8 @@ Status DBImpl::GetImpl(const ReadOptions& read_options,
   if (!done) {
     PERF_TIMER_GUARD(get_from_output_files_time);
     sv->current->Get(read_options, lkey, pinnable_val, &s, &merge_context,
-                     &range_del_agg, value_found, nullptr, nullptr, callback,
-                     is_blob_index);
+                     &max_covering_tombstone_seq, value_found, nullptr, nullptr,
+                     callback, is_blob_index);
     RecordTick(stats_, MEMTABLE_MISS);
   }
 
@@ -1238,8 +1389,7 @@ std::vector<Status> DBImpl::MultiGet(
 
     LookupKey lkey(keys[i], snapshot);
     auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family[i]);
-    RangeDelAggregator range_del_agg(cfh->cfd()->internal_comparator(),
-                                     snapshot);
+    SequenceNumber max_covering_tombstone_seq = 0;
     auto mgd_iter = multiget_cf_data.find(cfh->cfd()->GetID());
     assert(mgd_iter != multiget_cf_data.end());
     auto mgd = mgd_iter->second;
@@ -1250,11 +1400,12 @@ std::vector<Status> DBImpl::MultiGet(
     bool done = false;
     if (!skip_memtable) {
       if (super_version->mem->Get(lkey, value, &s, &merge_context,
-                                  &range_del_agg, read_options)) {
+                                  &max_covering_tombstone_seq, read_options)) {
         done = true;
         RecordTick(stats_, MEMTABLE_HIT);
       } else if (super_version->imm->Get(lkey, value, &s, &merge_context,
-                                         &range_del_agg, read_options)) {
+                                         &max_covering_tombstone_seq,
+                                         read_options)) {
         done = true;
         RecordTick(stats_, MEMTABLE_HIT);
       }
@@ -1263,7 +1414,7 @@ std::vector<Status> DBImpl::MultiGet(
       PinnableSlice pinnable_val;
       PERF_TIMER_GUARD(get_from_output_files_time);
       super_version->current->Get(read_options, lkey, &pinnable_val, &s,
-                                  &merge_context, &range_del_agg);
+                                  &merge_context, &max_covering_tombstone_seq);
       value->assign(pinnable_val.data(), pinnable_val.size());
       RecordTick(stats_, MEMTABLE_MISS);
     }
@@ -1691,7 +1842,7 @@ ArenaWrappedDBIter* DBImpl::NewIteratorImpl(const ReadOptions& read_options,
 
   InternalIterator* internal_iter =
       NewInternalIterator(read_options, cfd, sv, db_iter->GetArena(),
-                          db_iter->GetRangeDelAggregator());
+                          db_iter->GetRangeDelAggregator(), snapshot);
   db_iter->SetIterUnderDBIter(internal_iter);
 
   return db_iter;
@@ -2062,17 +2213,18 @@ ColumnFamilyHandle* DBImpl::GetColumnFamilyHandle(uint32_t column_family_id) {
 }
 
 // REQUIRED: mutex is NOT held.
-ColumnFamilyHandle* DBImpl::GetColumnFamilyHandleUnlocked(
+std::unique_ptr<ColumnFamilyHandle> DBImpl::GetColumnFamilyHandleUnlocked(
     uint32_t column_family_id) {
-  ColumnFamilyMemTables* cf_memtables = column_family_memtables_.get();
-
   InstrumentedMutexLock l(&mutex_);
 
-  if (!cf_memtables->Seek(column_family_id)) {
+  auto* cfd =
+      versions_->GetColumnFamilySet()->GetColumnFamily(column_family_id);
+  if (cfd == nullptr) {
     return nullptr;
   }
 
-  return cf_memtables->GetColumnFamilyHandle();
+  return std::unique_ptr<ColumnFamilyHandleImpl>(
+      new ColumnFamilyHandleImpl(cfd, this, &mutex_));
 }
 
 void DBImpl::GetApproximateMemTableStats(ColumnFamilyHandle* column_family,
@@ -2143,9 +2295,8 @@ void DBImpl::ReleaseFileNumberFromPendingOutputs(
 
 #ifndef ROCKSDB_LITE
 Status DBImpl::GetUpdatesSince(
-    SequenceNumber seq, unique_ptr<TransactionLogIterator>* iter,
+    SequenceNumber seq, std::unique_ptr<TransactionLogIterator>* iter,
     const TransactionLogIterator::ReadOptions& read_options) {
-
   RecordTick(stats_, GET_UPDATES_SINCE_CALLS);
   if (seq > versions_->LastSequence()) {
     return Status::NotFound("Requested sequence not yet written in the db");
@@ -2393,10 +2544,10 @@ Status DBImpl::CheckConsistency() {
 Status DBImpl::GetDbIdentity(std::string& identity) const {
   std::string idfilename = IdentityFileName(dbname_);
   const EnvOptions soptions;
-  unique_ptr<SequentialFileReader> id_file_reader;
+  std::unique_ptr<SequentialFileReader> id_file_reader;
   Status s;
   {
-    unique_ptr<SequentialFile> idfile;
+    std::unique_ptr<SequentialFile> idfile;
     s = env_->NewSequentialFile(idfilename, &idfile, soptions);
     if (!s.ok()) {
       return s;
@@ -2410,7 +2561,7 @@ Status DBImpl::GetDbIdentity(std::string& identity) const {
   if (!s.ok()) {
     return s;
   }
-  char* buffer = reinterpret_cast<char*>(alloca(file_size));
+  char* buffer = reinterpret_cast<char*>(alloca(static_cast<size_t>(file_size)));
   Slice id;
   s = id_file_reader->Read(static_cast<size_t>(file_size), &id, buffer);
   if (!s.ok()) {
@@ -2793,8 +2944,7 @@ Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
                                        bool* is_blob_index) {
   Status s;
   MergeContext merge_context;
-  RangeDelAggregator range_del_agg(sv->mem->GetInternalKeyComparator(),
-                                   kMaxSequenceNumber);
+  SequenceNumber max_covering_tombstone_seq = 0;
 
   ReadOptions read_options;
   SequenceNumber current_seq = versions_->LastSequence();
@@ -2804,8 +2954,8 @@ Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
   *found_record_for_key = false;
 
   // Check if there is a record for this key in the latest memtable
-  sv->mem->Get(lkey, nullptr, &s, &merge_context, &range_del_agg, seq,
-               read_options, nullptr /*read_callback*/, is_blob_index);
+  sv->mem->Get(lkey, nullptr, &s, &merge_context, &max_covering_tombstone_seq,
+               seq, read_options, nullptr /*read_callback*/, is_blob_index);
 
   if (!(s.ok() || s.IsNotFound() || s.IsMergeInProgress())) {
     // unexpected error reading memtable.
@@ -2823,8 +2973,8 @@ Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
   }
 
   // Check if there is a record for this key in the immutable memtables
-  sv->imm->Get(lkey, nullptr, &s, &merge_context, &range_del_agg, seq,
-               read_options, nullptr /*read_callback*/, is_blob_index);
+  sv->imm->Get(lkey, nullptr, &s, &merge_context, &max_covering_tombstone_seq,
+               seq, read_options, nullptr /*read_callback*/, is_blob_index);
 
   if (!(s.ok() || s.IsNotFound() || s.IsMergeInProgress())) {
     // unexpected error reading memtable.
@@ -2842,8 +2992,9 @@ Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
   }
 
   // Check if there is a record for this key in the immutable memtables
-  sv->imm->GetFromHistory(lkey, nullptr, &s, &merge_context, &range_del_agg,
-                          seq, read_options, is_blob_index);
+  sv->imm->GetFromHistory(lkey, nullptr, &s, &merge_context,
+                          &max_covering_tombstone_seq, seq, read_options,
+                          is_blob_index);
 
   if (!(s.ok() || s.IsNotFound() || s.IsMergeInProgress())) {
     // unexpected error reading memtable.
@@ -2866,7 +3017,7 @@ Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
   if (!cache_only) {
     // Check tables
     sv->current->Get(read_options, lkey, nullptr, &s, &merge_context,
-                     &range_del_agg, nullptr /* value_found */,
+                     &max_covering_tombstone_seq, nullptr /* value_found */,
                      found_record_for_key, seq, nullptr /*read_callback*/,
                      is_blob_index);
 
@@ -2875,12 +3026,10 @@ Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
       ROCKS_LOG_ERROR(immutable_db_options_.info_log,
                       "Unexpected status returned from Version::Get: %s\n",
                       s.ToString().c_str());
-
-      return s;
     }
   }
 
-  return Status::OK();
+  return s;
 }
 
 Status DBImpl::IngestExternalFile(
@@ -2967,6 +3116,7 @@ Status DBImpl::IngestExternalFile(
     }
 
     num_running_ingest_file_++;
+    TEST_SYNC_POINT("DBImpl::IngestExternalFile:AfterIncIngestFileCounter");
 
     // We cannot ingest a file into a dropped CF
     if (cfd->IsDropped()) {
@@ -2981,10 +3131,21 @@ Status DBImpl::IngestExternalFile(
       TEST_SYNC_POINT_CALLBACK("DBImpl::IngestExternalFile:NeedFlush",
                                &need_flush);
       if (status.ok() && need_flush) {
-        mutex_.Unlock();
-        status = FlushMemTable(cfd, FlushOptions(),
-                               FlushReason::kExternalFileIngestion,
-                               true /* writes_stopped */);
+        FlushOptions flush_opts;
+        flush_opts.allow_write_stall = true;
+        if (immutable_db_options_.atomic_flush) {
+          autovector<ColumnFamilyData*> cfds;
+          SelectColumnFamiliesForAtomicFlush(&cfds);
+          mutex_.Unlock();
+          status = AtomicFlushMemTables(cfds, flush_opts,
+                                        FlushReason::kExternalFileIngestion,
+                                        true /* writes_stopped */);
+        } else {
+          mutex_.Unlock();
+          status = FlushMemTable(cfd, flush_opts,
+                                 FlushReason::kExternalFileIngestion,
+                                 true /* writes_stopped */);
+        }
         mutex_.Lock();
       }
     }
@@ -3118,10 +3279,10 @@ void DBImpl::WaitForIngestFile() {
   }
 }
 
-Status DBImpl::StartTrace(const TraceOptions& /* options */,
+Status DBImpl::StartTrace(const TraceOptions& trace_options,
                           std::unique_ptr<TraceWriter>&& trace_writer) {
   InstrumentedMutexLock lock(&trace_mutex_);
-  tracer_.reset(new Tracer(env_, std::move(trace_writer)));
+  tracer_.reset(new Tracer(env_, trace_options, std::move(trace_writer)));
   return Status::OK();
 }
 
@@ -3143,7 +3304,8 @@ Status DBImpl::TraceIteratorSeek(const uint32_t& cf_id, const Slice& key) {
   return s;
 }
 
-Status DBImpl::TraceIteratorSeekForPrev(const uint32_t& cf_id, const Slice& key) {
+Status DBImpl::TraceIteratorSeekForPrev(const uint32_t& cf_id,
+                                        const Slice& key) {
   Status s;
   if (tracer_) {
     InstrumentedMutexLock lock(&trace_mutex_);
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_impl.h b/3rdParty/rocksdb/v5.18.X/db/db_impl.h
similarity index 89%
rename from 3rdParty/rocksdb/v5.16.X/db/db_impl.h
rename to 3rdParty/rocksdb/v5.18.X/db/db_impl.h
index 36428f33ea..2cabe756ad 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_impl.h
+++ b/3rdParty/rocksdb/v5.18.X/db/db_impl.h
@@ -22,15 +22,16 @@
 #include "db/column_family.h"
 #include "db/compaction_job.h"
 #include "db/dbformat.h"
-#include "db/external_sst_file_ingestion_job.h"
 #include "db/error_handler.h"
 #include "db/event_helpers.h"
+#include "db/external_sst_file_ingestion_job.h"
 #include "db/flush_job.h"
 #include "db/flush_scheduler.h"
 #include "db/internal_stats.h"
 #include "db/log_writer.h"
 #include "db/logs_with_prep_tracker.h"
 #include "db/pre_release_callback.h"
+#include "db/range_del_aggregator_v2.h"
 #include "db/read_callback.h"
 #include "db/snapshot_checker.h"
 #include "db/snapshot_impl.h"
@@ -53,6 +54,7 @@
 #include "util/autovector.h"
 #include "util/event_logger.h"
 #include "util/hash.h"
+#include "util/repeatable_thread.h"
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
 #include "util/trace_replay.h"
@@ -227,6 +229,9 @@ class DBImpl : public DB {
   using DB::Flush;
   virtual Status Flush(const FlushOptions& options,
                        ColumnFamilyHandle* column_family) override;
+  virtual Status Flush(
+      const FlushOptions& options,
+      const std::vector<ColumnFamilyHandle*>& column_families) override;
   virtual Status FlushWAL(bool sync) override;
   bool TEST_WALBufferIsEmpty();
   virtual Status SyncWAL() override;
@@ -255,9 +260,9 @@ class DBImpl : public DB {
   virtual Status GetSortedWalFiles(VectorLogPtr& files) override;
 
   virtual Status GetUpdatesSince(
-      SequenceNumber seq_number, unique_ptr<TransactionLogIterator>* iter,
-      const TransactionLogIterator::ReadOptions&
-          read_options = TransactionLogIterator::ReadOptions()) override;
+      SequenceNumber seq_number, std::unique_ptr<TransactionLogIterator>* iter,
+      const TransactionLogIterator::ReadOptions& read_options =
+          TransactionLogIterator::ReadOptions()) override;
   virtual Status DeleteFile(std::string name) override;
   Status DeleteFilesInRanges(ColumnFamilyHandle* column_family,
                              const RangePtr* ranges, size_t n,
@@ -369,8 +374,8 @@ class DBImpl : public DB {
   // The keys of this iterator are internal keys (see format.h).
   // The returned iterator should be deleted when no longer needed.
   InternalIterator* NewInternalIterator(
-      Arena* arena, RangeDelAggregator* range_del_agg,
-      ColumnFamilyHandle* column_family = nullptr);
+      Arena* arena, RangeDelAggregatorV2* range_del_agg,
+      SequenceNumber sequence, ColumnFamilyHandle* column_family = nullptr);
 
   LogsWithPrepTracker* logs_with_prep_tracker() {
     return &logs_with_prep_tracker_;
@@ -396,7 +401,7 @@ class DBImpl : public DB {
   Status TEST_SwitchMemtable(ColumnFamilyData* cfd = nullptr);
 
   // Force current memtable contents to be flushed.
-  Status TEST_FlushMemTable(bool wait = true,
+  Status TEST_FlushMemTable(bool wait = true, bool allow_write_stall = false,
                             ColumnFamilyHandle* cfh = nullptr);
 
   // Wait for memtable compaction
@@ -464,6 +469,8 @@ class DBImpl : public DB {
 
   int TEST_BGCompactionsAllowed() const;
   int TEST_BGFlushesAllowed() const;
+  size_t TEST_GetWalPreallocateBlockSize(uint64_t write_buffer_size) const;
+  void TEST_WaitForTimedTaskRun(std::function<void()> callback) const;
 
 #endif  // NDEBUG
 
@@ -485,6 +492,14 @@ class DBImpl : public DB {
 
   uint64_t MinLogNumberToKeep();
 
+  // Returns the lower bound file number for SSTs that won't be deleted, even if
+  // they're obsolete. This lower bound is used internally to prevent newly
+  // created flush/compaction output files from being deleted before they're
+  // installed. This technique avoids the need for tracking the exact numbers of
+  // files pending creation, although it prevents more files than necessary from
+  // being deleted.
+  uint64_t MinObsoleteSstNumberToKeep();
+
   // Returns the list of live files in 'live' and the list
   // of all files in the filesystem in 'candidate_files'.
   // If force == false and the last call was less than
@@ -544,7 +559,8 @@ class DBImpl : public DB {
   ColumnFamilyHandle* GetColumnFamilyHandle(uint32_t column_family_id);
 
   // Same as above, should called without mutex held and not on write thread.
-  ColumnFamilyHandle* GetColumnFamilyHandleUnlocked(uint32_t column_family_id);
+  std::unique_ptr<ColumnFamilyHandle> GetColumnFamilyHandleUnlocked(
+      uint32_t column_family_id);
 
   // Returns the number of currently running flushes.
   // REQUIREMENT: mutex_ must be held when calling this function.
@@ -566,7 +582,8 @@ class DBImpl : public DB {
                                         ColumnFamilyData* cfd,
                                         SuperVersion* super_version,
                                         Arena* arena,
-                                        RangeDelAggregator* range_del_agg);
+                                        RangeDelAggregatorV2* range_del_agg,
+                                        SequenceNumber sequence);
 
   // hollow transactions shell used for recovery.
   // these will then be passed to TransactionDB so that
@@ -699,7 +716,7 @@ class DBImpl : public DB {
  protected:
   Env* const env_;
   const std::string dbname_;
-  unique_ptr<VersionSet> versions_;
+  std::unique_ptr<VersionSet> versions_;
   // Flag to check whether we allocated and own the info log file
   bool own_info_log_;
   const DBOptions initial_db_options_;
@@ -731,6 +748,11 @@ class DBImpl : public DB {
                               const MutableCFOptions& mutable_cf_options,
                               int job_id, TableProperties prop);
 
+  void NotifyOnCompactionBegin(ColumnFamilyData* cfd,
+                               Compaction *c, const Status &st,
+                               const CompactionJobStats& job_stats,
+                               int job_id);
+
   void NotifyOnCompactionCompleted(ColumnFamilyData* cfd,
                                    Compaction *c, const Status &st,
                                    const CompactionJobStats& job_stats,
@@ -795,6 +817,7 @@ class DBImpl : public DB {
 
  private:
   friend class DB;
+  friend class ErrorHandler;
   friend class InternalStats;
   friend class PessimisticTransaction;
   friend class TransactionBaseImpl;
@@ -811,6 +834,7 @@ class DBImpl : public DB {
   friend struct SuperVersion;
   friend class CompactedDBImpl;
   friend class DBTest_ConcurrentFlushWAL_Test;
+  friend class DBTest_MixedSlowdownOptionsStop_Test;
 #ifndef NDEBUG
   friend class DBTest2_ReadCallbackTest_Test;
   friend class WriteCallbackTest_WriteWithCallbackTest_Test;
@@ -845,6 +869,8 @@ class DBImpl : public DB {
                  bool read_only = false, bool error_if_log_file_exist = false,
                  bool error_if_data_exists_in_logs = false);
 
+  Status ResumeImpl();
+
   void MaybeIgnoreError(Status* s) const;
 
   const Status CreateArchivalDirectory();
@@ -884,12 +910,45 @@ class DBImpl : public DB {
   Status SyncClosedLogs(JobContext* job_context);
 
   // Flush the in-memory write buffer to storage.  Switches to a new
-  // log-file/memtable and writes a new descriptor iff successful.
+  // log-file/memtable and writes a new descriptor iff successful. Then
+  // installs a new super version for the column family.
   Status FlushMemTableToOutputFile(ColumnFamilyData* cfd,
                                    const MutableCFOptions& mutable_cf_options,
                                    bool* madeProgress, JobContext* job_context,
+                                   SuperVersionContext* superversion_context,
                                    LogBuffer* log_buffer);
 
+  // Argument required by background flush thread.
+  struct BGFlushArg {
+    BGFlushArg()
+        : cfd_(nullptr), max_memtable_id_(0), superversion_context_(nullptr) {}
+    BGFlushArg(ColumnFamilyData* cfd, uint64_t max_memtable_id,
+               SuperVersionContext* superversion_context)
+        : cfd_(cfd),
+          max_memtable_id_(max_memtable_id),
+          superversion_context_(superversion_context) {}
+
+    // Column family to flush.
+    ColumnFamilyData* cfd_;
+    // Maximum ID of memtable to flush. In this column family, memtables with
+    // IDs smaller than this value must be flushed before this flush completes.
+    uint64_t max_memtable_id_;
+    // Pointer to a SuperVersionContext object. After flush completes, RocksDB
+    // installs a new superversion for the column family. This operation
+    // requires a SuperVersionContext object (currently embedded in JobContext).
+    SuperVersionContext* superversion_context_;
+  };
+
+  // Flush the memtables of (multiple) column families to multiple files on
+  // persistent storage.
+  Status FlushMemTablesToOutputFiles(
+      const autovector<BGFlushArg>& bg_flush_args, bool* made_progress,
+      JobContext* job_context, LogBuffer* log_buffer);
+
+  Status AtomicFlushMemTablesToOutputFiles(
+      const autovector<BGFlushArg>& bg_flush_args, bool* made_progress,
+      JobContext* job_context, LogBuffer* log_buffer);
+
   // REQUIRES: log_numbers are sorted in ascending order
   Status RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
                          SequenceNumber* next_sequence, bool read_only);
@@ -902,6 +961,12 @@ class DBImpl : public DB {
   Status WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
                                      MemTable* mem, VersionEdit* edit);
 
+  // Restore alive_log_files_ and total_log_size_ after recovery.
+  // It needs to run only when there's no flush during recovery
+  // (e.g. avoid_flush_during_recovery=true). May also trigger flush
+  // in case total_log_size > max_total_wal_size.
+  Status RestoreAliveLogFiles(const std::vector<uint64_t>& log_numbers);
+
   // num_bytes: for slowdown case, delay time is calculated based on
   //            `num_bytes` going through.
   Status DelayWrite(uint64_t num_bytes, const WriteOptions& write_options);
@@ -911,19 +976,43 @@ class DBImpl : public DB {
 
   Status ScheduleFlushes(WriteContext* context);
 
-  Status SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
-                        FlushReason flush_reason = FlushReason::kOthers);
+  Status SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context);
+
+  void SelectColumnFamiliesForAtomicFlush(autovector<ColumnFamilyData*>* cfds);
 
   // Force current memtable contents to be flushed.
   Status FlushMemTable(ColumnFamilyData* cfd, const FlushOptions& options,
                        FlushReason flush_reason, bool writes_stopped = false);
 
+  Status AtomicFlushMemTables(
+      const autovector<ColumnFamilyData*>& column_family_datas,
+      const FlushOptions& options, FlushReason flush_reason,
+      bool writes_stopped = false);
+
+  // Wait until flushing this column family won't stall writes
+  Status WaitUntilFlushWouldNotStallWrites(ColumnFamilyData* cfd,
+                                           bool* flush_needed);
+
   // Wait for memtable flushed.
   // If flush_memtable_id is non-null, wait until the memtable with the ID
   // gets flush. Otherwise, wait until the column family don't have any
   // memtable pending flush.
+  // resuming_from_bg_err indicates whether the caller is attempting to resume
+  // from background error.
   Status WaitForFlushMemTable(ColumnFamilyData* cfd,
-                              const uint64_t* flush_memtable_id = nullptr);
+                              const uint64_t* flush_memtable_id = nullptr,
+                              bool resuming_from_bg_err = false) {
+    return WaitForFlushMemTables({cfd}, {flush_memtable_id},
+                                 resuming_from_bg_err);
+  }
+  // Wait for memtables to be flushed for multiple column families.
+  Status WaitForFlushMemTables(
+      const autovector<ColumnFamilyData*>& cfds,
+      const autovector<const uint64_t*>& flush_memtable_ids,
+      bool resuming_from_bg_err);
+
+  // REQUIRES: mutex locked and in write thread.
+  void AssignAtomicFlushSeq(const autovector<ColumnFamilyData*>& cfds);
 
   // REQUIRES: mutex locked
   Status SwitchWAL(WriteContext* write_context);
@@ -979,7 +1068,20 @@ class DBImpl : public DB {
   ColumnFamilyData* GetColumnFamilyDataByName(const std::string& cf_name);
 
   void MaybeScheduleFlushOrCompaction();
-  void SchedulePendingFlush(ColumnFamilyData* cfd, FlushReason flush_reason);
+
+  // A flush request specifies the column families to flush as well as the
+  // largest memtable id to persist for each column family. Once all the
+  // memtables whose IDs are smaller than or equal to this per-column-family
+  // specified value, this flush request is considered to have completed its
+  // work of flushing this column family. After completing the work for all
+  // column families in this request, this flush is considered complete.
+  typedef std::vector<std::pair<ColumnFamilyData*, uint64_t>> FlushRequest;
+
+  void GenerateFlushRequest(const autovector<ColumnFamilyData*>& cfds,
+                            FlushRequest* req);
+
+  void SchedulePendingFlush(const FlushRequest& req, FlushReason flush_reason);
+
   void SchedulePendingCompaction(ColumnFamilyData* cfd);
   void SchedulePendingPurge(std::string fname, std::string dir_to_sync,
                             FileType type, uint64_t number, int job_id);
@@ -998,15 +1100,19 @@ class DBImpl : public DB {
                               LogBuffer* log_buffer,
                               PrepickedCompaction* prepicked_compaction);
   Status BackgroundFlush(bool* madeProgress, JobContext* job_context,
-                         LogBuffer* log_buffer);
+                         LogBuffer* log_buffer, FlushReason* reason);
 
-  bool EnoughRoomForCompaction(const std::vector<CompactionInputFiles>& inputs,
+  bool EnoughRoomForCompaction(ColumnFamilyData* cfd,
+                               const std::vector<CompactionInputFiles>& inputs,
                                bool* sfm_bookkeeping, LogBuffer* log_buffer);
 
+  // Schedule background tasks
+  void StartTimedTasks();
+
   void PrintStatistics();
 
   // dump rocksdb.stats to LOG
-  void MaybeDumpStats();
+  void DumpStats();
 
   // Return the minimum empty level that could hold the total data in the
   // input level. Return the input level, if such level could not be found.
@@ -1021,8 +1127,7 @@ class DBImpl : public DB {
   // helper functions for adding and removing from flush & compaction queues
   void AddToCompactionQueue(ColumnFamilyData* cfd);
   ColumnFamilyData* PopFirstFromCompactionQueue();
-  void AddToFlushQueue(ColumnFamilyData* cfd, FlushReason flush_reason);
-  ColumnFamilyData* PopFirstFromFlushQueue();
+  FlushRequest PopFirstFromFlushQueue();
 
   // helper function to call after some of the logs_ were synced
   void MarkLogsSynced(uint64_t up_to, bool synced_dir, const Status& status);
@@ -1035,6 +1140,8 @@ class DBImpl : public DB {
 
   Status CloseHelper();
 
+  void WaitForBackgroundWork();
+
   // table_cache_ provides its own synchronization
   std::shared_ptr<Cache> table_cache_;
 
@@ -1085,7 +1192,7 @@ class DBImpl : public DB {
   bool log_empty_;
   ColumnFamilyHandleImpl* default_cf_handle_;
   InternalStats* default_cf_internal_stats_;
-  unique_ptr<ColumnFamilyMemTablesImpl> column_family_memtables_;
+  std::unique_ptr<ColumnFamilyMemTablesImpl> column_family_memtables_;
   struct LogFileNumberSize {
     explicit LogFileNumberSize(uint64_t _number)
         : number(_number) {}
@@ -1113,7 +1220,7 @@ class DBImpl : public DB {
 
     uint64_t number;
     // Visual Studio doesn't support deque's member to be noncopyable because
-    // of a unique_ptr as a member.
+    // of a std::unique_ptr as a member.
     log::Writer* writer;  // own
     // true for some prefix of logs_
     bool getting_synced = false;
@@ -1199,7 +1306,7 @@ class DBImpl : public DB {
 
   WriteController write_controller_;
 
-  unique_ptr<RateLimiter> low_pri_write_rate_limiter_;
+  std::unique_ptr<RateLimiter> low_pri_write_rate_limiter_;
 
   // Size of the last batch group. In slowdown mode, next write needs to
   // sleep if it uses up the quota.
@@ -1255,7 +1362,7 @@ class DBImpl : public DB {
   // in MaybeScheduleFlushOrCompaction()
   // invariant(column family present in flush_queue_ <==>
   // ColumnFamilyData::pending_flush_ == true)
-  std::deque<ColumnFamilyData*> flush_queue_;
+  std::deque<FlushRequest> flush_queue_;
   // invariant(column family present in compaction_queue_ <==>
   // ColumnFamilyData::pending_compaction_ == true)
   std::deque<ColumnFamilyData*> compaction_queue_;
@@ -1406,6 +1513,10 @@ class DBImpl : public DB {
   // Only to be set during initialization
   std::unique_ptr<PreReleaseCallback> recoverable_state_pre_release_callback_;
 
+  // handle for scheduling jobs at fixed intervals
+  // REQUIRES: mutex locked
+  std::unique_ptr<rocksdb::RepeatableThread> thread_dump_stats_;
+
   // No copying allowed
   DBImpl(const DBImpl&);
   void operator=(const DBImpl&);
@@ -1479,6 +1590,16 @@ class DBImpl : public DB {
   // flush/compaction and if it is not provided vis SnapshotChecker, we should
   // disable gc to be safe.
   const bool use_custom_gc_;
+  // Flag to indicate that the DB instance shutdown has been initiated. This
+  // different from shutting_down_ atomic in that it is set at the beginning
+  // of shutdown sequence, specifically in order to prevent any background
+  // error recovery from going on in parallel. The latter, shutting_down_,
+  // is set a little later during the shutdown after scheduling memtable
+  // flushes
+  std::atomic<bool> shutdown_initiated_;
+  // Flag to indicate whether sst_file_manager object was allocated in
+  // DB::Open() or passed to us
+  bool own_sfm_;
 
   // Clients must periodically call SetPreserveDeletesSequenceNumber()
   // to advance this seqnum. Default value is 0 which means ALL deletes are
@@ -1491,6 +1612,16 @@ class DBImpl : public DB {
   bool closed_;
 
   ErrorHandler error_handler_;
+
+  // True if the DB is committing atomic flush.
+  // TODO (yanqin) the current impl assumes that the entire DB belongs to
+  // a single atomic flush group. In the future we need to add a new class
+  // (struct) similar to the following to make it more general.
+  // struct AtomicFlushGroup {
+  //   bool commit_in_progress_;
+  //   std::vector<MemTableList*> imm_lists;
+  // };
+  bool atomic_flush_commit_in_progress_;
 };
 
 extern Options SanitizeOptions(const std::string& db,
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_impl_compaction_flush.cc b/3rdParty/rocksdb/v5.18.X/db/db_impl_compaction_flush.cc
similarity index 73%
rename from 3rdParty/rocksdb/v5.16.X/db/db_impl_compaction_flush.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_impl_compaction_flush.cc
index 0d4afcbdaa..fa0b918773 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_impl_compaction_flush.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_impl_compaction_flush.cc
@@ -26,7 +26,7 @@
 namespace rocksdb {
 
 bool DBImpl::EnoughRoomForCompaction(
-    const std::vector<CompactionInputFiles>& inputs,
+    ColumnFamilyData* cfd, const std::vector<CompactionInputFiles>& inputs,
     bool* sfm_reserved_compact_space, LogBuffer* log_buffer) {
   // Check if we have enough room to do the compaction
   bool enough_room = true;
@@ -34,12 +34,17 @@ bool DBImpl::EnoughRoomForCompaction(
   auto sfm = static_cast<SstFileManagerImpl*>(
       immutable_db_options_.sst_file_manager.get());
   if (sfm) {
-    enough_room = sfm->EnoughRoomForCompaction(inputs);
+    // Pass the current bg_error_ to SFM so it can decide what checks to
+    // perform. If this DB instance hasn't seen any error yet, the SFM can be
+    // optimistic and not do disk space checks
+    enough_room =
+        sfm->EnoughRoomForCompaction(cfd, inputs, error_handler_.GetBGError());
     if (enough_room) {
       *sfm_reserved_compact_space = true;
     }
   }
 #else
+  (void)cfd;
   (void)inputs;
   (void)sfm_reserved_compact_space;
 #endif  // ROCKSDB_LITE
@@ -104,7 +109,8 @@ Status DBImpl::SyncClosedLogs(JobContext* job_context) {
 
 Status DBImpl::FlushMemTableToOutputFile(
     ColumnFamilyData* cfd, const MutableCFOptions& mutable_cf_options,
-    bool* made_progress, JobContext* job_context, LogBuffer* log_buffer) {
+    bool* made_progress, JobContext* job_context,
+    SuperVersionContext* superversion_context, LogBuffer* log_buffer) {
   mutex_.AssertHeld();
   assert(cfd->imm()->NumNotFlushed() != 0);
   assert(cfd->imm()->IsFlushPending());
@@ -119,15 +125,19 @@ Status DBImpl::FlushMemTableToOutputFile(
   }
   FlushJob flush_job(
       dbname_, cfd, immutable_db_options_, mutable_cf_options,
-      env_options_for_compaction_, versions_.get(), &mutex_, &shutting_down_,
-      snapshot_seqs, earliest_write_conflict_snapshot, snapshot_checker,
-      job_context, log_buffer, directories_.GetDbDir(), GetDataDir(cfd, 0U),
+      nullptr /* memtable_id */, env_options_for_compaction_, versions_.get(),
+      &mutex_, &shutting_down_, snapshot_seqs, earliest_write_conflict_snapshot,
+      snapshot_checker, job_context, log_buffer, directories_.GetDbDir(),
+      GetDataDir(cfd, 0U),
       GetCompressionFlush(*cfd->ioptions(), mutable_cf_options), stats_,
-      &event_logger_, mutable_cf_options.report_bg_io_stats);
+      &event_logger_, mutable_cf_options.report_bg_io_stats,
+      true /* sync_output_directory */, true /* write_manifest */);
 
   FileMetaData file_meta;
 
+  TEST_SYNC_POINT("DBImpl::FlushMemTableToOutputFile:BeforePickMemtables");
   flush_job.PickMemTable();
+  TEST_SYNC_POINT("DBImpl::FlushMemTableToOutputFile:AfterPickMemtables");
 
 #ifndef ROCKSDB_LITE
   // may temporarily unlock and lock the mutex.
@@ -137,7 +147,7 @@ Status DBImpl::FlushMemTableToOutputFile(
 
   Status s;
   if (logfile_number_ > 0 &&
-      versions_->GetColumnFamilySet()->NumberOfColumnFamilies() > 0) {
+      versions_->GetColumnFamilySet()->NumberOfColumnFamilies() > 1) {
     // If there are more than one column families, we need to make sure that
     // all the log files except the most recent one are synced. Otherwise if
     // the host crashes after flushing and before WAL is persistent, the
@@ -145,6 +155,8 @@ Status DBImpl::FlushMemTableToOutputFile(
     // other column families are missing.
     // SyncClosedLogs() may unlock and re-lock the db_mutex.
     s = SyncClosedLogs(job_context);
+  } else {
+    TEST_SYNC_POINT("DBImpl::SyncClosedLogs:Skip");
   }
 
   // Within flush_job.Run, rocksdb may call event listener to notify
@@ -160,10 +172,10 @@ Status DBImpl::FlushMemTableToOutputFile(
   }
 
   if (s.ok()) {
-    InstallSuperVersionAndScheduleWork(
-        cfd, &job_context->superversion_contexts[0], mutable_cf_options);
+    InstallSuperVersionAndScheduleWork(cfd, superversion_context,
+                                       mutable_cf_options);
     if (made_progress) {
-      *made_progress = 1;
+      *made_progress = true;
     }
     VersionStorageInfo::LevelSummaryStorage tmp;
     ROCKS_LOG_BUFFER(log_buffer, "[%s] Level summary: %s\n",
@@ -200,6 +212,252 @@ Status DBImpl::FlushMemTableToOutputFile(
   return s;
 }
 
+Status DBImpl::FlushMemTablesToOutputFiles(
+    const autovector<BGFlushArg>& bg_flush_args, bool* made_progress,
+    JobContext* job_context, LogBuffer* log_buffer) {
+  if (immutable_db_options_.atomic_flush) {
+    return AtomicFlushMemTablesToOutputFiles(bg_flush_args, made_progress,
+                                             job_context, log_buffer);
+  }
+  Status s;
+  for (auto& arg : bg_flush_args) {
+    ColumnFamilyData* cfd = arg.cfd_;
+    const MutableCFOptions& mutable_cf_options =
+        *cfd->GetLatestMutableCFOptions();
+    SuperVersionContext* superversion_context = arg.superversion_context_;
+    s = FlushMemTableToOutputFile(cfd, mutable_cf_options, made_progress,
+                                  job_context, superversion_context,
+                                  log_buffer);
+    if (!s.ok()) {
+      break;
+    }
+  }
+  return s;
+}
+
+/*
+ * Atomically flushes multiple column families.
+ *
+ * For each column family, all memtables with ID smaller than or equal to the
+ * ID specified in bg_flush_args will be flushed. Only after all column
+ * families finish flush will this function commit to MANIFEST. If any of the
+ * column families are not flushed successfully, this function does not have
+ * any side-effect on the state of the database.
+ */
+Status DBImpl::AtomicFlushMemTablesToOutputFiles(
+    const autovector<BGFlushArg>& bg_flush_args, bool* made_progress,
+    JobContext* job_context, LogBuffer* log_buffer) {
+  mutex_.AssertHeld();
+
+  autovector<ColumnFamilyData*> cfds;
+  for (const auto& arg : bg_flush_args) {
+    cfds.emplace_back(arg.cfd_);
+  }
+
+#ifndef NDEBUG
+  for (const auto cfd : cfds) {
+    assert(cfd->imm()->NumNotFlushed() != 0);
+    assert(cfd->imm()->IsFlushPending());
+  }
+#endif /* !NDEBUG */
+
+  SequenceNumber earliest_write_conflict_snapshot;
+  std::vector<SequenceNumber> snapshot_seqs =
+      snapshots_.GetAll(&earliest_write_conflict_snapshot);
+
+  auto snapshot_checker = snapshot_checker_.get();
+  if (use_custom_gc_ && snapshot_checker == nullptr) {
+    snapshot_checker = DisableGCSnapshotChecker::Instance();
+  }
+  autovector<Directory*> distinct_output_dirs;
+  std::vector<FlushJob> jobs;
+  int num_cfs = static_cast<int>(cfds.size());
+  for (int i = 0; i < num_cfs; ++i) {
+    auto cfd = cfds[i];
+    Directory* data_dir = GetDataDir(cfd, 0U);
+
+    // Add to distinct output directories if eligible. Use linear search. Since
+    // the number of elements in the vector is not large, performance should be
+    // tolerable.
+    bool found = false;
+    for (const auto dir : distinct_output_dirs) {
+      if (dir == data_dir) {
+        found = true;
+        break;
+      }
+    }
+    if (!found) {
+      distinct_output_dirs.emplace_back(data_dir);
+    }
+
+    const MutableCFOptions& mutable_cf_options =
+        *cfd->GetLatestMutableCFOptions();
+    const uint64_t* max_memtable_id = &(bg_flush_args[i].max_memtable_id_);
+    jobs.emplace_back(
+        dbname_, cfds[i], immutable_db_options_, mutable_cf_options,
+        max_memtable_id, env_options_for_compaction_, versions_.get(), &mutex_,
+        &shutting_down_, snapshot_seqs, earliest_write_conflict_snapshot,
+        snapshot_checker, job_context, log_buffer, directories_.GetDbDir(),
+        data_dir, GetCompressionFlush(*cfd->ioptions(), mutable_cf_options),
+        stats_, &event_logger_, mutable_cf_options.report_bg_io_stats,
+        false /* sync_output_directory */, false /* write_manifest */);
+    jobs.back().PickMemTable();
+  }
+
+  autovector<FileMetaData> file_meta;
+  Status s;
+  assert(num_cfs == static_cast<int>(jobs.size()));
+
+  for (int i = 0; i != num_cfs; ++i) {
+    file_meta.emplace_back();
+
+#ifndef ROCKSDB_LITE
+    const MutableCFOptions& mutable_cf_options =
+        *cfds[i]->GetLatestMutableCFOptions();
+    // may temporarily unlock and lock the mutex.
+    NotifyOnFlushBegin(cfds[i], &file_meta[i], mutable_cf_options,
+                       job_context->job_id, jobs[i].GetTableProperties());
+#endif /* !ROCKSDB_LITE */
+  }
+
+  if (logfile_number_ > 0) {
+    // TODO (yanqin) investigate whether we should sync the closed logs for
+    // single column family case.
+    s = SyncClosedLogs(job_context);
+  }
+
+  // exec_status stores the execution status of flush_jobs as
+  // <bool /* executed */, Status /* status code */>
+  autovector<std::pair<bool, Status>> exec_status;
+  for (int i = 0; i != num_cfs; ++i) {
+    // Initially all jobs are not executed, with status OK.
+    std::pair<bool, Status> elem(false, Status::OK());
+    exec_status.emplace_back(elem);
+  }
+
+  if (s.ok()) {
+    // TODO (yanqin): parallelize jobs with threads.
+    for (int i = 1; i != num_cfs; ++i) {
+      exec_status[i].second =
+          jobs[i].Run(&logs_with_prep_tracker_, &file_meta[i]);
+      exec_status[i].first = true;
+      if (!exec_status[i].second.ok()) {
+        s = exec_status[i].second;
+        break;
+      }
+    }
+    if (num_cfs > 1) {
+      TEST_SYNC_POINT(
+          "DBImpl::AtomicFlushMemTablesToOutputFiles:SomeFlushJobsComplete:1");
+      TEST_SYNC_POINT(
+          "DBImpl::AtomicFlushMemTablesToOutputFiles:SomeFlushJobsComplete:2");
+    }
+    if (s.ok()) {
+      exec_status[0].second =
+          jobs[0].Run(&logs_with_prep_tracker_, &file_meta[0]);
+      exec_status[0].first = true;
+      if (!exec_status[0].second.ok()) {
+        s = exec_status[0].second;
+      }
+    }
+  }
+
+  if (s.ok()) {
+    // Sync on all distinct output directories.
+    for (auto dir : distinct_output_dirs) {
+      if (dir != nullptr) {
+        s = dir->Fsync();
+        if (!s.ok()) {
+          break;
+        }
+      }
+    }
+
+    if (s.ok()) {
+      autovector<const autovector<MemTable*>*> mems_list;
+      for (int i = 0; i != num_cfs; ++i) {
+        const auto& mems = jobs[i].GetMemTables();
+        mems_list.emplace_back(&mems);
+      }
+      autovector<ColumnFamilyData*> all_cfds;
+      autovector<MemTableList*> imm_lists;
+      autovector<const MutableCFOptions*> mutable_cf_options_list;
+      for (auto cfd : *versions_->GetColumnFamilySet()) {
+        all_cfds.emplace_back(cfd);
+        imm_lists.emplace_back(cfd->imm());
+        mutable_cf_options_list.emplace_back(cfd->GetLatestMutableCFOptions());
+      }
+
+      s = MemTableList::TryInstallMemtableFlushResults(
+          imm_lists, all_cfds, mutable_cf_options_list, mems_list,
+          &atomic_flush_commit_in_progress_, &logs_with_prep_tracker_,
+          versions_.get(), &mutex_, file_meta, &job_context->memtables_to_free,
+          directories_.GetDbDir(), log_buffer);
+    }
+  }
+
+  if (s.ok()) {
+    assert(num_cfs ==
+           static_cast<int>(job_context->superversion_contexts.size()));
+    for (int i = 0; i != num_cfs; ++i) {
+      InstallSuperVersionAndScheduleWork(cfds[i],
+                                         &job_context->superversion_contexts[i],
+                                         *cfds[i]->GetLatestMutableCFOptions());
+      VersionStorageInfo::LevelSummaryStorage tmp;
+      ROCKS_LOG_BUFFER(log_buffer, "[%s] Level summary: %s\n",
+                       cfds[i]->GetName().c_str(),
+                       cfds[i]->current()->storage_info()->LevelSummary(&tmp));
+    }
+    if (made_progress) {
+      *made_progress = true;
+    }
+#ifndef ROCKSDB_LITE
+    auto sfm = static_cast<SstFileManagerImpl*>(
+        immutable_db_options_.sst_file_manager.get());
+    for (int i = 0; i != num_cfs; ++i) {
+      NotifyOnFlushCompleted(cfds[i], &file_meta[i],
+                             *cfds[i]->GetLatestMutableCFOptions(),
+                             job_context->job_id, jobs[i].GetTableProperties());
+      if (sfm) {
+        std::string file_path = MakeTableFileName(
+            cfds[i]->ioptions()->cf_paths[0].path, file_meta[i].fd.GetNumber());
+        sfm->OnAddFile(file_path);
+        if (sfm->IsMaxAllowedSpaceReached() &&
+            error_handler_.GetBGError().ok()) {
+          Status new_bg_error =
+              Status::SpaceLimit("Max allowed space was reached");
+          error_handler_.SetBGError(new_bg_error,
+                                    BackgroundErrorReason::kFlush);
+        }
+      }
+    }
+#endif  // ROCKSDB_LITE
+  }
+
+  if (!s.ok()) {
+    // Have to cancel the flush jobs that have NOT executed because we need to
+    // unref the versions.
+    for (int i = 0; i != num_cfs; ++i) {
+      if (!exec_status[i].first) {
+        jobs[i].Cancel();
+      }
+    }
+    if (!s.IsShutdownInProgress()) {
+      for (int i = 0; i != num_cfs; ++i) {
+        if (exec_status[i].first && exec_status[i].second.ok()) {
+          auto& mems = jobs[i].GetMemTables();
+          cfds[i]->imm()->RollbackMemtableFlush(mems,
+                                                file_meta[i].fd.GetNumber());
+        }
+      }
+      Status new_bg_error = s;
+      error_handler_.SetBGError(new_bg_error, BackgroundErrorReason::kFlush);
+    }
+  }
+
+  return s;
+}
+
 void DBImpl::NotifyOnFlushBegin(ColumnFamilyData* cfd, FileMetaData* file_meta,
                                 const MutableCFOptions& mutable_cf_options,
                                 int job_id, TableProperties prop) {
@@ -324,60 +582,21 @@ Status DBImpl::CompactRange(const CompactRangeOptions& options,
     CleanupSuperVersion(super_version);
   }
 
-  if (!options.allow_write_stall && flush_needed) {
-    InstrumentedMutexLock l(&mutex_);
-    uint64_t orig_active_memtable_id = cfd->mem()->GetID();
-    WriteStallCondition write_stall_condition = WriteStallCondition::kNormal;
-    do {
-      if (write_stall_condition != WriteStallCondition::kNormal) {
-        TEST_SYNC_POINT("DBImpl::CompactRange:StallWait");
-        ROCKS_LOG_INFO(immutable_db_options_.info_log,
-                       "[%s] CompactRange waiting on stall conditions to clear",
-                       cfd->GetName().c_str());
-        bg_cv_.Wait();
-      }
-      if (cfd->IsDropped() || shutting_down_.load(std::memory_order_acquire)) {
-        return Status::ShutdownInProgress();
-      }
-
-      uint64_t earliest_memtable_id =
-          std::min(cfd->mem()->GetID(), cfd->imm()->GetEarliestMemTableID());
-      if (earliest_memtable_id > orig_active_memtable_id) {
-        // We waited so long that the memtable we were originally waiting on was
-        // flushed.
-        flush_needed = false;
-        break;
-      }
-
-      const auto& mutable_cf_options = *cfd->GetLatestMutableCFOptions();
-      const auto* vstorage = cfd->current()->storage_info();
-
-      // Skip stalling check if we're below auto-flush and auto-compaction
-      // triggers. If it stalled in these conditions, that'd mean the stall
-      // triggers are so low that stalling is needed for any background work. In
-      // that case we shouldn't wait since background work won't be scheduled.
-      if (cfd->imm()->NumNotFlushed() <
-              cfd->ioptions()->min_write_buffer_number_to_merge &&
-          vstorage->l0_delay_trigger_count() <
-              mutable_cf_options.level0_file_num_compaction_trigger) {
-        break;
-      }
-
-      // check whether one extra immutable memtable or an extra L0 file would
-      // cause write stalling mode to be entered. It could still enter stall
-      // mode due to pending compaction bytes, but that's less common
-      write_stall_condition =
-          ColumnFamilyData::GetWriteStallConditionAndCause(
-              cfd->imm()->NumNotFlushed() + 1,
-              vstorage->l0_delay_trigger_count() + 1,
-              vstorage->estimated_compaction_needed_bytes(), mutable_cf_options)
-              .first;
-    } while (write_stall_condition != WriteStallCondition::kNormal);
-  }
-  TEST_SYNC_POINT("DBImpl::CompactRange:StallWaitDone");
   Status s;
   if (flush_needed) {
-    s = FlushMemTable(cfd, FlushOptions(), FlushReason::kManualCompaction);
+    FlushOptions fo;
+    fo.allow_write_stall = options.allow_write_stall;
+    if (immutable_db_options_.atomic_flush) {
+      autovector<ColumnFamilyData*> cfds;
+      mutex_.Lock();
+      SelectColumnFamiliesForAtomicFlush(&cfds);
+      mutex_.Unlock();
+      s = AtomicFlushMemTables(cfds, fo, FlushReason::kManualCompaction,
+                               false /* writes_stopped */);
+    } else {
+      s = FlushMemTable(cfd, fo, FlushReason::kManualCompaction,
+                        false /* writes_stopped*/);
+    }
     if (!s.ok()) {
       LogFlush(immutable_db_options_.info_log);
       return s;
@@ -508,7 +727,7 @@ Status DBImpl::CompactFiles(const CompactionOptions& compact_options,
                        immutable_db_options_.info_log.get());
 
   // Perform CompactFiles
-  SuperVersion* sv = cfd->GetReferencedSuperVersion(&mutex_);
+  TEST_SYNC_POINT("TestCompactFiles::IngestExternalFile2");
   {
     InstrumentedMutexLock l(&mutex_);
 
@@ -516,15 +735,16 @@ Status DBImpl::CompactFiles(const CompactionOptions& compact_options,
     // IngestExternalFile() calls to finish.
     WaitForIngestFile();
 
-    s = CompactFilesImpl(compact_options, cfd, sv->current, input_file_names,
+    // We need to get current after `WaitForIngestFile`, because
+    // `IngestExternalFile` may add files that overlap with `input_file_names`
+    auto* current = cfd->current();
+    current->Ref();
+
+    s = CompactFilesImpl(compact_options, cfd, current, input_file_names,
                          output_file_names, output_level, output_path_id,
                          &job_context, &log_buffer);
-  }
-  if (sv->Unref()) {
-    mutex_.Lock();
-    sv->Cleanup();
-    mutex_.Unlock();
-    delete sv;
+
+    current->Unref();
   }
 
   // Find and delete obsolete files
@@ -570,7 +790,7 @@ Status DBImpl::CompactFilesImpl(
   }
 
   std::unordered_set<uint64_t> input_set;
-  for (auto file_name : input_file_names) {
+  for (const auto& file_name : input_file_names) {
     input_set.insert(TableFileNameToNumber(file_name));
   }
 
@@ -602,7 +822,7 @@ Status DBImpl::CompactFilesImpl(
     return s;
   }
 
-  for (auto inputs : input_files) {
+  for (const auto& inputs : input_files) {
     if (cfd->compaction_picker()->AreFilesInCompaction(inputs.files)) {
       return Status::Aborted(
           "Some of the necessary compaction input "
@@ -612,7 +832,7 @@ Status DBImpl::CompactFilesImpl(
   bool sfm_reserved_compact_space = false;
   // First check if we have enough room to do the compaction
   bool enough_room = EnoughRoomForCompaction(
-      input_files, &sfm_reserved_compact_space, log_buffer);
+      cfd, input_files, &sfm_reserved_compact_space, log_buffer);
 
   if (!enough_room) {
     // m's vars will get set properly at the end of this function,
@@ -623,7 +843,7 @@ Status DBImpl::CompactFilesImpl(
   // At this point, CompactFiles will be run.
   bg_compaction_scheduled_++;
 
-  unique_ptr<Compaction> c;
+  std::unique_ptr<Compaction> c;
   assert(cfd->compaction_picker());
   c.reset(cfd->compaction_picker()->CompactFiles(
       compact_options, input_files, output_level, version->storage_info(),
@@ -767,6 +987,69 @@ Status DBImpl::ContinueBackgroundWork() {
   return Status::OK();
 }
 
+void DBImpl::NotifyOnCompactionBegin(ColumnFamilyData* cfd,
+                                     Compaction *c, const Status &st,
+                                     const CompactionJobStats& job_stats,
+                                     int job_id) {
+#ifndef ROCKSDB_LITE
+  if (immutable_db_options_.listeners.empty()) {
+    return;
+  }
+  mutex_.AssertHeld();
+  if (shutting_down_.load(std::memory_order_acquire)) {
+    return;
+  }
+  Version* current = cfd->current();
+  current->Ref();
+  // release lock while notifying events
+  mutex_.Unlock();
+  TEST_SYNC_POINT("DBImpl::NotifyOnCompactionBegin::UnlockMutex");
+  {
+    CompactionJobInfo info;
+    info.cf_name = cfd->GetName();
+    info.status = st;
+    info.thread_id = env_->GetThreadID();
+    info.job_id = job_id;
+    info.base_input_level = c->start_level();
+    info.output_level = c->output_level();
+    info.stats = job_stats;
+    info.table_properties = c->GetOutputTableProperties();
+    info.compaction_reason = c->compaction_reason();
+    info.compression = c->output_compression();
+    for (size_t i = 0; i < c->num_input_levels(); ++i) {
+      for (const auto fmd : *c->inputs(i)) {
+        auto fn = TableFileName(c->immutable_cf_options()->cf_paths,
+                                fmd->fd.GetNumber(), fmd->fd.GetPathId());
+        info.input_files.push_back(fn);
+        if (info.table_properties.count(fn) == 0) {
+          std::shared_ptr<const TableProperties> tp;
+          auto s = current->GetTableProperties(&tp, fmd, &fn);
+          if (s.ok()) {
+            info.table_properties[fn] = tp;
+          }
+        }
+      }
+    }
+    for (const auto newf : c->edit()->GetNewFiles()) {
+      info.output_files.push_back(TableFileName(
+          c->immutable_cf_options()->cf_paths, newf.second.fd.GetNumber(),
+          newf.second.fd.GetPathId()));
+    }
+    for (auto listener : immutable_db_options_.listeners) {
+      listener->OnCompactionBegin(this, info);
+    }
+  }
+  mutex_.Lock();
+  current->Unref();
+#else
+  (void)cfd;
+  (void)c;
+  (void)st;
+  (void)job_stats;
+  (void)job_id;
+#endif  // ROCKSDB_LITE
+}
+
 void DBImpl::NotifyOnCompactionCompleted(
     ColumnFamilyData* cfd, Compaction* c, const Status& st,
     const CompactionJobStats& compaction_job_stats, const int job_id) {
@@ -785,6 +1068,7 @@ void DBImpl::NotifyOnCompactionCompleted(
   TEST_SYNC_POINT("DBImpl::NotifyOnCompactionCompleted::UnlockMutex");
   {
     CompactionJobInfo info;
+    info.cf_id = cfd->GetID();
     info.cf_name = cfd->GetName();
     info.status = st;
     info.thread_id = env_->GetThreadID();
@@ -934,14 +1218,62 @@ Status DBImpl::Flush(const FlushOptions& flush_options,
   auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
   ROCKS_LOG_INFO(immutable_db_options_.info_log, "[%s] Manual flush start.",
                  cfh->GetName().c_str());
-  Status s =
-      FlushMemTable(cfh->cfd(), flush_options, FlushReason::kManualFlush);
+  Status s;
+  if (immutable_db_options_.atomic_flush) {
+    s = AtomicFlushMemTables({cfh->cfd()}, flush_options,
+                             FlushReason::kManualFlush);
+  } else {
+    s = FlushMemTable(cfh->cfd(), flush_options, FlushReason::kManualFlush);
+  }
+
   ROCKS_LOG_INFO(immutable_db_options_.info_log,
                  "[%s] Manual flush finished, status: %s\n",
                  cfh->GetName().c_str(), s.ToString().c_str());
   return s;
 }
 
+Status DBImpl::Flush(const FlushOptions& flush_options,
+                     const std::vector<ColumnFamilyHandle*>& column_families) {
+  Status s;
+  if (!immutable_db_options_.atomic_flush) {
+    for (auto cfh : column_families) {
+      s = Flush(flush_options, cfh);
+      if (!s.ok()) {
+        break;
+      }
+    }
+  } else {
+    ROCKS_LOG_INFO(immutable_db_options_.info_log,
+                   "Manual atomic flush start.\n"
+                   "=====Column families:=====");
+    for (auto cfh : column_families) {
+      auto cfhi = static_cast<ColumnFamilyHandleImpl*>(cfh);
+      ROCKS_LOG_INFO(immutable_db_options_.info_log, "%s",
+                     cfhi->GetName().c_str());
+    }
+    ROCKS_LOG_INFO(immutable_db_options_.info_log,
+                   "=====End of column families list=====");
+    autovector<ColumnFamilyData*> cfds;
+    std::for_each(column_families.begin(), column_families.end(),
+                  [&cfds](ColumnFamilyHandle* elem) {
+                    auto cfh = static_cast<ColumnFamilyHandleImpl*>(elem);
+                    cfds.emplace_back(cfh->cfd());
+                  });
+    s = AtomicFlushMemTables(cfds, flush_options, FlushReason::kManualFlush);
+    ROCKS_LOG_INFO(immutable_db_options_.info_log,
+                   "Manual atomic flush finished, status: %s\n",
+                   "=====Column families:=====", s.ToString().c_str());
+    for (auto cfh : column_families) {
+      auto cfhi = static_cast<ColumnFamilyHandleImpl*>(cfh);
+      ROCKS_LOG_INFO(immutable_db_options_.info_log, "%s",
+                     cfhi->GetName().c_str());
+    }
+    ROCKS_LOG_INFO(immutable_db_options_.info_log,
+                   "=====End of column families list=====");
+  }
+  return s;
+}
+
 Status DBImpl::RunManualCompaction(ColumnFamilyData* cfd, int input_level,
                                    int output_level, uint32_t output_path_id,
                                    uint32_t max_subcompactions,
@@ -1072,69 +1404,279 @@ Status DBImpl::RunManualCompaction(ColumnFamilyData* cfd, int input_level,
   return manual.status;
 }
 
+void DBImpl::GenerateFlushRequest(const autovector<ColumnFamilyData*>& cfds,
+                                  FlushRequest* req) {
+  assert(req != nullptr);
+  for (const auto cfd : cfds) {
+    if (nullptr == cfd) {
+      // cfd may be null, see DBImpl::ScheduleFlushes
+      continue;
+    }
+    uint64_t max_memtable_id = cfd->imm()->GetLatestMemTableID();
+    req->emplace_back(cfd, max_memtable_id);
+  }
+}
+
 Status DBImpl::FlushMemTable(ColumnFamilyData* cfd,
                              const FlushOptions& flush_options,
                              FlushReason flush_reason, bool writes_stopped) {
   Status s;
   uint64_t flush_memtable_id = 0;
+  if (!flush_options.allow_write_stall) {
+    bool flush_needed = true;
+    s = WaitUntilFlushWouldNotStallWrites(cfd, &flush_needed);
+    TEST_SYNC_POINT("DBImpl::FlushMemTable:StallWaitDone");
+    if (!s.ok() || !flush_needed) {
+      return s;
+    }
+  }
+  FlushRequest flush_req;
   {
     WriteContext context;
     InstrumentedMutexLock guard_lock(&mutex_);
 
-    if (cfd->imm()->NumNotFlushed() == 0 && cfd->mem()->IsEmpty() &&
-        cached_recoverable_state_empty_.load()) {
-      // Nothing to flush
-      return Status::OK();
-    }
-
     WriteThread::Writer w;
     if (!writes_stopped) {
       write_thread_.EnterUnbatched(&w, &mutex_);
     }
 
-    // SwitchMemtable() will release and reacquire mutex during execution
-    s = SwitchMemtable(cfd, &context);
-    flush_memtable_id = cfd->imm()->GetLatestMemTableID();
+    if (cfd->imm()->NumNotFlushed() != 0 || !cfd->mem()->IsEmpty() ||
+        !cached_recoverable_state_empty_.load()) {
+      s = SwitchMemtable(cfd, &context);
+      flush_memtable_id = cfd->imm()->GetLatestMemTableID();
+      flush_req.emplace_back(cfd, flush_memtable_id);
+    }
+
+    if (s.ok() && !flush_req.empty()) {
+      for (auto& elem : flush_req) {
+        ColumnFamilyData* loop_cfd = elem.first;
+        loop_cfd->imm()->FlushRequested();
+      }
+      SchedulePendingFlush(flush_req, flush_reason);
+      MaybeScheduleFlushOrCompaction();
+    }
 
     if (!writes_stopped) {
       write_thread_.ExitUnbatched(&w);
     }
-
-    cfd->imm()->FlushRequested();
-
-    // schedule flush
-    SchedulePendingFlush(cfd, flush_reason);
-    MaybeScheduleFlushOrCompaction();
   }
 
   if (s.ok() && flush_options.wait) {
-    // Wait until the compaction completes
-    s = WaitForFlushMemTable(cfd, &flush_memtable_id);
+    autovector<ColumnFamilyData*> cfds;
+    autovector<const uint64_t*> flush_memtable_ids;
+    for (auto& iter : flush_req) {
+      cfds.push_back(iter.first);
+      flush_memtable_ids.push_back(&(iter.second));
+    }
+    s = WaitForFlushMemTables(cfds, flush_memtable_ids,
+                              (flush_reason == FlushReason::kErrorRecovery));
   }
   TEST_SYNC_POINT("FlushMemTableFinished");
   return s;
 }
 
-Status DBImpl::WaitForFlushMemTable(ColumnFamilyData* cfd,
-                                    const uint64_t* flush_memtable_id) {
+// Flush all elments in 'column_family_datas'
+// and atomically record the result to the MANIFEST.
+Status DBImpl::AtomicFlushMemTables(
+    const autovector<ColumnFamilyData*>& column_family_datas,
+    const FlushOptions& flush_options, FlushReason flush_reason,
+    bool writes_stopped) {
   Status s;
+  if (!flush_options.allow_write_stall) {
+    int num_cfs_to_flush = 0;
+    for (auto cfd : column_family_datas) {
+      bool flush_needed = true;
+      s = WaitUntilFlushWouldNotStallWrites(cfd, &flush_needed);
+      if (!s.ok()) {
+        return s;
+      } else if (flush_needed) {
+        ++num_cfs_to_flush;
+      }
+    }
+    if (0 == num_cfs_to_flush) {
+      return s;
+    }
+  }
+  FlushRequest flush_req;
+  autovector<ColumnFamilyData*> cfds;
+  {
+    WriteContext context;
+    InstrumentedMutexLock guard_lock(&mutex_);
+
+    WriteThread::Writer w;
+    if (!writes_stopped) {
+      write_thread_.EnterUnbatched(&w, &mutex_);
+    }
+
+    for (auto cfd : column_family_datas) {
+      if (cfd->IsDropped()) {
+        continue;
+      }
+      if (cfd->imm()->NumNotFlushed() != 0 || !cfd->mem()->IsEmpty() ||
+          !cached_recoverable_state_empty_.load()) {
+        cfds.emplace_back(cfd);
+      }
+    }
+    for (auto cfd : cfds) {
+      cfd->Ref();
+      s = SwitchMemtable(cfd, &context);
+      cfd->Unref();
+      if (!s.ok()) {
+        break;
+      }
+    }
+    if (s.ok()) {
+      AssignAtomicFlushSeq(cfds);
+      for (auto cfd : cfds) {
+        cfd->imm()->FlushRequested();
+      }
+      GenerateFlushRequest(cfds, &flush_req);
+      SchedulePendingFlush(flush_req, flush_reason);
+      MaybeScheduleFlushOrCompaction();
+    }
+
+    if (!writes_stopped) {
+      write_thread_.ExitUnbatched(&w);
+    }
+  }
+
+  if (s.ok() && flush_options.wait) {
+    autovector<const uint64_t*> flush_memtable_ids;
+    for (auto& iter : flush_req) {
+      flush_memtable_ids.push_back(&(iter.second));
+    }
+    s = WaitForFlushMemTables(cfds, flush_memtable_ids,
+                              (flush_reason == FlushReason::kErrorRecovery));
+  }
+  return s;
+}
+
+// Calling FlushMemTable(), whether from DB::Flush() or from Backup Engine, can
+// cause write stall, for example if one memtable is being flushed already.
+// This method tries to avoid write stall (similar to CompactRange() behavior)
+// it emulates how the SuperVersion / LSM would change if flush happens, checks
+// it against various constrains and delays flush if it'd cause write stall.
+// Called should check status and flush_needed to see if flush already happened.
+Status DBImpl::WaitUntilFlushWouldNotStallWrites(ColumnFamilyData* cfd,
+    bool* flush_needed) {
+  {
+    *flush_needed = true;
+    InstrumentedMutexLock l(&mutex_);
+    uint64_t orig_active_memtable_id = cfd->mem()->GetID();
+    WriteStallCondition write_stall_condition = WriteStallCondition::kNormal;
+    do {
+      if (write_stall_condition != WriteStallCondition::kNormal) {
+        // Same error handling as user writes: Don't wait if there's a
+        // background error, even if it's a soft error. We might wait here
+        // indefinitely as the pending flushes/compactions may never finish
+        // successfully, resulting in the stall condition lasting indefinitely
+        if (error_handler_.IsBGWorkStopped()) {
+          return error_handler_.GetBGError();
+        }
+
+        TEST_SYNC_POINT("DBImpl::WaitUntilFlushWouldNotStallWrites:StallWait");
+        ROCKS_LOG_INFO(immutable_db_options_.info_log,
+                       "[%s] WaitUntilFlushWouldNotStallWrites"
+                       " waiting on stall conditions to clear",
+                       cfd->GetName().c_str());
+        bg_cv_.Wait();
+      }
+      if (cfd->IsDropped() || shutting_down_.load(std::memory_order_acquire)) {
+        return Status::ShutdownInProgress();
+      }
+
+      uint64_t earliest_memtable_id =
+          std::min(cfd->mem()->GetID(), cfd->imm()->GetEarliestMemTableID());
+      if (earliest_memtable_id > orig_active_memtable_id) {
+        // We waited so long that the memtable we were originally waiting on was
+        // flushed.
+        *flush_needed = false;
+        return Status::OK();
+      }
+
+      const auto& mutable_cf_options = *cfd->GetLatestMutableCFOptions();
+      const auto* vstorage = cfd->current()->storage_info();
+
+      // Skip stalling check if we're below auto-flush and auto-compaction
+      // triggers. If it stalled in these conditions, that'd mean the stall
+      // triggers are so low that stalling is needed for any background work. In
+      // that case we shouldn't wait since background work won't be scheduled.
+      if (cfd->imm()->NumNotFlushed() <
+              cfd->ioptions()->min_write_buffer_number_to_merge &&
+          vstorage->l0_delay_trigger_count() <
+              mutable_cf_options.level0_file_num_compaction_trigger) {
+        break;
+      }
+
+      // check whether one extra immutable memtable or an extra L0 file would
+      // cause write stalling mode to be entered. It could still enter stall
+      // mode due to pending compaction bytes, but that's less common
+      write_stall_condition =
+          ColumnFamilyData::GetWriteStallConditionAndCause(
+              cfd->imm()->NumNotFlushed() + 1,
+              vstorage->l0_delay_trigger_count() + 1,
+              vstorage->estimated_compaction_needed_bytes(), mutable_cf_options)
+              .first;
+    } while (write_stall_condition != WriteStallCondition::kNormal);
+  }
+  return Status::OK();
+}
+
+// Wait for memtables to be flushed for multiple column families.
+// let N = cfds.size()
+// for i in [0, N),
+//  1) if flush_memtable_ids[i] is not null, then the memtables with lower IDs
+//     have to be flushed for THIS column family;
+//  2) if flush_memtable_ids[i] is null, then all memtables in THIS column
+//     family have to be flushed.
+// Finish waiting when ALL column families finish flushing memtables.
+// resuming_from_bg_err indicates whether the caller is trying to resume from
+// background error or in normal processing.
+Status DBImpl::WaitForFlushMemTables(
+    const autovector<ColumnFamilyData*>& cfds,
+    const autovector<const uint64_t*>& flush_memtable_ids,
+    bool resuming_from_bg_err) {
+  int num = static_cast<int>(cfds.size());
   // Wait until the compaction completes
   InstrumentedMutexLock l(&mutex_);
-  while (cfd->imm()->NumNotFlushed() > 0 && !error_handler_.IsDBStopped() &&
-         (flush_memtable_id == nullptr ||
-          cfd->imm()->GetEarliestMemTableID() <= *flush_memtable_id)) {
+  // If the caller is trying to resume from bg error, then
+  // error_handler_.IsDBStopped() is true.
+  while (resuming_from_bg_err || !error_handler_.IsDBStopped()) {
     if (shutting_down_.load(std::memory_order_acquire)) {
       return Status::ShutdownInProgress();
     }
-    if (cfd->IsDropped()) {
-      // FlushJob cannot flush a dropped CF, if we did not break here
-      // we will loop forever since cfd->imm()->NumNotFlushed() will never
-      // drop to zero
+    // If an error has occurred during resumption, then no need to wait.
+    if (!error_handler_.GetRecoveryError().ok()) {
+      break;
+    }
+    // Number of column families that have been dropped.
+    int num_dropped = 0;
+    // Number of column families that have finished flush.
+    int num_finished = 0;
+    for (int i = 0; i < num; ++i) {
+      if (cfds[i]->IsDropped()) {
+        ++num_dropped;
+      } else if (cfds[i]->imm()->NumNotFlushed() == 0 ||
+                 (flush_memtable_ids[i] != nullptr &&
+                  cfds[i]->imm()->GetEarliestMemTableID() >
+                      *flush_memtable_ids[i])) {
+        ++num_finished;
+      }
+    }
+    if (1 == num_dropped && 1 == num) {
       return Status::InvalidArgument("Cannot flush a dropped CF");
     }
+    // Column families involved in this flush request have either been dropped
+    // or finished flush. Then it's time to finish waiting.
+    if (num_dropped + num_finished == num) {
+      break;
+    }
     bg_cv_.Wait();
   }
-  if (error_handler_.IsDBStopped()) {
+  Status s;
+  // If not resuming from bg error, and an error has caused the DB to stop,
+  // then report the bg error to caller.
+  if (!resuming_from_bg_err && error_handler_.IsDBStopped()) {
     s = error_handler_.GetBGError();
   }
   return s;
@@ -1163,6 +1705,12 @@ void DBImpl::MaybeScheduleFlushOrCompaction() {
   if (bg_work_paused_ > 0) {
     // we paused the background work
     return;
+  } else if (error_handler_.IsBGWorkStopped() &&
+      !error_handler_.IsRecoveryInProgress()) {
+    // There has been a hard error and this call is not part of the recovery
+    // sequence. Bail out here so we don't get into an endless loop of
+    // scheduling BG work which will again call this function
+    return;
   } else if (shutting_down_.load(std::memory_order_acquire)) {
     // DB is being deleted; no more background compactions
     return;
@@ -1172,7 +1720,6 @@ void DBImpl::MaybeScheduleFlushOrCompaction() {
       env_->GetBackgroundThreads(Env::Priority::HIGH) == 0;
   while (!is_flush_pool_empty && unscheduled_flushes_ > 0 &&
          bg_flush_scheduled_ < bg_job_limits.max_flushes) {
-    unscheduled_flushes_--;
     bg_flush_scheduled_++;
     env_->Schedule(&DBImpl::BGWorkFlush, this, Env::Priority::HIGH, this);
   }
@@ -1183,7 +1730,6 @@ void DBImpl::MaybeScheduleFlushOrCompaction() {
     while (unscheduled_flushes_ > 0 &&
            bg_flush_scheduled_ + bg_compaction_scheduled_ <
                bg_job_limits.max_flushes) {
-      unscheduled_flushes_--;
       bg_flush_scheduled_++;
       env_->Schedule(&DBImpl::BGWorkFlush, this, Env::Priority::LOW, this);
     }
@@ -1192,6 +1738,12 @@ void DBImpl::MaybeScheduleFlushOrCompaction() {
   if (bg_compaction_paused_ > 0) {
     // we paused the background compaction
     return;
+  } else if (error_handler_.IsBGWorkStopped()) {
+    // Compaction is not part of the recovery sequence from a hard error. We
+    // might get here because recovery might do a flush and install a new
+    // super version, which will try to schedule pending compactions. Bail
+    // out here and let the higher level recovery handle compactions
+    return;
   }
 
   if (HasExclusiveManualCompaction()) {
@@ -1260,30 +1812,28 @@ ColumnFamilyData* DBImpl::PopFirstFromCompactionQueue() {
   return cfd;
 }
 
-void DBImpl::AddToFlushQueue(ColumnFamilyData* cfd, FlushReason flush_reason) {
-  assert(!cfd->queued_for_flush());
-  cfd->Ref();
-  flush_queue_.push_back(cfd);
-  cfd->set_queued_for_flush(true);
-  cfd->SetFlushReason(flush_reason);
-}
-
-ColumnFamilyData* DBImpl::PopFirstFromFlushQueue() {
+DBImpl::FlushRequest DBImpl::PopFirstFromFlushQueue() {
   assert(!flush_queue_.empty());
-  auto cfd = *flush_queue_.begin();
+  FlushRequest flush_req = flush_queue_.front();
+  assert(unscheduled_flushes_ >= static_cast<int>(flush_req.size()));
+  unscheduled_flushes_ -= static_cast<int>(flush_req.size());
   flush_queue_.pop_front();
-  assert(cfd->queued_for_flush());
-  cfd->set_queued_for_flush(false);
   // TODO: need to unset flush reason?
-  return cfd;
+  return flush_req;
 }
 
-void DBImpl::SchedulePendingFlush(ColumnFamilyData* cfd,
+void DBImpl::SchedulePendingFlush(const FlushRequest& flush_req,
                                   FlushReason flush_reason) {
-  if (!cfd->queued_for_flush() && cfd->imm()->IsFlushPending()) {
-    AddToFlushQueue(cfd, flush_reason);
-    ++unscheduled_flushes_;
+  if (flush_req.empty()) {
+    return;
   }
+  for (auto& iter : flush_req) {
+    ColumnFamilyData* cfd = iter.first;
+    cfd->Ref();
+    cfd->SetFlushReason(flush_reason);
+  }
+  unscheduled_flushes_ += static_cast<int>(flush_req.size());
+  flush_queue_.push_back(flush_req);
 }
 
 void DBImpl::SchedulePendingCompaction(ColumnFamilyData* cfd) {
@@ -1351,15 +1901,18 @@ void DBImpl::UnscheduleCallback(void* arg) {
 }
 
 Status DBImpl::BackgroundFlush(bool* made_progress, JobContext* job_context,
-                               LogBuffer* log_buffer) {
+                               LogBuffer* log_buffer, FlushReason* reason) {
   mutex_.AssertHeld();
 
   Status status;
+  *reason = FlushReason::kOthers;
+  // If BG work is stopped due to an error, but a recovery is in progress,
+  // that means this flush is part of the recovery. So allow it to go through
   if (!error_handler_.IsBGWorkStopped()) {
     if (shutting_down_.load(std::memory_order_acquire)) {
       status = Status::ShutdownInProgress();
     }
-  } else {
+  } else if (!error_handler_.IsRecoveryInProgress()) {
     status = error_handler_.GetBGError();
   }
 
@@ -1367,40 +1920,58 @@ Status DBImpl::BackgroundFlush(bool* made_progress, JobContext* job_context,
     return status;
   }
 
-  ColumnFamilyData* cfd = nullptr;
+  autovector<BGFlushArg> bg_flush_args;
+  std::vector<SuperVersionContext>& superversion_contexts =
+      job_context->superversion_contexts;
   while (!flush_queue_.empty()) {
     // This cfd is already referenced
-    auto first_cfd = PopFirstFromFlushQueue();
+    const FlushRequest& flush_req = PopFirstFromFlushQueue();
+    superversion_contexts.clear();
+    superversion_contexts.reserve(flush_req.size());
 
-    if (first_cfd->IsDropped() || !first_cfd->imm()->IsFlushPending()) {
-      // can't flush this CF, try next one
-      if (first_cfd->Unref()) {
-        delete first_cfd;
+    for (const auto& iter : flush_req) {
+      ColumnFamilyData* cfd = iter.first;
+      if (cfd->IsDropped() || !cfd->imm()->IsFlushPending()) {
+        // can't flush this CF, try next one
+        if (cfd->Unref()) {
+          delete cfd;
+        }
+        continue;
       }
-      continue;
+      superversion_contexts.emplace_back(SuperVersionContext(true));
+      bg_flush_args.emplace_back(cfd, iter.second,
+                                 &(superversion_contexts.back()));
+    }
+    if (!bg_flush_args.empty()) {
+      break;
     }
-
-    // found a flush!
-    cfd = first_cfd;
-    break;
   }
 
-  if (cfd != nullptr) {
-    const MutableCFOptions mutable_cf_options =
-        *cfd->GetLatestMutableCFOptions();
+  if (!bg_flush_args.empty()) {
     auto bg_job_limits = GetBGJobLimits();
-    ROCKS_LOG_BUFFER(
-        log_buffer,
-        "Calling FlushMemTableToOutputFile with column "
-        "family [%s], flush slots available %d, compaction slots available %d, "
-        "flush slots scheduled %d, compaction slots scheduled %d",
-        cfd->GetName().c_str(), bg_job_limits.max_flushes,
-        bg_job_limits.max_compactions, bg_flush_scheduled_,
-        bg_compaction_scheduled_);
-    status = FlushMemTableToOutputFile(cfd, mutable_cf_options, made_progress,
-                                       job_context, log_buffer);
-    if (cfd->Unref()) {
-      delete cfd;
+    for (const auto& arg : bg_flush_args) {
+      ColumnFamilyData* cfd = arg.cfd_;
+      ROCKS_LOG_BUFFER(
+          log_buffer,
+          "Calling FlushMemTableToOutputFile with column "
+          "family [%s], flush slots available %d, compaction slots available "
+          "%d, "
+          "flush slots scheduled %d, compaction slots scheduled %d",
+          cfd->GetName().c_str(), bg_job_limits.max_flushes,
+          bg_job_limits.max_compactions, bg_flush_scheduled_,
+          bg_compaction_scheduled_);
+    }
+    status = FlushMemTablesToOutputFiles(bg_flush_args, made_progress,
+                                         job_context, log_buffer);
+    // All the CFDs in the FlushReq must have the same flush reason, so just
+    // grab the first one
+    *reason = bg_flush_args[0].cfd_->GetFlushReason();
+    for (auto& arg : bg_flush_args) {
+      ColumnFamilyData* cfd = arg.cfd_;
+      if (cfd->Unref()) {
+        delete cfd;
+        arg.cfd_ = nullptr;
+      }
     }
   }
   return status;
@@ -1421,9 +1992,12 @@ void DBImpl::BackgroundCallFlush() {
 
     auto pending_outputs_inserted_elem =
         CaptureCurrentFileNumberInPendingOutputs();
+    FlushReason reason;
 
-    Status s = BackgroundFlush(&made_progress, &job_context, &log_buffer);
-    if (!s.ok() && !s.IsShutdownInProgress()) {
+    Status s =
+        BackgroundFlush(&made_progress, &job_context, &log_buffer, &reason);
+    if (!s.ok() && !s.IsShutdownInProgress() &&
+        reason != FlushReason::kErrorRecovery) {
       // Wait a little bit before retrying background flush in
       // case this is an environmental problem and we do not want to
       // chew up resources for failed flushes for the duration of
@@ -1442,6 +2016,7 @@ void DBImpl::BackgroundCallFlush() {
       mutex_.Lock();
     }
 
+    TEST_SYNC_POINT("DBImpl::BackgroundCallFlush:FlushFinish:0");
     ReleaseFileNumberFromPendingOutputs(pending_outputs_inserted_elem);
 
     // If flush failed, we want to delete all temporary files that we might have
@@ -1464,6 +2039,7 @@ void DBImpl::BackgroundCallFlush() {
       job_context.Clean();
       mutex_.Lock();
     }
+    TEST_SYNC_POINT("DBImpl::BackgroundCallFlush:ContextCleanedUp");
 
     assert(num_running_flushes_ > 0);
     num_running_flushes_--;
@@ -1483,7 +2059,6 @@ void DBImpl::BackgroundCallCompaction(PrepickedCompaction* prepicked_compaction,
   bool made_progress = false;
   JobContext job_context(next_job_id_.fetch_add(1), true);
   TEST_SYNC_POINT("BackgroundCallCompaction:0");
-  MaybeDumpStats();
   LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL,
                        immutable_db_options_.info_log.get());
   {
@@ -1594,7 +2169,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
   TEST_SYNC_POINT("DBImpl::BackgroundCompaction:Start");
 
   bool is_manual = (manual_compaction != nullptr);
-  unique_ptr<Compaction> c;
+  std::unique_ptr<Compaction> c;
   if (prepicked_compaction != nullptr &&
       prepicked_compaction->compaction != nullptr) {
     c.reset(prepicked_compaction->compaction);
@@ -1613,6 +2188,11 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     }
   } else {
     status = error_handler_.GetBGError();
+    // If we get here, it means a hard error happened after this compaction
+    // was scheduled by MaybeScheduleFlushOrCompaction(), but before it got
+    // a chance to execute. Since we didn't pop a cfd from the compaction
+    // queue, increment unscheduled_compactions_
+    unscheduled_compactions_++;
   }
 
   if (!status.ok()) {
@@ -1622,6 +2202,10 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
       manual_compaction->in_progress = false;
       manual_compaction = nullptr;
     }
+    if (c) {
+      c->ReleaseCompactionFiles(status);
+      c.reset();
+    }
     return status;
   }
 
@@ -1648,7 +2232,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     } else {
       // First check if we have enough room to do the compaction
       bool enough_room = EnoughRoomForCompaction(
-          *(c->inputs()), &sfm_reserved_compact_space, log_buffer);
+          m->cfd, *(c->inputs()), &sfm_reserved_compact_space, log_buffer);
 
       if (!enough_room) {
         // Then don't do the compaction
@@ -1711,7 +2295,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
 
       if (c != nullptr) {
         bool enough_room = EnoughRoomForCompaction(
-            *(c->inputs()), &sfm_reserved_compact_space, log_buffer);
+            cfd, *(c->inputs()), &sfm_reserved_compact_space, log_buffer);
 
         if (!enough_room) {
           // Then don't do the compaction
@@ -1768,6 +2352,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
 
     compaction_job_stats.num_input_files = c->num_input_files(0);
 
+    NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
+                            compaction_job_stats, job_context->job_id);
+
     for (const auto& f : *c->inputs(0)) {
       c->edit()->DeleteFile(c->level(), f->fd.GetNumber());
     }
@@ -1792,6 +2379,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
 
     compaction_job_stats.num_input_files = c->num_input_files(0);
 
+    NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
+                            compaction_job_stats, job_context->job_id);
+
     // Move files to next level
     int32_t moved_files = 0;
     int64_t moved_bytes = 0;
@@ -1891,6 +2481,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
         &compaction_job_stats);
     compaction_job.Prepare();
 
+    NotifyOnCompactionBegin(c->column_family_data(), c.get(), status,
+                            compaction_job_stats, job_context->job_id);
+
     mutex_.Unlock();
     compaction_job.Run();
     TEST_SYNC_POINT("DBImpl::BackgroundCompaction:NonTrivial:AfterRun");
@@ -1920,8 +2513,6 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     NotifyOnCompactionCompleted(c->column_family_data(), c.get(), status,
                                 compaction_job_stats, job_context->job_id);
   }
-  // this will unref its input_version and column_family_data
-  c.reset();
 
   if (status.ok() || status.IsCompactionTooLarge()) {
     // Done
@@ -1931,7 +2522,26 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
     ROCKS_LOG_WARN(immutable_db_options_.info_log, "Compaction error: %s",
                    status.ToString().c_str());
     error_handler_.SetBGError(status, BackgroundErrorReason::kCompaction);
+    if (c != nullptr && !is_manual && !error_handler_.IsBGWorkStopped()) {
+      // Put this cfd back in the compaction queue so we can retry after some
+      // time
+      auto cfd = c->column_family_data();
+      assert(cfd != nullptr);
+      // Since this compaction failed, we need to recompute the score so it
+      // takes the original input files into account
+      c->column_family_data()
+          ->current()
+          ->storage_info()
+          ->ComputeCompactionScore(*(c->immutable_cf_options()),
+                                   *(c->mutable_cf_options()));
+      if (!cfd->queued_for_compaction()) {
+        AddToCompactionQueue(cfd);
+        ++unscheduled_compactions_;
+      }
+    }
   }
+  // this will unref its input_version and column_family_data
+  c.reset();
 
   if (is_manual) {
     ManualCompactionState* m = manual_compaction;
@@ -2080,7 +2690,10 @@ bool DBImpl::MCOverlap(ManualCompactionState* m, ManualCompactionState* m1) {
 
 void DBImpl::InstallSuperVersionAndScheduleWork(
     ColumnFamilyData* cfd, SuperVersionContext* sv_context,
-    const MutableCFOptions& mutable_cf_options, FlushReason flush_reason) {
+    const MutableCFOptions& mutable_cf_options,
+    FlushReason /* flush_reason */) {
+  // TODO(yanqin) investigate if 'flush_reason' can be removed since it's not
+  // used.
   mutex_.AssertHeld();
 
   // Update max_total_in_memory_state_
@@ -2099,7 +2712,6 @@ void DBImpl::InstallSuperVersionAndScheduleWork(
 
   // Whenever we install new SuperVersion, we might need to issue new flushes or
   // compactions.
-  SchedulePendingFlush(cfd, flush_reason);
   SchedulePendingCompaction(cfd);
   MaybeScheduleFlushOrCompaction();
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_impl_debug.cc b/3rdParty/rocksdb/v5.18.X/db/db_impl_debug.cc
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/db/db_impl_debug.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_impl_debug.cc
index 2b7720e580..bbdd5df379 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_impl_debug.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_impl_debug.cc
@@ -100,9 +100,11 @@ Status DBImpl::TEST_SwitchMemtable(ColumnFamilyData* cfd) {
   return SwitchMemtable(cfd, &write_context);
 }
 
-Status DBImpl::TEST_FlushMemTable(bool wait, ColumnFamilyHandle* cfh) {
+Status DBImpl::TEST_FlushMemTable(bool wait, bool allow_write_stall,
+    ColumnFamilyHandle* cfh) {
   FlushOptions fo;
   fo.wait = wait;
+  fo.allow_write_stall = allow_write_stall;
   ColumnFamilyData* cfd;
   if (cfh == nullptr) {
     cfd = default_cf_handle_->cfd();
@@ -121,7 +123,7 @@ Status DBImpl::TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family) {
     auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
     cfd = cfh->cfd();
   }
-  return WaitForFlushMemTable(cfd);
+  return WaitForFlushMemTable(cfd, nullptr, false);
 }
 
 Status DBImpl::TEST_WaitForCompact(bool wait_unscheduled) {
@@ -135,7 +137,7 @@ Status DBImpl::TEST_WaitForCompact(bool wait_unscheduled) {
   while ((bg_bottom_compaction_scheduled_ || bg_compaction_scheduled_ ||
           bg_flush_scheduled_ ||
           (wait_unscheduled && unscheduled_compactions_)) &&
-         !error_handler_.IsDBStopped()) {
+         (error_handler_.GetBGError() == Status::OK())) {
     bg_cv_.Wait();
   }
   return error_handler_.GetBGError();
@@ -235,5 +237,16 @@ SequenceNumber DBImpl::TEST_GetLastVisibleSequence() const {
   }
 }
 
+size_t DBImpl::TEST_GetWalPreallocateBlockSize(
+    uint64_t write_buffer_size) const {
+  InstrumentedMutexLock l(&mutex_);
+  return GetWalPreallocateBlockSize(write_buffer_size);
+}
+
+void DBImpl::TEST_WaitForTimedTaskRun(std::function<void()> callback) const {
+  if (thread_dump_stats_ != nullptr) {
+    thread_dump_stats_->TEST_WaitForRun(callback);
+  }
+}
 }  // namespace rocksdb
 #endif  // NDEBUG
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_impl_experimental.cc b/3rdParty/rocksdb/v5.18.X/db/db_impl_experimental.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_impl_experimental.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_impl_experimental.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_impl_files.cc b/3rdParty/rocksdb/v5.18.X/db/db_impl_files.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/db_impl_files.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_impl_files.cc
index 99fb1df40c..523192f002 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_impl_files.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_impl_files.cc
@@ -20,6 +20,7 @@
 #include "util/sst_file_manager_impl.h"
 
 namespace rocksdb {
+
 uint64_t DBImpl::MinLogNumberToKeep() {
   if (allow_2pc()) {
     return versions_->min_log_number_to_keep_2pc();
@@ -28,6 +29,14 @@ uint64_t DBImpl::MinLogNumberToKeep() {
   }
 }
 
+uint64_t DBImpl::MinObsoleteSstNumberToKeep() {
+  mutex_.AssertHeld();
+  if (!pending_outputs_.empty()) {
+    return *pending_outputs_.begin();
+  }
+  return std::numeric_limits<uint64_t>::max();
+}
+
 // * Returns the list of live files in 'sst_live'
 // If it's doing full scan:
 // * Returns the list of all files in the filesystem in
@@ -456,7 +465,13 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
     } else {
       dir_to_sync =
           (type == kLogFile) ? immutable_db_options_.wal_dir : dbname_;
-      fname = dir_to_sync + "/" + to_delete;
+      fname = dir_to_sync
+            + (
+                (!dir_to_sync.empty() && dir_to_sync.back() == '/') ||
+                (!to_delete.empty() && to_delete.front() == '/')
+                ? "" : "/"
+              )
+            + to_delete;
     }
 
 #ifndef ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_impl_open.cc b/3rdParty/rocksdb/v5.18.X/db/db_impl_open.cc
similarity index 88%
rename from 3rdParty/rocksdb/v5.16.X/db/db_impl_open.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_impl_open.cc
index 4e68327dd5..5ea8c61b50 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_impl_open.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_impl_open.cc
@@ -23,8 +23,7 @@
 #include "util/sync_point.h"
 
 namespace rocksdb {
-Options SanitizeOptions(const std::string& dbname,
-                        const Options& src) {
+Options SanitizeOptions(const std::string& dbname, const Options& src) {
   auto db_options = SanitizeOptions(dbname, DBOptions(src));
   ImmutableDBOptions immutable_db_options(db_options);
   auto cf_options =
@@ -56,10 +55,9 @@ DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src) {
     result.write_buffer_manager.reset(
         new WriteBufferManager(result.db_write_buffer_size));
   }
-  auto bg_job_limits = DBImpl::GetBGJobLimits(result.max_background_flushes,
-                                              result.max_background_compactions,
-                                              result.max_background_jobs,
-                                              true /* parallelize_compactions */);
+  auto bg_job_limits = DBImpl::GetBGJobLimits(
+      result.max_background_flushes, result.max_background_compactions,
+      result.max_background_jobs, true /* parallelize_compactions */);
   result.env->IncBackgroundThreadsIfNeeded(bg_job_limits.max_compactions,
                                            Env::Priority::LOW);
   result.env->IncBackgroundThreadsIfNeeded(bg_job_limits.max_flushes,
@@ -107,14 +105,12 @@ DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src) {
     result.db_paths.emplace_back(dbname, std::numeric_limits<uint64_t>::max());
   }
 
-  if (result.use_direct_reads &&
-      result.compaction_readahead_size == 0) {
+  if (result.use_direct_reads && result.compaction_readahead_size == 0) {
     TEST_SYNC_POINT_CALLBACK("SanitizeOptions:direct_io", nullptr);
     result.compaction_readahead_size = 1024 * 1024 * 2;
   }
 
-  if (result.compaction_readahead_size > 0 ||
-      result.use_direct_reads) {
+  if (result.compaction_readahead_size > 0 || result.use_direct_reads) {
     result.new_table_reader_for_compaction_inputs = true;
   }
 
@@ -134,8 +130,15 @@ DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src) {
   for (size_t i = 0; i < result.db_paths.size(); i++) {
     DeleteScheduler::CleanupDirectory(result.env, sfm, result.db_paths[i].path);
   }
-#endif
 
+  // Create a default SstFileManager for purposes of tracking compaction size
+  // and facilitating recovery from out of space errors.
+  if (result.sst_file_manager.get() == nullptr) {
+    std::shared_ptr<SstFileManager> sst_file_manager(
+        NewSstFileManager(result.env, result.info_log));
+    result.sst_file_manager = sst_file_manager;
+  }
+#endif
   return result;
 }
 
@@ -211,7 +214,7 @@ static Status ValidateOptions(
 
   return Status::OK();
 }
-} // namespace
+}  // namespace
 Status DBImpl::NewDB() {
   VersionEdit new_db;
   new_db.SetLogNumber(0);
@@ -223,7 +226,7 @@ Status DBImpl::NewDB() {
   ROCKS_LOG_INFO(immutable_db_options_.info_log, "Creating manifest 1 \n");
   const std::string manifest = DescriptorFileName(dbname_, 1);
   {
-    unique_ptr<WritableFile> file;
+    std::unique_ptr<WritableFile> file;
     EnvOptions env_options = env_->OptimizeForManifestWrite(env_options_);
     s = NewWritableFile(env_, manifest, &file, env_options);
     if (!s.ok()) {
@@ -231,8 +234,9 @@ Status DBImpl::NewDB() {
     }
     file->SetPreallocationBlockSize(
         immutable_db_options_.manifest_preallocation_size);
-    unique_ptr<WritableFileWriter> file_writer(
-        new WritableFileWriter(std::move(file), env_options));
+    std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
+        std::move(file), manifest, env_options, nullptr /* stats */,
+        immutable_db_options_.listeners));
     log::Writer log(std::move(file_writer), 0, false);
     std::string record;
     new_db.EncodeTo(&record);
@@ -250,9 +254,8 @@ Status DBImpl::NewDB() {
   return s;
 }
 
-Status DBImpl::CreateAndNewDirectory(
-    Env* env, const std::string& dirname,
-    std::unique_ptr<Directory>* directory) {
+Status DBImpl::CreateAndNewDirectory(Env* env, const std::string& dirname,
+                                     std::unique_ptr<Directory>* directory) {
   // We call CreateDirIfMissing() as the directory may already exist (if we
   // are reopening a DB), when this happens we don't want creating the
   // directory to cause an error. However, we need to check if creating the
@@ -333,8 +336,8 @@ Status DBImpl::Recover(
       }
     } else if (s.ok()) {
       if (immutable_db_options_.error_if_exists) {
-        return Status::InvalidArgument(
-            dbname_, "exists (error_if_exists is true)");
+        return Status::InvalidArgument(dbname_,
+                                       "exists (error_if_exists is true)");
       }
     } else {
       // Unexpected error reading file
@@ -354,7 +357,7 @@ Status DBImpl::Recover(
     }
     // Verify compatibility of env_options_ and filesystem
     {
-      unique_ptr<RandomAccessFile> idfile;
+      std::unique_ptr<RandomAccessFile> idfile;
       EnvOptions customized_env(env_options_);
       customized_env.use_direct_reads |=
           immutable_db_options_.use_direct_io_for_flush_and_compaction;
@@ -389,6 +392,16 @@ Status DBImpl::Recover(
       }
     }
   }
+
+  // Initial max_total_in_memory_state_ before recovery logs. Log recovery
+  // may check this value to decide whether to flush.
+  max_total_in_memory_state_ = 0;
+  for (auto cfd : *versions_->GetColumnFamilySet()) {
+    auto* mutable_cf_options = cfd->GetLatestMutableCFOptions();
+    max_total_in_memory_state_ += mutable_cf_options->write_buffer_size *
+                                  mutable_cf_options->max_write_buffer_number;
+  }
+
   if (s.ok()) {
     SequenceNumber next_sequence(kMaxSequenceNumber);
     default_cf_handle_ = new ColumnFamilyHandleImpl(
@@ -461,14 +474,6 @@ Status DBImpl::Recover(
     }
   }
 
-  // Initial value
-  max_total_in_memory_state_ = 0;
-  for (auto cfd : *versions_->GetColumnFamilySet()) {
-    auto* mutable_cf_options = cfd->GetLatestMutableCFOptions();
-    max_total_in_memory_state_ += mutable_cf_options->write_buffer_size *
-                                  mutable_cf_options->max_write_buffer_number;
-  }
-
   return s;
 }
 
@@ -517,10 +522,9 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
     std::map<std::string, uint32_t> cf_name_id_map;
     std::map<uint32_t, uint64_t> cf_lognumber_map;
     for (auto cfd : *versions_->GetColumnFamilySet()) {
-      cf_name_id_map.insert(
-        std::make_pair(cfd->GetName(), cfd->GetID()));
+      cf_name_id_map.insert(std::make_pair(cfd->GetName(), cfd->GetID()));
       cf_lognumber_map.insert(
-        std::make_pair(cfd->GetID(), cfd->GetLogNumber()));
+          std::make_pair(cfd->GetID(), cfd->GetLogNumber()));
     }
 
     immutable_db_options_.wal_filter->ColumnFamilyLogNumberMap(cf_lognumber_map,
@@ -563,9 +567,9 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
       continue;
     }
 
-    unique_ptr<SequentialFileReader> file_reader;
+    std::unique_ptr<SequentialFileReader> file_reader;
     {
-      unique_ptr<SequentialFile> file;
+      std::unique_ptr<SequentialFile> file;
       status = env_->NewSequentialFile(fname, &file,
                                        env_->OptimizeForLogRead(env_options_));
       if (!status.ok()) {
@@ -598,8 +602,8 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
     // to be skipped instead of propagating bad information (like overly
     // large sequence numbers).
     log::Reader reader(immutable_db_options_.info_log, std::move(file_reader),
-                       &reporter, true /*checksum*/, 0 /*initial_offset*/,
-                       log_number);
+                       &reporter, true /*checksum*/, log_number,
+                       false /* retry_after_eof */);
 
     // Determine if we should tolerate incomplete records at the tail end of the
     // Read all the records and add to a memtable
@@ -870,8 +874,8 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
       // VersionSet::next_file_number_ always to be strictly greater than any
       // log number
       versions_->MarkFileNumberUsed(max_log_number + 1);
-      status = versions_->LogAndApply(
-          cfd, *cfd->GetLatestMutableCFOptions(), edit, &mutex_);
+      status = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
+                                      edit, &mutex_);
       if (!status.ok()) {
         // Recovery failed
         break;
@@ -879,18 +883,8 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
     }
   }
 
-  if (data_seen && !flushed) {
-    // Mark these as alive so they'll be considered for deletion later by
-    // FindObsoleteFiles()
-    if (two_write_queues_) {
-      log_write_mutex_.Lock();
-    }
-    for (auto log_number : log_numbers) {
-      alive_log_files_.push_back(LogFileNumberSize(log_number));
-    }
-    if (two_write_queues_) {
-      log_write_mutex_.Unlock();
-    }
+  if (status.ok() && data_seen && !flushed) {
+    status = RestoreAliveLogFiles(log_numbers);
   }
 
   event_logger_.Log() << "job" << job_id << "event"
@@ -899,6 +893,60 @@ Status DBImpl::RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
   return status;
 }
 
+Status DBImpl::RestoreAliveLogFiles(const std::vector<uint64_t>& log_numbers) {
+  if (log_numbers.empty()) {
+    return Status::OK();
+  }
+  Status s;
+  mutex_.AssertHeld();
+  assert(immutable_db_options_.avoid_flush_during_recovery);
+  if (two_write_queues_) {
+    log_write_mutex_.Lock();
+  }
+  // Mark these as alive so they'll be considered for deletion later by
+  // FindObsoleteFiles()
+  total_log_size_ = 0;
+  log_empty_ = false;
+  for (auto log_number : log_numbers) {
+    LogFileNumberSize log(log_number);
+    std::string fname = LogFileName(immutable_db_options_.wal_dir, log_number);
+    // This gets the appear size of the logs, not including preallocated space.
+    s = env_->GetFileSize(fname, &log.size);
+    if (!s.ok()) {
+      break;
+    }
+    total_log_size_ += log.size;
+    alive_log_files_.push_back(log);
+    // We preallocate space for logs, but then after a crash and restart, those
+    // preallocated space are not needed anymore. It is likely only the last
+    // log has such preallocated space, so we only truncate for the last log.
+    if (log_number == log_numbers.back()) {
+      std::unique_ptr<WritableFile> last_log;
+      Status truncate_status = env_->ReopenWritableFile(
+          fname, &last_log,
+          env_->OptimizeForLogWrite(
+              env_options_,
+              BuildDBOptions(immutable_db_options_, mutable_db_options_)));
+      if (truncate_status.ok()) {
+        truncate_status = last_log->Truncate(log.size);
+      }
+      if (truncate_status.ok()) {
+        truncate_status = last_log->Close();
+      }
+      // Not a critical error if fail to truncate.
+      if (!truncate_status.ok()) {
+        ROCKS_LOG_WARN(immutable_db_options_.info_log,
+                       "Failed to truncate log #%" PRIu64 ": %s", log_number,
+                       truncate_status.ToString().c_str());
+      }
+    }
+  }
+  if (two_write_queues_) {
+    log_write_mutex_.Unlock();
+  }
+  return s;
+}
+
 Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
                                            MemTable* mem, VersionEdit* edit) {
   mutex_.AssertHeld();
@@ -940,11 +988,17 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
       if (use_custom_gc_ && snapshot_checker == nullptr) {
         snapshot_checker = DisableGCSnapshotChecker::Instance();
       }
+      std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
+          range_del_iters;
+      auto range_del_iter =
+          mem->NewRangeTombstoneIterator(ro, kMaxSequenceNumber);
+      if (range_del_iter != nullptr) {
+        range_del_iters.emplace_back(range_del_iter);
+      }
       s = BuildTable(
           dbname_, env_, *cfd->ioptions(), mutable_cf_options,
           env_options_for_compaction_, cfd->table_cache(), iter.get(),
-          std::unique_ptr<InternalIterator>(mem->NewRangeTombstoneIterator(ro)),
-          &meta, cfd->internal_comparator(),
+          std::move(range_del_iters), &meta, cfd->internal_comparator(),
           cfd->int_tbl_prop_collector_factories(), cfd->GetID(), cfd->GetName(),
           snapshot_seqs, earliest_write_conflict_snapshot, snapshot_checker,
           GetCompressionFlush(*cfd->ioptions(), mutable_cf_options),
@@ -978,8 +1032,8 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
   stats.bytes_written = meta.fd.GetFileSize();
   stats.num_output_files = 1;
   cfd->internal_stats()->AddCompactionStats(level, stats);
-  cfd->internal_stats()->AddCFStats(
-      InternalStats::BYTES_FLUSHED, meta.fd.GetFileSize());
+  cfd->internal_stats()->AddCFStats(InternalStats::BYTES_FLUSHED,
+                                    meta.fd.GetFileSize());
   RecordTick(stats_, COMPACT_WRITE_BYTES, meta.fd.GetFileSize());
   return s;
 }
@@ -1051,6 +1105,12 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
         break;
       }
     }
+
+    // For recovery from NoSpace() error, we can only handle
+    // the case where the database is stored in a single path
+    if (paths.size() <= 1) {
+      impl->error_handler_.EnableAutoRecovery();
+    }
   }
 
   if (!s.ok()) {
@@ -1069,16 +1129,16 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
   s = impl->Recover(column_families);
   if (s.ok()) {
     uint64_t new_log_number = impl->versions_->NewFileNumber();
-    unique_ptr<WritableFile> lfile;
+    std::unique_ptr<WritableFile> lfile;
     EnvOptions soptions(db_options);
     EnvOptions opt_env_options =
         impl->immutable_db_options_.env->OptimizeForLogWrite(
             soptions, BuildDBOptions(impl->immutable_db_options_,
                                      impl->mutable_db_options_));
-    s = NewWritableFile(
-        impl->immutable_db_options_.env,
-        LogFileName(impl->immutable_db_options_.wal_dir, new_log_number),
-        &lfile, opt_env_options);
+    std::string log_fname =
+        LogFileName(impl->immutable_db_options_.wal_dir, new_log_number);
+    s = NewWritableFile(impl->immutable_db_options_.env, log_fname, &lfile,
+                        opt_env_options);
     if (s.ok()) {
       lfile->SetWriteLifeTimeHint(write_hint);
       lfile->SetPreallocationBlockSize(
@@ -1086,8 +1146,10 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
       {
         InstrumentedMutexLock wl(&impl->log_write_mutex_);
         impl->logfile_number_ = new_log_number;
-        unique_ptr<WritableFileWriter> file_writer(
-            new WritableFileWriter(std::move(lfile), opt_env_options));
+        const auto& listeners = impl->immutable_db_options_.listeners;
+        std::unique_ptr<WritableFileWriter> file_writer(
+            new WritableFileWriter(std::move(lfile), log_fname, opt_env_options,
+                                   nullptr /* stats */, listeners));
         impl->logs_.emplace_back(
             new_log_number,
             new log::Writer(
@@ -1164,7 +1226,8 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
           !cfd->mem()->IsMergeOperatorSupported()) {
         s = Status::InvalidArgument(
             "The memtable of column family %s does not support merge operator "
-            "its options.merge_operator is non-null", cfd->GetName().c_str());
+            "its options.merge_operator is non-null",
+            cfd->GetName().c_str());
       }
       if (!s.ok()) {
         break;
@@ -1214,6 +1277,14 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
         }
       }
     }
+
+    // Reserve some disk buffer space. This is a heuristic - when we run out
+    // of disk space, this ensures that there is atleast write_buffer_size
+    // amount of free space before we resume DB writes. In low disk space
+    // conditions, we want to avoid a lot of small L0 files due to frequent
+    // WAL write failures and resultant forced flushes
+    sfm->ReserveDiskBuffer(max_write_buffer_size,
+                           impl->immutable_db_options_.db_paths[0].path);
   }
 #endif  // !ROCKSDB_LITE
 
@@ -1229,6 +1300,9 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
           persist_options_status.ToString());
     }
   }
+  if (s.ok()) {
+    impl->StartTimedTasks();
+  }
   if (!s.ok()) {
     for (auto* h : *handles) {
       delete h;
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_impl_readonly.cc b/3rdParty/rocksdb/v5.18.X/db/db_impl_readonly.cc
similarity index 85%
rename from 3rdParty/rocksdb/v5.16.X/db/db_impl_readonly.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_impl_readonly.cc
index c1c1943b2d..c4a55b6ec0 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_impl_readonly.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_impl_readonly.cc
@@ -31,6 +31,8 @@ Status DBImplReadOnly::Get(const ReadOptions& read_options,
                            ColumnFamilyHandle* column_family, const Slice& key,
                            PinnableSlice* pinnable_val) {
   assert(pinnable_val != nullptr);
+  // TODO: stopwatch DB_GET needed?, perf timer needed?
+  PERF_TIMER_GUARD(get_snapshot_time);
   Status s;
   SequenceNumber snapshot = versions_->LastSequence();
   auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
@@ -43,16 +45,24 @@ Status DBImplReadOnly::Get(const ReadOptions& read_options,
   }
   SuperVersion* super_version = cfd->GetSuperVersion();
   MergeContext merge_context;
-  RangeDelAggregator range_del_agg(cfd->internal_comparator(), snapshot);
+  SequenceNumber max_covering_tombstone_seq = 0;
   LookupKey lkey(key, snapshot);
+  PERF_TIMER_STOP(get_snapshot_time);
   if (super_version->mem->Get(lkey, pinnable_val->GetSelf(), &s, &merge_context,
-                              &range_del_agg, read_options)) {
+                              &max_covering_tombstone_seq, read_options)) {
     pinnable_val->PinSelf();
+    RecordTick(stats_, MEMTABLE_HIT);
   } else {
     PERF_TIMER_GUARD(get_from_output_files_time);
     super_version->current->Get(read_options, lkey, pinnable_val, &s,
-                                &merge_context, &range_del_agg);
+                                &merge_context, &max_covering_tombstone_seq);
+    RecordTick(stats_, MEMTABLE_MISS);
   }
+  RecordTick(stats_, NUMBER_KEYS_READ);
+  size_t size = pinnable_val->size();
+  RecordTick(stats_, BYTES_READ, size);
+  MeasureTime(stats_, BYTES_PER_READ, size);
+  PERF_COUNTER_ADD(get_read_bytes, size);
   return s;
 }
 
@@ -62,18 +72,20 @@ Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
   auto cfd = cfh->cfd();
   SuperVersion* super_version = cfd->GetSuperVersion()->Ref();
   SequenceNumber latest_snapshot = versions_->LastSequence();
+  SequenceNumber read_seq =
+      read_options.snapshot != nullptr
+          ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
+                ->number_
+          : latest_snapshot;
   ReadCallback* read_callback = nullptr;  // No read callback provided.
   auto db_iter = NewArenaWrappedDbIterator(
       env_, read_options, *cfd->ioptions(), super_version->mutable_cf_options,
-      (read_options.snapshot != nullptr
-           ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
-                 ->number_
-           : latest_snapshot),
+      read_seq,
       super_version->mutable_cf_options.max_sequential_skip_in_iterations,
       super_version->version_number, read_callback);
   auto internal_iter =
       NewInternalIterator(read_options, cfd, super_version, db_iter->GetArena(),
-                          db_iter->GetRangeDelAggregator());
+                          db_iter->GetRangeDelAggregator(), read_seq);
   db_iter->SetIterUnderDBIter(internal_iter);
   return db_iter;
 }
@@ -89,21 +101,22 @@ Status DBImplReadOnly::NewIterators(
   iterators->clear();
   iterators->reserve(column_families.size());
   SequenceNumber latest_snapshot = versions_->LastSequence();
+  SequenceNumber read_seq =
+      read_options.snapshot != nullptr
+          ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
+                ->number_
+          : latest_snapshot;
 
   for (auto cfh : column_families) {
     auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh)->cfd();
     auto* sv = cfd->GetSuperVersion()->Ref();
     auto* db_iter = NewArenaWrappedDbIterator(
-        env_, read_options, *cfd->ioptions(), sv->mutable_cf_options,
-        (read_options.snapshot != nullptr
-             ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
-                   ->number_
-             : latest_snapshot),
+        env_, read_options, *cfd->ioptions(), sv->mutable_cf_options, read_seq,
         sv->mutable_cf_options.max_sequential_skip_in_iterations,
         sv->version_number, read_callback);
     auto* internal_iter =
         NewInternalIterator(read_options, cfd, sv, db_iter->GetArena(),
-                            db_iter->GetRangeDelAggregator());
+                            db_iter->GetRangeDelAggregator(), read_seq);
     db_iter->SetIterUnderDBIter(internal_iter);
     iterators->push_back(db_iter);
   }
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_impl_readonly.h b/3rdParty/rocksdb/v5.18.X/db/db_impl_readonly.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_impl_readonly.h
rename to 3rdParty/rocksdb/v5.18.X/db/db_impl_readonly.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_impl_write.cc b/3rdParty/rocksdb/v5.18.X/db/db_impl_write.cc
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/db/db_impl_write.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_impl_write.cc
index de4c9b3c8f..6bfc980250 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_impl_write.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_impl_write.cc
@@ -338,8 +338,6 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
           }
         }
         write_group.last_sequence = last_sequence;
-        write_group.running.store(static_cast<uint32_t>(write_group.size),
-                                  std::memory_order_relaxed);
         write_thread_.LaunchParallelMemTableWriters(&write_group);
         in_parallel_group = true;
 
@@ -710,6 +708,10 @@ Status DBImpl::PreprocessWrite(const WriteOptions& write_options,
   assert(write_context != nullptr && need_log_sync != nullptr);
   Status status;
 
+  if (error_handler_.IsDBStopped()) {
+    status = error_handler_.GetBGError();
+  }
+
   PERF_TIMER_GUARD(write_scheduling_flushes_compactions_time);
 
   assert(!single_column_family_mode_ ||
@@ -728,10 +730,6 @@ Status DBImpl::PreprocessWrite(const WriteOptions& write_options,
     status = HandleWriteBufferFull(write_context);
   }
 
-  if (UNLIKELY(status.ok())) {
-    status = error_handler_.GetBGError();
-  }
-
   if (UNLIKELY(status.ok() && !flush_scheduler_.Empty())) {
     status = ScheduleFlushes(write_context);
   }
@@ -1016,6 +1014,28 @@ Status DBImpl::WriteRecoverableState() {
   return Status::OK();
 }
 
+void DBImpl::SelectColumnFamiliesForAtomicFlush(
+    autovector<ColumnFamilyData*>* cfds) {
+  for (ColumnFamilyData* cfd : *versions_->GetColumnFamilySet()) {
+    if (cfd->IsDropped()) {
+      continue;
+    }
+    if (cfd->imm()->NumNotFlushed() != 0 || !cfd->mem()->IsEmpty() ||
+        !cached_recoverable_state_empty_.load()) {
+      cfds->push_back(cfd);
+    }
+  }
+}
+
+// Assign sequence number for atomic flush.
+void DBImpl::AssignAtomicFlushSeq(const autovector<ColumnFamilyData*>& cfds) {
+  assert(immutable_db_options_.atomic_flush);
+  auto seq = versions_->LastSequence();
+  for (auto cfd : cfds) {
+    cfd->imm()->AssignAtomicFlushSeq(seq);
+  }
+}
+
 Status DBImpl::SwitchWAL(WriteContext* write_context) {
   mutex_.AssertHeld();
   assert(write_context != nullptr);
@@ -1064,20 +1084,39 @@ Status DBImpl::SwitchWAL(WriteContext* write_context) {
                  oldest_alive_log, total_log_size_.load(), GetMaxTotalWalSize());
   // no need to refcount because drop is happening in write thread, so can't
   // happen while we're in the write thread
-  for (auto cfd : *versions_->GetColumnFamilySet()) {
-    if (cfd->IsDropped()) {
-      continue;
-    }
-    if (cfd->OldestLogToKeep() <= oldest_alive_log) {
-      status = SwitchMemtable(cfd, write_context);
-      if (!status.ok()) {
-        break;
+  autovector<ColumnFamilyData*> cfds;
+  if (immutable_db_options_.atomic_flush) {
+    SelectColumnFamiliesForAtomicFlush(&cfds);
+  } else {
+    for (auto cfd : *versions_->GetColumnFamilySet()) {
+      if (cfd->IsDropped()) {
+        continue;
+      }
+      if (cfd->OldestLogToKeep() <= oldest_alive_log) {
+        cfds.push_back(cfd);
       }
-      cfd->imm()->FlushRequested();
-      SchedulePendingFlush(cfd, FlushReason::kWriteBufferManager);
     }
   }
-  MaybeScheduleFlushOrCompaction();
+  for (const auto cfd : cfds) {
+    cfd->Ref();
+    status = SwitchMemtable(cfd, write_context);
+    cfd->Unref();
+    if (!status.ok()) {
+      break;
+    }
+  }
+  if (status.ok()) {
+    if (immutable_db_options_.atomic_flush) {
+      AssignAtomicFlushSeq(cfds);
+    }
+    for (auto cfd : cfds) {
+      cfd->imm()->FlushRequested();
+    }
+    FlushRequest flush_req;
+    GenerateFlushRequest(cfds, &flush_req);
+    SchedulePendingFlush(flush_req, FlushReason::kWriteBufferManager);
+    MaybeScheduleFlushOrCompaction();
+  }
   return status;
 }
 
@@ -1099,32 +1138,55 @@ Status DBImpl::HandleWriteBufferFull(WriteContext* write_context) {
       write_buffer_manager_->buffer_size());
   // no need to refcount because drop is happening in write thread, so can't
   // happen while we're in the write thread
-  ColumnFamilyData* cfd_picked = nullptr;
-  SequenceNumber seq_num_for_cf_picked = kMaxSequenceNumber;
+  autovector<ColumnFamilyData*> cfds;
+  if (immutable_db_options_.atomic_flush) {
+    SelectColumnFamiliesForAtomicFlush(&cfds);
+  } else {
+    ColumnFamilyData* cfd_picked = nullptr;
+    SequenceNumber seq_num_for_cf_picked = kMaxSequenceNumber;
 
-  for (auto cfd : *versions_->GetColumnFamilySet()) {
-    if (cfd->IsDropped()) {
-      continue;
-    }
-    if (!cfd->mem()->IsEmpty()) {
-      // We only consider active mem table, hoping immutable memtable is
-      // already in the process of flushing.
-      uint64_t seq = cfd->mem()->GetCreationSeq();
-      if (cfd_picked == nullptr || seq < seq_num_for_cf_picked) {
-        cfd_picked = cfd;
-        seq_num_for_cf_picked = seq;
+    for (auto cfd : *versions_->GetColumnFamilySet()) {
+      if (cfd->IsDropped()) {
+        continue;
+      }
+      if (!cfd->mem()->IsEmpty()) {
+        // We only consider active mem table, hoping immutable memtable is
+        // already in the process of flushing.
+        uint64_t seq = cfd->mem()->GetCreationSeq();
+        if (cfd_picked == nullptr || seq < seq_num_for_cf_picked) {
+          cfd_picked = cfd;
+          seq_num_for_cf_picked = seq;
+        }
       }
     }
-  }
-  if (cfd_picked != nullptr) {
-    status = SwitchMemtable(cfd_picked, write_context,
-                            FlushReason::kWriteBufferFull);
-    if (status.ok()) {
-      cfd_picked->imm()->FlushRequested();
-      SchedulePendingFlush(cfd_picked, FlushReason::kWriteBufferFull);
-      MaybeScheduleFlushOrCompaction();
+    if (cfd_picked != nullptr) {
+      cfds.push_back(cfd_picked);
     }
   }
+
+  for (const auto cfd : cfds) {
+    if (cfd->mem()->IsEmpty()) {
+      continue;
+    }
+    cfd->Ref();
+    status = SwitchMemtable(cfd, write_context);
+    cfd->Unref();
+    if (!status.ok()) {
+      break;
+    }
+  }
+  if (status.ok()) {
+    if (immutable_db_options_.atomic_flush) {
+      AssignAtomicFlushSeq(cfds);
+    }
+    for (const auto cfd : cfds) {
+      cfd->imm()->FlushRequested();
+    }
+    FlushRequest flush_req;
+    GenerateFlushRequest(cfds, &flush_req);
+    SchedulePendingFlush(flush_req, FlushReason::kWriteBufferFull);
+    MaybeScheduleFlushOrCompaction();
+  }
   return status;
 }
 
@@ -1146,10 +1208,14 @@ Status DBImpl::DelayWrite(uint64_t num_bytes,
     uint64_t delay = write_controller_.GetDelay(env_, num_bytes);
     if (delay > 0) {
       if (write_options.no_slowdown) {
-        return Status::Incomplete();
+        return Status::Incomplete("Write stall");
       }
       TEST_SYNC_POINT("DBImpl::DelayWrite:Sleep");
 
+      // Notify write_thread_ about the stall so it can setup a barrier and
+      // fail any pending writers with no_slowdown
+      write_thread_.BeginWriteStall();
+      TEST_SYNC_POINT("DBImpl::DelayWrite:BeginWriteStallDone");
       mutex_.Unlock();
       // We will delay the write until we have slept for delay ms or
       // we don't need a delay anymore
@@ -1166,15 +1232,25 @@ Status DBImpl::DelayWrite(uint64_t num_bytes,
         env_->SleepForMicroseconds(kDelayInterval);
       }
       mutex_.Lock();
+      write_thread_.EndWriteStall();
     }
 
-    while (!error_handler_.IsDBStopped() && write_controller_.IsStopped()) {
+    // Don't wait if there's a background error, even if its a soft error. We
+    // might wait here indefinitely as the background compaction may never
+    // finish successfully, resulting in the stall condition lasting
+    // indefinitely
+    while (error_handler_.GetBGError().ok() && write_controller_.IsStopped()) {
       if (write_options.no_slowdown) {
-        return Status::Incomplete();
+        return Status::Incomplete("Write stall");
       }
       delayed = true;
+
+      // Notify write_thread_ about the stall so it can setup a barrier and
+      // fail any pending writers with no_slowdown
+      write_thread_.BeginWriteStall();
       TEST_SYNC_POINT("DBImpl::DelayWrite:Wait");
       bg_cv_.Wait();
+      write_thread_.EndWriteStall();
     }
   }
   assert(!delayed || !write_options.no_slowdown);
@@ -1184,7 +1260,19 @@ Status DBImpl::DelayWrite(uint64_t num_bytes,
     RecordTick(stats_, STALL_MICROS, time_delayed);
   }
 
-  return error_handler_.GetBGError();
+  // If DB is not in read-only mode and write_controller is not stopping
+  // writes, we can ignore any background errors and allow the write to
+  // proceed
+  Status s;
+  if (write_controller_.IsStopped()) {
+    // If writes are still stopped, it means we bailed due to a background
+    // error
+    s = Status::Incomplete(error_handler_.GetBGError().ToString());
+  }
+  if (error_handler_.IsDBStopped()) {
+    s = error_handler_.GetBGError();
+  }
+  return s;
 }
 
 Status DBImpl::ThrottleLowPriWritesIfNeeded(const WriteOptions& write_options,
@@ -1218,17 +1306,42 @@ Status DBImpl::ThrottleLowPriWritesIfNeeded(const WriteOptions& write_options,
 }
 
 Status DBImpl::ScheduleFlushes(WriteContext* context) {
-  ColumnFamilyData* cfd;
-  while ((cfd = flush_scheduler_.TakeNextColumnFamily()) != nullptr) {
-    auto status = SwitchMemtable(cfd, context, FlushReason::kWriteBufferFull);
-    if (cfd->Unref()) {
-      delete cfd;
+  autovector<ColumnFamilyData*> cfds;
+  if (immutable_db_options_.atomic_flush) {
+    SelectColumnFamiliesForAtomicFlush(&cfds);
+    for (auto cfd : cfds) {
+      cfd->Ref();
     }
-    if (!status.ok()) {
-      return status;
+    flush_scheduler_.Clear();
+  } else {
+    ColumnFamilyData* tmp_cfd;
+    while ((tmp_cfd = flush_scheduler_.TakeNextColumnFamily()) != nullptr) {
+      cfds.push_back(tmp_cfd);
     }
   }
-  return Status::OK();
+  Status status;
+  for (auto& cfd : cfds) {
+    if (!cfd->mem()->IsEmpty()) {
+      status = SwitchMemtable(cfd, context);
+    }
+    if (cfd->Unref()) {
+      delete cfd;
+      cfd = nullptr;
+    }
+    if (!status.ok()) {
+      break;
+    }
+  }
+  if (status.ok()) {
+    if (immutable_db_options_.atomic_flush) {
+      AssignAtomicFlushSeq(cfds);
+    }
+    FlushRequest flush_req;
+    GenerateFlushRequest(cfds, &flush_req);
+    SchedulePendingFlush(flush_req, FlushReason::kWriteBufferFull);
+    MaybeScheduleFlushOrCompaction();
+  }
+  return status;
 }
 
 #ifndef ROCKSDB_LITE
@@ -1249,8 +1362,7 @@ void DBImpl::NotifyOnMemTableSealed(ColumnFamilyData* /*cfd*/,
 
 // REQUIRES: mutex_ is held
 // REQUIRES: this thread is currently at the front of the writer queue
-Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
-                              FlushReason flush_reason) {
+Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context) {
   mutex_.AssertHeld();
   WriteThread::Writer nonmem_w;
   if (two_write_queues_) {
@@ -1259,7 +1371,7 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
     nonmem_write_thread_.EnterUnbatched(&nonmem_w, &mutex_);
   }
 
-  unique_ptr<WritableFile> lfile;
+  std::unique_ptr<WritableFile> lfile;
   log::Writer* new_log = nullptr;
   MemTable* new_mem = nullptr;
 
@@ -1319,6 +1431,8 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
   auto write_hint = CalculateWALWriteHint();
   mutex_.Unlock();
   {
+    std::string log_fname =
+        LogFileName(immutable_db_options_.wal_dir, new_log_number);
     if (creating_new_log) {
       EnvOptions opt_env_opt =
           env_->OptimizeForLogWrite(env_options_, db_options);
@@ -1326,14 +1440,12 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
         ROCKS_LOG_INFO(immutable_db_options_.info_log,
                        "reusing log %" PRIu64 " from recycle list\n",
                        recycle_log_number);
-        s = env_->ReuseWritableFile(
-            LogFileName(immutable_db_options_.wal_dir, new_log_number),
-            LogFileName(immutable_db_options_.wal_dir, recycle_log_number),
-            &lfile, opt_env_opt);
+        std::string old_log_fname =
+            LogFileName(immutable_db_options_.wal_dir, recycle_log_number);
+        s = env_->ReuseWritableFile(log_fname, old_log_fname, &lfile,
+                                    opt_env_opt);
       } else {
-        s = NewWritableFile(
-            env_, LogFileName(immutable_db_options_.wal_dir, new_log_number),
-            &lfile, opt_env_opt);
+        s = NewWritableFile(env_, log_fname, &lfile, opt_env_opt);
       }
       if (s.ok()) {
         // Our final size should be less than write_buffer_size
@@ -1343,8 +1455,9 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
         // of calling GetWalPreallocateBlockSize()
         lfile->SetPreallocationBlockSize(preallocate_block_size);
         lfile->SetWriteLifeTimeHint(write_hint);
-        unique_ptr<WritableFileWriter> file_writer(
-            new WritableFileWriter(std::move(lfile), opt_env_opt));
+        std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
+            std::move(lfile), log_fname, opt_env_opt, nullptr /* stats */,
+            immutable_db_options_.listeners));
         new_log = new log::Writer(
             std::move(file_writer), new_log_number,
             immutable_db_options_.recycle_log_file_num > 0, manual_wal_flush_);
@@ -1422,7 +1535,7 @@ Status DBImpl::SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context,
   new_mem->Ref();
   cfd->SetMemtable(new_mem);
   InstallSuperVersionAndScheduleWork(cfd, &context->superversion_context,
-                                     mutable_cf_options, flush_reason);
+                                     mutable_cf_options);
   if (two_write_queues_) {
     nonmem_write_thread_.ExitUnbatched(&nonmem_w);
   }
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_info_dumper.cc b/3rdParty/rocksdb/v5.18.X/db/db_info_dumper.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/db/db_info_dumper.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_info_dumper.cc
index 1668a1638f..31050d20a2 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_info_dumper.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_info_dumper.cc
@@ -42,7 +42,7 @@ void DumpDBFileSummary(const ImmutableDBOptions& options,
           "Error when reading %s dir\n", dbname.c_str());
   }
   std::sort(files.begin(), files.end());
-  for (std::string file : files) {
+  for (const std::string& file : files) {
     if (!ParseFileName(file, &number, &type)) {
       continue;
     }
@@ -85,7 +85,7 @@ void DumpDBFileSummary(const ImmutableDBOptions& options,
         continue;
       }
       std::sort(files.begin(), files.end());
-      for (std::string file : files) {
+      for (const std::string& file : files) {
         if (ParseFileName(file, &number, &type)) {
           if (type == kTableFile && ++file_num < 10) {
             file_info.append(file).append(" ");
@@ -109,7 +109,7 @@ void DumpDBFileSummary(const ImmutableDBOptions& options,
       return;
     }
     wal_info.clear();
-    for (std::string file : files) {
+    for (const std::string& file : files) {
       if (ParseFileName(file, &number, &type)) {
         if (type == kLogFile) {
           env->GetFileSize(options.wal_dir + "/" + file, &file_size);
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_info_dumper.h b/3rdParty/rocksdb/v5.18.X/db/db_info_dumper.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_info_dumper.h
rename to 3rdParty/rocksdb/v5.18.X/db/db_info_dumper.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_inplace_update_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_inplace_update_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_inplace_update_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_inplace_update_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_io_failure_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_io_failure_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_io_failure_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_io_failure_test.cc
index 9f4dcc5d05..ba8f197596 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_io_failure_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_io_failure_test.cc
@@ -88,7 +88,6 @@ TEST_F(DBIOFailureTest, DropWritesFlush) {
     env_->drop_writes_.store(false, std::memory_order_release);
   } while (ChangeCompactOptions());
 }
-#endif  // ROCKSDB_LITE
 
 // Check that CompactRange() returns failure if there is not enough space left
 // on device
@@ -116,6 +115,7 @@ TEST_F(DBIOFailureTest, NoSpaceCompactRange) {
     env_->no_space_.store(false, std::memory_order_release);
   } while (ChangeCompactOptions());
 }
+#endif  // ROCKSDB_LITE
 
 TEST_F(DBIOFailureTest, NonWritableFileSystem) {
   do {
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_iter.cc b/3rdParty/rocksdb/v5.18.X/db/db_iter.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/db_iter.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_iter.cc
index 701d0d8fca..cc4a0d5f44 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_iter.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_iter.cc
@@ -134,15 +134,14 @@ class DBIter final: public Iterator {
         prefix_same_as_start_(read_options.prefix_same_as_start),
         pin_thru_lifetime_(read_options.pin_data),
         total_order_seek_(read_options.total_order_seek),
-        range_del_agg_(cf_options.internal_comparator, s,
-                       true /* collapse_deletions */),
+        range_del_agg_(&cf_options.internal_comparator, s),
         read_callback_(read_callback),
         db_impl_(db_impl),
         cfd_(cfd),
         allow_blob_(allow_blob),
         is_blob_(false),
         start_seqnum_(read_options.iter_start_seqnum) {
-    RecordTick(statistics_, NO_ITERATORS);
+    RecordTick(statistics_, NO_ITERATOR_CREATED);
     prefix_extractor_ = mutable_cf_options.prefix_extractor.get();
     max_skip_ = max_sequential_skip_in_iterations;
     max_skippable_internal_keys_ = read_options.max_skippable_internal_keys;
@@ -158,9 +157,7 @@ class DBIter final: public Iterator {
     if (pinned_iters_mgr_.PinningEnabled()) {
       pinned_iters_mgr_.ReleasePinnedData();
     }
-    // Compiler warning issue filed:
-    // https://github.com/facebook/rocksdb/issues/3013
-    RecordTick(statistics_, NO_ITERATORS, uint64_t(-1));
+    RecordTick(statistics_, NO_ITERATOR_DELETED);
     ResetInternalKeysSkippedCounter();
     local_stats_.BumpGlobalStatistics(statistics_);
     if (!arena_mode_) {
@@ -174,7 +171,7 @@ class DBIter final: public Iterator {
     iter_ = iter;
     iter_->SetPinnedItersMgr(&pinned_iters_mgr_);
   }
-  virtual RangeDelAggregator* GetRangeDelAggregator() {
+  virtual ReadRangeDelAggregatorV2* GetRangeDelAggregator() {
     return &range_del_agg_;
   }
 
@@ -232,7 +229,7 @@ class DBIter final: public Iterator {
       *prop = saved_key_.GetUserKey().ToString();
       return Status::OK();
     }
-    return Status::InvalidArgument("Undentified property.");
+    return Status::InvalidArgument("Unidentified property.");
   }
 
   virtual void Next() override;
@@ -344,7 +341,7 @@ class DBIter final: public Iterator {
   const bool total_order_seek_;
   // List of operands for merge operator.
   MergeContext merge_context_;
-  RangeDelAggregator range_del_agg_;
+  ReadRangeDelAggregatorV2 range_del_agg_;
   LocalStatistics local_stats_;
   PinnedIteratorsManager pinned_iters_mgr_;
   ReadCallback* read_callback_;
@@ -1115,7 +1112,7 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
 
     if (ikey.type == kTypeDeletion || ikey.type == kTypeSingleDeletion ||
         range_del_agg_.ShouldDelete(
-            ikey, RangeDelPositioningMode::kBackwardTraversal)) {
+            ikey, RangeDelPositioningMode::kForwardTraversal)) {
       break;
     } else if (ikey.type == kTypeValue) {
       const Slice val = iter_->value();
@@ -1482,7 +1479,7 @@ Iterator* NewDBIterator(Env* env, const ReadOptions& read_options,
 
 ArenaWrappedDBIter::~ArenaWrappedDBIter() { db_iter_->~DBIter(); }
 
-RangeDelAggregator* ArenaWrappedDBIter::GetRangeDelAggregator() {
+ReadRangeDelAggregatorV2* ArenaWrappedDBIter::GetRangeDelAggregator() {
   return db_iter_->GetRangeDelAggregator();
 }
 
@@ -1558,7 +1555,8 @@ Status ArenaWrappedDBIter::Refresh() {
          allow_refresh_);
 
     InternalIterator* internal_iter = db_impl_->NewInternalIterator(
-        read_options_, cfd_, sv, &arena_, db_iter_->GetRangeDelAggregator());
+        read_options_, cfd_, sv, &arena_, db_iter_->GetRangeDelAggregator(),
+        latest_seq);
     SetIterUnderDBIter(internal_iter);
   } else {
     db_iter_->set_sequence(latest_seq);
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_iter.h b/3rdParty/rocksdb/v5.18.X/db/db_iter.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/db/db_iter.h
rename to 3rdParty/rocksdb/v5.18.X/db/db_iter.h
index 8e18f03fc3..6ee869135e 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_iter.h
+++ b/3rdParty/rocksdb/v5.18.X/db/db_iter.h
@@ -12,7 +12,7 @@
 #include <string>
 #include "db/db_impl.h"
 #include "db/dbformat.h"
-#include "db/range_del_aggregator.h"
+#include "db/range_del_aggregator_v2.h"
 #include "options/cf_options.h"
 #include "rocksdb/db.h"
 #include "rocksdb/iterator.h"
@@ -48,7 +48,7 @@ class ArenaWrappedDBIter : public Iterator {
   // Get the arena to be used to allocate memory for DBIter to be wrapped,
   // as well as child iterators in it.
   virtual Arena* GetArena() { return &arena_; }
-  virtual RangeDelAggregator* GetRangeDelAggregator();
+  virtual ReadRangeDelAggregatorV2* GetRangeDelAggregator();
 
   // Set the internal iterator wrapped inside the DB Iterator. Usually it is
   // a merging iterator.
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_iter_stress_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_iter_stress_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_iter_stress_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_iter_stress_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_iter_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_iter_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_iter_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_iter_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_iterator_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_iterator_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/db_iterator_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_iterator_test.cc
index eb7b52c0c0..0e8c78155a 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_iterator_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_iterator_test.cc
@@ -85,7 +85,7 @@ TEST_P(DBIteratorTest, IteratorProperty) {
   ReadOptions ropt;
   ropt.pin_data = false;
   {
-    unique_ptr<Iterator> iter(NewIterator(ropt, handles_[1]));
+    std::unique_ptr<Iterator> iter(NewIterator(ropt, handles_[1]));
     iter->SeekToFirst();
     std::string prop_value;
     ASSERT_NOK(iter->GetProperty("non_existing.value", &prop_value));
@@ -1951,6 +1951,7 @@ TEST_P(DBIteratorTest, ReadAhead) {
   size_t bytes_read = env_->random_read_bytes_counter_;
   delete iter;
 
+  int64_t num_file_closes = TestGetTickerCount(options, NO_FILE_CLOSES);
   env_->random_read_bytes_counter_ = 0;
   options.statistics->setTickerCount(NO_FILE_OPENS, 0);
   read_options.readahead_size = 1024 * 10;
@@ -1959,7 +1960,10 @@ TEST_P(DBIteratorTest, ReadAhead) {
   int64_t num_file_opens_readahead = TestGetTickerCount(options, NO_FILE_OPENS);
   size_t bytes_read_readahead = env_->random_read_bytes_counter_;
   delete iter;
+  int64_t num_file_closes_readahead =
+      TestGetTickerCount(options, NO_FILE_CLOSES);
   ASSERT_EQ(num_file_opens + 3, num_file_opens_readahead);
+  ASSERT_EQ(num_file_closes + 3, num_file_closes_readahead);
   ASSERT_GT(bytes_read_readahead, bytes_read);
   ASSERT_GT(bytes_read_readahead, read_options.readahead_size * 3);
 
@@ -2373,7 +2377,7 @@ TEST_P(DBIteratorTest, SeekAfterHittingManyInternalKeys) {
   Delete("5");
   Put("6", "val_6");
 
-  unique_ptr<Iterator> iter(NewIterator(ropts));
+  std::unique_ptr<Iterator> iter(NewIterator(ropts));
   iter->SeekToFirst();
 
   ASSERT_TRUE(iter->Valid());
@@ -2392,7 +2396,7 @@ TEST_P(DBIteratorTest, SeekAfterHittingManyInternalKeys) {
   ASSERT_EQ("4", prop_value);
 
   // Create a new iterator to seek to the internal key.
-  unique_ptr<Iterator> iter2(NewIterator(ropts));
+  std::unique_ptr<Iterator> iter2(NewIterator(ropts));
   iter2->Seek(prop_value);
   ASSERT_TRUE(iter2->Valid());
   ASSERT_OK(iter2->status());
@@ -2420,7 +2424,7 @@ TEST_P(DBIteratorTest, NonBlockingIterationBugRepro) {
   // Create a nonblocking iterator before writing to memtable.
   ReadOptions ropt;
   ropt.read_tier = kBlockCacheTier;
-  unique_ptr<Iterator> iter(NewIterator(ropt));
+  std::unique_ptr<Iterator> iter(NewIterator(ropt));
 
   // Overwrite a key in memtable many times to hit
   // max_sequential_skip_in_iterations (which is 8 by default).
@@ -2430,7 +2434,7 @@ TEST_P(DBIteratorTest, NonBlockingIterationBugRepro) {
 
   // Load the second block in sst file into the block cache.
   {
-    unique_ptr<Iterator> iter2(NewIterator(ReadOptions()));
+    std::unique_ptr<Iterator> iter2(NewIterator(ReadOptions()));
     iter2->Seek("d");
   }
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_log_iter_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_log_iter_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/db_log_iter_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_log_iter_test.cc
index 1370c65ca6..a8c92ca26f 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_log_iter_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_log_iter_test.cc
@@ -23,7 +23,7 @@ class DBTestXactLogIterator : public DBTestBase {
 
   std::unique_ptr<TransactionLogIterator> OpenTransactionLogIter(
       const SequenceNumber seq) {
-    unique_ptr<TransactionLogIterator> iter;
+    std::unique_ptr<TransactionLogIterator> iter;
     Status status = dbfull()->GetUpdatesSince(seq, &iter);
     EXPECT_OK(status);
     EXPECT_TRUE(iter->Valid());
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_memtable_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_memtable_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_memtable_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_memtable_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_merge_operator_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_merge_operator_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_merge_operator_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_merge_operator_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_options_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_options_test.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/db/db_options_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_options_test.cc
index dc79316246..1f4e99073c 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_options_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_options_test.cc
@@ -514,6 +514,33 @@ TEST_F(DBOptionsTest, SetStatsDumpPeriodSec) {
   }
 }
 
+TEST_F(DBOptionsTest, RunStatsDumpPeriodSec) {
+  Options options;
+  options.create_if_missing = true;
+  options.stats_dump_period_sec = 5;
+  std::unique_ptr<rocksdb::MockTimeEnv> mock_env;
+  mock_env.reset(new rocksdb::MockTimeEnv(env_));
+  mock_env->set_current_time(0); // in seconds
+  options.env = mock_env.get();
+  int counter = 0;
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::DumpStats:1", [&](void* /*arg*/) {
+        counter++;
+      });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  Reopen(options);
+  ASSERT_EQ(5, dbfull()->GetDBOptions().stats_dump_period_sec);
+  dbfull()->TEST_WaitForTimedTaskRun([&] { mock_env->set_current_time(5); });
+  ASSERT_GE(counter, 1);
+
+  // Test cacel job through SetOptions
+  ASSERT_OK(dbfull()->SetDBOptions({{"stats_dump_period_sec", "0"}}));
+  int old_val = counter;
+  env_->SleepForMicroseconds(10000000);
+  ASSERT_EQ(counter, old_val);
+  Close();
+}
+
 static void assert_candidate_files_empty(DBImpl* dbfull, const bool empty) {
   dbfull->TEST_LockMutex();
   JobContext job_context(0);
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_properties_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_properties_test.cc
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/db/db_properties_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_properties_test.cc
index bdd50ec6cf..3745135bf7 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_properties_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_properties_test.cc
@@ -170,6 +170,8 @@ void ResetTableProperties(TableProperties* tp) {
   tp->raw_value_size = 0;
   tp->num_data_blocks = 0;
   tp->num_entries = 0;
+  tp->num_deletions = 0;
+  tp->num_merge_operands = 0;
   tp->num_range_deletions = 0;
 }
 
@@ -179,17 +181,19 @@ void ParseTablePropertiesString(std::string tp_string, TableProperties* tp) {
   std::replace(tp_string.begin(), tp_string.end(), '=', ' ');
   ResetTableProperties(tp);
   sscanf(tp_string.c_str(),
-         "# data blocks %" SCNu64 " # entries %" SCNu64
-         " # range deletions %" SCNu64 " raw key size %" SCNu64
+         "# data blocks %" SCNu64 " # entries %" SCNu64 " # deletions %" SCNu64
+         " # merge operands %" SCNu64 " # range deletions %" SCNu64
+         " raw key size %" SCNu64
          " raw average key size %lf "
          " raw value size %" SCNu64
          " raw average value size %lf "
          " data block size %" SCNu64 " index block size (user-key? %" SCNu64
          ", delta-value? %" SCNu64 ") %" SCNu64 " filter block size %" SCNu64,
-         &tp->num_data_blocks, &tp->num_entries, &tp->num_range_deletions,
-         &tp->raw_key_size, &dummy_double, &tp->raw_value_size, &dummy_double,
-         &tp->data_size, &tp->index_key_is_user_key,
-         &tp->index_value_is_delta_encoded, &tp->index_size, &tp->filter_size);
+         &tp->num_data_blocks, &tp->num_entries, &tp->num_deletions,
+         &tp->num_merge_operands, &tp->num_range_deletions, &tp->raw_key_size,
+         &dummy_double, &tp->raw_value_size, &dummy_double, &tp->data_size,
+         &tp->index_key_is_user_key, &tp->index_value_is_delta_encoded,
+         &tp->index_size, &tp->filter_size);
 }
 
 void VerifySimilar(uint64_t a, uint64_t b, double bias) {
@@ -217,28 +221,43 @@ void VerifyTableProperties(const TableProperties& base_tp,
   VerifySimilar(base_tp.filter_size, new_tp.filter_size, filter_size_bias);
   VerifySimilar(base_tp.num_data_blocks, new_tp.num_data_blocks,
                 num_data_blocks_bias);
+
   ASSERT_EQ(base_tp.raw_key_size, new_tp.raw_key_size);
   ASSERT_EQ(base_tp.raw_value_size, new_tp.raw_value_size);
   ASSERT_EQ(base_tp.num_entries, new_tp.num_entries);
+  ASSERT_EQ(base_tp.num_deletions, new_tp.num_deletions);
   ASSERT_EQ(base_tp.num_range_deletions, new_tp.num_range_deletions);
+
+  // Merge operands may become Puts, so we only have an upper bound the exact
+  // number of merge operands.
+  ASSERT_GE(base_tp.num_merge_operands, new_tp.num_merge_operands);
 }
 
 void GetExpectedTableProperties(
     TableProperties* expected_tp, const int kKeySize, const int kValueSize,
-    const int kKeysPerTable, const int kRangeDeletionsPerTable,
+    const int kPutsPerTable, const int kDeletionsPerTable,
+    const int kMergeOperandsPerTable, const int kRangeDeletionsPerTable,
     const int kTableCount, const int kBloomBitsPerKey, const size_t kBlockSize,
     const bool index_key_is_user_key, const bool value_delta_encoding) {
-  const int kKeyCount = kTableCount * kKeysPerTable;
+  const int kKeysPerTable =
+      kPutsPerTable + kDeletionsPerTable + kMergeOperandsPerTable;
+  const int kPutCount = kTableCount * kPutsPerTable;
+  const int kDeletionCount = kTableCount * kDeletionsPerTable;
+  const int kMergeCount = kTableCount * kMergeOperandsPerTable;
   const int kRangeDeletionCount = kTableCount * kRangeDeletionsPerTable;
+  const int kKeyCount = kPutCount + kDeletionCount + kMergeCount;
   const int kAvgSuccessorSize = kKeySize / 5;
   const int kEncodingSavePerKey = kKeySize / 4;
-  expected_tp->raw_key_size = (kKeyCount + kRangeDeletionCount) * (kKeySize + 8);
-  expected_tp->raw_value_size = (kKeyCount + kRangeDeletionCount) * kValueSize;
+  expected_tp->raw_key_size =
+      (kKeyCount + kRangeDeletionCount) * (kKeySize + 8);
+  expected_tp->raw_value_size =
+      (kPutCount + kMergeCount + kRangeDeletionCount) * kValueSize;
   expected_tp->num_entries = kKeyCount;
+  expected_tp->num_deletions = kDeletionCount;
+  expected_tp->num_merge_operands = kMergeCount;
   expected_tp->num_range_deletions = kRangeDeletionCount;
   expected_tp->num_data_blocks =
-      kTableCount *
-      (kKeysPerTable * (kKeySize - kEncodingSavePerKey + kValueSize)) /
+      kTableCount * (kKeysPerTable * (kKeySize - kEncodingSavePerKey + kValueSize)) /
       kBlockSize;
   expected_tp->data_size =
       kTableCount * (kKeysPerTable * (kKeySize + 8 + kValueSize));
@@ -298,8 +317,10 @@ TEST_F(DBPropertiesTest, ValidateSampleNumber) {
 
 TEST_F(DBPropertiesTest, AggregatedTableProperties) {
   for (int kTableCount = 40; kTableCount <= 100; kTableCount += 30) {
+    const int kDeletionsPerTable = 5;
+    const int kMergeOperandsPerTable = 15;
     const int kRangeDeletionsPerTable = 5;
-    const int kKeysPerTable = 100;
+    const int kPutsPerTable = 100;
     const int kKeySize = 80;
     const int kValueSize = 200;
     const int kBloomBitsPerKey = 20;
@@ -308,6 +329,8 @@ TEST_F(DBPropertiesTest, AggregatedTableProperties) {
     options.level0_file_num_compaction_trigger = 8;
     options.compression = kNoCompression;
     options.create_if_missing = true;
+    options.preserve_deletes = true;
+    options.merge_operator.reset(new TestPutOperator());
 
     BlockBasedTableOptions table_options;
     table_options.filter_policy.reset(
@@ -323,10 +346,17 @@ TEST_F(DBPropertiesTest, AggregatedTableProperties) {
 
     Random rnd(5632);
     for (int table = 1; table <= kTableCount; ++table) {
-      for (int i = 0; i < kKeysPerTable; ++i) {
+      for (int i = 0; i < kPutsPerTable; ++i) {
         db_->Put(WriteOptions(), RandomString(&rnd, kKeySize),
                  RandomString(&rnd, kValueSize));
       }
+      for (int i = 0; i < kDeletionsPerTable; i++) {
+        db_->Delete(WriteOptions(), RandomString(&rnd, kKeySize));
+      }
+      for (int i = 0; i < kMergeOperandsPerTable; i++) {
+        db_->Merge(WriteOptions(), RandomString(&rnd, kKeySize),
+                   RandomString(&rnd, kValueSize));
+      }
       for (int i = 0; i < kRangeDeletionsPerTable; i++) {
         std::string start = RandomString(&rnd, kKeySize);
         std::string end = start;
@@ -343,11 +373,11 @@ TEST_F(DBPropertiesTest, AggregatedTableProperties) {
     bool value_is_delta_encoded = output_tp.index_value_is_delta_encoded > 0;
 
     TableProperties expected_tp;
-    GetExpectedTableProperties(&expected_tp, kKeySize, kValueSize,
-                               kKeysPerTable, kRangeDeletionsPerTable,
-                               kTableCount, kBloomBitsPerKey,
-                               table_options.block_size, index_key_is_user_key,
-                               value_is_delta_encoded);
+    GetExpectedTableProperties(
+        &expected_tp, kKeySize, kValueSize, kPutsPerTable, kDeletionsPerTable,
+        kMergeOperandsPerTable, kRangeDeletionsPerTable, kTableCount,
+        kBloomBitsPerKey, table_options.block_size, index_key_is_user_key,
+        value_is_delta_encoded);
 
     VerifyTableProperties(expected_tp, output_tp);
   }
@@ -416,7 +446,7 @@ TEST_F(DBPropertiesTest, ReadLatencyHistogramByLevel) {
   ASSERT_EQ(std::string::npos, prop.find("** Level 1 read latency histogram"));
   ASSERT_EQ(std::string::npos, prop.find("** Level 2 read latency histogram"));
   {
-    unique_ptr<Iterator> iter(db_->NewIterator(ReadOptions()));
+    std::unique_ptr<Iterator> iter(db_->NewIterator(ReadOptions()));
     for (iter->Seek(Key(0)); iter->Valid(); iter->Next()) {
     }
   }
@@ -469,8 +499,10 @@ TEST_F(DBPropertiesTest, ReadLatencyHistogramByLevel) {
 
 TEST_F(DBPropertiesTest, AggregatedTablePropertiesAtLevel) {
   const int kTableCount = 100;
+  const int kDeletionsPerTable = 2;
+  const int kMergeOperandsPerTable = 2;
   const int kRangeDeletionsPerTable = 2;
-  const int kKeysPerTable = 10;
+  const int kPutsPerTable = 10;
   const int kKeySize = 50;
   const int kValueSize = 400;
   const int kMaxLevel = 7;
@@ -486,6 +518,8 @@ TEST_F(DBPropertiesTest, AggregatedTablePropertiesAtLevel) {
   options.max_bytes_for_level_multiplier = 2;
   // This ensures there no compaction happening when we call GetProperty().
   options.disable_auto_compactions = true;
+  options.preserve_deletes = true;
+  options.merge_operator.reset(new TestPutOperator());
 
   BlockBasedTableOptions table_options;
   table_options.filter_policy.reset(
@@ -503,10 +537,17 @@ TEST_F(DBPropertiesTest, AggregatedTablePropertiesAtLevel) {
   TableProperties level_tps[kMaxLevel];
   TableProperties tp, sum_tp, expected_tp;
   for (int table = 1; table <= kTableCount; ++table) {
-    for (int i = 0; i < kKeysPerTable; ++i) {
+    for (int i = 0; i < kPutsPerTable; ++i) {
       db_->Put(WriteOptions(), RandomString(&rnd, kKeySize),
                RandomString(&rnd, kValueSize));
     }
+    for (int i = 0; i < kDeletionsPerTable; i++) {
+      db_->Delete(WriteOptions(), RandomString(&rnd, kKeySize));
+    }
+    for (int i = 0; i < kMergeOperandsPerTable; i++) {
+      db_->Merge(WriteOptions(), RandomString(&rnd, kKeySize),
+                 RandomString(&rnd, kValueSize));
+    }
     for (int i = 0; i < kRangeDeletionsPerTable; i++) {
       std::string start = RandomString(&rnd, kKeySize);
       std::string end = start;
@@ -528,6 +569,8 @@ TEST_F(DBPropertiesTest, AggregatedTablePropertiesAtLevel) {
       sum_tp.raw_value_size += level_tps[level].raw_value_size;
       sum_tp.num_data_blocks += level_tps[level].num_data_blocks;
       sum_tp.num_entries += level_tps[level].num_entries;
+      sum_tp.num_deletions += level_tps[level].num_deletions;
+      sum_tp.num_merge_operands += level_tps[level].num_merge_operands;
       sum_tp.num_range_deletions += level_tps[level].num_range_deletions;
     }
     db_->GetProperty(DB::Properties::kAggregatedTableProperties, &tp_string);
@@ -541,12 +584,15 @@ TEST_F(DBPropertiesTest, AggregatedTablePropertiesAtLevel) {
     ASSERT_EQ(sum_tp.raw_value_size, tp.raw_value_size);
     ASSERT_EQ(sum_tp.num_data_blocks, tp.num_data_blocks);
     ASSERT_EQ(sum_tp.num_entries, tp.num_entries);
+    ASSERT_EQ(sum_tp.num_deletions, tp.num_deletions);
+    ASSERT_EQ(sum_tp.num_merge_operands, tp.num_merge_operands);
     ASSERT_EQ(sum_tp.num_range_deletions, tp.num_range_deletions);
     if (table > 3) {
-      GetExpectedTableProperties(&expected_tp, kKeySize, kValueSize,
-                                 kKeysPerTable, kRangeDeletionsPerTable, table,
-                                 kBloomBitsPerKey, table_options.block_size,
-                                 index_key_is_user_key, value_is_delta_encoded);
+      GetExpectedTableProperties(
+          &expected_tp, kKeySize, kValueSize, kPutsPerTable, kDeletionsPerTable,
+          kMergeOperandsPerTable, kRangeDeletionsPerTable, table,
+          kBloomBitsPerKey, table_options.block_size, index_key_is_user_key,
+          value_is_delta_encoded);
       // Gives larger bias here as index block size, filter block size,
       // and data block size become much harder to estimate in this test.
       VerifyTableProperties(expected_tp, tp, 0.5, 0.4, 0.4, 0.25);
@@ -1483,6 +1529,64 @@ TEST_F(DBPropertiesTest, SstFilesSize) {
   ASSERT_TRUE(listener->callback_triggered);
 }
 
+TEST_F(DBPropertiesTest, MinObsoleteSstNumberToKeep) {
+  class TestListener : public EventListener {
+   public:
+    void OnTableFileCreated(const TableFileCreationInfo& info) override {
+      if (info.reason == TableFileCreationReason::kCompaction) {
+        // Verify the property indicates that SSTs created by a running
+        // compaction cannot be deleted.
+        uint64_t created_file_num;
+        FileType created_file_type;
+        std::string filename =
+            info.file_path.substr(info.file_path.rfind('/') + 1);
+        ASSERT_TRUE(
+            ParseFileName(filename, &created_file_num, &created_file_type));
+        ASSERT_EQ(kTableFile, created_file_type);
+
+        uint64_t keep_sst_lower_bound;
+        ASSERT_TRUE(
+            db_->GetIntProperty(DB::Properties::kMinObsoleteSstNumberToKeep,
+                                &keep_sst_lower_bound));
+
+        ASSERT_LE(keep_sst_lower_bound, created_file_num);
+        validated_ = true;
+      }
+    }
+
+    void SetDB(DB* db) { db_ = db; }
+
+    int GetNumCompactions() { return num_compactions_; }
+
+    // True if we've verified the property for at least one output file
+    bool Validated() { return validated_; }
+
+   private:
+    int num_compactions_ = 0;
+    bool validated_ = false;
+    DB* db_ = nullptr;
+  };
+
+  const int kNumL0Files = 4;
+
+  std::shared_ptr<TestListener> listener = std::make_shared<TestListener>();
+
+  Options options = CurrentOptions();
+  options.listeners.push_back(listener);
+  options.level0_file_num_compaction_trigger = kNumL0Files;
+  DestroyAndReopen(options);
+  listener->SetDB(db_);
+
+  for (int i = 0; i < kNumL0Files; ++i) {
+    // Make sure they overlap in keyspace to prevent trivial move
+    Put("key1", "val");
+    Put("key2", "val");
+    Flush();
+  }
+  dbfull()->TEST_WaitForCompact();
+  ASSERT_TRUE(listener->Validated());
+}
+
 TEST_F(DBPropertiesTest, BlockCacheProperties) {
   Options options;
   uint64_t value;
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_range_del_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_range_del_test.cc
similarity index 74%
rename from 3rdParty/rocksdb/v5.16.X/db/db_range_del_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_range_del_test.cc
index 9ca0633355..508149a340 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_range_del_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_range_del_test.cc
@@ -1103,6 +1103,386 @@ TEST_F(DBRangeDelTest, UnorderedTombstones) {
   ASSERT_TRUE(s.IsNotFound());
 }
 
+class MockMergeOperator : public MergeOperator {
+  // Mock non-associative operator. Non-associativity is expressed by lack of
+  // implementation for any `PartialMerge*` functions.
+ public:
+  virtual bool FullMergeV2(const MergeOperationInput& merge_in,
+                           MergeOperationOutput* merge_out) const override {
+    assert(merge_out != nullptr);
+    merge_out->new_value = merge_in.operand_list.back().ToString();
+    return true;
+  }
+
+  virtual const char* Name() const override { return "MockMergeOperator"; }
+};
+
+TEST_F(DBRangeDelTest, KeyAtOverlappingEndpointReappears) {
+  // This test uses a non-associative merge operator since that is a convenient
+  // way to get compaction to write out files with overlapping user-keys at the
+  // endpoints. Note, however, overlapping endpoints can also occur with other
+  // value types (Put, etc.), assuming the right snapshots are present.
+  const int kFileBytes = 1 << 20;
+  const int kValueBytes = 1 << 10;
+  const int kNumFiles = 4;
+
+  Options options = CurrentOptions();
+  options.compression = kNoCompression;
+  options.disable_auto_compactions = true;
+  options.merge_operator.reset(new MockMergeOperator());
+  options.target_file_size_base = kFileBytes;
+  Reopen(options);
+
+  Random rnd(301);
+  const Snapshot* snapshot = nullptr;
+  for (int i = 0; i < kNumFiles; ++i) {
+    for (int j = 0; j < kFileBytes / kValueBytes; ++j) {
+      auto value = RandomString(&rnd, kValueBytes);
+      ASSERT_OK(db_->Merge(WriteOptions(), "key", value));
+    }
+    if (i == kNumFiles - 1) {
+      // Take snapshot to prevent covered merge operands from being dropped by
+      // compaction.
+      snapshot = db_->GetSnapshot();
+      // The DeleteRange is the last write so all merge operands are covered.
+      ASSERT_OK(db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(),
+                                 "key", "key_"));
+    }
+    ASSERT_OK(db_->Flush(FlushOptions()));
+  }
+  ASSERT_EQ(kNumFiles, NumTableFilesAtLevel(0));
+  std::string value;
+  ASSERT_TRUE(db_->Get(ReadOptions(), "key", &value).IsNotFound());
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr /* begin_key */,
+                              nullptr /* end_key */));
+  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+  // Now we have multiple files at L1 all containing a single user key, thus
+  // guaranteeing overlap in the file endpoints.
+  ASSERT_GT(NumTableFilesAtLevel(1), 1);
+
+  // Verify no merge operands reappeared after the compaction.
+  ASSERT_TRUE(db_->Get(ReadOptions(), "key", &value).IsNotFound());
+
+  // Compact and verify again. It's worthwhile because now the files have
+  // tighter endpoints, so we can verify that doesn't mess anything up.
+  dbfull()->TEST_CompactRange(1 /* level */, nullptr /* begin */,
+                              nullptr /* end */, nullptr /* column_family */,
+                              true /* disallow_trivial_move */);
+  ASSERT_GT(NumTableFilesAtLevel(2), 1);
+  ASSERT_TRUE(db_->Get(ReadOptions(), "key", &value).IsNotFound());
+
+  db_->ReleaseSnapshot(snapshot);
+}
+
+TEST_F(DBRangeDelTest, UntruncatedTombstoneDoesNotDeleteNewerKey) {
+  // Verify a key newer than a range tombstone cannot be deleted by being
+  // compacted to the bottom level (and thus having its seqnum zeroed) before
+  // the range tombstone. This used to happen when range tombstones were
+  // untruncated on reads such that they extended past their file boundaries.
+  //
+  // Test summary:
+  //
+  // - L1 is bottommost.
+  // - A couple snapshots are strategically taken to prevent seqnums from being
+  //   zeroed, range tombstone from being dropped, merge operands from being
+  //   dropped, and merge operands from being combined.
+  // - Left half of files in L1 all have same user key, ensuring their file
+  //   boundaries overlap. In the past this would cause range tombstones to be
+  //   untruncated.
+  // - Right half of L1 files all have different keys, ensuring no overlap.
+  // - A range tombstone spans all L1 keys, so it is stored in every L1 file.
+  // - Keys in the right side of the key-range are overwritten. These are
+  //   compacted down to L1 after releasing snapshots such that their seqnums
+  //   will be zeroed.
+  // - A full range scan is performed. If the tombstone in the left L1 files
+  //   were untruncated, it would now cover keys newer than it (but with zeroed
+  //   seqnums) in the right L1 files.
+  const int kFileBytes = 1 << 20;
+  const int kValueBytes = 1 << 10;
+  const int kNumFiles = 4;
+  const int kMaxKey = kNumFiles* kFileBytes / kValueBytes;
+  const int kKeysOverwritten = 10;
+
+  Options options = CurrentOptions();
+  options.compression = kNoCompression;
+  options.disable_auto_compactions = true;
+  options.merge_operator.reset(new MockMergeOperator());
+  options.num_levels = 2;
+  options.target_file_size_base = kFileBytes;
+  Reopen(options);
+
+  Random rnd(301);
+  // - snapshots[0] prevents merge operands from being combined during
+  //   compaction.
+  // - snapshots[1] prevents merge operands from being dropped due to the
+  //   covering range tombstone.
+  const Snapshot* snapshots[] = {nullptr, nullptr};
+  for (int i = 0; i < kNumFiles; ++i) {
+    for (int j = 0; j < kFileBytes / kValueBytes; ++j) {
+      auto value = RandomString(&rnd, kValueBytes);
+      std::string key;
+      if (i < kNumFiles / 2) {
+        key = Key(0);
+      } else {
+        key = Key(1 + i * kFileBytes / kValueBytes + j);
+      }
+      ASSERT_OK(db_->Merge(WriteOptions(), key, value));
+    }
+    if (i == 0) {
+      snapshots[0] = db_->GetSnapshot();
+    }
+    if (i == kNumFiles - 1) {
+      snapshots[1] = db_->GetSnapshot();
+      // The DeleteRange is the last write so all merge operands are covered.
+      ASSERT_OK(db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(),
+                                 Key(0), Key(kMaxKey + 1)));
+    }
+    ASSERT_OK(db_->Flush(FlushOptions()));
+  }
+  ASSERT_EQ(kNumFiles, NumTableFilesAtLevel(0));
+
+  auto get_key_count = [this]() -> int {
+    auto* iter = db_->NewIterator(ReadOptions());
+    iter->SeekToFirst();
+    int keys_found = 0;
+    for (; iter->Valid(); iter->Next()) {
+      ++keys_found;
+    }
+    delete iter;
+    return keys_found;
+  };
+
+  // All keys should be covered
+  ASSERT_EQ(0, get_key_count());
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr /* begin_key */,
+                              nullptr /* end_key */));
+  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+  // Roughly the left half of L1 files should have overlapping boundary keys,
+  // while the right half should not.
+  ASSERT_GE(NumTableFilesAtLevel(1), kNumFiles);
+
+  // Now overwrite a few keys that are in L1 files that definitely don't have
+  // overlapping boundary keys.
+  for (int i = kMaxKey; i > kMaxKey - kKeysOverwritten; --i) {
+    auto value = RandomString(&rnd, kValueBytes);
+    ASSERT_OK(db_->Merge(WriteOptions(), Key(i), value));
+  }
+  ASSERT_OK(db_->Flush(FlushOptions()));
+
+  // The overwritten keys are in L0 now, so clearly aren't covered by the range
+  // tombstone in L1.
+  ASSERT_EQ(kKeysOverwritten, get_key_count());
+
+  // Release snapshots so seqnums can be zeroed when L0->L1 happens.
+  db_->ReleaseSnapshot(snapshots[0]);
+  db_->ReleaseSnapshot(snapshots[1]);
+
+  auto begin_key_storage = Key(kMaxKey - kKeysOverwritten + 1);
+  auto end_key_storage = Key(kMaxKey);
+  Slice begin_key(begin_key_storage);
+  Slice end_key(end_key_storage);
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), &begin_key, &end_key));
+  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+  ASSERT_GE(NumTableFilesAtLevel(1), kNumFiles);
+
+  ASSERT_EQ(kKeysOverwritten, get_key_count());
+}
+
+TEST_F(DBRangeDelTest, DeletedMergeOperandReappearsIterPrev) {
+  // Exposes a bug where we were using
+  // `RangeDelPositioningMode::kBackwardTraversal` while scanning merge operands
+  // in the forward direction. Confusingly, this case happened during
+  // `DBIter::Prev`. It could cause assertion failure, or reappearing keys.
+  const int kFileBytes = 1 << 20;
+  const int kValueBytes = 1 << 10;
+  // Need multiple keys so we can get results when calling `Prev()` after
+  // `SeekToLast()`.
+  const int kNumKeys = 3;
+  const int kNumFiles = 4;
+
+  Options options = CurrentOptions();
+  options.compression = kNoCompression;
+  options.disable_auto_compactions = true;
+  options.merge_operator.reset(new MockMergeOperator());
+  options.target_file_size_base = kFileBytes;
+  Reopen(options);
+
+  Random rnd(301);
+  const Snapshot* snapshot = nullptr;
+  for (int i = 0; i < kNumFiles; ++i) {
+    for (int j = 0; j < kFileBytes / kValueBytes; ++j) {
+      auto value = RandomString(&rnd, kValueBytes);
+      ASSERT_OK(db_->Merge(WriteOptions(), Key(j % kNumKeys), value));
+      if (i == 0 && j == kNumKeys) {
+        // Take snapshot to prevent covered merge operands from being dropped or
+        // merged by compaction.
+        snapshot = db_->GetSnapshot();
+        // Do a DeleteRange near the beginning so only the oldest merge operand
+        // for each key is covered. This ensures the sequence of events:
+        //
+        // - `DBIter::Prev()` is called
+        // - After several same versions of the same user key are encountered,
+        //   it decides to seek using `DBIter::FindValueForCurrentKeyUsingSeek`.
+        // - Binary searches to the newest version of the key, which is in the
+        //   leftmost file containing the user key.
+        // - Scans forwards to collect all merge operands. Eventually reaches
+        //   the rightmost file containing the oldest merge operand, which
+        //   should be covered by the `DeleteRange`. If `RangeDelAggregator`
+        //   were not properly using `kForwardTraversal` here, that operand
+        //   would reappear.
+        ASSERT_OK(db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(),
+                                   Key(0), Key(kNumKeys + 1)));
+      }
+    }
+    ASSERT_OK(db_->Flush(FlushOptions()));
+  }
+  ASSERT_EQ(kNumFiles, NumTableFilesAtLevel(0));
+
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr /* begin_key */,
+                              nullptr /* end_key */));
+  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+  ASSERT_GT(NumTableFilesAtLevel(1), 1);
+
+  auto* iter = db_->NewIterator(ReadOptions());
+  iter->SeekToLast();
+  int keys_found = 0;
+  for (; iter->Valid(); iter->Prev()) {
+    ++keys_found;
+  }
+  delete iter;
+  ASSERT_EQ(kNumKeys, keys_found);
+
+  db_->ReleaseSnapshot(snapshot);
+}
+
+TEST_F(DBRangeDelTest, SnapshotPreventsDroppedKeys) {
+  const int kFileBytes = 1 << 20;
+
+  Options options = CurrentOptions();
+  options.compression = kNoCompression;
+  options.disable_auto_compactions = true;
+  options.target_file_size_base = kFileBytes;
+  Reopen(options);
+
+  ASSERT_OK(Put(Key(0), "a"));
+  const Snapshot* snapshot = db_->GetSnapshot();
+
+  ASSERT_OK(db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(), Key(0),
+                             Key(10)));
+
+  db_->Flush(FlushOptions());
+
+  ReadOptions read_opts;
+  read_opts.snapshot = snapshot;
+  auto* iter = db_->NewIterator(read_opts);
+
+  iter->SeekToFirst();
+  ASSERT_TRUE(iter->Valid());
+  ASSERT_EQ(Key(0), iter->key());
+
+  iter->Next();
+  ASSERT_FALSE(iter->Valid());
+
+  delete iter;
+  db_->ReleaseSnapshot(snapshot);
+}
+
+TEST_F(DBRangeDelTest, RangeTombstoneWrittenToMinimalSsts) {
+  // Adapted from
+  // https://github.com/cockroachdb/cockroach/blob/de8b3ea603dd1592d9dc26443c2cc92c356fbc2f/pkg/storage/engine/rocksdb_test.go#L1267-L1398.
+  // Regression test for issue where range tombstone was written to more files
+  // than necessary when it began exactly at the begin key in the next
+  // compaction output file.
+  const int kFileBytes = 1 << 20;
+  const int kValueBytes = 4 << 10;
+  Options options = CurrentOptions();
+  options.compression = kNoCompression;
+  options.disable_auto_compactions = true;
+  // Have a bit of slack in the size limits but we enforce them more strictly
+  // when manually flushing/compacting.
+  options.max_compaction_bytes = 2 * kFileBytes;
+  options.target_file_size_base = 2 * kFileBytes;
+  options.write_buffer_size = 2 * kFileBytes;
+  Reopen(options);
+
+  Random rnd(301);
+  for (char first_char : {'a', 'b', 'c'}) {
+    for (int i = 0; i < kFileBytes / kValueBytes; ++i) {
+      std::string key(1, first_char);
+      key.append(Key(i));
+      std::string value = RandomString(&rnd, kValueBytes);
+      ASSERT_OK(Put(key, value));
+    }
+    db_->Flush(FlushOptions());
+    MoveFilesToLevel(2);
+  }
+  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+  ASSERT_EQ(3, NumTableFilesAtLevel(2));
+
+  // Populate the memtable lightly while spanning the whole key-space. The
+  // setting of `max_compaction_bytes` will cause the L0->L1 to output multiple
+  // files to prevent a large L1->L2 compaction later.
+  ASSERT_OK(Put("a", "val"));
+  ASSERT_OK(db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(),
+                             "c" + Key(1), "d"));
+  // Our compaction output file cutting logic currently only considers point
+  // keys. So, in order for the range tombstone to have a chance at landing at
+  // the start of a new file, we need a point key at the range tombstone's
+  // start.
+  // TODO(ajkr): remove this `Put` after file cutting accounts for range
+  // tombstones (#3977).
+  ASSERT_OK(Put("c" + Key(1), "value"));
+  db_->Flush(FlushOptions());
+
+  // Ensure manual L0->L1 compaction cuts the outputs before the range tombstone
+  // and the range tombstone is only placed in the second SST.
+  std::string begin_key_storage("c" + Key(1));
+  Slice begin_key(begin_key_storage);
+  std::string end_key_storage("d");
+  Slice end_key(end_key_storage);
+  dbfull()->TEST_CompactRange(0 /* level */, &begin_key /* begin */,
+                              &end_key /* end */, nullptr /* column_family */,
+                              true /* disallow_trivial_move */);
+  ASSERT_EQ(2, NumTableFilesAtLevel(1));
+
+  std::vector<LiveFileMetaData> all_metadata;
+  std::vector<LiveFileMetaData> l1_metadata;
+  db_->GetLiveFilesMetaData(&all_metadata);
+  for (const auto& metadata : all_metadata) {
+    if (metadata.level == 1) {
+      l1_metadata.push_back(metadata);
+    }
+  }
+  std::sort(l1_metadata.begin(), l1_metadata.end(),
+            [&](const LiveFileMetaData& a, const LiveFileMetaData& b) {
+              return options.comparator->Compare(a.smallestkey, b.smallestkey) <
+                     0;
+            });
+  ASSERT_EQ("a", l1_metadata[0].smallestkey);
+  ASSERT_EQ("a", l1_metadata[0].largestkey);
+  ASSERT_EQ("c" + Key(1), l1_metadata[1].smallestkey);
+  ASSERT_EQ("d", l1_metadata[1].largestkey);
+
+  TablePropertiesCollection all_table_props;
+  ASSERT_OK(db_->GetPropertiesOfAllTables(&all_table_props));
+  int64_t num_range_deletions = 0;
+  for (const auto& name_and_table_props : all_table_props) {
+    const auto& name = name_and_table_props.first;
+    const auto& table_props = name_and_table_props.second;
+    // The range tombstone should only be output to the second L1 SST.
+    if (name.size() >= l1_metadata[1].name.size() &&
+        name.substr(name.size() - l1_metadata[1].name.size()).compare(l1_metadata[1].name) == 0) {
+      ASSERT_EQ(1, table_props->num_range_deletions);
+      ++num_range_deletions;
+    } else {
+      ASSERT_EQ(0, table_props->num_range_deletions);
+    }
+  }
+  ASSERT_EQ(1, num_range_deletions);
+}
+
 #endif  // ROCKSDB_LITE
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_sst_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_sst_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_sst_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_sst_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_statistics_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_statistics_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_statistics_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_statistics_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_table_properties_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_table_properties_test.cc
similarity index 84%
rename from 3rdParty/rocksdb/v5.16.X/db/db_table_properties_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_table_properties_test.cc
index b12a568025..5a54fd81c0 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_table_properties_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_table_properties_test.cc
@@ -252,13 +252,14 @@ TEST_F(DBTablePropertiesTest, GetColumnFamilyNameProperty) {
 }
 
 TEST_F(DBTablePropertiesTest, DeletionTriggeredCompactionMarking) {
-  const int kNumKeys = 1000;
-  const int kWindowSize = 100;
-  const int kNumDelsTrigger = 90;
+  int kNumKeys = 1000;
+  int kWindowSize = 100;
+  int kNumDelsTrigger = 90;
+  std::shared_ptr<TablePropertiesCollectorFactory> compact_on_del =
+    NewCompactOnDeletionCollectorFactory(kWindowSize, kNumDelsTrigger);
 
   Options opts = CurrentOptions();
-  opts.table_properties_collector_factories.emplace_back(
-      NewCompactOnDeletionCollectorFactory(kWindowSize, kNumDelsTrigger));
+  opts.table_properties_collector_factories.emplace_back(compact_on_del);
   Reopen(opts);
 
   // add an L1 file to prevent tombstones from dropping due to obsolescence
@@ -280,6 +281,48 @@ TEST_F(DBTablePropertiesTest, DeletionTriggeredCompactionMarking) {
   dbfull()->TEST_WaitForCompact();
   ASSERT_EQ(0, NumTableFilesAtLevel(0));
   ASSERT_GT(NumTableFilesAtLevel(1), 0);
+
+  // Change the window size and deletion trigger and ensure new values take
+  // effect
+  kWindowSize = 50;
+  kNumDelsTrigger = 40;
+  static_cast<CompactOnDeletionCollectorFactory*>
+    (compact_on_del.get())->SetWindowSize(kWindowSize);
+  static_cast<CompactOnDeletionCollectorFactory*>
+    (compact_on_del.get())->SetDeletionTrigger(kNumDelsTrigger);
+  for (int i = 0; i < kNumKeys; ++i) {
+    if (i >= kNumKeys - kWindowSize &&
+        i < kNumKeys - kWindowSize + kNumDelsTrigger) {
+      Delete(Key(i));
+    } else {
+      Put(Key(i), "val");
+    }
+  }
+  Flush();
+
+  dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+  ASSERT_GT(NumTableFilesAtLevel(1), 0);
+
+  // Change the window size to disable delete triggered compaction
+  kWindowSize = 0;
+  static_cast<CompactOnDeletionCollectorFactory*>
+    (compact_on_del.get())->SetWindowSize(kWindowSize);
+  static_cast<CompactOnDeletionCollectorFactory*>
+    (compact_on_del.get())->SetDeletionTrigger(kNumDelsTrigger);
+  for (int i = 0; i < kNumKeys; ++i) {
+    if (i >= kNumKeys - kWindowSize &&
+        i < kNumKeys - kWindowSize + kNumDelsTrigger) {
+      Delete(Key(i));
+    } else {
+      Put(Key(i), "val");
+    }
+  }
+  Flush();
+
+  dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(1, NumTableFilesAtLevel(0));
+
 }
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_tailing_iter_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_tailing_iter_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_tailing_iter_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_tailing_iter_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_test.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/db/db_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_test.cc
index f65007052d..5a9c394692 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_test.cc
@@ -93,7 +93,7 @@ class DBTestWithParam
 };
 
 TEST_F(DBTest, MockEnvTest) {
-  unique_ptr<MockEnv> env{new MockEnv(Env::Default())};
+  std::unique_ptr<MockEnv> env{new MockEnv(Env::Default())};
   Options options;
   options.create_if_missing = true;
   options.env = env.get();
@@ -143,7 +143,7 @@ TEST_F(DBTest, MockEnvTest) {
 // defined.
 #ifndef ROCKSDB_LITE
 TEST_F(DBTest, MemEnvTest) {
-  unique_ptr<Env> env{NewMemEnv(Env::Default())};
+  std::unique_ptr<Env> env{NewMemEnv(Env::Default())};
   Options options;
   options.create_if_missing = true;
   options.env = env.get();
@@ -262,6 +262,196 @@ TEST_F(DBTest, SkipDelay) {
   }
 }
 
+TEST_F(DBTest, MixedSlowdownOptions) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.write_buffer_size = 100000;
+  CreateAndReopenWithCF({"pikachu"}, options);
+  std::vector<port::Thread> threads;
+  std::atomic<int> thread_num(0);
+
+  std::function<void()> write_slowdown_func = [&]() {
+    int a = thread_num.fetch_add(1);
+    std::string key = "foo" + std::to_string(a);
+    WriteOptions wo;
+    wo.no_slowdown = false;
+    ASSERT_OK(dbfull()->Put(wo, key, "bar"));
+  };
+  std::function<void()> write_no_slowdown_func = [&]() {
+    int a = thread_num.fetch_add(1);
+    std::string key = "foo" + std::to_string(a);
+    WriteOptions wo;
+    wo.no_slowdown = true;
+    ASSERT_NOK(dbfull()->Put(wo, key, "bar"));
+  };
+  // Use a small number to ensure a large delay that is still effective
+  // when we do Put
+  // TODO(myabandeh): this is time dependent and could potentially make
+  // the test flaky
+  auto token = dbfull()->TEST_write_controler().GetDelayToken(1);
+  std::atomic<int> sleep_count(0);
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::DelayWrite:BeginWriteStallDone",
+      [&](void* /*arg*/) {
+        sleep_count.fetch_add(1);
+        if (threads.empty()) {
+          for (int i = 0; i < 2; ++i) {
+            threads.emplace_back(write_slowdown_func);
+          }
+          for (int i = 0; i < 2; ++i) {
+            threads.emplace_back(write_no_slowdown_func);
+          }
+        }
+      });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  WriteOptions wo;
+  wo.sync = false;
+  wo.disableWAL = false;
+  wo.no_slowdown = false;
+  dbfull()->Put(wo, "foo", "bar");
+  // We need the 2nd write to trigger delay. This is because delay is
+  // estimated based on the last write size which is 0 for the first write.
+  ASSERT_OK(dbfull()->Put(wo, "foo2", "bar2"));
+          token.reset();
+
+  for (auto& t : threads) {
+    t.join();
+  }
+  ASSERT_GE(sleep_count.load(), 1);
+
+  wo.no_slowdown = true;
+  ASSERT_OK(dbfull()->Put(wo, "foo3", "bar"));
+}
+
+TEST_F(DBTest, MixedSlowdownOptionsInQueue) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.write_buffer_size = 100000;
+  CreateAndReopenWithCF({"pikachu"}, options);
+  std::vector<port::Thread> threads;
+  std::atomic<int> thread_num(0);
+
+  std::function<void()> write_no_slowdown_func = [&]() {
+    int a = thread_num.fetch_add(1);
+    std::string key = "foo" + std::to_string(a);
+    WriteOptions wo;
+    wo.no_slowdown = true;
+    ASSERT_NOK(dbfull()->Put(wo, key, "bar"));
+  };
+  // Use a small number to ensure a large delay that is still effective
+  // when we do Put
+  // TODO(myabandeh): this is time dependent and could potentially make
+  // the test flaky
+  auto token = dbfull()->TEST_write_controler().GetDelayToken(1);
+  std::atomic<int> sleep_count(0);
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::DelayWrite:Sleep",
+      [&](void* /*arg*/) {
+        sleep_count.fetch_add(1);
+        if (threads.empty()) {
+          for (int i = 0; i < 2; ++i) {
+            threads.emplace_back(write_no_slowdown_func);
+          }
+          // Sleep for 2s to allow the threads to insert themselves into the
+          // write queue
+          env_->SleepForMicroseconds(3000000ULL);
+        }
+      });
+  std::atomic<int> wait_count(0);
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::DelayWrite:Wait",
+      [&](void* /*arg*/) { wait_count.fetch_add(1); });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  WriteOptions wo;
+  wo.sync = false;
+  wo.disableWAL = false;
+  wo.no_slowdown = false;
+  dbfull()->Put(wo, "foo", "bar");
+  // We need the 2nd write to trigger delay. This is because delay is
+  // estimated based on the last write size which is 0 for the first write.
+  ASSERT_OK(dbfull()->Put(wo, "foo2", "bar2"));
+          token.reset();
+
+  for (auto& t : threads) {
+    t.join();
+  }
+  ASSERT_EQ(sleep_count.load(), 1);
+  ASSERT_GE(wait_count.load(), 0);
+}
+
+TEST_F(DBTest, MixedSlowdownOptionsStop) {
+  Options options = CurrentOptions();
+  options.env = env_;
+  options.write_buffer_size = 100000;
+  CreateAndReopenWithCF({"pikachu"}, options);
+  std::vector<port::Thread> threads;
+  std::atomic<int> thread_num(0);
+
+  std::function<void()> write_slowdown_func = [&]() {
+    int a = thread_num.fetch_add(1);
+    std::string key = "foo" + std::to_string(a);
+    WriteOptions wo;
+    wo.no_slowdown = false;
+    ASSERT_OK(dbfull()->Put(wo, key, "bar"));
+  };
+  std::function<void()> write_no_slowdown_func = [&]() {
+    int a = thread_num.fetch_add(1);
+    std::string key = "foo" + std::to_string(a);
+    WriteOptions wo;
+    wo.no_slowdown = true;
+    ASSERT_NOK(dbfull()->Put(wo, key, "bar"));
+  };
+  std::function<void()> wakeup_writer = [&]() {
+    dbfull()->mutex_.Lock();
+    dbfull()->bg_cv_.SignalAll();
+    dbfull()->mutex_.Unlock();
+  };
+  // Use a small number to ensure a large delay that is still effective
+  // when we do Put
+  // TODO(myabandeh): this is time dependent and could potentially make
+  // the test flaky
+  auto token = dbfull()->TEST_write_controler().GetStopToken();
+  std::atomic<int> wait_count(0);
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "DBImpl::DelayWrite:Wait",
+      [&](void* /*arg*/) {
+        wait_count.fetch_add(1);
+        if (threads.empty()) {
+          for (int i = 0; i < 2; ++i) {
+            threads.emplace_back(write_slowdown_func);
+          }
+          for (int i = 0; i < 2; ++i) {
+            threads.emplace_back(write_no_slowdown_func);
+          }
+          // Sleep for 2s to allow the threads to insert themselves into the
+          // write queue
+          env_->SleepForMicroseconds(3000000ULL);
+        }
+        token.reset();
+        threads.emplace_back(wakeup_writer);
+      });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  WriteOptions wo;
+  wo.sync = false;
+  wo.disableWAL = false;
+  wo.no_slowdown = false;
+  dbfull()->Put(wo, "foo", "bar");
+  // We need the 2nd write to trigger delay. This is because delay is
+  // estimated based on the last write size which is 0 for the first write.
+  ASSERT_OK(dbfull()->Put(wo, "foo2", "bar2"));
+          token.reset();
+
+  for (auto& t : threads) {
+    t.join();
+  }
+  ASSERT_GE(wait_count.load(), 1);
+
+  wo.no_slowdown = true;
+  ASSERT_OK(dbfull()->Put(wo, "foo3", "bar"));
+}
 #ifndef ROCKSDB_LITE
 
 TEST_F(DBTest, LevelLimitReopen) {
@@ -2123,6 +2313,9 @@ INSTANTIATE_TEST_CASE_P(
 #endif  // ROCKSDB_LITE
 
 // Group commit test:
+#if !defined(TRAVIS) && !defined(OS_WIN)
+// Disable this test temporarily on Travis and appveyor as it fails
+// intermittently. Github issue: #4151
 namespace {
 
 static const int kGCNumThreads = 4;
@@ -2149,9 +2342,6 @@ static void GCThreadBody(void* arg) {
 
 }  // namespace
 
-#ifndef TRAVIS
-// Disable this test temporarily on Travis as it fails intermittently.
-// Github issue: #4151
 TEST_F(DBTest, GroupCommitTest) {
   do {
     Options options = CurrentOptions();
@@ -2161,7 +2351,9 @@ TEST_F(DBTest, GroupCommitTest) {
 
     rocksdb::SyncPoint::GetInstance()->LoadDependency(
         {{"WriteThread::JoinBatchGroup:BeganWaiting",
-          "DBImpl::WriteImpl:BeforeLeaderEnters"}});
+          "DBImpl::WriteImpl:BeforeLeaderEnters"},
+          {"WriteThread::AwaitState:BlockingWaiting",
+          "WriteThread::EnterAsBatchGroupLeader:End"}});
     rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
     // Start threads
@@ -2469,6 +2661,11 @@ class ModelDB : public DB {
     Status ret;
     return ret;
   }
+  virtual Status Flush(
+      const rocksdb::FlushOptions& /*options*/,
+      const std::vector<ColumnFamilyHandle*>& /*column_families*/) override {
+    return Status::OK();
+  }
 
   virtual Status SyncWAL() override { return Status::OK(); }
 
@@ -2492,7 +2689,8 @@ class ModelDB : public DB {
   }
 
   virtual Status GetUpdatesSince(
-      rocksdb::SequenceNumber, unique_ptr<rocksdb::TransactionLogIterator>*,
+      rocksdb::SequenceNumber,
+      std::unique_ptr<rocksdb::TransactionLogIterator>*,
       const TransactionLogIterator::ReadOptions& /*read_options*/ =
           TransactionLogIterator::ReadOptions()) override {
     return Status::NotSupported("Not supported in Model DB");
@@ -3314,8 +3512,14 @@ TEST_F(DBTest, SanitizeNumThreads) {
                      (i < 4) ? Env::Priority::LOW : Env::Priority::HIGH);
     }
 
-    // Wait 100 milliseconds for they are scheduled.
-    env_->SleepForMicroseconds(100000);
+    // Wait until 10s for they are scheduled.
+    for (int i = 0; i < 10000; i++) {
+      if (options.env->GetThreadPoolQueueLen(Env::Priority::LOW) <= 1 &&
+          options.env->GetThreadPoolQueueLen(Env::Priority::HIGH) <= 2) {
+        break;
+      }
+      env_->SleepForMicroseconds(1000);
+    }
 
     // pool size 3, total task 4. Queue size should be 1.
     ASSERT_EQ(1U, options.env->GetThreadPoolQueueLen(Env::Priority::LOW));
@@ -4331,7 +4535,7 @@ TEST_F(DBTest, DynamicCompactionOptions) {
   // Clean up memtable and L0. Block compaction threads. If continue to write
   // and flush memtables. We should see put stop after 8 memtable flushes
   // since level0_stop_writes_trigger = 8
-  dbfull()->TEST_FlushMemTable(true);
+  dbfull()->TEST_FlushMemTable(true, true);
   dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
   // Block compaction
   test::SleepingBackgroundTask sleeping_task_low;
@@ -4344,7 +4548,7 @@ TEST_F(DBTest, DynamicCompactionOptions) {
   WriteOptions wo;
   while (count < 64) {
     ASSERT_OK(Put(Key(count), RandomString(&rnd, 1024), wo));
-    dbfull()->TEST_FlushMemTable(true);
+    dbfull()->TEST_FlushMemTable(true, true);
     count++;
     if (dbfull()->TEST_write_controler().IsStopped()) {
       sleeping_task_low.WakeUp();
@@ -4372,7 +4576,7 @@ TEST_F(DBTest, DynamicCompactionOptions) {
   count = 0;
   while (count < 64) {
     ASSERT_OK(Put(Key(count), RandomString(&rnd, 1024), wo));
-    dbfull()->TEST_FlushMemTable(true);
+    dbfull()->TEST_FlushMemTable(true, true);
     count++;
     if (dbfull()->TEST_write_controler().IsStopped()) {
       sleeping_task_low.WakeUp();
@@ -5451,41 +5655,18 @@ TEST_F(DBTest, HardLimit) {
 #if !defined(ROCKSDB_LITE) && !defined(ROCKSDB_DISABLE_STALL_NOTIFICATION)
 class WriteStallListener : public EventListener {
  public:
-  WriteStallListener()
-      : cond_(&mutex_),
-        condition_(WriteStallCondition::kNormal),
-        expected_(WriteStallCondition::kNormal),
-        expected_set_(false) {}
+  WriteStallListener() : condition_(WriteStallCondition::kNormal) {}
   void OnStallConditionsChanged(const WriteStallInfo& info) override {
     MutexLock l(&mutex_);
     condition_ = info.condition.cur;
-    if (expected_set_ && condition_ == expected_) {
-      cond_.Signal();
-      expected_set_ = false;
-    }
   }
   bool CheckCondition(WriteStallCondition expected) {
     MutexLock l(&mutex_);
-    if (expected != condition_) {
-      expected_ = expected;
-      expected_set_ = true;
-      while (expected != condition_) {
-        // We bail out on timeout 500 milliseconds
-        const uint64_t timeout_us = 500000;
-        if (cond_.TimedWait(timeout_us)) {
-          expected_set_ = false;
-          return false;
-        }
-      }
-    }
-    return true;
+    return expected == condition_;
   }
  private:
   port::Mutex   mutex_;
-  port::CondVar cond_;
   WriteStallCondition condition_;
-  WriteStallCondition expected_;
-  bool                expected_set_;
 };
 
 TEST_F(DBTest, SoftLimit) {
@@ -5506,13 +5687,48 @@ TEST_F(DBTest, SoftLimit) {
   WriteStallListener* listener = new WriteStallListener();
   options.listeners.emplace_back(listener);
 
+  // FlushMemtable with opt.wait=true does not wait for
+  // `OnStallConditionsChanged` being called. The event listener is triggered
+  // on `JobContext::Clean`, which happens after flush result is installed.
+  // We use sync point to create a custom WaitForFlush that waits for
+  // context cleanup.
+  port::Mutex flush_mutex;
+  port::CondVar flush_cv(&flush_mutex);
+  bool flush_finished = false;
+  auto InstallFlushCallback = [&]() {
+    {
+      MutexLock l(&flush_mutex);
+      flush_finished = false;
+    }
+    SyncPoint::GetInstance()->SetCallBack(
+        "DBImpl::BackgroundCallFlush:ContextCleanedUp", [&](void*) {
+          {
+            MutexLock l(&flush_mutex);
+            flush_finished = true;
+          }
+          flush_cv.SignalAll();
+        });
+  };
+  auto WaitForFlush = [&]() {
+    {
+      MutexLock l(&flush_mutex);
+      while (!flush_finished) {
+        flush_cv.Wait();
+      }
+    }
+    SyncPoint::GetInstance()->ClearCallBack(
+        "DBImpl::BackgroundCallFlush:ContextCleanedUp");
+  };
+
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
   Reopen(options);
 
   // Generating 360KB in Level 3
   for (int i = 0; i < 72; i++) {
     Put(Key(i), std::string(5000, 'x'));
     if (i % 10 == 0) {
-      Flush();
+      dbfull()->TEST_FlushMemTable(true, true);
     }
   }
   dbfull()->TEST_WaitForCompact();
@@ -5522,7 +5738,7 @@ TEST_F(DBTest, SoftLimit) {
   for (int i = 0; i < 72; i++) {
     Put(Key(i), std::string(5000, 'x'));
     if (i % 10 == 0) {
-      Flush();
+      dbfull()->TEST_FlushMemTable(true, true);
     }
   }
   dbfull()->TEST_WaitForCompact();
@@ -5541,7 +5757,9 @@ TEST_F(DBTest, SoftLimit) {
     Put(Key(i), std::string(5000, 'x'));
     Put(Key(100 - i), std::string(5000, 'x'));
     // Flush the file. File size is around 30KB.
-    Flush();
+    InstallFlushCallback();
+    dbfull()->TEST_FlushMemTable(true, true);
+    WaitForFlush();
   }
   ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
   ASSERT_TRUE(listener->CheckCondition(WriteStallCondition::kDelayed));
@@ -5566,8 +5784,6 @@ TEST_F(DBTest, SoftLimit) {
                        &sleeping_task_low, Env::Priority::LOW);
       });
 
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
   env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask, &sleeping_task_low,
                  Env::Priority::LOW);
   sleeping_task_low.WaitUntilSleeping();
@@ -5576,7 +5792,9 @@ TEST_F(DBTest, SoftLimit) {
     Put(Key(10 + i), std::string(5000, 'x'));
     Put(Key(90 - i), std::string(5000, 'x'));
     // Flush the file. File size is around 30KB.
-    Flush();
+    InstallFlushCallback();
+    dbfull()->TEST_FlushMemTable(true, true);
+    WaitForFlush();
   }
 
   // Wake up sleep task to enable compaction to run and waits
@@ -5597,7 +5815,9 @@ TEST_F(DBTest, SoftLimit) {
     Put(Key(20 + i), std::string(5000, 'x'));
     Put(Key(80 - i), std::string(5000, 'x'));
     // Flush the file. File size is around 30KB.
-    Flush();
+    InstallFlushCallback();
+    dbfull()->TEST_FlushMemTable(true, true);
+    WaitForFlush();
   }
   // Wake up sleep task to enable compaction to run and waits
   // for it to go to sleep state again to make sure one compaction
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_test2.cc b/3rdParty/rocksdb/v5.18.X/db/db_test2.cc
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/db/db_test2.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_test2.cc
index 7800144bad..2d6fadc351 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_test2.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_test2.cc
@@ -61,7 +61,7 @@ TEST_P(PrefixFullBloomWithReverseComparator,
     bbto.block_cache->EraseUnRefEntries();
   }
 
-  unique_ptr<Iterator> iter(db_->NewIterator(ReadOptions()));
+  std::unique_ptr<Iterator> iter(db_->NewIterator(ReadOptions()));
   iter->Seek("bar345");
   ASSERT_OK(iter->status());
   ASSERT_TRUE(iter->Valid());
@@ -454,6 +454,22 @@ TEST_F(DBTest2, SharedWriteBufferLimitAcrossDB) {
   rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 }
 
+TEST_F(DBTest2, TestWriteBufferNoLimitWithCache) {
+  Options options = CurrentOptions();
+  options.arena_block_size = 4096;
+  std::shared_ptr<Cache> cache =
+      NewLRUCache(LRUCacheOptions(10000000, 1, false, 0.0));
+  options.write_buffer_size = 50000;  // this is never hit
+  // Use a write buffer total size so that the soft limit is about
+  // 105000.
+  options.write_buffer_manager.reset(new WriteBufferManager(0, cache));
+  Reopen(options);
+
+  ASSERT_OK(Put("foo", "bar"));
+  // One dummy entry is 1MB.
+  ASSERT_GT(cache->GetUsage(), 500000);
+}
+
 namespace {
   void ValidateKeyExistence(DB* db, const std::vector<Slice>& keys_must_exist,
     const std::vector<Slice>& keys_must_not_exist) {
@@ -1228,7 +1244,14 @@ TEST_F(DBTest2, CompressionOptions) {
 
 class CompactionStallTestListener : public EventListener {
  public:
-  CompactionStallTestListener() : compacted_files_cnt_(0) {}
+  CompactionStallTestListener() : compacting_files_cnt_(0), compacted_files_cnt_(0) {}
+
+  void OnCompactionBegin(DB* /*db*/, const CompactionJobInfo& ci) override {
+    ASSERT_EQ(ci.cf_name, "default");
+    ASSERT_EQ(ci.base_input_level, 0);
+    ASSERT_EQ(ci.compaction_reason, CompactionReason::kLevelL0FilesNum);
+    compacting_files_cnt_ += ci.input_files.size();
+  }
 
   void OnCompactionCompleted(DB* /*db*/, const CompactionJobInfo& ci) override {
     ASSERT_EQ(ci.cf_name, "default");
@@ -1236,6 +1259,8 @@ class CompactionStallTestListener : public EventListener {
     ASSERT_EQ(ci.compaction_reason, CompactionReason::kLevelL0FilesNum);
     compacted_files_cnt_ += ci.input_files.size();
   }
+
+  std::atomic<size_t> compacting_files_cnt_;
   std::atomic<size_t> compacted_files_cnt_;
 };
 
@@ -1244,6 +1269,8 @@ TEST_F(DBTest2, CompactionStall) {
       {{"DBImpl::BGWorkCompaction", "DBTest2::CompactionStall:0"},
        {"DBImpl::BGWorkCompaction", "DBTest2::CompactionStall:1"},
        {"DBTest2::CompactionStall:2",
+        "DBImpl::NotifyOnCompactionBegin::UnlockMutex"},
+       {"DBTest2::CompactionStall:3",
         "DBImpl::NotifyOnCompactionCompleted::UnlockMutex"}});
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
@@ -1285,14 +1312,18 @@ TEST_F(DBTest2, CompactionStall) {
   // Wait for another compaction to be triggered
   TEST_SYNC_POINT("DBTest2::CompactionStall:1");
 
-  // Hold NotifyOnCompactionCompleted in the unlock mutex section
+  // Hold NotifyOnCompactionBegin in the unlock mutex section
   TEST_SYNC_POINT("DBTest2::CompactionStall:2");
 
+  // Hold NotifyOnCompactionCompleted in the unlock mutex section
+  TEST_SYNC_POINT("DBTest2::CompactionStall:3");
+
   dbfull()->TEST_WaitForCompact();
   ASSERT_LT(NumTableFilesAtLevel(0),
             options.level0_file_num_compaction_trigger);
   ASSERT_GT(listener->compacted_files_cnt_.load(),
             10 - options.level0_file_num_compaction_trigger);
+  ASSERT_EQ(listener->compacting_files_cnt_.load(), listener->compacted_files_cnt_.load());
 
   rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 }
@@ -2500,6 +2531,61 @@ TEST_F(DBTest2, LiveFilesOmitObsoleteFiles) {
   rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 }
 
+TEST_F(DBTest2, TestNumPread) {
+  Options options = CurrentOptions();
+  // disable block cache
+  BlockBasedTableOptions table_options;
+  table_options.no_block_cache = true;
+  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
+  Reopen(options);
+  env_->count_random_reads_ = true;
+
+  env_->random_file_open_counter_.store(0);
+  ASSERT_OK(Put("bar", "foo"));
+  ASSERT_OK(Put("foo", "bar"));
+  ASSERT_OK(Flush());
+  // After flush, we'll open the file and read footer, meta block,
+  // property block and index block.
+  ASSERT_EQ(4, env_->random_read_counter_.Read());
+  ASSERT_EQ(1, env_->random_file_open_counter_.load());
+
+  // One pread per a normal data block read
+  env_->random_file_open_counter_.store(0);
+  env_->random_read_counter_.Reset();
+  ASSERT_EQ("bar", Get("foo"));
+  ASSERT_EQ(1, env_->random_read_counter_.Read());
+  // All files are already opened.
+  ASSERT_EQ(0, env_->random_file_open_counter_.load());
+
+  env_->random_file_open_counter_.store(0);
+  env_->random_read_counter_.Reset();
+  ASSERT_OK(Put("bar2", "foo2"));
+  ASSERT_OK(Put("foo2", "bar2"));
+  ASSERT_OK(Flush());
+  // After flush, we'll open the file and read footer, meta block,
+  // property block and index block.
+  ASSERT_EQ(4, env_->random_read_counter_.Read());
+  ASSERT_EQ(1, env_->random_file_open_counter_.load());
+
+  // Compaction needs two input blocks, which requires 2 preads, and
+  // generate a new SST file which needs 4 preads (footer, meta block,
+  // property block and index block). In total 6.
+  env_->random_file_open_counter_.store(0);
+  env_->random_read_counter_.Reset();
+  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
+  ASSERT_EQ(6, env_->random_read_counter_.Read());
+  // All compactin input files should have already been opened.
+  ASSERT_EQ(1, env_->random_file_open_counter_.load());
+
+  // One pread per a normal data block read
+  env_->random_file_open_counter_.store(0);
+  env_->random_read_counter_.Reset();
+  ASSERT_EQ("foo2", Get("bar2"));
+  ASSERT_EQ(1, env_->random_read_counter_.Read());
+  // SST files are already opened.
+  ASSERT_EQ(0, env_->random_file_open_counter_.load());
+}
+
 TEST_F(DBTest2, TraceAndReplay) {
   Options options = CurrentOptions();
   options.merge_operator = MergeOperators::CreatePutOperator();
@@ -2602,6 +2688,74 @@ TEST_F(DBTest2, TraceAndReplay) {
   ASSERT_OK(DestroyDB(dbname2, options));
 }
 
+TEST_F(DBTest2, TraceWithLimit) {
+  Options options = CurrentOptions();
+  options.merge_operator = MergeOperators::CreatePutOperator();
+  ReadOptions ro;
+  WriteOptions wo;
+  TraceOptions trace_opts;
+  EnvOptions env_opts;
+  CreateAndReopenWithCF({"pikachu"}, options);
+  Random rnd(301);
+
+  // test the max trace file size options
+  trace_opts.max_trace_file_size = 5;
+  std::string trace_filename = dbname_ + "/rocksdb.trace1";
+  std::unique_ptr<TraceWriter> trace_writer;
+  ASSERT_OK(NewFileTraceWriter(env_, env_opts, trace_filename, &trace_writer));
+  ASSERT_OK(db_->StartTrace(trace_opts, std::move(trace_writer)));
+  ASSERT_OK(Put(0, "a", "1"));
+  ASSERT_OK(Put(0, "b", "1"));
+  ASSERT_OK(Put(0, "c", "1"));
+  ASSERT_OK(db_->EndTrace());
+
+  std::string dbname2 = test::TmpDir(env_) + "/db_replay2";
+  std::string value;
+  ASSERT_OK(DestroyDB(dbname2, options));
+
+  // Using a different name than db2, to pacify infer's use-after-lifetime
+  // warnings (http://fbinfer.com).
+  DB* db2_init = nullptr;
+  options.create_if_missing = true;
+  ASSERT_OK(DB::Open(options, dbname2, &db2_init));
+  ColumnFamilyHandle* cf;
+  ASSERT_OK(
+      db2_init->CreateColumnFamily(ColumnFamilyOptions(), "pikachu", &cf));
+  delete cf;
+  delete db2_init;
+
+  DB* db2 = nullptr;
+  std::vector<ColumnFamilyDescriptor> column_families;
+  ColumnFamilyOptions cf_options;
+  cf_options.merge_operator = MergeOperators::CreatePutOperator();
+  column_families.push_back(ColumnFamilyDescriptor("default", cf_options));
+  column_families.push_back(
+      ColumnFamilyDescriptor("pikachu", ColumnFamilyOptions()));
+  std::vector<ColumnFamilyHandle*> handles;
+  ASSERT_OK(DB::Open(DBOptions(), dbname2, column_families, &handles, &db2));
+
+  env_->SleepForMicroseconds(100);
+  // Verify that the keys don't already exist
+  ASSERT_TRUE(db2->Get(ro, handles[0], "a", &value).IsNotFound());
+  ASSERT_TRUE(db2->Get(ro, handles[0], "b", &value).IsNotFound());
+  ASSERT_TRUE(db2->Get(ro, handles[0], "c", &value).IsNotFound());
+
+  std::unique_ptr<TraceReader> trace_reader;
+  ASSERT_OK(NewFileTraceReader(env_, env_opts, trace_filename, &trace_reader));
+  Replayer replayer(db2, handles_, std::move(trace_reader));
+  ASSERT_OK(replayer.Replay());
+
+  ASSERT_TRUE(db2->Get(ro, handles[0], "a", &value).IsNotFound());
+  ASSERT_TRUE(db2->Get(ro, handles[0], "b", &value).IsNotFound());
+  ASSERT_TRUE(db2->Get(ro, handles[0], "c", &value).IsNotFound());
+
+  for (auto handle : handles) {
+    delete handle;
+  }
+  delete db2;
+  ASSERT_OK(DestroyDB(dbname2, options));
+}
+
 #endif  // ROCKSDB_LITE
 
 TEST_F(DBTest2, PinnableSliceAndMmapReads) {
@@ -2649,7 +2803,7 @@ TEST_F(DBTest2, PinnableSliceAndMmapReads) {
 #endif
 }
 
-TEST_F(DBTest2, IteratorPinnedMemory) {
+TEST_F(DBTest2, DISABLED_IteratorPinnedMemory) {
   Options options = CurrentOptions();
   options.create_if_missing = true;
   options.statistics = rocksdb::CreateDBStatistics();
@@ -2677,7 +2831,7 @@ TEST_F(DBTest2, IteratorPinnedMemory) {
   // Verify that iterators don't pin more than one data block in block cache
   // at each time.
   {
-    unique_ptr<Iterator> iter(db_->NewIterator(ReadOptions()));
+    std::unique_ptr<Iterator> iter(db_->NewIterator(ReadOptions()));
     iter->SeekToFirst();
 
     for (int i = 0; i < 4; i++) {
@@ -2835,6 +2989,105 @@ TEST_F(DBTest2, TestBBTTailPrefetch) {
   rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
+TEST_F(DBTest2, TestGetColumnFamilyHandleUnlocked) {
+  // Setup sync point dependency to reproduce the race condition of
+  // DBImpl::GetColumnFamilyHandleUnlocked
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
+      { {"TestGetColumnFamilyHandleUnlocked::GetColumnFamilyHandleUnlocked1",
+         "TestGetColumnFamilyHandleUnlocked::PreGetColumnFamilyHandleUnlocked2"},
+        {"TestGetColumnFamilyHandleUnlocked::GetColumnFamilyHandleUnlocked2",
+         "TestGetColumnFamilyHandleUnlocked::ReadColumnFamilyHandle1"},
+      });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  CreateColumnFamilies({"test1", "test2"}, Options());
+  ASSERT_EQ(handles_.size(), 2);
+
+  DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
+  port::Thread user_thread1([&]() {
+    auto cfh = dbi->GetColumnFamilyHandleUnlocked(handles_[0]->GetID());
+    ASSERT_EQ(cfh->GetID(), handles_[0]->GetID());
+    TEST_SYNC_POINT("TestGetColumnFamilyHandleUnlocked::GetColumnFamilyHandleUnlocked1");
+    TEST_SYNC_POINT("TestGetColumnFamilyHandleUnlocked::ReadColumnFamilyHandle1");
+    ASSERT_EQ(cfh->GetID(), handles_[0]->GetID());
+  });
+
+  port::Thread user_thread2([&]() {
+    TEST_SYNC_POINT("TestGetColumnFamilyHandleUnlocked::PreGetColumnFamilyHandleUnlocked2");
+    auto cfh = dbi->GetColumnFamilyHandleUnlocked(handles_[1]->GetID());
+    ASSERT_EQ(cfh->GetID(), handles_[1]->GetID());
+    TEST_SYNC_POINT("TestGetColumnFamilyHandleUnlocked::GetColumnFamilyHandleUnlocked2");
+    ASSERT_EQ(cfh->GetID(), handles_[1]->GetID());
+  });
+
+  user_thread1.join();
+  user_thread2.join();
+
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+
+#ifndef ROCKSDB_LITE
+TEST_F(DBTest2, TestCompactFiles) {
+  // Setup sync point dependency to reproduce the race condition of
+  // DBImpl::GetColumnFamilyHandleUnlocked
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
+      {"TestCompactFiles::IngestExternalFile1",
+       "TestCompactFiles::IngestExternalFile2"},
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  Options options;
+  options.num_levels = 2;
+  options.disable_auto_compactions = true;
+  Reopen(options);
+  auto* handle = db_->DefaultColumnFamily();
+  ASSERT_EQ(db_->NumberLevels(handle), 2);
+
+  rocksdb::SstFileWriter sst_file_writer{rocksdb::EnvOptions(), options};
+  std::string external_file1 = dbname_ + "/test_compact_files1.sst_t";
+  std::string external_file2 = dbname_ + "/test_compact_files2.sst_t";
+  std::string external_file3 = dbname_ + "/test_compact_files3.sst_t";
+
+  ASSERT_OK(sst_file_writer.Open(external_file1));
+  ASSERT_OK(sst_file_writer.Put("1", "1"));
+  ASSERT_OK(sst_file_writer.Put("2", "2"));
+  ASSERT_OK(sst_file_writer.Finish());
+
+  ASSERT_OK(sst_file_writer.Open(external_file2));
+  ASSERT_OK(sst_file_writer.Put("3", "3"));
+  ASSERT_OK(sst_file_writer.Put("4", "4"));
+  ASSERT_OK(sst_file_writer.Finish());
+
+  ASSERT_OK(sst_file_writer.Open(external_file3));
+  ASSERT_OK(sst_file_writer.Put("5", "5"));
+  ASSERT_OK(sst_file_writer.Put("6", "6"));
+  ASSERT_OK(sst_file_writer.Finish());
+
+  ASSERT_OK(db_->IngestExternalFile(handle, {external_file1, external_file3},
+                                    IngestExternalFileOptions()));
+  ASSERT_EQ(NumTableFilesAtLevel(1, 0), 2);
+  std::vector<std::string> files;
+  GetSstFiles(env_, dbname_, &files);
+  ASSERT_EQ(files.size(), 2);
+
+  port::Thread user_thread1(
+      [&]() { db_->CompactFiles(CompactionOptions(), handle, files, 1); });
+
+  port::Thread user_thread2([&]() {
+    ASSERT_OK(db_->IngestExternalFile(handle, {external_file2},
+                                      IngestExternalFileOptions()));
+    TEST_SYNC_POINT("TestCompactFiles::IngestExternalFile1");
+  });
+
+  user_thread1.join();
+  user_thread2.join();
+
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
+}
+#endif  // ROCKSDB_LITE
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_test_util.cc b/3rdParty/rocksdb/v5.18.X/db/db_test_util.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/db/db_test_util.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_test_util.cc
index 90560d90ed..eeff7be514 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_test_util.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_test_util.cc
@@ -259,6 +259,47 @@ bool DBTestBase::ChangeFilterOptions() {
   return true;
 }
 
+// Switch between different DB options for file ingestion tests.
+bool DBTestBase::ChangeOptionsForFileIngestionTest() {
+  if (option_config_ == kDefault) {
+    option_config_ = kUniversalCompaction;
+    Destroy(last_options_);
+    auto options = CurrentOptions();
+    options.create_if_missing = true;
+    TryReopen(options);
+    return true;
+  } else if (option_config_ == kUniversalCompaction) {
+    option_config_ = kUniversalCompactionMultiLevel;
+    Destroy(last_options_);
+    auto options = CurrentOptions();
+    options.create_if_missing = true;
+    TryReopen(options);
+    return true;
+  } else if (option_config_ == kUniversalCompactionMultiLevel) {
+    option_config_ = kLevelSubcompactions;
+    Destroy(last_options_);
+    auto options = CurrentOptions();
+    assert(options.max_subcompactions > 1);
+    TryReopen(options);
+    return true;
+  } else if (option_config_ == kLevelSubcompactions) {
+    option_config_ = kUniversalSubcompactions;
+    Destroy(last_options_);
+    auto options = CurrentOptions();
+    assert(options.max_subcompactions > 1);
+    TryReopen(options);
+    return true;
+  } else if (option_config_ == kUniversalSubcompactions) {
+    option_config_ = kDirectIO;
+    Destroy(last_options_);
+    auto options = CurrentOptions();
+    TryReopen(options);
+    return true;
+  } else {
+    return false;
+  }
+}
+
 // Return the current option configuration.
 Options DBTestBase::CurrentOptions(
     const anon::OptionsOverride& options_override) const {
@@ -430,6 +471,10 @@ Options DBTestBase::GetOptions(
       table_options.checksum = kxxHash;
       break;
     }
+    case kxxHash64Checksum: {
+      table_options.checksum = kxxHash64;
+      break;
+    }
     case kFIFOCompaction: {
       options.compaction_style = kCompactionStyleFIFO;
       break;
@@ -451,13 +496,14 @@ Options DBTestBase::GetOptions(
     }
     case kBlockBasedTableWithPartitionedIndexFormat4: {
       table_options.format_version = 4;
-      // Format 3 changes the binary index format. Since partitioned index is a
+      // Format 4 changes the binary index format. Since partitioned index is a
       // super-set of simple indexes, we are also using kTwoLevelIndexSearch to
       // test this format.
       table_options.index_type = BlockBasedTableOptions::kTwoLevelIndexSearch;
-      // The top-level index in partition filters are also affected by format 3.
+      // The top-level index in partition filters are also affected by format 4.
       table_options.filter_policy.reset(NewBloomFilterPolicy(10, false));
       table_options.partition_filters = true;
+      table_options.index_block_restart_interval = 8;
       break;
     }
     case kBlockBasedTableWithIndexRestartInterval: {
@@ -607,30 +653,19 @@ Status DBTestBase::ReadOnlyReopen(const Options& options) {
 Status DBTestBase::TryReopen(const Options& options) {
   Close();
   last_options_.table_factory.reset();
-  // Note: operator= is an unsafe approach here since it destructs shared_ptr in
-  // the same order of their creation, in contrast to destructors which
-  // destructs them in the opposite order of creation. One particular problme is
-  // that the cache destructor might invoke callback functions that use Option
-  // members such as statistics. To work around this problem, we manually call
-  // destructor of table_facotry which eventually clears the block cache.
+  // Note: operator= is an unsafe approach here since it destructs
+  // std::shared_ptr in the same order of their creation, in contrast to
+  // destructors which destructs them in the opposite order of creation. One
+  // particular problme is that the cache destructor might invoke callback
+  // functions that use Option members such as statistics. To work around this
+  // problem, we manually call destructor of table_facotry which eventually
+  // clears the block cache.
   last_options_ = options;
   return DB::Open(options, dbname_, &db_);
 }
 
 bool DBTestBase::IsDirectIOSupported() {
-  EnvOptions env_options;
-  env_options.use_mmap_writes = false;
-  env_options.use_direct_writes = true;
-  std::string tmp = TempFileName(dbname_, 999);
-  Status s;
-  {
-    unique_ptr<WritableFile> file;
-    s = env_->NewWritableFile(tmp, &file, env_options);
-  }
-  if (s.ok()) {
-    s = env_->DeleteFile(tmp);
-  }
-  return s.ok();
+  return test::IsDirectIOSupported(env_, dbname_);
 }
 
 bool DBTestBase::IsMemoryMappedAccessSupported() const {
@@ -645,6 +680,13 @@ Status DBTestBase::Flush(int cf) {
   }
 }
 
+Status DBTestBase::Flush(const std::vector<int>& cf_ids) {
+  std::vector<ColumnFamilyHandle*> cfhs;
+  std::for_each(cf_ids.begin(), cf_ids.end(),
+                [&cfhs, this](int id) { cfhs.emplace_back(handles_[id]); });
+  return db_->Flush(FlushOptions(), cfhs);
+}
+
 Status DBTestBase::Put(const Slice& k, const Slice& v, WriteOptions wo) {
   if (kMergePut == option_config_) {
     return db_->Merge(wo, k, v);
@@ -772,13 +814,15 @@ std::string DBTestBase::AllEntriesFor(const Slice& user_key, int cf) {
   Arena arena;
   auto options = CurrentOptions();
   InternalKeyComparator icmp(options.comparator);
-  RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
+  ReadRangeDelAggregatorV2 range_del_agg(&icmp,
+                                         kMaxSequenceNumber /* upper_bound */);
   ScopedArenaIterator iter;
   if (cf == 0) {
-    iter.set(dbfull()->NewInternalIterator(&arena, &range_del_agg));
+    iter.set(dbfull()->NewInternalIterator(&arena, &range_del_agg,
+                                           kMaxSequenceNumber));
   } else {
-    iter.set(
-        dbfull()->NewInternalIterator(&arena, &range_del_agg, handles_[cf]));
+    iter.set(dbfull()->NewInternalIterator(&arena, &range_del_agg,
+                                           kMaxSequenceNumber, handles_[cf]));
   }
   InternalKey target(user_key, kMaxSequenceNumber, kTypeValue);
   iter->Seek(target.Encode());
@@ -1183,15 +1227,17 @@ void DBTestBase::validateNumberOfEntries(int numValues, int cf) {
   Arena arena;
   auto options = CurrentOptions();
   InternalKeyComparator icmp(options.comparator);
-  RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
+  ReadRangeDelAggregatorV2 range_del_agg(&icmp,
+                                         kMaxSequenceNumber /* upper_bound */);
   // This should be defined after range_del_agg so that it destructs the
   // assigned iterator before it range_del_agg is already destructed.
   ScopedArenaIterator iter;
   if (cf != 0) {
-    iter.set(
-        dbfull()->NewInternalIterator(&arena, &range_del_agg, handles_[cf]));
+    iter.set(dbfull()->NewInternalIterator(&arena, &range_del_agg,
+                                           kMaxSequenceNumber, handles_[cf]));
   } else {
-    iter.set(dbfull()->NewInternalIterator(&arena, &range_del_agg));
+    iter.set(dbfull()->NewInternalIterator(&arena, &range_del_agg,
+                                           kMaxSequenceNumber));
   }
   iter->SeekToFirst();
   ASSERT_EQ(iter->status().ok(), true);
@@ -1211,9 +1257,9 @@ void DBTestBase::validateNumberOfEntries(int numValues, int cf) {
 void DBTestBase::CopyFile(const std::string& source,
                           const std::string& destination, uint64_t size) {
   const EnvOptions soptions;
-  unique_ptr<SequentialFile> srcfile;
+  std::unique_ptr<SequentialFile> srcfile;
   ASSERT_OK(env_->NewSequentialFile(source, &srcfile, soptions));
-  unique_ptr<WritableFile> destfile;
+  std::unique_ptr<WritableFile> destfile;
   ASSERT_OK(env_->NewWritableFile(destination, &destfile, soptions));
 
   if (size == 0) {
@@ -1391,8 +1437,10 @@ void DBTestBase::VerifyDBInternal(
     std::vector<std::pair<std::string, std::string>> true_data) {
   Arena arena;
   InternalKeyComparator icmp(last_options_.comparator);
-  RangeDelAggregator range_del_agg(icmp, {});
-  auto iter = dbfull()->NewInternalIterator(&arena, &range_del_agg);
+  ReadRangeDelAggregatorV2 range_del_agg(&icmp,
+                                         kMaxSequenceNumber /* upper_bound */);
+  auto iter =
+      dbfull()->NewInternalIterator(&arena, &range_del_agg, kMaxSequenceNumber);
   iter->SeekToFirst();
   for (auto p : true_data) {
     ASSERT_TRUE(iter->Valid());
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_test_util.h b/3rdParty/rocksdb/v5.18.X/db/db_test_util.h
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/db/db_test_util.h
rename to 3rdParty/rocksdb/v5.18.X/db/db_test_util.h
index 30ee2e0c2a..7c2d79498b 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_test_util.h
+++ b/3rdParty/rocksdb/v5.18.X/db/db_test_util.h
@@ -46,6 +46,7 @@
 #include "table/scoped_arena_iterator.h"
 #include "util/compression.h"
 #include "util/filename.h"
+#include "util/mock_time_env.h"
 #include "util/mutexlock.h"
 
 #include "util/string_util.h"
@@ -109,8 +110,6 @@ struct OptionsOverride {
   // These will be used only if filter_policy is set
   bool partition_filters = false;
   uint64_t metadata_block_size = 1024;
-  BlockBasedTableOptions::IndexType index_type =
-      BlockBasedTableOptions::IndexType::kBinarySearch;
 
   // Used as a bit mask of individual enums in which to skip an XF test point
   int skip_policy = 0;
@@ -170,7 +169,7 @@ class SpecialMemTableRep : public MemTableRep {
   virtual ~SpecialMemTableRep() override {}
 
  private:
-  unique_ptr<MemTableRep> memtable_;
+  std::unique_ptr<MemTableRep> memtable_;
   int num_entries_flush_;
   int num_entries_;
 };
@@ -208,15 +207,15 @@ class SpecialEnv : public EnvWrapper {
  public:
   explicit SpecialEnv(Env* base);
 
-  Status NewWritableFile(const std::string& f, unique_ptr<WritableFile>* r,
+  Status NewWritableFile(const std::string& f, std::unique_ptr<WritableFile>* r,
                          const EnvOptions& soptions) override {
     class SSTableFile : public WritableFile {
      private:
       SpecialEnv* env_;
-      unique_ptr<WritableFile> base_;
+      std::unique_ptr<WritableFile> base_;
 
      public:
-      SSTableFile(SpecialEnv* env, unique_ptr<WritableFile>&& base)
+      SSTableFile(SpecialEnv* env, std::unique_ptr<WritableFile>&& base)
           : env_(env), base_(std::move(base)) {}
       Status Append(const Slice& data) override {
         if (env_->table_write_callback_) {
@@ -296,7 +295,7 @@ class SpecialEnv : public EnvWrapper {
     };
     class ManifestFile : public WritableFile {
      public:
-      ManifestFile(SpecialEnv* env, unique_ptr<WritableFile>&& b)
+      ManifestFile(SpecialEnv* env, std::unique_ptr<WritableFile>&& b)
           : env_(env), base_(std::move(b)) {}
       Status Append(const Slice& data) override {
         if (env_->manifest_write_error_.load(std::memory_order_acquire)) {
@@ -317,14 +316,17 @@ class SpecialEnv : public EnvWrapper {
         }
       }
       uint64_t GetFileSize() override { return base_->GetFileSize(); }
+      Status Allocate(uint64_t offset, uint64_t len) override {
+        return base_->Allocate(offset, len);
+      }
 
      private:
       SpecialEnv* env_;
-      unique_ptr<WritableFile> base_;
+      std::unique_ptr<WritableFile> base_;
     };
     class WalFile : public WritableFile {
      public:
-      WalFile(SpecialEnv* env, unique_ptr<WritableFile>&& b)
+      WalFile(SpecialEnv* env, std::unique_ptr<WritableFile>&& b)
           : env_(env), base_(std::move(b)) {
         env_->num_open_wal_file_.fetch_add(1);
       }
@@ -370,10 +372,13 @@ class SpecialEnv : public EnvWrapper {
       bool IsSyncThreadSafe() const override {
         return env_->is_wal_sync_thread_safe_.load();
       }
+      Status Allocate(uint64_t offset, uint64_t len) override {
+        return base_->Allocate(offset, len);
+      }
 
      private:
       SpecialEnv* env_;
-      unique_ptr<WritableFile> base_;
+      std::unique_ptr<WritableFile> base_;
     };
 
     if (non_writeable_rate_.load(std::memory_order_acquire) > 0) {
@@ -415,11 +420,11 @@ class SpecialEnv : public EnvWrapper {
   }
 
   Status NewRandomAccessFile(const std::string& f,
-                             unique_ptr<RandomAccessFile>* r,
+                             std::unique_ptr<RandomAccessFile>* r,
                              const EnvOptions& soptions) override {
     class CountingFile : public RandomAccessFile {
      public:
-      CountingFile(unique_ptr<RandomAccessFile>&& target,
+      CountingFile(std::unique_ptr<RandomAccessFile>&& target,
                    anon::AtomicCounter* counter,
                    std::atomic<size_t>* bytes_read)
           : target_(std::move(target)),
@@ -434,7 +439,7 @@ class SpecialEnv : public EnvWrapper {
       }
 
      private:
-      unique_ptr<RandomAccessFile> target_;
+      std::unique_ptr<RandomAccessFile> target_;
       anon::AtomicCounter* counter_;
       std::atomic<size_t>* bytes_read_;
     };
@@ -452,11 +457,11 @@ class SpecialEnv : public EnvWrapper {
   }
 
   virtual Status NewSequentialFile(const std::string& f,
-                                   unique_ptr<SequentialFile>* r,
+                                   std::unique_ptr<SequentialFile>* r,
                                    const EnvOptions& soptions) override {
     class CountingFile : public SequentialFile {
      public:
-      CountingFile(unique_ptr<SequentialFile>&& target,
+      CountingFile(std::unique_ptr<SequentialFile>&& target,
                    anon::AtomicCounter* counter)
           : target_(std::move(target)), counter_(counter) {}
       virtual Status Read(size_t n, Slice* result, char* scratch) override {
@@ -466,7 +471,7 @@ class SpecialEnv : public EnvWrapper {
       virtual Status Skip(uint64_t n) override { return target_->Skip(n); }
 
      private:
-      unique_ptr<SequentialFile> target_;
+      std::unique_ptr<SequentialFile> target_;
       anon::AtomicCounter* counter_;
     };
 
@@ -569,44 +574,13 @@ class SpecialEnv : public EnvWrapper {
 
   std::atomic<int> delete_count_;
 
-  bool time_elapse_only_sleep_;
+  std::atomic<bool> time_elapse_only_sleep_;
 
   bool no_slowdown_;
 
   std::atomic<bool> is_wal_sync_thread_safe_{true};
 
-  std::atomic<size_t> compaction_readahead_size_;
-};
-
-class MockTimeEnv : public EnvWrapper {
- public:
-  explicit MockTimeEnv(Env* base) : EnvWrapper(base) {}
-
-  virtual Status GetCurrentTime(int64_t* time) override {
-    assert(time != nullptr);
-    assert(current_time_ <=
-           static_cast<uint64_t>(std::numeric_limits<int64_t>::max()));
-    *time = static_cast<int64_t>(current_time_);
-    return Status::OK();
-  }
-
-  virtual uint64_t NowMicros() override {
-    assert(current_time_ <= std::numeric_limits<uint64_t>::max() / 1000000);
-    return current_time_ * 1000000;
-  }
-
-  virtual uint64_t NowNanos() override {
-    assert(current_time_ <= std::numeric_limits<uint64_t>::max() / 1000000000);
-    return current_time_ * 1000000000;
-  }
-
-  void set_current_time(uint64_t time) {
-    assert(time >= current_time_);
-    current_time_ = time;
-  }
-
- private:
-  std::atomic<uint64_t> current_time_{0};
+  std::atomic<size_t> compaction_readahead_size_{};
 };
 
 #ifndef ROCKSDB_LITE
@@ -701,6 +675,7 @@ class DBTestBase : public testing::Test {
     kBlockBasedTableWithPartitionedIndexFormat4,
     kPartitionedFilterWithNewTableReaderForCompactions,
     kUniversalSubcompactions,
+    kxxHash64Checksum,
     // This must be the last line
     kEnd,
   };
@@ -772,6 +747,9 @@ class DBTestBase : public testing::Test {
   // Jump from kDefault to kFilter to kFullFilter
   bool ChangeFilterOptions();
 
+  // Switch between different DB options for file ingestion tests.
+  bool ChangeOptionsForFileIngestionTest();
+
   // Return the current option configuration.
   Options CurrentOptions(const anon::OptionsOverride& options_override =
                              anon::OptionsOverride()) const;
@@ -825,6 +803,8 @@ class DBTestBase : public testing::Test {
 
   Status Flush(int cf = 0);
 
+  Status Flush(const std::vector<int>& cf_ids);
+
   Status Put(const Slice& k, const Slice& v, WriteOptions wo = WriteOptions());
 
   Status Put(int cf, const Slice& k, const Slice& v,
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_universal_compaction_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_universal_compaction_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/db_universal_compaction_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_universal_compaction_test.cc
index 4f6a1aeada..2c17d9f829 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_universal_compaction_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_universal_compaction_test.cc
@@ -1154,7 +1154,7 @@ TEST_P(DBTestUniversalCompaction, UniversalCompactionCompressRatio2) {
     dbfull()->TEST_WaitForFlushMemTable();
     dbfull()->TEST_WaitForCompact();
   }
-  ASSERT_LT(TotalSize(), 120000U * 12 * 0.8 + 120000 * 2);
+  ASSERT_LT(TotalSize(), 120000U * 12 * 0.82 + 120000 * 2);
 }
 
 #ifndef ROCKSDB_VALGRIND_RUN
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_wal_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_wal_test.cc
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/db/db_wal_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_wal_test.cc
index 0349bdc8da..1ba5024582 100644
--- a/3rdParty/rocksdb/v5.16.X/db/db_wal_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/db_wal_test.cc
@@ -18,13 +18,23 @@ namespace rocksdb {
 class DBWALTest : public DBTestBase {
  public:
   DBWALTest() : DBTestBase("/db_wal_test") {}
+
+#if defined(ROCKSDB_PLATFORM_POSIX)
+  uint64_t GetAllocatedFileSize(std::string file_name) {
+    struct stat sbuf;
+    int err = stat(file_name.c_str(), &sbuf);
+    assert(err == 0);
+    return sbuf.st_blocks * 512;
+  }
+#endif
 };
 
 // A SpecialEnv enriched to give more insight about deleted files
 class EnrichedSpecialEnv : public SpecialEnv {
  public:
   explicit EnrichedSpecialEnv(Env* base) : SpecialEnv(base) {}
-  Status NewSequentialFile(const std::string& f, unique_ptr<SequentialFile>* r,
+  Status NewSequentialFile(const std::string& f,
+                           std::unique_ptr<SequentialFile>* r,
                            const EnvOptions& soptions) override {
     InstrumentedMutexLock l(&env_mutex_);
     if (f == skipped_wal) {
@@ -79,6 +89,7 @@ class DBWALTestWithEnrichedEnv : public DBTestBase {
     enriched_env_ = new EnrichedSpecialEnv(env_->target());
     auto options = CurrentOptions();
     options.env = enriched_env_;
+    options.allow_2pc = true;
     Reopen(options);
     delete env_;
     // to be deleted by the parent class
@@ -793,12 +804,12 @@ class RecoveryTestHelper {
 
     *count = 0;
 
-    shared_ptr<Cache> table_cache = NewLRUCache(50, 0);
+    std::shared_ptr<Cache> table_cache = NewLRUCache(50, 0);
     EnvOptions env_options;
     WriteBufferManager write_buffer_manager(db_options.db_write_buffer_size);
 
-    unique_ptr<VersionSet> versions;
-    unique_ptr<WalManager> wal_manager;
+    std::unique_ptr<VersionSet> versions;
+    std::unique_ptr<WalManager> wal_manager;
     WriteController write_controller;
 
     versions.reset(new VersionSet(test->dbname_, &db_options, env_options,
@@ -812,10 +823,10 @@ class RecoveryTestHelper {
     for (size_t j = kWALFileOffset; j < wal_count + kWALFileOffset; j++) {
       uint64_t current_log_number = j;
       std::string fname = LogFileName(test->dbname_, current_log_number);
-      unique_ptr<WritableFile> file;
+      std::unique_ptr<WritableFile> file;
       ASSERT_OK(db_options.env->NewWritableFile(fname, &file, env_options));
-      unique_ptr<WritableFileWriter> file_writer(
-          new WritableFileWriter(std::move(file), env_options));
+      std::unique_ptr<WritableFileWriter> file_writer(
+          new WritableFileWriter(std::move(file), fname, env_options));
       current_log_writer.reset(
           new log::Writer(std::move(file_writer), current_log_number,
                           db_options.recycle_log_file_num > 0));
@@ -1329,6 +1340,99 @@ TEST_F(DBWALTest, RecoverFromCorruptedWALWithoutFlush) {
   }
 }
 
+// Tests that total log size is recovered if we set
+// avoid_flush_during_recovery=true.
+// Flush should trigger if max_total_wal_size is reached.
+TEST_F(DBWALTest, RestoreTotalLogSizeAfterRecoverWithoutFlush) {
+  class TestFlushListener : public EventListener {
+   public:
+    std::atomic<int> count{0};
+
+    TestFlushListener() = default;
+
+    void OnFlushBegin(DB* /*db*/, const FlushJobInfo& flush_job_info) override {
+      count++;
+      assert(FlushReason::kWriteBufferManager == flush_job_info.flush_reason);
+    }
+  };
+  std::shared_ptr<TestFlushListener> test_listener =
+      std::make_shared<TestFlushListener>();
+
+  constexpr size_t kKB = 1024;
+  constexpr size_t kMB = 1024 * 1024;
+  Options options = CurrentOptions();
+  options.avoid_flush_during_recovery = true;
+  options.max_total_wal_size = 1 * kMB;
+  options.listeners.push_back(test_listener);
+  // Have to open DB in multi-CF mode to trigger flush when
+  // max_total_wal_size is reached.
+  CreateAndReopenWithCF({"one"}, options);
+  // Write some keys and we will end up with one log file which is slightly
+  // smaller than 1MB.
+  std::string value_100k(100 * kKB, 'v');
+  std::string value_300k(300 * kKB, 'v');
+  ASSERT_OK(Put(0, "foo", "v1"));
+  for (int i = 0; i < 9; i++) {
+    ASSERT_OK(Put(1, "key" + ToString(i), value_100k));
+  }
+  // Get log files before reopen.
+  VectorLogPtr log_files_before;
+  ASSERT_OK(dbfull()->GetSortedWalFiles(log_files_before));
+  ASSERT_EQ(1, log_files_before.size());
+  uint64_t log_size_before = log_files_before[0]->SizeFileBytes();
+  ASSERT_GT(log_size_before, 900 * kKB);
+  ASSERT_LT(log_size_before, 1 * kMB);
+  ReopenWithColumnFamilies({"default", "one"}, options);
+  // Write one more value to make log larger than 1MB.
+  ASSERT_OK(Put(1, "bar", value_300k));
+  // Get log files again. A new log file will be opened.
+  VectorLogPtr log_files_after_reopen;
+  ASSERT_OK(dbfull()->GetSortedWalFiles(log_files_after_reopen));
+  ASSERT_EQ(2, log_files_after_reopen.size());
+  ASSERT_EQ(log_files_before[0]->LogNumber(),
+            log_files_after_reopen[0]->LogNumber());
+  ASSERT_GT(log_files_after_reopen[0]->SizeFileBytes() +
+                log_files_after_reopen[1]->SizeFileBytes(),
+            1 * kMB);
+  // Write one more key to trigger flush.
+  ASSERT_OK(Put(0, "foo", "v2"));
+  dbfull()->TEST_WaitForFlushMemTable();
+  // Flushed two column families.
+  ASSERT_EQ(2, test_listener->count.load());
+}
+
+#if defined(ROCKSDB_PLATFORM_POSIX)
+#if defined(ROCKSDB_FALLOCATE_PRESENT)
+// Tests that we will truncate the preallocated space of the last log from
+// previous.
+TEST_F(DBWALTest, TruncateLastLogAfterRecoverWithoutFlush) {
+  constexpr size_t kKB = 1024;
+  Options options = CurrentOptions();
+  options.avoid_flush_during_recovery = true;
+  DestroyAndReopen(options);
+  size_t preallocated_size =
+      dbfull()->TEST_GetWalPreallocateBlockSize(options.write_buffer_size);
+  ASSERT_OK(Put("foo", "v1"));
+  VectorLogPtr log_files_before;
+  ASSERT_OK(dbfull()->GetSortedWalFiles(log_files_before));
+  ASSERT_EQ(1, log_files_before.size());
+  auto& file_before = log_files_before[0];
+  ASSERT_LT(file_before->SizeFileBytes(), 1 * kKB);
+  // The log file has preallocated space.
+  ASSERT_GE(GetAllocatedFileSize(dbname_ + file_before->PathName()),
+            preallocated_size);
+  Reopen(options);
+  VectorLogPtr log_files_after;
+  ASSERT_OK(dbfull()->GetSortedWalFiles(log_files_after));
+  ASSERT_EQ(1, log_files_after.size());
+  ASSERT_LT(log_files_after[0]->SizeFileBytes(), 1 * kKB);
+  // The preallocated space should be truncated.
+  ASSERT_LT(GetAllocatedFileSize(dbname_ + file_before->PathName()),
+            preallocated_size);
+}
+#endif  // ROCKSDB_FALLOCATE_PRESENT
+#endif  // ROCKSDB_PLATFORM_POSIX
+
 #endif  // ROCKSDB_LITE
 
 TEST_F(DBWALTest, WalTermTest) {
diff --git a/3rdParty/rocksdb/v5.16.X/db/db_write_test.cc b/3rdParty/rocksdb/v5.18.X/db/db_write_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/db_write_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/db_write_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/dbformat.cc b/3rdParty/rocksdb/v5.18.X/db/dbformat.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/dbformat.cc
rename to 3rdParty/rocksdb/v5.18.X/db/dbformat.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/dbformat.h b/3rdParty/rocksdb/v5.18.X/db/dbformat.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/dbformat.h
rename to 3rdParty/rocksdb/v5.18.X/db/dbformat.h
index 2b88de7323..f5ee7d3a07 100644
--- a/3rdParty/rocksdb/v5.16.X/db/dbformat.h
+++ b/3rdParty/rocksdb/v5.18.X/db/dbformat.h
@@ -674,5 +674,16 @@ int InternalKeyComparator::CompareKeySeq(const Slice& akey,
   return r;
 }
 
+struct ParsedInternalKeyComparator {
+  explicit ParsedInternalKeyComparator(const InternalKeyComparator* c)
+      : cmp(c) {}
+
+  bool operator()(const ParsedInternalKey& a,
+                  const ParsedInternalKey& b) const {
+    return cmp->Compare(a, b) < 0;
+  }
+
+  const InternalKeyComparator* cmp;
+};
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/db/dbformat_test.cc b/3rdParty/rocksdb/v5.18.X/db/dbformat_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/dbformat_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/dbformat_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/deletefile_test.cc b/3rdParty/rocksdb/v5.18.X/db/deletefile_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/deletefile_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/deletefile_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/error_handler.cc b/3rdParty/rocksdb/v5.18.X/db/error_handler.cc
similarity index 53%
rename from 3rdParty/rocksdb/v5.16.X/db/error_handler.cc
rename to 3rdParty/rocksdb/v5.18.X/db/error_handler.cc
index a5b23a4b81..afec14edcb 100644
--- a/3rdParty/rocksdb/v5.16.X/db/error_handler.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/error_handler.cc
@@ -4,7 +4,9 @@
 //  (found in the LICENSE.Apache file in the root directory).
 //
 #include "db/error_handler.h"
+#include "db/db_impl.h"
 #include "db/event_helpers.h"
+#include "util/sst_file_manager_impl.h"
 
 namespace rocksdb {
 
@@ -33,7 +35,7 @@ std::map<std::tuple<BackgroundErrorReason, Status::Code, Status::SubCode, bool>,
         // Errors during BG flush
         {std::make_tuple(BackgroundErrorReason::kFlush, Status::Code::kIOError,
                          Status::SubCode::kNoSpace, true),
-         Status::Severity::kSoftError},
+         Status::Severity::kHardError},
         {std::make_tuple(BackgroundErrorReason::kFlush, Status::Code::kIOError,
                          Status::SubCode::kNoSpace, false),
          Status::Severity::kNoError},
@@ -44,11 +46,11 @@ std::map<std::tuple<BackgroundErrorReason, Status::Code, Status::SubCode, bool>,
         {std::make_tuple(BackgroundErrorReason::kWriteCallback,
                          Status::Code::kIOError, Status::SubCode::kNoSpace,
                          true),
-         Status::Severity::kFatalError},
+         Status::Severity::kHardError},
         {std::make_tuple(BackgroundErrorReason::kWriteCallback,
                          Status::Code::kIOError, Status::SubCode::kNoSpace,
                          false),
-         Status::Severity::kFatalError},
+         Status::Severity::kHardError},
 };
 
 std::map<std::tuple<BackgroundErrorReason, Status::Code, bool>, Status::Severity>
@@ -118,6 +120,45 @@ std::map<std::tuple<BackgroundErrorReason, bool>, Status::Severity>
           Status::Severity::kFatalError},
 };
 
+void ErrorHandler::CancelErrorRecovery() {
+#ifndef ROCKSDB_LITE
+  db_mutex_->AssertHeld();
+
+  // We'll release the lock before calling sfm, so make sure no new
+  // recovery gets scheduled at that point
+  auto_recovery_ = false;
+  SstFileManagerImpl* sfm = reinterpret_cast<SstFileManagerImpl*>(
+      db_options_.sst_file_manager.get());
+  if (sfm) {
+    // This may or may not cancel a pending recovery
+    db_mutex_->Unlock();
+    bool cancelled = sfm->CancelErrorRecovery(this);
+    db_mutex_->Lock();
+    if (cancelled) {
+      recovery_in_prog_ = false;
+    }
+  }
+#endif
+}
+
+// This is the main function for looking at an error during a background
+// operation and deciding the severity, and error recovery strategy. The high
+// level algorithm is as follows -
+// 1. Classify the severity of the error based on the ErrorSeverityMap,
+//    DefaultErrorSeverityMap and DefaultReasonMap defined earlier
+// 2. Call a Status code specific override function to adjust the severity
+//    if needed. The reason for this is our ability to recover may depend on
+//    the exact options enabled in DBOptions
+// 3. Determine if auto recovery is possible. A listener notification callback
+//    is called, which can disable the auto recovery even if we decide its
+//    feasible
+// 4. For Status::NoSpace() errors, rely on SstFileManagerImpl to control
+//    the actual recovery. If no sst file manager is specified in DBOptions,
+//    a default one is allocated during DB::Open(), so there will always be
+//    one.
+// This can also get called as part of a recovery operation. In that case, we
+// also track the error separately in recovery_error_ so we can tell in the
+// end whether recovery succeeded or not
 Status ErrorHandler::SetBGError(const Status& bg_err, BackgroundErrorReason reason) {
   db_mutex_->AssertHeld();
 
@@ -125,6 +166,12 @@ Status ErrorHandler::SetBGError(const Status& bg_err, BackgroundErrorReason reas
     return Status::OK();
   }
 
+  // Check if recovery is currently in progress. If it is, we will save this
+  // error so we can check it at the end to see if recovery succeeded or not
+  if (recovery_in_prog_ && recovery_error_.ok()) {
+    recovery_error_ = bg_err;
+  }
+
   bool paranoid = db_options_.paranoid_checks;
   Status::Severity sev = Status::Severity::kFatalError;
   Status new_bg_err;
@@ -156,15 +203,143 @@ Status ErrorHandler::SetBGError(const Status& bg_err, BackgroundErrorReason reas
   }
 
   new_bg_err = Status(bg_err, sev);
+
+  bool auto_recovery = auto_recovery_;
+  if (new_bg_err.severity() >= Status::Severity::kFatalError && auto_recovery) {
+    auto_recovery = false;
+    ;
+  }
+
+  // Allow some error specific overrides
+  if (new_bg_err == Status::NoSpace()) {
+    new_bg_err = OverrideNoSpaceError(new_bg_err, &auto_recovery);
+  }
+
   if (!new_bg_err.ok()) {
     Status s = new_bg_err;
-    EventHelpers::NotifyOnBackgroundError(db_options_.listeners, reason, &s, db_mutex_);
+    EventHelpers::NotifyOnBackgroundError(db_options_.listeners, reason, &s,
+                                          db_mutex_, &auto_recovery);
     if (!s.ok() && (s.severity() > bg_error_.severity())) {
       bg_error_ = s;
+    } else {
+      // This error is less severe than previously encountered error. Don't
+      // take any further action
+      return bg_error_;
     }
   }
 
+  if (auto_recovery) {
+    recovery_in_prog_ = true;
+
+    // Kick-off error specific recovery
+    if (bg_error_ == Status::NoSpace()) {
+      RecoverFromNoSpace();
+    }
+  }
   return bg_error_;
 }
 
+Status ErrorHandler::OverrideNoSpaceError(Status bg_error,
+                                          bool* auto_recovery) {
+#ifndef ROCKSDB_LITE
+  if (bg_error.severity() >= Status::Severity::kFatalError) {
+    return bg_error;
+  }
+
+  if (db_options_.sst_file_manager.get() == nullptr) {
+    // We rely on SFM to poll for enough disk space and recover
+    *auto_recovery = false;
+    return bg_error;
+  }
+
+  if (db_options_.allow_2pc &&
+      (bg_error.severity() <= Status::Severity::kSoftError)) {
+    // Don't know how to recover, as the contents of the current WAL file may
+    // be inconsistent, and it may be needed for 2PC. If 2PC is not enabled,
+    // we can just flush the memtable and discard the log
+    *auto_recovery = false;
+    return Status(bg_error, Status::Severity::kFatalError);
+  }
+
+  {
+    uint64_t free_space;
+    if (db_options_.env->GetFreeSpace(db_options_.db_paths[0].path,
+                                      &free_space) == Status::NotSupported()) {
+      *auto_recovery = false;
+    }
+  }
+
+  return bg_error;
+#else
+  (void)auto_recovery;
+  return Status(bg_error, Status::Severity::kFatalError);
+#endif
+}
+
+void ErrorHandler::RecoverFromNoSpace() {
+#ifndef ROCKSDB_LITE
+  SstFileManagerImpl* sfm =
+      reinterpret_cast<SstFileManagerImpl*>(db_options_.sst_file_manager.get());
+
+  // Inform SFM of the error, so it can kick-off the recovery
+  if (sfm) {
+    sfm->StartErrorRecovery(this, bg_error_);
+  }
+#endif
+}
+
+Status ErrorHandler::ClearBGError() {
+#ifndef ROCKSDB_LITE
+  db_mutex_->AssertHeld();
+
+  // Signal that recovery succeeded
+  if (recovery_error_.ok()) {
+    Status old_bg_error = bg_error_;
+    bg_error_ = Status::OK();
+    recovery_in_prog_ = false;
+    EventHelpers::NotifyOnErrorRecoveryCompleted(db_options_.listeners,
+                                                 old_bg_error, db_mutex_);
+  }
+  return recovery_error_;
+#else
+  return bg_error_;
+#endif
+}
+
+Status ErrorHandler::RecoverFromBGError(bool is_manual) {
+#ifndef ROCKSDB_LITE
+  InstrumentedMutexLock l(db_mutex_);
+  if (is_manual) {
+    // If its a manual recovery and there's a background recovery in progress
+    // return busy status
+    if (recovery_in_prog_) {
+      return Status::Busy();
+    }
+    recovery_in_prog_ = true;
+  }
+
+  if (bg_error_.severity() == Status::Severity::kSoftError) {
+    // Simply clear the background error and return
+    recovery_error_ = Status::OK();
+    return ClearBGError();
+  }
+
+  // Reset recovery_error_. We will use this to record any errors that happen
+  // during the recovery process. While recovering, the only operations that
+  // can generate background errors should be the flush operations
+  recovery_error_ = Status::OK();
+  Status s = db_->ResumeImpl();
+  // For manual recover, shutdown, and fatal error  cases, set
+  // recovery_in_prog_ to false. For automatic background recovery, leave it
+  // as is regardless of success or failure as it will be retried
+  if (is_manual || s.IsShutdownInProgress() ||
+      bg_error_.severity() >= Status::Severity::kFatalError) {
+    recovery_in_prog_ = false;
+  }
+  return s;
+#else
+  (void)is_manual;
+  return bg_error_;
+#endif
+}
 }
diff --git a/3rdParty/rocksdb/v5.18.X/db/error_handler.h b/3rdParty/rocksdb/v5.18.X/db/error_handler.h
new file mode 100644
index 0000000000..c2af809fc6
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/error_handler.h
@@ -0,0 +1,75 @@
+//  Copyright (c) 2018-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+#pragma once
+
+#include "monitoring/instrumented_mutex.h"
+#include "options/db_options.h"
+#include "rocksdb/listener.h"
+#include "rocksdb/status.h"
+
+namespace rocksdb {
+
+class DBImpl;
+
+class ErrorHandler {
+  public:
+   ErrorHandler(DBImpl* db, const ImmutableDBOptions& db_options,
+                InstrumentedMutex* db_mutex)
+       : db_(db),
+         db_options_(db_options),
+         bg_error_(Status::OK()),
+         recovery_error_(Status::OK()),
+         db_mutex_(db_mutex),
+         auto_recovery_(false),
+         recovery_in_prog_(false) {}
+   ~ErrorHandler() {}
+
+   void EnableAutoRecovery() { auto_recovery_ = true; }
+
+   Status::Severity GetErrorSeverity(BackgroundErrorReason reason,
+                                     Status::Code code,
+                                     Status::SubCode subcode);
+
+   Status SetBGError(const Status& bg_err, BackgroundErrorReason reason);
+
+   Status GetBGError() { return bg_error_; }
+
+   Status GetRecoveryError() { return recovery_error_; }
+
+   Status ClearBGError();
+
+   bool IsDBStopped() {
+     return !bg_error_.ok() &&
+            bg_error_.severity() >= Status::Severity::kHardError;
+    }
+
+    bool IsBGWorkStopped() {
+      return !bg_error_.ok() &&
+             (bg_error_.severity() >= Status::Severity::kHardError ||
+              !auto_recovery_);
+    }
+
+    bool IsRecoveryInProgress() { return recovery_in_prog_; }
+
+    Status RecoverFromBGError(bool is_manual = false);
+    void CancelErrorRecovery();
+
+   private:
+    DBImpl* db_;
+    const ImmutableDBOptions& db_options_;
+    Status bg_error_;
+    // A separate Status variable used to record any errors during the
+    // recovery process from hard errors
+    Status recovery_error_;
+    InstrumentedMutex* db_mutex_;
+    // A flag indicating whether automatic recovery from errors is enabled
+    bool auto_recovery_;
+    bool recovery_in_prog_;
+
+    Status OverrideNoSpaceError(Status bg_error, bool* auto_recovery);
+    void RecoverFromNoSpace();
+};
+
+}
diff --git a/3rdParty/rocksdb/v5.18.X/db/error_handler_test.cc b/3rdParty/rocksdb/v5.18.X/db/error_handler_test.cc
new file mode 100644
index 0000000000..d33e19df5d
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/error_handler_test.cc
@@ -0,0 +1,691 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+#ifndef ROCKSDB_LITE
+
+#include "db/db_test_util.h"
+#include "port/stack_trace.h"
+#include "rocksdb/perf_context.h"
+#include "rocksdb/sst_file_manager.h"
+#include "util/fault_injection_test_env.h"
+#if !defined(ROCKSDB_LITE)
+#include "util/sync_point.h"
+#endif
+
+namespace rocksdb {
+
+class DBErrorHandlingTest : public DBTestBase {
+ public:
+  DBErrorHandlingTest() : DBTestBase("/db_error_handling_test") {}
+};
+
+class DBErrorHandlingEnv : public EnvWrapper {
+  public:
+    DBErrorHandlingEnv() : EnvWrapper(Env::Default()),
+      trig_no_space(false), trig_io_error(false) {}
+
+    void SetTrigNoSpace() {trig_no_space = true;}
+    void SetTrigIoError() {trig_io_error = true;}
+  private:
+    bool trig_no_space;
+    bool trig_io_error;
+};
+
+class ErrorHandlerListener : public EventListener {
+ public:
+  ErrorHandlerListener()
+      : mutex_(),
+        cv_(&mutex_),
+        no_auto_recovery_(false),
+        recovery_complete_(false),
+        file_creation_started_(false),
+        override_bg_error_(false),
+        file_count_(0),
+        fault_env_(nullptr) {}
+
+  void OnTableFileCreationStarted(
+      const TableFileCreationBriefInfo& /*ti*/) override {
+    InstrumentedMutexLock l(&mutex_);
+    file_creation_started_ = true;
+    if (file_count_ > 0) {
+      if (--file_count_ == 0) {
+        fault_env_->SetFilesystemActive(false, file_creation_error_);
+        file_creation_error_ = Status::OK();
+      }
+    }
+    cv_.SignalAll();
+  }
+
+  void OnErrorRecoveryBegin(BackgroundErrorReason /*reason*/,
+                            Status /*bg_error*/,
+                            bool* auto_recovery) override {
+    if (*auto_recovery && no_auto_recovery_) {
+      *auto_recovery = false;
+    }
+  }
+
+  void OnErrorRecoveryCompleted(Status /*old_bg_error*/) override {
+    InstrumentedMutexLock l(&mutex_);
+    recovery_complete_ = true;
+    cv_.SignalAll();
+  }
+
+  bool WaitForRecovery(uint64_t /*abs_time_us*/) {
+    InstrumentedMutexLock l(&mutex_);
+    while (!recovery_complete_) {
+      cv_.Wait(/*abs_time_us*/);
+    }
+    if (recovery_complete_) {
+      recovery_complete_ = false;
+      return true;
+    }
+    return false;
+  }
+
+  void WaitForTableFileCreationStarted(uint64_t /*abs_time_us*/) {
+    InstrumentedMutexLock l(&mutex_);
+    while (!file_creation_started_) {
+      cv_.Wait(/*abs_time_us*/);
+    }
+    file_creation_started_ = false;
+  }
+
+  void OnBackgroundError(BackgroundErrorReason /*reason*/,
+                         Status* bg_error) override {
+    if (override_bg_error_) {
+      *bg_error = bg_error_;
+      override_bg_error_ = false;
+    }
+  }
+
+  void EnableAutoRecovery(bool enable = true) { no_auto_recovery_ = !enable; }
+
+  void OverrideBGError(Status bg_err) {
+    bg_error_ = bg_err;
+    override_bg_error_ = true;
+  }
+
+  void InjectFileCreationError(FaultInjectionTestEnv* env, int file_count,
+                               Status s) {
+    fault_env_ = env;
+    file_count_ = file_count;
+    file_creation_error_ = s;
+  }
+
+ private:
+  InstrumentedMutex mutex_;
+  InstrumentedCondVar cv_;
+  bool no_auto_recovery_;
+  bool recovery_complete_;
+  bool file_creation_started_;
+  bool override_bg_error_;
+  int file_count_;
+  Status file_creation_error_;
+  Status bg_error_;
+  FaultInjectionTestEnv* fault_env_;
+};
+
+TEST_F(DBErrorHandlingTest, FLushWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.env = fault_env.get();
+  options.listeners.emplace_back(listener);
+  Status s;
+
+  listener->EnableAutoRecovery(false);
+  DestroyAndReopen(options);
+
+  Put(Key(0), "val");
+  SyncPoint::GetInstance()->SetCallBack(
+      "FlushJob::Start", [&](void *) {
+    fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+  s = Flush();
+  ASSERT_EQ(s.severity(), rocksdb::Status::Severity::kHardError);
+  SyncPoint::GetInstance()->DisableProcessing();
+  fault_env->SetFilesystemActive(true);
+  s = dbfull()->Resume();
+  ASSERT_EQ(s, Status::OK());
+
+  Reopen(options);
+  ASSERT_EQ("val", Get(Key(0)));
+  Destroy(options);
+}
+
+TEST_F(DBErrorHandlingTest, CompactionWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.level0_file_num_compaction_trigger = 2;
+  options.listeners.emplace_back(listener);
+  options.env = fault_env.get();
+  Status s;
+  DestroyAndReopen(options);
+
+  Put(Key(0), "va;");
+  Put(Key(2), "va;");
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+
+  listener->OverrideBGError(
+      Status(Status::NoSpace(), Status::Severity::kHardError)
+      );
+  listener->EnableAutoRecovery(false);
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
+      {{"FlushMemTableFinished", "BackgroundCallCompaction:0"}});
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "BackgroundCallCompaction:0", [&](void *) {
+      fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
+      });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  Put(Key(1), "val");
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s.severity(), rocksdb::Status::Severity::kHardError);
+
+  fault_env->SetFilesystemActive(true);
+  s = dbfull()->Resume();
+  ASSERT_EQ(s, Status::OK());
+  Destroy(options);
+}
+
+TEST_F(DBErrorHandlingTest, CorruptionError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.level0_file_num_compaction_trigger = 2;
+  options.env = fault_env.get();
+  Status s;
+  DestroyAndReopen(options);
+
+  Put(Key(0), "va;");
+  Put(Key(2), "va;");
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
+      {{"FlushMemTableFinished", "BackgroundCallCompaction:0"}});
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
+      "BackgroundCallCompaction:0", [&](void *) {
+      fault_env->SetFilesystemActive(false, Status::Corruption("Corruption"));
+      });
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+
+  Put(Key(1), "val");
+  s = Flush();
+  ASSERT_EQ(s, Status::OK());
+
+  s = dbfull()->TEST_WaitForCompact();
+  ASSERT_EQ(s.severity(), rocksdb::Status::Severity::kUnrecoverableError);
+
+  fault_env->SetFilesystemActive(true);
+  s = dbfull()->Resume();
+  ASSERT_NE(s, Status::OK());
+  Destroy(options);
+}
+
+TEST_F(DBErrorHandlingTest, AutoRecoverFlushError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.env = fault_env.get();
+  options.listeners.emplace_back(listener);
+  Status s;
+
+  listener->EnableAutoRecovery();
+  DestroyAndReopen(options);
+
+  Put(Key(0), "val");
+  SyncPoint::GetInstance()->SetCallBack("FlushJob::Start", [&](void*) {
+    fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+  s = Flush();
+  ASSERT_EQ(s.severity(), rocksdb::Status::Severity::kHardError);
+  SyncPoint::GetInstance()->DisableProcessing();
+  fault_env->SetFilesystemActive(true);
+  ASSERT_EQ(listener->WaitForRecovery(5000000), true);
+
+  s = Put(Key(1), "val");
+  ASSERT_EQ(s, Status::OK());
+
+  Reopen(options);
+  ASSERT_EQ("val", Get(Key(0)));
+  ASSERT_EQ("val", Get(Key(1)));
+  Destroy(options);
+}
+
+TEST_F(DBErrorHandlingTest, FailRecoverFlushError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.env = fault_env.get();
+  options.listeners.emplace_back(listener);
+  Status s;
+
+  listener->EnableAutoRecovery();
+  DestroyAndReopen(options);
+
+  Put(Key(0), "val");
+  SyncPoint::GetInstance()->SetCallBack("FlushJob::Start", [&](void*) {
+    fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
+  });
+  SyncPoint::GetInstance()->EnableProcessing();
+  s = Flush();
+  ASSERT_EQ(s.severity(), rocksdb::Status::Severity::kHardError);
+  // We should be able to shutdown the database while auto recovery is going
+  // on in the background
+  Close();
+  DestroyDB(dbname_, options);
+}
+
+TEST_F(DBErrorHandlingTest, WALWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.writable_file_max_buffer_size = 32768;
+  options.env = fault_env.get();
+  options.listeners.emplace_back(listener);
+  Status s;
+  Random rnd(301);
+
+  listener->EnableAutoRecovery();
+  DestroyAndReopen(options);
+
+  {
+    WriteBatch batch;
+
+    for (auto i = 0; i<100; ++i) {
+      batch.Put(Key(i), RandomString(&rnd, 1024));
+    }
+
+    WriteOptions wopts;
+    wopts.sync = true;
+    ASSERT_EQ(dbfull()->Write(wopts, &batch), Status::OK());
+  };
+
+  {
+    WriteBatch batch;
+    int write_error = 0;
+
+    for (auto i = 100; i<199; ++i) {
+      batch.Put(Key(i), RandomString(&rnd, 1024));
+    }
+
+    SyncPoint::GetInstance()->SetCallBack("WritableFileWriter::Append:BeforePrepareWrite", [&](void*) {
+      write_error++;
+      if (write_error > 2) {
+        fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
+      }
+    });
+    SyncPoint::GetInstance()->EnableProcessing();
+    WriteOptions wopts;
+    wopts.sync = true;
+    s = dbfull()->Write(wopts, &batch);
+    ASSERT_EQ(s, s.NoSpace());
+  }
+  SyncPoint::GetInstance()->DisableProcessing();
+  fault_env->SetFilesystemActive(true);
+  ASSERT_EQ(listener->WaitForRecovery(5000000), true);
+  for (auto i=0; i<199; ++i) {
+    if (i < 100) {
+      ASSERT_NE(Get(Key(i)), "NOT_FOUND");
+    } else {
+      ASSERT_EQ(Get(Key(i)), "NOT_FOUND");
+    }
+  }
+  Reopen(options);
+  for (auto i=0; i<199; ++i) {
+    if (i < 100) {
+      ASSERT_NE(Get(Key(i)), "NOT_FOUND");
+    } else {
+      ASSERT_EQ(Get(Key(i)), "NOT_FOUND");
+    }
+  }
+  Close();
+}
+
+TEST_F(DBErrorHandlingTest, MultiCFWALWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
+  Options options = GetDefaultOptions();
+  options.create_if_missing = true;
+  options.writable_file_max_buffer_size = 32768;
+  options.env = fault_env.get();
+  options.listeners.emplace_back(listener);
+  Status s;
+  Random rnd(301);
+
+  listener->EnableAutoRecovery();
+  CreateAndReopenWithCF({"one", "two", "three"}, options);
+
+  {
+    WriteBatch batch;
+
+    for (auto i = 1; i < 4; ++i) {
+      for (auto j = 0; j < 100; ++j) {
+        batch.Put(handles_[i], Key(j), RandomString(&rnd, 1024));
+      }
+    }
+
+    WriteOptions wopts;
+    wopts.sync = true;
+    ASSERT_EQ(dbfull()->Write(wopts, &batch), Status::OK());
+  };
+
+  {
+    WriteBatch batch;
+    int write_error = 0;
+
+    // Write to one CF
+    for (auto i = 100; i < 199; ++i) {
+      batch.Put(handles_[2], Key(i), RandomString(&rnd, 1024));
+    }
+
+    SyncPoint::GetInstance()->SetCallBack(
+        "WritableFileWriter::Append:BeforePrepareWrite", [&](void*) {
+          write_error++;
+          if (write_error > 2) {
+            fault_env->SetFilesystemActive(false,
+                                           Status::NoSpace("Out of space"));
+          }
+        });
+    SyncPoint::GetInstance()->EnableProcessing();
+    WriteOptions wopts;
+    wopts.sync = true;
+    s = dbfull()->Write(wopts, &batch);
+    ASSERT_EQ(s, s.NoSpace());
+  }
+  SyncPoint::GetInstance()->DisableProcessing();
+  fault_env->SetFilesystemActive(true);
+  ASSERT_EQ(listener->WaitForRecovery(5000000), true);
+
+  for (auto i = 1; i < 4; ++i) {
+    // Every CF should have been flushed
+    ASSERT_EQ(NumTableFilesAtLevel(0, i), 1);
+  }
+
+  for (auto i = 1; i < 4; ++i) {
+    for (auto j = 0; j < 199; ++j) {
+      if (j < 100) {
+        ASSERT_NE(Get(i, Key(j)), "NOT_FOUND");
+      } else {
+        ASSERT_EQ(Get(i, Key(j)), "NOT_FOUND");
+      }
+    }
+  }
+  ReopenWithColumnFamilies({"default", "one", "two", "three"}, options);
+  for (auto i = 1; i < 4; ++i) {
+    for (auto j = 0; j < 199; ++j) {
+      if (j < 100) {
+        ASSERT_NE(Get(i, Key(j)), "NOT_FOUND");
+      } else {
+        ASSERT_EQ(Get(i, Key(j)), "NOT_FOUND");
+      }
+    }
+  }
+  Close();
+}
+
+TEST_F(DBErrorHandlingTest, MultiDBCompactionError) {
+  FaultInjectionTestEnv* def_env = new FaultInjectionTestEnv(Env::Default());
+  std::vector<std::unique_ptr<FaultInjectionTestEnv>> fault_env;
+  std::vector<Options> options;
+  std::vector<std::shared_ptr<ErrorHandlerListener>> listener;
+  std::vector<DB*> db;
+  std::shared_ptr<SstFileManager> sfm(NewSstFileManager(def_env));
+  int kNumDbInstances = 3;
+  Random rnd(301);
+
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    listener.emplace_back(new ErrorHandlerListener());
+    options.emplace_back(GetDefaultOptions());
+    fault_env.emplace_back(new FaultInjectionTestEnv(Env::Default()));
+    options[i].create_if_missing = true;
+    options[i].level0_file_num_compaction_trigger = 2;
+    options[i].writable_file_max_buffer_size = 32768;
+    options[i].env = fault_env[i].get();
+    options[i].listeners.emplace_back(listener[i]);
+    options[i].sst_file_manager = sfm;
+    DB* dbptr;
+    char buf[16];
+
+    listener[i]->EnableAutoRecovery();
+    // Setup for returning error for the 3rd SST, which would be level 1
+    listener[i]->InjectFileCreationError(fault_env[i].get(), 3,
+                                         Status::NoSpace("Out of space"));
+    snprintf(buf, sizeof(buf), "_%d", i);
+    DestroyDB(dbname_ + std::string(buf), options[i]);
+    ASSERT_EQ(DB::Open(options[i], dbname_ + std::string(buf), &dbptr),
+              Status::OK());
+    db.emplace_back(dbptr);
+  }
+
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    WriteBatch batch;
+
+    for (auto j = 0; j <= 100; ++j) {
+      batch.Put(Key(j), RandomString(&rnd, 1024));
+    }
+
+    WriteOptions wopts;
+    wopts.sync = true;
+    ASSERT_EQ(db[i]->Write(wopts, &batch), Status::OK());
+    ASSERT_EQ(db[i]->Flush(FlushOptions()), Status::OK());
+  }
+
+  def_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    WriteBatch batch;
+
+    // Write to one CF
+    for (auto j = 100; j < 199; ++j) {
+      batch.Put(Key(j), RandomString(&rnd, 1024));
+    }
+
+    WriteOptions wopts;
+    wopts.sync = true;
+    ASSERT_EQ(db[i]->Write(wopts, &batch), Status::OK());
+    ASSERT_EQ(db[i]->Flush(FlushOptions()), Status::OK());
+  }
+
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    Status s = static_cast<DBImpl*>(db[i])->TEST_WaitForCompact(true);
+    ASSERT_EQ(s.severity(), Status::Severity::kSoftError);
+    fault_env[i]->SetFilesystemActive(true);
+  }
+
+  def_env->SetFilesystemActive(true);
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    std::string prop;
+    ASSERT_EQ(listener[i]->WaitForRecovery(5000000), true);
+    EXPECT_TRUE(db[i]->GetProperty(
+        "rocksdb.num-files-at-level" + NumberToString(0), &prop));
+    EXPECT_EQ(atoi(prop.c_str()), 0);
+    EXPECT_TRUE(db[i]->GetProperty(
+        "rocksdb.num-files-at-level" + NumberToString(1), &prop));
+    EXPECT_EQ(atoi(prop.c_str()), 1);
+  }
+
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    char buf[16];
+    snprintf(buf, sizeof(buf), "_%d", i);
+    delete db[i];
+    fault_env[i]->SetFilesystemActive(true);
+    if (getenv("KEEP_DB")) {
+      printf("DB is still at %s%s\n", dbname_.c_str(), buf);
+    } else {
+      Status s = DestroyDB(dbname_ + std::string(buf), options[i]);
+    }
+  }
+  options.clear();
+  sfm.reset();
+  delete def_env;
+}
+
+TEST_F(DBErrorHandlingTest, MultiDBVariousErrors) {
+  FaultInjectionTestEnv* def_env = new FaultInjectionTestEnv(Env::Default());
+  std::vector<std::unique_ptr<FaultInjectionTestEnv>> fault_env;
+  std::vector<Options> options;
+  std::vector<std::shared_ptr<ErrorHandlerListener>> listener;
+  std::vector<DB*> db;
+  std::shared_ptr<SstFileManager> sfm(NewSstFileManager(def_env));
+  int kNumDbInstances = 3;
+  Random rnd(301);
+
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    listener.emplace_back(new ErrorHandlerListener());
+    options.emplace_back(GetDefaultOptions());
+    fault_env.emplace_back(new FaultInjectionTestEnv(Env::Default()));
+    options[i].create_if_missing = true;
+    options[i].level0_file_num_compaction_trigger = 2;
+    options[i].writable_file_max_buffer_size = 32768;
+    options[i].env = fault_env[i].get();
+    options[i].listeners.emplace_back(listener[i]);
+    options[i].sst_file_manager = sfm;
+    DB* dbptr;
+    char buf[16];
+
+    listener[i]->EnableAutoRecovery();
+    switch (i) {
+      case 0:
+        // Setup for returning error for the 3rd SST, which would be level 1
+        listener[i]->InjectFileCreationError(fault_env[i].get(), 3,
+                                             Status::NoSpace("Out of space"));
+        break;
+      case 1:
+        // Setup for returning error after the 1st SST, which would result
+        // in a hard error
+        listener[i]->InjectFileCreationError(fault_env[i].get(), 2,
+                                             Status::NoSpace("Out of space"));
+        break;
+      default:
+        break;
+    }
+    snprintf(buf, sizeof(buf), "_%d", i);
+    DestroyDB(dbname_ + std::string(buf), options[i]);
+    ASSERT_EQ(DB::Open(options[i], dbname_ + std::string(buf), &dbptr),
+              Status::OK());
+    db.emplace_back(dbptr);
+  }
+
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    WriteBatch batch;
+
+    for (auto j = 0; j <= 100; ++j) {
+      batch.Put(Key(j), RandomString(&rnd, 1024));
+    }
+
+    WriteOptions wopts;
+    wopts.sync = true;
+    ASSERT_EQ(db[i]->Write(wopts, &batch), Status::OK());
+    ASSERT_EQ(db[i]->Flush(FlushOptions()), Status::OK());
+  }
+
+  def_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    WriteBatch batch;
+
+    // Write to one CF
+    for (auto j = 100; j < 199; ++j) {
+      batch.Put(Key(j), RandomString(&rnd, 1024));
+    }
+
+    WriteOptions wopts;
+    wopts.sync = true;
+    ASSERT_EQ(db[i]->Write(wopts, &batch), Status::OK());
+    if (i != 1) {
+      ASSERT_EQ(db[i]->Flush(FlushOptions()), Status::OK());
+    } else {
+      ASSERT_EQ(db[i]->Flush(FlushOptions()), Status::NoSpace());
+    }
+  }
+
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    Status s = static_cast<DBImpl*>(db[i])->TEST_WaitForCompact(true);
+    switch (i) {
+      case 0:
+        ASSERT_EQ(s.severity(), Status::Severity::kSoftError);
+        break;
+      case 1:
+        ASSERT_EQ(s.severity(), Status::Severity::kHardError);
+        break;
+      case 2:
+        ASSERT_EQ(s, Status::OK());
+        break;
+    }
+    fault_env[i]->SetFilesystemActive(true);
+  }
+
+  def_env->SetFilesystemActive(true);
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    std::string prop;
+    if (i < 2) {
+      ASSERT_EQ(listener[i]->WaitForRecovery(5000000), true);
+    }
+    if (i == 1) {
+      ASSERT_EQ(static_cast<DBImpl*>(db[i])->TEST_WaitForCompact(true),
+                Status::OK());
+    }
+    EXPECT_TRUE(db[i]->GetProperty(
+        "rocksdb.num-files-at-level" + NumberToString(0), &prop));
+    EXPECT_EQ(atoi(prop.c_str()), 0);
+    EXPECT_TRUE(db[i]->GetProperty(
+        "rocksdb.num-files-at-level" + NumberToString(1), &prop));
+    EXPECT_EQ(atoi(prop.c_str()), 1);
+  }
+
+  for (auto i = 0; i < kNumDbInstances; ++i) {
+    char buf[16];
+    snprintf(buf, sizeof(buf), "_%d", i);
+    fault_env[i]->SetFilesystemActive(true);
+    delete db[i];
+    if (getenv("KEEP_DB")) {
+      printf("DB is still at %s%s\n", dbname_.c_str(), buf);
+    } else {
+      DestroyDB(dbname_ + std::string(buf), options[i]);
+    }
+  }
+  options.clear();
+  delete def_env;
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  rocksdb::port::InstallStackTraceHandler();
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
+
+#else
+#include <stdio.h>
+
+int main(int /*argc*/, char** /*argv*/) {
+  fprintf(stderr, "SKIPPED as Cuckoo table is not supported in ROCKSDB_LITE\n");
+  return 0;
+}
+
+#endif  // ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.16.X/db/event_helpers.cc b/3rdParty/rocksdb/v5.18.X/db/event_helpers.cc
similarity index 86%
rename from 3rdParty/rocksdb/v5.16.X/db/event_helpers.cc
rename to 3rdParty/rocksdb/v5.18.X/db/event_helpers.cc
index e4fd642260..c80c5aefb7 100644
--- a/3rdParty/rocksdb/v5.16.X/db/event_helpers.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/event_helpers.cc
@@ -40,8 +40,8 @@ void EventHelpers::NotifyTableFileCreationStarted(
 
 void EventHelpers::NotifyOnBackgroundError(
     const std::vector<std::shared_ptr<EventListener>>& listeners,
-    BackgroundErrorReason reason, Status* bg_error,
-    InstrumentedMutex* db_mutex) {
+    BackgroundErrorReason reason, Status* bg_error, InstrumentedMutex* db_mutex,
+    bool* auto_recovery) {
 #ifndef ROCKSDB_LITE
   if (listeners.size() == 0U) {
     return;
@@ -51,6 +51,9 @@ void EventHelpers::NotifyOnBackgroundError(
   db_mutex->Unlock();
   for (auto& listener : listeners) {
     listener->OnBackgroundError(reason, bg_error);
+    if (*auto_recovery) {
+      listener->OnErrorRecoveryBegin(reason, *bg_error, auto_recovery);
+    }
   }
   db_mutex->Lock();
 #else
@@ -58,6 +61,7 @@ void EventHelpers::NotifyOnBackgroundError(
   (void)reason;
   (void)bg_error;
   (void)db_mutex;
+  (void)auto_recovery;
 #endif  // ROCKSDB_LITE
 }
 
@@ -167,4 +171,25 @@ void EventHelpers::LogAndNotifyTableFileDeletion(
 #endif  // !ROCKSDB_LITE
 }
 
+void EventHelpers::NotifyOnErrorRecoveryCompleted(
+    const std::vector<std::shared_ptr<EventListener>>& listeners,
+    Status old_bg_error, InstrumentedMutex* db_mutex) {
+#ifndef ROCKSDB_LITE
+  if (listeners.size() == 0U) {
+    return;
+  }
+  db_mutex->AssertHeld();
+  // release lock while notifying events
+  db_mutex->Unlock();
+  for (auto& listener : listeners) {
+    listener->OnErrorRecoveryCompleted(old_bg_error);
+  }
+  db_mutex->Lock();
+#else
+  (void)listeners;
+  (void)old_bg_error;
+  (void)db_mutex;
+#endif  // ROCKSDB_LITE
+}
+
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/db/event_helpers.h b/3rdParty/rocksdb/v5.18.X/db/event_helpers.h
similarity index 89%
rename from 3rdParty/rocksdb/v5.16.X/db/event_helpers.h
rename to 3rdParty/rocksdb/v5.18.X/db/event_helpers.h
index 674e6c5f6f..ea35b4b5b1 100644
--- a/3rdParty/rocksdb/v5.16.X/db/event_helpers.h
+++ b/3rdParty/rocksdb/v5.18.X/db/event_helpers.h
@@ -28,7 +28,7 @@ class EventHelpers {
   static void NotifyOnBackgroundError(
       const std::vector<std::shared_ptr<EventListener>>& listeners,
       BackgroundErrorReason reason, Status* bg_error,
-      InstrumentedMutex* db_mutex);
+      InstrumentedMutex* db_mutex, bool* auto_recovery);
   static void LogAndNotifyTableFileCreationFinished(
       EventLogger* event_logger,
       const std::vector<std::shared_ptr<EventListener>>& listeners,
@@ -41,6 +41,9 @@ class EventHelpers {
       uint64_t file_number, const std::string& file_path,
       const Status& status, const std::string& db_name,
       const std::vector<std::shared_ptr<EventListener>>& listeners);
+  static void NotifyOnErrorRecoveryCompleted(
+      const std::vector<std::shared_ptr<EventListener>>& listeners,
+      Status bg_error, InstrumentedMutex* db_mutex);
 
  private:
   static void LogAndNotifyTableFileCreation(
diff --git a/3rdParty/rocksdb/v5.16.X/db/experimental.cc b/3rdParty/rocksdb/v5.18.X/db/experimental.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/experimental.cc
rename to 3rdParty/rocksdb/v5.18.X/db/experimental.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/external_sst_file_basic_test.cc b/3rdParty/rocksdb/v5.18.X/db/external_sst_file_basic_test.cc
similarity index 77%
rename from 3rdParty/rocksdb/v5.16.X/db/external_sst_file_basic_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/external_sst_file_basic_test.cc
index 02451f41ba..79853181d6 100644
--- a/3rdParty/rocksdb/v5.16.X/db/external_sst_file_basic_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/external_sst_file_basic_test.cc
@@ -14,7 +14,8 @@
 namespace rocksdb {
 
 #ifndef ROCKSDB_LITE
-class ExternalSSTFileBasicTest : public DBTestBase {
+class ExternalSSTFileBasicTest : public DBTestBase,
+                                 public ::testing::WithParamInterface<bool> {
  public:
   ExternalSSTFileBasicTest() : DBTestBase("/external_sst_file_test") {
     sst_files_dir_ = dbname_ + "/sst_files/";
@@ -41,7 +42,7 @@ class ExternalSSTFileBasicTest : public DBTestBase {
       const Options options, std::vector<int> keys,
       const std::vector<ValueType>& value_types,
       std::vector<std::pair<int, int>> range_deletions, int file_id,
-      std::map<std::string, std::string>* true_data) {
+      bool write_global_seqno, std::map<std::string, std::string>* true_data) {
     assert(value_types.size() == 1 || keys.size() == value_types.size());
     std::string file_path = sst_files_dir_ + ToString(file_id);
     SstFileWriter sst_file_writer(EnvOptions(), options);
@@ -105,6 +106,7 @@ class ExternalSSTFileBasicTest : public DBTestBase {
     if (s.ok()) {
       IngestExternalFileOptions ifo;
       ifo.allow_global_seqno = true;
+      ifo.write_global_seqno = write_global_seqno;
       s = db_->IngestExternalFile({file_path}, ifo);
     }
     return s;
@@ -113,17 +115,18 @@ class ExternalSSTFileBasicTest : public DBTestBase {
   Status GenerateAndAddExternalFile(
       const Options options, std::vector<int> keys,
       const std::vector<ValueType>& value_types, int file_id,
-      std::map<std::string, std::string>* true_data) {
+      bool write_global_seqno, std::map<std::string, std::string>* true_data) {
     return GenerateAndAddExternalFile(options, keys, value_types, {}, file_id,
-                                      true_data);
+                                      write_global_seqno, true_data);
   }
 
   Status GenerateAndAddExternalFile(
       const Options options, std::vector<int> keys, const ValueType value_type,
-      int file_id, std::map<std::string, std::string>* true_data) {
+      int file_id, bool write_global_seqno,
+      std::map<std::string, std::string>* true_data) {
     return GenerateAndAddExternalFile(options, keys,
                                       std::vector<ValueType>(1, value_type),
-                                      file_id, true_data);
+                                      file_id, write_global_seqno, true_data);
   }
 
   ~ExternalSSTFileBasicTest() { test::DestroyDir(env_, sst_files_dir_); }
@@ -245,7 +248,8 @@ TEST_F(ExternalSSTFileBasicTest, NoCopy) {
   }
 }
 
-TEST_F(ExternalSSTFileBasicTest, IngestFileWithGlobalSeqnoPickedSeqno) {
+TEST_P(ExternalSSTFileBasicTest, IngestFileWithGlobalSeqnoPickedSeqno) {
+  bool write_global_seqno = GetParam();
   do {
     Options options = CurrentOptions();
     DestroyAndReopen(options);
@@ -255,33 +259,37 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithGlobalSeqnoPickedSeqno) {
 
     ASSERT_OK(GenerateAndAddExternalFile(options, {1, 2, 3, 4, 5, 6},
                                          ValueType::kTypeValue, file_id++,
-                                         &true_data));
+                                         write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 0);
 
     ASSERT_OK(GenerateAndAddExternalFile(options, {10, 11, 12, 13},
                                          ValueType::kTypeValue, file_id++,
-                                         &true_data));
+                                         write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 0);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {1, 4, 6}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {1, 4, 6},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 1);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {11, 15, 19}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {11, 15, 19},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 2);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {120, 130}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {120, 130},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 2);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {1, 130}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {1, 130},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 3);
 
@@ -292,18 +300,21 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithGlobalSeqnoPickedSeqno) {
     }
     SequenceNumber last_seqno = dbfull()->GetLatestSequenceNumber();
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {60, 61, 62}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {60, 61, 62},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {40, 41, 42}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {40, 41, 42},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 1);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {20, 30, 40}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {20, 30, 40},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 2);
 
@@ -311,35 +322,39 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithGlobalSeqnoPickedSeqno) {
 
     // We will need a seqno for the file regardless if the file overwrite
     // keys in the DB or not because we have a snapshot
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {1000, 1002}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {1000, 1002},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // A global seqno will be assigned anyway because of the snapshot
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 3);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {2000, 3002}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {2000, 3002},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // A global seqno will be assigned anyway because of the snapshot
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 4);
 
     ASSERT_OK(GenerateAndAddExternalFile(options, {1, 20, 40, 100, 150},
                                          ValueType::kTypeValue, file_id++,
-                                         &true_data));
+                                         write_global_seqno, &true_data));
     // A global seqno will be assigned anyway because of the snapshot
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 5);
 
     db_->ReleaseSnapshot(snapshot);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {5000, 5001}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {5000, 5001},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // No snapshot anymore, no need to assign a seqno
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 5);
 
     size_t kcnt = 0;
     VerifyDBFromMap(true_data, &kcnt, false);
-  } while (ChangeCompactOptions());
+  } while (ChangeOptionsForFileIngestionTest());
 }
 
-TEST_F(ExternalSSTFileBasicTest, IngestFileWithMultipleValueType) {
+TEST_P(ExternalSSTFileBasicTest, IngestFileWithMultipleValueType) {
+  bool write_global_seqno = GetParam();
   do {
     Options options = CurrentOptions();
     options.merge_operator.reset(new TestPutOperator());
@@ -350,52 +365,57 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMultipleValueType) {
 
     ASSERT_OK(GenerateAndAddExternalFile(options, {1, 2, 3, 4, 5, 6},
                                          ValueType::kTypeValue, file_id++,
-                                         &true_data));
+                                         write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 0);
 
     ASSERT_OK(GenerateAndAddExternalFile(options, {10, 11, 12, 13},
                                          ValueType::kTypeValue, file_id++,
-                                         &true_data));
+                                         write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 0);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {1, 4, 6}, ValueType::kTypeMerge, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {1, 4, 6},
+                                         ValueType::kTypeMerge, file_id++,
+                                         write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 1);
 
     ASSERT_OK(GenerateAndAddExternalFile(options, {11, 15, 19},
                                          ValueType::kTypeDeletion, file_id++,
-                                         &true_data));
+                                         write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 2);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {120, 130}, ValueType::kTypeMerge, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {120, 130},
+                                         ValueType::kTypeMerge, file_id++,
+                                         write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 2);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {1, 130}, ValueType::kTypeDeletion, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {1, 130},
+                                         ValueType::kTypeDeletion, file_id++,
+                                         write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 3);
 
-    ASSERT_OK(GenerateAndAddExternalFile(options, {120},
-                                         {ValueType::kTypeValue}, {{120, 135}},
-                                         file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(
+        options, {120}, {ValueType::kTypeValue}, {{120, 135}}, file_id++,
+        write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 4);
 
     ASSERT_OK(GenerateAndAddExternalFile(options, {}, {}, {{110, 120}},
-                                         file_id++, &true_data));
+                                         file_id++, write_global_seqno,
+                                         &true_data));
     // The range deletion ends on a key, but it doesn't actually delete
     // this key because the largest key in the range is exclusive. Still,
     // it counts as an overlap so a new seqno will be assigned.
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 5);
 
     ASSERT_OK(GenerateAndAddExternalFile(options, {}, {}, {{100, 109}},
-                                         file_id++, &true_data));
+                                         file_id++, write_global_seqno,
+                                         &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 5);
 
@@ -406,19 +426,21 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMultipleValueType) {
     }
     SequenceNumber last_seqno = dbfull()->GetLatestSequenceNumber();
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {60, 61, 62}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {60, 61, 62},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {40, 41, 42}, ValueType::kTypeMerge, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {40, 41, 42},
+                                         ValueType::kTypeMerge, file_id++,
+                                         write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 1);
 
     ASSERT_OK(GenerateAndAddExternalFile(options, {20, 30, 40},
                                          ValueType::kTypeDeletion, file_id++,
-                                         &true_data));
+                                         write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 2);
 
@@ -426,35 +448,39 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMultipleValueType) {
 
     // We will need a seqno for the file regardless if the file overwrite
     // keys in the DB or not because we have a snapshot
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {1000, 1002}, ValueType::kTypeMerge, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {1000, 1002},
+                                         ValueType::kTypeMerge, file_id++,
+                                         write_global_seqno, &true_data));
     // A global seqno will be assigned anyway because of the snapshot
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 3);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {2000, 3002}, ValueType::kTypeMerge, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {2000, 3002},
+                                         ValueType::kTypeMerge, file_id++,
+                                         write_global_seqno, &true_data));
     // A global seqno will be assigned anyway because of the snapshot
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 4);
 
     ASSERT_OK(GenerateAndAddExternalFile(options, {1, 20, 40, 100, 150},
                                          ValueType::kTypeMerge, file_id++,
-                                         &true_data));
+                                         write_global_seqno, &true_data));
     // A global seqno will be assigned anyway because of the snapshot
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 5);
 
     db_->ReleaseSnapshot(snapshot);
 
-    ASSERT_OK(GenerateAndAddExternalFile(
-        options, {5000, 5001}, ValueType::kTypeValue, file_id++, &true_data));
+    ASSERT_OK(GenerateAndAddExternalFile(options, {5000, 5001},
+                                         ValueType::kTypeValue, file_id++,
+                                         write_global_seqno, &true_data));
     // No snapshot anymore, no need to assign a seqno
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 5);
 
     size_t kcnt = 0;
     VerifyDBFromMap(true_data, &kcnt, false);
-  } while (ChangeCompactOptions());
+  } while (ChangeOptionsForFileIngestionTest());
 }
 
-TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
+TEST_P(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
+  bool write_global_seqno = GetParam();
   do {
     Options options = CurrentOptions();
     options.merge_operator.reset(new TestPutOperator());
@@ -467,7 +493,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
         options, {1, 2, 3, 4, 5, 6},
         {ValueType::kTypeValue, ValueType::kTypeMerge, ValueType::kTypeValue,
          ValueType::kTypeMerge, ValueType::kTypeValue, ValueType::kTypeMerge},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 0);
 
@@ -475,33 +501,35 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
         options, {10, 11, 12, 13},
         {ValueType::kTypeValue, ValueType::kTypeMerge, ValueType::kTypeValue,
          ValueType::kTypeMerge},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 0);
 
     ASSERT_OK(GenerateAndAddExternalFile(
-        options, {1, 4, 6}, {ValueType::kTypeDeletion, ValueType::kTypeValue,
-                             ValueType::kTypeMerge},
-        file_id++, &true_data));
+        options, {1, 4, 6},
+        {ValueType::kTypeDeletion, ValueType::kTypeValue,
+         ValueType::kTypeMerge},
+        file_id++, write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 1);
 
     ASSERT_OK(GenerateAndAddExternalFile(
-        options, {11, 15, 19}, {ValueType::kTypeDeletion, ValueType::kTypeMerge,
-                                ValueType::kTypeValue},
-        file_id++, &true_data));
+        options, {11, 15, 19},
+        {ValueType::kTypeDeletion, ValueType::kTypeMerge,
+         ValueType::kTypeValue},
+        file_id++, write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 2);
 
     ASSERT_OK(GenerateAndAddExternalFile(
         options, {120, 130}, {ValueType::kTypeValue, ValueType::kTypeMerge},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 2);
 
     ASSERT_OK(GenerateAndAddExternalFile(
         options, {1, 130}, {ValueType::kTypeMerge, ValueType::kTypeDeletion},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 3);
 
@@ -509,14 +537,14 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
         options, {150, 151, 152},
         {ValueType::kTypeValue, ValueType::kTypeMerge,
          ValueType::kTypeDeletion},
-        {{150, 160}, {180, 190}}, file_id++, &true_data));
+        {{150, 160}, {180, 190}}, file_id++, write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 3);
 
     ASSERT_OK(GenerateAndAddExternalFile(
         options, {150, 151, 152},
         {ValueType::kTypeValue, ValueType::kTypeMerge, ValueType::kTypeValue},
-        {{200, 250}}, file_id++, &true_data));
+        {{200, 250}}, file_id++, write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 4);
 
@@ -524,7 +552,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
         options, {300, 301, 302},
         {ValueType::kTypeValue, ValueType::kTypeMerge,
          ValueType::kTypeDeletion},
-        {{1, 2}, {152, 154}}, file_id++, &true_data));
+        {{1, 2}, {152, 154}}, file_id++, write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), 5);
 
@@ -538,7 +566,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
     ASSERT_OK(GenerateAndAddExternalFile(
         options, {60, 61, 62},
         {ValueType::kTypeValue, ValueType::kTypeMerge, ValueType::kTypeValue},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // File doesn't overwrite any keys, no seqno needed
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno);
 
@@ -546,7 +574,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
         options, {40, 41, 42},
         {ValueType::kTypeValue, ValueType::kTypeDeletion,
          ValueType::kTypeDeletion},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 1);
 
@@ -554,7 +582,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
         options, {20, 30, 40},
         {ValueType::kTypeDeletion, ValueType::kTypeDeletion,
          ValueType::kTypeDeletion},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // File overwrites some keys, a seqno will be assigned
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 2);
 
@@ -564,13 +592,13 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
     // keys in the DB or not because we have a snapshot
     ASSERT_OK(GenerateAndAddExternalFile(
         options, {1000, 1002}, {ValueType::kTypeValue, ValueType::kTypeMerge},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // A global seqno will be assigned anyway because of the snapshot
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 3);
 
     ASSERT_OK(GenerateAndAddExternalFile(
         options, {2000, 3002}, {ValueType::kTypeValue, ValueType::kTypeMerge},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // A global seqno will be assigned anyway because of the snapshot
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 4);
 
@@ -578,7 +606,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
         options, {1, 20, 40, 100, 150},
         {ValueType::kTypeDeletion, ValueType::kTypeDeletion,
          ValueType::kTypeValue, ValueType::kTypeMerge, ValueType::kTypeMerge},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // A global seqno will be assigned anyway because of the snapshot
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 5);
 
@@ -586,13 +614,13 @@ TEST_F(ExternalSSTFileBasicTest, IngestFileWithMixedValueType) {
 
     ASSERT_OK(GenerateAndAddExternalFile(
         options, {5000, 5001}, {ValueType::kTypeValue, ValueType::kTypeMerge},
-        file_id++, &true_data));
+        file_id++, write_global_seqno, &true_data));
     // No snapshot anymore, no need to assign a seqno
     ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno + 5);
 
     size_t kcnt = 0;
     VerifyDBFromMap(true_data, &kcnt, false);
-  } while (ChangeCompactOptions());
+  } while (ChangeOptionsForFileIngestionTest());
 }
 
 TEST_F(ExternalSSTFileBasicTest, FadviseTrigger) {
@@ -635,7 +663,7 @@ TEST_F(ExternalSSTFileBasicTest, FadviseTrigger) {
   rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 }
 
-TEST_F(ExternalSSTFileBasicTest, IngestionWithRangeDeletions) {
+TEST_P(ExternalSSTFileBasicTest, IngestionWithRangeDeletions) {
   int kNumLevels = 7;
   Options options = CurrentOptions();
   options.disable_auto_compactions = true;
@@ -662,12 +690,13 @@ TEST_F(ExternalSSTFileBasicTest, IngestionWithRangeDeletions) {
   ASSERT_EQ(0, NumTableFilesAtLevel(kNumLevels - 2));
   ASSERT_EQ(1, NumTableFilesAtLevel(kNumLevels - 1));
 
+  bool write_global_seqno = GetParam();
   // overlaps with L0 file but not memtable, so flush is skipped and file is
   // ingested into L0
   SequenceNumber last_seqno = dbfull()->GetLatestSequenceNumber();
   ASSERT_OK(GenerateAndAddExternalFile(
       options, {60, 90}, {ValueType::kTypeValue, ValueType::kTypeValue},
-      {{65, 70}, {70, 85}}, file_id++, &true_data));
+      {{65, 70}, {70, 85}}, file_id++, write_global_seqno, &true_data));
   ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), ++last_seqno);
   ASSERT_EQ(2, NumTableFilesAtLevel(0));
   ASSERT_EQ(0, NumTableFilesAtLevel(kNumLevels - 2));
@@ -677,7 +706,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestionWithRangeDeletions) {
   // file is ingested into L5
   ASSERT_OK(GenerateAndAddExternalFile(
       options, {10, 40}, {ValueType::kTypeValue, ValueType::kTypeValue},
-      file_id++, &true_data));
+      file_id++, write_global_seqno, &true_data));
   ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), ++last_seqno);
   ASSERT_EQ(2, NumTableFilesAtLevel(0));
   ASSERT_EQ(1, NumTableFilesAtLevel(kNumLevels - 2));
@@ -686,7 +715,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestionWithRangeDeletions) {
   // overlaps with L5 file but not memtable or L0 file, so flush is skipped and
   // file is ingested into L4
   ASSERT_OK(GenerateAndAddExternalFile(options, {}, {}, {{5, 15}}, file_id++,
-                                       &true_data));
+                                       write_global_seqno, &true_data));
   ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), ++last_seqno);
   ASSERT_EQ(2, NumTableFilesAtLevel(0));
   ASSERT_EQ(1, NumTableFilesAtLevel(kNumLevels - 2));
@@ -698,7 +727,7 @@ TEST_F(ExternalSSTFileBasicTest, IngestionWithRangeDeletions) {
   // count increases by two.
   ASSERT_OK(GenerateAndAddExternalFile(
       options, {100, 140}, {ValueType::kTypeValue, ValueType::kTypeValue},
-      file_id++, &true_data));
+      file_id++, write_global_seqno, &true_data));
   ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), ++last_seqno);
   ASSERT_EQ(4, NumTableFilesAtLevel(0));
   ASSERT_EQ(1, NumTableFilesAtLevel(kNumLevels - 2));
@@ -711,13 +740,16 @@ TEST_F(ExternalSSTFileBasicTest, IngestionWithRangeDeletions) {
   // seqnum.
   ASSERT_OK(GenerateAndAddExternalFile(
       options, {151, 175}, {ValueType::kTypeValue, ValueType::kTypeValue},
-      {{160, 200}}, file_id++, &true_data));
+      {{160, 200}}, file_id++, write_global_seqno, &true_data));
   ASSERT_EQ(dbfull()->GetLatestSequenceNumber(), last_seqno);
   ASSERT_EQ(4, NumTableFilesAtLevel(0));
   ASSERT_EQ(1, NumTableFilesAtLevel(kNumLevels - 2));
   ASSERT_EQ(2, NumTableFilesAtLevel(options.num_levels - 1));
 }
 
+INSTANTIATE_TEST_CASE_P(ExternalSSTFileBasicTest, ExternalSSTFileBasicTest,
+                        testing::Bool());
+
 #endif  // ROCKSDB_LITE
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/db/external_sst_file_ingestion_job.cc b/3rdParty/rocksdb/v5.18.X/db/external_sst_file_ingestion_job.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/external_sst_file_ingestion_job.cc
rename to 3rdParty/rocksdb/v5.18.X/db/external_sst_file_ingestion_job.cc
index c31a5d6f52..af11f6de9b 100644
--- a/3rdParty/rocksdb/v5.16.X/db/external_sst_file_ingestion_job.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/external_sst_file_ingestion_job.cc
@@ -225,7 +225,7 @@ void ExternalSstFileIngestionJob::UpdateStats() {
   for (IngestedFileInfo& f : files_to_ingest_) {
     InternalStats::CompactionStats stats(CompactionReason::kExternalSstIngestion, 1);
     stats.micros = total_time;
-    // If actual copy occured for this file, then we need to count the file
+    // If actual copy occurred for this file, then we need to count the file
     // size as the actual bytes written. If the file was linked, then we ignore
     // the bytes written for file metadata.
     // TODO (yanqin) maybe account for file metadata bytes for exact accuracy?
@@ -344,7 +344,7 @@ Status ExternalSstFileIngestionJob::GetIngestedFileInfo(
       file_to_ingest->global_seqno_offset = 0;
       return Status::Corruption("Was not able to find file global seqno field");
     }
-    file_to_ingest->global_seqno_offset = offsets_iter->second;
+    file_to_ingest->global_seqno_offset = static_cast<size_t>(offsets_iter->second);
   } else if (file_to_ingest->version == 1) {
     // SST file V1 should not have global seqno field
     assert(seqno_iter == uprops.end());
diff --git a/3rdParty/rocksdb/v5.16.X/db/external_sst_file_ingestion_job.h b/3rdParty/rocksdb/v5.18.X/db/external_sst_file_ingestion_job.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/external_sst_file_ingestion_job.h
rename to 3rdParty/rocksdb/v5.18.X/db/external_sst_file_ingestion_job.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/external_sst_file_test.cc b/3rdParty/rocksdb/v5.18.X/db/external_sst_file_test.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/db/external_sst_file_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/external_sst_file_test.cc
index d4d86b3811..5c41cbb8b4 100644
--- a/3rdParty/rocksdb/v5.16.X/db/external_sst_file_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/external_sst_file_test.cc
@@ -15,7 +15,8 @@
 
 namespace rocksdb {
 
-class ExternalSSTFileTest : public DBTestBase {
+class ExternalSSTFileTest : public DBTestBase,
+                            public ::testing::WithParamInterface<bool> {
  public:
   ExternalSSTFileTest() : DBTestBase("/external_sst_file_test") {
     sst_files_dir_ = dbname_ + "/sst_files/";
@@ -30,7 +31,8 @@ class ExternalSSTFileTest : public DBTestBase {
   Status GenerateAndAddExternalFile(
       const Options options,
       std::vector<std::pair<std::string, std::string>> data, int file_id = -1,
-      bool allow_global_seqno = false, bool sort_data = false,
+      bool allow_global_seqno = false, bool write_global_seqno = false,
+      bool sort_data = false,
       std::map<std::string, std::string>* true_data = nullptr,
       ColumnFamilyHandle* cfh = nullptr) {
     // Generate a file id if not provided
@@ -73,6 +75,7 @@ class ExternalSSTFileTest : public DBTestBase {
     if (s.ok()) {
       IngestExternalFileOptions ifo;
       ifo.allow_global_seqno = allow_global_seqno;
+      ifo.write_global_seqno = allow_global_seqno ? write_global_seqno : false;
       if (cfh) {
         s = db_->IngestExternalFile(cfh, {file_path}, ifo);
       } else {
@@ -149,11 +152,10 @@ class ExternalSSTFileTest : public DBTestBase {
     return s;
   }
 
-
-
   Status GenerateAndAddExternalFile(
       const Options options, std::vector<std::pair<int, std::string>> data,
-      int file_id = -1, bool allow_global_seqno = false, bool sort_data = false,
+      int file_id = -1, bool allow_global_seqno = false,
+      bool write_global_seqno = false, bool sort_data = false,
       std::map<std::string, std::string>* true_data = nullptr,
       ColumnFamilyHandle* cfh = nullptr) {
     std::vector<std::pair<std::string, std::string>> file_data;
@@ -161,13 +163,14 @@ class ExternalSSTFileTest : public DBTestBase {
       file_data.emplace_back(Key(entry.first), entry.second);
     }
     return GenerateAndAddExternalFile(options, file_data, file_id,
-                                      allow_global_seqno, sort_data, true_data,
-                                      cfh);
+                                      allow_global_seqno, write_global_seqno,
+                                      sort_data, true_data, cfh);
   }
 
   Status GenerateAndAddExternalFile(
       const Options options, std::vector<int> keys, int file_id = -1,
-      bool allow_global_seqno = false, bool sort_data = false,
+      bool allow_global_seqno = false, bool write_global_seqno = false,
+      bool sort_data = false,
       std::map<std::string, std::string>* true_data = nullptr,
       ColumnFamilyHandle* cfh = nullptr) {
     std::vector<std::pair<std::string, std::string>> file_data;
@@ -175,18 +178,20 @@ class ExternalSSTFileTest : public DBTestBase {
       file_data.emplace_back(Key(k), Key(k) + ToString(file_id));
     }
     return GenerateAndAddExternalFile(options, file_data, file_id,
-                                      allow_global_seqno, sort_data, true_data,
-                                      cfh);
+                                      allow_global_seqno, write_global_seqno,
+                                      sort_data, true_data, cfh);
   }
 
   Status DeprecatedAddFile(const std::vector<std::string>& files,
                            bool move_files = false,
-                           bool skip_snapshot_check = false) {
+                           bool skip_snapshot_check = false,
+                           bool skip_write_global_seqno = false) {
     IngestExternalFileOptions opts;
     opts.move_files = move_files;
     opts.snapshot_consistency = !skip_snapshot_check;
     opts.allow_global_seqno = false;
     opts.allow_blocking_flush = false;
+    opts.write_global_seqno = !skip_write_global_seqno;
     return db_->IngestExternalFile(files, opts);
   }
 
@@ -453,6 +458,7 @@ TEST_F(ExternalSSTFileTest, Basic) {
   } while (ChangeOptions(kSkipPlainTable | kSkipFIFOCompaction |
                          kRangeDelSkipConfigs));
 }
+
 class SstFileWriterCollector : public TablePropertiesCollector {
  public:
   explicit SstFileWriterCollector(const std::string prefix) : prefix_(prefix) {
@@ -1141,7 +1147,7 @@ TEST_F(ExternalSSTFileTest, OverlappingRanges) {
   } while (ChangeOptions(kSkipPlainTable | kSkipFIFOCompaction));
 }
 
-TEST_F(ExternalSSTFileTest, PickedLevel) {
+TEST_P(ExternalSSTFileTest, PickedLevel) {
   Options options = CurrentOptions();
   options.disable_auto_compactions = false;
   options.level0_file_num_compaction_trigger = 4;
@@ -1152,11 +1158,11 @@ TEST_F(ExternalSSTFileTest, PickedLevel) {
 
   // File 0 will go to last level (L3)
   ASSERT_OK(GenerateAndAddExternalFile(options, {1, 10}, -1, false, false,
-                                       &true_data));
+                                       false, &true_data));
   EXPECT_EQ(FilesPerLevel(), "0,0,0,1");
 
   // File 1 will go to level L2 (since it overlap with file 0 in L3)
-  ASSERT_OK(GenerateAndAddExternalFile(options, {2, 9}, -1, false, false,
+  ASSERT_OK(GenerateAndAddExternalFile(options, {2, 9}, -1, false, false, false,
                                        &true_data));
   EXPECT_EQ(FilesPerLevel(), "0,0,1,1");
 
@@ -1186,13 +1192,13 @@ TEST_F(ExternalSSTFileTest, PickedLevel) {
 
   // This file overlaps with file 0 (L3), file 1 (L2) and the
   // output of compaction going to L1
-  ASSERT_OK(GenerateAndAddExternalFile(options, {4, 7}, -1, false, false,
+  ASSERT_OK(GenerateAndAddExternalFile(options, {4, 7}, -1, false, false, false,
                                        &true_data));
   EXPECT_EQ(FilesPerLevel(), "5,0,1,1");
 
   // This file does not overlap with any file or with the running compaction
   ASSERT_OK(GenerateAndAddExternalFile(options, {9000, 9001}, -1, false, false,
-                                       &true_data));
+                                       false, &true_data));
   EXPECT_EQ(FilesPerLevel(), "5,0,1,2");
 
   // Hold compaction from finishing
@@ -1311,7 +1317,8 @@ TEST_F(ExternalSSTFileTest, IngestNonExistingFile) {
   ASSERT_OK(Flush());
 
   ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-
+  ASSERT_OK(dbfull()->TEST_WaitForCompact(true));
+  
   // After full compaction, there should be only 1 file.
   std::vector<std::string> files;
   env_->GetChildren(dbname_, &files);
@@ -1422,12 +1429,12 @@ TEST_F(ExternalSSTFileTest, PickedLevelDynamic) {
   // This file overlaps with the output of the compaction (going to L3)
   // so the file will be added to L0 since L3 is the base level
   ASSERT_OK(GenerateAndAddExternalFile(options, {31, 32, 33, 34}, -1, false,
-                                       false, &true_data));
+                                       false, false, &true_data));
   EXPECT_EQ(FilesPerLevel(), "5");
 
   // This file does not overlap with the current running compactiong
   ASSERT_OK(GenerateAndAddExternalFile(options, {9000, 9001}, -1, false, false,
-                                       &true_data));
+                                       false, &true_data));
   EXPECT_EQ(FilesPerLevel(), "5,0,0,1");
 
   // Hold compaction from finishing
@@ -1442,24 +1449,24 @@ TEST_F(ExternalSSTFileTest, PickedLevelDynamic) {
   Reopen(options);
 
   ASSERT_OK(GenerateAndAddExternalFile(options, {1, 15, 19}, -1, false, false,
-                                       &true_data));
+                                       false, &true_data));
   ASSERT_EQ(FilesPerLevel(), "1,0,0,3");
 
   ASSERT_OK(GenerateAndAddExternalFile(options, {1000, 1001, 1002}, -1, false,
-                                       false, &true_data));
+                                       false, false, &true_data));
   ASSERT_EQ(FilesPerLevel(), "1,0,0,4");
 
   ASSERT_OK(GenerateAndAddExternalFile(options, {500, 600, 700}, -1, false,
-                                       false, &true_data));
+                                       false, false, &true_data));
   ASSERT_EQ(FilesPerLevel(), "1,0,0,5");
 
   // File 5 overlaps with file 2 (L3 / base level)
   ASSERT_OK(GenerateAndAddExternalFile(options, {2, 10}, -1, false, false,
-                                       &true_data));
+                                       false, &true_data));
   ASSERT_EQ(FilesPerLevel(), "2,0,0,5");
 
   // File 6 overlaps with file 2 (L3 / base level) and file 5 (L0)
-  ASSERT_OK(GenerateAndAddExternalFile(options, {3, 9}, -1, false, false,
+  ASSERT_OK(GenerateAndAddExternalFile(options, {3, 9}, -1, false, false, false,
                                        &true_data));
   ASSERT_EQ(FilesPerLevel(), "3,0,0,5");
 
@@ -1479,7 +1486,7 @@ TEST_F(ExternalSSTFileTest, PickedLevelDynamic) {
 
   // File 7 overlaps with file 4 (L3)
   ASSERT_OK(GenerateAndAddExternalFile(options, {650, 651, 652}, -1, false,
-                                       false, &true_data));
+                                       false, false, &true_data));
   ASSERT_EQ(FilesPerLevel(), "5,0,0,5");
 
   VerifyDBFromMap(true_data, &kcnt, false);
@@ -1613,12 +1620,13 @@ TEST_F(ExternalSSTFileTest, SstFileWriterNonSharedKeys) {
   ASSERT_OK(DeprecatedAddFile({file_path}));
 }
 
-TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoRandomized) {
+TEST_P(ExternalSSTFileTest, IngestFileWithGlobalSeqnoRandomized) {
   Options options = CurrentOptions();
   options.IncreaseParallelism(20);
   options.level0_slowdown_writes_trigger = 256;
   options.level0_stop_writes_trigger = 256;
 
+  bool write_global_seqno = GetParam();
   for (int iter = 0; iter < 2; iter++) {
     bool write_to_memtable = (iter == 0);
     DestroyAndReopen(options);
@@ -1643,7 +1651,8 @@ TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoRandomized) {
         }
       } else {
         ASSERT_OK(GenerateAndAddExternalFile(options, random_data, -1, true,
-                                             true, &true_data));
+                                             write_global_seqno, true,
+                                             &true_data));
       }
     }
     size_t kcnt = 0;
@@ -1653,7 +1662,7 @@ TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoRandomized) {
   }
 }
 
-TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoAssignedLevel) {
+TEST_P(ExternalSSTFileTest, IngestFileWithGlobalSeqnoAssignedLevel) {
   Options options = CurrentOptions();
   options.num_levels = 5;
   options.disable_auto_compactions = true;
@@ -1672,8 +1681,9 @@ TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoAssignedLevel) {
   for (int i = 0; i <= 20; i++) {
     file_data.emplace_back(Key(i), "L4");
   }
-  ASSERT_OK(GenerateAndAddExternalFile(options, file_data, -1, true, false,
-                                       &true_data));
+  bool write_global_seqno = GetParam();
+  ASSERT_OK(GenerateAndAddExternalFile(options, file_data, -1, true,
+                                       write_global_seqno, false, &true_data));
 
   // This file dont overlap with anything in the DB, will go to L4
   ASSERT_EQ("0,0,0,0,1", FilesPerLevel());
@@ -1683,8 +1693,8 @@ TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoAssignedLevel) {
   for (int i = 80; i <= 130; i++) {
     file_data.emplace_back(Key(i), "L0");
   }
-  ASSERT_OK(GenerateAndAddExternalFile(options, file_data, -1, true, false,
-                                       &true_data));
+  ASSERT_OK(GenerateAndAddExternalFile(options, file_data, -1, true,
+                                       write_global_seqno, false, &true_data));
 
   // This file overlap with the memtable, so it will flush it and add
   // it self to L0
@@ -1695,8 +1705,8 @@ TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoAssignedLevel) {
   for (int i = 30; i <= 50; i++) {
     file_data.emplace_back(Key(i), "L4");
   }
-  ASSERT_OK(GenerateAndAddExternalFile(options, file_data, -1, true, false,
-                                       &true_data));
+  ASSERT_OK(GenerateAndAddExternalFile(options, file_data, -1, true,
+                                       write_global_seqno, false, &true_data));
 
   // This file dont overlap with anything in the DB and fit in L4 as well
   ASSERT_EQ("2,0,0,0,2", FilesPerLevel());
@@ -1706,8 +1716,8 @@ TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoAssignedLevel) {
   for (int i = 10; i <= 40; i++) {
     file_data.emplace_back(Key(i), "L3");
   }
-  ASSERT_OK(GenerateAndAddExternalFile(options, file_data, -1, true, false,
-                                       &true_data));
+  ASSERT_OK(GenerateAndAddExternalFile(options, file_data, -1, true,
+                                       write_global_seqno, false, &true_data));
 
   // This file overlap with files in L4, we will ingest it in L3
   ASSERT_EQ("2,0,0,1,2", FilesPerLevel());
@@ -1716,7 +1726,7 @@ TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoAssignedLevel) {
   VerifyDBFromMap(true_data, &kcnt, false);
 }
 
-TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoMemtableFlush) {
+TEST_P(ExternalSSTFileTest, IngestFileWithGlobalSeqnoMemtableFlush) {
   Options options = CurrentOptions();
   DestroyAndReopen(options);
   uint64_t entries_in_memtable;
@@ -1730,16 +1740,17 @@ TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoMemtableFlush) {
                       &entries_in_memtable);
   ASSERT_GE(entries_in_memtable, 1);
 
+  bool write_global_seqno = GetParam();
   // No need for flush
-  ASSERT_OK(GenerateAndAddExternalFile(options, {90, 100, 110}, -1, true, false,
-                                       &true_data));
+  ASSERT_OK(GenerateAndAddExternalFile(options, {90, 100, 110}, -1, true,
+                                       write_global_seqno, false, &true_data));
   db_->GetIntProperty(DB::Properties::kNumEntriesActiveMemTable,
                       &entries_in_memtable);
   ASSERT_GE(entries_in_memtable, 1);
 
   // This file will flush the memtable
-  ASSERT_OK(GenerateAndAddExternalFile(options, {19, 20, 21}, -1, true, false,
-                                       &true_data));
+  ASSERT_OK(GenerateAndAddExternalFile(options, {19, 20, 21}, -1, true,
+                                       write_global_seqno, false, &true_data));
   db_->GetIntProperty(DB::Properties::kNumEntriesActiveMemTable,
                       &entries_in_memtable);
   ASSERT_EQ(entries_in_memtable, 0);
@@ -1754,14 +1765,14 @@ TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoMemtableFlush) {
 
   // No need for flush, this file keys fit between the memtable keys
   ASSERT_OK(GenerateAndAddExternalFile(options, {202, 203, 204}, -1, true,
-                                       false, &true_data));
+                                       write_global_seqno, false, &true_data));
   db_->GetIntProperty(DB::Properties::kNumEntriesActiveMemTable,
                       &entries_in_memtable);
   ASSERT_GE(entries_in_memtable, 1);
 
   // This file will flush the memtable
   ASSERT_OK(GenerateAndAddExternalFile(options, {206, 207}, -1, true, false,
-                                       &true_data));
+                                       write_global_seqno, &true_data));
   db_->GetIntProperty(DB::Properties::kNumEntriesActiveMemTable,
                       &entries_in_memtable);
   ASSERT_EQ(entries_in_memtable, 0);
@@ -1770,7 +1781,7 @@ TEST_F(ExternalSSTFileTest, IngestFileWithGlobalSeqnoMemtableFlush) {
   VerifyDBFromMap(true_data, &kcnt, false);
 }
 
-TEST_F(ExternalSSTFileTest, L0SortingIssue) {
+TEST_P(ExternalSSTFileTest, L0SortingIssue) {
   Options options = CurrentOptions();
   options.num_levels = 2;
   DestroyAndReopen(options);
@@ -1779,10 +1790,13 @@ TEST_F(ExternalSSTFileTest, L0SortingIssue) {
   ASSERT_OK(Put(Key(1), "memtable"));
   ASSERT_OK(Put(Key(10), "memtable"));
 
+  bool write_global_seqno = GetParam();
   // No Flush needed, No global seqno needed, Ingest in L1
-  ASSERT_OK(GenerateAndAddExternalFile(options, {7, 8}, -1, true, false));
+  ASSERT_OK(GenerateAndAddExternalFile(options, {7, 8}, -1, true,
+                                       write_global_seqno, false));
   // No Flush needed, but need a global seqno, Ingest in L0
-  ASSERT_OK(GenerateAndAddExternalFile(options, {7, 8}, -1, true, false));
+  ASSERT_OK(GenerateAndAddExternalFile(options, {7, 8}, -1, true,
+                                       write_global_seqno, false));
   printf("%s\n", FilesPerLevel().c_str());
 
   // Overwrite what we added using external files
@@ -2011,15 +2025,17 @@ class TestIngestExternalFileListener : public EventListener {
   std::vector<ExternalFileIngestionInfo> ingested_files;
 };
 
-TEST_F(ExternalSSTFileTest, IngestionListener) {
+TEST_P(ExternalSSTFileTest, IngestionListener) {
   Options options = CurrentOptions();
   TestIngestExternalFileListener* listener =
       new TestIngestExternalFileListener();
   options.listeners.emplace_back(listener);
   CreateAndReopenWithCF({"koko", "toto"}, options);
 
+  bool write_global_seqno = GetParam();
   // Ingest into default cf
-  ASSERT_OK(GenerateAndAddExternalFile(options, {1, 2}, -1, true, true, nullptr,
+  ASSERT_OK(GenerateAndAddExternalFile(options, {1, 2}, -1, true,
+                                       write_global_seqno, true, nullptr,
                                        handles_[0]));
   ASSERT_EQ(listener->ingested_files.size(), 1);
   ASSERT_EQ(listener->ingested_files.back().cf_name, "default");
@@ -2030,7 +2046,8 @@ TEST_F(ExternalSSTFileTest, IngestionListener) {
             "default");
 
   // Ingest into cf1
-  ASSERT_OK(GenerateAndAddExternalFile(options, {1, 2}, -1, true, true, nullptr,
+  ASSERT_OK(GenerateAndAddExternalFile(options, {1, 2}, -1, true,
+                                       write_global_seqno, true, nullptr,
                                        handles_[1]));
   ASSERT_EQ(listener->ingested_files.size(), 2);
   ASSERT_EQ(listener->ingested_files.back().cf_name, "koko");
@@ -2041,7 +2058,8 @@ TEST_F(ExternalSSTFileTest, IngestionListener) {
             "koko");
 
   // Ingest into cf2
-  ASSERT_OK(GenerateAndAddExternalFile(options, {1, 2}, -1, true, true, nullptr,
+  ASSERT_OK(GenerateAndAddExternalFile(options, {1, 2}, -1, true,
+                                       write_global_seqno, true, nullptr,
                                        handles_[2]));
   ASSERT_EQ(listener->ingested_files.size(), 3);
   ASSERT_EQ(listener->ingested_files.back().cf_name, "toto");
@@ -2084,7 +2102,7 @@ TEST_F(ExternalSSTFileTest, SnapshotInconsistencyBug) {
   db_->ReleaseSnapshot(snap);
 }
 
-TEST_F(ExternalSSTFileTest, IngestBehind) {
+TEST_P(ExternalSSTFileTest, IngestBehind) {
   Options options = CurrentOptions();
   options.compaction_style = kCompactionStyleUniversal;
   options.num_levels = 3;
@@ -2108,6 +2126,7 @@ TEST_F(ExternalSSTFileTest, IngestBehind) {
   IngestExternalFileOptions ifo;
   ifo.allow_global_seqno = true;
   ifo.ingest_behind = true;
+  ifo.write_global_seqno = GetParam();
 
   // Can't ingest behind since allow_ingest_behind isn't set to true
   ASSERT_NOK(GenerateAndAddExternalFileIngestBehind(options, ifo,
@@ -2195,6 +2214,9 @@ TEST_F(ExternalSSTFileTest, SkipBloomFilter) {
   }
 }
 
+INSTANTIATE_TEST_CASE_P(ExternalSSTFileTest, ExternalSSTFileTest,
+                        testing::Bool());
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
diff --git a/3rdParty/rocksdb/v5.16.X/db/fault_injection_test.cc b/3rdParty/rocksdb/v5.18.X/db/fault_injection_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/fault_injection_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/fault_injection_test.cc
index a6328e9700..45f5a94026 100644
--- a/3rdParty/rocksdb/v5.16.X/db/fault_injection_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/fault_injection_test.cc
@@ -70,7 +70,7 @@ class FaultInjectionTest
   std::unique_ptr<Env> base_env_;
   FaultInjectionTestEnv* env_;
   std::string dbname_;
-  shared_ptr<Cache> tiny_cache_;
+  std::shared_ptr<Cache> tiny_cache_;
   Options options_;
   DB* db_;
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/file_indexer.cc b/3rdParty/rocksdb/v5.18.X/db/file_indexer.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/file_indexer.cc
rename to 3rdParty/rocksdb/v5.18.X/db/file_indexer.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/file_indexer.h b/3rdParty/rocksdb/v5.18.X/db/file_indexer.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/file_indexer.h
rename to 3rdParty/rocksdb/v5.18.X/db/file_indexer.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/file_indexer_test.cc b/3rdParty/rocksdb/v5.18.X/db/file_indexer_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/file_indexer_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/file_indexer_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/filename_test.cc b/3rdParty/rocksdb/v5.18.X/db/filename_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/filename_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/filename_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/flush_job.cc b/3rdParty/rocksdb/v5.18.X/db/flush_job.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/db/flush_job.cc
rename to 3rdParty/rocksdb/v5.18.X/db/flush_job.cc
index 1fee162abf..8769c849e4 100644
--- a/3rdParty/rocksdb/v5.16.X/db/flush_job.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/flush_job.cc
@@ -24,14 +24,15 @@
 #include "db/event_helpers.h"
 #include "db/log_reader.h"
 #include "db/log_writer.h"
+#include "db/memtable.h"
 #include "db/memtable_list.h"
 #include "db/merge_context.h"
+#include "db/range_tombstone_fragmenter.h"
 #include "db/version_set.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/perf_context_imp.h"
 #include "monitoring/thread_status_util.h"
 #include "port/port.h"
-#include "db/memtable.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/statistics.h"
@@ -78,16 +79,18 @@ const char* GetFlushReasonString (FlushReason flush_reason) {
       return "Auto Compaction";
     case FlushReason::kManualFlush:
       return "Manual Flush";
+    case FlushReason::kErrorRecovery:
+      return "Error Recovery";
     default:
       return "Invalid";
   }
 }
 
-
 FlushJob::FlushJob(const std::string& dbname, ColumnFamilyData* cfd,
                    const ImmutableDBOptions& db_options,
                    const MutableCFOptions& mutable_cf_options,
-                   const EnvOptions env_options, VersionSet* versions,
+                   const uint64_t* max_memtable_id,
+                   const EnvOptions& env_options, VersionSet* versions,
                    InstrumentedMutex* db_mutex,
                    std::atomic<bool>* shutting_down,
                    std::vector<SequenceNumber> existing_snapshots,
@@ -96,11 +99,13 @@ FlushJob::FlushJob(const std::string& dbname, ColumnFamilyData* cfd,
                    LogBuffer* log_buffer, Directory* db_directory,
                    Directory* output_file_directory,
                    CompressionType output_compression, Statistics* stats,
-                   EventLogger* event_logger, bool measure_io_stats)
+                   EventLogger* event_logger, bool measure_io_stats,
+                   const bool sync_output_directory, const bool write_manifest)
     : dbname_(dbname),
       cfd_(cfd),
       db_options_(db_options),
       mutable_cf_options_(mutable_cf_options),
+      max_memtable_id_(max_memtable_id),
       env_options_(env_options),
       versions_(versions),
       db_mutex_(db_mutex),
@@ -116,6 +121,8 @@ FlushJob::FlushJob(const std::string& dbname, ColumnFamilyData* cfd,
       stats_(stats),
       event_logger_(event_logger),
       measure_io_stats_(measure_io_stats),
+      sync_output_directory_(sync_output_directory),
+      write_manifest_(write_manifest),
       edit_(nullptr),
       base_(nullptr),
       pick_memtable_called(false) {
@@ -160,7 +167,7 @@ void FlushJob::PickMemTable() {
   assert(!pick_memtable_called);
   pick_memtable_called = true;
   // Save the contents of the earliest memtable as a new Table
-  cfd_->imm()->PickMemtablesToFlush(&mems_);
+  cfd_->imm()->PickMemtablesToFlush(max_memtable_id_, &mems_);
   if (mems_.empty()) {
     return;
   }
@@ -224,10 +231,10 @@ Status FlushJob::Run(LogsWithPrepTracker* prep_tracker,
 
   if (!s.ok()) {
     cfd_->imm()->RollbackMemtableFlush(mems_, meta_.fd.GetNumber());
-  } else {
+  } else if (write_manifest_) {
     TEST_SYNC_POINT("FlushJob::InstallResults");
     // Replace immutable memtable with the generated Table
-    s = cfd_->imm()->InstallMemtableFlushResults(
+    s = cfd_->imm()->TryInstallMemtableFlushResults(
         cfd_, mutable_cf_options_, mems_, prep_tracker, versions_, db_mutex_,
         meta_.fd.GetNumber(), &job_context_->memtables_to_free, db_directory_,
         log_buffer_);
@@ -289,7 +296,8 @@ Status FlushJob::WriteLevel0Table() {
     // memtable and its associated range deletion memtable, respectively, at
     // corresponding indexes.
     std::vector<InternalIterator*> memtables;
-    std::vector<InternalIterator*> range_del_iters;
+    std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
+        range_del_iters;
     ReadOptions ro;
     ro.total_order_seek = true;
     Arena arena;
@@ -301,9 +309,10 @@ Status FlushJob::WriteLevel0Table() {
           "[%s] [JOB %d] Flushing memtable with next log file: %" PRIu64 "\n",
           cfd_->GetName().c_str(), job_context_->job_id, m->GetNextLogNumber());
       memtables.push_back(m->NewIterator(ro, &arena));
-      auto* range_del_iter = m->NewRangeTombstoneIterator(ro);
+      auto* range_del_iter =
+          m->NewRangeTombstoneIterator(ro, kMaxSequenceNumber);
       if (range_del_iter != nullptr) {
-        range_del_iters.push_back(range_del_iter);
+        range_del_iters.emplace_back(range_del_iter);
       }
       total_num_entries += m->num_entries();
       total_num_deletes += m->num_deletes();
@@ -322,10 +331,6 @@ Status FlushJob::WriteLevel0Table() {
       ScopedArenaIterator iter(
           NewMergingIterator(&cfd_->internal_comparator(), &memtables[0],
                              static_cast<int>(memtables.size()), &arena));
-      std::unique_ptr<InternalIterator> range_del_iter(NewMergingIterator(
-          &cfd_->internal_comparator(),
-          range_del_iters.empty() ? nullptr : &range_del_iters[0],
-          static_cast<int>(range_del_iters.size())));
       ROCKS_LOG_INFO(db_options_.info_log,
                      "[%s] [JOB %d] Level-0 flush table #%" PRIu64 ": started",
                      cfd_->GetName().c_str(), job_context_->job_id,
@@ -351,7 +356,7 @@ Status FlushJob::WriteLevel0Table() {
       s = BuildTable(
           dbname_, db_options_.env, *cfd_->ioptions(), mutable_cf_options_,
           env_options_, cfd_->table_cache(), iter.get(),
-          std::move(range_del_iter), &meta_, cfd_->internal_comparator(),
+          std::move(range_del_iters), &meta_, cfd_->internal_comparator(),
           cfd_->int_tbl_prop_collector_factories(), cfd_->GetID(),
           cfd_->GetName(), existing_snapshots_,
           earliest_write_conflict_snapshot_, snapshot_checker_,
@@ -371,7 +376,7 @@ Status FlushJob::WriteLevel0Table() {
                    s.ToString().c_str(),
                    meta_.marked_for_compaction ? " (needs compaction)" : "");
 
-    if (s.ok() && output_file_directory_ != nullptr) {
+    if (s.ok() && output_file_directory_ != nullptr && sync_output_directory_) {
       s = output_file_directory_->Fsync();
     }
     TEST_SYNC_POINT("FlushJob::WriteLevel0Table");
diff --git a/3rdParty/rocksdb/v5.16.X/db/flush_job.h b/3rdParty/rocksdb/v5.18.X/db/flush_job.h
similarity index 67%
rename from 3rdParty/rocksdb/v5.16.X/db/flush_job.h
rename to 3rdParty/rocksdb/v5.18.X/db/flush_job.h
index c3115c4a65..d993e410d1 100644
--- a/3rdParty/rocksdb/v5.16.X/db/flush_job.h
+++ b/3rdParty/rocksdb/v5.18.X/db/flush_job.h
@@ -59,14 +59,16 @@ class FlushJob {
   FlushJob(const std::string& dbname, ColumnFamilyData* cfd,
            const ImmutableDBOptions& db_options,
            const MutableCFOptions& mutable_cf_options,
-           const EnvOptions env_options, VersionSet* versions,
-           InstrumentedMutex* db_mutex, std::atomic<bool>* shutting_down,
+           const uint64_t* max_memtable_id, const EnvOptions& env_options,
+           VersionSet* versions, InstrumentedMutex* db_mutex,
+           std::atomic<bool>* shutting_down,
            std::vector<SequenceNumber> existing_snapshots,
            SequenceNumber earliest_write_conflict_snapshot,
            SnapshotChecker* snapshot_checker, JobContext* job_context,
            LogBuffer* log_buffer, Directory* db_directory,
            Directory* output_file_directory, CompressionType output_compression,
-           Statistics* stats, EventLogger* event_logger, bool measure_io_stats);
+           Statistics* stats, EventLogger* event_logger, bool measure_io_stats,
+           const bool sync_output_directory, const bool write_manifest);
 
   ~FlushJob();
 
@@ -77,16 +79,24 @@ class FlushJob {
              FileMetaData* file_meta = nullptr);
   void Cancel();
   TableProperties GetTableProperties() const { return table_properties_; }
+  const autovector<MemTable*>& GetMemTables() const { return mems_; }
 
  private:
   void ReportStartedFlush();
   void ReportFlushInputSize(const autovector<MemTable*>& mems);
   void RecordFlushIOStats();
   Status WriteLevel0Table();
+
   const std::string& dbname_;
   ColumnFamilyData* cfd_;
   const ImmutableDBOptions& db_options_;
   const MutableCFOptions& mutable_cf_options_;
+  // Pointer to a variable storing the largest memtable id to flush in this
+  // flush job. RocksDB uses this variable to select the memtables to flush in
+  // this job. All memtables in this column family with an ID smaller than or
+  // equal to *max_memtable_id_ will be selected for flush. If null, then all
+  // memtables in the column family will be selected.
+  const uint64_t* max_memtable_id_;
   const EnvOptions env_options_;
   VersionSet* versions_;
   InstrumentedMutex* db_mutex_;
@@ -103,6 +113,23 @@ class FlushJob {
   EventLogger* event_logger_;
   TableProperties table_properties_;
   bool measure_io_stats_;
+  // True if this flush job should call fsync on the output directory. False
+  // otherwise.
+  // Usually sync_output_directory_ is true. A flush job needs to call sync on
+  // the output directory before committing to the MANIFEST.
+  // However, an individual flush job does not have to call sync on the output
+  // directory if it is part of an atomic flush. After all flush jobs in the
+  // atomic flush succeed, call sync once on each distinct output directory.
+  const bool sync_output_directory_;
+  // True if this flush job should write to MANIFEST after successfully
+  // flushing memtables. False otherwise.
+  // Usually write_manifest_ is true. A flush job commits to the MANIFEST after
+  // flushing the memtables.
+  // However, an individual flush job cannot rashly write to the MANIFEST
+  // immediately after it finishes the flush if it is part of an atomic flush.
+  // In this case, only after all flush jobs succeed in flush can RocksDB
+  // commit to the MANIFEST.
+  const bool write_manifest_;
 
   // Variables below are set by PickMemTable():
   FileMetaData meta_;
diff --git a/3rdParty/rocksdb/v5.18.X/db/flush_job_test.cc b/3rdParty/rocksdb/v5.18.X/db/flush_job_test.cc
new file mode 100644
index 0000000000..519e01f2a5
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/flush_job_test.cc
@@ -0,0 +1,438 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include <algorithm>
+#include <map>
+#include <string>
+
+#include "db/column_family.h"
+#include "db/flush_job.h"
+#include "db/version_set.h"
+#include "rocksdb/cache.h"
+#include "rocksdb/write_buffer_manager.h"
+#include "table/mock_table.h"
+#include "util/file_reader_writer.h"
+#include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
+
+namespace rocksdb {
+
+// TODO(icanadi) Mock out everything else:
+// 1. VersionSet
+// 2. Memtable
+class FlushJobTest : public testing::Test {
+ public:
+  FlushJobTest()
+      : env_(Env::Default()),
+        dbname_(test::PerThreadDBPath("flush_job_test")),
+        options_(),
+        db_options_(options_),
+        column_family_names_({kDefaultColumnFamilyName, "foo", "bar"}),
+        table_cache_(NewLRUCache(50000, 16)),
+        write_buffer_manager_(db_options_.db_write_buffer_size),
+        versions_(new VersionSet(dbname_, &db_options_, env_options_,
+                                 table_cache_.get(), &write_buffer_manager_,
+                                 &write_controller_)),
+        shutting_down_(false),
+        mock_table_factory_(new mock::MockTableFactory()) {
+    EXPECT_OK(env_->CreateDirIfMissing(dbname_));
+    db_options_.db_paths.emplace_back(dbname_,
+                                      std::numeric_limits<uint64_t>::max());
+    db_options_.statistics = rocksdb::CreateDBStatistics();
+    // TODO(icanadi) Remove this once we mock out VersionSet
+    NewDB();
+    std::vector<ColumnFamilyDescriptor> column_families;
+    cf_options_.table_factory = mock_table_factory_;
+    for (const auto& cf_name : column_family_names_) {
+      column_families.emplace_back(cf_name, cf_options_);
+    }
+
+    EXPECT_OK(versions_->Recover(column_families, false));
+  }
+
+  void NewDB() {
+    VersionEdit new_db;
+    new_db.SetLogNumber(0);
+    new_db.SetNextFile(2);
+    new_db.SetLastSequence(0);
+
+    autovector<VersionEdit> new_cfs;
+    SequenceNumber last_seq = 1;
+    uint32_t cf_id = 1;
+    for (size_t i = 1; i != column_family_names_.size(); ++i) {
+      VersionEdit new_cf;
+      new_cf.AddColumnFamily(column_family_names_[i]);
+      new_cf.SetColumnFamily(cf_id++);
+      new_cf.SetLogNumber(0);
+      new_cf.SetNextFile(2);
+      new_cf.SetLastSequence(last_seq++);
+      new_cfs.emplace_back(new_cf);
+    }
+
+    const std::string manifest = DescriptorFileName(dbname_, 1);
+    std::unique_ptr<WritableFile> file;
+    Status s = env_->NewWritableFile(
+        manifest, &file, env_->OptimizeForManifestWrite(env_options_));
+    ASSERT_OK(s);
+    std::unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(file), manifest, EnvOptions()));
+    {
+      log::Writer log(std::move(file_writer), 0, false);
+      std::string record;
+      new_db.EncodeTo(&record);
+      s = log.AddRecord(record);
+
+      for (const auto& e : new_cfs) {
+        record.clear();
+        e.EncodeTo(&record);
+        s = log.AddRecord(record);
+        ASSERT_OK(s);
+      }
+    }
+    ASSERT_OK(s);
+    // Make "CURRENT" file that points to the new manifest file.
+    s = SetCurrentFile(env_, dbname_, 1, nullptr);
+  }
+
+  Env* env_;
+  std::string dbname_;
+  EnvOptions env_options_;
+  Options options_;
+  ImmutableDBOptions db_options_;
+  const std::vector<std::string> column_family_names_;
+  std::shared_ptr<Cache> table_cache_;
+  WriteController write_controller_;
+  WriteBufferManager write_buffer_manager_;
+  ColumnFamilyOptions cf_options_;
+  std::unique_ptr<VersionSet> versions_;
+  InstrumentedMutex mutex_;
+  std::atomic<bool> shutting_down_;
+  std::shared_ptr<mock::MockTableFactory> mock_table_factory_;
+};
+
+TEST_F(FlushJobTest, Empty) {
+  JobContext job_context(0);
+  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
+  EventLogger event_logger(db_options_.info_log.get());
+  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
+  FlushJob flush_job(
+      dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
+      *cfd->GetLatestMutableCFOptions(), nullptr /* memtable_id */,
+      env_options_, versions_.get(), &mutex_, &shutting_down_, {},
+      kMaxSequenceNumber, snapshot_checker, &job_context, nullptr, nullptr,
+      nullptr, kNoCompression, nullptr, &event_logger, false,
+      true /* sync_output_directory */, true /* write_manifest */);
+  {
+    InstrumentedMutexLock l(&mutex_);
+    flush_job.PickMemTable();
+    ASSERT_OK(flush_job.Run());
+  }
+  job_context.Clean();
+}
+
+TEST_F(FlushJobTest, NonEmpty) {
+  JobContext job_context(0);
+  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
+  auto new_mem = cfd->ConstructNewMemtable(*cfd->GetLatestMutableCFOptions(),
+                                           kMaxSequenceNumber);
+  new_mem->Ref();
+  auto inserted_keys = mock::MakeMockFile();
+  // Test data:
+  //   seqno [    1,    2 ... 8998, 8999, 9000, 9001, 9002 ... 9999 ]
+  //   key   [ 1001, 1002 ... 9998, 9999,    0,    1,    2 ...  999 ]
+  //   range-delete "9995" -> "9999" at seqno 10000
+  for (int i = 1; i < 10000; ++i) {
+    std::string key(ToString((i + 1000) % 10000));
+    std::string value("value" + key);
+    new_mem->Add(SequenceNumber(i), kTypeValue, key, value);
+    if ((i + 1000) % 10000 < 9995) {
+      InternalKey internal_key(key, SequenceNumber(i), kTypeValue);
+      inserted_keys.insert({internal_key.Encode().ToString(), value});
+    }
+  }
+  new_mem->Add(SequenceNumber(10000), kTypeRangeDeletion, "9995", "9999a");
+  InternalKey internal_key("9995", SequenceNumber(10000), kTypeRangeDeletion);
+  inserted_keys.insert({internal_key.Encode().ToString(), "9999a"});
+
+  autovector<MemTable*> to_delete;
+  cfd->imm()->Add(new_mem, &to_delete);
+  for (auto& m : to_delete) {
+    delete m;
+  }
+
+  EventLogger event_logger(db_options_.info_log.get());
+  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
+  FlushJob flush_job(
+      dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
+      *cfd->GetLatestMutableCFOptions(), nullptr /* memtable_id */,
+      env_options_, versions_.get(), &mutex_, &shutting_down_, {},
+      kMaxSequenceNumber, snapshot_checker, &job_context, nullptr, nullptr,
+      nullptr, kNoCompression, db_options_.statistics.get(), &event_logger,
+      true, true /* sync_output_directory */, true /* write_manifest */);
+
+  HistogramData hist;
+  FileMetaData file_meta;
+  mutex_.Lock();
+  flush_job.PickMemTable();
+  ASSERT_OK(flush_job.Run(nullptr, &file_meta));
+  mutex_.Unlock();
+  db_options_.statistics->histogramData(FLUSH_TIME, &hist);
+  ASSERT_GT(hist.average, 0.0);
+
+  ASSERT_EQ(ToString(0), file_meta.smallest.user_key().ToString());
+  ASSERT_EQ(
+      "9999a",
+      file_meta.largest.user_key().ToString());  // range tombstone end key
+  ASSERT_EQ(1, file_meta.fd.smallest_seqno);
+  ASSERT_EQ(10000, file_meta.fd.largest_seqno);  // range tombstone seqnum 10000
+  mock_table_factory_->AssertSingleFile(inserted_keys);
+  job_context.Clean();
+}
+
+TEST_F(FlushJobTest, FlushMemTablesSingleColumnFamily) {
+  const size_t num_mems = 2;
+  const size_t num_mems_to_flush = 1;
+  const size_t num_keys_per_table = 100;
+  JobContext job_context(0);
+  ColumnFamilyData* cfd = versions_->GetColumnFamilySet()->GetDefault();
+  std::vector<uint64_t> memtable_ids;
+  std::vector<MemTable*> new_mems;
+  for (size_t i = 0; i != num_mems; ++i) {
+    MemTable* mem = cfd->ConstructNewMemtable(*cfd->GetLatestMutableCFOptions(),
+                                              kMaxSequenceNumber);
+    mem->SetID(i);
+    mem->Ref();
+    new_mems.emplace_back(mem);
+    memtable_ids.push_back(mem->GetID());
+
+    for (size_t j = 0; j < num_keys_per_table; ++j) {
+      std::string key(ToString(j + i * num_keys_per_table));
+      std::string value("value" + key);
+      mem->Add(SequenceNumber(j + i * num_keys_per_table), kTypeValue, key,
+               value);
+    }
+  }
+
+  autovector<MemTable*> to_delete;
+  for (auto mem : new_mems) {
+    cfd->imm()->Add(mem, &to_delete);
+  }
+
+  EventLogger event_logger(db_options_.info_log.get());
+  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
+
+  assert(memtable_ids.size() == num_mems);
+  uint64_t smallest_memtable_id = memtable_ids.front();
+  uint64_t flush_memtable_id = smallest_memtable_id + num_mems_to_flush - 1;
+
+  FlushJob flush_job(
+      dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
+      *cfd->GetLatestMutableCFOptions(), &flush_memtable_id, env_options_,
+      versions_.get(), &mutex_, &shutting_down_, {}, kMaxSequenceNumber,
+      snapshot_checker, &job_context, nullptr, nullptr, nullptr, kNoCompression,
+      db_options_.statistics.get(), &event_logger, true,
+      true /* sync_output_directory */, true /* write_manifest */);
+  HistogramData hist;
+  FileMetaData file_meta;
+  mutex_.Lock();
+  flush_job.PickMemTable();
+  ASSERT_OK(flush_job.Run(nullptr /* prep_tracker */, &file_meta));
+  mutex_.Unlock();
+  db_options_.statistics->histogramData(FLUSH_TIME, &hist);
+  ASSERT_GT(hist.average, 0.0);
+
+  ASSERT_EQ(ToString(0), file_meta.smallest.user_key().ToString());
+  ASSERT_EQ("99", file_meta.largest.user_key().ToString());
+  ASSERT_EQ(0, file_meta.fd.smallest_seqno);
+  ASSERT_EQ(SequenceNumber(num_mems_to_flush * num_keys_per_table - 1),
+            file_meta.fd.largest_seqno);
+
+  for (auto m : to_delete) {
+    delete m;
+  }
+  to_delete.clear();
+  job_context.Clean();
+}
+
+TEST_F(FlushJobTest, FlushMemtablesMultipleColumnFamilies) {
+  autovector<ColumnFamilyData*> all_cfds;
+  for (auto cfd : *versions_->GetColumnFamilySet()) {
+    all_cfds.push_back(cfd);
+  }
+  const std::vector<size_t> num_memtables = {2, 1, 3};
+  assert(num_memtables.size() == column_family_names_.size());
+  const size_t num_keys_per_memtable = 1000;
+  JobContext job_context(0);
+  std::vector<uint64_t> memtable_ids;
+  std::vector<SequenceNumber> smallest_seqs;
+  std::vector<SequenceNumber> largest_seqs;
+  autovector<MemTable*> to_delete;
+  SequenceNumber curr_seqno = 0;
+  size_t k = 0;
+  for (auto cfd : all_cfds) {
+    smallest_seqs.push_back(curr_seqno);
+    for (size_t i = 0; i != num_memtables[k]; ++i) {
+      MemTable* mem = cfd->ConstructNewMemtable(
+          *cfd->GetLatestMutableCFOptions(), kMaxSequenceNumber);
+      mem->SetID(i);
+      mem->Ref();
+      mem->TEST_AtomicFlushSequenceNumber() = 123;
+
+      for (size_t j = 0; j != num_keys_per_memtable; ++j) {
+        std::string key(ToString(j + i * num_keys_per_memtable));
+        std::string value("value" + key);
+        mem->Add(curr_seqno++, kTypeValue, key, value);
+      }
+
+      cfd->imm()->Add(mem, &to_delete);
+    }
+    largest_seqs.push_back(curr_seqno - 1);
+    memtable_ids.push_back(num_memtables[k++] - 1);
+  }
+
+  EventLogger event_logger(db_options_.info_log.get());
+  SnapshotChecker* snapshot_checker = nullptr;  // not relevant
+  std::vector<FlushJob> flush_jobs;
+  k = 0;
+  for (auto cfd : all_cfds) {
+    std::vector<SequenceNumber> snapshot_seqs;
+    flush_jobs.emplace_back(
+        dbname_, cfd, db_options_, *cfd->GetLatestMutableCFOptions(),
+        &memtable_ids[k], env_options_, versions_.get(), &mutex_,
+        &shutting_down_, snapshot_seqs, kMaxSequenceNumber, snapshot_checker,
+        &job_context, nullptr, nullptr, nullptr, kNoCompression,
+        db_options_.statistics.get(), &event_logger, true,
+        false /* sync_output_directory */, false /* write_manifest */);
+    k++;
+  }
+  HistogramData hist;
+  autovector<FileMetaData> file_metas;
+  mutex_.Lock();
+  for (auto& job : flush_jobs) {
+    job.PickMemTable();
+  }
+  for (auto& job : flush_jobs) {
+    FileMetaData meta;
+    // Run will release and re-acquire  mutex
+    ASSERT_OK(job.Run(nullptr /**/, &meta));
+    file_metas.emplace_back(meta);
+  }
+  autovector<const autovector<MemTable*>*> mems_list;
+  for (size_t i = 0; i != all_cfds.size(); ++i) {
+    const auto& mems = flush_jobs[i].GetMemTables();
+    mems_list.push_back(&mems);
+  }
+  autovector<MemTableList*> imm_lists;
+  autovector<const MutableCFOptions*> mutable_cf_options_list;
+  for (auto cfd : all_cfds) {
+    imm_lists.push_back(cfd->imm());
+    mutable_cf_options_list.push_back(cfd->GetLatestMutableCFOptions());
+  }
+
+  bool atomic_flush_commit_in_progress = false;
+  Status s = MemTableList::TryInstallMemtableFlushResults(
+      imm_lists, all_cfds, mutable_cf_options_list, mems_list,
+      &atomic_flush_commit_in_progress, nullptr /* logs_prep_tracker */,
+      versions_.get(), &mutex_, file_metas, &job_context.memtables_to_free,
+      nullptr /* db_directory */, nullptr /* log_buffer */);
+  ASSERT_OK(s);
+
+  mutex_.Unlock();
+  db_options_.statistics->histogramData(FLUSH_TIME, &hist);
+  ASSERT_GT(hist.average, 0.0);
+  k = 0;
+  for (const auto& file_meta : file_metas) {
+    ASSERT_EQ(ToString(0), file_meta.smallest.user_key().ToString());
+    ASSERT_EQ("999", file_meta.largest.user_key()
+                         .ToString());  // max key by bytewise comparator
+    ASSERT_EQ(smallest_seqs[k], file_meta.fd.smallest_seqno);
+    ASSERT_EQ(largest_seqs[k], file_meta.fd.largest_seqno);
+    // Verify that imm is empty
+    ASSERT_EQ(std::numeric_limits<uint64_t>::max(),
+              all_cfds[k]->imm()->GetEarliestMemTableID());
+    ASSERT_EQ(0, all_cfds[k]->imm()->GetLatestMemTableID());
+    ++k;
+  }
+
+  for (auto m : to_delete) {
+    delete m;
+  }
+  to_delete.clear();
+  job_context.Clean();
+}
+
+TEST_F(FlushJobTest, Snapshots) {
+  JobContext job_context(0);
+  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
+  auto new_mem = cfd->ConstructNewMemtable(*cfd->GetLatestMutableCFOptions(),
+                                           kMaxSequenceNumber);
+
+  std::vector<SequenceNumber> snapshots;
+  std::set<SequenceNumber> snapshots_set;
+  int keys = 10000;
+  int max_inserts_per_keys = 8;
+
+  Random rnd(301);
+  for (int i = 0; i < keys / 2; ++i) {
+    snapshots.push_back(rnd.Uniform(keys * (max_inserts_per_keys / 2)) + 1);
+    snapshots_set.insert(snapshots.back());
+  }
+  std::sort(snapshots.begin(), snapshots.end());
+
+  new_mem->Ref();
+  SequenceNumber current_seqno = 0;
+  auto inserted_keys = mock::MakeMockFile();
+  for (int i = 1; i < keys; ++i) {
+    std::string key(ToString(i));
+    int insertions = rnd.Uniform(max_inserts_per_keys);
+    for (int j = 0; j < insertions; ++j) {
+      std::string value(test::RandomHumanReadableString(&rnd, 10));
+      auto seqno = ++current_seqno;
+      new_mem->Add(SequenceNumber(seqno), kTypeValue, key, value);
+      // a key is visible only if:
+      // 1. it's the last one written (j == insertions - 1)
+      // 2. there's a snapshot pointing at it
+      bool visible = (j == insertions - 1) ||
+                     (snapshots_set.find(seqno) != snapshots_set.end());
+      if (visible) {
+        InternalKey internal_key(key, seqno, kTypeValue);
+        inserted_keys.insert({internal_key.Encode().ToString(), value});
+      }
+    }
+  }
+
+  autovector<MemTable*> to_delete;
+  cfd->imm()->Add(new_mem, &to_delete);
+  for (auto& m : to_delete) {
+    delete m;
+  }
+
+  EventLogger event_logger(db_options_.info_log.get());
+  SnapshotChecker* snapshot_checker = nullptr;  // not relavant
+  FlushJob flush_job(
+      dbname_, versions_->GetColumnFamilySet()->GetDefault(), db_options_,
+      *cfd->GetLatestMutableCFOptions(), nullptr /* memtable_id */,
+      env_options_, versions_.get(), &mutex_, &shutting_down_, snapshots,
+      kMaxSequenceNumber, snapshot_checker, &job_context, nullptr, nullptr,
+      nullptr, kNoCompression, db_options_.statistics.get(), &event_logger,
+      true, true /* sync_output_directory */, true /* write_manifest */);
+  mutex_.Lock();
+  flush_job.PickMemTable();
+  ASSERT_OK(flush_job.Run());
+  mutex_.Unlock();
+  mock_table_factory_->AssertSingleFile(inserted_keys);
+  HistogramData hist;
+  db_options_.statistics->histogramData(FLUSH_TIME, &hist);
+  ASSERT_GT(hist.average, 0.0);
+  job_context.Clean();
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
diff --git a/3rdParty/rocksdb/v5.16.X/db/flush_scheduler.cc b/3rdParty/rocksdb/v5.18.X/db/flush_scheduler.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/flush_scheduler.cc
rename to 3rdParty/rocksdb/v5.18.X/db/flush_scheduler.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/flush_scheduler.h b/3rdParty/rocksdb/v5.18.X/db/flush_scheduler.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/flush_scheduler.h
rename to 3rdParty/rocksdb/v5.18.X/db/flush_scheduler.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/forward_iterator.cc b/3rdParty/rocksdb/v5.18.X/db/forward_iterator.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/db/forward_iterator.cc
rename to 3rdParty/rocksdb/v5.18.X/db/forward_iterator.cc
index 42395cc46b..226d56d5f9 100644
--- a/3rdParty/rocksdb/v5.16.X/db/forward_iterator.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/forward_iterator.cc
@@ -15,6 +15,8 @@
 #include "db/db_iter.h"
 #include "db/dbformat.h"
 #include "db/job_context.h"
+#include "db/range_del_aggregator_v2.h"
+#include "db/range_tombstone_fragmenter.h"
 #include "rocksdb/env.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/slice_transform.h"
@@ -71,8 +73,8 @@ class ForwardLevelIterator : public InternalIterator {
       delete file_iter_;
     }
 
-    RangeDelAggregator range_del_agg(
-        cfd_->internal_comparator(), {} /* snapshots */);
+    ReadRangeDelAggregatorV2 range_del_agg(
+        &cfd_->internal_comparator(), kMaxSequenceNumber /* upper_bound */);
     file_iter_ = cfd_->table_cache()->NewIterator(
         read_options_, *(cfd_->soptions()), cfd_->internal_comparator(),
         *files_[file_index_],
@@ -608,13 +610,14 @@ void ForwardIterator::RebuildIterators(bool refresh_sv) {
     // New
     sv_ = cfd_->GetReferencedSuperVersion(&(db_->mutex_));
   }
-  RangeDelAggregator range_del_agg(
-      cfd_->internal_comparator(), {} /* snapshots */);
+  ReadRangeDelAggregatorV2 range_del_agg(&cfd_->internal_comparator(),
+                                         kMaxSequenceNumber /* upper_bound */);
   mutable_iter_ = sv_->mem->NewIterator(read_options_, &arena_);
   sv_->imm->AddIterators(read_options_, &imm_iters_, &arena_);
   if (!read_options_.ignore_range_deletions) {
-    std::unique_ptr<InternalIterator> range_del_iter(
-        sv_->mem->NewRangeTombstoneIterator(read_options_));
+    std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter(
+        sv_->mem->NewRangeTombstoneIterator(
+            read_options_, sv_->current->version_set()->LastSequence()));
     range_del_agg.AddTombstones(std::move(range_del_iter));
     sv_->imm->AddRangeTombstoneIterators(read_options_, &arena_,
                                          &range_del_agg);
@@ -666,11 +669,12 @@ void ForwardIterator::RenewIterators() {
 
   mutable_iter_ = svnew->mem->NewIterator(read_options_, &arena_);
   svnew->imm->AddIterators(read_options_, &imm_iters_, &arena_);
-  RangeDelAggregator range_del_agg(
-      cfd_->internal_comparator(), {} /* snapshots */);
+  ReadRangeDelAggregatorV2 range_del_agg(&cfd_->internal_comparator(),
+                                         kMaxSequenceNumber /* upper_bound */);
   if (!read_options_.ignore_range_deletions) {
-    std::unique_ptr<InternalIterator> range_del_iter(
-        svnew->mem->NewRangeTombstoneIterator(read_options_));
+    std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter(
+        svnew->mem->NewRangeTombstoneIterator(
+            read_options_, sv_->current->version_set()->LastSequence()));
     range_del_agg.AddTombstones(std::move(range_del_iter));
     svnew->imm->AddRangeTombstoneIterators(read_options_, &arena_,
                                            &range_del_agg);
@@ -916,21 +920,13 @@ bool ForwardIterator::TEST_CheckDeletedIters(int* pdeleted_iters,
 uint32_t ForwardIterator::FindFileInRange(
     const std::vector<FileMetaData*>& files, const Slice& internal_key,
     uint32_t left, uint32_t right) {
-  while (left < right) {
-    uint32_t mid = (left + right) / 2;
-    const FileMetaData* f = files[mid];
-    if (cfd_->internal_comparator().InternalKeyComparator::Compare(
-          f->largest.Encode(), internal_key) < 0) {
-      // Key at "mid.largest" is < "target".  Therefore all
-      // files at or before "mid" are uninteresting.
-      left = mid + 1;
-    } else {
-      // Key at "mid.largest" is >= "target".  Therefore all files
-      // after "mid" are uninteresting.
-      right = mid;
-    }
-  }
-  return right;
+  auto cmp = [&](const FileMetaData* f, const Slice& key) -> bool {
+    return cfd_->internal_comparator().InternalKeyComparator::Compare(
+            f->largest.Encode(), key) < 0;
+  };
+  const auto &b = files.begin();
+  return static_cast<uint32_t>(std::lower_bound(b + left,
+                                 b + right, internal_key, cmp) - b);
 }
 
 void ForwardIterator::DeleteIterator(InternalIterator* iter, bool is_arena) {
diff --git a/3rdParty/rocksdb/v5.16.X/db/forward_iterator.h b/3rdParty/rocksdb/v5.18.X/db/forward_iterator.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/forward_iterator.h
rename to 3rdParty/rocksdb/v5.18.X/db/forward_iterator.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/forward_iterator_bench.cc b/3rdParty/rocksdb/v5.18.X/db/forward_iterator_bench.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/forward_iterator_bench.cc
rename to 3rdParty/rocksdb/v5.18.X/db/forward_iterator_bench.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/internal_stats.cc b/3rdParty/rocksdb/v5.18.X/db/internal_stats.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/internal_stats.cc
rename to 3rdParty/rocksdb/v5.18.X/db/internal_stats.cc
index 906d007959..b330a40f12 100644
--- a/3rdParty/rocksdb/v5.16.X/db/internal_stats.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/internal_stats.cc
@@ -231,6 +231,8 @@ static const std::string current_version_number =
     "current-super-version-number";
 static const std::string estimate_live_data_size = "estimate-live-data-size";
 static const std::string min_log_number_to_keep_str = "min-log-number-to-keep";
+static const std::string min_obsolete_sst_number_to_keep_str =
+    "min-obsolete-sst-number-to-keep";
 static const std::string base_level_str = "base-level";
 static const std::string total_sst_files_size = "total-sst-files-size";
 static const std::string live_sst_files_size = "live-sst-files-size";
@@ -310,6 +312,8 @@ const std::string DB::Properties::kEstimateLiveDataSize =
     rocksdb_prefix + estimate_live_data_size;
 const std::string DB::Properties::kMinLogNumberToKeep =
     rocksdb_prefix + min_log_number_to_keep_str;
+const std::string DB::Properties::kMinObsoleteSstNumberToKeep =
+    rocksdb_prefix + min_obsolete_sst_number_to_keep_str;
 const std::string DB::Properties::kTotalSstFilesSize =
     rocksdb_prefix + total_sst_files_size;
 const std::string DB::Properties::kLiveSstFilesSize =
@@ -430,6 +434,9 @@ const std::unordered_map<std::string, DBPropertyInfo>
         {DB::Properties::kMinLogNumberToKeep,
          {false, nullptr, &InternalStats::HandleMinLogNumberToKeep, nullptr,
           nullptr}},
+        {DB::Properties::kMinObsoleteSstNumberToKeep,
+         {false, nullptr, &InternalStats::HandleMinObsoleteSstNumberToKeep,
+          nullptr, nullptr}},
         {DB::Properties::kBaseLevel,
          {false, nullptr, &InternalStats::HandleBaseLevel, nullptr, nullptr}},
         {DB::Properties::kTotalSstFilesSize,
@@ -826,6 +833,13 @@ bool InternalStats::HandleMinLogNumberToKeep(uint64_t* value, DBImpl* db,
   return true;
 }
 
+bool InternalStats::HandleMinObsoleteSstNumberToKeep(uint64_t* value,
+                                                     DBImpl* db,
+                                                     Version* /*version*/) {
+  *value = db->MinObsoleteSstNumberToKeep();
+  return true;
+}
+
 bool InternalStats::HandleActualDelayedWriteRate(uint64_t* value, DBImpl* db,
                                                  Version* /*version*/) {
   const WriteController& wc = db->write_controller();
diff --git a/3rdParty/rocksdb/v5.16.X/db/internal_stats.h b/3rdParty/rocksdb/v5.18.X/db/internal_stats.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/internal_stats.h
rename to 3rdParty/rocksdb/v5.18.X/db/internal_stats.h
index 620ae47349..6f01275132 100644
--- a/3rdParty/rocksdb/v5.16.X/db/internal_stats.h
+++ b/3rdParty/rocksdb/v5.18.X/db/internal_stats.h
@@ -533,6 +533,8 @@ class InternalStats {
   bool HandleEstimateLiveDataSize(uint64_t* value, DBImpl* db,
                                   Version* version);
   bool HandleMinLogNumberToKeep(uint64_t* value, DBImpl* db, Version* version);
+  bool HandleMinObsoleteSstNumberToKeep(uint64_t* value, DBImpl* db,
+                                        Version* version);
   bool HandleActualDelayedWriteRate(uint64_t* value, DBImpl* db,
                                     Version* version);
   bool HandleIsWriteStopped(uint64_t* value, DBImpl* db, Version* version);
diff --git a/3rdParty/rocksdb/v5.16.X/db/job_context.h b/3rdParty/rocksdb/v5.18.X/db/job_context.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/db/job_context.h
rename to 3rdParty/rocksdb/v5.18.X/db/job_context.h
index af640dab29..498ef7d176 100644
--- a/3rdParty/rocksdb/v5.16.X/db/job_context.h
+++ b/3rdParty/rocksdb/v5.18.X/db/job_context.h
@@ -30,7 +30,8 @@ struct SuperVersionContext {
 #ifndef ROCKSDB_DISABLE_STALL_NOTIFICATION
   autovector<WriteStallNotification> write_stall_notifications;
 #endif
-  unique_ptr<SuperVersion> new_superversion;  // if nullptr no new superversion
+  std::unique_ptr<SuperVersion>
+      new_superversion;  // if nullptr no new superversion
 
   explicit SuperVersionContext(bool create_superversion = false)
     : new_superversion(create_superversion ? new SuperVersion() : nullptr) {}
@@ -44,7 +45,7 @@ struct SuperVersionContext {
   }
 
   void NewSuperVersion() {
-    new_superversion = unique_ptr<SuperVersion>(new SuperVersion());
+    new_superversion = std::unique_ptr<SuperVersion>(new SuperVersion());
   }
 
   inline bool HaveSomethingToDelete() const {
diff --git a/3rdParty/rocksdb/v5.16.X/db/listener_test.cc b/3rdParty/rocksdb/v5.18.X/db/listener_test.cc
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/db/listener_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/listener_test.cc
index afb046f49a..cbbffc8cb7 100644
--- a/3rdParty/rocksdb/v5.16.X/db/listener_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/listener_test.cc
@@ -417,7 +417,9 @@ TEST_F(EventListenerTest, DisableBGCompaction) {
   for (int i = 0; static_cast<int>(cf_meta.file_count) < kSlowdownTrigger * 10;
        ++i) {
     Put(1, ToString(i), std::string(10000, 'x'), WriteOptions());
-    db_->Flush(FlushOptions(), handles_[1]);
+    FlushOptions fo;
+    fo.allow_write_stall = true;
+    db_->Flush(fo, handles_[1]);
     db_->GetColumnFamilyMetaData(handles_[1], &cf_meta);
   }
   ASSERT_GE(listener->slowdown_count, kSlowdownTrigger * 9);
@@ -880,10 +882,66 @@ TEST_F(EventListenerTest, BackgroundErrorListenerFailedCompactionTest) {
   ASSERT_EQ(1, listener->counter());
 
   // trigger flush so compaction is triggered again; this time it succeeds
+  // The previous failed compaction may get retried automatically, so we may
+  // be left with 0 or 1 files in level 1, depending on when the retry gets
+  // scheduled
   ASSERT_OK(Put("key0", "val"));
   ASSERT_OK(dbfull()->TEST_WaitForFlushMemTable());
   ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+  ASSERT_LE(1, NumTableFilesAtLevel(0));
+}
+
+class TestFileOperationListener : public EventListener {
+ public:
+  TestFileOperationListener() {
+    file_reads_.store(0);
+    file_reads_success_.store(0);
+    file_writes_.store(0);
+    file_writes_success_.store(0);
+  }
+
+  void OnFileReadFinish(const FileOperationInfo& info) override {
+    ++file_reads_;
+    if (info.status.ok()) {
+      ++file_reads_success_;
+    }
+  }
+
+  void OnFileWriteFinish(const FileOperationInfo& info) override {
+    ++file_writes_;
+    if (info.status.ok()) {
+      ++file_writes_success_;
+    }
+  }
+
+  bool ShouldBeNotifiedOnFileIO() override { return true; }
+
+  std::atomic<size_t> file_reads_;
+  std::atomic<size_t> file_reads_success_;
+  std::atomic<size_t> file_writes_;
+  std::atomic<size_t> file_writes_success_;
+};
+
+TEST_F(EventListenerTest, OnFileOperationTest) {
+  Options options;
+  options.env = CurrentOptions().env;
+  options.create_if_missing = true;
+
+  TestFileOperationListener* listener = new TestFileOperationListener();
+  options.listeners.emplace_back(listener);
+
+  DestroyAndReopen(options);
+  ASSERT_OK(Put("foo", "aaa"));
+  dbfull()->Flush(FlushOptions());
+  dbfull()->TEST_WaitForFlushMemTable();
+  ASSERT_GE(listener->file_writes_.load(),
+            listener->file_writes_success_.load());
+  ASSERT_GT(listener->file_writes_.load(), 0);
+  Close();
+
+  Reopen(options);
+  ASSERT_GE(listener->file_reads_.load(), listener->file_reads_success_.load());
+  ASSERT_GT(listener->file_reads_.load(), 0);
 }
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/db/log_format.h b/3rdParty/rocksdb/v5.18.X/db/log_format.h
similarity index 88%
rename from 3rdParty/rocksdb/v5.16.X/db/log_format.h
rename to 3rdParty/rocksdb/v5.18.X/db/log_format.h
index be22201af0..5aeb5aa5fd 100644
--- a/3rdParty/rocksdb/v5.16.X/db/log_format.h
+++ b/3rdParty/rocksdb/v5.18.X/db/log_format.h
@@ -37,9 +37,9 @@ static const unsigned int kBlockSize = 32768;
 // Header is checksum (4 bytes), length (2 bytes), type (1 byte)
 static const int kHeaderSize = 4 + 2 + 1;
 
-// Recyclable header is checksum (4 bytes), type (1 byte), log number
-// (4 bytes), length (2 bytes).
-static const int kRecyclableHeaderSize = 4 + 1 + 4 + 2;
+// Recyclable header is checksum (4 bytes), length (2 bytes), type (1 byte),
+// log number (4 bytes).
+static const int kRecyclableHeaderSize = 4 + 2 + 1 + 4;
 
 }  // namespace log
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/db/log_reader.cc b/3rdParty/rocksdb/v5.18.X/db/log_reader.cc
similarity index 86%
rename from 3rdParty/rocksdb/v5.16.X/db/log_reader.cc
rename to 3rdParty/rocksdb/v5.18.X/db/log_reader.cc
index 0db96a75c0..2c57cde5d5 100644
--- a/3rdParty/rocksdb/v5.16.X/db/log_reader.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/log_reader.cc
@@ -23,8 +23,9 @@ Reader::Reporter::~Reporter() {
 }
 
 Reader::Reader(std::shared_ptr<Logger> info_log,
-               unique_ptr<SequentialFileReader>&& _file, Reporter* reporter,
-               bool checksum, uint64_t initial_offset, uint64_t log_num)
+               std::unique_ptr<SequentialFileReader>&& _file,
+               Reporter* reporter, bool checksum, uint64_t log_num,
+               bool retry_after_eof)
     : info_log_(info_log),
       file_(std::move(_file)),
       reporter_(reporter),
@@ -36,37 +37,14 @@ Reader::Reader(std::shared_ptr<Logger> info_log,
       eof_offset_(0),
       last_record_offset_(0),
       end_of_buffer_offset_(0),
-      initial_offset_(initial_offset),
       log_number_(log_num),
-      recycled_(false) {}
+      recycled_(false),
+      retry_after_eof_(retry_after_eof) {}
 
 Reader::~Reader() {
   delete[] backing_store_;
 }
 
-bool Reader::SkipToInitialBlock() {
-  size_t initial_offset_in_block = initial_offset_ % kBlockSize;
-  uint64_t block_start_location = initial_offset_ - initial_offset_in_block;
-
-  // Don't search a block if we'd be in the trailer
-  if (initial_offset_in_block > kBlockSize - 6) {
-    block_start_location += kBlockSize;
-  }
-
-  end_of_buffer_offset_ = block_start_location;
-
-  // Skip to start of first block that can contain the initial record
-  if (block_start_location > 0) {
-    Status skip_status = file_->Skip(block_start_location);
-    if (!skip_status.ok()) {
-      ReportDrop(static_cast<size_t>(block_start_location), skip_status);
-      return false;
-    }
-  }
-
-  return true;
-}
-
 // For kAbsoluteConsistency, on clean shutdown we don't expect any error
 // in the log files.  For other modes, we can ignore only incomplete records
 // in the last log file, which are presumably due to a write in progress
@@ -76,12 +54,6 @@ bool Reader::SkipToInitialBlock() {
 // restrict the inconsistency to only the last log
 bool Reader::ReadRecord(Slice* record, std::string* scratch,
                         WALRecoveryMode wal_recovery_mode) {
-  if (last_record_offset_ < initial_offset_) {
-    if (!SkipToInitialBlock()) {
-      return false;
-    }
-  }
-
   scratch->clear();
   record->clear();
   bool in_fragmented_record = false;
@@ -152,7 +124,7 @@ bool Reader::ReadRecord(Slice* record, std::string* scratch,
           // in clean shutdown we don't expect any error in the log files
           ReportCorruption(drop_size, "truncated header");
         }
-	FALLTHROUGH_INTENDED;
+        FALLTHROUGH_INTENDED;
 
       case kEof:
         if (in_fragmented_record) {
@@ -182,7 +154,7 @@ bool Reader::ReadRecord(Slice* record, std::string* scratch,
           }
           return false;
         }
-	FALLTHROUGH_INTENDED;
+        FALLTHROUGH_INTENDED;
 
       case kBadRecord:
         if (in_fragmented_record) {
@@ -238,7 +210,8 @@ void Reader::UnmarkEOF() {
 
   eof_ = false;
 
-  if (eof_offset_ == 0) {
+  // If retry_after_eof_ is true, we have to proceed to read anyway.
+  if (!retry_after_eof_ && eof_offset_ == 0) {
     return;
   }
 
@@ -299,8 +272,7 @@ void Reader::ReportCorruption(size_t bytes, const char* reason) {
 }
 
 void Reader::ReportDrop(size_t bytes, const Status& reason) {
-  if (reporter_ != nullptr &&
-      end_of_buffer_offset_ - buffer_.size() - bytes >= initial_offset_) {
+  if (reporter_ != nullptr) {
     reporter_->Corruption(bytes, reason);
   }
 }
@@ -317,11 +289,15 @@ bool Reader::ReadMore(size_t* drop_size, int *error) {
       read_error_ = true;
       *error = kEof;
       return false;
-    } else if (buffer_.size() < (size_t)kBlockSize) {
+    } else if (buffer_.size() < static_cast<size_t>(kBlockSize)) {
       eof_ = true;
       eof_offset_ = buffer_.size();
+      TEST_SYNC_POINT("LogReader::ReadMore:FirstEOF");
     }
     return true;
+  } else if (retry_after_eof_ && !read_error_) {
+    UnmarkEOF();
+    return !read_error_;
   } else {
     // Note that if buffer_ is non-empty, we have a truncated header at the
     //  end of the file, which can be caused by the writer crashing in the
@@ -342,8 +318,11 @@ bool Reader::ReadMore(size_t* drop_size, int *error) {
 unsigned int Reader::ReadPhysicalRecord(Slice* result, size_t* drop_size) {
   while (true) {
     // We need at least the minimum header size
-    if (buffer_.size() < (size_t)kHeaderSize) {
-      int r;
+    if (buffer_.size() < static_cast<size_t>(kHeaderSize)) {
+      // the default value of r is meaningless because ReadMore will overwrite
+      // it if it returns false; in case it returns true, the return value will
+      // not be used anyway
+      int r = kEof;
       if (!ReadMore(drop_size, &r)) {
         return r;
       }
@@ -363,8 +342,8 @@ unsigned int Reader::ReadPhysicalRecord(Slice* result, size_t* drop_size) {
       }
       header_size = kRecyclableHeaderSize;
       // We need enough for the larger header
-      if (buffer_.size() < (size_t)kRecyclableHeaderSize) {
-        int r;
+      if (buffer_.size() < static_cast<size_t>(kRecyclableHeaderSize)) {
+        int r = kEof;
         if (!ReadMore(drop_size, &r)) {
           return r;
         }
@@ -376,16 +355,24 @@ unsigned int Reader::ReadPhysicalRecord(Slice* result, size_t* drop_size) {
       }
     }
     if (header_size + length > buffer_.size()) {
-      *drop_size = buffer_.size();
-      buffer_.clear();
-      if (!eof_) {
-        return kBadRecordLen;
-      }
-      // If the end of the file has been reached without reading |length| bytes
-      // of payload, assume the writer died in the middle of writing the record.
-      // Don't report a corruption unless requested.
-      if (*drop_size) {
-        return kBadHeader;
+      if (!retry_after_eof_) {
+        *drop_size = buffer_.size();
+        buffer_.clear();
+        if (!eof_) {
+          return kBadRecordLen;
+        }
+        // If the end of the file has been reached without reading |length|
+        // bytes of payload, assume the writer died in the middle of writing the
+        // record. Don't report a corruption unless requested.
+        if (*drop_size) {
+          return kBadHeader;
+        }
+      } else {
+        int r = kEof;
+        if (!ReadMore(drop_size, &r)) {
+          return r;
+        }
+        continue;
       }
       return kEof;
     }
@@ -417,13 +404,6 @@ unsigned int Reader::ReadPhysicalRecord(Slice* result, size_t* drop_size) {
 
     buffer_.remove_prefix(header_size + length);
 
-    // Skip physical record that started before initial_offset_
-    if (end_of_buffer_offset_ - buffer_.size() - header_size - length <
-        initial_offset_) {
-      result->clear();
-      return kBadRecord;
-    }
-
     *result = Slice(header + header_size, length);
     return type;
   }
diff --git a/3rdParty/rocksdb/v5.16.X/db/log_reader.h b/3rdParty/rocksdb/v5.18.X/db/log_reader.h
similarity index 87%
rename from 3rdParty/rocksdb/v5.16.X/db/log_reader.h
rename to 3rdParty/rocksdb/v5.18.X/db/log_reader.h
index 44db677029..2c4f4f0599 100644
--- a/3rdParty/rocksdb/v5.16.X/db/log_reader.h
+++ b/3rdParty/rocksdb/v5.18.X/db/log_reader.h
@@ -50,14 +50,10 @@ class Reader {
   // live while this Reader is in use.
   //
   // If "checksum" is true, verify checksums if available.
-  //
-  // The Reader will start reading at the first record located at physical
-  // position >= initial_offset within the file.
   Reader(std::shared_ptr<Logger> info_log,
-  // @lint-ignore TXT2 T25377293 Grandfathered in
-	 unique_ptr<SequentialFileReader>&& file,
-         Reporter* reporter, bool checksum, uint64_t initial_offset,
-         uint64_t log_num);
+         // @lint-ignore TXT2 T25377293 Grandfathered in
+         std::unique_ptr<SequentialFileReader>&& file, Reporter* reporter,
+         bool checksum, uint64_t log_num, bool retry_after_eof);
 
   ~Reader();
 
@@ -91,7 +87,7 @@ class Reader {
 
  private:
   std::shared_ptr<Logger> info_log_;
-  const unique_ptr<SequentialFileReader> file_;
+  const std::unique_ptr<SequentialFileReader> file_;
   Reporter* const reporter_;
   bool const checksum_;
   char* const backing_store_;
@@ -108,15 +104,17 @@ class Reader {
   // Offset of the first location past the end of buffer_.
   uint64_t end_of_buffer_offset_;
 
-  // Offset at which to start looking for the first record to return
-  uint64_t const initial_offset_;
-
   // which log number this is
   uint64_t const log_number_;
 
   // Whether this is a recycled log file
   bool recycled_;
 
+  // Whether retry after encountering EOF
+  // TODO (yanqin) add support for retry policy, e.g. sleep, max retry limit,
+  // etc.
+  const bool retry_after_eof_;
+
   // Extend record types with the following special values
   enum {
     kEof = kMaxRecordType + 1,
@@ -124,7 +122,6 @@ class Reader {
     // Currently there are three situations in which this happens:
     // * The record has an invalid CRC (ReadPhysicalRecord reports a drop)
     // * The record is a 0-length record (No drop is reported)
-    // * The record is below constructor's initial_offset (No drop is reported)
     kBadRecord = kMaxRecordType + 2,
     // Returned when we fail to read a valid header.
     kBadHeader = kMaxRecordType + 3,
@@ -136,11 +133,6 @@ class Reader {
     kBadRecordChecksum = kMaxRecordType + 6,
   };
 
-  // Skips all blocks that are completely before "initial_offset_".
-  //
-  // Returns true on success. Handles reporting.
-  bool SkipToInitialBlock();
-
   // Return type, or one of the preceding special values
   unsigned int ReadPhysicalRecord(Slice* result, size_t* drop_size);
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/log_test.cc b/3rdParty/rocksdb/v5.18.X/db/log_test.cc
similarity index 75%
rename from 3rdParty/rocksdb/v5.16.X/db/log_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/log_test.cc
index 992851fe26..9e8148f653 100644
--- a/3rdParty/rocksdb/v5.16.X/db/log_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/log_test.cc
@@ -145,8 +145,8 @@ class LogTest : public ::testing::TestWithParam<int> {
   }
 
   Slice reader_contents_;
-  unique_ptr<WritableFileWriter> dest_holder_;
-  unique_ptr<SequentialFileReader> source_holder_;
+  std::unique_ptr<WritableFileWriter> dest_holder_;
+  std::unique_ptr<SequentialFileReader> source_holder_;
   ReportCollector report_;
   Writer writer_;
   Reader reader_;
@@ -159,12 +159,13 @@ class LogTest : public ::testing::TestWithParam<int> {
   LogTest()
       : reader_contents_(),
         dest_holder_(test::GetWritableFileWriter(
-            new test::StringSink(&reader_contents_))),
+            new test::StringSink(&reader_contents_), "" /* don't care */)),
         source_holder_(test::GetSequentialFileReader(
             new StringSource(reader_contents_), "" /* file name */)),
         writer_(std::move(dest_holder_), 123, GetParam()),
-        reader_(nullptr, std::move(source_holder_), &report_, true /*checksum*/,
-                0 /*initial_offset*/, 123) {
+        reader_(nullptr, std::move(source_holder_), &report_,
+                true /* checksum */, 123 /* log_number */,
+                false /* retry_after_eof */) {
     int header_size = GetParam() ? kRecyclableHeaderSize : kHeaderSize;
     initial_offset_last_record_offsets_[0] = 0;
     initial_offset_last_record_offsets_[1] = header_size + 10000;
@@ -266,36 +267,6 @@ class LogTest : public ::testing::TestWithParam<int> {
     }
   }
 
-  void CheckOffsetPastEndReturnsNoRecords(uint64_t offset_past_end) {
-    WriteInitialOffsetLog();
-    unique_ptr<SequentialFileReader> file_reader(test::GetSequentialFileReader(
-        new StringSource(reader_contents_), "" /* fname */));
-    unique_ptr<Reader> offset_reader(
-        new Reader(nullptr, std::move(file_reader), &report_,
-                   true /*checksum*/, WrittenBytes() + offset_past_end, 123));
-    Slice record;
-    std::string scratch;
-    ASSERT_TRUE(!offset_reader->ReadRecord(&record, &scratch));
-  }
-
-  void CheckInitialOffsetRecord(uint64_t initial_offset,
-                                int expected_record_offset) {
-    WriteInitialOffsetLog();
-    unique_ptr<SequentialFileReader> file_reader(test::GetSequentialFileReader(
-        new StringSource(reader_contents_), "" /* fname */));
-    unique_ptr<Reader> offset_reader(
-        new Reader(nullptr, std::move(file_reader), &report_,
-                   true /*checksum*/, initial_offset, 123));
-    Slice record;
-    std::string scratch;
-    ASSERT_TRUE(offset_reader->ReadRecord(&record, &scratch));
-    ASSERT_EQ(initial_offset_record_sizes_[expected_record_offset],
-              record.size());
-    ASSERT_EQ(initial_offset_last_record_offsets_[expected_record_offset],
-              offset_reader->LastRecordOffset());
-    ASSERT_EQ((char)('a' + expected_record_offset), record.data()[0]);
-  }
-
 };
 
 size_t LogTest::initial_offset_record_sizes_[] =
@@ -590,55 +561,6 @@ TEST_P(LogTest, ErrorJoinsRecords) {
   }
 }
 
-TEST_P(LogTest, ReadStart) { CheckInitialOffsetRecord(0, 0); }
-
-TEST_P(LogTest, ReadSecondOneOff) { CheckInitialOffsetRecord(1, 1); }
-
-TEST_P(LogTest, ReadSecondTenThousand) { CheckInitialOffsetRecord(10000, 1); }
-
-TEST_P(LogTest, ReadSecondStart) {
-  int header_size = GetParam() ? kRecyclableHeaderSize : kHeaderSize;
-  CheckInitialOffsetRecord(10000 + header_size, 1);
-}
-
-TEST_P(LogTest, ReadThirdOneOff) {
-  int header_size = GetParam() ? kRecyclableHeaderSize : kHeaderSize;
-  CheckInitialOffsetRecord(10000 + header_size + 1, 2);
-}
-
-TEST_P(LogTest, ReadThirdStart) {
-  int header_size = GetParam() ? kRecyclableHeaderSize : kHeaderSize;
-  CheckInitialOffsetRecord(20000 + 2 * header_size, 2);
-}
-
-TEST_P(LogTest, ReadFourthOneOff) {
-  int header_size = GetParam() ? kRecyclableHeaderSize : kHeaderSize;
-  CheckInitialOffsetRecord(20000 + 2 * header_size + 1, 3);
-}
-
-TEST_P(LogTest, ReadFourthFirstBlockTrailer) {
-  CheckInitialOffsetRecord(log::kBlockSize - 4, 3);
-}
-
-TEST_P(LogTest, ReadFourthMiddleBlock) {
-  CheckInitialOffsetRecord(log::kBlockSize + 1, 3);
-}
-
-TEST_P(LogTest, ReadFourthLastBlock) {
-  CheckInitialOffsetRecord(2 * log::kBlockSize + 1, 3);
-}
-
-TEST_P(LogTest, ReadFourthStart) {
-  int header_size = GetParam() ? kRecyclableHeaderSize : kHeaderSize;
-  CheckInitialOffsetRecord(
-      2 * (header_size + 1000) + (2 * log::kBlockSize - 1000) + 3 * header_size,
-      3);
-}
-
-TEST_P(LogTest, ReadEnd) { CheckOffsetPastEndReturnsNoRecords(0); }
-
-TEST_P(LogTest, ReadPastEnd) { CheckOffsetPastEndReturnsNoRecords(5); }
-
 TEST_P(LogTest, ClearEofSingleBlock) {
   Write("foo");
   Write("bar");
@@ -717,8 +639,9 @@ TEST_P(LogTest, Recycle) {
   while (get_reader_contents()->size() < log::kBlockSize * 2) {
     Write("xxxxxxxxxxxxxxxx");
   }
-  unique_ptr<WritableFileWriter> dest_holder(test::GetWritableFileWriter(
-      new test::OverwritingStringSink(get_reader_contents())));
+  std::unique_ptr<WritableFileWriter> dest_holder(test::GetWritableFileWriter(
+      new test::OverwritingStringSink(get_reader_contents()),
+      "" /* don't care */));
   Writer recycle_writer(std::move(dest_holder), 123, true);
   recycle_writer.AddRecord(Slice("foooo"));
   recycle_writer.AddRecord(Slice("bar"));
@@ -730,6 +653,177 @@ TEST_P(LogTest, Recycle) {
 
 INSTANTIATE_TEST_CASE_P(bool, LogTest, ::testing::Values(0, 2));
 
+class RetriableLogTest : public ::testing::TestWithParam<int> {
+ private:
+  class ReportCollector : public Reader::Reporter {
+   public:
+    size_t dropped_bytes_;
+    std::string message_;
+
+    ReportCollector() : dropped_bytes_(0) {}
+    virtual void Corruption(size_t bytes, const Status& status) override {
+      dropped_bytes_ += bytes;
+      message_.append(status.ToString());
+    }
+  };
+
+  Slice contents_;
+  std::unique_ptr<WritableFileWriter> dest_holder_;
+  std::unique_ptr<Writer> log_writer_;
+  Env* env_;
+  EnvOptions env_options_;
+  const std::string test_dir_;
+  const std::string log_file_;
+  std::unique_ptr<WritableFileWriter> writer_;
+  std::unique_ptr<SequentialFileReader> reader_;
+  ReportCollector report_;
+  std::unique_ptr<Reader> log_reader_;
+
+ public:
+  RetriableLogTest()
+      : contents_(),
+        dest_holder_(nullptr),
+        log_writer_(nullptr),
+        env_(Env::Default()),
+        test_dir_(test::PerThreadDBPath("retriable_log_test")),
+        log_file_(test_dir_ + "/log"),
+        writer_(nullptr),
+        reader_(nullptr),
+        log_reader_(nullptr) {}
+
+  Status SetupTestEnv() {
+    dest_holder_.reset(test::GetWritableFileWriter(
+        new test::StringSink(&contents_), "" /* file name */));
+    assert(dest_holder_ != nullptr);
+    log_writer_.reset(new Writer(std::move(dest_holder_), 123, GetParam()));
+    assert(log_writer_ != nullptr);
+
+    Status s;
+    s = env_->CreateDirIfMissing(test_dir_);
+    std::unique_ptr<WritableFile> writable_file;
+    if (s.ok()) {
+      s = env_->NewWritableFile(log_file_, &writable_file, env_options_);
+    }
+    if (s.ok()) {
+      writer_.reset(new WritableFileWriter(std::move(writable_file), log_file_,
+                                           env_options_));
+      assert(writer_ != nullptr);
+    }
+    std::unique_ptr<SequentialFile> seq_file;
+    if (s.ok()) {
+      s = env_->NewSequentialFile(log_file_, &seq_file, env_options_);
+    }
+    if (s.ok()) {
+      reader_.reset(new SequentialFileReader(std::move(seq_file), log_file_));
+      assert(reader_ != nullptr);
+      log_reader_.reset(new Reader(nullptr, std::move(reader_), &report_,
+                                   true /* checksum */, 123 /* log_number */,
+                                   true /* retry_after_eof */));
+      assert(log_reader_ != nullptr);
+    }
+    return s;
+  }
+
+  std::string contents() {
+    auto file =
+        dynamic_cast<test::StringSink*>(log_writer_->file()->writable_file());
+    assert(file != nullptr);
+    return file->contents_;
+  }
+
+  void Encode(const std::string& msg) { log_writer_->AddRecord(Slice(msg)); }
+
+  void Write(const Slice& data) {
+    writer_->Append(data);
+    writer_->Sync(true);
+  }
+
+  std::string Read() {
+    auto wal_recovery_mode = WALRecoveryMode::kTolerateCorruptedTailRecords;
+    std::string scratch;
+    Slice record;
+    if (log_reader_->ReadRecord(&record, &scratch, wal_recovery_mode)) {
+      return record.ToString();
+    } else {
+      return "Read error";
+    }
+  }
+};
+
+TEST_P(RetriableLogTest, TailLog_PartialHeader) {
+  ASSERT_OK(SetupTestEnv());
+  std::vector<int> remaining_bytes_in_last_record;
+  size_t header_size = GetParam() ? kRecyclableHeaderSize : kHeaderSize;
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"RetriableLogTest::TailLog:AfterPart1",
+        "RetriableLogTest::TailLog:BeforeReadRecord"},
+       {"LogReader::ReadMore:FirstEOF",
+        "RetriableLogTest::TailLog:BeforePart2"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  size_t delta = header_size - 1;
+  port::Thread log_writer_thread([&]() {
+    size_t old_sz = contents().size();
+    Encode("foo");
+    size_t new_sz = contents().size();
+    std::string part1 = contents().substr(old_sz, delta);
+    std::string part2 =
+        contents().substr(old_sz + delta, new_sz - old_sz - delta);
+    Write(Slice(part1));
+    TEST_SYNC_POINT("RetriableLogTest::TailLog:AfterPart1");
+    TEST_SYNC_POINT("RetriableLogTest::TailLog:BeforePart2");
+    Write(Slice(part2));
+  });
+
+  std::string record;
+  port::Thread log_reader_thread([&]() {
+    TEST_SYNC_POINT("RetriableLogTest::TailLog:BeforeReadRecord");
+    record = Read();
+  });
+  log_reader_thread.join();
+  log_writer_thread.join();
+  ASSERT_EQ("foo", record);
+}
+
+TEST_P(RetriableLogTest, TailLog_FullHeader) {
+  ASSERT_OK(SetupTestEnv());
+  std::vector<int> remaining_bytes_in_last_record;
+  size_t header_size = GetParam() ? kRecyclableHeaderSize : kHeaderSize;
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->LoadDependency(
+      {{"RetriableLogTest::TailLog:AfterPart1",
+        "RetriableLogTest::TailLog:BeforeReadRecord"},
+       {"LogReader::ReadMore:FirstEOF",
+        "RetriableLogTest::TailLog:BeforePart2"}});
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  size_t delta = header_size + 1;
+  port::Thread log_writer_thread([&]() {
+    size_t old_sz = contents().size();
+    Encode("foo");
+    size_t new_sz = contents().size();
+    std::string part1 = contents().substr(old_sz, delta);
+    std::string part2 =
+        contents().substr(old_sz + delta, new_sz - old_sz - delta);
+    Write(Slice(part1));
+    TEST_SYNC_POINT("RetriableLogTest::TailLog:AfterPart1");
+    TEST_SYNC_POINT("RetriableLogTest::TailLog:BeforePart2");
+    Write(Slice(part2));
+  });
+
+  std::string record;
+  port::Thread log_reader_thread([&]() {
+    TEST_SYNC_POINT("RetriableLogTest::TailLog:BeforeReadRecord");
+    record = Read();
+  });
+  log_reader_thread.join();
+  log_writer_thread.join();
+  ASSERT_EQ("foo", record);
+}
+
+INSTANTIATE_TEST_CASE_P(bool, RetriableLogTest, ::testing::Values(0, 2));
+
 }  // namespace log
 }  // namespace rocksdb
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/log_writer.cc b/3rdParty/rocksdb/v5.18.X/db/log_writer.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/log_writer.cc
rename to 3rdParty/rocksdb/v5.18.X/db/log_writer.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/log_writer.h b/3rdParty/rocksdb/v5.18.X/db/log_writer.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/log_writer.h
rename to 3rdParty/rocksdb/v5.18.X/db/log_writer.h
index abd7977b94..dea5033872 100644
--- a/3rdParty/rocksdb/v5.16.X/db/log_writer.h
+++ b/3rdParty/rocksdb/v5.18.X/db/log_writer.h
@@ -88,7 +88,7 @@ class Writer {
   bool TEST_BufferIsEmpty();
 
  private:
-  unique_ptr<WritableFileWriter> dest_;
+  std::unique_ptr<WritableFileWriter> dest_;
   size_t block_offset_;       // Current offset in block
   uint64_t log_number_;
   bool recycle_log_files_;
diff --git a/3rdParty/rocksdb/v5.16.X/db/logs_with_prep_tracker.cc b/3rdParty/rocksdb/v5.18.X/db/logs_with_prep_tracker.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/logs_with_prep_tracker.cc
rename to 3rdParty/rocksdb/v5.18.X/db/logs_with_prep_tracker.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/logs_with_prep_tracker.h b/3rdParty/rocksdb/v5.18.X/db/logs_with_prep_tracker.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/logs_with_prep_tracker.h
rename to 3rdParty/rocksdb/v5.18.X/db/logs_with_prep_tracker.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/malloc_stats.cc b/3rdParty/rocksdb/v5.18.X/db/malloc_stats.cc
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/db/malloc_stats.cc
rename to 3rdParty/rocksdb/v5.18.X/db/malloc_stats.cc
index 02e8950386..ba971b547e 100644
--- a/3rdParty/rocksdb/v5.16.X/db/malloc_stats.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/malloc_stats.cc
@@ -18,9 +18,11 @@ namespace rocksdb {
 #ifdef ROCKSDB_JEMALLOC
 #ifdef __FreeBSD__
 #include <malloc_np.h>
-#define je_malloc_stats_print malloc_stats_print
 #else
 #include "jemalloc/jemalloc.h"
+#ifdef JEMALLOC_NO_RENAME
+#define malloc_stats_print je_malloc_stats_print
+#endif
 #endif
 
 typedef struct {
@@ -48,7 +50,7 @@ void DumpMallocStats(std::string* stats) {
   std::unique_ptr<char[]> buf{new char[kMallocStatusLen + 1]};
   mstat.cur = buf.get();
   mstat.end = buf.get() + kMallocStatusLen;
-  je_malloc_stats_print(GetJemallocStatus, &mstat, "");
+  malloc_stats_print(GetJemallocStatus, &mstat, "");
   stats->append(buf.get());
 }
 #else
diff --git a/3rdParty/rocksdb/v5.16.X/db/malloc_stats.h b/3rdParty/rocksdb/v5.18.X/db/malloc_stats.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/malloc_stats.h
rename to 3rdParty/rocksdb/v5.18.X/db/malloc_stats.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/manual_compaction_test.cc b/3rdParty/rocksdb/v5.18.X/db/manual_compaction_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/manual_compaction_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/manual_compaction_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/memtable.cc b/3rdParty/rocksdb/v5.18.X/db/memtable.cc
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/db/memtable.cc
rename to 3rdParty/rocksdb/v5.18.X/db/memtable.cc
index 70e6d9da52..51b54d6368 100644
--- a/3rdParty/rocksdb/v5.16.X/db/memtable.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/memtable.cc
@@ -17,6 +17,7 @@
 #include "db/merge_context.h"
 #include "db/merge_helper.h"
 #include "db/pinned_iterators_manager.h"
+#include "db/range_tombstone_fragmenter.h"
 #include "db/read_callback.h"
 #include "monitoring/perf_context_imp.h"
 #include "monitoring/statistics.h"
@@ -68,12 +69,13 @@ MemTable::MemTable(const InternalKeyComparator& cmp,
       refs_(0),
       kArenaBlockSize(OptimizeBlockSize(moptions_.arena_block_size)),
       mem_tracker_(write_buffer_manager),
-      arena_(
-          moptions_.arena_block_size,
-          (write_buffer_manager != nullptr && write_buffer_manager->enabled())
-              ? &mem_tracker_
-              : nullptr,
-          mutable_cf_options.memtable_huge_page_size),
+      arena_(moptions_.arena_block_size,
+             (write_buffer_manager != nullptr &&
+              (write_buffer_manager->enabled() ||
+               write_buffer_manager->cost_to_cache()))
+                 ? &mem_tracker_
+                 : nullptr,
+             mutable_cf_options.memtable_huge_page_size),
       table_(ioptions.memtable_factory->CreateMemTableRep(
           comparator_, &arena_, mutable_cf_options.prefix_extractor.get(),
           ioptions.info_log, column_family_id)),
@@ -101,7 +103,8 @@ MemTable::MemTable(const InternalKeyComparator& cmp,
       env_(ioptions.env),
       insert_with_hint_prefix_extractor_(
           ioptions.memtable_insert_with_hint_prefix_extractor),
-      oldest_key_time_(std::numeric_limits<uint64_t>::max()) {
+      oldest_key_time_(std::numeric_limits<uint64_t>::max()),
+      atomic_flush_seqno_(kMaxSequenceNumber) {
   UpdateFlushState();
   // something went wrong if we need to flush before inserting anything
   assert(!ShouldScheduleFlush());
@@ -409,13 +412,24 @@ InternalIterator* MemTable::NewIterator(const ReadOptions& read_options,
   return new (mem) MemTableIterator(*this, read_options, arena);
 }
 
-InternalIterator* MemTable::NewRangeTombstoneIterator(
-    const ReadOptions& read_options) {
+FragmentedRangeTombstoneIterator* MemTable::NewRangeTombstoneIterator(
+    const ReadOptions& read_options, SequenceNumber read_seq) {
   if (read_options.ignore_range_deletions || is_range_del_table_empty_) {
     return nullptr;
   }
-  return new MemTableIterator(*this, read_options, nullptr /* arena */,
-                              true /* use_range_del_table */);
+  auto* unfragmented_iter = new MemTableIterator(
+      *this, read_options, nullptr /* arena */, true /* use_range_del_table */);
+  if (unfragmented_iter == nullptr) {
+    return nullptr;
+  }
+  auto fragmented_tombstone_list =
+      std::make_shared<FragmentedRangeTombstoneList>(
+          std::unique_ptr<InternalIterator>(unfragmented_iter),
+          comparator_.comparator);
+
+  auto* fragmented_iter = new FragmentedRangeTombstoneIterator(
+      fragmented_tombstone_list, comparator_.comparator, read_seq);
+  return fragmented_iter;
 }
 
 port::RWMutex* MemTable::GetLock(const Slice& key) {
@@ -569,7 +583,7 @@ struct Saver {
   const MergeOperator* merge_operator;
   // the merge operations encountered;
   MergeContext* merge_context;
-  RangeDelAggregator* range_del_agg;
+  SequenceNumber max_covering_tombstone_seq;
   MemTable* mem;
   Logger* logger;
   Statistics* statistics;
@@ -591,10 +605,10 @@ static bool SaveValue(void* arg, const char* entry) {
   Saver* s = reinterpret_cast<Saver*>(arg);
   assert(s != nullptr);
   MergeContext* merge_context = s->merge_context;
-  RangeDelAggregator* range_del_agg = s->range_del_agg;
+  SequenceNumber max_covering_tombstone_seq = s->max_covering_tombstone_seq;
   const MergeOperator* merge_operator = s->merge_operator;
 
-  assert(merge_context != nullptr && range_del_agg != nullptr);
+  assert(merge_context != nullptr);
 
   // entry format is:
   //    klength  varint32
@@ -622,7 +636,7 @@ static bool SaveValue(void* arg, const char* entry) {
     s->seq = seq;
 
     if ((type == kTypeValue || type == kTypeMerge || type == kTypeBlobIndex) &&
-        range_del_agg->ShouldDelete(Slice(key_ptr, key_length))) {
+        max_covering_tombstone_seq > seq) {
       type = kTypeRangeDeletion;
     }
     switch (type) {
@@ -640,7 +654,7 @@ static bool SaveValue(void* arg, const char* entry) {
           *(s->found_final_value) = true;
           return false;
         }
-	FALLTHROUGH_INTENDED;
+        FALLTHROUGH_INTENDED;
       case kTypeValue: {
         if (s->inplace_update_support) {
           s->mem->GetLock(s->key->user_key())->ReadLock();
@@ -719,9 +733,9 @@ static bool SaveValue(void* arg, const char* entry) {
 
 bool MemTable::Get(const LookupKey& key, std::string* value, Status* s,
                    MergeContext* merge_context,
-                   RangeDelAggregator* range_del_agg, SequenceNumber* seq,
-                   const ReadOptions& read_opts, ReadCallback* callback,
-                   bool* is_blob_index) {
+                   SequenceNumber* max_covering_tombstone_seq,
+                   SequenceNumber* seq, const ReadOptions& read_opts,
+                   ReadCallback* callback, bool* is_blob_index) {
   // The sequence number is updated synchronously in version_set.h
   if (IsEmpty()) {
     // Avoiding recording stats for speed.
@@ -729,12 +743,13 @@ bool MemTable::Get(const LookupKey& key, std::string* value, Status* s,
   }
   PERF_TIMER_GUARD(get_from_memtable_time);
 
-  std::unique_ptr<InternalIterator> range_del_iter(
-      NewRangeTombstoneIterator(read_opts));
-  Status status = range_del_agg->AddTombstones(std::move(range_del_iter));
-  if (!status.ok()) {
-    *s = status;
-    return false;
+  std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter(
+      NewRangeTombstoneIterator(read_opts,
+                                GetInternalKeySeqno(key.internal_key())));
+  if (range_del_iter != nullptr) {
+    *max_covering_tombstone_seq =
+        std::max(*max_covering_tombstone_seq,
+                 range_del_iter->MaxCoveringTombstoneSeqnum(key.user_key()));
   }
 
   Slice user_key = key.user_key();
@@ -761,7 +776,7 @@ bool MemTable::Get(const LookupKey& key, std::string* value, Status* s,
     saver.seq = kMaxSequenceNumber;
     saver.mem = this;
     saver.merge_context = merge_context;
-    saver.range_del_agg = range_del_agg;
+    saver.max_covering_tombstone_seq = *max_covering_tombstone_seq;
     saver.merge_operator = moptions_.merge_operator;
     saver.logger = moptions_.info_log;
     saver.inplace_update_support = moptions_.inplace_update_support;
diff --git a/3rdParty/rocksdb/v5.16.X/db/memtable.h b/3rdParty/rocksdb/v5.18.X/db/memtable.h
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/db/memtable.h
rename to 3rdParty/rocksdb/v5.18.X/db/memtable.h
index f1dbb70120..aac09af401 100644
--- a/3rdParty/rocksdb/v5.16.X/db/memtable.h
+++ b/3rdParty/rocksdb/v5.18.X/db/memtable.h
@@ -16,7 +16,7 @@
 #include <unordered_map>
 #include <vector>
 #include "db/dbformat.h"
-#include "db/range_del_aggregator.h"
+#include "db/range_tombstone_fragmenter.h"
 #include "db/read_callback.h"
 #include "db/version_edit.h"
 #include "monitoring/instrumented_mutex.h"
@@ -158,7 +158,8 @@ class MemTable {
   //        those allocated in arena.
   InternalIterator* NewIterator(const ReadOptions& read_options, Arena* arena);
 
-  InternalIterator* NewRangeTombstoneIterator(const ReadOptions& read_options);
+  FragmentedRangeTombstoneIterator* NewRangeTombstoneIterator(
+      const ReadOptions& read_options, SequenceNumber read_seq);
 
   // Add an entry into memtable that maps key to value at the
   // specified sequence number and with the specified type.
@@ -187,17 +188,19 @@ class MemTable {
   // On success, *s may be set to OK, NotFound, or MergeInProgress.  Any other
   // status returned indicates a corruption or other unexpected error.
   bool Get(const LookupKey& key, std::string* value, Status* s,
-           MergeContext* merge_context, RangeDelAggregator* range_del_agg,
-           SequenceNumber* seq, const ReadOptions& read_opts,
-           ReadCallback* callback = nullptr, bool* is_blob_index = nullptr);
+           MergeContext* merge_context,
+           SequenceNumber* max_covering_tombstone_seq, SequenceNumber* seq,
+           const ReadOptions& read_opts, ReadCallback* callback = nullptr,
+           bool* is_blob_index = nullptr);
 
   bool Get(const LookupKey& key, std::string* value, Status* s,
-           MergeContext* merge_context, RangeDelAggregator* range_del_agg,
+           MergeContext* merge_context,
+           SequenceNumber* max_covering_tombstone_seq,
            const ReadOptions& read_opts, ReadCallback* callback = nullptr,
            bool* is_blob_index = nullptr) {
     SequenceNumber seq;
-    return Get(key, value, s, merge_context, range_del_agg, &seq, read_opts,
-               callback, is_blob_index);
+    return Get(key, value, s, merge_context, max_covering_tombstone_seq, &seq,
+               read_opts, callback, is_blob_index);
   }
 
   // Attempts to update the new_value inplace, else does normal Add
@@ -336,6 +339,14 @@ class MemTable {
     mem_tracker_.DoneAllocating();
   }
 
+  // Notify the underlying storage that all data it contained has been
+  // persisted.
+  // REQUIRES: external synchronization to prevent simultaneous
+  // operations on the same MemTable.
+  void MarkFlushed() {
+    table_->MarkFlushed();
+  }
+
   // return true if the current MemTableRep supports merge operator.
   bool IsMergeOperatorSupported() const {
     return table_->IsMergeOperatorSupported();
@@ -375,6 +386,14 @@ class MemTable {
 
   uint64_t GetID() const { return id_; }
 
+  SequenceNumber& TEST_AtomicFlushSequenceNumber() {
+    return atomic_flush_seqno_;
+  }
+
+  void TEST_SetFlushCompleted(bool completed) { flush_completed_ = completed; }
+
+  void TEST_SetFileNumber(uint64_t file_num) { file_number_ = file_num; }
+
  private:
   enum FlushStateEnum { FLUSH_NOT_REQUESTED, FLUSH_REQUESTED, FLUSH_SCHEDULED };
 
@@ -388,8 +407,8 @@ class MemTable {
   const size_t kArenaBlockSize;
   AllocTracker mem_tracker_;
   ConcurrentArena arena_;
-  unique_ptr<MemTableRep> table_;
-  unique_ptr<MemTableRep> range_del_table_;
+  std::unique_ptr<MemTableRep> table_;
+  std::unique_ptr<MemTableRep> range_del_table_;
   bool is_range_del_table_empty_;
 
   // Total data size of all data inserted
@@ -447,6 +466,12 @@ class MemTable {
   // Memtable id to track flush.
   uint64_t id_ = 0;
 
+  // Sequence number of the atomic flush that is responsible for this memtable.
+  // The sequence number of atomic flush is a seq, such that no writes with
+  // sequence numbers greater than or equal to seq are flushed, while all
+  // writes with sequence number smaller than seq are flushed.
+  SequenceNumber atomic_flush_seqno_;
+
   // Returns a heuristic flush decision
   bool ShouldFlushNow() const;
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/memtable_list.cc b/3rdParty/rocksdb/v5.18.X/db/memtable_list.cc
similarity index 59%
rename from 3rdParty/rocksdb/v5.16.X/db/memtable_list.cc
rename to 3rdParty/rocksdb/v5.18.X/db/memtable_list.cc
index d89e31e762..4c0af1e89f 100644
--- a/3rdParty/rocksdb/v5.16.X/db/memtable_list.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/memtable_list.cc
@@ -11,9 +11,11 @@
 
 #include <inttypes.h>
 #include <limits>
+#include <queue>
 #include <string>
 #include "db/db_impl.h"
 #include "db/memtable.h"
+#include "db/range_tombstone_fragmenter.h"
 #include "db/version_set.h"
 #include "monitoring/thread_status_util.h"
 #include "rocksdb/db.h"
@@ -103,34 +105,36 @@ int MemTableList::NumFlushed() const {
 // Operands stores the list of merge operations to apply, so far.
 bool MemTableListVersion::Get(const LookupKey& key, std::string* value,
                               Status* s, MergeContext* merge_context,
-                              RangeDelAggregator* range_del_agg,
+                              SequenceNumber* max_covering_tombstone_seq,
                               SequenceNumber* seq, const ReadOptions& read_opts,
                               ReadCallback* callback, bool* is_blob_index) {
-  return GetFromList(&memlist_, key, value, s, merge_context, range_del_agg,
-                     seq, read_opts, callback, is_blob_index);
+  return GetFromList(&memlist_, key, value, s, merge_context,
+                     max_covering_tombstone_seq, seq, read_opts, callback,
+                     is_blob_index);
 }
 
 bool MemTableListVersion::GetFromHistory(
     const LookupKey& key, std::string* value, Status* s,
-    MergeContext* merge_context, RangeDelAggregator* range_del_agg,
+    MergeContext* merge_context, SequenceNumber* max_covering_tombstone_seq,
     SequenceNumber* seq, const ReadOptions& read_opts, bool* is_blob_index) {
   return GetFromList(&memlist_history_, key, value, s, merge_context,
-                     range_del_agg, seq, read_opts, nullptr /*read_callback*/,
-                     is_blob_index);
+                     max_covering_tombstone_seq, seq, read_opts,
+                     nullptr /*read_callback*/, is_blob_index);
 }
 
 bool MemTableListVersion::GetFromList(
     std::list<MemTable*>* list, const LookupKey& key, std::string* value,
-    Status* s, MergeContext* merge_context, RangeDelAggregator* range_del_agg,
-    SequenceNumber* seq, const ReadOptions& read_opts, ReadCallback* callback,
-    bool* is_blob_index) {
+    Status* s, MergeContext* merge_context,
+    SequenceNumber* max_covering_tombstone_seq, SequenceNumber* seq,
+    const ReadOptions& read_opts, ReadCallback* callback, bool* is_blob_index) {
   *seq = kMaxSequenceNumber;
 
   for (auto& memtable : *list) {
     SequenceNumber current_seq = kMaxSequenceNumber;
 
-    bool done = memtable->Get(key, value, s, merge_context, range_del_agg,
-                              &current_seq, read_opts, callback, is_blob_index);
+    bool done =
+        memtable->Get(key, value, s, merge_context, max_covering_tombstone_seq,
+                      &current_seq, read_opts, callback, is_blob_index);
     if (*seq == kMaxSequenceNumber) {
       // Store the most recent sequence number of any operation on this key.
       // Since we only care about the most recent change, we only need to
@@ -143,7 +147,7 @@ bool MemTableListVersion::GetFromList(
     }
 
     if (done) {
-      assert(*seq != kMaxSequenceNumber);
+      assert(*seq != kMaxSequenceNumber || s->IsNotFound());
       return true;
     }
     if (!done && !s->ok() && !s->IsMergeInProgress() && !s->IsNotFound()) {
@@ -155,27 +159,14 @@ bool MemTableListVersion::GetFromList(
 
 Status MemTableListVersion::AddRangeTombstoneIterators(
     const ReadOptions& read_opts, Arena* /*arena*/,
-    RangeDelAggregator* range_del_agg) {
+    RangeDelAggregatorV2* range_del_agg) {
   assert(range_del_agg != nullptr);
   for (auto& m : memlist_) {
-    std::unique_ptr<InternalIterator> range_del_iter(
-        m->NewRangeTombstoneIterator(read_opts));
-    Status s = range_del_agg->AddTombstones(std::move(range_del_iter));
-    if (!s.ok()) {
-      return s;
-    }
-  }
-  return Status::OK();
-}
-
-Status MemTableListVersion::AddRangeTombstoneIterators(
-    const ReadOptions& read_opts,
-    std::vector<InternalIterator*>* range_del_iters) {
-  for (auto& m : memlist_) {
-    auto* range_del_iter = m->NewRangeTombstoneIterator(read_opts);
-    if (range_del_iter != nullptr) {
-      range_del_iters->push_back(range_del_iter);
-    }
+    // Using kMaxSequenceNumber is OK because these are immutable memtables.
+    std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter(
+        m->NewRangeTombstoneIterator(read_opts,
+                                     kMaxSequenceNumber /* read_seq */));
+    range_del_agg->AddTombstones(std::move(range_del_iter));
   }
   return Status::OK();
 }
@@ -248,6 +239,7 @@ void MemTableListVersion::Remove(MemTable* m,
   assert(refs_ == 1);  // only when refs_ == 1 is MemTableListVersion mutable
   memlist_.remove(m);
 
+  m->MarkFlushed();
   if (max_write_buffer_number_to_maintain_ > 0) {
     memlist_history_.push_front(m);
     TrimHistory(to_delete);
@@ -268,10 +260,232 @@ void MemTableListVersion::TrimHistory(autovector<MemTable*>* to_delete) {
   }
 }
 
+// Try to record multiple successful flush to the MANIFEST as an atomic unit.
+// This function may just return Status::OK if there has already been
+// a concurrent thread performing actual recording.
+Status MemTableList::TryInstallMemtableFlushResults(
+    autovector<MemTableList*>& imm_lists,
+    const autovector<ColumnFamilyData*>& cfds,
+    const autovector<const MutableCFOptions*>& mutable_cf_options_list,
+    const autovector<const autovector<MemTable*>*>& mems_list,
+    bool* atomic_flush_commit_in_progress, LogsWithPrepTracker* prep_tracker,
+    VersionSet* vset, InstrumentedMutex* mu,
+    const autovector<FileMetaData>& file_metas,
+    autovector<MemTable*>* to_delete, Directory* db_directory,
+    LogBuffer* log_buffer) {
+  AutoThreadOperationStageUpdater stage_updater(
+      ThreadStatus::STAGE_MEMTABLE_INSTALL_FLUSH_RESULTS);
+  mu->AssertHeld();
+
+  for (size_t k = 0; k != mems_list.size(); ++k) {
+    for (size_t i = 0; i != mems_list[k]->size(); ++i) {
+      assert(i == 0 || (*mems_list[k])[i]->GetEdits()->NumEntries() == 0);
+      (*mems_list[k])[i]->flush_completed_ = true;
+      (*mems_list[k])[i]->file_number_ = file_metas[k].fd.GetNumber();
+    }
+  }
+
+  assert(atomic_flush_commit_in_progress != nullptr);
+  Status s;
+  if (*atomic_flush_commit_in_progress) {
+    // If the function reaches here, there must be a concurrent thread that
+    // have already started recording to MANIFEST. Therefore we should just
+    // return Status::OK and let the othe thread finish writing to MANIFEST on
+    // our behalf.
+    return s;
+  }
+
+  // If the function reaches here, the current thread will start writing to
+  // MANIFEST. It may record to MANIFEST the flush results of other flushes.
+  *atomic_flush_commit_in_progress = true;
+
+  auto comp = [&imm_lists](size_t lh, size_t rh) {
+    const auto& memlist1 = imm_lists[lh]->current_->memlist_;
+    const auto& memlist2 = imm_lists[rh]->current_->memlist_;
+    auto it1 = memlist1.rbegin();
+    auto it2 = memlist2.rbegin();
+    return (*it1)->atomic_flush_seqno_ > (*it2)->atomic_flush_seqno_;
+  };
+  // The top of the heap is the memtable with smallest atomic_flush_seqno_.
+  std::priority_queue<size_t, std::vector<size_t>, decltype(comp)> heap(comp);
+  // Sequence number of the oldest unfinished atomic flush.
+  SequenceNumber min_unfinished_seqno = kMaxSequenceNumber;
+  // Populate the heap with first element of each imm iff. it has been
+  // flushed to storage, i.e. flush_completed_ is true.
+  size_t num = imm_lists.size();
+  assert(num == cfds.size());
+  for (size_t i = 0; i != num; ++i) {
+    std::list<MemTable*>& memlist = imm_lists[i]->current_->memlist_;
+    if (memlist.empty()) {
+      continue;
+    }
+    auto it = memlist.rbegin();
+    if ((*it)->flush_completed_) {
+      heap.emplace(i);
+    } else if (min_unfinished_seqno > (*it)->atomic_flush_seqno_) {
+      min_unfinished_seqno = (*it)->atomic_flush_seqno_;
+    }
+  }
+
+  while (s.ok() && !heap.empty()) {
+    autovector<size_t> batch;
+    SequenceNumber seqno = kMaxSequenceNumber;
+    // Pop from the heap the memtables that belong to the same atomic flush,
+    // namely their atomic_flush_seqno_ are equal.
+    do {
+      size_t pos = heap.top();
+      const auto& memlist = imm_lists[pos]->current_->memlist_;
+      MemTable* mem = *(memlist.rbegin());
+      if (seqno == kMaxSequenceNumber) {
+        // First mem in this batch.
+        seqno = mem->atomic_flush_seqno_;
+        batch.emplace_back(pos);
+        heap.pop();
+      } else if (mem->atomic_flush_seqno_ == seqno) {
+        // mem has the same atomic_flush_seqno_, thus in the same atomic flush.
+        batch.emplace_back(pos);
+        heap.pop();
+      } else if (mem->atomic_flush_seqno_ > seqno) {
+        // mem belongs to another atomic flush with higher seqno, break the
+        // loop.
+        break;
+      }
+    } while (!heap.empty());
+    if (seqno >= min_unfinished_seqno) {
+      // If there is an older, unfinished atomic flush, then we should not
+      // proceed.
+      TEST_SYNC_POINT_CALLBACK(
+          "MemTableList::TryInstallMemtableFlushResults:"
+          "HasOlderUnfinishedAtomicFlush:0",
+          nullptr);
+      break;
+    }
+
+    // Found the earliest, complete atomic flush. No earlier atomic flush is
+    // pending. Therefore ready to record it to the MANIFEST.
+    uint32_t num_entries = 0;
+    autovector<ColumnFamilyData*> tmp_cfds;
+    autovector<const MutableCFOptions*> tmp_mutable_cf_options_list;
+    std::vector<autovector<MemTable*>> memtables_to_flush;
+    autovector<autovector<VersionEdit*>> edit_lists;
+    for (auto pos : batch) {
+      tmp_cfds.emplace_back(cfds[pos]);
+      tmp_mutable_cf_options_list.emplace_back(mutable_cf_options_list[pos]);
+      const auto& memlist = imm_lists[pos]->current_->memlist_;
+      uint64_t batch_file_number = 0;
+      autovector<MemTable*> tmp_mems;
+      autovector<VersionEdit*> edits;
+      for (auto it = memlist.rbegin(); it != memlist.rend(); ++it) {
+        MemTable* m = *it;
+        if (!m->flush_completed_ ||
+            (it != memlist.rbegin() && m->file_number_ != batch_file_number)) {
+          break;
+        }
+        if (it == memlist.rbegin()) {
+          batch_file_number = m->file_number_;
+          edits.push_back(m->GetEdits());
+          ++num_entries;
+        }
+        tmp_mems.push_back(m);
+      }
+      edit_lists.push_back(edits);
+      memtables_to_flush.push_back(tmp_mems);
+    }
+    TEST_SYNC_POINT_CALLBACK(
+        "MemTableList::TryInstallMemtableFlushResults:FoundBatchToCommit:0",
+        &num_entries);
+
+    // Mark the version edits as an atomic group
+    uint32_t remaining = num_entries;
+    for (auto& edit_list : edit_lists) {
+      assert(edit_list.size() == 1);
+      edit_list[0]->MarkAtomicGroup(--remaining);
+    }
+    assert(remaining == 0);
+
+    size_t batch_sz = batch.size();
+    assert(batch_sz > 0);
+    assert(batch_sz == memtables_to_flush.size());
+    assert(batch_sz == tmp_cfds.size());
+    assert(batch_sz == edit_lists.size());
+
+    if (vset->db_options()->allow_2pc) {
+      for (size_t i = 0; i != batch_sz; ++i) {
+        auto& edit_list = edit_lists[i];
+        assert(!edit_list.empty());
+        edit_list.back()->SetMinLogNumberToKeep(
+            PrecomputeMinLogNumberToKeep(vset, *tmp_cfds[i], edit_list,
+                                         memtables_to_flush[i], prep_tracker));
+      }
+    }
+    // this can release and reacquire the mutex.
+    s = vset->LogAndApply(tmp_cfds, tmp_mutable_cf_options_list, edit_lists, mu,
+                          db_directory);
+
+    for (const auto pos : batch) {
+      imm_lists[pos]->InstallNewVersion();
+    }
+
+    if (s.ok()) {
+      for (size_t i = 0; i != batch_sz; ++i) {
+        if (tmp_cfds[i]->IsDropped()) {
+          continue;
+        }
+        size_t pos = batch[i];
+        for (auto m : memtables_to_flush[i]) {
+          assert(m->file_number_ > 0);
+          uint64_t mem_id = m->GetID();
+          ROCKS_LOG_BUFFER(log_buffer,
+                           "[%s] Level-0 commit table #%" PRIu64
+                           ": memtable #%" PRIu64 " done",
+                           tmp_cfds[i]->GetName().c_str(), m->file_number_,
+                           mem_id);
+          imm_lists[pos]->current_->Remove(m, to_delete);
+        }
+      }
+    } else {
+      for (size_t i = 0; i != batch_sz; ++i) {
+        size_t pos = batch[i];
+        for (auto m : memtables_to_flush[i]) {
+          uint64_t mem_id = m->GetID();
+          ROCKS_LOG_BUFFER(log_buffer,
+                           "[%s] Level-0 commit table #%" PRIu64
+                           ": memtable #%" PRIu64 " failed",
+                           tmp_cfds[i]->GetName().c_str(), m->file_number_,
+                           mem_id);
+          m->flush_completed_ = false;
+          m->flush_in_progress_ = false;
+          m->edit_.Clear();
+          m->file_number_ = 0;
+          imm_lists[pos]->num_flush_not_started_++;
+        }
+        imm_lists[pos]->imm_flush_needed.store(true, std::memory_order_release);
+      }
+    }
+    // Adjust the heap AFTER installing new MemTableListVersions because the
+    // compare function 'comp' needs to capture the most up-to-date state of
+    // imm_lists.
+    for (auto pos : batch) {
+      const auto& memlist = imm_lists[pos]->current_->memlist_;
+      if (!memlist.empty()) {
+        MemTable* mem = *(memlist.rbegin());
+        if (mem->flush_completed_) {
+          heap.emplace(pos);
+        } else if (min_unfinished_seqno > mem->atomic_flush_seqno_) {
+          min_unfinished_seqno = mem->atomic_flush_seqno_;
+        }
+      }
+    }
+  }
+
+  *atomic_flush_commit_in_progress = false;
+  return s;
+}
+
 // Returns true if there is at least one memtable on which flush has
 // not yet started.
 bool MemTableList::IsFlushPending() const {
-  if ((flush_requested_ && num_flush_not_started_ >= 1) ||
+  if ((flush_requested_ && num_flush_not_started_ > 0) ||
       (num_flush_not_started_ >= min_write_buffer_number_to_merge_)) {
     assert(imm_flush_needed.load(std::memory_order_relaxed));
     return true;
@@ -280,12 +494,16 @@ bool MemTableList::IsFlushPending() const {
 }
 
 // Returns the memtables that need to be flushed.
-void MemTableList::PickMemtablesToFlush(autovector<MemTable*>* ret) {
+void MemTableList::PickMemtablesToFlush(const uint64_t* max_memtable_id,
+                                        autovector<MemTable*>* ret) {
   AutoThreadOperationStageUpdater stage_updater(
       ThreadStatus::STAGE_PICK_MEMTABLES_TO_FLUSH);
   const auto& memlist = current_->memlist_;
   for (auto it = memlist.rbegin(); it != memlist.rend(); ++it) {
     MemTable* m = *it;
+    if (max_memtable_id != nullptr && m->GetID() > *max_memtable_id) {
+      break;
+    }
     if (!m->flush_in_progress_) {
       assert(!m->flush_completed_);
       num_flush_not_started_--;
@@ -319,8 +537,9 @@ void MemTableList::RollbackMemtableFlush(const autovector<MemTable*>& mems,
   imm_flush_needed.store(true, std::memory_order_release);
 }
 
-// Record a successful flush in the manifest file
-Status MemTableList::InstallMemtableFlushResults(
+// Try record a successful flush in the manifest file. It might just return
+// Status::OK letting a concurrent flush to do actual the recording..
+Status MemTableList::TryInstallMemtableFlushResults(
     ColumnFamilyData* cfd, const MutableCFOptions& mutable_cf_options,
     const autovector<MemTable*>& mems, LogsWithPrepTracker* prep_tracker,
     VersionSet* vset, InstrumentedMutex* mu, uint64_t file_number,
@@ -330,7 +549,9 @@ Status MemTableList::InstallMemtableFlushResults(
       ThreadStatus::STAGE_MEMTABLE_INSTALL_FLUSH_RESULTS);
   mu->AssertHeld();
 
-  // flush was successful
+  // Flush was successful
+  // Record the status on the memtable object. Either this call or a call by a
+  // concurrent flush thread will read the status and write it to manifest.
   for (size_t i = 0; i < mems.size(); ++i) {
     // All the edits are associated with the first memtable of this batch.
     assert(i == 0 || mems[i]->GetEdits()->NumEntries() == 0);
@@ -342,7 +563,7 @@ Status MemTableList::InstallMemtableFlushResults(
   // if some other thread is already committing, then return
   Status s;
   if (commit_in_progress_) {
-    TEST_SYNC_POINT("MemTableList::InstallMemtableFlushResults:InProgress");
+    TEST_SYNC_POINT("MemTableList::TryInstallMemtableFlushResults:InProgress");
     return s;
   }
 
@@ -353,11 +574,16 @@ Status MemTableList::InstallMemtableFlushResults(
   // while the current thread is writing manifest where mutex is released.
   while (s.ok()) {
     auto& memlist = current_->memlist_;
+    // The back is the oldest; if flush_completed_ is not set to it, it means
+    // that we were assigned a more recent memtable. The memtables' flushes must
+    // be recorded in manifest in order. A concurrent flush thread, who is
+    // assigned to flush the oldest memtable, will later wake up and does all
+    // the pending writes to manifest, in order.
     if (memlist.empty() || !memlist.back()->flush_completed_) {
       break;
     }
     // scan all memtables from the earliest, and commit those
-    // (in that order) that have finished flushing. Memetables
+    // (in that order) that have finished flushing. Memtables
     // are always committed in the order that they were created.
     uint64_t batch_file_number = 0;
     size_t batch_count = 0;
@@ -380,6 +606,7 @@ Status MemTableList::InstallMemtableFlushResults(
       batch_count++;
     }
 
+    // TODO(myabandeh): Not sure how batch_count could be 0 here.
     if (batch_count > 0) {
       if (vset->db_options()->allow_2pc) {
         assert(edit_list.size() > 0);
@@ -405,7 +632,7 @@ Status MemTableList::InstallMemtableFlushResults(
       // The reason is as follows (refer to
       // ColumnFamilyTest.FlushAndDropRaceCondition).
       // If the column family is dropped, then according to LogAndApply, its
-      // corrresponding flush operation is NOT written to the MANIFEST. This
+      // corresponding flush operation is NOT written to the MANIFEST. This
       // means the DB is not aware of the L0 files generated from the flush.
       // By committing the new state, we remove the memtable from the memtable
       // list. Creating an iterator on this column family will not be able to
diff --git a/3rdParty/rocksdb/v5.16.X/db/memtable_list.h b/3rdParty/rocksdb/v5.18.X/db/memtable_list.h
similarity index 78%
rename from 3rdParty/rocksdb/v5.16.X/db/memtable_list.h
rename to 3rdParty/rocksdb/v5.18.X/db/memtable_list.h
index 7fd9de7ada..70bab1c38c 100644
--- a/3rdParty/rocksdb/v5.16.X/db/memtable_list.h
+++ b/3rdParty/rocksdb/v5.18.X/db/memtable_list.h
@@ -15,7 +15,7 @@
 #include "db/dbformat.h"
 #include "db/logs_with_prep_tracker.h"
 #include "db/memtable.h"
-#include "db/range_del_aggregator.h"
+#include "db/range_del_aggregator_v2.h"
 #include "monitoring/instrumented_mutex.h"
 #include "rocksdb/db.h"
 #include "rocksdb/iterator.h"
@@ -55,17 +55,19 @@ class MemTableListVersion {
   // will be stored in *seq on success (regardless of whether true/false is
   // returned).  Otherwise, *seq will be set to kMaxSequenceNumber.
   bool Get(const LookupKey& key, std::string* value, Status* s,
-           MergeContext* merge_context, RangeDelAggregator* range_del_agg,
-           SequenceNumber* seq, const ReadOptions& read_opts,
-           ReadCallback* callback = nullptr, bool* is_blob_index = nullptr);
+           MergeContext* merge_context,
+           SequenceNumber* max_covering_tombstone_seq, SequenceNumber* seq,
+           const ReadOptions& read_opts, ReadCallback* callback = nullptr,
+           bool* is_blob_index = nullptr);
 
   bool Get(const LookupKey& key, std::string* value, Status* s,
-           MergeContext* merge_context, RangeDelAggregator* range_del_agg,
+           MergeContext* merge_context,
+           SequenceNumber* max_covering_tombstone_seq,
            const ReadOptions& read_opts, ReadCallback* callback = nullptr,
            bool* is_blob_index = nullptr) {
     SequenceNumber seq;
-    return Get(key, value, s, merge_context, range_del_agg, &seq, read_opts,
-               callback, is_blob_index);
+    return Get(key, value, s, merge_context, max_covering_tombstone_seq, &seq,
+               read_opts, callback, is_blob_index);
   }
 
   // Similar to Get(), but searches the Memtable history of memtables that
@@ -74,24 +76,22 @@ class MemTableListVersion {
   // writes that are also present in the SST files.
   bool GetFromHistory(const LookupKey& key, std::string* value, Status* s,
                       MergeContext* merge_context,
-                      RangeDelAggregator* range_del_agg, SequenceNumber* seq,
-                      const ReadOptions& read_opts,
+                      SequenceNumber* max_covering_tombstone_seq,
+                      SequenceNumber* seq, const ReadOptions& read_opts,
                       bool* is_blob_index = nullptr);
   bool GetFromHistory(const LookupKey& key, std::string* value, Status* s,
                       MergeContext* merge_context,
-                      RangeDelAggregator* range_del_agg,
+                      SequenceNumber* max_covering_tombstone_seq,
                       const ReadOptions& read_opts,
                       bool* is_blob_index = nullptr) {
     SequenceNumber seq;
-    return GetFromHistory(key, value, s, merge_context, range_del_agg, &seq,
-                          read_opts, is_blob_index);
+    return GetFromHistory(key, value, s, merge_context,
+                          max_covering_tombstone_seq, &seq, read_opts,
+                          is_blob_index);
   }
 
   Status AddRangeTombstoneIterators(const ReadOptions& read_opts, Arena* arena,
-                                    RangeDelAggregator* range_del_agg);
-  Status AddRangeTombstoneIterators(
-      const ReadOptions& read_opts,
-      std::vector<InternalIterator*>* range_del_iters);
+                                    RangeDelAggregatorV2* range_del_agg);
 
   void AddIterators(const ReadOptions& options,
                     std::vector<InternalIterator*>* iterator_list,
@@ -123,8 +123,8 @@ class MemTableListVersion {
 
   bool GetFromList(std::list<MemTable*>* list, const LookupKey& key,
                    std::string* value, Status* s, MergeContext* merge_context,
-                   RangeDelAggregator* range_del_agg, SequenceNumber* seq,
-                   const ReadOptions& read_opts,
+                   SequenceNumber* max_covering_tombstone_seq,
+                   SequenceNumber* seq, const ReadOptions& read_opts,
                    ReadCallback* callback = nullptr,
                    bool* is_blob_index = nullptr);
 
@@ -163,6 +163,18 @@ class MemTableListVersion {
 // write thread.)
 class MemTableList {
  public:
+  // Commit a successful atomic flush in the manifest file
+  static Status TryInstallMemtableFlushResults(
+      autovector<MemTableList*>& imm_lists,
+      const autovector<ColumnFamilyData*>& cfds,
+      const autovector<const MutableCFOptions*>& mutable_cf_options_list,
+      const autovector<const autovector<MemTable*>*>& mems_list,
+      bool* atomic_flush_commit_in_progress, LogsWithPrepTracker* prep_tracker,
+      VersionSet* vset, InstrumentedMutex* mu,
+      const autovector<FileMetaData>& file_meta,
+      autovector<MemTable*>* to_delete, Directory* db_directory,
+      LogBuffer* log_buffer);
+
   // A list of memtables.
   explicit MemTableList(int min_write_buffer_number_to_merge,
                         int max_write_buffer_number_to_maintain)
@@ -201,15 +213,17 @@ class MemTableList {
 
   // Returns the earliest memtables that needs to be flushed. The returned
   // memtables are guaranteed to be in the ascending order of created time.
-  void PickMemtablesToFlush(autovector<MemTable*>* mems);
+  void PickMemtablesToFlush(const uint64_t* max_memtable_id,
+                            autovector<MemTable*>* mems);
 
   // Reset status of the given memtable list back to pending state so that
   // they can get picked up again on the next round of flush.
   void RollbackMemtableFlush(const autovector<MemTable*>& mems,
                              uint64_t file_number);
 
-  // Commit a successful flush in the manifest file
-  Status InstallMemtableFlushResults(
+  // Try commit a successful flush in the manifest file. It might just return
+  // Status::OK letting a concurrent flush to do the actual the recording.
+  Status TryInstallMemtableFlushResults(
       ColumnFamilyData* cfd, const MutableCFOptions& mutable_cf_options,
       const autovector<MemTable*>& m, LogsWithPrepTracker* prep_tracker,
       VersionSet* vset, InstrumentedMutex* mu, uint64_t file_number,
@@ -266,6 +280,21 @@ class MemTableList {
     return memlist.front()->GetID();
   }
 
+  void AssignAtomicFlushSeq(const SequenceNumber& seq) {
+    const auto& memlist = current_->memlist_;
+    // Scan the memtable list from new to old
+    for (auto it = memlist.begin(); it != memlist.end(); ++it) {
+      MemTable* mem = *it;
+      if (mem->atomic_flush_seqno_ == kMaxSequenceNumber) {
+        mem->atomic_flush_seqno_ = seq;
+      } else {
+        // Earlier memtables must have been assigned a atomic flush seq, no
+        // need to continue scan.
+        break;
+      }
+    }
+  }
+
  private:
   // DB mutex held
   void InstallNewVersion();
@@ -280,7 +309,8 @@ class MemTableList {
   // committing in progress
   bool commit_in_progress_;
 
-  // Requested a flush of all memtables to storage
+  // Requested a flush of memtables to storage. It's possible to request that
+  // a subset of memtables be flushed.
   bool flush_requested_;
 
   // The current memory usage.
diff --git a/3rdParty/rocksdb/v5.18.X/db/memtable_list_test.cc b/3rdParty/rocksdb/v5.18.X/db/memtable_list_test.cc
new file mode 100644
index 0000000000..06554f1abb
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/memtable_list_test.cc
@@ -0,0 +1,1063 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/memtable_list.h"
+#include <algorithm>
+#include <string>
+#include <vector>
+#include "db/merge_context.h"
+#include "db/range_del_aggregator.h"
+#include "db/version_set.h"
+#include "db/write_controller.h"
+#include "rocksdb/db.h"
+#include "rocksdb/status.h"
+#include "rocksdb/write_buffer_manager.h"
+#include "util/string_util.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
+
+namespace rocksdb {
+
+class MemTableListTest : public testing::Test {
+ public:
+  std::string dbname;
+  DB* db;
+  Options options;
+  std::vector<ColumnFamilyHandle*> handles;
+  std::atomic<uint64_t> file_number;
+
+  MemTableListTest() : db(nullptr), file_number(1) {
+    dbname = test::PerThreadDBPath("memtable_list_test");
+    options.create_if_missing = true;
+    DestroyDB(dbname, options);
+  }
+
+  // Create a test db if not yet created
+  void CreateDB() {
+    if (db == nullptr) {
+      options.create_if_missing = true;
+      DestroyDB(dbname, options);
+      // Open DB only with default column family
+      ColumnFamilyOptions cf_options;
+      std::vector<ColumnFamilyDescriptor> cf_descs;
+      cf_descs.emplace_back(kDefaultColumnFamilyName, cf_options);
+      Status s = DB::Open(options, dbname, cf_descs, &handles, &db);
+      EXPECT_OK(s);
+
+      ColumnFamilyOptions cf_opt1, cf_opt2;
+      cf_opt1.cf_paths.emplace_back(dbname + "_one_1",
+                                    std::numeric_limits<uint64_t>::max());
+      cf_opt2.cf_paths.emplace_back(dbname + "_two_1",
+                                    std::numeric_limits<uint64_t>::max());
+      int sz = static_cast<int>(handles.size());
+      handles.resize(sz + 2);
+      s = db->CreateColumnFamily(cf_opt1, "one", &handles[1]);
+      EXPECT_OK(s);
+      s = db->CreateColumnFamily(cf_opt2, "two", &handles[2]);
+      EXPECT_OK(s);
+
+      cf_descs.emplace_back("one", cf_options);
+      cf_descs.emplace_back("two", cf_options);
+    }
+  }
+
+  ~MemTableListTest() {
+    if (db) {
+      std::vector<ColumnFamilyDescriptor> cf_descs(handles.size());
+      for (int i = 0; i != static_cast<int>(handles.size()); ++i) {
+        handles[i]->GetDescriptor(&cf_descs[i]);
+      }
+      for (auto h : handles) {
+        if (h) {
+          db->DestroyColumnFamilyHandle(h);
+        }
+      }
+      handles.clear();
+      delete db;
+      db = nullptr;
+      DestroyDB(dbname, options, cf_descs);
+    }
+  }
+
+  // Calls MemTableList::TryInstallMemtableFlushResults() and sets up all
+  // structures needed to call this function.
+  Status Mock_InstallMemtableFlushResults(
+      MemTableList* list, const MutableCFOptions& mutable_cf_options,
+      const autovector<MemTable*>& m, autovector<MemTable*>* to_delete) {
+    autovector<MemTableList*> lists;
+    lists.emplace_back(list);
+    autovector<const autovector<MemTable*>*> mems_list;
+    mems_list.emplace_back(&m);
+    return Mock_InstallMemtableFlushResults(
+        lists, {0} /* cf_ids */, {&mutable_cf_options}, mems_list, to_delete);
+  }
+
+  // Calls MemTableList::InstallMemtableFlushResults() and sets up all
+  // structures needed to call this function.
+  Status Mock_InstallMemtableFlushResults(
+      autovector<MemTableList*>& lists, const autovector<uint32_t>& cf_ids,
+      const autovector<const MutableCFOptions*>& mutable_cf_options_list,
+      const autovector<const autovector<MemTable*>*>& mems_list,
+      autovector<MemTable*>* to_delete) {
+    // Create a mock Logger
+    test::NullLogger logger;
+    LogBuffer log_buffer(DEBUG_LEVEL, &logger);
+
+    CreateDB();
+    // Create a mock VersionSet
+    DBOptions db_options;
+    ImmutableDBOptions immutable_db_options(db_options);
+    EnvOptions env_options;
+    std::shared_ptr<Cache> table_cache(NewLRUCache(50000, 16));
+    WriteBufferManager write_buffer_manager(db_options.db_write_buffer_size);
+    WriteController write_controller(10000000u);
+
+    VersionSet versions(dbname, &immutable_db_options, env_options,
+                        table_cache.get(), &write_buffer_manager,
+                        &write_controller);
+    std::vector<ColumnFamilyDescriptor> cf_descs;
+    cf_descs.emplace_back(kDefaultColumnFamilyName, ColumnFamilyOptions());
+    cf_descs.emplace_back("one", ColumnFamilyOptions());
+    cf_descs.emplace_back("two", ColumnFamilyOptions());
+    EXPECT_OK(versions.Recover(cf_descs, false));
+
+    // Create mock default ColumnFamilyData
+
+    auto column_family_set = versions.GetColumnFamilySet();
+
+    LogsWithPrepTracker dummy_prep_tracker;
+    if (1 == cf_ids.size()) {
+      auto cfd = column_family_set->GetColumnFamily(cf_ids[0]);
+      EXPECT_TRUE(nullptr != cfd);
+      EXPECT_EQ(1, lists.size());
+      MemTableList* list = lists[0];
+      EXPECT_EQ(1, mutable_cf_options_list.size());
+      const MutableCFOptions& mutable_cf_options =
+          *(mutable_cf_options_list.at(0));
+      const autovector<MemTable*>* mems = mems_list.at(0);
+      EXPECT_TRUE(nullptr != mems);
+
+      uint64_t file_num = file_number.fetch_add(1);
+      // Create dummy mutex.
+      InstrumentedMutex mutex;
+      InstrumentedMutexLock l(&mutex);
+      return list->TryInstallMemtableFlushResults(
+          cfd, mutable_cf_options, *mems, &dummy_prep_tracker, &versions,
+          &mutex, file_num, to_delete, nullptr, &log_buffer);
+    }
+    autovector<ColumnFamilyData*> cfds;
+    for (int i = 0; i != static_cast<int>(cf_ids.size()); ++i) {
+      cfds.emplace_back(column_family_set->GetColumnFamily(cf_ids[i]));
+      EXPECT_NE(nullptr, cfds[i]);
+    }
+    autovector<FileMetaData> file_metas;
+    for (size_t i = 0; i != cf_ids.size(); ++i) {
+      FileMetaData meta;
+      uint64_t file_num = file_number.fetch_add(1);
+      meta.fd = FileDescriptor(file_num, 0, 0);
+      file_metas.emplace_back(meta);
+    }
+    bool atomic_flush_commit_in_progress = false;
+    InstrumentedMutex mutex;
+    InstrumentedMutexLock l(&mutex);
+    return MemTableList::TryInstallMemtableFlushResults(
+        lists, cfds, mutable_cf_options_list, mems_list,
+        &atomic_flush_commit_in_progress, &dummy_prep_tracker, &versions,
+        &mutex, file_metas, to_delete, nullptr, &log_buffer);
+  }
+};
+
+TEST_F(MemTableListTest, Empty) {
+  // Create an empty MemTableList and validate basic functions.
+  MemTableList list(1, 0);
+
+  ASSERT_EQ(0, list.NumNotFlushed());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+  ASSERT_FALSE(list.IsFlushPending());
+
+  autovector<MemTable*> mems;
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &mems);
+  ASSERT_EQ(0, mems.size());
+
+  autovector<MemTable*> to_delete;
+  list.current()->Unref(&to_delete);
+  ASSERT_EQ(0, to_delete.size());
+}
+
+TEST_F(MemTableListTest, GetTest) {
+  // Create MemTableList
+  int min_write_buffer_number_to_merge = 2;
+  int max_write_buffer_number_to_maintain = 0;
+  MemTableList list(min_write_buffer_number_to_merge,
+                    max_write_buffer_number_to_maintain);
+
+  SequenceNumber seq = 1;
+  std::string value;
+  Status s;
+  MergeContext merge_context;
+  InternalKeyComparator ikey_cmp(options.comparator);
+  SequenceNumber max_covering_tombstone_seq = 0;
+  autovector<MemTable*> to_delete;
+
+  LookupKey lkey("key1", seq);
+  bool found = list.current()->Get(lkey, &value, &s, &merge_context,
+                                   &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_FALSE(found);
+
+  // Create a MemTable
+  InternalKeyComparator cmp(BytewiseComparator());
+  auto factory = std::make_shared<SkipListFactory>();
+  options.memtable_factory = factory;
+  ImmutableCFOptions ioptions(options);
+
+  WriteBufferManager wb(options.db_write_buffer_size);
+  MemTable* mem = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb,
+                               kMaxSequenceNumber, 0 /* column_family_id */);
+  mem->Ref();
+
+  // Write some keys to this memtable.
+  mem->Add(++seq, kTypeDeletion, "key1", "");
+  mem->Add(++seq, kTypeValue, "key2", "value2");
+  mem->Add(++seq, kTypeValue, "key1", "value1");
+  mem->Add(++seq, kTypeValue, "key2", "value2.2");
+
+  // Fetch the newly written keys
+  merge_context.Clear();
+  found = mem->Get(LookupKey("key1", seq), &value, &s, &merge_context,
+                   &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(s.ok() && found);
+  ASSERT_EQ(value, "value1");
+
+  merge_context.Clear();
+  found = mem->Get(LookupKey("key1", 2), &value, &s, &merge_context,
+                   &max_covering_tombstone_seq, ReadOptions());
+  // MemTable found out that this key is *not* found (at this sequence#)
+  ASSERT_TRUE(found && s.IsNotFound());
+
+  merge_context.Clear();
+  found = mem->Get(LookupKey("key2", seq), &value, &s, &merge_context,
+                   &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(s.ok() && found);
+  ASSERT_EQ(value, "value2.2");
+
+  ASSERT_EQ(4, mem->num_entries());
+  ASSERT_EQ(1, mem->num_deletes());
+
+  // Add memtable to list
+  list.Add(mem, &to_delete);
+
+  SequenceNumber saved_seq = seq;
+
+  // Create another memtable and write some keys to it
+  WriteBufferManager wb2(options.db_write_buffer_size);
+  MemTable* mem2 = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb2,
+                                kMaxSequenceNumber, 0 /* column_family_id */);
+  mem2->Ref();
+
+  mem2->Add(++seq, kTypeDeletion, "key1", "");
+  mem2->Add(++seq, kTypeValue, "key2", "value2.3");
+
+  // Add second memtable to list
+  list.Add(mem2, &to_delete);
+
+  // Fetch keys via MemTableList
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key1", seq), &value, &s, &merge_context,
+                          &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(found && s.IsNotFound());
+
+  merge_context.Clear();
+  found = list.current()->Get(LookupKey("key1", saved_seq), &value, &s,
+                              &merge_context, &max_covering_tombstone_seq,
+                              ReadOptions());
+  ASSERT_TRUE(s.ok() && found);
+  ASSERT_EQ("value1", value);
+
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key2", seq), &value, &s, &merge_context,
+                          &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(s.ok() && found);
+  ASSERT_EQ(value, "value2.3");
+
+  merge_context.Clear();
+  found = list.current()->Get(LookupKey("key2", 1), &value, &s, &merge_context,
+                              &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_FALSE(found);
+
+  ASSERT_EQ(2, list.NumNotFlushed());
+
+  list.current()->Unref(&to_delete);
+  for (MemTable* m : to_delete) {
+    delete m;
+  }
+}
+
+TEST_F(MemTableListTest, GetFromHistoryTest) {
+  // Create MemTableList
+  int min_write_buffer_number_to_merge = 2;
+  int max_write_buffer_number_to_maintain = 2;
+  MemTableList list(min_write_buffer_number_to_merge,
+                    max_write_buffer_number_to_maintain);
+
+  SequenceNumber seq = 1;
+  std::string value;
+  Status s;
+  MergeContext merge_context;
+  InternalKeyComparator ikey_cmp(options.comparator);
+  SequenceNumber max_covering_tombstone_seq = 0;
+  autovector<MemTable*> to_delete;
+
+  LookupKey lkey("key1", seq);
+  bool found = list.current()->Get(lkey, &value, &s, &merge_context,
+                                   &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_FALSE(found);
+
+  // Create a MemTable
+  InternalKeyComparator cmp(BytewiseComparator());
+  auto factory = std::make_shared<SkipListFactory>();
+  options.memtable_factory = factory;
+  ImmutableCFOptions ioptions(options);
+
+  WriteBufferManager wb(options.db_write_buffer_size);
+  MemTable* mem = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb,
+                               kMaxSequenceNumber, 0 /* column_family_id */);
+  mem->Ref();
+
+  // Write some keys to this memtable.
+  mem->Add(++seq, kTypeDeletion, "key1", "");
+  mem->Add(++seq, kTypeValue, "key2", "value2");
+  mem->Add(++seq, kTypeValue, "key2", "value2.2");
+
+  // Fetch the newly written keys
+  merge_context.Clear();
+  found = mem->Get(LookupKey("key1", seq), &value, &s, &merge_context,
+                   &max_covering_tombstone_seq, ReadOptions());
+  // MemTable found out that this key is *not* found (at this sequence#)
+  ASSERT_TRUE(found && s.IsNotFound());
+
+  merge_context.Clear();
+  found = mem->Get(LookupKey("key2", seq), &value, &s, &merge_context,
+                   &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(s.ok() && found);
+  ASSERT_EQ(value, "value2.2");
+
+  // Add memtable to list
+  list.Add(mem, &to_delete);
+  ASSERT_EQ(0, to_delete.size());
+
+  // Fetch keys via MemTableList
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key1", seq), &value, &s, &merge_context,
+                          &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(found && s.IsNotFound());
+
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key2", seq), &value, &s, &merge_context,
+                          &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(s.ok() && found);
+  ASSERT_EQ("value2.2", value);
+
+  // Flush this memtable from the list.
+  // (It will then be a part of the memtable history).
+  autovector<MemTable*> to_flush;
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &to_flush);
+  ASSERT_EQ(1, to_flush.size());
+
+  MutableCFOptions mutable_cf_options(options);
+  s = Mock_InstallMemtableFlushResults(&list, mutable_cf_options, to_flush,
+                                       &to_delete);
+  ASSERT_OK(s);
+  ASSERT_EQ(0, list.NumNotFlushed());
+  ASSERT_EQ(1, list.NumFlushed());
+  ASSERT_EQ(0, to_delete.size());
+
+  // Verify keys are no longer in MemTableList
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key1", seq), &value, &s, &merge_context,
+                          &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_FALSE(found);
+
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key2", seq), &value, &s, &merge_context,
+                          &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_FALSE(found);
+
+  // Verify keys are present in history
+  merge_context.Clear();
+  found = list.current()->GetFromHistory(
+      LookupKey("key1", seq), &value, &s, &merge_context,
+      &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(found && s.IsNotFound());
+
+  merge_context.Clear();
+  found = list.current()->GetFromHistory(
+      LookupKey("key2", seq), &value, &s, &merge_context,
+      &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(found);
+  ASSERT_EQ("value2.2", value);
+
+  // Create another memtable and write some keys to it
+  WriteBufferManager wb2(options.db_write_buffer_size);
+  MemTable* mem2 = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb2,
+                                kMaxSequenceNumber, 0 /* column_family_id */);
+  mem2->Ref();
+
+  mem2->Add(++seq, kTypeDeletion, "key1", "");
+  mem2->Add(++seq, kTypeValue, "key3", "value3");
+
+  // Add second memtable to list
+  list.Add(mem2, &to_delete);
+  ASSERT_EQ(0, to_delete.size());
+
+  to_flush.clear();
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &to_flush);
+  ASSERT_EQ(1, to_flush.size());
+
+  // Flush second memtable
+  s = Mock_InstallMemtableFlushResults(&list, mutable_cf_options, to_flush,
+                                       &to_delete);
+  ASSERT_OK(s);
+  ASSERT_EQ(0, list.NumNotFlushed());
+  ASSERT_EQ(2, list.NumFlushed());
+  ASSERT_EQ(0, to_delete.size());
+
+  // Add a third memtable to push the first memtable out of the history
+  WriteBufferManager wb3(options.db_write_buffer_size);
+  MemTable* mem3 = new MemTable(cmp, ioptions, MutableCFOptions(options), &wb3,
+                                kMaxSequenceNumber, 0 /* column_family_id */);
+  mem3->Ref();
+  list.Add(mem3, &to_delete);
+  ASSERT_EQ(1, list.NumNotFlushed());
+  ASSERT_EQ(1, list.NumFlushed());
+  ASSERT_EQ(1, to_delete.size());
+
+  // Verify keys are no longer in MemTableList
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key1", seq), &value, &s, &merge_context,
+                          &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_FALSE(found);
+
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key2", seq), &value, &s, &merge_context,
+                          &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_FALSE(found);
+
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key3", seq), &value, &s, &merge_context,
+                          &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_FALSE(found);
+
+  // Verify that the second memtable's keys are in the history
+  merge_context.Clear();
+  found = list.current()->GetFromHistory(
+      LookupKey("key1", seq), &value, &s, &merge_context,
+      &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(found && s.IsNotFound());
+
+  merge_context.Clear();
+  found = list.current()->GetFromHistory(
+      LookupKey("key3", seq), &value, &s, &merge_context,
+      &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_TRUE(found);
+  ASSERT_EQ("value3", value);
+
+  // Verify that key2 from the first memtable is no longer in the history
+  merge_context.Clear();
+  found =
+      list.current()->Get(LookupKey("key2", seq), &value, &s, &merge_context,
+                          &max_covering_tombstone_seq, ReadOptions());
+  ASSERT_FALSE(found);
+
+  // Cleanup
+  list.current()->Unref(&to_delete);
+  ASSERT_EQ(3, to_delete.size());
+  for (MemTable* m : to_delete) {
+    delete m;
+  }
+}
+
+TEST_F(MemTableListTest, FlushPendingTest) {
+  const int num_tables = 6;
+  SequenceNumber seq = 1;
+  Status s;
+
+  auto factory = std::make_shared<SkipListFactory>();
+  options.memtable_factory = factory;
+  ImmutableCFOptions ioptions(options);
+  InternalKeyComparator cmp(BytewiseComparator());
+  WriteBufferManager wb(options.db_write_buffer_size);
+  autovector<MemTable*> to_delete;
+
+  // Create MemTableList
+  int min_write_buffer_number_to_merge = 3;
+  int max_write_buffer_number_to_maintain = 7;
+  MemTableList list(min_write_buffer_number_to_merge,
+                    max_write_buffer_number_to_maintain);
+
+  // Create some MemTables
+  uint64_t memtable_id = 0;
+  std::vector<MemTable*> tables;
+  MutableCFOptions mutable_cf_options(options);
+  for (int i = 0; i < num_tables; i++) {
+    MemTable* mem = new MemTable(cmp, ioptions, mutable_cf_options, &wb,
+                                 kMaxSequenceNumber, 0 /* column_family_id */);
+    mem->SetID(memtable_id++);
+    mem->Ref();
+
+    std::string value;
+    MergeContext merge_context;
+
+    mem->Add(++seq, kTypeValue, "key1", ToString(i));
+    mem->Add(++seq, kTypeValue, "keyN" + ToString(i), "valueN");
+    mem->Add(++seq, kTypeValue, "keyX" + ToString(i), "value");
+    mem->Add(++seq, kTypeValue, "keyM" + ToString(i), "valueM");
+    mem->Add(++seq, kTypeDeletion, "keyX" + ToString(i), "");
+
+    tables.push_back(mem);
+  }
+
+  // Nothing to flush
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+  autovector<MemTable*> to_flush;
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &to_flush);
+  ASSERT_EQ(0, to_flush.size());
+
+  // Request a flush even though there is nothing to flush
+  list.FlushRequested();
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Attempt to 'flush' to clear request for flush
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &to_flush);
+  ASSERT_EQ(0, to_flush.size());
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Request a flush again
+  list.FlushRequested();
+  // No flush pending since the list is empty.
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Add 2 tables
+  list.Add(tables[0], &to_delete);
+  list.Add(tables[1], &to_delete);
+  ASSERT_EQ(2, list.NumNotFlushed());
+  ASSERT_EQ(0, to_delete.size());
+
+  // Even though we have less than the minimum to flush, a flush is
+  // pending since we had previously requested a flush and never called
+  // PickMemtablesToFlush() to clear the flush.
+  ASSERT_TRUE(list.IsFlushPending());
+  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Pick tables to flush
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &to_flush);
+  ASSERT_EQ(2, to_flush.size());
+  ASSERT_EQ(2, list.NumNotFlushed());
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Revert flush
+  list.RollbackMemtableFlush(to_flush, 0);
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+  to_flush.clear();
+
+  // Add another table
+  list.Add(tables[2], &to_delete);
+  // We now have the minimum to flush regardles of whether FlushRequested()
+  // was called.
+  ASSERT_TRUE(list.IsFlushPending());
+  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+  ASSERT_EQ(0, to_delete.size());
+
+  // Pick tables to flush
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &to_flush);
+  ASSERT_EQ(3, to_flush.size());
+  ASSERT_EQ(3, list.NumNotFlushed());
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Pick tables to flush again
+  autovector<MemTable*> to_flush2;
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &to_flush2);
+  ASSERT_EQ(0, to_flush2.size());
+  ASSERT_EQ(3, list.NumNotFlushed());
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Add another table
+  list.Add(tables[3], &to_delete);
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+  ASSERT_EQ(0, to_delete.size());
+
+  // Request a flush again
+  list.FlushRequested();
+  ASSERT_TRUE(list.IsFlushPending());
+  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Pick tables to flush again
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &to_flush2);
+  ASSERT_EQ(1, to_flush2.size());
+  ASSERT_EQ(4, list.NumNotFlushed());
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Rollback first pick of tables
+  list.RollbackMemtableFlush(to_flush, 0);
+  ASSERT_TRUE(list.IsFlushPending());
+  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+  to_flush.clear();
+
+  // Add another tables
+  list.Add(tables[4], &to_delete);
+  ASSERT_EQ(5, list.NumNotFlushed());
+  // We now have the minimum to flush regardles of whether FlushRequested()
+  ASSERT_TRUE(list.IsFlushPending());
+  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+  ASSERT_EQ(0, to_delete.size());
+
+  // Pick tables to flush
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &to_flush);
+  // Should pick 4 of 5 since 1 table has been picked in to_flush2
+  ASSERT_EQ(4, to_flush.size());
+  ASSERT_EQ(5, list.NumNotFlushed());
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Pick tables to flush again
+  autovector<MemTable*> to_flush3;
+  list.PickMemtablesToFlush(nullptr /* memtable_id */, &to_flush3);
+  ASSERT_EQ(0, to_flush3.size());  // nothing not in progress of being flushed
+  ASSERT_EQ(5, list.NumNotFlushed());
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Flush the 4 memtables that were picked in to_flush
+  s = Mock_InstallMemtableFlushResults(&list, mutable_cf_options, to_flush,
+                                       &to_delete);
+  ASSERT_OK(s);
+
+  // Note:  now to_flush contains tables[0,1,2,4].  to_flush2 contains
+  // tables[3].
+  // Current implementation will only commit memtables in the order they were
+  // created. So TryInstallMemtableFlushResults will install the first 3 tables
+  // in to_flush and stop when it encounters a table not yet flushed.
+  ASSERT_EQ(2, list.NumNotFlushed());
+  int num_in_history = std::min(3, max_write_buffer_number_to_maintain);
+  ASSERT_EQ(num_in_history, list.NumFlushed());
+  ASSERT_EQ(5 - list.NumNotFlushed() - num_in_history, to_delete.size());
+
+  // Request a flush again. Should be nothing to flush
+  list.FlushRequested();
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+
+  // Flush the 1 memtable that was picked in to_flush2
+  s = MemTableListTest::Mock_InstallMemtableFlushResults(
+      &list, mutable_cf_options, to_flush2, &to_delete);
+  ASSERT_OK(s);
+
+  // This will actually install 2 tables.  The 1 we told it to flush, and also
+  // tables[4] which has been waiting for tables[3] to commit.
+  ASSERT_EQ(0, list.NumNotFlushed());
+  num_in_history = std::min(5, max_write_buffer_number_to_maintain);
+  ASSERT_EQ(num_in_history, list.NumFlushed());
+  ASSERT_EQ(5 - list.NumNotFlushed() - num_in_history, to_delete.size());
+
+  for (const auto& m : to_delete) {
+    // Refcount should be 0 after calling TryInstallMemtableFlushResults.
+    // Verify this, by Ref'ing then UnRef'ing:
+    m->Ref();
+    ASSERT_EQ(m, m->Unref());
+    delete m;
+  }
+  to_delete.clear();
+
+  // Add another table
+  list.Add(tables[5], &to_delete);
+  ASSERT_EQ(1, list.NumNotFlushed());
+  ASSERT_EQ(5, list.GetLatestMemTableID());
+  memtable_id = 4;
+  // Pick tables to flush. The tables to pick must have ID smaller than or
+  // equal to 4. Therefore, no table will be selected in this case.
+  autovector<MemTable*> to_flush4;
+  list.FlushRequested();
+  ASSERT_TRUE(list.HasFlushRequested());
+  list.PickMemtablesToFlush(&memtable_id, &to_flush4);
+  ASSERT_TRUE(to_flush4.empty());
+  ASSERT_EQ(1, list.NumNotFlushed());
+  ASSERT_TRUE(list.imm_flush_needed.load(std::memory_order_acquire));
+  ASSERT_FALSE(list.IsFlushPending());
+  ASSERT_FALSE(list.HasFlushRequested());
+
+  // Pick tables to flush. The tables to pick must have ID smaller than or
+  // equal to 5. Therefore, only tables[5] will be selected.
+  memtable_id = 5;
+  list.FlushRequested();
+  list.PickMemtablesToFlush(&memtable_id, &to_flush4);
+  ASSERT_EQ(1, static_cast<int>(to_flush4.size()));
+  ASSERT_EQ(1, list.NumNotFlushed());
+  ASSERT_FALSE(list.imm_flush_needed.load(std::memory_order_acquire));
+  ASSERT_FALSE(list.IsFlushPending());
+  to_delete.clear();
+
+  list.current()->Unref(&to_delete);
+  int to_delete_size =
+      std::min(num_tables, max_write_buffer_number_to_maintain);
+  ASSERT_EQ(to_delete_size, to_delete.size());
+
+  for (const auto& m : to_delete) {
+    // Refcount should be 0 after calling TryInstallMemtableFlushResults.
+    // Verify this, by Ref'ing then UnRef'ing:
+    m->Ref();
+    ASSERT_EQ(m, m->Unref());
+    delete m;
+  }
+  to_delete.clear();
+}
+
+TEST_F(MemTableListTest, FlushMultipleCFsTest) {
+  const int num_cfs = 3;
+  const int num_tables_per_cf = 5;
+  SequenceNumber seq = 1;
+  Status s;
+
+  auto factory = std::make_shared<SkipListFactory>();
+  options.memtable_factory = factory;
+  ImmutableCFOptions ioptions(options);
+  InternalKeyComparator cmp(BytewiseComparator());
+  WriteBufferManager wb(options.db_write_buffer_size);
+  autovector<MemTable*> to_delete;
+
+  // Create MemTableLists
+  int min_write_buffer_number_to_merge = 3;
+  int max_write_buffer_number_to_maintain = 7;
+  autovector<MemTableList*> lists;
+  for (int i = 0; i != num_cfs; ++i) {
+    lists.emplace_back(new MemTableList(min_write_buffer_number_to_merge,
+                                        max_write_buffer_number_to_maintain));
+  }
+
+  autovector<uint32_t> cf_ids;
+  std::vector<std::vector<MemTable*>> tables(num_cfs);
+  autovector<const MutableCFOptions*> mutable_cf_options_list;
+  uint32_t cf_id = 0;
+  for (auto& elem : tables) {
+    mutable_cf_options_list.emplace_back(new MutableCFOptions(options));
+    uint64_t memtable_id = 0;
+    for (int i = 0; i != num_tables_per_cf; ++i) {
+      MemTable* mem =
+          new MemTable(cmp, ioptions, *(mutable_cf_options_list.back()), &wb,
+                       kMaxSequenceNumber, cf_id);
+      mem->SetID(memtable_id++);
+      mem->Ref();
+
+      std::string value;
+
+      mem->Add(++seq, kTypeValue, "key1", ToString(i));
+      mem->Add(++seq, kTypeValue, "keyN" + ToString(i), "valueN");
+      mem->Add(++seq, kTypeValue, "keyX" + ToString(i), "value");
+      mem->Add(++seq, kTypeValue, "keyM" + ToString(i), "valueM");
+      mem->Add(++seq, kTypeDeletion, "keyX" + ToString(i), "");
+
+      elem.push_back(mem);
+    }
+    cf_ids.push_back(cf_id++);
+  }
+
+  std::vector<autovector<MemTable*>> flush_candidates(num_cfs);
+
+  // Nothing to flush
+  for (int i = 0; i != num_cfs; ++i) {
+    auto list = lists[i];
+    ASSERT_FALSE(list->IsFlushPending());
+    ASSERT_FALSE(list->imm_flush_needed.load(std::memory_order_acquire));
+    list->PickMemtablesToFlush(nullptr /* memtable_id */, &flush_candidates[i]);
+    ASSERT_EQ(0, static_cast<int>(flush_candidates[i].size()));
+  }
+
+  // Request flush even though there is nothing to flush
+  for (int i = 0; i != num_cfs; ++i) {
+    auto list = lists[i];
+    list->FlushRequested();
+    ASSERT_FALSE(list->IsFlushPending());
+    ASSERT_FALSE(list->imm_flush_needed.load(std::memory_order_acquire));
+  }
+
+  // Add tables to column families
+  for (int i = 0; i != num_cfs; ++i) {
+    for (int j = 0; j != num_tables_per_cf; ++j) {
+      lists[i]->Add(tables[i][j], &to_delete);
+    }
+    ASSERT_EQ(num_tables_per_cf, lists[i]->NumNotFlushed());
+    ASSERT_TRUE(lists[i]->IsFlushPending());
+    ASSERT_TRUE(lists[i]->imm_flush_needed.load(std::memory_order_acquire));
+  }
+
+  autovector<const autovector<MemTable*>*> to_flush;
+  std::vector<uint64_t> prev_memtable_ids;
+  // For each column family, determine the memtables to flush
+  for (int k = 0; k != 4; ++k) {
+    std::vector<uint64_t> flush_memtable_ids;
+    if (0 == k) {
+      //          +----+
+      // list[0]: |0  1|  2 3 4
+      // list[1]: |0  1|  2 3 4
+      //          | +--+
+      // list[2]: |0| 1   2 3 4
+      //          +-+
+      flush_memtable_ids = {1, 1, 0};
+    } else if (1 == k) {
+      //          +----+ +---+
+      // list[0]: |0  1| |2 3|  4
+      // list[1]: |0  1| |2 3|  4
+      //          | +--+ +---+
+      // list[2]: |0| 1   2 3   4
+      //          +-+
+      flush_memtable_ids = {3, 3, 0};
+    } else if (2 == k) {
+      //          +-----+ +---+
+      // list[0]: |0   1| |2 3|  4
+      // list[1]: |0   1| |2 3|  4
+      //          | +---+ +---+
+      //          | | +-------+
+      // list[2]: |0| |1   2 3|  4
+      //          +-+ +-------+
+      flush_memtable_ids = {3, 3, 3};
+    } else {
+      //          +-----+ +---+ +-+
+      // list[0]: |0   1| |2 3| |4|
+      // list[1]: |0   1| |2 3| |4|
+      //          | +---+ +---+ | |
+      //          | | +-------+ | |
+      // list[2]: |0| |1   2 3| |4|
+      //          +-+ +-------+ +-+
+      flush_memtable_ids = {4, 4, 4};
+    }
+    assert(num_cfs == static_cast<int>(flush_memtable_ids.size()));
+
+    // Pick memtables to flush
+    for (int i = 0; i != num_cfs; ++i) {
+      flush_candidates[i].clear();
+      lists[i]->PickMemtablesToFlush(&flush_memtable_ids[i],
+                                     &flush_candidates[i]);
+      for (auto mem : flush_candidates[i]) {
+        mem->TEST_AtomicFlushSequenceNumber() = SequenceNumber(k);
+      }
+      if (prev_memtable_ids.empty()) {
+        ASSERT_EQ(flush_memtable_ids[i] - 0 + 1, flush_candidates[i].size());
+      } else {
+        ASSERT_EQ(flush_memtable_ids[i] - prev_memtable_ids[i],
+                  flush_candidates[i].size());
+      }
+      ASSERT_EQ(num_tables_per_cf, lists[i]->NumNotFlushed());
+      ASSERT_FALSE(lists[i]->HasFlushRequested());
+      if (flush_memtable_ids[i] == num_tables_per_cf - 1) {
+        ASSERT_FALSE(
+            lists[i]->imm_flush_needed.load(std::memory_order_acquire));
+      } else {
+        ASSERT_TRUE(lists[i]->imm_flush_needed.load(std::memory_order_acquire));
+      }
+    }
+    prev_memtable_ids = flush_memtable_ids;
+
+    if (k < 3) {
+      for (const auto& mems : flush_candidates) {
+        uint64_t file_num = file_number.fetch_add(1);
+        for (auto m : mems) {
+          m->TEST_SetFlushCompleted(true);
+          m->TEST_SetFileNumber(file_num);
+        }
+      }
+    }
+
+    if (k == 0) {
+      // Rollback first pick of tables
+      for (int i = 0; i != num_cfs; ++i) {
+        auto list = lists[i];
+        const auto& mems = flush_candidates[i];
+        for (auto m : mems) {
+          m->TEST_SetFileNumber(0);
+        }
+        list->RollbackMemtableFlush(flush_candidates[i], 0);
+        ASSERT_TRUE(list->IsFlushPending());
+        ASSERT_TRUE(list->imm_flush_needed.load(std::memory_order_acquire));
+      }
+      prev_memtable_ids.clear();
+    }
+
+    if (k == 3) {
+      for (int i = 0; i != num_cfs; ++i) {
+        to_flush.emplace_back(&flush_candidates[i]);
+      }
+    }
+  }
+
+  s = Mock_InstallMemtableFlushResults(lists, cf_ids, mutable_cf_options_list,
+                                       to_flush, &to_delete);
+  ASSERT_OK(s);
+
+  to_delete.clear();
+  for (auto list : lists) {
+    list->current()->Unref(&to_delete);
+    delete list;
+  }
+  for (auto& mutable_cf_options : mutable_cf_options_list) {
+    if (mutable_cf_options != nullptr) {
+      delete mutable_cf_options;
+      mutable_cf_options = nullptr;
+    }
+  }
+  // All memtables in tables array must have been flushed, thus ready to be
+  // deleted.
+  ASSERT_EQ(to_delete.size(), tables.size() * tables.front().size());
+  for (const auto& m : to_delete) {
+    // Refcount should be 0 after calling InstallMemtableFlushResults.
+    // Verify this by Ref'ing and then Unref'ing.
+    m->Ref();
+    ASSERT_EQ(m, m->Unref());
+    delete m;
+  }
+  to_delete.clear();
+}
+
+TEST_F(MemTableListTest, HasOlderAtomicFlush) {
+  const size_t num_cfs = 3;
+  const size_t num_memtables_per_cf = 2;
+  SequenceNumber seq = 1;
+  Status s;
+
+  auto factory = std::make_shared<SkipListFactory>();
+  options.memtable_factory = factory;
+  ImmutableCFOptions ioptions(options);
+  InternalKeyComparator cmp(BytewiseComparator());
+  WriteBufferManager wb(options.db_write_buffer_size);
+  autovector<MemTable*> to_delete;
+
+  // Create MemTableLists
+  int min_write_buffer_number_to_merge = 3;
+  int max_write_buffer_number_to_maintain = 7;
+  autovector<MemTableList*> lists;
+  for (size_t i = 0; i != num_cfs; ++i) {
+    lists.emplace_back(new MemTableList(min_write_buffer_number_to_merge,
+                                        max_write_buffer_number_to_maintain));
+  }
+
+  autovector<uint32_t> cf_ids;
+  std::vector<std::vector<MemTable*>> tables;
+  autovector<const MutableCFOptions*> mutable_cf_options_list;
+  uint32_t cf_id = 0;
+  for (size_t k = 0; k != num_cfs; ++k) {
+    std::vector<MemTable*> elem;
+    mutable_cf_options_list.emplace_back(new MutableCFOptions(options));
+    uint64_t memtable_id = 0;
+    for (int i = 0; i != num_memtables_per_cf; ++i) {
+      MemTable* mem =
+          new MemTable(cmp, ioptions, *(mutable_cf_options_list.back()), &wb,
+                       kMaxSequenceNumber, cf_id);
+      mem->SetID(memtable_id++);
+      mem->Ref();
+
+      std::string value;
+
+      mem->Add(++seq, kTypeValue, "key1", ToString(i));
+      mem->Add(++seq, kTypeValue, "keyN" + ToString(i), "valueN");
+      mem->Add(++seq, kTypeValue, "keyX" + ToString(i), "value");
+      mem->Add(++seq, kTypeValue, "keyM" + ToString(i), "valueM");
+      mem->Add(++seq, kTypeDeletion, "keyX" + ToString(i), "");
+
+      elem.push_back(mem);
+    }
+    tables.emplace_back(elem);
+    cf_ids.push_back(cf_id++);
+  }
+
+  // Add tables to column families' immutable memtable lists
+  for (size_t i = 0; i != num_cfs; ++i) {
+    for (size_t j = 0; j != num_memtables_per_cf; ++j) {
+      lists[i]->Add(tables[i][j], &to_delete);
+    }
+    lists[i]->FlushRequested();
+    ASSERT_EQ(num_memtables_per_cf, lists[i]->NumNotFlushed());
+    ASSERT_TRUE(lists[i]->IsFlushPending());
+    ASSERT_TRUE(lists[i]->imm_flush_needed.load(std::memory_order_acquire));
+  }
+  std::vector<autovector<MemTable*>> flush_candidates(num_cfs);
+  for (size_t i = 0; i != num_cfs; ++i) {
+    lists[i]->PickMemtablesToFlush(nullptr, &flush_candidates[i]);
+    for (auto m : flush_candidates[i]) {
+      m->TEST_AtomicFlushSequenceNumber() = 123;
+    }
+    lists[i]->RollbackMemtableFlush(flush_candidates[i], 0);
+  }
+  uint64_t memtable_id = num_memtables_per_cf - 1;
+  autovector<MemTable*> other_flush_candidates;
+  lists[0]->PickMemtablesToFlush(&memtable_id, &other_flush_candidates);
+  for (auto m : other_flush_candidates) {
+    m->TEST_AtomicFlushSequenceNumber() = 124;
+    m->TEST_SetFlushCompleted(true);
+    m->TEST_SetFileNumber(1);
+  }
+  autovector<const autovector<MemTable*>*> to_flush;
+  to_flush.emplace_back(&other_flush_candidates);
+  bool has_older_unfinished_atomic_flush = false;
+  bool found_batch_to_commit = false;
+
+  SyncPoint::GetInstance()->SetCallBack(
+      "MemTableList::TryInstallMemtableFlushResults:"
+      "HasOlderUnfinishedAtomicFlush:0",
+      [&](void* /*arg*/) { has_older_unfinished_atomic_flush = true; });
+  SyncPoint::GetInstance()->SetCallBack(
+      "MemTableList::TryInstallMemtableFlushResults:FoundBatchToCommit:0",
+      [&](void* /*arg*/) { found_batch_to_commit = true; });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  s = Mock_InstallMemtableFlushResults(lists, cf_ids, mutable_cf_options_list,
+                                       to_flush, &to_delete);
+  ASSERT_OK(s);
+  ASSERT_TRUE(has_older_unfinished_atomic_flush);
+  ASSERT_FALSE(found_batch_to_commit);
+
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  ASSERT_TRUE(to_delete.empty());
+  for (auto list : lists) {
+    list->current()->Unref(&to_delete);
+    delete list;
+  }
+  lists.clear();
+  ASSERT_EQ(num_cfs * num_memtables_per_cf, to_delete.size());
+  for (auto m : to_delete) {
+    m->Ref();
+    ASSERT_EQ(m, m->Unref());
+    delete m;
+  }
+  to_delete.clear();
+  for (auto& opts : mutable_cf_options_list) {
+    delete opts;
+    opts = nullptr;
+  }
+  mutable_cf_options_list.clear();
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
diff --git a/3rdParty/rocksdb/v5.16.X/db/merge_context.h b/3rdParty/rocksdb/v5.18.X/db/merge_context.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/merge_context.h
rename to 3rdParty/rocksdb/v5.18.X/db/merge_context.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/merge_helper.cc b/3rdParty/rocksdb/v5.18.X/db/merge_helper.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/merge_helper.cc
rename to 3rdParty/rocksdb/v5.18.X/db/merge_helper.cc
index dc6baa9630..6f7e760eca 100644
--- a/3rdParty/rocksdb/v5.16.X/db/merge_helper.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/merge_helper.cc
@@ -110,8 +110,11 @@ Status MergeHelper::TimedFullMerge(const MergeOperator* merge_operator,
 //       keys_ stores the list of keys encountered while merging.
 //       operands_ stores the list of merge operands encountered while merging.
 //       keys_[i] corresponds to operands_[i] for each i.
+//
+// TODO: Avoid the snapshot stripe map lookup in CompactionRangeDelAggregator
+// and just pass the StripeRep corresponding to the stripe being merged.
 Status MergeHelper::MergeUntil(InternalIterator* iter,
-                               RangeDelAggregator* range_del_agg,
+                               CompactionRangeDelAggregatorV2* range_del_agg,
                                const SequenceNumber stop_before,
                                const bool at_bottom) {
   // Get a copy of the internal key, before it's invalidated by iter->Next()
diff --git a/3rdParty/rocksdb/v5.16.X/db/merge_helper.h b/3rdParty/rocksdb/v5.18.X/db/merge_helper.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/merge_helper.h
rename to 3rdParty/rocksdb/v5.18.X/db/merge_helper.h
index abb1e17563..1c92a34920 100644
--- a/3rdParty/rocksdb/v5.16.X/db/merge_helper.h
+++ b/3rdParty/rocksdb/v5.18.X/db/merge_helper.h
@@ -3,8 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 //
-#ifndef MERGE_HELPER_H
-#define MERGE_HELPER_H
+#pragma once
 
 #include <deque>
 #include <string>
@@ -12,7 +11,7 @@
 
 #include "db/dbformat.h"
 #include "db/merge_context.h"
-#include "db/range_del_aggregator.h"
+#include "db/range_del_aggregator_v2.h"
 #include "db/snapshot_checker.h"
 #include "rocksdb/compaction_filter.h"
 #include "rocksdb/env.h"
@@ -79,7 +78,7 @@ class MergeHelper {
   //
   // REQUIRED: The first key in the input is not corrupted.
   Status MergeUntil(InternalIterator* iter,
-                    RangeDelAggregator* range_del_agg = nullptr,
+                    CompactionRangeDelAggregatorV2* range_del_agg = nullptr,
                     const SequenceNumber stop_before = 0,
                     const bool at_bottom = false);
 
@@ -193,5 +192,3 @@ class MergeOutputIterator {
 };
 
 } // namespace rocksdb
-
-#endif
diff --git a/3rdParty/rocksdb/v5.16.X/db/merge_helper_test.cc b/3rdParty/rocksdb/v5.18.X/db/merge_helper_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/merge_helper_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/merge_helper_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/merge_operator.cc b/3rdParty/rocksdb/v5.18.X/db/merge_operator.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/merge_operator.cc
rename to 3rdParty/rocksdb/v5.18.X/db/merge_operator.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/merge_test.cc b/3rdParty/rocksdb/v5.18.X/db/merge_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/merge_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/merge_test.cc
index 15f6f5125a..a24b3e7f97 100644
--- a/3rdParty/rocksdb/v5.16.X/db/merge_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/merge_test.cc
@@ -246,7 +246,7 @@ class MergeBasedCounters : public Counters {
 };
 
 void dumpDb(DB* db) {
-  auto it = unique_ptr<Iterator>(db->NewIterator(ReadOptions()));
+  auto it = std::unique_ptr<Iterator>(db->NewIterator(ReadOptions()));
   for (it->SeekToFirst(); it->Valid(); it->Next()) {
     //uint64_t value = DecodeFixed64(it->value().data());
     //std::cout << it->key().ToString() << ": " << value << std::endl;
diff --git a/3rdParty/rocksdb/v5.16.X/db/obsolete_files_test.cc b/3rdParty/rocksdb/v5.18.X/db/obsolete_files_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/obsolete_files_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/obsolete_files_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/options_file_test.cc b/3rdParty/rocksdb/v5.18.X/db/options_file_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/options_file_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/options_file_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/perf_context_test.cc b/3rdParty/rocksdb/v5.18.X/db/perf_context_test.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/db/perf_context_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/perf_context_test.cc
index c6b712cd81..e7dc976461 100644
--- a/3rdParty/rocksdb/v5.16.X/db/perf_context_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/perf_context_test.cc
@@ -10,6 +10,7 @@
 
 #include "monitoring/histogram.h"
 #include "monitoring/instrumented_mutex.h"
+#include "monitoring/perf_context_imp.h"
 #include "monitoring/thread_status_util.h"
 #include "port/port.h"
 #include "rocksdb/db.h"
@@ -469,7 +470,7 @@ void ProfileQueries(bool enabled_time = false) {
     ASSERT_GT(hist_num_memtable_checked.Average(), 0);
     // In read-only mode Get(), no super version operation is needed
     ASSERT_EQ(hist_get_post_process.Average(), 0);
-    ASSERT_EQ(hist_get_snapshot.Average(), 0);
+    ASSERT_GT(hist_get_snapshot.Average(), 0);
 
     ASSERT_GT(hist_mget.Average(), 0);
     ASSERT_GT(hist_mget_snapshot.Average(), 0);
@@ -579,18 +580,18 @@ TEST_F(PerfContextTest, SeekKeyComparison) {
 
 TEST_F(PerfContextTest, DBMutexLockCounter) {
   int stats_code[] = {0, static_cast<int>(DB_MUTEX_WAIT_MICROS)};
-  for (PerfLevel perf_level :
+  for (PerfLevel perf_level_test :
        {PerfLevel::kEnableTimeExceptForMutex, PerfLevel::kEnableTime}) {
     for (int c = 0; c < 2; ++c) {
     InstrumentedMutex mutex(nullptr, Env::Default(), stats_code[c]);
     mutex.Lock();
     rocksdb::port::Thread child_thread([&] {
-      SetPerfLevel(perf_level);
+      SetPerfLevel(perf_level_test);
       get_perf_context()->Reset();
       ASSERT_EQ(get_perf_context()->db_mutex_lock_nanos, 0);
       mutex.Lock();
       mutex.Unlock();
-      if (perf_level == PerfLevel::kEnableTimeExceptForMutex ||
+      if (perf_level_test == PerfLevel::kEnableTimeExceptForMutex ||
           stats_code[c] != DB_MUTEX_WAIT_MICROS) {
         ASSERT_EQ(get_perf_context()->db_mutex_lock_nanos, 0);
       } else {
@@ -686,7 +687,34 @@ TEST_F(PerfContextTest, MergeOperatorTime) {
 
   delete db;
 }
+
+TEST_F(PerfContextTest, PerfContextByLevelGetSet) {
+  get_perf_context()->Reset();
+  get_perf_context()->EnablePerLevelPerfContext();
+  PERF_COUNTER_BY_LEVEL_ADD(bloom_filter_full_positive, 1, 0);
+  PERF_COUNTER_BY_LEVEL_ADD(bloom_filter_useful, 1, 5);
+  PERF_COUNTER_BY_LEVEL_ADD(bloom_filter_useful, 1, 7);
+  PERF_COUNTER_BY_LEVEL_ADD(bloom_filter_useful, 1, 7);
+  PERF_COUNTER_BY_LEVEL_ADD(bloom_filter_full_true_positive, 1, 2);
+  ASSERT_EQ(
+      0, (*(get_perf_context()->level_to_perf_context))[0].bloom_filter_useful);
+  ASSERT_EQ(
+      1, (*(get_perf_context()->level_to_perf_context))[5].bloom_filter_useful);
+  ASSERT_EQ(
+      2, (*(get_perf_context()->level_to_perf_context))[7].bloom_filter_useful);
+  ASSERT_EQ(1, (*(get_perf_context()->level_to_perf_context))[0]
+                   .bloom_filter_full_positive);
+  ASSERT_EQ(1, (*(get_perf_context()->level_to_perf_context))[2]
+                   .bloom_filter_full_true_positive);
+  std::string zero_excluded = get_perf_context()->ToString(true);
+  ASSERT_NE(std::string::npos,
+            zero_excluded.find("bloom_filter_useful = 1@level5, 2@level7"));
+  ASSERT_NE(std::string::npos,
+            zero_excluded.find("bloom_filter_full_positive = 1@level0"));
+  ASSERT_NE(std::string::npos,
+            zero_excluded.find("bloom_filter_full_true_positive = 1@level2"));
 }
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);
diff --git a/3rdParty/rocksdb/v5.16.X/db/pinned_iterators_manager.h b/3rdParty/rocksdb/v5.18.X/db/pinned_iterators_manager.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/pinned_iterators_manager.h
rename to 3rdParty/rocksdb/v5.18.X/db/pinned_iterators_manager.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/plain_table_db_test.cc b/3rdParty/rocksdb/v5.18.X/db/plain_table_db_test.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/plain_table_db_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/plain_table_db_test.cc
index dffd77ddca..a98b1629a6 100644
--- a/3rdParty/rocksdb/v5.16.X/db/plain_table_db_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/plain_table_db_test.cc
@@ -50,10 +50,11 @@ TEST_F(PlainTableKeyDecoderTest, ReadNonMmap) {
   test::StringSource* string_source =
       new test::StringSource(contents, 0, false);
 
-  unique_ptr<RandomAccessFileReader> file_reader(
+  std::unique_ptr<RandomAccessFileReader> file_reader(
       test::GetRandomAccessFileReader(string_source));
-  unique_ptr<PlainTableReaderFileInfo> file_info(new PlainTableReaderFileInfo(
-      std::move(file_reader), EnvOptions(), kLength));
+  std::unique_ptr<PlainTableReaderFileInfo> file_info(
+      new PlainTableReaderFileInfo(std::move(file_reader), EnvOptions(),
+                                   kLength));
 
   {
     PlainTableFileReader reader(file_info.get());
@@ -260,7 +261,7 @@ class TestPlainTableReader : public PlainTableReader {
                        int bloom_bits_per_key, double hash_table_ratio,
                        size_t index_sparseness,
                        const TableProperties* table_properties,
-                       unique_ptr<RandomAccessFileReader>&& file,
+                       std::unique_ptr<RandomAccessFileReader>&& file,
                        const ImmutableCFOptions& ioptions,
                        const SliceTransform* prefix_extractor,
                        bool* expect_bloom_not_match, bool store_index_in_file,
@@ -327,8 +328,8 @@ class TestPlainTableFactory : public PlainTableFactory {
 
   Status NewTableReader(
       const TableReaderOptions& table_reader_options,
-      unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
-      unique_ptr<TableReader>* table,
+      std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+      std::unique_ptr<TableReader>* table,
       bool /*prefetch_index_and_filter_in_cache*/) const override {
     TableProperties* props = nullptr;
     auto s =
diff --git a/3rdParty/rocksdb/v5.16.X/db/pre_release_callback.h b/3rdParty/rocksdb/v5.18.X/db/pre_release_callback.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/pre_release_callback.h
rename to 3rdParty/rocksdb/v5.18.X/db/pre_release_callback.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/prefix_test.cc b/3rdParty/rocksdb/v5.18.X/db/prefix_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/prefix_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/prefix_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/range_del_aggregator.cc b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator.cc
similarity index 72%
rename from 3rdParty/rocksdb/v5.16.X/db/range_del_aggregator.cc
rename to 3rdParty/rocksdb/v5.18.X/db/range_del_aggregator.cc
index 201345c919..331758558c 100644
--- a/3rdParty/rocksdb/v5.16.X/db/range_del_aggregator.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator.cc
@@ -11,19 +11,21 @@
 namespace rocksdb {
 
 struct TombstoneStartKeyComparator {
-  TombstoneStartKeyComparator(const Comparator* c) : cmp(c) {}
+  explicit TombstoneStartKeyComparator(const InternalKeyComparator* c)
+      : cmp(c) {}
 
-  bool operator()(const RangeTombstone& a, const RangeTombstone& b) const {
+  bool operator()(const TruncatedRangeTombstone& a,
+                  const TruncatedRangeTombstone& b) const {
     return cmp->Compare(a.start_key_, b.start_key_) < 0;
   }
 
-  const Comparator* cmp;
+  const InternalKeyComparator* cmp;
 };
 
 // An UncollapsedRangeDelMap is quick to create but slow to answer ShouldDelete
 // queries.
 class UncollapsedRangeDelMap : public RangeDelMap {
-  typedef std::multiset<RangeTombstone, TombstoneStartKeyComparator> Rep;
+  typedef std::vector<TruncatedRangeTombstone> Rep;
 
   class Iterator : public RangeDelIterator {
     const Rep& rep_;
@@ -35,54 +37,66 @@ class UncollapsedRangeDelMap : public RangeDelMap {
     void Next() override { iter_++; }
 
     void Seek(const Slice&) override {
-      fprintf(stderr, "UncollapsedRangeDelMap::Iterator::Seek unimplemented\n");
+      fprintf(stderr,
+              "UncollapsedRangeDelMap::Iterator::Seek(Slice&) unimplemented\n");
       abort();
     }
 
-    RangeTombstone Tombstone() const override { return *iter_; }
+    void Seek(const ParsedInternalKey&) override {
+      fprintf(stderr,
+              "UncollapsedRangeDelMap::Iterator::Seek(ParsedInternalKey&) "
+              "unimplemented\n");
+      abort();
+    }
+
+    RangeTombstone Tombstone() const override { return iter_->Tombstone(); }
   };
 
   Rep rep_;
-  const Comparator* ucmp_;
+  const InternalKeyComparator* icmp_;
 
  public:
-  UncollapsedRangeDelMap(const Comparator* ucmp)
-      : rep_(TombstoneStartKeyComparator(ucmp)), ucmp_(ucmp) {}
+  explicit UncollapsedRangeDelMap(const InternalKeyComparator* icmp)
+      : icmp_(icmp) {}
 
   bool ShouldDelete(const ParsedInternalKey& parsed,
                     RangeDelPositioningMode mode) override {
     (void)mode;
     assert(mode == RangeDelPositioningMode::kFullScan);
     for (const auto& tombstone : rep_) {
-      if (ucmp_->Compare(parsed.user_key, tombstone.start_key_) < 0) {
-        break;
+      if (icmp_->Compare(parsed, tombstone.start_key_) < 0) {
+        continue;
       }
       if (parsed.sequence < tombstone.seq_ &&
-          ucmp_->Compare(parsed.user_key, tombstone.end_key_) < 0) {
+          icmp_->Compare(parsed, tombstone.end_key_) < 0) {
         return true;
       }
     }
     return false;
   }
 
-  bool IsRangeOverlapped(const Slice& start, const Slice& end) override {
+  bool IsRangeOverlapped(const ParsedInternalKey& start,
+                         const ParsedInternalKey& end) override {
     for (const auto& tombstone : rep_) {
-      if (ucmp_->Compare(start, tombstone.end_key_) < 0 &&
-          ucmp_->Compare(tombstone.start_key_, end) <= 0 &&
-          ucmp_->Compare(tombstone.start_key_, tombstone.end_key_) < 0) {
+      if (icmp_->Compare(start, tombstone.end_key_) < 0 &&
+          icmp_->Compare(tombstone.start_key_, end) <= 0 &&
+          icmp_->Compare(tombstone.start_key_, tombstone.end_key_) < 0) {
         return true;
       }
     }
     return false;
   }
 
-  void AddTombstone(RangeTombstone tombstone) override { rep_.emplace(tombstone); }
+  void AddTombstone(TruncatedRangeTombstone tombstone) override {
+    rep_.emplace_back(tombstone);
+  }
 
   size_t Size() const override { return rep_.size(); }
 
   void InvalidatePosition() override {}  // no-op
 
   std::unique_ptr<RangeDelIterator> NewIterator() override {
+    std::sort(rep_.begin(), rep_.end(), TombstoneStartKeyComparator(icmp_));
     return std::unique_ptr<RangeDelIterator>(new Iterator(this->rep_));
   }
 };
@@ -124,7 +138,9 @@ class UncollapsedRangeDelMap : public RangeDelMap {
 // compared against the map entry g → 3 and determined to be uncovered. By
 // contrast, the key h @ 2 would be determined to be covered.
 class CollapsedRangeDelMap : public RangeDelMap {
-  typedef std::map<Slice, SequenceNumber, stl_wrappers::LessOfComparator> Rep;
+  typedef std::map<ParsedInternalKey, SequenceNumber,
+                   ParsedInternalKeyComparator>
+      Rep;
 
   class Iterator : public RangeDelIterator {
     void MaybeSeekPastSentinel() {
@@ -146,7 +162,12 @@ class CollapsedRangeDelMap : public RangeDelMap {
       MaybeSeekPastSentinel();
     }
 
-    void Seek(const Slice& target) override {
+    void Seek(const Slice&) override {
+      fprintf(stderr, "CollapsedRangeDelMap::Iterator::Seek(Slice&) unimplemented\n");
+      abort();
+    }
+
+    void Seek(const ParsedInternalKey& target) override {
       iter_ = rep_.upper_bound(target);
       if (iter_ != rep_.begin()) {
         iter_--;
@@ -159,8 +180,8 @@ class CollapsedRangeDelMap : public RangeDelMap {
       assert(std::next(iter_) != rep_.end());
       assert(iter_->second != 0);
       RangeTombstone tombstone;
-      tombstone.start_key_ = iter_->first;
-      tombstone.end_key_ = std::next(iter_)->first;
+      tombstone.start_key_ = iter_->first.user_key;
+      tombstone.end_key_ = std::next(iter_)->first.user_key;
       tombstone.seq_ = iter_->second;
       return tombstone;
     }
@@ -168,12 +189,12 @@ class CollapsedRangeDelMap : public RangeDelMap {
 
   Rep rep_;
   Rep::iterator iter_;
-  const Comparator* ucmp_;
+  const InternalKeyComparator* icmp_;
 
  public:
-  CollapsedRangeDelMap(const Comparator* ucmp) 
-    : rep_(stl_wrappers::LessOfComparator(ucmp)), 
-      ucmp_(ucmp) {
+  explicit CollapsedRangeDelMap(const InternalKeyComparator* icmp)
+    : rep_(ParsedInternalKeyComparator(icmp)),
+      icmp_(icmp) {
     InvalidatePosition();
   }
 
@@ -192,29 +213,29 @@ class CollapsedRangeDelMap : public RangeDelMap {
       case RangeDelPositioningMode::kForwardTraversal:
         assert(iter_ != rep_.end());
         if (iter_ == rep_.begin() &&
-            ucmp_->Compare(parsed.user_key, iter_->first) < 0) {
+            icmp_->Compare(parsed, iter_->first) < 0) {
           // before start of deletion intervals
           return false;
         }
         while (std::next(iter_) != rep_.end() &&
-               ucmp_->Compare(std::next(iter_)->first, parsed.user_key) <= 0) {
+               icmp_->Compare(std::next(iter_)->first, parsed) <= 0) {
           ++iter_;
         }
         break;
       case RangeDelPositioningMode::kBackwardTraversal:
         assert(iter_ != rep_.end());
         while (iter_ != rep_.begin() &&
-               ucmp_->Compare(parsed.user_key, iter_->first) < 0) {
+               icmp_->Compare(parsed, iter_->first) < 0) {
           --iter_;
         }
         if (iter_ == rep_.begin() &&
-            ucmp_->Compare(parsed.user_key, iter_->first) < 0) {
+            icmp_->Compare(parsed, iter_->first) < 0) {
           // before start of deletion intervals
           return false;
         }
         break;
       case RangeDelPositioningMode::kBinarySearch:
-        iter_ = rep_.upper_bound(parsed.user_key);
+        iter_ = rep_.upper_bound(parsed);
         if (iter_ == rep_.begin()) {
           // before start of deletion intervals
           return false;
@@ -223,21 +244,22 @@ class CollapsedRangeDelMap : public RangeDelMap {
         break;
     }
     assert(iter_ != rep_.end() &&
-           ucmp_->Compare(iter_->first, parsed.user_key) <= 0);
+           icmp_->Compare(iter_->first, parsed) <= 0);
     assert(std::next(iter_) == rep_.end() ||
-           ucmp_->Compare(parsed.user_key, std::next(iter_)->first) < 0);
+           icmp_->Compare(parsed, std::next(iter_)->first) < 0);
     return parsed.sequence < iter_->second;
   }
 
-  bool IsRangeOverlapped(const Slice&, const Slice&) override {
+  bool IsRangeOverlapped(const ParsedInternalKey&,
+                         const ParsedInternalKey&) override {
     // Unimplemented because the only client of this method, file ingestion,
     // uses uncollapsed maps.
     fprintf(stderr, "CollapsedRangeDelMap::IsRangeOverlapped unimplemented");
     abort();
   }
 
-  void AddTombstone(RangeTombstone t) override {
-    if (ucmp_->Compare(t.start_key_, t.end_key_) >= 0 || t.seq_ == 0) {
+  void AddTombstone(TruncatedRangeTombstone t) override {
+    if (icmp_->Compare(t.start_key_, t.end_key_) >= 0 || t.seq_ == 0) {
       // The tombstone covers no keys. Nothing to do.
       return;
     }
@@ -270,7 +292,8 @@ class CollapsedRangeDelMap : public RangeDelMap {
       end_seq = prev_seq();
       Rep::iterator pit;
       if (it != rep_.begin() && (pit = std::prev(it)) != rep_.begin() &&
-          ucmp_->Compare(pit->first, t.start_key_) == 0 && std::prev(pit)->second == t.seq_) {
+          icmp_->Compare(pit->first, t.start_key_) == 0 &&
+          std::prev(pit)->second == t.seq_) {
         // The new tombstone starts at the end of an existing tombstone with an
         // identical seqno:
         //
@@ -295,7 +318,7 @@ class CollapsedRangeDelMap : public RangeDelMap {
     }
 
     // Look at all the existing transitions that overlap the new tombstone.
-    while (it != rep_.end() && ucmp_->Compare(it->first, t.end_key_) < 0) {
+    while (it != rep_.end() && icmp_->Compare(it->first, t.end_key_) < 0) {
       if (t.seq_ >= it->second) {
         // The transition is to an existing tombstone that the new tombstone
         // covers. Save the covered tombstone's seqno. We'll need to return to
@@ -341,12 +364,14 @@ class CollapsedRangeDelMap : public RangeDelMap {
 
     if (t.seq_ == prev_seq()) {
       // The new tombstone is unterminated in the map.
-      if (it != rep_.end() && t.seq_ == it->second && ucmp_->Compare(it->first, t.end_key_) == 0) {
+      if (it != rep_.end() && t.seq_ == it->second &&
+          icmp_->Compare(it->first, t.end_key_) == 0) {
         // The new tombstone ends at the start of another tombstone with an
         // identical seqno. Merge the tombstones by removing the existing
         // tombstone's start key.
         rep_.erase(it);
-      } else if (end_seq == prev_seq() || (it != rep_.end() && end_seq == it->second)) {
+      } else if (end_seq == prev_seq() ||
+                 (it != rep_.end() && end_seq == it->second)) {
         // The new tombstone is implicitly ended because its end point is
         // contained within an existing tombstone with the same seqno:
         //
@@ -361,7 +386,8 @@ class CollapsedRangeDelMap : public RangeDelMap {
         // Install one that returns to the last seqno we covered. Because end
         // keys are exclusive, if there's an existing transition at t.end_key_,
         // it takes precedence over the transition that we install here.
-        rep_.emplace(t.end_key_, end_seq);  // emplace is a noop if existing entry
+        rep_.emplace(t.end_key_,
+                     end_seq);  // emplace is a noop if existing entry
       }
     } else {
       // The new tombstone is implicitly ended because its end point is covered
@@ -374,7 +400,7 @@ class CollapsedRangeDelMap : public RangeDelMap {
     }
   }
 
-  size_t Size() const override { return rep_.size() - 1; }
+  size_t Size() const override { return rep_.empty() ? 0 : rep_.size() - 1; }
 
   void InvalidatePosition() override { iter_ = rep_.end(); }
 
@@ -403,20 +429,18 @@ RangeDelAggregator::RangeDelAggregator(const InternalKeyComparator& icmp,
 void RangeDelAggregator::InitRep(const std::vector<SequenceNumber>& snapshots) {
   assert(rep_ == nullptr);
   rep_.reset(new Rep());
-  for (auto snapshot : snapshots) {
-    rep_->stripe_map_.emplace(snapshot, NewRangeDelMap());
-  }
+  rep_->snapshots_ = snapshots;
   // Data newer than any snapshot falls in this catch-all stripe
-  rep_->stripe_map_.emplace(kMaxSequenceNumber, NewRangeDelMap());
+  rep_->snapshots_.emplace_back(kMaxSequenceNumber);
   rep_->pinned_iters_mgr_.StartPinning();
 }
 
 std::unique_ptr<RangeDelMap> RangeDelAggregator::NewRangeDelMap() {
   RangeDelMap* tombstone_map;
   if (collapse_deletions_) {
-    tombstone_map = new CollapsedRangeDelMap(icmp_.user_comparator());
+    tombstone_map = new CollapsedRangeDelMap(&icmp_);
   } else {
-    tombstone_map = new UncollapsedRangeDelMap(icmp_.user_comparator());
+    tombstone_map = new UncollapsedRangeDelMap(&icmp_);
   }
   return std::unique_ptr<RangeDelMap>(tombstone_map);
 }
@@ -427,19 +451,20 @@ bool RangeDelAggregator::ShouldDeleteImpl(const Slice& internal_key,
   ParsedInternalKey parsed;
   if (!ParseInternalKey(internal_key, &parsed)) {
     assert(false);
+    return false;
   }
-  return ShouldDelete(parsed, mode);
+  return ShouldDeleteImpl(parsed, mode);
 }
 
 bool RangeDelAggregator::ShouldDeleteImpl(const ParsedInternalKey& parsed,
                                           RangeDelPositioningMode mode) {
   assert(IsValueType(parsed.type));
   assert(rep_ != nullptr);
-  auto& tombstone_map = GetRangeDelMap(parsed.sequence);
-  if (tombstone_map.IsEmpty()) {
+  auto* tombstone_map = GetRangeDelMapIfExists(parsed.sequence);
+  if (tombstone_map == nullptr || tombstone_map->IsEmpty()) {
     return false;
   }
-  return tombstone_map.ShouldDelete(parsed, mode);
+  return tombstone_map->ShouldDelete(parsed, mode);
 }
 
 bool RangeDelAggregator::IsRangeOverlapped(const Slice& start,
@@ -450,8 +475,10 @@ bool RangeDelAggregator::IsRangeOverlapped(const Slice& start,
   if (rep_ == nullptr) {
     return false;
   }
+  ParsedInternalKey start_ikey(start, kMaxSequenceNumber, kMaxValue);
+  ParsedInternalKey end_ikey(end, 0, static_cast<ValueType>(0));
   for (const auto& stripe : rep_->stripe_map_) {
-    if (stripe.second->IsRangeOverlapped(start, end)) {
+    if (stripe.second.first->IsRangeOverlapped(start_ikey, end_ikey)) {
       return true;
     }
   }
@@ -490,41 +517,49 @@ Status RangeDelAggregator::AddTombstones(
     if (!parsed) {
       return Status::Corruption("Unable to parse range tombstone InternalKey");
     }
-    RangeTombstone tombstone;
+    Slice end_user_key;
     if (input->IsValuePinned()) {
-      tombstone = RangeTombstone(parsed_key, input->value());
+      end_user_key = input->value();
     } else {
       // The tombstone map holds slices into the iterator's memory. Make a
       // copy of the value if it is not pinned.
       rep_->pinned_slices_.emplace_back(input->value().data(),
                                         input->value().size());
-      tombstone = RangeTombstone(parsed_key, rep_->pinned_slices_.back());
+      end_user_key = rep_->pinned_slices_.back();
     }
+    ParsedInternalKey start_key(parsed_key.user_key, kMaxSequenceNumber,
+                                kMaxValue);
+    ParsedInternalKey end_key(end_user_key, kMaxSequenceNumber, kMaxValue);
     // Truncate the tombstone to the range [smallest, largest].
     if (smallest != nullptr) {
-      if (icmp_.user_comparator()->Compare(
-              tombstone.start_key_, smallest->user_key()) < 0) {
-        tombstone.start_key_ = smallest->user_key();
+      ParsedInternalKey parsed_smallest;
+      if (ParseInternalKey(smallest->Encode(), &parsed_smallest) &&
+          icmp_.Compare(start_key, parsed_smallest) < 0) {
+        start_key.user_key = parsed_smallest.user_key;
+        start_key.sequence = parsed_smallest.sequence;
       }
     }
     if (largest != nullptr) {
-      // This is subtly correct despite the discrepancy between
-      // FileMetaData::largest being inclusive while RangeTombstone::end_key_
-      // is exclusive. A tombstone will only extend past the bounds of an
-      // sstable if its end-key is the largest key in the table. If that
-      // occurs, the largest key for the table is set based on the smallest
-      // key in the next table in the level. In that case, largest->user_key()
-      // is not actually a key in the current table and thus we can use it as
-      // the exclusive end-key for the tombstone.
-      if (icmp_.user_comparator()->Compare(
-              tombstone.end_key_, largest->user_key()) > 0) {
-        // The largest key should be a tombstone sentinel key.
-        assert(GetInternalKeySeqno(largest->Encode()) == kMaxSequenceNumber);
-        tombstone.end_key_ = largest->user_key();
+      ParsedInternalKey parsed_largest;
+      if (ParseInternalKey(largest->Encode(), &parsed_largest) &&
+          icmp_.Compare(end_key, parsed_largest) > 0) {
+        end_key.user_key = parsed_largest.user_key;
+        if (parsed_largest.sequence != kMaxSequenceNumber) {
+          // The same user key straddles two adjacent sstables. To make sure we
+          // can truncate to a range that includes the largest point key in the
+          // first sstable, set the tombstone end key's sequence number to 1
+          // less than the largest key.
+          assert(parsed_largest.sequence != 0);
+          end_key.sequence = parsed_largest.sequence - 1;
+        } else {
+          // The SST file boundary was artificially extended by a range tombstone.
+          // We will not see any entries in this SST with this user key, so we
+          // can leave the seqnum at kMaxSequenceNumber.
+        }
       }
     }
-    auto seq = tombstone.seq_;
-    GetRangeDelMap(seq).AddTombstone(std::move(tombstone));
+    TruncatedRangeTombstone tombstone(start_key, end_key, parsed_key.sequence);
+    GetRangeDelMap(parsed_key.sequence).AddTombstone(std::move(tombstone));
     input->Next();
   }
   if (!first_iter) {
@@ -538,24 +573,42 @@ void RangeDelAggregator::InvalidateRangeDelMapPositions() {
     return;
   }
   for (auto& stripe : rep_->stripe_map_) {
-    stripe.second->InvalidatePosition();
+    stripe.second.first->InvalidatePosition();
   }
 }
 
+RangeDelMap* RangeDelAggregator::GetRangeDelMapIfExists(SequenceNumber seq) {
+  assert(rep_ != nullptr);
+  // The stripe includes seqnum for the snapshot above and excludes seqnum for
+  // the snapshot below.
+  if (rep_->stripe_map_.empty()) {
+    return nullptr;
+  }
+  StripeMap::iterator iter = rep_->stripe_map_.lower_bound(seq);
+  if (iter == rep_->stripe_map_.end()) {
+    return nullptr;
+  }
+  size_t snapshot_idx = iter->second.second;
+  if (snapshot_idx > 0 && seq <= rep_->snapshots_[snapshot_idx - 1]) {
+    return nullptr;
+  }
+  return iter->second.first.get();
+}
+
 RangeDelMap& RangeDelAggregator::GetRangeDelMap(SequenceNumber seq) {
   assert(rep_ != nullptr);
   // The stripe includes seqnum for the snapshot above and excludes seqnum for
   // the snapshot below.
-  StripeMap::iterator iter;
-  if (seq > 0) {
-    // upper_bound() checks strict inequality so need to subtract one
-    iter = rep_->stripe_map_.upper_bound(seq - 1);
-  } else {
-    iter = rep_->stripe_map_.begin();
-  }
+  std::vector<SequenceNumber>::iterator iter =
+      std::lower_bound(rep_->snapshots_.begin(), rep_->snapshots_.end(), seq);
   // catch-all stripe justifies this assertion in either of above cases
-  assert(iter != rep_->stripe_map_.end());
-  return *iter->second;
+  assert(iter != rep_->snapshots_.end());
+  if (rep_->stripe_map_.find(*iter) == rep_->stripe_map_.end()) {
+    rep_->stripe_map_.emplace(
+        *iter,
+        std::make_pair(NewRangeDelMap(), iter - rep_->snapshots_.begin()));
+  }
+  return *rep_->stripe_map_[*iter].first;
 }
 
 bool RangeDelAggregator::IsEmpty() {
@@ -563,7 +616,7 @@ bool RangeDelAggregator::IsEmpty() {
     return true;
   }
   for (const auto& stripe : rep_->stripe_map_) {
-    if (!stripe.second->IsEmpty()) {
+    if (!stripe.second.first->IsEmpty()) {
       return false;
     }
   }
@@ -603,6 +656,11 @@ class MergingRangeDelIter : public RangeDelIterator {
   }
 
   void Seek(const Slice& target) override {
+    ParsedInternalKey ikey(target, kMaxSequenceNumber, kMaxValue);
+    Seek(ikey);
+  }
+
+  void Seek(const ParsedInternalKey& target) override {
     heap_.clear();
     for (auto& iter : iters_) {
       iter->Seek(target);
@@ -642,7 +700,7 @@ std::unique_ptr<RangeDelIterator> RangeDelAggregator::NewIterator() {
       new MergingRangeDelIter(icmp_.user_comparator()));
   if (rep_ != nullptr) {
     for (const auto& stripe : rep_->stripe_map_) {
-      iter->AddIterator(stripe.second->NewIterator());
+      iter->AddIterator(stripe.second.first->NewIterator());
     }
   }
   return std::move(iter);
diff --git a/3rdParty/rocksdb/v5.16.X/db/range_del_aggregator.h b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator.h
similarity index 79%
rename from 3rdParty/rocksdb/v5.16.X/db/range_del_aggregator.h
rename to 3rdParty/rocksdb/v5.18.X/db/range_del_aggregator.h
index 66088b3d4e..8a89ec9f1b 100644
--- a/3rdParty/rocksdb/v5.16.X/db/range_del_aggregator.h
+++ b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator.h
@@ -40,6 +40,35 @@ enum class RangeDelPositioningMode {
   kBinarySearch,
 };
 
+// TruncatedRangeTombstones are a slight generalization of regular
+// RangeTombstones that can represent truncations caused by SST boundaries.
+// Instead of using user keys to represent the start and end keys, they instead
+// use internal keys, whose sequence number indicates the sequence number of
+// the smallest/largest SST key (in the case where a tombstone is untruncated,
+// the sequence numbers will be kMaxSequenceNumber for both start and end
+// keys). Like RangeTombstones, TruncatedRangeTombstone are also
+// end-key-exclusive.
+struct TruncatedRangeTombstone {
+  TruncatedRangeTombstone(const ParsedInternalKey& sk,
+                          const ParsedInternalKey& ek, SequenceNumber s)
+      : start_key_(sk), end_key_(ek), seq_(s) {}
+
+  RangeTombstone Tombstone() const {
+    // The RangeTombstone returned here can cover less than the
+    // TruncatedRangeTombstone when its end key has a seqnum that is not
+    // kMaxSequenceNumber. Since this method is only used by RangeDelIterators
+    // (which in turn are only used during flush/compaction), we avoid this
+    // problem by using truncation boundaries spanning multiple SSTs, which
+    // are selected in a way that guarantee a clean break at the end key.
+    assert(end_key_.sequence == kMaxSequenceNumber);
+    return RangeTombstone(start_key_.user_key, end_key_.user_key, seq_);
+  }
+
+  ParsedInternalKey start_key_;
+  ParsedInternalKey end_key_;
+  SequenceNumber seq_;
+};
+
 // A RangeDelIterator iterates over range deletion tombstones.
 class RangeDelIterator {
  public:
@@ -47,7 +76,9 @@ class RangeDelIterator {
 
   virtual bool Valid() const = 0;
   virtual void Next() = 0;
+  // NOTE: the Slice passed to this method must be a user key.
   virtual void Seek(const Slice& target) = 0;
+  virtual void Seek(const ParsedInternalKey& target) = 0;
   virtual RangeTombstone Tombstone() const = 0;
 };
 
@@ -62,13 +93,14 @@ class RangeDelMap {
 
   virtual bool ShouldDelete(const ParsedInternalKey& parsed,
                             RangeDelPositioningMode mode) = 0;
-  virtual bool IsRangeOverlapped(const Slice& start, const Slice& end) = 0;
+  virtual bool IsRangeOverlapped(const ParsedInternalKey& start,
+                                 const ParsedInternalKey& end) = 0;
   virtual void InvalidatePosition() = 0;
 
   virtual size_t Size() const = 0;
   bool IsEmpty() const { return Size() == 0; }
 
-  virtual void AddTombstone(RangeTombstone tombstone) = 0;
+  virtual void AddTombstone(TruncatedRangeTombstone tombstone) = 0;
   virtual std::unique_ptr<RangeDelIterator> NewIterator() = 0;
 };
 
@@ -168,10 +200,15 @@ class RangeDelAggregator {
 
  private:
   // Maps snapshot seqnum -> map of tombstones that fall in that stripe, i.e.,
-  // their seqnums are greater than the next smaller snapshot's seqnum.
-  typedef std::map<SequenceNumber, std::unique_ptr<RangeDelMap>> StripeMap;
+  // their seqnums are greater than the next smaller snapshot's seqnum, and the
+  // corresponding index into the list of snapshots. Each entry is lazily
+  // initialized.
+  typedef std::map<SequenceNumber,
+                   std::pair<std::unique_ptr<RangeDelMap>, size_t>>
+      StripeMap;
 
   struct Rep {
+    std::vector<SequenceNumber> snapshots_;
     StripeMap stripe_map_;
     PinnedIteratorsManager pinned_iters_mgr_;
     std::list<std::string> pinned_slices_;
@@ -183,6 +220,7 @@ class RangeDelAggregator {
   void InitRep(const std::vector<SequenceNumber>& snapshots);
 
   std::unique_ptr<RangeDelMap> NewRangeDelMap();
+  RangeDelMap* GetRangeDelMapIfExists(SequenceNumber seq);
   RangeDelMap& GetRangeDelMap(SequenceNumber seq);
 
   SequenceNumber upper_bound_;
diff --git a/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_bench.cc b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_bench.cc
new file mode 100644
index 0000000000..0b82609601
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_bench.cc
@@ -0,0 +1,279 @@
+//  Copyright (c) 2018-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#ifndef GFLAGS
+#include <cstdio>
+int main() {
+  fprintf(stderr, "Please install gflags to run rocksdb tools\n");
+  return 1;
+}
+#else
+
+#include <iostream>
+#include <iomanip>
+#include <memory>
+#include <random>
+#include <set>
+#include <string>
+#include <vector>
+
+#include "db/range_del_aggregator.h"
+#include "db/range_del_aggregator_v2.h"
+#include "db/range_tombstone_fragmenter.h"
+#include "rocksdb/comparator.h"
+#include "rocksdb/env.h"
+#include "util/coding.h"
+#include "util/random.h"
+#include "util/stop_watch.h"
+#include "util/testutil.h"
+
+#include "util/gflags_compat.h"
+
+using GFLAGS_NAMESPACE::ParseCommandLineFlags;
+
+DEFINE_int32(num_range_tombstones, 1000, "number of range tombstones created");
+
+DEFINE_int32(num_runs, 1000, "number of test runs");
+
+DEFINE_int32(tombstone_start_upper_bound, 1000,
+             "exclusive upper bound on range tombstone start keys");
+
+DEFINE_int32(should_delete_upper_bound, 1000,
+             "exclusive upper bound on keys passed to ShouldDelete");
+
+DEFINE_double(tombstone_width_mean, 100.0, "average range tombstone width");
+
+DEFINE_double(tombstone_width_stddev, 0.0,
+              "standard deviation of range tombstone width");
+
+DEFINE_bool(use_collapsed, true, "use the collapsed range tombstone map");
+
+DEFINE_int32(seed, 0, "random number generator seed");
+
+DEFINE_int32(should_deletes_per_run, 1, "number of ShouldDelete calls per run");
+
+DEFINE_int32(add_tombstones_per_run, 1,
+             "number of AddTombstones calls per run");
+
+DEFINE_bool(use_v2_aggregator, false, "benchmark RangeDelAggregatorV2");
+
+namespace {
+
+struct Stats {
+  uint64_t time_add_tombstones = 0;
+  uint64_t time_first_should_delete = 0;
+  uint64_t time_rest_should_delete = 0;
+};
+
+std::ostream& operator<<(std::ostream& os, const Stats& s) {
+  std::ios fmt_holder(nullptr);
+  fmt_holder.copyfmt(os);
+
+  os << std::left;
+  os << std::setw(25) << "AddTombstones: "
+     << s.time_add_tombstones /
+            (FLAGS_add_tombstones_per_run * FLAGS_num_runs * 1.0e3)
+     << " us\n";
+  os << std::setw(25) << "ShouldDelete (first): "
+     << s.time_first_should_delete / (FLAGS_num_runs * 1.0e3) << " us\n";
+  if (FLAGS_should_deletes_per_run > 1) {
+    os << std::setw(25) << "ShouldDelete (rest): "
+       << s.time_rest_should_delete /
+              ((FLAGS_should_deletes_per_run - 1) * FLAGS_num_runs * 1.0e3)
+       << " us\n";
+  }
+
+  os.copyfmt(fmt_holder);
+  return os;
+}
+
+auto icmp = rocksdb::InternalKeyComparator(rocksdb::BytewiseComparator());
+
+}  // anonymous namespace
+
+namespace rocksdb {
+
+namespace {
+
+// A wrapper around RangeTombstones and the underlying data of its start and end
+// keys.
+struct PersistentRangeTombstone {
+  std::string start_key;
+  std::string end_key;
+  RangeTombstone tombstone;
+
+  PersistentRangeTombstone(std::string start, std::string end,
+                           SequenceNumber seq)
+      : start_key(std::move(start)), end_key(std::move(end)) {
+    tombstone = RangeTombstone(start_key, end_key, seq);
+  }
+
+  PersistentRangeTombstone() = default;
+
+  PersistentRangeTombstone(const PersistentRangeTombstone& t) { *this = t; }
+
+  PersistentRangeTombstone& operator=(const PersistentRangeTombstone& t) {
+    start_key = t.start_key;
+    end_key = t.end_key;
+    tombstone = RangeTombstone(start_key, end_key, t.tombstone.seq_);
+
+    return *this;
+  }
+
+  PersistentRangeTombstone(PersistentRangeTombstone&& t) noexcept { *this = t; }
+
+  PersistentRangeTombstone& operator=(PersistentRangeTombstone&& t) {
+    start_key = std::move(t.start_key);
+    end_key = std::move(t.end_key);
+    tombstone = RangeTombstone(start_key, end_key, t.tombstone.seq_);
+
+    return *this;
+  }
+};
+
+struct TombstoneStartKeyComparator {
+  explicit TombstoneStartKeyComparator(const Comparator* c) : cmp(c) {}
+
+  bool operator()(const RangeTombstone& a, const RangeTombstone& b) const {
+    return cmp->Compare(a.start_key_, b.start_key_) < 0;
+  }
+
+  const Comparator* cmp;
+};
+
+std::unique_ptr<InternalIterator> MakeRangeDelIterator(
+    const std::vector<PersistentRangeTombstone>& range_dels) {
+  std::vector<std::string> keys, values;
+  for (const auto& range_del : range_dels) {
+    auto key_and_value = range_del.tombstone.Serialize();
+    keys.push_back(key_and_value.first.Encode().ToString());
+    values.push_back(key_and_value.second.ToString());
+  }
+  return std::unique_ptr<test::VectorIterator>(
+      new test::VectorIterator(keys, values));
+}
+
+// convert long to a big-endian slice key
+static std::string Key(int64_t val) {
+  std::string little_endian_key;
+  std::string big_endian_key;
+  PutFixed64(&little_endian_key, val);
+  assert(little_endian_key.size() == sizeof(val));
+  big_endian_key.resize(sizeof(val));
+  for (size_t i = 0; i < sizeof(val); ++i) {
+    big_endian_key[i] = little_endian_key[sizeof(val) - 1 - i];
+  }
+  return big_endian_key;
+}
+
+}  // anonymous namespace
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  ParseCommandLineFlags(&argc, &argv, true);
+
+  Stats stats;
+  rocksdb::Random64 rnd(FLAGS_seed);
+  std::default_random_engine random_gen(FLAGS_seed);
+  std::normal_distribution<double> normal_dist(FLAGS_tombstone_width_mean,
+                                               FLAGS_tombstone_width_stddev);
+  std::vector<std::vector<rocksdb::PersistentRangeTombstone> >
+      all_persistent_range_tombstones(FLAGS_add_tombstones_per_run);
+  for (int i = 0; i < FLAGS_add_tombstones_per_run; i++) {
+    all_persistent_range_tombstones[i] =
+        std::vector<rocksdb::PersistentRangeTombstone>(
+            FLAGS_num_range_tombstones);
+  }
+  auto mode = FLAGS_use_collapsed
+                  ? rocksdb::RangeDelPositioningMode::kForwardTraversal
+                  : rocksdb::RangeDelPositioningMode::kFullScan;
+
+  for (int i = 0; i < FLAGS_num_runs; i++) {
+    rocksdb::RangeDelAggregator range_del_agg(icmp, {} /* snapshots */,
+                                              FLAGS_use_collapsed);
+    rocksdb::ReadRangeDelAggregatorV2 range_del_agg_v2(
+        &icmp, rocksdb::kMaxSequenceNumber /* upper_bound */);
+
+    std::vector<std::unique_ptr<rocksdb::FragmentedRangeTombstoneList> >
+        fragmented_range_tombstone_lists(FLAGS_add_tombstones_per_run);
+
+    for (auto& persistent_range_tombstones : all_persistent_range_tombstones) {
+      // TODO(abhimadan): consider whether creating the range tombstones right
+      // before AddTombstones is artificially warming the cache compared to
+      // real workloads.
+      for (int j = 0; j < FLAGS_num_range_tombstones; j++) {
+        uint64_t start = rnd.Uniform(FLAGS_tombstone_start_upper_bound);
+        uint64_t end = start + std::max(1.0, normal_dist(random_gen));
+        persistent_range_tombstones[j] = rocksdb::PersistentRangeTombstone(
+            rocksdb::Key(start), rocksdb::Key(end), j);
+      }
+
+      auto range_del_iter =
+          rocksdb::MakeRangeDelIterator(persistent_range_tombstones);
+      fragmented_range_tombstone_lists.emplace_back(
+          new rocksdb::FragmentedRangeTombstoneList(
+              rocksdb::MakeRangeDelIterator(persistent_range_tombstones),
+              icmp));
+      std::unique_ptr<rocksdb::FragmentedRangeTombstoneIterator>
+          fragmented_range_del_iter(
+              new rocksdb::FragmentedRangeTombstoneIterator(
+                  fragmented_range_tombstone_lists.back().get(), icmp,
+                  rocksdb::kMaxSequenceNumber));
+
+      if (FLAGS_use_v2_aggregator) {
+        rocksdb::StopWatchNano stop_watch_add_tombstones(
+            rocksdb::Env::Default(), true /* auto_start */);
+        range_del_agg_v2.AddTombstones(std::move(fragmented_range_del_iter));
+        stats.time_add_tombstones += stop_watch_add_tombstones.ElapsedNanos();
+      } else {
+        rocksdb::StopWatchNano stop_watch_add_tombstones(
+            rocksdb::Env::Default(), true /* auto_start */);
+        range_del_agg.AddTombstones(std::move(range_del_iter));
+        stats.time_add_tombstones += stop_watch_add_tombstones.ElapsedNanos();
+      }
+    }
+
+    rocksdb::ParsedInternalKey parsed_key;
+    parsed_key.sequence = FLAGS_num_range_tombstones / 2;
+    parsed_key.type = rocksdb::kTypeValue;
+
+    uint64_t first_key = rnd.Uniform(FLAGS_should_delete_upper_bound -
+                                     FLAGS_should_deletes_per_run + 1);
+
+    for (int j = 0; j < FLAGS_should_deletes_per_run; j++) {
+      std::string key_string = rocksdb::Key(first_key + j);
+      parsed_key.user_key = key_string;
+
+      uint64_t call_time;
+      if (FLAGS_use_v2_aggregator) {
+        rocksdb::StopWatchNano stop_watch_should_delete(rocksdb::Env::Default(),
+                                                        true /* auto_start */);
+        range_del_agg_v2.ShouldDelete(parsed_key, mode);
+        call_time = stop_watch_should_delete.ElapsedNanos();
+      } else {
+        rocksdb::StopWatchNano stop_watch_should_delete(rocksdb::Env::Default(),
+                                                        true /* auto_start */);
+        range_del_agg.ShouldDelete(parsed_key, mode);
+        call_time = stop_watch_should_delete.ElapsedNanos();
+      }
+
+      if (j == 0) {
+        stats.time_first_should_delete += call_time;
+      } else {
+        stats.time_rest_should_delete += call_time;
+      }
+    }
+  }
+
+  std::cout << "=========================\n"
+            << "Results:\n"
+            << "=========================\n"
+            << stats;
+
+  return 0;
+}
+
+#endif  // GFLAGS
diff --git a/3rdParty/rocksdb/v5.16.X/db/range_del_aggregator_test.cc b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_test.cc
similarity index 51%
rename from 3rdParty/rocksdb/v5.16.X/db/range_del_aggregator_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_test.cc
index eacc4e0cc5..2cfc6540ea 100644
--- a/3rdParty/rocksdb/v5.16.X/db/range_del_aggregator_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_test.cc
@@ -27,7 +27,13 @@ enum Direction {
   kReverse,
 };
 
-static auto icmp = InternalKeyComparator(BytewiseComparator());
+struct AddTombstonesArgs {
+  const std::vector<RangeTombstone> tombstones;
+  const InternalKey* smallest;
+  const InternalKey* largest;
+};
+
+static auto bytewise_icmp = InternalKeyComparator(BytewiseComparator());
 
 void AddTombstones(RangeDelAggregator* range_del_agg,
                    const std::vector<RangeTombstone>& range_dels,
@@ -54,8 +60,7 @@ void VerifyRangeDelIter(
     RangeDelIterator* range_del_iter,
     const std::vector<RangeTombstone>& expected_range_dels) {
   size_t i = 0;
-  for (; range_del_iter->Valid() && i < expected_range_dels.size();
-       range_del_iter->Next(), i++) {
+  for (; range_del_iter->Valid(); range_del_iter->Next(), i++) {
     VerifyTombstonesEq(expected_range_dels[i], range_del_iter->Tombstone());
   }
   ASSERT_EQ(expected_range_dels.size(), i);
@@ -63,22 +68,26 @@ void VerifyRangeDelIter(
 }
 
 void VerifyRangeDels(
-    const std::vector<RangeTombstone>& range_dels_in,
+    const std::vector<AddTombstonesArgs>& all_args,
     const std::vector<ExpectedPoint>& expected_points,
     const std::vector<RangeTombstone>& expected_collapsed_range_dels,
-    const InternalKey* smallest = nullptr,
-    const InternalKey* largest = nullptr) {
+    const InternalKeyComparator& icmp = bytewise_icmp) {
   // Test same result regardless of which order the range deletions are added
   // and regardless of collapsed mode.
   for (bool collapsed : {false, true}) {
     for (Direction dir : {kForward, kReverse}) {
       RangeDelAggregator range_del_agg(icmp, {} /* snapshots */, collapsed);
+      std::vector<RangeTombstone> all_range_dels;
 
-      std::vector<RangeTombstone> range_dels = range_dels_in;
-      if (dir == kReverse) {
-        std::reverse(range_dels.begin(), range_dels.end());
+      for (const auto& args : all_args) {
+        std::vector<RangeTombstone> range_dels = args.tombstones;
+        if (dir == kReverse) {
+          std::reverse(range_dels.begin(), range_dels.end());
+        }
+        all_range_dels.insert(all_range_dels.end(), range_dels.begin(),
+                              range_dels.end());
+        AddTombstones(&range_del_agg, range_dels, args.smallest, args.largest);
       }
-      AddTombstones(&range_del_agg, range_dels, smallest, largest);
 
       auto mode = RangeDelPositioningMode::kFullScan;
       if (collapsed) {
@@ -90,38 +99,45 @@ void VerifyRangeDels(
         parsed_key.user_key = expected_point.begin;
         parsed_key.sequence = expected_point.seq;
         parsed_key.type = kTypeValue;
-        ASSERT_FALSE(range_del_agg.ShouldDelete(parsed_key, mode));
+        std::string ikey;
+        AppendInternalKey(&ikey, parsed_key);
+        ASSERT_FALSE(range_del_agg.ShouldDelete(ikey, mode));
         if (parsed_key.sequence > 0) {
           --parsed_key.sequence;
+          ikey.clear();
+          AppendInternalKey(&ikey, parsed_key);
           if (expected_point.expectAlive) {
-            ASSERT_FALSE(range_del_agg.ShouldDelete(parsed_key, mode));
+            ASSERT_FALSE(range_del_agg.ShouldDelete(ikey, mode));
           } else {
-            ASSERT_TRUE(range_del_agg.ShouldDelete(parsed_key, mode));
+            ASSERT_TRUE(range_del_agg.ShouldDelete(ikey, mode));
           }
         }
       }
 
       if (collapsed) {
-        range_dels = expected_collapsed_range_dels;
-        VerifyRangeDelIter(range_del_agg.NewIterator().get(), range_dels);
-      } else if (smallest == nullptr && largest == nullptr) {
+        all_range_dels = expected_collapsed_range_dels;
+        VerifyRangeDelIter(range_del_agg.NewIterator().get(), all_range_dels);
+      } else if (all_args.size() == 1 && all_args[0].smallest == nullptr &&
+                 all_args[0].largest == nullptr) {
         // Tombstones in an uncollapsed map are presented in start key
         // order. Tombstones with the same start key are presented in
         // insertion order. We don't handle tombstone truncation here, so the
         // verification is only performed if no truncation was requested.
-        std::stable_sort(range_dels.begin(), range_dels.end(),
+        std::stable_sort(all_range_dels.begin(), all_range_dels.end(),
                          [&](const RangeTombstone& a, const RangeTombstone& b) {
                            return icmp.user_comparator()->Compare(
                                       a.start_key_, b.start_key_) < 0;
                          });
-        VerifyRangeDelIter(range_del_agg.NewIterator().get(), range_dels);
+        VerifyRangeDelIter(range_del_agg.NewIterator().get(), all_range_dels);
       }
     }
   }
 
   RangeDelAggregator range_del_agg(icmp, {} /* snapshots */,
                                    false /* collapse_deletions */);
-  AddTombstones(&range_del_agg, range_dels_in);
+  for (const auto& args : all_args) {
+    AddTombstones(&range_del_agg, args.tombstones, args.smallest, args.largest);
+  }
   for (size_t i = 1; i < expected_points.size(); ++i) {
     bool overlapped = range_del_agg.IsRangeOverlapped(
         expected_points[i - 1].begin, expected_points[i].begin);
@@ -138,57 +154,64 @@ void VerifyRangeDels(
 TEST_F(RangeDelAggregatorTest, Empty) { VerifyRangeDels({}, {{"a", 0}}, {}); }
 
 TEST_F(RangeDelAggregatorTest, SameStartAndEnd) {
-  VerifyRangeDels({{"a", "a", 5}}, {{" ", 0}, {"a", 0}, {"b", 0}}, {});
+  VerifyRangeDels({{{{"a", "a", 5}}}}, {{" ", 0}, {"a", 0}, {"b", 0}}, {});
 }
 
 TEST_F(RangeDelAggregatorTest, Single) {
-  VerifyRangeDels({{"a", "b", 10}}, {{" ", 0}, {"a", 10}, {"b", 0}},
+  VerifyRangeDels({{{{"a", "b", 10}}}}, {{" ", 0}, {"a", 10}, {"b", 0}},
                   {{"a", "b", 10}});
 }
 
 TEST_F(RangeDelAggregatorTest, OverlapAboveLeft) {
-  VerifyRangeDels({{"a", "c", 10}, {"b", "d", 5}},
+  VerifyRangeDels({{{{"a", "c", 10}, {"b", "d", 5}}}},
                   {{" ", 0}, {"a", 10}, {"c", 5}, {"d", 0}},
                   {{"a", "c", 10}, {"c", "d", 5}});
 }
 
 TEST_F(RangeDelAggregatorTest, OverlapAboveRight) {
-  VerifyRangeDels({{"a", "c", 5}, {"b", "d", 10}},
+  VerifyRangeDels({{{{"a", "c", 5}, {"b", "d", 10}}}},
                   {{" ", 0}, {"a", 5}, {"b", 10}, {"d", 0}},
                   {{"a", "b", 5}, {"b", "d", 10}});
 }
 
 TEST_F(RangeDelAggregatorTest, OverlapAboveMiddle) {
-  VerifyRangeDels({{"a", "d", 5}, {"b", "c", 10}},
+  VerifyRangeDels({{{{"a", "d", 5}, {"b", "c", 10}}}},
                   {{" ", 0}, {"a", 5}, {"b", 10}, {"c", 5}, {"d", 0}},
                   {{"a", "b", 5}, {"b", "c", 10}, {"c", "d", 5}});
 }
 
+TEST_F(RangeDelAggregatorTest, OverlapAboveMiddleReverse) {
+  VerifyRangeDels({{{{"d", "a", 5}, {"c", "b", 10}}}},
+                  {{"z", 0}, {"d", 5}, {"c", 10}, {"b", 5}, {"a", 0}},
+                  {{"d", "c", 5}, {"c", "b", 10}, {"b", "a", 5}},
+                  InternalKeyComparator(ReverseBytewiseComparator()));
+}
+
 TEST_F(RangeDelAggregatorTest, OverlapFully) {
-  VerifyRangeDels({{"a", "d", 10}, {"b", "c", 5}},
+  VerifyRangeDels({{{{"a", "d", 10}, {"b", "c", 5}}}},
                   {{" ", 0}, {"a", 10}, {"d", 0}}, {{"a", "d", 10}});
 }
 
 TEST_F(RangeDelAggregatorTest, OverlapPoint) {
-  VerifyRangeDels({{"a", "b", 5}, {"b", "c", 10}},
+  VerifyRangeDels({{{{"a", "b", 5}, {"b", "c", 10}}}},
                   {{" ", 0}, {"a", 5}, {"b", 10}, {"c", 0}},
                   {{"a", "b", 5}, {"b", "c", 10}});
 }
 
 TEST_F(RangeDelAggregatorTest, SameStartKey) {
-  VerifyRangeDels({{"a", "c", 5}, {"a", "b", 10}},
+  VerifyRangeDels({{{{"a", "c", 5}, {"a", "b", 10}}}},
                   {{" ", 0}, {"a", 10}, {"b", 5}, {"c", 0}},
                   {{"a", "b", 10}, {"b", "c", 5}});
 }
 
 TEST_F(RangeDelAggregatorTest, SameEndKey) {
-  VerifyRangeDels({{"a", "d", 5}, {"b", "d", 10}},
+  VerifyRangeDels({{{{"a", "d", 5}, {"b", "d", 10}}}},
                   {{" ", 0}, {"a", 5}, {"b", 10}, {"d", 0}},
                   {{"a", "b", 5}, {"b", "d", 10}});
 }
 
 TEST_F(RangeDelAggregatorTest, GapsBetweenRanges) {
-  VerifyRangeDels({{"a", "b", 5}, {"c", "d", 10}, {"e", "f", 15}},
+  VerifyRangeDels({{{{"a", "b", 5}, {"c", "d", 10}, {"e", "f", 15}}}},
                   {{" ", 0},
                    {"a", 5},
                    {"b", 0},
@@ -201,25 +224,25 @@ TEST_F(RangeDelAggregatorTest, GapsBetweenRanges) {
 }
 
 TEST_F(RangeDelAggregatorTest, IdenticalSameSeqNo) {
-  VerifyRangeDels({{"a", "b", 5}, {"a", "b", 5}},
+  VerifyRangeDels({{{{"a", "b", 5}, {"a", "b", 5}}}},
                   {{" ", 0}, {"a", 5}, {"b", 0}},
                   {{"a", "b", 5}});
 }
 
 TEST_F(RangeDelAggregatorTest, ContiguousSameSeqNo) {
-  VerifyRangeDels({{"a", "b", 5}, {"b", "c", 5}},
+  VerifyRangeDels({{{{"a", "b", 5}, {"b", "c", 5}}}},
                   {{" ", 0}, {"a", 5}, {"b", 5}, {"c", 0}},
                   {{"a", "c", 5}});
 }
 
 TEST_F(RangeDelAggregatorTest, OverlappingSameSeqNo) {
-  VerifyRangeDels({{"a", "c", 5}, {"b", "d", 5}},
+  VerifyRangeDels({{{{"a", "c", 5}, {"b", "d", 5}}}},
                   {{" ", 0}, {"a", 5}, {"b", 5}, {"c", 5}, {"d", 0}},
                   {{"a", "d", 5}});
 }
 
 TEST_F(RangeDelAggregatorTest, CoverSameSeqNo) {
-  VerifyRangeDels({{"a", "d", 5}, {"b", "c", 5}},
+  VerifyRangeDels({{{{"a", "d", 5}, {"b", "c", 5}}}},
                   {{" ", 0}, {"a", 5}, {"b", 5}, {"c", 5}, {"d", 0}},
                   {{"a", "d", 5}});
 }
@@ -228,27 +251,27 @@ TEST_F(RangeDelAggregatorTest, CoverSameSeqNo) {
 // larger one when VerifyRangeDels() runs them in reverse
 TEST_F(RangeDelAggregatorTest, CoverMultipleFromLeft) {
   VerifyRangeDels(
-      {{"b", "d", 5}, {"c", "f", 10}, {"e", "g", 15}, {"a", "f", 20}},
+      {{{{"b", "d", 5}, {"c", "f", 10}, {"e", "g", 15}, {"a", "f", 20}}}},
       {{" ", 0}, {"a", 20}, {"f", 15}, {"g", 0}},
       {{"a", "f", 20}, {"f", "g", 15}});
 }
 
 TEST_F(RangeDelAggregatorTest, CoverMultipleFromRight) {
   VerifyRangeDels(
-      {{"b", "d", 5}, {"c", "f", 10}, {"e", "g", 15}, {"c", "h", 20}},
+      {{{{"b", "d", 5}, {"c", "f", 10}, {"e", "g", 15}, {"c", "h", 20}}}},
       {{" ", 0}, {"b", 5}, {"c", 20}, {"h", 0}},
       {{"b", "c", 5}, {"c", "h", 20}});
 }
 
 TEST_F(RangeDelAggregatorTest, CoverMultipleFully) {
   VerifyRangeDels(
-      {{"b", "d", 5}, {"c", "f", 10}, {"e", "g", 15}, {"a", "h", 20}},
+      {{{{"b", "d", 5}, {"c", "f", 10}, {"e", "g", 15}, {"a", "h", 20}}}},
       {{" ", 0}, {"a", 20}, {"h", 0}}, {{"a", "h", 20}});
 }
 
 TEST_F(RangeDelAggregatorTest, AlternateMultipleAboveBelow) {
   VerifyRangeDels(
-      {{"b", "d", 15}, {"c", "f", 10}, {"e", "g", 20}, {"a", "h", 5}},
+      {{{{"b", "d", 15}, {"c", "f", 10}, {"e", "g", 20}, {"a", "h", 5}}}},
       {{" ", 0}, {"a", 5}, {"b", 15}, {"d", 10}, {"e", 20}, {"g", 5}, {"h", 0}},
       {{"a", "b", 5},
        {"b", "d", 15},
@@ -259,14 +282,14 @@ TEST_F(RangeDelAggregatorTest, AlternateMultipleAboveBelow) {
 
 TEST_F(RangeDelAggregatorTest, MergingIteratorAllEmptyStripes) {
   for (bool collapsed : {true, false}) {
-    RangeDelAggregator range_del_agg(icmp, {1, 2}, collapsed);
+    RangeDelAggregator range_del_agg(bytewise_icmp, {1, 2}, collapsed);
     VerifyRangeDelIter(range_del_agg.NewIterator().get(), {});
   }
 }
 
 TEST_F(RangeDelAggregatorTest, MergingIteratorOverlappingStripes) {
   for (bool collapsed : {true, false}) {
-    RangeDelAggregator range_del_agg(icmp, {5, 15, 25, 35}, collapsed);
+    RangeDelAggregator range_del_agg(bytewise_icmp, {5, 15, 25, 35}, collapsed);
     AddTombstones(
         &range_del_agg,
         {{"d", "e", 10}, {"aa", "b", 20}, {"c", "d", 30}, {"a", "b", 10}});
@@ -277,7 +300,8 @@ TEST_F(RangeDelAggregatorTest, MergingIteratorOverlappingStripes) {
 }
 
 TEST_F(RangeDelAggregatorTest, MergingIteratorSeek) {
-  RangeDelAggregator range_del_agg(icmp, {5, 15}, true /* collapsed */);
+  RangeDelAggregator range_del_agg(bytewise_icmp, {5, 15},
+                                   true /* collapsed */);
   AddTombstones(&range_del_agg, {{"a", "c", 10},
                                  {"b", "c", 11},
                                  {"f", "g", 10},
@@ -312,16 +336,132 @@ TEST_F(RangeDelAggregatorTest, MergingIteratorSeek) {
 }
 
 TEST_F(RangeDelAggregatorTest, TruncateTombstones) {
-  const InternalKey smallest("b", 1, kTypeRangeDeletion);
+  const InternalKey smallest("b", kMaxSequenceNumber, kTypeRangeDeletion);
   const InternalKey largest("e", kMaxSequenceNumber, kTypeRangeDeletion);
   VerifyRangeDels(
-      {{"a", "c", 10}, {"d", "f", 10}},
+      {{{{"a", "c", 10}, {"d", "f", 10}}, &smallest, &largest}},
       {{"a", 10, true},  // truncated
        {"b", 10, false}, // not truncated
        {"d", 10, false}, // not truncated
        {"e", 10, true}}, // truncated
-      {{"b", "c", 10}, {"d", "e", 10}},
-      &smallest, &largest);
+      {{"b", "c", 10}, {"d", "e", 10}});
+}
+
+TEST_F(RangeDelAggregatorTest, OverlappingLargestKeyTruncateBelowTombstone) {
+  const InternalKey smallest("b", kMaxSequenceNumber, kTypeRangeDeletion);
+  const InternalKey largest(
+      "e", 3,  // could happen if "e" is in consecutive sstables
+      kTypeValue);
+  VerifyRangeDels(
+      {{{{"a", "c", 10}, {"d", "f", 10}}, &smallest, &largest}},
+      {{"a", 10, true},  // truncated
+       {"b", 10, false}, // not truncated
+       {"d", 10, false}, // not truncated
+       {"e", 10, false}, // not truncated
+       {"e", 2, true}},  // truncated here
+      {{"b", "c", 10}, {"d", "e", 10}});
+}
+
+TEST_F(RangeDelAggregatorTest, OverlappingLargestKeyTruncateAboveTombstone) {
+  const InternalKey smallest("b", kMaxSequenceNumber, kTypeRangeDeletion);
+  const InternalKey largest(
+      "e", 15,  // could happen if "e" is in consecutive sstables
+      kTypeValue);
+  VerifyRangeDels(
+      {{{{"a", "c", 10}, {"d", "f", 10}}, &smallest, &largest}},
+      {{"a", 10, true},  // truncated
+       {"b", 10, false}, // not truncated
+       {"d", 10, false}, // not truncated
+       {"e", kMaxSequenceNumber, true}},  // truncated
+      {{"b", "c", 10}, {"d", "e", 10}});
+}
+
+TEST_F(RangeDelAggregatorTest, OverlappingSmallestKeyTruncateBelowTombstone) {
+  const InternalKey smallest("b", 5, kTypeValue);
+  const InternalKey largest("e", kMaxSequenceNumber, kTypeRangeDeletion);
+  VerifyRangeDels(
+      {{{{"a", "c", 10}, {"d", "f", 10}}, &smallest, &largest}},
+      {{"a", 10, true},  // truncated
+       {"b", 10, true}, // truncated
+       {"b", 6, false}, // not truncated; start boundary moved
+       {"d", 10, false}, // not truncated
+       {"e", kMaxSequenceNumber, true}}, // truncated
+      {{"b", "c", 10}, {"d", "e", 10}});
+}
+
+TEST_F(RangeDelAggregatorTest, OverlappingSmallestKeyTruncateAboveTombstone) {
+  const InternalKey smallest("b", 15, kTypeValue);
+  const InternalKey largest("e", kMaxSequenceNumber, kTypeRangeDeletion);
+  VerifyRangeDels(
+      {{{{"a", "c", 10}, {"d", "f", 10}}, &smallest, &largest}},
+      {{"a", 10, true},  // truncated
+       {"b", 15, true}, // truncated
+       {"b", 10, false}, // not truncated
+       {"d", 10, false}, // not truncated
+       {"e", kMaxSequenceNumber, true}}, // truncated
+      {{"b", "c", 10}, {"d", "e", 10}});
+}
+
+TEST_F(RangeDelAggregatorTest, OverlappingBoundaryGapAboveTombstone) {
+  const InternalKey smallest1("b", kMaxSequenceNumber, kTypeRangeDeletion);
+  const InternalKey largest1("c", 20, kTypeValue);
+  const InternalKey smallest2("c", 10, kTypeValue);
+  const InternalKey largest2("e", kMaxSequenceNumber, kTypeRangeDeletion);
+  VerifyRangeDels(
+      {{{{"b", "d", 5}}, &smallest1, &largest1},
+       {{{"b", "d", 5}}, &smallest2, &largest2}},
+      {{"b", 5, false}, // not truncated
+       {"c", 5, false}}, // not truncated
+      {{"b", "c", 5}, {"c", "d", 5}}); // not collapsed due to boundaries
+}
+
+TEST_F(RangeDelAggregatorTest, OverlappingBoundaryGapBelowTombstone) {
+  const InternalKey smallest1("b", kMaxSequenceNumber, kTypeRangeDeletion);
+  const InternalKey largest1("c", 20, kTypeValue);
+  const InternalKey smallest2("c", 10, kTypeValue);
+  const InternalKey largest2("e", kMaxSequenceNumber, kTypeRangeDeletion);
+  VerifyRangeDels(
+      {{{{"b", "d", 30}}, &smallest1, &largest1},
+       {{{"b", "d", 30}}, &smallest2, &largest2}},
+      {{"b", 30, false}, // not truncated
+       {"c", 30, false}, // not truncated
+       {"c", 19, true}, // truncated here (keys in this range should not exist)
+       {"c", 11, false}}, // not truncated again
+      {{"b", "c", 30}, {"c", "d", 30}}); // not collapsed due to boundaries
+}
+
+TEST_F(RangeDelAggregatorTest, OverlappingBoundaryGapContainsTombstone) {
+  const InternalKey smallest1("b", kMaxSequenceNumber, kTypeRangeDeletion);
+  const InternalKey largest1("c", 20, kTypeValue);
+  const InternalKey smallest2("c", 10, kTypeValue);
+  const InternalKey largest2("e", kMaxSequenceNumber, kTypeRangeDeletion);
+  VerifyRangeDels(
+      {{{{"b", "d", 15}}, &smallest1, &largest1},
+       {{{"b", "d", 15}}, &smallest2, &largest2}},
+      {{"b", 15, false}, // not truncated
+       {"c", 15, true}, // truncated (keys in this range should not exist)
+       {"c", 11, false}}, // not truncated here
+      {{"b", "c", 15}, {"c", "d", 15}}); // not collapsed due to boundaries
+}
+
+TEST_F(RangeDelAggregatorTest, FileCoversOneKeyAndTombstoneAbove) {
+  const InternalKey smallest("a", kMaxSequenceNumber, kTypeRangeDeletion);
+  const InternalKey largest("a", 20, kTypeValue);
+  VerifyRangeDels(
+      {{{{"a", "b", 35}}, &smallest, &largest}},
+      {{"a", 40, true}, // not truncated
+       {"a", 35, false}}, // not truncated
+      {{"a", "a", 35}}); // empty tombstone but can't occur during a compaction
+}
+
+TEST_F(RangeDelAggregatorTest, FileCoversOneKeyAndTombstoneBelow) {
+  const InternalKey smallest("a", kMaxSequenceNumber, kTypeRangeDeletion);
+  const InternalKey largest("a", 20, kTypeValue);
+  VerifyRangeDels(
+      {{{{"a", "b", 15}}, &smallest, &largest}},
+      {{"a", 20, true}, // truncated here
+       {"a", 15, true}}, // truncated
+      {{"a", "a", 15}}); // empty tombstone but can't occur during a compaction
 }
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_v2.cc b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_v2.cc
new file mode 100644
index 0000000000..b0667f6fd0
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_v2.cc
@@ -0,0 +1,492 @@
+//  Copyright (c) 2018-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/range_del_aggregator_v2.h"
+
+#include "db/compaction_iteration_stats.h"
+#include "db/dbformat.h"
+#include "db/pinned_iterators_manager.h"
+#include "db/range_del_aggregator.h"
+#include "db/range_tombstone_fragmenter.h"
+#include "db/version_edit.h"
+#include "include/rocksdb/comparator.h"
+#include "include/rocksdb/types.h"
+#include "table/internal_iterator.h"
+#include "table/scoped_arena_iterator.h"
+#include "table/table_builder.h"
+#include "util/heap.h"
+#include "util/kv_map.h"
+#include "util/vector_iterator.h"
+
+namespace rocksdb {
+
+TruncatedRangeDelIterator::TruncatedRangeDelIterator(
+    std::unique_ptr<FragmentedRangeTombstoneIterator> iter,
+    const InternalKeyComparator* icmp, const InternalKey* smallest,
+    const InternalKey* largest)
+    : iter_(std::move(iter)),
+      icmp_(icmp),
+      smallest_ikey_(smallest),
+      largest_ikey_(largest) {
+  if (smallest != nullptr) {
+    pinned_bounds_.emplace_back();
+    auto& parsed_smallest = pinned_bounds_.back();
+    if (!ParseInternalKey(smallest->Encode(), &parsed_smallest)) {
+      assert(false);
+    }
+    smallest_ = &parsed_smallest;
+  }
+  if (largest != nullptr) {
+    pinned_bounds_.emplace_back();
+    auto& parsed_largest = pinned_bounds_.back();
+    if (!ParseInternalKey(largest->Encode(), &parsed_largest)) {
+      assert(false);
+    }
+    if (parsed_largest.type == kTypeRangeDeletion &&
+        parsed_largest.sequence == kMaxSequenceNumber) {
+      // The file boundary has been artificially extended by a range tombstone.
+      // We do not need to adjust largest to properly truncate range
+      // tombstones that extend past the boundary.
+    } else if (parsed_largest.sequence == 0) {
+      // The largest key in the sstable has a sequence number of 0. Since we
+      // guarantee that no internal keys with the same user key and sequence
+      // number can exist in a DB, we know that the largest key in this sstable
+      // cannot exist as the smallest key in the next sstable. This further
+      // implies that no range tombstone in this sstable covers largest;
+      // otherwise, the file boundary would have been artificially extended.
+      //
+      // Therefore, we will never truncate a range tombstone at largest, so we
+      // can leave it unchanged.
+    } else {
+      // The same user key may straddle two sstable boundaries. To ensure that
+      // the truncated end key can cover the largest key in this sstable, reduce
+      // its sequence number by 1.
+      parsed_largest.sequence -= 1;
+    }
+    largest_ = &parsed_largest;
+  }
+}
+
+bool TruncatedRangeDelIterator::Valid() const {
+  return iter_->Valid() &&
+         (smallest_ == nullptr ||
+          icmp_->Compare(*smallest_, iter_->parsed_end_key()) < 0) &&
+         (largest_ == nullptr ||
+          icmp_->Compare(iter_->parsed_start_key(), *largest_) < 0);
+}
+
+void TruncatedRangeDelIterator::Next() { iter_->TopNext(); }
+
+void TruncatedRangeDelIterator::Prev() { iter_->TopPrev(); }
+
+void TruncatedRangeDelIterator::InternalNext() { iter_->Next(); }
+
+// NOTE: target is a user key
+void TruncatedRangeDelIterator::Seek(const Slice& target) {
+  if (largest_ != nullptr &&
+      icmp_->Compare(*largest_, ParsedInternalKey(target, kMaxSequenceNumber,
+                                                  kTypeRangeDeletion)) <= 0) {
+    iter_->Invalidate();
+    return;
+  }
+  if (smallest_ != nullptr &&
+      icmp_->user_comparator()->Compare(target, smallest_->user_key) < 0) {
+    iter_->Seek(smallest_->user_key);
+    return;
+  }
+  iter_->Seek(target);
+}
+
+// NOTE: target is a user key
+void TruncatedRangeDelIterator::SeekForPrev(const Slice& target) {
+  if (smallest_ != nullptr &&
+      icmp_->Compare(ParsedInternalKey(target, 0, kTypeRangeDeletion),
+                     *smallest_) < 0) {
+    iter_->Invalidate();
+    return;
+  }
+  if (largest_ != nullptr &&
+      icmp_->user_comparator()->Compare(largest_->user_key, target) < 0) {
+    iter_->SeekForPrev(largest_->user_key);
+    return;
+  }
+  iter_->SeekForPrev(target);
+}
+
+void TruncatedRangeDelIterator::SeekToFirst() {
+  if (smallest_ != nullptr) {
+    iter_->Seek(smallest_->user_key);
+    return;
+  }
+  iter_->SeekToTopFirst();
+}
+
+void TruncatedRangeDelIterator::SeekToLast() {
+  if (largest_ != nullptr) {
+    iter_->SeekForPrev(largest_->user_key);
+    return;
+  }
+  iter_->SeekToTopLast();
+}
+
+std::map<SequenceNumber, std::unique_ptr<TruncatedRangeDelIterator>>
+TruncatedRangeDelIterator::SplitBySnapshot(
+    const std::vector<SequenceNumber>& snapshots) {
+  using FragmentedIterPair =
+      std::pair<const SequenceNumber,
+                std::unique_ptr<FragmentedRangeTombstoneIterator>>;
+
+  auto split_untruncated_iters = iter_->SplitBySnapshot(snapshots);
+  std::map<SequenceNumber, std::unique_ptr<TruncatedRangeDelIterator>>
+      split_truncated_iters;
+  std::for_each(
+      split_untruncated_iters.begin(), split_untruncated_iters.end(),
+      [&](FragmentedIterPair& iter_pair) {
+        std::unique_ptr<TruncatedRangeDelIterator> truncated_iter(
+            new TruncatedRangeDelIterator(std::move(iter_pair.second), icmp_,
+                                          smallest_ikey_, largest_ikey_));
+        split_truncated_iters.emplace(iter_pair.first,
+                                      std::move(truncated_iter));
+      });
+  return split_truncated_iters;
+}
+
+ForwardRangeDelIterator::ForwardRangeDelIterator(
+    const InternalKeyComparator* icmp,
+    const std::vector<std::unique_ptr<TruncatedRangeDelIterator>>* iters)
+    : icmp_(icmp),
+      iters_(iters),
+      unused_idx_(0),
+      active_seqnums_(SeqMaxComparator()),
+      active_iters_(EndKeyMinComparator(icmp)),
+      inactive_iters_(StartKeyMinComparator(icmp)) {}
+
+bool ForwardRangeDelIterator::ShouldDelete(const ParsedInternalKey& parsed) {
+  assert(iters_ != nullptr);
+  // Move active iterators that end before parsed.
+  while (!active_iters_.empty() &&
+         icmp_->Compare((*active_iters_.top())->end_key(), parsed) <= 0) {
+    TruncatedRangeDelIterator* iter = PopActiveIter();
+    do {
+      iter->Next();
+    } while (iter->Valid() && icmp_->Compare(iter->end_key(), parsed) <= 0);
+    PushIter(iter, parsed);
+    assert(active_iters_.size() == active_seqnums_.size());
+  }
+
+  // Move inactive iterators that start before parsed.
+  while (!inactive_iters_.empty() &&
+         icmp_->Compare(inactive_iters_.top()->start_key(), parsed) <= 0) {
+    TruncatedRangeDelIterator* iter = PopInactiveIter();
+    while (iter->Valid() && icmp_->Compare(iter->end_key(), parsed) <= 0) {
+      iter->Next();
+    }
+    PushIter(iter, parsed);
+    assert(active_iters_.size() == active_seqnums_.size());
+  }
+
+  return active_seqnums_.empty()
+             ? false
+             : (*active_seqnums_.begin())->seq() > parsed.sequence;
+}
+
+void ForwardRangeDelIterator::Invalidate() {
+  unused_idx_ = 0;
+  active_iters_.clear();
+  active_seqnums_.clear();
+  inactive_iters_.clear();
+}
+
+ReverseRangeDelIterator::ReverseRangeDelIterator(
+    const InternalKeyComparator* icmp,
+    const std::vector<std::unique_ptr<TruncatedRangeDelIterator>>* iters)
+    : icmp_(icmp),
+      iters_(iters),
+      unused_idx_(0),
+      active_seqnums_(SeqMaxComparator()),
+      active_iters_(StartKeyMaxComparator(icmp)),
+      inactive_iters_(EndKeyMaxComparator(icmp)) {}
+
+bool ReverseRangeDelIterator::ShouldDelete(const ParsedInternalKey& parsed) {
+  assert(iters_ != nullptr);
+  // Move active iterators that start after parsed.
+  while (!active_iters_.empty() &&
+         icmp_->Compare(parsed, (*active_iters_.top())->start_key()) < 0) {
+    TruncatedRangeDelIterator* iter = PopActiveIter();
+    do {
+      iter->Prev();
+    } while (iter->Valid() && icmp_->Compare(parsed, iter->start_key()) < 0);
+    PushIter(iter, parsed);
+    assert(active_iters_.size() == active_seqnums_.size());
+  }
+
+  // Move inactive iterators that end after parsed.
+  while (!inactive_iters_.empty() &&
+         icmp_->Compare(parsed, inactive_iters_.top()->end_key()) < 0) {
+    TruncatedRangeDelIterator* iter = PopInactiveIter();
+    while (iter->Valid() && icmp_->Compare(parsed, iter->start_key()) < 0) {
+      iter->Prev();
+    }
+    PushIter(iter, parsed);
+    assert(active_iters_.size() == active_seqnums_.size());
+  }
+
+  return active_seqnums_.empty()
+             ? false
+             : (*active_seqnums_.begin())->seq() > parsed.sequence;
+}
+
+void ReverseRangeDelIterator::Invalidate() {
+  unused_idx_ = 0;
+  active_iters_.clear();
+  active_seqnums_.clear();
+  inactive_iters_.clear();
+}
+
+bool RangeDelAggregatorV2::StripeRep::ShouldDelete(
+    const ParsedInternalKey& parsed, RangeDelPositioningMode mode) {
+  if (!InStripe(parsed.sequence) || IsEmpty()) {
+    return false;
+  }
+  switch (mode) {
+    case RangeDelPositioningMode::kForwardTraversal:
+      InvalidateReverseIter();
+
+      // Pick up previously unseen iterators.
+      for (auto it = std::next(iters_.begin(), forward_iter_.UnusedIdx());
+           it != iters_.end(); ++it, forward_iter_.IncUnusedIdx()) {
+        auto& iter = *it;
+        forward_iter_.AddNewIter(iter.get(), parsed);
+      }
+
+      return forward_iter_.ShouldDelete(parsed);
+    case RangeDelPositioningMode::kBackwardTraversal:
+      InvalidateForwardIter();
+
+      // Pick up previously unseen iterators.
+      for (auto it = std::next(iters_.begin(), reverse_iter_.UnusedIdx());
+           it != iters_.end(); ++it, reverse_iter_.IncUnusedIdx()) {
+        auto& iter = *it;
+        reverse_iter_.AddNewIter(iter.get(), parsed);
+      }
+
+      return reverse_iter_.ShouldDelete(parsed);
+    default:
+      assert(false);
+      return false;
+  }
+}
+
+bool RangeDelAggregatorV2::StripeRep::IsRangeOverlapped(const Slice& start,
+                                                        const Slice& end) {
+  Invalidate();
+
+  // Set the internal start/end keys so that:
+  // - if start_ikey has the same user key and sequence number as the
+  // current end key, start_ikey will be considered greater; and
+  // - if end_ikey has the same user key and sequence number as the current
+  // start key, end_ikey will be considered greater.
+  ParsedInternalKey start_ikey(start, kMaxSequenceNumber,
+                               static_cast<ValueType>(0));
+  ParsedInternalKey end_ikey(end, 0, static_cast<ValueType>(0));
+  for (auto& iter : iters_) {
+    bool checked_candidate_tombstones = false;
+    for (iter->SeekForPrev(start);
+         iter->Valid() && icmp_->Compare(iter->start_key(), end_ikey) <= 0;
+         iter->Next()) {
+      checked_candidate_tombstones = true;
+      if (icmp_->Compare(start_ikey, iter->end_key()) < 0 &&
+          icmp_->Compare(iter->start_key(), end_ikey) <= 0) {
+        return true;
+      }
+    }
+
+    if (!checked_candidate_tombstones) {
+      // Do an additional check for when the end of the range is the begin
+      // key of a tombstone, which we missed earlier since SeekForPrev'ing
+      // to the start was invalid.
+      iter->SeekForPrev(end);
+      if (iter->Valid() && icmp_->Compare(start_ikey, iter->end_key()) < 0 &&
+          icmp_->Compare(iter->start_key(), end_ikey) <= 0) {
+        return true;
+      }
+    }
+  }
+  return false;
+}
+
+void ReadRangeDelAggregatorV2::AddTombstones(
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter,
+    const InternalKey* smallest, const InternalKey* largest) {
+  if (input_iter == nullptr || input_iter->empty()) {
+    return;
+  }
+  rep_.AddTombstones(
+      std::unique_ptr<TruncatedRangeDelIterator>(new TruncatedRangeDelIterator(
+          std::move(input_iter), icmp_, smallest, largest)));
+}
+
+bool ReadRangeDelAggregatorV2::ShouldDelete(const ParsedInternalKey& parsed,
+                                            RangeDelPositioningMode mode) {
+  return rep_.ShouldDelete(parsed, mode);
+}
+
+bool ReadRangeDelAggregatorV2::IsRangeOverlapped(const Slice& start,
+                                                 const Slice& end) {
+  InvalidateRangeDelMapPositions();
+  return rep_.IsRangeOverlapped(start, end);
+}
+
+void CompactionRangeDelAggregatorV2::AddTombstones(
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter,
+    const InternalKey* smallest, const InternalKey* largest) {
+  if (input_iter == nullptr || input_iter->empty()) {
+    return;
+  }
+  assert(input_iter->lower_bound() == 0);
+  assert(input_iter->upper_bound() == kMaxSequenceNumber);
+  parent_iters_.emplace_back(new TruncatedRangeDelIterator(
+      std::move(input_iter), icmp_, smallest, largest));
+
+  auto split_iters = parent_iters_.back()->SplitBySnapshot(*snapshots_);
+  for (auto& split_iter : split_iters) {
+    auto it = reps_.find(split_iter.first);
+    if (it == reps_.end()) {
+      bool inserted;
+      SequenceNumber upper_bound = split_iter.second->upper_bound();
+      SequenceNumber lower_bound = split_iter.second->lower_bound();
+      std::tie(it, inserted) = reps_.emplace(
+          split_iter.first, StripeRep(icmp_, upper_bound, lower_bound));
+      assert(inserted);
+    }
+    assert(it != reps_.end());
+    it->second.AddTombstones(std::move(split_iter.second));
+  }
+}
+
+bool CompactionRangeDelAggregatorV2::ShouldDelete(
+    const ParsedInternalKey& parsed, RangeDelPositioningMode mode) {
+  auto it = reps_.lower_bound(parsed.sequence);
+  if (it == reps_.end()) {
+    return false;
+  }
+  return it->second.ShouldDelete(parsed, mode);
+}
+
+namespace {
+
+class TruncatedRangeDelMergingIter : public InternalIterator {
+ public:
+  TruncatedRangeDelMergingIter(
+      const InternalKeyComparator* icmp, const Slice* lower_bound,
+      const Slice* upper_bound, bool upper_bound_inclusive,
+      const std::vector<std::unique_ptr<TruncatedRangeDelIterator>>& children)
+      : icmp_(icmp),
+        lower_bound_(lower_bound),
+        upper_bound_(upper_bound),
+        upper_bound_inclusive_(upper_bound_inclusive),
+        heap_(StartKeyMinComparator(icmp)) {
+    for (auto& child : children) {
+      if (child != nullptr) {
+        assert(child->lower_bound() == 0);
+        assert(child->upper_bound() == kMaxSequenceNumber);
+        children_.push_back(child.get());
+      }
+    }
+  }
+
+  bool Valid() const override {
+    return !heap_.empty() && BeforeEndKey(heap_.top());
+  }
+  Status status() const override { return Status::OK(); }
+
+  void SeekToFirst() override {
+    heap_.clear();
+    for (auto& child : children_) {
+      if (lower_bound_ != nullptr) {
+        child->Seek(*lower_bound_);
+      } else {
+        child->SeekToFirst();
+      }
+      if (child->Valid()) {
+        heap_.push(child);
+      }
+    }
+  }
+
+  void Next() override {
+    auto* top = heap_.top();
+    top->InternalNext();
+    if (top->Valid()) {
+      heap_.replace_top(top);
+    } else {
+      heap_.pop();
+    }
+  }
+
+  Slice key() const override {
+    auto* top = heap_.top();
+    cur_start_key_.Set(top->start_key().user_key, top->seq(),
+                       kTypeRangeDeletion);
+    return cur_start_key_.Encode();
+  }
+
+  Slice value() const override {
+    auto* top = heap_.top();
+    assert(top->end_key().sequence == kMaxSequenceNumber);
+    return top->end_key().user_key;
+  }
+
+  // Unused InternalIterator methods
+  void Prev() override { assert(false); }
+  void Seek(const Slice& /* target */) override { assert(false); }
+  void SeekForPrev(const Slice& /* target */) override { assert(false); }
+  void SeekToLast() override { assert(false); }
+
+ private:
+  bool BeforeEndKey(const TruncatedRangeDelIterator* iter) const {
+    if (upper_bound_ == nullptr) {
+      return true;
+    }
+    int cmp = icmp_->user_comparator()->Compare(iter->start_key().user_key,
+                                                *upper_bound_);
+    return upper_bound_inclusive_ ? cmp <= 0 : cmp < 0;
+  }
+
+  const InternalKeyComparator* icmp_;
+  const Slice* lower_bound_;
+  const Slice* upper_bound_;
+  bool upper_bound_inclusive_;
+  BinaryHeap<TruncatedRangeDelIterator*, StartKeyMinComparator> heap_;
+  std::vector<TruncatedRangeDelIterator*> children_;
+
+  mutable InternalKey cur_start_key_;
+};
+
+}  // namespace
+
+std::unique_ptr<FragmentedRangeTombstoneIterator>
+CompactionRangeDelAggregatorV2::NewIterator(const Slice* lower_bound,
+                                            const Slice* upper_bound,
+                                            bool upper_bound_inclusive) {
+  InvalidateRangeDelMapPositions();
+  std::unique_ptr<TruncatedRangeDelMergingIter> merging_iter(
+      new TruncatedRangeDelMergingIter(icmp_, lower_bound, upper_bound,
+                                       upper_bound_inclusive, parent_iters_));
+
+  // TODO: add tests where tombstone fragments can be outside of upper and lower
+  // bound range
+  auto fragmented_tombstone_list =
+      std::make_shared<FragmentedRangeTombstoneList>(
+          std::move(merging_iter), *icmp_, true /* for_compaction */,
+          *snapshots_);
+
+  return std::unique_ptr<FragmentedRangeTombstoneIterator>(
+      new FragmentedRangeTombstoneIterator(
+          fragmented_tombstone_list, *icmp_,
+          kMaxSequenceNumber /* upper_bound */));
+}
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_v2.h b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_v2.h
new file mode 100644
index 0000000000..306dbf249b
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_v2.h
@@ -0,0 +1,436 @@
+//  Copyright (c) 2018-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include <algorithm>
+#include <iterator>
+#include <list>
+#include <map>
+#include <set>
+#include <string>
+#include <vector>
+
+#include "db/compaction_iteration_stats.h"
+#include "db/dbformat.h"
+#include "db/pinned_iterators_manager.h"
+#include "db/range_del_aggregator.h"
+#include "db/range_tombstone_fragmenter.h"
+#include "db/version_edit.h"
+#include "include/rocksdb/comparator.h"
+#include "include/rocksdb/types.h"
+#include "table/internal_iterator.h"
+#include "table/scoped_arena_iterator.h"
+#include "table/table_builder.h"
+#include "util/heap.h"
+#include "util/kv_map.h"
+
+namespace rocksdb {
+
+class TruncatedRangeDelIterator {
+ public:
+  TruncatedRangeDelIterator(
+      std::unique_ptr<FragmentedRangeTombstoneIterator> iter,
+      const InternalKeyComparator* icmp, const InternalKey* smallest,
+      const InternalKey* largest);
+
+  bool Valid() const;
+
+  void Next();
+  void Prev();
+
+  void InternalNext();
+
+  // Seeks to the tombstone with the highest viisble sequence number that covers
+  // target (a user key). If no such tombstone exists, the position will be at
+  // the earliest tombstone that ends after target.
+  void Seek(const Slice& target);
+
+  // Seeks to the tombstone with the highest viisble sequence number that covers
+  // target (a user key). If no such tombstone exists, the position will be at
+  // the latest tombstone that starts before target.
+  void SeekForPrev(const Slice& target);
+
+  void SeekToFirst();
+  void SeekToLast();
+
+  ParsedInternalKey start_key() const {
+    return (smallest_ == nullptr ||
+            icmp_->Compare(*smallest_, iter_->parsed_start_key()) <= 0)
+               ? iter_->parsed_start_key()
+               : *smallest_;
+  }
+
+  ParsedInternalKey end_key() const {
+    return (largest_ == nullptr ||
+            icmp_->Compare(iter_->parsed_end_key(), *largest_) <= 0)
+               ? iter_->parsed_end_key()
+               : *largest_;
+  }
+
+  SequenceNumber seq() const { return iter_->seq(); }
+
+  std::map<SequenceNumber, std::unique_ptr<TruncatedRangeDelIterator>>
+  SplitBySnapshot(const std::vector<SequenceNumber>& snapshots);
+
+  SequenceNumber upper_bound() const { return iter_->upper_bound(); }
+
+  SequenceNumber lower_bound() const { return iter_->lower_bound(); }
+
+ private:
+  std::unique_ptr<FragmentedRangeTombstoneIterator> iter_;
+  const InternalKeyComparator* icmp_;
+  const ParsedInternalKey* smallest_ = nullptr;
+  const ParsedInternalKey* largest_ = nullptr;
+  std::list<ParsedInternalKey> pinned_bounds_;
+
+  const InternalKey* smallest_ikey_;
+  const InternalKey* largest_ikey_;
+};
+
+struct SeqMaxComparator {
+  bool operator()(const TruncatedRangeDelIterator* a,
+                  const TruncatedRangeDelIterator* b) const {
+    return a->seq() > b->seq();
+  }
+};
+
+struct StartKeyMinComparator {
+  explicit StartKeyMinComparator(const InternalKeyComparator* c) : icmp(c) {}
+
+  bool operator()(const TruncatedRangeDelIterator* a,
+                  const TruncatedRangeDelIterator* b) const {
+    return icmp->Compare(a->start_key(), b->start_key()) > 0;
+  }
+
+  const InternalKeyComparator* icmp;
+};
+
+class ForwardRangeDelIterator {
+ public:
+  ForwardRangeDelIterator(
+      const InternalKeyComparator* icmp,
+      const std::vector<std::unique_ptr<TruncatedRangeDelIterator>>* iters);
+
+  bool ShouldDelete(const ParsedInternalKey& parsed);
+  void Invalidate();
+
+  void AddNewIter(TruncatedRangeDelIterator* iter,
+                  const ParsedInternalKey& parsed) {
+    iter->Seek(parsed.user_key);
+    PushIter(iter, parsed);
+    assert(active_iters_.size() == active_seqnums_.size());
+  }
+
+  size_t UnusedIdx() const { return unused_idx_; }
+  void IncUnusedIdx() { unused_idx_++; }
+
+ private:
+  using ActiveSeqSet =
+      std::multiset<TruncatedRangeDelIterator*, SeqMaxComparator>;
+
+  struct EndKeyMinComparator {
+    explicit EndKeyMinComparator(const InternalKeyComparator* c) : icmp(c) {}
+
+    bool operator()(const ActiveSeqSet::const_iterator& a,
+                    const ActiveSeqSet::const_iterator& b) const {
+      return icmp->Compare((*a)->end_key(), (*b)->end_key()) > 0;
+    }
+
+    const InternalKeyComparator* icmp;
+  };
+
+  void PushIter(TruncatedRangeDelIterator* iter,
+                const ParsedInternalKey& parsed) {
+    if (!iter->Valid()) {
+      // The iterator has been fully consumed, so we don't need to add it to
+      // either of the heaps.
+      return;
+    }
+    int cmp = icmp_->Compare(parsed, iter->start_key());
+    if (cmp < 0) {
+      PushInactiveIter(iter);
+    } else {
+      PushActiveIter(iter);
+    }
+  }
+
+  void PushActiveIter(TruncatedRangeDelIterator* iter) {
+    auto seq_pos = active_seqnums_.insert(iter);
+    active_iters_.push(seq_pos);
+  }
+
+  TruncatedRangeDelIterator* PopActiveIter() {
+    auto active_top = active_iters_.top();
+    auto iter = *active_top;
+    active_iters_.pop();
+    active_seqnums_.erase(active_top);
+    return iter;
+  }
+
+  void PushInactiveIter(TruncatedRangeDelIterator* iter) {
+    inactive_iters_.push(iter);
+  }
+
+  TruncatedRangeDelIterator* PopInactiveIter() {
+    auto* iter = inactive_iters_.top();
+    inactive_iters_.pop();
+    return iter;
+  }
+
+  const InternalKeyComparator* icmp_;
+  const std::vector<std::unique_ptr<TruncatedRangeDelIterator>>* iters_;
+  size_t unused_idx_;
+  ActiveSeqSet active_seqnums_;
+  BinaryHeap<ActiveSeqSet::const_iterator, EndKeyMinComparator> active_iters_;
+  BinaryHeap<TruncatedRangeDelIterator*, StartKeyMinComparator> inactive_iters_;
+};
+
+class ReverseRangeDelIterator {
+ public:
+  ReverseRangeDelIterator(
+      const InternalKeyComparator* icmp,
+      const std::vector<std::unique_ptr<TruncatedRangeDelIterator>>* iters);
+
+  bool ShouldDelete(const ParsedInternalKey& parsed);
+  void Invalidate();
+
+  void AddNewIter(TruncatedRangeDelIterator* iter,
+                  const ParsedInternalKey& parsed) {
+    iter->SeekForPrev(parsed.user_key);
+    PushIter(iter, parsed);
+    assert(active_iters_.size() == active_seqnums_.size());
+  }
+
+  size_t UnusedIdx() const { return unused_idx_; }
+  void IncUnusedIdx() { unused_idx_++; }
+
+ private:
+  using ActiveSeqSet =
+      std::multiset<TruncatedRangeDelIterator*, SeqMaxComparator>;
+
+  struct EndKeyMaxComparator {
+    explicit EndKeyMaxComparator(const InternalKeyComparator* c) : icmp(c) {}
+
+    bool operator()(const TruncatedRangeDelIterator* a,
+                    const TruncatedRangeDelIterator* b) const {
+      return icmp->Compare(a->end_key(), b->end_key()) < 0;
+    }
+
+    const InternalKeyComparator* icmp;
+  };
+  struct StartKeyMaxComparator {
+    explicit StartKeyMaxComparator(const InternalKeyComparator* c) : icmp(c) {}
+
+    bool operator()(const ActiveSeqSet::const_iterator& a,
+                    const ActiveSeqSet::const_iterator& b) const {
+      return icmp->Compare((*a)->start_key(), (*b)->start_key()) < 0;
+    }
+
+    const InternalKeyComparator* icmp;
+  };
+
+  void PushIter(TruncatedRangeDelIterator* iter,
+                const ParsedInternalKey& parsed) {
+    if (!iter->Valid()) {
+      // The iterator has been fully consumed, so we don't need to add it to
+      // either of the heaps.
+    } else if (icmp_->Compare(iter->end_key(), parsed) <= 0) {
+      PushInactiveIter(iter);
+    } else {
+      PushActiveIter(iter);
+    }
+  }
+
+  void PushActiveIter(TruncatedRangeDelIterator* iter) {
+    auto seq_pos = active_seqnums_.insert(iter);
+    active_iters_.push(seq_pos);
+  }
+
+  TruncatedRangeDelIterator* PopActiveIter() {
+    auto active_top = active_iters_.top();
+    auto iter = *active_top;
+    active_iters_.pop();
+    active_seqnums_.erase(active_top);
+    return iter;
+  }
+
+  void PushInactiveIter(TruncatedRangeDelIterator* iter) {
+    inactive_iters_.push(iter);
+  }
+
+  TruncatedRangeDelIterator* PopInactiveIter() {
+    auto* iter = inactive_iters_.top();
+    inactive_iters_.pop();
+    return iter;
+  }
+
+  const InternalKeyComparator* icmp_;
+  const std::vector<std::unique_ptr<TruncatedRangeDelIterator>>* iters_;
+  size_t unused_idx_;
+  ActiveSeqSet active_seqnums_;
+  BinaryHeap<ActiveSeqSet::const_iterator, StartKeyMaxComparator> active_iters_;
+  BinaryHeap<TruncatedRangeDelIterator*, EndKeyMaxComparator> inactive_iters_;
+};
+
+class RangeDelAggregatorV2 {
+ public:
+  explicit RangeDelAggregatorV2(const InternalKeyComparator* icmp)
+      : icmp_(icmp) {}
+  virtual ~RangeDelAggregatorV2() {}
+
+  virtual void AddTombstones(
+      std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter,
+      const InternalKey* smallest = nullptr,
+      const InternalKey* largest = nullptr) = 0;
+
+  bool ShouldDelete(const Slice& key, RangeDelPositioningMode mode) {
+    ParsedInternalKey parsed;
+    if (!ParseInternalKey(key, &parsed)) {
+      return false;
+    }
+    return ShouldDelete(parsed, mode);
+  }
+  virtual bool ShouldDelete(const ParsedInternalKey& parsed,
+                            RangeDelPositioningMode mode) = 0;
+
+  virtual void InvalidateRangeDelMapPositions() = 0;
+
+  virtual bool IsEmpty() const = 0;
+
+  bool AddFile(uint64_t file_number) {
+    return files_seen_.insert(file_number).second;
+  }
+
+ protected:
+  class StripeRep {
+   public:
+    StripeRep(const InternalKeyComparator* icmp, SequenceNumber upper_bound,
+              SequenceNumber lower_bound)
+        : icmp_(icmp),
+          forward_iter_(icmp, &iters_),
+          reverse_iter_(icmp, &iters_),
+          upper_bound_(upper_bound),
+          lower_bound_(lower_bound) {}
+
+    void AddTombstones(std::unique_ptr<TruncatedRangeDelIterator> input_iter) {
+      iters_.push_back(std::move(input_iter));
+    }
+
+    bool IsEmpty() const { return iters_.empty(); }
+
+    bool ShouldDelete(const ParsedInternalKey& parsed,
+                      RangeDelPositioningMode mode);
+
+    void Invalidate() {
+      InvalidateForwardIter();
+      InvalidateReverseIter();
+    }
+
+    bool IsRangeOverlapped(const Slice& start, const Slice& end);
+
+   private:
+    bool InStripe(SequenceNumber seq) const {
+      return lower_bound_ <= seq && seq <= upper_bound_;
+    }
+
+    void InvalidateForwardIter() { forward_iter_.Invalidate(); }
+
+    void InvalidateReverseIter() { reverse_iter_.Invalidate(); }
+
+    const InternalKeyComparator* icmp_;
+    std::vector<std::unique_ptr<TruncatedRangeDelIterator>> iters_;
+    ForwardRangeDelIterator forward_iter_;
+    ReverseRangeDelIterator reverse_iter_;
+    SequenceNumber upper_bound_;
+    SequenceNumber lower_bound_;
+  };
+
+  const InternalKeyComparator* icmp_;
+
+ private:
+  std::set<uint64_t> files_seen_;
+};
+
+class ReadRangeDelAggregatorV2 : public RangeDelAggregatorV2 {
+ public:
+  ReadRangeDelAggregatorV2(const InternalKeyComparator* icmp,
+                           SequenceNumber upper_bound)
+      : RangeDelAggregatorV2(icmp),
+        rep_(icmp, upper_bound, 0 /* lower_bound */) {}
+  ~ReadRangeDelAggregatorV2() override {}
+
+  using RangeDelAggregatorV2::ShouldDelete;
+  void AddTombstones(
+      std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter,
+      const InternalKey* smallest = nullptr,
+      const InternalKey* largest = nullptr) override;
+
+  bool ShouldDelete(const ParsedInternalKey& parsed,
+                    RangeDelPositioningMode mode) override;
+
+  bool IsRangeOverlapped(const Slice& start, const Slice& end);
+
+  void InvalidateRangeDelMapPositions() override { rep_.Invalidate(); }
+
+  bool IsEmpty() const override { return rep_.IsEmpty(); }
+
+ private:
+  StripeRep rep_;
+};
+
+class CompactionRangeDelAggregatorV2 : public RangeDelAggregatorV2 {
+ public:
+  CompactionRangeDelAggregatorV2(const InternalKeyComparator* icmp,
+                                 const std::vector<SequenceNumber>& snapshots)
+      : RangeDelAggregatorV2(icmp), snapshots_(&snapshots) {}
+  ~CompactionRangeDelAggregatorV2() override {}
+
+  void AddTombstones(
+      std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter,
+      const InternalKey* smallest = nullptr,
+      const InternalKey* largest = nullptr) override;
+
+  using RangeDelAggregatorV2::ShouldDelete;
+  bool ShouldDelete(const ParsedInternalKey& parsed,
+                    RangeDelPositioningMode mode) override;
+
+  bool IsRangeOverlapped(const Slice& start, const Slice& end);
+
+  void InvalidateRangeDelMapPositions() override {
+    for (auto& rep : reps_) {
+      rep.second.Invalidate();
+    }
+  }
+
+  bool IsEmpty() const override {
+    for (const auto& rep : reps_) {
+      if (!rep.second.IsEmpty()) {
+        return false;
+      }
+    }
+    return true;
+  }
+
+  // Creates an iterator over all the range tombstones in the aggregator, for
+  // use in compaction. Nullptr arguments indicate that the iterator range is
+  // unbounded.
+  // NOTE: the boundaries are used for optimization purposes to reduce the
+  // number of tombstones that are passed to the fragmenter; they do not
+  // guarantee that the resulting iterator only contains range tombstones that
+  // cover keys in the provided range. If required, these bounds must be
+  // enforced during iteration.
+  std::unique_ptr<FragmentedRangeTombstoneIterator> NewIterator(
+      const Slice* lower_bound = nullptr, const Slice* upper_bound = nullptr,
+      bool upper_bound_inclusive = false);
+
+ private:
+  std::vector<std::unique_ptr<TruncatedRangeDelIterator>> parent_iters_;
+  std::map<SequenceNumber, StripeRep> reps_;
+
+  const std::vector<SequenceNumber>* snapshots_;
+};
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_v2_test.cc b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_v2_test.cc
new file mode 100644
index 0000000000..64f8ed0794
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/range_del_aggregator_v2_test.cc
@@ -0,0 +1,709 @@
+//  Copyright (c) 2018-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/range_del_aggregator_v2.h"
+
+#include <memory>
+#include <string>
+#include <vector>
+
+#include "db/db_test_util.h"
+#include "db/dbformat.h"
+#include "db/range_tombstone_fragmenter.h"
+#include "util/testutil.h"
+
+namespace rocksdb {
+
+class RangeDelAggregatorV2Test : public testing::Test {};
+
+namespace {
+
+static auto bytewise_icmp = InternalKeyComparator(BytewiseComparator());
+
+std::unique_ptr<InternalIterator> MakeRangeDelIter(
+    const std::vector<RangeTombstone>& range_dels) {
+  std::vector<std::string> keys, values;
+  for (const auto& range_del : range_dels) {
+    auto key_and_value = range_del.Serialize();
+    keys.push_back(key_and_value.first.Encode().ToString());
+    values.push_back(key_and_value.second.ToString());
+  }
+  return std::unique_ptr<test::VectorIterator>(
+      new test::VectorIterator(keys, values));
+}
+
+std::vector<std::unique_ptr<FragmentedRangeTombstoneList>>
+MakeFragmentedTombstoneLists(
+    const std::vector<std::vector<RangeTombstone>>& range_dels_list) {
+  std::vector<std::unique_ptr<FragmentedRangeTombstoneList>> fragment_lists;
+  for (const auto& range_dels : range_dels_list) {
+    auto range_del_iter = MakeRangeDelIter(range_dels);
+    fragment_lists.emplace_back(new FragmentedRangeTombstoneList(
+        std::move(range_del_iter), bytewise_icmp));
+  }
+  return fragment_lists;
+}
+
+struct TruncatedIterScanTestCase {
+  ParsedInternalKey start;
+  ParsedInternalKey end;
+  SequenceNumber seq;
+};
+
+struct TruncatedIterSeekTestCase {
+  Slice target;
+  ParsedInternalKey start;
+  ParsedInternalKey end;
+  SequenceNumber seq;
+  bool invalid;
+};
+
+struct ShouldDeleteTestCase {
+  ParsedInternalKey lookup_key;
+  bool result;
+};
+
+struct IsRangeOverlappedTestCase {
+  Slice start;
+  Slice end;
+  bool result;
+};
+
+ParsedInternalKey UncutEndpoint(const Slice& s) {
+  return ParsedInternalKey(s, kMaxSequenceNumber, kTypeRangeDeletion);
+}
+
+ParsedInternalKey InternalValue(const Slice& key, SequenceNumber seq) {
+  return ParsedInternalKey(key, seq, kTypeValue);
+}
+
+void VerifyIterator(
+    TruncatedRangeDelIterator* iter, const InternalKeyComparator& icmp,
+    const std::vector<TruncatedIterScanTestCase>& expected_range_dels) {
+  // Test forward iteration.
+  iter->SeekToFirst();
+  for (size_t i = 0; i < expected_range_dels.size(); i++, iter->Next()) {
+    ASSERT_TRUE(iter->Valid());
+    EXPECT_EQ(0, icmp.Compare(iter->start_key(), expected_range_dels[i].start));
+    EXPECT_EQ(0, icmp.Compare(iter->end_key(), expected_range_dels[i].end));
+    EXPECT_EQ(expected_range_dels[i].seq, iter->seq());
+  }
+  EXPECT_FALSE(iter->Valid());
+
+  // Test reverse iteration.
+  iter->SeekToLast();
+  std::vector<TruncatedIterScanTestCase> reverse_expected_range_dels(
+      expected_range_dels.rbegin(), expected_range_dels.rend());
+  for (size_t i = 0; i < reverse_expected_range_dels.size();
+       i++, iter->Prev()) {
+    ASSERT_TRUE(iter->Valid());
+    EXPECT_EQ(0, icmp.Compare(iter->start_key(),
+                              reverse_expected_range_dels[i].start));
+    EXPECT_EQ(
+        0, icmp.Compare(iter->end_key(), reverse_expected_range_dels[i].end));
+    EXPECT_EQ(reverse_expected_range_dels[i].seq, iter->seq());
+  }
+  EXPECT_FALSE(iter->Valid());
+}
+
+void VerifySeek(TruncatedRangeDelIterator* iter,
+                const InternalKeyComparator& icmp,
+                const std::vector<TruncatedIterSeekTestCase>& test_cases) {
+  for (const auto& test_case : test_cases) {
+    iter->Seek(test_case.target);
+    if (test_case.invalid) {
+      ASSERT_FALSE(iter->Valid());
+    } else {
+      ASSERT_TRUE(iter->Valid());
+      EXPECT_EQ(0, icmp.Compare(iter->start_key(), test_case.start));
+      EXPECT_EQ(0, icmp.Compare(iter->end_key(), test_case.end));
+      EXPECT_EQ(test_case.seq, iter->seq());
+    }
+  }
+}
+
+void VerifySeekForPrev(
+    TruncatedRangeDelIterator* iter, const InternalKeyComparator& icmp,
+    const std::vector<TruncatedIterSeekTestCase>& test_cases) {
+  for (const auto& test_case : test_cases) {
+    iter->SeekForPrev(test_case.target);
+    if (test_case.invalid) {
+      ASSERT_FALSE(iter->Valid());
+    } else {
+      ASSERT_TRUE(iter->Valid());
+      EXPECT_EQ(0, icmp.Compare(iter->start_key(), test_case.start));
+      EXPECT_EQ(0, icmp.Compare(iter->end_key(), test_case.end));
+      EXPECT_EQ(test_case.seq, iter->seq());
+    }
+  }
+}
+
+void VerifyShouldDelete(RangeDelAggregatorV2* range_del_agg,
+                        const std::vector<ShouldDeleteTestCase>& test_cases) {
+  for (const auto& test_case : test_cases) {
+    EXPECT_EQ(
+        test_case.result,
+        range_del_agg->ShouldDelete(
+            test_case.lookup_key, RangeDelPositioningMode::kForwardTraversal));
+  }
+  for (auto it = test_cases.rbegin(); it != test_cases.rend(); ++it) {
+    const auto& test_case = *it;
+    EXPECT_EQ(
+        test_case.result,
+        range_del_agg->ShouldDelete(
+            test_case.lookup_key, RangeDelPositioningMode::kBackwardTraversal));
+  }
+}
+
+void VerifyIsRangeOverlapped(
+    ReadRangeDelAggregatorV2* range_del_agg,
+    const std::vector<IsRangeOverlappedTestCase>& test_cases) {
+  for (const auto& test_case : test_cases) {
+    EXPECT_EQ(test_case.result,
+              range_del_agg->IsRangeOverlapped(test_case.start, test_case.end));
+  }
+}
+
+void CheckIterPosition(const RangeTombstone& tombstone,
+                       const FragmentedRangeTombstoneIterator* iter) {
+  // Test InternalIterator interface.
+  EXPECT_EQ(tombstone.start_key_, ExtractUserKey(iter->key()));
+  EXPECT_EQ(tombstone.end_key_, iter->value());
+  EXPECT_EQ(tombstone.seq_, iter->seq());
+
+  // Test FragmentedRangeTombstoneIterator interface.
+  EXPECT_EQ(tombstone.start_key_, iter->start_key());
+  EXPECT_EQ(tombstone.end_key_, iter->end_key());
+  EXPECT_EQ(tombstone.seq_, GetInternalKeySeqno(iter->key()));
+}
+
+void VerifyFragmentedRangeDels(
+    FragmentedRangeTombstoneIterator* iter,
+    const std::vector<RangeTombstone>& expected_tombstones) {
+  iter->SeekToFirst();
+  for (size_t i = 0; i < expected_tombstones.size(); i++, iter->Next()) {
+    ASSERT_TRUE(iter->Valid());
+    CheckIterPosition(expected_tombstones[i], iter);
+  }
+  EXPECT_FALSE(iter->Valid());
+}
+
+}  // namespace
+
+TEST_F(RangeDelAggregatorV2Test, EmptyTruncatedIter) {
+  auto range_del_iter = MakeRangeDelIter({});
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+      new FragmentedRangeTombstoneIterator(&fragment_list, bytewise_icmp,
+                                           kMaxSequenceNumber));
+
+  TruncatedRangeDelIterator iter(std::move(input_iter), &bytewise_icmp, nullptr,
+                                 nullptr);
+
+  iter.SeekToFirst();
+  ASSERT_FALSE(iter.Valid());
+
+  iter.SeekToLast();
+  ASSERT_FALSE(iter.Valid());
+}
+
+TEST_F(RangeDelAggregatorV2Test, UntruncatedIter) {
+  auto range_del_iter =
+      MakeRangeDelIter({{"a", "e", 10}, {"e", "g", 8}, {"j", "n", 4}});
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+      new FragmentedRangeTombstoneIterator(&fragment_list, bytewise_icmp,
+                                           kMaxSequenceNumber));
+
+  TruncatedRangeDelIterator iter(std::move(input_iter), &bytewise_icmp, nullptr,
+                                 nullptr);
+
+  VerifyIterator(&iter, bytewise_icmp,
+                 {{UncutEndpoint("a"), UncutEndpoint("e"), 10},
+                  {UncutEndpoint("e"), UncutEndpoint("g"), 8},
+                  {UncutEndpoint("j"), UncutEndpoint("n"), 4}});
+
+  VerifySeek(
+      &iter, bytewise_icmp,
+      {{"d", UncutEndpoint("a"), UncutEndpoint("e"), 10},
+       {"e", UncutEndpoint("e"), UncutEndpoint("g"), 8},
+       {"ia", UncutEndpoint("j"), UncutEndpoint("n"), 4},
+       {"n", UncutEndpoint(""), UncutEndpoint(""), 0, true /* invalid */},
+       {"", UncutEndpoint("a"), UncutEndpoint("e"), 10}});
+
+  VerifySeekForPrev(
+      &iter, bytewise_icmp,
+      {{"d", UncutEndpoint("a"), UncutEndpoint("e"), 10},
+       {"e", UncutEndpoint("e"), UncutEndpoint("g"), 8},
+       {"ia", UncutEndpoint("e"), UncutEndpoint("g"), 8},
+       {"n", UncutEndpoint("j"), UncutEndpoint("n"), 4},
+       {"", UncutEndpoint(""), UncutEndpoint(""), 0, true /* invalid */}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, UntruncatedIterWithSnapshot) {
+  auto range_del_iter =
+      MakeRangeDelIter({{"a", "e", 10}, {"e", "g", 8}, {"j", "n", 4}});
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+      new FragmentedRangeTombstoneIterator(&fragment_list, bytewise_icmp,
+                                           9 /* snapshot */));
+
+  TruncatedRangeDelIterator iter(std::move(input_iter), &bytewise_icmp, nullptr,
+                                 nullptr);
+
+  VerifyIterator(&iter, bytewise_icmp,
+                 {{UncutEndpoint("e"), UncutEndpoint("g"), 8},
+                  {UncutEndpoint("j"), UncutEndpoint("n"), 4}});
+
+  VerifySeek(
+      &iter, bytewise_icmp,
+      {{"d", UncutEndpoint("e"), UncutEndpoint("g"), 8},
+       {"e", UncutEndpoint("e"), UncutEndpoint("g"), 8},
+       {"ia", UncutEndpoint("j"), UncutEndpoint("n"), 4},
+       {"n", UncutEndpoint(""), UncutEndpoint(""), 0, true /* invalid */},
+       {"", UncutEndpoint("e"), UncutEndpoint("g"), 8}});
+
+  VerifySeekForPrev(
+      &iter, bytewise_icmp,
+      {{"d", UncutEndpoint(""), UncutEndpoint(""), 0, true /* invalid */},
+       {"e", UncutEndpoint("e"), UncutEndpoint("g"), 8},
+       {"ia", UncutEndpoint("e"), UncutEndpoint("g"), 8},
+       {"n", UncutEndpoint("j"), UncutEndpoint("n"), 4},
+       {"", UncutEndpoint(""), UncutEndpoint(""), 0, true /* invalid */}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, TruncatedIterPartiallyCutTombstones) {
+  auto range_del_iter =
+      MakeRangeDelIter({{"a", "e", 10}, {"e", "g", 8}, {"j", "n", 4}});
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+      new FragmentedRangeTombstoneIterator(&fragment_list, bytewise_icmp,
+                                           kMaxSequenceNumber));
+
+  InternalKey smallest("d", 7, kTypeValue);
+  InternalKey largest("m", 9, kTypeValue);
+  TruncatedRangeDelIterator iter(std::move(input_iter), &bytewise_icmp,
+                                 &smallest, &largest);
+
+  VerifyIterator(&iter, bytewise_icmp,
+                 {{InternalValue("d", 7), UncutEndpoint("e"), 10},
+                  {UncutEndpoint("e"), UncutEndpoint("g"), 8},
+                  {UncutEndpoint("j"), InternalValue("m", 8), 4}});
+
+  VerifySeek(
+      &iter, bytewise_icmp,
+      {{"d", InternalValue("d", 7), UncutEndpoint("e"), 10},
+       {"e", UncutEndpoint("e"), UncutEndpoint("g"), 8},
+       {"ia", UncutEndpoint("j"), InternalValue("m", 8), 4},
+       {"n", UncutEndpoint(""), UncutEndpoint(""), 0, true /* invalid */},
+       {"", InternalValue("d", 7), UncutEndpoint("e"), 10}});
+
+  VerifySeekForPrev(
+      &iter, bytewise_icmp,
+      {{"d", InternalValue("d", 7), UncutEndpoint("e"), 10},
+       {"e", UncutEndpoint("e"), UncutEndpoint("g"), 8},
+       {"ia", UncutEndpoint("e"), UncutEndpoint("g"), 8},
+       {"n", UncutEndpoint("j"), InternalValue("m", 8), 4},
+       {"", UncutEndpoint(""), UncutEndpoint(""), 0, true /* invalid */}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, TruncatedIterFullyCutTombstones) {
+  auto range_del_iter =
+      MakeRangeDelIter({{"a", "e", 10}, {"e", "g", 8}, {"j", "n", 4}});
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+      new FragmentedRangeTombstoneIterator(&fragment_list, bytewise_icmp,
+                                           kMaxSequenceNumber));
+
+  InternalKey smallest("f", 7, kTypeValue);
+  InternalKey largest("i", 9, kTypeValue);
+  TruncatedRangeDelIterator iter(std::move(input_iter), &bytewise_icmp,
+                                 &smallest, &largest);
+
+  VerifyIterator(&iter, bytewise_icmp,
+                 {{InternalValue("f", 7), UncutEndpoint("g"), 8}});
+
+  VerifySeek(
+      &iter, bytewise_icmp,
+      {{"d", InternalValue("f", 7), UncutEndpoint("g"), 8},
+       {"f", InternalValue("f", 7), UncutEndpoint("g"), 8},
+       {"j", UncutEndpoint(""), UncutEndpoint(""), 0, true /* invalid */}});
+
+  VerifySeekForPrev(
+      &iter, bytewise_icmp,
+      {{"d", UncutEndpoint(""), UncutEndpoint(""), 0, true /* invalid */},
+       {"f", InternalValue("f", 7), UncutEndpoint("g"), 8},
+       {"j", InternalValue("f", 7), UncutEndpoint("g"), 8}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, SingleIterInAggregator) {
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10}, {"c", "g", 8}});
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+      new FragmentedRangeTombstoneIterator(&fragment_list, bytewise_icmp,
+                                           kMaxSequenceNumber));
+
+  ReadRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, kMaxSequenceNumber);
+  range_del_agg.AddTombstones(std::move(input_iter));
+
+  VerifyShouldDelete(&range_del_agg, {{InternalValue("a", 19), false},
+                                      {InternalValue("b", 9), true},
+                                      {InternalValue("d", 9), true},
+                                      {InternalValue("e", 7), true},
+                                      {InternalValue("g", 7), false}});
+
+  VerifyIsRangeOverlapped(&range_del_agg, {{"", "_", false},
+                                           {"_", "a", true},
+                                           {"a", "c", true},
+                                           {"d", "f", true},
+                                           {"g", "l", false}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, MultipleItersInAggregator) {
+  auto fragment_lists = MakeFragmentedTombstoneLists(
+      {{{"a", "e", 10}, {"c", "g", 8}},
+       {{"a", "b", 20}, {"h", "i", 25}, {"ii", "j", 15}}});
+
+  ReadRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, kMaxSequenceNumber);
+  for (const auto& fragment_list : fragment_lists) {
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+        new FragmentedRangeTombstoneIterator(fragment_list.get(), bytewise_icmp,
+                                             kMaxSequenceNumber));
+    range_del_agg.AddTombstones(std::move(input_iter));
+  }
+
+  VerifyShouldDelete(&range_del_agg, {{InternalValue("a", 19), true},
+                                      {InternalValue("b", 19), false},
+                                      {InternalValue("b", 9), true},
+                                      {InternalValue("d", 9), true},
+                                      {InternalValue("e", 7), true},
+                                      {InternalValue("g", 7), false},
+                                      {InternalValue("h", 24), true},
+                                      {InternalValue("i", 24), false},
+                                      {InternalValue("ii", 14), true},
+                                      {InternalValue("j", 14), false}});
+
+  VerifyIsRangeOverlapped(&range_del_agg, {{"", "_", false},
+                                           {"_", "a", true},
+                                           {"a", "c", true},
+                                           {"d", "f", true},
+                                           {"g", "l", true},
+                                           {"x", "y", false}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, MultipleItersInAggregatorWithUpperBound) {
+  auto fragment_lists = MakeFragmentedTombstoneLists(
+      {{{"a", "e", 10}, {"c", "g", 8}},
+       {{"a", "b", 20}, {"h", "i", 25}, {"ii", "j", 15}}});
+
+  ReadRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, 19);
+  for (const auto& fragment_list : fragment_lists) {
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+        new FragmentedRangeTombstoneIterator(fragment_list.get(), bytewise_icmp,
+                                             19 /* snapshot */));
+    range_del_agg.AddTombstones(std::move(input_iter));
+  }
+
+  VerifyShouldDelete(&range_del_agg, {{InternalValue("a", 19), false},
+                                      {InternalValue("a", 9), true},
+                                      {InternalValue("b", 9), true},
+                                      {InternalValue("d", 9), true},
+                                      {InternalValue("e", 7), true},
+                                      {InternalValue("g", 7), false},
+                                      {InternalValue("h", 24), false},
+                                      {InternalValue("i", 24), false},
+                                      {InternalValue("ii", 14), true},
+                                      {InternalValue("j", 14), false}});
+
+  VerifyIsRangeOverlapped(&range_del_agg, {{"", "_", false},
+                                           {"_", "a", true},
+                                           {"a", "c", true},
+                                           {"d", "f", true},
+                                           {"g", "l", true},
+                                           {"x", "y", false}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, MultipleTruncatedItersInAggregator) {
+  auto fragment_lists = MakeFragmentedTombstoneLists(
+      {{{"a", "z", 10}}, {{"a", "z", 10}}, {{"a", "z", 10}}});
+  std::vector<std::pair<InternalKey, InternalKey>> iter_bounds = {
+      {InternalKey("a", 4, kTypeValue),
+       InternalKey("m", kMaxSequenceNumber, kTypeRangeDeletion)},
+      {InternalKey("m", 20, kTypeValue),
+       InternalKey("x", kMaxSequenceNumber, kTypeRangeDeletion)},
+      {InternalKey("x", 5, kTypeValue), InternalKey("zz", 30, kTypeValue)}};
+
+  ReadRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, 19);
+  for (size_t i = 0; i < fragment_lists.size(); i++) {
+    const auto& fragment_list = fragment_lists[i];
+    const auto& bounds = iter_bounds[i];
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+        new FragmentedRangeTombstoneIterator(fragment_list.get(), bytewise_icmp,
+                                             19 /* snapshot */));
+    range_del_agg.AddTombstones(std::move(input_iter), &bounds.first,
+                                &bounds.second);
+  }
+
+  VerifyShouldDelete(&range_del_agg, {{InternalValue("a", 10), false},
+                                      {InternalValue("a", 9), false},
+                                      {InternalValue("a", 4), true},
+                                      {InternalValue("m", 10), false},
+                                      {InternalValue("m", 9), true},
+                                      {InternalValue("x", 10), false},
+                                      {InternalValue("x", 9), false},
+                                      {InternalValue("x", 5), true},
+                                      {InternalValue("z", 9), false}});
+
+  VerifyIsRangeOverlapped(&range_del_agg, {{"", "_", false},
+                                           {"_", "a", true},
+                                           {"a", "n", true},
+                                           {"l", "x", true},
+                                           {"w", "z", true},
+                                           {"zzz", "zz", false},
+                                           {"zz", "zzz", false}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, MultipleTruncatedItersInAggregatorSameLevel) {
+  auto fragment_lists = MakeFragmentedTombstoneLists(
+      {{{"a", "z", 10}}, {{"a", "z", 10}}, {{"a", "z", 10}}});
+  std::vector<std::pair<InternalKey, InternalKey>> iter_bounds = {
+      {InternalKey("a", 4, kTypeValue),
+       InternalKey("m", kMaxSequenceNumber, kTypeRangeDeletion)},
+      {InternalKey("m", 20, kTypeValue),
+       InternalKey("x", kMaxSequenceNumber, kTypeRangeDeletion)},
+      {InternalKey("x", 5, kTypeValue), InternalKey("zz", 30, kTypeValue)}};
+
+  ReadRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, 19);
+
+  auto add_iter_to_agg = [&](size_t i) {
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+        new FragmentedRangeTombstoneIterator(fragment_lists[i].get(),
+                                             bytewise_icmp, 19 /* snapshot */));
+    range_del_agg.AddTombstones(std::move(input_iter), &iter_bounds[i].first,
+                                &iter_bounds[i].second);
+  };
+
+  add_iter_to_agg(0);
+  VerifyShouldDelete(&range_del_agg, {{InternalValue("a", 10), false},
+                                      {InternalValue("a", 9), false},
+                                      {InternalValue("a", 4), true}});
+
+  add_iter_to_agg(1);
+  VerifyShouldDelete(&range_del_agg, {{InternalValue("m", 10), false},
+                                      {InternalValue("m", 9), true}});
+
+  add_iter_to_agg(2);
+  VerifyShouldDelete(&range_del_agg, {{InternalValue("x", 10), false},
+                                      {InternalValue("x", 9), false},
+                                      {InternalValue("x", 5), true},
+                                      {InternalValue("z", 9), false}});
+
+  VerifyIsRangeOverlapped(&range_del_agg, {{"", "_", false},
+                                           {"_", "a", true},
+                                           {"a", "n", true},
+                                           {"l", "x", true},
+                                           {"w", "z", true},
+                                           {"zzz", "zz", false},
+                                           {"zz", "zzz", false}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, CompactionAggregatorNoSnapshots) {
+  auto fragment_lists = MakeFragmentedTombstoneLists(
+      {{{"a", "e", 10}, {"c", "g", 8}},
+       {{"a", "b", 20}, {"h", "i", 25}, {"ii", "j", 15}}});
+
+  std::vector<SequenceNumber> snapshots;
+  CompactionRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, snapshots);
+  for (const auto& fragment_list : fragment_lists) {
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+        new FragmentedRangeTombstoneIterator(fragment_list.get(), bytewise_icmp,
+                                             kMaxSequenceNumber));
+    range_del_agg.AddTombstones(std::move(input_iter));
+  }
+
+  VerifyShouldDelete(&range_del_agg, {{InternalValue("a", 19), true},
+                                      {InternalValue("b", 19), false},
+                                      {InternalValue("b", 9), true},
+                                      {InternalValue("d", 9), true},
+                                      {InternalValue("e", 7), true},
+                                      {InternalValue("g", 7), false},
+                                      {InternalValue("h", 24), true},
+                                      {InternalValue("i", 24), false},
+                                      {InternalValue("ii", 14), true},
+                                      {InternalValue("j", 14), false}});
+
+  auto range_del_compaction_iter = range_del_agg.NewIterator();
+  VerifyFragmentedRangeDels(range_del_compaction_iter.get(), {{"a", "b", 20},
+                                                              {"b", "c", 10},
+                                                              {"c", "e", 10},
+                                                              {"e", "g", 8},
+                                                              {"h", "i", 25},
+                                                              {"ii", "j", 15}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, CompactionAggregatorWithSnapshots) {
+  auto fragment_lists = MakeFragmentedTombstoneLists(
+      {{{"a", "e", 10}, {"c", "g", 8}},
+       {{"a", "b", 20}, {"h", "i", 25}, {"ii", "j", 15}}});
+
+  std::vector<SequenceNumber> snapshots{9, 19};
+  CompactionRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, snapshots);
+  for (const auto& fragment_list : fragment_lists) {
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+        new FragmentedRangeTombstoneIterator(fragment_list.get(), bytewise_icmp,
+                                             kMaxSequenceNumber));
+    range_del_agg.AddTombstones(std::move(input_iter));
+  }
+
+  VerifyShouldDelete(
+      &range_del_agg,
+      {
+          {InternalValue("a", 19), false},  // [10, 19]
+          {InternalValue("a", 9), false},   // [0, 9]
+          {InternalValue("b", 9), false},   // [0, 9]
+          {InternalValue("d", 9), false},   // [0, 9]
+          {InternalValue("d", 7), true},    // [0, 9]
+          {InternalValue("e", 7), true},    // [0, 9]
+          {InternalValue("g", 7), false},   // [0, 9]
+          {InternalValue("h", 24), true},   // [20, kMaxSequenceNumber]
+          {InternalValue("i", 24), false},  // [20, kMaxSequenceNumber]
+          {InternalValue("ii", 14), true},  // [10, 19]
+          {InternalValue("j", 14), false}   // [10, 19]
+      });
+
+  auto range_del_compaction_iter = range_del_agg.NewIterator();
+  VerifyFragmentedRangeDels(range_del_compaction_iter.get(), {{"a", "b", 20},
+                                                              {"a", "b", 10},
+                                                              {"b", "c", 10},
+                                                              {"c", "e", 10},
+                                                              {"c", "e", 8},
+                                                              {"e", "g", 8},
+                                                              {"h", "i", 25},
+                                                              {"ii", "j", 15}});
+}
+
+TEST_F(RangeDelAggregatorV2Test, CompactionAggregatorEmptyIteratorLeft) {
+  auto fragment_lists = MakeFragmentedTombstoneLists(
+      {{{"a", "e", 10}, {"c", "g", 8}},
+       {{"a", "b", 20}, {"h", "i", 25}, {"ii", "j", 15}}});
+
+  std::vector<SequenceNumber> snapshots{9, 19};
+  CompactionRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, snapshots);
+  for (const auto& fragment_list : fragment_lists) {
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+        new FragmentedRangeTombstoneIterator(fragment_list.get(), bytewise_icmp,
+                                             kMaxSequenceNumber));
+    range_del_agg.AddTombstones(std::move(input_iter));
+  }
+
+  Slice start("_");
+  Slice end("__");
+}
+
+TEST_F(RangeDelAggregatorV2Test, CompactionAggregatorEmptyIteratorRight) {
+  auto fragment_lists = MakeFragmentedTombstoneLists(
+      {{{"a", "e", 10}, {"c", "g", 8}},
+       {{"a", "b", 20}, {"h", "i", 25}, {"ii", "j", 15}}});
+
+  std::vector<SequenceNumber> snapshots{9, 19};
+  CompactionRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, snapshots);
+  for (const auto& fragment_list : fragment_lists) {
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+        new FragmentedRangeTombstoneIterator(fragment_list.get(), bytewise_icmp,
+                                             kMaxSequenceNumber));
+    range_del_agg.AddTombstones(std::move(input_iter));
+  }
+
+  Slice start("p");
+  Slice end("q");
+  auto range_del_compaction_iter1 =
+      range_del_agg.NewIterator(&start, &end, false /* end_key_inclusive */);
+  VerifyFragmentedRangeDels(range_del_compaction_iter1.get(), {});
+
+  auto range_del_compaction_iter2 =
+      range_del_agg.NewIterator(&start, &end, true /* end_key_inclusive */);
+  VerifyFragmentedRangeDels(range_del_compaction_iter2.get(), {});
+}
+
+TEST_F(RangeDelAggregatorV2Test, CompactionAggregatorBoundedIterator) {
+  auto fragment_lists = MakeFragmentedTombstoneLists(
+      {{{"a", "e", 10}, {"c", "g", 8}},
+       {{"a", "b", 20}, {"h", "i", 25}, {"ii", "j", 15}}});
+
+  std::vector<SequenceNumber> snapshots{9, 19};
+  CompactionRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, snapshots);
+  for (const auto& fragment_list : fragment_lists) {
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+        new FragmentedRangeTombstoneIterator(fragment_list.get(), bytewise_icmp,
+                                             kMaxSequenceNumber));
+    range_del_agg.AddTombstones(std::move(input_iter));
+  }
+
+  Slice start("bb");
+  Slice end("e");
+  auto range_del_compaction_iter1 =
+      range_del_agg.NewIterator(&start, &end, false /* end_key_inclusive */);
+  VerifyFragmentedRangeDels(range_del_compaction_iter1.get(),
+                            {{"a", "c", 10}, {"c", "e", 10}, {"c", "e", 8}});
+
+  auto range_del_compaction_iter2 =
+      range_del_agg.NewIterator(&start, &end, true /* end_key_inclusive */);
+  VerifyFragmentedRangeDels(
+      range_del_compaction_iter2.get(),
+      {{"a", "c", 10}, {"c", "e", 10}, {"c", "e", 8}, {"e", "g", 8}});
+}
+
+TEST_F(RangeDelAggregatorV2Test,
+       CompactionAggregatorBoundedIteratorExtraFragments) {
+  auto fragment_lists = MakeFragmentedTombstoneLists(
+      {{{"a", "d", 10}, {"c", "g", 8}},
+       {{"b", "c", 20}, {"d", "f", 30}, {"h", "i", 25}, {"ii", "j", 15}}});
+
+  std::vector<SequenceNumber> snapshots{9, 19};
+  CompactionRangeDelAggregatorV2 range_del_agg(&bytewise_icmp, snapshots);
+  for (const auto& fragment_list : fragment_lists) {
+    std::unique_ptr<FragmentedRangeTombstoneIterator> input_iter(
+        new FragmentedRangeTombstoneIterator(fragment_list.get(), bytewise_icmp,
+                                             kMaxSequenceNumber));
+    range_del_agg.AddTombstones(std::move(input_iter));
+  }
+
+  Slice start("bb");
+  Slice end("e");
+  auto range_del_compaction_iter1 =
+      range_del_agg.NewIterator(&start, &end, false /* end_key_inclusive */);
+  VerifyFragmentedRangeDels(range_del_compaction_iter1.get(), {{"a", "b", 10},
+                                                               {"b", "c", 20},
+                                                               {"b", "c", 10},
+                                                               {"c", "d", 10},
+                                                               {"c", "d", 8},
+                                                               {"d", "f", 30},
+                                                               {"d", "f", 8},
+                                                               {"f", "g", 8}});
+
+  auto range_del_compaction_iter2 =
+      range_del_agg.NewIterator(&start, &end, true /* end_key_inclusive */);
+  VerifyFragmentedRangeDels(range_del_compaction_iter2.get(), {{"a", "b", 10},
+                                                               {"b", "c", 20},
+                                                               {"b", "c", 10},
+                                                               {"c", "d", 10},
+                                                               {"c", "d", 8},
+                                                               {"d", "f", 30},
+                                                               {"d", "f", 8},
+                                                               {"f", "g", 8}});
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
diff --git a/3rdParty/rocksdb/v5.18.X/db/range_tombstone_fragmenter.cc b/3rdParty/rocksdb/v5.18.X/db/range_tombstone_fragmenter.cc
new file mode 100644
index 0000000000..f9d9f2feb4
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/range_tombstone_fragmenter.cc
@@ -0,0 +1,438 @@
+//  Copyright (c) 2018-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/range_tombstone_fragmenter.h"
+
+#include <algorithm>
+#include <functional>
+#include <set>
+
+#include <inttypes.h>
+#include <stdio.h>
+
+#include "util/autovector.h"
+#include "util/kv_map.h"
+#include "util/vector_iterator.h"
+
+namespace rocksdb {
+
+FragmentedRangeTombstoneList::FragmentedRangeTombstoneList(
+    std::unique_ptr<InternalIterator> unfragmented_tombstones,
+    const InternalKeyComparator& icmp, bool for_compaction,
+    const std::vector<SequenceNumber>& snapshots) {
+  if (unfragmented_tombstones == nullptr) {
+    return;
+  }
+  bool is_sorted = true;
+  int num_tombstones = 0;
+  InternalKey pinned_last_start_key;
+  Slice last_start_key;
+  for (unfragmented_tombstones->SeekToFirst(); unfragmented_tombstones->Valid();
+       unfragmented_tombstones->Next(), num_tombstones++) {
+    if (num_tombstones > 0 &&
+        icmp.Compare(last_start_key, unfragmented_tombstones->key()) > 0) {
+      is_sorted = false;
+      break;
+    }
+    if (unfragmented_tombstones->IsKeyPinned()) {
+      last_start_key = unfragmented_tombstones->key();
+    } else {
+      pinned_last_start_key.DecodeFrom(unfragmented_tombstones->key());
+      last_start_key = pinned_last_start_key.Encode();
+    }
+  }
+  if (is_sorted) {
+    FragmentTombstones(std::move(unfragmented_tombstones), icmp, for_compaction,
+                       snapshots);
+    return;
+  }
+
+  // Sort the tombstones before fragmenting them.
+  std::vector<std::string> keys, values;
+  keys.reserve(num_tombstones);
+  values.reserve(num_tombstones);
+  for (unfragmented_tombstones->SeekToFirst(); unfragmented_tombstones->Valid();
+       unfragmented_tombstones->Next()) {
+    keys.emplace_back(unfragmented_tombstones->key().data(),
+                      unfragmented_tombstones->key().size());
+    values.emplace_back(unfragmented_tombstones->value().data(),
+                        unfragmented_tombstones->value().size());
+  }
+  // VectorIterator implicitly sorts by key during construction.
+  auto iter = std::unique_ptr<VectorIterator>(
+      new VectorIterator(std::move(keys), std::move(values), &icmp));
+  FragmentTombstones(std::move(iter), icmp, for_compaction, snapshots);
+}
+
+void FragmentedRangeTombstoneList::FragmentTombstones(
+    std::unique_ptr<InternalIterator> unfragmented_tombstones,
+    const InternalKeyComparator& icmp, bool for_compaction,
+    const std::vector<SequenceNumber>& snapshots) {
+  Slice cur_start_key(nullptr, 0);
+  auto cmp = ParsedInternalKeyComparator(&icmp);
+
+  // Stores the end keys and sequence numbers of range tombstones with a start
+  // key less than or equal to cur_start_key. Provides an ordering by end key
+  // for use in flush_current_tombstones.
+  std::set<ParsedInternalKey, ParsedInternalKeyComparator> cur_end_keys(cmp);
+
+  // Given the next start key in unfragmented_tombstones,
+  // flush_current_tombstones writes every tombstone fragment that starts
+  // and ends with a key before next_start_key, and starts with a key greater
+  // than or equal to cur_start_key.
+  auto flush_current_tombstones = [&](const Slice& next_start_key) {
+    auto it = cur_end_keys.begin();
+    bool reached_next_start_key = false;
+    for (; it != cur_end_keys.end() && !reached_next_start_key; ++it) {
+      Slice cur_end_key = it->user_key;
+      if (icmp.user_comparator()->Compare(cur_start_key, cur_end_key) == 0) {
+        // Empty tombstone.
+        continue;
+      }
+      if (icmp.user_comparator()->Compare(next_start_key, cur_end_key) <= 0) {
+        // All of the end keys in [it, cur_end_keys.end()) are after
+        // next_start_key, so the tombstones they represent can be used in
+        // fragments that start with keys greater than or equal to
+        // next_start_key. However, the end keys we already passed will not be
+        // used in any more tombstone fragments.
+        //
+        // Remove the fully fragmented tombstones and stop iteration after a
+        // final round of flushing to preserve the tombstones we can create more
+        // fragments from.
+        reached_next_start_key = true;
+        cur_end_keys.erase(cur_end_keys.begin(), it);
+        cur_end_key = next_start_key;
+      }
+
+      // Flush a range tombstone fragment [cur_start_key, cur_end_key), which
+      // should not overlap with the last-flushed tombstone fragment.
+      assert(tombstones_.empty() ||
+             icmp.user_comparator()->Compare(tombstones_.back().end_key,
+                                             cur_start_key) <= 0);
+
+      // Sort the sequence numbers of the tombstones being fragmented in
+      // descending order, and then flush them in that order.
+      autovector<SequenceNumber> seqnums_to_flush;
+      for (auto flush_it = it; flush_it != cur_end_keys.end(); ++flush_it) {
+        seqnums_to_flush.push_back(flush_it->sequence);
+      }
+      std::sort(seqnums_to_flush.begin(), seqnums_to_flush.end(),
+                std::greater<SequenceNumber>());
+
+      size_t start_idx = tombstone_seqs_.size();
+      size_t end_idx = start_idx + seqnums_to_flush.size();
+
+      if (for_compaction) {
+        // Drop all tombstone seqnums that are not preserved by a snapshot.
+        SequenceNumber next_snapshot = kMaxSequenceNumber;
+        for (auto seq : seqnums_to_flush) {
+          if (seq <= next_snapshot) {
+            // This seqnum is visible by a lower snapshot.
+            tombstone_seqs_.push_back(seq);
+            seq_set_.insert(seq);
+            auto upper_bound_it =
+                std::lower_bound(snapshots.begin(), snapshots.end(), seq);
+            if (upper_bound_it == snapshots.begin()) {
+              // This seqnum is the topmost one visible by the earliest
+              // snapshot. None of the seqnums below it will be visible, so we
+              // can skip them.
+              break;
+            }
+            next_snapshot = *std::prev(upper_bound_it);
+          }
+        }
+        end_idx = tombstone_seqs_.size();
+      } else {
+        // The fragmentation is being done for reads, so preserve all seqnums.
+        tombstone_seqs_.insert(tombstone_seqs_.end(), seqnums_to_flush.begin(),
+                               seqnums_to_flush.end());
+        seq_set_.insert(seqnums_to_flush.begin(), seqnums_to_flush.end());
+      }
+
+      assert(start_idx < end_idx);
+      tombstones_.emplace_back(cur_start_key, cur_end_key, start_idx, end_idx);
+
+      cur_start_key = cur_end_key;
+    }
+    if (!reached_next_start_key) {
+      // There is a gap between the last flushed tombstone fragment and
+      // the next tombstone's start key. Remove all the end keys in
+      // the working set, since we have fully fragmented their corresponding
+      // tombstones.
+      cur_end_keys.clear();
+    }
+    cur_start_key = next_start_key;
+  };
+
+  pinned_iters_mgr_.StartPinning();
+
+  bool no_tombstones = true;
+  for (unfragmented_tombstones->SeekToFirst(); unfragmented_tombstones->Valid();
+       unfragmented_tombstones->Next()) {
+    const Slice& ikey = unfragmented_tombstones->key();
+    Slice tombstone_start_key = ExtractUserKey(ikey);
+    SequenceNumber tombstone_seq = GetInternalKeySeqno(ikey);
+    if (!unfragmented_tombstones->IsKeyPinned()) {
+      pinned_slices_.emplace_back(tombstone_start_key.data(),
+                                  tombstone_start_key.size());
+      tombstone_start_key = pinned_slices_.back();
+    }
+    no_tombstones = false;
+
+    Slice tombstone_end_key = unfragmented_tombstones->value();
+    if (!unfragmented_tombstones->IsValuePinned()) {
+      pinned_slices_.emplace_back(tombstone_end_key.data(),
+                                  tombstone_end_key.size());
+      tombstone_end_key = pinned_slices_.back();
+    }
+    if (!cur_end_keys.empty() && icmp.user_comparator()->Compare(
+                                     cur_start_key, tombstone_start_key) != 0) {
+      // The start key has changed. Flush all tombstones that start before
+      // this new start key.
+      flush_current_tombstones(tombstone_start_key);
+    }
+    cur_start_key = tombstone_start_key;
+
+    cur_end_keys.emplace(tombstone_end_key, tombstone_seq, kTypeRangeDeletion);
+  }
+  if (!cur_end_keys.empty()) {
+    ParsedInternalKey last_end_key = *std::prev(cur_end_keys.end());
+    flush_current_tombstones(last_end_key.user_key);
+  }
+
+  if (!no_tombstones) {
+    pinned_iters_mgr_.PinIterator(unfragmented_tombstones.release(),
+                                  false /* arena */);
+  }
+}
+
+bool FragmentedRangeTombstoneList::ContainsRange(SequenceNumber lower,
+                                                 SequenceNumber upper) const {
+  auto seq_it = seq_set_.lower_bound(lower);
+  return seq_it != seq_set_.end() && *seq_it <= upper;
+}
+
+FragmentedRangeTombstoneIterator::FragmentedRangeTombstoneIterator(
+    const FragmentedRangeTombstoneList* tombstones,
+    const InternalKeyComparator& icmp, SequenceNumber _upper_bound,
+    SequenceNumber _lower_bound)
+    : tombstone_start_cmp_(icmp.user_comparator()),
+      tombstone_end_cmp_(icmp.user_comparator()),
+      icmp_(&icmp),
+      ucmp_(icmp.user_comparator()),
+      tombstones_(tombstones),
+      upper_bound_(_upper_bound),
+      lower_bound_(_lower_bound) {
+  assert(tombstones_ != nullptr);
+  Invalidate();
+}
+
+FragmentedRangeTombstoneIterator::FragmentedRangeTombstoneIterator(
+    const std::shared_ptr<const FragmentedRangeTombstoneList>& tombstones,
+    const InternalKeyComparator& icmp, SequenceNumber _upper_bound,
+    SequenceNumber _lower_bound)
+    : tombstone_start_cmp_(icmp.user_comparator()),
+      tombstone_end_cmp_(icmp.user_comparator()),
+      icmp_(&icmp),
+      ucmp_(icmp.user_comparator()),
+      tombstones_ref_(tombstones),
+      tombstones_(tombstones_ref_.get()),
+      upper_bound_(_upper_bound),
+      lower_bound_(_lower_bound) {
+  assert(tombstones_ != nullptr);
+  Invalidate();
+}
+
+void FragmentedRangeTombstoneIterator::SeekToFirst() {
+  pos_ = tombstones_->begin();
+  seq_pos_ = tombstones_->seq_begin();
+}
+
+void FragmentedRangeTombstoneIterator::SeekToTopFirst() {
+  if (tombstones_->empty()) {
+    Invalidate();
+    return;
+  }
+  pos_ = tombstones_->begin();
+  seq_pos_ = std::lower_bound(tombstones_->seq_iter(pos_->seq_start_idx),
+                              tombstones_->seq_iter(pos_->seq_end_idx),
+                              upper_bound_, std::greater<SequenceNumber>());
+  ScanForwardToVisibleTombstone();
+}
+
+void FragmentedRangeTombstoneIterator::SeekToLast() {
+  pos_ = std::prev(tombstones_->end());
+  seq_pos_ = std::prev(tombstones_->seq_end());
+}
+
+void FragmentedRangeTombstoneIterator::SeekToTopLast() {
+  if (tombstones_->empty()) {
+    Invalidate();
+    return;
+  }
+  pos_ = std::prev(tombstones_->end());
+  seq_pos_ = std::lower_bound(tombstones_->seq_iter(pos_->seq_start_idx),
+                              tombstones_->seq_iter(pos_->seq_end_idx),
+                              upper_bound_, std::greater<SequenceNumber>());
+  ScanBackwardToVisibleTombstone();
+}
+
+void FragmentedRangeTombstoneIterator::Seek(const Slice& target) {
+  if (tombstones_->empty()) {
+    Invalidate();
+    return;
+  }
+  SeekToCoveringTombstone(target);
+  ScanForwardToVisibleTombstone();
+}
+
+void FragmentedRangeTombstoneIterator::SeekForPrev(const Slice& target) {
+  if (tombstones_->empty()) {
+    Invalidate();
+    return;
+  }
+  SeekForPrevToCoveringTombstone(target);
+  ScanBackwardToVisibleTombstone();
+}
+
+void FragmentedRangeTombstoneIterator::SeekToCoveringTombstone(
+    const Slice& target) {
+  pos_ = std::upper_bound(tombstones_->begin(), tombstones_->end(), target,
+                          tombstone_end_cmp_);
+  if (pos_ == tombstones_->end()) {
+    // All tombstones end before target.
+    seq_pos_ = tombstones_->seq_end();
+    return;
+  }
+  seq_pos_ = std::lower_bound(tombstones_->seq_iter(pos_->seq_start_idx),
+                              tombstones_->seq_iter(pos_->seq_end_idx),
+                              upper_bound_, std::greater<SequenceNumber>());
+}
+
+void FragmentedRangeTombstoneIterator::SeekForPrevToCoveringTombstone(
+    const Slice& target) {
+  if (tombstones_->empty()) {
+    Invalidate();
+    return;
+  }
+  pos_ = std::upper_bound(tombstones_->begin(), tombstones_->end(), target,
+                          tombstone_start_cmp_);
+  if (pos_ == tombstones_->begin()) {
+    // All tombstones start after target.
+    Invalidate();
+    return;
+  }
+  --pos_;
+  seq_pos_ = std::lower_bound(tombstones_->seq_iter(pos_->seq_start_idx),
+                              tombstones_->seq_iter(pos_->seq_end_idx),
+                              upper_bound_, std::greater<SequenceNumber>());
+}
+
+void FragmentedRangeTombstoneIterator::ScanForwardToVisibleTombstone() {
+  while (pos_ != tombstones_->end() &&
+         (seq_pos_ == tombstones_->seq_iter(pos_->seq_end_idx) ||
+          *seq_pos_ < lower_bound_)) {
+    ++pos_;
+    if (pos_ == tombstones_->end()) {
+      Invalidate();
+      return;
+    }
+    seq_pos_ = std::lower_bound(tombstones_->seq_iter(pos_->seq_start_idx),
+                                tombstones_->seq_iter(pos_->seq_end_idx),
+                                upper_bound_, std::greater<SequenceNumber>());
+  }
+}
+
+void FragmentedRangeTombstoneIterator::ScanBackwardToVisibleTombstone() {
+  while (pos_ != tombstones_->end() &&
+         (seq_pos_ == tombstones_->seq_iter(pos_->seq_end_idx) ||
+          *seq_pos_ < lower_bound_)) {
+    if (pos_ == tombstones_->begin()) {
+      Invalidate();
+      return;
+    }
+    --pos_;
+    seq_pos_ = std::lower_bound(tombstones_->seq_iter(pos_->seq_start_idx),
+                                tombstones_->seq_iter(pos_->seq_end_idx),
+                                upper_bound_, std::greater<SequenceNumber>());
+  }
+}
+
+void FragmentedRangeTombstoneIterator::Next() {
+  ++seq_pos_;
+  if (seq_pos_ == tombstones_->seq_iter(pos_->seq_end_idx)) {
+    ++pos_;
+  }
+}
+
+void FragmentedRangeTombstoneIterator::TopNext() {
+  ++pos_;
+  if (pos_ == tombstones_->end()) {
+    return;
+  }
+  seq_pos_ = std::lower_bound(tombstones_->seq_iter(pos_->seq_start_idx),
+                              tombstones_->seq_iter(pos_->seq_end_idx),
+                              upper_bound_, std::greater<SequenceNumber>());
+  ScanForwardToVisibleTombstone();
+}
+
+void FragmentedRangeTombstoneIterator::Prev() {
+  if (seq_pos_ == tombstones_->seq_begin()) {
+    Invalidate();
+    return;
+  }
+  --seq_pos_;
+  if (pos_ == tombstones_->end() ||
+      seq_pos_ == tombstones_->seq_iter(pos_->seq_start_idx - 1)) {
+    --pos_;
+  }
+}
+
+void FragmentedRangeTombstoneIterator::TopPrev() {
+  if (pos_ == tombstones_->begin()) {
+    Invalidate();
+    return;
+  }
+  --pos_;
+  seq_pos_ = std::lower_bound(tombstones_->seq_iter(pos_->seq_start_idx),
+                              tombstones_->seq_iter(pos_->seq_end_idx),
+                              upper_bound_, std::greater<SequenceNumber>());
+  ScanBackwardToVisibleTombstone();
+}
+
+bool FragmentedRangeTombstoneIterator::Valid() const {
+  return tombstones_ != nullptr && pos_ != tombstones_->end();
+}
+
+SequenceNumber FragmentedRangeTombstoneIterator::MaxCoveringTombstoneSeqnum(
+    const Slice& user_key) {
+  SeekToCoveringTombstone(user_key);
+  return ValidPos() && ucmp_->Compare(start_key(), user_key) <= 0 ? seq() : 0;
+}
+
+std::map<SequenceNumber, std::unique_ptr<FragmentedRangeTombstoneIterator>>
+FragmentedRangeTombstoneIterator::SplitBySnapshot(
+    const std::vector<SequenceNumber>& snapshots) {
+  std::map<SequenceNumber, std::unique_ptr<FragmentedRangeTombstoneIterator>>
+      splits;
+  SequenceNumber lower = 0;
+  SequenceNumber upper;
+  for (size_t i = 0; i <= snapshots.size(); i++) {
+    if (i >= snapshots.size()) {
+      upper = kMaxSequenceNumber;
+    } else {
+      upper = snapshots[i];
+    }
+    if (tombstones_->ContainsRange(lower, upper)) {
+      splits.emplace(upper, std::unique_ptr<FragmentedRangeTombstoneIterator>(
+                                new FragmentedRangeTombstoneIterator(
+                                    tombstones_, *icmp_, upper, lower)));
+    }
+    lower = upper + 1;
+  }
+  return splits;
+}
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.18.X/db/range_tombstone_fragmenter.h b/3rdParty/rocksdb/v5.18.X/db/range_tombstone_fragmenter.h
new file mode 100644
index 0000000000..a0b77b6777
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/range_tombstone_fragmenter.h
@@ -0,0 +1,254 @@
+//  Copyright (c) 2018-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include <list>
+#include <memory>
+#include <set>
+#include <string>
+#include <vector>
+
+#include "db/dbformat.h"
+#include "db/pinned_iterators_manager.h"
+#include "rocksdb/status.h"
+#include "table/internal_iterator.h"
+
+namespace rocksdb {
+
+struct FragmentedRangeTombstoneList {
+ public:
+  // A compact representation of a "stack" of range tombstone fragments, which
+  // start and end at the same user keys but have different sequence numbers.
+  // The members seq_start_idx and seq_end_idx are intended to be parameters to
+  // seq_iter().
+  struct RangeTombstoneStack {
+    RangeTombstoneStack(const Slice& start, const Slice& end, size_t start_idx,
+                        size_t end_idx)
+        : start_key(start),
+          end_key(end),
+          seq_start_idx(start_idx),
+          seq_end_idx(end_idx) {}
+
+    Slice start_key;
+    Slice end_key;
+    size_t seq_start_idx;
+    size_t seq_end_idx;
+  };
+  FragmentedRangeTombstoneList(
+      std::unique_ptr<InternalIterator> unfragmented_tombstones,
+      const InternalKeyComparator& icmp, bool for_compaction = false,
+      const std::vector<SequenceNumber>& snapshots = {});
+
+  std::vector<RangeTombstoneStack>::const_iterator begin() const {
+    return tombstones_.begin();
+  }
+
+  std::vector<RangeTombstoneStack>::const_iterator end() const {
+    return tombstones_.end();
+  }
+
+  std::vector<SequenceNumber>::const_iterator seq_iter(size_t idx) const {
+    return std::next(tombstone_seqs_.begin(), idx);
+  }
+
+  std::vector<SequenceNumber>::const_iterator seq_begin() const {
+    return tombstone_seqs_.begin();
+  }
+
+  std::vector<SequenceNumber>::const_iterator seq_end() const {
+    return tombstone_seqs_.end();
+  }
+
+  bool empty() const { return tombstones_.empty(); }
+
+  // Returns true if the stored tombstones contain with one with a sequence
+  // number in [lower, upper].
+  bool ContainsRange(SequenceNumber lower, SequenceNumber upper) const;
+
+ private:
+  // Given an ordered range tombstone iterator unfragmented_tombstones,
+  // "fragment" the tombstones into non-overlapping pieces, and store them in
+  // tombstones_ and tombstone_seqs_.
+  void FragmentTombstones(
+      std::unique_ptr<InternalIterator> unfragmented_tombstones,
+      const InternalKeyComparator& icmp, bool for_compaction,
+      const std::vector<SequenceNumber>& snapshots);
+
+  std::vector<RangeTombstoneStack> tombstones_;
+  std::vector<SequenceNumber> tombstone_seqs_;
+  std::set<SequenceNumber> seq_set_;
+  std::list<std::string> pinned_slices_;
+  PinnedIteratorsManager pinned_iters_mgr_;
+};
+
+// FragmentedRangeTombstoneIterator converts an InternalIterator of a range-del
+// meta block into an iterator over non-overlapping tombstone fragments. The
+// tombstone fragmentation process should be more efficient than the range
+// tombstone collapsing algorithm in RangeDelAggregator because this leverages
+// the internal key ordering already provided by the input iterator, if
+// applicable (when the iterator is unsorted, a new sorted iterator is created
+// before proceeding). If there are few overlaps, creating a
+// FragmentedRangeTombstoneIterator should be O(n), while the RangeDelAggregator
+// tombstone collapsing is always O(n log n).
+class FragmentedRangeTombstoneIterator : public InternalIterator {
+ public:
+  FragmentedRangeTombstoneIterator(
+      const FragmentedRangeTombstoneList* tombstones,
+      const InternalKeyComparator& icmp, SequenceNumber upper_bound,
+      SequenceNumber lower_bound = 0);
+  FragmentedRangeTombstoneIterator(
+      const std::shared_ptr<const FragmentedRangeTombstoneList>& tombstones,
+      const InternalKeyComparator& icmp, SequenceNumber upper_bound,
+      SequenceNumber lower_bound = 0);
+
+  void SeekToFirst() override;
+  void SeekToLast() override;
+
+  void SeekToTopFirst();
+  void SeekToTopLast();
+
+  // NOTE: Seek and SeekForPrev do not behave in the way InternalIterator
+  // seeking should behave. This is OK because they are not currently used, but
+  // eventually FragmentedRangeTombstoneIterator should no longer implement
+  // InternalIterator.
+  //
+  // Seeks to the range tombstone that covers target at a seqnum in the
+  // snapshot. If no such tombstone exists, seek to the earliest tombstone in
+  // the snapshot that ends after target.
+  void Seek(const Slice& target) override;
+  // Seeks to the range tombstone that covers target at a seqnum in the
+  // snapshot. If no such tombstone exists, seek to the latest tombstone in the
+  // snapshot that starts before target.
+  void SeekForPrev(const Slice& target) override;
+
+  void Next() override;
+  void Prev() override;
+
+  void TopNext();
+  void TopPrev();
+
+  bool Valid() const override;
+  Slice key() const override {
+    MaybePinKey();
+    return current_start_key_.Encode();
+  }
+  Slice value() const override { return pos_->end_key; }
+  bool IsKeyPinned() const override { return false; }
+  bool IsValuePinned() const override { return true; }
+  Status status() const override { return Status::OK(); }
+
+  bool empty() const { return tombstones_->empty(); }
+  void Invalidate() {
+    pos_ = tombstones_->end();
+    seq_pos_ = tombstones_->seq_end();
+  }
+
+  RangeTombstone Tombstone() const {
+    return RangeTombstone(start_key(), end_key(), seq());
+  }
+  Slice start_key() const { return pos_->start_key; }
+  Slice end_key() const { return pos_->end_key; }
+  SequenceNumber seq() const { return *seq_pos_; }
+  ParsedInternalKey parsed_start_key() const {
+    return ParsedInternalKey(pos_->start_key, kMaxSequenceNumber,
+                             kTypeRangeDeletion);
+  }
+  ParsedInternalKey parsed_end_key() const {
+    return ParsedInternalKey(pos_->end_key, kMaxSequenceNumber,
+                             kTypeRangeDeletion);
+  }
+
+  SequenceNumber MaxCoveringTombstoneSeqnum(const Slice& user_key);
+
+  // Splits the iterator into n+1 iterators (where n is the number of
+  // snapshots), each providing a view over a "stripe" of sequence numbers. The
+  // iterators are keyed by the upper bound of their ranges (the provided
+  // snapshots + kMaxSequenceNumber).
+  //
+  // NOTE: the iterators in the returned map are no longer valid if their
+  // parent iterator is deleted, since they do not modify the refcount of the
+  // underlying tombstone list. Therefore, this map should be deleted before
+  // the parent iterator.
+  std::map<SequenceNumber, std::unique_ptr<FragmentedRangeTombstoneIterator>>
+  SplitBySnapshot(const std::vector<SequenceNumber>& snapshots);
+
+  SequenceNumber upper_bound() const { return upper_bound_; }
+  SequenceNumber lower_bound() const { return lower_bound_; }
+
+ private:
+  using RangeTombstoneStack = FragmentedRangeTombstoneList::RangeTombstoneStack;
+
+  struct RangeTombstoneStackStartComparator {
+    explicit RangeTombstoneStackStartComparator(const Comparator* c) : cmp(c) {}
+
+    bool operator()(const RangeTombstoneStack& a,
+                    const RangeTombstoneStack& b) const {
+      return cmp->Compare(a.start_key, b.start_key) < 0;
+    }
+
+    bool operator()(const RangeTombstoneStack& a, const Slice& b) const {
+      return cmp->Compare(a.start_key, b) < 0;
+    }
+
+    bool operator()(const Slice& a, const RangeTombstoneStack& b) const {
+      return cmp->Compare(a, b.start_key) < 0;
+    }
+
+    const Comparator* cmp;
+  };
+
+  struct RangeTombstoneStackEndComparator {
+    explicit RangeTombstoneStackEndComparator(const Comparator* c) : cmp(c) {}
+
+    bool operator()(const RangeTombstoneStack& a,
+                    const RangeTombstoneStack& b) const {
+      return cmp->Compare(a.end_key, b.end_key) < 0;
+    }
+
+    bool operator()(const RangeTombstoneStack& a, const Slice& b) const {
+      return cmp->Compare(a.end_key, b) < 0;
+    }
+
+    bool operator()(const Slice& a, const RangeTombstoneStack& b) const {
+      return cmp->Compare(a, b.end_key) < 0;
+    }
+
+    const Comparator* cmp;
+  };
+
+  void MaybePinKey() const {
+    if (pos_ != tombstones_->end() && seq_pos_ != tombstones_->seq_end() &&
+        (pinned_pos_ != pos_ || pinned_seq_pos_ != seq_pos_)) {
+      current_start_key_.Set(pos_->start_key, *seq_pos_, kTypeRangeDeletion);
+      pinned_pos_ = pos_;
+      pinned_seq_pos_ = seq_pos_;
+    }
+  }
+
+  void SeekToCoveringTombstone(const Slice& key);
+  void SeekForPrevToCoveringTombstone(const Slice& key);
+  void ScanForwardToVisibleTombstone();
+  void ScanBackwardToVisibleTombstone();
+  bool ValidPos() const {
+    return Valid() && seq_pos_ != tombstones_->seq_iter(pos_->seq_end_idx);
+  }
+
+  const RangeTombstoneStackStartComparator tombstone_start_cmp_;
+  const RangeTombstoneStackEndComparator tombstone_end_cmp_;
+  const InternalKeyComparator* icmp_;
+  const Comparator* ucmp_;
+  std::shared_ptr<const FragmentedRangeTombstoneList> tombstones_ref_;
+  const FragmentedRangeTombstoneList* tombstones_;
+  SequenceNumber upper_bound_;
+  SequenceNumber lower_bound_;
+  std::vector<RangeTombstoneStack>::const_iterator pos_;
+  std::vector<SequenceNumber>::const_iterator seq_pos_;
+  mutable std::vector<RangeTombstoneStack>::const_iterator pinned_pos_;
+  mutable std::vector<SequenceNumber>::const_iterator pinned_seq_pos_;
+  mutable InternalKey current_start_key_;
+};
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.18.X/db/range_tombstone_fragmenter_test.cc b/3rdParty/rocksdb/v5.18.X/db/range_tombstone_fragmenter_test.cc
new file mode 100644
index 0000000000..ddd3f77417
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/db/range_tombstone_fragmenter_test.cc
@@ -0,0 +1,552 @@
+//  Copyright (c) 2018-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "db/range_tombstone_fragmenter.h"
+
+#include "db/db_test_util.h"
+#include "rocksdb/comparator.h"
+#include "util/testutil.h"
+
+namespace rocksdb {
+
+class RangeTombstoneFragmenterTest : public testing::Test {};
+
+namespace {
+
+static auto bytewise_icmp = InternalKeyComparator(BytewiseComparator());
+
+std::unique_ptr<InternalIterator> MakeRangeDelIter(
+    const std::vector<RangeTombstone>& range_dels) {
+  std::vector<std::string> keys, values;
+  for (const auto& range_del : range_dels) {
+    auto key_and_value = range_del.Serialize();
+    keys.push_back(key_and_value.first.Encode().ToString());
+    values.push_back(key_and_value.second.ToString());
+  }
+  return std::unique_ptr<test::VectorIterator>(
+      new test::VectorIterator(keys, values));
+}
+
+void CheckIterPosition(const RangeTombstone& tombstone,
+                       const FragmentedRangeTombstoneIterator* iter) {
+  // Test InternalIterator interface.
+  EXPECT_EQ(tombstone.start_key_, ExtractUserKey(iter->key()));
+  EXPECT_EQ(tombstone.end_key_, iter->value());
+  EXPECT_EQ(tombstone.seq_, iter->seq());
+
+  // Test FragmentedRangeTombstoneIterator interface.
+  EXPECT_EQ(tombstone.start_key_, iter->start_key());
+  EXPECT_EQ(tombstone.end_key_, iter->end_key());
+  EXPECT_EQ(tombstone.seq_, GetInternalKeySeqno(iter->key()));
+}
+
+void VerifyFragmentedRangeDels(
+    FragmentedRangeTombstoneIterator* iter,
+    const std::vector<RangeTombstone>& expected_tombstones) {
+  iter->SeekToFirst();
+  for (size_t i = 0; i < expected_tombstones.size(); i++, iter->Next()) {
+    ASSERT_TRUE(iter->Valid());
+    CheckIterPosition(expected_tombstones[i], iter);
+  }
+  EXPECT_FALSE(iter->Valid());
+}
+
+void VerifyVisibleTombstones(
+    FragmentedRangeTombstoneIterator* iter,
+    const std::vector<RangeTombstone>& expected_tombstones) {
+  iter->SeekToTopFirst();
+  for (size_t i = 0; i < expected_tombstones.size(); i++, iter->TopNext()) {
+    ASSERT_TRUE(iter->Valid());
+    CheckIterPosition(expected_tombstones[i], iter);
+  }
+  EXPECT_FALSE(iter->Valid());
+}
+
+struct SeekTestCase {
+  Slice seek_target;
+  RangeTombstone expected_position;
+  bool out_of_range;
+};
+
+void VerifySeek(FragmentedRangeTombstoneIterator* iter,
+                const std::vector<SeekTestCase>& cases) {
+  for (const auto& testcase : cases) {
+    iter->Seek(testcase.seek_target);
+    if (testcase.out_of_range) {
+      ASSERT_FALSE(iter->Valid());
+    } else {
+      ASSERT_TRUE(iter->Valid());
+      CheckIterPosition(testcase.expected_position, iter);
+    }
+  }
+}
+
+void VerifySeekForPrev(FragmentedRangeTombstoneIterator* iter,
+                       const std::vector<SeekTestCase>& cases) {
+  for (const auto& testcase : cases) {
+    iter->SeekForPrev(testcase.seek_target);
+    if (testcase.out_of_range) {
+      ASSERT_FALSE(iter->Valid());
+    } else {
+      ASSERT_TRUE(iter->Valid());
+      CheckIterPosition(testcase.expected_position, iter);
+    }
+  }
+}
+
+struct MaxCoveringTombstoneSeqnumTestCase {
+  Slice user_key;
+  SequenceNumber result;
+};
+
+void VerifyMaxCoveringTombstoneSeqnum(
+    FragmentedRangeTombstoneIterator* iter,
+    const std::vector<MaxCoveringTombstoneSeqnumTestCase>& cases) {
+  for (const auto& testcase : cases) {
+    EXPECT_EQ(testcase.result,
+              iter->MaxCoveringTombstoneSeqnum(testcase.user_key));
+  }
+}
+
+}  // anonymous namespace
+
+TEST_F(RangeTombstoneFragmenterTest, NonOverlappingTombstones) {
+  auto range_del_iter = MakeRangeDelIter({{"a", "b", 10}, {"c", "d", 5}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber);
+  ASSERT_EQ(0, iter.lower_bound());
+  ASSERT_EQ(kMaxSequenceNumber, iter.upper_bound());
+  VerifyFragmentedRangeDels(&iter, {{"a", "b", 10}, {"c", "d", 5}});
+  VerifyMaxCoveringTombstoneSeqnum(&iter,
+                                   {{"", 0}, {"a", 10}, {"b", 0}, {"c", 5}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, OverlappingTombstones) {
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10}, {"c", "g", 15}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber);
+  ASSERT_EQ(0, iter.lower_bound());
+  ASSERT_EQ(kMaxSequenceNumber, iter.upper_bound());
+  VerifyFragmentedRangeDels(
+      &iter, {{"a", "c", 10}, {"c", "e", 15}, {"c", "e", 10}, {"e", "g", 15}});
+  VerifyMaxCoveringTombstoneSeqnum(&iter,
+                                   {{"a", 10}, {"c", 15}, {"e", 15}, {"g", 0}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, ContiguousTombstones) {
+  auto range_del_iter = MakeRangeDelIter(
+      {{"a", "c", 10}, {"c", "e", 20}, {"c", "e", 5}, {"e", "g", 15}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber);
+  ASSERT_EQ(0, iter.lower_bound());
+  ASSERT_EQ(kMaxSequenceNumber, iter.upper_bound());
+  VerifyFragmentedRangeDels(
+      &iter, {{"a", "c", 10}, {"c", "e", 20}, {"c", "e", 5}, {"e", "g", 15}});
+  VerifyMaxCoveringTombstoneSeqnum(&iter,
+                                   {{"a", 10}, {"c", 20}, {"e", 15}, {"g", 0}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, RepeatedStartAndEndKey) {
+  auto range_del_iter =
+      MakeRangeDelIter({{"a", "c", 10}, {"a", "c", 7}, {"a", "c", 3}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber);
+  ASSERT_EQ(0, iter.lower_bound());
+  ASSERT_EQ(kMaxSequenceNumber, iter.upper_bound());
+  VerifyFragmentedRangeDels(&iter,
+                            {{"a", "c", 10}, {"a", "c", 7}, {"a", "c", 3}});
+  VerifyMaxCoveringTombstoneSeqnum(&iter, {{"a", 10}, {"b", 10}, {"c", 0}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, RepeatedStartKeyDifferentEndKeys) {
+  auto range_del_iter =
+      MakeRangeDelIter({{"a", "e", 10}, {"a", "g", 7}, {"a", "c", 3}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber);
+  ASSERT_EQ(0, iter.lower_bound());
+  ASSERT_EQ(kMaxSequenceNumber, iter.upper_bound());
+  VerifyFragmentedRangeDels(&iter, {{"a", "c", 10},
+                                    {"a", "c", 7},
+                                    {"a", "c", 3},
+                                    {"c", "e", 10},
+                                    {"c", "e", 7},
+                                    {"e", "g", 7}});
+  VerifyMaxCoveringTombstoneSeqnum(&iter,
+                                   {{"a", 10}, {"c", 10}, {"e", 7}, {"g", 0}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, RepeatedStartKeyMixedEndKeys) {
+  auto range_del_iter = MakeRangeDelIter({{"a", "c", 30},
+                                          {"a", "g", 20},
+                                          {"a", "e", 10},
+                                          {"a", "g", 7},
+                                          {"a", "c", 3}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber);
+  ASSERT_EQ(0, iter.lower_bound());
+  ASSERT_EQ(kMaxSequenceNumber, iter.upper_bound());
+  VerifyFragmentedRangeDels(&iter, {{"a", "c", 30},
+                                    {"a", "c", 20},
+                                    {"a", "c", 10},
+                                    {"a", "c", 7},
+                                    {"a", "c", 3},
+                                    {"c", "e", 20},
+                                    {"c", "e", 10},
+                                    {"c", "e", 7},
+                                    {"e", "g", 20},
+                                    {"e", "g", 7}});
+  VerifyMaxCoveringTombstoneSeqnum(&iter,
+                                   {{"a", 30}, {"c", 20}, {"e", 20}, {"g", 0}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, OverlapAndRepeatedStartKey) {
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10},
+                                          {"c", "g", 8},
+                                          {"c", "i", 6},
+                                          {"j", "n", 4},
+                                          {"j", "l", 2}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  FragmentedRangeTombstoneIterator iter1(&fragment_list, bytewise_icmp,
+                                         kMaxSequenceNumber);
+  FragmentedRangeTombstoneIterator iter2(&fragment_list, bytewise_icmp,
+                                         9 /* upper_bound */);
+  FragmentedRangeTombstoneIterator iter3(&fragment_list, bytewise_icmp,
+                                         7 /* upper_bound */);
+  FragmentedRangeTombstoneIterator iter4(&fragment_list, bytewise_icmp,
+                                         5 /* upper_bound */);
+  FragmentedRangeTombstoneIterator iter5(&fragment_list, bytewise_icmp,
+                                         3 /* upper_bound */);
+  for (auto* iter : {&iter1, &iter2, &iter3, &iter4, &iter5}) {
+    VerifyFragmentedRangeDels(iter, {{"a", "c", 10},
+                                     {"c", "e", 10},
+                                     {"c", "e", 8},
+                                     {"c", "e", 6},
+                                     {"e", "g", 8},
+                                     {"e", "g", 6},
+                                     {"g", "i", 6},
+                                     {"j", "l", 4},
+                                     {"j", "l", 2},
+                                     {"l", "n", 4}});
+  }
+
+  ASSERT_EQ(0, iter1.lower_bound());
+  ASSERT_EQ(kMaxSequenceNumber, iter1.upper_bound());
+  VerifyVisibleTombstones(&iter1, {{"a", "c", 10},
+                                   {"c", "e", 10},
+                                   {"e", "g", 8},
+                                   {"g", "i", 6},
+                                   {"j", "l", 4},
+                                   {"l", "n", 4}});
+  VerifyMaxCoveringTombstoneSeqnum(
+      &iter1, {{"a", 10}, {"c", 10}, {"e", 8}, {"i", 0}, {"j", 4}, {"m", 4}});
+
+  ASSERT_EQ(0, iter2.lower_bound());
+  ASSERT_EQ(9, iter2.upper_bound());
+  VerifyVisibleTombstones(&iter2, {{"c", "e", 8},
+                                   {"e", "g", 8},
+                                   {"g", "i", 6},
+                                   {"j", "l", 4},
+                                   {"l", "n", 4}});
+  VerifyMaxCoveringTombstoneSeqnum(
+      &iter2, {{"a", 0}, {"c", 8}, {"e", 8}, {"i", 0}, {"j", 4}, {"m", 4}});
+
+  ASSERT_EQ(0, iter3.lower_bound());
+  ASSERT_EQ(7, iter3.upper_bound());
+  VerifyVisibleTombstones(&iter3, {{"c", "e", 6},
+                                   {"e", "g", 6},
+                                   {"g", "i", 6},
+                                   {"j", "l", 4},
+                                   {"l", "n", 4}});
+  VerifyMaxCoveringTombstoneSeqnum(
+      &iter3, {{"a", 0}, {"c", 6}, {"e", 6}, {"i", 0}, {"j", 4}, {"m", 4}});
+
+  ASSERT_EQ(0, iter4.lower_bound());
+  ASSERT_EQ(5, iter4.upper_bound());
+  VerifyVisibleTombstones(&iter4, {{"j", "l", 4}, {"l", "n", 4}});
+  VerifyMaxCoveringTombstoneSeqnum(
+      &iter4, {{"a", 0}, {"c", 0}, {"e", 0}, {"i", 0}, {"j", 4}, {"m", 4}});
+
+  ASSERT_EQ(0, iter5.lower_bound());
+  ASSERT_EQ(3, iter5.upper_bound());
+  VerifyVisibleTombstones(&iter5, {{"j", "l", 2}});
+  VerifyMaxCoveringTombstoneSeqnum(
+      &iter5, {{"a", 0}, {"c", 0}, {"e", 0}, {"i", 0}, {"j", 2}, {"m", 0}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, OverlapAndRepeatedStartKeyUnordered) {
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10},
+                                          {"j", "n", 4},
+                                          {"c", "i", 6},
+                                          {"c", "g", 8},
+                                          {"j", "l", 2}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        9 /* upper_bound */);
+  ASSERT_EQ(0, iter.lower_bound());
+  ASSERT_EQ(9, iter.upper_bound());
+  VerifyFragmentedRangeDels(&iter, {{"a", "c", 10},
+                                    {"c", "e", 10},
+                                    {"c", "e", 8},
+                                    {"c", "e", 6},
+                                    {"e", "g", 8},
+                                    {"e", "g", 6},
+                                    {"g", "i", 6},
+                                    {"j", "l", 4},
+                                    {"j", "l", 2},
+                                    {"l", "n", 4}});
+  VerifyMaxCoveringTombstoneSeqnum(
+      &iter, {{"a", 0}, {"c", 8}, {"e", 8}, {"i", 0}, {"j", 4}, {"m", 4}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, OverlapAndRepeatedStartKeyForCompaction) {
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10},
+                                          {"j", "n", 4},
+                                          {"c", "i", 6},
+                                          {"c", "g", 8},
+                                          {"j", "l", 2}});
+
+  FragmentedRangeTombstoneList fragment_list(
+      std::move(range_del_iter), bytewise_icmp, true /* for_compaction */,
+      {} /* snapshots */);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber /* upper_bound */);
+  VerifyFragmentedRangeDels(&iter, {{"a", "c", 10},
+                                    {"c", "e", 10},
+                                    {"e", "g", 8},
+                                    {"g", "i", 6},
+                                    {"j", "l", 4},
+                                    {"l", "n", 4}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest,
+       OverlapAndRepeatedStartKeyForCompactionWithSnapshot) {
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10},
+                                          {"j", "n", 4},
+                                          {"c", "i", 6},
+                                          {"c", "g", 8},
+                                          {"j", "l", 2}});
+
+  FragmentedRangeTombstoneList fragment_list(
+      std::move(range_del_iter), bytewise_icmp, true /* for_compaction */,
+      {20, 9} /* upper_bounds */);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber /* upper_bound */);
+  VerifyFragmentedRangeDels(&iter, {{"a", "c", 10},
+                                    {"c", "e", 10},
+                                    {"c", "e", 8},
+                                    {"e", "g", 8},
+                                    {"g", "i", 6},
+                                    {"j", "l", 4},
+                                    {"l", "n", 4}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, IteratorSplitNoSnapshots) {
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10},
+                                          {"j", "n", 4},
+                                          {"c", "i", 6},
+                                          {"c", "g", 8},
+                                          {"j", "l", 2}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber /* upper_bound */);
+
+  auto split_iters = iter.SplitBySnapshot({} /* snapshots */);
+  ASSERT_EQ(1, split_iters.size());
+
+  auto* split_iter = split_iters[kMaxSequenceNumber].get();
+  ASSERT_EQ(0, split_iter->lower_bound());
+  ASSERT_EQ(kMaxSequenceNumber, split_iter->upper_bound());
+  VerifyVisibleTombstones(split_iter, {{"a", "c", 10},
+                                       {"c", "e", 10},
+                                       {"e", "g", 8},
+                                       {"g", "i", 6},
+                                       {"j", "l", 4},
+                                       {"l", "n", 4}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, IteratorSplitWithSnapshots) {
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10},
+                                          {"j", "n", 4},
+                                          {"c", "i", 6},
+                                          {"c", "g", 8},
+                                          {"j", "l", 2}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber /* upper_bound */);
+
+  auto split_iters = iter.SplitBySnapshot({3, 5, 7, 9} /* snapshots */);
+  ASSERT_EQ(5, split_iters.size());
+
+  auto* split_iter1 = split_iters[3].get();
+  ASSERT_EQ(0, split_iter1->lower_bound());
+  ASSERT_EQ(3, split_iter1->upper_bound());
+  VerifyVisibleTombstones(split_iter1, {{"j", "l", 2}});
+
+  auto* split_iter2 = split_iters[5].get();
+  ASSERT_EQ(4, split_iter2->lower_bound());
+  ASSERT_EQ(5, split_iter2->upper_bound());
+  VerifyVisibleTombstones(split_iter2, {{"j", "l", 4}, {"l", "n", 4}});
+
+  auto* split_iter3 = split_iters[7].get();
+  ASSERT_EQ(6, split_iter3->lower_bound());
+  ASSERT_EQ(7, split_iter3->upper_bound());
+  VerifyVisibleTombstones(split_iter3,
+                          {{"c", "e", 6}, {"e", "g", 6}, {"g", "i", 6}});
+
+  auto* split_iter4 = split_iters[9].get();
+  ASSERT_EQ(8, split_iter4->lower_bound());
+  ASSERT_EQ(9, split_iter4->upper_bound());
+  VerifyVisibleTombstones(split_iter4, {{"c", "e", 8}, {"e", "g", 8}});
+
+  auto* split_iter5 = split_iters[kMaxSequenceNumber].get();
+  ASSERT_EQ(10, split_iter5->lower_bound());
+  ASSERT_EQ(kMaxSequenceNumber, split_iter5->upper_bound());
+  VerifyVisibleTombstones(split_iter5, {{"a", "c", 10}, {"c", "e", 10}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, SeekStartKey) {
+  // Same tombstones as OverlapAndRepeatedStartKey.
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10},
+                                          {"c", "g", 8},
+                                          {"c", "i", 6},
+                                          {"j", "n", 4},
+                                          {"j", "l", 2}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+
+  FragmentedRangeTombstoneIterator iter1(&fragment_list, bytewise_icmp,
+                                         kMaxSequenceNumber);
+  VerifySeek(
+      &iter1,
+      {{"a", {"a", "c", 10}}, {"e", {"e", "g", 8}}, {"l", {"l", "n", 4}}});
+  VerifySeekForPrev(
+      &iter1,
+      {{"a", {"a", "c", 10}}, {"e", {"e", "g", 8}}, {"l", {"l", "n", 4}}});
+
+  FragmentedRangeTombstoneIterator iter2(&fragment_list, bytewise_icmp,
+                                         3 /* upper_bound */);
+  VerifySeek(&iter2, {{"a", {"j", "l", 2}},
+                      {"e", {"j", "l", 2}},
+                      {"l", {}, true /* out of range */}});
+  VerifySeekForPrev(&iter2, {{"a", {}, true /* out of range */},
+                             {"e", {}, true /* out of range */},
+                             {"l", {"j", "l", 2}}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, SeekCovered) {
+  // Same tombstones as OverlapAndRepeatedStartKey.
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10},
+                                          {"c", "g", 8},
+                                          {"c", "i", 6},
+                                          {"j", "n", 4},
+                                          {"j", "l", 2}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+
+  FragmentedRangeTombstoneIterator iter1(&fragment_list, bytewise_icmp,
+                                         kMaxSequenceNumber);
+  VerifySeek(
+      &iter1,
+      {{"b", {"a", "c", 10}}, {"f", {"e", "g", 8}}, {"m", {"l", "n", 4}}});
+  VerifySeekForPrev(
+      &iter1,
+      {{"b", {"a", "c", 10}}, {"f", {"e", "g", 8}}, {"m", {"l", "n", 4}}});
+
+  FragmentedRangeTombstoneIterator iter2(&fragment_list, bytewise_icmp,
+                                         3 /* upper_bound */);
+  VerifySeek(&iter2, {{"b", {"j", "l", 2}},
+                      {"f", {"j", "l", 2}},
+                      {"m", {}, true /* out of range */}});
+  VerifySeekForPrev(&iter2, {{"b", {}, true /* out of range */},
+                             {"f", {}, true /* out of range */},
+                             {"m", {"j", "l", 2}}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, SeekEndKey) {
+  // Same tombstones as OverlapAndRepeatedStartKey.
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10},
+                                          {"c", "g", 8},
+                                          {"c", "i", 6},
+                                          {"j", "n", 4},
+                                          {"j", "l", 2}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+
+  FragmentedRangeTombstoneIterator iter1(&fragment_list, bytewise_icmp,
+                                         kMaxSequenceNumber);
+  VerifySeek(&iter1, {{"c", {"c", "e", 10}},
+                      {"g", {"g", "i", 6}},
+                      {"i", {"j", "l", 4}},
+                      {"n", {}, true /* out of range */}});
+  VerifySeekForPrev(&iter1, {{"c", {"c", "e", 10}},
+                             {"g", {"g", "i", 6}},
+                             {"i", {"g", "i", 6}},
+                             {"n", {"l", "n", 4}}});
+
+  FragmentedRangeTombstoneIterator iter2(&fragment_list, bytewise_icmp,
+                                         3 /* upper_bound */);
+  VerifySeek(&iter2, {{"c", {"j", "l", 2}},
+                      {"g", {"j", "l", 2}},
+                      {"i", {"j", "l", 2}},
+                      {"n", {}, true /* out of range */}});
+  VerifySeekForPrev(&iter2, {{"c", {}, true /* out of range */},
+                             {"g", {}, true /* out of range */},
+                             {"i", {}, true /* out of range */},
+                             {"n", {"j", "l", 2}}});
+}
+
+TEST_F(RangeTombstoneFragmenterTest, SeekOutOfBounds) {
+  // Same tombstones as OverlapAndRepeatedStartKey.
+  auto range_del_iter = MakeRangeDelIter({{"a", "e", 10},
+                                          {"c", "g", 8},
+                                          {"c", "i", 6},
+                                          {"j", "n", 4},
+                                          {"j", "l", 2}});
+
+  FragmentedRangeTombstoneList fragment_list(std::move(range_del_iter),
+                                             bytewise_icmp);
+
+  FragmentedRangeTombstoneIterator iter(&fragment_list, bytewise_icmp,
+                                        kMaxSequenceNumber);
+  VerifySeek(&iter, {{"", {"a", "c", 10}}, {"z", {}, true /* out of range */}});
+  VerifySeekForPrev(&iter,
+                    {{"", {}, true /* out of range */}, {"z", {"l", "n", 4}}});
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
diff --git a/3rdParty/rocksdb/v5.16.X/db/read_callback.h b/3rdParty/rocksdb/v5.18.X/db/read_callback.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/read_callback.h
rename to 3rdParty/rocksdb/v5.18.X/db/read_callback.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/repair.cc b/3rdParty/rocksdb/v5.18.X/db/repair.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/db/repair.cc
rename to 3rdParty/rocksdb/v5.18.X/db/repair.cc
index 91c64734c0..4e93a161cf 100644
--- a/3rdParty/rocksdb/v5.16.X/db/repair.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/repair.cc
@@ -118,7 +118,8 @@ class Repairer {
         wc_(db_options_.delayed_write_rate),
         vset_(dbname_, &immutable_db_options_, env_options_,
               raw_table_cache_.get(), &wb_, &wc_),
-        next_file_number_(1) {
+        next_file_number_(1),
+        db_lock_(nullptr) {
     for (const auto& cfd : column_families) {
       cf_name_to_opts_[cfd.name] = cfd.options;
     }
@@ -163,11 +164,18 @@ class Repairer {
   }
 
   ~Repairer() {
+    if (db_lock_ != nullptr) {
+      env_->UnlockFile(db_lock_);
+    }
     delete table_cache_;
   }
 
   Status Run() {
-    Status status = FindFiles();
+    Status status = env_->LockFile(LockFileName(dbname_), &db_lock_);
+    if (!status.ok()) {
+      return status;
+    }
+    status = FindFiles();
     if (status.ok()) {
       // Discard older manifests and start a fresh one
       for (size_t i = 0; i < manifests_.size(); i++) {
@@ -245,6 +253,9 @@ class Repairer {
   std::vector<uint64_t> logs_;
   std::vector<TableInfo> tables_;
   uint64_t next_file_number_;
+  // Lock over the persistent DB state. Non-nullptr iff successfully
+  // acquired.
+  FileLock* db_lock_;
 
   Status FindFiles() {
     std::vector<std::string> filenames;
@@ -334,13 +345,13 @@ class Repairer {
 
     // Open the log file
     std::string logname = LogFileName(db_options_.wal_dir, log);
-    unique_ptr<SequentialFile> lfile;
+    std::unique_ptr<SequentialFile> lfile;
     Status status = env_->NewSequentialFile(
         logname, &lfile, env_->OptimizeForLogRead(env_options_));
     if (!status.ok()) {
       return status;
     }
-    unique_ptr<SequentialFileReader> lfile_reader(
+    std::unique_ptr<SequentialFileReader> lfile_reader(
         new SequentialFileReader(std::move(lfile), logname));
 
     // Create the log reader.
@@ -353,7 +364,8 @@ class Repairer {
     // propagating bad information (like overly large sequence
     // numbers).
     log::Reader reader(db_options_.info_log, std::move(lfile_reader), &reporter,
-                       true /*enable checksum*/, 0 /*initial_offset*/, log);
+                       true /*enable checksum*/, log,
+                       false /* retry_after_eof */);
 
     // Initialize per-column family memtables
     for (auto* cfd : *vset_.GetColumnFamilySet()) {
@@ -405,10 +417,16 @@ class Repairer {
       SnapshotChecker* snapshot_checker = DisableGCSnapshotChecker::Instance();
 
       auto write_hint = cfd->CalculateSSTWriteHint(0);
+      std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
+          range_del_iters;
+      auto range_del_iter =
+          mem->NewRangeTombstoneIterator(ro, kMaxSequenceNumber);
+      if (range_del_iter != nullptr) {
+        range_del_iters.emplace_back(range_del_iter);
+      }
       status = BuildTable(
           dbname_, env_, *cfd->ioptions(), *cfd->GetLatestMutableCFOptions(),
-          env_options_, table_cache_, iter.get(),
-          std::unique_ptr<InternalIterator>(mem->NewRangeTombstoneIterator(ro)),
+          env_options_, table_cache_, iter.get(), std::move(range_del_iters),
           &meta, cfd->internal_comparator(),
           cfd->int_tbl_prop_collector_factories(), cfd->GetID(), cfd->GetName(),
           {}, kMaxSequenceNumber, snapshot_checker, kNoCompression,
diff --git a/3rdParty/rocksdb/v5.16.X/db/repair_test.cc b/3rdParty/rocksdb/v5.18.X/db/repair_test.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/repair_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/repair_test.cc
index 93dcfc14d6..3422532da4 100644
--- a/3rdParty/rocksdb/v5.16.X/db/repair_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/repair_test.cc
@@ -74,7 +74,7 @@ TEST_F(RepairTest, CorruptManifest) {
 
   Close();
   ASSERT_OK(env_->FileExists(manifest_path));
-  CreateFile(env_, manifest_path, "blah");
+  CreateFile(env_, manifest_path, "blah", false /* use_fsync */);
   ASSERT_OK(RepairDB(dbname_, CurrentOptions()));
   Reopen(CurrentOptions());
 
@@ -153,7 +153,7 @@ TEST_F(RepairTest, CorruptSst) {
   Flush();
   auto sst_path = GetFirstSstPath();
   ASSERT_FALSE(sst_path.empty());
-  CreateFile(env_, sst_path, "blah");
+  CreateFile(env_, sst_path, "blah", false /* use_fsync */);
 
   Close();
   ASSERT_OK(RepairDB(dbname_, CurrentOptions()));
@@ -313,6 +313,7 @@ TEST_F(RepairTest, RepairColumnFamilyOptions) {
     ASSERT_EQ(comparator_name,
               fname_and_props.second->comparator_name);
   }
+  Close();
 
   // Also check comparator when it's provided via "unknown" CF options
   ASSERT_OK(RepairDB(dbname_, opts, {{"default", opts}},
diff --git a/3rdParty/rocksdb/v5.16.X/db/snapshot_checker.h b/3rdParty/rocksdb/v5.18.X/db/snapshot_checker.h
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/db/snapshot_checker.h
rename to 3rdParty/rocksdb/v5.18.X/db/snapshot_checker.h
index 4570aee9c6..67d17bd6d1 100644
--- a/3rdParty/rocksdb/v5.16.X/db/snapshot_checker.h
+++ b/3rdParty/rocksdb/v5.18.X/db/snapshot_checker.h
@@ -19,8 +19,9 @@ class SnapshotChecker {
 class DisableGCSnapshotChecker : public SnapshotChecker {
  public:
   virtual ~DisableGCSnapshotChecker() {}
-  virtual bool IsInSnapshot(SequenceNumber /*sequence*/,
-                            SequenceNumber /*snapshot_sequence*/) const override {
+  virtual bool IsInSnapshot(
+      SequenceNumber /*sequence*/,
+      SequenceNumber /*snapshot_sequence*/) const override {
     // By returning false, we prevent all the values from being GCed
     return false;
   }
diff --git a/3rdParty/rocksdb/v5.16.X/db/snapshot_impl.cc b/3rdParty/rocksdb/v5.18.X/db/snapshot_impl.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/snapshot_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/db/snapshot_impl.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/snapshot_impl.h b/3rdParty/rocksdb/v5.18.X/db/snapshot_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/snapshot_impl.h
rename to 3rdParty/rocksdb/v5.18.X/db/snapshot_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/table_cache.cc b/3rdParty/rocksdb/v5.18.X/db/table_cache.cc
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/db/table_cache.cc
rename to 3rdParty/rocksdb/v5.18.X/db/table_cache.cc
index f374a68766..829f5b21ff 100644
--- a/3rdParty/rocksdb/v5.16.X/db/table_cache.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/table_cache.cc
@@ -10,6 +10,7 @@
 #include "db/table_cache.h"
 
 #include "db/dbformat.h"
+#include "db/range_tombstone_fragmenter.h"
 #include "db/version_edit.h"
 #include "util/filename.h"
 
@@ -41,8 +42,10 @@ static void UnrefEntry(void* arg1, void* arg2) {
   cache->Release(h);
 }
 
-static void DeleteTableReader(void* arg1, void* /*arg2*/) {
+static void DeleteTableReader(void* arg1, void* arg2) {
   TableReader* table_reader = reinterpret_cast<TableReader*>(arg1);
+  Statistics* stats = reinterpret_cast<Statistics*>(arg2);
+  RecordTick(stats, NO_FILE_CLOSES);
   delete table_reader;
 }
 
@@ -91,12 +94,12 @@ Status TableCache::GetTableReader(
     const EnvOptions& env_options,
     const InternalKeyComparator& internal_comparator, const FileDescriptor& fd,
     bool sequential_mode, size_t readahead, bool record_read_stats,
-    HistogramImpl* file_read_hist, unique_ptr<TableReader>* table_reader,
+    HistogramImpl* file_read_hist, std::unique_ptr<TableReader>* table_reader,
     const SliceTransform* prefix_extractor, bool skip_filters, int level,
     bool prefetch_index_and_filter_in_cache, bool for_compaction) {
   std::string fname =
       TableFileName(ioptions_.cf_paths, fd.GetNumber(), fd.GetPathId());
-  unique_ptr<RandomAccessFile> file;
+  std::unique_ptr<RandomAccessFile> file;
   Status s = ioptions_.env->NewRandomAccessFile(fname, &file, env_options);
 
   RecordTick(ioptions_.statistics, NO_FILE_OPENS);
@@ -116,7 +119,8 @@ Status TableCache::GetTableReader(
         new RandomAccessFileReader(
             std::move(file), fname, ioptions_.env,
             record_read_stats ? ioptions_.statistics : nullptr, SST_READ_MICROS,
-            file_read_hist, ioptions_.rate_limiter, for_compaction));
+            file_read_hist, ioptions_.rate_limiter, for_compaction,
+            ioptions_.listeners));
     s = ioptions_.table_factory->NewTableReader(
         TableReaderOptions(ioptions_, prefix_extractor, env_options,
                            internal_comparator, skip_filters, immortal_tables_,
@@ -155,7 +159,7 @@ Status TableCache::FindTable(const EnvOptions& env_options,
     if (no_io) {  // Don't do IO and return a not-found status
       return Status::Incomplete("Table not found in table_cache, no_io is set");
     }
-    unique_ptr<TableReader> table_reader;
+    std::unique_ptr<TableReader> table_reader;
     s = GetTableReader(env_options, internal_comparator, fd,
                        false /* sequential mode */, 0 /* readahead */,
                        record_read_stats, file_read_hist, &table_reader,
@@ -181,9 +185,11 @@ Status TableCache::FindTable(const EnvOptions& env_options,
 InternalIterator* TableCache::NewIterator(
     const ReadOptions& options, const EnvOptions& env_options,
     const InternalKeyComparator& icomparator, const FileMetaData& file_meta,
-    RangeDelAggregator* range_del_agg, const SliceTransform* prefix_extractor,
+    RangeDelAggregatorV2* range_del_agg, const SliceTransform* prefix_extractor,
     TableReader** table_reader_ptr, HistogramImpl* file_read_hist,
-    bool for_compaction, Arena* arena, bool skip_filters, int level) {
+    bool for_compaction, Arena* arena, bool skip_filters, int level,
+    const InternalKey* smallest_compaction_key,
+    const InternalKey* largest_compaction_key) {
   PERF_TIMER_GUARD(new_table_iterator_nanos);
 
   Status s;
@@ -213,7 +219,7 @@ InternalIterator* TableCache::NewIterator(
 
   auto& fd = file_meta.fd;
   if (create_new_table_reader) {
-    unique_ptr<TableReader> table_reader_unique_ptr;
+    std::unique_ptr<TableReader> table_reader_unique_ptr;
     s = GetTableReader(
         env_options, icomparator, fd, true /* sequential_mode */, readahead,
         !for_compaction /* record stats */, nullptr, &table_reader_unique_ptr,
@@ -245,7 +251,8 @@ InternalIterator* TableCache::NewIterator(
     }
     if (create_new_table_reader) {
       assert(handle == nullptr);
-      result->RegisterCleanup(&DeleteTableReader, table_reader, nullptr);
+      result->RegisterCleanup(&DeleteTableReader, table_reader,
+                              ioptions_.statistics);
     } else if (handle != nullptr) {
       result->RegisterCleanup(&UnrefEntry, cache_, handle);
       handle = nullptr;  // prevent from releasing below
@@ -260,16 +267,23 @@ InternalIterator* TableCache::NewIterator(
   }
   if (s.ok() && range_del_agg != nullptr && !options.ignore_range_deletions) {
     if (range_del_agg->AddFile(fd.GetNumber())) {
-      std::unique_ptr<InternalIterator> range_del_iter(
-          table_reader->NewRangeTombstoneIterator(options));
+      std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter(
+          static_cast<FragmentedRangeTombstoneIterator*>(
+              table_reader->NewRangeTombstoneIterator(options)));
       if (range_del_iter != nullptr) {
         s = range_del_iter->status();
       }
       if (s.ok()) {
-        s = range_del_agg->AddTombstones(
-            std::move(range_del_iter),
-            &file_meta.smallest,
-            &file_meta.largest);
+        const InternalKey* smallest = &file_meta.smallest;
+        const InternalKey* largest = &file_meta.largest;
+        if (smallest_compaction_key != nullptr) {
+          smallest = smallest_compaction_key;
+        }
+        if (largest_compaction_key != nullptr) {
+          largest = largest_compaction_key;
+        }
+        range_del_agg->AddTombstones(std::move(range_del_iter), smallest,
+                                     largest);
       }
     }
   }
@@ -363,18 +377,16 @@ Status TableCache::Get(const ReadOptions& options,
         t = GetTableReaderFromHandle(handle);
       }
     }
-    if (s.ok() && get_context->range_del_agg() != nullptr &&
+    SequenceNumber* max_covering_tombstone_seq =
+        get_context->max_covering_tombstone_seq();
+    if (s.ok() && max_covering_tombstone_seq != nullptr &&
         !options.ignore_range_deletions) {
-      std::unique_ptr<InternalIterator> range_del_iter(
+      std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter(
           t->NewRangeTombstoneIterator(options));
       if (range_del_iter != nullptr) {
-        s = range_del_iter->status();
-      }
-      if (s.ok()) {
-        s = get_context->range_del_agg()->AddTombstones(
-            std::move(range_del_iter),
-            &file_meta.smallest,
-            &file_meta.largest);
+        *max_covering_tombstone_seq = std::max(
+            *max_covering_tombstone_seq,
+            range_del_iter->MaxCoveringTombstoneSeqnum(ExtractUserKey(k)));
       }
     }
     if (s.ok()) {
diff --git a/3rdParty/rocksdb/v5.16.X/db/table_cache.h b/3rdParty/rocksdb/v5.18.X/db/table_cache.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/db/table_cache.h
rename to 3rdParty/rocksdb/v5.18.X/db/table_cache.h
index 7e7f53cc1f..04485c4dcc 100644
--- a/3rdParty/rocksdb/v5.16.X/db/table_cache.h
+++ b/3rdParty/rocksdb/v5.18.X/db/table_cache.h
@@ -15,7 +15,7 @@
 #include <stdint.h>
 
 #include "db/dbformat.h"
-#include "db/range_del_aggregator.h"
+#include "db/range_del_aggregator_v2.h"
 #include "options/cf_options.h"
 #include "port/port.h"
 #include "rocksdb/cache.h"
@@ -52,11 +52,13 @@ class TableCache {
   InternalIterator* NewIterator(
       const ReadOptions& options, const EnvOptions& toptions,
       const InternalKeyComparator& internal_comparator,
-      const FileMetaData& file_meta, RangeDelAggregator* range_del_agg,
+      const FileMetaData& file_meta, RangeDelAggregatorV2* range_del_agg,
       const SliceTransform* prefix_extractor = nullptr,
       TableReader** table_reader_ptr = nullptr,
       HistogramImpl* file_read_hist = nullptr, bool for_compaction = false,
-      Arena* arena = nullptr, bool skip_filters = false, int level = -1);
+      Arena* arena = nullptr, bool skip_filters = false, int level = -1,
+      const InternalKey* smallest_compaction_key = nullptr,
+      const InternalKey* largest_compaction_key = nullptr);
 
   // If a seek to internal key "k" in specified file finds an entry,
   // call (*handle_result)(arg, found_key, found_value) repeatedly until
@@ -139,7 +141,7 @@ class TableCache {
                         const FileDescriptor& fd, bool sequential_mode,
                         size_t readahead, bool record_read_stats,
                         HistogramImpl* file_read_hist,
-                        unique_ptr<TableReader>* table_reader,
+                        std::unique_ptr<TableReader>* table_reader,
                         const SliceTransform* prefix_extractor = nullptr,
                         bool skip_filters = false, int level = -1,
                         bool prefetch_index_and_filter_in_cache = true,
diff --git a/3rdParty/rocksdb/v5.16.X/db/table_properties_collector.cc b/3rdParty/rocksdb/v5.18.X/db/table_properties_collector.cc
similarity index 50%
rename from 3rdParty/rocksdb/v5.16.X/db/table_properties_collector.cc
rename to 3rdParty/rocksdb/v5.18.X/db/table_properties_collector.cc
index 084cf139db..4254e179c9 100644
--- a/3rdParty/rocksdb/v5.16.X/db/table_properties_collector.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/table_properties_collector.cc
@@ -11,52 +11,6 @@
 
 namespace rocksdb {
 
-Status InternalKeyPropertiesCollector::InternalAdd(const Slice& key,
-                                                   const Slice& /*value*/,
-                                                   uint64_t /*file_size*/) {
-  ParsedInternalKey ikey;
-  if (!ParseInternalKey(key, &ikey)) {
-    return Status::InvalidArgument("Invalid internal key");
-  }
-
-  // Note: We count both, deletions and single deletions here.
-  if (ikey.type == ValueType::kTypeDeletion ||
-      ikey.type == ValueType::kTypeSingleDeletion) {
-    ++deleted_keys_;
-  } else if (ikey.type == ValueType::kTypeMerge) {
-    ++merge_operands_;
-  }
-
-  return Status::OK();
-}
-
-Status InternalKeyPropertiesCollector::Finish(
-    UserCollectedProperties* properties) {
-  assert(properties);
-  assert(properties->find(
-        InternalKeyTablePropertiesNames::kDeletedKeys) == properties->end());
-  assert(properties->find(InternalKeyTablePropertiesNames::kMergeOperands) ==
-         properties->end());
-
-  std::string val_deleted_keys;
-  PutVarint64(&val_deleted_keys, deleted_keys_);
-  properties->insert(
-      {InternalKeyTablePropertiesNames::kDeletedKeys, val_deleted_keys});
-
-  std::string val_merge_operands;
-  PutVarint64(&val_merge_operands, merge_operands_);
-  properties->insert(
-      {InternalKeyTablePropertiesNames::kMergeOperands, val_merge_operands});
-
-  return Status::OK();
-}
-
-UserCollectedProperties
-InternalKeyPropertiesCollector::GetReadableProperties() const {
-  return {{"kDeletedKeys", ToString(deleted_keys_)},
-          {"kMergeOperands", ToString(merge_operands_)}};
-}
-
 namespace {
 
 uint64_t GetUint64Property(const UserCollectedProperties& props,
@@ -97,23 +51,17 @@ UserKeyTablePropertiesCollector::GetReadableProperties() const {
   return collector_->GetReadableProperties();
 }
 
-
-const std::string InternalKeyTablePropertiesNames::kDeletedKeys
-  = "rocksdb.deleted.keys";
-const std::string InternalKeyTablePropertiesNames::kMergeOperands =
-    "rocksdb.merge.operands";
-
 uint64_t GetDeletedKeys(
     const UserCollectedProperties& props) {
   bool property_present_ignored;
-  return GetUint64Property(props, InternalKeyTablePropertiesNames::kDeletedKeys,
+  return GetUint64Property(props, TablePropertiesNames::kDeletedKeys,
                            &property_present_ignored);
 }
 
 uint64_t GetMergeOperands(const UserCollectedProperties& props,
                           bool* property_present) {
   return GetUint64Property(
-      props, InternalKeyTablePropertiesNames::kMergeOperands, property_present);
+      props, TablePropertiesNames::kMergeOperands, property_present);
 }
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/db/table_properties_collector.h b/3rdParty/rocksdb/v5.18.X/db/table_properties_collector.h
similarity index 74%
rename from 3rdParty/rocksdb/v5.16.X/db/table_properties_collector.h
rename to 3rdParty/rocksdb/v5.18.X/db/table_properties_collector.h
index 7216ec3190..4792b1a817 100644
--- a/3rdParty/rocksdb/v5.16.X/db/table_properties_collector.h
+++ b/3rdParty/rocksdb/v5.18.X/db/table_properties_collector.h
@@ -14,11 +14,6 @@
 
 namespace rocksdb {
 
-struct InternalKeyTablePropertiesNames {
-  static const std::string kDeletedKeys;
-  static const std::string kMergeOperands;
-};
-
 // Base class for internal table properties collector.
 class IntTblPropCollector {
  public:
@@ -49,39 +44,6 @@ class IntTblPropCollectorFactory {
   virtual const char* Name() const = 0;
 };
 
-// Collecting the statistics for internal keys. Visible only by internal
-// rocksdb modules.
-class InternalKeyPropertiesCollector : public IntTblPropCollector {
- public:
-  virtual Status InternalAdd(const Slice& key, const Slice& value,
-                             uint64_t file_size) override;
-
-  virtual Status Finish(UserCollectedProperties* properties) override;
-
-  virtual const char* Name() const override {
-    return "InternalKeyPropertiesCollector";
-  }
-
-  UserCollectedProperties GetReadableProperties() const override;
-
- private:
-  uint64_t deleted_keys_ = 0;
-  uint64_t merge_operands_ = 0;
-};
-
-class InternalKeyPropertiesCollectorFactory
-    : public IntTblPropCollectorFactory {
- public:
-  virtual IntTblPropCollector* CreateIntTblPropCollector(
-      uint32_t /*column_family_id*/) override {
-    return new InternalKeyPropertiesCollector();
-  }
-
-  virtual const char* Name() const override {
-    return "InternalKeyPropertiesCollectorFactory";
-  }
-};
-
 // When rocksdb creates a new table, it will encode all "user keys" into
 // "internal keys", which contains meta information of a given entry.
 //
diff --git a/3rdParty/rocksdb/v5.16.X/db/table_properties_collector_test.cc b/3rdParty/rocksdb/v5.18.X/db/table_properties_collector_test.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/db/table_properties_collector_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/table_properties_collector_test.cc
index a51a36f628..ebeb5962b1 100644
--- a/3rdParty/rocksdb/v5.16.X/db/table_properties_collector_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/table_properties_collector_test.cc
@@ -45,8 +45,9 @@ void MakeBuilder(const Options& options, const ImmutableCFOptions& ioptions,
                      int_tbl_prop_collector_factories,
                  std::unique_ptr<WritableFileWriter>* writable,
                  std::unique_ptr<TableBuilder>* builder) {
-  unique_ptr<WritableFile> wf(new test::StringSink);
-  writable->reset(new WritableFileWriter(std::move(wf), EnvOptions()));
+  std::unique_ptr<WritableFile> wf(new test::StringSink);
+  writable->reset(
+      new WritableFileWriter(std::move(wf), "" /* don't care */, EnvOptions()));
   int unknown_level = -1;
   builder->reset(NewTableBuilder(
       ioptions, moptions, internal_comparator, int_tbl_prop_collector_factories,
@@ -398,9 +399,6 @@ void TestInternalKeyPropertiesCollector(
     ImmutableCFOptions ioptions(options);
     GetIntTblPropCollectorFactory(ioptions, &int_tbl_prop_collector_factories);
     options.comparator = comparator;
-  } else {
-    int_tbl_prop_collector_factories.emplace_back(
-        new InternalKeyPropertiesCollectorFactory);
   }
   const ImmutableCFOptions ioptions(options);
   MutableCFOptions moptions(options);
@@ -417,8 +415,9 @@ void TestInternalKeyPropertiesCollector(
 
     test::StringSink* fwf =
         static_cast<test::StringSink*>(writable->writable_file());
-    unique_ptr<RandomAccessFileReader> reader(test::GetRandomAccessFileReader(
-        new test::StringSource(fwf->contents())));
+    std::unique_ptr<RandomAccessFileReader> reader(
+        test::GetRandomAccessFileReader(
+            new test::StringSource(fwf->contents())));
     TableProperties* props;
     Status s =
         ReadTableProperties(reader.get(), fwf->contents().size(), magic_number,
diff --git a/3rdParty/rocksdb/v5.16.X/db/transaction_log_impl.cc b/3rdParty/rocksdb/v5.18.X/db/transaction_log_impl.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/db/transaction_log_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/db/transaction_log_impl.cc
index d0b95543d6..4d6671ef66 100644
--- a/3rdParty/rocksdb/v5.16.X/db/transaction_log_impl.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/transaction_log_impl.cc
@@ -43,9 +43,10 @@ TransactionLogIteratorImpl::TransactionLogIteratorImpl(
 }
 
 Status TransactionLogIteratorImpl::OpenLogFile(
-    const LogFile* logFile, unique_ptr<SequentialFileReader>* file_reader) {
+    const LogFile* logFile,
+    std::unique_ptr<SequentialFileReader>* file_reader) {
   Env* env = options_->env;
-  unique_ptr<SequentialFile> file;
+  std::unique_ptr<SequentialFile> file;
   std::string fname;
   Status s;
   EnvOptions optimized_env_options = env->OptimizeForLogRead(soptions_);
@@ -104,7 +105,7 @@ void TransactionLogIteratorImpl::SeekToStartSequence(
   if (files_->size() <= startFileIndex) {
     return;
   }
-  Status s = OpenLogReader(files_->at(startFileIndex).get());
+  Status s = OpenLogReader(files_->at(static_cast<size_t>(startFileIndex)).get());
   if (!s.ok()) {
     currentStatus_ = s;
     reporter_.Info(currentStatus_.ToString().c_str());
@@ -306,15 +307,16 @@ void TransactionLogIteratorImpl::UpdateCurrentWriteBatch(const Slice& record) {
 }
 
 Status TransactionLogIteratorImpl::OpenLogReader(const LogFile* logFile) {
-  unique_ptr<SequentialFileReader> file;
+  std::unique_ptr<SequentialFileReader> file;
   Status s = OpenLogFile(logFile, &file);
   if (!s.ok()) {
     return s;
   }
   assert(file);
-  currentLogReader_.reset(new log::Reader(
-      options_->info_log, std::move(file), &reporter_,
-      read_options_.verify_checksums_, 0, logFile->LogNumber()));
+  currentLogReader_.reset(
+      new log::Reader(options_->info_log, std::move(file), &reporter_,
+                      read_options_.verify_checksums_, logFile->LogNumber(),
+                      false /* retry_after_eof */));
   return Status::OK();
 }
 }  //  namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/db/transaction_log_impl.h b/3rdParty/rocksdb/v5.18.X/db/transaction_log_impl.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/db/transaction_log_impl.h
rename to 3rdParty/rocksdb/v5.18.X/db/transaction_log_impl.h
index b6762bf5f8..3c27a8f378 100644
--- a/3rdParty/rocksdb/v5.16.X/db/transaction_log_impl.h
+++ b/3rdParty/rocksdb/v5.18.X/db/transaction_log_impl.h
@@ -85,9 +85,9 @@ class TransactionLogIteratorImpl : public TransactionLogIterator {
   Status currentStatus_;
   size_t currentFileIndex_;
   std::unique_ptr<WriteBatch> currentBatch_;
-  unique_ptr<log::Reader> currentLogReader_;
+  std::unique_ptr<log::Reader> currentLogReader_;
   Status OpenLogFile(const LogFile* logFile,
-                     unique_ptr<SequentialFileReader>* file);
+                     std::unique_ptr<SequentialFileReader>* file);
 
   struct LogReporter : public log::Reader::Reporter {
     Env* env;
diff --git a/3rdParty/rocksdb/v5.16.X/db/version_builder.cc b/3rdParty/rocksdb/v5.18.X/db/version_builder.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/db/version_builder.cc
rename to 3rdParty/rocksdb/v5.18.X/db/version_builder.cc
index b1f558f6f3..5d0d6d9277 100644
--- a/3rdParty/rocksdb/v5.16.X/db/version_builder.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/version_builder.cc
@@ -324,8 +324,6 @@ class VersionBuilder::Rep {
       // Merge the set of added files with the set of pre-existing files.
       // Drop any deleted files.  Store the result in *v.
       const auto& base_files = base_vstorage_->LevelFiles(level);
-      auto base_iter = base_files.begin();
-      auto base_end = base_files.end();
       const auto& unordered_added_files = levels_[level].added_files;
       vstorage->Reserve(level,
                         base_files.size() + unordered_added_files.size());
@@ -339,30 +337,27 @@ class VersionBuilder::Rep {
       std::sort(added_files.begin(), added_files.end(), cmp);
 
 #ifndef NDEBUG
-      FileMetaData* prev_file = nullptr;
-#endif
-
+      FileMetaData* prev_added_file = nullptr;
       for (const auto& added : added_files) {
-#ifndef NDEBUG
-        if (level > 0 && prev_file != nullptr) {
+        if (level > 0 && prev_added_file != nullptr) {
           assert(base_vstorage_->InternalComparator()->Compare(
-                     prev_file->smallest, added->smallest) <= 0);
+                     prev_added_file->smallest, added->smallest) <= 0);
         }
-        prev_file = added;
+        prev_added_file = added;
+      }
 #endif
 
-        // Add all smaller files listed in base_
-        for (auto bpos = std::upper_bound(base_iter, base_end, added, cmp);
-             base_iter != bpos; ++base_iter) {
-          MaybeAddFile(vstorage, level, *base_iter);
+      auto base_iter = base_files.begin();
+      auto base_end = base_files.end();
+      auto added_iter = added_files.begin();
+      auto added_end = added_files.end();
+      while (added_iter != added_end || base_iter != base_end) {
+        if (base_iter == base_end ||
+                (added_iter != added_end && cmp(*added_iter, *base_iter))) {
+          MaybeAddFile(vstorage, level, *added_iter++);
+        } else {
+          MaybeAddFile(vstorage, level, *base_iter++);
         }
-
-        MaybeAddFile(vstorage, level, added);
-      }
-
-      // Add remaining base files
-      for (; base_iter != base_end; ++base_iter) {
-        MaybeAddFile(vstorage, level, *base_iter);
       }
     }
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/version_builder.h b/3rdParty/rocksdb/v5.18.X/db/version_builder.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/version_builder.h
rename to 3rdParty/rocksdb/v5.18.X/db/version_builder.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/version_builder_test.cc b/3rdParty/rocksdb/v5.18.X/db/version_builder_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/version_builder_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/version_builder_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/version_edit.cc b/3rdParty/rocksdb/v5.18.X/db/version_edit.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/version_edit.cc
rename to 3rdParty/rocksdb/v5.18.X/db/version_edit.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/version_edit.h b/3rdParty/rocksdb/v5.18.X/db/version_edit.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/version_edit.h
rename to 3rdParty/rocksdb/v5.18.X/db/version_edit.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/version_edit_test.cc b/3rdParty/rocksdb/v5.18.X/db/version_edit_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/version_edit_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/version_edit_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/version_set.cc b/3rdParty/rocksdb/v5.18.X/db/version_set.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/db/version_set.cc
rename to 3rdParty/rocksdb/v5.18.X/db/version_set.cc
index ede91c6133..ad5f898d0d 100644
--- a/3rdParty/rocksdb/v5.16.X/db/version_set.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/version_set.cc
@@ -16,6 +16,7 @@
 #include <inttypes.h>
 #include <stdio.h>
 #include <algorithm>
+#include <list>
 #include <map>
 #include <set>
 #include <string>
@@ -62,20 +63,12 @@ int FindFileInRange(const InternalKeyComparator& icmp,
     const Slice& key,
     uint32_t left,
     uint32_t right) {
-  while (left < right) {
-    uint32_t mid = (left + right) / 2;
-    const FdWithKeyRange& f = file_level.files[mid];
-    if (icmp.InternalKeyComparator::Compare(f.largest_key, key) < 0) {
-      // Key at "mid.largest" is < "target".  Therefore all
-      // files at or before "mid" are uninteresting.
-      left = mid + 1;
-    } else {
-      // Key at "mid.largest" is >= "target".  Therefore all files
-      // after "mid" are uninteresting.
-      right = mid;
-    }
-  }
-  return right;
+  auto cmp = [&](const FdWithKeyRange& f, const Slice& k) -> bool {
+    return icmp.InternalKeyComparator::Compare(f.largest_key, k) < 0;
+  };
+  const auto &b = file_level.files;
+  return static_cast<int>(std::lower_bound(b + left,
+                                           b + right, key, cmp) - b);
 }
 
 Status OverlapWithIterator(const Comparator* ucmp,
@@ -458,15 +451,17 @@ bool SomeFileOverlapsRange(
 }
 
 namespace {
+
 class LevelIterator final : public InternalIterator {
  public:
-  LevelIterator(TableCache* table_cache, const ReadOptions& read_options,
-                const EnvOptions& env_options,
-                const InternalKeyComparator& icomparator,
-                const LevelFilesBrief* flevel,
-                const SliceTransform* prefix_extractor, bool should_sample,
-                HistogramImpl* file_read_hist, bool for_compaction,
-                bool skip_filters, int level, RangeDelAggregator* range_del_agg)
+  LevelIterator(
+      TableCache* table_cache, const ReadOptions& read_options,
+      const EnvOptions& env_options, const InternalKeyComparator& icomparator,
+      const LevelFilesBrief* flevel, const SliceTransform* prefix_extractor,
+      bool should_sample, HistogramImpl* file_read_hist, bool for_compaction,
+      bool skip_filters, int level, RangeDelAggregatorV2* range_del_agg,
+      const std::vector<AtomicCompactionUnitBoundary>* compaction_boundaries =
+          nullptr)
       : table_cache_(table_cache),
         read_options_(read_options),
         env_options_(env_options),
@@ -480,7 +475,8 @@ class LevelIterator final : public InternalIterator {
         file_index_(flevel_->num_files),
         level_(level),
         range_del_agg_(range_del_agg),
-        pinned_iters_mgr_(nullptr) {
+        pinned_iters_mgr_(nullptr),
+        compaction_boundaries_(compaction_boundaries) {
     // Empty level is not supported.
     assert(flevel_ != nullptr && flevel_->num_files > 0);
   }
@@ -547,12 +543,18 @@ class LevelIterator final : public InternalIterator {
       sample_file_read_inc(file_meta.file_metadata);
     }
 
+    const InternalKey* smallest_compaction_key = nullptr;
+    const InternalKey* largest_compaction_key = nullptr;
+    if (compaction_boundaries_ != nullptr) {
+      smallest_compaction_key = (*compaction_boundaries_)[file_index_].smallest;
+      largest_compaction_key = (*compaction_boundaries_)[file_index_].largest;
+    }
     return table_cache_->NewIterator(
         read_options_, env_options_, icomparator_, *file_meta.file_metadata,
         range_del_agg_, prefix_extractor_,
         nullptr /* don't need reference to table */,
         file_read_hist_, for_compaction_, nullptr /* arena */, skip_filters_,
-        level_);
+        level_, smallest_compaction_key, largest_compaction_key);
   }
 
   TableCache* table_cache_;
@@ -569,9 +571,13 @@ class LevelIterator final : public InternalIterator {
   bool skip_filters_;
   size_t file_index_;
   int level_;
-  RangeDelAggregator* range_del_agg_;
+  RangeDelAggregatorV2* range_del_agg_;
   IteratorWrapper file_iter_;  // May be nullptr
   PinnedIteratorsManager* pinned_iters_mgr_;
+
+  // To be propagated to RangeDelAggregator in order to safely truncate range
+  // tombstones.
+  const std::vector<AtomicCompactionUnitBoundary>* compaction_boundaries_;
 };
 
 void LevelIterator::Seek(const Slice& target) {
@@ -759,7 +765,11 @@ Status Version::GetTableProperties(std::shared_ptr<const TableProperties>* tp,
   // By setting the magic number to kInvalidTableMagicNumber, we can by
   // pass the magic number check in the footer.
   std::unique_ptr<RandomAccessFileReader> file_reader(
-      new RandomAccessFileReader(std::move(file), file_name));
+      new RandomAccessFileReader(
+          std::move(file), file_name, nullptr /* env */, nullptr /* stats */,
+          0 /* hist_type */, nullptr /* file_read_hist */,
+          nullptr /* rate_limiter */, false /* for_compaction*/,
+          ioptions->listeners));
   s = ReadTableProperties(
       file_reader.get(), file_meta->fd.GetFileSize(),
       Footer::kInvalidTableMagicNumber /* table's magic number */, *ioptions,
@@ -895,13 +905,18 @@ void Version::GetColumnFamilyMetaData(ColumnFamilyMetaData* cf_meta) {
         assert(!ioptions->cf_paths.empty());
         file_path = ioptions->cf_paths.back().path;
       }
-      files.emplace_back(
-          MakeTableFileName("", file->fd.GetNumber()), file_path,
-          file->fd.GetFileSize(), file->fd.smallest_seqno,
-          file->fd.largest_seqno, file->smallest.user_key().ToString(),
+      files.emplace_back(SstFileMetaData{
+          MakeTableFileName("", file->fd.GetNumber()),
+          file_path,
+          static_cast<size_t>(file->fd.GetFileSize()),
+          file->fd.smallest_seqno,
+          file->fd.largest_seqno,
+          file->smallest.user_key().ToString(),
           file->largest.user_key().ToString(),
           file->stats.num_reads_sampled.load(std::memory_order_relaxed),
-          file->being_compacted);
+          file->being_compacted});
+      files.back().num_entries = file->num_entries;
+      files.back().num_deletions = file->num_deletions;
       level_size += file->fd.GetFileSize();
     }
     cf_meta->levels.emplace_back(
@@ -970,7 +985,7 @@ double VersionStorageInfo::GetEstimatedCompressionRatioAtLevel(
 void Version::AddIterators(const ReadOptions& read_options,
                            const EnvOptions& soptions,
                            MergeIteratorBuilder* merge_iter_builder,
-                           RangeDelAggregator* range_del_agg) {
+                           RangeDelAggregatorV2* range_del_agg) {
   assert(storage_info_.finalized_);
 
   for (int level = 0; level < storage_info_.num_non_empty_levels(); level++) {
@@ -983,7 +998,7 @@ void Version::AddIteratorsForLevel(const ReadOptions& read_options,
                                    const EnvOptions& soptions,
                                    MergeIteratorBuilder* merge_iter_builder,
                                    int level,
-                                   RangeDelAggregator* range_del_agg) {
+                                   RangeDelAggregatorV2* range_del_agg) {
   assert(storage_info_.finalized_);
   if (level >= storage_info_.num_non_empty_levels()) {
     // This is an empty level
@@ -1042,7 +1057,8 @@ Status Version::OverlapWithLevelIterator(const ReadOptions& read_options,
 
   Arena arena;
   Status status;
-  RangeDelAggregator range_del_agg(icmp, {}, false);
+  ReadRangeDelAggregatorV2 range_del_agg(&icmp,
+                                         kMaxSequenceNumber /* upper_bound */);
 
   *overlap = false;
 
@@ -1098,6 +1114,7 @@ VersionStorageInfo::VersionStorageInfo(
       compaction_style_(compaction_style),
       files_(new std::vector<FileMetaData*>[num_levels_]),
       base_level_(num_levels_ == 1 ? -1 : 1),
+      level_multiplier_(0.0),
       files_by_compaction_pri_(num_levels_),
       level0_non_overlapping_(false),
       next_file_to_compact_by_size_(num_levels_),
@@ -1162,7 +1179,7 @@ Version::Version(ColumnFamilyData* column_family_data, VersionSet* vset,
 void Version::Get(const ReadOptions& read_options, const LookupKey& k,
                   PinnableSlice* value, Status* status,
                   MergeContext* merge_context,
-                  RangeDelAggregator* range_del_agg, bool* value_found,
+                  SequenceNumber* max_covering_tombstone_seq, bool* value_found,
                   bool* key_exists, SequenceNumber* seq, ReadCallback* callback,
                   bool* is_blob) {
   Slice ikey = k.internal_key();
@@ -1179,8 +1196,8 @@ void Version::Get(const ReadOptions& read_options, const LookupKey& k,
   GetContext get_context(
       user_comparator(), merge_operator_, info_log_, db_statistics_,
       status->ok() ? GetContext::kNotFound : GetContext::kMerge, user_key,
-      value, value_found, merge_context, range_del_agg, this->env_, seq,
-      merge_operator_ ? &pinned_iters_mgr : nullptr, callback, is_blob);
+      value, value_found, merge_context, max_covering_tombstone_seq, this->env_,
+      seq, merge_operator_ ? &pinned_iters_mgr : nullptr, callback, is_blob);
 
   // Pin blocks that we read to hold merge operands
   if (merge_operator_) {
@@ -1194,10 +1211,19 @@ void Version::Get(const ReadOptions& read_options, const LookupKey& k,
   FdWithKeyRange* f = fp.GetNextFile();
 
   while (f != nullptr) {
+    if (*max_covering_tombstone_seq > 0) {
+      // The remaining files we look at will only contain covered keys, so we
+      // stop here.
+      break;
+    }
     if (get_context.sample()) {
       sample_file_read_inc(f->file_metadata);
     }
 
+    bool timer_enabled =
+        GetPerfLevel() >= PerfLevel::kEnableTimeExceptForMutex &&
+        get_perf_context()->per_level_perf_context_enabled;
+    StopWatchNano timer(env_, timer_enabled /* auto_start */);
     *status = table_cache_->Get(
         read_options, *internal_comparator(), *f->file_metadata, ikey,
         &get_context, mutable_cf_options_.prefix_extractor.get(),
@@ -1206,6 +1232,10 @@ void Version::Get(const ReadOptions& read_options, const LookupKey& k,
                         fp.IsHitFileLastInLevel()),
         fp.GetCurrentLevel());
     // TODO: examine the behavior for corrupted key
+    if (timer_enabled) {
+      PERF_COUNTER_BY_LEVEL_ADD(get_from_table_nanos, timer.ElapsedNanos(),
+                                fp.GetCurrentLevel());
+    }
     if (!status->ok()) {
       return;
     }
@@ -1221,6 +1251,7 @@ void Version::Get(const ReadOptions& read_options, const LookupKey& k,
         // Keep searching in other files
         break;
       case GetContext::kMerge:
+        // TODO: update per-level perfcontext user_key_return_count for kMerge
         break;
       case GetContext::kFound:
         if (fp.GetHitFileLevel() == 0) {
@@ -1230,6 +1261,7 @@ void Version::Get(const ReadOptions& read_options, const LookupKey& k,
         } else if (fp.GetHitFileLevel() >= 2) {
           RecordTick(db_statistics_, GET_HIT_L2_AND_UP);
         }
+        PERF_COUNTER_BY_LEVEL_ADD(user_key_return_count, 1, fp.GetHitFileLevel());
         return;
       case GetContext::kDeleted:
         // Use empty error message for speed
@@ -1321,7 +1353,7 @@ bool Version::MaybeInitializeFileMetaData(FileMetaData* file_meta) {
   }
   if (tp.get() == nullptr) return false;
   file_meta->num_entries = tp->num_entries;
-  file_meta->num_deletions = GetDeletedKeys(tp->user_collected_properties);
+  file_meta->num_deletions = tp->num_deletions;
   file_meta->raw_value_size = tp->raw_value_size;
   file_meta->raw_key_size = tp->raw_key_size;
 
@@ -1960,7 +1992,9 @@ void VersionStorageInfo::GenerateBottommostFiles() {
       } else {
         l0_file_idx = -1;
       }
-      if (!RangeMightExistAfterSortedRun(f.smallest_key, f.largest_key,
+      Slice smallest_user_key = ExtractUserKey(f.smallest_key);
+      Slice largest_user_key = ExtractUserKey(f.largest_key);
+      if (!RangeMightExistAfterSortedRun(smallest_user_key, largest_user_key,
                                          static_cast<int>(level),
                                          l0_file_idx)) {
         bottommost_files_.emplace_back(static_cast<int>(level),
@@ -2032,13 +2066,29 @@ bool VersionStorageInfo::OverlapInLevel(int level,
 void VersionStorageInfo::GetOverlappingInputs(
     int level, const InternalKey* begin, const InternalKey* end,
     std::vector<FileMetaData*>* inputs, int hint_index, int* file_index,
-    bool expand_range) const {
+    bool expand_range, InternalKey** next_smallest) const {
   if (level >= num_non_empty_levels_) {
     // this level is empty, no overlapping inputs
     return;
   }
 
   inputs->clear();
+  if (file_index) {
+    *file_index = -1;
+  }
+  const Comparator* user_cmp = user_comparator_;
+  if (level > 0) {
+    GetOverlappingInputsRangeBinarySearch(level, begin, end, inputs, hint_index,
+                                          file_index, false, next_smallest);
+    return;
+  }
+
+  if (next_smallest) {
+    // next_smallest key only makes sense for non-level 0, where files are
+    // non-overlapping
+    *next_smallest = nullptr;
+  }
+
   Slice user_begin, user_end;
   if (begin != nullptr) {
     user_begin = begin->user_key();
@@ -2046,43 +2096,52 @@ void VersionStorageInfo::GetOverlappingInputs(
   if (end != nullptr) {
     user_end = end->user_key();
   }
-  if (file_index) {
-    *file_index = -1;
-  }
-  const Comparator* user_cmp = user_comparator_;
-  if (level > 0) {
-    GetOverlappingInputsRangeBinarySearch(level, begin, end, inputs,
-                                          hint_index, file_index);
-    return;
+
+  // index stores the file index need to check.
+  std::list<size_t> index;
+  for (size_t i = 0; i < level_files_brief_[level].num_files; i++) {
+    index.emplace_back(i);
   }
 
-  for (size_t i = 0; i < level_files_brief_[level].num_files; ) {
-    FdWithKeyRange* f = &(level_files_brief_[level].files[i++]);
-    const Slice file_start = ExtractUserKey(f->smallest_key);
-    const Slice file_limit = ExtractUserKey(f->largest_key);
-    if (begin != nullptr && user_cmp->Compare(file_limit, user_begin) < 0) {
-      // "f" is completely before specified range; skip it
-    } else if (end != nullptr && user_cmp->Compare(file_start, user_end) > 0) {
-      // "f" is completely after specified range; skip it
-    } else {
-      inputs->push_back(files_[level][i-1]);
-      if (level == 0 && expand_range) {
-        // Level-0 files may overlap each other.  So check if the newly
-        // added file has expanded the range.  If so, restart search.
-        if (begin != nullptr && user_cmp->Compare(file_start, user_begin) < 0) {
-          user_begin = file_start;
-          inputs->clear();
-          i = 0;
-        } else if (end != nullptr
-            && user_cmp->Compare(file_limit, user_end) > 0) {
-          user_end = file_limit;
-          inputs->clear();
-          i = 0;
+  while (!index.empty()) {
+    bool found_overlapping_file = false;
+    auto iter = index.begin();
+    while (iter != index.end()) {
+      FdWithKeyRange* f = &(level_files_brief_[level].files[*iter]);
+      const Slice file_start = ExtractUserKey(f->smallest_key);
+      const Slice file_limit = ExtractUserKey(f->largest_key);
+      if (begin != nullptr && user_cmp->Compare(file_limit, user_begin) < 0) {
+        // "f" is completely before specified range; skip it
+        iter++;
+      } else if (end != nullptr &&
+                 user_cmp->Compare(file_start, user_end) > 0) {
+        // "f" is completely after specified range; skip it
+        iter++;
+      } else {
+        // if overlap
+        inputs->emplace_back(files_[level][*iter]);
+        found_overlapping_file = true;
+        // record the first file index.
+        if (file_index && *file_index == -1) {
+          *file_index = static_cast<int>(*iter);
+        }
+        // the related file is overlap, erase to avoid checking again.
+        iter = index.erase(iter);
+        if (expand_range) {
+          if (begin != nullptr &&
+              user_cmp->Compare(file_start, user_begin) < 0) {
+            user_begin = file_start;
+          }
+          if (end != nullptr && user_cmp->Compare(file_limit, user_end) > 0) {
+            user_end = file_limit;
+          }
         }
-      } else if (file_index) {
-        *file_index = static_cast<int>(i) - 1;
       }
     }
+    // if all the files left are not overlap, break
+    if (!found_overlapping_file) {
+      break;
+    }
   }
 }
 
@@ -2119,60 +2178,6 @@ void VersionStorageInfo::GetCleanInputsWithinInterval(
                                         true /* within_interval */);
 }
 
-namespace {
-
-const uint64_t kRangeTombstoneSentinel =
-    PackSequenceAndType(kMaxSequenceNumber, kTypeRangeDeletion);
-
-// Utility for comparing sstable boundary keys. Returns -1 if either a or b is
-// null which provides the property that a==null indicates a key that is less
-// than any key and b==null indicates a key that is greater than any key. Note
-// that the comparison is performed primarily on the user-key portion of the
-// key. If the user-keys compare equal, an additional test is made to sort
-// range tombstone sentinel keys before other keys with the same user-key. The
-// result is that 2 user-keys will compare equal if they differ purely on
-// their sequence number and value, but the range tombstone sentinel for that
-// user-key will compare not equal. This is necessary because the range
-// tombstone sentinel key is set as the largest key for an sstable even though
-// that key never appears in the database. We don't want adjacent sstables to
-// be considered overlapping if they are separated by the range tombstone
-// sentinel.
-int sstableKeyCompare(const Comparator* user_cmp,
-                      const InternalKey& a, const InternalKey& b) {
-  auto c = user_cmp->Compare(a.user_key(), b.user_key());
-  if (c != 0) {
-    return c;
-  }
-  auto a_footer = ExtractInternalKeyFooter(a.Encode());
-  auto b_footer = ExtractInternalKeyFooter(b.Encode());
-  if (a_footer == kRangeTombstoneSentinel) {
-    if (b_footer != kRangeTombstoneSentinel) {
-      return -1;
-    }
-  } else if (b_footer == kRangeTombstoneSentinel) {
-    return 1;
-  }
-  return 0;
-}
-
-int sstableKeyCompare(const Comparator* user_cmp,
-                      const InternalKey* a, const InternalKey& b) {
-  if (a == nullptr) {
-    return -1;
-  }
-  return sstableKeyCompare(user_cmp, *a, b);
-}
-
-int sstableKeyCompare(const Comparator* user_cmp,
-                      const InternalKey& a, const InternalKey* b) {
-  if (b == nullptr) {
-    return -1;
-  }
-  return sstableKeyCompare(user_cmp, a, *b);
-}
-
-} // namespace
-
 // Store in "*inputs" all files in "level" that overlap [begin,end]
 // Employ binary search to find at least one file that overlaps the
 // specified range. From that file, iterate backwards and
@@ -2183,7 +2188,7 @@ int sstableKeyCompare(const Comparator* user_cmp,
 void VersionStorageInfo::GetOverlappingInputsRangeBinarySearch(
     int level, const InternalKey* begin, const InternalKey* end,
     std::vector<FileMetaData*>* inputs, int hint_index, int* file_index,
-    bool within_interval) const {
+    bool within_interval, InternalKey** next_smallest) const {
   assert(level > 0);
   int min = 0;
   int mid = 0;
@@ -2219,6 +2224,9 @@ void VersionStorageInfo::GetOverlappingInputsRangeBinarySearch(
 
   // If there were no overlapping files, return immediately.
   if (!foundOverlap) {
+    if (next_smallest) {
+      next_smallest = nullptr;
+    }
     return;
   }
   // returns the index where an overlap is found
@@ -2239,6 +2247,15 @@ void VersionStorageInfo::GetOverlappingInputsRangeBinarySearch(
   for (int i = start_index; i <= end_index; i++) {
     inputs->push_back(files_[level][i]);
   }
+
+  if (next_smallest != nullptr) {
+    // Provide the next key outside the range covered by inputs
+    if (++end_index < static_cast<int>(files_[level].size())) {
+      **next_smallest = files_[level][end_index]->smallest;
+    } else {
+      *next_smallest = nullptr;
+    }
+  }
 }
 
 // Store in *start_index and *end_index the range of all files in
@@ -2382,9 +2399,12 @@ const char* VersionStorageInfo::LevelSummary(
   int len = 0;
   if (compaction_style_ == kCompactionStyleLevel && num_levels() > 1) {
     assert(base_level_ < static_cast<int>(level_max_bytes_.size()));
-    len = snprintf(scratch->buffer, sizeof(scratch->buffer),
-                   "base level %d max bytes base %" PRIu64 " ", base_level_,
-                   level_max_bytes_[base_level_]);
+    if (level_multiplier_ != 0.0) {
+      len = snprintf(
+          scratch->buffer, sizeof(scratch->buffer),
+          "base level %d level multiplier %.2f max bytes base %" PRIu64 " ",
+          base_level_, level_multiplier_, level_max_bytes_[base_level_]);
+    }
   }
   len +=
       snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len, "files[");
@@ -2520,7 +2540,13 @@ void VersionStorageInfo::CalculateBaseBytes(const ImmutableCFOptions& ioptions,
       // No compaction from L1+ needs to be scheduled.
       base_level_ = num_levels_ - 1;
     } else {
-      uint64_t base_bytes_max = options.max_bytes_for_level_base;
+      uint64_t l0_size = 0;
+      for (const auto& f : files_[0]) {
+        l0_size += f->fd.GetFileSize();
+      }
+
+      uint64_t base_bytes_max =
+          std::max(options.max_bytes_for_level_base, l0_size);
       uint64_t base_bytes_min = static_cast<uint64_t>(
           base_bytes_max / options.max_bytes_for_level_multiplier);
 
@@ -2560,11 +2586,33 @@ void VersionStorageInfo::CalculateBaseBytes(const ImmutableCFOptions& ioptions,
         }
       }
 
+      level_multiplier_ = options.max_bytes_for_level_multiplier;
+      assert(base_level_size > 0);
+      if (l0_size > base_level_size &&
+          (l0_size > options.max_bytes_for_level_base ||
+           static_cast<int>(files_[0].size() / 2) >=
+               options.level0_file_num_compaction_trigger)) {
+        // We adjust the base level according to actual L0 size, and adjust
+        // the level multiplier accordingly, when:
+        //   1. the L0 size is larger than level size base, or
+        //   2. number of L0 files reaches twice the L0->L1 compaction trigger
+        // We don't do this otherwise to keep the LSM-tree structure stable
+        // unless the L0 compation is backlogged.
+        base_level_size = l0_size;
+        if (base_level_ == num_levels_ - 1) {
+          level_multiplier_ = 1.0;
+        } else {
+          level_multiplier_ = std::pow(
+              static_cast<double>(max_level_size) /
+                  static_cast<double>(base_level_size),
+              1.0 / static_cast<double>(num_levels_ - base_level_ - 1));
+        }
+      }
+
       uint64_t level_size = base_level_size;
       for (int i = base_level_; i < num_levels_; i++) {
         if (i > base_level_) {
-          level_size = MultiplyCheckOverflow(
-              level_size, options.max_bytes_for_level_multiplier);
+          level_size = MultiplyCheckOverflow(level_size, level_multiplier_);
         }
         // Don't set any level below base_bytes_max. Otherwise, the LSM can
         // assume an hourglass shape where L1+ sizes are smaller than L0. This
@@ -2611,8 +2659,8 @@ uint64_t VersionStorageInfo::EstimateLiveDataSize() const {
 }
 
 bool VersionStorageInfo::RangeMightExistAfterSortedRun(
-    const Slice& smallest_key, const Slice& largest_key, int last_level,
-    int last_l0_idx) {
+    const Slice& smallest_user_key, const Slice& largest_user_key,
+    int last_level, int last_l0_idx) {
   assert((last_l0_idx != -1) == (last_level == 0));
   // TODO(ajkr): this preserves earlier behavior where we considered an L0 file
   // bottommost only if it's the oldest L0 file and there are no files on older
@@ -2634,7 +2682,7 @@ bool VersionStorageInfo::RangeMightExistAfterSortedRun(
     // which overlap with [`smallest_key`, `largest_key`].
     if (files_[level].size() > 0 &&
         (last_level == 0 ||
-         OverlapInLevel(level, &smallest_key, &largest_key))) {
+         OverlapInLevel(level, &smallest_user_key, &largest_user_key))) {
       return true;
     }
   }
@@ -2901,16 +2949,18 @@ Status VersionSet::ProcessManifestWrites(
       // create new manifest file
       ROCKS_LOG_INFO(db_options_->info_log, "Creating manifest %" PRIu64 "\n",
                      pending_manifest_file_number_);
-      unique_ptr<WritableFile> descriptor_file;
-      s = NewWritableFile(
-          env_, DescriptorFileName(dbname_, pending_manifest_file_number_),
-          &descriptor_file, opt_env_opts);
+      std::string descriptor_fname =
+          DescriptorFileName(dbname_, pending_manifest_file_number_);
+      std::unique_ptr<WritableFile> descriptor_file;
+      s = NewWritableFile(env_, descriptor_fname, &descriptor_file,
+                          opt_env_opts);
       if (s.ok()) {
         descriptor_file->SetPreallocationBlockSize(
             db_options_->manifest_preallocation_size);
 
-        unique_ptr<WritableFileWriter> file_writer(
-            new WritableFileWriter(std::move(descriptor_file), opt_env_opts));
+        std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
+            std::move(descriptor_file), descriptor_fname, opt_env_opts, nullptr,
+            db_options_->listeners));
         descriptor_log_.reset(
             new log::Writer(std::move(file_writer), 0, false));
         s = WriteSnapshot(descriptor_log_.get());
@@ -3083,9 +3133,9 @@ Status VersionSet::ProcessManifestWrites(
 // 'datas' is gramatically incorrect. We still use this notation is to indicate
 // that this variable represents a collection of column_family_data.
 Status VersionSet::LogAndApply(
-    const std::vector<ColumnFamilyData*>& column_family_datas,
-    const std::vector<MutableCFOptions>& mutable_cf_options_list,
-    const std::vector<autovector<VersionEdit*>>& edit_lists,
+    const autovector<ColumnFamilyData*>& column_family_datas,
+    const autovector<const MutableCFOptions*>& mutable_cf_options_list,
+    const autovector<autovector<VersionEdit*>>& edit_lists,
     InstrumentedMutex* mu, Directory* db_directory, bool new_descriptor_log,
     const ColumnFamilyOptions* new_cf_options) {
   mu->AssertHeld();
@@ -3117,8 +3167,8 @@ Status VersionSet::LogAndApply(
     assert(static_cast<size_t>(num_cfds) == edit_lists.size());
   }
   for (int i = 0; i < num_cfds; ++i) {
-    writers.emplace_back(mu, column_family_datas[i], mutable_cf_options_list[i],
-                         edit_lists[i]);
+    writers.emplace_back(mu, column_family_datas[i],
+                         *mutable_cf_options_list[i], edit_lists[i]);
     manifest_writers_.push_back(&writers[i]);
   }
   assert(!writers.empty());
@@ -3372,9 +3422,9 @@ Status VersionSet::Recover(
                  manifest_filename.c_str());
 
   manifest_filename = dbname_ + "/" + manifest_filename;
-  unique_ptr<SequentialFileReader> manifest_file_reader;
+  std::unique_ptr<SequentialFileReader> manifest_file_reader;
   {
-    unique_ptr<SequentialFile> manifest_file;
+    std::unique_ptr<SequentialFile> manifest_file;
     s = env_->NewSequentialFile(manifest_filename, &manifest_file,
                                 env_->OptimizeForManifestRead(env_options_));
     if (!s.ok()) {
@@ -3420,7 +3470,8 @@ Status VersionSet::Recover(
     VersionSet::LogReporter reporter;
     reporter.status = &s;
     log::Reader reader(nullptr, std::move(manifest_file_reader), &reporter,
-                       true /*checksum*/, 0 /*initial_offset*/, 0);
+                       true /* checksum */, 0 /* log_number */,
+                       false /* retry_after_eof */);
     Slice record;
     std::string scratch;
     std::vector<VersionEdit> replay_buffer;
@@ -3435,14 +3486,21 @@ Status VersionSet::Recover(
       if (edit.is_in_atomic_group_) {
         if (replay_buffer.empty()) {
           replay_buffer.resize(edit.remaining_entries_ + 1);
+          TEST_SYNC_POINT_CALLBACK("VersionSet::Recover:FirstInAtomicGroup",
+                                   &edit);
         }
         ++num_entries_decoded;
         if (num_entries_decoded + edit.remaining_entries_ !=
             static_cast<uint32_t>(replay_buffer.size())) {
-          return Status::Corruption("corrupted atomic group");
+          TEST_SYNC_POINT_CALLBACK(
+              "VersionSet::Recover:IncorrectAtomicGroupSize", &edit);
+          s = Status::Corruption("corrupted atomic group");
+          break;
         }
         replay_buffer[num_entries_decoded - 1] = std::move(edit);
         if (num_entries_decoded == replay_buffer.size()) {
+          TEST_SYNC_POINT_CALLBACK("VersionSet::Recover:LastInAtomicGroup",
+                                   &edit);
           for (auto& e : replay_buffer) {
             s = ApplyOneVersionEdit(
                 e, cf_name_to_options, column_families_not_found, builders,
@@ -3457,9 +3515,13 @@ Status VersionSet::Recover(
           replay_buffer.clear();
           num_entries_decoded = 0;
         }
+        TEST_SYNC_POINT("VersionSet::Recover:AtomicGroup");
       } else {
         if (!replay_buffer.empty()) {
-          return Status::Corruption("corrupted atomic group");
+          TEST_SYNC_POINT_CALLBACK(
+              "VersionSet::Recover:AtomicGroupMixedWithNormalEdits", &edit);
+          s = Status::Corruption("corrupted atomic group");
+          break;
         }
         s = ApplyOneVersionEdit(
             edit, cf_name_to_options, column_families_not_found, builders,
@@ -3610,12 +3672,12 @@ Status VersionSet::ListColumnFamilies(std::vector<std::string>* column_families,
 
   std::string dscname = dbname + "/" + current;
 
-  unique_ptr<SequentialFileReader> file_reader;
+  std::unique_ptr<SequentialFileReader> file_reader;
   {
-  unique_ptr<SequentialFile> file;
-  s = env->NewSequentialFile(dscname, &file, soptions);
-  if (!s.ok()) {
-    return s;
+    std::unique_ptr<SequentialFile> file;
+    s = env->NewSequentialFile(dscname, &file, soptions);
+    if (!s.ok()) {
+      return s;
   }
   file_reader.reset(new SequentialFileReader(std::move(file), dscname));
   }
@@ -3625,8 +3687,9 @@ Status VersionSet::ListColumnFamilies(std::vector<std::string>* column_families,
   column_family_names.insert({0, kDefaultColumnFamilyName});
   VersionSet::LogReporter reporter;
   reporter.status = &s;
-  log::Reader reader(nullptr, std::move(file_reader), &reporter, true /*checksum*/,
-                     0 /*initial_offset*/, 0);
+  log::Reader reader(nullptr, std::move(file_reader), &reporter,
+                     true /* checksum */, 0 /* log_number */,
+                     false /* retry_after_eof */);
   Slice record;
   std::string scratch;
   while (reader.ReadRecord(&record, &scratch) && s.ok()) {
@@ -3752,10 +3815,10 @@ Status VersionSet::ReduceNumberOfLevels(const std::string& dbname,
 Status VersionSet::DumpManifest(Options& options, std::string& dscname,
                                 bool verbose, bool hex, bool json) {
   // Open the specified manifest file.
-  unique_ptr<SequentialFileReader> file_reader;
+  std::unique_ptr<SequentialFileReader> file_reader;
   Status s;
   {
-    unique_ptr<SequentialFile> file;
+    std::unique_ptr<SequentialFile> file;
     s = options.env->NewSequentialFile(
         dscname, &file, env_->OptimizeForManifestRead(env_options_));
     if (!s.ok()) {
@@ -3786,7 +3849,8 @@ Status VersionSet::DumpManifest(Options& options, std::string& dscname,
     VersionSet::LogReporter reporter;
     reporter.status = &s;
     log::Reader reader(nullptr, std::move(file_reader), &reporter,
-                       true /*checksum*/, 0 /*initial_offset*/, 0);
+                       true /* checksum */, 0 /* log_number */,
+                       false /* retry_after_eof */);
     Slice record;
     std::string scratch;
     while (reader.ReadRecord(&record, &scratch) && s.ok()) {
@@ -4189,7 +4253,7 @@ void VersionSet::AddLiveFiles(std::vector<FileDescriptor>* live_list) {
 }
 
 InternalIterator* VersionSet::MakeInputIterator(
-    const Compaction* c, RangeDelAggregator* range_del_agg,
+    const Compaction* c, RangeDelAggregatorV2* range_del_agg,
     const EnvOptions& env_options_compactions) {
   auto cfd = c->column_family_data();
   ReadOptions read_options;
@@ -4232,7 +4296,8 @@ InternalIterator* VersionSet::MakeInputIterator(
             false /* should_sample */,
             nullptr /* no per level latency histogram */,
             true /* for_compaction */, false /* skip_filters */,
-            static_cast<int>(which) /* level */, range_del_agg);
+            static_cast<int>(which) /* level */, range_del_agg,
+            c->boundaries(which));
       }
     }
   }
@@ -4337,11 +4402,16 @@ void VersionSet::GetLiveFilesMetaData(std::vector<LiveFileMetaData>* metadata) {
         }
         filemetadata.name = MakeTableFileName("", file->fd.GetNumber());
         filemetadata.level = level;
-        filemetadata.size = file->fd.GetFileSize();
+        filemetadata.size = static_cast<size_t>(file->fd.GetFileSize());
         filemetadata.smallestkey = file->smallest.user_key().ToString();
         filemetadata.largestkey = file->largest.user_key().ToString();
         filemetadata.smallest_seqno = file->fd.smallest_seqno;
         filemetadata.largest_seqno = file->fd.largest_seqno;
+        filemetadata.num_reads_sampled = file->stats.num_reads_sampled.load(
+            std::memory_order_relaxed);
+        filemetadata.being_compacted = file->being_compacted;
+        filemetadata.num_entries = file->num_entries;
+        filemetadata.num_deletions = file->num_deletions;
         metadata->push_back(filemetadata);
       }
     }
diff --git a/3rdParty/rocksdb/v5.16.X/db/version_set.h b/3rdParty/rocksdb/v5.18.X/db/version_set.h
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/db/version_set.h
rename to 3rdParty/rocksdb/v5.18.X/db/version_set.h
index 4e3b2bec2d..ec9084beb6 100644
--- a/3rdParty/rocksdb/v5.16.X/db/version_set.h
+++ b/3rdParty/rocksdb/v5.18.X/db/version_set.h
@@ -34,7 +34,7 @@
 #include "db/dbformat.h"
 #include "db/file_indexer.h"
 #include "db/log_reader.h"
-#include "db/range_del_aggregator.h"
+#include "db/range_del_aggregator_v2.h"
 #include "db/read_callback.h"
 #include "db/table_cache.h"
 #include "db/version_builder.h"
@@ -188,9 +188,11 @@ class VersionStorageInfo {
       std::vector<FileMetaData*>* inputs,
       int hint_index = -1,        // index of overlap file
       int* file_index = nullptr,  // return index of overlap file
-      bool expand_range = true)   // if set, returns files which overlap the
-      const;                      // range and overlap each other. If false,
+      bool expand_range = true,   // if set, returns files which overlap the
+                                  // range and overlap each other. If false,
                                   // then just files intersecting the range
+      InternalKey** next_smallest = nullptr)  // if non-null, returns the
+      const;  // smallest key of next file not included
   void GetCleanInputsWithinInterval(
       int level, const InternalKey* begin,  // nullptr means before all keys
       const InternalKey* end,               // nullptr means after all keys
@@ -200,14 +202,15 @@ class VersionStorageInfo {
       const;
 
   void GetOverlappingInputsRangeBinarySearch(
-      int level,           // level > 0
+      int level,                 // level > 0
       const InternalKey* begin,  // nullptr means before all keys
       const InternalKey* end,    // nullptr means after all keys
       std::vector<FileMetaData*>* inputs,
       int hint_index,                // index of overlap file
       int* file_index,               // return index of overlap file
-      bool within_interval = false)  // if set, force the inputs within interval
-      const;
+      bool within_interval = false,  // if set, force the inputs within interval
+      InternalKey** next_smallest = nullptr)  // if non-null, returns the
+      const;  // smallest key of next file not included
 
   void ExtendFileRangeOverlappingInterval(
       int level,
@@ -306,6 +309,7 @@ class VersionStorageInfo {
   }
 
   int base_level() const { return base_level_; }
+  double level_multiplier() const { return level_multiplier_; }
 
   // REQUIRES: lock is held
   // Set the index that is used to offset into files_by_compaction_pri_ to find
@@ -404,9 +408,9 @@ class VersionStorageInfo {
   // @param last_level Level after which we check for overlap
   // @param last_l0_idx If `last_level == 0`, index of L0 file after which we
   //    check for overlap; otherwise, must be -1
-  bool RangeMightExistAfterSortedRun(const Slice& smallest_key,
-                                     const Slice& largest_key, int last_level,
-                                     int last_l0_idx);
+  bool RangeMightExistAfterSortedRun(const Slice& smallest_user_key,
+                                     const Slice& largest_user_key,
+                                     int last_level, int last_l0_idx);
 
  private:
   const InternalKeyComparator* internal_comparator_;
@@ -432,6 +436,8 @@ class VersionStorageInfo {
   // be empty. -1 if it is not level-compaction so it's not applicable.
   int base_level_;
 
+  double level_multiplier_;
+
   // A list for the same set of files that are stored in files_,
   // but files in each level are now sorted based on file
   // size. The file with the largest size is at the front.
@@ -532,11 +538,11 @@ class Version {
   // REQUIRES: This version has been saved (see VersionSet::SaveTo)
   void AddIterators(const ReadOptions&, const EnvOptions& soptions,
                     MergeIteratorBuilder* merger_iter_builder,
-                    RangeDelAggregator* range_del_agg);
+                    RangeDelAggregatorV2* range_del_agg);
 
   void AddIteratorsForLevel(const ReadOptions&, const EnvOptions& soptions,
                             MergeIteratorBuilder* merger_iter_builder,
-                            int level, RangeDelAggregator* range_del_agg);
+                            int level, RangeDelAggregatorV2* range_del_agg);
 
   Status OverlapWithLevelIterator(const ReadOptions&, const EnvOptions&,
                                   const Slice& smallest_user_key,
@@ -561,9 +567,10 @@ class Version {
   // REQUIRES: lock is not held
   void Get(const ReadOptions&, const LookupKey& key, PinnableSlice* value,
            Status* status, MergeContext* merge_context,
-           RangeDelAggregator* range_del_agg, bool* value_found = nullptr,
-           bool* key_exists = nullptr, SequenceNumber* seq = nullptr,
-           ReadCallback* callback = nullptr, bool* is_blob = nullptr);
+           SequenceNumber* max_covering_tombstone_seq,
+           bool* value_found = nullptr, bool* key_exists = nullptr,
+           SequenceNumber* seq = nullptr, ReadCallback* callback = nullptr,
+           bool* is_blob = nullptr);
 
   // Loads some stats information from files. Call without mutex held. It needs
   // to be called before applying the version to the version set.
@@ -598,7 +605,7 @@ class Version {
   // REQUIRES: lock is held
   // On success, *props will be populated with all SSTables' table properties.
   // The keys of `props` are the sst file name, the values of `props` are the
-  // tables' properties, represented as shared_ptr.
+  // tables' properties, represented as std::shared_ptr.
   Status GetPropertiesOfAllTables(TablePropertiesCollection* props);
   Status GetPropertiesOfAllTables(TablePropertiesCollection* props, int level);
   Status GetPropertiesOfTablesInRange(const Range* range, std::size_t n,
@@ -752,10 +759,14 @@ class VersionSet {
       InstrumentedMutex* mu, Directory* db_directory = nullptr,
       bool new_descriptor_log = false,
       const ColumnFamilyOptions* column_family_options = nullptr) {
-    std::vector<ColumnFamilyData*> cfds(1, column_family_data);
-    std::vector<MutableCFOptions> mutable_cf_options_list(1,
-                                                          mutable_cf_options);
-    std::vector<autovector<VersionEdit*>> edit_lists(1, {edit});
+    autovector<ColumnFamilyData*> cfds;
+    cfds.emplace_back(column_family_data);
+    autovector<const MutableCFOptions*> mutable_cf_options_list;
+    mutable_cf_options_list.emplace_back(&mutable_cf_options);
+    autovector<autovector<VersionEdit*>> edit_lists;
+    autovector<VersionEdit*> edit_list;
+    edit_list.emplace_back(edit);
+    edit_lists.emplace_back(edit_list);
     return LogAndApply(cfds, mutable_cf_options_list, edit_lists, mu,
                        db_directory, new_descriptor_log, column_family_options);
   }
@@ -767,10 +778,12 @@ class VersionSet {
       const autovector<VersionEdit*>& edit_list, InstrumentedMutex* mu,
       Directory* db_directory = nullptr, bool new_descriptor_log = false,
       const ColumnFamilyOptions* column_family_options = nullptr) {
-    std::vector<ColumnFamilyData*> cfds(1, column_family_data);
-    std::vector<MutableCFOptions> mutable_cf_options_list(1,
-                                                          mutable_cf_options);
-    std::vector<autovector<VersionEdit*>> edit_lists(1, edit_list);
+    autovector<ColumnFamilyData*> cfds;
+    cfds.emplace_back(column_family_data);
+    autovector<const MutableCFOptions*> mutable_cf_options_list;
+    mutable_cf_options_list.emplace_back(&mutable_cf_options);
+    autovector<autovector<VersionEdit*>> edit_lists;
+    edit_lists.emplace_back(edit_list);
     return LogAndApply(cfds, mutable_cf_options_list, edit_lists, mu,
                        db_directory, new_descriptor_log, column_family_options);
   }
@@ -778,12 +791,13 @@ class VersionSet {
   // The across-multi-cf batch version. If edit_lists contain more than
   // 1 version edits, caller must ensure that no edit in the []list is column
   // family manipulation.
-  Status LogAndApply(const std::vector<ColumnFamilyData*>& cfds,
-                     const std::vector<MutableCFOptions>& mutable_cf_options,
-                     const std::vector<autovector<VersionEdit*>>& edit_lists,
-                     InstrumentedMutex* mu, Directory* db_directory = nullptr,
-                     bool new_descriptor_log = false,
-                     const ColumnFamilyOptions* new_cf_options = nullptr);
+  Status LogAndApply(
+      const autovector<ColumnFamilyData*>& cfds,
+      const autovector<const MutableCFOptions*>& mutable_cf_options_list,
+      const autovector<autovector<VersionEdit*>>& edit_lists,
+      InstrumentedMutex* mu, Directory* db_directory = nullptr,
+      bool new_descriptor_log = false,
+      const ColumnFamilyOptions* new_cf_options = nullptr);
 
   // Recover the last saved descriptor from persistent storage.
   // If read_only == true, Recover() will not complain if some column families
@@ -921,7 +935,7 @@ class VersionSet {
   // Create an iterator that reads over the compaction inputs for "*c".
   // The caller should delete the iterator when no longer needed.
   InternalIterator* MakeInputIterator(
-      const Compaction* c, RangeDelAggregator* range_del_agg,
+      const Compaction* c, RangeDelAggregatorV2* range_del_agg,
       const EnvOptions& env_options_compactions);
 
   // Add all files listed in any live version to *live.
@@ -1039,7 +1053,7 @@ class VersionSet {
   uint64_t prev_log_number_;  // 0 or backing store for memtable being compacted
 
   // Opened lazily
-  unique_ptr<log::Writer> descriptor_log_;
+  std::unique_ptr<log::Writer> descriptor_log_;
 
   // generates a increasing version number for every new version
   uint64_t current_version_number_;
diff --git a/3rdParty/rocksdb/v5.16.X/db/version_set_test.cc b/3rdParty/rocksdb/v5.18.X/db/version_set_test.cc
similarity index 62%
rename from 3rdParty/rocksdb/v5.16.X/db/version_set_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/version_set_test.cc
index 7ad823cb42..c94ffb154c 100644
--- a/3rdParty/rocksdb/v5.16.X/db/version_set_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/version_set_test.cc
@@ -268,6 +268,93 @@ TEST_F(VersionStorageInfoTest, MaxBytesForLevelDynamicLargeLevel) {
   ASSERT_EQ(0, logger_->log_count);
 }
 
+TEST_F(VersionStorageInfoTest, MaxBytesForLevelDynamicWithLargeL0_1) {
+  ioptions_.level_compaction_dynamic_level_bytes = true;
+  mutable_cf_options_.max_bytes_for_level_base = 40000;
+  mutable_cf_options_.max_bytes_for_level_multiplier = 5;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+
+  Add(0, 1U, "1", "2", 10000U);
+  Add(0, 2U, "1", "2", 10000U);
+  Add(0, 3U, "1", "2", 10000U);
+
+  Add(5, 4U, "1", "2", 1286250U);
+  Add(4, 5U, "1", "2", 200000U);
+  Add(3, 6U, "1", "2", 40000U);
+  Add(2, 7U, "1", "2", 8000U);
+
+  vstorage_.CalculateBaseBytes(ioptions_, mutable_cf_options_);
+  ASSERT_EQ(0, logger_->log_count);
+  ASSERT_EQ(2, vstorage_.base_level());
+  // level multiplier should be 3.5
+  ASSERT_EQ(vstorage_.level_multiplier(), 5.0);
+  // Level size should be around 30,000, 105,000, 367,500
+  ASSERT_EQ(40000U, vstorage_.MaxBytesForLevel(2));
+  ASSERT_EQ(51450U, vstorage_.MaxBytesForLevel(3));
+  ASSERT_EQ(257250U, vstorage_.MaxBytesForLevel(4));
+}
+
+TEST_F(VersionStorageInfoTest, MaxBytesForLevelDynamicWithLargeL0_2) {
+  ioptions_.level_compaction_dynamic_level_bytes = true;
+  mutable_cf_options_.max_bytes_for_level_base = 10000;
+  mutable_cf_options_.max_bytes_for_level_multiplier = 5;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+
+  Add(0, 11U, "1", "2", 10000U);
+  Add(0, 12U, "1", "2", 10000U);
+  Add(0, 13U, "1", "2", 10000U);
+
+  Add(5, 4U, "1", "2", 1286250U);
+  Add(4, 5U, "1", "2", 200000U);
+  Add(3, 6U, "1", "2", 40000U);
+  Add(2, 7U, "1", "2", 8000U);
+
+  vstorage_.CalculateBaseBytes(ioptions_, mutable_cf_options_);
+  ASSERT_EQ(0, logger_->log_count);
+  ASSERT_EQ(2, vstorage_.base_level());
+  // level multiplier should be 3.5
+  ASSERT_LT(vstorage_.level_multiplier(), 3.6);
+  ASSERT_GT(vstorage_.level_multiplier(), 3.4);
+  // Level size should be around 30,000, 105,000, 367,500
+  ASSERT_EQ(30000U, vstorage_.MaxBytesForLevel(2));
+  ASSERT_LT(vstorage_.MaxBytesForLevel(3), 110000U);
+  ASSERT_GT(vstorage_.MaxBytesForLevel(3), 100000U);
+  ASSERT_LT(vstorage_.MaxBytesForLevel(4), 370000U);
+  ASSERT_GT(vstorage_.MaxBytesForLevel(4), 360000U);
+}
+
+TEST_F(VersionStorageInfoTest, MaxBytesForLevelDynamicWithLargeL0_3) {
+  ioptions_.level_compaction_dynamic_level_bytes = true;
+  mutable_cf_options_.max_bytes_for_level_base = 10000;
+  mutable_cf_options_.max_bytes_for_level_multiplier = 5;
+  mutable_cf_options_.level0_file_num_compaction_trigger = 2;
+
+  Add(0, 11U, "1", "2", 5000U);
+  Add(0, 12U, "1", "2", 5000U);
+  Add(0, 13U, "1", "2", 5000U);
+  Add(0, 14U, "1", "2", 5000U);
+  Add(0, 15U, "1", "2", 5000U);
+  Add(0, 16U, "1", "2", 5000U);
+
+  Add(5, 4U, "1", "2", 1286250U);
+  Add(4, 5U, "1", "2", 200000U);
+  Add(3, 6U, "1", "2", 40000U);
+  Add(2, 7U, "1", "2", 8000U);
+
+  vstorage_.CalculateBaseBytes(ioptions_, mutable_cf_options_);
+  ASSERT_EQ(0, logger_->log_count);
+  ASSERT_EQ(2, vstorage_.base_level());
+  // level multiplier should be 3.5
+  ASSERT_LT(vstorage_.level_multiplier(), 3.6);
+  ASSERT_GT(vstorage_.level_multiplier(), 3.4);
+  // Level size should be around 30,000, 105,000, 367,500
+  ASSERT_EQ(30000U, vstorage_.MaxBytesForLevel(2));
+  ASSERT_LT(vstorage_.MaxBytesForLevel(3), 110000U);
+  ASSERT_GT(vstorage_.MaxBytesForLevel(3), 100000U);
+  ASSERT_LT(vstorage_.MaxBytesForLevel(4), 370000U);
+  ASSERT_GT(vstorage_.MaxBytesForLevel(4), 360000U);
+}
+
 TEST_F(VersionStorageInfoTest, EstimateLiveDataSize) {
   // Test whether the overlaps are detected as expected
   Add(1, 1U, "4", "7", 1U);  // Perfect overlap with last level
@@ -518,9 +605,9 @@ TEST_F(FindLevelFileTest, LevelOverlappingFiles) {
   ASSERT_TRUE(Overlaps("600", "700"));
 }
 
-class ManifestWriterTest : public testing::Test {
+class VersionSetTest : public testing::Test {
  public:
-  ManifestWriterTest()
+  VersionSetTest()
       : env_(Env::Default()),
         dbname_(test::PerThreadDBPath("version_set_test")),
         db_options_(),
@@ -537,8 +624,12 @@ class ManifestWriterTest : public testing::Test {
                                       std::numeric_limits<uint64_t>::max());
   }
 
-  // Create DB with 3 column families.
-  void NewDB() {
+  void PrepareManifest(std::vector<ColumnFamilyDescriptor>* column_families,
+                       SequenceNumber* last_seqno,
+                       std::unique_ptr<log::Writer>* log_writer) {
+    assert(column_families != nullptr);
+    assert(last_seqno != nullptr);
+    assert(log_writer != nullptr);
     VersionEdit new_db;
     new_db.SetLogNumber(0);
     new_db.SetNextFile(2);
@@ -559,41 +650,50 @@ class ManifestWriterTest : public testing::Test {
       new_cf.SetLastSequence(last_seq++);
       new_cfs.emplace_back(new_cf);
     }
+    *last_seqno = last_seq;
 
     const std::string manifest = DescriptorFileName(dbname_, 1);
-    unique_ptr<WritableFile> file;
+    std::unique_ptr<WritableFile> file;
     Status s = env_->NewWritableFile(
         manifest, &file, env_->OptimizeForManifestWrite(env_options_));
     ASSERT_OK(s);
-    unique_ptr<WritableFileWriter> file_writer(
-        new WritableFileWriter(std::move(file), env_options_));
+    std::unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(file), manifest, env_options_));
     {
-      log::Writer log(std::move(file_writer), 0, false);
+      log_writer->reset(new log::Writer(std::move(file_writer), 0, false));
       std::string record;
       new_db.EncodeTo(&record);
-      s = log.AddRecord(record);
+      s = (*log_writer)->AddRecord(record);
       for (const auto& e : new_cfs) {
+        record.clear();
         e.EncodeTo(&record);
-        s = log.AddRecord(record);
+        s = (*log_writer)->AddRecord(record);
         ASSERT_OK(s);
       }
     }
     ASSERT_OK(s);
-    // Make "CURRENT" file point to the new manifest file.
-    s = SetCurrentFile(env_, dbname_, 1, nullptr);
 
-    std::vector<ColumnFamilyDescriptor> column_families;
     cf_options_.table_factory = mock_table_factory_;
     for (const auto& cf_name : cf_names) {
-      column_families.emplace_back(cf_name, cf_options_);
+      column_families->emplace_back(cf_name, cf_options_);
     }
+  }
+
+  // Create DB with 3 column families.
+  void NewDB() {
+    std::vector<ColumnFamilyDescriptor> column_families;
+    SequenceNumber last_seqno;
+    std::unique_ptr<log::Writer> log_writer;
+
+    PrepareManifest(&column_families, &last_seqno, &log_writer);
+    log_writer.reset();
+    // Make "CURRENT" file point to the new manifest file.
+    Status s = SetCurrentFile(env_, dbname_, 1, nullptr);
+    ASSERT_OK(s);
 
     EXPECT_OK(versions_->Recover(column_families, false));
-    EXPECT_EQ(kInitialNumOfCfs,
+    EXPECT_EQ(column_families.size(),
               versions_->GetColumnFamilySet()->NumberOfColumnFamilies());
-    for (auto cfd : *versions_->GetColumnFamilySet()) {
-      cfds_.emplace_back(cfd);
-    }
   }
 
   Env* env_;
@@ -605,25 +705,32 @@ class ManifestWriterTest : public testing::Test {
   std::shared_ptr<Cache> table_cache_;
   WriteController write_controller_;
   WriteBufferManager write_buffer_manager_;
-  std::unique_ptr<VersionSet> versions_;
+  std::shared_ptr<VersionSet> versions_;
   InstrumentedMutex mutex_;
   std::atomic<bool> shutting_down_;
   std::shared_ptr<mock::MockTableFactory> mock_table_factory_;
-  std::vector<ColumnFamilyData*> cfds_;
 };
 
-TEST_F(ManifestWriterTest, SameColumnFamilyGroupCommit) {
+TEST_F(VersionSetTest, SameColumnFamilyGroupCommit) {
   NewDB();
   const int kGroupSize = 5;
-  std::vector<VersionEdit> edits(kGroupSize);
-  std::vector<ColumnFamilyData*> cfds(kGroupSize, cfds_[0]);
-  std::vector<MutableCFOptions> all_mutable_cf_options(kGroupSize,
-                                                       mutable_cf_options_);
-  std::vector<autovector<VersionEdit*>> edit_lists(kGroupSize);
+  autovector<VersionEdit> edits;
   for (int i = 0; i != kGroupSize; ++i) {
-    edit_lists[i].emplace_back(&edits[i]);
+    edits.emplace_back(VersionEdit());
+  }
+  autovector<ColumnFamilyData*> cfds;
+  autovector<const MutableCFOptions*> all_mutable_cf_options;
+  autovector<autovector<VersionEdit*>> edit_lists;
+  for (int i = 0; i != kGroupSize; ++i) {
+    cfds.emplace_back(versions_->GetColumnFamilySet()->GetDefault());
+    all_mutable_cf_options.emplace_back(&mutable_cf_options_);
+    autovector<VersionEdit*> edit_list;
+    edit_list.emplace_back(&edits[i]);
+    edit_lists.emplace_back(edit_list);
   }
 
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
   int count = 0;
   SyncPoint::GetInstance()->SetCallBack(
       "VersionSet::ProcessManifestWrites:SameColumnFamily", [&](void* arg) {
@@ -639,6 +746,218 @@ TEST_F(ManifestWriterTest, SameColumnFamilyGroupCommit) {
   EXPECT_OK(s);
   EXPECT_EQ(kGroupSize - 1, count);
 }
+
+TEST_F(VersionSetTest, HandleValidAtomicGroup) {
+  std::vector<ColumnFamilyDescriptor> column_families;
+  SequenceNumber last_seqno;
+  std::unique_ptr<log::Writer> log_writer;
+  PrepareManifest(&column_families, &last_seqno, &log_writer);
+
+  // Append multiple version edits that form an atomic group
+  const int kAtomicGroupSize = 3;
+  std::vector<VersionEdit> edits(kAtomicGroupSize);
+  int remaining = kAtomicGroupSize;
+  for (size_t i = 0; i != edits.size(); ++i) {
+    edits[i].SetLogNumber(0);
+    edits[i].SetNextFile(2);
+    edits[i].MarkAtomicGroup(--remaining);
+    edits[i].SetLastSequence(last_seqno++);
+  }
+  Status s;
+  for (const auto& edit : edits) {
+    std::string record;
+    edit.EncodeTo(&record);
+    s = log_writer->AddRecord(record);
+    ASSERT_OK(s);
+  }
+  log_writer.reset();
+
+  s = SetCurrentFile(env_, dbname_, 1, nullptr);
+  ASSERT_OK(s);
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  bool first_in_atomic_group = false;
+  bool last_in_atomic_group = false;
+
+  SyncPoint::GetInstance()->SetCallBack(
+      "VersionSet::Recover:FirstInAtomicGroup", [&](void* arg) {
+        VersionEdit* e = reinterpret_cast<VersionEdit*>(arg);
+        EXPECT_EQ(edits.front().DebugString(),
+                  e->DebugString());  // compare based on value
+        first_in_atomic_group = true;
+      });
+  SyncPoint::GetInstance()->SetCallBack(
+      "VersionSet::Recover:LastInAtomicGroup", [&](void* arg) {
+        VersionEdit* e = reinterpret_cast<VersionEdit*>(arg);
+        EXPECT_EQ(edits.back().DebugString(),
+                  e->DebugString());  // compare based on value
+        EXPECT_TRUE(first_in_atomic_group);
+        last_in_atomic_group = true;
+      });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  EXPECT_OK(versions_->Recover(column_families, false));
+  EXPECT_EQ(column_families.size(),
+            versions_->GetColumnFamilySet()->NumberOfColumnFamilies());
+  EXPECT_TRUE(first_in_atomic_group);
+  EXPECT_TRUE(last_in_atomic_group);
+}
+
+TEST_F(VersionSetTest, HandleIncompleteTrailingAtomicGroup) {
+  std::vector<ColumnFamilyDescriptor> column_families;
+  SequenceNumber last_seqno;
+  std::unique_ptr<log::Writer> log_writer;
+  PrepareManifest(&column_families, &last_seqno, &log_writer);
+
+  // Append multiple version edits that form an atomic group
+  const int kAtomicGroupSize = 4;
+  const int kNumberOfPersistedVersionEdits = kAtomicGroupSize - 1;
+  std::vector<VersionEdit> edits(kNumberOfPersistedVersionEdits);
+  int remaining = kAtomicGroupSize;
+  for (size_t i = 0; i != edits.size(); ++i) {
+    edits[i].SetLogNumber(0);
+    edits[i].SetNextFile(2);
+    edits[i].MarkAtomicGroup(--remaining);
+    edits[i].SetLastSequence(last_seqno++);
+  }
+  Status s;
+  for (const auto& edit : edits) {
+    std::string record;
+    edit.EncodeTo(&record);
+    s = log_writer->AddRecord(record);
+    ASSERT_OK(s);
+  }
+  log_writer.reset();
+
+  s = SetCurrentFile(env_, dbname_, 1, nullptr);
+  ASSERT_OK(s);
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  bool first_in_atomic_group = false;
+  bool last_in_atomic_group = false;
+  size_t num = 0;
+
+  SyncPoint::GetInstance()->SetCallBack(
+      "VersionSet::Recover:FirstInAtomicGroup", [&](void* arg) {
+        VersionEdit* e = reinterpret_cast<VersionEdit*>(arg);
+        EXPECT_EQ(edits.front().DebugString(),
+                  e->DebugString());  // compare based on value
+        first_in_atomic_group = true;
+      });
+  SyncPoint::GetInstance()->SetCallBack(
+      "VersionSet::Recover:LastInAtomicGroup",
+      [&](void* /* arg */) { last_in_atomic_group = true; });
+  SyncPoint::GetInstance()->SetCallBack("VersionSet::Recover:AtomicGroup",
+                                        [&](void* /* arg */) { ++num; });
+  SyncPoint::GetInstance()->EnableProcessing();
+
+  EXPECT_OK(versions_->Recover(column_families, false));
+  EXPECT_EQ(column_families.size(),
+            versions_->GetColumnFamilySet()->NumberOfColumnFamilies());
+  EXPECT_TRUE(first_in_atomic_group);
+  EXPECT_FALSE(last_in_atomic_group);
+  EXPECT_EQ(kNumberOfPersistedVersionEdits, num);
+}
+
+TEST_F(VersionSetTest, HandleCorruptedAtomicGroup) {
+  std::vector<ColumnFamilyDescriptor> column_families;
+  SequenceNumber last_seqno;
+  std::unique_ptr<log::Writer> log_writer;
+  PrepareManifest(&column_families, &last_seqno, &log_writer);
+
+  // Append multiple version edits that form an atomic group
+  const int kAtomicGroupSize = 4;
+  std::vector<VersionEdit> edits(kAtomicGroupSize);
+  int remaining = kAtomicGroupSize;
+  for (size_t i = 0; i != edits.size(); ++i) {
+    edits[i].SetLogNumber(0);
+    edits[i].SetNextFile(2);
+    if (i != (kAtomicGroupSize / 2)) {
+      edits[i].MarkAtomicGroup(--remaining);
+    }
+    edits[i].SetLastSequence(last_seqno++);
+  }
+  Status s;
+  for (const auto& edit : edits) {
+    std::string record;
+    edit.EncodeTo(&record);
+    s = log_writer->AddRecord(record);
+    ASSERT_OK(s);
+  }
+  log_writer.reset();
+
+  s = SetCurrentFile(env_, dbname_, 1, nullptr);
+  ASSERT_OK(s);
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  bool mixed = false;
+  SyncPoint::GetInstance()->SetCallBack(
+      "VersionSet::Recover:AtomicGroupMixedWithNormalEdits", [&](void* arg) {
+        VersionEdit* e = reinterpret_cast<VersionEdit*>(arg);
+        EXPECT_EQ(edits[kAtomicGroupSize / 2].DebugString(), e->DebugString());
+        mixed = true;
+      });
+  SyncPoint::GetInstance()->EnableProcessing();
+  EXPECT_NOK(versions_->Recover(column_families, false));
+  EXPECT_EQ(column_families.size(),
+            versions_->GetColumnFamilySet()->NumberOfColumnFamilies());
+  EXPECT_TRUE(mixed);
+}
+
+TEST_F(VersionSetTest, HandleIncorrectAtomicGroupSize) {
+  std::vector<ColumnFamilyDescriptor> column_families;
+  SequenceNumber last_seqno;
+  std::unique_ptr<log::Writer> log_writer;
+  PrepareManifest(&column_families, &last_seqno, &log_writer);
+
+  // Append multiple version edits that form an atomic group
+  const int kAtomicGroupSize = 4;
+  std::vector<VersionEdit> edits(kAtomicGroupSize);
+  int remaining = kAtomicGroupSize;
+  for (size_t i = 0; i != edits.size(); ++i) {
+    edits[i].SetLogNumber(0);
+    edits[i].SetNextFile(2);
+    if (i != 1) {
+      edits[i].MarkAtomicGroup(--remaining);
+    } else {
+      edits[i].MarkAtomicGroup(remaining--);
+    }
+    edits[i].SetLastSequence(last_seqno++);
+  }
+  Status s;
+  for (const auto& edit : edits) {
+    std::string record;
+    edit.EncodeTo(&record);
+    s = log_writer->AddRecord(record);
+    ASSERT_OK(s);
+  }
+  log_writer.reset();
+
+  s = SetCurrentFile(env_, dbname_, 1, nullptr);
+  ASSERT_OK(s);
+
+  SyncPoint::GetInstance()->DisableProcessing();
+  SyncPoint::GetInstance()->ClearAllCallBacks();
+
+  bool incorrect_group_size = false;
+  SyncPoint::GetInstance()->SetCallBack(
+      "VersionSet::Recover:IncorrectAtomicGroupSize", [&](void* arg) {
+        VersionEdit* e = reinterpret_cast<VersionEdit*>(arg);
+        EXPECT_EQ(edits[1].DebugString(), e->DebugString());
+        incorrect_group_size = true;
+      });
+  SyncPoint::GetInstance()->EnableProcessing();
+  EXPECT_NOK(versions_->Recover(column_families, false));
+  EXPECT_EQ(column_families.size(),
+            versions_->GetColumnFamilySet()->NumberOfColumnFamilies());
+  EXPECT_TRUE(incorrect_group_size);
+}
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
diff --git a/3rdParty/rocksdb/v5.16.X/db/wal_manager.cc b/3rdParty/rocksdb/v5.18.X/db/wal_manager.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/db/wal_manager.cc
rename to 3rdParty/rocksdb/v5.18.X/db/wal_manager.cc
index 3b0ef7ca58..667ecae41a 100644
--- a/3rdParty/rocksdb/v5.16.X/db/wal_manager.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/wal_manager.cc
@@ -237,7 +237,7 @@ void WalManager::PurgeObsoleteWALFiles() {
   }
 
   size_t const files_keep_num =
-      db_options_.wal_size_limit_mb * 1024 * 1024 / log_file_size;
+      static_cast<size_t>(db_options_.wal_size_limit_mb * 1024 * 1024 / log_file_size);
   if (log_files_num <= files_keep_num) {
     return;
   }
@@ -352,7 +352,7 @@ Status WalManager::RetainProbableWalFiles(VectorLogPtr& all_logs,
   // Binary Search. avoid opening all files.
   while (end >= start) {
     int64_t mid = start + (end - start) / 2;  // Avoid overflow.
-    SequenceNumber current_seq_num = all_logs.at(mid)->StartSequence();
+    SequenceNumber current_seq_num = all_logs.at(static_cast<size_t>(mid))->StartSequence();
     if (current_seq_num == target) {
       end = mid;
       break;
@@ -363,7 +363,7 @@ Status WalManager::RetainProbableWalFiles(VectorLogPtr& all_logs,
     }
   }
   // end could be -ve.
-  size_t start_index = std::max(static_cast<int64_t>(0), end);
+  size_t start_index = static_cast<size_t>(std::max(static_cast<int64_t>(0), end));
   // The last wal file is always included
   all_logs.erase(all_logs.begin(), all_logs.begin() + start_index);
   return Status::OK();
@@ -443,7 +443,7 @@ Status WalManager::ReadFirstLine(const std::string& fname,
   std::unique_ptr<SequentialFile> file;
   Status status = env_->NewSequentialFile(
       fname, &file, env_->OptimizeForLogRead(env_options_));
-  unique_ptr<SequentialFileReader> file_reader(
+  std::unique_ptr<SequentialFileReader> file_reader(
       new SequentialFileReader(std::move(file), fname));
 
   if (!status.ok()) {
@@ -457,7 +457,7 @@ Status WalManager::ReadFirstLine(const std::string& fname,
   reporter.status = &status;
   reporter.ignore_error = !db_options_.paranoid_checks;
   log::Reader reader(db_options_.info_log, std::move(file_reader), &reporter,
-                     true /*checksum*/, 0 /*initial_offset*/, number);
+                     true /*checksum*/, number, false /* retry_after_eof */);
   std::string scratch;
   Slice record;
 
diff --git a/3rdParty/rocksdb/v5.16.X/db/wal_manager.h b/3rdParty/rocksdb/v5.18.X/db/wal_manager.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/wal_manager.h
rename to 3rdParty/rocksdb/v5.18.X/db/wal_manager.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/wal_manager_test.cc b/3rdParty/rocksdb/v5.18.X/db/wal_manager_test.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/db/wal_manager_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/wal_manager_test.cc
index 3bcc19888d..379f12f52a 100644
--- a/3rdParty/rocksdb/v5.16.X/db/wal_manager_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/wal_manager_test.cc
@@ -76,10 +76,10 @@ class WalManagerTest : public testing::Test {
   void RollTheLog(bool /*archived*/) {
     current_log_number_++;
     std::string fname = ArchivedLogFileName(dbname_, current_log_number_);
-    unique_ptr<WritableFile> file;
+    std::unique_ptr<WritableFile> file;
     ASSERT_OK(env_->NewWritableFile(fname, &file, env_options_));
-    unique_ptr<WritableFileWriter> file_writer(
-        new WritableFileWriter(std::move(file), env_options_));
+    std::unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(file), fname, env_options_));
     current_log_writer_.reset(new log::Writer(std::move(file_writer), 0, false));
   }
 
@@ -94,7 +94,7 @@ class WalManagerTest : public testing::Test {
 
   std::unique_ptr<TransactionLogIterator> OpenTransactionLogIter(
       const SequenceNumber seq) {
-    unique_ptr<TransactionLogIterator> iter;
+    std::unique_ptr<TransactionLogIterator> iter;
     Status status = wal_manager_->GetUpdatesSince(
         seq, &iter, TransactionLogIterator::ReadOptions(), versions_.get());
     EXPECT_OK(status);
@@ -118,7 +118,7 @@ class WalManagerTest : public testing::Test {
 TEST_F(WalManagerTest, ReadFirstRecordCache) {
   Init();
   std::string path = dbname_ + "/000001.log";
-  unique_ptr<WritableFile> file;
+  std::unique_ptr<WritableFile> file;
   ASSERT_OK(env_->NewWritableFile(path, &file, EnvOptions()));
 
   SequenceNumber s;
@@ -129,8 +129,8 @@ TEST_F(WalManagerTest, ReadFirstRecordCache) {
       wal_manager_->TEST_ReadFirstRecord(kAliveLogFile, 1 /* number */, &s));
   ASSERT_EQ(s, 0U);
 
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(file), path, EnvOptions()));
   log::Writer writer(std::move(file_writer), 1,
                      db_options_.recycle_log_file_num > 0);
   WriteBatch batch;
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_batch.cc b/3rdParty/rocksdb/v5.18.X/db/write_batch.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/write_batch.cc
rename to 3rdParty/rocksdb/v5.18.X/db/write_batch.cc
index d7003481dc..19ec243592 100644
--- a/3rdParty/rocksdb/v5.16.X/db/write_batch.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/write_batch.cc
@@ -414,12 +414,13 @@ Status WriteBatch::Iterate(Handler* handler) const {
   char tag = 0;
   uint32_t column_family = 0;  // default
   bool last_was_try_again = false;
-  bool handlerContinue = true;
+  bool handler_continue = true;
   while (((s.ok() && !input.empty()) || UNLIKELY(s.IsTryAgain()))) {
-    if (!(handlerContinue = handler->Continue())) {
+    handler_continue = handler->Continue();
+    if (!handler_continue) {
       break;
     }
-    
+
     if (LIKELY(!s.IsTryAgain())) {
       last_was_try_again = false;
       tag = 0;
@@ -587,7 +588,7 @@ Status WriteBatch::Iterate(Handler* handler) const {
   if (!s.ok()) {
     return s;
   }
-  if (handlerContinue && found != WriteBatchInternal::Count(this)) {
+  if (handler_continue && found != WriteBatchInternal::Count(this)) {
     return Status::Corruption("WriteBatch has wrong count");
   } else {
     return Status::OK();
@@ -1052,7 +1053,7 @@ class MemTableInserter : public WriteBatch::Handler {
   // a map is too expensive in the Write() path as they
   // cause memory allocations though unused.
   // Make creation optional but do not incur
-  // unique_ptr additional allocation
+  // std::unique_ptr additional allocation
   using MemPostInfoMap = std::map<MemTable*, MemTablePostProcessInfo>;
   using PostMapType = std::aligned_storage<sizeof(MemPostInfoMap)>::type;
   PostMapType mem_post_info_map_;
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_batch_base.cc b/3rdParty/rocksdb/v5.18.X/db/write_batch_base.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/write_batch_base.cc
rename to 3rdParty/rocksdb/v5.18.X/db/write_batch_base.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_batch_internal.h b/3rdParty/rocksdb/v5.18.X/db/write_batch_internal.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/write_batch_internal.h
rename to 3rdParty/rocksdb/v5.18.X/db/write_batch_internal.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_batch_test.cc b/3rdParty/rocksdb/v5.18.X/db/write_batch_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/db/write_batch_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/write_batch_test.cc
index 84b866a316..52c0fab24f 100644
--- a/3rdParty/rocksdb/v5.16.X/db/write_batch_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/write_batch_test.cc
@@ -51,7 +51,8 @@ static std::string PrintContents(WriteBatch* b) {
       iter = mem->NewIterator(ReadOptions(), &arena);
       arena_iter_guard.set(iter);
     } else {
-      iter = mem->NewRangeTombstoneIterator(ReadOptions());
+      iter = mem->NewRangeTombstoneIterator(ReadOptions(),
+                                            kMaxSequenceNumber /* read_seq */);
       iter_guard.reset(iter);
     }
     if (iter == nullptr) {
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_callback.h b/3rdParty/rocksdb/v5.18.X/db/write_callback.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/write_callback.h
rename to 3rdParty/rocksdb/v5.18.X/db/write_callback.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_callback_test.cc b/3rdParty/rocksdb/v5.18.X/db/write_callback_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/write_callback_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/write_callback_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_controller.cc b/3rdParty/rocksdb/v5.18.X/db/write_controller.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/write_controller.cc
rename to 3rdParty/rocksdb/v5.18.X/db/write_controller.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_controller.h b/3rdParty/rocksdb/v5.18.X/db/write_controller.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/write_controller.h
rename to 3rdParty/rocksdb/v5.18.X/db/write_controller.h
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_controller_test.cc b/3rdParty/rocksdb/v5.18.X/db/write_controller_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/db/write_controller_test.cc
rename to 3rdParty/rocksdb/v5.18.X/db/write_controller_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_thread.cc b/3rdParty/rocksdb/v5.18.X/db/write_thread.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/db/write_thread.cc
rename to 3rdParty/rocksdb/v5.18.X/db/write_thread.cc
index 6eb140b6bc..835992c8fc 100644
--- a/3rdParty/rocksdb/v5.16.X/db/write_thread.cc
+++ b/3rdParty/rocksdb/v5.18.X/db/write_thread.cc
@@ -24,7 +24,10 @@ WriteThread::WriteThread(const ImmutableDBOptions& db_options)
       enable_pipelined_write_(db_options.enable_pipelined_write),
       newest_writer_(nullptr),
       newest_memtable_writer_(nullptr),
-      last_sequence_(0) {}
+      last_sequence_(0),
+      write_stall_dummy_(),
+      stall_mu_(),
+      stall_cv_(&stall_mu_) {}
 
 uint8_t WriteThread::BlockingAwaitState(Writer* w, uint8_t goal_mask) {
   // We're going to block.  Lazily create the mutex.  We guarantee
@@ -178,6 +181,7 @@ uint8_t WriteThread::AwaitState(Writer* w, uint8_t goal_mask,
   }
 
   if ((state & goal_mask) == 0) {
+    TEST_SYNC_POINT_CALLBACK("WriteThread::AwaitState:BlockingWaiting", w);
     state = BlockingAwaitState(w, goal_mask);
   }
 
@@ -219,6 +223,28 @@ bool WriteThread::LinkOne(Writer* w, std::atomic<Writer*>* newest_writer) {
   assert(w->state == STATE_INIT);
   Writer* writers = newest_writer->load(std::memory_order_relaxed);
   while (true) {
+    // If write stall in effect, and w->no_slowdown is not true,
+    // block here until stall is cleared. If its true, then return
+    // immediately
+    if (writers == &write_stall_dummy_) {
+      if (w->no_slowdown) {
+        w->status = Status::Incomplete("Write stall");
+        SetState(w, STATE_COMPLETED);
+        return false;
+      }
+      // Since no_slowdown is false, wait here to be notified of the write
+      // stall clearing
+      {
+        MutexLock lock(&stall_mu_);
+        writers = newest_writer->load(std::memory_order_relaxed);
+        if (writers == &write_stall_dummy_) {
+          stall_cv_.Wait();
+          // Load newest_writers_ again since it may have changed
+          writers = newest_writer->load(std::memory_order_relaxed);
+          continue;
+        }
+      }
+    }
     w->link_older = writers;
     if (newest_writer->compare_exchange_weak(writers, w)) {
       return (writers == nullptr);
@@ -303,12 +329,44 @@ void WriteThread::CompleteFollower(Writer* w, WriteGroup& write_group) {
   SetState(w, STATE_COMPLETED);
 }
 
+void WriteThread::BeginWriteStall() {
+  LinkOne(&write_stall_dummy_, &newest_writer_);
+
+  // Walk writer list until w->write_group != nullptr. The current write group
+  // will not have a mix of slowdown/no_slowdown, so its ok to stop at that
+  // point
+  Writer* w = write_stall_dummy_.link_older;
+  Writer* prev = &write_stall_dummy_;
+  while (w != nullptr && w->write_group == nullptr) {
+    if (w->no_slowdown) {
+      prev->link_older = w->link_older;
+      w->status = Status::Incomplete("Write stall");
+      SetState(w, STATE_COMPLETED);
+      w = prev->link_older;
+    } else {
+      prev = w;
+      w = w->link_older;
+    }
+  }
+}
+
+void WriteThread::EndWriteStall() {
+  MutexLock lock(&stall_mu_);
+
+  assert(newest_writer_.load(std::memory_order_relaxed) == &write_stall_dummy_);
+  newest_writer_.exchange(write_stall_dummy_.link_older);
+
+  // Wake up writers
+  stall_cv_.SignalAll();
+}
+
 static WriteThread::AdaptationContext jbg_ctx("JoinBatchGroup");
 void WriteThread::JoinBatchGroup(Writer* w) {
   TEST_SYNC_POINT_CALLBACK("WriteThread::JoinBatchGroup:Start", w);
   assert(w->batch != nullptr);
 
   bool linked_as_leader = LinkOne(w, &newest_writer_);
+
   if (linked_as_leader) {
     SetState(w, STATE_GROUP_LEADER);
   }
diff --git a/3rdParty/rocksdb/v5.16.X/db/write_thread.h b/3rdParty/rocksdb/v5.18.X/db/write_thread.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/db/write_thread.h
rename to 3rdParty/rocksdb/v5.18.X/db/write_thread.h
index 31190199b4..a3802c996b 100644
--- a/3rdParty/rocksdb/v5.16.X/db/write_thread.h
+++ b/3rdParty/rocksdb/v5.18.X/db/write_thread.h
@@ -342,6 +342,13 @@ class WriteThread {
     return last_sequence_;
   }
 
+  // Insert a dummy writer at the tail of the write queue to indicate a write
+  // stall, and fail any writers in the queue with no_slowdown set to true
+  void BeginWriteStall();
+
+  // Remove the dummy writer and wake up waiting writers
+  void EndWriteStall();
+
  private:
   // See AwaitState.
   const uint64_t max_yield_usec_;
@@ -365,6 +372,17 @@ class WriteThread {
   // is not necessary visible to reads because the writer can be ongoing.
   SequenceNumber last_sequence_;
 
+  // A dummy writer to indicate a write stall condition. This will be inserted
+  // at the tail of the writer queue by the leader, so newer writers can just
+  // check for this and bail
+  Writer write_stall_dummy_;
+
+  // Mutex and condvar for writers to block on a write stall. During a write
+  // stall, writers with no_slowdown set to false will wait on this rather
+  // on the writer queue
+  port::Mutex stall_mu_;
+  port::CondVar stall_cv_;
+
   // Waits for w->state & goal_mask using w->StateMutex().  Returns
   // the state that satisfies goal_mask.
   uint8_t BlockingAwaitState(Writer* w, uint8_t goal_mask);
diff --git a/3rdParty/rocksdb/v5.16.X/docs/.gitignore b/3rdParty/rocksdb/v5.18.X/docs/.gitignore
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/.gitignore
rename to 3rdParty/rocksdb/v5.18.X/docs/.gitignore
diff --git a/3rdParty/rocksdb/v5.16.X/docs/CNAME b/3rdParty/rocksdb/v5.18.X/docs/CNAME
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/CNAME
rename to 3rdParty/rocksdb/v5.18.X/docs/CNAME
diff --git a/3rdParty/rocksdb/v5.16.X/docs/CONTRIBUTING.md b/3rdParty/rocksdb/v5.18.X/docs/CONTRIBUTING.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/CONTRIBUTING.md
rename to 3rdParty/rocksdb/v5.18.X/docs/CONTRIBUTING.md
diff --git a/3rdParty/rocksdb/v5.16.X/docs/Gemfile b/3rdParty/rocksdb/v5.18.X/docs/Gemfile
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/Gemfile
rename to 3rdParty/rocksdb/v5.18.X/docs/Gemfile
diff --git a/3rdParty/rocksdb/v5.16.X/docs/Gemfile.lock b/3rdParty/rocksdb/v5.18.X/docs/Gemfile.lock
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/docs/Gemfile.lock
rename to 3rdParty/rocksdb/v5.18.X/docs/Gemfile.lock
index 33f4dbc447..78dc919a98 100644
--- a/3rdParty/rocksdb/v5.16.X/docs/Gemfile.lock
+++ b/3rdParty/rocksdb/v5.18.X/docs/Gemfile.lock
@@ -25,7 +25,7 @@ GEM
     github-pages (104)
       activesupport (= 4.2.7)
       github-pages-health-check (= 1.2.0)
-      jekyll (= 3.3.0)
+      jekyll (>= 3.8.4)
       jekyll-avatar (= 0.4.2)
       jekyll-coffeescript (= 1.0.1)
       jekyll-feed (= 0.8.0)
@@ -56,7 +56,7 @@ GEM
       activesupport (>= 2)
       nokogiri (~> 1.8.2)
     i18n (0.7.0)
-    jekyll (3.3.0)
+    jekyll (3.8.4)
       addressable (~> 2.4)
       colorator (~> 1.0)
       jekyll-sass-converter (~> 1.0)
diff --git a/3rdParty/rocksdb/v5.16.X/docs/LICENSE-DOCUMENTATION b/3rdParty/rocksdb/v5.18.X/docs/LICENSE-DOCUMENTATION
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/LICENSE-DOCUMENTATION
rename to 3rdParty/rocksdb/v5.18.X/docs/LICENSE-DOCUMENTATION
diff --git a/3rdParty/rocksdb/v5.16.X/docs/README.md b/3rdParty/rocksdb/v5.18.X/docs/README.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/README.md
rename to 3rdParty/rocksdb/v5.18.X/docs/README.md
diff --git a/3rdParty/rocksdb/v5.16.X/docs/TEMPLATE-INFORMATION.md b/3rdParty/rocksdb/v5.18.X/docs/TEMPLATE-INFORMATION.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/TEMPLATE-INFORMATION.md
rename to 3rdParty/rocksdb/v5.18.X/docs/TEMPLATE-INFORMATION.md
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_config.yml b/3rdParty/rocksdb/v5.18.X/docs/_config.yml
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_config.yml
rename to 3rdParty/rocksdb/v5.18.X/docs/_config.yml
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_data/authors.yml b/3rdParty/rocksdb/v5.18.X/docs/_data/authors.yml
similarity index 86%
rename from 3rdParty/rocksdb/v5.16.X/docs/_data/authors.yml
rename to 3rdParty/rocksdb/v5.18.X/docs/_data/authors.yml
index b3ed49e539..13225be9df 100644
--- a/3rdParty/rocksdb/v5.16.X/docs/_data/authors.yml
+++ b/3rdParty/rocksdb/v5.18.X/docs/_data/authors.yml
@@ -51,7 +51,11 @@ IslamAbdelRahman:
 
 ajkr:
   full_name: Andrew Kryczka
-  fbid: 100010829806660
+  fbid: 568694102
+
+abhimadan:
+  full_name: Abhishek Madan
+  fbid: 1850247869
 
 sagar0:
   full_name: Sagar Vemuri
@@ -60,3 +64,7 @@ sagar0:
 lightmark:
   full_name: Aaron Gao
   fbid: 1351549072
+
+fgwu:
+  full_name: Fenggang Wu
+  fbid: 100002297362180
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_data/features.yml b/3rdParty/rocksdb/v5.18.X/docs/_data/features.yml
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_data/features.yml
rename to 3rdParty/rocksdb/v5.18.X/docs/_data/features.yml
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_data/nav.yml b/3rdParty/rocksdb/v5.18.X/docs/_data/nav.yml
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_data/nav.yml
rename to 3rdParty/rocksdb/v5.18.X/docs/_data/nav.yml
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_data/nav_docs.yml b/3rdParty/rocksdb/v5.18.X/docs/_data/nav_docs.yml
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_data/nav_docs.yml
rename to 3rdParty/rocksdb/v5.18.X/docs/_data/nav_docs.yml
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_data/powered_by.yml b/3rdParty/rocksdb/v5.18.X/docs/_data/powered_by.yml
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_data/powered_by.yml
rename to 3rdParty/rocksdb/v5.18.X/docs/_data/powered_by.yml
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_data/powered_by_highlight.yml b/3rdParty/rocksdb/v5.18.X/docs/_data/powered_by_highlight.yml
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_data/powered_by_highlight.yml
rename to 3rdParty/rocksdb/v5.18.X/docs/_data/powered_by_highlight.yml
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_data/promo.yml b/3rdParty/rocksdb/v5.18.X/docs/_data/promo.yml
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_data/promo.yml
rename to 3rdParty/rocksdb/v5.18.X/docs/_data/promo.yml
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_docs/faq.md b/3rdParty/rocksdb/v5.18.X/docs/_docs/faq.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_docs/faq.md
rename to 3rdParty/rocksdb/v5.18.X/docs/_docs/faq.md
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_docs/getting-started.md b/3rdParty/rocksdb/v5.18.X/docs/_docs/getting-started.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_docs/getting-started.md
rename to 3rdParty/rocksdb/v5.18.X/docs/_docs/getting-started.md
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/blog_pagination.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/blog_pagination.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/blog_pagination.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/blog_pagination.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/content/gridblocks.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/content/gridblocks.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/content/gridblocks.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/content/gridblocks.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/content/items/gridblock.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/content/items/gridblock.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/content/items/gridblock.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/content/items/gridblock.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/doc.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/doc.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/doc.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/doc.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/doc_paging.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/doc_paging.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/doc_paging.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/doc_paging.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/footer.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/footer.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/footer.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/footer.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/head.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/head.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/head.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/head.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/header.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/header.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/header.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/header.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/hero.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/hero.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/hero.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/hero.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/home_header.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/home_header.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/home_header.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/home_header.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/katex_import.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/katex_import.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/katex_import.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/katex_import.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/katex_render.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/katex_render.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/katex_render.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/katex_render.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/nav.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/nav.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/nav.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/nav.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/nav/collection_nav.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/nav/collection_nav.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/nav/collection_nav.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/nav/collection_nav.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/nav/collection_nav_group.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/nav/collection_nav_group.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/nav/collection_nav_group.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/nav/collection_nav_group.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/nav/collection_nav_group_item.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/nav/collection_nav_group_item.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/nav/collection_nav_group_item.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/nav/collection_nav_group_item.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/nav/header_nav.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/nav/header_nav.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/nav/header_nav.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/nav/header_nav.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/nav_search.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/nav_search.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/nav_search.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/nav_search.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/all_share.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/all_share.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/all_share.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/all_share.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/ascii_cinema.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/ascii_cinema.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/ascii_cinema.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/ascii_cinema.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/button.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/button.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/button.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/button.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/github_star.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/github_star.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/github_star.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/github_star.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/github_watch.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/github_watch.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/github_watch.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/github_watch.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/google_share.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/google_share.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/google_share.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/google_share.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/iframe.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/iframe.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/iframe.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/iframe.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/like_button.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/like_button.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/like_button.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/like_button.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/plugin_row.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/plugin_row.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/plugin_row.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/plugin_row.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/post_social_plugins.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/post_social_plugins.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/post_social_plugins.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/post_social_plugins.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/slideshow.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/slideshow.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/slideshow.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/slideshow.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/twitter_follow.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/twitter_follow.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/twitter_follow.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/twitter_follow.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/twitter_share.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/twitter_share.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/plugins/twitter_share.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/plugins/twitter_share.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/post.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/post.html
similarity index 57%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/post.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/post.html
index 4c4b5b1ace..3ae0a2a808 100644
--- a/3rdParty/rocksdb/v5.16.X/docs/_includes/post.html
+++ b/3rdParty/rocksdb/v5.18.X/docs/_includes/post.html
@@ -1,18 +1,23 @@
 <div class="post">
-  {% assign author = site.data.authors[page.author] %}
   <header class="post-header">
-    {% if author.fbid %}
-    <div class="authorPhoto">
-      <img src="http://graph.facebook.com/{{ author.fbid }}/picture/" alt="{{ author.fullname }}" title="{{ author.fullname }}" />
+    <div style="display: flex; align-content: center; align-items: center; justify-content: center">
+    {% for author_idx in page.author %}
+      <div style="padding: 16px; display: inline-block; text-align: center">
+        {% assign author = site.data.authors[author_idx] %}
+        {% if author.fbid %}
+        <div class="authorPhoto">
+          <img src="http://graph.facebook.com/{{ author.fbid }}/picture/" alt="{{ author.fullname }}" title="{{ author.fullname }}" />
+        </div>
+        {% endif %}
+        {% if author.full_name %}
+        <p class="post-authorName">{{ author.full_name }}</p>
+        {% endif %}
+      </div>
+    {% endfor %}
     </div>
-    {% endif %}
-    {% if author.full_name %}
-    <p class="post-authorName">{{ author.full_name }}</p>
-    {% endif %}
     <h1 class="post-title">{% if include.truncate %}<a href="{{ page.url | absolute_url }}">{{ page.title }}</a>{% else %}{{ page.title }}{% endif %}</h1>
     <p class="post-meta">Posted {{ page.date | date: '%B %d, %Y' }}{% if page.meta %} • {{ page.meta }}{% endif %}</p>
   </header>
-
   <article class="post-content">
   {% if include.truncate %}
     {% if page.content contains '<!--truncate-->' %}
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/powered_by.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/powered_by.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/powered_by.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/powered_by.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/social_plugins.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/social_plugins.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/social_plugins.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/social_plugins.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_includes/ui/button.html b/3rdParty/rocksdb/v5.18.X/docs/_includes/ui/button.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_includes/ui/button.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_includes/ui/button.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/basic.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/basic.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/basic.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/basic.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/blog.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/blog.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/blog.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/blog.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/blog_default.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/blog_default.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/blog_default.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/blog_default.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/default.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/default.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/default.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/default.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/doc_default.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/doc_default.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/doc_default.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/doc_default.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/doc_page.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/doc_page.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/doc_page.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/doc_page.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/docs.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/docs.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/docs.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/docs.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/home.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/home.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/home.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/home.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/page.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/page.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/page.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/page.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/plain.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/plain.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/plain.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/plain.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/post.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/post.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/post.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/post.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/redirect.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/redirect.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/redirect.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/redirect.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_layouts/top-level.html b/3rdParty/rocksdb/v5.18.X/docs/_layouts/top-level.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_layouts/top-level.html
rename to 3rdParty/rocksdb/v5.18.X/docs/_layouts/top-level.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-03-27-how-to-backup-rocksdb.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-03-27-how-to-backup-rocksdb.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-03-27-how-to-backup-rocksdb.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-03-27-how-to-backup-rocksdb.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-03-27-how-to-persist-in-memory-rocksdb-database.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-03-27-how-to-persist-in-memory-rocksdb-database.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-03-27-how-to-persist-in-memory-rocksdb-database.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-03-27-how-to-persist-in-memory-rocksdb-database.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-04-02-the-1st-rocksdb-local-meetup-held-on-march-27-2014.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-04-02-the-1st-rocksdb-local-meetup-held-on-march-27-2014.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-04-02-the-1st-rocksdb-local-meetup-held-on-march-27-2014.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-04-02-the-1st-rocksdb-local-meetup-held-on-march-27-2014.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-04-07-rocksdb-2-8-release.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-04-07-rocksdb-2-8-release.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-04-07-rocksdb-2-8-release.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-04-07-rocksdb-2-8-release.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-04-21-indexing-sst-files-for-better-lookup-performance.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-04-21-indexing-sst-files-for-better-lookup-performance.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-04-21-indexing-sst-files-for-better-lookup-performance.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-04-21-indexing-sst-files-for-better-lookup-performance.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-05-14-lock.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-05-14-lock.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-05-14-lock.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-05-14-lock.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-05-19-rocksdb-3-0-release.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-05-19-rocksdb-3-0-release.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-05-19-rocksdb-3-0-release.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-05-19-rocksdb-3-0-release.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-05-22-rocksdb-3-1-release.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-05-22-rocksdb-3-1-release.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-05-22-rocksdb-3-1-release.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-05-22-rocksdb-3-1-release.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-06-23-plaintable-a-new-file-format.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-06-23-plaintable-a-new-file-format.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-06-23-plaintable-a-new-file-format.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-06-23-plaintable-a-new-file-format.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-06-27-avoid-expensive-locks-in-get.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-06-27-avoid-expensive-locks-in-get.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-06-27-avoid-expensive-locks-in-get.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-06-27-avoid-expensive-locks-in-get.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-06-27-rocksdb-3-2-release.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-06-27-rocksdb-3-2-release.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-06-27-rocksdb-3-2-release.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-06-27-rocksdb-3-2-release.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-07-29-rocksdb-3-3-release.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-07-29-rocksdb-3-3-release.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-07-29-rocksdb-3-3-release.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-07-29-rocksdb-3-3-release.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-09-12-cuckoo.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-09-12-cuckoo.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-09-12-cuckoo.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-09-12-cuckoo.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-09-12-new-bloom-filter-format.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-09-12-new-bloom-filter-format.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-09-12-new-bloom-filter-format.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-09-12-new-bloom-filter-format.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2014-09-15-rocksdb-3-5-release.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2014-09-15-rocksdb-3-5-release.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2014-09-15-rocksdb-3-5-release.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2014-09-15-rocksdb-3-5-release.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-01-16-migrating-from-leveldb-to-rocksdb-2.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-01-16-migrating-from-leveldb-to-rocksdb-2.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-01-16-migrating-from-leveldb-to-rocksdb-2.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-01-16-migrating-from-leveldb-to-rocksdb-2.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-02-24-reading-rocksdb-options-from-a-file.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-02-24-reading-rocksdb-options-from-a-file.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-02-24-reading-rocksdb-options-from-a-file.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-02-24-reading-rocksdb-options-from-a-file.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-02-27-write-batch-with-index.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-02-27-write-batch-with-index.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-02-27-write-batch-with-index.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-02-27-write-batch-with-index.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-04-22-integrating-rocksdb-with-mongodb-2.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-04-22-integrating-rocksdb-with-mongodb-2.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-04-22-integrating-rocksdb-with-mongodb-2.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-04-22-integrating-rocksdb-with-mongodb-2.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-06-12-rocksdb-in-osquery.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-06-12-rocksdb-in-osquery.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-06-12-rocksdb-in-osquery.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-06-12-rocksdb-in-osquery.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-07-15-rocksdb-2015-h2-roadmap.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-07-15-rocksdb-2015-h2-roadmap.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-07-15-rocksdb-2015-h2-roadmap.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-07-15-rocksdb-2015-h2-roadmap.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-07-17-spatial-indexing-in-rocksdb.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-07-17-spatial-indexing-in-rocksdb.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-07-17-spatial-indexing-in-rocksdb.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-07-17-spatial-indexing-in-rocksdb.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-07-22-rocksdb-is-now-available-in-windows-platform.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-07-22-rocksdb-is-now-available-in-windows-platform.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-07-22-rocksdb-is-now-available-in-windows-platform.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-07-22-rocksdb-is-now-available-in-windows-platform.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-07-23-dynamic-level.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-07-23-dynamic-level.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-07-23-dynamic-level.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-07-23-dynamic-level.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-10-27-getthreadlist.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-10-27-getthreadlist.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-10-27-getthreadlist.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-10-27-getthreadlist.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-11-10-use-checkpoints-for-efficient-snapshots.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-11-10-use-checkpoints-for-efficient-snapshots.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-11-10-use-checkpoints-for-efficient-snapshots.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-11-10-use-checkpoints-for-efficient-snapshots.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2015-11-16-analysis-file-read-latency-by-level.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2015-11-16-analysis-file-read-latency-by-level.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2015-11-16-analysis-file-read-latency-by-level.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2015-11-16-analysis-file-read-latency-by-level.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2016-01-29-compaction_pri.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2016-01-29-compaction_pri.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2016-01-29-compaction_pri.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2016-01-29-compaction_pri.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2016-02-24-rocksdb-4-2-release.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2016-02-24-rocksdb-4-2-release.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2016-02-24-rocksdb-4-2-release.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2016-02-24-rocksdb-4-2-release.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2016-02-25-rocksdb-ama.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2016-02-25-rocksdb-ama.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2016-02-25-rocksdb-ama.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2016-02-25-rocksdb-ama.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2016-03-07-rocksdb-options-file.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2016-03-07-rocksdb-options-file.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2016-03-07-rocksdb-options-file.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2016-03-07-rocksdb-options-file.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2016-04-26-rocksdb-4-5-1-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2016-04-26-rocksdb-4-5-1-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2016-04-26-rocksdb-4-5-1-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2016-04-26-rocksdb-4-5-1-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2016-07-26-rocksdb-4-8-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2016-07-26-rocksdb-4-8-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2016-07-26-rocksdb-4-8-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2016-07-26-rocksdb-4-8-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2016-09-28-rocksdb-4-11-2-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2016-09-28-rocksdb-4-11-2-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2016-09-28-rocksdb-4-11-2-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2016-09-28-rocksdb-4-11-2-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-01-06-rocksdb-5-0-1-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-01-06-rocksdb-5-0-1-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-01-06-rocksdb-5-0-1-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-01-06-rocksdb-5-0-1-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-02-07-rocksdb-5-1-2-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-02-07-rocksdb-5-1-2-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-02-07-rocksdb-5-1-2-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-02-07-rocksdb-5-1-2-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-02-17-bulkoad-ingest-sst-file.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-02-17-bulkoad-ingest-sst-file.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-02-17-bulkoad-ingest-sst-file.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-02-17-bulkoad-ingest-sst-file.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-03-02-rocksdb-5-2-1-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-03-02-rocksdb-5-2-1-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-03-02-rocksdb-5-2-1-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-03-02-rocksdb-5-2-1-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-05-12-partitioned-index-filter.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-05-12-partitioned-index-filter.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-05-12-partitioned-index-filter.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-05-12-partitioned-index-filter.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-05-14-core-local-stats.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-05-14-core-local-stats.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-05-14-core-local-stats.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-05-14-core-local-stats.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-05-26-rocksdb-5-4-5-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-05-26-rocksdb-5-4-5-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-05-26-rocksdb-5-4-5-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-05-26-rocksdb-5-4-5-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-06-26-17-level-based-changes.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-06-26-17-level-based-changes.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-06-26-17-level-based-changes.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-06-26-17-level-based-changes.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-06-29-rocksdb-5-5-1-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-06-29-rocksdb-5-5-1-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-06-29-rocksdb-5-5-1-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-06-29-rocksdb-5-5-1-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-07-25-rocksdb-5-6-1-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-07-25-rocksdb-5-6-1-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-07-25-rocksdb-5-6-1-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-07-25-rocksdb-5-6-1-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-08-24-pinnableslice.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-08-24-pinnableslice.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-08-24-pinnableslice.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-08-24-pinnableslice.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-08-25-flushwal.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-08-25-flushwal.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-08-25-flushwal.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-08-25-flushwal.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-09-28-rocksdb-5-8-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-09-28-rocksdb-5-8-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-09-28-rocksdb-5-8-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-09-28-rocksdb-5-8-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-12-18-17-auto-tuned-rate-limiter.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-12-18-17-auto-tuned-rate-limiter.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-12-18-17-auto-tuned-rate-limiter.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-12-18-17-auto-tuned-rate-limiter.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-12-19-write-prepared-txn.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-12-19-write-prepared-txn.markdown
similarity index 88%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2017-12-19-write-prepared-txn.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2017-12-19-write-prepared-txn.markdown
index d592b6f7b1..439b3f83cc 100644
--- a/3rdParty/rocksdb/v5.16.X/docs/_posts/2017-12-19-write-prepared-txn.markdown
+++ b/3rdParty/rocksdb/v5.18.X/docs/_posts/2017-12-19-write-prepared-txn.markdown
@@ -7,8 +7,6 @@ category: blog
 
 RocksDB supports both optimistic and pessimistic concurrency controls. The pessimistic transactions make use of locks to provide isolation between the transactions. The default write policy in pessimistic transactions is _WriteCommitted_, which means that the data is written to the DB, i.e., the memtable, only after the transaction is committed. This policy simplified the implementation but came with some limitations in throughput, transaction size, and variety in supported isolation levels. In the below, we explain these in detail and present the other write policies, _WritePrepared_ and _WriteUnprepared_. We then dive into the design of _WritePrepared_ transactions.
 
-> _WritePrepared_ are to be announced as production-ready soon.
-
 ### WriteCommitted, Pros and Cons
 
 With _WriteCommitted_ write policy, the data is written to the memtable only after the transaction commits. This greatly simplifies the read path as any data that is read by other transactions can be assumed to be committed. This write policy, however, implies that the writes are buffered in memory in the meanwhile. This makes memory a bottleneck for large transactions. The delay of the commit phase in 2PC (two-phase commit) also becomes noticeable since most of the work, i.e., writing to memtable, is done at the commit phase. When the commit of multiple transactions are done in a serial fashion, such as in 2PC implementation of MySQL, the lengthy commit latency becomes a major contributor to lower throughput. Moreover this write policy cannot provide weaker isolation levels, such as READ UNCOMMITTED, that could potentially provide higher throughput for some applications.
@@ -28,10 +26,16 @@ With _WritePrepared_, a transaction still buffers the writes in a write batch ob
 
 The _CommitCache_ is a lock-free data structure that caches the recent commit entries. Looking up the entries in the cache must be enough for almost all th transactions that commit in a timely manner. When evicting the older entries from the cache, it still maintains some other data structures to cover the corner cases for transactions that takes abnormally too long to finish. We will cover them in the design details below.
 
-### Preliminary Results
-The full experimental results are to be reported soon. Here we present the improvement in tps observed in some preliminary experiments with MyRocks:
-* sysbench update-noindex: 25%
-* sysbench read-write: 7.6%
-* linkbench: 3.7%
+### Benchmark Results
+Here we presents the improvements observed in MyRocks with sysbench and linkbench:
+* benchmark...........tps.........p95 latency....cpu/query
+* insert...................68%
+* update-noindex...30%......38%
+* update-index.......61%.......28%
+* read-write............6%........3.5%
+* read-only...........-1.2%.....-1.8%
+* linkbench.............1.9%......+overall........0.6%
+
+Here are also the detailed results for [In-Memory Sysbench](https://gist.github.com/maysamyabandeh/bdb868091b2929a6d938615fdcf58424) and [SSD Sysbench](https://gist.github.com/maysamyabandeh/ff94f378ab48925025c34c47eff99306) curtesy of [@mdcallag](https://github.com/mdcallag).
 
 Learn more [here](https://github.com/facebook/rocksdb/wiki/WritePrepared-Transactions).
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2018-02-05-rocksdb-5-10-2-released.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2018-02-05-rocksdb-5-10-2-released.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2018-02-05-rocksdb-5-10-2-released.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2018-02-05-rocksdb-5-10-2-released.markdown
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_posts/2018-08-01-rocksdb-tuning-advisor.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2018-08-01-rocksdb-tuning-advisor.markdown
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_posts/2018-08-01-rocksdb-tuning-advisor.markdown
rename to 3rdParty/rocksdb/v5.18.X/docs/_posts/2018-08-01-rocksdb-tuning-advisor.markdown
diff --git a/3rdParty/rocksdb/v5.18.X/docs/_posts/2018-08-23-data-block-hash-index.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2018-08-23-data-block-hash-index.markdown
new file mode 100644
index 0000000000..c4b24ec2ac
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/docs/_posts/2018-08-23-data-block-hash-index.markdown
@@ -0,0 +1,118 @@
+---
+title: Improving Point-Lookup Using Data Block Hash Index
+layout: post
+author: fgwu
+category: blog
+---
+We've designed and implemented a _data block hash index_ in RocksDB that has the benefit of both reducing the CPU util and increasing the throughput for point lookup queries with a reasonable and tunable space overhead. 
+
+Specifially, we append a compact hash table to the end of the data block for efficient indexing. It is backward compatible with the data base created without this feature. After turned on the hash index feature, existing data will be gradually converted to the hash index format.
+
+Benchmarks with `db_bench`  show the CPU utilization of one of the main functions in the point lookup code path, `DataBlockIter::Seek()`, is reduced by 21.8%, and the overall RocksDB throughput is increased by 10% under purely cached workloads, at an overhead of 4.6% more space. Shadow testing with Facebook production traffic shows good CPU improvements too.
+
+
+### How to use it
+Two new options are added as part of this feature: `BlockBasedTableOptions::data_block_index_type` and `BlockBasedTableOptions::data_block_hash_table_util_ratio`.
+
+The hash index is disabled by default unless `BlockBasedTableOptions::data_block_index_type` is set to `data_block_index_type = kDataBlockBinaryAndHash`. The hash table utilization ratio is adjustable using `BlockBasedTableOptions::data_block_hash_table_util_ratio`, which is valid only if `data_block_index_type = kDataBlockBinaryAndHash`.
+
+
+```
+// the definitions can be found in include/rocksdb/table.h
+
+// The index type that will be used for the data block.
+enum DataBlockIndexType : char {
+  kDataBlockBinarySearch = 0,  // traditional block type
+  kDataBlockBinaryAndHash = 1, // additional hash index
+};
+
+// Set to kDataBlockBinaryAndHash to enable hash index
+DataBlockIndexType data_block_index_type = kDataBlockBinarySearch;
+
+// #entries/#buckets. It is valid only when data_block_hash_index_type is
+// kDataBlockBinaryAndHash.
+double data_block_hash_table_util_ratio = 0.75;
+
+```
+
+
+### Data Block Hash Index Design
+
+Current data block format groups adjacent keys together as a restart interval. One block consists of multiple restart intervals. The byte offset of the beginning of each restart interval, i.e. a restart point, is stored in an array called restart interval index or binary seek index. RocksDB does a binary search when performing point lookup for keys in data blocks to find the right restart interval the key may reside. We will use binary seek and binary search interchangeably in this post.
+
+In order to find the right location where the key may reside using binary search, multiple key parsing and comparison are needed. Each binary search branching triggers CPU cache miss, causing much CPU utilization. We have seen that this binary search takes up considerable CPU in production use-cases.
+
+![](/static/images/data-block-hash-index/block-format-binary-seek.png)
+
+We implemented a hash map at the end of the block to index the key to reduce the CPU overhead of the binary search. The hash index is just an array of pointers pointing into the binary seek index.
+
+![](/static/images/data-block-hash-index/block-format-hash-index.png)
+
+
+Each array element is considered as a hash bucket when storing the location of a key (or more precisely, the restart index of the restart interval where the key resides). When multiple keys happen to hash into the same bucket (hash collision), we just mark the bucket as “collision”. So that when later querying on that key, the hash table lookup knows that there was a hash collision happened so it can fall back to the traditional binary search to find the location of the key.
+
+We define hash table utilization ratio as the #keys/#buckets. If a utilization ratio is 0.5 and there are 100 buckets, 50 keys are stored in the bucket. The less the util ratio, the less hash collision, and the less chance for a point lookup falls back to binary seek (fall back ratio) due to the collision. So a small util ratio has more benefit to reduce the CPU time but introduces more space overhead.
+
+Space overhead depends on the util ratio. Each bucket is a `uint8_t`  (i.e. one byte). For a util ratio of 1, the space overhead is 1Byte per key, the fall back ratio observed is ~52%.
+
+![](/static/images/data-block-hash-index/hash-index-data-structure.png)
+
+### Things that Need Attention
+
+**Customized Comparator**
+
+Hash index will hash different keys (keys with different content, or byte sequence) into different hash values. This assumes the comparator will not treat different keys as equal if they have different content. 
+
+The default bytewise comparator orders the keys in alphabetical order and works well with hash index, as different keys will never be regarded as equal. However, some specially crafted comparators will do. For example, say, a `StringToIntComparator` can convert a string into an integer, and use the integer to perform the comparison. Key string “16” and “0x10” is equal to each other as seen by this `StringToIntComparator`, but they probably hash to different value. Later queries to one form of the key will not be able to find the existing key been stored in the other format.
+
+We add a new function member to the comparator interface: 
+
+```
+virtual bool CanKeysWithDifferentByteContentsBeEqual() const { return true; }
+```
+
+
+Every comparator implementation should override this function and specify the behavior of the comparator. If a comparator can regard different keys equal, the function returns true, and as a result the hash index feature will not be enabled, and vice versa.
+
+NOTE: to use the hash index feature, one should 1) have a comparator that can never treat different keys as equal; and 2) override the `CanKeysWithDifferentByteContentsBeEqual()` function to return `false`, so the hash index can be enabled.
+
+
+**Util Ratio's Impact on Data Block Cache**
+
+Adding the hash index to the end of the data block essentially takes up the data block cache space, making the effective data block cache size smaller and increasing the data block cache miss ratio. Therefore, a very small util ratio will result in a large data block cache miss ratio, and the extra I/O may drag down the throughput gain achieved by the hash index lookup. Besides, when compression is enabled, cache miss also incurs data block decompression, which is CPU-consuming. Therefore the CPU may even increase if using a too small util ratio. The best util ratio depends on workloads, cache to data ratio, disk bandwidth/latency etc. In our experiment, we found util ratio = 0.5 ~ 1 is a good range to explore that brings both CPU and throughput gains.
+
+
+### Limitations
+
+As we use `uint8_t` to store binary seek index, i.e. restart interval index, the total number of restart intervals cannot be more than 253 (we reserved  255 and 254 as special flags). For blocks having a larger number of restart intervals, the hash index will not be created and the point lookup will be done by traditional binary seek.
+
+Data block hash index only supports point lookup. We do not support range lookup. Range lookup request will fall back to BinarySeek.
+
+RocksDB supports many types of records, such as `Put`, `Delete`, `Merge`, etc (visit [here](https://github.com/facebook/rocksdb/wiki/rocksdb-basics) for more information). Currently we only support `Put` and `Delete`, but not `Merge`. Internally we have a limited set of supported record types:
+
+
+```
+kPutRecord,          <=== supported
+kDeleteRecord,       <=== supported
+kSingleDeleteRecord, <=== supported
+kTypeBlobIndex,      <=== supported
+```
+
+For records not supported, the searching process will fall back to the traditional binary seek. 
+
+
+
+### Evaluation
+To evaluate the CPU util reduction and isolate other factors such as disk I/O and block decompression, we first evaluate the hash idnex in a purely cached workload. We observe that the CPU utilization of one of the main functions in the point lookup code path, DataBlockIter::Seek(), is reduced by 21.8% and the overall throughput is increased by 10% at an overhead of 4.6% more space.
+
+However, general worload is not always purely cached. So we also evaluate the performance under different cache space pressure. In the following test, we use `db_bench` with RocksDB deployed on SSDs. The total DB size is 5~6GB, and it is about 14GB if decompressed. Different block cache sizes are used, ranging from 14GB down to 2GB, with an increasing cache miss ratio.
+
+Orange bars are representing our hash index performance. We use a hash util ratio of 1.0 in this test. Block size are set to 16KiB with the restart interval as 16.
+
+![](/static/images/data-block-hash-index/perf-throughput.png)
+![](/static/images/data-block-hash-index/perf-cache-miss.png)
+
+We can see that if cache size is greater than 8GB, hash index can bring throughput gain. Cache size greater than 8GB can be translated to a cache miss ratio smaller than 40%. So if the workload has a cache miss ratio smaller than 40%, hash index is able to increase the throughput.
+
+Besides, shadow testing with Facebook production traffic shows good CPU improvements too.
+
diff --git a/3rdParty/rocksdb/v5.18.X/docs/_posts/2018-11-21-delete-range.markdown b/3rdParty/rocksdb/v5.18.X/docs/_posts/2018-11-21-delete-range.markdown
new file mode 100644
index 0000000000..96fc3562d1
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/docs/_posts/2018-11-21-delete-range.markdown
@@ -0,0 +1,292 @@
+---
+title: "DeleteRange: A New Native RocksDB Operation"
+layout: post
+author:
+- abhimadan
+- ajkr
+category: blog
+---
+## Motivation
+
+### Deletion patterns in LSM
+
+Deleting a range of keys is a common pattern in RocksDB. Most systems built on top of
+RocksDB have multi-component key schemas, where keys sharing a common prefix are
+logically related. Here are some examples.
+
+MyRocks is a MySQL fork using RocksDB as its storage engine. Each key's first
+four bytes identify the table or index to which that key belongs. Thus dropping
+a table or index involves deleting all the keys with that prefix.
+
+Rockssandra is a Cassandra variant that uses RocksDB as its storage engine. One
+of its admin tool commands, `nodetool cleanup`, removes key-ranges that have been migrated
+to other nodes in the cluster.
+
+Marketplace uses RocksDB to store product data. Its key begins with product ID,
+and it stores various data associated with the product in separate keys. When a
+product is removed, all these keys must be deleted.
+
+When we decide what to improve, we try to find a use case that's common across
+users, since we want to build a generally useful system, not one that has many
+one-off features for individual users. The range deletion pattern is common as
+illustrated above, so from this perspective it's a good target for optimization.
+
+### Existing mechanisms: challenges and opportunities
+
+The most common pattern we see is scan-and-delete, i.e., advance an iterator
+through the to-be-deleted range, and issue a `Delete` for each key. This is
+slow (involves read I/O) so cannot be done in any critical path. Additionally,
+it creates many tombstones, which slows down iterators and doesn't offer a deadline
+for space reclamation.
+
+Another common pattern is using a custom compaction filter that drops keys in
+the deleted range(s). This deletes the range asynchronously, so cannot be used
+in cases where readers must not see keys in deleted ranges. Further, it has the
+disadvantage of outputting tombstones to all but the bottom level. That's
+because compaction cannot detect whether dropping a key would cause an older
+version at a lower level to reappear.
+
+If space reclamation time is important, or it is important that the deleted
+range not affect iterators, the user can trigger `CompactRange` on the deleted
+range. This can involve arbitrarily long waits in the compaction queue, and
+increases write-amp. By the time it's finished, however, the range is completely
+gone from the LSM.
+
+`DeleteFilesInRange` can be used prior to compacting the deleted range as long
+as snapshot readers do not need to access them. It drops files that are
+completely contained in the deleted range. That saves write-amp because, in
+`CompactRange`, the file data would have to be rewritten several times before it
+reaches the bottom of the LSM, where tombstones can finally be dropped.
+
+In addition to the above approaches having various drawbacks, they are quite
+complicated to reason about and implement. In an ideal world, deleting a range
+of keys would be (1) simple, i.e., a single API call; (2) synchronous, i.e.,
+when the call finishes, the keys are guaranteed to be wiped from the DB; (3) low
+latency so it can be used in critical paths; and (4) a first-class operation
+with all the guarantees of any other write, like atomicity, crash-recovery, etc.
+
+## v1: Getting it to work
+
+### Where to persist them?
+
+The first place we thought about storing them is inline with the data blocks.
+We could not think of a good way to do it, however, since the start of a range
+tombstone covering a key could be anywhere, making binary search impossible.
+So, we decided to investigate segregated storage.
+
+A second solution we considered is appending to the manifest. This file is
+append-only, periodically compacted, and stores metadata like the level to which
+each SST belongs. This is tempting because it leverages an existing file, which
+is maintained in the background and fully read when the DB is opened. However,
+it conceptually violates the manifest's purpose, which is to store metadata. It
+also has no way to detect when a range tombstone no longer covers anything and
+is droppable. Further, it'd be possible for keys above a range tombstone to disappear
+when they have their seqnums zeroed upon compaction to the bottommost level.
+
+A third candidate is using a separate column family. This has similar problems
+to the manifest approach. That is, we cannot easily detect when a range
+tombstone is obsolete, and seqnum zeroing can cause a key
+to go from above a range tombstone to below, i.e., disappearing. The upside is
+we can reuse logic for memory buffering, consistent reads/writes, etc.
+
+The problems with the second and third solutions indicate a need for range
+tombstones to be aware of flush/compaction. An easy way to achieve this is put
+them in the SST files themselves - but not in the data blocks, as explained for
+the first solution. So, we introduced a separate meta-block for range tombstones.
+This resolved the problem of when to obsolete range tombstones, as it's simple:
+when they're compacted to the bottom level. We also reused the LSM invariants
+that newer versions of a key are always in a higher level to prevent the seqnum
+zeroing problem. This approach has the side benefit of constraining the range
+tombstones seen during reads to ones in a similar key-range.
+
+![](/static/images/delrange/delrange_sst_blocks.png)
+{: style="display: block; margin-left: auto; margin-right: auto; width: 80%"}
+
+*When there are range tombstones in an SST, they are segregated in a separate meta-block*
+{: style="text-align: center"}
+
+![](/static/images/delrange/delrange_key_schema.png)
+{: style="display: block; margin-left: auto; margin-right: auto; width: 80%"}
+
+*Logical range tombstones (left) and their corresponding physical key-value representation (right)*
+{: style="text-align: center"}
+
+### Write path
+
+`WriteBatch` stores range tombstones in its buffer which are logged to the WAL and
+then applied to a dedicated range tombstone memtable during `Write`. Later in
+the background the range tombstone memtable and its corresponding data memtable
+are flushed together into a single SST with a range tombstone meta-block. SSTs
+periodically undergo compaction which rewrites SSTs with point data and range
+tombstones dropped or merged wherever possible.
+
+We chose to use a dedicated memtable for range tombstones. The memtable
+representation is always skiplist in order to minimize overhead in the usual
+case, which is the memtable contains zero or a small number of range tombstones.
+The range tombstones are segregated to a separate memtable for the same reason
+we segregated range tombstones in SSTs. That is, we did not know how to
+interleave the range tombstone with point data in a way that we would be able to
+find it for arbitrary keys that it covers.
+
+![](/static/images/delrange/delrange_write_path.png)
+{: style="display: block; margin-left: auto; margin-right: auto; width: 70%"}
+
+*Lifetime of point keys and range tombstones in RocksDB*
+{: style="text-align: center"}
+
+During flush and compaction, we chose to write out all non-obsolete range
+tombstones unsorted. Sorting by a single dimension is easy to implement, but
+doesn't bring asymptotic improvement to queries over range data. Ideally, we
+want to store skylines (see “Read Path” subsection below) computed over our ranges so we can binary search.
+However, a couple of concerns cause doing this in flush and compaction to feel
+unsatisfactory: (1) we need to store multiple skylines, one for each snapshot,
+which further complicates the range tombstone meta-block encoding; and (2) even
+if we implement this, the range tombstone memtable still needs to be linearly
+scanned. Given these concerns we decided to defer collapsing work to the read
+side, hoping a good caching strategy could optimize this at some future point.
+
+
+### Read path
+
+In point lookups, we aggregate range tombstones in an unordered vector as we
+search through live memtable, immutable memtables, and then SSTs. When a key is
+found that matches the lookup key, we do a scan through the vector, checking
+whether the key is deleted.
+
+In iterators, we aggregate range tombstones into a skyline as we visit live
+memtable, immutable memtables, and SSTs. The skyline is expensive to construct but fast to determine whether a key is covered. The skyline keeps track of the most recent range tombstone found to optimize `Next` and `Prev`.
+
+|![](/static/images/delrange/delrange_uncollapsed.png)	|![](/static/images/delrange/delrange_collapsed.png)	|
+
+*([Image source: Leetcode](https://leetcode.com/problems/the-skyline-problem/description/)) The skyline problem involves taking building location/height data in the
+unsearchable form of A and converting it to the form of B, which is
+binary-searchable. With overlapping range tombstones, to achieve efficient
+searching we need to solve an analogous problem, where the x-axis is the
+key-space and the y-axis is the sequence number.*
+{: style="text-align: center"}
+
+### Performance characteristics
+
+For the v1 implementation, writes are much faster compared to the scan and
+delete (optionally within a transaction) pattern. `DeleteRange` only logs to WAL
+and applies to memtable. Logging to WAL always `fflush`es, and optionally
+`fsync`s or `fdatasync`s. Applying to memtable is always an in-memory operation.
+Since range tombstones have a dedicated skiplist memtable, the complexity of inserting is O(log(T)), where T is the number of existing buffered range tombstones.
+
+Reading in the presence of v1 range tombstones, however, is much slower than reads
+in a database where scan-and-delete has happened, due to the linear scan over
+range tombstone memtables/meta-blocks.
+
+Iterating in a database with v1 range tombstones is usually slower than in a
+scan-and-delete database, although the gap lessens as iterations grow longer.
+When an iterator is first created and seeked, we construct a skyline over its
+tombstones. This operation is O(T\*log(T)) where T is the number of tombstones
+found across live memtable, immutable memtable, L0 files, and one file from each
+of the L1+ levels. However, moving the iterator forwards or backwards is simply
+a constant-time operation (excluding edge cases, e.g., many range tombstones
+between consecutive point keys).
+
+## v2: Making it fast
+
+`DeleteRange`’s negative impact on read perf is a barrier to its adoption. The
+root cause is range tombstones are not stored or cached in a format that can be
+efficiently searched. We needed to design DeleteRange so that we could maintain
+write performance while making read performance competitive with workarounds
+used in production (e.g., scan-and-delete).
+
+### Representations
+
+The key idea of the redesign is that, instead of globally collapsing range tombstones,
+ we can locally “fragment” them for each SST file and memtable to guarantee that:
+
+* no range tombstones overlap; and
+* range tombstones are ordered by start key.
+
+Combined, these properties make range tombstones binary searchable. This
+ fragmentation will happen on the read path, but unlike the previous design, we can
+ easily cache many of these range tombstone fragments on the read path.
+
+### Write path
+
+The write path remains unchanged.
+
+### Read path
+
+When an SST file is opened, its range tombstones are fragmented and cached. For point
+ lookups, we binary search each file's fragmented range tombstones for one that covers
+ the lookup key. Unlike the old design, once we find a tombstone, we no longer need to
+ search for the key in lower levels, since we know that any keys on those levels will be
+ covered (though we do still check the current level since there may be keys written after
+ the range tombstone).
+
+For range scans, we create iterators over all the fragmented range
+ tombstones and store them in a list, seeking each one to cover the start key of the range
+ scan (if possible), and query each encountered key in this structure as in the old design,
+ advancing range tombstone iterators as necessary. In effect, we implicitly create a skyline.
+ This requires significantly less work on iterator creation, but since each memtable/SST has
+its own range tombstone iterator, querying range tombstones requires key comparisons (and
+possibly iterator increments) for several iterators (as opposed to v1, where we had a global
+collapsed representation of all range tombstones). As a result, very long range scans may become
+ slower than before, but short range scans are an order of magnitude faster, which are the
+ more common class of range scan.
+
+## Benchmarks
+
+To understand the performance of this new design, we used `db_bench` to compare point lookup, short range scan,
+ and long range scan performance across:
+
+* the v1 DeleteRange design,
+* the scan-and-delete workaround, and
+* the v2 DeleteRange design.
+
+In these benchmarks, we used a database with 5 million data keys, and 10000 range tombstones (ignoring
+those dropped during compaction) that were written in regular intervals after 4.5 million data keys were written.
+Writing the range tombstones ensures that most of them are not compacted away, and we have more tombstones
+in higher levels that cover keys in lower levels, which allows the benchmarks to exercise more interesting behavior
+when reading deleted keys.
+
+Point lookup benchmarks read 100000 keys from a database using `readwhilewriting`. Range scan benchmarks used
+`seekrandomwhilewriting` and seeked 100000 times, and advanced up to 10 keys away from the seek position for short range scans, and advanced up to 1000 keys away from the seek position for long range scans.
+
+The results are summarized in the tables below, averaged over 10 runs (note the
+different SHAs for v1 benchmarks are due to a new `db_bench` flag that was added in order to compare performance with databases with no tombstones; for brevity, those results are not reported here). Also note that the block cache was large enough to hold the entire db, so the large throughput is due to limited I/Os and little time spent on decompression. The range tombstone blocks are always pinned uncompressed in memory. We believe these setup details should not affect relative performance between versions.
+
+### Point Lookups
+
+|Name	|SHA	|avg micros/op	|avg ops/sec	|
+|v1	|35cd754a6	|1.3179	|759,830.90	|
+|scan-del	|7528130e3	|0.6036	|1,667,237.70	|
+|v2	|7528130e3	|0.6128	|1,634,633.40	|
+
+### Short Range Scans
+
+|Name	|SHA	|avg micros/op	|avg ops/sec	|
+|v1	|0ed738fdd	|6.23	|176,562.00	|
+|scan-del	|PR 4677	|2.6844	|377,313.00	|
+|v2	|PR 4677	|2.8226	|361,249.70	|
+
+### Long Range scans
+
+|Name	|SHA	|avg micros/op	|avg ops/sec	|
+|v1	|0ed738fdd	|52.7066	|19,074.00	|
+|scan-del	|PR 4677	|38.0325	|26,648.60	|
+|v2	|PR 4677	|41.2882	|24,714.70	|
+
+## Future Work
+
+Note that memtable range tombstones are fragmented every read; for now this is acceptable,
+ since we expect there to be relatively few range tombstones in memtables (and users can
+ enforce this by keeping track of the number of memtable range deletions and manually flushing
+ after it passes a threshold). In the future, a specialized data structure can be used for storing
+ range tombstones in memory to avoid this work.
+
+Another future optimization is to create a new format version that requires range tombstones to
+ be stored in a fragmented form. This would save time when opening SST files, and when `max_open_files` 
+is not -1 (i.e., files may be opened several times).
+
+## Acknowledgements
+
+Special thanks to Peter Mattis and Nikhil Benesch from Cockroach Labs, who were early users of
+DeleteRange v1 in production, contributed the cleanest/most efficient v1 aggregation implementation, found and fixed bugs, and provided initial DeleteRange v2 design and continued help.
+
+Thanks to Huachao Huang and Jinpeng Zhang from PingCAP for early DeleteRange v1 adoption, bug reports, and fixes.
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_base.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_base.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_base.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_base.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_blog.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_blog.scss
similarity index 85%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_blog.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_blog.scss
index 74335d10b4..12a73c1fcd 100644
--- a/3rdParty/rocksdb/v5.16.X/docs/_sass/_blog.scss
+++ b/3rdParty/rocksdb/v5.18.X/docs/_sass/_blog.scss
@@ -35,11 +35,13 @@
       border-radius: 50%;
       height: 50px;
       left: 50%;
-      margin-left: -25px;
+      margin-left: auto;
+      margin-right: auto;
+      display: inline-block;
       overflow: hidden;
-      position: absolute;
+      position: static;
       top: -25px;
       width: 50px;
     }
   }
-}
\ No newline at end of file
+}
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_buttons.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_buttons.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_buttons.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_buttons.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_footer.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_footer.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_footer.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_footer.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_gridBlock.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_gridBlock.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_gridBlock.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_gridBlock.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_header.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_header.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_header.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_header.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_poweredby.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_poweredby.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_poweredby.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_poweredby.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_promo.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_promo.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_promo.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_promo.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_react_docs_nav.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_react_docs_nav.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_react_docs_nav.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_react_docs_nav.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_react_header_nav.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_react_header_nav.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_react_header_nav.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_react_header_nav.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_reset.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_reset.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_reset.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_reset.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_search.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_search.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_search.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_search.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_slideshow.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_slideshow.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_slideshow.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_slideshow.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_syntax-highlighting.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_syntax-highlighting.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_syntax-highlighting.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_syntax-highlighting.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_sass/_tables.scss b/3rdParty/rocksdb/v5.18.X/docs/_sass/_tables.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_sass/_tables.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/_sass/_tables.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/_top-level/support.md b/3rdParty/rocksdb/v5.18.X/docs/_top-level/support.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/_top-level/support.md
rename to 3rdParty/rocksdb/v5.18.X/docs/_top-level/support.md
diff --git a/3rdParty/rocksdb/v5.16.X/docs/blog/all.html b/3rdParty/rocksdb/v5.18.X/docs/blog/all.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/blog/all.html
rename to 3rdParty/rocksdb/v5.18.X/docs/blog/all.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/blog/index.html b/3rdParty/rocksdb/v5.18.X/docs/blog/index.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/blog/index.html
rename to 3rdParty/rocksdb/v5.18.X/docs/blog/index.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/css/main.scss b/3rdParty/rocksdb/v5.18.X/docs/css/main.scss
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/css/main.scss
rename to 3rdParty/rocksdb/v5.18.X/docs/css/main.scss
diff --git a/3rdParty/rocksdb/v5.16.X/docs/doc-type-examples/2016-04-07-blog-post-example.md b/3rdParty/rocksdb/v5.18.X/docs/doc-type-examples/2016-04-07-blog-post-example.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/doc-type-examples/2016-04-07-blog-post-example.md
rename to 3rdParty/rocksdb/v5.18.X/docs/doc-type-examples/2016-04-07-blog-post-example.md
diff --git a/3rdParty/rocksdb/v5.16.X/docs/doc-type-examples/docs-hello-world.md b/3rdParty/rocksdb/v5.18.X/docs/doc-type-examples/docs-hello-world.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/doc-type-examples/docs-hello-world.md
rename to 3rdParty/rocksdb/v5.18.X/docs/doc-type-examples/docs-hello-world.md
diff --git a/3rdParty/rocksdb/v5.16.X/docs/doc-type-examples/top-level-example.md b/3rdParty/rocksdb/v5.18.X/docs/doc-type-examples/top-level-example.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/doc-type-examples/top-level-example.md
rename to 3rdParty/rocksdb/v5.18.X/docs/doc-type-examples/top-level-example.md
diff --git a/3rdParty/rocksdb/v5.16.X/docs/docs/index.html b/3rdParty/rocksdb/v5.18.X/docs/docs/index.html
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/docs/index.html
rename to 3rdParty/rocksdb/v5.18.X/docs/docs/index.html
diff --git a/3rdParty/rocksdb/v5.16.X/docs/feed.xml b/3rdParty/rocksdb/v5.18.X/docs/feed.xml
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/docs/feed.xml
rename to 3rdParty/rocksdb/v5.18.X/docs/feed.xml
index 590cbd9d76..725f00566c 100644
--- a/3rdParty/rocksdb/v5.16.X/docs/feed.xml
+++ b/3rdParty/rocksdb/v5.18.X/docs/feed.xml
@@ -6,7 +6,7 @@ layout: null
   <channel>
     <title>{{ site.title | xml_escape }}</title>
     <description>{{ site.description | xml_escape }}</description>
-    <link>{{ absolute_url }}/</link>
+    <link>https://rocksdb.org/feed.xml</link>
     <atom:link href="{{ '/feed.xml' | absolute_url }}" rel="self" type="application/rss+xml"/>
     <pubDate>{{ site.time | date_to_rfc822 }}</pubDate>
     <lastBuildDate>{{ site.time | date_to_rfc822 }}</lastBuildDate>
diff --git a/3rdParty/rocksdb/v5.16.X/docs/index.md b/3rdParty/rocksdb/v5.18.X/docs/index.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/index.md
rename to 3rdParty/rocksdb/v5.18.X/docs/index.md
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/favicon.png b/3rdParty/rocksdb/v5.18.X/docs/static/favicon.png
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/favicon.png
rename to 3rdParty/rocksdb/v5.18.X/docs/static/favicon.png
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Black.woff b/3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Black.woff
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Black.woff
rename to 3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Black.woff
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Black.woff2 b/3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Black.woff2
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Black.woff2
rename to 3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Black.woff2
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-BlackItalic.woff b/3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-BlackItalic.woff
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-BlackItalic.woff
rename to 3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-BlackItalic.woff
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-BlackItalic.woff2 b/3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-BlackItalic.woff2
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-BlackItalic.woff2
rename to 3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-BlackItalic.woff2
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Italic.woff b/3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Italic.woff
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Italic.woff
rename to 3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Italic.woff
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Italic.woff2 b/3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Italic.woff2
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Italic.woff2
rename to 3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Italic.woff2
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Light.woff b/3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Light.woff
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Light.woff
rename to 3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Light.woff
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Light.woff2 b/3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Light.woff2
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Light.woff2
rename to 3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Light.woff2
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Regular.woff b/3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Regular.woff
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Regular.woff
rename to 3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Regular.woff
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Regular.woff2 b/3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Regular.woff2
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/fonts/LatoLatin-Regular.woff2
rename to 3rdParty/rocksdb/v5.18.X/docs/static/fonts/LatoLatin-Regular.woff2
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/Resize-of-20140327_200754-300x225.jpg b/3rdParty/rocksdb/v5.18.X/docs/static/images/Resize-of-20140327_200754-300x225.jpg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/Resize-of-20140327_200754-300x225.jpg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/Resize-of-20140327_200754-300x225.jpg
diff --git a/3rdParty/rocksdb/v5.18.X/docs/static/images/binaryseek.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/binaryseek.png
new file mode 100644
index 0000000000..0e213f0482
Binary files /dev/null and b/3rdParty/rocksdb/v5.18.X/docs/static/images/binaryseek.png differ
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/compaction/full-range.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/compaction/full-range.png
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/compaction/full-range.png
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/compaction/full-range.png
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/compaction/l0-l1-contend.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/compaction/l0-l1-contend.png
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/compaction/l0-l1-contend.png
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/compaction/l0-l1-contend.png
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/compaction/l1-l2-contend.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/compaction/l1-l2-contend.png
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/compaction/l1-l2-contend.png
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/compaction/l1-l2-contend.png
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/compaction/part-range-old.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/compaction/part-range-old.png
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/compaction/part-range-old.png
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/compaction/part-range-old.png
diff --git a/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_collapsed.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_collapsed.png
new file mode 100644
index 0000000000..52246c2c1d
Binary files /dev/null and b/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_collapsed.png differ
diff --git a/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_key_schema.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_key_schema.png
new file mode 100644
index 0000000000..0a14d4a3a5
Binary files /dev/null and b/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_key_schema.png differ
diff --git a/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_sst_blocks.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_sst_blocks.png
new file mode 100644
index 0000000000..6003e42ae8
Binary files /dev/null and b/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_sst_blocks.png differ
diff --git a/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_uncollapsed.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_uncollapsed.png
new file mode 100644
index 0000000000..39c7097af9
Binary files /dev/null and b/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_uncollapsed.png differ
diff --git a/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_write_path.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_write_path.png
new file mode 100644
index 0000000000..229dfb349a
Binary files /dev/null and b/3rdParty/rocksdb/v5.18.X/docs/static/images/delrange/delrange_write_path.png differ
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-blockindex.jpg b/3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-blockindex.jpg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-blockindex.jpg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-blockindex.jpg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-fileindex.jpg b/3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-fileindex.jpg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-fileindex.jpg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-fileindex.jpg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-filelayout.jpg b/3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-filelayout.jpg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-filelayout.jpg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-filelayout.jpg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-readiopath.jpg b/3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-readiopath.jpg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-readiopath.jpg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-readiopath.jpg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-tieredstorage.jpg b/3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-tieredstorage.jpg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-tieredstorage.jpg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-tieredstorage.jpg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-writeiopath.jpg b/3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-writeiopath.jpg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/pcache-writeiopath.jpg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/pcache-writeiopath.jpg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/promo-adapt.svg b/3rdParty/rocksdb/v5.18.X/docs/static/images/promo-adapt.svg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/promo-adapt.svg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/promo-adapt.svg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/promo-flash.svg b/3rdParty/rocksdb/v5.18.X/docs/static/images/promo-flash.svg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/promo-flash.svg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/promo-flash.svg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/promo-operations.svg b/3rdParty/rocksdb/v5.18.X/docs/static/images/promo-operations.svg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/promo-operations.svg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/promo-operations.svg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/promo-performance.svg b/3rdParty/rocksdb/v5.18.X/docs/static/images/promo-performance.svg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/promo-performance.svg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/promo-performance.svg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/rate-limiter/auto-tuned-write-KBps-series.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/rate-limiter/auto-tuned-write-KBps-series.png
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/rate-limiter/auto-tuned-write-KBps-series.png
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/rate-limiter/auto-tuned-write-KBps-series.png
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/rate-limiter/write-KBps-cdf.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/rate-limiter/write-KBps-cdf.png
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/rate-limiter/write-KBps-cdf.png
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/rate-limiter/write-KBps-cdf.png
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/rate-limiter/write-KBps-series.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/rate-limiter/write-KBps-series.png
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/rate-limiter/write-KBps-series.png
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/rate-limiter/write-KBps-series.png
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/images/tree_example1.png b/3rdParty/rocksdb/v5.18.X/docs/static/images/tree_example1.png
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/images/tree_example1.png
rename to 3rdParty/rocksdb/v5.18.X/docs/static/images/tree_example1.png
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/logo.svg b/3rdParty/rocksdb/v5.18.X/docs/static/logo.svg
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/logo.svg
rename to 3rdParty/rocksdb/v5.18.X/docs/static/logo.svg
diff --git a/3rdParty/rocksdb/v5.16.X/docs/static/og_image.png b/3rdParty/rocksdb/v5.18.X/docs/static/og_image.png
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/docs/static/og_image.png
rename to 3rdParty/rocksdb/v5.18.X/docs/static/og_image.png
diff --git a/3rdParty/rocksdb/v5.16.X/env/env.cc b/3rdParty/rocksdb/v5.18.X/env/env.cc
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/env/env.cc
rename to 3rdParty/rocksdb/v5.18.X/env/env.cc
index 9b7f5e40de..a41feaf00e 100644
--- a/3rdParty/rocksdb/v5.16.X/env/env.cc
+++ b/3rdParty/rocksdb/v5.18.X/env/env.cc
@@ -43,7 +43,7 @@ uint64_t Env::GetThreadID() const {
 
 Status Env::ReuseWritableFile(const std::string& fname,
                               const std::string& old_fname,
-                              unique_ptr<WritableFile>* result,
+                              std::unique_ptr<WritableFile>* result,
                               const EnvOptions& options) {
   Status s = RenameFile(old_fname, fname);
   if (!s.ok()) {
@@ -242,11 +242,11 @@ void Fatal(Logger* info_log, const char* format, ...) {
   va_end(ap);
 }
 
-void LogFlush(const shared_ptr<Logger>& info_log) {
+void LogFlush(const std::shared_ptr<Logger>& info_log) {
   LogFlush(info_log.get());
 }
 
-void Log(const InfoLogLevel log_level, const shared_ptr<Logger>& info_log,
+void Log(const InfoLogLevel log_level, const std::shared_ptr<Logger>& info_log,
          const char* format, ...) {
   va_list ap;
   va_start(ap, format);
@@ -254,49 +254,49 @@ void Log(const InfoLogLevel log_level, const shared_ptr<Logger>& info_log,
   va_end(ap);
 }
 
-void Header(const shared_ptr<Logger>& info_log, const char* format, ...) {
+void Header(const std::shared_ptr<Logger>& info_log, const char* format, ...) {
   va_list ap;
   va_start(ap, format);
   Headerv(info_log.get(), format, ap);
   va_end(ap);
 }
 
-void Debug(const shared_ptr<Logger>& info_log, const char* format, ...) {
+void Debug(const std::shared_ptr<Logger>& info_log, const char* format, ...) {
   va_list ap;
   va_start(ap, format);
   Debugv(info_log.get(), format, ap);
   va_end(ap);
 }
 
-void Info(const shared_ptr<Logger>& info_log, const char* format, ...) {
+void Info(const std::shared_ptr<Logger>& info_log, const char* format, ...) {
   va_list ap;
   va_start(ap, format);
   Infov(info_log.get(), format, ap);
   va_end(ap);
 }
 
-void Warn(const shared_ptr<Logger>& info_log, const char* format, ...) {
+void Warn(const std::shared_ptr<Logger>& info_log, const char* format, ...) {
   va_list ap;
   va_start(ap, format);
   Warnv(info_log.get(), format, ap);
   va_end(ap);
 }
 
-void Error(const shared_ptr<Logger>& info_log, const char* format, ...) {
+void Error(const std::shared_ptr<Logger>& info_log, const char* format, ...) {
   va_list ap;
   va_start(ap, format);
   Errorv(info_log.get(), format, ap);
   va_end(ap);
 }
 
-void Fatal(const shared_ptr<Logger>& info_log, const char* format, ...) {
+void Fatal(const std::shared_ptr<Logger>& info_log, const char* format, ...) {
   va_list ap;
   va_start(ap, format);
   Fatalv(info_log.get(), format, ap);
   va_end(ap);
 }
 
-void Log(const shared_ptr<Logger>& info_log, const char* format, ...) {
+void Log(const std::shared_ptr<Logger>& info_log, const char* format, ...) {
   va_list ap;
   va_start(ap, format);
   Logv(info_log.get(), format, ap);
@@ -305,7 +305,7 @@ void Log(const shared_ptr<Logger>& info_log, const char* format, ...) {
 
 Status WriteStringToFile(Env* env, const Slice& data, const std::string& fname,
                          bool should_sync) {
-  unique_ptr<WritableFile> file;
+  std::unique_ptr<WritableFile> file;
   EnvOptions soptions;
   Status s = env->NewWritableFile(fname, &file, soptions);
   if (!s.ok()) {
@@ -324,7 +324,7 @@ Status WriteStringToFile(Env* env, const Slice& data, const std::string& fname,
 Status ReadFileToString(Env* env, const std::string& fname, std::string* data) {
   EnvOptions soptions;
   data->clear();
-  unique_ptr<SequentialFile> file;
+  std::unique_ptr<SequentialFile> file;
   Status s = env->NewSequentialFile(fname, &file, soptions);
   if (!s.ok()) {
     return s;
diff --git a/3rdParty/rocksdb/v5.16.X/env/env_basic_test.cc b/3rdParty/rocksdb/v5.18.X/env/env_basic_test.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/env/env_basic_test.cc
rename to 3rdParty/rocksdb/v5.18.X/env/env_basic_test.cc
index e05f61aa65..22983dbecd 100644
--- a/3rdParty/rocksdb/v5.16.X/env/env_basic_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/env/env_basic_test.cc
@@ -133,7 +133,7 @@ INSTANTIATE_TEST_CASE_P(CustomEnv, EnvMoreTestWithParam,
 
 TEST_P(EnvBasicTestWithParam, Basics) {
   uint64_t file_size;
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   std::vector<std::string> children;
 
   // Check that the directory is empty.
@@ -186,8 +186,8 @@ TEST_P(EnvBasicTestWithParam, Basics) {
   ASSERT_EQ(0U, file_size);
 
   // Check that opening non-existent file fails.
-  unique_ptr<SequentialFile> seq_file;
-  unique_ptr<RandomAccessFile> rand_file;
+  std::unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<RandomAccessFile> rand_file;
   ASSERT_TRUE(!env_->NewSequentialFile(test_dir_ + "/non_existent", &seq_file,
                                        soptions_)
                    .ok());
@@ -208,9 +208,9 @@ TEST_P(EnvBasicTestWithParam, Basics) {
 }
 
 TEST_P(EnvBasicTestWithParam, ReadWrite) {
-  unique_ptr<WritableFile> writable_file;
-  unique_ptr<SequentialFile> seq_file;
-  unique_ptr<RandomAccessFile> rand_file;
+  std::unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<RandomAccessFile> rand_file;
   Slice result;
   char scratch[100];
 
@@ -247,7 +247,7 @@ TEST_P(EnvBasicTestWithParam, ReadWrite) {
 }
 
 TEST_P(EnvBasicTestWithParam, Misc) {
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   ASSERT_OK(env_->NewWritableFile(test_dir_ + "/b", &writable_file, soptions_));
 
   // These are no-ops, but we test they return success.
@@ -266,14 +266,14 @@ TEST_P(EnvBasicTestWithParam, LargeWrite) {
     write_data.append(1, static_cast<char>(i));
   }
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   ASSERT_OK(env_->NewWritableFile(test_dir_ + "/f", &writable_file, soptions_));
   ASSERT_OK(writable_file->Append("foo"));
   ASSERT_OK(writable_file->Append(write_data));
   ASSERT_OK(writable_file->Close());
   writable_file.reset();
 
-  unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<SequentialFile> seq_file;
   Slice result;
   ASSERT_OK(env_->NewSequentialFile(test_dir_ + "/f", &seq_file, soptions_));
   ASSERT_OK(seq_file->Read(3, &result, scratch));  // Read "foo".
@@ -340,7 +340,7 @@ TEST_P(EnvMoreTestWithParam, GetChildren) {
 
   // if dir is a file, returns IOError
   ASSERT_OK(env_->CreateDir(test_dir_));
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   ASSERT_OK(
       env_->NewWritableFile(test_dir_ + "/file", &writable_file, soptions_));
   ASSERT_OK(writable_file->Close());
diff --git a/3rdParty/rocksdb/v5.16.X/env/env_chroot.cc b/3rdParty/rocksdb/v5.18.X/env/env_chroot.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/env/env_chroot.cc
rename to 3rdParty/rocksdb/v5.18.X/env/env_chroot.cc
index 6a1fda8a83..f6236c81b2 100644
--- a/3rdParty/rocksdb/v5.16.X/env/env_chroot.cc
+++ b/3rdParty/rocksdb/v5.18.X/env/env_chroot.cc
@@ -50,7 +50,7 @@ class ChrootEnv : public EnvWrapper {
   }
 
   virtual Status NewRandomAccessFile(const std::string& fname,
-                                     unique_ptr<RandomAccessFile>* result,
+                                     std::unique_ptr<RandomAccessFile>* result,
                                      const EnvOptions& options) override {
     auto status_and_enc_path = EncodePathWithNewBasename(fname);
     if (!status_and_enc_path.first.ok()) {
@@ -61,7 +61,7 @@ class ChrootEnv : public EnvWrapper {
   }
 
   virtual Status NewWritableFile(const std::string& fname,
-                                 unique_ptr<WritableFile>* result,
+                                 std::unique_ptr<WritableFile>* result,
                                  const EnvOptions& options) override {
     auto status_and_enc_path = EncodePathWithNewBasename(fname);
     if (!status_and_enc_path.first.ok()) {
@@ -73,7 +73,7 @@ class ChrootEnv : public EnvWrapper {
 
   virtual Status ReuseWritableFile(const std::string& fname,
                                    const std::string& old_fname,
-                                   unique_ptr<WritableFile>* result,
+                                   std::unique_ptr<WritableFile>* result,
                                    const EnvOptions& options) override {
     auto status_and_enc_path = EncodePathWithNewBasename(fname);
     if (!status_and_enc_path.first.ok()) {
@@ -89,7 +89,7 @@ class ChrootEnv : public EnvWrapper {
   }
 
   virtual Status NewRandomRWFile(const std::string& fname,
-                                 unique_ptr<RandomRWFile>* result,
+                                 std::unique_ptr<RandomRWFile>* result,
                                  const EnvOptions& options) override {
     auto status_and_enc_path = EncodePathWithNewBasename(fname);
     if (!status_and_enc_path.first.ok()) {
@@ -100,7 +100,7 @@ class ChrootEnv : public EnvWrapper {
   }
 
   virtual Status NewDirectory(const std::string& dir,
-                              unique_ptr<Directory>* result) override {
+                              std::unique_ptr<Directory>* result) override {
     auto status_and_enc_path = EncodePathWithNewBasename(dir);
     if (!status_and_enc_path.first.ok()) {
       return status_and_enc_path.first;
@@ -238,7 +238,7 @@ class ChrootEnv : public EnvWrapper {
   }
 
   virtual Status NewLogger(const std::string& fname,
-                           shared_ptr<Logger>* result) override {
+                           std::shared_ptr<Logger>* result) override {
     auto status_and_enc_path = EncodePathWithNewBasename(fname);
     if (!status_and_enc_path.first.ok()) {
       return status_and_enc_path.first;
diff --git a/3rdParty/rocksdb/v5.16.X/env/env_chroot.h b/3rdParty/rocksdb/v5.18.X/env/env_chroot.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/env/env_chroot.h
rename to 3rdParty/rocksdb/v5.18.X/env/env_chroot.h
diff --git a/3rdParty/rocksdb/v5.16.X/env/env_encryption.cc b/3rdParty/rocksdb/v5.18.X/env/env_encryption.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/env/env_encryption.cc
rename to 3rdParty/rocksdb/v5.18.X/env/env_encryption.cc
index e80796fe0c..e38693e3ce 100644
--- a/3rdParty/rocksdb/v5.16.X/env/env_encryption.cc
+++ b/3rdParty/rocksdb/v5.18.X/env/env_encryption.cc
@@ -422,7 +422,7 @@ class EncryptedEnv : public EnvWrapper {
 
   // NewRandomAccessFile opens a file for random read access.
   virtual Status NewRandomAccessFile(const std::string& fname,
-                                     unique_ptr<RandomAccessFile>* result,
+                                     std::unique_ptr<RandomAccessFile>* result,
                                      const EnvOptions& options) override {
     result->reset();
     if (options.use_mmap_reads) {
@@ -456,10 +456,10 @@ class EncryptedEnv : public EnvWrapper {
     (*result) = std::unique_ptr<RandomAccessFile>(new EncryptedRandomAccessFile(underlying.release(), stream.release(), prefixLength));
     return Status::OK();
   }
-  
+
   // NewWritableFile opens a file for sequential writing.
   virtual Status NewWritableFile(const std::string& fname,
-                                 unique_ptr<WritableFile>* result,
+                                 std::unique_ptr<WritableFile>* result,
                                  const EnvOptions& options) override {
     result->reset();
     if (options.use_mmap_writes) {
@@ -505,8 +505,8 @@ class EncryptedEnv : public EnvWrapper {
   //
   // The returned file will only be accessed by one thread at a time.
   virtual Status ReopenWritableFile(const std::string& fname,
-                                   unique_ptr<WritableFile>* result,
-                                   const EnvOptions& options) override {
+                                    std::unique_ptr<WritableFile>* result,
+                                    const EnvOptions& options) override {
     result->reset();
     if (options.use_mmap_writes) {
       return Status::InvalidArgument();
@@ -546,7 +546,7 @@ class EncryptedEnv : public EnvWrapper {
   // Reuse an existing file by renaming it and opening it as writable.
   virtual Status ReuseWritableFile(const std::string& fname,
                                    const std::string& old_fname,
-                                   unique_ptr<WritableFile>* result,
+                                   std::unique_ptr<WritableFile>* result,
                                    const EnvOptions& options) override {
     result->reset();
     if (options.use_mmap_writes) {
@@ -590,7 +590,7 @@ class EncryptedEnv : public EnvWrapper {
   //
   // The returned file will only be accessed by one thread at a time.
   virtual Status NewRandomRWFile(const std::string& fname,
-                                 unique_ptr<RandomRWFile>* result,
+                                 std::unique_ptr<RandomRWFile>* result,
                                  const EnvOptions& options) override {
     result->reset();
     if (options.use_mmap_reads || options.use_mmap_writes) {
@@ -692,7 +692,7 @@ Status BlockAccessCipherStream::Encrypt(uint64_t fileOffset, char *data, size_t
   auto blockSize = BlockSize();
   uint64_t blockIndex = fileOffset / blockSize;
   size_t blockOffset = fileOffset % blockSize;
-  unique_ptr<char[]> blockBuffer;
+  std::unique_ptr<char[]> blockBuffer;
 
   std::string scratch;
   AllocateScratch(scratch);
@@ -705,8 +705,8 @@ Status BlockAccessCipherStream::Encrypt(uint64_t fileOffset, char *data, size_t
       // We're not encrypting a full block. 
       // Copy data to blockBuffer
       if (!blockBuffer.get()) {
-        // Allocate buffer 
-        blockBuffer = unique_ptr<char[]>(new char[blockSize]);
+        // Allocate buffer
+        blockBuffer = std::unique_ptr<char[]>(new char[blockSize]);
       }
       block = blockBuffer.get();
       // Copy plain data to block buffer 
@@ -737,7 +737,7 @@ Status BlockAccessCipherStream::Decrypt(uint64_t fileOffset, char *data, size_t
   auto blockSize = BlockSize();
   uint64_t blockIndex = fileOffset / blockSize;
   size_t blockOffset = fileOffset % blockSize;
-  unique_ptr<char[]> blockBuffer;
+  std::unique_ptr<char[]> blockBuffer;
 
   std::string scratch;
   AllocateScratch(scratch);
@@ -750,8 +750,8 @@ Status BlockAccessCipherStream::Decrypt(uint64_t fileOffset, char *data, size_t
       // We're not decrypting a full block. 
       // Copy data to blockBuffer
       if (!blockBuffer.get()) {
-        // Allocate buffer 
-        blockBuffer = unique_ptr<char[]>(new char[blockSize]);
+        // Allocate buffer
+        blockBuffer = std::unique_ptr<char[]>(new char[blockSize]);
       }
       block = blockBuffer.get();
       // Copy encrypted data to block buffer 
@@ -882,7 +882,9 @@ size_t CTREncryptionProvider::PopulateSecretPrefixPart(char* /*prefix*/,
   return 0;
 }
 
-Status CTREncryptionProvider::CreateCipherStream(const std::string& fname, const EnvOptions& options, Slice &prefix, unique_ptr<BlockAccessCipherStream>* result) {
+Status CTREncryptionProvider::CreateCipherStream(
+    const std::string& fname, const EnvOptions& options, Slice& prefix,
+    std::unique_ptr<BlockAccessCipherStream>* result) {
   // Read plain text part of prefix.
   auto blockSize = cipher_.BlockSize();
   uint64_t initialCounter;
@@ -905,8 +907,9 @@ Status CTREncryptionProvider::CreateCipherStream(const std::string& fname, const
 Status CTREncryptionProvider::CreateCipherStreamFromPrefix(
     const std::string& /*fname*/, const EnvOptions& /*options*/,
     uint64_t initialCounter, const Slice& iv, const Slice& /*prefix*/,
-    unique_ptr<BlockAccessCipherStream>* result) {
-  (*result) = unique_ptr<BlockAccessCipherStream>(new CTRCipherStream(cipher_, iv.data(), initialCounter));
+    std::unique_ptr<BlockAccessCipherStream>* result) {
+  (*result) = std::unique_ptr<BlockAccessCipherStream>(
+      new CTRCipherStream(cipher_, iv.data(), initialCounter));
   return Status::OK();
 }
 
diff --git a/3rdParty/rocksdb/v5.16.X/env/env_hdfs.cc b/3rdParty/rocksdb/v5.18.X/env/env_hdfs.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/env/env_hdfs.cc
rename to 3rdParty/rocksdb/v5.18.X/env/env_hdfs.cc
index 1eaea3a1ce..14fb902f0d 100644
--- a/3rdParty/rocksdb/v5.16.X/env/env_hdfs.cc
+++ b/3rdParty/rocksdb/v5.18.X/env/env_hdfs.cc
@@ -381,7 +381,7 @@ const std::string HdfsEnv::pathsep = "/";
 
 // open a file for sequential reading
 Status HdfsEnv::NewSequentialFile(const std::string& fname,
-                                  unique_ptr<SequentialFile>* result,
+                                  std::unique_ptr<SequentialFile>* result,
                                   const EnvOptions& options) {
   result->reset();
   HdfsReadableFile* f = new HdfsReadableFile(fileSys_, fname);
@@ -396,7 +396,7 @@ Status HdfsEnv::NewSequentialFile(const std::string& fname,
 
 // open a file for random reading
 Status HdfsEnv::NewRandomAccessFile(const std::string& fname,
-                                    unique_ptr<RandomAccessFile>* result,
+                                    std::unique_ptr<RandomAccessFile>* result,
                                     const EnvOptions& options) {
   result->reset();
   HdfsReadableFile* f = new HdfsReadableFile(fileSys_, fname);
@@ -411,7 +411,7 @@ Status HdfsEnv::NewRandomAccessFile(const std::string& fname,
 
 // create a new file for writing
 Status HdfsEnv::NewWritableFile(const std::string& fname,
-                                unique_ptr<WritableFile>* result,
+                                std::unique_ptr<WritableFile>* result,
                                 const EnvOptions& options) {
   result->reset();
   Status s;
@@ -437,7 +437,7 @@ class HdfsDirectory : public Directory {
 };
 
 Status HdfsEnv::NewDirectory(const std::string& name,
-                             unique_ptr<Directory>* result) {
+                             std::unique_ptr<Directory>* result) {
   int value = hdfsExists(fileSys_, name.c_str());
   switch (value) {
     case HDFS_EXISTS:
@@ -581,7 +581,7 @@ Status HdfsEnv::UnlockFile(FileLock* lock) {
 }
 
 Status HdfsEnv::NewLogger(const std::string& fname,
-                          shared_ptr<Logger>* result) {
+                          std::shared_ptr<Logger>* result) {
   HdfsWritableFile* f = new HdfsWritableFile(fileSys_, fname);
   if (f == nullptr || !f->isValid()) {
     delete f;
@@ -610,10 +610,10 @@ Status NewHdfsEnv(Env** hdfs_env, const std::string& fsname) {
 // dummy placeholders used when HDFS is not available
 namespace rocksdb {
 Status HdfsEnv::NewSequentialFile(const std::string& /*fname*/,
-                                  unique_ptr<SequentialFile>* /*result*/,
+                                  std::unique_ptr<SequentialFile>* /*result*/,
                                   const EnvOptions& /*options*/) {
   return Status::NotSupported("Not compiled with hdfs support");
- }
+}
 
  Status NewHdfsEnv(Env** /*hdfs_env*/, const std::string& /*fsname*/) {
    return Status::NotSupported("Not compiled with hdfs support");
diff --git a/3rdParty/rocksdb/v5.16.X/env/env_posix.cc b/3rdParty/rocksdb/v5.18.X/env/env_posix.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/env/env_posix.cc
rename to 3rdParty/rocksdb/v5.18.X/env/env_posix.cc
index ae8088f657..c2e456a661 100644
--- a/3rdParty/rocksdb/v5.16.X/env/env_posix.cc
+++ b/3rdParty/rocksdb/v5.18.X/env/env_posix.cc
@@ -25,6 +25,7 @@
 #include <sys/syscall.h>
 #include <sys/sysmacros.h>
 #endif
+#include <sys/statvfs.h>
 #include <sys/time.h>
 #include <sys/types.h>
 #include <time.h>
@@ -102,6 +103,18 @@ class PosixFileLock : public FileLock {
   std::string filename;
 };
 
+int cloexec_flags(int flags, const EnvOptions* options) {
+  // If the system supports opening the file with cloexec enabled,
+  // do so, as this avoids a race condition if a db is opened around
+  // the same time that a child process is forked
+#ifdef O_CLOEXEC
+  if (options == nullptr || options->set_fd_cloexec) {
+    flags |= O_CLOEXEC;
+  }
+#endif
+  return flags;
+}
+
 class PosixEnv : public Env {
  public:
   PosixEnv();
@@ -129,11 +142,11 @@ class PosixEnv : public Env {
   }
 
   virtual Status NewSequentialFile(const std::string& fname,
-                                   unique_ptr<SequentialFile>* result,
+                                   std::unique_ptr<SequentialFile>* result,
                                    const EnvOptions& options) override {
     result->reset();
     int fd = -1;
-    int flags = O_RDONLY;
+    int flags = cloexec_flags(O_RDONLY, &options);
     FILE* file = nullptr;
 
     if (options.use_direct_reads && !options.use_mmap_reads) {
@@ -179,12 +192,13 @@ class PosixEnv : public Env {
   }
 
   virtual Status NewRandomAccessFile(const std::string& fname,
-                                     unique_ptr<RandomAccessFile>* result,
+                                     std::unique_ptr<RandomAccessFile>* result,
                                      const EnvOptions& options) override {
     result->reset();
     Status s;
     int fd;
-    int flags = O_RDONLY;
+    int flags = cloexec_flags(O_RDONLY, &options);
+
     if (options.use_direct_reads && !options.use_mmap_reads) {
 #ifdef ROCKSDB_LITE
       return Status::IOError(fname, "Direct I/O not supported in RocksDB lite");
@@ -235,7 +249,7 @@ class PosixEnv : public Env {
   }
 
   virtual Status OpenWritableFile(const std::string& fname,
-                                  unique_ptr<WritableFile>* result,
+                                  std::unique_ptr<WritableFile>* result,
                                   const EnvOptions& options,
                                   bool reopen = false) {
     result->reset();
@@ -266,6 +280,8 @@ class PosixEnv : public Env {
       flags |= O_WRONLY;
     }
 
+    flags = cloexec_flags(flags, &options);
+
     do {
       IOSTATS_TIMER_GUARD(open_nanos);
       fd = open(fname.c_str(), flags, GetDBFileMode(allow_non_owner_access_));
@@ -317,20 +333,20 @@ class PosixEnv : public Env {
   }
 
   virtual Status NewWritableFile(const std::string& fname,
-                                 unique_ptr<WritableFile>* result,
+                                 std::unique_ptr<WritableFile>* result,
                                  const EnvOptions& options) override {
     return OpenWritableFile(fname, result, options, false);
   }
 
   virtual Status ReopenWritableFile(const std::string& fname,
-                                    unique_ptr<WritableFile>* result,
+                                    std::unique_ptr<WritableFile>* result,
                                     const EnvOptions& options) override {
     return OpenWritableFile(fname, result, options, true);
   }
 
   virtual Status ReuseWritableFile(const std::string& fname,
                                    const std::string& old_fname,
-                                   unique_ptr<WritableFile>* result,
+                                   std::unique_ptr<WritableFile>* result,
                                    const EnvOptions& options) override {
     result->reset();
     Status s;
@@ -354,6 +370,8 @@ class PosixEnv : public Env {
       flags |= O_WRONLY;
     }
 
+    flags = cloexec_flags(flags, &options);
+
     do {
       IOSTATS_TIMER_GUARD(open_nanos);
       fd = open(old_fname.c_str(), flags,
@@ -412,12 +430,15 @@ class PosixEnv : public Env {
   }
 
   virtual Status NewRandomRWFile(const std::string& fname,
-                                 unique_ptr<RandomRWFile>* result,
+                                 std::unique_ptr<RandomRWFile>* result,
                                  const EnvOptions& options) override {
     int fd = -1;
+    int flags = cloexec_flags(O_RDWR, &options);
+
     while (fd < 0) {
       IOSTATS_TIMER_GUARD(open_nanos);
-      fd = open(fname.c_str(), O_RDWR, GetDBFileMode(allow_non_owner_access_));
+
+      fd = open(fname.c_str(), flags, GetDBFileMode(allow_non_owner_access_));
       if (fd < 0) {
         // Error while opening the file
         if (errno == EINTR) {
@@ -434,12 +455,14 @@ class PosixEnv : public Env {
 
   virtual Status NewMemoryMappedFileBuffer(
       const std::string& fname,
-      unique_ptr<MemoryMappedFileBuffer>* result) override {
+      std::unique_ptr<MemoryMappedFileBuffer>* result) override {
     int fd = -1;
     Status status;
+    int flags = cloexec_flags(O_RDWR, nullptr);
+
     while (fd < 0) {
       IOSTATS_TIMER_GUARD(open_nanos);
-      fd = open(fname.c_str(), O_RDWR, 0644);
+      fd = open(fname.c_str(), flags, 0644);
       if (fd < 0) {
         // Error while opening the file
         if (errno == EINTR) {
@@ -474,12 +497,13 @@ class PosixEnv : public Env {
   }
 
   virtual Status NewDirectory(const std::string& name,
-                              unique_ptr<Directory>* result) override {
+                              std::unique_ptr<Directory>* result) override {
     result->reset();
     int fd;
+    int flags = cloexec_flags(0, nullptr);
     {
       IOSTATS_TIMER_GUARD(open_nanos);
-      fd = open(name.c_str(), 0);
+      fd = open(name.c_str(), flags);
     }
     if (fd < 0) {
       return IOError("While open directory", name, errno);
@@ -496,7 +520,8 @@ class PosixEnv : public Env {
       return Status::OK();
     }
 
-    switch (errno) {
+    int err = errno;
+    switch (err) {
       case EACCES:
       case ELOOP:
       case ENAMETOOLONG:
@@ -504,8 +529,8 @@ class PosixEnv : public Env {
       case ENOTDIR:
         return Status::NotFound();
       default:
-        assert(result == EIO || result == ENOMEM);
-        return Status::IOError("Unexpected error(" + ToString(result) +
+        assert(err == EIO || err == ENOMEM);
+        return Status::IOError("Unexpected error(" + ToString(err) +
                                ") accessing file `" + fname + "' ");
     }
   }
@@ -663,9 +688,11 @@ class PosixEnv : public Env {
     }
 
     int fd;
+    int flags = cloexec_flags(O_RDWR | O_CREAT, nullptr);
+
     {
       IOSTATS_TIMER_GUARD(open_nanos);
-      fd = open(fname.c_str(), O_RDWR | O_CREAT, 0644);
+      fd = open(fname.c_str(), flags, 0644);
     }
     if (fd < 0) {
       result = IOError("while open a file for lock", fname, errno);
@@ -751,12 +778,30 @@ class PosixEnv : public Env {
     return gettid(pthread_self());
   }
 
+  virtual Status GetFreeSpace(const std::string& fname,
+                              uint64_t* free_space) override {
+    struct statvfs sbuf;
+
+    if (statvfs(fname.c_str(), &sbuf) < 0) {
+      return IOError("While doing statvfs", fname, errno);
+    }
+
+    *free_space = ((uint64_t)sbuf.f_bsize * sbuf.f_bfree);
+    return Status::OK();
+  }
+
   virtual Status NewLogger(const std::string& fname,
-                           shared_ptr<Logger>* result) override {
+                           std::shared_ptr<Logger>* result) override {
     FILE* f;
     {
       IOSTATS_TIMER_GUARD(open_nanos);
-      f = fopen(fname.c_str(), "w");
+      f = fopen(fname.c_str(), "w"
+#ifdef __GLIBC_PREREQ
+#if __GLIBC_PREREQ(2, 7)
+          "e" // glibc extension to enable O_CLOEXEC
+#endif
+#endif
+          );
     }
     if (f == nullptr) {
       result->reset();
diff --git a/3rdParty/rocksdb/v5.16.X/env/env_test.cc b/3rdParty/rocksdb/v5.18.X/env/env_test.cc
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/env/env_test.cc
rename to 3rdParty/rocksdb/v5.18.X/env/env_test.cc
index eda6b9d5d7..36cbd735d7 100644
--- a/3rdParty/rocksdb/v5.16.X/env/env_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/env/env_test.cc
@@ -181,11 +181,11 @@ TEST_F(EnvPosixTest, DISABLED_FilePermission) {
     std::vector<std::string> fileNames{
         test::PerThreadDBPath(env_, "testfile"),
         test::PerThreadDBPath(env_, "testfile1")};
-    unique_ptr<WritableFile> wfile;
+    std::unique_ptr<WritableFile> wfile;
     ASSERT_OK(env_->NewWritableFile(fileNames[0], &wfile, soptions));
     ASSERT_OK(env_->NewWritableFile(fileNames[1], &wfile, soptions));
     wfile.reset();
-    unique_ptr<RandomRWFile> rwfile;
+    std::unique_ptr<RandomRWFile> rwfile;
     ASSERT_OK(env_->NewRandomRWFile(fileNames[1], &rwfile, soptions));
 
     struct stat sb;
@@ -217,7 +217,7 @@ TEST_F(EnvPosixTest, MemoryMappedFileBuffer) {
   std::string expected_data;
   std::string fname = test::PerThreadDBPath(env_, "testfile");
   {
-    unique_ptr<WritableFile> wfile;
+    std::unique_ptr<WritableFile> wfile;
     const EnvOptions soptions;
     ASSERT_OK(env_->NewWritableFile(fname, &wfile, soptions));
 
@@ -812,7 +812,7 @@ class IoctlFriendlyTmpdir {
 
 #ifndef ROCKSDB_LITE
 TEST_F(EnvPosixTest, PositionedAppend) {
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   EnvOptions options;
   options.use_direct_writes = true;
   options.use_mmap_writes = false;
@@ -832,7 +832,7 @@ TEST_F(EnvPosixTest, PositionedAppend) {
   // The file now has 1 sector worth of a followed by a page worth of b
 
   // Verify the above
-  unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<SequentialFile> seq_file;
   ASSERT_OK(env_->NewSequentialFile(ift.name() + "/f", &seq_file, options));
   char scratch[kPageSize * 2];
   Slice result;
@@ -851,10 +851,10 @@ TEST_P(EnvPosixTestWithParam, RandomAccessUniqueID) {
     soptions.use_direct_reads = soptions.use_direct_writes = direct_io_;
     IoctlFriendlyTmpdir ift;
     std::string fname = ift.name() + "/testfile";
-    unique_ptr<WritableFile> wfile;
+    std::unique_ptr<WritableFile> wfile;
     ASSERT_OK(env_->NewWritableFile(fname, &wfile, soptions));
 
-    unique_ptr<RandomAccessFile> file;
+    std::unique_ptr<RandomAccessFile> file;
 
     // Get Unique ID
     ASSERT_OK(env_->NewRandomAccessFile(fname, &file, soptions));
@@ -921,7 +921,7 @@ TEST_P(EnvPosixTestWithParam, AllocateTest) {
     EnvOptions soptions;
     soptions.use_mmap_writes = false;
     soptions.use_direct_reads = soptions.use_direct_writes = direct_io_;
-    unique_ptr<WritableFile> wfile;
+    std::unique_ptr<WritableFile> wfile;
     ASSERT_OK(env_->NewWritableFile(fname, &wfile, soptions));
 
     // allocate 100 MB
@@ -990,14 +990,14 @@ TEST_P(EnvPosixTestWithParam, RandomAccessUniqueIDConcurrent) {
       fnames.push_back(ift.name() + "/" + "testfile" + ToString(i));
 
       // Create file.
-      unique_ptr<WritableFile> wfile;
+      std::unique_ptr<WritableFile> wfile;
       ASSERT_OK(env_->NewWritableFile(fnames[i], &wfile, soptions));
     }
 
     // Collect and check whether the IDs are unique.
     std::unordered_set<std::string> ids;
     for (const std::string fname : fnames) {
-      unique_ptr<RandomAccessFile> file;
+      std::unique_ptr<RandomAccessFile> file;
       std::string unique_id;
       ASSERT_OK(env_->NewRandomAccessFile(fname, &file, soptions));
       size_t id_size = file->GetUniqueId(temp_id, MAX_ID_SIZE);
@@ -1033,14 +1033,14 @@ TEST_P(EnvPosixTestWithParam, RandomAccessUniqueIDDeletes) {
     for (int i = 0; i < 1000; ++i) {
       // Create file.
       {
-        unique_ptr<WritableFile> wfile;
+        std::unique_ptr<WritableFile> wfile;
         ASSERT_OK(env_->NewWritableFile(fname, &wfile, soptions));
       }
 
       // Get Unique ID
       std::string unique_id;
       {
-        unique_ptr<RandomAccessFile> file;
+        std::unique_ptr<RandomAccessFile> file;
         ASSERT_OK(env_->NewRandomAccessFile(fname, &file, soptions));
         size_t id_size = file->GetUniqueId(temp_id, MAX_ID_SIZE);
         ASSERT_TRUE(id_size > 0);
@@ -1076,7 +1076,7 @@ TEST_P(EnvPosixTestWithParam, InvalidateCache) {
 
     // Create file.
     {
-      unique_ptr<WritableFile> wfile;
+      std::unique_ptr<WritableFile> wfile;
 #if !defined(OS_MACOSX) && !defined(OS_WIN) && !defined(OS_SOLARIS) && !defined(OS_AIX)
       if (soptions.use_direct_writes) {
         soptions.use_direct_writes = false;
@@ -1090,7 +1090,7 @@ TEST_P(EnvPosixTestWithParam, InvalidateCache) {
 
     // Random Read
     {
-      unique_ptr<RandomAccessFile> file;
+      std::unique_ptr<RandomAccessFile> file;
       auto scratch = NewAligned(kSectorSize, 0);
       Slice result;
 #if !defined(OS_MACOSX) && !defined(OS_WIN) && !defined(OS_SOLARIS) && !defined(OS_AIX)
@@ -1107,7 +1107,7 @@ TEST_P(EnvPosixTestWithParam, InvalidateCache) {
 
     // Sequential Read
     {
-      unique_ptr<SequentialFile> file;
+      std::unique_ptr<SequentialFile> file;
       auto scratch = NewAligned(kSectorSize, 0);
       Slice result;
 #if !defined(OS_MACOSX) && !defined(OS_WIN) && !defined(OS_SOLARIS) && !defined(OS_AIX)
@@ -1252,7 +1252,7 @@ TEST_P(EnvPosixTestWithParam, LogBufferMaxSizeTest) {
 TEST_P(EnvPosixTestWithParam, Preallocation) {
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
   const std::string src = test::PerThreadDBPath(env_, "testfile");
-  unique_ptr<WritableFile> srcfile;
+  std::unique_ptr<WritableFile> srcfile;
   EnvOptions soptions;
   soptions.use_direct_reads = soptions.use_direct_writes = direct_io_;
 #if !defined(OS_MACOSX) && !defined(OS_WIN) && !defined(OS_SOLARIS) && !defined(OS_AIX) && !defined(OS_OPENBSD) && !defined(OS_FREEBSD)
@@ -1315,7 +1315,7 @@ TEST_P(EnvPosixTestWithParam, ConsistentChildrenAttributes) {
     for (int i = 0; i < kNumChildren; ++i) {
       const std::string path =
           test::TmpDir(env_) + "/" + "testfile_" + std::to_string(i);
-      unique_ptr<WritableFile> file;
+      std::unique_ptr<WritableFile> file;
 #if !defined(OS_MACOSX) && !defined(OS_WIN) && !defined(OS_SOLARIS) && !defined(OS_AIX) && !defined(OS_OPENBSD) && !defined(OS_FREEBSD)
       if (soptions.use_direct_writes) {
         rocksdb::SyncPoint::GetInstance()->SetCallBack(
@@ -1368,50 +1368,110 @@ TEST_P(EnvPosixTestWithParam, WritableFileWrapper) {
       inc(1);
       return Status::OK();
     }
-    Status Truncate(uint64_t /*size*/) override { return Status::OK(); }
-    Status Close() override { inc(2); return Status::OK(); }
-    Status Flush() override { inc(3); return Status::OK(); }
-    Status Sync() override { inc(4); return Status::OK(); }
-    Status Fsync() override { inc(5); return Status::OK(); }
-    void SetIOPriority(Env::IOPriority /*pri*/) override { inc(6); }
-    uint64_t GetFileSize() override { inc(7); return 0; }
-    void GetPreallocationStatus(size_t* /*block_size*/,
-                                size_t* /*last_allocated_block*/) override {
-      inc(8);
-    }
-    size_t GetUniqueId(char* /*id*/, size_t /*max_size*/) const override {
-      inc(9);
-      return 0;
-    }
-    Status InvalidateCache(size_t /*offset*/, size_t /*length*/) override {
-      inc(10);
+
+    Status PositionedAppend(const Slice& /*data*/,
+                            uint64_t /*offset*/) override {
+      inc(2);
       return Status::OK();
     }
 
-   protected:
-    Status Allocate(uint64_t /*offset*/, uint64_t /*len*/) override {
-      inc(11);
+    Status Truncate(uint64_t /*size*/) override {
+      inc(3);
       return Status::OK();
     }
-    Status RangeSync(uint64_t /*offset*/, uint64_t /*nbytes*/) override {
+
+    Status Close() override {
+      inc(4);
+      return Status::OK();
+    }
+
+    Status Flush() override {
+      inc(5);
+      return Status::OK();
+    }
+
+    Status Sync() override {
+      inc(6);
+      return Status::OK();
+    }
+
+    Status Fsync() override {
+      inc(7);
+      return Status::OK();
+    }
+
+    bool IsSyncThreadSafe() const override {
+      inc(8);
+      return true;
+    }
+
+    bool use_direct_io() const override {
+      inc(9);
+      return true;
+    }
+
+    size_t GetRequiredBufferAlignment() const override {
+      inc(10);
+      return 0;
+    }
+
+    void SetIOPriority(Env::IOPriority /*pri*/) override { inc(11); }
+
+    Env::IOPriority GetIOPriority() override {
       inc(12);
+      return Env::IOPriority::IO_LOW;
+    }
+
+    void SetWriteLifeTimeHint(Env::WriteLifeTimeHint /*hint*/) override {
+      inc(13);
+    }
+
+    Env::WriteLifeTimeHint GetWriteLifeTimeHint() override {
+      inc(14);
+      return Env::WriteLifeTimeHint::WLTH_NOT_SET;
+    }
+
+    uint64_t GetFileSize() override {
+      inc(15);
+      return 0;
+    }
+
+    void SetPreallocationBlockSize(size_t /*size*/) override { inc(16); }
+
+    void GetPreallocationStatus(size_t* /*block_size*/,
+                                size_t* /*last_allocated_block*/) override {
+      inc(17);
+    }
+
+    size_t GetUniqueId(char* /*id*/, size_t /*max_size*/) const override {
+      inc(18);
+      return 0;
+    }
+
+    Status InvalidateCache(size_t /*offset*/, size_t /*length*/) override {
+      inc(19);
+      return Status::OK();
+    }
+
+    Status RangeSync(uint64_t /*offset*/, uint64_t /*nbytes*/) override {
+      inc(20);
+      return Status::OK();
+    }
+
+    void PrepareWrite(size_t /*offset*/, size_t /*len*/) override { inc(21); }
+
+    Status Allocate(uint64_t /*offset*/, uint64_t /*len*/) override {
+      inc(22);
       return Status::OK();
     }
 
    public:
-    ~Base() {
-      inc(13);
-    }
+    ~Base() { inc(23); }
   };
 
   class Wrapper : public WritableFileWrapper {
    public:
     explicit Wrapper(WritableFile* target) : WritableFileWrapper(target) {}
-
-    void CallProtectedMethods() {
-      Allocate(0, 0);
-      RangeSync(0, 0);
-    }
   };
 
   int step = 0;
@@ -1420,19 +1480,30 @@ TEST_P(EnvPosixTestWithParam, WritableFileWrapper) {
     Base b(&step);
     Wrapper w(&b);
     w.Append(Slice());
+    w.PositionedAppend(Slice(), 0);
+    w.Truncate(0);
     w.Close();
     w.Flush();
     w.Sync();
     w.Fsync();
+    w.IsSyncThreadSafe();
+    w.use_direct_io();
+    w.GetRequiredBufferAlignment();
     w.SetIOPriority(Env::IOPriority::IO_HIGH);
+    w.GetIOPriority();
+    w.SetWriteLifeTimeHint(Env::WriteLifeTimeHint::WLTH_NOT_SET);
+    w.GetWriteLifeTimeHint();
     w.GetFileSize();
+    w.SetPreallocationBlockSize(0);
     w.GetPreallocationStatus(nullptr, nullptr);
     w.GetUniqueId(nullptr, 0);
     w.InvalidateCache(0, 0);
-    w.CallProtectedMethods();
+    w.RangeSync(0, 0);
+    w.PrepareWrite(0, 0);
+    w.Allocate(0, 0);
   }
 
-  EXPECT_EQ(14, step);
+  EXPECT_EQ(24, step);
 }
 
 TEST_P(EnvPosixTestWithParam, PosixRandomRWFile) {
@@ -1567,7 +1638,7 @@ TEST_P(EnvPosixTestWithParam, PosixRandomRWFileRandomized) {
   const std::string path = test::PerThreadDBPath(env_, "random_rw_file_rand");
   env_->DeleteFile(path);
 
-  unique_ptr<RandomRWFile> file;
+  std::unique_ptr<RandomRWFile> file;
 
 #ifdef OS_LINUX
   // Cannot open non-existing file.
@@ -1641,7 +1712,7 @@ class TestEnv : public EnvWrapper {
   int GetCloseCount() { return close_count; }
 
   virtual Status NewLogger(const std::string& /*fname*/,
-                           shared_ptr<Logger>* result) {
+                           std::shared_ptr<Logger>* result) {
     result->reset(new TestLogger(this));
     return Status::OK();
   }
@@ -1685,8 +1756,8 @@ INSTANTIATE_TEST_CASE_P(DefaultEnvWithDirectIO, EnvPosixTestWithParam,
 #endif  // !defined(ROCKSDB_LITE)
 
 #if !defined(ROCKSDB_LITE) && !defined(OS_WIN)
-static unique_ptr<Env> chroot_env(NewChrootEnv(Env::Default(),
-                                               test::TmpDir(Env::Default())));
+static std::unique_ptr<Env> chroot_env(
+    NewChrootEnv(Env::Default(), test::TmpDir(Env::Default())));
 INSTANTIATE_TEST_CASE_P(
     ChrootEnvWithoutDirectIO, EnvPosixTestWithParam,
     ::testing::Values(std::pair<Env*, bool>(chroot_env.get(), false)));
diff --git a/3rdParty/rocksdb/v5.16.X/env/io_posix.cc b/3rdParty/rocksdb/v5.18.X/env/io_posix.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/env/io_posix.cc
rename to 3rdParty/rocksdb/v5.18.X/env/io_posix.cc
diff --git a/3rdParty/rocksdb/v5.16.X/env/io_posix.h b/3rdParty/rocksdb/v5.18.X/env/io_posix.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/env/io_posix.h
rename to 3rdParty/rocksdb/v5.18.X/env/io_posix.h
diff --git a/3rdParty/rocksdb/v5.16.X/env/mock_env.cc b/3rdParty/rocksdb/v5.18.X/env/mock_env.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/env/mock_env.cc
rename to 3rdParty/rocksdb/v5.18.X/env/mock_env.cc
index 9b019260dd..84b3060717 100644
--- a/3rdParty/rocksdb/v5.16.X/env/mock_env.cc
+++ b/3rdParty/rocksdb/v5.18.X/env/mock_env.cc
@@ -201,7 +201,7 @@ class MockSequentialFile : public SequentialFile {
     if (n > available) {
       n = available;
     }
-    pos_ += n;
+    pos_ += static_cast<size_t>(n);
     return Status::OK();
   }
 
@@ -319,7 +319,7 @@ class TestMemLogger : public Logger {
   static const uint64_t flush_every_seconds_ = 5;
   std::atomic_uint_fast64_t last_flush_micros_;
   Env* env_;
-  bool flush_pending_;
+  std::atomic<bool> flush_pending_;
 
  public:
   TestMemLogger(std::unique_ptr<WritableFile> f, Env* env,
@@ -424,7 +424,7 @@ MockEnv::~MockEnv() {
 
 // Partial implementation of the Env interface.
 Status MockEnv::NewSequentialFile(const std::string& fname,
-                                  unique_ptr<SequentialFile>* result,
+                                  std::unique_ptr<SequentialFile>* result,
                                   const EnvOptions& /*soptions*/) {
   auto fn = NormalizePath(fname);
   MutexLock lock(&mutex_);
@@ -441,7 +441,7 @@ Status MockEnv::NewSequentialFile(const std::string& fname,
 }
 
 Status MockEnv::NewRandomAccessFile(const std::string& fname,
-                                    unique_ptr<RandomAccessFile>* result,
+                                    std::unique_ptr<RandomAccessFile>* result,
                                     const EnvOptions& /*soptions*/) {
   auto fn = NormalizePath(fname);
   MutexLock lock(&mutex_);
@@ -458,7 +458,7 @@ Status MockEnv::NewRandomAccessFile(const std::string& fname,
 }
 
 Status MockEnv::NewRandomRWFile(const std::string& fname,
-                                unique_ptr<RandomRWFile>* result,
+                                std::unique_ptr<RandomRWFile>* result,
                                 const EnvOptions& /*soptions*/) {
   auto fn = NormalizePath(fname);
   MutexLock lock(&mutex_);
@@ -476,7 +476,7 @@ Status MockEnv::NewRandomRWFile(const std::string& fname,
 
 Status MockEnv::ReuseWritableFile(const std::string& fname,
                                   const std::string& old_fname,
-                                  unique_ptr<WritableFile>* result,
+                                  std::unique_ptr<WritableFile>* result,
                                   const EnvOptions& options) {
   auto s = RenameFile(old_fname, fname);
   if (!s.ok()) {
@@ -487,7 +487,7 @@ Status MockEnv::ReuseWritableFile(const std::string& fname,
 }
 
 Status MockEnv::NewWritableFile(const std::string& fname,
-                                unique_ptr<WritableFile>* result,
+                                std::unique_ptr<WritableFile>* result,
                                 const EnvOptions& env_options) {
   auto fn = NormalizePath(fname);
   MutexLock lock(&mutex_);
@@ -503,7 +503,7 @@ Status MockEnv::NewWritableFile(const std::string& fname,
 }
 
 Status MockEnv::NewDirectory(const std::string& /*name*/,
-                             unique_ptr<Directory>* result) {
+                             std::unique_ptr<Directory>* result) {
   result->reset(new MockEnvDirectory());
   return Status::OK();
 }
@@ -660,7 +660,7 @@ Status MockEnv::LinkFile(const std::string& src, const std::string& dest) {
 }
 
 Status MockEnv::NewLogger(const std::string& fname,
-                          shared_ptr<Logger>* result) {
+                          std::shared_ptr<Logger>* result) {
   auto fn = NormalizePath(fname);
   MutexLock lock(&mutex_);
   auto iter = file_map_.find(fn);
diff --git a/3rdParty/rocksdb/v5.16.X/env/mock_env.h b/3rdParty/rocksdb/v5.18.X/env/mock_env.h
similarity index 87%
rename from 3rdParty/rocksdb/v5.16.X/env/mock_env.h
rename to 3rdParty/rocksdb/v5.18.X/env/mock_env.h
index 816256ab08..87b8deaf8c 100644
--- a/3rdParty/rocksdb/v5.16.X/env/mock_env.h
+++ b/3rdParty/rocksdb/v5.18.X/env/mock_env.h
@@ -28,28 +28,28 @@ class MockEnv : public EnvWrapper {
 
   // Partial implementation of the Env interface.
   virtual Status NewSequentialFile(const std::string& fname,
-                                   unique_ptr<SequentialFile>* result,
+                                   std::unique_ptr<SequentialFile>* result,
                                    const EnvOptions& soptions) override;
 
   virtual Status NewRandomAccessFile(const std::string& fname,
-                                     unique_ptr<RandomAccessFile>* result,
+                                     std::unique_ptr<RandomAccessFile>* result,
                                      const EnvOptions& soptions) override;
 
   virtual Status NewRandomRWFile(const std::string& fname,
-                                 unique_ptr<RandomRWFile>* result,
+                                 std::unique_ptr<RandomRWFile>* result,
                                  const EnvOptions& options) override;
 
   virtual Status ReuseWritableFile(const std::string& fname,
                                    const std::string& old_fname,
-                                   unique_ptr<WritableFile>* result,
+                                   std::unique_ptr<WritableFile>* result,
                                    const EnvOptions& options) override;
 
   virtual Status NewWritableFile(const std::string& fname,
-                                 unique_ptr<WritableFile>* result,
+                                 std::unique_ptr<WritableFile>* result,
                                  const EnvOptions& env_options) override;
 
   virtual Status NewDirectory(const std::string& name,
-                              unique_ptr<Directory>* result) override;
+                              std::unique_ptr<Directory>* result) override;
 
   virtual Status FileExists(const std::string& fname) override;
 
@@ -81,7 +81,7 @@ class MockEnv : public EnvWrapper {
                           const std::string& target) override;
 
   virtual Status NewLogger(const std::string& fname,
-                           shared_ptr<Logger>* result) override;
+                           std::shared_ptr<Logger>* result) override;
 
   virtual Status LockFile(const std::string& fname, FileLock** flock) override;
 
diff --git a/3rdParty/rocksdb/v5.16.X/env/mock_env_test.cc b/3rdParty/rocksdb/v5.18.X/env/mock_env_test.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/env/mock_env_test.cc
rename to 3rdParty/rocksdb/v5.18.X/env/mock_env_test.cc
index 19e259ccd8..abd5b89f0b 100644
--- a/3rdParty/rocksdb/v5.16.X/env/mock_env_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/env/mock_env_test.cc
@@ -29,7 +29,7 @@ TEST_F(MockEnvTest, Corrupt) {
   const std::string kGood = "this is a good string, synced to disk";
   const std::string kCorrupted = "this part may be corrupted";
   const std::string kFileName = "/dir/f";
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   ASSERT_OK(env_->NewWritableFile(kFileName, &writable_file, soptions_));
   ASSERT_OK(writable_file->Append(kGood));
   ASSERT_TRUE(writable_file->GetFileSize() == kGood.size());
@@ -37,7 +37,7 @@ TEST_F(MockEnvTest, Corrupt) {
   std::string scratch;
   scratch.resize(kGood.size() + kCorrupted.size() + 16);
   Slice result;
-  unique_ptr<RandomAccessFile> rand_file;
+  std::unique_ptr<RandomAccessFile> rand_file;
   ASSERT_OK(env_->NewRandomAccessFile(kFileName, &rand_file, soptions_));
   ASSERT_OK(rand_file->Read(0, kGood.size(), &result, &(scratch[0])));
   ASSERT_EQ(result.compare(kGood), 0);
diff --git a/3rdParty/rocksdb/v5.16.X/env/posix_logger.h b/3rdParty/rocksdb/v5.18.X/env/posix_logger.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/env/posix_logger.h
rename to 3rdParty/rocksdb/v5.18.X/env/posix_logger.h
index e983ba704e..401df6a3ff 100644
--- a/3rdParty/rocksdb/v5.16.X/env/posix_logger.h
+++ b/3rdParty/rocksdb/v5.18.X/env/posix_logger.h
@@ -165,7 +165,6 @@ class PosixLogger : public Logger {
 
       size_t sz = fwrite(base, 1, write_size, file_);
       flush_pending_ = true;
-      assert(sz == write_size);
       if (sz > 0) {
         log_size_ += write_size;
       }
diff --git a/3rdParty/rocksdb/v5.16.X/examples/.gitignore b/3rdParty/rocksdb/v5.18.X/examples/.gitignore
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/.gitignore
rename to 3rdParty/rocksdb/v5.18.X/examples/.gitignore
diff --git a/3rdParty/rocksdb/v5.16.X/examples/Makefile b/3rdParty/rocksdb/v5.18.X/examples/Makefile
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/Makefile
rename to 3rdParty/rocksdb/v5.18.X/examples/Makefile
diff --git a/3rdParty/rocksdb/v5.16.X/examples/README.md b/3rdParty/rocksdb/v5.18.X/examples/README.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/README.md
rename to 3rdParty/rocksdb/v5.18.X/examples/README.md
diff --git a/3rdParty/rocksdb/v5.16.X/examples/c_simple_example.c b/3rdParty/rocksdb/v5.18.X/examples/c_simple_example.c
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/c_simple_example.c
rename to 3rdParty/rocksdb/v5.18.X/examples/c_simple_example.c
diff --git a/3rdParty/rocksdb/v5.16.X/examples/column_families_example.cc b/3rdParty/rocksdb/v5.18.X/examples/column_families_example.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/column_families_example.cc
rename to 3rdParty/rocksdb/v5.18.X/examples/column_families_example.cc
diff --git a/3rdParty/rocksdb/v5.16.X/examples/compact_files_example.cc b/3rdParty/rocksdb/v5.18.X/examples/compact_files_example.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/compact_files_example.cc
rename to 3rdParty/rocksdb/v5.18.X/examples/compact_files_example.cc
diff --git a/3rdParty/rocksdb/v5.16.X/examples/compaction_filter_example.cc b/3rdParty/rocksdb/v5.18.X/examples/compaction_filter_example.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/compaction_filter_example.cc
rename to 3rdParty/rocksdb/v5.18.X/examples/compaction_filter_example.cc
diff --git a/3rdParty/rocksdb/v5.16.X/examples/optimistic_transaction_example.cc b/3rdParty/rocksdb/v5.18.X/examples/optimistic_transaction_example.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/optimistic_transaction_example.cc
rename to 3rdParty/rocksdb/v5.18.X/examples/optimistic_transaction_example.cc
diff --git a/3rdParty/rocksdb/v5.16.X/examples/options_file_example.cc b/3rdParty/rocksdb/v5.18.X/examples/options_file_example.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/options_file_example.cc
rename to 3rdParty/rocksdb/v5.18.X/examples/options_file_example.cc
diff --git a/3rdParty/rocksdb/v5.16.X/examples/rocksdb_option_file_example.ini b/3rdParty/rocksdb/v5.18.X/examples/rocksdb_option_file_example.ini
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/rocksdb_option_file_example.ini
rename to 3rdParty/rocksdb/v5.18.X/examples/rocksdb_option_file_example.ini
diff --git a/3rdParty/rocksdb/v5.16.X/examples/simple_example.cc b/3rdParty/rocksdb/v5.18.X/examples/simple_example.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/simple_example.cc
rename to 3rdParty/rocksdb/v5.18.X/examples/simple_example.cc
diff --git a/3rdParty/rocksdb/v5.16.X/examples/transaction_example.cc b/3rdParty/rocksdb/v5.18.X/examples/transaction_example.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/examples/transaction_example.cc
rename to 3rdParty/rocksdb/v5.18.X/examples/transaction_example.cc
diff --git a/3rdParty/rocksdb/v5.16.X/hdfs/README b/3rdParty/rocksdb/v5.18.X/hdfs/README
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/hdfs/README
rename to 3rdParty/rocksdb/v5.18.X/hdfs/README
diff --git a/3rdParty/rocksdb/v5.16.X/hdfs/env_hdfs.h b/3rdParty/rocksdb/v5.18.X/hdfs/env_hdfs.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/hdfs/env_hdfs.h
rename to 3rdParty/rocksdb/v5.18.X/hdfs/env_hdfs.h
index b0c9e33fd7..a77c42e0af 100644
--- a/3rdParty/rocksdb/v5.16.X/hdfs/env_hdfs.h
+++ b/3rdParty/rocksdb/v5.18.X/hdfs/env_hdfs.h
@@ -255,23 +255,24 @@ class HdfsEnv : public Env {
   }
 
   virtual Status NewSequentialFile(const std::string& fname,
-                                   unique_ptr<SequentialFile>* result,
+                                   std::unique_ptr<SequentialFile>* result,
                                    const EnvOptions& options) override;
 
-  virtual Status NewRandomAccessFile(const std::string& /*fname*/,
-                                     unique_ptr<RandomAccessFile>* /*result*/,
-                                     const EnvOptions& /*options*/) override {
+  virtual Status NewRandomAccessFile(
+      const std::string& /*fname*/,
+      std::unique_ptr<RandomAccessFile>* /*result*/,
+      const EnvOptions& /*options*/) override {
     return notsup;
   }
 
   virtual Status NewWritableFile(const std::string& /*fname*/,
-                                 unique_ptr<WritableFile>* /*result*/,
+                                 std::unique_ptr<WritableFile>* /*result*/,
                                  const EnvOptions& /*options*/) override {
     return notsup;
   }
 
   virtual Status NewDirectory(const std::string& /*name*/,
-                              unique_ptr<Directory>* /*result*/) override {
+                              std::unique_ptr<Directory>* /*result*/) override {
     return notsup;
   }
 
@@ -328,7 +329,7 @@ class HdfsEnv : public Env {
   virtual Status UnlockFile(FileLock* /*lock*/) override { return notsup; }
 
   virtual Status NewLogger(const std::string& /*fname*/,
-                           shared_ptr<Logger>* /*result*/) override {
+                           std::shared_ptr<Logger>* /*result*/) override {
     return notsup;
   }
 
diff --git a/3rdParty/rocksdb/v5.16.X/hdfs/setup.sh b/3rdParty/rocksdb/v5.18.X/hdfs/setup.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/hdfs/setup.sh
rename to 3rdParty/rocksdb/v5.18.X/hdfs/setup.sh
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/advanced_options.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/advanced_options.h
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/advanced_options.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/advanced_options.h
index 940a6f6b74..fe331482e2 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/advanced_options.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/advanced_options.h
@@ -413,6 +413,7 @@ struct AdvancedColumnFamilyOptions {
   //    of the level.
   // At the same time max_bytes_for_level_multiplier and
   // max_bytes_for_level_multiplier_additional are still satisfied.
+  // (When L0 is too large, we make some adjustment. See below.)
   //
   // With this option on, from an empty DB, we make last level the base level,
   // which means merging L0 data into the last level, until it exceeds
@@ -451,6 +452,29 @@ struct AdvancedColumnFamilyOptions {
   // max_bytes_for_level_base, for a more predictable LSM tree shape. It is
   // useful to limit worse case space amplification.
   //
+  //
+  // If the compaction from L0 is lagged behind, a special mode will be turned
+  // on to prioritize write amplification against max_bytes_for_level_multiplier
+  // or max_bytes_for_level_base. The L0 compaction is lagged behind by looking
+  // at number of L0 files and total L0 size. If number of L0 files is at least
+  // the double of level0_file_num_compaction_trigger, or the total size is
+  // at least max_bytes_for_level_base, this mode is on. The target of L1 grows
+  // to the actual data size in L0, and then determine the target for each level
+  // so that each level will have the same level multiplier.
+  //
+  // For example, when L0 size is 100MB, the size of last level is 1600MB,
+  // max_bytes_for_level_base = 80MB, and max_bytes_for_level_multiplier = 10.
+  // Since L0 size is larger than max_bytes_for_level_base, this is a L0
+  // compaction backlogged mode. So that the L1 size is determined to be 100MB.
+  // Based on max_bytes_for_level_multiplier = 10, at least 3 non-0 levels will
+  // be needed. The level multiplier will be calculated to be 4 and the three
+  // levels' target to be [100MB, 400MB, 1600MB].
+  //
+  // In this mode, The number of levels will be no more than the normal mode,
+  // and the level multiplier will be lower. The write amplification will
+  // likely to be reduced.
+  //
+  //
   // max_bytes_for_level_multiplier_additional is ignored with this flag on.
   //
   // Turning this feature on or off for an existing DB can cause unexpected
@@ -478,19 +502,25 @@ struct AdvancedColumnFamilyOptions {
   // threshold. But it's not guaranteed.
   // Value 0 will be sanitized.
   //
-  // Default: result.target_file_size_base * 25
+  // Default: target_file_size_base * 25
+  //
+  // Dynamically changeable through SetOptions() API
   uint64_t max_compaction_bytes = 0;
 
   // All writes will be slowed down to at least delayed_write_rate if estimated
   // bytes needed to be compaction exceed this threshold.
   //
   // Default: 64GB
+  //
+  // Dynamically changeable through SetOptions() API
   uint64_t soft_pending_compaction_bytes_limit = 64 * 1073741824ull;
 
   // All writes are stopped if estimated bytes needed to be compaction exceed
   // this threshold.
   //
   // Default: 256GB
+  //
+  // Dynamically changeable through SetOptions() API
   uint64_t hard_pending_compaction_bytes_limit = 256 * 1073741824ull;
 
   // The compaction style. Default: kCompactionStyleLevel
@@ -502,13 +532,17 @@ struct AdvancedColumnFamilyOptions {
   CompactionPri compaction_pri = kByCompensatedSize;
 
   // The options needed to support Universal Style compactions
+  //
+  // Dynamically changeable through SetOptions() API
+  // Dynamic change example:
+  // SetOptions("compaction_options_universal", "{size_ratio=2;}")
   CompactionOptionsUniversal compaction_options_universal;
 
   // The options for FIFO compaction style
   //
   // Dynamically changeable through SetOptions() API
   // Dynamic change example:
-  // SetOption("compaction_options_fifo", "{max_table_files_size=100;ttl=2;}")
+  // SetOptions("compaction_options_fifo", "{max_table_files_size=100;ttl=2;}")
   CompactionOptionsFIFO compaction_options_fifo;
 
   // An iteration->Next() sequentially skips over keys with the same
@@ -578,7 +612,10 @@ struct AdvancedColumnFamilyOptions {
   bool optimize_filters_for_hits = false;
 
   // After writing every SST file, reopen it and read all the keys.
+  //
   // Default: false
+  //
+  // Dynamically changeable through SetOptions() API
   bool paranoid_file_checks = false;
 
   // In debug mode, RocksDB run consistency checks on the LSM every time the LSM
@@ -588,7 +625,10 @@ struct AdvancedColumnFamilyOptions {
   bool force_consistency_checks = false;
 
   // Measure IO stats in compactions and flushes, if true.
+  //
   // Default: false
+  //
+  // Dynamically changeable through SetOptions() API
   bool report_bg_io_stats = false;
 
   // Non-bottom-level files older than TTL will go through the compaction
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/c.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/c.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/c.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/c.h
index d86b9737d9..cf46054aa3 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/c.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/c.h
@@ -42,9 +42,6 @@
   (5) All of the pointer arguments must be non-NULL.
 */
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_C_H_
-#define STORAGE_ROCKSDB_INCLUDE_C_H_
-
 #pragma once
 
 #ifdef _WIN32
@@ -126,6 +123,8 @@ typedef struct rocksdb_transaction_t rocksdb_transaction_t;
 typedef struct rocksdb_checkpoint_t rocksdb_checkpoint_t;
 typedef struct rocksdb_wal_iterator_t rocksdb_wal_iterator_t;
 typedef struct rocksdb_wal_readoptions_t rocksdb_wal_readoptions_t;
+typedef struct rocksdb_memory_consumers_t rocksdb_memory_consumers_t;
+typedef struct rocksdb_memory_usage_t rocksdb_memory_usage_t;
 
 /* DB operations */
 
@@ -1423,6 +1422,10 @@ extern ROCKSDB_LIBRARY_API const char* rocksdb_livefiles_smallestkey(
     const rocksdb_livefiles_t*, int index, size_t* size);
 extern ROCKSDB_LIBRARY_API const char* rocksdb_livefiles_largestkey(
     const rocksdb_livefiles_t*, int index, size_t* size);
+extern ROCKSDB_LIBRARY_API uint64_t rocksdb_livefiles_entries(
+    const rocksdb_livefiles_t*, int index);
+extern ROCKSDB_LIBRARY_API uint64_t rocksdb_livefiles_deletions(
+    const rocksdb_livefiles_t*, int index);
 extern ROCKSDB_LIBRARY_API void rocksdb_livefiles_destroy(
     const rocksdb_livefiles_t*);
 
@@ -1675,8 +1678,33 @@ extern ROCKSDB_LIBRARY_API void rocksdb_pinnableslice_destroy(
 extern ROCKSDB_LIBRARY_API const char* rocksdb_pinnableslice_value(
     const rocksdb_pinnableslice_t* t, size_t* vlen);
 
+extern ROCKSDB_LIBRARY_API rocksdb_memory_consumers_t*
+    rocksdb_memory_consumers_create();
+extern ROCKSDB_LIBRARY_API void rocksdb_memory_consumers_add_db(
+    rocksdb_memory_consumers_t* consumers, rocksdb_t* db);
+extern ROCKSDB_LIBRARY_API void rocksdb_memory_consumers_add_cache(
+    rocksdb_memory_consumers_t* consumers, rocksdb_cache_t* cache);
+extern ROCKSDB_LIBRARY_API void rocksdb_memory_consumers_destroy(
+    rocksdb_memory_consumers_t* consumers);
+extern ROCKSDB_LIBRARY_API rocksdb_memory_usage_t*
+rocksdb_approximate_memory_usage_create(rocksdb_memory_consumers_t* consumers,
+                                       char** errptr);
+extern ROCKSDB_LIBRARY_API void rocksdb_approximate_memory_usage_destroy(
+    rocksdb_memory_usage_t* usage);
+
+extern ROCKSDB_LIBRARY_API uint64_t
+rocksdb_approximate_memory_usage_get_mem_table_total(
+    rocksdb_memory_usage_t* memory_usage);
+extern ROCKSDB_LIBRARY_API uint64_t
+rocksdb_approximate_memory_usage_get_mem_table_unflushed(
+    rocksdb_memory_usage_t* memory_usage);
+extern ROCKSDB_LIBRARY_API uint64_t
+rocksdb_approximate_memory_usage_get_mem_table_readers_total(
+    rocksdb_memory_usage_t* memory_usage);
+extern ROCKSDB_LIBRARY_API uint64_t
+rocksdb_approximate_memory_usage_get_cache_total(
+    rocksdb_memory_usage_t* memory_usage);
+
 #ifdef __cplusplus
 }  /* end extern "C" */
 #endif
-
-#endif  /* STORAGE_ROCKSDB_INCLUDE_C_H_ */
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/cache.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/cache.h
similarity index 89%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/cache.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/cache.h
index da3b934d83..190112b37e 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/cache.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/cache.h
@@ -25,6 +25,7 @@
 #include <stdint.h>
 #include <memory>
 #include <string>
+#include "rocksdb/memory_allocator.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/statistics.h"
 #include "rocksdb/status.h"
@@ -58,13 +59,24 @@ struct LRUCacheOptions {
   // BlockBasedTableOptions::cache_index_and_filter_blocks_with_high_priority.
   double high_pri_pool_ratio = 0.0;
 
+  // If non-nullptr will use this allocator instead of system allocator when
+  // allocating memory for cache blocks. Call this method before you start using
+  // the cache!
+  //
+  // Caveat: when the cache is used as block cache, the memory allocator is
+  // ignored when dealing with compression libraries that allocate memory
+  // internally (currently only XPRESS).
+  std::shared_ptr<MemoryAllocator> memory_allocator;
+
   LRUCacheOptions() {}
   LRUCacheOptions(size_t _capacity, int _num_shard_bits,
-                  bool _strict_capacity_limit, double _high_pri_pool_ratio)
+                  bool _strict_capacity_limit, double _high_pri_pool_ratio,
+                  std::shared_ptr<MemoryAllocator> _memory_allocator = nullptr)
       : capacity(_capacity),
         num_shard_bits(_num_shard_bits),
         strict_capacity_limit(_strict_capacity_limit),
-        high_pri_pool_ratio(_high_pri_pool_ratio) {}
+        high_pri_pool_ratio(_high_pri_pool_ratio),
+        memory_allocator(std::move(_memory_allocator)) {}
 };
 
 // Create a new cache with a fixed size capacity. The cache is sharded
@@ -75,10 +87,10 @@ struct LRUCacheOptions {
 // high_pri_pool_pct.
 // num_shard_bits = -1 means it is automatically determined: every shard
 // will be at least 512KB and number of shard bits will not exceed 6.
-extern std::shared_ptr<Cache> NewLRUCache(size_t capacity,
-                                          int num_shard_bits = -1,
-                                          bool strict_capacity_limit = false,
-                                          double high_pri_pool_ratio = 0.0);
+extern std::shared_ptr<Cache> NewLRUCache(
+    size_t capacity, int num_shard_bits = -1,
+    bool strict_capacity_limit = false, double high_pri_pool_ratio = 0.0,
+    std::shared_ptr<MemoryAllocator> memory_allocator = nullptr);
 
 extern std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts);
 
@@ -97,7 +109,8 @@ class Cache {
   // likely to get evicted than low priority entries.
   enum class Priority { HIGH, LOW };
 
-  Cache() {}
+  Cache(std::shared_ptr<MemoryAllocator> allocator = nullptr)
+      : memory_allocator_(std::move(allocator)) {}
 
   // Destroys all existing entries by calling the "deleter"
   // function that was passed via the Insert() function.
@@ -228,10 +241,14 @@ class Cache {
   virtual void TEST_mark_as_data_block(const Slice& /*key*/,
                                        size_t /*charge*/) {}
 
+  MemoryAllocator* memory_allocator() const { return memory_allocator_.get(); }
+
  private:
   // No copying allowed
   Cache(const Cache&);
   Cache& operator=(const Cache&);
+
+  std::shared_ptr<MemoryAllocator> memory_allocator_;
 };
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/cleanable.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/cleanable.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/cleanable.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/cleanable.h
index ee4ee44241..6dba8d9531 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/cleanable.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/cleanable.h
@@ -16,8 +16,7 @@
 // non-const method, all threads accessing the same Iterator must use
 // external synchronization.
 
-#ifndef INCLUDE_ROCKSDB_CLEANABLE_H_
-#define INCLUDE_ROCKSDB_CLEANABLE_H_
+#pragma once
 
 namespace rocksdb {
 
@@ -78,5 +77,3 @@ class Cleanable {
 };
 
 }  // namespace rocksdb
-
-#endif  // INCLUDE_ROCKSDB_CLEANABLE_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/compaction_filter.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/compaction_filter.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/compaction_filter.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/compaction_filter.h
index 29b7e50771..98f86c2812 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/compaction_filter.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/compaction_filter.h
@@ -6,8 +6,7 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_COMPACTION_FILTER_H_
-#define STORAGE_ROCKSDB_INCLUDE_COMPACTION_FILTER_H_
+#pragma once
 
 #include <cassert>
 #include <memory>
@@ -206,5 +205,3 @@ class CompactionFilterFactory {
 };
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_COMPACTION_FILTER_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/compaction_job_stats.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/compaction_job_stats.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/compaction_job_stats.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/compaction_job_stats.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/comparator.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/comparator.h
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/comparator.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/comparator.h
index b048ebaf42..12e05ffee7 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/comparator.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/comparator.h
@@ -6,8 +6,7 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_COMPARATOR_H_
-#define STORAGE_ROCKSDB_INCLUDE_COMPARATOR_H_
+#pragma once
 
 #include <string>
 
@@ -92,5 +91,3 @@ extern const Comparator* BytewiseComparator();
 extern const Comparator* ReverseBytewiseComparator();
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_COMPARATOR_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/convenience.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/convenience.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/convenience.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/convenience.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/db.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/db.h
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/db.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/db.h
index 746770836e..6a37084c52 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/db.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/db.h
@@ -6,8 +6,7 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_DB_H_
-#define STORAGE_ROCKSDB_INCLUDE_DB_H_
+#pragma once
 
 #include <stdint.h>
 #include <stdio.h>
@@ -288,16 +287,12 @@ class DB {
   // a non-OK status on error. It is not an error if no keys exist in the range
   // ["begin_key", "end_key").
   //
-  // This feature is currently an experimental performance optimization for
-  // deleting very large ranges of contiguous keys. Invoking it many times or on
-  // small ranges may severely degrade read performance; in particular, the
-  // resulting performance can be worse than calling Delete() for each key in
-  // the range. Note also the degraded read performance affects keys outside the
-  // deleted ranges, and affects database operations involving scans, like flush
-  // and compaction.
-  //
-  // Consider setting ReadOptions::ignore_range_deletions = true to speed
-  // up reads for key(s) that are known to be unaffected by range deletions.
+  // This feature is now usable in production, with the following caveats:
+  // 1) Accumulating many range tombstones in the memtable will degrade read
+  // performance; this can be avoided by manually flushing occasionally.
+  // 2) Limiting the maximum number of open files in the presence of range
+  // tombstones can degrade read performance. To avoid this problem, set
+  // max_open_files to -1 whenever possible.
   virtual Status DeleteRange(const WriteOptions& options,
                              ColumnFamilyHandle* column_family,
                              const Slice& begin_key, const Slice& end_key);
@@ -573,6 +568,11 @@ class DB {
     //      log files that should be kept.
     static const std::string kMinLogNumberToKeep;
 
+    //  "rocksdb.min-obsolete-sst-number-to-keep" - return the minimum file
+    //      number for an obsolete SST to be kept. The max value of `uint64_t`
+    //      will be returned if all obsolete files can be deleted.
+    static const std::string kMinObsoleteSstNumberToKeep;
+
     //  "rocksdb.total-sst-files-size" - returns total size (bytes) of all SST
     //      files.
     //  WARNING: may slow down online queries if there are too many files.
@@ -671,6 +671,7 @@ class DB {
   //  "rocksdb.current-super-version-number"
   //  "rocksdb.estimate-live-data-size"
   //  "rocksdb.min-log-number-to-keep"
+  //  "rocksdb.min-obsolete-sst-number-to-keep"
   //  "rocksdb.total-sst-files-size"
   //  "rocksdb.live-sst-files-size"
   //  "rocksdb.base-level"
@@ -901,11 +902,22 @@ class DB {
   virtual DBOptions GetDBOptions() const = 0;
 
   // Flush all mem-table data.
+  // Flush a single column family, even when atomic flush is enabled. To flush
+  // multiple column families, use Flush(options, column_families).
   virtual Status Flush(const FlushOptions& options,
                        ColumnFamilyHandle* column_family) = 0;
   virtual Status Flush(const FlushOptions& options) {
     return Flush(options, DefaultColumnFamily());
   }
+  // Flushes multiple column families.
+  // If atomic flush is not enabled, Flush(options, column_families) is
+  // equivalent to calling Flush(options, column_family) multiple times.
+  // If atomic flush is enabled, Flush(options, column_families) will flush all
+  // column families specified in 'column_families' up to the latest sequence
+  // number at the time when flush is requested.
+  virtual Status Flush(
+      const FlushOptions& options,
+      const std::vector<ColumnFamilyHandle*>& column_families) = 0;
 
   // Flush the WAL memory buffer to the file. If sync is true, it calls SyncWAL
   // afterwards.
@@ -950,14 +962,14 @@ class DB {
   // GetLiveFiles followed by GetSortedWalFiles can generate a lossless backup
 
   // Retrieve the list of all files in the database. The files are
-  // relative to the dbname and are not absolute paths. The valid size of the
-  // manifest file is returned in manifest_file_size. The manifest file is an
-  // ever growing file, but only the portion specified by manifest_file_size is
-  // valid for this snapshot.
-  // Setting flush_memtable to true does Flush before recording the live files.
-  // Setting flush_memtable to false is useful when we don't want to wait for
-  // flush which may have to wait for compaction to complete taking an
-  // indeterminate time.
+  // relative to the dbname and are not absolute paths. Despite being relative
+  // paths, the file names begin with "/". The valid size of the manifest file
+  // is returned in manifest_file_size. The manifest file is an ever growing
+  // file, but only the portion specified by manifest_file_size is valid for
+  // this snapshot. Setting flush_memtable to true does Flush before recording
+  // the live files. Setting flush_memtable to false is useful when we don't
+  // want to wait for flush which may have to wait for compaction to complete
+  // taking an indeterminate time.
   //
   // In case you have multiple column families, even if flush_memtable is true,
   // you still need to call GetSortedWalFiles after GetLiveFiles to compensate
@@ -980,9 +992,9 @@ class DB {
   // cleared aggressively and the iterator might keep getting invalid before
   // an update is read.
   virtual Status GetUpdatesSince(
-      SequenceNumber seq_number, unique_ptr<TransactionLogIterator>* iter,
-      const TransactionLogIterator::ReadOptions&
-          read_options = TransactionLogIterator::ReadOptions()) = 0;
+      SequenceNumber seq_number, std::unique_ptr<TransactionLogIterator>* iter,
+      const TransactionLogIterator::ReadOptions& read_options =
+          TransactionLogIterator::ReadOptions()) = 0;
 
 // Windows API macro interference
 #undef DeleteFile
@@ -1221,5 +1233,3 @@ Status RepairDB(const std::string& dbname, const Options& options);
 #endif
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_DB_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/db_bench_tool.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/db_bench_tool.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/db_bench_tool.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/db_bench_tool.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/db_dump_tool.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/db_dump_tool.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/db_dump_tool.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/db_dump_tool.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/env.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/env.h
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/env.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/env.h
index c6ca725c52..bc439ac1c4 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/env.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/env.h
@@ -14,8 +14,7 @@
 // All Env implementations are safe for concurrent access from
 // multiple threads without any external synchronization.
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_ENV_H_
-#define STORAGE_ROCKSDB_INCLUDE_ENV_H_
+#pragma once
 
 #include <stdint.h>
 #include <cstdarg>
@@ -138,9 +137,8 @@ class Env {
   //
   // The returned file will only be accessed by one thread at a time.
   virtual Status NewSequentialFile(const std::string& fname,
-                                   unique_ptr<SequentialFile>* result,
-                                   const EnvOptions& options)
-                                   = 0;
+                                   std::unique_ptr<SequentialFile>* result,
+                                   const EnvOptions& options) = 0;
 
   // Create a brand new random access read-only file with the
   // specified name.  On success, stores a pointer to the new file in
@@ -150,9 +148,8 @@ class Env {
   //
   // The returned file may be concurrently accessed by multiple threads.
   virtual Status NewRandomAccessFile(const std::string& fname,
-                                     unique_ptr<RandomAccessFile>* result,
-                                     const EnvOptions& options)
-                                     = 0;
+                                     std::unique_ptr<RandomAccessFile>* result,
+                                     const EnvOptions& options) = 0;
   // These values match Linux definition
   // https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/include/uapi/linux/fcntl.h#n56
   enum WriteLifeTimeHint {
@@ -172,7 +169,7 @@ class Env {
   //
   // The returned file will only be accessed by one thread at a time.
   virtual Status NewWritableFile(const std::string& fname,
-                                 unique_ptr<WritableFile>* result,
+                                 std::unique_ptr<WritableFile>* result,
                                  const EnvOptions& options) = 0;
 
   // Create an object that writes to a new file with the specified
@@ -183,7 +180,7 @@ class Env {
   //
   // The returned file will only be accessed by one thread at a time.
   virtual Status ReopenWritableFile(const std::string& /*fname*/,
-                                    unique_ptr<WritableFile>* /*result*/,
+                                    std::unique_ptr<WritableFile>* /*result*/,
                                     const EnvOptions& /*options*/) {
     return Status::NotSupported();
   }
@@ -191,7 +188,7 @@ class Env {
   // Reuse an existing file by renaming it and opening it as writable.
   virtual Status ReuseWritableFile(const std::string& fname,
                                    const std::string& old_fname,
-                                   unique_ptr<WritableFile>* result,
+                                   std::unique_ptr<WritableFile>* result,
                                    const EnvOptions& options);
 
   // Open `fname` for random read and write, if file doesn't exist the file
@@ -200,7 +197,7 @@ class Env {
   //
   // The returned file will only be accessed by one thread at a time.
   virtual Status NewRandomRWFile(const std::string& /*fname*/,
-                                 unique_ptr<RandomRWFile>* /*result*/,
+                                 std::unique_ptr<RandomRWFile>* /*result*/,
                                  const EnvOptions& /*options*/) {
     return Status::NotSupported("RandomRWFile is not implemented in this Env");
   }
@@ -210,7 +207,7 @@ class Env {
   // file in `*result`. The file must exist prior to this call.
   virtual Status NewMemoryMappedFileBuffer(
       const std::string& /*fname*/,
-      unique_ptr<MemoryMappedFileBuffer>* /*result*/) {
+      std::unique_ptr<MemoryMappedFileBuffer>* /*result*/) {
     return Status::NotSupported(
         "MemoryMappedFileBuffer is not implemented in this Env");
   }
@@ -223,7 +220,7 @@ class Env {
   // *result and returns OK. On failure stores nullptr in *result and
   // returns non-OK.
   virtual Status NewDirectory(const std::string& name,
-                              unique_ptr<Directory>* result) = 0;
+                              std::unique_ptr<Directory>* result) = 0;
 
   // Returns OK if the named file exists.
   //         NotFound if the named file does not exist,
@@ -371,7 +368,7 @@ class Env {
 
   // Create and return a log file for storing informational messages.
   virtual Status NewLogger(const std::string& fname,
-                           shared_ptr<Logger>* result) = 0;
+                           std::shared_ptr<Logger>* result) = 0;
 
   // Returns the number of micro-seconds since some fixed point in time.
   // It is often used as system time such as in GenericRateLimiter
@@ -478,6 +475,15 @@ class Env {
   // Returns the ID of the current thread.
   virtual uint64_t GetThreadID() const;
 
+// This seems to clash with a macro on Windows, so #undef it here
+#undef GetFreeSpace
+
+  // Get the amount of free disk space
+  virtual Status GetFreeSpace(const std::string& /*path*/,
+                              uint64_t* /*diskfree*/) {
+    return Status::NotSupported();
+  }
+
  protected:
   // The pointer to an internal structure that will update the
   // status of each thread.
@@ -934,24 +940,32 @@ class FileLock {
   void operator=(const FileLock&);
 };
 
-extern void LogFlush(const shared_ptr<Logger>& info_log);
+extern void LogFlush(const std::shared_ptr<Logger>& info_log);
 
 extern void Log(const InfoLogLevel log_level,
-                const shared_ptr<Logger>& info_log, const char* format, ...);
+                const std::shared_ptr<Logger>& info_log, const char* format,
+                ...);
 
 // a set of log functions with different log levels.
-extern void Header(const shared_ptr<Logger>& info_log, const char* format, ...);
-extern void Debug(const shared_ptr<Logger>& info_log, const char* format, ...);
-extern void Info(const shared_ptr<Logger>& info_log, const char* format, ...);
-extern void Warn(const shared_ptr<Logger>& info_log, const char* format, ...);
-extern void Error(const shared_ptr<Logger>& info_log, const char* format, ...);
-extern void Fatal(const shared_ptr<Logger>& info_log, const char* format, ...);
+extern void Header(const std::shared_ptr<Logger>& info_log, const char* format,
+                   ...);
+extern void Debug(const std::shared_ptr<Logger>& info_log, const char* format,
+                  ...);
+extern void Info(const std::shared_ptr<Logger>& info_log, const char* format,
+                 ...);
+extern void Warn(const std::shared_ptr<Logger>& info_log, const char* format,
+                 ...);
+extern void Error(const std::shared_ptr<Logger>& info_log, const char* format,
+                  ...);
+extern void Fatal(const std::shared_ptr<Logger>& info_log, const char* format,
+                  ...);
 
 // Log the specified data to *info_log if info_log is non-nullptr.
 // The default info log level is InfoLogLevel::INFO_LEVEL.
-extern void Log(const shared_ptr<Logger>& info_log, const char* format, ...)
+extern void Log(const std::shared_ptr<Logger>& info_log, const char* format,
+                ...)
 #   if defined(__GNUC__) || defined(__clang__)
-    __attribute__((__format__ (__printf__, 2, 3)))
+    __attribute__((__format__(__printf__, 2, 3)))
 #   endif
     ;
 
@@ -997,37 +1011,38 @@ class EnvWrapper : public Env {
   Env* target() const { return target_; }
 
   // The following text is boilerplate that forwards all methods to target()
-  Status NewSequentialFile(const std::string& f, unique_ptr<SequentialFile>* r,
+  Status NewSequentialFile(const std::string& f,
+                           std::unique_ptr<SequentialFile>* r,
                            const EnvOptions& options) override {
     return target_->NewSequentialFile(f, r, options);
   }
   Status NewRandomAccessFile(const std::string& f,
-                             unique_ptr<RandomAccessFile>* r,
+                             std::unique_ptr<RandomAccessFile>* r,
                              const EnvOptions& options) override {
     return target_->NewRandomAccessFile(f, r, options);
   }
-  Status NewWritableFile(const std::string& f, unique_ptr<WritableFile>* r,
+  Status NewWritableFile(const std::string& f, std::unique_ptr<WritableFile>* r,
                          const EnvOptions& options) override {
     return target_->NewWritableFile(f, r, options);
   }
   Status ReopenWritableFile(const std::string& fname,
-                            unique_ptr<WritableFile>* result,
+                            std::unique_ptr<WritableFile>* result,
                             const EnvOptions& options) override {
     return target_->ReopenWritableFile(fname, result, options);
   }
   Status ReuseWritableFile(const std::string& fname,
                            const std::string& old_fname,
-                           unique_ptr<WritableFile>* r,
+                           std::unique_ptr<WritableFile>* r,
                            const EnvOptions& options) override {
     return target_->ReuseWritableFile(fname, old_fname, r, options);
   }
   Status NewRandomRWFile(const std::string& fname,
-                         unique_ptr<RandomRWFile>* result,
+                         std::unique_ptr<RandomRWFile>* result,
                          const EnvOptions& options) override {
     return target_->NewRandomRWFile(fname, result, options);
   }
   Status NewDirectory(const std::string& name,
-                      unique_ptr<Directory>* result) override {
+                      std::unique_ptr<Directory>* result) override {
     return target_->NewDirectory(name, result);
   }
   Status FileExists(const std::string& f) override {
@@ -1105,7 +1120,7 @@ class EnvWrapper : public Env {
     return target_->GetTestDirectory(path);
   }
   Status NewLogger(const std::string& fname,
-                   shared_ptr<Logger>* result) override {
+                   std::shared_ptr<Logger>* result) override {
     return target_->NewLogger(fname, result);
   }
   uint64_t NowMicros() override { return target_->NowMicros(); }
@@ -1216,36 +1231,57 @@ class WritableFileWrapper : public WritableFile {
   Status Sync() override { return target_->Sync(); }
   Status Fsync() override { return target_->Fsync(); }
   bool IsSyncThreadSafe() const override { return target_->IsSyncThreadSafe(); }
+
+  bool use_direct_io() const override { return target_->use_direct_io(); }
+
+  size_t GetRequiredBufferAlignment() const override {
+    return target_->GetRequiredBufferAlignment();
+  }
+
   void SetIOPriority(Env::IOPriority pri) override {
     target_->SetIOPriority(pri);
   }
+
   Env::IOPriority GetIOPriority() override { return target_->GetIOPriority(); }
+
+  void SetWriteLifeTimeHint(Env::WriteLifeTimeHint hint) override {
+    target_->SetWriteLifeTimeHint(hint);
+  }
+
+  Env::WriteLifeTimeHint GetWriteLifeTimeHint() override {
+    return target_->GetWriteLifeTimeHint();
+  }
+
   uint64_t GetFileSize() override { return target_->GetFileSize(); }
-  void GetPreallocationStatus(size_t* block_size,
-                              size_t* last_allocated_block) override {
-    target_->GetPreallocationStatus(block_size, last_allocated_block);
-  }
-  size_t GetUniqueId(char* id, size_t max_size) const override {
-    return target_->GetUniqueId(id, max_size);
-  }
-  Status InvalidateCache(size_t offset, size_t length) override {
-    return target_->InvalidateCache(offset, length);
-  }
 
   void SetPreallocationBlockSize(size_t size) override {
     target_->SetPreallocationBlockSize(size);
   }
+
+  void GetPreallocationStatus(size_t* block_size,
+                              size_t* last_allocated_block) override {
+    target_->GetPreallocationStatus(block_size, last_allocated_block);
+  }
+
+  size_t GetUniqueId(char* id, size_t max_size) const override {
+    return target_->GetUniqueId(id, max_size);
+  }
+
+  Status InvalidateCache(size_t offset, size_t length) override {
+    return target_->InvalidateCache(offset, length);
+  }
+
+  Status RangeSync(uint64_t offset, uint64_t nbytes) override {
+    return target_->RangeSync(offset, nbytes);
+  }
+
   void PrepareWrite(size_t offset, size_t len) override {
     target_->PrepareWrite(offset, len);
   }
 
- protected:
   Status Allocate(uint64_t offset, uint64_t len) override {
     return target_->Allocate(offset, len);
   }
-  Status RangeSync(uint64_t offset, uint64_t nbytes) override {
-    return target_->RangeSync(offset, nbytes);
-  }
 
  private:
   WritableFile* target_;
@@ -1267,5 +1303,3 @@ Status NewHdfsEnv(Env** hdfs_env, const std::string& fsname);
 Env* NewTimedEnv(Env* base_env);
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_ENV_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/env_encryption.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/env_encryption.h
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/env_encryption.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/env_encryption.h
index 70dce616a6..a6e9195465 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/env_encryption.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/env_encryption.h
@@ -142,8 +142,9 @@ class EncryptionProvider {
 
     // CreateCipherStream creates a block access cipher stream for a file given
     // given name and options.
-    virtual Status CreateCipherStream(const std::string& fname, const EnvOptions& options,
-      Slice& prefix, unique_ptr<BlockAccessCipherStream>* result) = 0;
+    virtual Status CreateCipherStream(
+        const std::string& fname, const EnvOptions& options, Slice& prefix,
+        std::unique_ptr<BlockAccessCipherStream>* result) = 0;
 };
 
 // This encryption provider uses a CTR cipher stream, with a given block cipher 
@@ -174,10 +175,11 @@ class CTREncryptionProvider : public EncryptionProvider {
 
     // CreateCipherStream creates a block access cipher stream for a file given
     // given name and options.
-    virtual Status CreateCipherStream(const std::string& fname, const EnvOptions& options,
-      Slice& prefix, unique_ptr<BlockAccessCipherStream>* result) override;
+    virtual Status CreateCipherStream(
+        const std::string& fname, const EnvOptions& options, Slice& prefix,
+        std::unique_ptr<BlockAccessCipherStream>* result) override;
 
-  protected:
+   protected:
     // PopulateSecretPrefixPart initializes the data into a new prefix block 
     // that will be encrypted. This function will store the data in plain text. 
     // It will be encrypted later (before written to disk).
@@ -187,8 +189,10 @@ class CTREncryptionProvider : public EncryptionProvider {
 
     // CreateCipherStreamFromPrefix creates a block access cipher stream for a file given
     // given name and options. The given prefix is already decrypted.
-    virtual Status CreateCipherStreamFromPrefix(const std::string& fname, const EnvOptions& options,
-      uint64_t initialCounter, const Slice& iv, const Slice& prefix, unique_ptr<BlockAccessCipherStream>* result);
+    virtual Status CreateCipherStreamFromPrefix(
+        const std::string& fname, const EnvOptions& options,
+        uint64_t initialCounter, const Slice& iv, const Slice& prefix,
+        std::unique_ptr<BlockAccessCipherStream>* result);
 };
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/experimental.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/experimental.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/experimental.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/experimental.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/filter_policy.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/filter_policy.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/filter_policy.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/filter_policy.h
index 4706f38c30..9c0904456f 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/filter_policy.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/filter_policy.h
@@ -17,8 +17,7 @@
 // Most people will want to use the builtin bloom filter support (see
 // NewBloomFilterPolicy() below).
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_FILTER_POLICY_H_
-#define STORAGE_ROCKSDB_INCLUDE_FILTER_POLICY_H_
+#pragma once
 
 #include <memory>
 #include <stdexcept>
@@ -146,8 +145,6 @@ class FilterPolicy {
 // ignores trailing spaces, it would be incorrect to use a
 // FilterPolicy (like NewBloomFilterPolicy) that does not ignore
 // trailing spaces in keys.
-extern const FilterPolicy* NewBloomFilterPolicy(int bits_per_key,
-    bool use_block_based_builder = true);
+extern const FilterPolicy* NewBloomFilterPolicy(
+    int bits_per_key, bool use_block_based_builder = false);
 }
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_FILTER_POLICY_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/flush_block_policy.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/flush_block_policy.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/flush_block_policy.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/flush_block_policy.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/iostats_context.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/iostats_context.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/iostats_context.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/iostats_context.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/iterator.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/iterator.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/iterator.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/iterator.h
index 4475eb396f..e99b434a01 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/iterator.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/iterator.h
@@ -16,8 +16,7 @@
 // non-const method, all threads accessing the same Iterator must use
 // external synchronization.
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_ITERATOR_H_
-#define STORAGE_ROCKSDB_INCLUDE_ITERATOR_H_
+#pragma once
 
 #include <string>
 #include "rocksdb/cleanable.h"
@@ -119,5 +118,3 @@ extern Iterator* NewEmptyIterator();
 extern Iterator* NewErrorIterator(const Status& status);
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_ITERATOR_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/ldb_tool.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/ldb_tool.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/ldb_tool.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/ldb_tool.h
index 0ec2da9fc0..0dbc65c4bb 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/ldb_tool.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/ldb_tool.h
@@ -2,8 +2,8 @@
 //  This source code is licensed under both the GPLv2 (found in the
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
-#ifndef ROCKSDB_LITE
 #pragma once
+#ifndef ROCKSDB_LITE
 #include <string>
 #include <vector>
 #include "rocksdb/db.h"
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/listener.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/listener.h
similarity index 87%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/listener.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/listener.h
index 601951cd0f..8ceb2ed4c0 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/listener.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/listener.h
@@ -27,6 +27,7 @@ enum class TableFileCreationReason {
   kFlush,
   kCompaction,
   kRecovery,
+  kMisc,
 };
 
 struct TableFileCreationBriefInfo {
@@ -103,6 +104,7 @@ enum class FlushReason : int {
   kDeleteFiles = 0x08,
   kAutoCompaction = 0x09,
   kManualFlush = 0x0a,
+  kErrorRecovery = 0xb,
 };
 
 enum class BackgroundErrorReason {
@@ -141,6 +143,16 @@ struct TableFileDeletionInfo {
   Status status;
 };
 
+struct FileOperationInfo {
+  const std::string& path;
+  uint64_t offset;
+  size_t length;
+  time_t start_timestamp;
+  time_t finish_timestamp;
+  Status status;
+  FileOperationInfo(const std::string& _path) : path(_path) {}
+};
+
 struct FlushJobInfo {
   // the name of the column family
   std::string cf_name;
@@ -175,6 +187,8 @@ struct CompactionJobInfo {
   explicit CompactionJobInfo(const CompactionJobStats& _stats) :
       stats(_stats) {}
 
+  // the id of the column family where the compaction happened.
+  uint32_t cf_id;
   // the name of the column family where the compaction happened.
   std::string cf_name;
   // the status indicating whether the compaction was successful or not.
@@ -295,6 +309,16 @@ class EventListener {
   // returned value.
   virtual void OnTableFileDeleted(const TableFileDeletionInfo& /*info*/) {}
 
+  // A callback function to RocksDB which will be called before a
+  // RocksDB starts to compact.  The default implementation is
+  // no-op.
+  //
+  // Note that the this function must be implemented in a way such that
+  // it should not run for an extended period of time before the function
+  // returns.  Otherwise, RocksDB may be blocked.
+  virtual void OnCompactionBegin(DB* /*db*/,
+                                 const CompactionJobInfo& /*ci*/) {}
+
   // A callback function for RocksDB which will be called whenever
   // a registered RocksDB compacts a file. The default implementation
   // is a no-op.
@@ -393,6 +417,33 @@ class EventListener {
   // returns.  Otherwise, RocksDB may be blocked.
   virtual void OnStallConditionsChanged(const WriteStallInfo& /*info*/) {}
 
+  // A callback function for RocksDB which will be called whenever a file read
+  // operation finishes.
+  virtual void OnFileReadFinish(const FileOperationInfo& /* info */) {}
+
+  // A callback function for RocksDB which will be called whenever a file write
+  // operation finishes.
+  virtual void OnFileWriteFinish(const FileOperationInfo& /* info */) {}
+
+  // If true, the OnFileReadFinish and OnFileWriteFinish will be called. If
+  // false, then they won't be called.
+  virtual bool ShouldBeNotifiedOnFileIO() { return false; }
+
+  // A callback function for RocksDB which will be called just before
+  // starting the automatic recovery process for recoverable background
+  // errors, such as NoSpace(). The callback can suppress the automatic
+  // recovery by setting *auto_recovery to false. The database will then
+  // have to be transitioned out of read-only mode by calling DB::Resume()
+  virtual void OnErrorRecoveryBegin(BackgroundErrorReason /* reason */,
+                                    Status /* bg_error */,
+                                    bool* /* auto_recovery */) {}
+
+  // A callback function for RocksDB which will be called once the database
+  // is recovered from read-only mode after an error. When this is called, it
+  // means normal writes to the database can be issued and the user can
+  // initiate any further recovery actions needed
+  virtual void OnErrorRecoveryCompleted(Status /* old_bg_error */) {}
+
   virtual ~EventListener() {}
 };
 
diff --git a/3rdParty/rocksdb/v5.18.X/include/rocksdb/memory_allocator.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/memory_allocator.h
new file mode 100644
index 0000000000..889c0e9218
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/memory_allocator.h
@@ -0,0 +1,77 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include "rocksdb/status.h"
+
+#include <memory>
+
+namespace rocksdb {
+
+// MemoryAllocator is an interface that a client can implement to supply custom
+// memory allocation and deallocation methods. See rocksdb/cache.h for more
+// information.
+// All methods should be thread-safe.
+class MemoryAllocator {
+ public:
+  virtual ~MemoryAllocator() = default;
+
+  // Name of the cache allocator, printed in the log
+  virtual const char* Name() const = 0;
+
+  // Allocate a block of at least size. Has to be thread-safe.
+  virtual void* Allocate(size_t size) = 0;
+
+  // Deallocate previously allocated block. Has to be thread-safe.
+  virtual void Deallocate(void* p) = 0;
+
+  // Returns the memory size of the block allocated at p. The default
+  // implementation that just returns the original allocation_size is fine.
+  virtual size_t UsableSize(void* /*p*/, size_t allocation_size) const {
+    // default implementation just returns the allocation size
+    return allocation_size;
+  }
+};
+
+struct JemallocAllocatorOptions {
+  // Jemalloc tcache cache allocations by size class. For each size class,
+  // it caches between 20 (for large size classes) to 200 (for small size
+  // classes). To reduce tcache memory usage in case the allocator is access
+  // by large number of threads, we can control whether to cache an allocation
+  // by its size.
+  bool limit_tcache_size = false;
+
+  // Lower bound of allocation size to use tcache, if limit_tcache_size=true.
+  // When used with block cache, it is recommneded to set it to block_size/4.
+  size_t tcache_size_lower_bound = 1024;
+
+  // Upper bound of allocation size to use tcache, if limit_tcache_size=true.
+  // When used with block cache, it is recommneded to set it to block_size.
+  size_t tcache_size_upper_bound = 16 * 1024;
+};
+
+// Generate memory allocators which allocates through Jemalloc and utilize
+// MADV_DONTDUMP through madvice to exclude cache items from core dump.
+// Applications can use the allocator with block cache to exclude block cache
+// usage from core dump.
+//
+// Implementation details:
+// The JemallocNodumpAllocator creates a delicated jemalloc arena, and all
+// allocations of the JemallocNodumpAllocator is through the same arena.
+// The memory allocator hooks memory allocation of the arena, and call
+// madvice() with MADV_DONTDUMP flag to exclude the piece of memory from
+// core dump. Side benefit of using single arena would be reduce of jemalloc
+// metadata for some workload.
+//
+// To mitigate mutex contention for using one single arena, jemalloc tcache
+// (thread-local cache) is enabled to cache unused allocations for future use.
+// The tcache normally incur 0.5M extra memory usage per-thread. The usage
+// can be reduce by limitting allocation sizes to cache.
+extern Status NewJemallocNodumpAllocator(
+    JemallocAllocatorOptions& options,
+    std::shared_ptr<MemoryAllocator>* memory_allocator);
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/memtablerep.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/memtablerep.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/memtablerep.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/memtablerep.h
index 4b6e897a6d..4c2a23e0a8 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/memtablerep.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/memtablerep.h
@@ -144,6 +144,14 @@ class MemTableRep {
   // or any writes done directly to entries accessed through the iterator.)
   virtual void MarkReadOnly() { }
 
+  // Notify this table rep that it has been flushed to stable storage.
+  // By default, does nothing.
+  //
+  // Invariant: MarkReadOnly() is called, before MarkFlushed().
+  // Note that this method if overridden, should not run for an extended period
+  // of time. Otherwise, RocksDB may be blocked.
+  virtual void MarkFlushed() { }
+
   // Look up key from the mem table, since the first key in the mem table whose
   // user_key matches the one given k, call the function callback_func(), with
   // callback_args directly forwarded as the first parameter, and the mem table
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/merge_operator.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/merge_operator.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/merge_operator.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/merge_operator.h
index 8406d4a74f..b90f3d72f1 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/merge_operator.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/merge_operator.h
@@ -3,8 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_MERGE_OPERATOR_H_
-#define STORAGE_ROCKSDB_INCLUDE_MERGE_OPERATOR_H_
+#pragma once
 
 #include <deque>
 #include <memory>
@@ -241,5 +240,3 @@ class AssociativeMergeOperator : public MergeOperator {
 };
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_MERGE_OPERATOR_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/metadata.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/metadata.h
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/metadata.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/metadata.h
index f6be889ba9..e62d4f4098 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/metadata.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/metadata.h
@@ -63,9 +63,12 @@ struct SstFileMetaData {
         smallestkey(""),
         largestkey(""),
         num_reads_sampled(0),
-        being_compacted(false) {}
+        being_compacted(false),
+        num_entries(0),
+        num_deletions(0) {}
+
   SstFileMetaData(const std::string& _file_name, const std::string& _path,
-                  uint64_t _size, SequenceNumber _smallest_seqno,
+                  size_t _size, SequenceNumber _smallest_seqno,
                   SequenceNumber _largest_seqno,
                   const std::string& _smallestkey,
                   const std::string& _largestkey, uint64_t _num_reads_sampled,
@@ -78,10 +81,12 @@ struct SstFileMetaData {
         smallestkey(_smallestkey),
         largestkey(_largestkey),
         num_reads_sampled(_num_reads_sampled),
-        being_compacted(_being_compacted) {}
+        being_compacted(_being_compacted),
+        num_entries(0),
+        num_deletions(0) {}
 
   // File size in bytes.
-  uint64_t size;
+  size_t size;
   // The name of the file.
   std::string name;
   // The full path where the file locates.
@@ -93,11 +98,15 @@ struct SstFileMetaData {
   std::string largestkey;      // Largest user defined key in the file.
   uint64_t num_reads_sampled;  // How many times the file is read.
   bool being_compacted;  // true if the file is currently being compacted.
+
+  uint64_t num_entries;
+  uint64_t num_deletions;
 };
 
 // The full set of metadata associated with each SST file.
 struct LiveFileMetaData : SstFileMetaData {
   std::string column_family_name;  // Name of the column family
   int level;               // Level at which this file resides.
+  LiveFileMetaData() : column_family_name(), level(0) {}
 };
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/options.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/options.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/options.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/options.h
index 5499595d5e..c3ba448394 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/options.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/options.h
@@ -6,8 +6,7 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_OPTIONS_H_
-#define STORAGE_ROCKSDB_INCLUDE_OPTIONS_H_
+#pragma once
 
 #include <stddef.h>
 #include <stdint.h>
@@ -189,8 +188,7 @@ struct ColumnFamilyOptions : public AdvancedColumnFamilyOptions {
   // Dynamically changeable through SetOptions() API
   size_t write_buffer_size = 64 << 20;
 
-  // Compress blocks using the specified compression algorithm.  This
-  // parameter can be changed dynamically.
+  // Compress blocks using the specified compression algorithm.
   //
   // Default: kSnappyCompression, if it's supported. If snappy is not linked
   // with the library, the default is kNoCompression.
@@ -213,6 +211,8 @@ struct ColumnFamilyOptions : public AdvancedColumnFamilyOptions {
   // - kZlibCompression: Z_DEFAULT_COMPRESSION (currently -1)
   // - kLZ4HCCompression: 0
   // - For all others, we do not specify a compression level
+  //
+  // Dynamically changeable through SetOptions() API
   CompressionType compression;
 
   // Compression algorithm that will be used for the bottommost level that
@@ -417,7 +417,10 @@ struct DBOptions {
   // files opened are always kept open. You can estimate number of files based
   // on target_file_size_base and target_file_size_multiplier for level-based
   // compaction. For universal-style compaction, you can usually set it to -1.
+  //
   // Default: -1
+  //
+  // Dynamically changeable through SetDBOptions() API.
   int max_open_files = -1;
 
   // If max_open_files is -1, DB will open all files on DB::Open(). You can
@@ -432,7 +435,10 @@ struct DBOptions {
   // [sum of all write_buffer_size * max_write_buffer_number] * 4
   // This option takes effect only when there are more than one column family as
   // otherwise the wal size is dictated by the write_buffer_size.
+  //
   // Default: 0
+  //
+  // Dynamically changeable through SetDBOptions() API.
   uint64_t max_total_wal_size = 0;
 
   // If non-null, then we should collect metrics about database operations
@@ -493,13 +499,23 @@ struct DBOptions {
   // value is 6 hours. The files that get out of scope by compaction
   // process will still get automatically delete on every compaction,
   // regardless of this setting
+  //
+  // Default: 6 hours
+  //
+  // Dynamically changeable through SetDBOptions() API.
   uint64_t delete_obsolete_files_period_micros = 6ULL * 60 * 60 * 1000000;
 
   // Maximum number of concurrent background jobs (compactions and flushes).
+  //
+  // Default: 2
+  //
+  // Dynamically changeable through SetDBOptions() API.
   int max_background_jobs = 2;
 
   // NOT SUPPORTED ANYMORE: RocksDB automatically decides this based on the
   // value of max_background_jobs. This option is ignored.
+  //
+  // Dynamically changeable through SetDBOptions() API.
   int base_background_compactions = -1;
 
   // NOT SUPPORTED ANYMORE: RocksDB automatically decides this based on the
@@ -514,7 +530,10 @@ struct DBOptions {
   // If you're increasing this, also consider increasing number of threads in
   // LOW priority thread pool. For more information, see
   // Env::SetBackgroundThreads
+  //
   // Default: -1
+  //
+  // Dynamically changeable through SetDBOptions() API.
   int max_background_compactions = -1;
 
   // This value represents the maximum number of threads that will
@@ -643,7 +662,10 @@ struct DBOptions {
   bool skip_log_error_on_recovery = false;
 
   // if not zero, dump rocksdb.stats to LOG every stats_dump_period_sec
+  //
   // Default: 600 (10 min)
+  //
+  // Dynamically changeable through SetDBOptions() API.
   unsigned int stats_dump_period_sec = 600;
 
   // If set true, will hint the underlying file system that the file
@@ -710,6 +732,8 @@ struct DBOptions {
   // true.
   //
   // Default: 0
+  //
+  // Dynamically changeable through SetDBOptions() API.
   size_t compaction_readahead_size = 0;
 
   // This is a maximum buffer size that is used by WinMmapReadableFile in
@@ -736,6 +760,8 @@ struct DBOptions {
   // write requests if the logical sector size is unusual
   //
   // Default: 1024 * 1024 (1 MB)
+  //
+  // Dynamically changeable through SetDBOptions() API.
   size_t writable_file_max_buffer_size = 1024 * 1024;
 
 
@@ -758,17 +784,23 @@ struct DBOptions {
   // to smooth out write I/Os over time. Users shouldn't rely on it for
   // persistency guarantee.
   // Issue one request for every bytes_per_sync written. 0 turns it off.
-  // Default: 0
   //
   // You may consider using rate_limiter to regulate write rate to device.
   // When rate limiter is enabled, it automatically enables bytes_per_sync
   // to 1MB.
   //
   // This option applies to table files
+  //
+  // Default: 0, turned off
+  //
+  // Dynamically changeable through SetDBOptions() API.
   uint64_t bytes_per_sync = 0;
 
   // Same as bytes_per_sync, but applies to WAL files
+  //
   // Default: 0, turned off
+  //
+  // Dynamically changeable through SetDBOptions() API.
   uint64_t wal_bytes_per_sync = 0;
 
   // A vector of EventListeners which callback functions will be called
@@ -795,6 +827,8 @@ struct DBOptions {
   // Unit: byte per second.
   //
   // Default: 0
+  //
+  // Dynamically changeable through SetDBOptions() API.
   uint64_t delayed_write_rate = 0;
 
   // By default, a single write thread queue is maintained. The thread gets
@@ -944,6 +978,20 @@ struct DBOptions {
   // relies on manual invocation of FlushWAL to write the WAL buffer to its
   // file.
   bool manual_wal_flush = false;
+
+  // If true, RocksDB supports flushing multiple column families and committing
+  // their results atomically to MANIFEST. Note that it is not
+  // necessary to set atomic_flush to true if WAL is always enabled since WAL
+  // allows the database to be restored to the last persistent state in WAL.
+  // This option is useful when there are column families with writes NOT
+  // protected by WAL.
+  // For manual flush, application has to specify which column families to
+  // flush atomically in DB::Flush.
+  // For auto-triggered flush, RocksDB atomically flushes ALL column families.
+  //
+  // Currently, any WAL-enabled writes after atomic flush may be replayed
+  // independently if the process crashes later and tries to recover.
+  bool atomic_flush = false;
 };
 
 // Options to control the behavior of a database (passed to DB::Open)
@@ -1183,8 +1231,13 @@ struct FlushOptions {
   // If true, the flush will wait until the flush is done.
   // Default: true
   bool wait;
-
-  FlushOptions() : wait(true) {}
+  // If true, the flush would proceed immediately even it means writes will
+  // stall for the duration of the flush; if false the operation will wait
+  // until it's possible to do flush w/o causing stall or until required flush
+  // is performed by someone else (foreground call or background thread).
+  // Default: false
+  bool allow_write_stall;
+  FlushOptions() : wait(true), allow_write_stall(false) {}
 };
 
 // Create a Logger from provided DBOptions
@@ -1196,6 +1249,9 @@ extern Status CreateLoggerFromOptions(const std::string& dbname,
 struct CompactionOptions {
   // Compaction output compression type
   // Default: snappy
+  // If set to `kDisableCompressionOption`, RocksDB will choose compression type
+  // according to the `ColumnFamilyOptions`, taking into account the output
+  // level if `compression_per_level` is specified.
   CompressionType compression;
   // Compaction will create files of size `output_file_size_limit`.
   // Default: MAX, which means that compaction will create a single file
@@ -1281,8 +1337,11 @@ struct IngestExternalFileOptions {
   bool write_global_seqno = true;
 };
 
-struct TraceOptions {};
+// TraceOptions is used for StartTrace
+struct TraceOptions {
+  // To avoid the trace file size grows large than the storage space,
+  // user can set the max trace file size in Bytes. Default is 64GB
+  uint64_t max_trace_file_size = uint64_t{64} * 1024 * 1024 * 1024;
+};
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_OPTIONS_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/perf_context.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/perf_context.h
similarity index 85%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/perf_context.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/perf_context.h
index c3d61a3f62..1b11fa3cc2 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/perf_context.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/perf_context.h
@@ -3,9 +3,9 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_PERF_CONTEXT_H
-#define STORAGE_ROCKSDB_INCLUDE_PERF_CONTEXT_H
+#pragma once
 
+#include <map>
 #include <stdint.h>
 #include <string>
 
@@ -17,12 +17,44 @@ namespace rocksdb {
 // and transparently.
 // Use SetPerfLevel(PerfLevel::kEnableTime) to enable time stats.
 
+// Break down performance counters by level and store per-level perf context in
+// PerfContextByLevel
+struct PerfContextByLevel {
+  // # of times bloom filter has avoided file reads, i.e., negatives.
+  uint64_t bloom_filter_useful = 0;
+  // # of times bloom FullFilter has not avoided the reads.
+  uint64_t bloom_filter_full_positive = 0;
+  // # of times bloom FullFilter has not avoided the reads and data actually
+  // exist.
+  uint64_t bloom_filter_full_true_positive = 0;
+
+  // total number of user key returned (only include keys that are found, does
+  // not include keys that are deleted or merged without a final put
+  uint64_t user_key_return_count;
+
+  // total nanos spent on reading data from SST files
+  uint64_t get_from_table_nanos;
+
+  void Reset(); // reset all performance counters to zero
+};
+
 struct PerfContext {
 
+  ~PerfContext();
+
   void Reset(); // reset all performance counters to zero
 
   std::string ToString(bool exclude_zero_counters = false) const;
 
+  // enable per level perf context and allocate storage for PerfContextByLevel
+  void EnablePerLevelPerfContext();
+
+  // temporarily disable per level perf contxt by setting the flag to false
+  void DisablePerLevelPerfContext();
+
+  // free the space for PerfContextByLevel, also disable per level perf context
+  void ClearPerLevelPerfContext();
+
   uint64_t user_key_comparison_count; // total number of user key comparisons
   uint64_t block_cache_hit_count;     // total number of block cache hits
   uint64_t block_read_count;          // total number of block reads (with IO)
@@ -169,6 +201,8 @@ struct PerfContext {
   uint64_t env_lock_file_nanos;
   uint64_t env_unlock_file_nanos;
   uint64_t env_new_logger_nanos;
+  std::map<uint32_t, PerfContextByLevel>* level_to_perf_context;
+  bool per_level_perf_context_enabled;
 };
 
 // Get Thread-local PerfContext object pointer
@@ -176,5 +210,3 @@ struct PerfContext {
 PerfContext* get_perf_context();
 
 }
-
-#endif
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/perf_level.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/perf_level.h
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/perf_level.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/perf_level.h
index 84a331c355..218c6015f8 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/perf_level.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/perf_level.h
@@ -3,8 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#ifndef INCLUDE_ROCKSDB_PERF_LEVEL_H_
-#define INCLUDE_ROCKSDB_PERF_LEVEL_H_
+#pragma once
 
 #include <stdint.h>
 #include <string>
@@ -29,5 +28,3 @@ void SetPerfLevel(PerfLevel level);
 PerfLevel GetPerfLevel();
 
 }  // namespace rocksdb
-
-#endif  // INCLUDE_ROCKSDB_PERF_LEVEL_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/persistent_cache.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/persistent_cache.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/persistent_cache.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/persistent_cache.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/rate_limiter.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/rate_limiter.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/rate_limiter.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/rate_limiter.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/slice.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/slice.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/slice.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/slice.h
index 2eeedb9cf6..9ccbdc51e5 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/slice.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/slice.h
@@ -16,8 +16,7 @@
 // non-const method, all threads accessing the same Slice must use
 // external synchronization.
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_SLICE_H_
-#define STORAGE_ROCKSDB_INCLUDE_SLICE_H_
+#pragma once
 
 #include <assert.h>
 #include <cstdio>
@@ -48,7 +47,7 @@ class Slice {
 #ifdef __cpp_lib_string_view
   // Create a slice that refers to the same contents as "sv"
   /* implicit */
-  Slice(std::string_view sv) : data_(sv.data()), size_(sv.size()) { }
+  Slice(std::string_view sv) : data_(sv.data()), size_(sv.size()) {}
 #endif
 
   // Create a slice that refers to s[0,strlen(s)-1]
@@ -256,6 +255,4 @@ inline size_t Slice::difference_offset(const Slice& b) const {
   return off;
 }
 
-}  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_SLICE_H_
+}  // namespace rocksdb
\ No newline at end of file
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/slice_transform.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/slice_transform.h
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/slice_transform.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/slice_transform.h
index 5a461b7769..2bbe06153a 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/slice_transform.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/slice_transform.h
@@ -12,8 +12,7 @@
 // define InDomain and InRange to determine which slices are in either
 // of these sets respectively.
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_SLICE_TRANSFORM_H_
-#define STORAGE_ROCKSDB_INCLUDE_SLICE_TRANSFORM_H_
+#pragma once
 
 #include <string>
 
@@ -100,5 +99,3 @@ extern const SliceTransform* NewCappedPrefixTransform(size_t cap_len);
 extern const SliceTransform* NewNoopTransform();
 
 }
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_SLICE_TRANSFORM_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/snapshot.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/snapshot.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/snapshot.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/snapshot.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/sst_dump_tool.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/sst_dump_tool.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/sst_dump_tool.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/sst_dump_tool.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/sst_file_manager.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/sst_file_manager.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/sst_file_manager.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/sst_file_manager.h
diff --git a/3rdParty/rocksdb/v5.18.X/include/rocksdb/sst_file_reader.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/sst_file_reader.h
new file mode 100644
index 0000000000..e58c84792e
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/sst_file_reader.h
@@ -0,0 +1,45 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#ifndef ROCKSDB_LITE
+
+#include "rocksdb/slice.h"
+#include "rocksdb/options.h"
+#include "rocksdb/iterator.h"
+#include "rocksdb/table_properties.h"
+
+namespace rocksdb {
+
+// SstFileReader is used to read sst files that are generated by DB or
+// SstFileWriter.
+class SstFileReader {
+ public:
+  SstFileReader(const Options& options);
+
+  ~SstFileReader();
+
+  // Prepares to read from the file located at "file_path".
+  Status Open(const std::string& file_path);
+
+  // Returns a new iterator over the table contents.
+  // Most read options provide the same control as we read from DB.
+  // If "snapshot" is nullptr, the iterator returns only the latest keys.
+  Iterator* NewIterator(const ReadOptions& options);
+
+  std::shared_ptr<const TableProperties> GetTableProperties() const;
+
+  // Verifies whether there is corruption in this table.
+  Status VerifyChecksum();
+
+ private:
+  struct Rep;
+  std::unique_ptr<Rep> rep_;
+};
+
+}  // namespace rocksdb
+
+#endif  // !ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/sst_file_writer.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/sst_file_writer.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/sst_file_writer.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/sst_file_writer.h
index 97e3e30d70..24bcdbd135 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/sst_file_writer.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/sst_file_writer.h
@@ -3,10 +3,10 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#ifndef ROCKSDB_LITE
-
 #pragma once
 
+#ifndef ROCKSDB_LITE
+
 #include <memory>
 #include <string>
 
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/statistics.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/statistics.h
similarity index 58%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/statistics.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/statistics.h
index 30e79b0998..14e6195fae 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/statistics.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/statistics.h
@@ -3,8 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_STATISTICS_H_
-#define STORAGE_ROCKSDB_INCLUDE_STATISTICS_H_
+#pragma once
 
 #include <atomic>
 #include <cstddef>
@@ -156,7 +155,8 @@ enum Tickers : uint32_t {
   // Disabled by default. To enable it set stats level to kAll
   DB_MUTEX_WAIT_MICROS,
   RATE_LIMIT_DELAY_MILLIS,
-  NO_ITERATORS,  // number of iterators currently open
+  // DEPRECATED number of iterators currently open
+  NO_ITERATORS,
 
   // Number of MultiGet calls, keys read, and bytes read
   NUMBER_MULTIGET_CALLS,
@@ -323,159 +323,15 @@ enum Tickers : uint32_t {
   // Number of keys actually found in MultiGet calls (vs number requested by caller)
   // NUMBER_MULTIGET_KEYS_READ gives the number requested by caller
   NUMBER_MULTIGET_KEYS_FOUND,
+
+  NO_ITERATOR_CREATED,  // number of iterators created
+  NO_ITERATOR_DELETED,  // number of iterators deleted
   TICKER_ENUM_MAX
 };
 
 // The order of items listed in  Tickers should be the same as
 // the order listed in TickersNameMap
-const std::vector<std::pair<Tickers, std::string>> TickersNameMap = {
-    {BLOCK_CACHE_MISS, "rocksdb.block.cache.miss"},
-    {BLOCK_CACHE_HIT, "rocksdb.block.cache.hit"},
-    {BLOCK_CACHE_ADD, "rocksdb.block.cache.add"},
-    {BLOCK_CACHE_ADD_FAILURES, "rocksdb.block.cache.add.failures"},
-    {BLOCK_CACHE_INDEX_MISS, "rocksdb.block.cache.index.miss"},
-    {BLOCK_CACHE_INDEX_HIT, "rocksdb.block.cache.index.hit"},
-    {BLOCK_CACHE_INDEX_ADD, "rocksdb.block.cache.index.add"},
-    {BLOCK_CACHE_INDEX_BYTES_INSERT, "rocksdb.block.cache.index.bytes.insert"},
-    {BLOCK_CACHE_INDEX_BYTES_EVICT, "rocksdb.block.cache.index.bytes.evict"},
-    {BLOCK_CACHE_FILTER_MISS, "rocksdb.block.cache.filter.miss"},
-    {BLOCK_CACHE_FILTER_HIT, "rocksdb.block.cache.filter.hit"},
-    {BLOCK_CACHE_FILTER_ADD, "rocksdb.block.cache.filter.add"},
-    {BLOCK_CACHE_FILTER_BYTES_INSERT,
-     "rocksdb.block.cache.filter.bytes.insert"},
-    {BLOCK_CACHE_FILTER_BYTES_EVICT, "rocksdb.block.cache.filter.bytes.evict"},
-    {BLOCK_CACHE_DATA_MISS, "rocksdb.block.cache.data.miss"},
-    {BLOCK_CACHE_DATA_HIT, "rocksdb.block.cache.data.hit"},
-    {BLOCK_CACHE_DATA_ADD, "rocksdb.block.cache.data.add"},
-    {BLOCK_CACHE_DATA_BYTES_INSERT, "rocksdb.block.cache.data.bytes.insert"},
-    {BLOCK_CACHE_BYTES_READ, "rocksdb.block.cache.bytes.read"},
-    {BLOCK_CACHE_BYTES_WRITE, "rocksdb.block.cache.bytes.write"},
-    {BLOOM_FILTER_USEFUL, "rocksdb.bloom.filter.useful"},
-    {BLOOM_FILTER_FULL_POSITIVE, "rocksdb.bloom.filter.full.positive"},
-    {BLOOM_FILTER_FULL_TRUE_POSITIVE,
-     "rocksdb.bloom.filter.full.true.positive"},
-    {PERSISTENT_CACHE_HIT, "rocksdb.persistent.cache.hit"},
-    {PERSISTENT_CACHE_MISS, "rocksdb.persistent.cache.miss"},
-    {SIM_BLOCK_CACHE_HIT, "rocksdb.sim.block.cache.hit"},
-    {SIM_BLOCK_CACHE_MISS, "rocksdb.sim.block.cache.miss"},
-    {MEMTABLE_HIT, "rocksdb.memtable.hit"},
-    {MEMTABLE_MISS, "rocksdb.memtable.miss"},
-    {GET_HIT_L0, "rocksdb.l0.hit"},
-    {GET_HIT_L1, "rocksdb.l1.hit"},
-    {GET_HIT_L2_AND_UP, "rocksdb.l2andup.hit"},
-    {COMPACTION_KEY_DROP_NEWER_ENTRY, "rocksdb.compaction.key.drop.new"},
-    {COMPACTION_KEY_DROP_OBSOLETE, "rocksdb.compaction.key.drop.obsolete"},
-    {COMPACTION_KEY_DROP_RANGE_DEL, "rocksdb.compaction.key.drop.range_del"},
-    {COMPACTION_KEY_DROP_USER, "rocksdb.compaction.key.drop.user"},
-    {COMPACTION_RANGE_DEL_DROP_OBSOLETE,
-     "rocksdb.compaction.range_del.drop.obsolete"},
-    {COMPACTION_OPTIMIZED_DEL_DROP_OBSOLETE,
-     "rocksdb.compaction.optimized.del.drop.obsolete"},
-    {COMPACTION_CANCELLED, "rocksdb.compaction.cancelled"},
-    {NUMBER_KEYS_WRITTEN, "rocksdb.number.keys.written"},
-    {NUMBER_KEYS_READ, "rocksdb.number.keys.read"},
-    {NUMBER_KEYS_UPDATED, "rocksdb.number.keys.updated"},
-    {BYTES_WRITTEN, "rocksdb.bytes.written"},
-    {BYTES_READ, "rocksdb.bytes.read"},
-    {NUMBER_DB_SEEK, "rocksdb.number.db.seek"},
-    {NUMBER_DB_NEXT, "rocksdb.number.db.next"},
-    {NUMBER_DB_PREV, "rocksdb.number.db.prev"},
-    {NUMBER_DB_SEEK_FOUND, "rocksdb.number.db.seek.found"},
-    {NUMBER_DB_NEXT_FOUND, "rocksdb.number.db.next.found"},
-    {NUMBER_DB_PREV_FOUND, "rocksdb.number.db.prev.found"},
-    {ITER_BYTES_READ, "rocksdb.db.iter.bytes.read"},
-    {NO_FILE_CLOSES, "rocksdb.no.file.closes"},
-    {NO_FILE_OPENS, "rocksdb.no.file.opens"},
-    {NO_FILE_ERRORS, "rocksdb.no.file.errors"},
-    {STALL_L0_SLOWDOWN_MICROS, "rocksdb.l0.slowdown.micros"},
-    {STALL_MEMTABLE_COMPACTION_MICROS, "rocksdb.memtable.compaction.micros"},
-    {STALL_L0_NUM_FILES_MICROS, "rocksdb.l0.num.files.stall.micros"},
-    {STALL_MICROS, "rocksdb.stall.micros"},
-    {DB_MUTEX_WAIT_MICROS, "rocksdb.db.mutex.wait.micros"},
-    {RATE_LIMIT_DELAY_MILLIS, "rocksdb.rate.limit.delay.millis"},
-    {NO_ITERATORS, "rocksdb.num.iterators"},
-    {NUMBER_MULTIGET_CALLS, "rocksdb.number.multiget.get"},
-    {NUMBER_MULTIGET_KEYS_READ, "rocksdb.number.multiget.keys.read"},
-    {NUMBER_MULTIGET_BYTES_READ, "rocksdb.number.multiget.bytes.read"},
-    {NUMBER_FILTERED_DELETES, "rocksdb.number.deletes.filtered"},
-    {NUMBER_MERGE_FAILURES, "rocksdb.number.merge.failures"},
-    {BLOOM_FILTER_PREFIX_CHECKED, "rocksdb.bloom.filter.prefix.checked"},
-    {BLOOM_FILTER_PREFIX_USEFUL, "rocksdb.bloom.filter.prefix.useful"},
-    {NUMBER_OF_RESEEKS_IN_ITERATION, "rocksdb.number.reseeks.iteration"},
-    {GET_UPDATES_SINCE_CALLS, "rocksdb.getupdatessince.calls"},
-    {BLOCK_CACHE_COMPRESSED_MISS, "rocksdb.block.cachecompressed.miss"},
-    {BLOCK_CACHE_COMPRESSED_HIT, "rocksdb.block.cachecompressed.hit"},
-    {BLOCK_CACHE_COMPRESSED_ADD, "rocksdb.block.cachecompressed.add"},
-    {BLOCK_CACHE_COMPRESSED_ADD_FAILURES,
-     "rocksdb.block.cachecompressed.add.failures"},
-    {WAL_FILE_SYNCED, "rocksdb.wal.synced"},
-    {WAL_FILE_BYTES, "rocksdb.wal.bytes"},
-    {WRITE_DONE_BY_SELF, "rocksdb.write.self"},
-    {WRITE_DONE_BY_OTHER, "rocksdb.write.other"},
-    {WRITE_TIMEDOUT, "rocksdb.write.timeout"},
-    {WRITE_WITH_WAL, "rocksdb.write.wal"},
-    {COMPACT_READ_BYTES, "rocksdb.compact.read.bytes"},
-    {COMPACT_WRITE_BYTES, "rocksdb.compact.write.bytes"},
-    {FLUSH_WRITE_BYTES, "rocksdb.flush.write.bytes"},
-    {NUMBER_DIRECT_LOAD_TABLE_PROPERTIES,
-     "rocksdb.number.direct.load.table.properties"},
-    {NUMBER_SUPERVERSION_ACQUIRES, "rocksdb.number.superversion_acquires"},
-    {NUMBER_SUPERVERSION_RELEASES, "rocksdb.number.superversion_releases"},
-    {NUMBER_SUPERVERSION_CLEANUPS, "rocksdb.number.superversion_cleanups"},
-    {NUMBER_BLOCK_COMPRESSED, "rocksdb.number.block.compressed"},
-    {NUMBER_BLOCK_DECOMPRESSED, "rocksdb.number.block.decompressed"},
-    {NUMBER_BLOCK_NOT_COMPRESSED, "rocksdb.number.block.not_compressed"},
-    {MERGE_OPERATION_TOTAL_TIME, "rocksdb.merge.operation.time.nanos"},
-    {FILTER_OPERATION_TOTAL_TIME, "rocksdb.filter.operation.time.nanos"},
-    {ROW_CACHE_HIT, "rocksdb.row.cache.hit"},
-    {ROW_CACHE_MISS, "rocksdb.row.cache.miss"},
-    {READ_AMP_ESTIMATE_USEFUL_BYTES, "rocksdb.read.amp.estimate.useful.bytes"},
-    {READ_AMP_TOTAL_READ_BYTES, "rocksdb.read.amp.total.read.bytes"},
-    {NUMBER_RATE_LIMITER_DRAINS, "rocksdb.number.rate_limiter.drains"},
-    {NUMBER_ITER_SKIP, "rocksdb.number.iter.skip"},
-    {BLOB_DB_NUM_PUT, "rocksdb.blobdb.num.put"},
-    {BLOB_DB_NUM_WRITE, "rocksdb.blobdb.num.write"},
-    {BLOB_DB_NUM_GET, "rocksdb.blobdb.num.get"},
-    {BLOB_DB_NUM_MULTIGET, "rocksdb.blobdb.num.multiget"},
-    {BLOB_DB_NUM_SEEK, "rocksdb.blobdb.num.seek"},
-    {BLOB_DB_NUM_NEXT, "rocksdb.blobdb.num.next"},
-    {BLOB_DB_NUM_PREV, "rocksdb.blobdb.num.prev"},
-    {BLOB_DB_NUM_KEYS_WRITTEN, "rocksdb.blobdb.num.keys.written"},
-    {BLOB_DB_NUM_KEYS_READ, "rocksdb.blobdb.num.keys.read"},
-    {BLOB_DB_BYTES_WRITTEN, "rocksdb.blobdb.bytes.written"},
-    {BLOB_DB_BYTES_READ, "rocksdb.blobdb.bytes.read"},
-    {BLOB_DB_WRITE_INLINED, "rocksdb.blobdb.write.inlined"},
-    {BLOB_DB_WRITE_INLINED_TTL, "rocksdb.blobdb.write.inlined.ttl"},
-    {BLOB_DB_WRITE_BLOB, "rocksdb.blobdb.write.blob"},
-    {BLOB_DB_WRITE_BLOB_TTL, "rocksdb.blobdb.write.blob.ttl"},
-    {BLOB_DB_BLOB_FILE_BYTES_WRITTEN, "rocksdb.blobdb.blob.file.bytes.written"},
-    {BLOB_DB_BLOB_FILE_BYTES_READ, "rocksdb.blobdb.blob.file.bytes.read"},
-    {BLOB_DB_BLOB_FILE_SYNCED, "rocksdb.blobdb.blob.file.synced"},
-    {BLOB_DB_BLOB_INDEX_EXPIRED_COUNT,
-     "rocksdb.blobdb.blob.index.expired.count"},
-    {BLOB_DB_BLOB_INDEX_EXPIRED_SIZE, "rocksdb.blobdb.blob.index.expired.size"},
-    {BLOB_DB_BLOB_INDEX_EVICTED_COUNT,
-     "rocksdb.blobdb.blob.index.evicted.count"},
-    {BLOB_DB_BLOB_INDEX_EVICTED_SIZE, "rocksdb.blobdb.blob.index.evicted.size"},
-    {BLOB_DB_GC_NUM_FILES, "rocksdb.blobdb.gc.num.files"},
-    {BLOB_DB_GC_NUM_NEW_FILES, "rocksdb.blobdb.gc.num.new.files"},
-    {BLOB_DB_GC_FAILURES, "rocksdb.blobdb.gc.failures"},
-    {BLOB_DB_GC_NUM_KEYS_OVERWRITTEN, "rocksdb.blobdb.gc.num.keys.overwritten"},
-    {BLOB_DB_GC_NUM_KEYS_EXPIRED, "rocksdb.blobdb.gc.num.keys.expired"},
-    {BLOB_DB_GC_NUM_KEYS_RELOCATED, "rocksdb.blobdb.gc.num.keys.relocated"},
-    {BLOB_DB_GC_BYTES_OVERWRITTEN, "rocksdb.blobdb.gc.bytes.overwritten"},
-    {BLOB_DB_GC_BYTES_EXPIRED, "rocksdb.blobdb.gc.bytes.expired"},
-    {BLOB_DB_GC_BYTES_RELOCATED, "rocksdb.blobdb.gc.bytes.relocated"},
-    {BLOB_DB_FIFO_NUM_FILES_EVICTED, "rocksdb.blobdb.fifo.num.files.evicted"},
-    {BLOB_DB_FIFO_NUM_KEYS_EVICTED, "rocksdb.blobdb.fifo.num.keys.evicted"},
-    {BLOB_DB_FIFO_BYTES_EVICTED, "rocksdb.blobdb.fifo.bytes.evicted"},
-    {TXN_PREPARE_MUTEX_OVERHEAD, "rocksdb.txn.overhead.mutex.prepare"},
-    {TXN_OLD_COMMIT_MAP_MUTEX_OVERHEAD,
-     "rocksdb.txn.overhead.mutex.old.commit.map"},
-    {TXN_DUPLICATE_KEY_OVERHEAD, "rocksdb.txn.overhead.duplicate.key"},
-    {TXN_SNAPSHOT_MUTEX_OVERHEAD, "rocksdb.txn.overhead.mutex.snapshot"},
-    {NUMBER_MULTIGET_KEYS_FOUND, "rocksdb.number.multiget.keys.found"},
-};
+extern const std::vector<std::pair<Tickers, std::string>> TickersNameMap;
 
 /**
  * Keep adding histogram's here.
@@ -558,57 +414,10 @@ enum Histograms : uint32_t {
   // Time spent flushing memtable to disk
   FLUSH_TIME,
 
-  HISTOGRAM_ENUM_MAX,  // TODO(ldemailly): enforce HistogramsNameMap match
+  HISTOGRAM_ENUM_MAX,
 };
 
-const std::vector<std::pair<Histograms, std::string>> HistogramsNameMap = {
-    {DB_GET, "rocksdb.db.get.micros"},
-    {DB_WRITE, "rocksdb.db.write.micros"},
-    {COMPACTION_TIME, "rocksdb.compaction.times.micros"},
-    {SUBCOMPACTION_SETUP_TIME, "rocksdb.subcompaction.setup.times.micros"},
-    {TABLE_SYNC_MICROS, "rocksdb.table.sync.micros"},
-    {COMPACTION_OUTFILE_SYNC_MICROS, "rocksdb.compaction.outfile.sync.micros"},
-    {WAL_FILE_SYNC_MICROS, "rocksdb.wal.file.sync.micros"},
-    {MANIFEST_FILE_SYNC_MICROS, "rocksdb.manifest.file.sync.micros"},
-    {TABLE_OPEN_IO_MICROS, "rocksdb.table.open.io.micros"},
-    {DB_MULTIGET, "rocksdb.db.multiget.micros"},
-    {READ_BLOCK_COMPACTION_MICROS, "rocksdb.read.block.compaction.micros"},
-    {READ_BLOCK_GET_MICROS, "rocksdb.read.block.get.micros"},
-    {WRITE_RAW_BLOCK_MICROS, "rocksdb.write.raw.block.micros"},
-    {STALL_L0_SLOWDOWN_COUNT, "rocksdb.l0.slowdown.count"},
-    {STALL_MEMTABLE_COMPACTION_COUNT, "rocksdb.memtable.compaction.count"},
-    {STALL_L0_NUM_FILES_COUNT, "rocksdb.num.files.stall.count"},
-    {HARD_RATE_LIMIT_DELAY_COUNT, "rocksdb.hard.rate.limit.delay.count"},
-    {SOFT_RATE_LIMIT_DELAY_COUNT, "rocksdb.soft.rate.limit.delay.count"},
-    {NUM_FILES_IN_SINGLE_COMPACTION, "rocksdb.numfiles.in.singlecompaction"},
-    {DB_SEEK, "rocksdb.db.seek.micros"},
-    {WRITE_STALL, "rocksdb.db.write.stall"},
-    {SST_READ_MICROS, "rocksdb.sst.read.micros"},
-    {NUM_SUBCOMPACTIONS_SCHEDULED, "rocksdb.num.subcompactions.scheduled"},
-    {BYTES_PER_READ, "rocksdb.bytes.per.read"},
-    {BYTES_PER_WRITE, "rocksdb.bytes.per.write"},
-    {BYTES_PER_MULTIGET, "rocksdb.bytes.per.multiget"},
-    {BYTES_COMPRESSED, "rocksdb.bytes.compressed"},
-    {BYTES_DECOMPRESSED, "rocksdb.bytes.decompressed"},
-    {COMPRESSION_TIMES_NANOS, "rocksdb.compression.times.nanos"},
-    {DECOMPRESSION_TIMES_NANOS, "rocksdb.decompression.times.nanos"},
-    {READ_NUM_MERGE_OPERANDS, "rocksdb.read.num.merge_operands"},
-    {BLOB_DB_KEY_SIZE, "rocksdb.blobdb.key.size"},
-    {BLOB_DB_VALUE_SIZE, "rocksdb.blobdb.value.size"},
-    {BLOB_DB_WRITE_MICROS, "rocksdb.blobdb.write.micros"},
-    {BLOB_DB_GET_MICROS, "rocksdb.blobdb.get.micros"},
-    {BLOB_DB_MULTIGET_MICROS, "rocksdb.blobdb.multiget.micros"},
-    {BLOB_DB_SEEK_MICROS, "rocksdb.blobdb.seek.micros"},
-    {BLOB_DB_NEXT_MICROS, "rocksdb.blobdb.next.micros"},
-    {BLOB_DB_PREV_MICROS, "rocksdb.blobdb.prev.micros"},
-    {BLOB_DB_BLOB_FILE_WRITE_MICROS, "rocksdb.blobdb.blob.file.write.micros"},
-    {BLOB_DB_BLOB_FILE_READ_MICROS, "rocksdb.blobdb.blob.file.read.micros"},
-    {BLOB_DB_BLOB_FILE_SYNC_MICROS, "rocksdb.blobdb.blob.file.sync.micros"},
-    {BLOB_DB_GC_MICROS, "rocksdb.blobdb.gc.micros"},
-    {BLOB_DB_COMPRESSION_MICROS, "rocksdb.blobdb.compression.micros"},
-    {BLOB_DB_DECOMPRESSION_MICROS, "rocksdb.blobdb.decompression.micros"},
-    {FLUSH_TIME, "rocksdb.db.flush.micros"},
-};
+extern const std::vector<std::pair<Histograms, std::string>> HistogramsNameMap;
 
 struct HistogramData {
   double median;
@@ -673,5 +482,3 @@ class Statistics {
 std::shared_ptr<Statistics> CreateDBStatistics();
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_STATISTICS_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/status.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/status.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/status.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/status.h
index db41c3efdb..40b374ecf6 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/status.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/status.h
@@ -14,8 +14,7 @@
 // non-const method, all threads accessing the same Status must use
 // external synchronization.
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_STATUS_H_
-#define STORAGE_ROCKSDB_INCLUDE_STATUS_H_
+#pragma once
 
 #include <string>
 #include "rocksdb/slice.h"
@@ -348,5 +347,3 @@ inline bool Status::operator!=(const Status& rhs) const {
 }
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_STATUS_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/table.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/table.h
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/table.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/table.h
index 701fff8b4a..a99c8bf6e7 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/table.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/table.h
@@ -16,6 +16,7 @@
 //   https://github.com/facebook/rocksdb/wiki/A-Tutorial-of-RocksDB-SST-formats#wiki-examples
 
 #pragma once
+
 #include <memory>
 #include <string>
 #include <unordered_map>
@@ -46,6 +47,7 @@ enum ChecksumType : char {
   kNoChecksum = 0x0,
   kCRC32c = 0x1,
   kxxHash = 0x2,
+  kxxHash64 = 0x3,
 };
 
 // For advanced user only
@@ -136,6 +138,8 @@ struct BlockBasedTableOptions {
 
   // If non-NULL use the specified cache for compressed blocks.
   // If NULL, rocksdb will not use a compressed block cache.
+  // Note: though it looks similar to `block_cache`, RocksDB doesn't put the
+  //       same type of object there.
   std::shared_ptr<Cache> block_cache_compressed = nullptr;
 
   // Approximate size of user data packed per block.  Note that the
@@ -238,6 +242,12 @@ struct BlockBasedTableOptions {
   // version 5.15, you should probably use this.
   // This option only affects newly written tables. When reading existing
   // tables, the information about version is read from the footer.
+  // 4 -- Can be read by RocksDB's versions since 5.16. Changes the way we
+  // encode the values in index blocks. If you don't plan to run RocksDB before
+  // version 5.16 and you are using index_block_restart_interval > 1, you should
+  // probably use this as it would reduce the index size.
+  // This option only affects newly written tables. When reading existing
+  // tables, the information about version is read from the footer.
   uint32_t format_version = 2;
 
   // Store index blocks on disk in compressed format. Changing this option to
@@ -442,7 +452,7 @@ class TableFactory {
   // NewTableReader() is called in three places:
   // (1) TableCache::FindTable() calls the function when table cache miss
   //     and cache the table object returned.
-  // (2) SstFileReader (for SST Dump) opens the table and dump the table
+  // (2) SstFileDumper (for SST Dump) opens the table and dump the table
   //     contents using the iterator of the table.
   // (3) DBImpl::IngestExternalFile() calls this function to read the contents of
   //     the sst file it's attempting to add
@@ -454,8 +464,8 @@ class TableFactory {
   // table_reader is the output table reader.
   virtual Status NewTableReader(
       const TableReaderOptions& table_reader_options,
-      unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
-      unique_ptr<TableReader>* table_reader,
+      std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+      std::unique_ptr<TableReader>* table_reader,
       bool prefetch_index_and_filter_in_cache = true) const = 0;
 
   // Return a table builder to write to a file for this table type.
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/table_properties.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/table_properties.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/table_properties.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/table_properties.h
index d545e455ff..75c180ff4f 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/table_properties.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/table_properties.h
@@ -40,6 +40,8 @@ struct TablePropertiesNames {
   static const std::string kRawValueSize;
   static const std::string kNumDataBlocks;
   static const std::string kNumEntries;
+  static const std::string kDeletedKeys;
+  static const std::string kMergeOperands;
   static const std::string kNumRangeDeletions;
   static const std::string kFormatVersion;
   static const std::string kFixedKeyLen;
@@ -152,6 +154,10 @@ struct TableProperties {
   uint64_t num_data_blocks = 0;
   // the number of entries in this table
   uint64_t num_entries = 0;
+  // the number of deletions in the table
+  uint64_t num_deletions = 0;
+  // the number of merge operands in the table
+  uint64_t num_merge_operands = 0;
   // the number of range deletions in this table
   uint64_t num_range_deletions = 0;
   // format version, reserved for backward compatibility
@@ -216,6 +222,10 @@ struct TableProperties {
 // Below is a list of non-basic properties that are collected by database
 // itself. Especially some properties regarding to the internal keys (which
 // is unknown to `table`).
+//
+// DEPRECATED: these properties now belong as TableProperties members. Please
+// use TableProperties::num_deletions and TableProperties::num_merge_operands,
+// respectively.
 extern uint64_t GetDeletedKeys(const UserCollectedProperties& props);
 extern uint64_t GetMergeOperands(const UserCollectedProperties& props,
                                  bool* property_present);
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/thread_status.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/thread_status.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/thread_status.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/thread_status.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/threadpool.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/threadpool.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/threadpool.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/threadpool.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/trace_reader_writer.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/trace_reader_writer.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/trace_reader_writer.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/trace_reader_writer.h
index 31226487b8..28919a0fad 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/trace_reader_writer.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/trace_reader_writer.h
@@ -24,6 +24,7 @@ class TraceWriter {
 
   virtual Status Write(const Slice& data) = 0;
   virtual Status Close() = 0;
+  virtual uint64_t GetFileSize() = 0;
 };
 
 // TraceReader allows reading RocksDB traces from any system, one operation at
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/transaction_log.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/transaction_log.h
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/transaction_log.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/transaction_log.h
index 7fc46ae264..cf80a633f1 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/transaction_log.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/transaction_log.h
@@ -3,8 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_TRANSACTION_LOG_ITERATOR_H_
-#define STORAGE_ROCKSDB_INCLUDE_TRANSACTION_LOG_ITERATOR_H_
+#pragma once
 
 #include "rocksdb/status.h"
 #include "rocksdb/types.h"
@@ -61,7 +60,7 @@ struct BatchResult {
 
   // Add empty __ctor and __dtor for the rule of five
   // However, preserve the original semantics and prohibit copying
-  // as the unique_ptr member does not copy.
+  // as the std::unique_ptr member does not copy.
   BatchResult() {}
 
   ~BatchResult() {}
@@ -121,5 +120,3 @@ class TransactionLogIterator {
   };
 };
 } //  namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_TRANSACTION_LOG_ITERATOR_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/types.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/types.h
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/types.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/types.h
index 3a73b7d96c..0868a74157 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/types.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/types.h
@@ -3,8 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_TYPES_H_
-#define STORAGE_ROCKSDB_INCLUDE_TYPES_H_
+#pragma once
 
 #include <stdint.h>
 #include "rocksdb/slice.h"
@@ -53,5 +52,3 @@ struct FullKey {
 bool ParseFullKey(const Slice& internal_key, FullKey* result);
 
 }  //  namespace rocksdb
-
-#endif //  STORAGE_ROCKSDB_INCLUDE_TYPES_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/universal_compaction.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/universal_compaction.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/universal_compaction.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/universal_compaction.h
index ed2220873c..04e2c849f9 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/universal_compaction.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/universal_compaction.h
@@ -3,8 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#ifndef STORAGE_ROCKSDB_UNIVERSAL_COMPACTION_OPTIONS_H
-#define STORAGE_ROCKSDB_UNIVERSAL_COMPACTION_OPTIONS_H
+#pragma once
 
 #include <stdint.h>
 #include <climits>
@@ -86,5 +85,3 @@ class CompactionOptionsUniversal {
 };
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_UNIVERSAL_COMPACTION_OPTIONS_H
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/backupable_db.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/backupable_db.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/backupable_db.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/backupable_db.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/checkpoint.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/checkpoint.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/checkpoint.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/checkpoint.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/convenience.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/convenience.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/convenience.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/convenience.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/date_tiered_db.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/date_tiered_db.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/date_tiered_db.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/date_tiered_db.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/db_ttl.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/db_ttl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/db_ttl.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/db_ttl.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/debug.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/debug.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/debug.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/debug.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/document_db.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/document_db.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/document_db.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/document_db.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/env_librados.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/env_librados.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/env_librados.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/env_librados.h
index 272365f0c6..82a1f0ba5a 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/env_librados.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/env_librados.h
@@ -2,8 +2,8 @@
 //  This source code is licensed under both the GPLv2 (found in the
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
-#ifndef ROCKSDB_UTILITIES_ENV_LIBRADOS_H
-#define ROCKSDB_UTILITIES_ENV_LIBRADOS_H
+
+#pragma once
 
 #include <memory>
 #include <string>
@@ -173,4 +173,3 @@ class EnvLibrados : public EnvWrapper {
   friend class LibradosWritableFile;
 };
 }
-#endif
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/env_mirror.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/env_mirror.h
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/env_mirror.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/env_mirror.h
index bc27cdc488..40e9411ffa 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/env_mirror.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/env_mirror.h
@@ -48,20 +48,21 @@ class EnvMirror : public EnvWrapper {
       delete b_;
   }
 
-  Status NewSequentialFile(const std::string& f, unique_ptr<SequentialFile>* r,
+  Status NewSequentialFile(const std::string& f,
+                           std::unique_ptr<SequentialFile>* r,
                            const EnvOptions& options) override;
   Status NewRandomAccessFile(const std::string& f,
-                             unique_ptr<RandomAccessFile>* r,
+                             std::unique_ptr<RandomAccessFile>* r,
                              const EnvOptions& options) override;
-  Status NewWritableFile(const std::string& f, unique_ptr<WritableFile>* r,
+  Status NewWritableFile(const std::string& f, std::unique_ptr<WritableFile>* r,
                          const EnvOptions& options) override;
   Status ReuseWritableFile(const std::string& fname,
                            const std::string& old_fname,
-                           unique_ptr<WritableFile>* r,
+                           std::unique_ptr<WritableFile>* r,
                            const EnvOptions& options) override;
   virtual Status NewDirectory(const std::string& name,
-                              unique_ptr<Directory>* result) override {
-    unique_ptr<Directory> br;
+                              std::unique_ptr<Directory>* result) override {
+    std::unique_ptr<Directory> br;
     Status as = a_->NewDirectory(name, result);
     Status bs = b_->NewDirectory(name, &br);
     assert(as == bs);
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/geo_db.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/geo_db.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/geo_db.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/geo_db.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/info_log_finder.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/info_log_finder.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/info_log_finder.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/info_log_finder.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/json_document.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/json_document.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/json_document.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/json_document.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/ldb_cmd.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/ldb_cmd.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/ldb_cmd.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/ldb_cmd.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/ldb_cmd_execute_result.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/ldb_cmd_execute_result.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/ldb_cmd_execute_result.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/ldb_cmd_execute_result.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/leveldb_options.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/leveldb_options.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/leveldb_options.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/leveldb_options.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/lua/rocks_lua_compaction_filter.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/lua/rocks_lua_compaction_filter.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/lua/rocks_lua_compaction_filter.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/lua/rocks_lua_compaction_filter.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/lua/rocks_lua_custom_library.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/lua/rocks_lua_custom_library.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/lua/rocks_lua_custom_library.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/lua/rocks_lua_custom_library.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/lua/rocks_lua_util.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/lua/rocks_lua_util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/lua/rocks_lua_util.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/lua/rocks_lua_util.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/memory_util.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/memory_util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/memory_util.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/memory_util.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/object_registry.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/object_registry.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/object_registry.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/object_registry.h
index b046ba7c1f..86a51b92ea 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/object_registry.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/object_registry.h
@@ -27,8 +27,8 @@ namespace rocksdb {
 template <typename T>
 T* NewCustomObject(const std::string& target, std::unique_ptr<T>* res_guard);
 
-// Returns a new T when called with a string. Populates the unique_ptr argument
-// if granting ownership to caller.
+// Returns a new T when called with a string. Populates the std::unique_ptr
+// argument if granting ownership to caller.
 template <typename T>
 using FactoryFunc = std::function<T*(const std::string&, std::unique_ptr<T>*)>;
 
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/optimistic_transaction_db.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/optimistic_transaction_db.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/optimistic_transaction_db.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/optimistic_transaction_db.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/option_change_migration.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/option_change_migration.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/option_change_migration.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/option_change_migration.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/options_util.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/options_util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/options_util.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/options_util.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/sim_cache.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/sim_cache.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/sim_cache.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/sim_cache.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/spatial_db.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/spatial_db.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/spatial_db.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/spatial_db.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/stackable_db.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/stackable_db.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/stackable_db.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/stackable_db.h
index 721203f7ce..eae3a85ea1 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/stackable_db.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/stackable_db.h
@@ -278,6 +278,11 @@ class StackableDB : public DB {
                        ColumnFamilyHandle* column_family) override {
     return db_->Flush(fopts, column_family);
   }
+  virtual Status Flush(
+      const FlushOptions& fopts,
+      const std::vector<ColumnFamilyHandle*>& column_families) override {
+    return db_->Flush(fopts, column_families);
+  }
 
   virtual Status SyncWAL() override {
     return db_->SyncWAL();
@@ -364,7 +369,7 @@ class StackableDB : public DB {
   }
 
   virtual Status GetUpdatesSince(
-      SequenceNumber seq_number, unique_ptr<TransactionLogIterator>* iter,
+      SequenceNumber seq_number, std::unique_ptr<TransactionLogIterator>* iter,
       const TransactionLogIterator::ReadOptions& read_options) override {
     return db_->GetUpdatesSince(seq_number, iter, read_options);
   }
diff --git a/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/table_properties_collectors.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/table_properties_collectors.h
new file mode 100644
index 0000000000..c74f89bc9a
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/table_properties_collectors.h
@@ -0,0 +1,77 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+#ifndef ROCKSDB_LITE
+#include <atomic>
+#include <memory>
+
+#include "rocksdb/table_properties.h"
+
+namespace rocksdb {
+
+// A factory of a table property collector that marks a SST
+// file as need-compaction when it observe at least "D" deletion
+// entries in any "N" consecutive entires.
+class CompactOnDeletionCollectorFactory
+    : public TablePropertiesCollectorFactory {
+ public:
+  virtual ~CompactOnDeletionCollectorFactory() {}
+
+  virtual TablePropertiesCollector* CreateTablePropertiesCollector(
+      TablePropertiesCollectorFactory::Context context) override;
+
+  // Change the value of sliding_window_size "N"
+  // Setting it to 0 disables the delete triggered compaction
+  void SetWindowSize(size_t sliding_window_size) {
+    sliding_window_size_.store(sliding_window_size);
+  }
+
+  // Change the value of deletion_trigger "D"
+  void SetDeletionTrigger(size_t deletion_trigger) {
+    deletion_trigger_.store(deletion_trigger);
+  }
+
+  virtual const char* Name() const override {
+    return "CompactOnDeletionCollector";
+  }
+
+ private:
+  friend std::shared_ptr<CompactOnDeletionCollectorFactory>
+    NewCompactOnDeletionCollectorFactory(
+        size_t sliding_window_size,
+        size_t deletion_trigger);
+  // A factory of a table property collector that marks a SST
+  // file as need-compaction when it observe at least "D" deletion
+  // entries in any "N" consecutive entires.
+  //
+  // @param sliding_window_size "N"
+  // @param deletion_trigger "D"
+  CompactOnDeletionCollectorFactory(
+      size_t sliding_window_size,
+      size_t deletion_trigger) :
+          sliding_window_size_(sliding_window_size),
+          deletion_trigger_(deletion_trigger) {}
+
+  std::atomic<size_t> sliding_window_size_;
+  std::atomic<size_t> deletion_trigger_;
+};
+
+// Creates a factory of a table property collector that marks a SST
+// file as need-compaction when it observe at least "D" deletion
+// entries in any "N" consecutive entires.
+//
+// @param sliding_window_size "N". Note that this number will be
+//     round up to the smallest multiple of 128 that is no less
+//     than the specified size.
+// @param deletion_trigger "D".  Note that even when "N" is changed,
+//     the specified number for "D" will not be changed.
+extern std::shared_ptr<CompactOnDeletionCollectorFactory>
+    NewCompactOnDeletionCollectorFactory(
+        size_t sliding_window_size,
+        size_t deletion_trigger);
+}  // namespace rocksdb
+
+#endif  // !ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/transaction.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/transaction.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/transaction.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/transaction.h
index d6974ca6e2..c1e2441bc3 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/transaction.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/transaction.h
@@ -239,14 +239,15 @@ class Transaction {
   // An overload of the above method that receives a PinnableSlice
   // For backward compatibility a default implementation is provided
   virtual Status GetForUpdate(const ReadOptions& options,
-                              ColumnFamilyHandle* /*column_family*/,
+                              ColumnFamilyHandle* column_family,
                               const Slice& key, PinnableSlice* pinnable_val,
-                              bool /*exclusive*/ = true) {
+                              bool exclusive = true) {
     if (pinnable_val == nullptr) {
       std::string* null_str = nullptr;
-      return GetForUpdate(options, key, null_str);
+      return GetForUpdate(options, column_family, key, null_str, exclusive);
     } else {
-      auto s = GetForUpdate(options, key, pinnable_val->GetSelf());
+      auto s = GetForUpdate(options, column_family, key,
+                            pinnable_val->GetSelf(), exclusive);
       pinnable_val->PinSelf();
       return s;
     }
@@ -437,12 +438,6 @@ class Transaction {
   virtual void SetLogNumber(uint64_t log) { log_number_ = log; }
 
   virtual uint64_t GetLogNumber() const { return log_number_; }
-  
-  // Sequence number in WAL where operations start, only valid after
-  // a successfull commit with the WRITE_COMMITTED db txn policy
-  virtual SequenceNumber GetCommitedSeqNumber() const {
-    return 0;
-  }
 
   virtual Status SetName(const TransactionName& name) = 0;
 
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/transaction_db.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/transaction_db.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/transaction_db.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/transaction_db.h
index 92b2d98a59..1a692f2a7a 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/transaction_db.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/transaction_db.h
@@ -137,6 +137,15 @@ struct TransactionOptions {
 
   // The maximum number of bytes used for the write batch. 0 means no limit.
   size_t max_write_batch_size = 0;
+
+  // Skip Concurrency Control. This could be as an optimization if the
+  // application knows that the transaction would not have any conflict with
+  // concurrent transactions. It could also be used during recovery if (i)
+  // application guarantees no conflict between prepared transactions in the WAL
+  // (ii) application guarantees that recovered transactions will be rolled
+  // back/commit before new transactions start.
+  // Default: false
+  bool skip_concurrency_control = false;
 };
 
 // The per-write optimizations that do not involve transactions. TransactionDB
@@ -162,8 +171,8 @@ struct KeyLockInfo {
 struct DeadlockInfo {
   TransactionID m_txn_id;
   uint32_t m_cf_id;
-  std::string m_waiting_key;
   bool m_exclusive;
+  std::string m_waiting_key;
 };
 
 struct DeadlockPath {
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/transaction_db_mutex.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/transaction_db_mutex.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/transaction_db_mutex.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/transaction_db_mutex.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/utility_db.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/utility_db.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/utility_db.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/utility_db.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/write_batch_with_index.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/write_batch_with_index.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/utilities/write_batch_with_index.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/utilities/write_batch_with_index.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/version.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/version.h
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/version.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/version.h
index a2a6426fb5..89802521d9 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/version.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/version.h
@@ -5,7 +5,7 @@
 #pragma once
 
 #define ROCKSDB_MAJOR 5
-#define ROCKSDB_MINOR 16
+#define ROCKSDB_MINOR 18
 #define ROCKSDB_PATCH 0
 
 // Do not use these. We made the mistake of declaring macros starting with
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/wal_filter.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/wal_filter.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/wal_filter.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/wal_filter.h
index a22dca9237..b8be77b232 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/wal_filter.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/wal_filter.h
@@ -4,6 +4,7 @@
 //  (found in the LICENSE.Apache file in the root directory).
 
 #pragma once
+
 #include <string>
 #include <map>
 
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/write_batch.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/write_batch.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/write_batch.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/write_batch.h
index 7db177f866..c40c448fdd 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/write_batch.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/write_batch.h
@@ -22,8 +22,7 @@
 // non-const method, all threads accessing the same WriteBatch must use
 // external synchronization.
 
-#ifndef STORAGE_ROCKSDB_INCLUDE_WRITE_BATCH_H_
-#define STORAGE_ROCKSDB_INCLUDE_WRITE_BATCH_H_
+#pragma once
 
 #include <atomic>
 #include <stack>
@@ -367,5 +366,3 @@ class WriteBatch : public WriteBatchBase {
 };
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_ROCKSDB_INCLUDE_WRITE_BATCH_H_
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/write_batch_base.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/write_batch_base.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/write_batch_base.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/write_batch_base.h
diff --git a/3rdParty/rocksdb/v5.16.X/include/rocksdb/write_buffer_manager.h b/3rdParty/rocksdb/v5.18.X/include/rocksdb/write_buffer_manager.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/include/rocksdb/write_buffer_manager.h
rename to 3rdParty/rocksdb/v5.18.X/include/rocksdb/write_buffer_manager.h
index 856cf4b246..dea904c187 100644
--- a/3rdParty/rocksdb/v5.16.X/include/rocksdb/write_buffer_manager.h
+++ b/3rdParty/rocksdb/v5.18.X/include/rocksdb/write_buffer_manager.h
@@ -30,6 +30,8 @@ class WriteBufferManager {
 
   bool enabled() const { return buffer_size_ != 0; }
 
+  bool cost_to_cache() const { return cache_rep_ != nullptr; }
+
   // Only valid if enabled()
   size_t memory_usage() const {
     return memory_used_.load(std::memory_order_relaxed);
diff --git a/3rdParty/rocksdb/v5.16.X/issue_template.md b/3rdParty/rocksdb/v5.18.X/issue_template.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/issue_template.md
rename to 3rdParty/rocksdb/v5.18.X/issue_template.md
diff --git a/3rdParty/rocksdb/v5.16.X/java/CMakeLists.txt b/3rdParty/rocksdb/v5.18.X/java/CMakeLists.txt
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/java/CMakeLists.txt
rename to 3rdParty/rocksdb/v5.18.X/java/CMakeLists.txt
index 96c08b2318..8f4ec9a568 100644
--- a/3rdParty/rocksdb/v5.16.X/java/CMakeLists.txt
+++ b/3rdParty/rocksdb/v5.18.X/java/CMakeLists.txt
@@ -25,6 +25,7 @@ set(JNI_NATIVE_SOURCES
         rocksjni/jnicallback.cc
         rocksjni/loggerjnicallback.cc
         rocksjni/lru_cache.cc
+        rocksjni/memory_util.cc
         rocksjni/memtablejni.cc
         rocksjni/merge_operator.cc
         rocksjni/native_comparator_wrapper_test.cc
@@ -57,6 +58,7 @@ set(JNI_NATIVE_SOURCES
         rocksjni/writebatchhandlerjnicallback.cc
         rocksjni/write_batch_test.cc
         rocksjni/write_batch_with_index.cc
+        rocksjni/write_buffer_manager.cc
 )
 
 set(NATIVE_JAVA_CLASSES
@@ -96,6 +98,7 @@ set(NATIVE_JAVA_CLASSES
         org.rocksdb.IngestExternalFileOptions
         org.rocksdb.Logger
         org.rocksdb.LRUCache
+        org.rocksdb.MemoryUtil
         org.rocksdb.MemTableConfig
         org.rocksdb.NativeComparatorWrapper
         org.rocksdb.NativeLibraryLoader
@@ -130,6 +133,7 @@ set(NATIVE_JAVA_CLASSES
         org.rocksdb.TransactionLogIterator
         org.rocksdb.TransactionOptions
         org.rocksdb.TtlDB
+        org.rocksdb.UInt64AddOperator
         org.rocksdb.VectorMemTableConfig
         org.rocksdb.WBWIRocksIterator
         org.rocksdb.WriteBatch
@@ -142,6 +146,7 @@ set(NATIVE_JAVA_CLASSES
         org.rocksdb.SnapshotTest
         org.rocksdb.WriteBatchTest
         org.rocksdb.WriteBatchTestInternalHelper
+        org.rocksdb.WriteBufferManager
 )
 
 include(FindJava)
@@ -222,6 +227,8 @@ add_jar(
   src/main/java/org/rocksdb/IngestExternalFileOptions.java
   src/main/java/org/rocksdb/Logger.java
   src/main/java/org/rocksdb/LRUCache.java
+  src/main/java/org/rocksdb/MemoryUsageType.java
+  src/main/java/org/rocksdb/MemoryUtil.java
   src/main/java/org/rocksdb/MemTableConfig.java
   src/main/java/org/rocksdb/MergeOperator.java
   src/main/java/org/rocksdb/MutableColumnFamilyOptionsInterface.java
@@ -278,6 +285,7 @@ add_jar(
   src/main/java/org/rocksdb/WriteBatch.java
   src/main/java/org/rocksdb/WriteBatchWithIndex.java
   src/main/java/org/rocksdb/WriteOptions.java
+  src/main/java/org/rocksdb/WriteBufferManager.java
   src/main/java/org/rocksdb/util/BytewiseComparator.java
   src/main/java/org/rocksdb/util/DirectBytewiseComparator.java
   src/main/java/org/rocksdb/util/Environment.java
@@ -290,6 +298,7 @@ add_jar(
   src/test/java/org/rocksdb/RocksDBExceptionTest.java
   src/test/java/org/rocksdb/RocksMemoryResource.java
   src/test/java/org/rocksdb/SnapshotTest.java
+  src/main/java/org/rocksdb/UInt64AddOperator.java
   src/test/java/org/rocksdb/WriteBatchTest.java
   src/test/java/org/rocksdb/util/CapturingWriteBatchHandler.java
   src/test/java/org/rocksdb/util/WriteBatchGetter.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/HISTORY-JAVA.md b/3rdParty/rocksdb/v5.18.X/java/HISTORY-JAVA.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/HISTORY-JAVA.md
rename to 3rdParty/rocksdb/v5.18.X/java/HISTORY-JAVA.md
diff --git a/3rdParty/rocksdb/v5.16.X/java/Makefile b/3rdParty/rocksdb/v5.18.X/java/Makefile
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/java/Makefile
rename to 3rdParty/rocksdb/v5.18.X/java/Makefile
index f58fff06e5..b3b89eb837 100644
--- a/3rdParty/rocksdb/v5.16.X/java/Makefile
+++ b/3rdParty/rocksdb/v5.18.X/java/Makefile
@@ -30,6 +30,8 @@ NATIVE_JAVA_CLASSES = org.rocksdb.AbstractCompactionFilter\
 	org.rocksdb.HashSkipListMemTableConfig\
 	org.rocksdb.Logger\
 	org.rocksdb.LRUCache\
+	org.rocksdb.MemoryUsageType\
+	org.rocksdb.MemoryUtil\
 	org.rocksdb.MergeOperator\
 	org.rocksdb.NativeComparatorWrapper\
 	org.rocksdb.OptimisticTransactionDB\
@@ -60,10 +62,12 @@ NATIVE_JAVA_CLASSES = org.rocksdb.AbstractCompactionFilter\
 	org.rocksdb.VectorMemTableConfig\
 	org.rocksdb.Snapshot\
 	org.rocksdb.StringAppendOperator\
+	org.rocksdb.UInt64AddOperator\
 	org.rocksdb.WriteBatch\
 	org.rocksdb.WriteBatch.Handler\
 	org.rocksdb.WriteOptions\
 	org.rocksdb.WriteBatchWithIndex\
+	org.rocksdb.WriteBufferManager\
 	org.rocksdb.WBWIRocksIterator
 
 NATIVE_JAVA_TEST_CLASSES = org.rocksdb.RocksDBExceptionTest\
@@ -111,6 +115,7 @@ JAVA_TESTS = org.rocksdb.BackupableDBOptionsTest\
 	org.rocksdb.KeyMayExistTest\
 	org.rocksdb.LoggerTest\
 	org.rocksdb.LRUCacheTest\
+	org.rocksdb.MemoryUtilTest\
 	org.rocksdb.MemTableTest\
 	org.rocksdb.MergeTest\
 	org.rocksdb.MixedOptionsTest\
diff --git a/3rdParty/rocksdb/v5.16.X/java/RELEASE.md b/3rdParty/rocksdb/v5.18.X/java/RELEASE.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/RELEASE.md
rename to 3rdParty/rocksdb/v5.18.X/java/RELEASE.md
diff --git a/3rdParty/rocksdb/v5.16.X/java/benchmark/src/main/java/org/rocksdb/benchmark/DbBenchmark.java b/3rdParty/rocksdb/v5.18.X/java/benchmark/src/main/java/org/rocksdb/benchmark/DbBenchmark.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/benchmark/src/main/java/org/rocksdb/benchmark/DbBenchmark.java
rename to 3rdParty/rocksdb/v5.18.X/java/benchmark/src/main/java/org/rocksdb/benchmark/DbBenchmark.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/crossbuild/Vagrantfile b/3rdParty/rocksdb/v5.18.X/java/crossbuild/Vagrantfile
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/crossbuild/Vagrantfile
rename to 3rdParty/rocksdb/v5.18.X/java/crossbuild/Vagrantfile
diff --git a/3rdParty/rocksdb/v5.16.X/java/crossbuild/build-linux-centos.sh b/3rdParty/rocksdb/v5.18.X/java/crossbuild/build-linux-centos.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/crossbuild/build-linux-centos.sh
rename to 3rdParty/rocksdb/v5.18.X/java/crossbuild/build-linux-centos.sh
diff --git a/3rdParty/rocksdb/v5.16.X/java/crossbuild/build-linux.sh b/3rdParty/rocksdb/v5.18.X/java/crossbuild/build-linux.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/crossbuild/build-linux.sh
rename to 3rdParty/rocksdb/v5.18.X/java/crossbuild/build-linux.sh
diff --git a/3rdParty/rocksdb/v5.16.X/java/crossbuild/docker-build-linux-centos.sh b/3rdParty/rocksdb/v5.18.X/java/crossbuild/docker-build-linux-centos.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/crossbuild/docker-build-linux-centos.sh
rename to 3rdParty/rocksdb/v5.18.X/java/crossbuild/docker-build-linux-centos.sh
diff --git a/3rdParty/rocksdb/v5.16.X/java/jdb_bench.sh b/3rdParty/rocksdb/v5.18.X/java/jdb_bench.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/jdb_bench.sh
rename to 3rdParty/rocksdb/v5.18.X/java/jdb_bench.sh
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni.pom b/3rdParty/rocksdb/v5.18.X/java/rocksjni.pom
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni.pom
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni.pom
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/backupablejni.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/backupablejni.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/backupablejni.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/backupablejni.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/backupenginejni.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/backupenginejni.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/backupenginejni.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/backupenginejni.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/cassandra_compactionfilterjni.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/cassandra_compactionfilterjni.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/cassandra_compactionfilterjni.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/cassandra_compactionfilterjni.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/cassandra_value_operator.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/cassandra_value_operator.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/cassandra_value_operator.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/cassandra_value_operator.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/checkpoint.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/checkpoint.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/checkpoint.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/checkpoint.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/clock_cache.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/clock_cache.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/clock_cache.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/clock_cache.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/columnfamilyhandle.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/columnfamilyhandle.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/columnfamilyhandle.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/columnfamilyhandle.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/compact_range_options.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/compact_range_options.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/compact_range_options.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/compact_range_options.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_filter.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_filter.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_filter.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_filter.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_filter_factory.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_filter_factory.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_filter_factory.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_filter_factory.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_filter_factory_jnicallback.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_filter_factory_jnicallback.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_filter_factory_jnicallback.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_filter_factory_jnicallback.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_filter_factory_jnicallback.h b/3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_filter_factory_jnicallback.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_filter_factory_jnicallback.h
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_filter_factory_jnicallback.h
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_options_fifo.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_options_fifo.cc
similarity index 56%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_options_fifo.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_options_fifo.cc
index 95bbfc621d..00761b6ac5 100644
--- a/3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_options_fifo.cc
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_options_fifo.cc
@@ -46,6 +46,53 @@ jlong Java_org_rocksdb_CompactionOptionsFIFO_maxTableFilesSize(JNIEnv* /*env*/,
   return static_cast<jlong>(opt->max_table_files_size);
 }
 
+/*
+ * Class:     org_rocksdb_CompactionOptionsFIFO
+ * Method:    setTtl
+ * Signature: (JJ)V
+ */
+void Java_org_rocksdb_CompactionOptionsFIFO_setTtl(JNIEnv* /*env*/,
+                                                   jobject /*jobj*/,
+                                                   jlong jhandle, jlong ttl) {
+  auto* opt = reinterpret_cast<rocksdb::CompactionOptionsFIFO*>(jhandle);
+  opt->ttl = static_cast<uint64_t>(ttl);
+}
+
+/*
+ * Class:     org_rocksdb_CompactionOptionsFIFO
+ * Method:    ttl
+ * Signature: (J)J
+ */
+jlong Java_org_rocksdb_CompactionOptionsFIFO_ttl(JNIEnv* /*env*/,
+                                                 jobject /*jobj*/,
+                                                 jlong jhandle) {
+  auto* opt = reinterpret_cast<rocksdb::CompactionOptionsFIFO*>(jhandle);
+  return static_cast<jlong>(opt->ttl);
+}
+
+/*
+ * Class:     org_rocksdb_CompactionOptionsFIFO
+ * Method:    setAllowCompaction
+ * Signature: (JZ)V
+ */
+void Java_org_rocksdb_CompactionOptionsFIFO_setAllowCompaction(
+    JNIEnv* /*env*/, jobject /*jobj*/, jlong jhandle,
+    jboolean allow_compaction) {
+  auto* opt = reinterpret_cast<rocksdb::CompactionOptionsFIFO*>(jhandle);
+  opt->allow_compaction = static_cast<bool>(allow_compaction);
+}
+
+/*
+ * Class:     org_rocksdb_CompactionOptionsFIFO
+ * Method:    allowCompaction
+ * Signature: (J)Z
+ */
+jboolean Java_org_rocksdb_CompactionOptionsFIFO_allowCompaction(
+    JNIEnv* /*env*/, jobject /*jobj*/, jlong jhandle) {
+  auto* opt = reinterpret_cast<rocksdb::CompactionOptionsFIFO*>(jhandle);
+  return static_cast<jboolean>(opt->allow_compaction);
+}
+
 /*
  * Class:     org_rocksdb_CompactionOptionsFIFO
  * Method:    disposeInternal
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_options_universal.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_options_universal.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/compaction_options_universal.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/compaction_options_universal.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/comparator.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/comparator.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/comparator.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/comparator.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/comparatorjnicallback.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/comparatorjnicallback.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/comparatorjnicallback.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/comparatorjnicallback.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/comparatorjnicallback.h b/3rdParty/rocksdb/v5.18.X/java/rocksjni/comparatorjnicallback.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/comparatorjnicallback.h
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/comparatorjnicallback.h
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/compression_options.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/compression_options.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/compression_options.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/compression_options.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/env.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/env.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/env.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/env.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/env_options.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/env_options.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/env_options.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/env_options.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/filter.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/filter.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/filter.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/filter.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/ingest_external_file_options.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/ingest_external_file_options.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/ingest_external_file_options.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/ingest_external_file_options.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/iterator.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/iterator.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/iterator.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/iterator.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/jnicallback.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/jnicallback.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/jnicallback.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/jnicallback.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/jnicallback.h b/3rdParty/rocksdb/v5.18.X/java/rocksjni/jnicallback.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/jnicallback.h
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/jnicallback.h
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/loggerjnicallback.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/loggerjnicallback.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/loggerjnicallback.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/loggerjnicallback.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/loggerjnicallback.h b/3rdParty/rocksdb/v5.18.X/java/rocksjni/loggerjnicallback.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/loggerjnicallback.h
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/loggerjnicallback.h
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/lru_cache.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/lru_cache.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/lru_cache.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/lru_cache.cc
diff --git a/3rdParty/rocksdb/v5.18.X/java/rocksjni/memory_util.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/memory_util.cc
new file mode 100644
index 0000000000..9c2bfd04e2
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/memory_util.cc
@@ -0,0 +1,100 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include <jni.h>
+#include <map>
+#include <string>
+#include <unordered_set>
+#include <vector>
+
+#include "include/org_rocksdb_MemoryUtil.h"
+
+#include "rocksjni/portal.h"
+
+#include "rocksdb/utilities/memory_util.h"
+
+
+/*
+ * Class:     org_rocksdb_MemoryUtil
+ * Method:    getApproximateMemoryUsageByType
+ * Signature: ([J[J)Ljava/util/Map;
+ */
+jobject Java_org_rocksdb_MemoryUtil_getApproximateMemoryUsageByType(
+    JNIEnv *env, jclass /*jclazz*/, jlongArray jdb_handles, jlongArray jcache_handles) {
+
+  std::vector<rocksdb::DB*> dbs;
+  jsize db_handle_count = env->GetArrayLength(jdb_handles);
+  if(db_handle_count > 0) {
+    jlong *ptr_jdb_handles = env->GetLongArrayElements(jdb_handles, nullptr);
+    if (ptr_jdb_handles == nullptr) {
+      // exception thrown: OutOfMemoryError
+      return nullptr;
+    }
+    for (jsize i = 0; i < db_handle_count; i++) {
+      dbs.push_back(reinterpret_cast<rocksdb::DB *>(ptr_jdb_handles[i]));
+    }
+    env->ReleaseLongArrayElements(jdb_handles, ptr_jdb_handles, JNI_ABORT);
+  }
+
+  std::unordered_set<const rocksdb::Cache*> cache_set;
+  jsize cache_handle_count = env->GetArrayLength(jcache_handles);
+  if(cache_handle_count > 0) {
+    jlong *ptr_jcache_handles = env->GetLongArrayElements(jcache_handles, nullptr);
+    if (ptr_jcache_handles == nullptr) {
+      // exception thrown: OutOfMemoryError
+      return nullptr;
+    }
+    for (jsize i = 0; i < cache_handle_count; i++) {
+      auto *cache_ptr =
+          reinterpret_cast<std::shared_ptr<rocksdb::Cache> *>(ptr_jcache_handles[i]);
+      cache_set.insert(cache_ptr->get());
+    }
+    env->ReleaseLongArrayElements(jcache_handles, ptr_jcache_handles, JNI_ABORT);
+  }
+
+  std::map<rocksdb::MemoryUtil::UsageType, uint64_t> usage_by_type;
+  if(rocksdb::MemoryUtil::GetApproximateMemoryUsageByType(dbs, cache_set, &usage_by_type) != rocksdb::Status::OK()) {
+    // Non-OK status
+    return nullptr;
+  }
+
+  jobject jusage_by_type = rocksdb::HashMapJni::construct(
+      env, static_cast<uint32_t>(usage_by_type.size()));
+  if (jusage_by_type == nullptr) {
+    // exception occurred
+    return nullptr;
+  }
+  const rocksdb::HashMapJni::FnMapKV<const rocksdb::MemoryUtil::UsageType, const uint64_t>
+      fn_map_kv =
+      [env](const std::pair<rocksdb::MemoryUtil::UsageType, uint64_t>& pair) {
+        // Construct key
+        const jobject jusage_type =
+            rocksdb::ByteJni::valueOf(env, rocksdb::MemoryUsageTypeJni::toJavaMemoryUsageType(pair.first));
+        if (jusage_type == nullptr) {
+          // an error occurred
+          return std::unique_ptr<std::pair<jobject, jobject>>(nullptr);
+        }
+        // Construct value
+        const jobject jusage_value =
+            rocksdb::LongJni::valueOf(env, pair.second);
+        if (jusage_value == nullptr) {
+          // an error occurred
+          return std::unique_ptr<std::pair<jobject, jobject>>(nullptr);
+        }
+        // Construct and return pointer to pair of jobjects
+        return std::unique_ptr<std::pair<jobject, jobject>>(
+            new std::pair<jobject, jobject>(jusage_type,
+                                            jusage_value));
+      };
+
+  if (!rocksdb::HashMapJni::putAll(env, jusage_by_type, usage_by_type.begin(),
+                                   usage_by_type.end(), fn_map_kv)) {
+    // exception occcurred
+    jusage_by_type = nullptr;
+  }
+
+  return jusage_by_type;
+
+}
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/memtablejni.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/memtablejni.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/memtablejni.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/memtablejni.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/merge_operator.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/merge_operator.cc
similarity index 65%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/merge_operator.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/merge_operator.cc
index 782153f571..e06a06f7e3 100644
--- a/3rdParty/rocksdb/v5.16.X/java/rocksjni/merge_operator.cc
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/merge_operator.cc
@@ -13,6 +13,7 @@
 #include <string>
 
 #include "include/org_rocksdb_StringAppendOperator.h"
+#include "include/org_rocksdb_UInt64AddOperator.h"
 #include "rocksdb/db.h"
 #include "rocksdb/memtablerep.h"
 #include "rocksdb/merge_operator.h"
@@ -47,3 +48,28 @@ void Java_org_rocksdb_StringAppendOperator_disposeInternal(JNIEnv* /*env*/,
       reinterpret_cast<std::shared_ptr<rocksdb::MergeOperator>*>(jhandle);
   delete sptr_string_append_op;  // delete std::shared_ptr
 }
+
+/*
+ * Class:     org_rocksdb_UInt64AddOperator
+ * Method:    newSharedUInt64AddOperator
+ * Signature: ()J
+ */
+jlong Java_org_rocksdb_UInt64AddOperator_newSharedUInt64AddOperator(
+    JNIEnv* /*env*/, jclass /*jclazz*/) {
+  auto* sptr_uint64_add_op = new std::shared_ptr<rocksdb::MergeOperator>(
+      rocksdb::MergeOperators::CreateUInt64AddOperator());
+  return reinterpret_cast<jlong>(sptr_uint64_add_op);
+}
+
+/*
+ * Class:     org_rocksdb_UInt64AddOperator
+ * Method:    disposeInternal
+ * Signature: (J)V
+ */
+void Java_org_rocksdb_UInt64AddOperator_disposeInternal(JNIEnv* /*env*/,
+                                                        jobject /*jobj*/,
+                                                        jlong jhandle) {
+  auto* sptr_uint64_add_op =
+      reinterpret_cast<std::shared_ptr<rocksdb::MergeOperator>*>(jhandle);
+  delete sptr_uint64_add_op;  // delete std::shared_ptr
+}
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/native_comparator_wrapper_test.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/native_comparator_wrapper_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/native_comparator_wrapper_test.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/native_comparator_wrapper_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/optimistic_transaction_db.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/optimistic_transaction_db.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/optimistic_transaction_db.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/optimistic_transaction_db.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/optimistic_transaction_options.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/optimistic_transaction_options.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/optimistic_transaction_options.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/optimistic_transaction_options.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/options.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/options.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/options.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/options.cc
index 9aed80e1e6..342ee3e9e4 100644
--- a/3rdParty/rocksdb/v5.16.X/java/rocksjni/options.cc
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/options.cc
@@ -250,6 +250,20 @@ void Java_org_rocksdb_Options_setWriteBufferSize(JNIEnv* env, jobject /*jobj*/,
   }
 }
 
+/*
+ * Class:     org_rocksdb_Options
+ * Method:    setWriteBufferManager
+ * Signature: (JJ)V
+ */
+void Java_org_rocksdb_Options_setWriteBufferManager(JNIEnv* /*env*/, jobject /*jobj*/,
+                                                    jlong joptions_handle,
+                                                    jlong jwrite_buffer_manager_handle) {
+  auto* write_buffer_manager =
+          reinterpret_cast<std::shared_ptr<rocksdb::WriteBufferManager> *>(jwrite_buffer_manager_handle);
+  reinterpret_cast<rocksdb::Options*>(joptions_handle)->write_buffer_manager =
+          *write_buffer_manager;
+}
+
 /*
  * Class:     org_rocksdb_Options
  * Method:    writeBufferSize
@@ -1956,8 +1970,8 @@ jbyte Java_org_rocksdb_Options_compressionType(JNIEnv* /*env*/,
  * @param jcompression_levels A reference to a java byte array
  *     where each byte indicates a compression level
  *
- * @return A unique_ptr to the vector, or unique_ptr(nullptr) if a JNI exception
- * occurs
+ * @return A std::unique_ptr to the vector, or std::unique_ptr(nullptr) if a JNI
+ * exception occurs
  */
 std::unique_ptr<std::vector<rocksdb::CompressionType>>
 rocksdb_compression_vector_helper(JNIEnv* env, jbyteArray jcompression_levels) {
@@ -5518,6 +5532,20 @@ void Java_org_rocksdb_DBOptions_setDbWriteBufferSize(
   opt->db_write_buffer_size = static_cast<size_t>(jdb_write_buffer_size);
 }
 
+/*
+ * Class:     org_rocksdb_DBOptions
+ * Method:    setWriteBufferManager
+ * Signature: (JJ)V
+ */
+void Java_org_rocksdb_DBOptions_setWriteBufferManager(JNIEnv* /*env*/, jobject /*jobj*/,
+                                                      jlong jdb_options_handle,
+                                                      jlong jwrite_buffer_manager_handle) {
+  auto* write_buffer_manager =
+      reinterpret_cast<std::shared_ptr<rocksdb::WriteBufferManager> *>(jwrite_buffer_manager_handle);
+  reinterpret_cast<rocksdb::DBOptions*>(jdb_options_handle)->write_buffer_manager =
+      *write_buffer_manager;
+}
+
 /*
  * Class:     org_rocksdb_DBOptions
  * Method:    dbWriteBufferSize
@@ -6525,6 +6553,31 @@ jlong Java_org_rocksdb_ReadOptions_iterateUpperBound(JNIEnv* /*env*/,
   return reinterpret_cast<jlong>(upper_bound_slice_handle);
 }
 
+/*
+ * Class:     org_rocksdb_ReadOptions
+ * Method:    setIterateLowerBound
+ * Signature: (JJ)I
+ */
+void Java_org_rocksdb_ReadOptions_setIterateLowerBound(
+    JNIEnv* /*env*/, jobject /*jobj*/, jlong jhandle,
+    jlong jlower_bound_slice_handle) {
+  reinterpret_cast<rocksdb::ReadOptions*>(jhandle)->iterate_lower_bound =
+      reinterpret_cast<rocksdb::Slice*>(jlower_bound_slice_handle);
+}
+
+/*
+ * Class:     org_rocksdb_ReadOptions
+ * Method:    iterateLowerBound
+ * Signature: (J)J
+ */
+jlong Java_org_rocksdb_ReadOptions_iterateLowerBound(JNIEnv* /*env*/,
+                                                     jobject /*jobj*/,
+                                                     jlong jhandle) {
+  auto& lower_bound_slice_handle =
+      reinterpret_cast<rocksdb::ReadOptions*>(jhandle)->iterate_lower_bound;
+  return reinterpret_cast<jlong>(lower_bound_slice_handle);
+}
+
 /////////////////////////////////////////////////////////////////////
 // rocksdb::ComparatorOptions
 
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/options_util.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/options_util.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/options_util.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/options_util.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/portal.h b/3rdParty/rocksdb/v5.18.X/java/rocksjni/portal.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/portal.h
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/portal.h
index a0d1846a65..0bf2867c1c 100644
--- a/3rdParty/rocksdb/v5.16.X/java/rocksjni/portal.h
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/portal.h
@@ -26,6 +26,7 @@
 #include "rocksdb/rate_limiter.h"
 #include "rocksdb/status.h"
 #include "rocksdb/utilities/backupable_db.h"
+#include "rocksdb/utilities/memory_util.h"
 #include "rocksdb/utilities/transaction_db.h"
 #include "rocksdb/utilities/write_batch_with_index.h"
 #include "rocksjni/compaction_filter_factory_jnicallback.h"
@@ -2251,7 +2252,7 @@ class ByteJni : public JavaClass {
    * @param env A pointer to the Java environment
    *
    * @return The Java Method ID or nullptr if the class or method id could not
-   *     be retieved
+   *     be retrieved
    */
   static jmethodID getByteValueMethod(JNIEnv* env) {
     jclass clazz = getJClass(env);
@@ -2264,6 +2265,39 @@ class ByteJni : public JavaClass {
     assert(mid != nullptr);
     return mid;
   }
+
+  /**
+   * Calls the Java Method: Byte#valueOf, returning a constructed Byte jobject
+   *
+   * @param env A pointer to the Java environment
+   *
+   * @return A constructing Byte object or nullptr if the class or method id could not
+   *     be retrieved, or an exception occurred
+   */
+  static jobject valueOf(JNIEnv* env, jbyte jprimitive_byte) {
+    jclass clazz = getJClass(env);
+    if (clazz == nullptr) {
+      // exception occurred accessing class
+      return nullptr;
+    }
+
+    static jmethodID mid =
+        env->GetStaticMethodID(clazz, "valueOf", "(B)Ljava/lang/Byte;");
+    if (mid == nullptr) {
+      // exception thrown: NoSuchMethodException or OutOfMemoryError
+      return nullptr;
+    }
+
+    const jobject jbyte_obj =
+        env->CallStaticObjectMethod(clazz, mid, jprimitive_byte);
+    if (env->ExceptionCheck()) {
+      // exception occurred
+      return nullptr;
+    }
+
+    return jbyte_obj;
+  }
+
 };
 
 // The portal class for java.lang.StringBuilder
@@ -3345,8 +3379,12 @@ class TickerTypeJni {
         return 0x5D;
       case rocksdb::Tickers::NUMBER_MULTIGET_KEYS_FOUND:
         return 0x5E;
-      case rocksdb::Tickers::TICKER_ENUM_MAX:
+      case rocksdb::Tickers::NO_ITERATOR_CREATED:
         return 0x5F;
+      case rocksdb::Tickers::NO_ITERATOR_DELETED:
+        return 0x60;
+      case rocksdb::Tickers::TICKER_ENUM_MAX:
+        return 0x61;
 
       default:
         // undefined/default
@@ -3549,6 +3587,10 @@ class TickerTypeJni {
       case 0x5E:
         return rocksdb::Tickers::NUMBER_MULTIGET_KEYS_FOUND;
       case 0x5F:
+        return rocksdb::Tickers::NO_ITERATOR_CREATED;
+      case 0x60:
+        return rocksdb::Tickers::NO_ITERATOR_DELETED;
+      case 0x61:
         return rocksdb::Tickers::TICKER_ENUM_MAX;
 
       default:
@@ -3795,6 +3837,48 @@ class RateLimiterModeJni {
   }
 };
 
+// The portal class for org.rocksdb.MemoryUsageType
+class MemoryUsageTypeJni {
+public:
+  // Returns the equivalent org.rocksdb.MemoryUsageType for the provided
+  // C++ rocksdb::MemoryUtil::UsageType enum
+  static jbyte toJavaMemoryUsageType(
+      const rocksdb::MemoryUtil::UsageType& usage_type) {
+    switch(usage_type) {
+      case rocksdb::MemoryUtil::UsageType::kMemTableTotal:
+        return 0x0;
+      case rocksdb::MemoryUtil::UsageType::kMemTableUnFlushed:
+        return 0x1;
+      case rocksdb::MemoryUtil::UsageType::kTableReadersTotal:
+        return 0x2;
+      case rocksdb::MemoryUtil::UsageType::kCacheTotal:
+        return 0x3;
+      default:
+        // undefined: use kNumUsageTypes
+        return 0x4;
+    }
+  }
+
+  // Returns the equivalent C++ rocksdb::MemoryUtil::UsageType enum for the
+  // provided Java org.rocksdb.MemoryUsageType
+  static rocksdb::MemoryUtil::UsageType toCppMemoryUsageType(
+      jbyte usage_type) {
+    switch(usage_type) {
+      case 0x0:
+        return rocksdb::MemoryUtil::UsageType::kMemTableTotal;
+      case 0x1:
+        return rocksdb::MemoryUtil::UsageType::kMemTableUnFlushed;
+      case 0x2:
+        return rocksdb::MemoryUtil::UsageType::kTableReadersTotal;
+      case 0x3:
+        return rocksdb::MemoryUtil::UsageType::kCacheTotal;
+      default:
+        // undefined/default: use kNumUsageTypes
+        return rocksdb::MemoryUtil::UsageType::kNumUsageTypes;
+    }
+  }
+};
+
 // The portal class for org.rocksdb.Transaction
 class TransactionJni : public JavaClass {
  public:
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/ratelimiterjni.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/ratelimiterjni.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/ratelimiterjni.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/ratelimiterjni.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/remove_emptyvalue_compactionfilterjni.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/remove_emptyvalue_compactionfilterjni.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/remove_emptyvalue_compactionfilterjni.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/remove_emptyvalue_compactionfilterjni.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/restorejni.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/restorejni.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/restorejni.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/restorejni.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/rocks_callback_object.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/rocks_callback_object.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/rocks_callback_object.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/rocks_callback_object.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/rocksdb_exception_test.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/rocksdb_exception_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/rocksdb_exception_test.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/rocksdb_exception_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/rocksjni.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/rocksjni.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/rocksjni.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/rocksjni.cc
index c5b9fd591c..6e50c32f7a 100644
--- a/3rdParty/rocksdb/v5.16.X/java/rocksjni/rocksjni.cc
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/rocksjni.cc
@@ -1844,6 +1844,32 @@ jlong Java_org_rocksdb_RocksDB_getLongProperty__JJLjava_lang_String_2I(
   return 0;
 }
 
+/*
+ * Class:     org_rocksdb_RocksDB
+ * Method:    getAggregatedLongProperty
+ * Signature: (JLjava/lang/String;I)J
+ */
+jlong Java_org_rocksdb_RocksDB_getAggregatedLongProperty(
+    JNIEnv* env, jobject, jlong db_handle, jstring jproperty, jint jproperty_len) {
+  const char* property = env->GetStringUTFChars(jproperty, nullptr);
+  if (property == nullptr) {
+    return 0;
+  }
+  rocksdb::Slice property_slice(property, jproperty_len);
+  auto* db = reinterpret_cast<rocksdb::DB*>(db_handle);
+  uint64_t property_value = 0;
+  bool retCode = db->GetAggregatedIntProperty(property_slice, &property_value);
+  env->ReleaseStringUTFChars(jproperty, property);
+
+  if (retCode) {
+    return property_value;
+  }
+
+  rocksdb::RocksDBExceptionJni::ThrowNew(env, rocksdb::Status::NotFound());
+  return 0;
+}
+
+
 //////////////////////////////////////////////////////////////////////////////
 // rocksdb::DB::Flush
 
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/slice.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/slice.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/slice.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/slice.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/snapshot.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/snapshot.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/snapshot.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/snapshot.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/sst_file_manager.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/sst_file_manager.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/sst_file_manager.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/sst_file_manager.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/sst_file_writerjni.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/sst_file_writerjni.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/sst_file_writerjni.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/sst_file_writerjni.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/statistics.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/statistics.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/statistics.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/statistics.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/statisticsjni.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/statisticsjni.cc
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/statisticsjni.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/statisticsjni.cc
index 3ac1e5b413..8fddc437a0 100644
--- a/3rdParty/rocksdb/v5.16.X/java/rocksjni/statisticsjni.cc
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/statisticsjni.cc
@@ -11,11 +11,11 @@
 namespace rocksdb {
 
   StatisticsJni::StatisticsJni(std::shared_ptr<Statistics> stats)
-      : StatisticsImpl(stats, false), m_ignore_histograms() {
+      : StatisticsImpl(stats), m_ignore_histograms() {
   }
 
   StatisticsJni::StatisticsJni(std::shared_ptr<Statistics> stats,
-      const std::set<uint32_t> ignore_histograms) : StatisticsImpl(stats, false),
+      const std::set<uint32_t> ignore_histograms) : StatisticsImpl(stats),
       m_ignore_histograms(ignore_histograms) {
   }
 
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/statisticsjni.h b/3rdParty/rocksdb/v5.18.X/java/rocksjni/statisticsjni.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/statisticsjni.h
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/statisticsjni.h
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/table.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/table.cc
similarity index 89%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/table.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/table.cc
index 5f5f8cd2ab..3dbd13280a 100644
--- a/3rdParty/rocksdb/v5.16.X/java/rocksjni/table.cc
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/table.cc
@@ -37,7 +37,7 @@ jlong Java_org_rocksdb_PlainTableConfig_newTableFactoryHandle(
 /*
  * Class:     org_rocksdb_BlockBasedTableConfig
  * Method:    newTableFactoryHandle
- * Signature: (ZJIJJIIZIZZZJIBBI)J
+ * Signature: (ZJIJJIIZJZZZZJZZJIBBI)J
  */
 jlong Java_org_rocksdb_BlockBasedTableConfig_newTableFactoryHandle(
     JNIEnv * /*env*/, jobject /*jobj*/, jboolean no_block_cache,
@@ -45,7 +45,10 @@ jlong Java_org_rocksdb_BlockBasedTableConfig_newTableFactoryHandle(
     jlong block_size, jint block_size_deviation, jint block_restart_interval,
     jboolean whole_key_filtering, jlong jfilter_policy,
     jboolean cache_index_and_filter_blocks,
+    jboolean cache_index_and_filter_blocks_with_high_priority,
     jboolean pin_l0_filter_and_index_blocks_in_cache,
+    jboolean partition_filters, jlong metadata_block_size,
+    jboolean pin_top_level_index_and_filter,
     jboolean hash_index_allow_collision, jlong block_cache_compressed_size,
     jint block_cache_compressd_num_shard_bits, jbyte jchecksum_type,
     jbyte jindex_type, jint jformat_version) {
@@ -77,8 +80,13 @@ jlong Java_org_rocksdb_BlockBasedTableConfig_newTableFactoryHandle(
     options.filter_policy = *pFilterPolicy;
   }
   options.cache_index_and_filter_blocks = cache_index_and_filter_blocks;
+  options.cache_index_and_filter_blocks_with_high_priority =
+      cache_index_and_filter_blocks_with_high_priority;
   options.pin_l0_filter_and_index_blocks_in_cache =
       pin_l0_filter_and_index_blocks_in_cache;
+  options.partition_filters = partition_filters;
+  options.metadata_block_size = metadata_block_size;
+  options.pin_top_level_index_and_filter = pin_top_level_index_and_filter;
   options.hash_index_allow_collision = hash_index_allow_collision;
   if (block_cache_compressed_size > 0) {
     if (block_cache_compressd_num_shard_bits > 0) {
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction.cc
index 43be095600..a29736df2d 100644
--- a/3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction.cc
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction.cc
@@ -612,7 +612,11 @@ void txn_write_kv_parts_helper(JNIEnv* env,
                                const jint& jkey_parts_len,
                                const jobjectArray& jvalue_parts,
                                const jint& jvalue_parts_len) {
+#ifndef DEBUG
+  (void) jvalue_parts_len;
+#else
   assert(jkey_parts_len == jvalue_parts_len);
+#endif
 
   auto key_parts = std::vector<rocksdb::Slice>();
   auto value_parts = std::vector<rocksdb::Slice>();
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_db.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_db.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_db.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_db.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_db_options.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_db_options.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_db_options.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_db_options.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_log.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_log.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_log.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_log.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_notifier.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_notifier.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_notifier.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_notifier.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_notifier_jnicallback.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_notifier_jnicallback.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_notifier_jnicallback.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_notifier_jnicallback.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_notifier_jnicallback.h b/3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_notifier_jnicallback.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_notifier_jnicallback.h
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_notifier_jnicallback.h
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_options.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_options.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/transaction_options.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/transaction_options.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/ttl.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/ttl.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/ttl.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/ttl.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/write_batch.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/write_batch.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/write_batch.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/write_batch.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/write_batch_test.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/write_batch_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/write_batch_test.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/write_batch_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/write_batch_with_index.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/write_batch_with_index.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/write_batch_with_index.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/write_batch_with_index.cc
diff --git a/3rdParty/rocksdb/v5.18.X/java/rocksjni/write_buffer_manager.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/write_buffer_manager.cc
new file mode 100644
index 0000000000..043f69031c
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/write_buffer_manager.cc
@@ -0,0 +1,38 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include <jni.h>
+
+#include "include/org_rocksdb_WriteBufferManager.h"
+
+#include "rocksdb/cache.h"
+#include "rocksdb/write_buffer_manager.h"
+
+/*
+ * Class:     org_rocksdb_WriteBufferManager
+ * Method:    newWriteBufferManager
+ * Signature: (JJ)J
+ */
+jlong Java_org_rocksdb_WriteBufferManager_newWriteBufferManager(
+        JNIEnv* /*env*/, jclass /*jclazz*/, jlong jbuffer_size, jlong jcache_handle) {
+    auto* cache_ptr =
+            reinterpret_cast<std::shared_ptr<rocksdb::Cache> *>(jcache_handle);
+    auto* write_buffer_manager = new std::shared_ptr<rocksdb::WriteBufferManager>(
+            std::make_shared<rocksdb::WriteBufferManager>(jbuffer_size, *cache_ptr));
+    return reinterpret_cast<jlong>(write_buffer_manager);
+}
+
+/*
+ * Class:     org_rocksdb_WriteBufferManager
+ * Method:    disposeInternal
+ * Signature: (J)V
+ */
+void Java_org_rocksdb_WriteBufferManager_disposeInternal(
+        JNIEnv* /*env*/, jobject /*jobj*/, jlong jhandle) {
+    auto* write_buffer_manager =
+            reinterpret_cast<std::shared_ptr<rocksdb::WriteBufferManager> *>(jhandle);
+    assert(write_buffer_manager != nullptr);
+    delete write_buffer_manager;
+}
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/writebatchhandlerjnicallback.cc b/3rdParty/rocksdb/v5.18.X/java/rocksjni/writebatchhandlerjnicallback.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/writebatchhandlerjnicallback.cc
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/writebatchhandlerjnicallback.cc
index 69fe876590..bf9001110a 100644
--- a/3rdParty/rocksdb/v5.16.X/java/rocksjni/writebatchhandlerjnicallback.cc
+++ b/3rdParty/rocksdb/v5.18.X/java/rocksjni/writebatchhandlerjnicallback.cc
@@ -306,7 +306,11 @@ rocksdb::Status WriteBatchHandlerJniCallback::PutBlobIndexCF(uint32_t column_fam
 }
 
 rocksdb::Status WriteBatchHandlerJniCallback::MarkBeginPrepare(bool unprepare) {
+#ifndef DEBUG
+  (void) unprepare;
+#else
   assert(!unprepare);
+#endif
   m_env->CallVoidMethod(m_jcallback_obj, m_jMarkBeginPrepareMethodId);
 
   // check for Exception, in-particular RocksDBException
diff --git a/3rdParty/rocksdb/v5.16.X/java/rocksjni/writebatchhandlerjnicallback.h b/3rdParty/rocksdb/v5.18.X/java/rocksjni/writebatchhandlerjnicallback.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/rocksjni/writebatchhandlerjnicallback.h
rename to 3rdParty/rocksdb/v5.18.X/java/rocksjni/writebatchhandlerjnicallback.h
diff --git a/3rdParty/rocksdb/v5.16.X/java/samples/src/main/java/OptimisticTransactionSample.java b/3rdParty/rocksdb/v5.18.X/java/samples/src/main/java/OptimisticTransactionSample.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/samples/src/main/java/OptimisticTransactionSample.java
rename to 3rdParty/rocksdb/v5.18.X/java/samples/src/main/java/OptimisticTransactionSample.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/samples/src/main/java/RocksDBColumnFamilySample.java b/3rdParty/rocksdb/v5.18.X/java/samples/src/main/java/RocksDBColumnFamilySample.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/samples/src/main/java/RocksDBColumnFamilySample.java
rename to 3rdParty/rocksdb/v5.18.X/java/samples/src/main/java/RocksDBColumnFamilySample.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/samples/src/main/java/RocksDBSample.java b/3rdParty/rocksdb/v5.18.X/java/samples/src/main/java/RocksDBSample.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/samples/src/main/java/RocksDBSample.java
rename to 3rdParty/rocksdb/v5.18.X/java/samples/src/main/java/RocksDBSample.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/samples/src/main/java/TransactionSample.java b/3rdParty/rocksdb/v5.18.X/java/samples/src/main/java/TransactionSample.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/samples/src/main/java/TransactionSample.java
rename to 3rdParty/rocksdb/v5.18.X/java/samples/src/main/java/TransactionSample.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractCompactionFilter.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractCompactionFilter.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractCompactionFilter.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractCompactionFilter.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractCompactionFilterFactory.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractCompactionFilterFactory.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractCompactionFilterFactory.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractCompactionFilterFactory.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractComparator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractComparator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractComparator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractComparator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractImmutableNativeReference.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractImmutableNativeReference.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractImmutableNativeReference.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractImmutableNativeReference.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractNativeReference.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractNativeReference.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractNativeReference.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractNativeReference.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractRocksIterator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractRocksIterator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractRocksIterator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractRocksIterator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractSlice.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractSlice.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractSlice.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractSlice.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractTransactionNotifier.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractTransactionNotifier.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractTransactionNotifier.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractTransactionNotifier.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractWriteBatch.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractWriteBatch.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AbstractWriteBatch.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AbstractWriteBatch.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AccessHint.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AccessHint.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AccessHint.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AccessHint.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AdvancedColumnFamilyOptionsInterface.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AdvancedColumnFamilyOptionsInterface.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AdvancedColumnFamilyOptionsInterface.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AdvancedColumnFamilyOptionsInterface.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AdvancedMutableColumnFamilyOptionsInterface.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AdvancedMutableColumnFamilyOptionsInterface.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/AdvancedMutableColumnFamilyOptionsInterface.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/AdvancedMutableColumnFamilyOptionsInterface.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BackupEngine.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BackupEngine.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BackupEngine.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BackupEngine.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BackupInfo.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BackupInfo.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BackupInfo.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BackupInfo.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BackupableDBOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BackupableDBOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BackupableDBOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BackupableDBOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BlockBasedTableConfig.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BlockBasedTableConfig.java
similarity index 78%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BlockBasedTableConfig.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BlockBasedTableConfig.java
index 2dbbc64d35..1032be6e79 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BlockBasedTableConfig.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BlockBasedTableConfig.java
@@ -22,7 +22,11 @@ public class BlockBasedTableConfig extends TableFormatConfig {
     wholeKeyFiltering_ = true;
     filter_ = null;
     cacheIndexAndFilterBlocks_ = false;
+    cacheIndexAndFilterBlocksWithHighPriority_ = false;
     pinL0FilterAndIndexBlocksInCache_ = false;
+    partitionFilters_ = false;
+    metadataBlockSize_ = 4096;
+    pinTopLevelIndexAndFilter_ = true;
     hashIndexAllowCollision_ = true;
     blockCacheCompressedSize_ = 0;
     blockCacheCompressedNumShardBits_ = 0;
@@ -246,6 +250,31 @@ public class BlockBasedTableConfig extends TableFormatConfig {
     return this;
   }
 
+  /**
+   * Indicates if index and filter blocks will be treated as high-priority in the block cache.
+   * See note below about applicability. If not specified, defaults to false.
+   *
+   * @return if index and filter blocks will be treated as high-priority.
+   */
+  public boolean cacheIndexAndFilterBlocksWithHighPriority() {
+    return cacheIndexAndFilterBlocksWithHighPriority_;
+  }
+
+  /**
+   * If true, cache index and filter blocks with high priority. If set to true,
+   * depending on implementation of block cache, index and filter blocks may be
+   * less likely to be evicted than data blocks.
+   *
+   * @param cacheIndexAndFilterBlocksWithHighPriority if index and filter blocks
+   *            will be treated as high-priority.
+   * @return the reference to the current config.
+   */
+  public BlockBasedTableConfig setCacheIndexAndFilterBlocksWithHighPriority(
+          final boolean cacheIndexAndFilterBlocksWithHighPriority) {
+    cacheIndexAndFilterBlocksWithHighPriority_ = cacheIndexAndFilterBlocksWithHighPriority;
+    return this;
+  }
+
   /**
    * Indicating if we'd like to pin L0 index/filter blocks to the block cache.
      If not specified, defaults to false.
@@ -269,6 +298,70 @@ public class BlockBasedTableConfig extends TableFormatConfig {
     return this;
   }
 
+  /**
+   * Indicating if we're using partitioned filters. Defaults to false.
+   *
+   * @return if we're using partition filters.
+   */
+  public boolean partitionFilters() {
+    return partitionFilters_;
+  }
+
+  /**
+   * Use partitioned full filters for each SST file. This option is incompatible with
+   * block-based filters.
+   *
+   * @param partitionFilters use partition filters.
+   * @return the reference to the current config.
+   */
+  public BlockBasedTableConfig setPartitionFilters(final boolean partitionFilters) {
+    partitionFilters_ = partitionFilters;
+    return this;
+  }
+
+  /**
+   * @return block size for partitioned metadata.
+   */
+  public long metadataBlockSize() {
+    return metadataBlockSize_;
+  }
+
+  /**
+   * Set block size for partitioned metadata.
+   *
+   * @param metadataBlockSize Partitioned metadata block size.
+   * @return the reference to the current config.
+   */
+  public BlockBasedTableConfig setMetadataBlockSize(
+          final long metadataBlockSize) {
+    metadataBlockSize_ = metadataBlockSize;
+    return this;
+  }
+
+  /**
+   * Indicates if top-level index and filter blocks should be pinned.
+   *
+   * @return if top-level index and filter blocks should be pinned.
+   */
+  public boolean pinTopLevelIndexAndFilter() {
+    return pinTopLevelIndexAndFilter_;
+  }
+
+  /**
+   * If cacheIndexAndFilterBlocks is true and the below is true, then
+   * the top-level index of partitioned filter and index blocks are stored in
+   * the cache, but a reference is held in the "table reader" object so the
+   * blocks are pinned and only evicted from cache when the table reader is
+   * freed. This is not limited to l0 in LSM tree.
+   *
+   * @param pinTopLevelIndexAndFilter if top-level index and filter blocks should be pinned.
+   * @return the reference to the current config.
+   */
+  public BlockBasedTableConfig setPinTopLevelIndexAndFilter(final boolean pinTopLevelIndexAndFilter) {
+    pinTopLevelIndexAndFilter_ = pinTopLevelIndexAndFilter;
+    return this;
+  }
+
   /**
    * Influence the behavior when kHashSearch is used.
      if false, stores a precise prefix to block range mapping
@@ -440,20 +533,27 @@ public class BlockBasedTableConfig extends TableFormatConfig {
     return newTableFactoryHandle(noBlockCache_, blockCacheSize_, blockCacheNumShardBits_,
         blockCacheHandle, blockSize_, blockSizeDeviation_, blockRestartInterval_,
         wholeKeyFiltering_, filterHandle, cacheIndexAndFilterBlocks_,
-        pinL0FilterAndIndexBlocksInCache_, hashIndexAllowCollision_, blockCacheCompressedSize_,
-        blockCacheCompressedNumShardBits_, checksumType_.getValue(), indexType_.getValue(),
-        formatVersion_);
+        cacheIndexAndFilterBlocksWithHighPriority_, pinL0FilterAndIndexBlocksInCache_,
+        partitionFilters_, metadataBlockSize_, pinTopLevelIndexAndFilter_,
+        hashIndexAllowCollision_, blockCacheCompressedSize_, blockCacheCompressedNumShardBits_,
+        checksumType_.getValue(), indexType_.getValue(), formatVersion_);
   }
 
   private native long newTableFactoryHandle(boolean noBlockCache, long blockCacheSize,
       int blockCacheNumShardBits, long blockCacheHandle, long blockSize, int blockSizeDeviation,
       int blockRestartInterval, boolean wholeKeyFiltering, long filterPolicyHandle,
-      boolean cacheIndexAndFilterBlocks, boolean pinL0FilterAndIndexBlocksInCache,
-      boolean hashIndexAllowCollision, long blockCacheCompressedSize,
-      int blockCacheCompressedNumShardBits, byte checkSumType, byte indexType, int formatVersion);
+      boolean cacheIndexAndFilterBlocks, boolean cacheIndexAndFilterBlocksWithHighPriority,
+      boolean pinL0FilterAndIndexBlocksInCache, boolean partitionFilters, long metadataBlockSize,
+      boolean pinTopLevelIndexAndFilter, boolean hashIndexAllowCollision,
+      long blockCacheCompressedSize, int blockCacheCompressedNumShardBits,
+      byte checkSumType, byte indexType, int formatVersion);
 
   private boolean cacheIndexAndFilterBlocks_;
+  private boolean cacheIndexAndFilterBlocksWithHighPriority_;
   private boolean pinL0FilterAndIndexBlocksInCache_;
+  private boolean partitionFilters_;
+  private long metadataBlockSize_;
+  private boolean pinTopLevelIndexAndFilter_;
   private IndexType indexType_;
   private boolean hashIndexAllowCollision_;
   private ChecksumType checksumType_;
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BloomFilter.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BloomFilter.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BloomFilter.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BloomFilter.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BuiltinComparator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BuiltinComparator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/BuiltinComparator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/BuiltinComparator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Cache.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Cache.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Cache.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Cache.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CassandraCompactionFilter.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CassandraCompactionFilter.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CassandraCompactionFilter.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CassandraCompactionFilter.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CassandraValueMergeOperator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CassandraValueMergeOperator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CassandraValueMergeOperator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CassandraValueMergeOperator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Checkpoint.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Checkpoint.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Checkpoint.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Checkpoint.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ChecksumType.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ChecksumType.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ChecksumType.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ChecksumType.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ClockCache.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ClockCache.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ClockCache.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ClockCache.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ColumnFamilyDescriptor.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ColumnFamilyDescriptor.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ColumnFamilyDescriptor.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ColumnFamilyDescriptor.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ColumnFamilyHandle.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ColumnFamilyHandle.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ColumnFamilyHandle.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ColumnFamilyHandle.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ColumnFamilyOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ColumnFamilyOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ColumnFamilyOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ColumnFamilyOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ColumnFamilyOptionsInterface.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ColumnFamilyOptionsInterface.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ColumnFamilyOptionsInterface.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ColumnFamilyOptionsInterface.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactRangeOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactRangeOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactRangeOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactRangeOptions.java
diff --git a/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionOptionsFIFO.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionOptionsFIFO.java
new file mode 100644
index 0000000000..36d78fe6e6
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionOptionsFIFO.java
@@ -0,0 +1,119 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+package org.rocksdb;
+
+/**
+ * Options for FIFO Compaction
+ */
+public class CompactionOptionsFIFO extends RocksObject {
+
+  public CompactionOptionsFIFO() {
+    super(newCompactionOptionsFIFO());
+  }
+
+  /**
+   * Once the total sum of table files reaches this, we will delete the oldest
+   * table file
+   *
+   * Default: 1GB
+   *
+   * @param maxTableFilesSize The maximum size of the table files
+   *
+   * @return the reference to the current options.
+   */
+  public CompactionOptionsFIFO setMaxTableFilesSize(
+      final long maxTableFilesSize) {
+    setMaxTableFilesSize(nativeHandle_, maxTableFilesSize);
+    return this;
+  }
+
+  /**
+   * Once the total sum of table files reaches this, we will delete the oldest
+   * table file
+   *
+   * Default: 1GB
+   *
+   * @return max table file size in bytes
+   */
+  public long maxTableFilesSize() {
+    return maxTableFilesSize(nativeHandle_);
+  }
+
+  /**
+   * Drop files older than TTL. TTL based deletion will take precedence over
+   * size based deletion if ttl &gt; 0.
+   * delete if sst_file_creation_time &lt; (current_time - ttl).
+   * unit: seconds. Ex: 1 day = 1 * 24 * 60 * 60
+   *
+   * Default: 0 (disabled)
+   *
+   * @param ttl The ttl for the table files in seconds
+   *
+   * @return the reference to the current options.
+   */
+  public CompactionOptionsFIFO setTtl(final long ttl) {
+    setTtl(nativeHandle_, ttl);
+    return this;
+  }
+
+  /**
+   * The current ttl value.
+   * Drop files older than TTL. TTL based deletion will take precedence over
+   * size based deletion if ttl &gt; 0.
+   * delete if sst_file_creation_time &lt; (current_time - ttl).
+   *
+   * Default: 0 (disabled)
+   *
+   * @return the ttl in seconds
+   */
+  public long ttl() {
+    return ttl(nativeHandle_);
+  }
+
+  /**
+   * If true, try to do compaction to compact smaller files into larger ones.
+   * Minimum files to compact follows options.level0_file_num_compaction_trigger
+   * and compaction won't trigger if average compact bytes per del file is
+   * larger than options.write_buffer_size. This is to protect large files
+   * from being compacted again.
+   *
+   * Default: false
+   *
+   * @param allowCompaction should allow intra-L0 compaction?
+   *
+   * @return the reference to the current options.
+   */
+  public CompactionOptionsFIFO setAllowCompaction(final boolean allowCompaction) {
+    setAllowCompaction(nativeHandle_, allowCompaction);
+    return this;
+  }
+
+  /**
+   * Check if intra-L0 compaction is enabled.
+   * If true, try to do compaction to compact smaller files into larger ones.
+   * Minimum files to compact follows options.level0_file_num_compaction_trigger
+   * and compaction won't trigger if average compact bytes per del file is
+   * larger than options.write_buffer_size. This is to protect large files
+   * from being compacted again.
+   *
+   * Default: false
+   *
+   * @return a boolean value indicating whether intra-L0 compaction is enabled
+   */
+  public boolean allowCompaction() {
+    return allowCompaction(nativeHandle_);
+  }
+
+  private native void setMaxTableFilesSize(long handle, long maxTableFilesSize);
+  private native long maxTableFilesSize(long handle);
+  private native void setTtl(long handle, long ttl);
+  private native long ttl(long handle);
+  private native void setAllowCompaction(long handle, boolean allowCompaction);
+  private native boolean allowCompaction(long handle);
+
+  private native static long newCompactionOptionsFIFO();
+  @Override protected final native void disposeInternal(final long handle);
+}
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionOptionsUniversal.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionOptionsUniversal.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionOptionsUniversal.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionOptionsUniversal.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionPriority.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionPriority.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionPriority.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionPriority.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionStopStyle.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionStopStyle.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionStopStyle.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionStopStyle.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionStyle.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionStyle.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompactionStyle.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompactionStyle.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Comparator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Comparator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Comparator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Comparator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ComparatorOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ComparatorOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ComparatorOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ComparatorOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ComparatorType.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ComparatorType.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ComparatorType.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ComparatorType.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompressionOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompressionOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompressionOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompressionOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompressionType.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompressionType.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/CompressionType.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/CompressionType.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DBOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DBOptions.java
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DBOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DBOptions.java
index c323293889..280623a208 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DBOptions.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DBOptions.java
@@ -46,6 +46,7 @@ public class DBOptions
     this.numShardBits_ = other.numShardBits_;
     this.rateLimiter_ = other.rateLimiter_;
     this.rowCache_ = other.rowCache_;
+    this.writeBufferManager_ = other.writeBufferManager_;
   }
 
   /**
@@ -668,6 +669,20 @@ public class DBOptions
   }
 
   @Override
+  public DBOptions setWriteBufferManager(final WriteBufferManager writeBufferManager) {
+    assert(isOwningHandle());
+    setWriteBufferManager(nativeHandle_, writeBufferManager.nativeHandle_);
+    this.writeBufferManager_ = writeBufferManager;
+    return this;
+  }
+
+  @Override
+  public WriteBufferManager writeBufferManager() {
+    assert(isOwningHandle());
+    return this.writeBufferManager_;
+  }
+
+    @Override
   public long dbWriteBufferSize() {
     assert(isOwningHandle());
     return dbWriteBufferSize(nativeHandle_);
@@ -1087,6 +1102,8 @@ public class DBOptions
   private native boolean adviseRandomOnOpen(long handle);
   private native void setDbWriteBufferSize(final long handle,
       final long dbWriteBufferSize);
+  private native void setWriteBufferManager(final long dbOptionsHandle,
+      final long writeBufferManagerHandle);
   private native long dbWriteBufferSize(final long handle);
   private native void setAccessHintOnCompactionStart(final long handle,
       final byte accessHintOnCompactionStart);
@@ -1158,4 +1175,5 @@ public class DBOptions
   private int numShardBits_;
   private RateLimiter rateLimiter_;
   private Cache rowCache_;
+  private WriteBufferManager writeBufferManager_;
 }
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DBOptionsInterface.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DBOptionsInterface.java
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DBOptionsInterface.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DBOptionsInterface.java
index 7c406eaf8a..accfb4c59a 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DBOptionsInterface.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DBOptionsInterface.java
@@ -991,6 +991,28 @@ public interface DBOptionsInterface<T extends DBOptionsInterface> {
    */
   T setDbWriteBufferSize(long dbWriteBufferSize);
 
+  /**
+   * Use passed {@link WriteBufferManager} to control memory usage across
+   * multiple column families and/or DB instances.
+   *
+   * Check <a href="https://github.com/facebook/rocksdb/wiki/Write-Buffer-Manager">
+   *     https://github.com/facebook/rocksdb/wiki/Write-Buffer-Manager</a>
+   * for more details on when to use it
+   *
+   * @param writeBufferManager The WriteBufferManager to use
+   * @return the reference of the current options.
+   */
+  T setWriteBufferManager(final WriteBufferManager writeBufferManager);
+
+  /**
+   * Reference to {@link WriteBufferManager} used by it. <br>
+   *
+   * Default: null (Disabled)
+   *
+   * @return a reference to WriteBufferManager
+   */
+  WriteBufferManager writeBufferManager();
+
   /**
    * Amount of data to build up in memtables across all column
    * families before writing to disk.
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DbPath.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DbPath.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DbPath.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DbPath.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DirectComparator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DirectComparator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DirectComparator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DirectComparator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DirectSlice.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DirectSlice.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/DirectSlice.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/DirectSlice.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/EncodingType.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/EncodingType.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/EncodingType.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/EncodingType.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Env.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Env.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Env.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Env.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/EnvOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/EnvOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/EnvOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/EnvOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Experimental.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Experimental.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Experimental.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Experimental.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Filter.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Filter.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Filter.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Filter.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/FlushOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/FlushOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/FlushOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/FlushOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/HashLinkedListMemTableConfig.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/HashLinkedListMemTableConfig.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/HashLinkedListMemTableConfig.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/HashLinkedListMemTableConfig.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/HashSkipListMemTableConfig.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/HashSkipListMemTableConfig.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/HashSkipListMemTableConfig.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/HashSkipListMemTableConfig.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/HistogramData.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/HistogramData.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/HistogramData.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/HistogramData.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/HistogramType.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/HistogramType.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/HistogramType.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/HistogramType.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/IndexType.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/IndexType.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/IndexType.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/IndexType.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/InfoLogLevel.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/InfoLogLevel.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/InfoLogLevel.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/InfoLogLevel.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/IngestExternalFileOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/IngestExternalFileOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/IngestExternalFileOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/IngestExternalFileOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/LRUCache.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/LRUCache.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/LRUCache.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/LRUCache.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Logger.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Logger.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Logger.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Logger.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/MemTableConfig.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MemTableConfig.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/MemTableConfig.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MemTableConfig.java
diff --git a/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MemoryUsageType.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MemoryUsageType.java
new file mode 100644
index 0000000000..3523cd0ee6
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MemoryUsageType.java
@@ -0,0 +1,72 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+package org.rocksdb;
+
+/**
+ * MemoryUsageType
+ *
+ * <p>The value will be used as a key to indicate the type of memory usage
+ * described</p>
+ */
+public enum MemoryUsageType {
+  /**
+   * Memory usage of all the mem-tables.
+   */
+  kMemTableTotal((byte) 0),
+  /**
+   * Memory usage of those un-flushed mem-tables.
+   */
+  kMemTableUnFlushed((byte) 1),
+  /**
+   * Memory usage of all the table readers.
+   */
+  kTableReadersTotal((byte) 2),
+  /**
+   * Memory usage by Cache.
+   */
+  kCacheTotal((byte) 3),
+  /**
+   * Max usage types - copied to keep 1:1 with native.
+   */
+  kNumUsageTypes((byte) 4);
+
+  /**
+   * Returns the byte value of the enumerations value
+   *
+   * @return byte representation
+   */
+  public byte getValue() {
+    return value_;
+  }
+
+  /**
+   * <p>Get the MemoryUsageType enumeration value by
+   * passing the byte identifier to this method.</p>
+   *
+   * @param byteIdentifier of MemoryUsageType.
+   *
+   * @return MemoryUsageType instance.
+   *
+   * @throws IllegalArgumentException if the usage type for the byteIdentifier
+   *     cannot be found
+   */
+  public static MemoryUsageType getMemoryUsageType(final byte byteIdentifier) {
+    for (final MemoryUsageType MemoryUsageType : MemoryUsageType.values()) {
+      if (MemoryUsageType.getValue() == byteIdentifier) {
+        return MemoryUsageType;
+      }
+    }
+
+    throw new IllegalArgumentException(
+        "Illegal value provided for MemoryUsageType.");
+  }
+
+  private MemoryUsageType(byte value) {
+    value_ = value;
+  }
+
+  private final byte value_;
+}
diff --git a/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MemoryUtil.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MemoryUtil.java
new file mode 100644
index 0000000000..52b2175e6b
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MemoryUtil.java
@@ -0,0 +1,60 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+package org.rocksdb;
+
+import java.util.*;
+
+/**
+ * JNI passthrough for MemoryUtil.
+ */
+public class MemoryUtil {
+
+  /**
+   * <p>Returns the approximate memory usage of different types in the input
+   * list of DBs and Cache set.  For instance, in the output map the key
+   * kMemTableTotal will be associated with the memory
+   * usage of all the mem-tables from all the input rocksdb instances.</p>
+   *
+   * <p>Note that for memory usage inside Cache class, we will
+   * only report the usage of the input "cache_set" without
+   * including those Cache usage inside the input list "dbs"
+   * of DBs.</p>
+   *
+   * @param dbs List of dbs to collect memory usage for.
+   * @param caches Set of caches to collect memory usage for.
+   * @return Map from {@link MemoryUsageType} to memory usage as a {@link Long}.
+   */
+  public static Map<MemoryUsageType, Long> getApproximateMemoryUsageByType(final List<RocksDB> dbs, final Set<Cache> caches) {
+    int dbCount = (dbs == null) ? 0 : dbs.size();
+    int cacheCount = (caches == null) ? 0 : caches.size();
+    long[] dbHandles = new long[dbCount];
+    long[] cacheHandles = new long[cacheCount];
+    if (dbCount > 0) {
+      ListIterator<RocksDB> dbIter = dbs.listIterator();
+      while (dbIter.hasNext()) {
+        dbHandles[dbIter.nextIndex()] = dbIter.next().nativeHandle_;
+      }
+    }
+    if (cacheCount > 0) {
+      // NOTE: This index handling is super ugly but I couldn't get a clean way to track both the
+      // index and the iterator simultaneously within a Set.
+      int i = 0;
+      for (Cache cache : caches) {
+        cacheHandles[i] = cache.nativeHandle_;
+        i++;
+      }
+    }
+    Map<Byte, Long> byteOutput = getApproximateMemoryUsageByType(dbHandles, cacheHandles);
+    Map<MemoryUsageType, Long> output = new HashMap<>();
+    for(Map.Entry<Byte, Long> longEntry : byteOutput.entrySet()) {
+      output.put(MemoryUsageType.getMemoryUsageType(longEntry.getKey()), longEntry.getValue());
+    }
+    return output;
+  }
+
+  private native static Map<Byte, Long> getApproximateMemoryUsageByType(final long[] dbHandles,
+      final long[] cacheHandles);
+}
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/MergeOperator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MergeOperator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/MergeOperator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MergeOperator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/MutableColumnFamilyOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MutableColumnFamilyOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/MutableColumnFamilyOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MutableColumnFamilyOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/MutableColumnFamilyOptionsInterface.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MutableColumnFamilyOptionsInterface.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/MutableColumnFamilyOptionsInterface.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/MutableColumnFamilyOptionsInterface.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/NativeComparatorWrapper.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/NativeComparatorWrapper.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/NativeComparatorWrapper.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/NativeComparatorWrapper.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/NativeLibraryLoader.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/NativeLibraryLoader.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/NativeLibraryLoader.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/NativeLibraryLoader.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/OptimisticTransactionDB.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/OptimisticTransactionDB.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/OptimisticTransactionDB.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/OptimisticTransactionDB.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/OptimisticTransactionOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/OptimisticTransactionOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/OptimisticTransactionOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/OptimisticTransactionOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Options.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Options.java
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Options.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Options.java
index cac4fc5a36..2ff4ec1204 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Options.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Options.java
@@ -70,6 +70,7 @@ public class Options extends RocksObject
     this.compactionOptionsFIFO_ = other.compactionOptionsFIFO_;
     this.compressionOptions_ = other.compressionOptions_;
     this.rowCache_ = other.rowCache_;
+    this.writeBufferManager_ = other.writeBufferManager_;
   }
 
   @Override
@@ -724,6 +725,20 @@ public class Options extends RocksObject
   }
 
   @Override
+  public Options setWriteBufferManager(final WriteBufferManager writeBufferManager) {
+    assert(isOwningHandle());
+    setWriteBufferManager(nativeHandle_, writeBufferManager.nativeHandle_);
+    this.writeBufferManager_ = writeBufferManager;
+    return this;
+  }
+
+  @Override
+  public WriteBufferManager writeBufferManager() {
+    assert(isOwningHandle());
+    return this.writeBufferManager_;
+  }
+
+    @Override
   public long dbWriteBufferSize() {
     assert(isOwningHandle());
     return dbWriteBufferSize(nativeHandle_);
@@ -1690,6 +1705,8 @@ public class Options extends RocksObject
   private native boolean adviseRandomOnOpen(long handle);
   private native void setDbWriteBufferSize(final long handle,
       final long dbWriteBufferSize);
+  private native void setWriteBufferManager(final long handle,
+      final long writeBufferManagerHandle);
   private native long dbWriteBufferSize(final long handle);
   private native void setAccessHintOnCompactionStart(final long handle,
       final byte accessHintOnCompactionStart);
@@ -1909,4 +1926,5 @@ public class Options extends RocksObject
   private CompactionOptionsFIFO compactionOptionsFIFO_;
   private CompressionOptions compressionOptions_;
   private Cache rowCache_;
+  private WriteBufferManager writeBufferManager_;
 }
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/OptionsUtil.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/OptionsUtil.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/OptionsUtil.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/OptionsUtil.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/PlainTableConfig.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/PlainTableConfig.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/PlainTableConfig.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/PlainTableConfig.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RateLimiter.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RateLimiter.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RateLimiter.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RateLimiter.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RateLimiterMode.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RateLimiterMode.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RateLimiterMode.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RateLimiterMode.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ReadOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ReadOptions.java
similarity index 87%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ReadOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ReadOptions.java
index be8aec6b32..f176d249b0 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ReadOptions.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ReadOptions.java
@@ -27,6 +27,7 @@ public class ReadOptions extends RocksObject {
   public ReadOptions(ReadOptions other) {
     super(copyReadOptions(other.nativeHandle_));
     iterateUpperBoundSlice_ = other.iterateUpperBoundSlice_;
+    iterateLowerBoundSlice_ = other.iterateLowerBoundSlice_;
   }
 
   /**
@@ -423,15 +424,65 @@ public class ReadOptions extends RocksObject {
     return null;
   }
 
+  /**
+   * Defines the smallest key at which the backward iterator can return an
+   * entry. Once the bound is passed, Valid() will be false.
+   * `iterate_lower_bound` is inclusive ie the bound value is a valid entry.
+   *
+   * If prefix_extractor is not null, the Seek target and `iterate_lower_bound`
+   * need to have the same prefix. This is because ordering is not guaranteed
+   * outside of prefix domain.
+   *
+   * Default: nullptr
+   *
+   * @param iterateLowerBound Slice representing the lower bound
+   * @return the reference to the current ReadOptions.
+   */
+  public ReadOptions setIterateLowerBound(final Slice iterateLowerBound) {
+    assert(isOwningHandle());
+    if (iterateLowerBound != null) {
+      // Hold onto a reference so it doesn't get garbaged collected out from under us.
+      iterateLowerBoundSlice_ = iterateLowerBound;
+      setIterateLowerBound(nativeHandle_, iterateLowerBoundSlice_.getNativeHandle());
+    }
+    return this;
+  }
+
+  /**
+   * Defines the smallest key at which the backward iterator can return an
+   * entry. Once the bound is passed, Valid() will be false.
+   * `iterate_lower_bound` is inclusive ie the bound value is a valid entry.
+   *
+   * If prefix_extractor is not null, the Seek target and `iterate_lower_bound`
+   * need to have the same prefix. This is because ordering is not guaranteed
+   * outside of prefix domain.
+   *
+   * Default: nullptr
+   *
+   * @return Slice representing current iterate_lower_bound setting, or null if
+   *         one does not exist.
+   */
+  public Slice iterateLowerBound() {
+    assert(isOwningHandle());
+    long lowerBoundSliceHandle = iterateLowerBound(nativeHandle_);
+    if (lowerBoundSliceHandle != 0) {
+      // Disown the new slice - it's owned by the C++ side of the JNI boundary
+      // from the perspective of this method.
+      return new Slice(lowerBoundSliceHandle, false);
+    }
+    return null;
+  }
+
   // instance variables
   // NOTE: If you add new member variables, please update the copy constructor above!
   //
-  // Hold a reference to any iterate upper bound that was set on this object
-  // until we're destroyed or it's overwritten.  That way the caller can freely
+  // Hold a reference to any iterate upper/lower bound that was set on this object
+  // until we're destroyed or it's overwritten. That way the caller can freely
   // leave scope without us losing the Java Slice object, which during close()
   // would also reap its associated rocksdb::Slice native object since it's
   // possibly (likely) to be an owning handle.
   protected Slice iterateUpperBoundSlice_;
+  protected Slice iterateLowerBoundSlice_;
 
   private native static long newReadOptions();
   private native static long copyReadOptions(long handle);
@@ -465,6 +516,9 @@ public class ReadOptions extends RocksObject {
   private native void setIterateUpperBound(final long handle,
       final long upperBoundSliceHandle);
   private native long iterateUpperBound(final long handle);
+  private native void setIterateLowerBound(final long handle,
+      final long upperBoundSliceHandle);
+  private native long iterateLowerBound(final long handle);
 
   @Override protected final native void disposeInternal(final long handle);
 
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ReadTier.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ReadTier.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/ReadTier.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/ReadTier.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RemoveEmptyValueCompactionFilter.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RemoveEmptyValueCompactionFilter.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RemoveEmptyValueCompactionFilter.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RemoveEmptyValueCompactionFilter.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RestoreOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RestoreOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RestoreOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RestoreOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksCallbackObject.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksCallbackObject.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksCallbackObject.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksCallbackObject.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksDB.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksDB.java
similarity index 76%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksDB.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksDB.java
index 3e2ba7b560..7ac08fdf05 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksDB.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksDB.java
@@ -439,6 +439,12 @@ public class RocksDB extends RocksObject {
     options_ = options;
   }
 
+  private static void checkBounds(int offset, int len, int size) {
+    if ((offset | len | (offset + len) | (size - (offset + len))) < 0) {
+      throw new IndexOutOfBoundsException(String.format("offset(%d), len(%d), size(%d)", offset, len, size));
+    }
+  }
+
   /**
    * Set the database entry for "key" to "value".
    *
@@ -453,6 +459,28 @@ public class RocksDB extends RocksObject {
     put(nativeHandle_, key, 0, key.length, value, 0, value.length);
   }
 
+  /**
+   * Set the database entry for "key" to "value"
+   *
+   * @param key The specified key to be inserted
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("key".length -  offset)
+   * @param value the value associated with the specified key
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   *
+   * @throws RocksDBException thrown if errors happens in underlying native library.
+   */
+  public void put(final byte[] key, int offset, int len, final byte[] value, int vOffset, int vLen) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    put(nativeHandle_, key, offset, len, value, vOffset, vLen);
+  }
+
   /**
    * Set the database entry for "key" to "value" in the specified
    * column family.
@@ -473,6 +501,32 @@ public class RocksDB extends RocksObject {
         columnFamilyHandle.nativeHandle_);
   }
 
+  /**
+   * Set the database entry for "key" to "value" in the specified
+   * column family.
+   *
+   * @param columnFamilyHandle {@link org.rocksdb.ColumnFamilyHandle}
+   *     instance
+   * @param key The specified key to be inserted
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("key".length -  offset)
+   * @param value the value associated with the specified key
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   *
+   * @throws RocksDBException thrown if errors happens in underlying native library.
+   */
+  public void put(final ColumnFamilyHandle columnFamilyHandle, final byte[] key, int offset, int len, final byte[] value, int vOffset, int vLen) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    put(nativeHandle_, key, offset, len, value, vOffset, vLen,
+        columnFamilyHandle.nativeHandle_);
+  }
+
   /**
    * Set the database entry for "key" to "value".
    *
@@ -489,6 +543,32 @@ public class RocksDB extends RocksObject {
         key, 0, key.length, value, 0, value.length);
   }
 
+  /**
+   * Set the database entry for "key" to "value".
+   *
+   * @param writeOpts {@link org.rocksdb.WriteOptions} instance.
+   * @param key The specified key to be inserted
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("key".length -  offset)
+   * @param value the value associated with the specified key
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public void put(final WriteOptions writeOpts, byte[] key, int offset, int len, byte[] value, int vOffset, int vLen) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    put(nativeHandle_, writeOpts.nativeHandle_,
+        key, offset, len, value, vOffset, vLen);
+  }
+
+
   /**
    * Set the database entry for "key" to "value" for the specified
    * column family.
@@ -512,6 +592,36 @@ public class RocksDB extends RocksObject {
         0, value.length, columnFamilyHandle.nativeHandle_);
   }
 
+  /**
+   * Set the database entry for "key" to "value" for the specified
+   * column family.
+   *
+   * @param columnFamilyHandle {@link org.rocksdb.ColumnFamilyHandle}
+   *     instance
+   * @param writeOpts {@link org.rocksdb.WriteOptions} instance.
+   * @param key The specified key to be inserted
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("key".length -  offset)
+   * @param value the value associated with the specified key
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public void put(final ColumnFamilyHandle columnFamilyHandle,
+      final WriteOptions writeOpts, final byte[] key, int offset, int len,
+      final byte[] value, int vOffset, int vLen) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    put(nativeHandle_, writeOpts.nativeHandle_, key, offset, len, value,
+        vOffset, vLen, columnFamilyHandle.nativeHandle_);
+  }
+
   /**
    * If the key definitely does not exist in the database, then this method
    * returns false, else true.
@@ -528,6 +638,27 @@ public class RocksDB extends RocksObject {
     return keyMayExist(nativeHandle_, key, 0, key.length, value);
   }
 
+  /**
+   * If the key definitely does not exist in the database, then this method
+   * returns false, else true.
+   *
+   * This check is potentially lighter-weight than invoking DB::Get(). One way
+   * to make this lighter weight is to avoid doing any IOs.
+   *
+   * @param key byte array of a key to search for
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value StringBuilder instance which is a out parameter if a value is
+   *    found in block-cache.
+   *
+   * @return boolean value indicating if key does not exist or might exist.
+   */
+  public boolean keyMayExist(final byte[] key, int offset, int len, final StringBuilder value) {
+    checkBounds(offset, len, key.length);
+    return keyMayExist(nativeHandle_, key, offset, len, value);
+  }
+
   /**
    * If the key definitely does not exist in the database, then this method
    * returns false, else true.
@@ -547,6 +678,30 @@ public class RocksDB extends RocksObject {
         columnFamilyHandle.nativeHandle_, value);
   }
 
+  /**
+   * If the key definitely does not exist in the database, then this method
+   * returns false, else true.
+   *
+   * This check is potentially lighter-weight than invoking DB::Get(). One way
+   * to make this lighter weight is to avoid doing any IOs.
+   *
+   * @param columnFamilyHandle {@link ColumnFamilyHandle} instance
+   * @param key byte array of a key to search for
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value StringBuilder instance which is a out parameter if a value is
+   *    found in block-cache.
+   * @return boolean value indicating if key does not exist or might exist.
+   */
+  public boolean keyMayExist(final ColumnFamilyHandle columnFamilyHandle,
+      final byte[] key, int offset, int len, final StringBuilder value) {
+    checkBounds(offset, len, key.length);
+    return keyMayExist(nativeHandle_, key, offset, len,
+        columnFamilyHandle.nativeHandle_, value);
+  }
+
+
   /**
    * If the key definitely does not exist in the database, then this method
    * returns false, else true.
@@ -566,6 +721,29 @@ public class RocksDB extends RocksObject {
         key, 0, key.length, value);
   }
 
+  /**
+   * If the key definitely does not exist in the database, then this method
+   * returns false, else true.
+   *
+   * This check is potentially lighter-weight than invoking DB::Get(). One way
+   * to make this lighter weight is to avoid doing any IOs.
+   *
+   * @param readOptions {@link ReadOptions} instance
+   * @param key byte array of a key to search for
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value StringBuilder instance which is a out parameter if a value is
+   *    found in block-cache.
+   * @return boolean value indicating if key does not exist or might exist.
+   */
+  public boolean keyMayExist(final ReadOptions readOptions,
+      final byte[] key, int offset, int len, final StringBuilder value) {
+    checkBounds(offset, len, key.length);
+    return keyMayExist(nativeHandle_, readOptions.nativeHandle_,
+        key, offset, len, value);
+  }
+
   /**
    * If the key definitely does not exist in the database, then this method
    * returns false, else true.
@@ -588,6 +766,32 @@ public class RocksDB extends RocksObject {
         value);
   }
 
+  /**
+   * If the key definitely does not exist in the database, then this method
+   * returns false, else true.
+   *
+   * This check is potentially lighter-weight than invoking DB::Get(). One way
+   * to make this lighter weight is to avoid doing any IOs.
+   *
+   * @param readOptions {@link ReadOptions} instance
+   * @param columnFamilyHandle {@link ColumnFamilyHandle} instance
+   * @param key byte array of a key to search for
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value StringBuilder instance which is a out parameter if a value is
+   *    found in block-cache.
+   * @return boolean value indicating if key does not exist or might exist.
+   */
+  public boolean keyMayExist(final ReadOptions readOptions,
+      final ColumnFamilyHandle columnFamilyHandle, final byte[] key, int offset, int len,
+      final StringBuilder value) {
+    checkBounds(offset, len, key.length);
+    return keyMayExist(nativeHandle_, readOptions.nativeHandle_,
+        key, offset, len, columnFamilyHandle.nativeHandle_,
+        value);
+  }
+
   /**
    * Apply the specified updates to the database.
    *
@@ -631,6 +835,30 @@ public class RocksDB extends RocksObject {
     merge(nativeHandle_, key, 0, key.length, value, 0, value.length);
   }
 
+  /**
+   * Add merge operand for key/value pair.
+   *
+   * @param key the specified key to be merged.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value the value to be merged with the current value for the specified key.
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public void merge(final byte[] key, int offset, int len, final byte[] value, int vOffset, int vLen)
+      throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    merge(nativeHandle_, key, offset, len, value, vOffset, vLen);
+  }
+
+
   /**
    * Add merge operand for key/value pair in a ColumnFamily.
    *
@@ -648,6 +876,32 @@ public class RocksDB extends RocksObject {
         columnFamilyHandle.nativeHandle_);
   }
 
+  /**
+   * Add merge operand for key/value pair in a ColumnFamily.
+   *
+   * @param columnFamilyHandle {@link ColumnFamilyHandle} instance
+   * @param key the specified key to be merged.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value the value to be merged with the current value for
+   * the specified key.
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public void merge(final ColumnFamilyHandle columnFamilyHandle,
+      final byte[] key, int offset, int len, final byte[] value, int vOffset, int vLen) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    merge(nativeHandle_, key, offset, len, value, vOffset, vLen,
+        columnFamilyHandle.nativeHandle_);
+  }
+
   /**
    * Add merge operand for key/value pair.
    *
@@ -665,6 +919,32 @@ public class RocksDB extends RocksObject {
         key, 0, key.length, value, 0, value.length);
   }
 
+  /**
+   * Add merge operand for key/value pair.
+   *
+   * @param writeOpts {@link WriteOptions} for this write.
+   * @param key the specified key to be merged.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value the value to be merged with the current value for
+   * the specified key.
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public void merge(final WriteOptions writeOpts, final byte[] key, int offset, int len,
+      final byte[] value, int vOffset, int vLen) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    merge(nativeHandle_, writeOpts.nativeHandle_,
+        key, offset, len, value, vOffset, vLen);
+  }
+
   /**
    * Add merge operand for key/value pair.
    *
@@ -685,13 +965,44 @@ public class RocksDB extends RocksObject {
         columnFamilyHandle.nativeHandle_);
   }
 
+  /**
+   * Add merge operand for key/value pair.
+   *
+   * @param columnFamilyHandle {@link ColumnFamilyHandle} instance
+   * @param writeOpts {@link WriteOptions} for this write.
+   * @param key the specified key to be merged.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value the value to be merged with the current value for
+   * the specified key.
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public void merge(final ColumnFamilyHandle columnFamilyHandle,
+      final WriteOptions writeOpts, final byte[] key, int offset, int len,
+      final byte[] value, int vOffset, int vLen) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    merge(nativeHandle_, writeOpts.nativeHandle_,
+        key, offset, len, value, vOffset, vLen,
+        columnFamilyHandle.nativeHandle_);
+  }
+
   // TODO(AR) we should improve the #get() API, returning -1 (RocksDB.NOT_FOUND) is not very nice
   // when we could communicate better status into, also the C++ code show that -2 could be returned
 
   /**
    * Get the value associated with the specified key within column family*
+   *
    * @param key the key to retrieve the value.
    * @param value the out-value to receive the retrieved value.
+   *
    * @return The size of the actual value that matches the specified
    *     {@code key} in byte.  If the return value is greater than the
    *     length of {@code value}, then it indicates that the size of the
@@ -706,6 +1017,35 @@ public class RocksDB extends RocksObject {
     return get(nativeHandle_, key, 0, key.length, value, 0, value.length);
   }
 
+  /**
+   * Get the value associated with the specified key within column family*
+   *
+   * @param key the key to retrieve the value.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value the out-value to receive the retrieved value.
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   *
+   * @return The size of the actual value that matches the specified
+   *     {@code key} in byte.  If the return value is greater than the
+   *     length of {@code value}, then it indicates that the size of the
+   *     input buffer {@code value} is insufficient and partial result will
+   *     be returned.  RocksDB.NOT_FOUND will be returned if the value not
+   *     found.
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public int get(final byte[] key, int offset, int len, final byte[] value, int vOffset, int vLen) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    return get(nativeHandle_, key, offset, len, value, vOffset, vLen);
+  }
+
   /**
    * Get the value associated with the specified key within column family.
    *
@@ -729,6 +1069,39 @@ public class RocksDB extends RocksObject {
         columnFamilyHandle.nativeHandle_);
   }
 
+  /**
+   * Get the value associated with the specified key within column family.
+   *
+   * @param columnFamilyHandle {@link org.rocksdb.ColumnFamilyHandle}
+   *     instance
+   * @param key the key to retrieve the value.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value the out-value to receive the retrieved value.
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   *
+   * @return The size of the actual value that matches the specified
+   *     {@code key} in byte.  If the return value is greater than the
+   *     length of {@code value}, then it indicates that the size of the
+   *     input buffer {@code value} is insufficient and partial result will
+   *     be returned.  RocksDB.NOT_FOUND will be returned if the value not
+   *     found.
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public int get(final ColumnFamilyHandle columnFamilyHandle, final byte[] key, int offset, int len,
+      final byte[] value, int vOffset, int vLen) throws RocksDBException, IllegalArgumentException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    return get(nativeHandle_, key, offset, len, value, vOffset, vLen,
+        columnFamilyHandle.nativeHandle_);
+  }
+
   /**
    * Get the value associated with the specified key.
    *
@@ -750,6 +1123,38 @@ public class RocksDB extends RocksObject {
     return get(nativeHandle_, opt.nativeHandle_,
                key, 0, key.length, value, 0, value.length);
   }
+
+  /**
+   * Get the value associated with the specified key.
+   *
+   * @param opt {@link org.rocksdb.ReadOptions} instance.
+   * @param key the key to retrieve the value.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value the out-value to receive the retrieved value.
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   * @return The size of the actual value that matches the specified
+   *     {@code key} in byte.  If the return value is greater than the
+   *     length of {@code value}, then it indicates that the size of the
+   *     input buffer {@code value} is insufficient and partial result will
+   *     be returned.  RocksDB.NOT_FOUND will be returned if the value not
+   *     found.
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public int get(final ReadOptions opt, final byte[] key, int offset, int len,
+      final byte[] value, int vOffset, int vLen) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    return get(nativeHandle_, opt.nativeHandle_,
+        key, offset, len, value, vOffset, vLen);
+  }
+
   /**
    * Get the value associated with the specified key within column family.
    *
@@ -775,6 +1180,40 @@ public class RocksDB extends RocksObject {
         0, value.length, columnFamilyHandle.nativeHandle_);
   }
 
+  /**
+   * Get the value associated with the specified key within column family.
+   *
+   * @param columnFamilyHandle {@link org.rocksdb.ColumnFamilyHandle}
+   *     instance
+   * @param opt {@link org.rocksdb.ReadOptions} instance.
+   * @param key the key to retrieve the value.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param value the out-value to receive the retrieved value.
+   * @param vOffset the offset of the "value" array to be used, must be non-negative and
+   *               no longer than "key".length
+   * @param vLen the length of the "value" array to be used, must be non-negative and
+   *            must be non-negative and no larger than ("value".length -  offset)
+   * @return The size of the actual value that matches the specified
+   *     {@code key} in byte.  If the return value is greater than the
+   *     length of {@code value}, then it indicates that the size of the
+   *     input buffer {@code value} is insufficient and partial result will
+   *     be returned.  RocksDB.NOT_FOUND will be returned if the value not
+   *     found.
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public int get(final ColumnFamilyHandle columnFamilyHandle,
+      final ReadOptions opt, final byte[] key, int offset, int len, final byte[] value, int vOffset, int vLen)
+      throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    checkBounds(vOffset, vLen, value.length);
+    return get(nativeHandle_, opt.nativeHandle_, key, offset, len, value,
+        vOffset, vLen, columnFamilyHandle.nativeHandle_);
+  }
+
   /**
    * The simplified version of get which returns a new byte array storing
    * the value associated with the specified input key if any.  null will be
@@ -791,6 +1230,26 @@ public class RocksDB extends RocksObject {
     return get(nativeHandle_, key, 0, key.length);
   }
 
+  /**
+   * The simplified version of get which returns a new byte array storing
+   * the value associated with the specified input key if any.  null will be
+   * returned if the specified key is not found.
+   *
+   * @param key the key retrieve the value.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @return a byte array storing the value associated with the input key if
+   *     any.  null if it does not find the specified key.
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public byte[] get(final byte[] key, int offset, int len) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    return get(nativeHandle_, key, offset, len);
+  }
+
   /**
    * The simplified version of get which returns a new byte array storing
    * the value associated with the specified input key if any.  null will be
@@ -811,6 +1270,30 @@ public class RocksDB extends RocksObject {
         columnFamilyHandle.nativeHandle_);
   }
 
+  /**
+   * The simplified version of get which returns a new byte array storing
+   * the value associated with the specified input key if any.  null will be
+   * returned if the specified key is not found.
+   *
+   * @param columnFamilyHandle {@link org.rocksdb.ColumnFamilyHandle}
+   *     instance
+   * @param key the key retrieve the value.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @return a byte array storing the value associated with the input key if
+   *     any.  null if it does not find the specified key.
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public byte[] get(final ColumnFamilyHandle columnFamilyHandle,
+      final byte[] key, int offset, int len) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    return get(nativeHandle_, key, offset, len,
+        columnFamilyHandle.nativeHandle_);
+  }
+
   /**
    * The simplified version of get which returns a new byte array storing
    * the value associated with the specified input key if any.  null will be
@@ -829,6 +1312,28 @@ public class RocksDB extends RocksObject {
     return get(nativeHandle_, opt.nativeHandle_, key, 0, key.length);
   }
 
+  /**
+   * The simplified version of get which returns a new byte array storing
+   * the value associated with the specified input key if any.  null will be
+   * returned if the specified key is not found.
+   *
+   * @param key the key retrieve the value.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param opt Read options.
+   * @return a byte array storing the value associated with the input key if
+   *     any.  null if it does not find the specified key.
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public byte[] get(final ReadOptions opt, final byte[] key, int offset, int len)
+      throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    return get(nativeHandle_, opt.nativeHandle_, key, offset, len);
+  }
+
   /**
    * The simplified version of get which returns a new byte array storing
    * the value associated with the specified input key if any.  null will be
@@ -850,6 +1355,31 @@ public class RocksDB extends RocksObject {
         columnFamilyHandle.nativeHandle_);
   }
 
+  /**
+   * The simplified version of get which returns a new byte array storing
+   * the value associated with the specified input key if any.  null will be
+   * returned if the specified key is not found.
+   *
+   * @param columnFamilyHandle {@link org.rocksdb.ColumnFamilyHandle}
+   *     instance
+   * @param key the key retrieve the value.
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   * @param opt Read options.
+   * @return a byte array storing the value associated with the input key if
+   *     any.  null if it does not find the specified key.
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public byte[] get(final ColumnFamilyHandle columnFamilyHandle,
+      final ReadOptions opt, final byte[] key, int offset, int len) throws RocksDBException {
+    checkBounds(offset, len, key.length);
+    return get(nativeHandle_, opt.nativeHandle_, key, offset, len,
+        columnFamilyHandle.nativeHandle_);
+  }
+
   /**
    * Returns a map of keys for which values were found in DB.
    *
@@ -1073,6 +1603,23 @@ public class RocksDB extends RocksObject {
     delete(nativeHandle_, key, 0, key.length);
   }
 
+  /**
+   * Delete the database entry (if any) for "key".  Returns OK on
+   * success, and a non-OK status on error.  It is not an error if "key"
+   * did not exist in the database.
+   *
+   * @param key Key to delete within database
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public void delete(final byte[] key, int offset, int len) throws RocksDBException {
+    delete(nativeHandle_, key, offset, len);
+  }
+
   /**
    * Remove the database entry (if any) for "key".  Returns OK on
    * success, and a non-OK status on error.  It is not an error if "key"
@@ -1110,6 +1657,26 @@ public class RocksDB extends RocksObject {
     delete(nativeHandle_, key, 0, key.length, columnFamilyHandle.nativeHandle_);
   }
 
+  /**
+   * Delete the database entry (if any) for "key".  Returns OK on
+   * success, and a non-OK status on error.  It is not an error if "key"
+   * did not exist in the database.
+   *
+   * @param columnFamilyHandle {@link org.rocksdb.ColumnFamilyHandle}
+   *     instance
+   * @param key Key to delete within database
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public void delete(final ColumnFamilyHandle columnFamilyHandle,
+      final byte[] key, int offset, int len) throws RocksDBException {
+    delete(nativeHandle_, key, offset, len, columnFamilyHandle.nativeHandle_);
+  }
+
   /**
    * Remove the database entry (if any) for "key".  Returns OK on
    * success, and a non-OK status on error.  It is not an error if "key"
@@ -1145,6 +1712,25 @@ public class RocksDB extends RocksObject {
     delete(nativeHandle_, writeOpt.nativeHandle_, key, 0, key.length);
   }
 
+  /**
+   * Delete the database entry (if any) for "key".  Returns OK on
+   * success, and a non-OK status on error.  It is not an error if "key"
+   * did not exist in the database.
+   *
+   * @param writeOpt WriteOptions to be used with delete operation
+   * @param key Key to delete within database
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public void delete(final WriteOptions writeOpt, final byte[] key, int offset, int len)
+      throws RocksDBException {
+    delete(nativeHandle_, writeOpt.nativeHandle_, key, offset, len);
+  }
+
   /**
    * Remove the database entry (if any) for "key".  Returns OK on
    * success, and a non-OK status on error.  It is not an error if "key"
@@ -1187,6 +1773,29 @@ public class RocksDB extends RocksObject {
         columnFamilyHandle.nativeHandle_);
   }
 
+  /**
+   * Delete the database entry (if any) for "key".  Returns OK on
+   * success, and a non-OK status on error.  It is not an error if "key"
+   * did not exist in the database.
+   *
+   * @param columnFamilyHandle {@link org.rocksdb.ColumnFamilyHandle}
+   *     instance
+   * @param writeOpt WriteOptions to be used with delete operation
+   * @param key Key to delete within database
+   * @param offset the offset of the "key" array to be used, must be non-negative and
+   *               no larger than "key".length
+   * @param len the length of the "key" array to be used, must be non-negative and
+   *
+   * @throws RocksDBException thrown if error happens in underlying
+   *    native library.
+   */
+  public void delete(final ColumnFamilyHandle columnFamilyHandle,
+      final WriteOptions writeOpt, final byte[] key, int offset, int len)
+      throws RocksDBException {
+    delete(nativeHandle_, writeOpt.nativeHandle_, key, offset, len,
+        columnFamilyHandle.nativeHandle_);
+  }
+
   /**
    * Remove the database entry for {@code key}. Requires that the key exists
    * and was not overwritten. It is not an error if the key did not exist
@@ -1518,6 +2127,31 @@ public class RocksDB extends RocksObject {
         property, property.length());
   }
 
+ /**
+   * <p> Return sum of the getLongProperty of all the column families</p>
+   *
+   * <p><strong>Note</strong>: As the returned property is of type
+   * {@code uint64_t} on C++ side the returning value can be negative
+   * because Java supports in Java 7 only signed long values.</p>
+   *
+   * <p><strong>Java 7</strong>: To mitigate the problem of the non
+   * existent unsigned long tpye, values should be encapsulated using
+   * {@link java.math.BigInteger} to reflect the correct value. The correct
+   * behavior is guaranteed if {@code 2^64} is added to negative values.</p>
+   *
+   * <p><strong>Java 8</strong>: In Java 8 the value should be treated as
+   * unsigned long using provided methods of type {@link Long}.</p>
+   *
+   * @param property to be fetched.
+   *
+   * @return numerical property value
+   *
+   * @throws RocksDBException if an error happens in the underlying native code.
+   */
+  public long getAggregatedLongProperty(final String property) throws RocksDBException {
+    return getAggregatedLongProperty(nativeHandle_, property, property.length());
+  }
+
   /**
    * <p>Return a heap-allocated iterator over the contents of the
    * database. The result of newIterator() is initially invalid
@@ -2383,6 +3017,8 @@ public class RocksDB extends RocksObject {
       int propertyLength) throws RocksDBException;
   protected native long getLongProperty(long nativeHandle, long cfHandle,
       String property, int propertyLength) throws RocksDBException;
+  protected native long getAggregatedLongProperty(long nativeHandle, String property,
+      int propertyLength) throws RocksDBException;
   protected native long iterator(long handle);
   protected native long iterator(long handle, long readOptHandle);
   protected native long iteratorCF(long handle, long cfHandle);
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksDBException.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksDBException.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksDBException.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksDBException.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksEnv.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksEnv.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksEnv.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksEnv.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksIterator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksIterator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksIterator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksIterator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksIteratorInterface.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksIteratorInterface.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksIteratorInterface.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksIteratorInterface.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksMemEnv.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksMemEnv.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksMemEnv.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksMemEnv.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksMutableObject.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksMutableObject.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksMutableObject.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksMutableObject.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksObject.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksObject.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/RocksObject.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/RocksObject.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/SkipListMemTableConfig.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/SkipListMemTableConfig.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/SkipListMemTableConfig.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/SkipListMemTableConfig.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Slice.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Slice.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Slice.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Slice.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Snapshot.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Snapshot.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Snapshot.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Snapshot.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/SstFileManager.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/SstFileManager.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/SstFileManager.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/SstFileManager.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/SstFileWriter.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/SstFileWriter.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/SstFileWriter.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/SstFileWriter.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Statistics.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Statistics.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Statistics.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Statistics.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StatisticsCollector.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StatisticsCollector.java
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StatisticsCollector.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StatisticsCollector.java
index 48cf8af88e..fb3f57150f 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StatisticsCollector.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StatisticsCollector.java
@@ -93,9 +93,9 @@ public class StatisticsCollector {
                   statsCallback.histogramCallback(histogramType, histogramData);
                 }
               }
-
-              Thread.sleep(_statsCollectionInterval);
             }
+
+            Thread.sleep(_statsCollectionInterval);
           }
           catch (final InterruptedException e) {
             Thread.currentThread().interrupt();
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StatisticsCollectorCallback.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StatisticsCollectorCallback.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StatisticsCollectorCallback.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StatisticsCollectorCallback.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StatsCollectorInput.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StatsCollectorInput.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StatsCollectorInput.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StatsCollectorInput.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StatsLevel.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StatsLevel.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StatsLevel.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StatsLevel.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Status.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Status.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Status.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Status.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StringAppendOperator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StringAppendOperator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/StringAppendOperator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/StringAppendOperator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TableFormatConfig.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TableFormatConfig.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TableFormatConfig.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TableFormatConfig.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TickerType.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TickerType.java
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TickerType.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TickerType.java
index fdcf62ff8a..08ed18fb3e 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TickerType.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TickerType.java
@@ -304,9 +304,9 @@ public enum TickerType {
     RATE_LIMIT_DELAY_MILLIS((byte) 0x37),
 
     /**
-     * Number of iterators currently open.
+     * Number of iterators created.
      */
-    NO_ITERATORS((byte) 0x38),
+    NO_ITERATOR_CREATED((byte) 0x38),
 
     /**
      * Number of MultiGet calls.
@@ -475,7 +475,12 @@ public enum TickerType {
      */
     NUMBER_MULTIGET_KEYS_FOUND((byte) 0x5E),
 
-    TICKER_ENUM_MAX((byte) 0x5F);
+    /**
+     * Number of iterators deleted.
+     */
+    NO_ITERATOR_DELETED((byte) 0x5F),
+
+    TICKER_ENUM_MAX((byte) 0x60);
 
 
     private final byte value;
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Transaction.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Transaction.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/Transaction.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/Transaction.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionDB.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionDB.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionDB.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionDB.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionDBOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionDBOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionDBOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionDBOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionLogIterator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionLogIterator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionLogIterator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionLogIterator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionalDB.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionalDB.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionalDB.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionalDB.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionalOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionalOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TransactionalOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TransactionalOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TtlDB.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TtlDB.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TtlDB.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TtlDB.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TxnDBWritePolicy.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TxnDBWritePolicy.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/TxnDBWritePolicy.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/TxnDBWritePolicy.java
diff --git a/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/UInt64AddOperator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/UInt64AddOperator.java
new file mode 100644
index 0000000000..cce9b298d8
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/UInt64AddOperator.java
@@ -0,0 +1,19 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+// This source code is licensed under both the GPLv2 (found in the
+// COPYING file in the root directory) and Apache 2.0 License
+// (found in the LICENSE.Apache file in the root directory).
+
+package org.rocksdb;
+
+/**
+ * Uint64AddOperator is a merge operator that accumlates a long
+ * integer value.
+ */
+public class UInt64AddOperator extends MergeOperator {
+    public UInt64AddOperator() {
+        super(newSharedUInt64AddOperator());
+    }
+
+    private native static long newSharedUInt64AddOperator();
+    @Override protected final native void disposeInternal(final long handle);
+}
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/VectorMemTableConfig.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/VectorMemTableConfig.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/VectorMemTableConfig.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/VectorMemTableConfig.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WALRecoveryMode.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WALRecoveryMode.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WALRecoveryMode.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WALRecoveryMode.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WBWIRocksIterator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WBWIRocksIterator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WBWIRocksIterator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WBWIRocksIterator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WriteBatch.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteBatch.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WriteBatch.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteBatch.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WriteBatchInterface.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteBatchInterface.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WriteBatchInterface.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteBatchInterface.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WriteBatchWithIndex.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteBatchWithIndex.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WriteBatchWithIndex.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteBatchWithIndex.java
diff --git a/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteBufferManager.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteBufferManager.java
new file mode 100644
index 0000000000..a5f80644fb
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteBufferManager.java
@@ -0,0 +1,30 @@
+package org.rocksdb;
+
+import org.rocksdb.Cache;
+
+/**
+ * Java wrapper over native write_buffer_manager class
+ */
+public class WriteBufferManager extends RocksObject {
+  static {
+    RocksDB.loadLibrary();
+  }
+
+  /**
+   * Construct a new instance of WriteBufferManager.
+   *
+   * Check <a href="https://github.com/facebook/rocksdb/wiki/Write-Buffer-Manager">
+   *     https://github.com/facebook/rocksdb/wiki/Write-Buffer-Manager</a>
+   * for more details on when to use it
+   *
+   * @param bufferSizeBytes buffer size(in bytes) to use for native write_buffer_manager
+   * @param cache cache whose memory should be bounded by this write buffer manager
+   */
+  public WriteBufferManager(final long bufferSizeBytes, final Cache cache){
+    super(newWriteBufferManager(bufferSizeBytes, cache.nativeHandle_));
+  }
+
+  private native static long newWriteBufferManager(final long bufferSizeBytes, final long cacheHandle);
+  @Override
+  protected native void disposeInternal(final long handle);
+}
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WriteOptions.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteOptions.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/WriteOptions.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/WriteOptions.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/util/BytewiseComparator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/util/BytewiseComparator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/util/BytewiseComparator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/util/BytewiseComparator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/util/DirectBytewiseComparator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/util/DirectBytewiseComparator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/util/DirectBytewiseComparator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/util/DirectBytewiseComparator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/util/Environment.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/util/Environment.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/util/Environment.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/util/Environment.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/util/ReverseBytewiseComparator.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/util/ReverseBytewiseComparator.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/util/ReverseBytewiseComparator.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/util/ReverseBytewiseComparator.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/util/SizeUnit.java b/3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/util/SizeUnit.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/main/java/org/rocksdb/util/SizeUnit.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/main/java/org/rocksdb/util/SizeUnit.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/AbstractComparatorTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/AbstractComparatorTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/AbstractComparatorTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/AbstractComparatorTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/AbstractTransactionTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/AbstractTransactionTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/AbstractTransactionTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/AbstractTransactionTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/BackupEngineTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/BackupEngineTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/BackupEngineTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/BackupEngineTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/BackupableDBOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/BackupableDBOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/BackupableDBOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/BackupableDBOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/BlockBasedTableConfigTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/BlockBasedTableConfigTest.java
similarity index 83%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/BlockBasedTableConfigTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/BlockBasedTableConfigTest.java
index 2b15b69f81..754cf11c03 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/BlockBasedTableConfigTest.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/BlockBasedTableConfigTest.java
@@ -95,6 +95,46 @@ public class BlockBasedTableConfigTest {
 
   }
 
+  @Test
+  public void cacheIndexAndFilterBlocksWithHighPriority() {
+    BlockBasedTableConfig blockBasedTableConfig = new BlockBasedTableConfig();
+    blockBasedTableConfig.setCacheIndexAndFilterBlocksWithHighPriority(true);
+    assertThat(blockBasedTableConfig.cacheIndexAndFilterBlocksWithHighPriority()).
+            isTrue();
+  }
+
+  @Test
+  public void pinL0FilterAndIndexBlocksInCache() {
+    BlockBasedTableConfig blockBasedTableConfig = new BlockBasedTableConfig();
+    blockBasedTableConfig.setPinL0FilterAndIndexBlocksInCache(true);
+    assertThat(blockBasedTableConfig.pinL0FilterAndIndexBlocksInCache()).
+            isTrue();
+  }
+
+  @Test
+  public void partitionFilters() {
+    BlockBasedTableConfig blockBasedTableConfig = new BlockBasedTableConfig();
+    blockBasedTableConfig.setPartitionFilters(true);
+    assertThat(blockBasedTableConfig.partitionFilters()).
+            isTrue();
+  }
+
+  @Test
+  public void metadataBlockSize() {
+    BlockBasedTableConfig blockBasedTableConfig = new BlockBasedTableConfig();
+    blockBasedTableConfig.setMetadataBlockSize(1024);
+    assertThat(blockBasedTableConfig.metadataBlockSize()).
+            isEqualTo(1024);
+  }
+
+  @Test
+  public void pinTopLevelIndexAndFilter() {
+    BlockBasedTableConfig blockBasedTableConfig = new BlockBasedTableConfig();
+    blockBasedTableConfig.setPinTopLevelIndexAndFilter(false);
+    assertThat(blockBasedTableConfig.pinTopLevelIndexAndFilter()).
+            isFalse();
+  }
+
   @Test
   public void hashIndexAllowCollision() {
     BlockBasedTableConfig blockBasedTableConfig = new BlockBasedTableConfig();
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CheckPointTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CheckPointTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CheckPointTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CheckPointTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ClockCacheTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ClockCacheTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ClockCacheTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ClockCacheTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ColumnFamilyOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ColumnFamilyOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ColumnFamilyOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ColumnFamilyOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ColumnFamilyTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ColumnFamilyTest.java
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ColumnFamilyTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ColumnFamilyTest.java
index 3df63c65ff..0b943ac96e 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ColumnFamilyTest.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ColumnFamilyTest.java
@@ -404,6 +404,10 @@ public class ColumnFamilyTest {
             "rocksdb.stats")).isNotNull();
         assertThat(db.getProperty(columnFamilyHandleList.get(1),
             "rocksdb.sstables")).isNotNull();
+        assertThat(db.getAggregatedLongProperty("rocksdb.estimate-num-keys")).
+            isNotNull();
+        assertThat(db.getAggregatedLongProperty("rocksdb.estimate-num-keys")).
+            isGreaterThanOrEqualTo(0);
       } finally {
         for (final ColumnFamilyHandle columnFamilyHandle :
             columnFamilyHandleList) {
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactRangeOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactRangeOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactRangeOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactRangeOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionFilterFactoryTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionFilterFactoryTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionFilterFactoryTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionFilterFactoryTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionOptionsFIFOTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionOptionsFIFOTest.java
similarity index 52%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionOptionsFIFOTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionOptionsFIFOTest.java
index 370a28e819..df4c98ec14 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionOptionsFIFOTest.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionOptionsFIFOTest.java
@@ -18,9 +18,27 @@ public class CompactionOptionsFIFOTest {
   @Test
   public void maxTableFilesSize() {
     final long size = 500 * 1024 * 1026;
-    try(final CompactionOptionsFIFO opt = new CompactionOptionsFIFO()) {
+    try (final CompactionOptionsFIFO opt = new CompactionOptionsFIFO()) {
       opt.setMaxTableFilesSize(size);
       assertThat(opt.maxTableFilesSize()).isEqualTo(size);
     }
   }
+
+  @Test
+  public void ttl() {
+    final long ttl = 7 * 24 * 60 * 60; // 7 days
+    try (final CompactionOptionsFIFO opt = new CompactionOptionsFIFO()) {
+      opt.setTtl(ttl);
+      assertThat(opt.ttl()).isEqualTo(ttl);
+    }
+  }
+
+  @Test
+  public void allowCompaction() {
+    final boolean allowCompaction = true;
+    try (final CompactionOptionsFIFO opt = new CompactionOptionsFIFO()) {
+      opt.setAllowCompaction(allowCompaction);
+      assertThat(opt.allowCompaction()).isEqualTo(allowCompaction);
+    }
+  }
 }
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionOptionsUniversalTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionOptionsUniversalTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionOptionsUniversalTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionOptionsUniversalTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionPriorityTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionPriorityTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionPriorityTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionPriorityTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionStopStyleTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionStopStyleTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompactionStopStyleTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompactionStopStyleTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ComparatorOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ComparatorOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ComparatorOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ComparatorOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ComparatorTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ComparatorTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ComparatorTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ComparatorTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompressionOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompressionOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompressionOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompressionOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompressionTypesTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompressionTypesTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/CompressionTypesTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/CompressionTypesTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/DBOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/DBOptionsTest.java
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/DBOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/DBOptionsTest.java
index 453639d574..bad01c4354 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/DBOptionsTest.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/DBOptionsTest.java
@@ -424,6 +424,26 @@ public class DBOptionsTest {
     }
   }
 
+  @Test
+  public void setWriteBufferManager() throws RocksDBException {
+    try (final DBOptions opt = new DBOptions();
+         final Cache cache = new LRUCache(1 * 1024 * 1024);
+         final WriteBufferManager writeBufferManager = new WriteBufferManager(2000l, cache)) {
+      opt.setWriteBufferManager(writeBufferManager);
+      assertThat(opt.writeBufferManager()).isEqualTo(writeBufferManager);
+    }
+  }
+
+  @Test
+  public void setWriteBufferManagerWithZeroBufferSize() throws RocksDBException {
+    try (final DBOptions opt = new DBOptions();
+         final Cache cache = new LRUCache(1 * 1024 * 1024);
+         final WriteBufferManager writeBufferManager = new WriteBufferManager(0l, cache)) {
+      opt.setWriteBufferManager(writeBufferManager);
+      assertThat(opt.writeBufferManager()).isEqualTo(writeBufferManager);
+    }
+  }
+
   @Test
   public void accessHintOnCompactionStart() {
     try(final DBOptions opt = new DBOptions()) {
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/DirectComparatorTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/DirectComparatorTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/DirectComparatorTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/DirectComparatorTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/DirectSliceTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/DirectSliceTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/DirectSliceTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/DirectSliceTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/EnvOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/EnvOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/EnvOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/EnvOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/FilterTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/FilterTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/FilterTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/FilterTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/FlushTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/FlushTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/FlushTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/FlushTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/InfoLogLevelTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/InfoLogLevelTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/InfoLogLevelTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/InfoLogLevelTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/IngestExternalFileOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/IngestExternalFileOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/IngestExternalFileOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/IngestExternalFileOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/KeyMayExistTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/KeyMayExistTest.java
similarity index 64%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/KeyMayExistTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/KeyMayExistTest.java
index 8092270eb2..577fe2eadf 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/KeyMayExistTest.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/KeyMayExistTest.java
@@ -48,12 +48,33 @@ public class KeyMayExistTest {
         assertThat(exists).isTrue();
         assertThat(retValue.toString()).isEqualTo("value");
 
+        // Slice key
+        StringBuilder builder = new StringBuilder("prefix");
+        int offset = builder.toString().length();
+        builder.append("slice key 0");
+        int len = builder.toString().length() - offset;
+        builder.append("suffix");
+
+        byte[] sliceKey = builder.toString().getBytes();
+        byte[] sliceValue = "slice value 0".getBytes();
+        db.put(sliceKey, offset, len, sliceValue, 0, sliceValue.length);
+
+        retValue = new StringBuilder();
+        exists = db.keyMayExist(sliceKey, offset, len, retValue);
+        assertThat(exists).isTrue();
+        assertThat(retValue.toString().getBytes()).isEqualTo(sliceValue);
+
         // Test without column family but with readOptions
         try (final ReadOptions readOptions = new ReadOptions()) {
           retValue = new StringBuilder();
           exists = db.keyMayExist(readOptions, "key".getBytes(), retValue);
           assertThat(exists).isTrue();
           assertThat(retValue.toString()).isEqualTo("value");
+
+          retValue = new StringBuilder();
+          exists = db.keyMayExist(readOptions, sliceKey, offset, len, retValue);
+          assertThat(exists).isTrue();
+          assertThat(retValue.toString().getBytes()).isEqualTo(sliceValue);
         }
 
         // Test with column family
@@ -63,6 +84,13 @@ public class KeyMayExistTest {
         assertThat(exists).isTrue();
         assertThat(retValue.toString()).isEqualTo("value");
 
+        // Test slice sky with column family
+        retValue = new StringBuilder();
+        exists = db.keyMayExist(columnFamilyHandleList.get(0), sliceKey, offset, len,
+            retValue);
+        assertThat(exists).isTrue();
+        assertThat(retValue.toString().getBytes()).isEqualTo(sliceValue);
+
         // Test with column family and readOptions
         try (final ReadOptions readOptions = new ReadOptions()) {
           retValue = new StringBuilder();
@@ -71,11 +99,23 @@ public class KeyMayExistTest {
               retValue);
           assertThat(exists).isTrue();
           assertThat(retValue.toString()).isEqualTo("value");
+
+          // Test slice key with column family and read options
+          retValue = new StringBuilder();
+          exists = db.keyMayExist(readOptions,
+              columnFamilyHandleList.get(0), sliceKey, offset, len,
+              retValue);
+          assertThat(exists).isTrue();
+          assertThat(retValue.toString().getBytes()).isEqualTo(sliceValue);
         }
 
         // KeyMayExist in CF1 must return false
         assertThat(db.keyMayExist(columnFamilyHandleList.get(1),
             "key".getBytes(), retValue)).isFalse();
+
+        // slice key
+        assertThat(db.keyMayExist(columnFamilyHandleList.get(1),
+           sliceKey, 1, 3, retValue)).isFalse();
       } finally {
         for (final ColumnFamilyHandle columnFamilyHandle :
             columnFamilyHandleList) {
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/LRUCacheTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/LRUCacheTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/LRUCacheTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/LRUCacheTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/LoggerTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/LoggerTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/LoggerTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/LoggerTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/MemTableTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MemTableTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/MemTableTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MemTableTest.java
diff --git a/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MemoryUtilTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MemoryUtilTest.java
new file mode 100644
index 0000000000..73fcc87c32
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MemoryUtilTest.java
@@ -0,0 +1,143 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+package org.rocksdb;
+
+import org.junit.ClassRule;
+import org.junit.Rule;
+import org.junit.Test;
+import org.junit.rules.TemporaryFolder;
+
+import java.nio.charset.StandardCharsets;
+import java.util.*;
+
+import static org.assertj.core.api.Assertions.assertThat;
+
+public class MemoryUtilTest {
+
+  private static final String MEMTABLE_SIZE = "rocksdb.size-all-mem-tables";
+  private static final String UNFLUSHED_MEMTABLE_SIZE = "rocksdb.cur-size-all-mem-tables";
+  private static final String TABLE_READERS = "rocksdb.estimate-table-readers-mem";
+
+  private final byte[] key = "some-key".getBytes(StandardCharsets.UTF_8);
+  private final byte[] value = "some-value".getBytes(StandardCharsets.UTF_8);
+
+  @ClassRule
+  public static final RocksMemoryResource rocksMemoryResource =
+      new RocksMemoryResource();
+
+  @Rule public TemporaryFolder dbFolder1 = new TemporaryFolder();
+  @Rule public TemporaryFolder dbFolder2 = new TemporaryFolder();
+
+  /**
+   * Test MemoryUtil.getApproximateMemoryUsageByType before and after a put + get
+   */
+  @Test
+  public void getApproximateMemoryUsageByType() throws RocksDBException {
+    try (final Cache cache = new LRUCache(8 * 1024 * 1024);
+         final Options options =
+                 new Options()
+                         .setCreateIfMissing(true)
+                         .setTableFormatConfig(new BlockBasedTableConfig().setBlockCache(cache));
+         final FlushOptions flushOptions =
+                 new FlushOptions().setWaitForFlush(true);
+         final RocksDB db =
+                 RocksDB.open(options, dbFolder1.getRoot().getAbsolutePath())) {
+
+      List<RocksDB> dbs = new ArrayList<>(1);
+      dbs.add(db);
+      Set<Cache> caches = new HashSet<>(1);
+      caches.add(cache);
+      Map<MemoryUsageType, Long> usage = MemoryUtil.getApproximateMemoryUsageByType(dbs, caches);
+
+      assertThat(usage.get(MemoryUsageType.kMemTableTotal)).isEqualTo(
+              db.getAggregatedLongProperty(MEMTABLE_SIZE));
+      assertThat(usage.get(MemoryUsageType.kMemTableUnFlushed)).isEqualTo(
+              db.getAggregatedLongProperty(UNFLUSHED_MEMTABLE_SIZE));
+      assertThat(usage.get(MemoryUsageType.kTableReadersTotal)).isEqualTo(
+              db.getAggregatedLongProperty(TABLE_READERS));
+      assertThat(usage.get(MemoryUsageType.kCacheTotal)).isEqualTo(0);
+
+      db.put(key, value);
+      db.flush(flushOptions);
+      db.get(key);
+
+      usage = MemoryUtil.getApproximateMemoryUsageByType(dbs, caches);
+      assertThat(usage.get(MemoryUsageType.kMemTableTotal)).isGreaterThan(0);
+      assertThat(usage.get(MemoryUsageType.kMemTableTotal)).isEqualTo(
+              db.getAggregatedLongProperty(MEMTABLE_SIZE));
+      assertThat(usage.get(MemoryUsageType.kMemTableUnFlushed)).isGreaterThan(0);
+      assertThat(usage.get(MemoryUsageType.kMemTableUnFlushed)).isEqualTo(
+              db.getAggregatedLongProperty(UNFLUSHED_MEMTABLE_SIZE));
+      assertThat(usage.get(MemoryUsageType.kTableReadersTotal)).isGreaterThan(0);
+      assertThat(usage.get(MemoryUsageType.kTableReadersTotal)).isEqualTo(
+              db.getAggregatedLongProperty(TABLE_READERS));
+      assertThat(usage.get(MemoryUsageType.kCacheTotal)).isGreaterThan(0);
+
+    }
+  }
+
+  /**
+   * Test MemoryUtil.getApproximateMemoryUsageByType with null inputs
+   */
+  @Test
+  public void getApproximateMemoryUsageByTypeNulls() throws RocksDBException {
+    Map<MemoryUsageType, Long> usage = MemoryUtil.getApproximateMemoryUsageByType(null, null);
+
+    assertThat(usage.get(MemoryUsageType.kMemTableTotal)).isEqualTo(null);
+    assertThat(usage.get(MemoryUsageType.kMemTableUnFlushed)).isEqualTo(null);
+    assertThat(usage.get(MemoryUsageType.kTableReadersTotal)).isEqualTo(null);
+    assertThat(usage.get(MemoryUsageType.kCacheTotal)).isEqualTo(null);
+  }
+
+  /**
+   * Test MemoryUtil.getApproximateMemoryUsageByType with two DBs and two caches
+   */
+  @Test
+  public void getApproximateMemoryUsageByTypeMultiple() throws RocksDBException {
+    try (final Cache cache1 = new LRUCache(1 * 1024 * 1024);
+         final Options options1 =
+                 new Options()
+                         .setCreateIfMissing(true)
+                         .setTableFormatConfig(new BlockBasedTableConfig().setBlockCache(cache1));
+         final RocksDB db1 =
+                 RocksDB.open(options1, dbFolder1.getRoot().getAbsolutePath());
+         final Cache cache2 = new LRUCache(1 * 1024 * 1024);
+         final Options options2 =
+                 new Options()
+                         .setCreateIfMissing(true)
+                         .setTableFormatConfig(new BlockBasedTableConfig().setBlockCache(cache2));
+         final RocksDB db2 =
+                 RocksDB.open(options2, dbFolder2.getRoot().getAbsolutePath());
+         final FlushOptions flushOptions =
+                 new FlushOptions().setWaitForFlush(true);
+
+    ) {
+      List<RocksDB> dbs = new ArrayList<>(1);
+      dbs.add(db1);
+      dbs.add(db2);
+      Set<Cache> caches = new HashSet<>(1);
+      caches.add(cache1);
+      caches.add(cache2);
+
+      for (RocksDB db: dbs) {
+        db.put(key, value);
+        db.flush(flushOptions);
+        db.get(key);
+      }
+
+      Map<MemoryUsageType, Long> usage = MemoryUtil.getApproximateMemoryUsageByType(dbs, caches);
+      assertThat(usage.get(MemoryUsageType.kMemTableTotal)).isEqualTo(
+              db1.getAggregatedLongProperty(MEMTABLE_SIZE) + db2.getAggregatedLongProperty(MEMTABLE_SIZE));
+      assertThat(usage.get(MemoryUsageType.kMemTableUnFlushed)).isEqualTo(
+              db1.getAggregatedLongProperty(UNFLUSHED_MEMTABLE_SIZE) + db2.getAggregatedLongProperty(UNFLUSHED_MEMTABLE_SIZE));
+      assertThat(usage.get(MemoryUsageType.kTableReadersTotal)).isEqualTo(
+              db1.getAggregatedLongProperty(TABLE_READERS) + db2.getAggregatedLongProperty(TABLE_READERS));
+      assertThat(usage.get(MemoryUsageType.kCacheTotal)).isGreaterThan(0);
+
+    }
+  }
+
+}
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/MergeTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MergeTest.java
similarity index 53%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/MergeTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MergeTest.java
index 73b90869cf..b2ec62635a 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/MergeTest.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MergeTest.java
@@ -5,6 +5,7 @@
 
 package org.rocksdb;
 
+import java.nio.ByteBuffer;
 import java.util.Arrays;
 import java.util.List;
 import java.util.ArrayList;
@@ -44,6 +45,38 @@ public class MergeTest {
     }
   }
 
+  private byte[] longToByteArray(long l) {
+    ByteBuffer buf = ByteBuffer.allocate(Long.BYTES);
+    buf.putLong(l);
+    return buf.array();
+  }
+
+  private long longFromByteArray(byte[] a) {
+    ByteBuffer buf = ByteBuffer.allocate(Long.BYTES);
+    buf.put(a);
+    buf.flip();
+    return buf.getLong();
+  }
+
+  @Test
+  public void uint64AddOption()
+      throws InterruptedException, RocksDBException {
+    try (final Options opt = new Options()
+        .setCreateIfMissing(true)
+        .setMergeOperatorName("uint64add");
+         final RocksDB db = RocksDB.open(opt,
+             dbFolder.getRoot().getAbsolutePath())) {
+      // writing (long)100 under key
+      db.put("key".getBytes(), longToByteArray(100));
+      // merge (long)1 under key
+      db.merge("key".getBytes(), longToByteArray(1));
+
+      final byte[] value = db.get("key".getBytes());
+      final long longValue = longFromByteArray(value);
+      assertThat(longValue).isEqualTo(101);
+    }
+  }
+
   @Test
   public void cFStringOption()
       throws InterruptedException, RocksDBException {
@@ -86,6 +119,48 @@ public class MergeTest {
     }
   }
 
+  @Test
+  public void cFUInt64AddOption()
+      throws InterruptedException, RocksDBException {
+
+    try (final ColumnFamilyOptions cfOpt1 = new ColumnFamilyOptions()
+        .setMergeOperatorName("uint64add");
+         final ColumnFamilyOptions cfOpt2 = new ColumnFamilyOptions()
+             .setMergeOperatorName("uint64add")
+    ) {
+      final List<ColumnFamilyDescriptor> cfDescriptors = Arrays.asList(
+          new ColumnFamilyDescriptor(RocksDB.DEFAULT_COLUMN_FAMILY, cfOpt1),
+          new ColumnFamilyDescriptor(RocksDB.DEFAULT_COLUMN_FAMILY, cfOpt2)
+      );
+
+      final List<ColumnFamilyHandle> columnFamilyHandleList = new ArrayList<>();
+      try (final DBOptions opt = new DBOptions()
+          .setCreateIfMissing(true)
+          .setCreateMissingColumnFamilies(true);
+           final RocksDB db = RocksDB.open(opt,
+               dbFolder.getRoot().getAbsolutePath(), cfDescriptors,
+               columnFamilyHandleList)) {
+        try {
+          // writing (long)100 under key
+          db.put(columnFamilyHandleList.get(1),
+              "cfkey".getBytes(), longToByteArray(100));
+          // merge (long)1 under key
+          db.merge(columnFamilyHandleList.get(1),
+              "cfkey".getBytes(), longToByteArray(1));
+
+          byte[] value = db.get(columnFamilyHandleList.get(1),
+              "cfkey".getBytes());
+          long longValue = longFromByteArray(value);
+          assertThat(longValue).isEqualTo(101);
+        } finally {
+          for (final ColumnFamilyHandle handle : columnFamilyHandleList) {
+            handle.close();
+          }
+        }
+      }
+    }
+  }
+
   @Test
   public void operatorOption()
       throws InterruptedException, RocksDBException {
@@ -108,6 +183,28 @@ public class MergeTest {
     }
   }
 
+  @Test
+  public void uint64AddOperatorOption()
+      throws InterruptedException, RocksDBException {
+    try (final UInt64AddOperator uint64AddOperator = new UInt64AddOperator();
+         final Options opt = new Options()
+            .setCreateIfMissing(true)
+            .setMergeOperator(uint64AddOperator);
+         final RocksDB db = RocksDB.open(opt,
+             dbFolder.getRoot().getAbsolutePath())) {
+      // Writing (long)100 under key
+      db.put("key".getBytes(), longToByteArray(100));
+
+      // Writing (long)1 under key
+      db.merge("key".getBytes(), longToByteArray(1));
+
+      final byte[] value = db.get("key".getBytes());
+      final long longValue = longFromByteArray(value);
+
+      assertThat(longValue).isEqualTo(101);
+    }
+  }
+
   @Test
   public void cFOperatorOption()
       throws InterruptedException, RocksDBException {
@@ -170,6 +267,68 @@ public class MergeTest {
     }
   }
 
+  @Test
+  public void cFUInt64AddOperatorOption()
+      throws InterruptedException, RocksDBException {
+    try (final UInt64AddOperator uint64AddOperator = new UInt64AddOperator();
+         final ColumnFamilyOptions cfOpt1 = new ColumnFamilyOptions()
+             .setMergeOperator(uint64AddOperator);
+         final ColumnFamilyOptions cfOpt2 = new ColumnFamilyOptions()
+             .setMergeOperator(uint64AddOperator)
+    ) {
+      final List<ColumnFamilyDescriptor> cfDescriptors = Arrays.asList(
+          new ColumnFamilyDescriptor(RocksDB.DEFAULT_COLUMN_FAMILY, cfOpt1),
+          new ColumnFamilyDescriptor("new_cf".getBytes(), cfOpt2)
+      );
+      final List<ColumnFamilyHandle> columnFamilyHandleList = new ArrayList<>();
+      try (final DBOptions opt = new DBOptions()
+          .setCreateIfMissing(true)
+          .setCreateMissingColumnFamilies(true);
+           final RocksDB db = RocksDB.open(opt,
+               dbFolder.getRoot().getAbsolutePath(), cfDescriptors,
+               columnFamilyHandleList)
+      ) {
+        try {
+          // writing (long)100 under key
+          db.put(columnFamilyHandleList.get(1),
+              "cfkey".getBytes(), longToByteArray(100));
+          // merge (long)1 under key
+          db.merge(columnFamilyHandleList.get(1),
+              "cfkey".getBytes(), longToByteArray(1));
+          byte[] value = db.get(columnFamilyHandleList.get(1),
+              "cfkey".getBytes());
+          long longValue = longFromByteArray(value);
+
+          // Test also with createColumnFamily
+          try (final ColumnFamilyOptions cfHandleOpts =
+                   new ColumnFamilyOptions()
+                       .setMergeOperator(uint64AddOperator);
+               final ColumnFamilyHandle cfHandle =
+                   db.createColumnFamily(
+                       new ColumnFamilyDescriptor("new_cf2".getBytes(),
+                           cfHandleOpts))
+          ) {
+            // writing (long)200 under cfkey2
+            db.put(cfHandle, "cfkey2".getBytes(), longToByteArray(200));
+            // merge (long)50 under cfkey2
+            db.merge(cfHandle, new WriteOptions(), "cfkey2".getBytes(),
+                longToByteArray(50));
+            value = db.get(cfHandle, "cfkey2".getBytes());
+            long longValueTmpCf = longFromByteArray(value);
+
+            assertThat(longValue).isEqualTo(101);
+            assertThat(longValueTmpCf).isEqualTo(250);
+          }
+        } finally {
+          for (final ColumnFamilyHandle columnFamilyHandle :
+              columnFamilyHandleList) {
+            columnFamilyHandle.close();
+          }
+        }
+      }
+    }
+  }
+
   @Test
   public void operatorGcBehaviour()
       throws RocksDBException {
@@ -182,7 +341,6 @@ public class MergeTest {
         //no-op
       }
 
-
       // test reuse
       try (final Options opt = new Options()
               .setMergeOperator(stringAppendOperator);
@@ -213,6 +371,48 @@ public class MergeTest {
     }
   }
 
+  @Test
+  public void uint64AddOperatorGcBehaviour()
+      throws RocksDBException {
+    try (final UInt64AddOperator uint64AddOperator = new UInt64AddOperator()) {
+      try (final Options opt = new Options()
+              .setCreateIfMissing(true)
+              .setMergeOperator(uint64AddOperator);
+           final RocksDB db = RocksDB.open(opt,
+                   dbFolder.getRoot().getAbsolutePath())) {
+        //no-op
+      }
+
+      // test reuse
+      try (final Options opt = new Options()
+              .setMergeOperator(uint64AddOperator);
+           final RocksDB db = RocksDB.open(opt,
+                   dbFolder.getRoot().getAbsolutePath())) {
+        //no-op
+      }
+
+      // test param init
+      try (final UInt64AddOperator uint64AddOperator2 = new UInt64AddOperator();
+           final Options opt = new Options()
+              .setMergeOperator(uint64AddOperator2);
+           final RocksDB db = RocksDB.open(opt,
+                   dbFolder.getRoot().getAbsolutePath())) {
+        //no-op
+      }
+
+      // test replace one with another merge operator instance
+      try (final Options opt = new Options()
+              .setMergeOperator(uint64AddOperator);
+           final UInt64AddOperator newUInt64AddOperator = new UInt64AddOperator()) {
+        opt.setMergeOperator(newUInt64AddOperator);
+        try (final RocksDB db = RocksDB.open(opt,
+                dbFolder.getRoot().getAbsolutePath())) {
+          //no-op
+        }
+      }
+    }
+  }
+
   @Test
   public void emptyStringInSetMergeOperatorByName() {
     try (final Options opt = new Options()
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/MixedOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MixedOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/MixedOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MixedOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/MutableColumnFamilyOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MutableColumnFamilyOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/MutableColumnFamilyOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/MutableColumnFamilyOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/NativeComparatorWrapperTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/NativeComparatorWrapperTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/NativeComparatorWrapperTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/NativeComparatorWrapperTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/NativeLibraryLoaderTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/NativeLibraryLoaderTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/NativeLibraryLoaderTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/NativeLibraryLoaderTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptimisticTransactionDBTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptimisticTransactionDBTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptimisticTransactionDBTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptimisticTransactionDBTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptimisticTransactionOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptimisticTransactionOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptimisticTransactionOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptimisticTransactionOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptimisticTransactionTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptimisticTransactionTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptimisticTransactionTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptimisticTransactionTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptionsTest.java
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptionsTest.java
index 7f7679d732..2571c3e26f 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptionsTest.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptionsTest.java
@@ -645,6 +645,26 @@ public class OptionsTest {
     }
   }
 
+  @Test
+  public void setWriteBufferManager() throws RocksDBException {
+    try (final Options opt = new Options();
+         final Cache cache = new LRUCache(1 * 1024 * 1024);
+         final WriteBufferManager writeBufferManager = new WriteBufferManager(2000l, cache)) {
+      opt.setWriteBufferManager(writeBufferManager);
+      assertThat(opt.writeBufferManager()).isEqualTo(writeBufferManager);
+    }
+  }
+
+  @Test
+  public void setWriteBufferManagerWithZeroBufferSize() throws RocksDBException {
+    try (final Options opt = new Options();
+         final Cache cache = new LRUCache(1 * 1024 * 1024);
+         final WriteBufferManager writeBufferManager = new WriteBufferManager(0l, cache)) {
+      opt.setWriteBufferManager(writeBufferManager);
+      assertThat(opt.writeBufferManager()).isEqualTo(writeBufferManager);
+    }
+  }
+
   @Test
   public void accessHintOnCompactionStart() {
     try (final Options opt = new Options()) {
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptionsUtilTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptionsUtilTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/OptionsUtilTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/OptionsUtilTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/PlainTableConfigTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/PlainTableConfigTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/PlainTableConfigTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/PlainTableConfigTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/PlatformRandomHelper.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/PlatformRandomHelper.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/PlatformRandomHelper.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/PlatformRandomHelper.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RateLimiterTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RateLimiterTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RateLimiterTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RateLimiterTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ReadOnlyTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ReadOnlyTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ReadOnlyTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ReadOnlyTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ReadOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ReadOptionsTest.java
similarity index 86%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ReadOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ReadOptionsTest.java
index f7d799909d..4e860ae4cc 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/ReadOptionsTest.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/ReadOptionsTest.java
@@ -144,16 +144,34 @@ public class ReadOptionsTest {
     }
   }
 
+  @Test
+  public void iterateLowerBound() {
+    try (final ReadOptions opt = new ReadOptions()) {
+      Slice lowerBound = buildRandomSlice();
+      opt.setIterateLowerBound(lowerBound);
+      assertThat(Arrays.equals(lowerBound.data(), opt.iterateLowerBound().data())).isTrue();
+    }
+  }
+
+  @Test
+  public void iterateLowerBoundNull() {
+    try (final ReadOptions opt = new ReadOptions()) {
+      assertThat(opt.iterateLowerBound()).isNull();
+    }
+  }
+
   @Test
   public void copyConstructor() {
     try (final ReadOptions opt = new ReadOptions()) {
       opt.setVerifyChecksums(false);
       opt.setFillCache(false);
       opt.setIterateUpperBound(buildRandomSlice());
+      opt.setIterateLowerBound(buildRandomSlice());
       ReadOptions other = new ReadOptions(opt);
       assertThat(opt.verifyChecksums()).isEqualTo(other.verifyChecksums());
       assertThat(opt.fillCache()).isEqualTo(other.fillCache());
       assertThat(Arrays.equals(opt.iterateUpperBound().data(), other.iterateUpperBound().data())).isTrue();
+      assertThat(Arrays.equals(opt.iterateLowerBound().data(), other.iterateLowerBound().data())).isTrue();
     }
   }
 
@@ -237,6 +255,22 @@ public class ReadOptionsTest {
     }
   }
 
+  @Test
+  public void failSetIterateLowerBoundUninitialized() {
+    try (final ReadOptions readOptions =
+             setupUninitializedReadOptions(exception)) {
+      readOptions.setIterateLowerBound(null);
+    }
+  }
+
+  @Test
+  public void failIterateLowerBoundUninitialized() {
+    try (final ReadOptions readOptions =
+             setupUninitializedReadOptions(exception)) {
+      readOptions.iterateLowerBound();
+    }
+  }
+
   private ReadOptions setupUninitializedReadOptions(
       ExpectedException exception) {
     final ReadOptions readOptions = new ReadOptions();
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksDBExceptionTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksDBExceptionTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksDBExceptionTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksDBExceptionTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksDBTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksDBTest.java
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksDBTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksDBTest.java
index 158b8d56a8..66ebc69db8 100644
--- a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksDBTest.java
+++ b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksDBTest.java
@@ -4,6 +4,7 @@
 //  (found in the LICENSE.Apache file in the root directory).
 package org.rocksdb;
 
+import org.junit.Assert;
 import org.junit.Assume;
 import org.junit.ClassRule;
 import org.junit.Rule;
@@ -11,6 +12,7 @@ import org.junit.Test;
 import org.junit.rules.ExpectedException;
 import org.junit.rules.TemporaryFolder;
 
+import java.nio.ByteBuffer;
 import java.util.*;
 
 import static org.assertj.core.api.Assertions.assertThat;
@@ -70,6 +72,57 @@ public class RocksDBTest {
           "value".getBytes());
       assertThat(db.get("key2".getBytes())).isEqualTo(
           "12345678".getBytes());
+
+
+      // put
+      Segment key3 = sliceSegment("key3");
+      Segment key4 = sliceSegment("key4");
+      Segment value0 = sliceSegment("value 0");
+      Segment value1 = sliceSegment("value 1");
+      db.put(key3.data, key3.offset, key3.len, value0.data, value0.offset, value0.len);
+      db.put(opt, key4.data, key4.offset, key4.len, value1.data, value1.offset, value1.len);
+
+      // compare
+      Assert.assertTrue(value0.isSamePayload(db.get(key3.data, key3.offset, key3.len)));
+      Assert.assertTrue(value1.isSamePayload(db.get(key4.data, key4.offset, key4.len)));
+    }
+  }
+
+  private static Segment sliceSegment(String key) {
+    ByteBuffer rawKey = ByteBuffer.allocate(key.length() + 4);
+    rawKey.put((byte)0);
+    rawKey.put((byte)0);
+    rawKey.put(key.getBytes());
+
+    return new Segment(rawKey.array(), 2, key.length());
+  }
+
+  private static class Segment {
+    final byte[] data;
+    final int offset;
+    final int len;
+
+    public boolean isSamePayload(byte[] value) {
+      if (value == null) {
+        return false;
+      }
+      if (value.length != len) {
+        return false;
+      }
+
+      for (int i = 0; i < value.length; i++) {
+        if (data[i + offset] != value[i]) {
+          return false;
+        }
+      }
+
+      return true;
+    }
+
+    public Segment(byte[] value, int offset, int len) {
+      this.data = value;
+      this.offset = offset;
+      this.len = len;
     }
   }
 
@@ -242,6 +295,18 @@ public class RocksDBTest {
       db.merge(wOpt, "key2".getBytes(), "xxxx".getBytes());
       assertThat(db.get("key2".getBytes())).isEqualTo(
           "xxxx".getBytes());
+
+      Segment key3 = sliceSegment("key3");
+      Segment key4 = sliceSegment("key4");
+      Segment value0 = sliceSegment("value 0");
+      Segment value1 = sliceSegment("value 1");
+
+      db.merge(key3.data, key3.offset, key3.len, value0.data, value0.offset, value0.len);
+      db.merge(wOpt, key4.data, key4.offset, key4.len, value1.data, value1.offset, value1.len);
+
+      // compare
+      Assert.assertTrue(value0.isSamePayload(db.get(key3.data, key3.offset, key3.len)));
+      Assert.assertTrue(value1.isSamePayload(db.get(key4.data, key4.offset, key4.len)));
     }
   }
 
@@ -259,6 +324,18 @@ public class RocksDBTest {
       db.delete(wOpt, "key2".getBytes());
       assertThat(db.get("key1".getBytes())).isNull();
       assertThat(db.get("key2".getBytes())).isNull();
+
+
+      Segment key3 = sliceSegment("key3");
+      Segment key4 = sliceSegment("key4");
+      db.put("key3".getBytes(), "key3 value".getBytes());
+      db.put("key4".getBytes(), "key4 value".getBytes());
+
+      db.delete(key3.data, key3.offset, key3.len);
+      db.delete(wOpt, key4.data, key4.offset, key4.len);
+
+      assertThat(db.get("key3".getBytes())).isNull();
+      assertThat(db.get("key4".getBytes())).isNull();
     }
   }
 
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksEnvTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksEnvTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksEnvTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksEnvTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksIteratorTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksIteratorTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksIteratorTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksIteratorTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksMemEnvTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksMemEnvTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksMemEnvTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksMemEnvTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksMemoryResource.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksMemoryResource.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/RocksMemoryResource.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/RocksMemoryResource.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/SliceTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/SliceTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/SliceTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/SliceTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/SnapshotTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/SnapshotTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/SnapshotTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/SnapshotTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/SstFileManagerTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/SstFileManagerTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/SstFileManagerTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/SstFileManagerTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/SstFileWriterTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/SstFileWriterTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/SstFileWriterTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/SstFileWriterTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/StatisticsCollectorTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/StatisticsCollectorTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/StatisticsCollectorTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/StatisticsCollectorTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/StatisticsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/StatisticsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/StatisticsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/StatisticsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/StatsCallbackMock.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/StatsCallbackMock.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/StatsCallbackMock.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/StatsCallbackMock.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TransactionDBOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TransactionDBOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TransactionDBOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TransactionDBOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TransactionDBTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TransactionDBTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TransactionDBTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TransactionDBTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TransactionLogIteratorTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TransactionLogIteratorTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TransactionLogIteratorTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TransactionLogIteratorTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TransactionOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TransactionOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TransactionOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TransactionOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TransactionTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TransactionTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TransactionTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TransactionTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TtlDBTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TtlDBTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/TtlDBTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/TtlDBTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/Types.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/Types.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/Types.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/Types.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WALRecoveryModeTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WALRecoveryModeTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WALRecoveryModeTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WALRecoveryModeTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WriteBatchHandlerTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WriteBatchHandlerTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WriteBatchHandlerTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WriteBatchHandlerTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WriteBatchTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WriteBatchTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WriteBatchTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WriteBatchTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WriteBatchThreadedTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WriteBatchThreadedTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WriteBatchThreadedTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WriteBatchThreadedTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WriteBatchWithIndexTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WriteBatchWithIndexTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WriteBatchWithIndexTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WriteBatchWithIndexTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WriteOptionsTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WriteOptionsTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/WriteOptionsTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/WriteOptionsTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/test/RocksJunitRunner.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/test/RocksJunitRunner.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/test/RocksJunitRunner.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/test/RocksJunitRunner.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/util/BytewiseComparatorTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/util/BytewiseComparatorTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/util/BytewiseComparatorTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/util/BytewiseComparatorTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/util/CapturingWriteBatchHandler.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/util/CapturingWriteBatchHandler.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/util/CapturingWriteBatchHandler.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/util/CapturingWriteBatchHandler.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/util/EnvironmentTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/util/EnvironmentTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/util/EnvironmentTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/util/EnvironmentTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/util/SizeUnitTest.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/util/SizeUnitTest.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/util/SizeUnitTest.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/util/SizeUnitTest.java
diff --git a/3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/util/WriteBatchGetter.java b/3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/util/WriteBatchGetter.java
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/java/src/test/java/org/rocksdb/util/WriteBatchGetter.java
rename to 3rdParty/rocksdb/v5.18.X/java/src/test/java/org/rocksdb/util/WriteBatchGetter.java
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/alloc_tracker.cc b/3rdParty/rocksdb/v5.18.X/memtable/alloc_tracker.cc
similarity index 86%
rename from 3rdParty/rocksdb/v5.16.X/memtable/alloc_tracker.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/alloc_tracker.cc
index 9889cc4230..a1fa4938c5 100644
--- a/3rdParty/rocksdb/v5.16.X/memtable/alloc_tracker.cc
+++ b/3rdParty/rocksdb/v5.18.X/memtable/alloc_tracker.cc
@@ -24,7 +24,8 @@ AllocTracker::~AllocTracker() { FreeMem(); }
 
 void AllocTracker::Allocate(size_t bytes) {
   assert(write_buffer_manager_ != nullptr);
-  if (write_buffer_manager_->enabled()) {
+  if (write_buffer_manager_->enabled() ||
+      write_buffer_manager_->cost_to_cache()) {
     bytes_allocated_.fetch_add(bytes, std::memory_order_relaxed);
     write_buffer_manager_->ReserveMem(bytes);
   }
@@ -32,7 +33,8 @@ void AllocTracker::Allocate(size_t bytes) {
 
 void AllocTracker::DoneAllocating() {
   if (write_buffer_manager_ != nullptr && !done_allocating_) {
-    if (write_buffer_manager_->enabled()) {
+    if (write_buffer_manager_->enabled() ||
+        write_buffer_manager_->cost_to_cache()) {
       write_buffer_manager_->ScheduleFreeMem(
           bytes_allocated_.load(std::memory_order_relaxed));
     } else {
@@ -47,7 +49,8 @@ void AllocTracker::FreeMem() {
     DoneAllocating();
   }
   if (write_buffer_manager_ != nullptr && !freed_) {
-    if (write_buffer_manager_->enabled()) {
+    if (write_buffer_manager_->enabled() ||
+        write_buffer_manager_->cost_to_cache()) {
       write_buffer_manager_->FreeMem(
           bytes_allocated_.load(std::memory_order_relaxed));
     } else {
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/hash_cuckoo_rep.cc b/3rdParty/rocksdb/v5.18.X/memtable/hash_cuckoo_rep.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/memtable/hash_cuckoo_rep.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/hash_cuckoo_rep.cc
index 39078633f6..aa6e3dbf3b 100644
--- a/3rdParty/rocksdb/v5.16.X/memtable/hash_cuckoo_rep.cc
+++ b/3rdParty/rocksdb/v5.18.X/memtable/hash_cuckoo_rep.cc
@@ -408,6 +408,7 @@ bool HashCuckooRep::QuickInsert(const char* internal_key, const Slice& user_key,
       const auto bucket_user_key = UserKey(stored_key);
       if (bucket_user_key.compare(user_key) == 0) {
         cuckoo_bucket_id = bucket_ids[hid];
+        assert(cuckoo_bucket_id != -1);
         break;
       }
     }
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/hash_cuckoo_rep.h b/3rdParty/rocksdb/v5.18.X/memtable/hash_cuckoo_rep.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/hash_cuckoo_rep.h
rename to 3rdParty/rocksdb/v5.18.X/memtable/hash_cuckoo_rep.h
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/hash_linklist_rep.cc b/3rdParty/rocksdb/v5.18.X/memtable/hash_linklist_rep.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/hash_linklist_rep.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/hash_linklist_rep.cc
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/hash_linklist_rep.h b/3rdParty/rocksdb/v5.18.X/memtable/hash_linklist_rep.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/hash_linklist_rep.h
rename to 3rdParty/rocksdb/v5.18.X/memtable/hash_linklist_rep.h
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/hash_skiplist_rep.cc b/3rdParty/rocksdb/v5.18.X/memtable/hash_skiplist_rep.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/memtable/hash_skiplist_rep.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/hash_skiplist_rep.cc
index 93082b1ec2..a5c46011e3 100644
--- a/3rdParty/rocksdb/v5.16.X/memtable/hash_skiplist_rep.cc
+++ b/3rdParty/rocksdb/v5.18.X/memtable/hash_skiplist_rep.cc
@@ -168,7 +168,7 @@ class HashSkipListRep : public MemTableRep {
     Bucket* list_;
     Bucket::Iterator iter_;
     // here we track if we own list_. If we own it, we are also
-    // responsible for it's cleaning. This is a poor man's shared_ptr
+    // responsible for it's cleaning. This is a poor man's std::shared_ptr
     bool own_list_;
     std::unique_ptr<Arena> arena_;
     std::string tmp_;       // For passing to EncodeKey
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/hash_skiplist_rep.h b/3rdParty/rocksdb/v5.18.X/memtable/hash_skiplist_rep.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/hash_skiplist_rep.h
rename to 3rdParty/rocksdb/v5.18.X/memtable/hash_skiplist_rep.h
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/inlineskiplist.h b/3rdParty/rocksdb/v5.18.X/memtable/inlineskiplist.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/inlineskiplist.h
rename to 3rdParty/rocksdb/v5.18.X/memtable/inlineskiplist.h
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/inlineskiplist_test.cc b/3rdParty/rocksdb/v5.18.X/memtable/inlineskiplist_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/inlineskiplist_test.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/inlineskiplist_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/memtablerep_bench.cc b/3rdParty/rocksdb/v5.18.X/memtable/memtablerep_bench.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/memtablerep_bench.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/memtablerep_bench.cc
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/skiplist.h b/3rdParty/rocksdb/v5.18.X/memtable/skiplist.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/skiplist.h
rename to 3rdParty/rocksdb/v5.18.X/memtable/skiplist.h
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/skiplist_test.cc b/3rdParty/rocksdb/v5.18.X/memtable/skiplist_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/skiplist_test.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/skiplist_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/skiplistrep.cc b/3rdParty/rocksdb/v5.18.X/memtable/skiplistrep.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/skiplistrep.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/skiplistrep.cc
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/stl_wrappers.h b/3rdParty/rocksdb/v5.18.X/memtable/stl_wrappers.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/stl_wrappers.h
rename to 3rdParty/rocksdb/v5.18.X/memtable/stl_wrappers.h
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/vectorrep.cc b/3rdParty/rocksdb/v5.18.X/memtable/vectorrep.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/vectorrep.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/vectorrep.cc
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/write_buffer_manager.cc b/3rdParty/rocksdb/v5.18.X/memtable/write_buffer_manager.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/memtable/write_buffer_manager.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/write_buffer_manager.cc
index 21b18c8f76..7f2e664ab5 100644
--- a/3rdParty/rocksdb/v5.16.X/memtable/write_buffer_manager.cc
+++ b/3rdParty/rocksdb/v5.18.X/memtable/write_buffer_manager.cc
@@ -79,7 +79,7 @@ WriteBufferManager::~WriteBufferManager() {
 void WriteBufferManager::ReserveMemWithCache(size_t mem) {
 #ifndef ROCKSDB_LITE
   assert(cache_rep_ != nullptr);
-  // Use a mutex to protect various data structures. Can be optimzied to a
+  // Use a mutex to protect various data structures. Can be optimized to a
   // lock-free solution if it ends up with a performance bottleneck.
   std::lock_guard<std::mutex> lock(cache_rep_->cache_mutex_);
 
@@ -102,14 +102,14 @@ void WriteBufferManager::ReserveMemWithCache(size_t mem) {
 void WriteBufferManager::FreeMemWithCache(size_t mem) {
 #ifndef ROCKSDB_LITE
   assert(cache_rep_ != nullptr);
-  // Use a mutex to protect various data structures. Can be optimzied to a
+  // Use a mutex to protect various data structures. Can be optimized to a
   // lock-free solution if it ends up with a performance bottleneck.
   std::lock_guard<std::mutex> lock(cache_rep_->cache_mutex_);
   size_t new_mem_used = memory_used_.load(std::memory_order_relaxed) - mem;
   memory_used_.store(new_mem_used, std::memory_order_relaxed);
   // Gradually shrink memory costed in the block cache if the actual
   // usage is less than 3/4 of what we reserve from the block cache.
-  // We do this becausse:
+  // We do this because:
   // 1. we don't pay the cost of the block cache immediately a memtable is
   //    freed, as block cache insert is expensive;
   // 2. eventually, if we walk away from a temporary memtable size increase,
diff --git a/3rdParty/rocksdb/v5.16.X/memtable/write_buffer_manager_test.cc b/3rdParty/rocksdb/v5.18.X/memtable/write_buffer_manager_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/memtable/write_buffer_manager_test.cc
rename to 3rdParty/rocksdb/v5.18.X/memtable/write_buffer_manager_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/file_read_sample.h b/3rdParty/rocksdb/v5.18.X/monitoring/file_read_sample.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/file_read_sample.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/file_read_sample.h
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/histogram.cc b/3rdParty/rocksdb/v5.18.X/monitoring/histogram.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/histogram.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/histogram.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/histogram.h b/3rdParty/rocksdb/v5.18.X/monitoring/histogram.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/histogram.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/histogram.h
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/histogram_test.cc b/3rdParty/rocksdb/v5.18.X/monitoring/histogram_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/histogram_test.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/histogram_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/histogram_windowing.cc b/3rdParty/rocksdb/v5.18.X/monitoring/histogram_windowing.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/histogram_windowing.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/histogram_windowing.cc
index 5c49fcd16b..ecd6f090a5 100644
--- a/3rdParty/rocksdb/v5.16.X/monitoring/histogram_windowing.cc
+++ b/3rdParty/rocksdb/v5.18.X/monitoring/histogram_windowing.cc
@@ -17,7 +17,7 @@ namespace rocksdb {
 
 HistogramWindowingImpl::HistogramWindowingImpl() {
   env_ = Env::Default();
-  window_stats_.reset(new HistogramStat[num_windows_]);
+  window_stats_.reset(new HistogramStat[static_cast<size_t>(num_windows_)]);
   Clear();
 }
 
@@ -29,7 +29,7 @@ HistogramWindowingImpl::HistogramWindowingImpl(
       micros_per_window_(micros_per_window),
       min_num_per_window_(min_num_per_window) {
   env_ = Env::Default();
-  window_stats_.reset(new HistogramStat[num_windows_]);
+  window_stats_.reset(new HistogramStat[static_cast<size_t>(num_windows_)]);
   Clear();
 }
 
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/histogram_windowing.h b/3rdParty/rocksdb/v5.18.X/monitoring/histogram_windowing.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/histogram_windowing.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/histogram_windowing.h
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/instrumented_mutex.cc b/3rdParty/rocksdb/v5.18.X/monitoring/instrumented_mutex.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/instrumented_mutex.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/instrumented_mutex.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/instrumented_mutex.h b/3rdParty/rocksdb/v5.18.X/monitoring/instrumented_mutex.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/instrumented_mutex.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/instrumented_mutex.h
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/iostats_context.cc b/3rdParty/rocksdb/v5.18.X/monitoring/iostats_context.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/iostats_context.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/iostats_context.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/iostats_context_imp.h b/3rdParty/rocksdb/v5.18.X/monitoring/iostats_context_imp.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/iostats_context_imp.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/iostats_context_imp.h
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/iostats_context_test.cc b/3rdParty/rocksdb/v5.18.X/monitoring/iostats_context_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/iostats_context_test.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/iostats_context_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/perf_context.cc b/3rdParty/rocksdb/v5.18.X/monitoring/perf_context.cc
similarity index 78%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/perf_context.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/perf_context.cc
index 9bba841f8f..423443869b 100644
--- a/3rdParty/rocksdb/v5.16.X/monitoring/perf_context.cc
+++ b/3rdParty/rocksdb/v5.18.X/monitoring/perf_context.cc
@@ -15,7 +15,7 @@ PerfContext perf_context;
 #if defined(OS_SOLARIS)
 __thread PerfContext perf_context_;
 #else
-__thread PerfContext perf_context;
+thread_local PerfContext perf_context;
 #endif
 #endif
 
@@ -31,6 +31,12 @@ PerfContext* get_perf_context() {
 #endif
 }
 
+PerfContext::~PerfContext() {
+#if !defined(NPERF_CONTEXT) && defined(ROCKSDB_SUPPORT_THREAD_LOCAL) && !defined(OS_SOLARIS)
+  ClearPerLevelPerfContext();
+#endif
+}
+
 void PerfContext::Reset() {
 #ifndef NPERF_CONTEXT
   user_key_comparison_count = 0;
@@ -104,6 +110,11 @@ void PerfContext::Reset() {
   env_lock_file_nanos = 0;
   env_unlock_file_nanos = 0;
   env_new_logger_nanos = 0;
+  if (per_level_perf_context_enabled && level_to_perf_context) {
+    for (auto& kv : *level_to_perf_context) {
+      kv.second.Reset();
+    }
+  }
 #endif
 }
 
@@ -112,6 +123,25 @@ void PerfContext::Reset() {
     ss << #counter << " = " << counter << ", ";  \
   }
 
+#define PERF_CONTEXT_BY_LEVEL_OUTPUT_ONE_COUNTER(counter)         \
+  if (per_level_perf_context_enabled && \
+      level_to_perf_context) {                                    \
+    ss << #counter << " = ";                                      \
+    for (auto& kv : *level_to_perf_context) {                     \
+      if (!exclude_zero_counters || (kv.second.counter > 0)) {    \
+        ss << kv.second.counter << "@level" << kv.first << ", ";  \
+      }                                                           \
+    }                                                             \
+  }
+
+void PerfContextByLevel::Reset() {
+#ifndef NPERF_CONTEXT
+  bloom_filter_useful = 0;
+  bloom_filter_full_positive = 0;
+  bloom_filter_full_true_positive = 0;
+#endif
+}
+
 std::string PerfContext::ToString(bool exclude_zero_counters) const {
 #ifdef NPERF_CONTEXT
   return "";
@@ -186,8 +216,30 @@ std::string PerfContext::ToString(bool exclude_zero_counters) const {
   PERF_CONTEXT_OUTPUT(env_lock_file_nanos);
   PERF_CONTEXT_OUTPUT(env_unlock_file_nanos);
   PERF_CONTEXT_OUTPUT(env_new_logger_nanos);
+  PERF_CONTEXT_BY_LEVEL_OUTPUT_ONE_COUNTER(bloom_filter_useful);
+  PERF_CONTEXT_BY_LEVEL_OUTPUT_ONE_COUNTER(bloom_filter_full_positive);
+  PERF_CONTEXT_BY_LEVEL_OUTPUT_ONE_COUNTER(bloom_filter_full_true_positive);
   return ss.str();
 #endif
 }
 
+void PerfContext::EnablePerLevelPerfContext() {
+  if (!level_to_perf_context) {
+    level_to_perf_context = new std::map<uint32_t, PerfContextByLevel>();
+  }
+  per_level_perf_context_enabled = true;
+}
+
+void PerfContext::DisablePerLevelPerfContext(){
+  per_level_perf_context_enabled = false;
+}
+
+void PerfContext::ClearPerLevelPerfContext(){
+  if (level_to_perf_context) {
+    delete level_to_perf_context;
+    level_to_perf_context = nullptr;
+  }
+  per_level_perf_context_enabled = false;
+}
+
 }
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/perf_context_imp.h b/3rdParty/rocksdb/v5.18.X/monitoring/perf_context_imp.h
similarity index 64%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/perf_context_imp.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/perf_context_imp.h
index cfcded1c96..d67654914e 100644
--- a/3rdParty/rocksdb/v5.16.X/monitoring/perf_context_imp.h
+++ b/3rdParty/rocksdb/v5.18.X/monitoring/perf_context_imp.h
@@ -16,7 +16,7 @@ extern PerfContext perf_context;
 extern __thread PerfContext perf_context_;
 #define perf_context (*get_perf_context())
 #else
-extern __thread PerfContext perf_context;
+extern thread_local PerfContext perf_context;
 #endif
 #endif
 
@@ -59,6 +59,22 @@ extern __thread PerfContext perf_context;
     perf_context.metric += value;              \
   }
 
+// Increase metric value
+#define PERF_COUNTER_BY_LEVEL_ADD(metric, value, level)                      \
+  if (perf_level >= PerfLevel::kEnableCount &&                               \
+      perf_context.per_level_perf_context_enabled &&                         \
+      perf_context.level_to_perf_context) {                                  \
+    if ((*(perf_context.level_to_perf_context)).find(level) !=               \
+        (*(perf_context.level_to_perf_context)).end()) {                     \
+      (*(perf_context.level_to_perf_context))[level].metric += value;        \
+    }                                                                        \
+    else {                                                                   \
+      PerfContextByLevel empty_context;                                      \
+      (*(perf_context.level_to_perf_context))[level] = empty_context;        \
+      (*(perf_context.level_to_perf_context))[level].metric += value;       \
+    }                                                                        \
+  }                                                                          \
+
 #endif
 
 }
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/perf_level.cc b/3rdParty/rocksdb/v5.18.X/monitoring/perf_level.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/perf_level.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/perf_level.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/perf_level_imp.h b/3rdParty/rocksdb/v5.18.X/monitoring/perf_level_imp.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/perf_level_imp.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/perf_level_imp.h
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/perf_step_timer.h b/3rdParty/rocksdb/v5.18.X/monitoring/perf_step_timer.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/perf_step_timer.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/perf_step_timer.h
diff --git a/3rdParty/rocksdb/v5.18.X/monitoring/statistics.cc b/3rdParty/rocksdb/v5.18.X/monitoring/statistics.cc
new file mode 100644
index 0000000000..cba427ae4b
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/monitoring/statistics.cc
@@ -0,0 +1,379 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+#include "monitoring/statistics.h"
+
+#ifndef __STDC_FORMAT_MACROS
+#define __STDC_FORMAT_MACROS
+#endif
+
+#include <inttypes.h>
+#include "rocksdb/statistics.h"
+#include "port/likely.h"
+#include <algorithm>
+#include <cstdio>
+
+namespace rocksdb {
+
+// The order of items listed in  Tickers should be the same as
+// the order listed in TickersNameMap
+const std::vector<std::pair<Tickers, std::string>> TickersNameMap = {
+    {BLOCK_CACHE_MISS, "rocksdb.block.cache.miss"},
+    {BLOCK_CACHE_HIT, "rocksdb.block.cache.hit"},
+    {BLOCK_CACHE_ADD, "rocksdb.block.cache.add"},
+    {BLOCK_CACHE_ADD_FAILURES, "rocksdb.block.cache.add.failures"},
+    {BLOCK_CACHE_INDEX_MISS, "rocksdb.block.cache.index.miss"},
+    {BLOCK_CACHE_INDEX_HIT, "rocksdb.block.cache.index.hit"},
+    {BLOCK_CACHE_INDEX_ADD, "rocksdb.block.cache.index.add"},
+    {BLOCK_CACHE_INDEX_BYTES_INSERT, "rocksdb.block.cache.index.bytes.insert"},
+    {BLOCK_CACHE_INDEX_BYTES_EVICT, "rocksdb.block.cache.index.bytes.evict"},
+    {BLOCK_CACHE_FILTER_MISS, "rocksdb.block.cache.filter.miss"},
+    {BLOCK_CACHE_FILTER_HIT, "rocksdb.block.cache.filter.hit"},
+    {BLOCK_CACHE_FILTER_ADD, "rocksdb.block.cache.filter.add"},
+    {BLOCK_CACHE_FILTER_BYTES_INSERT,
+     "rocksdb.block.cache.filter.bytes.insert"},
+    {BLOCK_CACHE_FILTER_BYTES_EVICT, "rocksdb.block.cache.filter.bytes.evict"},
+    {BLOCK_CACHE_DATA_MISS, "rocksdb.block.cache.data.miss"},
+    {BLOCK_CACHE_DATA_HIT, "rocksdb.block.cache.data.hit"},
+    {BLOCK_CACHE_DATA_ADD, "rocksdb.block.cache.data.add"},
+    {BLOCK_CACHE_DATA_BYTES_INSERT, "rocksdb.block.cache.data.bytes.insert"},
+    {BLOCK_CACHE_BYTES_READ, "rocksdb.block.cache.bytes.read"},
+    {BLOCK_CACHE_BYTES_WRITE, "rocksdb.block.cache.bytes.write"},
+    {BLOOM_FILTER_USEFUL, "rocksdb.bloom.filter.useful"},
+    {BLOOM_FILTER_FULL_POSITIVE, "rocksdb.bloom.filter.full.positive"},
+    {BLOOM_FILTER_FULL_TRUE_POSITIVE,
+     "rocksdb.bloom.filter.full.true.positive"},
+    {PERSISTENT_CACHE_HIT, "rocksdb.persistent.cache.hit"},
+    {PERSISTENT_CACHE_MISS, "rocksdb.persistent.cache.miss"},
+    {SIM_BLOCK_CACHE_HIT, "rocksdb.sim.block.cache.hit"},
+    {SIM_BLOCK_CACHE_MISS, "rocksdb.sim.block.cache.miss"},
+    {MEMTABLE_HIT, "rocksdb.memtable.hit"},
+    {MEMTABLE_MISS, "rocksdb.memtable.miss"},
+    {GET_HIT_L0, "rocksdb.l0.hit"},
+    {GET_HIT_L1, "rocksdb.l1.hit"},
+    {GET_HIT_L2_AND_UP, "rocksdb.l2andup.hit"},
+    {COMPACTION_KEY_DROP_NEWER_ENTRY, "rocksdb.compaction.key.drop.new"},
+    {COMPACTION_KEY_DROP_OBSOLETE, "rocksdb.compaction.key.drop.obsolete"},
+    {COMPACTION_KEY_DROP_RANGE_DEL, "rocksdb.compaction.key.drop.range_del"},
+    {COMPACTION_KEY_DROP_USER, "rocksdb.compaction.key.drop.user"},
+    {COMPACTION_RANGE_DEL_DROP_OBSOLETE,
+     "rocksdb.compaction.range_del.drop.obsolete"},
+    {COMPACTION_OPTIMIZED_DEL_DROP_OBSOLETE,
+     "rocksdb.compaction.optimized.del.drop.obsolete"},
+    {COMPACTION_CANCELLED, "rocksdb.compaction.cancelled"},
+    {NUMBER_KEYS_WRITTEN, "rocksdb.number.keys.written"},
+    {NUMBER_KEYS_READ, "rocksdb.number.keys.read"},
+    {NUMBER_KEYS_UPDATED, "rocksdb.number.keys.updated"},
+    {BYTES_WRITTEN, "rocksdb.bytes.written"},
+    {BYTES_READ, "rocksdb.bytes.read"},
+    {NUMBER_DB_SEEK, "rocksdb.number.db.seek"},
+    {NUMBER_DB_NEXT, "rocksdb.number.db.next"},
+    {NUMBER_DB_PREV, "rocksdb.number.db.prev"},
+    {NUMBER_DB_SEEK_FOUND, "rocksdb.number.db.seek.found"},
+    {NUMBER_DB_NEXT_FOUND, "rocksdb.number.db.next.found"},
+    {NUMBER_DB_PREV_FOUND, "rocksdb.number.db.prev.found"},
+    {ITER_BYTES_READ, "rocksdb.db.iter.bytes.read"},
+    {NO_FILE_CLOSES, "rocksdb.no.file.closes"},
+    {NO_FILE_OPENS, "rocksdb.no.file.opens"},
+    {NO_FILE_ERRORS, "rocksdb.no.file.errors"},
+    {STALL_L0_SLOWDOWN_MICROS, "rocksdb.l0.slowdown.micros"},
+    {STALL_MEMTABLE_COMPACTION_MICROS, "rocksdb.memtable.compaction.micros"},
+    {STALL_L0_NUM_FILES_MICROS, "rocksdb.l0.num.files.stall.micros"},
+    {STALL_MICROS, "rocksdb.stall.micros"},
+    {DB_MUTEX_WAIT_MICROS, "rocksdb.db.mutex.wait.micros"},
+    {RATE_LIMIT_DELAY_MILLIS, "rocksdb.rate.limit.delay.millis"},
+    {NO_ITERATORS, "rocksdb.num.iterators"},
+    {NUMBER_MULTIGET_CALLS, "rocksdb.number.multiget.get"},
+    {NUMBER_MULTIGET_KEYS_READ, "rocksdb.number.multiget.keys.read"},
+    {NUMBER_MULTIGET_BYTES_READ, "rocksdb.number.multiget.bytes.read"},
+    {NUMBER_FILTERED_DELETES, "rocksdb.number.deletes.filtered"},
+    {NUMBER_MERGE_FAILURES, "rocksdb.number.merge.failures"},
+    {BLOOM_FILTER_PREFIX_CHECKED, "rocksdb.bloom.filter.prefix.checked"},
+    {BLOOM_FILTER_PREFIX_USEFUL, "rocksdb.bloom.filter.prefix.useful"},
+    {NUMBER_OF_RESEEKS_IN_ITERATION, "rocksdb.number.reseeks.iteration"},
+    {GET_UPDATES_SINCE_CALLS, "rocksdb.getupdatessince.calls"},
+    {BLOCK_CACHE_COMPRESSED_MISS, "rocksdb.block.cachecompressed.miss"},
+    {BLOCK_CACHE_COMPRESSED_HIT, "rocksdb.block.cachecompressed.hit"},
+    {BLOCK_CACHE_COMPRESSED_ADD, "rocksdb.block.cachecompressed.add"},
+    {BLOCK_CACHE_COMPRESSED_ADD_FAILURES,
+     "rocksdb.block.cachecompressed.add.failures"},
+    {WAL_FILE_SYNCED, "rocksdb.wal.synced"},
+    {WAL_FILE_BYTES, "rocksdb.wal.bytes"},
+    {WRITE_DONE_BY_SELF, "rocksdb.write.self"},
+    {WRITE_DONE_BY_OTHER, "rocksdb.write.other"},
+    {WRITE_TIMEDOUT, "rocksdb.write.timeout"},
+    {WRITE_WITH_WAL, "rocksdb.write.wal"},
+    {COMPACT_READ_BYTES, "rocksdb.compact.read.bytes"},
+    {COMPACT_WRITE_BYTES, "rocksdb.compact.write.bytes"},
+    {FLUSH_WRITE_BYTES, "rocksdb.flush.write.bytes"},
+    {NUMBER_DIRECT_LOAD_TABLE_PROPERTIES,
+     "rocksdb.number.direct.load.table.properties"},
+    {NUMBER_SUPERVERSION_ACQUIRES, "rocksdb.number.superversion_acquires"},
+    {NUMBER_SUPERVERSION_RELEASES, "rocksdb.number.superversion_releases"},
+    {NUMBER_SUPERVERSION_CLEANUPS, "rocksdb.number.superversion_cleanups"},
+    {NUMBER_BLOCK_COMPRESSED, "rocksdb.number.block.compressed"},
+    {NUMBER_BLOCK_DECOMPRESSED, "rocksdb.number.block.decompressed"},
+    {NUMBER_BLOCK_NOT_COMPRESSED, "rocksdb.number.block.not_compressed"},
+    {MERGE_OPERATION_TOTAL_TIME, "rocksdb.merge.operation.time.nanos"},
+    {FILTER_OPERATION_TOTAL_TIME, "rocksdb.filter.operation.time.nanos"},
+    {ROW_CACHE_HIT, "rocksdb.row.cache.hit"},
+    {ROW_CACHE_MISS, "rocksdb.row.cache.miss"},
+    {READ_AMP_ESTIMATE_USEFUL_BYTES, "rocksdb.read.amp.estimate.useful.bytes"},
+    {READ_AMP_TOTAL_READ_BYTES, "rocksdb.read.amp.total.read.bytes"},
+    {NUMBER_RATE_LIMITER_DRAINS, "rocksdb.number.rate_limiter.drains"},
+    {NUMBER_ITER_SKIP, "rocksdb.number.iter.skip"},
+    {BLOB_DB_NUM_PUT, "rocksdb.blobdb.num.put"},
+    {BLOB_DB_NUM_WRITE, "rocksdb.blobdb.num.write"},
+    {BLOB_DB_NUM_GET, "rocksdb.blobdb.num.get"},
+    {BLOB_DB_NUM_MULTIGET, "rocksdb.blobdb.num.multiget"},
+    {BLOB_DB_NUM_SEEK, "rocksdb.blobdb.num.seek"},
+    {BLOB_DB_NUM_NEXT, "rocksdb.blobdb.num.next"},
+    {BLOB_DB_NUM_PREV, "rocksdb.blobdb.num.prev"},
+    {BLOB_DB_NUM_KEYS_WRITTEN, "rocksdb.blobdb.num.keys.written"},
+    {BLOB_DB_NUM_KEYS_READ, "rocksdb.blobdb.num.keys.read"},
+    {BLOB_DB_BYTES_WRITTEN, "rocksdb.blobdb.bytes.written"},
+    {BLOB_DB_BYTES_READ, "rocksdb.blobdb.bytes.read"},
+    {BLOB_DB_WRITE_INLINED, "rocksdb.blobdb.write.inlined"},
+    {BLOB_DB_WRITE_INLINED_TTL, "rocksdb.blobdb.write.inlined.ttl"},
+    {BLOB_DB_WRITE_BLOB, "rocksdb.blobdb.write.blob"},
+    {BLOB_DB_WRITE_BLOB_TTL, "rocksdb.blobdb.write.blob.ttl"},
+    {BLOB_DB_BLOB_FILE_BYTES_WRITTEN, "rocksdb.blobdb.blob.file.bytes.written"},
+    {BLOB_DB_BLOB_FILE_BYTES_READ, "rocksdb.blobdb.blob.file.bytes.read"},
+    {BLOB_DB_BLOB_FILE_SYNCED, "rocksdb.blobdb.blob.file.synced"},
+    {BLOB_DB_BLOB_INDEX_EXPIRED_COUNT,
+     "rocksdb.blobdb.blob.index.expired.count"},
+    {BLOB_DB_BLOB_INDEX_EXPIRED_SIZE, "rocksdb.blobdb.blob.index.expired.size"},
+    {BLOB_DB_BLOB_INDEX_EVICTED_COUNT,
+     "rocksdb.blobdb.blob.index.evicted.count"},
+    {BLOB_DB_BLOB_INDEX_EVICTED_SIZE, "rocksdb.blobdb.blob.index.evicted.size"},
+    {BLOB_DB_GC_NUM_FILES, "rocksdb.blobdb.gc.num.files"},
+    {BLOB_DB_GC_NUM_NEW_FILES, "rocksdb.blobdb.gc.num.new.files"},
+    {BLOB_DB_GC_FAILURES, "rocksdb.blobdb.gc.failures"},
+    {BLOB_DB_GC_NUM_KEYS_OVERWRITTEN, "rocksdb.blobdb.gc.num.keys.overwritten"},
+    {BLOB_DB_GC_NUM_KEYS_EXPIRED, "rocksdb.blobdb.gc.num.keys.expired"},
+    {BLOB_DB_GC_NUM_KEYS_RELOCATED, "rocksdb.blobdb.gc.num.keys.relocated"},
+    {BLOB_DB_GC_BYTES_OVERWRITTEN, "rocksdb.blobdb.gc.bytes.overwritten"},
+    {BLOB_DB_GC_BYTES_EXPIRED, "rocksdb.blobdb.gc.bytes.expired"},
+    {BLOB_DB_GC_BYTES_RELOCATED, "rocksdb.blobdb.gc.bytes.relocated"},
+    {BLOB_DB_FIFO_NUM_FILES_EVICTED, "rocksdb.blobdb.fifo.num.files.evicted"},
+    {BLOB_DB_FIFO_NUM_KEYS_EVICTED, "rocksdb.blobdb.fifo.num.keys.evicted"},
+    {BLOB_DB_FIFO_BYTES_EVICTED, "rocksdb.blobdb.fifo.bytes.evicted"},
+    {TXN_PREPARE_MUTEX_OVERHEAD, "rocksdb.txn.overhead.mutex.prepare"},
+    {TXN_OLD_COMMIT_MAP_MUTEX_OVERHEAD,
+     "rocksdb.txn.overhead.mutex.old.commit.map"},
+    {TXN_DUPLICATE_KEY_OVERHEAD, "rocksdb.txn.overhead.duplicate.key"},
+    {TXN_SNAPSHOT_MUTEX_OVERHEAD, "rocksdb.txn.overhead.mutex.snapshot"},
+    {NUMBER_MULTIGET_KEYS_FOUND, "rocksdb.number.multiget.keys.found"},
+    {NO_ITERATOR_CREATED, "rocksdb.num.iterator.created"},
+    {NO_ITERATOR_DELETED, "rocksdb.num.iterator.deleted"},
+};
+
+const std::vector<std::pair<Histograms, std::string>> HistogramsNameMap = {
+    {DB_GET, "rocksdb.db.get.micros"},
+    {DB_WRITE, "rocksdb.db.write.micros"},
+    {COMPACTION_TIME, "rocksdb.compaction.times.micros"},
+    {SUBCOMPACTION_SETUP_TIME, "rocksdb.subcompaction.setup.times.micros"},
+    {TABLE_SYNC_MICROS, "rocksdb.table.sync.micros"},
+    {COMPACTION_OUTFILE_SYNC_MICROS, "rocksdb.compaction.outfile.sync.micros"},
+    {WAL_FILE_SYNC_MICROS, "rocksdb.wal.file.sync.micros"},
+    {MANIFEST_FILE_SYNC_MICROS, "rocksdb.manifest.file.sync.micros"},
+    {TABLE_OPEN_IO_MICROS, "rocksdb.table.open.io.micros"},
+    {DB_MULTIGET, "rocksdb.db.multiget.micros"},
+    {READ_BLOCK_COMPACTION_MICROS, "rocksdb.read.block.compaction.micros"},
+    {READ_BLOCK_GET_MICROS, "rocksdb.read.block.get.micros"},
+    {WRITE_RAW_BLOCK_MICROS, "rocksdb.write.raw.block.micros"},
+    {STALL_L0_SLOWDOWN_COUNT, "rocksdb.l0.slowdown.count"},
+    {STALL_MEMTABLE_COMPACTION_COUNT, "rocksdb.memtable.compaction.count"},
+    {STALL_L0_NUM_FILES_COUNT, "rocksdb.num.files.stall.count"},
+    {HARD_RATE_LIMIT_DELAY_COUNT, "rocksdb.hard.rate.limit.delay.count"},
+    {SOFT_RATE_LIMIT_DELAY_COUNT, "rocksdb.soft.rate.limit.delay.count"},
+    {NUM_FILES_IN_SINGLE_COMPACTION, "rocksdb.numfiles.in.singlecompaction"},
+    {DB_SEEK, "rocksdb.db.seek.micros"},
+    {WRITE_STALL, "rocksdb.db.write.stall"},
+    {SST_READ_MICROS, "rocksdb.sst.read.micros"},
+    {NUM_SUBCOMPACTIONS_SCHEDULED, "rocksdb.num.subcompactions.scheduled"},
+    {BYTES_PER_READ, "rocksdb.bytes.per.read"},
+    {BYTES_PER_WRITE, "rocksdb.bytes.per.write"},
+    {BYTES_PER_MULTIGET, "rocksdb.bytes.per.multiget"},
+    {BYTES_COMPRESSED, "rocksdb.bytes.compressed"},
+    {BYTES_DECOMPRESSED, "rocksdb.bytes.decompressed"},
+    {COMPRESSION_TIMES_NANOS, "rocksdb.compression.times.nanos"},
+    {DECOMPRESSION_TIMES_NANOS, "rocksdb.decompression.times.nanos"},
+    {READ_NUM_MERGE_OPERANDS, "rocksdb.read.num.merge_operands"},
+    {BLOB_DB_KEY_SIZE, "rocksdb.blobdb.key.size"},
+    {BLOB_DB_VALUE_SIZE, "rocksdb.blobdb.value.size"},
+    {BLOB_DB_WRITE_MICROS, "rocksdb.blobdb.write.micros"},
+    {BLOB_DB_GET_MICROS, "rocksdb.blobdb.get.micros"},
+    {BLOB_DB_MULTIGET_MICROS, "rocksdb.blobdb.multiget.micros"},
+    {BLOB_DB_SEEK_MICROS, "rocksdb.blobdb.seek.micros"},
+    {BLOB_DB_NEXT_MICROS, "rocksdb.blobdb.next.micros"},
+    {BLOB_DB_PREV_MICROS, "rocksdb.blobdb.prev.micros"},
+    {BLOB_DB_BLOB_FILE_WRITE_MICROS, "rocksdb.blobdb.blob.file.write.micros"},
+    {BLOB_DB_BLOB_FILE_READ_MICROS, "rocksdb.blobdb.blob.file.read.micros"},
+    {BLOB_DB_BLOB_FILE_SYNC_MICROS, "rocksdb.blobdb.blob.file.sync.micros"},
+    {BLOB_DB_GC_MICROS, "rocksdb.blobdb.gc.micros"},
+    {BLOB_DB_COMPRESSION_MICROS, "rocksdb.blobdb.compression.micros"},
+    {BLOB_DB_DECOMPRESSION_MICROS, "rocksdb.blobdb.decompression.micros"},
+    {FLUSH_TIME, "rocksdb.db.flush.micros"},
+};
+
+std::shared_ptr<Statistics> CreateDBStatistics() {
+  return std::make_shared<StatisticsImpl>(nullptr);
+}
+
+StatisticsImpl::StatisticsImpl(std::shared_ptr<Statistics> stats)
+    : stats_(std::move(stats)) {}
+
+StatisticsImpl::~StatisticsImpl() {}
+
+uint64_t StatisticsImpl::getTickerCount(uint32_t tickerType) const {
+  MutexLock lock(&aggregate_lock_);
+  return getTickerCountLocked(tickerType);
+}
+
+uint64_t StatisticsImpl::getTickerCountLocked(uint32_t tickerType) const {
+  assert(tickerType < TICKER_ENUM_MAX);
+  uint64_t res = 0;
+  for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
+    res += per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType];
+  }
+  return res;
+}
+
+void StatisticsImpl::histogramData(uint32_t histogramType,
+                                   HistogramData* const data) const {
+  MutexLock lock(&aggregate_lock_);
+  getHistogramImplLocked(histogramType)->Data(data);
+}
+
+std::unique_ptr<HistogramImpl> StatisticsImpl::getHistogramImplLocked(
+    uint32_t histogramType) const {
+  assert(histogramType < HISTOGRAM_ENUM_MAX);
+  std::unique_ptr<HistogramImpl> res_hist(new HistogramImpl());
+  for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
+    res_hist->Merge(
+        per_core_stats_.AccessAtCore(core_idx)->histograms_[histogramType]);
+  }
+  return res_hist;
+}
+
+std::string StatisticsImpl::getHistogramString(uint32_t histogramType) const {
+  MutexLock lock(&aggregate_lock_);
+  return getHistogramImplLocked(histogramType)->ToString();
+}
+
+void StatisticsImpl::setTickerCount(uint32_t tickerType, uint64_t count) {
+  {
+    MutexLock lock(&aggregate_lock_);
+    setTickerCountLocked(tickerType, count);
+  }
+  if (stats_ && tickerType < TICKER_ENUM_MAX) {
+    stats_->setTickerCount(tickerType, count);
+  }
+}
+
+void StatisticsImpl::setTickerCountLocked(uint32_t tickerType, uint64_t count) {
+  assert(tickerType < TICKER_ENUM_MAX);
+  for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
+    if (core_idx == 0) {
+      per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType] = count;
+    } else {
+      per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType] = 0;
+    }
+  }
+}
+
+uint64_t StatisticsImpl::getAndResetTickerCount(uint32_t tickerType) {
+  uint64_t sum = 0;
+  {
+    MutexLock lock(&aggregate_lock_);
+    assert(tickerType < TICKER_ENUM_MAX);
+    for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
+      sum +=
+          per_core_stats_.AccessAtCore(core_idx)->tickers_[tickerType].exchange(
+              0, std::memory_order_relaxed);
+    }
+  }
+  if (stats_ && tickerType < TICKER_ENUM_MAX) {
+    stats_->setTickerCount(tickerType, 0);
+  }
+  return sum;
+}
+
+void StatisticsImpl::recordTick(uint32_t tickerType, uint64_t count) {
+  assert(tickerType < TICKER_ENUM_MAX);
+  per_core_stats_.Access()->tickers_[tickerType].fetch_add(
+      count, std::memory_order_relaxed);
+  if (stats_ && tickerType < TICKER_ENUM_MAX) {
+    stats_->recordTick(tickerType, count);
+  }
+}
+
+void StatisticsImpl::measureTime(uint32_t histogramType, uint64_t value) {
+  assert(histogramType < HISTOGRAM_ENUM_MAX);
+  per_core_stats_.Access()->histograms_[histogramType].Add(value);
+  if (stats_ && histogramType < HISTOGRAM_ENUM_MAX) {
+    stats_->measureTime(histogramType, value);
+  }
+}
+
+Status StatisticsImpl::Reset() {
+  MutexLock lock(&aggregate_lock_);
+  for (uint32_t i = 0; i < TICKER_ENUM_MAX; ++i) {
+    setTickerCountLocked(i, 0);
+  }
+  for (uint32_t i = 0; i < HISTOGRAM_ENUM_MAX; ++i) {
+    for (size_t core_idx = 0; core_idx < per_core_stats_.Size(); ++core_idx) {
+      per_core_stats_.AccessAtCore(core_idx)->histograms_[i].Clear();
+    }
+  }
+  return Status::OK();
+}
+
+namespace {
+
+// a buffer size used for temp string buffers
+const int kTmpStrBufferSize = 200;
+
+} // namespace
+
+std::string StatisticsImpl::ToString() const {
+  MutexLock lock(&aggregate_lock_);
+  std::string res;
+  res.reserve(20000);
+  for (const auto& t : TickersNameMap) {
+    assert(t.first < TICKER_ENUM_MAX);
+    char buffer[kTmpStrBufferSize];
+    snprintf(buffer, kTmpStrBufferSize, "%s COUNT : %" PRIu64 "\n",
+             t.second.c_str(), getTickerCountLocked(t.first));
+    res.append(buffer);
+  }
+  for (const auto& h : HistogramsNameMap) {
+    assert(h.first < HISTOGRAM_ENUM_MAX);
+    char buffer[kTmpStrBufferSize];
+    HistogramData hData;
+    getHistogramImplLocked(h.first)->Data(&hData);
+    // don't handle failures - buffer should always be big enough and arguments
+    // should be provided correctly
+    int ret = snprintf(
+        buffer, kTmpStrBufferSize,
+        "%s P50 : %f P95 : %f P99 : %f P100 : %f COUNT : %" PRIu64 " SUM : %"
+        PRIu64 "\n", h.second.c_str(), hData.median, hData.percentile95,
+        hData.percentile99, hData.max, hData.count, hData.sum);
+    if (ret < 0 || ret >= kTmpStrBufferSize) {
+      assert(false);
+      continue;
+    }
+    res.append(buffer);
+  }
+  res.shrink_to_fit();
+  return res;
+}
+
+bool StatisticsImpl::HistEnabledForType(uint32_t type) const {
+  return type < HISTOGRAM_ENUM_MAX;
+}
+
+} // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/statistics.h b/3rdParty/rocksdb/v5.18.X/monitoring/statistics.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/statistics.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/statistics.h
index 4427c8c546..dcd5f7a010 100644
--- a/3rdParty/rocksdb/v5.16.X/monitoring/statistics.h
+++ b/3rdParty/rocksdb/v5.18.X/monitoring/statistics.h
@@ -41,8 +41,7 @@ enum HistogramsInternal : uint32_t {
 
 class StatisticsImpl : public Statistics {
  public:
-  StatisticsImpl(std::shared_ptr<Statistics> stats,
-                 bool enable_internal_stats);
+  StatisticsImpl(std::shared_ptr<Statistics> stats);
   virtual ~StatisticsImpl();
 
   virtual uint64_t getTickerCount(uint32_t ticker_type) const override;
@@ -62,8 +61,6 @@ class StatisticsImpl : public Statistics {
  private:
   // If non-nullptr, forwards updates to the object pointed to by `stats_`.
   std::shared_ptr<Statistics> stats_;
-  // TODO(ajkr): clean this up since there are no internal stats anymore
-  bool enable_internal_stats_;
   // Synchronizes anything that operates across other cores' local data,
   // such that operations like Reset() can be performed atomically.
   mutable port::Mutex aggregate_lock_;
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/statistics_test.cc b/3rdParty/rocksdb/v5.18.X/monitoring/statistics_test.cc
similarity index 67%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/statistics_test.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/statistics_test.cc
index 43aacde9c1..a77022bfb3 100644
--- a/3rdParty/rocksdb/v5.16.X/monitoring/statistics_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/monitoring/statistics_test.cc
@@ -16,7 +16,7 @@ class StatisticsTest : public testing::Test {};
 
 // Sanity check to make sure that contents and order of TickersNameMap
 // match Tickers enum
-TEST_F(StatisticsTest, Sanity) {
+TEST_F(StatisticsTest, SanityTickers) {
   EXPECT_EQ(static_cast<size_t>(Tickers::TICKER_ENUM_MAX),
             TickersNameMap.size());
 
@@ -26,6 +26,18 @@ TEST_F(StatisticsTest, Sanity) {
   }
 }
 
+// Sanity check to make sure that contents and order of HistogramsNameMap
+// match Tickers enum
+TEST_F(StatisticsTest, SanityHistograms) {
+  EXPECT_EQ(static_cast<size_t>(Histograms::HISTOGRAM_ENUM_MAX),
+            HistogramsNameMap.size());
+
+  for (uint32_t h = 0; h < Histograms::HISTOGRAM_ENUM_MAX; h++) {
+    auto pair = HistogramsNameMap[static_cast<size_t>(h)];
+    ASSERT_EQ(pair.first, h) << "Miss match at " << pair.second;
+  }
+}
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/thread_status_impl.cc b/3rdParty/rocksdb/v5.18.X/monitoring/thread_status_impl.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/thread_status_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/thread_status_impl.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/thread_status_updater.cc b/3rdParty/rocksdb/v5.18.X/monitoring/thread_status_updater.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/thread_status_updater.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/thread_status_updater.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/thread_status_updater.h b/3rdParty/rocksdb/v5.18.X/monitoring/thread_status_updater.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/thread_status_updater.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/thread_status_updater.h
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/thread_status_updater_debug.cc b/3rdParty/rocksdb/v5.18.X/monitoring/thread_status_updater_debug.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/thread_status_updater_debug.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/thread_status_updater_debug.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/thread_status_util.cc b/3rdParty/rocksdb/v5.18.X/monitoring/thread_status_util.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/thread_status_util.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/thread_status_util.cc
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/thread_status_util.h b/3rdParty/rocksdb/v5.18.X/monitoring/thread_status_util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/thread_status_util.h
rename to 3rdParty/rocksdb/v5.18.X/monitoring/thread_status_util.h
diff --git a/3rdParty/rocksdb/v5.16.X/monitoring/thread_status_util_debug.cc b/3rdParty/rocksdb/v5.18.X/monitoring/thread_status_util_debug.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/monitoring/thread_status_util_debug.cc
rename to 3rdParty/rocksdb/v5.18.X/monitoring/thread_status_util_debug.cc
diff --git a/3rdParty/rocksdb/v5.16.X/options/cf_options.cc b/3rdParty/rocksdb/v5.18.X/options/cf_options.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/options/cf_options.cc
rename to 3rdParty/rocksdb/v5.18.X/options/cf_options.cc
diff --git a/3rdParty/rocksdb/v5.16.X/options/cf_options.h b/3rdParty/rocksdb/v5.18.X/options/cf_options.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/options/cf_options.h
rename to 3rdParty/rocksdb/v5.18.X/options/cf_options.h
index 1658bf427a..69b0b0105a 100644
--- a/3rdParty/rocksdb/v5.16.X/options/cf_options.h
+++ b/3rdParty/rocksdb/v5.18.X/options/cf_options.h
@@ -18,7 +18,7 @@ namespace rocksdb {
 // ImmutableCFOptions is a data struct used by RocksDB internal. It contains a
 // subset of Options that should not be changed during the entire lifetime
 // of DB. Raw pointers defined in this struct do not have ownership to the data
-// they point to. Options contains shared_ptr to these data.
+// they point to. Options contains std::shared_ptr to these data.
 struct ImmutableCFOptions {
   ImmutableCFOptions();
   explicit ImmutableCFOptions(const Options& options);
diff --git a/3rdParty/rocksdb/v5.16.X/options/db_options.cc b/3rdParty/rocksdb/v5.18.X/options/db_options.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/options/db_options.cc
rename to 3rdParty/rocksdb/v5.18.X/options/db_options.cc
index fd3cdcccd6..4e8134511b 100644
--- a/3rdParty/rocksdb/v5.16.X/options/db_options.cc
+++ b/3rdParty/rocksdb/v5.18.X/options/db_options.cc
@@ -85,7 +85,8 @@ ImmutableDBOptions::ImmutableDBOptions(const DBOptions& options)
       allow_ingest_behind(options.allow_ingest_behind),
       preserve_deletes(options.preserve_deletes),
       two_write_queues(options.two_write_queues),
-      manual_wal_flush(options.manual_wal_flush) {
+      manual_wal_flush(options.manual_wal_flush),
+      atomic_flush(options.atomic_flush) {
 }
 
 void ImmutableDBOptions::Dump(Logger* log) const {
diff --git a/3rdParty/rocksdb/v5.16.X/options/db_options.h b/3rdParty/rocksdb/v5.18.X/options/db_options.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/options/db_options.h
rename to 3rdParty/rocksdb/v5.18.X/options/db_options.h
index 107d35c877..2cd83b55d4 100644
--- a/3rdParty/rocksdb/v5.16.X/options/db_options.h
+++ b/3rdParty/rocksdb/v5.18.X/options/db_options.h
@@ -78,6 +78,7 @@ struct ImmutableDBOptions {
   bool preserve_deletes;
   bool two_write_queues;
   bool manual_wal_flush;
+  bool atomic_flush;
 };
 
 struct MutableDBOptions {
diff --git a/3rdParty/rocksdb/v5.16.X/options/options.cc b/3rdParty/rocksdb/v5.18.X/options/options.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/options/options.cc
rename to 3rdParty/rocksdb/v5.18.X/options/options.cc
diff --git a/3rdParty/rocksdb/v5.16.X/options/options_helper.cc b/3rdParty/rocksdb/v5.18.X/options/options_helper.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/options/options_helper.cc
rename to 3rdParty/rocksdb/v5.18.X/options/options_helper.cc
index f4c59ff06e..27a2252a02 100644
--- a/3rdParty/rocksdb/v5.16.X/options/options_helper.cc
+++ b/3rdParty/rocksdb/v5.18.X/options/options_helper.cc
@@ -126,6 +126,7 @@ DBOptions BuildDBOptions(const ImmutableDBOptions& immutable_db_options,
       immutable_db_options.preserve_deletes;
   options.two_write_queues = immutable_db_options.two_write_queues;
   options.manual_wal_flush = immutable_db_options.manual_wal_flush;
+  options.atomic_flush = immutable_db_options.atomic_flush;
 
   return options;
 }
@@ -215,7 +216,8 @@ std::map<CompactionStopStyle, std::string>
 std::unordered_map<std::string, ChecksumType>
     OptionsHelper::checksum_type_string_map = {{"kNoChecksum", kNoChecksum},
                                                {"kCRC32c", kCRC32c},
-                                               {"kxxHash", kxxHash}};
+                                               {"kxxHash", kxxHash},
+                                               {"kxxHash64", kxxHash64}};
 
 std::unordered_map<std::string, CompressionType>
     OptionsHelper::compression_type_string_map = {
@@ -1554,7 +1556,11 @@ std::unordered_map<std::string, OptionTypeInfo>
           offsetof(struct ImmutableDBOptions, manual_wal_flush)}},
         {"seq_per_batch",
          {0, OptionType::kBoolean, OptionVerificationType::kDeprecated, false,
-          0}}};
+          0}},
+        {"atomic_flush",
+         {offsetof(struct DBOptions, atomic_flush), OptionType::kBoolean,
+          OptionVerificationType::kNormal, false,
+          offsetof(struct ImmutableDBOptions, atomic_flush)}}};
 
 std::unordered_map<std::string, BlockBasedTableOptions::IndexType>
     OptionsHelper::block_base_table_index_type_string_map = {
diff --git a/3rdParty/rocksdb/v5.16.X/options/options_helper.h b/3rdParty/rocksdb/v5.18.X/options/options_helper.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/options/options_helper.h
rename to 3rdParty/rocksdb/v5.18.X/options/options_helper.h
diff --git a/3rdParty/rocksdb/v5.16.X/options/options_parser.cc b/3rdParty/rocksdb/v5.18.X/options/options_parser.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/options/options_parser.cc
rename to 3rdParty/rocksdb/v5.18.X/options/options_parser.cc
index 35bbc82cd2..32cfb8d531 100644
--- a/3rdParty/rocksdb/v5.16.X/options/options_parser.cc
+++ b/3rdParty/rocksdb/v5.18.X/options/options_parser.cc
@@ -48,8 +48,8 @@ Status PersistRocksDBOptions(const DBOptions& db_opt,
   if (!s.ok()) {
     return s;
   }
-  unique_ptr<WritableFileWriter> writable;
-  writable.reset(new WritableFileWriter(std::move(wf), EnvOptions(),
+  std::unique_ptr<WritableFileWriter> writable;
+  writable.reset(new WritableFileWriter(std::move(wf), file_name, EnvOptions(),
                                         nullptr /* statistics */));
 
   std::string options_file_content;
diff --git a/3rdParty/rocksdb/v5.16.X/options/options_parser.h b/3rdParty/rocksdb/v5.18.X/options/options_parser.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/options/options_parser.h
rename to 3rdParty/rocksdb/v5.18.X/options/options_parser.h
diff --git a/3rdParty/rocksdb/v5.16.X/options/options_sanity_check.cc b/3rdParty/rocksdb/v5.18.X/options/options_sanity_check.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/options/options_sanity_check.cc
rename to 3rdParty/rocksdb/v5.18.X/options/options_sanity_check.cc
diff --git a/3rdParty/rocksdb/v5.16.X/options/options_sanity_check.h b/3rdParty/rocksdb/v5.18.X/options/options_sanity_check.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/options/options_sanity_check.h
rename to 3rdParty/rocksdb/v5.18.X/options/options_sanity_check.h
diff --git a/3rdParty/rocksdb/v5.16.X/options/options_settable_test.cc b/3rdParty/rocksdb/v5.18.X/options/options_settable_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/options/options_settable_test.cc
rename to 3rdParty/rocksdb/v5.18.X/options/options_settable_test.cc
index ded152ba99..cad1af3d76 100644
--- a/3rdParty/rocksdb/v5.16.X/options/options_settable_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/options/options_settable_test.cc
@@ -291,7 +291,8 @@ TEST_F(OptionsSettableTest, DBOptionsAllFieldsSettable) {
                              "concurrent_prepare=false;"
                              "two_write_queues=false;"
                              "manual_wal_flush=false;"
-                             "seq_per_batch=false;",
+                             "seq_per_batch=false;"
+                             "atomic_flush=false",
                              new_options));
 
   ASSERT_EQ(unset_bytes_base, NumUnsetBytes(new_options_ptr, sizeof(DBOptions),
diff --git a/3rdParty/rocksdb/v5.16.X/options/options_test.cc b/3rdParty/rocksdb/v5.18.X/options/options_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/options/options_test.cc
rename to 3rdParty/rocksdb/v5.18.X/options/options_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/port/README b/3rdParty/rocksdb/v5.18.X/port/README
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/README
rename to 3rdParty/rocksdb/v5.18.X/port/README
diff --git a/3rdParty/rocksdb/v5.16.X/port/dirent.h b/3rdParty/rocksdb/v5.18.X/port/dirent.h
similarity index 89%
rename from 3rdParty/rocksdb/v5.16.X/port/dirent.h
rename to 3rdParty/rocksdb/v5.18.X/port/dirent.h
index 7bcc356978..cb1adbe129 100644
--- a/3rdParty/rocksdb/v5.16.X/port/dirent.h
+++ b/3rdParty/rocksdb/v5.18.X/port/dirent.h
@@ -9,8 +9,7 @@
 //
 // See port_example.h for documentation for the following types/functions.
 
-#ifndef STORAGE_LEVELDB_PORT_DIRENT_H_
-#define STORAGE_LEVELDB_PORT_DIRENT_H_
+#pragma once
 
 #ifdef ROCKSDB_PLATFORM_POSIX
 #include <dirent.h>
@@ -43,5 +42,3 @@ using port::closedir;
 }  // namespace rocksdb
 
 #endif  // OS_WIN
-
-#endif  // STORAGE_LEVELDB_PORT_DIRENT_H_
diff --git a/3rdParty/rocksdb/v5.16.X/port/likely.h b/3rdParty/rocksdb/v5.18.X/port/likely.h
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/port/likely.h
rename to 3rdParty/rocksdb/v5.18.X/port/likely.h
index e5ef786f2e..397d757133 100644
--- a/3rdParty/rocksdb/v5.16.X/port/likely.h
+++ b/3rdParty/rocksdb/v5.18.X/port/likely.h
@@ -7,8 +7,7 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#ifndef PORT_LIKELY_H_
-#define PORT_LIKELY_H_
+#pragma once
 
 #if defined(__GNUC__) && __GNUC__ >= 4
 #define LIKELY(x)   (__builtin_expect((x), 1))
@@ -17,5 +16,3 @@
 #define LIKELY(x)   (x)
 #define UNLIKELY(x) (x)
 #endif
-
-#endif  // PORT_LIKELY_H_
diff --git a/3rdParty/rocksdb/v5.16.X/port/port.h b/3rdParty/rocksdb/v5.18.X/port/port.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/port.h
rename to 3rdParty/rocksdb/v5.18.X/port/port.h
diff --git a/3rdParty/rocksdb/v5.16.X/port/port_example.h b/3rdParty/rocksdb/v5.18.X/port/port_example.h
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/port/port_example.h
rename to 3rdParty/rocksdb/v5.18.X/port/port_example.h
index 05b3240669..a94dc93c26 100644
--- a/3rdParty/rocksdb/v5.16.X/port/port_example.h
+++ b/3rdParty/rocksdb/v5.18.X/port/port_example.h
@@ -12,8 +12,7 @@
 // specific port_<platform>.h file.  Use this file as a reference for
 // how to port this package to a new platform.
 
-#ifndef STORAGE_LEVELDB_PORT_PORT_EXAMPLE_H_
-#define STORAGE_LEVELDB_PORT_PORT_EXAMPLE_H_
+#pragma once
 
 namespace rocksdb {
 namespace port {
@@ -100,5 +99,3 @@ extern bool Snappy_Uncompress(const char* input_data, size_t input_length,
 
 }  // namespace port
 }  // namespace rocksdb
-
-#endif  // STORAGE_LEVELDB_PORT_PORT_EXAMPLE_H_
diff --git a/3rdParty/rocksdb/v5.16.X/port/port_posix.cc b/3rdParty/rocksdb/v5.18.X/port/port_posix.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/port_posix.cc
rename to 3rdParty/rocksdb/v5.18.X/port/port_posix.cc
diff --git a/3rdParty/rocksdb/v5.16.X/port/port_posix.h b/3rdParty/rocksdb/v5.18.X/port/port_posix.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/port_posix.h
rename to 3rdParty/rocksdb/v5.18.X/port/port_posix.h
diff --git a/3rdParty/rocksdb/v5.16.X/port/stack_trace.cc b/3rdParty/rocksdb/v5.18.X/port/stack_trace.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/stack_trace.cc
rename to 3rdParty/rocksdb/v5.18.X/port/stack_trace.cc
diff --git a/3rdParty/rocksdb/v5.16.X/port/stack_trace.h b/3rdParty/rocksdb/v5.18.X/port/stack_trace.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/stack_trace.h
rename to 3rdParty/rocksdb/v5.18.X/port/stack_trace.h
diff --git a/3rdParty/rocksdb/v5.16.X/port/sys_time.h b/3rdParty/rocksdb/v5.18.X/port/sys_time.h
similarity index 89%
rename from 3rdParty/rocksdb/v5.16.X/port/sys_time.h
rename to 3rdParty/rocksdb/v5.18.X/port/sys_time.h
index 1e2ad0f5d6..2f83da8b3e 100644
--- a/3rdParty/rocksdb/v5.16.X/port/sys_time.h
+++ b/3rdParty/rocksdb/v5.18.X/port/sys_time.h
@@ -10,8 +10,7 @@
 // This file is a portable substitute for sys/time.h which does not exist on
 // Windows
 
-#ifndef STORAGE_LEVELDB_PORT_SYS_TIME_H_
-#define STORAGE_LEVELDB_PORT_SYS_TIME_H_
+#pragma once
 
 #if defined(OS_WIN) && defined(_MSC_VER)
 
@@ -44,5 +43,3 @@ using port::localtime_r;
 #include <time.h>
 #include <sys/time.h>
 #endif
-
-#endif  // STORAGE_LEVELDB_PORT_SYS_TIME_H_
diff --git a/3rdParty/rocksdb/v5.16.X/port/util_logger.h b/3rdParty/rocksdb/v5.18.X/port/util_logger.h
similarity index 85%
rename from 3rdParty/rocksdb/v5.16.X/port/util_logger.h
rename to 3rdParty/rocksdb/v5.18.X/port/util_logger.h
index a8255ad6d6..ba424705b2 100644
--- a/3rdParty/rocksdb/v5.16.X/port/util_logger.h
+++ b/3rdParty/rocksdb/v5.18.X/port/util_logger.h
@@ -7,8 +7,7 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#ifndef STORAGE_LEVELDB_PORT_UTIL_LOGGER_H_
-#define STORAGE_LEVELDB_PORT_UTIL_LOGGER_H_
+#pragma once
 
 // Include the appropriate platform specific file below.  If you are
 // porting to a new platform, see "port_example.h" for documentation
@@ -19,5 +18,3 @@
 #elif defined(OS_WIN)
 #include "port/win/win_logger.h"
 #endif
-
-#endif  // STORAGE_LEVELDB_PORT_UTIL_LOGGER_H_
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/env_default.cc b/3rdParty/rocksdb/v5.18.X/port/win/env_default.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/win/env_default.cc
rename to 3rdParty/rocksdb/v5.18.X/port/win/env_default.cc
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/env_win.cc b/3rdParty/rocksdb/v5.18.X/port/win/env_win.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/port/win/env_win.cc
rename to 3rdParty/rocksdb/v5.18.X/port/win/env_win.cc
index daa4789dc9..d301390670 100644
--- a/3rdParty/rocksdb/v5.16.X/port/win/env_win.cc
+++ b/3rdParty/rocksdb/v5.18.X/port/win/env_win.cc
@@ -236,7 +236,7 @@ Status WinEnvIO::NewRandomAccessFile(const std::string& fname,
         MapViewOfFileEx(hMap, FILE_MAP_READ,
         0,  // High DWORD of access start
         0,  // Low DWORD
-        fileSize,
+        static_cast<SIZE_T>(fileSize),
         NULL);  // Let the OS choose the mapping
 
       if (!mapped_region) {
@@ -247,7 +247,7 @@ Status WinEnvIO::NewRandomAccessFile(const std::string& fname,
       }
 
       result->reset(new WinMmapReadableFile(fname, hFile, hMap, mapped_region,
-        fileSize));
+				static_cast<size_t>(fileSize)));
 
       mapGuard.release();
       fileGuard.release();
@@ -449,7 +449,7 @@ Status WinEnvIO::NewMemoryMappedFileBuffer(const std::string & fname,
   void* base = MapViewOfFileEx(hMap, FILE_MAP_WRITE,
     0,  // High DWORD of access start
     0,  // Low DWORD
-    fileSize,
+		static_cast<SIZE_T>(fileSize),
     NULL);  // Let the OS choose the mapping
 
   if (!base) {
@@ -707,6 +707,9 @@ Status WinEnvIO::LinkFile(const std::string& src,
 
   if (!RX_CreateHardLink(RX_FN(target).c_str(), RX_FN(src).c_str(),  NULL)) {
     DWORD lastError = GetLastError();
+    if (lastError == ERROR_NOT_SAME_DEVICE) {
+      return Status::NotSupported("No cross FS links allowed");
+    }
 
     std::string text("Failed to link: ");
     text.append(src).append(" to: ").append(target);
@@ -717,30 +720,28 @@ Status WinEnvIO::LinkFile(const std::string& src,
   return result;
 }
 
-Status WinEnvIO::NumFileLinks(const std::string& fname, 
-  uint64_t* count) {
+Status WinEnvIO::NumFileLinks(const std::string& fname, uint64_t* count) {
   Status s;
-  HANDLE handle = RX_CreateFile(RX_FN(fname).c_str(), 0,
-    FILE_SHARE_DELETE | FILE_SHARE_READ | FILE_SHARE_WRITE,
-    NULL,
-    OPEN_EXISTING,
-    FILE_FLAG_BACKUP_SEMANTICS,
-    NULL);
+  HANDLE handle = RX_CreateFile(
+      RX_FN(fname).c_str(), 0,
+      FILE_SHARE_DELETE | FILE_SHARE_READ | FILE_SHARE_WRITE,
+      NULL, OPEN_EXISTING, FILE_FLAG_BACKUP_SEMANTICS, NULL);
 
   if (INVALID_HANDLE_VALUE == handle) {
     auto lastError = GetLastError();
-    s = IOErrorFromWindowsError(
-      "NumFileLinks: " + fname, lastError);
+    s = IOErrorFromWindowsError("NumFileLinks: " + fname, lastError);
     return s;
   }
   UniqueCloseHandlePtr handle_guard(handle, CloseHandleFunc);
   FILE_STANDARD_INFO standard_info;
-  if (0 != GetFileInformationByHandleEx(handle, FileStandardInfo, 
-                                        &standard_info, sizeof(standard_info))) {
+  if (0 != GetFileInformationByHandleEx(handle, FileStandardInfo,
+                                        &standard_info,
+                                        sizeof(standard_info))) {
     *count = standard_info.NumberOfLinks;
   } else {
     auto lastError = GetLastError();
-    s = IOErrorFromWindowsError("GetFileInformationByHandleEx: " + fname, lastError);
+    s = IOErrorFromWindowsError("GetFileInformationByHandleEx: " + fname,
+                                lastError);
   }
   return s;
 }
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/env_win.h b/3rdParty/rocksdb/v5.18.X/port/win/env_win.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/port/win/env_win.h
rename to 3rdParty/rocksdb/v5.18.X/port/win/env_win.h
index 08c1534f34..d61ac3acd6 100644
--- a/3rdParty/rocksdb/v5.16.X/port/win/env_win.h
+++ b/3rdParty/rocksdb/v5.18.X/port/win/env_win.h
@@ -109,8 +109,8 @@ public:
 
   // The returned file will only be accessed by one thread at a time.
   virtual Status NewRandomRWFile(const std::string& fname,
-    unique_ptr<RandomRWFile>* result,
-    const EnvOptions& options);
+                                 std::unique_ptr<RandomRWFile>* result,
+                                 const EnvOptions& options);
 
   virtual Status NewMemoryMappedFileBuffer(
     const std::string& fname,
@@ -145,7 +145,7 @@ public:
     const std::string& target);
 
   virtual Status NumFileLinks(const std::string& /*fname*/,
-    uint64_t* /*count*/);
+                              uint64_t* /*count*/);
 
   virtual Status AreFilesSame(const std::string& first,
     const std::string& second, bool* res);
@@ -271,8 +271,7 @@ public:
   Status LinkFile(const std::string& src,
     const std::string& target) override;
 
-  Status NumFileLinks(const std::string& fname,
-    uint64_t* count) override;
+  Status NumFileLinks(const std::string& fname, uint64_t* count) override;
 
   Status AreFilesSame(const std::string& first,
     const std::string& second, bool* res) override;
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/io_win.cc b/3rdParty/rocksdb/v5.18.X/port/win/io_win.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/port/win/io_win.cc
rename to 3rdParty/rocksdb/v5.18.X/port/win/io_win.cc
index 66fe8a11e6..128cb60b9f 100644
--- a/3rdParty/rocksdb/v5.16.X/port/win/io_win.cc
+++ b/3rdParty/rocksdb/v5.18.X/port/win/io_win.cc
@@ -260,7 +260,7 @@ Status WinMmapReadableFile::Read(uint64_t offset, size_t n, Slice* result,
     *result = Slice();
     return IOError(filename_, EINVAL);
   } else if (offset + n > length_) {
-    n = length_ - offset;
+    n = length_ - static_cast<size_t>(offset);
   }
   *result =
     Slice(reinterpret_cast<const char*>(mapped_region_)+offset, n);
@@ -317,7 +317,7 @@ Status WinMmapFile::MapNewRegion() {
 
   assert(mapped_begin_ == nullptr);
 
-  size_t minDiskSize = file_offset_ + view_size_;
+  size_t minDiskSize = static_cast<size_t>(file_offset_) + view_size_;
 
   if (minDiskSize > reserved_size_) {
     status = Allocate(file_offset_, view_size_);
@@ -579,7 +579,7 @@ Status WinMmapFile::Allocate(uint64_t offset, uint64_t len) {
   // Make sure that we reserve an aligned amount of space
   // since the reservation block size is driven outside so we want
   // to check if we are ok with reservation here
-  size_t spaceToReserve = Roundup(offset + len, view_size_);
+  size_t spaceToReserve = Roundup(static_cast<size_t>(offset + len), view_size_);
   // Nothing to do
   if (spaceToReserve <= reserved_size_) {
     return status;
@@ -656,14 +656,14 @@ Status WinSequentialFile::PositionedRead(uint64_t offset, size_t n, Slice* resul
     return Status::NotSupported("This function is only used for direct_io");
   }
 
-  if (!IsSectorAligned(offset) ||
+  if (!IsSectorAligned(static_cast<size_t>(offset)) ||
       !IsSectorAligned(n)) {
       return Status::InvalidArgument(
         "WinSequentialFile::PositionedRead: offset is not properly aligned");
   }
 
   size_t bytes_read = 0; // out param
-  s = PositionedReadInternal(scratch, n, offset, bytes_read);
+  s = PositionedReadInternal(scratch, static_cast<size_t>(n), offset, bytes_read);
   *result = Slice(scratch, bytes_read);
   return s;
 }
@@ -721,7 +721,7 @@ Status WinRandomAccessImpl::ReadImpl(uint64_t offset, size_t n, Slice* result,
 
   // Check buffer alignment
   if (file_base_->use_direct_io()) {
-    if (!IsSectorAligned(offset) ||
+    if (!IsSectorAligned(static_cast<size_t>(offset)) ||
         !IsAligned(alignment_, scratch)) {
       return Status::InvalidArgument(
         "WinRandomAccessImpl::ReadImpl: offset or scratch is not properly aligned");
@@ -818,7 +818,7 @@ Status WinWritableImpl::AppendImpl(const Slice& data) {
     // to the end of the file
     assert(IsSectorAligned(next_write_offset_));
     if (!IsSectorAligned(data.size()) ||
-        !IsAligned(GetAlignement(), data.data())) {
+        !IsAligned(static_cast<size_t>(GetAlignement()), data.data())) {
       s = Status::InvalidArgument(
         "WriteData must be page aligned, size must be sector aligned");
     } else {
@@ -857,9 +857,9 @@ inline
 Status WinWritableImpl::PositionedAppendImpl(const Slice& data, uint64_t offset) {
 
   if(file_data_->use_direct_io()) {
-    if (!IsSectorAligned(offset) ||
+    if (!IsSectorAligned(static_cast<size_t>(offset)) ||
         !IsSectorAligned(data.size()) ||
-        !IsAligned(GetAlignement(), data.data())) {
+        !IsAligned(static_cast<size_t>(GetAlignement()), data.data())) {
       return Status::InvalidArgument(
         "Data and offset must be page aligned, size must be sector aligned");
     }
@@ -944,7 +944,7 @@ Status WinWritableImpl::AllocateImpl(uint64_t offset, uint64_t len) {
   // Make sure that we reserve an aligned amount of space
   // since the reservation block size is driven outside so we want
   // to check if we are ok with reservation here
-  size_t spaceToReserve = Roundup(offset + len, alignment_);
+  size_t spaceToReserve = Roundup(static_cast<size_t>(offset + len), static_cast<size_t>(alignment_));
   // Nothing to do
   if (spaceToReserve <= reservedsize_) {
     return status;
@@ -977,7 +977,7 @@ WinWritableFile::~WinWritableFile() {
 bool WinWritableFile::use_direct_io() const { return WinFileData::use_direct_io(); }
 
 size_t WinWritableFile::GetRequiredBufferAlignment() const {
-  return GetAlignement();
+  return static_cast<size_t>(GetAlignement());
 }
 
 Status WinWritableFile::Append(const Slice& data) {
@@ -1037,7 +1037,7 @@ WinRandomRWFile::WinRandomRWFile(const std::string& fname, HANDLE hFile,
 bool WinRandomRWFile::use_direct_io() const { return WinFileData::use_direct_io(); }
 
 size_t WinRandomRWFile::GetRequiredBufferAlignment() const {
-  return GetAlignement();
+  return static_cast<size_t>(GetAlignement());
 }
 
 Status WinRandomRWFile::Write(uint64_t offset, const Slice & data) {
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/io_win.h b/3rdParty/rocksdb/v5.18.X/port/win/io_win.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/port/win/io_win.h
rename to 3rdParty/rocksdb/v5.18.X/port/win/io_win.h
index 3b08c394f4..c46876b8c0 100644
--- a/3rdParty/rocksdb/v5.16.X/port/win/io_win.h
+++ b/3rdParty/rocksdb/v5.18.X/port/win/io_win.h
@@ -58,7 +58,7 @@ class WinFileData {
  protected:
   const std::string filename_;
   HANDLE hFile_;
-  // If ture,  the I/O issued would be direct I/O which the buffer
+  // If true, the I/O issued would be direct I/O which the buffer
   // will need to be aligned (not sure there is a guarantee that the buffer
   // passed in is aligned).
   const bool use_direct_io_;
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/port_win.cc b/3rdParty/rocksdb/v5.18.X/port/win/port_win.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/port/win/port_win.cc
rename to 3rdParty/rocksdb/v5.18.X/port/win/port_win.cc
index a6587ab01a..6ca5bba3b9 100644
--- a/3rdParty/rocksdb/v5.16.X/port/win/port_win.cc
+++ b/3rdParty/rocksdb/v5.18.X/port/win/port_win.cc
@@ -38,6 +38,7 @@
 namespace rocksdb {
 namespace port {
 
+#ifdef ROCKSDB_WINDOWS_UTF8_FILENAMES
 std::string utf16_to_utf8(const std::wstring& utf16) {
   std::wstring_convert<std::codecvt_utf8_utf16<wchar_t>,wchar_t> convert;
   return convert.to_bytes(utf16);
@@ -47,6 +48,7 @@ std::wstring utf8_to_utf16(const std::string& utf8) {
   std::wstring_convert<std::codecvt_utf8_utf16<wchar_t>> converter;
   return converter.from_bytes(utf8);
 }
+#endif
 
 void gettimeofday(struct timeval* tv, struct timezone* /* tz */) {
   using namespace std::chrono;
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/port_win.h b/3rdParty/rocksdb/v5.18.X/port/win/port_win.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/port/win/port_win.h
rename to 3rdParty/rocksdb/v5.18.X/port/win/port_win.h
index 19ce244349..9b8ba9ff89 100644
--- a/3rdParty/rocksdb/v5.16.X/port/win/port_win.h
+++ b/3rdParty/rocksdb/v5.18.X/port/win/port_win.h
@@ -9,8 +9,7 @@
 //
 // See port_example.h for documentation for the following types/functions.
 
-#ifndef STORAGE_LEVELDB_PORT_PORT_WIN_H_
-#define STORAGE_LEVELDB_PORT_PORT_WIN_H_
+#pragma once
 
 // Always want minimum headers
 #ifndef WIN32_LEAN_AND_MEAN
@@ -392,5 +391,3 @@ using port::pthread_getspecific;
 using port::truncate;
 
 }  // namespace rocksdb
-
-#endif  // STORAGE_LEVELDB_PORT_PORT_WIN_H_
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/win_jemalloc.cc b/3rdParty/rocksdb/v5.18.X/port/win/win_jemalloc.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/win/win_jemalloc.cc
rename to 3rdParty/rocksdb/v5.18.X/port/win/win_jemalloc.cc
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/win_logger.cc b/3rdParty/rocksdb/v5.18.X/port/win/win_logger.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/win/win_logger.cc
rename to 3rdParty/rocksdb/v5.18.X/port/win/win_logger.cc
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/win_logger.h b/3rdParty/rocksdb/v5.18.X/port/win/win_logger.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/win/win_logger.h
rename to 3rdParty/rocksdb/v5.18.X/port/win/win_logger.h
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/win_thread.cc b/3rdParty/rocksdb/v5.18.X/port/win/win_thread.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/port/win/win_thread.cc
rename to 3rdParty/rocksdb/v5.18.X/port/win/win_thread.cc
index b48af2370f..9a976e2c6b 100644
--- a/3rdParty/rocksdb/v5.16.X/port/win/win_thread.cc
+++ b/3rdParty/rocksdb/v5.18.X/port/win/win_thread.cc
@@ -40,7 +40,7 @@ struct WindowsThread::Data {
 void WindowsThread::Init(std::function<void()>&& func) {
 
   data_ = std::make_shared<Data>(std::move(func));
-  // We create another instance of shared_ptr to get an additional ref
+  // We create another instance of std::shared_ptr to get an additional ref
   // since we may detach and destroy this instance before the threadproc
   // may start to run. We choose to allocate this additional ref on the heap
   // so we do not need to synchronize and allow this thread to proceed
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/win_thread.h b/3rdParty/rocksdb/v5.18.X/port/win/win_thread.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/win/win_thread.h
rename to 3rdParty/rocksdb/v5.18.X/port/win/win_thread.h
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/xpress_win.cc b/3rdParty/rocksdb/v5.18.X/port/win/xpress_win.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/win/xpress_win.cc
rename to 3rdParty/rocksdb/v5.18.X/port/win/xpress_win.cc
diff --git a/3rdParty/rocksdb/v5.16.X/port/win/xpress_win.h b/3rdParty/rocksdb/v5.18.X/port/win/xpress_win.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/win/xpress_win.h
rename to 3rdParty/rocksdb/v5.18.X/port/win/xpress_win.h
diff --git a/3rdParty/rocksdb/v5.16.X/port/xpress.h b/3rdParty/rocksdb/v5.18.X/port/xpress.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/port/xpress.h
rename to 3rdParty/rocksdb/v5.18.X/port/xpress.h
diff --git a/3rdParty/rocksdb/v5.16.X/src.mk b/3rdParty/rocksdb/v5.18.X/src.mk
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/src.mk
rename to 3rdParty/rocksdb/v5.18.X/src.mk
index 68aa8618c6..5ba7f4b7c0 100644
--- a/3rdParty/rocksdb/v5.16.X/src.mk
+++ b/3rdParty/rocksdb/v5.18.X/src.mk
@@ -11,6 +11,7 @@ LIB_SOURCES =                                                   \
   db/compaction_iterator.cc                                     \
   db/compaction_job.cc                                          \
   db/compaction_picker.cc                                       \
+  db/compaction_picker_fifo.cc                                  \
   db/compaction_picker_universal.cc                             \
   db/convenience.cc                                             \
   db/db_filesnapshot.cc                                         \
@@ -43,6 +44,8 @@ LIB_SOURCES =                                                   \
   db/merge_helper.cc                                            \
   db/merge_operator.cc                                          \
   db/range_del_aggregator.cc                                    \
+  db/range_del_aggregator_v2.cc                                 \
+  db/range_tombstone_fragmenter.cc                              \
   db/repair.cc                                                  \
   db/snapshot_impl.cc                                           \
   db/table_cache.cc                                             \
@@ -120,6 +123,7 @@ LIB_SOURCES =                                                   \
   table/plain_table_index.cc                                    \
   table/plain_table_key_coding.cc                               \
   table/plain_table_reader.cc                                   \
+  table/sst_file_reader.cc                                      \
   table/sst_file_writer.cc                                      \
   table/table_properties.cc                                     \
   table/two_level_iterator.cc                                   \
@@ -142,6 +146,7 @@ LIB_SOURCES =                                                   \
   util/filename.cc                                              \
   util/filter_policy.cc                                         \
   util/hash.cc                                                  \
+  util/jemalloc_nodump_allocator.cc                             \
   util/log_buffer.cc                                            \
   util/murmurhash.cc                                            \
   util/random.cc                                                \
@@ -161,6 +166,7 @@ LIB_SOURCES =                                                   \
   utilities/blob_db/blob_compaction_filter.cc                   \
   utilities/blob_db/blob_db.cc                                  \
   utilities/blob_db/blob_db_impl.cc                             \
+  utilities/blob_db/blob_db_impl_filesnapshot.cc                \
   utilities/blob_db/blob_file.cc                                \
   utilities/blob_db/blob_log_format.cc                          \
   utilities/blob_db/blob_log_reader.cc                          \
@@ -327,6 +333,9 @@ MAIN_SOURCES =                                                          \
   db/redis_test.cc                                                      \
   db/repair_test.cc                                                     \
   db/range_del_aggregator_test.cc                                       \
+  db/range_del_aggregator_bench.cc                                      \
+  db/range_del_aggregator_v2_test.cc                                    \
+  db/range_tombstone_fragmenter_test.cc                                 \
   db/table_properties_collector_test.cc                                 \
   db/util_merge_operators_test.cc                                       \
   db/version_builder_test.cc                                            \
@@ -355,6 +364,7 @@ MAIN_SOURCES =                                                          \
   table/data_block_hash_index_test.cc                                   \
   table/full_filter_block_test.cc                                       \
   table/merger_test.cc                                                  \
+  table/sst_file_reader_test.cc                                         \
   table/table_reader_bench.cc                                           \
   table/table_test.cc                                                   \
   third-party/gtest-1.7.0/fused-src/gtest/gtest-all.cc                  \
@@ -376,6 +386,7 @@ MAIN_SOURCES =                                                          \
   util/filelock_test.cc                                                 \
   util/log_write_bench.cc                                               \
   util/rate_limiter_test.cc                                             \
+  util/repeatable_thread_test.cc                                        \
   util/slice_transform_test.cc                                          \
   util/timer_queue_test.cc                                              \
   util/thread_list_test.cc                                              \
@@ -434,6 +445,7 @@ JNI_NATIVE_SOURCES =                                          \
   java/rocksjni/loggerjnicallback.cc                          \
   java/rocksjni/lru_cache.cc                                  \
   java/rocksjni/memtablejni.cc                                \
+  java/rocksjni/memory_util.cc                                \
   java/rocksjni/merge_operator.cc                             \
   java/rocksjni/native_comparator_wrapper_test.cc             \
   java/rocksjni/optimistic_transaction_db.cc                  \
@@ -466,4 +478,5 @@ JNI_NATIVE_SOURCES =                                          \
   java/rocksjni/write_batch.cc                                \
   java/rocksjni/writebatchhandlerjnicallback.cc               \
   java/rocksjni/write_batch_test.cc                           \
-  java/rocksjni/write_batch_with_index.cc
+  java/rocksjni/write_batch_with_index.cc                     \
+  java/rocksjni/write_buffer_manager.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/adaptive_table_factory.cc b/3rdParty/rocksdb/v5.18.X/table/adaptive_table_factory.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/table/adaptive_table_factory.cc
rename to 3rdParty/rocksdb/v5.18.X/table/adaptive_table_factory.cc
index 0a3e9415ad..bbba3b9193 100644
--- a/3rdParty/rocksdb/v5.16.X/table/adaptive_table_factory.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/adaptive_table_factory.cc
@@ -42,8 +42,8 @@ extern const uint64_t kCuckooTableMagicNumber;
 
 Status AdaptiveTableFactory::NewTableReader(
     const TableReaderOptions& table_reader_options,
-    unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
-    unique_ptr<TableReader>* table,
+    std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+    std::unique_ptr<TableReader>* table,
     bool /*prefetch_index_and_filter_in_cache*/) const {
   Footer footer;
   auto s = ReadFooterFromFile(file.get(), nullptr /* prefetch_buffer */,
diff --git a/3rdParty/rocksdb/v5.16.X/table/adaptive_table_factory.h b/3rdParty/rocksdb/v5.18.X/table/adaptive_table_factory.h
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/table/adaptive_table_factory.h
rename to 3rdParty/rocksdb/v5.18.X/table/adaptive_table_factory.h
index 00af6a76e9..2a82dbfa98 100644
--- a/3rdParty/rocksdb/v5.16.X/table/adaptive_table_factory.h
+++ b/3rdParty/rocksdb/v5.18.X/table/adaptive_table_factory.h
@@ -35,8 +35,8 @@ class AdaptiveTableFactory : public TableFactory {
 
   Status NewTableReader(
       const TableReaderOptions& table_reader_options,
-      unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
-      unique_ptr<TableReader>* table,
+      std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+      std::unique_ptr<TableReader>* table,
       bool prefetch_index_and_filter_in_cache = true) const override;
 
   TableBuilder* NewTableBuilder(
diff --git a/3rdParty/rocksdb/v5.16.X/table/block.cc b/3rdParty/rocksdb/v5.18.X/table/block.cc
similarity index 87%
rename from 3rdParty/rocksdb/v5.16.X/table/block.cc
rename to 3rdParty/rocksdb/v5.18.X/table/block.cc
index f26416e1b7..4e8d6e5ca5 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/block.cc
@@ -235,7 +235,7 @@ void DataBlockIter::Seek(const Slice& target) {
 //
 // If the return value is FALSE, iter location is undefined, and it means:
 // 1) there is no key in this block falling into the range:
-//    ["seek_user_key @ type | seqno", "seek_user_key @ type |  0"],
+//    ["seek_user_key @ type | seqno", "seek_user_key @ kTypeDeletion | 0"],
 //    inclusive; AND
 // 2) the last key of this block has a greater user_key from seek_user_key
 //
@@ -243,13 +243,21 @@ void DataBlockIter::Seek(const Slice& target) {
 // 1) If iter is valid, it is set to a location as if set by BinarySeek. In
 //    this case, it points to the first key_ with a larger user_key or a
 //    matching user_key with a seqno no greater than the seeking seqno.
-// 2) If the iter is invalid, it means either the block has no such user_key,
-//    or the block ends with a matching user_key but with a larger seqno.
+// 2) If the iter is invalid, it means that either all the user_key is less
+//    than the seek_user_key, or the block ends with a matching user_key but
+//    with a smaller [ type | seqno ] (i.e. a larger seqno, or the same seqno
+//    but larger type).
 bool DataBlockIter::SeekForGetImpl(const Slice& target) {
   Slice user_key = ExtractUserKey(target);
   uint32_t map_offset = restarts_ + num_restarts_ * sizeof(uint32_t);
   uint8_t entry = data_block_hash_index_->Lookup(data_, map_offset, user_key);
 
+  if (entry == kCollision) {
+    // HashSeek not effective, falling back
+    Seek(target);
+    return true;
+  }
+
   if (entry == kNoEntry) {
     // Even if we cannot find the user_key in this block, the result may
     // exist in the next block. Consider this exmpale:
@@ -260,16 +268,13 @@ bool DataBlockIter::SeekForGetImpl(const Slice& target) {
     //
     // If seek_key = axy@60, the search will starts from Block N.
     // Even if the user_key is not found in the hash map, the caller still
-    // have to conntinue searching the next block. So we invalidate the
-    // iterator to tell the caller to go on.
-    current_ = restarts_;  // Invalidate the iter
-    return true;
-  }
-
-  if (entry == kCollision) {
-    // HashSeek not effective, falling back
-    Seek(target);
-    return true;
+    // have to conntinue searching the next block.
+    //
+    // In this case, we pretend the key is the the last restart interval.
+    // The while-loop below will search the last restart interval for the
+    // key. It will stop at the first key that is larger than the seek_key,
+    // or to the end of the block if no one is larger.
+    entry = static_cast<uint8_t>(num_restarts_ - 1);
   }
 
   uint32_t restart_index = entry;
@@ -299,24 +304,26 @@ bool DataBlockIter::SeekForGetImpl(const Slice& target) {
   }
 
   if (current_ == restarts_) {
-    // Search reaches to the end of the block. There are two possibilites;
+    // Search reaches to the end of the block. There are three possibilites:
     // 1) there is only one user_key match in the block (otherwise collsion).
-    //    the matching user_key resides in the last restart interval.
-    //    it is the last key of the restart interval and of the block too.
-    //    ParseNextDataKey() skiped it as its seqno is newer.
+    //    the matching user_key resides in the last restart interval, and it
+    //    is the last key of the restart interval and of the block as well.
+    //    ParseNextDataKey() skiped it as its [ type | seqno ] is smaller.
     //
-    // 2) The seek_key is a false positive and got hashed to the last restart
-    //    interval.
-    //    All existing keys in the restart interval are less than seek_key.
+    // 2) The seek_key is not found in the HashIndex Lookup(), i.e. kNoEntry,
+    //    AND all existing user_keys in the restart interval are smaller than
+    //    seek_user_key.
     //
-    // The result may exist in the next block in either case, so may_exist is
-    // returned as true.
+    // 3) The seek_key is a false positive and happens to be hashed to the
+    //    last restart interval, AND all existing user_keys in the restart
+    //    interval are smaller than seek_user_key.
+    //
+    // The result may exist in the next block each case, so we return true.
     return true;
   }
 
   if (user_comparator_->Compare(key_.GetUserKey(), user_key) != 0) {
     // the key is not in this block and cannot be at the next block either.
-    // return false to tell the caller to break from the top-level for-loop
     return false;
   }
 
@@ -349,10 +356,10 @@ void IndexBlockIter::Seek(const Slice& target) {
     ok = PrefixSeek(target, &index);
   } else if (value_delta_encoded_) {
     ok = BinarySeek<DecodeKeyV4>(seek_key, 0, num_restarts_ - 1, &index,
-                                 active_comparator_);
+                                 comparator_);
   } else {
     ok = BinarySeek<DecodeKey>(seek_key, 0, num_restarts_ - 1, &index,
-                               active_comparator_);
+                               comparator_);
   }
 
   if (!ok) {
@@ -725,13 +732,16 @@ uint32_t Block::NumRestarts() const {
   uint32_t block_footer = DecodeFixed32(data_ + size_ - sizeof(uint32_t));
   uint32_t num_restarts = block_footer;
   if (size_ > kMaxBlockSizeSupportedByHashIndex) {
-    // We ensure a block with HashIndex is less than 64KiB in BlockBuilder.
-    // Therefore the footer cannot be encoded as a packed index type and
+    // In BlockBuilder, we have ensured a block with HashIndex is less than
+    // kMaxBlockSizeSupportedByHashIndex (64KiB).
+    //
+    // Therefore, if we encounter a block with a size > 64KiB, the block
+    // cannot have HashIndex. So the footer will directly interpreted as
     // num_restarts.
-    // Such check can ensure legacy block with a vary large num_restarts
-    // i.e. >= 0x10000000 can be interpreted correctly as no HashIndex.
-    // If a legacy block hash a num_restarts >= 0x10000000, size_ will be
-    // much large than 64KiB.
+    //
+    // Such check is for backward compatibility. We can ensure legacy block
+    // with a vary large num_restarts i.e. >= 0x80000000 can be interpreted
+    // correctly as no HashIndex even if the MSB of num_restarts is set.
     return num_restarts;
   }
   BlockBasedTableOptions::DataBlockIndexType index_type;
@@ -752,7 +762,11 @@ BlockBasedTableOptions::DataBlockIndexType Block::IndexType() const {
   return index_type;
 }
 
-Block::~Block() { TEST_SYNC_POINT("Block::~Block"); }
+Block::~Block() {
+  // This sync point can be re-enabled if RocksDB can control the
+  // initialization order of any/all static options created by the user.
+  // TEST_SYNC_POINT("Block::~Block");
+}
 
 Block::Block(BlockContents&& contents, SequenceNumber _global_seqno,
              size_t read_amp_bytes_per_bit, Statistics* statistics)
@@ -767,47 +781,45 @@ Block::Block(BlockContents&& contents, SequenceNumber _global_seqno,
     size_ = 0;  // Error marker
   } else {
     // Should only decode restart points for uncompressed blocks
-    if (compression_type() == kNoCompression) {
-      num_restarts_ = NumRestarts();
-      switch (IndexType()) {
-        case BlockBasedTableOptions::kDataBlockBinarySearch:
-          restart_offset_ = static_cast<uint32_t>(size_) -
-                            (1 + num_restarts_) * sizeof(uint32_t);
-          if (restart_offset_ > size_ - sizeof(uint32_t)) {
-            // The size is too small for NumRestarts() and therefore
-            // restart_offset_ wrapped around.
-            size_ = 0;
-          }
+    num_restarts_ = NumRestarts();
+    switch (IndexType()) {
+      case BlockBasedTableOptions::kDataBlockBinarySearch:
+        restart_offset_ = static_cast<uint32_t>(size_) -
+                          (1 + num_restarts_) * sizeof(uint32_t);
+        if (restart_offset_ > size_ - sizeof(uint32_t)) {
+          // The size is too small for NumRestarts() and therefore
+          // restart_offset_ wrapped around.
+          size_ = 0;
+        }
+        break;
+      case BlockBasedTableOptions::kDataBlockBinaryAndHash:
+        if (size_ < sizeof(uint32_t) /* block footer */ +
+                        sizeof(uint16_t) /* NUM_BUCK */) {
+          size_ = 0;
           break;
-        case BlockBasedTableOptions::kDataBlockBinaryAndHash:
-          if (size_ < sizeof(uint32_t) /* block footer */ +
-                          sizeof(uint16_t) /* NUM_BUCK */) {
-            size_ = 0;
-            break;
-          }
+        }
 
-          uint16_t map_offset;
-          data_block_hash_index_.Initialize(
-              contents.data.data(),
-              static_cast<uint16_t>(contents.data.size() -
-                                    sizeof(uint32_t)), /*chop off
-                                                   NUM_RESTARTS*/
-              &map_offset);
+        uint16_t map_offset;
+        data_block_hash_index_.Initialize(
+            contents.data.data(),
+            static_cast<uint16_t>(contents.data.size() -
+                                  sizeof(uint32_t)), /*chop off
+                                                 NUM_RESTARTS*/
+            &map_offset);
 
-          restart_offset_ = map_offset - num_restarts_ * sizeof(uint32_t);
+        restart_offset_ = map_offset - num_restarts_ * sizeof(uint32_t);
 
-          if (restart_offset_ > map_offset) {
-            // map_offset is too small for NumRestarts() and
-            // therefore restart_offset_ wrapped around.
-            size_ = 0;
-            break;
-          }
+        if (restart_offset_ > map_offset) {
+          // map_offset is too small for NumRestarts() and
+          // therefore restart_offset_ wrapped around.
+          size_ = 0;
           break;
-        default:
-          size_ = 0;  // Error marker
-      }
+        }
+        break;
+      default:
+        size_ = 0;  // Error marker
+    }
     }
-  }
   if (read_amp_bytes_per_bit != 0 && statistics && size_ != 0) {
     read_amp_bitmap_.reset(new BlockReadAmpBitmap(
         restart_offset_, read_amp_bytes_per_bit, statistics));
@@ -820,6 +832,7 @@ DataBlockIter* Block::NewIterator(const Comparator* cmp, const Comparator* ucmp,
                                   bool /*total_order_seek*/,
                                   bool /*key_includes_seq*/,
                                   bool /*value_is_full*/,
+                                  bool block_contents_pinned,
                                   BlockPrefixIndex* /*prefix_index*/) {
   DataBlockIter* ret_iter;
   if (iter != nullptr) {
@@ -838,7 +851,7 @@ DataBlockIter* Block::NewIterator(const Comparator* cmp, const Comparator* ucmp,
   } else {
     ret_iter->Initialize(
         cmp, ucmp, data_, restart_offset_, num_restarts_, global_seqno_,
-        read_amp_bitmap_.get(), cachable(),
+        read_amp_bitmap_.get(), block_contents_pinned,
         data_block_hash_index_.Valid() ? &data_block_hash_index_ : nullptr);
     if (read_amp_bitmap_) {
       if (read_amp_bitmap_->GetStatistics() != stats) {
@@ -856,6 +869,7 @@ IndexBlockIter* Block::NewIterator(const Comparator* cmp,
                                    const Comparator* ucmp, IndexBlockIter* iter,
                                    Statistics* /*stats*/, bool total_order_seek,
                                    bool key_includes_seq, bool value_is_full,
+                                   bool block_contents_pinned,
                                    BlockPrefixIndex* prefix_index) {
   IndexBlockIter* ret_iter;
   if (iter != nullptr) {
@@ -876,7 +890,8 @@ IndexBlockIter* Block::NewIterator(const Comparator* cmp,
         total_order_seek ? nullptr : prefix_index;
     ret_iter->Initialize(cmp, ucmp, data_, restart_offset_, num_restarts_,
                          prefix_index_ptr, key_includes_seq, value_is_full,
-                         cachable(), nullptr /* data_block_hash_index */);
+                         block_contents_pinned,
+                         nullptr /* data_block_hash_index */);
   }
 
   return ret_iter;
diff --git a/3rdParty/rocksdb/v5.16.X/table/block.h b/3rdParty/rocksdb/v5.18.X/table/block.h
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/table/block.h
rename to 3rdParty/rocksdb/v5.18.X/table/block.h
index ee3f07b43b..1a8073203b 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block.h
+++ b/3rdParty/rocksdb/v5.18.X/table/block.h
@@ -153,14 +153,12 @@ class Block {
 
   size_t size() const { return size_; }
   const char* data() const { return data_; }
-  bool cachable() const { return contents_.cachable; }
   // The additional memory space taken by the block data.
   size_t usable_size() const { return contents_.usable_size(); }
   uint32_t NumRestarts() const;
+  bool own_bytes() const { return contents_.own_bytes(); }
+
   BlockBasedTableOptions::DataBlockIndexType IndexType() const;
-  CompressionType compression_type() const {
-    return contents_.compression_type;
-  }
 
   // If comparator is InternalKeyComparator, user_comparator is its user
   // comparator; they are equal otherwise.
@@ -170,7 +168,7 @@ class Block {
   //
   // key_includes_seq, default true, means that the keys are in internal key
   // format.
-  // value_is_full, default ture, means that no delta encoding is
+  // value_is_full, default true, means that no delta encoding is
   // applied to values.
   //
   // NewIterator<DataBlockIter>
@@ -180,6 +178,14 @@ class Block {
   // If `prefix_index` is not nullptr this block will do hash lookup for the key
   // prefix. If total_order_seek is true, prefix_index_ is ignored.
   //
+  // If `block_contents_pinned` is true, the caller will guarantee that when
+  // the cleanup functions are transferred from the iterator to other
+  // classes, e.g. PinnableSlice, the pointer to the bytes will still be
+  // valid. Either the iterator holds cache handle or ownership of some resource
+  // and release them in a release function, or caller is sure that the data
+  // will not go away (for example, it's from mmapped file which will not be
+  // closed).
+  //
   // NOTE: for the hash based lookup, if a key prefix doesn't match any key,
   // the iterator will simply be set as "invalid", rather than returning
   // the key that is just pass the target key.
@@ -188,7 +194,8 @@ class Block {
       const Comparator* comparator, const Comparator* user_comparator,
       TBlockIter* iter = nullptr, Statistics* stats = nullptr,
       bool total_order_seek = true, bool key_includes_seq = true,
-      bool value_is_full = true, BlockPrefixIndex* prefix_index = nullptr);
+      bool value_is_full = true, bool block_contents_pinned = false,
+      BlockPrefixIndex* prefix_index = nullptr);
 
   // Report an approximation of how much memory has been used.
   size_t ApproximateMemoryUsage() const;
@@ -295,7 +302,9 @@ class BlockIter : public InternalIteratorBase<TValue> {
   Slice value_;
   Status status_;
   bool key_pinned_;
-  // whether the block data is guaranteed to outlive this iterator
+  // Whether the block data is guaranteed to outlive this iterator, and
+  // as long as the cleanup functions are transferred to another class,
+  // e.g. PinnableSlice, the pointer to the bytes will still be valid.
   bool block_contents_pinned_;
   SequenceNumber global_seqno_;
 
@@ -449,7 +458,7 @@ class IndexBlockIter final : public BlockIter<BlockHandle> {
   }
   // key_includes_seq, default true, means that the keys are in internal key
   // format.
-  // value_is_full, default ture, means that no delta encoding is
+  // value_is_full, default true, means that no delta encoding is
   // applied to values.
   IndexBlockIter(const Comparator* comparator,
                  const Comparator* user_comparator, const char* data,
@@ -468,10 +477,10 @@ class IndexBlockIter final : public BlockIter<BlockHandle> {
                   BlockPrefixIndex* prefix_index, bool key_includes_seq,
                   bool value_is_full, bool block_contents_pinned,
                   DataBlockHashIndex* /*data_block_hash_index*/) {
-    InitializeBase(comparator, data, restarts, num_restarts,
-                   kDisableGlobalSequenceNumber, block_contents_pinned);
+    InitializeBase(key_includes_seq ? comparator : user_comparator, data,
+                   restarts, num_restarts, kDisableGlobalSequenceNumber,
+                   block_contents_pinned);
     key_includes_seq_ = key_includes_seq;
-    active_comparator_ = key_includes_seq_ ? comparator_ : user_comparator;
     key_.SetIsUserKey(!key_includes_seq_);
     prefix_index_ = prefix_index;
     value_delta_encoded_ = !value_is_full;
@@ -517,8 +526,6 @@ class IndexBlockIter final : public BlockIter<BlockHandle> {
   // Key is in InternalKey format
   bool key_includes_seq_;
   bool value_delta_encoded_;
-  // key_includes_seq_ ? comparator_ : user_comparator_
-  const Comparator* active_comparator_;
   BlockPrefixIndex* prefix_index_;
   // Whether the value is delta encoded. In that case the value is assumed to be
   // BlockHandle. The first value in each restart interval is the full encoded
@@ -535,11 +542,11 @@ class IndexBlockIter final : public BlockIter<BlockHandle> {
   inline int CompareBlockKey(uint32_t block_index, const Slice& target);
 
   inline int Compare(const Slice& a, const Slice& b) const {
-    return active_comparator_->Compare(a, b);
+    return comparator_->Compare(a, b);
   }
 
   inline int Compare(const IterKey& ikey, const Slice& b) const {
-    return active_comparator_->Compare(ikey.GetKey(), b);
+    return comparator_->Compare(ikey.GetKey(), b);
   }
 
   inline bool ParseNextIndexKey();
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_based_filter_block.cc b/3rdParty/rocksdb/v5.18.X/table/block_based_filter_block.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/block_based_filter_block.cc
rename to 3rdParty/rocksdb/v5.18.X/table/block_based_filter_block.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_based_filter_block.h b/3rdParty/rocksdb/v5.18.X/table/block_based_filter_block.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/block_based_filter_block.h
rename to 3rdParty/rocksdb/v5.18.X/table/block_based_filter_block.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_based_filter_block_test.cc b/3rdParty/rocksdb/v5.18.X/table/block_based_filter_block_test.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/table/block_based_filter_block_test.cc
rename to 3rdParty/rocksdb/v5.18.X/table/block_based_filter_block_test.cc
index 8de857f4ef..3cba09847a 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block_based_filter_block_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/block_based_filter_block_test.cc
@@ -55,7 +55,7 @@ class FilterBlockTest : public testing::Test {
 
 TEST_F(FilterBlockTest, EmptyBuilder) {
   BlockBasedFilterBlockBuilder builder(nullptr, table_options_);
-  BlockContents block(builder.Finish(), false, kNoCompression);
+  BlockContents block(builder.Finish());
   ASSERT_EQ("\\x00\\x00\\x00\\x00\\x0b", EscapeString(block.data));
   BlockBasedFilterBlockReader reader(nullptr, table_options_, true,
                                      std::move(block), nullptr);
@@ -75,7 +75,7 @@ TEST_F(FilterBlockTest, SingleChunk) {
   builder.StartBlock(300);
   builder.Add("hello");
   ASSERT_EQ(5, builder.NumAdded());
-  BlockContents block(builder.Finish(), false, kNoCompression);
+  BlockContents block(builder.Finish());
   BlockBasedFilterBlockReader reader(nullptr, table_options_, true,
                                      std::move(block), nullptr);
   ASSERT_TRUE(reader.KeyMayMatch("foo", nullptr, 100));
@@ -107,7 +107,7 @@ TEST_F(FilterBlockTest, MultiChunk) {
   builder.Add("box");
   builder.Add("hello");
 
-  BlockContents block(builder.Finish(), false, kNoCompression);
+  BlockContents block(builder.Finish());
   BlockBasedFilterBlockReader reader(nullptr, table_options_, true,
                                      std::move(block), nullptr);
 
@@ -152,7 +152,7 @@ class BlockBasedFilterBlockTest : public testing::Test {
 TEST_F(BlockBasedFilterBlockTest, BlockBasedEmptyBuilder) {
   FilterBlockBuilder* builder = new BlockBasedFilterBlockBuilder(
       nullptr, table_options_);
-  BlockContents block(builder->Finish(), false, kNoCompression);
+  BlockContents block(builder->Finish());
   ASSERT_EQ("\\x00\\x00\\x00\\x00\\x0b", EscapeString(block.data));
   FilterBlockReader* reader = new BlockBasedFilterBlockReader(
       nullptr, table_options_, true, std::move(block), nullptr);
@@ -174,7 +174,7 @@ TEST_F(BlockBasedFilterBlockTest, BlockBasedSingleChunk) {
   builder->Add("box");
   builder->StartBlock(300);
   builder->Add("hello");
-  BlockContents block(builder->Finish(), false, kNoCompression);
+  BlockContents block(builder->Finish());
   FilterBlockReader* reader = new BlockBasedFilterBlockReader(
       nullptr, table_options_, true, std::move(block), nullptr);
   ASSERT_TRUE(reader->KeyMayMatch("foo", nullptr, 100));
@@ -210,7 +210,7 @@ TEST_F(BlockBasedFilterBlockTest, BlockBasedMultiChunk) {
   builder->Add("box");
   builder->Add("hello");
 
-  BlockContents block(builder->Finish(), false, kNoCompression);
+  BlockContents block(builder->Finish());
   FilterBlockReader* reader = new BlockBasedFilterBlockReader(
       nullptr, table_options_, true, std::move(block), nullptr);
 
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_based_table_builder.cc b/3rdParty/rocksdb/v5.18.X/table/block_based_table_builder.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/table/block_based_table_builder.cc
rename to 3rdParty/rocksdb/v5.18.X/table/block_based_table_builder.cc
index 59c385d65a..a4007b07a2 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block_based_table_builder.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/block_based_table_builder.cc
@@ -42,6 +42,7 @@
 #include "util/coding.h"
 #include "util/compression.h"
 #include "util/crc32c.h"
+#include "util/memory_allocator.h"
 #include "util/stop_watch.h"
 #include "util/string_util.h"
 #include "util/xxhash.h"
@@ -449,6 +450,11 @@ void BlockBasedTableBuilder::Add(const Slice& key, const Slice& value) {
     r->props.num_entries++;
     r->props.raw_key_size += key.size();
     r->props.raw_value_size += value.size();
+    if (value_type == kTypeDeletion || value_type == kTypeSingleDeletion) {
+      r->props.num_deletions++;
+    } else if (value_type == kTypeMerge) {
+      r->props.num_merge_operands++;
+    }
 
     r->index_builder->OnKeyAdded(key);
     NotifyCollectTableCollectorsOnAdd(key, value, r->offset,
@@ -609,6 +615,18 @@ void BlockBasedTableBuilder::WriteRawBlock(const Slice& block_contents,
         EncodeFixed32(trailer_without_type, XXH32_digest(xxh));
         break;
       }
+      case kxxHash64: {
+        XXH64_state_t* const state = XXH64_createState();
+        XXH64_reset(state, 0);
+        XXH64_update(state, block_contents.data(),
+                static_cast<uint32_t>(block_contents.size()));
+        XXH64_update(state, trailer, 1);  // Extend  to cover block type
+        EncodeFixed32(trailer_without_type,
+          static_cast<uint32_t>(XXH64_digest(state) & // lower 32 bits
+                                   uint64_t{0xffffffff}));
+        XXH64_freeState(state);
+        break;
+      }
     }
 
     assert(r->status.ok());
@@ -636,9 +654,9 @@ Status BlockBasedTableBuilder::status() const {
   return rep_->status;
 }
 
-static void DeleteCachedBlock(const Slice& /*key*/, void* value) {
-  Block* block = reinterpret_cast<Block*>(value);
-  delete block;
+static void DeleteCachedBlockContents(const Slice& /*key*/, void* value) {
+  BlockContents* bc = reinterpret_cast<BlockContents*>(value);
+  delete bc;
 }
 
 //
@@ -654,13 +672,16 @@ Status BlockBasedTableBuilder::InsertBlockInCache(const Slice& block_contents,
 
     size_t size = block_contents.size();
 
-    std::unique_ptr<char[]> ubuf(new char[size + 1]);
+    auto ubuf =
+        AllocateBlock(size + 1, block_cache_compressed->memory_allocator());
     memcpy(ubuf.get(), block_contents.data(), size);
     ubuf[size] = type;
 
-    BlockContents results(std::move(ubuf), size, true, type);
-
-    Block* block = new Block(std::move(results), kDisableGlobalSequenceNumber);
+    BlockContents* block_contents_to_cache =
+        new BlockContents(std::move(ubuf), size);
+#ifndef NDEBUG
+    block_contents_to_cache->is_raw_block = true;
+#endif  // NDEBUG
 
     // make cache key by appending the file offset to the cache prefix id
     char* end = EncodeVarint64(
@@ -671,8 +692,10 @@ Status BlockBasedTableBuilder::InsertBlockInCache(const Slice& block_contents,
               (end - r->compressed_cache_key_prefix));
 
     // Insert into compressed block cache.
-    block_cache_compressed->Insert(key, block, block->ApproximateMemoryUsage(),
-                                   &DeleteCachedBlock);
+    block_cache_compressed->Insert(
+        key, block_contents_to_cache,
+        block_contents_to_cache->ApproximateMemoryUsage(),
+        &DeleteCachedBlockContents);
 
     // Invalidate OS cache.
     r->file->InvalidateCache(static_cast<size_t>(r->offset), size);
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_based_table_builder.h b/3rdParty/rocksdb/v5.18.X/table/block_based_table_builder.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/block_based_table_builder.h
rename to 3rdParty/rocksdb/v5.18.X/table/block_based_table_builder.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_based_table_factory.cc b/3rdParty/rocksdb/v5.18.X/table/block_based_table_factory.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/table/block_based_table_factory.cc
rename to 3rdParty/rocksdb/v5.18.X/table/block_based_table_factory.cc
index 485aed8704..fbb7406a3d 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block_based_table_factory.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/block_based_table_factory.cc
@@ -194,8 +194,8 @@ BlockBasedTableFactory::BlockBasedTableFactory(
 
 Status BlockBasedTableFactory::NewTableReader(
     const TableReaderOptions& table_reader_options,
-    unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
-    unique_ptr<TableReader>* table_reader,
+    std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+    std::unique_ptr<TableReader>* table_reader,
     bool prefetch_index_and_filter_in_cache) const {
   return BlockBasedTable::Open(
       table_reader_options.ioptions, table_reader_options.env_options,
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_based_table_factory.h b/3rdParty/rocksdb/v5.18.X/table/block_based_table_factory.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/table/block_based_table_factory.h
rename to 3rdParty/rocksdb/v5.18.X/table/block_based_table_factory.h
index b30bd6232a..cde6f65357 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block_based_table_factory.h
+++ b/3rdParty/rocksdb/v5.18.X/table/block_based_table_factory.h
@@ -53,8 +53,8 @@ class BlockBasedTableFactory : public TableFactory {
 
   Status NewTableReader(
       const TableReaderOptions& table_reader_options,
-      unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
-      unique_ptr<TableReader>* table_reader,
+      std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+      std::unique_ptr<TableReader>* table_reader,
       bool prefetch_index_and_filter_in_cache = true) const override;
 
   TableBuilder* NewTableBuilder(
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_based_table_reader.cc b/3rdParty/rocksdb/v5.18.X/table/block_based_table_reader.cc
similarity index 89%
rename from 3rdParty/rocksdb/v5.16.X/table/block_based_table_reader.cc
rename to 3rdParty/rocksdb/v5.18.X/table/block_based_table_reader.cc
index f240b84b10..a126de88c0 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block_based_table_reader.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/block_based_table_reader.cc
@@ -78,13 +78,14 @@ Status ReadBlockFromFile(
     RandomAccessFileReader* file, FilePrefetchBuffer* prefetch_buffer,
     const Footer& footer, const ReadOptions& options, const BlockHandle& handle,
     std::unique_ptr<Block>* result, const ImmutableCFOptions& ioptions,
-    bool do_uncompress, const Slice& compression_dict,
+    bool do_uncompress, bool maybe_compressed, const Slice& compression_dict,
     const PersistentCacheOptions& cache_options, SequenceNumber global_seqno,
-    size_t read_amp_bytes_per_bit, const bool immortal_file = false) {
+    size_t read_amp_bytes_per_bit, MemoryAllocator* memory_allocator) {
   BlockContents contents;
   BlockFetcher block_fetcher(file, prefetch_buffer, footer, options, handle,
                              &contents, ioptions, do_uncompress,
-                             compression_dict, cache_options, immortal_file);
+                             maybe_compressed, compression_dict, cache_options,
+                             memory_allocator);
   Status s = block_fetcher.ReadBlockContents();
   if (s.ok()) {
     result->reset(new Block(std::move(contents), global_seqno,
@@ -94,6 +95,20 @@ Status ReadBlockFromFile(
   return s;
 }
 
+inline MemoryAllocator* GetMemoryAllocator(
+    const BlockBasedTableOptions& table_options) {
+  return table_options.block_cache.get()
+             ? table_options.block_cache->memory_allocator()
+             : nullptr;
+}
+
+inline MemoryAllocator* GetMemoryAllocatorForCompressedBlock(
+    const BlockBasedTableOptions& table_options) {
+  return table_options.block_cache_compressed.get()
+             ? table_options.block_cache_compressed->memory_allocator()
+             : nullptr;
+}
+
 // Delete the resource that is held by the iterator.
 template <class ResourceType>
 void DeleteHeldResource(void* arg, void* /*ignored*/) {
@@ -215,13 +230,15 @@ class PartitionIndexReader : public IndexReader, public Cleanable {
                        IndexReader** index_reader,
                        const PersistentCacheOptions& cache_options,
                        const int level, const bool index_key_includes_seq,
-                       const bool index_value_is_full) {
+                       const bool index_value_is_full,
+                       MemoryAllocator* memory_allocator) {
     std::unique_ptr<Block> index_block;
     auto s = ReadBlockFromFile(
         file, prefetch_buffer, footer, ReadOptions(), index_handle,
         &index_block, ioptions, true /* decompress */,
-        Slice() /*compression dict*/, cache_options,
-        kDisableGlobalSequenceNumber, 0 /* read_amp_bytes_per_bit */);
+        true /*maybe_compressed*/, Slice() /*compression dict*/, cache_options,
+        kDisableGlobalSequenceNumber, 0 /* read_amp_bytes_per_bit */,
+        memory_allocator);
 
     if (s.ok()) {
       *index_reader = new PartitionIndexReader(
@@ -239,6 +256,8 @@ class PartitionIndexReader : public IndexReader, public Cleanable {
     Statistics* kNullStats = nullptr;
     // Filters are already checked before seeking the index
     if (!partition_map_.empty()) {
+      // We don't return pinned datat from index blocks, so no need
+      // to set `block_contents_pinned`.
       return NewTwoLevelIterator(
           new BlockBasedTable::PartitionedIndexIteratorState(
               table_, &partition_map_, index_key_includes_seq_,
@@ -250,6 +269,8 @@ class PartitionIndexReader : public IndexReader, public Cleanable {
       auto ro = ReadOptions();
       ro.fill_cache = fill_cache;
       bool kIsIndex = true;
+      // We don't return pinned datat from index blocks, so no need
+      // to set `block_contents_pinned`.
       return new BlockBasedTableIterator<IndexBlockIter, BlockHandle>(
           table_, ro, *icomparator_,
           index_block_->NewIterator<IndexBlockIter>(
@@ -270,6 +291,8 @@ class PartitionIndexReader : public IndexReader, public Cleanable {
     IndexBlockIter biter;
     BlockHandle handle;
     Statistics* kNullStats = nullptr;
+    // We don't return pinned datat from index blocks, so no need
+    // to set `block_contents_pinned`.
     index_block_->NewIterator<IndexBlockIter>(
         icomparator_, icomparator_->user_comparator(), &biter, kNullStats, true,
         index_key_includes_seq_, index_value_is_full_);
@@ -312,7 +335,7 @@ class PartitionIndexReader : public IndexReader, public Cleanable {
       const bool is_index = true;
       // TODO: Support counter batch update for partitioned index and
       // filter blocks
-      s = table_->MaybeLoadDataBlockToCache(
+      s = table_->MaybeReadBlockAndLoadToCache(
           prefetch_buffer.get(), rep, ro, handle, compression_dict, &block,
           is_index, nullptr /* get_context */);
 
@@ -388,13 +411,15 @@ class BinarySearchIndexReader : public IndexReader {
                        IndexReader** index_reader,
                        const PersistentCacheOptions& cache_options,
                        const bool index_key_includes_seq,
-                       const bool index_value_is_full) {
+                       const bool index_value_is_full,
+                       MemoryAllocator* memory_allocator) {
     std::unique_ptr<Block> index_block;
     auto s = ReadBlockFromFile(
         file, prefetch_buffer, footer, ReadOptions(), index_handle,
         &index_block, ioptions, true /* decompress */,
-        Slice() /*compression dict*/, cache_options,
-        kDisableGlobalSequenceNumber, 0 /* read_amp_bytes_per_bit */);
+        true /*maybe_compressed*/, Slice() /*compression dict*/, cache_options,
+        kDisableGlobalSequenceNumber, 0 /* read_amp_bytes_per_bit */,
+        memory_allocator);
 
     if (s.ok()) {
       *index_reader = new BinarySearchIndexReader(
@@ -409,6 +434,8 @@ class BinarySearchIndexReader : public IndexReader {
       IndexBlockIter* iter = nullptr, bool /*dont_care*/ = true,
       bool /*dont_care*/ = true) override {
     Statistics* kNullStats = nullptr;
+    // We don't return pinned datat from index blocks, so no need
+    // to set `block_contents_pinned`.
     return index_block_->NewIterator<IndexBlockIter>(
         icomparator_, icomparator_->user_comparator(), iter, kNullStats, true,
         index_key_includes_seq_, index_value_is_full_);
@@ -458,13 +485,15 @@ class HashIndexReader : public IndexReader {
       InternalIterator* meta_index_iter, IndexReader** index_reader,
       bool /*hash_index_allow_collision*/,
       const PersistentCacheOptions& cache_options,
-      const bool index_key_includes_seq, const bool index_value_is_full) {
+      const bool index_key_includes_seq, const bool index_value_is_full,
+      MemoryAllocator* memory_allocator) {
     std::unique_ptr<Block> index_block;
     auto s = ReadBlockFromFile(
         file, prefetch_buffer, footer, ReadOptions(), index_handle,
         &index_block, ioptions, true /* decompress */,
-        Slice() /*compression dict*/, cache_options,
-        kDisableGlobalSequenceNumber, 0 /* read_amp_bytes_per_bit */);
+        true /*maybe_compressed*/, Slice() /*compression dict*/, cache_options,
+        kDisableGlobalSequenceNumber, 0 /* read_amp_bytes_per_bit */,
+        memory_allocator);
 
     if (!s.ok()) {
       return s;
@@ -502,8 +531,9 @@ class HashIndexReader : public IndexReader {
     BlockContents prefixes_contents;
     BlockFetcher prefixes_block_fetcher(
         file, prefetch_buffer, footer, ReadOptions(), prefixes_handle,
-        &prefixes_contents, ioptions, true /* decompress */,
-        dummy_comp_dict /*compression dict*/, cache_options);
+        &prefixes_contents, ioptions, true /*decompress*/,
+        true /*maybe_compressed*/, dummy_comp_dict /*compression dict*/,
+        cache_options, memory_allocator);
     s = prefixes_block_fetcher.ReadBlockContents();
     if (!s.ok()) {
       return s;
@@ -511,8 +541,9 @@ class HashIndexReader : public IndexReader {
     BlockContents prefixes_meta_contents;
     BlockFetcher prefixes_meta_block_fetcher(
         file, prefetch_buffer, footer, ReadOptions(), prefixes_meta_handle,
-        &prefixes_meta_contents, ioptions, true /* decompress */,
-        dummy_comp_dict /*compression dict*/, cache_options);
+        &prefixes_meta_contents, ioptions, true /*decompress*/,
+        true /*maybe_compressed*/, dummy_comp_dict /*compression dict*/,
+        cache_options, memory_allocator);
     s = prefixes_meta_block_fetcher.ReadBlockContents();
     if (!s.ok()) {
       // TODO: log error
@@ -534,10 +565,12 @@ class HashIndexReader : public IndexReader {
       IndexBlockIter* iter = nullptr, bool total_order_seek = true,
       bool /*dont_care*/ = true) override {
     Statistics* kNullStats = nullptr;
+    // We don't return pinned datat from index blocks, so no need
+    // to set `block_contents_pinned`.
     return index_block_->NewIterator<IndexBlockIter>(
         icomparator_, icomparator_->user_comparator(), iter, kNullStats,
         total_order_seek, index_key_includes_seq_, index_value_is_full_,
-        prefix_index_.get());
+        false /* block_contents_pinned */, prefix_index_.get());
   }
 
   virtual size_t size() const override { return index_block_->size(); }
@@ -572,8 +605,7 @@ class HashIndexReader : public IndexReader {
     assert(index_block_ != nullptr);
   }
 
-  ~HashIndexReader() {
-  }
+  ~HashIndexReader() {}
 
   std::unique_ptr<Block> index_block_;
   std::unique_ptr<BlockPrefixIndex> prefix_index_;
@@ -737,9 +769,9 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
                              const EnvOptions& env_options,
                              const BlockBasedTableOptions& table_options,
                              const InternalKeyComparator& internal_comparator,
-                             unique_ptr<RandomAccessFileReader>&& file,
+                             std::unique_ptr<RandomAccessFileReader>&& file,
                              uint64_t file_size,
-                             unique_ptr<TableReader>* table_reader,
+                             std::unique_ptr<TableReader>* table_reader,
                              const SliceTransform* prefix_extractor,
                              const bool prefetch_index_and_filter_in_cache,
                              const bool skip_filters, const int level,
@@ -807,7 +839,7 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
   // raw pointer will be used to create HashIndexReader, whose reset may
   // access a dangling pointer.
   Rep* rep = new BlockBasedTable::Rep(ioptions, env_options, table_options,
-                                      internal_comparator, skip_filters,
+                                      internal_comparator, skip_filters, level,
                                       immortal_table);
   rep->file = std::move(file);
   rep->footer = footer;
@@ -818,7 +850,7 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
   rep->internal_prefix_transform.reset(
       new InternalKeySliceTransform(prefix_extractor));
   SetupCacheKeyPrefix(rep, file_size);
-  unique_ptr<BlockBasedTable> new_table(new BlockBasedTable(rep));
+  std::unique_ptr<BlockBasedTable> new_table(new BlockBasedTable(rep));
 
   // page cache options
   rep->persistent_cache_options =
@@ -878,7 +910,9 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
     if (s.ok()) {
       s = ReadProperties(meta_iter->value(), rep->file.get(),
                          prefetch_buffer.get(), rep->footer, rep->ioptions,
-                         &table_properties, false /* compression_type_missing */);
+                         &table_properties,
+                         false /* compression_type_missing */,
+                         nullptr /* memory_allocator */);
     }
 
     if (!s.ok()) {
@@ -921,9 +955,10 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
     ReadOptions read_options;
     read_options.verify_checksums = false;
     BlockFetcher compression_block_fetcher(
-      rep->file.get(), prefetch_buffer.get(), rep->footer, read_options,
-      compression_dict_handle, compression_dict_cont.get(), rep->ioptions, false /* decompress */,
-      Slice() /*compression dict*/, cache_options);
+        rep->file.get(), prefetch_buffer.get(), rep->footer, read_options,
+        compression_dict_handle, compression_dict_cont.get(), rep->ioptions,
+        false /* decompress */, false /*maybe_compressed*/,
+        Slice() /*compression dict*/, cache_options);
     s = compression_block_fetcher.ReadBlockContents();
 
     if (!s.ok()) {
@@ -964,20 +999,22 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
         rep->ioptions.info_log,
         "Error when seeking to range delete tombstones block from file: %s",
         s.ToString().c_str());
-  } else {
-    if (found_range_del_block && !rep->range_del_handle.IsNull()) {
-      ReadOptions read_options;
-      s = MaybeLoadDataBlockToCache(
-          prefetch_buffer.get(), rep, read_options, rep->range_del_handle,
-          Slice() /* compression_dict */, &rep->range_del_entry,
-          false /* is_index */, nullptr /* get_context */);
-      if (!s.ok()) {
-        ROCKS_LOG_WARN(
-            rep->ioptions.info_log,
-            "Encountered error while reading data from range del block %s",
-            s.ToString().c_str());
-      }
+  } else if (found_range_del_block && !rep->range_del_handle.IsNull()) {
+    ReadOptions read_options;
+    s = MaybeReadBlockAndLoadToCache(
+        prefetch_buffer.get(), rep, read_options, rep->range_del_handle,
+        Slice() /* compression_dict */, &rep->range_del_entry,
+        false /* is_index */, nullptr /* get_context */);
+    if (!s.ok()) {
+      ROCKS_LOG_WARN(
+          rep->ioptions.info_log,
+          "Encountered error while reading data from range del block %s",
+          s.ToString().c_str());
     }
+    auto iter = std::unique_ptr<InternalIterator>(
+        new_table->NewUnfragmentedRangeTombstoneIterator(read_options));
+    rep->fragmented_range_dels = std::make_shared<FragmentedRangeTombstoneList>(
+        std::move(iter), internal_comparator);
   }
 
   bool need_upper_bound_check =
@@ -1019,7 +1056,7 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
       bool disable_prefix_seek =
           rep->index_type == BlockBasedTableOptions::kHashSearch &&
           need_upper_bound_check;
-      unique_ptr<InternalIteratorBase<BlockHandle>> iter(
+      std::unique_ptr<InternalIteratorBase<BlockHandle>> iter(
           new_table->NewIndexIterator(ReadOptions(), disable_prefix_seek,
                                       nullptr, &index_entry));
       s = iter->status();
@@ -1094,7 +1131,7 @@ Status BlockBasedTable::Open(const ImmutableCFOptions& ioptions,
     if (tail_prefetch_stats != nullptr) {
       assert(prefetch_buffer->min_offset_read() < file_size);
       tail_prefetch_stats->RecordEffectiveSize(
-          file_size - prefetch_buffer->min_offset_read());
+        static_cast<size_t>(file_size) - prefetch_buffer->min_offset_read());
     }
     *table_reader = std::move(new_table);
   }
@@ -1148,9 +1185,10 @@ Status BlockBasedTable::ReadMetaBlock(Rep* rep,
   Status s = ReadBlockFromFile(
       rep->file.get(), prefetch_buffer, rep->footer, ReadOptions(),
       rep->footer.metaindex_handle(), &meta, rep->ioptions,
-      true /* decompress */, Slice() /*compression dict*/,
-      rep->persistent_cache_options, kDisableGlobalSequenceNumber,
-      0 /* read_amp_bytes_per_bit */);
+      true /* decompress */, true /*maybe_compressed*/,
+      Slice() /*compression dict*/, rep->persistent_cache_options,
+      kDisableGlobalSequenceNumber, 0 /* read_amp_bytes_per_bit */,
+      GetMemoryAllocator(rep->table_options));
 
   if (!s.ok()) {
     ROCKS_LOG_ERROR(rep->ioptions.info_log,
@@ -1169,15 +1207,14 @@ Status BlockBasedTable::ReadMetaBlock(Rep* rep,
 
 Status BlockBasedTable::GetDataBlockFromCache(
     const Slice& block_cache_key, const Slice& compressed_block_cache_key,
-    Cache* block_cache, Cache* block_cache_compressed,
-    const ImmutableCFOptions& ioptions, const ReadOptions& read_options,
-    BlockBasedTable::CachableEntry<Block>* block, uint32_t format_version,
-    const Slice& compression_dict, size_t read_amp_bytes_per_bit, bool is_index,
-    GetContext* get_context) {
+    Cache* block_cache, Cache* block_cache_compressed, Rep* rep,
+    const ReadOptions& read_options,
+    BlockBasedTable::CachableEntry<Block>* block, const Slice& compression_dict,
+    size_t read_amp_bytes_per_bit, bool is_index, GetContext* get_context) {
   Status s;
-  Block* compressed_block = nullptr;
+  BlockContents* compressed_block = nullptr;
   Cache::Handle* block_cache_compressed_handle = nullptr;
-  Statistics* statistics = ioptions.statistics;
+  Statistics* statistics = rep->ioptions.statistics;
 
   // Lookup uncompressed cache first
   if (block_cache != nullptr) {
@@ -1220,32 +1257,34 @@ Status BlockBasedTable::GetDataBlockFromCache(
 
   // found compressed block
   RecordTick(statistics, BLOCK_CACHE_COMPRESSED_HIT);
-  compressed_block = reinterpret_cast<Block*>(
+  compressed_block = reinterpret_cast<BlockContents*>(
       block_cache_compressed->Value(block_cache_compressed_handle));
-  assert(compressed_block->compression_type() != kNoCompression);
+  CompressionType compression_type = compressed_block->get_compression_type();
+  assert(compression_type != kNoCompression);
 
   // Retrieve the uncompressed contents into a new buffer
   BlockContents contents;
-  UncompressionContext uncompresssion_ctx(compressed_block->compression_type(),
-                                          compression_dict);
-  s = UncompressBlockContents(uncompresssion_ctx, compressed_block->data(),
-                              compressed_block->size(), &contents,
-                              format_version, ioptions);
+  UncompressionContext uncompresssion_ctx(compression_type, compression_dict);
+  s = UncompressBlockContents(uncompresssion_ctx, compressed_block->data.data(),
+                              compressed_block->data.size(), &contents,
+                              rep->table_options.format_version, rep->ioptions,
+                              GetMemoryAllocator(rep->table_options));
 
   // Insert uncompressed block into block cache
   if (s.ok()) {
     block->value =
-        new Block(std::move(contents), compressed_block->global_seqno(),
+        new Block(std::move(contents), rep->get_global_seqno(is_index),
                   read_amp_bytes_per_bit,
                   statistics);  // uncompressed block
-    assert(block->value->compression_type() == kNoCompression);
-    if (block_cache != nullptr && block->value->cachable() &&
+    if (block_cache != nullptr && block->value->own_bytes() &&
         read_options.fill_cache) {
       size_t charge = block->value->ApproximateMemoryUsage();
       s = block_cache->Insert(block_cache_key, block->value, charge,
                               &DeleteCachedEntry<Block>,
                               &(block->cache_handle));
+#ifndef NDEBUG
       block_cache->TEST_mark_as_data_block(block_cache_key, charge);
+#endif  // NDEBUG
       if (s.ok()) {
         if (get_context != nullptr) {
           get_context->get_context_stats_.num_cache_add++;
@@ -1290,64 +1329,77 @@ Status BlockBasedTable::PutDataBlockToCache(
     const Slice& block_cache_key, const Slice& compressed_block_cache_key,
     Cache* block_cache, Cache* block_cache_compressed,
     const ReadOptions& /*read_options*/, const ImmutableCFOptions& ioptions,
-    CachableEntry<Block>* block, Block* raw_block, uint32_t format_version,
-    const Slice& compression_dict, size_t read_amp_bytes_per_bit, bool is_index,
-    Cache::Priority priority, GetContext* get_context) {
-  assert(raw_block->compression_type() == kNoCompression ||
+    CachableEntry<Block>* cached_block, BlockContents* raw_block_contents,
+    CompressionType raw_block_comp_type, uint32_t format_version,
+    const Slice& compression_dict, SequenceNumber seq_no,
+    size_t read_amp_bytes_per_bit, MemoryAllocator* memory_allocator,
+    bool is_index, Cache::Priority priority, GetContext* get_context) {
+  assert(raw_block_comp_type == kNoCompression ||
          block_cache_compressed != nullptr);
 
   Status s;
   // Retrieve the uncompressed contents into a new buffer
-  BlockContents contents;
+  BlockContents uncompressed_block_contents;
   Statistics* statistics = ioptions.statistics;
-  if (raw_block->compression_type() != kNoCompression) {
-    UncompressionContext uncompression_ctx(raw_block->compression_type(),
+  if (raw_block_comp_type != kNoCompression) {
+    UncompressionContext uncompression_ctx(raw_block_comp_type,
                                            compression_dict);
-    s = UncompressBlockContents(uncompression_ctx, raw_block->data(),
-                                raw_block->size(), &contents, format_version,
-                                ioptions);
+    s = UncompressBlockContents(
+        uncompression_ctx, raw_block_contents->data.data(),
+        raw_block_contents->data.size(), &uncompressed_block_contents,
+        format_version, ioptions, memory_allocator);
   }
   if (!s.ok()) {
-    delete raw_block;
     return s;
   }
 
-  if (raw_block->compression_type() != kNoCompression) {
-    block->value = new Block(std::move(contents), raw_block->global_seqno(),
-                             read_amp_bytes_per_bit,
-                             statistics);  // uncompressed block
+  if (raw_block_comp_type != kNoCompression) {
+    cached_block->value = new Block(std::move(uncompressed_block_contents),
+                                    seq_no, read_amp_bytes_per_bit,
+                                    statistics);  // uncompressed block
   } else {
-    block->value = raw_block;
-    raw_block = nullptr;
+    cached_block->value =
+        new Block(std::move(*raw_block_contents), seq_no,
+                  read_amp_bytes_per_bit, ioptions.statistics);
   }
 
   // Insert compressed block into compressed block cache.
   // Release the hold on the compressed cache entry immediately.
-  if (block_cache_compressed != nullptr && raw_block != nullptr &&
-      raw_block->cachable()) {
-    s = block_cache_compressed->Insert(compressed_block_cache_key, raw_block,
-                                       raw_block->ApproximateMemoryUsage(),
-                                       &DeleteCachedEntry<Block>);
+  if (block_cache_compressed != nullptr &&
+      raw_block_comp_type != kNoCompression && raw_block_contents != nullptr &&
+      raw_block_contents->own_bytes()) {
+#ifndef NDEBUG
+    assert(raw_block_contents->is_raw_block);
+#endif  // NDEBUG
+
+    // We cannot directly put raw_block_contents because this could point to
+    // an object in the stack.
+    BlockContents* block_cont_for_comp_cache =
+        new BlockContents(std::move(*raw_block_contents));
+    s = block_cache_compressed->Insert(
+        compressed_block_cache_key, block_cont_for_comp_cache,
+        block_cont_for_comp_cache->ApproximateMemoryUsage(),
+        &DeleteCachedEntry<BlockContents>);
     if (s.ok()) {
       // Avoid the following code to delete this cached block.
-      raw_block = nullptr;
       RecordTick(statistics, BLOCK_CACHE_COMPRESSED_ADD);
     } else {
       RecordTick(statistics, BLOCK_CACHE_COMPRESSED_ADD_FAILURES);
+      delete block_cont_for_comp_cache;
     }
   }
-  delete raw_block;
 
   // insert into uncompressed block cache
-  assert((block->value->compression_type() == kNoCompression));
-  if (block_cache != nullptr && block->value->cachable()) {
-    size_t charge = block->value->ApproximateMemoryUsage();
-    s = block_cache->Insert(block_cache_key, block->value, charge,
-                            &DeleteCachedEntry<Block>, &(block->cache_handle),
-                            priority);
+  if (block_cache != nullptr && cached_block->value->own_bytes()) {
+    size_t charge = cached_block->value->ApproximateMemoryUsage();
+    s = block_cache->Insert(block_cache_key, cached_block->value, charge,
+                            &DeleteCachedEntry<Block>,
+                            &(cached_block->cache_handle), priority);
+#ifndef NDEBUG
     block_cache->TEST_mark_as_data_block(block_cache_key, charge);
+#endif  // NDEBUG
     if (s.ok()) {
-      assert(block->cache_handle != nullptr);
+      assert(cached_block->cache_handle != nullptr);
       if (get_context != nullptr) {
         get_context->get_context_stats_.num_cache_add++;
         get_context->get_context_stats_.num_cache_bytes_write += charge;
@@ -1373,12 +1425,12 @@ Status BlockBasedTable::PutDataBlockToCache(
           RecordTick(statistics, BLOCK_CACHE_DATA_BYTES_INSERT, charge);
         }
       }
-      assert(reinterpret_cast<Block*>(
-                 block_cache->Value(block->cache_handle)) == block->value);
+      assert(reinterpret_cast<Block*>(block_cache->Value(
+                 cached_block->cache_handle)) == cached_block->value);
     } else {
       RecordTick(statistics, BLOCK_CACHE_ADD_FAILURES);
-      delete block->value;
-      block->value = nullptr;
+      delete cached_block->value;
+      cached_block->value = nullptr;
     }
   }
 
@@ -1399,10 +1451,11 @@ FilterBlockReader* BlockBasedTable::ReadFilter(
 
   Slice dummy_comp_dict;
 
-  BlockFetcher block_fetcher(rep->file.get(), prefetch_buffer, rep->footer,
-                             ReadOptions(), filter_handle, &block,
-                             rep->ioptions, false /* decompress */,
-                             dummy_comp_dict, rep->persistent_cache_options);
+  BlockFetcher block_fetcher(
+      rep->file.get(), prefetch_buffer, rep->footer, ReadOptions(),
+      filter_handle, &block, rep->ioptions, false /* decompress */,
+      false /*maybe_compressed*/, dummy_comp_dict,
+      rep->persistent_cache_options, GetMemoryAllocator(rep->table_options));
   Status s = block_fetcher.ReadBlockContents();
 
   if (!s.ok()) {
@@ -1551,12 +1604,16 @@ InternalIteratorBase<BlockHandle>* BlockBasedTable::NewIndexIterator(
     GetContext* get_context) {
   // index reader has already been pre-populated.
   if (rep_->index_reader) {
+    // We don't return pinned datat from index blocks, so no need
+    // to set `block_contents_pinned`.
     return rep_->index_reader->NewIterator(
         input_iter, read_options.total_order_seek || disable_prefix_seek,
         read_options.fill_cache);
   }
   // we have a pinned index block
   if (rep_->index_entry.IsSet()) {
+    // We don't return pinned datat from index blocks, so no need
+    // to set `block_contents_pinned`.
     return rep_->index_entry.value->NewIterator(
         input_iter, read_options.total_order_seek || disable_prefix_seek,
         read_options.fill_cache);
@@ -1639,6 +1696,8 @@ InternalIteratorBase<BlockHandle>* BlockBasedTable::NewIndexIterator(
   }
 
   assert(cache_handle);
+  // We don't return pinned datat from index blocks, so no need
+  // to set `block_contents_pinned`.
   auto* iter = index_reader->NewIterator(
       input_iter, read_options.total_order_seek || disable_prefix_seek);
 
@@ -1673,9 +1732,9 @@ TBlockIter* BlockBasedTable::NewDataBlockIterator(
     if (rep->compression_dict_block) {
       compression_dict = rep->compression_dict_block->data;
     }
-    s = MaybeLoadDataBlockToCache(prefetch_buffer, rep, ro, handle,
-                                  compression_dict, &block, is_index,
-                                  get_context);
+    s = MaybeReadBlockAndLoadToCache(prefetch_buffer, rep, ro, handle,
+                                     compression_dict, &block, is_index,
+                                     get_context);
   }
 
   TBlockIter* iter;
@@ -1697,10 +1756,13 @@ TBlockIter* BlockBasedTable::NewDataBlockIterator(
                    READ_BLOCK_GET_MICROS);
       s = ReadBlockFromFile(
           rep->file.get(), prefetch_buffer, rep->footer, ro, handle,
-          &block_value, rep->ioptions, rep->blocks_maybe_compressed,
-          compression_dict, rep->persistent_cache_options,
+          &block_value, rep->ioptions,
+          rep->blocks_maybe_compressed /*do_decompress*/,
+          rep->blocks_maybe_compressed, compression_dict,
+          rep->persistent_cache_options,
           is_index ? kDisableGlobalSequenceNumber : rep->global_seqno,
-          rep->table_options.read_amp_bytes_per_bit, rep->immortal_table);
+          rep->table_options.read_amp_bytes_per_bit,
+          GetMemoryAllocator(rep->table_options));
     }
     if (s.ok()) {
       block.value = block_value.release();
@@ -1710,10 +1772,20 @@ TBlockIter* BlockBasedTable::NewDataBlockIterator(
   if (s.ok()) {
     assert(block.value != nullptr);
     const bool kTotalOrderSeek = true;
+    // Block contents are pinned and it is still pinned after the iterator
+    // is destoryed as long as cleanup functions are moved to another object,
+    // when:
+    // 1. block cache handle is set to be released in cleanup function, or
+    // 2. it's pointing to immortable source. If own_bytes is true then we are
+    //    not reading data from the original source, weather immortal or not.
+    //    Otherwise, the block is pinned iff the source is immortal.
+    bool block_contents_pinned =
+        (block.cache_handle != nullptr ||
+         (!block.value->own_bytes() && rep->immortal_table));
     iter = block.value->NewIterator<TBlockIter>(
         &rep->internal_comparator, rep->internal_comparator.user_comparator(),
         iter, rep->ioptions.statistics, kTotalOrderSeek, key_includes_seq,
-        index_key_is_full);
+        index_key_is_full, block_contents_pinned);
     if (block.cache_handle != nullptr) {
       iter->RegisterCleanup(&ReleaseCachedEntry, block_cache,
                             block.cache_handle);
@@ -1722,7 +1794,7 @@ TBlockIter* BlockBasedTable::NewDataBlockIterator(
         // insert a dummy record to block cache to track the memory usage
         Cache::Handle* cache_handle;
         // There are two other types of cache keys: 1) SST cache key added in
-        // `MaybeLoadDataBlockToCache` 2) dummy cache key added in
+        // `MaybeReadBlockAndLoadToCache` 2) dummy cache key added in
         // `write_buffer_manager`. Use longer prefix (41 bytes) to differentiate
         // from SST cache key(31 bytes), and use non-zero prefix to
         // differentiate from `write_buffer_manager`
@@ -1758,25 +1830,28 @@ TBlockIter* BlockBasedTable::NewDataBlockIterator(
   return iter;
 }
 
-Status BlockBasedTable::MaybeLoadDataBlockToCache(
+Status BlockBasedTable::MaybeReadBlockAndLoadToCache(
     FilePrefetchBuffer* prefetch_buffer, Rep* rep, const ReadOptions& ro,
     const BlockHandle& handle, Slice compression_dict,
     CachableEntry<Block>* block_entry, bool is_index, GetContext* get_context) {
   assert(block_entry != nullptr);
   const bool no_io = (ro.read_tier == kBlockCacheTier);
   Cache* block_cache = rep->table_options.block_cache.get();
-  Cache* block_cache_compressed =
-      rep->table_options.block_cache_compressed.get();
 
+  // No point to cache compressed blocks if it never goes away
+  Cache* block_cache_compressed =
+      rep->immortal_table ? nullptr
+                          : rep->table_options.block_cache_compressed.get();
+
+  // First, try to get the block from the cache
+  //
   // If either block cache is enabled, we'll try to read from it.
   Status s;
+  char cache_key[kMaxCacheKeyPrefixSize + kMaxVarint64Length];
+  char compressed_cache_key[kMaxCacheKeyPrefixSize + kMaxVarint64Length];
+  Slice key /* key to the block cache */;
+  Slice ckey /* key to the compressed block cache */;
   if (block_cache != nullptr || block_cache_compressed != nullptr) {
-    Statistics* statistics = rep->ioptions.statistics;
-    char cache_key[kMaxCacheKeyPrefixSize + kMaxVarint64Length];
-    char compressed_cache_key[kMaxCacheKeyPrefixSize + kMaxVarint64Length];
-    Slice key, /* key to the block cache */
-        ckey /* key to the compressed block cache */;
-
     // create key for block cache
     if (block_cache != nullptr) {
       key = GetCacheKey(rep->cache_key_prefix, rep->cache_key_prefix_size,
@@ -1789,30 +1864,42 @@ Status BlockBasedTable::MaybeLoadDataBlockToCache(
                          compressed_cache_key);
     }
 
-    s = GetDataBlockFromCache(
-        key, ckey, block_cache, block_cache_compressed, rep->ioptions, ro,
-        block_entry, rep->table_options.format_version, compression_dict,
-        rep->table_options.read_amp_bytes_per_bit, is_index, get_context);
+    s = GetDataBlockFromCache(key, ckey, block_cache, block_cache_compressed,
+                              rep, ro, block_entry, compression_dict,
+                              rep->table_options.read_amp_bytes_per_bit,
+                              is_index, get_context);
 
+    // Can't find the block from the cache. If I/O is allowed, read from the
+    // file.
     if (block_entry->value == nullptr && !no_io && ro.fill_cache) {
-      std::unique_ptr<Block> raw_block;
+      Statistics* statistics = rep->ioptions.statistics;
+      bool do_decompress =
+          block_cache_compressed == nullptr && rep->blocks_maybe_compressed;
+      CompressionType raw_block_comp_type;
+      BlockContents raw_block_contents;
       {
         StopWatch sw(rep->ioptions.env, statistics, READ_BLOCK_GET_MICROS);
-        s = ReadBlockFromFile(
+        BlockFetcher block_fetcher(
             rep->file.get(), prefetch_buffer, rep->footer, ro, handle,
-            &raw_block, rep->ioptions,
-            block_cache_compressed == nullptr && rep->blocks_maybe_compressed,
+            &raw_block_contents, rep->ioptions,
+            do_decompress /* do uncompress */, rep->blocks_maybe_compressed,
             compression_dict, rep->persistent_cache_options,
-            is_index ? kDisableGlobalSequenceNumber : rep->global_seqno,
-            rep->table_options.read_amp_bytes_per_bit, rep->immortal_table);
+            GetMemoryAllocator(rep->table_options),
+            GetMemoryAllocatorForCompressedBlock(rep->table_options));
+        s = block_fetcher.ReadBlockContents();
+        raw_block_comp_type = block_fetcher.get_compression_type();
       }
 
       if (s.ok()) {
+        SequenceNumber seq_no = rep->get_global_seqno(is_index);
+        // If filling cache is allowed and a cache is configured, try to put the
+        // block to the cache.
         s = PutDataBlockToCache(
             key, ckey, block_cache, block_cache_compressed, ro, rep->ioptions,
-            block_entry, raw_block.release(), rep->table_options.format_version,
-            compression_dict, rep->table_options.read_amp_bytes_per_bit,
-            is_index,
+            block_entry, &raw_block_contents, raw_block_comp_type,
+            rep->table_options.format_version, compression_dict, seq_no,
+            rep->table_options.read_amp_bytes_per_bit,
+            GetMemoryAllocator(rep->table_options), is_index,
             is_index && rep->table_options
                             .cache_index_and_filter_blocks_with_high_priority
                 ? Cache::Priority::HIGH
@@ -1855,6 +1942,8 @@ BlockBasedTable::PartitionedIndexIteratorState::NewSecondaryIterator(
     RecordTick(rep->ioptions.statistics, BLOCK_CACHE_BYTES_READ,
                block_cache->GetUsage(block->second.cache_handle));
     Statistics* kNullStats = nullptr;
+    // We don't return pinned datat from index blocks, so no need
+    // to set `block_contents_pinned`.
     return block->second.value->NewIterator<IndexBlockIter>(
         &rep->internal_comparator, rep->internal_comparator.user_comparator(),
         nullptr, kNullStats, true, index_key_includes_seq_, index_key_is_full_);
@@ -1933,7 +2022,7 @@ bool BlockBasedTable::PrefixMayMatch(
       // Then, try find it within each block
       // we already know prefix_extractor and prefix_extractor_name must match
       // because `CheckPrefixMayMatch` first checks `check_filter_ == true`
-      unique_ptr<InternalIteratorBase<BlockHandle>> iiter(
+      std::unique_ptr<InternalIteratorBase<BlockHandle>> iiter(
           NewIndexIterator(no_io_read_options,
                            /* need_upper_bound_check */ false));
       iiter->Seek(internal_prefix);
@@ -2249,7 +2338,20 @@ InternalIterator* BlockBasedTable::NewIterator(
   }
 }
 
-InternalIterator* BlockBasedTable::NewRangeTombstoneIterator(
+FragmentedRangeTombstoneIterator* BlockBasedTable::NewRangeTombstoneIterator(
+    const ReadOptions& read_options) {
+  if (rep_->fragmented_range_dels == nullptr) {
+    return nullptr;
+  }
+  SequenceNumber snapshot = kMaxSequenceNumber;
+  if (read_options.snapshot != nullptr) {
+    snapshot = read_options.snapshot->GetSequenceNumber();
+  }
+  return new FragmentedRangeTombstoneIterator(
+      rep_->fragmented_range_dels, rep_->internal_comparator, snapshot);
+}
+
+InternalIterator* BlockBasedTable::NewUnfragmentedRangeTombstoneIterator(
     const ReadOptions& read_options) {
   if (rep_->range_del_handle.IsNull()) {
     // The block didn't exist, nullptr indicates no range tombstones.
@@ -2302,6 +2404,7 @@ bool BlockBasedTable::FullFilterKeyMayMatch(
   }
   if (may_match) {
     RecordTick(rep_->ioptions.statistics, BLOOM_FILTER_FULL_POSITIVE);
+    PERF_COUNTER_BY_LEVEL_ADD(bloom_filter_full_positive, 1, rep_->level);
   }
   return may_match;
 }
@@ -2326,6 +2429,7 @@ Status BlockBasedTable::Get(const ReadOptions& read_options, const Slice& key,
   if (!FullFilterKeyMayMatch(read_options, filter, key, no_io,
                              prefix_extractor)) {
     RecordTick(rep_->ioptions.statistics, BLOOM_FILTER_USEFUL);
+    PERF_COUNTER_BY_LEVEL_ADD(bloom_filter_useful, 1, rep_->level);
   } else {
     IndexBlockIter iiter_on_stack;
     // if prefix_extractor found in block differs from options, disable
@@ -2358,6 +2462,7 @@ Status BlockBasedTable::Get(const ReadOptions& read_options, const Slice& key,
         // TODO: think about interaction with Merge. If a user key cannot
         // cross one data block, we should be fine.
         RecordTick(rep_->ioptions.statistics, BLOOM_FILTER_USEFUL);
+        PERF_COUNTER_BY_LEVEL_ADD(bloom_filter_useful, 1, rep_->level);
         break;
       } else {
         DataBlockIter biter;
@@ -2410,6 +2515,8 @@ Status BlockBasedTable::Get(const ReadOptions& read_options, const Slice& key,
     }
     if (matched && filter != nullptr && !filter->IsBlockBased()) {
       RecordTick(rep_->ioptions.statistics, BLOOM_FILTER_FULL_TRUE_POSITIVE);
+      PERF_COUNTER_BY_LEVEL_ADD(bloom_filter_full_true_positive, 1,
+                                rep_->level);
     }
     if (s.ok()) {
       s = iiter->status();
@@ -2524,11 +2631,11 @@ Status BlockBasedTable::VerifyChecksumInBlocks(
     BlockHandle handle = index_iter->value();
     BlockContents contents;
     Slice dummy_comp_dict;
-    BlockFetcher block_fetcher(rep_->file.get(), nullptr /* prefetch buffer */,
-                               rep_->footer, ReadOptions(), handle, &contents,
-                               rep_->ioptions, false /* decompress */,
-                               dummy_comp_dict /*compression dict*/,
-                               rep_->persistent_cache_options);
+    BlockFetcher block_fetcher(
+        rep_->file.get(), nullptr /* prefetch buffer */, rep_->footer,
+        ReadOptions(), handle, &contents, rep_->ioptions,
+        false /* decompress */, false /*maybe_compressed*/,
+        dummy_comp_dict /*compression dict*/, rep_->persistent_cache_options);
     s = block_fetcher.ReadBlockContents();
     if (!s.ok()) {
       break;
@@ -2550,11 +2657,11 @@ Status BlockBasedTable::VerifyChecksumInBlocks(
     s = handle.DecodeFrom(&input);
     BlockContents contents;
     Slice dummy_comp_dict;
-    BlockFetcher block_fetcher(rep_->file.get(), nullptr /* prefetch buffer */,
-                               rep_->footer, ReadOptions(), handle, &contents,
-                               rep_->ioptions, false /* decompress */,
-                               dummy_comp_dict /*compression dict*/,
-                               rep_->persistent_cache_options);
+    BlockFetcher block_fetcher(
+        rep_->file.get(), nullptr /* prefetch buffer */, rep_->footer,
+        ReadOptions(), handle, &contents, rep_->ioptions,
+        false /* decompress */, false /*maybe_compressed*/,
+        dummy_comp_dict /*compression dict*/, rep_->persistent_cache_options);
     s = block_fetcher.ReadBlockContents();
     if (!s.ok()) {
       break;
@@ -2583,8 +2690,7 @@ bool BlockBasedTable::TEST_KeyInCache(const ReadOptions& options,
 
   Status s;
   s = GetDataBlockFromCache(
-      cache_key, ckey, block_cache, nullptr, rep_->ioptions, options, &block,
-      rep_->table_options.format_version,
+      cache_key, ckey, block_cache, nullptr, rep_, options, &block,
       rep_->compression_dict_block ? rep_->compression_dict_block->data
                                    : Slice(),
       0 /* read_amp_bytes_per_bit */);
@@ -2644,7 +2750,8 @@ Status BlockBasedTable::CreateIndexReader(
           rep_->table_properties == nullptr ||
               rep_->table_properties->index_key_is_user_key == 0,
           rep_->table_properties == nullptr ||
-              rep_->table_properties->index_value_is_delta_encoded == 0);
+              rep_->table_properties->index_value_is_delta_encoded == 0,
+          GetMemoryAllocator(rep_->table_options));
     }
     case BlockBasedTableOptions::kBinarySearch: {
       return BinarySearchIndexReader::Create(
@@ -2653,7 +2760,8 @@ Status BlockBasedTable::CreateIndexReader(
           rep_->table_properties == nullptr ||
               rep_->table_properties->index_key_is_user_key == 0,
           rep_->table_properties == nullptr ||
-              rep_->table_properties->index_value_is_delta_encoded == 0);
+              rep_->table_properties->index_value_is_delta_encoded == 0,
+          GetMemoryAllocator(rep_->table_options));
     }
     case BlockBasedTableOptions::kHashSearch: {
       std::unique_ptr<Block> meta_guard;
@@ -2675,7 +2783,8 @@ Status BlockBasedTable::CreateIndexReader(
               rep_->table_properties == nullptr ||
                   rep_->table_properties->index_key_is_user_key == 0,
               rep_->table_properties == nullptr ||
-                  rep_->table_properties->index_value_is_delta_encoded == 0);
+                  rep_->table_properties->index_value_is_delta_encoded == 0,
+              GetMemoryAllocator(rep_->table_options));
         }
         meta_index_iter = meta_iter_guard.get();
       }
@@ -2688,7 +2797,8 @@ Status BlockBasedTable::CreateIndexReader(
           rep_->table_properties == nullptr ||
               rep_->table_properties->index_key_is_user_key == 0,
           rep_->table_properties == nullptr ||
-              rep_->table_properties->index_value_is_delta_encoded == 0);
+              rep_->table_properties->index_value_is_delta_encoded == 0,
+          GetMemoryAllocator(rep_->table_options));
     }
     default: {
       std::string error_message =
@@ -2699,7 +2809,7 @@ Status BlockBasedTable::CreateIndexReader(
 }
 
 uint64_t BlockBasedTable::ApproximateOffsetOf(const Slice& key) {
-  unique_ptr<InternalIteratorBase<BlockHandle>> index_iter(
+  std::unique_ptr<InternalIteratorBase<BlockHandle>> index_iter(
       NewIndexIterator(ReadOptions()));
 
   index_iter->Seek(key);
@@ -2857,7 +2967,8 @@ Status BlockBasedTable::DumpTable(WritableFile* out_file,
           BlockFetcher block_fetcher(
               rep_->file.get(), nullptr /* prefetch_buffer */, rep_->footer,
               ReadOptions(), handle, &block, rep_->ioptions,
-              false /*decompress*/, dummy_comp_dict /*compression dict*/,
+              false /*decompress*/, false /*maybe_compressed*/,
+              dummy_comp_dict /*compression dict*/,
               rep_->persistent_cache_options);
           s = block_fetcher.ReadBlockContents();
           if (!s.ok()) {
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_based_table_reader.h b/3rdParty/rocksdb/v5.18.X/table/block_based_table_reader.h
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/table/block_based_table_reader.h
rename to 3rdParty/rocksdb/v5.18.X/table/block_based_table_reader.h
index 3cada0c2c2..cb6a865660 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block_based_table_reader.h
+++ b/3rdParty/rocksdb/v5.18.X/table/block_based_table_reader.h
@@ -16,6 +16,7 @@
 #include <utility>
 #include <vector>
 
+#include "db/range_tombstone_fragmenter.h"
 #include "options/cf_options.h"
 #include "rocksdb/options.h"
 #include "rocksdb/persistent_cache.h"
@@ -88,8 +89,9 @@ class BlockBasedTable : public TableReader {
                      const EnvOptions& env_options,
                      const BlockBasedTableOptions& table_options,
                      const InternalKeyComparator& internal_key_comparator,
-                     unique_ptr<RandomAccessFileReader>&& file,
-                     uint64_t file_size, unique_ptr<TableReader>* table_reader,
+                     std::unique_ptr<RandomAccessFileReader>&& file,
+                     uint64_t file_size,
+                     std::unique_ptr<TableReader>* table_reader,
                      const SliceTransform* prefix_extractor = nullptr,
                      bool prefetch_index_and_filter_in_cache = true,
                      bool skip_filters = false, int level = -1,
@@ -112,7 +114,7 @@ class BlockBasedTable : public TableReader {
                                 bool skip_filters = false,
                                 bool for_compaction = false) override;
 
-  InternalIterator* NewRangeTombstoneIterator(
+  FragmentedRangeTombstoneIterator* NewRangeTombstoneIterator(
       const ReadOptions& read_options) override;
 
   // @param skip_filters Disables loading/accessing the filter block
@@ -255,13 +257,11 @@ class BlockBasedTable : public TableReader {
   // @param block_entry value is set to the uncompressed block if found. If
   //    in uncompressed block cache, also sets cache_handle to reference that
   //    block.
-  static Status MaybeLoadDataBlockToCache(FilePrefetchBuffer* prefetch_buffer,
-                                          Rep* rep, const ReadOptions& ro,
-                                          const BlockHandle& handle,
-                                          Slice compression_dict,
-                                          CachableEntry<Block>* block_entry,
-                                          bool is_index = false,
-                                          GetContext* get_context = nullptr);
+  static Status MaybeReadBlockAndLoadToCache(
+      FilePrefetchBuffer* prefetch_buffer, Rep* rep, const ReadOptions& ro,
+      const BlockHandle& handle, Slice compression_dict,
+      CachableEntry<Block>* block_entry, bool is_index = false,
+      GetContext* get_context = nullptr);
 
   // For the following two functions:
   // if `no_io == true`, we will not try to read filter/index from sst file
@@ -299,9 +299,9 @@ class BlockBasedTable : public TableReader {
   //    dictionary.
   static Status GetDataBlockFromCache(
       const Slice& block_cache_key, const Slice& compressed_block_cache_key,
-      Cache* block_cache, Cache* block_cache_compressed,
-      const ImmutableCFOptions& ioptions, const ReadOptions& read_options,
-      BlockBasedTable::CachableEntry<Block>* block, uint32_t format_version,
+      Cache* block_cache, Cache* block_cache_compressed, Rep* rep,
+      const ReadOptions& read_options,
+      BlockBasedTable::CachableEntry<Block>* block,
       const Slice& compression_dict, size_t read_amp_bytes_per_bit,
       bool is_index = false, GetContext* get_context = nullptr);
 
@@ -311,16 +311,18 @@ class BlockBasedTable : public TableReader {
   // On success, Status::OK will be returned; also @block will be populated with
   // uncompressed block and its cache handle.
   //
-  // REQUIRES: raw_block is heap-allocated. PutDataBlockToCache() will be
-  // responsible for releasing its memory if error occurs.
+  // Allocated memory managed by raw_block_contents will be transferred to
+  // PutDataBlockToCache(). After the call, the object will be invalid.
   // @param compression_dict Data for presetting the compression library's
   //    dictionary.
   static Status PutDataBlockToCache(
       const Slice& block_cache_key, const Slice& compressed_block_cache_key,
       Cache* block_cache, Cache* block_cache_compressed,
       const ReadOptions& read_options, const ImmutableCFOptions& ioptions,
-      CachableEntry<Block>* block, Block* raw_block, uint32_t format_version,
-      const Slice& compression_dict, size_t read_amp_bytes_per_bit,
+      CachableEntry<Block>* block, BlockContents* raw_block_contents,
+      CompressionType raw_block_comp_type, uint32_t format_version,
+      const Slice& compression_dict, SequenceNumber seq_no,
+      size_t read_amp_bytes_per_bit, MemoryAllocator* memory_allocator,
       bool is_index = false, Cache::Priority pri = Cache::Priority::LOW,
       GetContext* get_context = nullptr);
 
@@ -383,6 +385,9 @@ class BlockBasedTable : public TableReader {
 
   friend class PartitionedFilterBlockReader;
   friend class PartitionedFilterBlockTest;
+
+  InternalIterator* NewUnfragmentedRangeTombstoneIterator(
+      const ReadOptions& read_options);
 };
 
 // Maitaning state of a two-level iteration on a partitioned index structure
@@ -431,7 +436,7 @@ struct BlockBasedTable::Rep {
   Rep(const ImmutableCFOptions& _ioptions, const EnvOptions& _env_options,
       const BlockBasedTableOptions& _table_opt,
       const InternalKeyComparator& _internal_comparator, bool skip_filters,
-      const bool _immortal_table)
+      int _level, const bool _immortal_table)
       : ioptions(_ioptions),
         env_options(_env_options),
         table_options(_table_opt),
@@ -444,6 +449,7 @@ struct BlockBasedTable::Rep {
         prefix_filtering(true),
         range_del_handle(BlockHandle::NullBlockHandle()),
         global_seqno(kDisableGlobalSequenceNumber),
+        level(_level),
         immortal_table(_immortal_table) {}
 
   const ImmutableCFOptions& ioptions;
@@ -452,7 +458,7 @@ struct BlockBasedTable::Rep {
   const FilterPolicy* const filter_policy;
   const InternalKeyComparator& internal_comparator;
   Status status;
-  unique_ptr<RandomAccessFileReader> file;
+  std::unique_ptr<RandomAccessFileReader> file;
   char cache_key_prefix[kMaxCacheKeyPrefixSize];
   size_t cache_key_prefix_size = 0;
   char persistent_cache_key_prefix[kMaxCacheKeyPrefixSize];
@@ -468,8 +474,8 @@ struct BlockBasedTable::Rep {
   // index_reader and filter will be populated and used only when
   // options.block_cache is nullptr; otherwise we will get the index block via
   // the block cache.
-  unique_ptr<IndexReader> index_reader;
-  unique_ptr<FilterBlockReader> filter;
+  std::unique_ptr<IndexReader> index_reader;
+  std::unique_ptr<FilterBlockReader> filter;
 
   enum class FilterType {
     kNoFilter,
@@ -494,7 +500,7 @@ struct BlockBasedTable::Rep {
   // module should not be relying on db module. However to make things easier
   // and compatible with existing code, we introduce a wrapper that allows
   // block to extract prefix without knowing if a key is internal or not.
-  unique_ptr<SliceTransform> internal_prefix_transform;
+  std::unique_ptr<SliceTransform> internal_prefix_transform;
   std::shared_ptr<const SliceTransform> table_prefix_extractor;
 
   // only used in level 0 files when pin_l0_filter_and_index_blocks_in_cache is
@@ -509,6 +515,7 @@ struct BlockBasedTable::Rep {
   // cache is enabled.
   CachableEntry<Block> range_del_entry;
   BlockHandle range_del_handle;
+  std::shared_ptr<const FragmentedRangeTombstoneList> fragmented_range_dels;
 
   // If global_seqno is used, all Keys in this file will have the same
   // seqno with value `global_seqno`.
@@ -517,12 +524,20 @@ struct BlockBasedTable::Rep {
   // and every key have it's own seqno.
   SequenceNumber global_seqno;
 
+  // the level when the table is opened, could potentially change when trivial
+  // move is involved
+  int level;
+
   // If false, blocks in this file are definitely all uncompressed. Knowing this
   // before reading individual blocks enables certain optimizations.
   bool blocks_maybe_compressed = true;
 
   bool closed = false;
   const bool immortal_table;
+
+  SequenceNumber get_global_seqno(bool is_index) const {
+    return is_index ? kDisableGlobalSequenceNumber : global_seqno;
+  }
 };
 
 template <class TBlockIter, typename TValue = Slice>
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_builder.cc b/3rdParty/rocksdb/v5.18.X/table/block_builder.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/block_builder.cc
rename to 3rdParty/rocksdb/v5.18.X/table/block_builder.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_builder.h b/3rdParty/rocksdb/v5.18.X/table/block_builder.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/table/block_builder.h
rename to 3rdParty/rocksdb/v5.18.X/table/block_builder.h
index 52b9571162..3b7fc1768b 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block_builder.h
+++ b/3rdParty/rocksdb/v5.18.X/table/block_builder.h
@@ -60,7 +60,7 @@ class BlockBuilder {
 
  private:
   const int          block_restart_interval_;
-  //TODO(myabandeh): put it into a separate IndexBlockBuilder
+  // TODO(myabandeh): put it into a separate IndexBlockBuilder
   const bool         use_delta_encoding_;
   // Refer to BlockIter::DecodeCurrentValue for format of delta encoded values
   const bool use_value_delta_encoding_;
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_fetcher.cc b/3rdParty/rocksdb/v5.18.X/table/block_fetcher.cc
similarity index 79%
rename from 3rdParty/rocksdb/v5.16.X/table/block_fetcher.cc
rename to 3rdParty/rocksdb/v5.18.X/table/block_fetcher.cc
index ea97066ec4..9ad254a59f 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block_fetcher.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/block_fetcher.cc
@@ -17,13 +17,14 @@
 #include "rocksdb/env.h"
 #include "table/block.h"
 #include "table/block_based_table_reader.h"
-#include "table/persistent_cache_helper.h"
 #include "table/format.h"
+#include "table/persistent_cache_helper.h"
 #include "util/coding.h"
 #include "util/compression.h"
 #include "util/crc32c.h"
 #include "util/file_reader_writer.h"
 #include "util/logging.h"
+#include "util/memory_allocator.h"
 #include "util/stop_watch.h"
 #include "util/string_util.h"
 #include "util/xxhash.h"
@@ -48,6 +49,12 @@ void BlockFetcher::CheckBlockChecksum() {
       case kxxHash:
         actual = XXH32(data, static_cast<int>(block_size_) + 1, 0);
         break;
+      case kxxHash64:
+        actual =static_cast<uint32_t> (
+             XXH64(data, static_cast<int>(block_size_) + 1, 0) &
+              uint64_t{0xffffffff}
+          );
+        break;
       default:
         status_ = Status::Corruption(
             "unknown checksum type " + ToString(footer_.checksum()) + " in " +
@@ -107,9 +114,11 @@ bool BlockFetcher::TryGetCompressedBlockFromPersistentCache() {
   if (cache_options_.persistent_cache &&
       cache_options_.persistent_cache->IsCompressed()) {
     // lookup uncompressed cache mode p-cache
+    std::unique_ptr<char[]> raw_data;
     status_ = PersistentCacheHelper::LookupRawPage(
-        cache_options_, handle_, &heap_buf_, block_size_ + kBlockTrailerSize);
+        cache_options_, handle_, &raw_data, block_size_ + kBlockTrailerSize);
     if (status_.ok()) {
+      heap_buf_ = CacheAllocationPtr(raw_data.release());
       used_buf_ = heap_buf_.get();
       slice_ = Slice(heap_buf_.get(), block_size_);
       return true;
@@ -131,8 +140,13 @@ void BlockFetcher::PrepareBufferForBlockFromFile() {
     // If we've got a small enough hunk of data, read it in to the
     // trivially allocated stack buffer instead of needing a full malloc()
     used_buf_ = &stack_buf_[0];
+  } else if (maybe_compressed_ && !do_uncompress_) {
+    compressed_buf_ = AllocateBlock(block_size_ + kBlockTrailerSize,
+                                    memory_allocator_compressed_);
+    used_buf_ = compressed_buf_.get();
   } else {
-    heap_buf_.reset(new char[block_size_ + kBlockTrailerSize]);
+    heap_buf_ =
+        AllocateBlock(block_size_ + kBlockTrailerSize, memory_allocator_);
     used_buf_ = heap_buf_.get();
   }
 }
@@ -159,29 +173,45 @@ void BlockFetcher::InsertUncompressedBlockToPersistentCacheIfNeeded() {
   }
 }
 
+inline void BlockFetcher::CopyBufferToHeap() {
+  assert(used_buf_ != heap_buf_.get());
+  heap_buf_ = AllocateBlock(block_size_ + kBlockTrailerSize, memory_allocator_);
+  memcpy(heap_buf_.get(), used_buf_, block_size_ + kBlockTrailerSize);
+}
+
 inline
 void BlockFetcher::GetBlockContents() {
   if (slice_.data() != used_buf_) {
     // the slice content is not the buffer provided
-    *contents_ = BlockContents(Slice(slice_.data(), block_size_),
-                               immortal_source_, compression_type);
+    *contents_ = BlockContents(Slice(slice_.data(), block_size_));
   } else {
     // page can be either uncompressed or compressed, the buffer either stack
     // or heap provided. Refer to https://github.com/facebook/rocksdb/pull/4096
     if (got_from_prefetch_buffer_ || used_buf_ == &stack_buf_[0]) {
-      assert(used_buf_ != heap_buf_.get());
-      heap_buf_.reset(new char[block_size_ + kBlockTrailerSize]);
-      memcpy(heap_buf_.get(), used_buf_, block_size_ + kBlockTrailerSize);
+      CopyBufferToHeap();
+    } else if (used_buf_ == compressed_buf_.get()) {
+      if (compression_type_ == kNoCompression &&
+          memory_allocator_ != memory_allocator_compressed_) {
+        CopyBufferToHeap();
+      } else {
+        heap_buf_ = std::move(compressed_buf_);
+      }
     }
-    *contents_ = BlockContents(std::move(heap_buf_), block_size_, true,
-                               compression_type);
+    *contents_ = BlockContents(std::move(heap_buf_), block_size_);
   }
+#ifndef NDEBUG
+  contents_->is_raw_block = true;
+#endif
 }
 
 Status BlockFetcher::ReadBlockContents() {
   block_size_ = static_cast<size_t>(handle_.size());
 
   if (TryGetUncompressBlockFromPersistentCache()) {
+    compression_type_ = kNoCompression;
+#ifndef NDEBUG
+    contents_->is_raw_block = true;
+#endif  // NDEBUG
     return Status::OK();
   }
   if (TryGetFromPrefetchBuffer()) {
@@ -222,15 +252,16 @@ Status BlockFetcher::ReadBlockContents() {
 
   PERF_TIMER_GUARD(block_decompress_time);
 
-  compression_type =
-      static_cast<rocksdb::CompressionType>(slice_.data()[block_size_]);
+  compression_type_ = get_block_compression_type(slice_.data(), block_size_);
 
-  if (do_uncompress_ && compression_type != kNoCompression) {
+  if (do_uncompress_ && compression_type_ != kNoCompression) {
     // compressed page, uncompress, update cache
-    UncompressionContext uncompression_ctx(compression_type, compression_dict_);
-    status_ =
-        UncompressBlockContents(uncompression_ctx, slice_.data(), block_size_,
-                                contents_, footer_.version(), ioptions_);
+    UncompressionContext uncompression_ctx(compression_type_,
+                                           compression_dict_);
+    status_ = UncompressBlockContents(uncompression_ctx, slice_.data(),
+                                      block_size_, contents_, footer_.version(),
+                                      ioptions_, memory_allocator_);
+    compression_type_ = kNoCompression;
   } else {
     GetBlockContents();
   }
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_fetcher.h b/3rdParty/rocksdb/v5.18.X/table/block_fetcher.h
similarity index 75%
rename from 3rdParty/rocksdb/v5.16.X/table/block_fetcher.h
rename to 3rdParty/rocksdb/v5.18.X/table/block_fetcher.h
index 9e0d2448dd..aed73a3925 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block_fetcher.h
+++ b/3rdParty/rocksdb/v5.18.X/table/block_fetcher.h
@@ -10,6 +10,7 @@
 #pragma once
 #include "table/block.h"
 #include "table/format.h"
+#include "util/memory_allocator.h"
 
 namespace rocksdb {
 class BlockFetcher {
@@ -24,9 +25,11 @@ class BlockFetcher {
                FilePrefetchBuffer* prefetch_buffer, const Footer& footer,
                const ReadOptions& read_options, const BlockHandle& handle,
                BlockContents* contents, const ImmutableCFOptions& ioptions,
-               bool do_uncompress, const Slice& compression_dict,
+               bool do_uncompress, bool maybe_compressed,
+               const Slice& compression_dict,
                const PersistentCacheOptions& cache_options,
-               const bool immortal_source = false)
+               MemoryAllocator* memory_allocator = nullptr,
+               MemoryAllocator* memory_allocator_compressed = nullptr)
       : file_(file),
         prefetch_buffer_(prefetch_buffer),
         footer_(footer),
@@ -35,10 +38,13 @@ class BlockFetcher {
         contents_(contents),
         ioptions_(ioptions),
         do_uncompress_(do_uncompress),
-        immortal_source_(immortal_source),
+        maybe_compressed_(maybe_compressed),
         compression_dict_(compression_dict),
-        cache_options_(cache_options) {}
+        cache_options_(cache_options),
+        memory_allocator_(memory_allocator),
+        memory_allocator_compressed_(memory_allocator_compressed) {}
   Status ReadBlockContents();
+  CompressionType get_compression_type() const { return compression_type_; }
 
  private:
   static const uint32_t kDefaultStackBufferSize = 5000;
@@ -51,17 +57,20 @@ class BlockFetcher {
   BlockContents* contents_;
   const ImmutableCFOptions& ioptions_;
   bool do_uncompress_;
-  const bool immortal_source_;
+  bool maybe_compressed_;
   const Slice& compression_dict_;
   const PersistentCacheOptions& cache_options_;
+  MemoryAllocator* memory_allocator_;
+  MemoryAllocator* memory_allocator_compressed_;
   Status status_;
   Slice slice_;
   char* used_buf_ = nullptr;
   size_t block_size_;
-  std::unique_ptr<char[]> heap_buf_;
+  CacheAllocationPtr heap_buf_;
+  CacheAllocationPtr compressed_buf_;
   char stack_buf_[kDefaultStackBufferSize];
   bool got_from_prefetch_buffer_ = false;
-  rocksdb::CompressionType compression_type;
+  rocksdb::CompressionType compression_type_;
 
   // return true if found
   bool TryGetUncompressBlockFromPersistentCache();
@@ -69,6 +78,8 @@ class BlockFetcher {
   bool TryGetFromPrefetchBuffer();
   bool TryGetCompressedBlockFromPersistentCache();
   void PrepareBufferForBlockFromFile();
+  // Copy content from used_buf_ to new heap buffer.
+  void CopyBufferToHeap();
   void GetBlockContents();
   void InsertCompressedBlockToPersistentCacheIfNeeded();
   void InsertUncompressedBlockToPersistentCacheIfNeeded();
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_prefix_index.cc b/3rdParty/rocksdb/v5.18.X/table/block_prefix_index.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/block_prefix_index.cc
rename to 3rdParty/rocksdb/v5.18.X/table/block_prefix_index.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_prefix_index.h b/3rdParty/rocksdb/v5.18.X/table/block_prefix_index.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/block_prefix_index.h
rename to 3rdParty/rocksdb/v5.18.X/table/block_prefix_index.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/block_test.cc b/3rdParty/rocksdb/v5.18.X/table/block_test.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/table/block_test.cc
rename to 3rdParty/rocksdb/v5.18.X/table/block_test.cc
index 009740a283..5ac9ffb214 100644
--- a/3rdParty/rocksdb/v5.16.X/table/block_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/block_test.cc
@@ -70,10 +70,10 @@ void GenerateRandomKVs(std::vector<std::string> *keys,
 
 // Same as GenerateRandomKVs but the values are BlockHandle
 void GenerateRandomKBHs(std::vector<std::string> *keys,
-                       std::vector<BlockHandle> *values, const int from,
-                       const int len, const int step = 1,
-                       const int padding_size = 0,
-                       const int keys_share_prefix = 1) {
+                        std::vector<BlockHandle> *values, const int from,
+                        const int len, const int step = 1,
+                        const int padding_size = 0,
+                        const int keys_share_prefix = 1) {
   Random rnd(302);
   uint64_t offset = 0;
 
@@ -117,7 +117,6 @@ TEST_F(BlockTest, SimpleTest) {
   // create block reader
   BlockContents contents;
   contents.data = rawblock;
-  contents.cachable = false;
   Block reader(std::move(contents), kDisableGlobalSequenceNumber);
 
   // read contents of block sequentially
@@ -188,7 +187,6 @@ TEST_F(BlockTest, ValueDeltaEncodingTest) {
   // create block reader
   BlockContents contents;
   contents.data = rawblock;
-  contents.cachable = false;
   Block reader(std::move(contents), kDisableGlobalSequenceNumber);
 
   const bool kTotalOrderSeek = true;
@@ -247,7 +245,6 @@ BlockContents GetBlockContents(std::unique_ptr<BlockBuilder> *builder,
 
   BlockContents contents;
   contents.data = rawblock;
-  contents.cachable = false;
 
   return contents;
 }
@@ -257,8 +254,7 @@ void CheckBlockContents(BlockContents contents, const int max_key,
                         const std::vector<std::string> &values) {
   const size_t prefix_size = 6;
   // create block reader
-  BlockContents contents_ref(contents.data, contents.cachable,
-                             contents.compression_type);
+  BlockContents contents_ref(contents.data);
   Block reader1(std::move(contents), kDisableGlobalSequenceNumber);
   Block reader2(std::move(contents_ref), kDisableGlobalSequenceNumber);
 
@@ -486,7 +482,6 @@ TEST_F(BlockTest, BlockWithReadAmpBitmap) {
     // create block reader
     BlockContents contents;
     contents.data = rawblock;
-    contents.cachable = true;
     Block reader(std::move(contents), kDisableGlobalSequenceNumber,
                  kBytesPerBit, stats.get());
 
@@ -521,7 +516,6 @@ TEST_F(BlockTest, BlockWithReadAmpBitmap) {
     // create block reader
     BlockContents contents;
     contents.data = rawblock;
-    contents.cachable = true;
     Block reader(std::move(contents), kDisableGlobalSequenceNumber,
                  kBytesPerBit, stats.get());
 
@@ -558,7 +552,6 @@ TEST_F(BlockTest, BlockWithReadAmpBitmap) {
     // create block reader
     BlockContents contents;
     contents.data = rawblock;
-    contents.cachable = true;
     Block reader(std::move(contents), kDisableGlobalSequenceNumber,
                  kBytesPerBit, stats.get());
 
diff --git a/3rdParty/rocksdb/v5.16.X/table/bloom_block.cc b/3rdParty/rocksdb/v5.18.X/table/bloom_block.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/bloom_block.cc
rename to 3rdParty/rocksdb/v5.18.X/table/bloom_block.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/bloom_block.h b/3rdParty/rocksdb/v5.18.X/table/bloom_block.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/bloom_block.h
rename to 3rdParty/rocksdb/v5.18.X/table/bloom_block.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/cleanable_test.cc b/3rdParty/rocksdb/v5.18.X/table/cleanable_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/cleanable_test.cc
rename to 3rdParty/rocksdb/v5.18.X/table/cleanable_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_builder.cc b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_builder.cc
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/table/cuckoo_table_builder.cc
rename to 3rdParty/rocksdb/v5.18.X/table/cuckoo_table_builder.cc
index 0da4d84ddc..f590e6ad40 100644
--- a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_builder.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_builder.cc
@@ -164,9 +164,9 @@ bool CuckooTableBuilder::IsDeletedKey(uint64_t idx) const {
 Slice CuckooTableBuilder::GetKey(uint64_t idx) const {
   assert(closed_);
   if (IsDeletedKey(idx)) {
-    return Slice(&deleted_keys_[(idx - num_values_) * key_size_], key_size_);
+    return Slice(&deleted_keys_[static_cast<size_t>((idx - num_values_) * key_size_)], static_cast<size_t>(key_size_));
   }
-  return Slice(&kvs_[idx * (key_size_ + value_size_)], key_size_);
+  return Slice(&kvs_[static_cast<size_t>(idx * (key_size_ + value_size_))], static_cast<size_t>(key_size_));
 }
 
 Slice CuckooTableBuilder::GetUserKey(uint64_t idx) const {
@@ -177,14 +177,14 @@ Slice CuckooTableBuilder::GetUserKey(uint64_t idx) const {
 Slice CuckooTableBuilder::GetValue(uint64_t idx) const {
   assert(closed_);
   if (IsDeletedKey(idx)) {
-    static std::string empty_value(value_size_, 'a');
+    static std::string empty_value(static_cast<unsigned int>(value_size_), 'a');
     return Slice(empty_value);
   }
-  return Slice(&kvs_[idx * (key_size_ + value_size_) + key_size_], value_size_);
+  return Slice(&kvs_[static_cast<size_t>(idx * (key_size_ + value_size_) + key_size_)], static_cast<size_t>(value_size_));
 }
 
 Status CuckooTableBuilder::MakeHashTable(std::vector<CuckooBucket>* buckets) {
-  buckets->resize(hash_table_size_ + cuckoo_block_size_ - 1);
+  buckets->resize(static_cast<size_t>(hash_table_size_ + cuckoo_block_size_ - 1));
   uint32_t make_space_for_key_call_id = 0;
   for (uint32_t vector_idx = 0; vector_idx < num_entries_; vector_idx++) {
     uint64_t bucket_id = 0;
@@ -200,13 +200,13 @@ Status CuckooTableBuilder::MakeHashTable(std::vector<CuckooBucket>* buckets) {
       // stop searching and proceed for next hash function.
       for (uint32_t block_idx = 0; block_idx < cuckoo_block_size_;
           ++block_idx, ++hash_val) {
-        if ((*buckets)[hash_val].vector_idx == kMaxVectorIdx) {
+        if ((*buckets)[static_cast<size_t>(hash_val)].vector_idx == kMaxVectorIdx) {
           bucket_id = hash_val;
           bucket_found = true;
           break;
         } else {
           if (ucomp_->Compare(user_key,
-                GetUserKey((*buckets)[hash_val].vector_idx)) == 0) {
+                GetUserKey((*buckets)[static_cast<size_t>(hash_val)].vector_idx)) == 0) {
             return Status::NotSupported("Same key is being inserted again.");
           }
           hash_vals.push_back(hash_val);
@@ -226,7 +226,7 @@ Status CuckooTableBuilder::MakeHashTable(std::vector<CuckooBucket>* buckets) {
       ++num_hash_func_;
       for (uint32_t block_idx = 0; block_idx < cuckoo_block_size_;
           ++block_idx, ++hash_val) {
-        if ((*buckets)[hash_val].vector_idx == kMaxVectorIdx) {
+        if ((*buckets)[static_cast<size_t>(hash_val)].vector_idx == kMaxVectorIdx) {
           bucket_found = true;
           bucket_id = hash_val;
           break;
@@ -235,7 +235,7 @@ Status CuckooTableBuilder::MakeHashTable(std::vector<CuckooBucket>* buckets) {
         }
       }
     }
-    (*buckets)[bucket_id].vector_idx = vector_idx;
+    (*buckets)[static_cast<size_t>(bucket_id)].vector_idx = vector_idx;
   }
   return Status::OK();
 }
@@ -289,13 +289,14 @@ Status CuckooTableBuilder::Finish() {
     }
   }
   properties_.num_entries = num_entries_;
+  properties_.num_deletions = num_entries_ - num_values_;
   properties_.fixed_key_len = key_size_;
   properties_.user_collected_properties[
         CuckooTablePropertyNames::kValueLength].assign(
         reinterpret_cast<const char*>(&value_size_), sizeof(value_size_));
 
   uint64_t bucket_size = key_size_ + value_size_;
-  unused_bucket.resize(bucket_size, 'a');
+  unused_bucket.resize(static_cast<size_t>(bucket_size), 'a');
   // Write the table.
   uint32_t num_added = 0;
   for (auto& bucket : buckets) {
@@ -320,7 +321,7 @@ Status CuckooTableBuilder::Finish() {
 
   uint64_t offset = buckets.size() * bucket_size;
   properties_.data_size = offset;
-  unused_bucket.resize(properties_.fixed_key_len);
+  unused_bucket.resize(static_cast<size_t>(properties_.fixed_key_len));
   properties_.user_collected_properties[
     CuckooTablePropertyNames::kEmptyKey] = unused_bucket;
   properties_.user_collected_properties[
@@ -456,7 +457,7 @@ bool CuckooTableBuilder::MakeSpaceForKey(
   // no. of times this will be called is <= max_num_hash_func_ + num_entries_.
   for (uint32_t hash_cnt = 0; hash_cnt < num_hash_func_; ++hash_cnt) {
     uint64_t bid = hash_vals[hash_cnt];
-    (*buckets)[bid].make_space_for_key_call_id = make_space_for_key_call_id;
+    (*buckets)[static_cast<size_t>(bid)].make_space_for_key_call_id = make_space_for_key_call_id;
     tree.push_back(CuckooNode(bid, 0, 0));
   }
   bool null_found = false;
@@ -467,7 +468,7 @@ bool CuckooTableBuilder::MakeSpaceForKey(
     if (curr_depth >= max_search_depth_) {
       break;
     }
-    CuckooBucket& curr_bucket = (*buckets)[curr_node.bucket_id];
+    CuckooBucket& curr_bucket = (*buckets)[static_cast<size_t>(curr_node.bucket_id)];
     for (uint32_t hash_cnt = 0;
         hash_cnt < num_hash_func_ && !null_found; ++hash_cnt) {
       uint64_t child_bucket_id = CuckooHash(GetUserKey(curr_bucket.vector_idx),
@@ -476,15 +477,15 @@ bool CuckooTableBuilder::MakeSpaceForKey(
       // Iterate inside Cuckoo Block.
       for (uint32_t block_idx = 0; block_idx < cuckoo_block_size_;
           ++block_idx, ++child_bucket_id) {
-        if ((*buckets)[child_bucket_id].make_space_for_key_call_id ==
+        if ((*buckets)[static_cast<size_t>(child_bucket_id)].make_space_for_key_call_id ==
             make_space_for_key_call_id) {
           continue;
         }
-        (*buckets)[child_bucket_id].make_space_for_key_call_id =
+        (*buckets)[static_cast<size_t>(child_bucket_id)].make_space_for_key_call_id =
           make_space_for_key_call_id;
         tree.push_back(CuckooNode(child_bucket_id, curr_depth + 1,
               curr_pos));
-        if ((*buckets)[child_bucket_id].vector_idx == kMaxVectorIdx) {
+        if ((*buckets)[static_cast<size_t>(child_bucket_id)].vector_idx == kMaxVectorIdx) {
           null_found = true;
           break;
         }
@@ -502,8 +503,8 @@ bool CuckooTableBuilder::MakeSpaceForKey(
     uint32_t bucket_to_replace_pos = static_cast<uint32_t>(tree.size()) - 1;
     while (bucket_to_replace_pos >= num_hash_func_) {
       CuckooNode& curr_node = tree[bucket_to_replace_pos];
-      (*buckets)[curr_node.bucket_id] =
-        (*buckets)[tree[curr_node.parent_pos].bucket_id];
+      (*buckets)[static_cast<size_t>(curr_node.bucket_id)] =
+        (*buckets)[static_cast<size_t>(tree[curr_node.parent_pos].bucket_id)];
       bucket_to_replace_pos = curr_node.parent_pos;
     }
     *bucket_id = tree[bucket_to_replace_pos].bucket_id;
diff --git a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_builder.h b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_builder.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/cuckoo_table_builder.h
rename to 3rdParty/rocksdb/v5.18.X/table/cuckoo_table_builder.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_builder_test.cc b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_builder_test.cc
similarity index 83%
rename from 3rdParty/rocksdb/v5.16.X/table/cuckoo_table_builder_test.cc
rename to 3rdParty/rocksdb/v5.18.X/table/cuckoo_table_builder_test.cc
index 0d24da7194..c1e350327f 100644
--- a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_builder_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_builder_test.cc
@@ -43,8 +43,15 @@ class CuckooBuilderTest : public testing::Test {
       std::string expected_unused_bucket, uint64_t expected_table_size,
       uint32_t expected_num_hash_func, bool expected_is_last_level,
       uint32_t expected_cuckoo_block_size = 1) {
+    uint64_t num_deletions = 0;
+    for (const auto& key : keys) {
+      ParsedInternalKey parsed;
+      if (ParseInternalKey(key, &parsed) && parsed.type == kTypeDeletion) {
+        num_deletions++;
+      }
+    }
     // Read file
-    unique_ptr<RandomAccessFile> read_file;
+    std::unique_ptr<RandomAccessFile> read_file;
     ASSERT_OK(env_->NewRandomAccessFile(fname, &read_file, env_options_));
     uint64_t read_file_size;
     ASSERT_OK(env_->GetFileSize(fname, &read_file_size));
@@ -56,7 +63,7 @@ class CuckooBuilderTest : public testing::Test {
 
     // Assert Table Properties.
     TableProperties* props = nullptr;
-    unique_ptr<RandomAccessFileReader> file_reader(
+    std::unique_ptr<RandomAccessFileReader> file_reader(
         new RandomAccessFileReader(std::move(read_file), fname));
     ASSERT_OK(ReadTableProperties(file_reader.get(), read_file_size,
                                   kCuckooTableMagicNumber, ioptions,
@@ -90,6 +97,7 @@ class CuckooBuilderTest : public testing::Test {
     ASSERT_EQ(expected_is_last_level, is_last_level_found);
 
     ASSERT_EQ(props->num_entries, keys.size());
+    ASSERT_EQ(props->num_deletions, num_deletions);
     ASSERT_EQ(props->fixed_key_len, keys.empty() ? 0 : keys[0].size());
     ASSERT_EQ(props->data_size, expected_unused_bucket.size() *
         (expected_table_size + expected_cuckoo_block_size - 1));
@@ -126,9 +134,10 @@ class CuckooBuilderTest : public testing::Test {
     }
   }
 
-  std::string GetInternalKey(Slice user_key, bool zero_seqno) {
+  std::string GetInternalKey(Slice user_key, bool zero_seqno,
+                             ValueType type = kTypeValue) {
     IterKey ikey;
-    ikey.SetInternalKey(user_key, zero_seqno ? 0 : 1000, kTypeValue);
+    ikey.SetInternalKey(user_key, zero_seqno ? 0 : 1000, type);
     return ikey.GetInternalKey().ToString();
   }
 
@@ -152,11 +161,11 @@ class CuckooBuilderTest : public testing::Test {
 };
 
 TEST_F(CuckooBuilderTest, SuccessWithEmptyFile) {
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   fname = test::PerThreadDBPath("EmptyFile");
   ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
   CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, 4, 100,
                              BytewiseComparator(), 1, false, false,
                              GetSliceHash, 0 /* column_family_id */,
@@ -169,50 +178,57 @@ TEST_F(CuckooBuilderTest, SuccessWithEmptyFile) {
 }
 
 TEST_F(CuckooBuilderTest, WriteSuccessNoCollisionFullKey) {
-  uint32_t num_hash_fun = 4;
-  std::vector<std::string> user_keys = {"key01", "key02", "key03", "key04"};
-  std::vector<std::string> values = {"v01", "v02", "v03", "v04"};
-  // Need to have a temporary variable here as VS compiler does not currently
-  // support operator= with initializer_list as a parameter
-  std::unordered_map<std::string, std::vector<uint64_t>> hm = {
-      {user_keys[0], {0, 1, 2, 3}},
-      {user_keys[1], {1, 2, 3, 4}},
-      {user_keys[2], {2, 3, 4, 5}},
-      {user_keys[3], {3, 4, 5, 6}}};
-  hash_map = std::move(hm);
+  for (auto type : {kTypeValue, kTypeDeletion}) {
+    uint32_t num_hash_fun = 4;
+    std::vector<std::string> user_keys = {"key01", "key02", "key03", "key04"};
+    std::vector<std::string> values;
+    if (type == kTypeValue) {
+      values = {"v01", "v02", "v03", "v04"};
+    } else {
+      values = {"", "", "", ""};
+    }
+    // Need to have a temporary variable here as VS compiler does not currently
+    // support operator= with initializer_list as a parameter
+    std::unordered_map<std::string, std::vector<uint64_t>> hm = {
+        {user_keys[0], {0, 1, 2, 3}},
+        {user_keys[1], {1, 2, 3, 4}},
+        {user_keys[2], {2, 3, 4, 5}},
+        {user_keys[3], {3, 4, 5, 6}}};
+    hash_map = std::move(hm);
 
-  std::vector<uint64_t> expected_locations = {0, 1, 2, 3};
-  std::vector<std::string> keys;
-  for (auto& user_key : user_keys) {
-    keys.push_back(GetInternalKey(user_key, false));
-  }
-  uint64_t expected_table_size = GetExpectedTableSize(keys.size());
+    std::vector<uint64_t> expected_locations = {0, 1, 2, 3};
+    std::vector<std::string> keys;
+    for (auto& user_key : user_keys) {
+      keys.push_back(GetInternalKey(user_key, false, type));
+    }
+    uint64_t expected_table_size = GetExpectedTableSize(keys.size());
 
-  unique_ptr<WritableFile> writable_file;
-  fname = test::PerThreadDBPath("NoCollisionFullKey");
-  ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
-  CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
-                             100, BytewiseComparator(), 1, false, false,
-                             GetSliceHash, 0 /* column_family_id */,
-                             kDefaultColumnFamilyName);
-  ASSERT_OK(builder.status());
-  for (uint32_t i = 0; i < user_keys.size(); i++) {
-    builder.Add(Slice(keys[i]), Slice(values[i]));
-    ASSERT_EQ(builder.NumEntries(), i + 1);
+    std::unique_ptr<WritableFile> writable_file;
+    fname = test::PerThreadDBPath("NoCollisionFullKey");
+    ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
+    std::unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
+    CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
+                               100, BytewiseComparator(), 1, false, false,
+                               GetSliceHash, 0 /* column_family_id */,
+                               kDefaultColumnFamilyName);
     ASSERT_OK(builder.status());
-  }
-  size_t bucket_size = keys[0].size() + values[0].size();
-  ASSERT_EQ(expected_table_size * bucket_size - 1, builder.FileSize());
-  ASSERT_OK(builder.Finish());
-  ASSERT_OK(file_writer->Close());
-  ASSERT_LE(expected_table_size * bucket_size, builder.FileSize());
+    for (uint32_t i = 0; i < user_keys.size(); i++) {
+      builder.Add(Slice(keys[i]), Slice(values[i]));
+      ASSERT_EQ(builder.NumEntries(), i + 1);
+      ASSERT_OK(builder.status());
+    }
+    size_t bucket_size = keys[0].size() + values[0].size();
+    ASSERT_EQ(expected_table_size * bucket_size - 1, builder.FileSize());
+    ASSERT_OK(builder.Finish());
+    ASSERT_OK(file_writer->Close());
+    ASSERT_LE(expected_table_size * bucket_size, builder.FileSize());
 
-  std::string expected_unused_bucket = GetInternalKey("key00", true);
-  expected_unused_bucket += std::string(values[0].size(), 'a');
-  CheckFileContents(keys, values, expected_locations,
-      expected_unused_bucket, expected_table_size, 2, false);
+    std::string expected_unused_bucket = GetInternalKey("key00", true);
+    expected_unused_bucket += std::string(values[0].size(), 'a');
+    CheckFileContents(keys, values, expected_locations, expected_unused_bucket,
+                      expected_table_size, 2, false);
+  }
 }
 
 TEST_F(CuckooBuilderTest, WriteSuccessWithCollisionFullKey) {
@@ -236,11 +252,11 @@ TEST_F(CuckooBuilderTest, WriteSuccessWithCollisionFullKey) {
   }
   uint64_t expected_table_size = GetExpectedTableSize(keys.size());
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   fname = test::PerThreadDBPath("WithCollisionFullKey");
   ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
   CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
                              100, BytewiseComparator(), 1, false, false,
                              GetSliceHash, 0 /* column_family_id */,
@@ -284,12 +300,12 @@ TEST_F(CuckooBuilderTest, WriteSuccessWithCollisionAndCuckooBlock) {
   }
   uint64_t expected_table_size = GetExpectedTableSize(keys.size());
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   uint32_t cuckoo_block_size = 2;
   fname = test::PerThreadDBPath("WithCollisionFullKey2");
   ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
   CuckooTableBuilder builder(
       file_writer.get(), kHashTableRatio, num_hash_fun, 100,
       BytewiseComparator(), cuckoo_block_size, false, false, GetSliceHash,
@@ -338,11 +354,11 @@ TEST_F(CuckooBuilderTest, WithCollisionPathFullKey) {
   }
   uint64_t expected_table_size = GetExpectedTableSize(keys.size());
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   fname = test::PerThreadDBPath("WithCollisionPathFullKey");
   ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
   CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
                              100, BytewiseComparator(), 1, false, false,
                              GetSliceHash, 0 /* column_family_id */,
@@ -388,11 +404,11 @@ TEST_F(CuckooBuilderTest, WithCollisionPathFullKeyAndCuckooBlock) {
   }
   uint64_t expected_table_size = GetExpectedTableSize(keys.size());
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   fname = test::PerThreadDBPath("WithCollisionPathFullKeyAndCuckooBlock");
   ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
   CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
                              100, BytewiseComparator(), 2, false, false,
                              GetSliceHash, 0 /* column_family_id */,
@@ -431,11 +447,11 @@ TEST_F(CuckooBuilderTest, WriteSuccessNoCollisionUserKey) {
   std::vector<uint64_t> expected_locations = {0, 1, 2, 3};
   uint64_t expected_table_size = GetExpectedTableSize(user_keys.size());
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   fname = test::PerThreadDBPath("NoCollisionUserKey");
   ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
   CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
                              100, BytewiseComparator(), 1, false, false,
                              GetSliceHash, 0 /* column_family_id */,
@@ -475,11 +491,11 @@ TEST_F(CuckooBuilderTest, WriteSuccessWithCollisionUserKey) {
   std::vector<uint64_t> expected_locations = {0, 1, 2, 3};
   uint64_t expected_table_size = GetExpectedTableSize(user_keys.size());
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   fname = test::PerThreadDBPath("WithCollisionUserKey");
   ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
   CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
                              100, BytewiseComparator(), 1, false, false,
                              GetSliceHash, 0 /* column_family_id */,
@@ -521,11 +537,11 @@ TEST_F(CuckooBuilderTest, WithCollisionPathUserKey) {
   std::vector<uint64_t> expected_locations = {0, 1, 3, 4, 2};
   uint64_t expected_table_size = GetExpectedTableSize(user_keys.size());
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   fname = test::PerThreadDBPath("WithCollisionPathUserKey");
   ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
   CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
                              2, BytewiseComparator(), 1, false, false,
                              GetSliceHash, 0 /* column_family_id */,
@@ -566,11 +582,11 @@ TEST_F(CuckooBuilderTest, FailWhenCollisionPathTooLong) {
   };
   hash_map = std::move(hm);
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   fname = test::PerThreadDBPath("WithCollisionPathUserKey");
   ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
   CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
                              2, BytewiseComparator(), 1, false, false,
                              GetSliceHash, 0 /* column_family_id */,
@@ -594,11 +610,11 @@ TEST_F(CuckooBuilderTest, FailWhenSameKeyInserted) {
   uint32_t num_hash_fun = 4;
   std::string user_key = "repeatedkey";
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   fname = test::PerThreadDBPath("FailWhenSameKeyInserted");
   ASSERT_OK(env_->NewWritableFile(fname, &writable_file, env_options_));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, EnvOptions()));
   CuckooTableBuilder builder(file_writer.get(), kHashTableRatio, num_hash_fun,
                              100, BytewiseComparator(), 1, false, false,
                              GetSliceHash, 0 /* column_family_id */,
diff --git a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_factory.cc b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_factory.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/table/cuckoo_table_factory.cc
rename to 3rdParty/rocksdb/v5.18.X/table/cuckoo_table_factory.cc
index 84d22468eb..74d18d5121 100644
--- a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_factory.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_factory.cc
@@ -14,7 +14,7 @@ namespace rocksdb {
 
 Status CuckooTableFactory::NewTableReader(
     const TableReaderOptions& table_reader_options,
-    unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+    std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
     std::unique_ptr<TableReader>* table,
     bool /*prefetch_index_and_filter_in_cache*/) const {
   std::unique_ptr<CuckooTableReader> new_reader(new CuckooTableReader(
diff --git a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_factory.h b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_factory.h
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/table/cuckoo_table_factory.h
rename to 3rdParty/rocksdb/v5.18.X/table/cuckoo_table_factory.h
index a96635de57..eb3c5e5176 100644
--- a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_factory.h
+++ b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_factory.h
@@ -60,8 +60,8 @@ class CuckooTableFactory : public TableFactory {
 
   Status NewTableReader(
       const TableReaderOptions& table_reader_options,
-      unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
-      unique_ptr<TableReader>* table,
+      std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+      std::unique_ptr<TableReader>* table,
       bool prefetch_index_and_filter_in_cache = true) const override;
 
   TableBuilder* NewTableBuilder(
diff --git a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_reader.cc b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_reader.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/table/cuckoo_table_reader.cc
rename to 3rdParty/rocksdb/v5.18.X/table/cuckoo_table_reader.cc
index fb14b17595..be7b1ffa9d 100644
--- a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_reader.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_reader.cc
@@ -136,7 +136,7 @@ CuckooTableReader::CuckooTableReader(
   cuckoo_block_size_ = *reinterpret_cast<const uint32_t*>(
       cuckoo_block_size->second.data());
   cuckoo_block_bytes_minus_one_ = cuckoo_block_size_ * bucket_length_ - 1;
-  status_ = file_->Read(0, file_size, &file_data_, nullptr);
+  status_ = file_->Read(0, static_cast<size_t>(file_size), &file_data_, nullptr);
 }
 
 Status CuckooTableReader::Get(const ReadOptions& /*readOptions*/,
@@ -268,7 +268,7 @@ void CuckooTableIterator::InitIfNeeded() {
   if (initialized_) {
     return;
   }
-  sorted_bucket_ids_.reserve(reader_->GetTableProperties()->num_entries);
+  sorted_bucket_ids_.reserve(static_cast<size_t>(reader_->GetTableProperties()->num_entries));
   uint64_t num_buckets = reader_->table_size_ + reader_->cuckoo_block_size_ - 1;
   assert(num_buckets < kInvalidIndex);
   const char* bucket = reader_->file_data_.data();
diff --git a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_reader.h b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_reader.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/cuckoo_table_reader.h
rename to 3rdParty/rocksdb/v5.18.X/table/cuckoo_table_reader.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_reader_test.cc b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_reader_test.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/table/cuckoo_table_reader_test.cc
rename to 3rdParty/rocksdb/v5.18.X/table/cuckoo_table_reader_test.cc
index 3aeca5e132..74fb52e6c7 100644
--- a/3rdParty/rocksdb/v5.16.X/table/cuckoo_table_reader_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/cuckoo_table_reader_test.cc
@@ -95,8 +95,8 @@ class CuckooReaderTest : public testing::Test {
       const Comparator* ucomp = BytewiseComparator()) {
     std::unique_ptr<WritableFile> writable_file;
     ASSERT_OK(env->NewWritableFile(fname, &writable_file, env_options));
-    unique_ptr<WritableFileWriter> file_writer(
-        new WritableFileWriter(std::move(writable_file), env_options));
+    std::unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(writable_file), fname, env_options));
 
     CuckooTableBuilder builder(
         file_writer.get(), 0.9, kNumHashFunc, 100, ucomp, 2, false, false,
@@ -115,7 +115,7 @@ class CuckooReaderTest : public testing::Test {
     // Check reader now.
     std::unique_ptr<RandomAccessFile> read_file;
     ASSERT_OK(env->NewRandomAccessFile(fname, &read_file, env_options));
-    unique_ptr<RandomAccessFileReader> file_reader(
+    std::unique_ptr<RandomAccessFileReader> file_reader(
         new RandomAccessFileReader(std::move(read_file), fname));
     const ImmutableCFOptions ioptions(options);
     CuckooTableReader reader(ioptions, std::move(file_reader), file_size, ucomp,
@@ -144,7 +144,7 @@ class CuckooReaderTest : public testing::Test {
   void CheckIterator(const Comparator* ucomp = BytewiseComparator()) {
     std::unique_ptr<RandomAccessFile> read_file;
     ASSERT_OK(env->NewRandomAccessFile(fname, &read_file, env_options));
-    unique_ptr<RandomAccessFileReader> file_reader(
+    std::unique_ptr<RandomAccessFileReader> file_reader(
         new RandomAccessFileReader(std::move(read_file), fname));
     const ImmutableCFOptions ioptions(options);
     CuckooTableReader reader(ioptions, std::move(file_reader), file_size, ucomp,
@@ -323,7 +323,7 @@ TEST_F(CuckooReaderTest, WhenKeyNotFound) {
   CreateCuckooFileAndCheckReader();
   std::unique_ptr<RandomAccessFile> read_file;
   ASSERT_OK(env->NewRandomAccessFile(fname, &read_file, env_options));
-  unique_ptr<RandomAccessFileReader> file_reader(
+  std::unique_ptr<RandomAccessFileReader> file_reader(
       new RandomAccessFileReader(std::move(read_file), fname));
   const ImmutableCFOptions ioptions(options);
   CuckooTableReader reader(ioptions, std::move(file_reader), file_size, ucmp,
@@ -411,8 +411,8 @@ void WriteFile(const std::vector<std::string>& keys,
 
   std::unique_ptr<WritableFile> writable_file;
   ASSERT_OK(env->NewWritableFile(fname, &writable_file, env_options));
-  unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(writable_file), env_options));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      new WritableFileWriter(std::move(writable_file), fname, env_options));
   CuckooTableBuilder builder(
       file_writer.get(), hash_ratio, 64, 1000, test::Uint64Comparator(), 5,
       false, FLAGS_identity_as_first_hash, nullptr, 0 /* column_family_id */,
@@ -432,7 +432,7 @@ void WriteFile(const std::vector<std::string>& keys,
   env->GetFileSize(fname, &file_size);
   std::unique_ptr<RandomAccessFile> read_file;
   ASSERT_OK(env->NewRandomAccessFile(fname, &read_file, env_options));
-  unique_ptr<RandomAccessFileReader> file_reader(
+  std::unique_ptr<RandomAccessFileReader> file_reader(
       new RandomAccessFileReader(std::move(read_file), fname));
 
   const ImmutableCFOptions ioptions(options);
@@ -464,7 +464,7 @@ void ReadKeys(uint64_t num, uint32_t batch_size) {
   env->GetFileSize(fname, &file_size);
   std::unique_ptr<RandomAccessFile> read_file;
   ASSERT_OK(env->NewRandomAccessFile(fname, &read_file, env_options));
-  unique_ptr<RandomAccessFileReader> file_reader(
+  std::unique_ptr<RandomAccessFileReader> file_reader(
       new RandomAccessFileReader(std::move(read_file), fname));
 
   const ImmutableCFOptions ioptions(options);
diff --git a/3rdParty/rocksdb/v5.16.X/table/data_block_footer.cc b/3rdParty/rocksdb/v5.18.X/table/data_block_footer.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/data_block_footer.cc
rename to 3rdParty/rocksdb/v5.18.X/table/data_block_footer.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/data_block_footer.h b/3rdParty/rocksdb/v5.18.X/table/data_block_footer.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/data_block_footer.h
rename to 3rdParty/rocksdb/v5.18.X/table/data_block_footer.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/data_block_hash_index.cc b/3rdParty/rocksdb/v5.18.X/table/data_block_hash_index.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/data_block_hash_index.cc
rename to 3rdParty/rocksdb/v5.18.X/table/data_block_hash_index.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/data_block_hash_index.h b/3rdParty/rocksdb/v5.18.X/table/data_block_hash_index.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/data_block_hash_index.h
rename to 3rdParty/rocksdb/v5.18.X/table/data_block_hash_index.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/data_block_hash_index_test.cc b/3rdParty/rocksdb/v5.18.X/table/data_block_hash_index_test.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/table/data_block_hash_index_test.cc
rename to 3rdParty/rocksdb/v5.18.X/table/data_block_hash_index_test.cc
index c2b059893f..ac12bbf935 100644
--- a/3rdParty/rocksdb/v5.16.X/table/data_block_hash_index_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/data_block_hash_index_test.cc
@@ -7,12 +7,14 @@
 #include <string>
 #include <unordered_map>
 
+#include "db/table_properties_collector.h"
 #include "rocksdb/slice.h"
 #include "table/block.h"
 #include "table/block_based_table_reader.h"
 #include "table/block_builder.h"
 #include "table/data_block_hash_index.h"
 #include "table/get_context.h"
+#include "table/table_builder.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
 
@@ -282,7 +284,6 @@ TEST(DataBlockHashIndex, BlockRestartIndexExceedMax) {
     // create block reader
     BlockContents contents;
     contents.data = rawblock;
-    contents.cachable = false;
     Block reader(std::move(contents), kDisableGlobalSequenceNumber);
 
     ASSERT_EQ(reader.IndexType(),
@@ -305,7 +306,6 @@ TEST(DataBlockHashIndex, BlockRestartIndexExceedMax) {
     // create block reader
     BlockContents contents;
     contents.data = rawblock;
-    contents.cachable = false;
     Block reader(std::move(contents), kDisableGlobalSequenceNumber);
 
     ASSERT_EQ(reader.IndexType(),
@@ -337,7 +337,6 @@ TEST(DataBlockHashIndex, BlockSizeExceedMax) {
     // create block reader
     BlockContents contents;
     contents.data = rawblock;
-    contents.cachable = false;
     Block reader(std::move(contents), kDisableGlobalSequenceNumber);
 
     ASSERT_EQ(reader.IndexType(),
@@ -362,7 +361,6 @@ TEST(DataBlockHashIndex, BlockSizeExceedMax) {
     // create block reader
     BlockContents contents;
     contents.data = rawblock;
-    contents.cachable = false;
     Block reader(std::move(contents), kDisableGlobalSequenceNumber);
 
     // the index type have fallen back to binary when build finish.
@@ -390,7 +388,6 @@ TEST(DataBlockHashIndex, BlockTestSingleKey) {
   // create block reader
   BlockContents contents;
   contents.data = rawblock;
-  contents.cachable = false;
   Block reader(std::move(contents), kDisableGlobalSequenceNumber);
 
   const InternalKeyComparator icmp(BytewiseComparator());
@@ -472,7 +469,6 @@ TEST(DataBlockHashIndex, BlockTestLarge) {
   // create block reader
   BlockContents contents;
   contents.data = rawblock;
-  contents.cachable = false;
   Block reader(std::move(contents), kDisableGlobalSequenceNumber);
   const InternalKeyComparator icmp(BytewiseComparator());
 
@@ -540,9 +536,9 @@ TEST(DataBlockHashIndex, BlockTestLarge) {
 void TestBoundary(InternalKey& ik1, std::string& v1, InternalKey& ik2,
                   std::string& v2, InternalKey& seek_ikey,
                   GetContext& get_context, Options& options) {
-  unique_ptr<WritableFileWriter> file_writer;
-  unique_ptr<RandomAccessFileReader> file_reader;
-  unique_ptr<TableReader> table_reader;
+  std::unique_ptr<WritableFileWriter> file_writer;
+  std::unique_ptr<RandomAccessFileReader> file_reader;
+  std::unique_ptr<TableReader> table_reader;
   int level_ = -1;
 
   std::vector<std::string> keys;
@@ -553,8 +549,9 @@ void TestBoundary(InternalKey& ik1, std::string& v1, InternalKey& ik2,
   EnvOptions soptions;
 
   soptions.use_mmap_reads = ioptions.allow_mmap_reads;
-  file_writer.reset(test::GetWritableFileWriter(new test::StringSink()));
-  unique_ptr<TableBuilder> builder;
+  file_writer.reset(
+      test::GetWritableFileWriter(new test::StringSink(), "" /* don't care */));
+  std::unique_ptr<TableBuilder> builder;
   std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
       int_tbl_prop_collector_factories;
   std::string column_family_name;
diff --git a/3rdParty/rocksdb/v5.16.X/table/filter_block.h b/3rdParty/rocksdb/v5.18.X/table/filter_block.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/filter_block.h
rename to 3rdParty/rocksdb/v5.18.X/table/filter_block.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/flush_block_policy.cc b/3rdParty/rocksdb/v5.18.X/table/flush_block_policy.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/flush_block_policy.cc
rename to 3rdParty/rocksdb/v5.18.X/table/flush_block_policy.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/format.cc b/3rdParty/rocksdb/v5.18.X/table/format.cc
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/table/format.cc
rename to 3rdParty/rocksdb/v5.18.X/table/format.cc
index a4e448870b..0e43e82433 100644
--- a/3rdParty/rocksdb/v5.16.X/table/format.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/format.cc
@@ -24,6 +24,7 @@
 #include "util/crc32c.h"
 #include "util/file_reader_writer.h"
 #include "util/logging.h"
+#include "util/memory_allocator.h"
 #include "util/stop_watch.h"
 #include "util/string_util.h"
 #include "util/xxhash.h"
@@ -54,13 +55,6 @@ void BlockHandle::EncodeTo(std::string* dst) const {
   PutVarint64Varint64(dst, offset_, size_);
 }
 
-void BlockHandle::EncodeSizeTo(std::string* dst) const {
-  // Sanity check that all fields have been set
-  assert(offset_ != ~static_cast<uint64_t>(0));
-  assert(size_ != ~static_cast<uint64_t>(0));
-  PutVarint64(dst, size_);
-}
-
 Status BlockHandle::DecodeFrom(Slice* input) {
   if (GetVarint64(input, &offset_) &&
       GetVarint64(input, &size_)) {
@@ -286,8 +280,8 @@ Status ReadFooterFromFile(RandomAccessFileReader* file,
 Status UncompressBlockContentsForCompressionType(
     const UncompressionContext& uncompression_ctx, const char* data, size_t n,
     BlockContents* contents, uint32_t format_version,
-    const ImmutableCFOptions& ioptions) {
-  std::unique_ptr<char[]> ubuf;
+    const ImmutableCFOptions& ioptions, MemoryAllocator* allocator) {
+  CacheAllocationPtr ubuf;
 
   assert(uncompression_ctx.type() != kNoCompression &&
          "Invalid compression type");
@@ -303,81 +297,82 @@ Status UncompressBlockContentsForCompressionType(
       if (!Snappy_GetUncompressedLength(data, n, &ulength)) {
         return Status::Corruption(snappy_corrupt_msg);
       }
-      ubuf.reset(new char[ulength]);
+      ubuf = AllocateBlock(ulength, allocator);
       if (!Snappy_Uncompress(data, n, ubuf.get())) {
         return Status::Corruption(snappy_corrupt_msg);
       }
-      *contents = BlockContents(std::move(ubuf), ulength, true, kNoCompression);
+      *contents = BlockContents(std::move(ubuf), ulength);
       break;
     }
     case kZlibCompression:
-      ubuf.reset(Zlib_Uncompress(
+      ubuf = Zlib_Uncompress(
           uncompression_ctx, data, n, &decompress_size,
-          GetCompressFormatForVersion(kZlibCompression, format_version)));
+          GetCompressFormatForVersion(kZlibCompression, format_version),
+          allocator);
       if (!ubuf) {
         static char zlib_corrupt_msg[] =
           "Zlib not supported or corrupted Zlib compressed block contents";
         return Status::Corruption(zlib_corrupt_msg);
       }
-      *contents =
-          BlockContents(std::move(ubuf), decompress_size, true, kNoCompression);
+      *contents = BlockContents(std::move(ubuf), decompress_size);
       break;
     case kBZip2Compression:
-      ubuf.reset(BZip2_Uncompress(
+      ubuf = BZip2_Uncompress(
           data, n, &decompress_size,
-          GetCompressFormatForVersion(kBZip2Compression, format_version)));
+          GetCompressFormatForVersion(kBZip2Compression, format_version),
+          allocator);
       if (!ubuf) {
         static char bzip2_corrupt_msg[] =
           "Bzip2 not supported or corrupted Bzip2 compressed block contents";
         return Status::Corruption(bzip2_corrupt_msg);
       }
-      *contents =
-          BlockContents(std::move(ubuf), decompress_size, true, kNoCompression);
+      *contents = BlockContents(std::move(ubuf), decompress_size);
       break;
     case kLZ4Compression:
-      ubuf.reset(LZ4_Uncompress(
+      ubuf = LZ4_Uncompress(
           uncompression_ctx, data, n, &decompress_size,
-          GetCompressFormatForVersion(kLZ4Compression, format_version)));
+          GetCompressFormatForVersion(kLZ4Compression, format_version),
+          allocator);
       if (!ubuf) {
         static char lz4_corrupt_msg[] =
           "LZ4 not supported or corrupted LZ4 compressed block contents";
         return Status::Corruption(lz4_corrupt_msg);
       }
-      *contents =
-          BlockContents(std::move(ubuf), decompress_size, true, kNoCompression);
+      *contents = BlockContents(std::move(ubuf), decompress_size);
       break;
     case kLZ4HCCompression:
-      ubuf.reset(LZ4_Uncompress(
+      ubuf = LZ4_Uncompress(
           uncompression_ctx, data, n, &decompress_size,
-          GetCompressFormatForVersion(kLZ4HCCompression, format_version)));
+          GetCompressFormatForVersion(kLZ4HCCompression, format_version),
+          allocator);
       if (!ubuf) {
         static char lz4hc_corrupt_msg[] =
           "LZ4HC not supported or corrupted LZ4HC compressed block contents";
         return Status::Corruption(lz4hc_corrupt_msg);
       }
-      *contents =
-          BlockContents(std::move(ubuf), decompress_size, true, kNoCompression);
+      *contents = BlockContents(std::move(ubuf), decompress_size);
       break;
     case kXpressCompression:
+      // XPRESS allocates memory internally, thus no support for custom
+      // allocator.
       ubuf.reset(XPRESS_Uncompress(data, n, &decompress_size));
       if (!ubuf) {
         static char xpress_corrupt_msg[] =
           "XPRESS not supported or corrupted XPRESS compressed block contents";
         return Status::Corruption(xpress_corrupt_msg);
       }
-      *contents =
-        BlockContents(std::move(ubuf), decompress_size, true, kNoCompression);
+      *contents = BlockContents(std::move(ubuf), decompress_size);
       break;
     case kZSTD:
     case kZSTDNotFinalCompression:
-      ubuf.reset(ZSTD_Uncompress(uncompression_ctx, data, n, &decompress_size));
+      ubuf = ZSTD_Uncompress(uncompression_ctx, data, n, &decompress_size,
+                             allocator);
       if (!ubuf) {
         static char zstd_corrupt_msg[] =
             "ZSTD not supported or corrupted ZSTD compressed block contents";
         return Status::Corruption(zstd_corrupt_msg);
       }
-      *contents =
-          BlockContents(std::move(ubuf), decompress_size, true, kNoCompression);
+      *contents = BlockContents(std::move(ubuf), decompress_size);
       break;
     default:
       return Status::Corruption("bad block type");
@@ -403,11 +398,13 @@ Status UncompressBlockContentsForCompressionType(
 Status UncompressBlockContents(const UncompressionContext& uncompression_ctx,
                                const char* data, size_t n,
                                BlockContents* contents, uint32_t format_version,
-                               const ImmutableCFOptions& ioptions) {
+                               const ImmutableCFOptions& ioptions,
+                               MemoryAllocator* allocator) {
   assert(data[n] != kNoCompression);
   assert(data[n] == uncompression_ctx.type());
-  return UncompressBlockContentsForCompressionType(
-      uncompression_ctx, data, n, contents, format_version, ioptions);
+  return UncompressBlockContentsForCompressionType(uncompression_ctx, data, n,
+                                                   contents, format_version,
+                                                   ioptions, allocator);
 }
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/table/format.h b/3rdParty/rocksdb/v5.18.X/table/format.h
similarity index 85%
rename from 3rdParty/rocksdb/v5.16.X/table/format.h
rename to 3rdParty/rocksdb/v5.18.X/table/format.h
index ebc9c25397..ae2bdafcc1 100644
--- a/3rdParty/rocksdb/v5.16.X/table/format.h
+++ b/3rdParty/rocksdb/v5.18.X/table/format.h
@@ -26,6 +26,7 @@
 #include "port/port.h"  // noexcept
 #include "table/persistent_cache_options.h"
 #include "util/file_reader_writer.h"
+#include "util/memory_allocator.h"
 
 namespace rocksdb {
 
@@ -55,7 +56,6 @@ class BlockHandle {
   void EncodeTo(std::string* dst) const;
   Status DecodeFrom(Slice* input);
   Status DecodeSizeFrom(uint64_t offset, Slice* input);
-  void EncodeSizeTo(std::string* dst) const;
 
   // Return a string that contains the copy of handle.
   std::string ToString(bool hex = true) const;
@@ -189,28 +189,50 @@ Status ReadFooterFromFile(RandomAccessFileReader* file,
 // 1-byte type + 32-bit crc
 static const size_t kBlockTrailerSize = 5;
 
+inline CompressionType get_block_compression_type(const char* block_data,
+                                                  size_t block_size) {
+  return static_cast<CompressionType>(block_data[block_size]);
+}
+
 struct BlockContents {
   Slice data;     // Actual contents of data
-  bool cachable;  // True iff data can be cached
-  CompressionType compression_type;
-  std::unique_ptr<char[]> allocation;
+  CacheAllocationPtr allocation;
 
-  BlockContents() : cachable(false), compression_type(kNoCompression) {}
+#ifndef NDEBUG
+  // Whether the block is a raw block, which contains compression type
+  // byte. It is only used for assertion.
+  bool is_raw_block = false;
+#endif  // NDEBUG
 
-  BlockContents(const Slice& _data, bool _cachable,
-                CompressionType _compression_type)
-      : data(_data), cachable(_cachable), compression_type(_compression_type) {}
+  BlockContents() {}
 
-  BlockContents(std::unique_ptr<char[]>&& _data, size_t _size, bool _cachable,
-                CompressionType _compression_type)
-      : data(_data.get(), _size),
-        cachable(_cachable),
-        compression_type(_compression_type),
-        allocation(std::move(_data)) {}
+  BlockContents(const Slice& _data) : data(_data) {}
+
+  BlockContents(CacheAllocationPtr&& _data, size_t _size)
+      : data(_data.get(), _size), allocation(std::move(_data)) {}
+
+  BlockContents(std::unique_ptr<char[]>&& _data, size_t _size)
+      : data(_data.get(), _size) {
+    allocation.reset(_data.release());
+  }
+
+  bool own_bytes() const { return allocation.get() != nullptr; }
+
+  // It's the caller's responsibility to make sure that this is
+  // for raw block contents, which contains the compression
+  // byte in the end.
+  CompressionType get_compression_type() const {
+    assert(is_raw_block);
+    return get_block_compression_type(data.data(), data.size());
+  }
 
   // The additional memory space taken by the block data.
   size_t usable_size() const {
     if (allocation.get() != nullptr) {
+      auto allocator = allocation.get_deleter().allocator;
+      if (allocator) {
+        return allocator->UsableSize(allocation.get(), data.size());
+      }
 #ifdef ROCKSDB_MALLOC_USABLE_SIZE
       return malloc_usable_size(allocation.get());
 #else
@@ -221,15 +243,20 @@ struct BlockContents {
     }
   }
 
+  size_t ApproximateMemoryUsage() const {
+    return usable_size() + sizeof(*this);
+  }
+
   BlockContents(BlockContents&& other) ROCKSDB_NOEXCEPT {
     *this = std::move(other);
   }
 
   BlockContents& operator=(BlockContents&& other) {
     data = std::move(other.data);
-    cachable = other.cachable;
-    compression_type = other.compression_type;
     allocation = std::move(other.allocation);
+#ifndef NDEBUG
+    is_raw_block = other.is_raw_block;
+#endif  // NDEBUG
     return *this;
   }
 };
@@ -253,7 +280,7 @@ extern Status ReadBlockContents(
 extern Status UncompressBlockContents(
     const UncompressionContext& uncompression_ctx, const char* data, size_t n,
     BlockContents* contents, uint32_t compress_format_version,
-    const ImmutableCFOptions& ioptions);
+    const ImmutableCFOptions& ioptions, MemoryAllocator* allocator = nullptr);
 
 // This is an extension to UncompressBlockContents that accepts
 // a specific compression type. This is used by un-wrapped blocks
@@ -261,7 +288,7 @@ extern Status UncompressBlockContents(
 extern Status UncompressBlockContentsForCompressionType(
     const UncompressionContext& uncompression_ctx, const char* data, size_t n,
     BlockContents* contents, uint32_t compress_format_version,
-    const ImmutableCFOptions& ioptions);
+    const ImmutableCFOptions& ioptions, MemoryAllocator* allocator = nullptr);
 
 // Implementation details follow.  Clients should ignore,
 
diff --git a/3rdParty/rocksdb/v5.16.X/table/full_filter_bits_builder.h b/3rdParty/rocksdb/v5.18.X/table/full_filter_bits_builder.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/full_filter_bits_builder.h
rename to 3rdParty/rocksdb/v5.18.X/table/full_filter_bits_builder.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/full_filter_block.cc b/3rdParty/rocksdb/v5.18.X/table/full_filter_block.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/full_filter_block.cc
rename to 3rdParty/rocksdb/v5.18.X/table/full_filter_block.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/full_filter_block.h b/3rdParty/rocksdb/v5.18.X/table/full_filter_block.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/full_filter_block.h
rename to 3rdParty/rocksdb/v5.18.X/table/full_filter_block.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/full_filter_block_test.cc b/3rdParty/rocksdb/v5.18.X/table/full_filter_block_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/full_filter_block_test.cc
rename to 3rdParty/rocksdb/v5.18.X/table/full_filter_block_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/get_context.cc b/3rdParty/rocksdb/v5.18.X/table/get_context.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/table/get_context.cc
rename to 3rdParty/rocksdb/v5.18.X/table/get_context.cc
index 0aa75b6079..6f0bd2ebbc 100644
--- a/3rdParty/rocksdb/v5.16.X/table/get_context.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/get_context.cc
@@ -43,7 +43,7 @@ GetContext::GetContext(const Comparator* ucmp,
                        Statistics* statistics, GetState init_state,
                        const Slice& user_key, PinnableSlice* pinnable_val,
                        bool* value_found, MergeContext* merge_context,
-                       RangeDelAggregator* _range_del_agg, Env* env,
+                       SequenceNumber* _max_covering_tombstone_seq, Env* env,
                        SequenceNumber* seq,
                        PinnedIteratorsManager* _pinned_iters_mgr,
                        ReadCallback* callback, bool* is_blob_index)
@@ -56,7 +56,7 @@ GetContext::GetContext(const Comparator* ucmp,
       pinnable_val_(pinnable_val),
       value_found_(value_found),
       merge_context_(merge_context),
-      range_del_agg_(_range_del_agg),
+      max_covering_tombstone_seq_(_max_covering_tombstone_seq),
       env_(env),
       seq_(seq),
       replay_log_(nullptr),
@@ -185,7 +185,8 @@ bool GetContext::SaveValue(const ParsedInternalKey& parsed_key,
     auto type = parsed_key.type;
     // Key matches. Process it
     if ((type == kTypeValue || type == kTypeMerge || type == kTypeBlobIndex) &&
-        range_del_agg_ != nullptr && range_del_agg_->ShouldDelete(parsed_key)) {
+        max_covering_tombstone_seq_ != nullptr &&
+        *max_covering_tombstone_seq_ > parsed_key.sequence) {
       type = kTypeRangeDeletion;
     }
     switch (type) {
diff --git a/3rdParty/rocksdb/v5.16.X/table/get_context.h b/3rdParty/rocksdb/v5.18.X/table/get_context.h
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/table/get_context.h
rename to 3rdParty/rocksdb/v5.18.X/table/get_context.h
index 066be104ba..407473808f 100644
--- a/3rdParty/rocksdb/v5.16.X/table/get_context.h
+++ b/3rdParty/rocksdb/v5.18.X/table/get_context.h
@@ -6,7 +6,6 @@
 #pragma once
 #include <string>
 #include "db/merge_context.h"
-#include "db/range_del_aggregator.h"
 #include "db/read_callback.h"
 #include "rocksdb/env.h"
 #include "rocksdb/statistics.h"
@@ -52,8 +51,9 @@ class GetContext {
   GetContext(const Comparator* ucmp, const MergeOperator* merge_operator,
              Logger* logger, Statistics* statistics, GetState init_state,
              const Slice& user_key, PinnableSlice* value, bool* value_found,
-             MergeContext* merge_context, RangeDelAggregator* range_del_agg,
-             Env* env, SequenceNumber* seq = nullptr,
+             MergeContext* merge_context,
+             SequenceNumber* max_covering_tombstone_seq, Env* env,
+             SequenceNumber* seq = nullptr,
              PinnedIteratorsManager* _pinned_iters_mgr = nullptr,
              ReadCallback* callback = nullptr, bool* is_blob_index = nullptr);
 
@@ -76,7 +76,9 @@ class GetContext {
 
   GetState State() const { return state_; }
 
-  RangeDelAggregator* range_del_agg() { return range_del_agg_; }
+  SequenceNumber* max_covering_tombstone_seq() {
+    return max_covering_tombstone_seq_;
+  }
 
   PinnedIteratorsManager* pinned_iters_mgr() { return pinned_iters_mgr_; }
 
@@ -111,7 +113,7 @@ class GetContext {
   PinnableSlice* pinnable_val_;
   bool* value_found_;  // Is value set correctly? Used by KeyMayExist
   MergeContext* merge_context_;
-  RangeDelAggregator* range_del_agg_;
+  SequenceNumber* max_covering_tombstone_seq_;
   Env* env_;
   // If a key is found, seq_ will be set to the SequenceNumber of most recent
   // write to the key or kMaxSequenceNumber if unknown
diff --git a/3rdParty/rocksdb/v5.16.X/table/index_builder.cc b/3rdParty/rocksdb/v5.18.X/table/index_builder.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/table/index_builder.cc
rename to 3rdParty/rocksdb/v5.18.X/table/index_builder.cc
index 5eaecbad10..cd28c42a8b 100644
--- a/3rdParty/rocksdb/v5.16.X/table/index_builder.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/index_builder.cc
@@ -210,7 +210,5 @@ Status PartitionedIndexBuilder::Finish(
   }
 }
 
-size_t PartitionedIndexBuilder::NumPartitions() const {
-  return partition_cnt_;
-}
+size_t PartitionedIndexBuilder::NumPartitions() const { return partition_cnt_; }
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/table/index_builder.h b/3rdParty/rocksdb/v5.18.X/table/index_builder.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/table/index_builder.h
rename to 3rdParty/rocksdb/v5.18.X/table/index_builder.h
index 147108d3b1..87d7b7a71b 100644
--- a/3rdParty/rocksdb/v5.16.X/table/index_builder.h
+++ b/3rdParty/rocksdb/v5.18.X/table/index_builder.h
@@ -181,9 +181,7 @@ class ShortenedIndexBuilder : public IndexBuilder {
     return Status::OK();
   }
 
-  virtual size_t IndexSize() const override {
-    return index_size_;
-  }
+  virtual size_t IndexSize() const override { return index_size_; }
 
   virtual bool seperator_is_key_plus_seq() override {
     return seperator_is_key_plus_seq_;
@@ -353,12 +351,8 @@ class PartitionedIndexBuilder : public IndexBuilder {
       IndexBlocks* index_blocks,
       const BlockHandle& last_partition_block_handle) override;
 
-  virtual size_t IndexSize() const override {
-    return index_size_;
-  }
-  size_t TopLevelIndexSize(uint64_t) const {
-    return top_level_index_size_;
-  }
+  virtual size_t IndexSize() const override { return index_size_; }
+  size_t TopLevelIndexSize(uint64_t) const { return top_level_index_size_; }
   size_t NumPartitions() const;
 
   inline bool ShouldCutFilterBlock() {
diff --git a/3rdParty/rocksdb/v5.16.X/table/internal_iterator.h b/3rdParty/rocksdb/v5.18.X/table/internal_iterator.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/internal_iterator.h
rename to 3rdParty/rocksdb/v5.18.X/table/internal_iterator.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/iter_heap.h b/3rdParty/rocksdb/v5.18.X/table/iter_heap.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/iter_heap.h
rename to 3rdParty/rocksdb/v5.18.X/table/iter_heap.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/iterator.cc b/3rdParty/rocksdb/v5.18.X/table/iterator.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/table/iterator.cc
rename to 3rdParty/rocksdb/v5.18.X/table/iterator.cc
index 97c47fb285..3a1063f6ef 100644
--- a/3rdParty/rocksdb/v5.16.X/table/iterator.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/iterator.cc
@@ -103,7 +103,7 @@ Status Iterator::GetProperty(std::string prop_name, std::string* prop) {
     *prop = "0";
     return Status::OK();
   }
-  return Status::InvalidArgument("Undentified property.");
+  return Status::InvalidArgument("Unidentified property.");
 }
 
 namespace {
diff --git a/3rdParty/rocksdb/v5.16.X/table/iterator_wrapper.h b/3rdParty/rocksdb/v5.18.X/table/iterator_wrapper.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/iterator_wrapper.h
rename to 3rdParty/rocksdb/v5.18.X/table/iterator_wrapper.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/merger_test.cc b/3rdParty/rocksdb/v5.18.X/table/merger_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/merger_test.cc
rename to 3rdParty/rocksdb/v5.18.X/table/merger_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/merging_iterator.cc b/3rdParty/rocksdb/v5.18.X/table/merging_iterator.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/merging_iterator.cc
rename to 3rdParty/rocksdb/v5.18.X/table/merging_iterator.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/merging_iterator.h b/3rdParty/rocksdb/v5.18.X/table/merging_iterator.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/merging_iterator.h
rename to 3rdParty/rocksdb/v5.18.X/table/merging_iterator.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/meta_blocks.cc b/3rdParty/rocksdb/v5.18.X/table/meta_blocks.cc
similarity index 85%
rename from 3rdParty/rocksdb/v5.16.X/table/meta_blocks.cc
rename to 3rdParty/rocksdb/v5.18.X/table/meta_blocks.cc
index 256730bfa7..fdf8a56120 100644
--- a/3rdParty/rocksdb/v5.16.X/table/meta_blocks.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/meta_blocks.cc
@@ -79,6 +79,8 @@ void PropertyBlockBuilder::AddTableProperty(const TableProperties& props) {
   Add(TablePropertiesNames::kIndexValueIsDeltaEncoded,
       props.index_value_is_delta_encoded);
   Add(TablePropertiesNames::kNumEntries, props.num_entries);
+  Add(TablePropertiesNames::kDeletedKeys, props.num_deletions);
+  Add(TablePropertiesNames::kMergeOperands, props.num_merge_operands);
   Add(TablePropertiesNames::kNumRangeDeletions, props.num_range_deletions);
   Add(TablePropertiesNames::kNumDataBlocks, props.num_data_blocks);
   Add(TablePropertiesNames::kFilterSize, props.filter_size);
@@ -173,7 +175,8 @@ Status ReadProperties(const Slice& handle_value, RandomAccessFileReader* file,
                       FilePrefetchBuffer* prefetch_buffer, const Footer& footer,
                       const ImmutableCFOptions& ioptions,
                       TableProperties** table_properties,
-                      bool compression_type_missing) {
+                      bool /*compression_type_missing*/,
+                      MemoryAllocator* memory_allocator) {
   assert(table_properties);
 
   Slice v = handle_value;
@@ -189,15 +192,13 @@ Status ReadProperties(const Slice& handle_value, RandomAccessFileReader* file,
   Slice compression_dict;
   PersistentCacheOptions cache_options;
 
-  BlockFetcher block_fetcher(
-      file, prefetch_buffer, footer, read_options, handle, &block_contents,
-      ioptions, false /* decompress */, compression_dict, cache_options);
+  BlockFetcher block_fetcher(file, prefetch_buffer, footer, read_options,
+                             handle, &block_contents, ioptions,
+                             false /* decompress */, false /*maybe_compressed*/,
+                             compression_dict, cache_options, memory_allocator);
   s = block_fetcher.ReadBlockContents();
-  // override compression_type when table file is known to contain undefined
-  // value at compression type marker
-  if (compression_type_missing) {
-    block_contents.compression_type = kNoCompression;
-  }
+  // property block is never compressed. Need to add uncompress logic if we are
+  // to compress it..
 
   if (!s.ok()) {
     return s;
@@ -229,6 +230,10 @@ Status ReadProperties(const Slice& handle_value, RandomAccessFileReader* file,
       {TablePropertiesNames::kNumDataBlocks,
        &new_table_properties->num_data_blocks},
       {TablePropertiesNames::kNumEntries, &new_table_properties->num_entries},
+      {TablePropertiesNames::kDeletedKeys,
+       &new_table_properties->num_deletions},
+      {TablePropertiesNames::kMergeOperands,
+       &new_table_properties->num_merge_operands},
       {TablePropertiesNames::kNumRangeDeletions,
        &new_table_properties->num_range_deletions},
       {TablePropertiesNames::kFormatVersion,
@@ -263,6 +268,12 @@ Status ReadProperties(const Slice& handle_value, RandomAccessFileReader* file,
         {key, handle.offset() + iter.ValueOffset()});
 
     if (pos != predefined_uint64_properties.end()) {
+      if (key == TablePropertiesNames::kDeletedKeys ||
+          key == TablePropertiesNames::kMergeOperands) {
+        // Insert in user-collected properties for API backwards compatibility
+        new_table_properties->user_collected_properties.insert(
+            {key, raw_val.ToString()});
+      }
       // handle predefined rocksdb properties
       uint64_t val;
       if (!GetVarint64(&raw_val, &val)) {
@@ -305,9 +316,10 @@ Status ReadProperties(const Slice& handle_value, RandomAccessFileReader* file,
 
 Status ReadTableProperties(RandomAccessFileReader* file, uint64_t file_size,
                            uint64_t table_magic_number,
-                           const ImmutableCFOptions &ioptions,
+                           const ImmutableCFOptions& ioptions,
                            TableProperties** properties,
-                           bool compression_type_missing) {
+                           bool compression_type_missing,
+                           MemoryAllocator* memory_allocator) {
   // -- Read metaindex block
   Footer footer;
   auto s = ReadFooterFromFile(file, nullptr /* prefetch_buffer */, file_size,
@@ -323,19 +335,17 @@ Status ReadTableProperties(RandomAccessFileReader* file, uint64_t file_size,
   Slice compression_dict;
   PersistentCacheOptions cache_options;
 
-  BlockFetcher block_fetcher(
-      file, nullptr /* prefetch_buffer */, footer, read_options,
-      metaindex_handle, &metaindex_contents, ioptions, false /* decompress */,
-      compression_dict, cache_options);
+  BlockFetcher block_fetcher(file, nullptr /* prefetch_buffer */, footer,
+                             read_options, metaindex_handle,
+                             &metaindex_contents, ioptions,
+                             false /* decompress */, false /*maybe_compressed*/,
+                             compression_dict, cache_options, memory_allocator);
   s = block_fetcher.ReadBlockContents();
   if (!s.ok()) {
     return s;
   }
-  // override compression_type when table file is known to contain undefined
-  // value at compression type marker
-  if (compression_type_missing) {
-    metaindex_contents.compression_type = kNoCompression;
-  }
+  // property blocks are never compressed. Need to add uncompress logic if we
+  // are to compress it.
   Block metaindex_block(std::move(metaindex_contents),
                         kDisableGlobalSequenceNumber);
   std::unique_ptr<InternalIterator> meta_iter(
@@ -352,7 +362,8 @@ Status ReadTableProperties(RandomAccessFileReader* file, uint64_t file_size,
   TableProperties table_properties;
   if (found_properties_block == true) {
     s = ReadProperties(meta_iter->value(), file, nullptr /* prefetch_buffer */,
-                       footer, ioptions, properties, compression_type_missing);
+                       footer, ioptions, properties, compression_type_missing,
+                       memory_allocator);
   } else {
     s = Status::NotFound();
   }
@@ -375,10 +386,11 @@ Status FindMetaBlock(InternalIterator* meta_index_iter,
 
 Status FindMetaBlock(RandomAccessFileReader* file, uint64_t file_size,
                      uint64_t table_magic_number,
-                     const ImmutableCFOptions &ioptions,
+                     const ImmutableCFOptions& ioptions,
                      const std::string& meta_block_name,
                      BlockHandle* block_handle,
-                     bool compression_type_missing) {
+                     bool /*compression_type_missing*/,
+                     MemoryAllocator* memory_allocator) {
   Footer footer;
   auto s = ReadFooterFromFile(file, nullptr /* prefetch_buffer */, file_size,
                               &footer, table_magic_number);
@@ -395,16 +407,14 @@ Status FindMetaBlock(RandomAccessFileReader* file, uint64_t file_size,
   BlockFetcher block_fetcher(
       file, nullptr /* prefetch_buffer */, footer, read_options,
       metaindex_handle, &metaindex_contents, ioptions,
-      false /* do decompression */, compression_dict, cache_options);
+      false /* do decompression */, false /*maybe_compressed*/,
+      compression_dict, cache_options, memory_allocator);
   s = block_fetcher.ReadBlockContents();
   if (!s.ok()) {
     return s;
   }
-  // override compression_type when table file is known to contain undefined
-  // value at compression type marker
-  if (compression_type_missing) {
-    metaindex_contents.compression_type = kNoCompression;
-  }
+  // meta blocks are never compressed. Need to add uncompress logic if we are to
+  // compress it.
   Block metaindex_block(std::move(metaindex_contents),
                         kDisableGlobalSequenceNumber);
 
@@ -420,7 +430,8 @@ Status ReadMetaBlock(RandomAccessFileReader* file,
                      uint64_t table_magic_number,
                      const ImmutableCFOptions& ioptions,
                      const std::string& meta_block_name,
-                     BlockContents* contents, bool compression_type_missing) {
+                     BlockContents* contents, bool /*compression_type_missing*/,
+                     MemoryAllocator* memory_allocator) {
   Status status;
   Footer footer;
   status = ReadFooterFromFile(file, prefetch_buffer, file_size, &footer,
@@ -439,17 +450,14 @@ Status ReadMetaBlock(RandomAccessFileReader* file,
 
   BlockFetcher block_fetcher(file, prefetch_buffer, footer, read_options,
                              metaindex_handle, &metaindex_contents, ioptions,
-                             false /* decompress */, compression_dict,
-                             cache_options);
+                             false /* decompress */, false /*maybe_compressed*/,
+                             compression_dict, cache_options, memory_allocator);
   status = block_fetcher.ReadBlockContents();
   if (!status.ok()) {
     return status;
   }
-  // override compression_type when table file is known to contain undefined
-  // value at compression type marker
-  if (compression_type_missing) {
-    metaindex_contents.compression_type = kNoCompression;
-  }
+  // meta block is never compressed. Need to add uncompress logic if we are to
+  // compress it.
 
   // Finding metablock
   Block metaindex_block(std::move(metaindex_contents),
@@ -469,7 +477,8 @@ Status ReadMetaBlock(RandomAccessFileReader* file,
   // Reading metablock
   BlockFetcher block_fetcher2(
       file, prefetch_buffer, footer, read_options, block_handle, contents,
-      ioptions, false /* decompress */, compression_dict, cache_options);
+      ioptions, false /* decompress */, false /*maybe_compressed*/,
+      compression_dict, cache_options, memory_allocator);
   return block_fetcher2.ReadBlockContents();
 }
 
diff --git a/3rdParty/rocksdb/v5.16.X/table/meta_blocks.h b/3rdParty/rocksdb/v5.18.X/table/meta_blocks.h
similarity index 89%
rename from 3rdParty/rocksdb/v5.16.X/table/meta_blocks.h
rename to 3rdParty/rocksdb/v5.18.X/table/meta_blocks.h
index a18c8edc47..1c8fe686ca 100644
--- a/3rdParty/rocksdb/v5.16.X/table/meta_blocks.h
+++ b/3rdParty/rocksdb/v5.18.X/table/meta_blocks.h
@@ -11,12 +11,13 @@
 
 #include "db/builder.h"
 #include "db/table_properties_collector.h"
-#include "util/kv_map.h"
 #include "rocksdb/comparator.h"
+#include "rocksdb/memory_allocator.h"
 #include "rocksdb/options.h"
 #include "rocksdb/slice.h"
 #include "table/block_builder.h"
 #include "table/format.h"
+#include "util/kv_map.h"
 
 namespace rocksdb {
 
@@ -96,7 +97,8 @@ Status ReadProperties(const Slice& handle_value, RandomAccessFileReader* file,
                       FilePrefetchBuffer* prefetch_buffer, const Footer& footer,
                       const ImmutableCFOptions& ioptions,
                       TableProperties** table_properties,
-                      bool compression_type_missing = false);
+                      bool compression_type_missing = false,
+                      MemoryAllocator* memory_allocator = nullptr);
 
 // Directly read the properties from the properties block of a plain table.
 // @returns a status to indicate if the operation succeeded. On success,
@@ -108,9 +110,10 @@ Status ReadProperties(const Slice& handle_value, RandomAccessFileReader* file,
 // `ReadProperties`, `FindMetaBlock`, and `ReadMetaBlock`
 Status ReadTableProperties(RandomAccessFileReader* file, uint64_t file_size,
                            uint64_t table_magic_number,
-                           const ImmutableCFOptions &ioptions,
+                           const ImmutableCFOptions& ioptions,
                            TableProperties** properties,
-                           bool compression_type_missing = false);
+                           bool compression_type_missing = false,
+                           MemoryAllocator* memory_allocator = nullptr);
 
 // Find the meta block from the meta index block.
 Status FindMetaBlock(InternalIterator* meta_index_iter,
@@ -120,10 +123,11 @@ Status FindMetaBlock(InternalIterator* meta_index_iter,
 // Find the meta block
 Status FindMetaBlock(RandomAccessFileReader* file, uint64_t file_size,
                      uint64_t table_magic_number,
-                     const ImmutableCFOptions &ioptions,
+                     const ImmutableCFOptions& ioptions,
                      const std::string& meta_block_name,
                      BlockHandle* block_handle,
-                     bool compression_type_missing = false);
+                     bool compression_type_missing = false,
+                     MemoryAllocator* memory_allocator = nullptr);
 
 // Read the specified meta block with name meta_block_name
 // from `file` and initialize `contents` with contents of this block.
@@ -134,6 +138,7 @@ Status ReadMetaBlock(RandomAccessFileReader* file,
                      const ImmutableCFOptions& ioptions,
                      const std::string& meta_block_name,
                      BlockContents* contents,
-                     bool compression_type_missing = false);
+                     bool compression_type_missing = false,
+                     MemoryAllocator* memory_allocator = nullptr);
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/table/mock_table.cc b/3rdParty/rocksdb/v5.18.X/table/mock_table.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/table/mock_table.cc
rename to 3rdParty/rocksdb/v5.18.X/table/mock_table.cc
index 54bab73d8a..65a4361696 100644
--- a/3rdParty/rocksdb/v5.16.X/table/mock_table.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/mock_table.cc
@@ -60,8 +60,8 @@ MockTableFactory::MockTableFactory() : next_id_(1) {}
 
 Status MockTableFactory::NewTableReader(
     const TableReaderOptions& /*table_reader_options*/,
-    unique_ptr<RandomAccessFileReader>&& file, uint64_t /*file_size*/,
-    unique_ptr<TableReader>* table_reader,
+    std::unique_ptr<RandomAccessFileReader>&& file, uint64_t /*file_size*/,
+    std::unique_ptr<TableReader>* table_reader,
     bool /*prefetch_index_and_filter_in_cache*/) const {
   uint32_t id = GetIDFromFile(file.get());
 
@@ -93,7 +93,7 @@ Status MockTableFactory::CreateMockTable(Env* env, const std::string& fname,
     return s;
   }
 
-  WritableFileWriter file_writer(std::move(file), EnvOptions());
+  WritableFileWriter file_writer(std::move(file), fname, EnvOptions());
 
   uint32_t id = GetAndWriteNextID(&file_writer);
   file_system_.files.insert({id, std::move(file_contents)});
diff --git a/3rdParty/rocksdb/v5.16.X/table/mock_table.h b/3rdParty/rocksdb/v5.18.X/table/mock_table.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/table/mock_table.h
rename to 3rdParty/rocksdb/v5.18.X/table/mock_table.h
index 92cf87370f..2f123a963c 100644
--- a/3rdParty/rocksdb/v5.16.X/table/mock_table.h
+++ b/3rdParty/rocksdb/v5.18.X/table/mock_table.h
@@ -157,8 +157,8 @@ class MockTableFactory : public TableFactory {
   const char* Name() const override { return "MockTable"; }
   Status NewTableReader(
       const TableReaderOptions& table_reader_options,
-      unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
-      unique_ptr<TableReader>* table_reader,
+      std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+      std::unique_ptr<TableReader>* table_reader,
       bool prefetch_index_and_filter_in_cache = true) const override;
   TableBuilder* NewTableBuilder(
       const TableBuilderOptions& table_builder_options,
diff --git a/3rdParty/rocksdb/v5.16.X/table/partitioned_filter_block.cc b/3rdParty/rocksdb/v5.18.X/table/partitioned_filter_block.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/table/partitioned_filter_block.cc
rename to 3rdParty/rocksdb/v5.18.X/table/partitioned_filter_block.cc
index 6084133b75..aab0f5509b 100644
--- a/3rdParty/rocksdb/v5.16.X/table/partitioned_filter_block.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/partitioned_filter_block.cc
@@ -79,7 +79,10 @@ Slice PartitionedFilterBlockBuilder::Finish(
     std::string handle_encoding;
     last_partition_block_handle.EncodeTo(&handle_encoding);
     std::string handle_delta_encoding;
-    last_partition_block_handle.EncodeSizeTo(&handle_delta_encoding);
+    PutVarsignedint64(
+        &handle_delta_encoding,
+        last_partition_block_handle.size() - last_encoded_handle_.size());
+    last_encoded_handle_ = last_partition_block_handle;
     const Slice handle_delta_encoding_slice(handle_delta_encoding);
     index_on_filter_block_builder_.Add(last_entry.key, handle_encoding,
                                        &handle_delta_encoding_slice);
diff --git a/3rdParty/rocksdb/v5.16.X/table/partitioned_filter_block.h b/3rdParty/rocksdb/v5.18.X/table/partitioned_filter_block.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/table/partitioned_filter_block.h
rename to 3rdParty/rocksdb/v5.18.X/table/partitioned_filter_block.h
index f6241749db..5d55da5449 100644
--- a/3rdParty/rocksdb/v5.16.X/table/partitioned_filter_block.h
+++ b/3rdParty/rocksdb/v5.18.X/table/partitioned_filter_block.h
@@ -66,6 +66,7 @@ class PartitionedFilterBlockBuilder : public FullFilterBlockBuilder {
   uint32_t filters_in_partition_;
   // Number of keys added
   size_t num_added_;
+  BlockHandle last_encoded_handle_;
 };
 
 class PartitionedFilterBlockReader : public FilterBlockReader,
diff --git a/3rdParty/rocksdb/v5.16.X/table/partitioned_filter_block_test.cc b/3rdParty/rocksdb/v5.18.X/table/partitioned_filter_block_test.cc
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/table/partitioned_filter_block_test.cc
rename to 3rdParty/rocksdb/v5.18.X/table/partitioned_filter_block_test.cc
index 150eac6a8d..ffa8a9a563 100644
--- a/3rdParty/rocksdb/v5.16.X/table/partitioned_filter_block_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/partitioned_filter_block_test.cc
@@ -33,7 +33,7 @@ class MockedBlockBasedTable : public BlockBasedTable {
       const SliceTransform* prefix_extractor) const override {
     Slice slice = slices[filter_blk_handle.offset()];
     auto obj = new FullFilterBlockReader(
-        prefix_extractor, true, BlockContents(slice, false, kNoCompression),
+        prefix_extractor, true, BlockContents(slice),
         rep_->table_options.filter_policy->GetFilterBitsReader(slice), nullptr);
     return {obj, nullptr};
   }
@@ -44,13 +44,15 @@ class MockedBlockBasedTable : public BlockBasedTable {
       const SliceTransform* prefix_extractor) const override {
     Slice slice = slices[filter_blk_handle.offset()];
     auto obj = new FullFilterBlockReader(
-        prefix_extractor, true, BlockContents(slice, false, kNoCompression),
+        prefix_extractor, true, BlockContents(slice),
         rep_->table_options.filter_policy->GetFilterBitsReader(slice), nullptr);
     return obj;
   }
 };
 
-class PartitionedFilterBlockTest : public testing::Test {
+class PartitionedFilterBlockTest
+    : public testing::Test,
+      virtual public ::testing::WithParamInterface<uint32_t> {
  public:
   BlockBasedTableOptions table_options_;
   InternalKeyComparator icomp = InternalKeyComparator(BytewiseComparator());
@@ -60,6 +62,8 @@ class PartitionedFilterBlockTest : public testing::Test {
     table_options_.no_block_cache = true;  // Otherwise BlockBasedTable::Close
                                            // will access variable that are not
                                            // initialized in our mocked version
+    table_options_.format_version = GetParam();
+    table_options_.index_block_restart_interval = 3;
   }
 
   std::shared_ptr<Cache> cache_;
@@ -143,10 +147,10 @@ class PartitionedFilterBlockTest : public testing::Test {
     const bool kImmortal = true;
     table.reset(new MockedBlockBasedTable(
         new BlockBasedTable::Rep(ioptions, env_options, table_options_, icomp,
-                                 !kSkipFilters, !kImmortal)));
+                                 !kSkipFilters, 0, !kImmortal)));
     auto reader = new PartitionedFilterBlockReader(
-        prefix_extractor, true, BlockContents(slice, false, kNoCompression),
-        nullptr, nullptr, icomp, table.get(), pib->seperator_is_key_plus_seq(),
+        prefix_extractor, true, BlockContents(slice), nullptr, nullptr, icomp,
+        table.get(), pib->seperator_is_key_plus_seq(),
         !pib->get_use_value_delta_encoding());
     return reader;
   }
@@ -279,14 +283,19 @@ class PartitionedFilterBlockTest : public testing::Test {
   }
 };
 
-TEST_F(PartitionedFilterBlockTest, EmptyBuilder) {
+INSTANTIATE_TEST_CASE_P(FormatDef, PartitionedFilterBlockTest,
+                        testing::Values(test::kDefaultFormatVersion));
+INSTANTIATE_TEST_CASE_P(FormatLatest, PartitionedFilterBlockTest,
+                        testing::Values(test::kLatestFormatVersion));
+
+TEST_P(PartitionedFilterBlockTest, EmptyBuilder) {
   std::unique_ptr<PartitionedIndexBuilder> pib(NewIndexBuilder());
   std::unique_ptr<PartitionedFilterBlockBuilder> builder(NewBuilder(pib.get()));
   const bool empty = true;
   VerifyReader(builder.get(), pib.get(), empty);
 }
 
-TEST_F(PartitionedFilterBlockTest, OneBlock) {
+TEST_P(PartitionedFilterBlockTest, OneBlock) {
   uint64_t max_index_size = MaxIndexSize();
   for (uint64_t i = 1; i < max_index_size + 1; i++) {
     table_options_.metadata_block_size = i;
@@ -294,7 +303,7 @@ TEST_F(PartitionedFilterBlockTest, OneBlock) {
   }
 }
 
-TEST_F(PartitionedFilterBlockTest, TwoBlocksPerKey) {
+TEST_P(PartitionedFilterBlockTest, TwoBlocksPerKey) {
   uint64_t max_index_size = MaxIndexSize();
   for (uint64_t i = 1; i < max_index_size + 1; i++) {
     table_options_.metadata_block_size = i;
@@ -304,7 +313,7 @@ TEST_F(PartitionedFilterBlockTest, TwoBlocksPerKey) {
 
 // This reproduces the bug that a prefix is the same among multiple consecutive
 // blocks but the bug would add it only to the first block.
-TEST_F(PartitionedFilterBlockTest, SamePrefixInMultipleBlocks) {
+TEST_P(PartitionedFilterBlockTest, SamePrefixInMultipleBlocks) {
   // some small number to cause partition cuts
   table_options_.metadata_block_size = 1;
   std::unique_ptr<const SliceTransform> prefix_extractor
@@ -330,7 +339,7 @@ TEST_F(PartitionedFilterBlockTest, SamePrefixInMultipleBlocks) {
   }
 }
 
-TEST_F(PartitionedFilterBlockTest, OneBlockPerKey) {
+TEST_P(PartitionedFilterBlockTest, OneBlockPerKey) {
   uint64_t max_index_size = MaxIndexSize();
   for (uint64_t i = 1; i < max_index_size + 1; i++) {
     table_options_.metadata_block_size = i;
@@ -338,7 +347,7 @@ TEST_F(PartitionedFilterBlockTest, OneBlockPerKey) {
   }
 }
 
-TEST_F(PartitionedFilterBlockTest, PartitionCount) {
+TEST_P(PartitionedFilterBlockTest, PartitionCount) {
   int num_keys = sizeof(keys) / sizeof(*keys);
   table_options_.metadata_block_size =
       std::max(MaxIndexSize(), MaxFilterSize());
diff --git a/3rdParty/rocksdb/v5.16.X/table/persistent_cache_helper.cc b/3rdParty/rocksdb/v5.18.X/table/persistent_cache_helper.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/table/persistent_cache_helper.cc
rename to 3rdParty/rocksdb/v5.18.X/table/persistent_cache_helper.cc
index 103f57c80a..4e90697a6e 100644
--- a/3rdParty/rocksdb/v5.16.X/table/persistent_cache_helper.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/persistent_cache_helper.cc
@@ -29,12 +29,9 @@ void PersistentCacheHelper::InsertUncompressedPage(
     const BlockContents& contents) {
   assert(cache_options.persistent_cache);
   assert(!cache_options.persistent_cache->IsCompressed());
-  if (!contents.cachable || contents.compression_type != kNoCompression) {
-    // We shouldn't cache this. Either
-    // (1) content is not cacheable
-    // (2) content is compressed
-    return;
-  }
+  // Precondition:
+  // (1) content is cacheable
+  // (2) content is not compressed
 
   // construct the page key
   char cache_key[BlockBasedTable::kMaxCacheKeyPrefixSize + kMaxVarint64Length];
@@ -109,8 +106,7 @@ Status PersistentCacheHelper::LookupUncompressedPage(
   // update stats
   RecordTick(cache_options.statistics, PERSISTENT_CACHE_HIT);
   // construct result and return
-  *contents =
-      BlockContents(std::move(data), size, false /*cacheable*/, kNoCompression);
+  *contents = BlockContents(std::move(data), size);
   return Status::OK();
 }
 
diff --git a/3rdParty/rocksdb/v5.16.X/table/persistent_cache_helper.h b/3rdParty/rocksdb/v5.18.X/table/persistent_cache_helper.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/persistent_cache_helper.h
rename to 3rdParty/rocksdb/v5.18.X/table/persistent_cache_helper.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/persistent_cache_options.h b/3rdParty/rocksdb/v5.18.X/table/persistent_cache_options.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/persistent_cache_options.h
rename to 3rdParty/rocksdb/v5.18.X/table/persistent_cache_options.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/plain_table_builder.cc b/3rdParty/rocksdb/v5.18.X/table/plain_table_builder.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/table/plain_table_builder.cc
rename to 3rdParty/rocksdb/v5.18.X/table/plain_table_builder.cc
index 717635cc1a..453b6c768b 100644
--- a/3rdParty/rocksdb/v5.16.X/table/plain_table_builder.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/plain_table_builder.cc
@@ -166,6 +166,12 @@ void PlainTableBuilder::Add(const Slice& key, const Slice& value) {
   properties_.num_entries++;
   properties_.raw_key_size += key.size();
   properties_.raw_value_size += value.size();
+  if (internal_key.type == kTypeDeletion ||
+      internal_key.type == kTypeSingleDeletion) {
+    properties_.num_deletions++;
+  } else if (internal_key.type == kTypeMerge) {
+    properties_.num_merge_operands++;
+  }
 
   // notify property collectors
   NotifyCollectTableCollectorsOnAdd(
diff --git a/3rdParty/rocksdb/v5.16.X/table/plain_table_builder.h b/3rdParty/rocksdb/v5.18.X/table/plain_table_builder.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/plain_table_builder.h
rename to 3rdParty/rocksdb/v5.18.X/table/plain_table_builder.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/plain_table_factory.cc b/3rdParty/rocksdb/v5.18.X/table/plain_table_factory.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/table/plain_table_factory.cc
rename to 3rdParty/rocksdb/v5.18.X/table/plain_table_factory.cc
index b88a689d4b..273a1bd4f2 100644
--- a/3rdParty/rocksdb/v5.16.X/table/plain_table_factory.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/plain_table_factory.cc
@@ -19,8 +19,8 @@ namespace rocksdb {
 
 Status PlainTableFactory::NewTableReader(
     const TableReaderOptions& table_reader_options,
-    unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
-    unique_ptr<TableReader>* table,
+    std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+    std::unique_ptr<TableReader>* table,
     bool /*prefetch_index_and_filter_in_cache*/) const {
   return PlainTableReader::Open(
       table_reader_options.ioptions, table_reader_options.env_options,
diff --git a/3rdParty/rocksdb/v5.16.X/table/plain_table_factory.h b/3rdParty/rocksdb/v5.18.X/table/plain_table_factory.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/table/plain_table_factory.h
rename to 3rdParty/rocksdb/v5.18.X/table/plain_table_factory.h
index f540a92b89..157e3acda0 100644
--- a/3rdParty/rocksdb/v5.16.X/table/plain_table_factory.h
+++ b/3rdParty/rocksdb/v5.18.X/table/plain_table_factory.h
@@ -149,8 +149,8 @@ class PlainTableFactory : public TableFactory {
 
   const char* Name() const override { return "PlainTable"; }
   Status NewTableReader(const TableReaderOptions& table_reader_options,
-                        unique_ptr<RandomAccessFileReader>&& file,
-                        uint64_t file_size, unique_ptr<TableReader>* table,
+                        std::unique_ptr<RandomAccessFileReader>&& file,
+                        uint64_t file_size, std::unique_ptr<TableReader>* table,
                         bool prefetch_index_and_filter_in_cache) const override;
 
   TableBuilder* NewTableBuilder(
diff --git a/3rdParty/rocksdb/v5.16.X/table/plain_table_index.cc b/3rdParty/rocksdb/v5.18.X/table/plain_table_index.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/plain_table_index.cc
rename to 3rdParty/rocksdb/v5.18.X/table/plain_table_index.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/plain_table_index.h b/3rdParty/rocksdb/v5.18.X/table/plain_table_index.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/plain_table_index.h
rename to 3rdParty/rocksdb/v5.18.X/table/plain_table_index.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/plain_table_key_coding.cc b/3rdParty/rocksdb/v5.18.X/table/plain_table_key_coding.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/plain_table_key_coding.cc
rename to 3rdParty/rocksdb/v5.18.X/table/plain_table_key_coding.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/plain_table_key_coding.h b/3rdParty/rocksdb/v5.18.X/table/plain_table_key_coding.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/table/plain_table_key_coding.h
rename to 3rdParty/rocksdb/v5.18.X/table/plain_table_key_coding.h
index 321e0aed59..9a27ad06b7 100644
--- a/3rdParty/rocksdb/v5.16.X/table/plain_table_key_coding.h
+++ b/3rdParty/rocksdb/v5.18.X/table/plain_table_key_coding.h
@@ -114,7 +114,7 @@ class PlainTableFileReader {
   };
 
   // Keep buffers for two recent reads.
-  std::array<unique_ptr<Buffer>, 2> buffers_;
+  std::array<std::unique_ptr<Buffer>, 2> buffers_;
   uint32_t num_buf_;
   Status status_;
 
diff --git a/3rdParty/rocksdb/v5.16.X/table/plain_table_reader.cc b/3rdParty/rocksdb/v5.18.X/table/plain_table_reader.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/table/plain_table_reader.cc
rename to 3rdParty/rocksdb/v5.18.X/table/plain_table_reader.cc
index 1143eb1cd2..ae656763cb 100644
--- a/3rdParty/rocksdb/v5.16.X/table/plain_table_reader.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/plain_table_reader.cc
@@ -91,14 +91,13 @@ class PlainTableIterator : public InternalIterator {
 };
 
 extern const uint64_t kPlainTableMagicNumber;
-PlainTableReader::PlainTableReader(const ImmutableCFOptions& ioptions,
-                                   unique_ptr<RandomAccessFileReader>&& file,
-                                   const EnvOptions& storage_options,
-                                   const InternalKeyComparator& icomparator,
-                                   EncodingType encoding_type,
-                                   uint64_t file_size,
-                                   const TableProperties* table_properties,
-                                   const SliceTransform* prefix_extractor)
+PlainTableReader::PlainTableReader(
+    const ImmutableCFOptions& ioptions,
+    std::unique_ptr<RandomAccessFileReader>&& file,
+    const EnvOptions& storage_options, const InternalKeyComparator& icomparator,
+    EncodingType encoding_type, uint64_t file_size,
+    const TableProperties* table_properties,
+    const SliceTransform* prefix_extractor)
     : internal_comparator_(icomparator),
       encoding_type_(encoding_type),
       full_scan_mode_(false),
@@ -118,8 +117,8 @@ PlainTableReader::~PlainTableReader() {
 Status PlainTableReader::Open(
     const ImmutableCFOptions& ioptions, const EnvOptions& env_options,
     const InternalKeyComparator& internal_comparator,
-    unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
-    unique_ptr<TableReader>* table_reader, const int bloom_bits_per_key,
+    std::unique_ptr<RandomAccessFileReader>&& file, uint64_t file_size,
+    std::unique_ptr<TableReader>* table_reader, const int bloom_bits_per_key,
     double hash_table_ratio, size_t index_sparseness, size_t huge_page_tlb_size,
     bool full_scan_mode, const SliceTransform* prefix_extractor) {
   if (file_size > PlainTableIndex::kMaxFileSize) {
@@ -277,7 +276,7 @@ void PlainTableReader::FillBloom(vector<uint32_t>* prefix_hashes) {
 Status PlainTableReader::MmapDataIfNeeded() {
   if (file_info_.is_mmap_mode) {
     // Get mmapped memory.
-    return file_info_.file->Read(0, file_size_, &file_info_.file_data, nullptr);
+    return file_info_.file->Read(0, static_cast<size_t>(file_size_), &file_info_.file_data, nullptr);
   }
   return Status::OK();
 }
diff --git a/3rdParty/rocksdb/v5.16.X/table/plain_table_reader.h b/3rdParty/rocksdb/v5.18.X/table/plain_table_reader.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/table/plain_table_reader.h
rename to 3rdParty/rocksdb/v5.18.X/table/plain_table_reader.h
index df08a98fa1..5f8248dd71 100644
--- a/3rdParty/rocksdb/v5.16.X/table/plain_table_reader.h
+++ b/3rdParty/rocksdb/v5.18.X/table/plain_table_reader.h
@@ -48,7 +48,7 @@ struct PlainTableReaderFileInfo {
   bool is_mmap_mode;
   Slice file_data;
   uint32_t data_end_offset;
-  unique_ptr<RandomAccessFileReader> file;
+  std::unique_ptr<RandomAccessFileReader> file;
 
   PlainTableReaderFileInfo(unique_ptr<RandomAccessFileReader>&& _file,
                            const EnvOptions& storage_options,
@@ -71,8 +71,8 @@ class PlainTableReader: public TableReader {
   static Status Open(const ImmutableCFOptions& ioptions,
                      const EnvOptions& env_options,
                      const InternalKeyComparator& internal_comparator,
-                     unique_ptr<RandomAccessFileReader>&& file,
-                     uint64_t file_size, unique_ptr<TableReader>* table,
+                     std::unique_ptr<RandomAccessFileReader>&& file,
+                     uint64_t file_size, std::unique_ptr<TableReader>* table,
                      const int bloom_bits_per_key, double hash_table_ratio,
                      size_t index_sparseness, size_t huge_page_tlb_size,
                      bool full_scan_mode,
@@ -104,7 +104,7 @@ class PlainTableReader: public TableReader {
   }
 
   PlainTableReader(const ImmutableCFOptions& ioptions,
-                   unique_ptr<RandomAccessFileReader>&& file,
+                   std::unique_ptr<RandomAccessFileReader>&& file,
                    const EnvOptions& env_options,
                    const InternalKeyComparator& internal_comparator,
                    EncodingType encoding_type, uint64_t file_size,
@@ -153,8 +153,8 @@ class PlainTableReader: public TableReader {
   DynamicBloom bloom_;
   PlainTableReaderFileInfo file_info_;
   Arena arena_;
-  std::unique_ptr<char[]> index_block_alloc_;
-  std::unique_ptr<char[]> bloom_block_alloc_;
+  CacheAllocationPtr index_block_alloc_;
+  CacheAllocationPtr bloom_block_alloc_;
 
   const ImmutableCFOptions& ioptions_;
   uint64_t file_size_;
diff --git a/3rdParty/rocksdb/v5.16.X/table/scoped_arena_iterator.h b/3rdParty/rocksdb/v5.18.X/table/scoped_arena_iterator.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/scoped_arena_iterator.h
rename to 3rdParty/rocksdb/v5.18.X/table/scoped_arena_iterator.h
diff --git a/3rdParty/rocksdb/v5.18.X/table/sst_file_reader.cc b/3rdParty/rocksdb/v5.18.X/table/sst_file_reader.cc
new file mode 100644
index 0000000000..a915449bee
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/table/sst_file_reader.cc
@@ -0,0 +1,84 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#ifndef ROCKSDB_LITE
+
+#include "rocksdb/sst_file_reader.h"
+
+#include "db/db_iter.h"
+#include "options/cf_options.h"
+#include "table/get_context.h"
+#include "table/table_reader.h"
+#include "table/table_builder.h"
+#include "util/file_reader_writer.h"
+
+namespace rocksdb {
+
+struct SstFileReader::Rep {
+  Options options;
+  EnvOptions soptions;
+  ImmutableCFOptions ioptions;
+  MutableCFOptions moptions;
+
+  std::unique_ptr<TableReader> table_reader;
+
+  Rep(const Options& opts)
+      : options(opts),
+        soptions(options),
+        ioptions(options),
+        moptions(ColumnFamilyOptions(options)) {}
+};
+
+SstFileReader::SstFileReader(const Options& options)
+    : rep_(new Rep(options)) {}
+
+SstFileReader::~SstFileReader() {}
+
+Status SstFileReader::Open(const std::string& file_path) {
+  auto r = rep_.get();
+  Status s;
+  uint64_t file_size = 0;
+  std::unique_ptr<RandomAccessFile> file;
+  std::unique_ptr<RandomAccessFileReader> file_reader;
+  s = r->options.env->GetFileSize(file_path, &file_size);
+  if (s.ok()) {
+    s = r->options.env->NewRandomAccessFile(file_path, &file, r->soptions);
+  }
+  if (s.ok()) {
+    file_reader.reset(new RandomAccessFileReader(std::move(file), file_path));
+  }
+  if (s.ok()) {
+    s = r->options.table_factory->NewTableReader(
+        TableReaderOptions(r->ioptions, r->moptions.prefix_extractor.get(),
+                           r->soptions, r->ioptions.internal_comparator),
+        std::move(file_reader), file_size, &r->table_reader);
+  }
+  return s;
+}
+
+Iterator* SstFileReader::NewIterator(const ReadOptions& options) {
+  auto r = rep_.get();
+  auto sequence = options.snapshot != nullptr ?
+                  options.snapshot->GetSequenceNumber() :
+                  kMaxSequenceNumber;
+  auto internal_iter = r->table_reader->NewIterator(
+      options, r->moptions.prefix_extractor.get());
+  return NewDBIterator(r->options.env, options, r->ioptions, r->moptions,
+                       r->ioptions.user_comparator, internal_iter, sequence,
+                       r->moptions.max_sequential_skip_in_iterations,
+                       nullptr /* read_callback */);
+}
+
+std::shared_ptr<const TableProperties> SstFileReader::GetTableProperties() const {
+  return rep_->table_reader->GetTableProperties();
+}
+
+Status SstFileReader::VerifyChecksum() {
+  return rep_->table_reader->VerifyChecksum();
+}
+
+}  // namespace rocksdb
+
+#endif  // !ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.18.X/table/sst_file_reader_test.cc b/3rdParty/rocksdb/v5.18.X/table/sst_file_reader_test.cc
new file mode 100644
index 0000000000..8da366fd7c
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/table/sst_file_reader_test.cc
@@ -0,0 +1,106 @@
+// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#ifndef ROCKSDB_LITE
+
+#include <inttypes.h>
+
+#include "rocksdb/sst_file_reader.h"
+#include "rocksdb/sst_file_writer.h"
+#include "util/testharness.h"
+#include "util/testutil.h"
+#include "utilities/merge_operators.h"
+
+namespace rocksdb {
+
+std::string EncodeAsString(uint64_t v) {
+  char buf[16];
+  snprintf(buf, sizeof(buf), "%08" PRIu64, v);
+  return std::string(buf);
+}
+
+std::string EncodeAsUint64(uint64_t v) {
+  std::string dst;
+  PutFixed64(&dst, v);
+  return dst;
+}
+
+class SstFileReaderTest : public testing::Test {
+ public:
+  SstFileReaderTest() {
+    options_.merge_operator = MergeOperators::CreateUInt64AddOperator();
+    sst_name_ = test::PerThreadDBPath("sst_file");
+  }
+
+  void CreateFileAndCheck(const std::vector<std::string>& keys) {
+    SstFileWriter writer(soptions_, options_);
+    ASSERT_OK(writer.Open(sst_name_));
+    for (size_t i = 0; i + 2 < keys.size(); i += 3) {
+      ASSERT_OK(writer.Put(keys[i], keys[i]));
+      ASSERT_OK(writer.Merge(keys[i+1], EncodeAsUint64(i+1)));
+      ASSERT_OK(writer.Delete(keys[i+2]));
+    }
+    ASSERT_OK(writer.Finish());
+
+    ReadOptions ropts;
+    SstFileReader reader(options_);
+    ASSERT_OK(reader.Open(sst_name_));
+    ASSERT_OK(reader.VerifyChecksum());
+    std::unique_ptr<Iterator> iter(reader.NewIterator(ropts));
+    iter->SeekToFirst();
+    for (size_t i = 0; i + 2 < keys.size(); i += 3) {
+      ASSERT_TRUE(iter->Valid());
+      ASSERT_EQ(iter->key().compare(keys[i]), 0);
+      ASSERT_EQ(iter->value().compare(keys[i]), 0);
+      iter->Next();
+      ASSERT_TRUE(iter->Valid());
+      ASSERT_EQ(iter->key().compare(keys[i+1]), 0);
+      ASSERT_EQ(iter->value().compare(EncodeAsUint64(i+1)), 0);
+      iter->Next();
+    }
+    ASSERT_FALSE(iter->Valid());
+  }
+
+ protected:
+  Options options_;
+  EnvOptions soptions_;
+  std::string sst_name_;
+};
+
+const uint64_t kNumKeys = 100;
+
+TEST_F(SstFileReaderTest, Basic) {
+  std::vector<std::string> keys;
+  for (uint64_t i = 0; i < kNumKeys; i++) {
+    keys.emplace_back(EncodeAsString(i));
+  }
+  CreateFileAndCheck(keys);
+}
+
+TEST_F(SstFileReaderTest, Uint64Comparator) {
+  options_.comparator = test::Uint64Comparator();
+  std::vector<std::string> keys;
+  for (uint64_t i = 0; i < kNumKeys; i++) {
+    keys.emplace_back(EncodeAsUint64(i));
+  }
+  CreateFileAndCheck(keys);
+}
+
+}  // namespace rocksdb
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+  return RUN_ALL_TESTS();
+}
+
+#else
+#include <stdio.h>
+
+int main(int /*argc*/, char** /*argv*/) {
+  fprintf(stderr, "SKIPPED as SstFileReader is not supported in ROCKSDB_LITE\n");
+  return 0;
+}
+
+#endif  // ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.16.X/table/sst_file_writer.cc b/3rdParty/rocksdb/v5.18.X/table/sst_file_writer.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/table/sst_file_writer.cc
rename to 3rdParty/rocksdb/v5.18.X/table/sst_file_writer.cc
index ae189daa59..a752504c8f 100644
--- a/3rdParty/rocksdb/v5.16.X/table/sst_file_writer.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/sst_file_writer.cc
@@ -238,7 +238,8 @@ Status SstFileWriter::Open(const std::string& file_path) {
       nullptr /* compression_dict */, r->skip_filters, r->column_family_name,
       unknown_level);
   r->file_writer.reset(
-      new WritableFileWriter(std::move(sst_file), r->env_options));
+      new WritableFileWriter(std::move(sst_file), file_path, r->env_options,
+                             nullptr /* stats */, r->ioptions.listeners));
 
   // TODO(tec) : If table_factory is using compressed block cache, we will
   // be adding the external sst file blocks into it, which is wasteful.
diff --git a/3rdParty/rocksdb/v5.16.X/table/sst_file_writer_collectors.h b/3rdParty/rocksdb/v5.18.X/table/sst_file_writer_collectors.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/sst_file_writer_collectors.h
rename to 3rdParty/rocksdb/v5.18.X/table/sst_file_writer_collectors.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/table_builder.h b/3rdParty/rocksdb/v5.18.X/table/table_builder.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/table_builder.h
rename to 3rdParty/rocksdb/v5.18.X/table/table_builder.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/table_properties.cc b/3rdParty/rocksdb/v5.18.X/table/table_properties.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/table/table_properties.cc
rename to 3rdParty/rocksdb/v5.18.X/table/table_properties.cc
index 207a641911..56e1d03f1f 100644
--- a/3rdParty/rocksdb/v5.16.X/table/table_properties.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/table_properties.cc
@@ -78,6 +78,9 @@ std::string TableProperties::ToString(
   AppendProperty(result, "# data blocks", num_data_blocks, prop_delim,
                  kv_delim);
   AppendProperty(result, "# entries", num_entries, prop_delim, kv_delim);
+  AppendProperty(result, "# deletions", num_deletions, prop_delim, kv_delim);
+  AppendProperty(result, "# merge operands", num_merge_operands, prop_delim,
+                 kv_delim);
   AppendProperty(result, "# range deletions", num_range_deletions, prop_delim,
                  kv_delim);
 
@@ -170,6 +173,8 @@ void TableProperties::Add(const TableProperties& tp) {
   raw_value_size += tp.raw_value_size;
   num_data_blocks += tp.num_data_blocks;
   num_entries += tp.num_entries;
+  num_deletions += tp.num_deletions;
+  num_merge_operands += tp.num_merge_operands;
   num_range_deletions += tp.num_range_deletions;
 }
 
@@ -195,6 +200,9 @@ const std::string TablePropertiesNames::kNumDataBlocks =
     "rocksdb.num.data.blocks";
 const std::string TablePropertiesNames::kNumEntries =
     "rocksdb.num.entries";
+const std::string TablePropertiesNames::kDeletedKeys = "rocksdb.deleted.keys";
+const std::string TablePropertiesNames::kMergeOperands =
+    "rocksdb.merge.operands";
 const std::string TablePropertiesNames::kNumRangeDeletions =
     "rocksdb.num.range-deletions";
 const std::string TablePropertiesNames::kFilterPolicy =
diff --git a/3rdParty/rocksdb/v5.16.X/table/table_properties_internal.h b/3rdParty/rocksdb/v5.18.X/table/table_properties_internal.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/table_properties_internal.h
rename to 3rdParty/rocksdb/v5.18.X/table/table_properties_internal.h
diff --git a/3rdParty/rocksdb/v5.16.X/table/table_reader.h b/3rdParty/rocksdb/v5.18.X/table/table_reader.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/table/table_reader.h
rename to 3rdParty/rocksdb/v5.18.X/table/table_reader.h
index 505b5ba1fb..a5f15e1304 100644
--- a/3rdParty/rocksdb/v5.16.X/table/table_reader.h
+++ b/3rdParty/rocksdb/v5.18.X/table/table_reader.h
@@ -9,6 +9,7 @@
 
 #pragma once
 #include <memory>
+#include "db/range_tombstone_fragmenter.h"
 #include "rocksdb/slice_transform.h"
 #include "table/internal_iterator.h"
 
@@ -44,7 +45,7 @@ class TableReader {
                                         bool skip_filters = false,
                                         bool for_compaction = false) = 0;
 
-  virtual InternalIterator* NewRangeTombstoneIterator(
+  virtual FragmentedRangeTombstoneIterator* NewRangeTombstoneIterator(
       const ReadOptions& /*read_options*/) {
     return nullptr;
   }
diff --git a/3rdParty/rocksdb/v5.16.X/table/table_reader_bench.cc b/3rdParty/rocksdb/v5.18.X/table/table_reader_bench.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/table/table_reader_bench.cc
rename to 3rdParty/rocksdb/v5.18.X/table/table_reader_bench.cc
index b05e3e0526..fbcfac826c 100644
--- a/3rdParty/rocksdb/v5.16.X/table/table_reader_bench.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/table_reader_bench.cc
@@ -86,15 +86,16 @@ void TableReaderBenchmark(Options& opts, EnvOptions& env_options,
   const ImmutableCFOptions ioptions(opts);
   const ColumnFamilyOptions cfo(opts);
   const MutableCFOptions moptions(cfo);
-  unique_ptr<WritableFileWriter> file_writer;
+  std::unique_ptr<WritableFileWriter> file_writer;
   if (!through_db) {
-    unique_ptr<WritableFile> file;
+    std::unique_ptr<WritableFile> file;
     env->NewWritableFile(file_name, &file, env_options);
 
     std::vector<std::unique_ptr<IntTblPropCollectorFactory> >
         int_tbl_prop_collector_factories;
 
-    file_writer.reset(new WritableFileWriter(std::move(file), env_options));
+    file_writer.reset(
+        new WritableFileWriter(std::move(file), file_name, env_options));
     int unknown_level = -1;
     tb = opts.table_factory->NewTableBuilder(
         TableBuilderOptions(
@@ -126,9 +127,9 @@ void TableReaderBenchmark(Options& opts, EnvOptions& env_options,
     db->Flush(FlushOptions());
   }
 
-  unique_ptr<TableReader> table_reader;
+  std::unique_ptr<TableReader> table_reader;
   if (!through_db) {
-    unique_ptr<RandomAccessFile> raf;
+    std::unique_ptr<RandomAccessFile> raf;
     s = env->NewRandomAccessFile(file_name, &raf, env_options);
     if (!s.ok()) {
       fprintf(stderr, "Create File Error: %s\n", s.ToString().c_str());
@@ -136,7 +137,7 @@ void TableReaderBenchmark(Options& opts, EnvOptions& env_options,
     }
     uint64_t file_size;
     env->GetFileSize(file_name, &file_size);
-    unique_ptr<RandomAccessFileReader> file_reader(
+    std::unique_ptr<RandomAccessFileReader> file_reader(
         new RandomAccessFileReader(std::move(raf), file_name));
     s = opts.table_factory->NewTableReader(
         TableReaderOptions(ioptions, moptions.prefix_extractor.get(),
@@ -169,12 +170,12 @@ void TableReaderBenchmark(Options& opts, EnvOptions& env_options,
           if (!through_db) {
             PinnableSlice value;
             MergeContext merge_context;
-            RangeDelAggregator range_del_agg(ikc, {} /* snapshots */);
+            SequenceNumber max_covering_tombstone_seq = 0;
             GetContext get_context(ioptions.user_comparator,
                                    ioptions.merge_operator, ioptions.info_log,
                                    ioptions.statistics, GetContext::kNotFound,
                                    Slice(key), &value, nullptr, &merge_context,
-                                   &range_del_agg, env);
+                                   &max_covering_tombstone_seq, env);
             s = table_reader->Get(read_options, key, &get_context, nullptr);
           } else {
             s = db->Get(read_options, key, &result);
diff --git a/3rdParty/rocksdb/v5.16.X/table/table_test.cc b/3rdParty/rocksdb/v5.18.X/table/table_test.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/table/table_test.cc
rename to 3rdParty/rocksdb/v5.18.X/table/table_test.cc
index af648bc053..5ec613bec4 100644
--- a/3rdParty/rocksdb/v5.16.X/table/table_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/table/table_test.cc
@@ -232,7 +232,6 @@ class BlockConstructor: public Constructor {
     data_ = builder.Finish().ToString();
     BlockContents contents;
     contents.data = data_;
-    contents.cachable = false;
     block_ = new Block(std::move(contents), kDisableGlobalSequenceNumber);
     return Status::OK();
   }
@@ -323,8 +322,9 @@ class TableConstructor: public Constructor {
                             const stl_wrappers::KVMap& kv_map) override {
     Reset();
     soptions.use_mmap_reads = ioptions.allow_mmap_reads;
-    file_writer_.reset(test::GetWritableFileWriter(new test::StringSink()));
-    unique_ptr<TableBuilder> builder;
+    file_writer_.reset(test::GetWritableFileWriter(new test::StringSink(),
+                                                   "" /* don't care */));
+    std::unique_ptr<TableBuilder> builder;
     std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
         int_tbl_prop_collector_factories;
     std::string column_family_name;
@@ -422,9 +422,9 @@ class TableConstructor: public Constructor {
   }
 
   uint64_t uniq_id_;
-  unique_ptr<WritableFileWriter> file_writer_;
-  unique_ptr<RandomAccessFileReader> file_reader_;
-  unique_ptr<TableReader> table_reader_;
+  std::unique_ptr<WritableFileWriter> file_writer_;
+  std::unique_ptr<RandomAccessFileReader> file_reader_;
+  std::unique_ptr<TableReader> table_reader_;
   bool convert_to_internal_key_;
   int level_;
 
@@ -507,7 +507,7 @@ class InternalIteratorFromIterator : public InternalIterator {
   virtual Status status() const override { return it_->status(); }
 
  private:
-  unique_ptr<Iterator> it_;
+  std::unique_ptr<Iterator> it_;
 };
 
 class DBConstructor: public Constructor {
@@ -1023,7 +1023,7 @@ class HarnessTest : public testing::Test {
   WriteBufferManager write_buffer_;
   bool support_prev_;
   bool only_support_prefix_seek_;
-  shared_ptr<InternalKeyComparator> internal_comparator_;
+  std::shared_ptr<InternalKeyComparator> internal_comparator_;
 };
 
 static bool Between(uint64_t val, uint64_t low, uint64_t high) {
@@ -1277,6 +1277,13 @@ TEST_P(BlockBasedTableTest, RangeDelBlock) {
   std::vector<std::string> keys = {"1pika", "2chu"};
   std::vector<std::string> vals = {"p", "c"};
 
+  std::vector<RangeTombstone> expected_tombstones = {
+      {"1pika", "2chu", 0},
+      {"2chu", "c", 1},
+      {"2chu", "c", 0},
+      {"c", "p", 0},
+  };
+
   for (int i = 0; i < 2; i++) {
     RangeTombstone t(keys[i], vals[i], i);
     std::pair<InternalKey, Slice> p = t.Serialize();
@@ -1309,14 +1316,15 @@ TEST_P(BlockBasedTableTest, RangeDelBlock) {
     ASSERT_FALSE(iter->Valid());
     iter->SeekToFirst();
     ASSERT_TRUE(iter->Valid());
-    for (int i = 0; i < 2; i++) {
+    for (size_t i = 0; i < expected_tombstones.size(); i++) {
       ASSERT_TRUE(iter->Valid());
       ParsedInternalKey parsed_key;
       ASSERT_TRUE(ParseInternalKey(iter->key(), &parsed_key));
       RangeTombstone t(parsed_key, iter->value());
-      ASSERT_EQ(t.start_key_, keys[i]);
-      ASSERT_EQ(t.end_key_, vals[i]);
-      ASSERT_EQ(t.seq_, i);
+      const auto& expected_t = expected_tombstones[i];
+      ASSERT_EQ(t.start_key_, expected_t.start_key_);
+      ASSERT_EQ(t.end_key_, expected_t.end_key_);
+      ASSERT_EQ(t.seq_, expected_t.seq_);
       iter->Next();
     }
     ASSERT_TRUE(!iter->Valid());
@@ -1384,8 +1392,8 @@ void PrefetchRange(TableConstructor* c, Options* opt,
   // prefetch
   auto* table_reader = dynamic_cast<BlockBasedTable*>(c->GetTableReader());
   Status s;
-  unique_ptr<Slice> begin, end;
-  unique_ptr<InternalKey> i_begin, i_end;
+  std::unique_ptr<Slice> begin, end;
+  std::unique_ptr<InternalKey> i_begin, i_end;
   if (key_begin != nullptr) {
     if (c->ConvertToInternalKey()) {
       i_begin.reset(new InternalKey(key_begin, kMaxSequenceNumber, kTypeValue));
@@ -1416,7 +1424,7 @@ TEST_P(BlockBasedTableTest, PrefetchTest) {
   // The purpose of this test is to test the prefetching operation built into
   // BlockBasedTable.
   Options opt;
-  unique_ptr<InternalKeyComparator> ikc;
+  std::unique_ptr<InternalKeyComparator> ikc;
   ikc.reset(new test::PlainInternalKeyComparator(opt.comparator));
   opt.compression = kNoCompression;
   BlockBasedTableOptions table_options = GetBlockBasedTableOptions();
@@ -2008,7 +2016,7 @@ TEST_P(BlockBasedTableTest, FilterBlockInBlockCache) {
 
   // -- PART 1: Open with regular block cache.
   // Since block_cache is disabled, no cache activities will be involved.
-  unique_ptr<InternalIterator> iter;
+  std::unique_ptr<InternalIterator> iter;
 
   int64_t last_cache_bytes_read = 0;
   // At first, no block will be accessed.
@@ -2342,7 +2350,7 @@ TEST_P(BlockBasedTableTest, NoObjectInCacheAfterTableClose) {
               }
               // Create a table
               Options opt;
-              unique_ptr<InternalKeyComparator> ikc;
+              std::unique_ptr<InternalKeyComparator> ikc;
               ikc.reset(new test::PlainInternalKeyComparator(opt.comparator));
               opt.compression = kNoCompression;
               BlockBasedTableOptions table_options =
@@ -2418,7 +2426,7 @@ TEST_P(BlockBasedTableTest, BlockCacheLeak) {
   // unique ID from the file.
 
   Options opt;
-  unique_ptr<InternalKeyComparator> ikc;
+  std::unique_ptr<InternalKeyComparator> ikc;
   ikc.reset(new test::PlainInternalKeyComparator(opt.comparator));
   opt.compression = kNoCompression;
   BlockBasedTableOptions table_options = GetBlockBasedTableOptions();
@@ -2441,7 +2449,7 @@ TEST_P(BlockBasedTableTest, BlockCacheLeak) {
   const MutableCFOptions moptions(opt);
   c.Finish(opt, ioptions, moptions, table_options, *ikc, &keys, &kvmap);
 
-  unique_ptr<InternalIterator> iter(
+  std::unique_ptr<InternalIterator> iter(
       c.NewIterator(moptions.prefix_extractor.get()));
   iter->SeekToFirst();
   while (iter->Valid()) {
@@ -2476,6 +2484,78 @@ TEST_P(BlockBasedTableTest, BlockCacheLeak) {
   c.ResetTableReader();
 }
 
+namespace {
+class CustomMemoryAllocator : public MemoryAllocator {
+ public:
+  virtual const char* Name() const override { return "CustomMemoryAllocator"; }
+
+  void* Allocate(size_t size) override {
+    ++numAllocations;
+    auto ptr = new char[size + 16];
+    memcpy(ptr, "memory_allocator_", 16);  // mangle first 16 bytes
+    return reinterpret_cast<void*>(ptr + 16);
+  }
+  void Deallocate(void* p) override {
+    ++numDeallocations;
+    char* ptr = reinterpret_cast<char*>(p) - 16;
+    delete[] ptr;
+  }
+
+  std::atomic<int> numAllocations;
+  std::atomic<int> numDeallocations;
+};
+}  // namespace
+
+TEST_P(BlockBasedTableTest, MemoryAllocator) {
+  auto custom_memory_allocator = std::make_shared<CustomMemoryAllocator>();
+  {
+    Options opt;
+    std::unique_ptr<InternalKeyComparator> ikc;
+    ikc.reset(new test::PlainInternalKeyComparator(opt.comparator));
+    opt.compression = kNoCompression;
+    BlockBasedTableOptions table_options;
+    table_options.block_size = 1024;
+    LRUCacheOptions lruOptions;
+    lruOptions.memory_allocator = custom_memory_allocator;
+    lruOptions.capacity = 16 * 1024 * 1024;
+    lruOptions.num_shard_bits = 4;
+    table_options.block_cache = NewLRUCache(std::move(lruOptions));
+    opt.table_factory.reset(NewBlockBasedTableFactory(table_options));
+
+    TableConstructor c(BytewiseComparator(),
+                       true /* convert_to_internal_key_ */);
+    c.Add("k01", "hello");
+    c.Add("k02", "hello2");
+    c.Add("k03", std::string(10000, 'x'));
+    c.Add("k04", std::string(200000, 'x'));
+    c.Add("k05", std::string(300000, 'x'));
+    c.Add("k06", "hello3");
+    c.Add("k07", std::string(100000, 'x'));
+    std::vector<std::string> keys;
+    stl_wrappers::KVMap kvmap;
+    const ImmutableCFOptions ioptions(opt);
+    const MutableCFOptions moptions(opt);
+    c.Finish(opt, ioptions, moptions, table_options, *ikc, &keys, &kvmap);
+
+    std::unique_ptr<InternalIterator> iter(
+        c.NewIterator(moptions.prefix_extractor.get()));
+    iter->SeekToFirst();
+    while (iter->Valid()) {
+      iter->key();
+      iter->value();
+      iter->Next();
+    }
+    ASSERT_OK(iter->status());
+  }
+
+  // out of scope, block cache should have been deleted, all allocations
+  // deallocated
+  EXPECT_EQ(custom_memory_allocator->numAllocations.load(),
+            custom_memory_allocator->numDeallocations.load());
+  // make sure that allocations actually happened through the cache allocator
+  EXPECT_GT(custom_memory_allocator->numAllocations.load(), 0);
+}
+
 TEST_P(BlockBasedTableTest, NewIndexIteratorLeak) {
   // A regression test to avoid data race described in
   // https://github.com/facebook/rocksdb/issues/1267
@@ -2549,8 +2629,8 @@ TEST_F(PlainTableTest, BasicPlainTableProperties) {
 
   PlainTableFactory factory(plain_table_options);
   test::StringSink sink;
-  unique_ptr<WritableFileWriter> file_writer(
-      test::GetWritableFileWriter(new test::StringSink()));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      test::GetWritableFileWriter(new test::StringSink(), "" /* don't care */));
   Options options;
   const ImmutableCFOptions ioptions(options);
   const MutableCFOptions moptions(options);
@@ -2578,7 +2658,7 @@ TEST_F(PlainTableTest, BasicPlainTableProperties) {
 
   test::StringSink* ss =
     static_cast<test::StringSink*>(file_writer->writable_file());
-  unique_ptr<RandomAccessFileReader> file_reader(
+  std::unique_ptr<RandomAccessFileReader> file_reader(
       test::GetRandomAccessFileReader(
           new test::StringSource(ss->contents(), 72242, true)));
 
@@ -2657,9 +2737,9 @@ static void DoCompressionTest(CompressionType comp) {
   ASSERT_TRUE(Between(c.ApproximateOffsetOf("abc"),       0,      0));
   ASSERT_TRUE(Between(c.ApproximateOffsetOf("k01"),       0,      0));
   ASSERT_TRUE(Between(c.ApproximateOffsetOf("k02"),       0,      0));
-  ASSERT_TRUE(Between(c.ApproximateOffsetOf("k03"),    2000,   3000));
-  ASSERT_TRUE(Between(c.ApproximateOffsetOf("k04"),    2000,   3000));
-  ASSERT_TRUE(Between(c.ApproximateOffsetOf("xyz"),    4000,   6100));
+  ASSERT_TRUE(Between(c.ApproximateOffsetOf("k03"),    2000,   3500));
+  ASSERT_TRUE(Between(c.ApproximateOffsetOf("k04"),    2000,   3500));
+  ASSERT_TRUE(Between(c.ApproximateOffsetOf("xyz"),    4000,   6500));
   c.ResetTableReader();
 }
 
@@ -2705,6 +2785,7 @@ TEST_F(GeneralTableTest, ApproximateOffsetOfCompressed) {
   }
 }
 
+#ifndef ROCKSDB_VALGRIND_RUN
 // RandomizedHarnessTest is very slow for certain combination of arguments
 // Split into 8 pieces to reduce the time individual tests take.
 TEST_F(HarnessTest, Randomized1) {
@@ -2788,6 +2869,7 @@ TEST_F(HarnessTest, RandomizedLongDB) {
   ASSERT_GT(files, 0);
 }
 #endif  // ROCKSDB_LITE
+#endif  // ROCKSDB_VALGRIND_RUN
 
 class MemTableTest : public testing::Test {};
 
@@ -2823,7 +2905,8 @@ TEST_F(MemTableTest, Simple) {
       iter = memtable->NewIterator(ReadOptions(), &arena);
       arena_iter_guard.set(iter);
     } else {
-      iter = memtable->NewRangeTombstoneIterator(ReadOptions());
+      iter = memtable->NewRangeTombstoneIterator(
+          ReadOptions(), kMaxSequenceNumber /* read_seq */);
       iter_guard.reset(iter);
     }
     if (iter == nullptr) {
@@ -2923,6 +3006,26 @@ TEST_F(HarnessTest, FooterTests) {
     ASSERT_EQ(decoded_footer.index_handle().size(), index.size());
     ASSERT_EQ(decoded_footer.version(), 1U);
   }
+  {
+    // xxhash64 block based
+    std::string encoded;
+    Footer footer(kBlockBasedTableMagicNumber, 1);
+    BlockHandle meta_index(10, 5), index(20, 15);
+    footer.set_metaindex_handle(meta_index);
+    footer.set_index_handle(index);
+    footer.set_checksum(kxxHash64);
+    footer.EncodeTo(&encoded);
+    Footer decoded_footer;
+    Slice encoded_slice(encoded);
+    decoded_footer.DecodeFrom(&encoded_slice);
+    ASSERT_EQ(decoded_footer.table_magic_number(), kBlockBasedTableMagicNumber);
+    ASSERT_EQ(decoded_footer.checksum(), kxxHash64);
+    ASSERT_EQ(decoded_footer.metaindex_handle().offset(), meta_index.offset());
+    ASSERT_EQ(decoded_footer.metaindex_handle().size(), meta_index.size());
+    ASSERT_EQ(decoded_footer.index_handle().offset(), index.offset());
+    ASSERT_EQ(decoded_footer.index_handle().size(), index.size());
+    ASSERT_EQ(decoded_footer.version(), 1U);
+  }
 // Plain table is not supported in ROCKSDB_LITE
 #ifndef ROCKSDB_LITE
   {
@@ -3150,7 +3253,8 @@ TEST_F(PrefixTest, PrefixAndWholeKeyTest) {
 TEST_P(BlockBasedTableTest, DISABLED_TableWithGlobalSeqno) {
   BlockBasedTableOptions bbto = GetBlockBasedTableOptions();
   test::StringSink* sink = new test::StringSink();
-  unique_ptr<WritableFileWriter> file_writer(test::GetWritableFileWriter(sink));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      test::GetWritableFileWriter(sink, "" /* don't care */));
   Options options;
   options.table_factory.reset(NewBlockBasedTableFactory(bbto));
   const ImmutableCFOptions ioptions(options);
@@ -3187,7 +3291,7 @@ TEST_P(BlockBasedTableTest, DISABLED_TableWithGlobalSeqno) {
 
   // Helper function to get version, global_seqno, global_seqno_offset
   std::function<void()> GetVersionAndGlobalSeqno = [&]() {
-    unique_ptr<RandomAccessFileReader> file_reader(
+    std::unique_ptr<RandomAccessFileReader> file_reader(
         test::GetRandomAccessFileReader(
             new test::StringSource(ss_rw.contents(), 73342, true)));
 
@@ -3216,9 +3320,9 @@ TEST_P(BlockBasedTableTest, DISABLED_TableWithGlobalSeqno) {
   };
 
   // Helper function to get the contents of the table InternalIterator
-  unique_ptr<TableReader> table_reader;
+  std::unique_ptr<TableReader> table_reader;
   std::function<InternalIterator*()> GetTableInternalIter = [&]() {
-    unique_ptr<RandomAccessFileReader> file_reader(
+    std::unique_ptr<RandomAccessFileReader> file_reader(
         test::GetRandomAccessFileReader(
             new test::StringSource(ss_rw.contents(), 73342, true)));
 
@@ -3331,7 +3435,8 @@ TEST_P(BlockBasedTableTest, BlockAlignTest) {
   BlockBasedTableOptions bbto = GetBlockBasedTableOptions();
   bbto.block_align = true;
   test::StringSink* sink = new test::StringSink();
-  unique_ptr<WritableFileWriter> file_writer(test::GetWritableFileWriter(sink));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      test::GetWritableFileWriter(sink, "" /* don't care */));
   Options options;
   options.compression = kNoCompression;
   options.table_factory.reset(NewBlockBasedTableFactory(bbto));
@@ -3362,7 +3467,7 @@ TEST_P(BlockBasedTableTest, BlockAlignTest) {
   file_writer->Flush();
 
   test::RandomRWStringSink ss_rw(sink);
-  unique_ptr<RandomAccessFileReader> file_reader(
+  std::unique_ptr<RandomAccessFileReader> file_reader(
       test::GetRandomAccessFileReader(
           new test::StringSource(ss_rw.contents(), 73342, true)));
 
@@ -3420,7 +3525,8 @@ TEST_P(BlockBasedTableTest, PropertiesBlockRestartPointTest) {
   BlockBasedTableOptions bbto = GetBlockBasedTableOptions();
   bbto.block_align = true;
   test::StringSink* sink = new test::StringSink();
-  unique_ptr<WritableFileWriter> file_writer(test::GetWritableFileWriter(sink));
+  std::unique_ptr<WritableFileWriter> file_writer(
+      test::GetWritableFileWriter(sink, "" /* don't care */));
 
   Options options;
   options.compression = kNoCompression;
@@ -3454,7 +3560,7 @@ TEST_P(BlockBasedTableTest, PropertiesBlockRestartPointTest) {
   file_writer->Flush();
 
   test::RandomRWStringSink ss_rw(sink);
-  unique_ptr<RandomAccessFileReader> file_reader(
+  std::unique_ptr<RandomAccessFileReader> file_reader(
       test::GetRandomAccessFileReader(
           new test::StringSource(ss_rw.contents(), 73342, true)));
 
@@ -3473,10 +3579,10 @@ TEST_P(BlockBasedTableTest, PropertiesBlockRestartPointTest) {
       Slice compression_dict;
       PersistentCacheOptions cache_options;
 
-      BlockFetcher block_fetcher(file, nullptr /* prefetch_buffer */, footer,
-                                 read_options, handle, contents, ioptions,
-                                 false /* decompress */, compression_dict,
-                                 cache_options);
+      BlockFetcher block_fetcher(
+          file, nullptr /* prefetch_buffer */, footer, read_options, handle,
+          contents, ioptions, false /* decompress */,
+          false /*maybe_compressed*/, compression_dict, cache_options);
 
       ASSERT_OK(block_fetcher.ReadBlockContents());
     };
@@ -3562,7 +3668,8 @@ TEST_P(BlockBasedTableTest, PropertiesMetaBlockLast) {
   BlockFetcher block_fetcher(
       table_reader.get(), nullptr /* prefetch_buffer */, footer, ReadOptions(),
       metaindex_handle, &metaindex_contents, ioptions, false /* decompress */,
-      compression_dict, pcache_opts);
+      false /*maybe_compressed*/, compression_dict, pcache_opts,
+      nullptr /*memory_allocator*/);
   ASSERT_OK(block_fetcher.ReadBlockContents());
   Block metaindex_block(std::move(metaindex_contents),
                         kDisableGlobalSequenceNumber);
diff --git a/3rdParty/rocksdb/v5.16.X/table/two_level_iterator.cc b/3rdParty/rocksdb/v5.18.X/table/two_level_iterator.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/two_level_iterator.cc
rename to 3rdParty/rocksdb/v5.18.X/table/two_level_iterator.cc
diff --git a/3rdParty/rocksdb/v5.16.X/table/two_level_iterator.h b/3rdParty/rocksdb/v5.18.X/table/two_level_iterator.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/table/two_level_iterator.h
rename to 3rdParty/rocksdb/v5.18.X/table/two_level_iterator.h
diff --git a/3rdParty/rocksdb/v5.16.X/third-party/fbson/COMMIT.md b/3rdParty/rocksdb/v5.18.X/third-party/fbson/COMMIT.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/third-party/fbson/COMMIT.md
rename to 3rdParty/rocksdb/v5.18.X/third-party/fbson/COMMIT.md
diff --git a/3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonDocument.h b/3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonDocument.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonDocument.h
rename to 3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonDocument.h
index 11b6fe28e4..c69fcb45f5 100644
--- a/3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonDocument.h
+++ b/3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonDocument.h
@@ -55,8 +55,7 @@
  * @author Tian Xia <tianx@fb.com>
  */
 
-#ifndef FBSON_FBSONDOCUMENT_H
-#define FBSON_FBSONDOCUMENT_H
+#pragma once
 
 #include <stdlib.h>
 #include <string.h>
@@ -889,5 +888,3 @@ inline FbsonValue* FbsonValue::findPath(const char* key_path,
 #pragma pack(pop)
 
 } // namespace fbson
-
-#endif // FBSON_FBSONDOCUMENT_H
diff --git a/3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonJsonParser.h b/3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonJsonParser.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonJsonParser.h
rename to 3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonJsonParser.h
index 47bff77fe5..f4b8ed2515 100644
--- a/3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonJsonParser.h
+++ b/3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonJsonParser.h
@@ -47,8 +47,7 @@
  * @author Tian Xia <tianx@fb.com>
  */
 
-#ifndef FBSON_FBSONPARSER_H
-#define FBSON_FBSONPARSER_H
+#pragma once
 
 #include <cmath>
 #include <limits>
@@ -741,5 +740,3 @@ class FbsonJsonParserT {
 typedef FbsonJsonParserT<FbsonOutStream> FbsonJsonParser;
 
 } // namespace fbson
-
-#endif // FBSON_FBSONPARSER_H
diff --git a/3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonStream.h b/3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonStream.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonStream.h
rename to 3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonStream.h
index 12723ea30e..b20cb1c3bf 100644
--- a/3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonStream.h
+++ b/3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonStream.h
@@ -18,8 +18,7 @@
  * @author Tian Xia <tianx@fb.com>
  */
 
-#ifndef FBSON_FBSONSTREAM_H
-#define FBSON_FBSONSTREAM_H
+#pragma once
 
 #ifndef __STDC_FORMAT_MACROS
 #define __STDC_FORMAT_MACROS
@@ -178,5 +177,3 @@ class FbsonOutStream : public std::ostream {
 };
 
 } // namespace fbson
-
-#endif // FBSON_FBSONSTREAM_H
diff --git a/3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonUtil.h b/3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonUtil.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonUtil.h
rename to 3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonUtil.h
index 2b6d6f5c97..70ac6cb2ba 100644
--- a/3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonUtil.h
+++ b/3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonUtil.h
@@ -9,8 +9,7 @@
  * @author Tian Xia <tianx@fb.com>
  */
 
-#ifndef FBSON_FBSONUTIL_H
-#define FBSON_FBSONUTIL_H
+#pragma once
 
 #include <sstream>
 #include "FbsonDocument.h"
@@ -159,5 +158,3 @@ class FbsonToJson {
 };
 
 } // namespace fbson
-
-#endif // FBSON_FBSONUTIL_H
diff --git a/3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonWriter.h b/3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonWriter.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonWriter.h
rename to 3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonWriter.h
index 2b94ef0a01..e5010fade2 100644
--- a/3rdParty/rocksdb/v5.16.X/third-party/fbson/FbsonWriter.h
+++ b/3rdParty/rocksdb/v5.18.X/third-party/fbson/FbsonWriter.h
@@ -25,8 +25,7 @@
  * @author Tian Xia <tianx@fb.com>
  */
 
-#ifndef FBSON_FBSONWRITER_H
-#define FBSON_FBSONWRITER_H
+#pragma once
 
 #include <stack>
 #include "FbsonDocument.h"
@@ -433,5 +432,3 @@ class FbsonWriterT {
 typedef FbsonWriterT<FbsonOutStream> FbsonWriter;
 
 } // namespace fbson
-
-#endif // FBSON_FBSONWRITER_H
diff --git a/3rdParty/rocksdb/v5.16.X/third-party/gtest-1.7.0/fused-src/gtest/CMakeLists.txt b/3rdParty/rocksdb/v5.18.X/third-party/gtest-1.7.0/fused-src/gtest/CMakeLists.txt
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/third-party/gtest-1.7.0/fused-src/gtest/CMakeLists.txt
rename to 3rdParty/rocksdb/v5.18.X/third-party/gtest-1.7.0/fused-src/gtest/CMakeLists.txt
diff --git a/3rdParty/rocksdb/v5.16.X/third-party/gtest-1.7.0/fused-src/gtest/gtest-all.cc b/3rdParty/rocksdb/v5.18.X/third-party/gtest-1.7.0/fused-src/gtest/gtest-all.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/third-party/gtest-1.7.0/fused-src/gtest/gtest-all.cc
rename to 3rdParty/rocksdb/v5.18.X/third-party/gtest-1.7.0/fused-src/gtest/gtest-all.cc
diff --git a/3rdParty/rocksdb/v5.16.X/third-party/gtest-1.7.0/fused-src/gtest/gtest.h b/3rdParty/rocksdb/v5.18.X/third-party/gtest-1.7.0/fused-src/gtest/gtest.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/third-party/gtest-1.7.0/fused-src/gtest/gtest.h
rename to 3rdParty/rocksdb/v5.18.X/third-party/gtest-1.7.0/fused-src/gtest/gtest.h
diff --git a/3rdParty/rocksdb/v5.16.X/thirdparty.inc b/3rdParty/rocksdb/v5.18.X/thirdparty.inc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/thirdparty.inc
rename to 3rdParty/rocksdb/v5.18.X/thirdparty.inc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/CMakeLists.txt b/3rdParty/rocksdb/v5.18.X/tools/CMakeLists.txt
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/CMakeLists.txt
rename to 3rdParty/rocksdb/v5.18.X/tools/CMakeLists.txt
diff --git a/3rdParty/rocksdb/v5.16.X/tools/Dockerfile b/3rdParty/rocksdb/v5.18.X/tools/Dockerfile
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/Dockerfile
rename to 3rdParty/rocksdb/v5.18.X/tools/Dockerfile
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/README.md b/3rdParty/rocksdb/v5.18.X/tools/advisor/README.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/README.md
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/README.md
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/__init__.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/__init__.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/__init__.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/__init__.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/bench_runner.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/bench_runner.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/bench_runner.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/bench_runner.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/config_optimizer_example.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/config_optimizer_example.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/config_optimizer_example.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/config_optimizer_example.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_bench_runner.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_bench_runner.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_bench_runner.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_bench_runner.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_config_optimizer.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_config_optimizer.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_config_optimizer.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_config_optimizer.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_log_parser.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_log_parser.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_log_parser.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_log_parser.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_options_parser.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_options_parser.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_options_parser.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_options_parser.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_stats_fetcher.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_stats_fetcher.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_stats_fetcher.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_stats_fetcher.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_timeseries_parser.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_timeseries_parser.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/db_timeseries_parser.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/db_timeseries_parser.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/ini_parser.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/ini_parser.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/ini_parser.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/ini_parser.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/rule_parser.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/rule_parser.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/rule_parser.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/rule_parser.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/rule_parser_example.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/rule_parser_example.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/rule_parser_example.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/rule_parser_example.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/rules.ini b/3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/rules.ini
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/advisor/rules.ini
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/advisor/rules.ini
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/__init__.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/__init__.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/__init__.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/__init__.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/LOG-0 b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/LOG-0
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/LOG-0
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/LOG-0
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/LOG-1 b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/LOG-1
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/LOG-1
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/LOG-1
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/OPTIONS-000005 b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/OPTIONS-000005
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/OPTIONS-000005
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/OPTIONS-000005
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/log_stats_parser_keys_ts b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/log_stats_parser_keys_ts
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/log_stats_parser_keys_ts
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/log_stats_parser_keys_ts
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/rules_err1.ini b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/rules_err1.ini
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/rules_err1.ini
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/rules_err1.ini
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/rules_err2.ini b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/rules_err2.ini
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/rules_err2.ini
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/rules_err2.ini
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/rules_err3.ini b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/rules_err3.ini
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/rules_err3.ini
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/rules_err3.ini
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/rules_err4.ini b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/rules_err4.ini
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/rules_err4.ini
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/rules_err4.ini
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/test_rules.ini b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/test_rules.ini
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/test_rules.ini
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/test_rules.ini
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/triggered_rules.ini b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/triggered_rules.ini
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/input_files/triggered_rules.ini
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/input_files/triggered_rules.ini
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/test_db_bench_runner.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/test_db_bench_runner.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/test_db_bench_runner.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/test_db_bench_runner.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/test_db_log_parser.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/test_db_log_parser.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/test_db_log_parser.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/test_db_log_parser.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/test_db_options_parser.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/test_db_options_parser.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/test_db_options_parser.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/test_db_options_parser.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/test_db_stats_fetcher.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/test_db_stats_fetcher.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/test_db_stats_fetcher.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/test_db_stats_fetcher.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/advisor/test/test_rule_parser.py b/3rdParty/rocksdb/v5.18.X/tools/advisor/test/test_rule_parser.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/advisor/test/test_rule_parser.py
rename to 3rdParty/rocksdb/v5.18.X/tools/advisor/test/test_rule_parser.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/auto_sanity_test.sh b/3rdParty/rocksdb/v5.18.X/tools/auto_sanity_test.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/auto_sanity_test.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/auto_sanity_test.sh
diff --git a/3rdParty/rocksdb/v5.16.X/tools/benchmark.sh b/3rdParty/rocksdb/v5.18.X/tools/benchmark.sh
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/tools/benchmark.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/benchmark.sh
index b7c2eefdb2..0ba1081e19 100755
--- a/3rdParty/rocksdb/v5.16.X/tools/benchmark.sh
+++ b/3rdParty/rocksdb/v5.18.X/tools/benchmark.sh
@@ -151,8 +151,8 @@ function summarize_result {
   stall_pct=$( grep "^Cumulative stall" $test_out| tail -1  | awk '{  print $5 }' )
   ops_sec=$( grep ^${bench_name} $test_out | awk '{ print $5 }' )
   mb_sec=$( grep ^${bench_name} $test_out | awk '{ print $7 }' )
-  lo_wgb=$( grep "^  L0" $test_out | tail -1 | awk '{ print $8 }' )
-  sum_wgb=$( grep "^ Sum" $test_out | tail -1 | awk '{ print $8 }' )
+  lo_wgb=$( grep "^  L0" $test_out | tail -1 | awk '{ print $9 }' )
+  sum_wgb=$( grep "^ Sum" $test_out | tail -1 | awk '{ print $9 }' )
   sum_size=$( grep "^ Sum" $test_out | tail -1 | awk '{ printf "%.1f", $3 / 1024.0 }' )
   wamp=$( echo "scale=1; $sum_wgb / $lo_wgb" | bc )
   wmb_ps=$( echo "scale=1; ( $sum_wgb * 1024.0 ) / $uptime" | bc )
@@ -177,6 +177,7 @@ function run_bulkload {
        $params_bulkload \
        --threads=1 \
        --memtablerep=vector \
+       --allow_concurrent_memtable_write=false \
        --disable_wal=1 \
        --seed=$( date +%s ) \
        2>&1 | tee -a $output_dir/benchmark_bulkload_fillrandom.log"
@@ -229,6 +230,7 @@ function run_manual_compaction_worker {
        --compaction_style=$2 \
        --subcompactions=$3 \
        --memtablerep=vector \
+       --allow_concurrent_memtable_write=false \
        --disable_wal=1 \
        --max_background_jobs=$4 \
        --seed=$( date +%s ) \
@@ -313,6 +315,7 @@ function run_fillseq {
        --min_level_to_compress=0 \
        --threads=1 \
        --memtablerep=vector \
+       --allow_concurrent_memtable_write=false \
        --disable_wal=$1 \
        --seed=$( date +%s ) \
        2>&1 | tee -a $log_file_name"
diff --git a/3rdParty/rocksdb/v5.16.X/tools/benchmark_leveldb.sh b/3rdParty/rocksdb/v5.18.X/tools/benchmark_leveldb.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/benchmark_leveldb.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/benchmark_leveldb.sh
diff --git a/3rdParty/rocksdb/v5.16.X/tools/blob_dump.cc b/3rdParty/rocksdb/v5.18.X/tools/blob_dump.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/blob_dump.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/blob_dump.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/check_format_compatible.sh b/3rdParty/rocksdb/v5.18.X/tools/check_format_compatible.sh
similarity index 68%
rename from 3rdParty/rocksdb/v5.16.X/tools/check_format_compatible.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/check_format_compatible.sh
index 39335446da..2d260c7ecc 100755
--- a/3rdParty/rocksdb/v5.16.X/tools/check_format_compatible.sh
+++ b/3rdParty/rocksdb/v5.18.X/tools/check_format_compatible.sh
@@ -17,7 +17,7 @@ mkdir $input_data_path || true
 rm -rf $script_copy_dir
 cp $scriptpath $script_copy_dir -rf
 
-# Generate four random files.
+# Generate random files.
 for i in {1..6}
 do
   input_data[$i]=$input_data_path/data$i
@@ -41,10 +41,22 @@ with open('${input_data[$i]}', 'w') as f:
 EOF
 done
 
+# Generate file(s) with sorted keys.
+sorted_input_data=$input_data_path/sorted_data
+echo == Generating file with sorted keys ${sorted_input_data}
+python - <<EOF
+with open('${sorted_input_data}', 'w') as f:
+  for i in range(0,10):
+    k = str(i)
+    v = "value" + k
+    print >> f, k + " ==> " + v
+EOF
+
 declare -a backward_compatible_checkout_objs=("2.2.fb.branch" "2.3.fb.branch" "2.4.fb.branch" "2.5.fb.branch" "2.6.fb.branch" "2.7.fb.branch" "2.8.1.fb" "3.0.fb.branch" "3.1.fb" "3.2.fb" "3.3.fb" "3.4.fb" "3.5.fb" "3.6.fb" "3.7.fb" "3.8.fb" "3.9.fb")
 declare -a forward_compatible_checkout_objs=("3.10.fb" "3.11.fb" "3.12.fb" "3.13.fb" "4.0.fb" "4.1.fb" "4.2.fb" "4.3.fb" "4.4.fb" "4.5.fb" "4.6.fb" "4.7.fb" "4.8.fb" "4.9.fb" "4.10.fb" "4.11.fb" "4.12.fb" "4.13.fb" "5.0.fb" "5.1.fb" "5.2.fb" "5.3.fb" "5.4.fb" "5.5.fb" "5.6.fb" "5.7.fb" "5.8.fb" "5.9.fb" "5.10.fb")
 declare -a forward_compatible_with_options_checkout_objs=("5.11.fb" "5.12.fb" "5.13.fb" "5.14.fb")
 declare -a checkout_objs=(${backward_compatible_checkout_objs[@]} ${forward_compatible_checkout_objs[@]} ${forward_compatible_with_options_checkout_objs[@]})
+declare -a extern_sst_ingestion_compatible_checkout_objs=("5.14.fb" "5.15.fb" "5.16.fb" "5.17.fb")
 
 generate_db()
 {
@@ -68,6 +80,28 @@ compare_db()
     set -e
 }
 
+write_external_sst()
+{
+    set +e
+    $script_copy_dir/write_external_sst.sh $1 $2 $3
+    if [ $? -ne 0 ]; then
+        echo ==== Error writing external SST file using data from $1 to $3 ====
+        exit 1
+    fi
+    set -e
+}
+
+ingest_external_sst()
+{
+    set +e
+    $script_copy_dir/ingest_external_sst.sh $1 $2
+    if [ $? -ne 0 ]; then
+        echo ==== Error ingesting external SST in $2 to DB at $1 ====
+        exit 1
+    fi
+    set -e
+}
+
 # Sandcastle sets us up with a remote that is just another directory on the same
 # machine and doesn't have our branches. Need to fetch them so checkout works.
 # Remote add may fail if added previously (we don't cleanup).
@@ -75,6 +109,41 @@ git remote add github_origin "https://github.com/facebook/rocksdb.git"
 set -e
 https_proxy="fwdproxy:8080" git fetch github_origin
 
+# Compatibility test for external SST file ingestion
+for checkout_obj in "${extern_sst_ingestion_compatible_checkout_objs[@]}"
+do
+  echo == Generating DB with extern SST file in "$checkout_obj" ...
+  https_proxy="fwdproxy:8080" git checkout github_origin/$checkout_obj -b $checkout_obj
+  make clean
+  make ldb -j32
+  write_external_sst $input_data_path $test_dir/$checkout_obj $test_dir/$checkout_obj
+  ingest_external_sst $test_dir/$checkout_obj $test_dir/$checkout_obj
+done
+
+checkout_flag=${1:-"master"}
+
+echo == Building $checkout_flag debug
+https_proxy="fwdproxy:8080" git checkout github_origin/$checkout_flag -b tmp-$checkout_flag
+make clean
+make ldb -j32
+compare_base_db_dir=$test_dir"/base_db_dir"
+write_external_sst $input_data_path $compare_base_db_dir $compare_base_db_dir
+ingest_external_sst $compare_base_db_dir $compare_base_db_dir
+
+for checkout_obj in "${extern_sst_ingestion_compatible_checkout_objs[@]}"
+do
+  echo == Build "$checkout_obj" and try to open DB generated using $checkout_flag
+  git checkout $checkout_obj
+  make clean
+  make ldb -j32
+  compare_db $test_dir/$checkout_obj $compare_base_db_dir db_dump.txt 1 1
+  git checkout tmp-$checkout_flag
+  # Clean up
+  git branch -D $checkout_obj
+done
+
+echo == Finish compatibility test for SST ingestion.
+
 for checkout_obj in "${checkout_objs[@]}"
 do
    echo == Generating DB from "$checkout_obj" ...
@@ -87,7 +156,7 @@ done
 checkout_flag=${1:-"master"}
 
 echo == Building $checkout_flag debug
-https_proxy="fwdproxy:8080" git checkout github_origin/$checkout_flag -b tmp-$checkout_flag
+git checkout tmp-$checkout_flag
 make clean
 make ldb -j32
 compare_base_db_dir=$test_dir"/base_db_dir"
diff --git a/3rdParty/rocksdb/v5.16.X/tools/db_bench.cc b/3rdParty/rocksdb/v5.18.X/tools/db_bench.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/db_bench.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/db_bench.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/db_bench_tool.cc b/3rdParty/rocksdb/v5.18.X/tools/db_bench_tool.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/tools/db_bench_tool.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/db_bench_tool.cc
index c32822c8f1..75f1d449d5 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/db_bench_tool.cc
+++ b/3rdParty/rocksdb/v5.18.X/tools/db_bench_tool.cc
@@ -33,10 +33,12 @@
 #include <unordered_map>
 
 #include "db/db_impl.h"
+#include "db/malloc_stats.h"
 #include "db/version_set.h"
 #include "hdfs/env_hdfs.h"
 #include "monitoring/histogram.h"
 #include "monitoring/statistics.h"
+#include "options/cf_options.h"
 #include "port/port.h"
 #include "port/stack_trace.h"
 #include "rocksdb/cache.h"
@@ -45,7 +47,6 @@
 #include "rocksdb/filter_policy.h"
 #include "rocksdb/memtablerep.h"
 #include "rocksdb/options.h"
-#include "options/cf_options.h"
 #include "rocksdb/perf_context.h"
 #include "rocksdb/persistent_cache.h"
 #include "rocksdb/rate_limiter.h"
@@ -248,6 +249,10 @@ DEFINE_bool(reverse_iterator, false,
             "When true use Prev rather than Next for iterators that do "
             "Seek and then Next");
 
+DEFINE_int64(max_scan_distance, 0,
+             "Used to define iterate_upper_bound (or iterate_lower_bound "
+             "if FLAGS_reverse_iterator is set to true) when value is nonzero");
+
 DEFINE_bool(use_uint64_comparator, false, "use Uint64 user comparator");
 
 DEFINE_int64(batch_size, 1, "Batch size");
@@ -640,9 +645,11 @@ DEFINE_bool(optimize_filters_for_hits, false,
 DEFINE_uint64(delete_obsolete_files_period_micros, 0,
               "Ignored. Left here for backward compatibility");
 
+DEFINE_int64(writes_before_delete_range, 0,
+             "Number of writes before DeleteRange is called regularly.");
+
 DEFINE_int64(writes_per_range_tombstone, 0,
-             "Number of writes between range "
-             "tombstones");
+             "Number of writes between range tombstones");
 
 DEFINE_int64(range_tombstone_width, 100, "Number of keys in tombstone's range");
 
@@ -935,6 +942,9 @@ DEFINE_uint64(max_compaction_bytes, rocksdb::Options().max_compaction_bytes,
 
 #ifndef ROCKSDB_LITE
 DEFINE_bool(readonly, false, "Run read only benchmarks.");
+
+DEFINE_bool(print_malloc_stats, false,
+            "Print malloc stats to stdout after benchmarks finish.");
 #endif  // ROCKSDB_LITE
 
 DEFINE_bool(disable_auto_compactions, false, "Do not auto trigger compactions");
@@ -1137,11 +1147,12 @@ class ReportFileOpEnv : public EnvWrapper {
     counters_.bytes_written_ = 0;
   }
 
-  Status NewSequentialFile(const std::string& f, unique_ptr<SequentialFile>* r,
+  Status NewSequentialFile(const std::string& f,
+                           std::unique_ptr<SequentialFile>* r,
                            const EnvOptions& soptions) override {
     class CountingFile : public SequentialFile {
      private:
-      unique_ptr<SequentialFile> target_;
+      std::unique_ptr<SequentialFile> target_;
       ReportFileOpCounters* counters_;
 
      public:
@@ -1169,11 +1180,11 @@ class ReportFileOpEnv : public EnvWrapper {
   }
 
   Status NewRandomAccessFile(const std::string& f,
-                             unique_ptr<RandomAccessFile>* r,
+                             std::unique_ptr<RandomAccessFile>* r,
                              const EnvOptions& soptions) override {
     class CountingFile : public RandomAccessFile {
      private:
-      unique_ptr<RandomAccessFile> target_;
+      std::unique_ptr<RandomAccessFile> target_;
       ReportFileOpCounters* counters_;
 
      public:
@@ -1198,11 +1209,11 @@ class ReportFileOpEnv : public EnvWrapper {
     return s;
   }
 
-  Status NewWritableFile(const std::string& f, unique_ptr<WritableFile>* r,
+  Status NewWritableFile(const std::string& f, std::unique_ptr<WritableFile>* r,
                          const EnvOptions& soptions) override {
     class CountingFile : public WritableFile {
      private:
-      unique_ptr<WritableFile> target_;
+      std::unique_ptr<WritableFile> target_;
       ReportFileOpCounters* counters_;
 
      public:
@@ -1968,12 +1979,15 @@ class Benchmark {
   int prefix_size_;
   int64_t keys_per_prefix_;
   int64_t entries_per_batch_;
+  int64_t writes_before_delete_range_;
   int64_t writes_per_range_tombstone_;
   int64_t range_tombstone_width_;
   int64_t max_num_range_tombstones_;
   WriteOptions write_options_;
   Options open_options_;  // keep options around to properly destroy db later
+#ifndef ROCKSDB_LITE
   TraceOptions trace_options_;
+#endif
   int64_t reads_;
   int64_t deletes_;
   double read_random_exp_range_;
@@ -1983,6 +1997,52 @@ class Benchmark {
   bool report_file_operations_;
   bool use_blob_db_;
 
+  class ErrorHandlerListener : public EventListener {
+   public:
+    ErrorHandlerListener()
+        : mutex_(),
+          cv_(&mutex_),
+          no_auto_recovery_(false),
+          recovery_complete_(false) {}
+
+    ~ErrorHandlerListener() {}
+
+    void OnErrorRecoveryBegin(BackgroundErrorReason /*reason*/,
+                              Status /*bg_error*/, bool* auto_recovery) {
+      if (*auto_recovery && no_auto_recovery_) {
+        *auto_recovery = false;
+      }
+    }
+
+    void OnErrorRecoveryCompleted(Status /*old_bg_error*/) {
+      InstrumentedMutexLock l(&mutex_);
+      recovery_complete_ = true;
+      cv_.SignalAll();
+    }
+
+    bool WaitForRecovery(uint64_t /*abs_time_us*/) {
+      InstrumentedMutexLock l(&mutex_);
+      if (!recovery_complete_) {
+        cv_.Wait(/*abs_time_us*/);
+      }
+      if (recovery_complete_) {
+        recovery_complete_ = false;
+        return true;
+      }
+      return false;
+    }
+
+    void EnableAutoRecovery(bool enable = true) { no_auto_recovery_ = !enable; }
+
+   private:
+    InstrumentedMutex mutex_;
+    InstrumentedCondVar cv_;
+    bool no_auto_recovery_;
+    bool recovery_complete_;
+  };
+
+  std::shared_ptr<ErrorHandlerListener> listener_;
+
   bool SanityCheck() {
     if (FLAGS_compression_ratio > 1) {
       fprintf(stderr, "compression_ratio should be between 0 and 1\n");
@@ -2318,6 +2378,8 @@ class Benchmark {
         }
       }
     }
+
+    listener_.reset(new ErrorHandlerListener());
   }
 
   ~Benchmark() {
@@ -2447,6 +2509,7 @@ void VerifyDBFromDB(std::string& truth_db_name) {
       value_size_ = FLAGS_value_size;
       key_size_ = FLAGS_key_size;
       entries_per_batch_ = FLAGS_batch_size;
+      writes_before_delete_range_ = FLAGS_writes_before_delete_range;
       writes_per_range_tombstone_ = FLAGS_writes_per_range_tombstone;
       range_tombstone_width_ = FLAGS_range_tombstone_width;
       max_num_range_tombstones_ = FLAGS_max_num_range_tombstones;
@@ -2801,6 +2864,7 @@ void VerifyDBFromDB(std::string& truth_db_name) {
     }
 
     SetPerfLevel(static_cast<PerfLevel> (shared->perf_level));
+    perf_context.EnablePerLevelPerfContext();
     thread->stats.Start(thread->tid);
     (arg->bm->*(arg->method))(thread);
     thread->stats.Stop();
@@ -2992,7 +3056,7 @@ void VerifyDBFromDB(std::string& truth_db_name) {
     int64_t bytes = 0;
     int decompress_size;
     while (ok && bytes < 1024 * 1048576) {
-      char *uncompressed = nullptr;
+      CacheAllocationPtr uncompressed;
       switch (FLAGS_compression_type_e) {
         case rocksdb::kSnappyCompression: {
           // get size and allocate here to make comparison fair
@@ -3002,45 +3066,44 @@ void VerifyDBFromDB(std::string& truth_db_name) {
             ok = false;
             break;
           }
-          uncompressed = new char[ulength];
+          uncompressed = AllocateBlock(ulength, nullptr);
           ok = Snappy_Uncompress(compressed.data(), compressed.size(),
-                                 uncompressed);
+                                 uncompressed.get());
           break;
         }
       case rocksdb::kZlibCompression:
         uncompressed = Zlib_Uncompress(uncompression_ctx, compressed.data(),
                                        compressed.size(), &decompress_size, 2);
-        ok = uncompressed != nullptr;
+        ok = uncompressed.get() != nullptr;
         break;
       case rocksdb::kBZip2Compression:
         uncompressed = BZip2_Uncompress(compressed.data(), compressed.size(),
                                         &decompress_size, 2);
-        ok = uncompressed != nullptr;
+        ok = uncompressed.get() != nullptr;
         break;
       case rocksdb::kLZ4Compression:
         uncompressed = LZ4_Uncompress(uncompression_ctx, compressed.data(),
                                       compressed.size(), &decompress_size, 2);
-        ok = uncompressed != nullptr;
+        ok = uncompressed.get() != nullptr;
         break;
       case rocksdb::kLZ4HCCompression:
         uncompressed = LZ4_Uncompress(uncompression_ctx, compressed.data(),
                                       compressed.size(), &decompress_size, 2);
-        ok = uncompressed != nullptr;
+        ok = uncompressed.get() != nullptr;
         break;
       case rocksdb::kXpressCompression:
-        uncompressed = XPRESS_Uncompress(compressed.data(), compressed.size(),
-          &decompress_size);
-        ok = uncompressed != nullptr;
+        uncompressed.reset(XPRESS_Uncompress(
+            compressed.data(), compressed.size(), &decompress_size));
+        ok = uncompressed.get() != nullptr;
         break;
       case rocksdb::kZSTD:
         uncompressed = ZSTD_Uncompress(uncompression_ctx, compressed.data(),
                                        compressed.size(), &decompress_size);
-        ok = uncompressed != nullptr;
+        ok = uncompressed.get() != nullptr;
         break;
       default:
         ok = false;
       }
-      delete[] uncompressed;
       bytes += input.size();
       thread->stats.FinishedOps(nullptr, nullptr, 1, kUncompress);
     }
@@ -3500,6 +3563,7 @@ void VerifyDBFromDB(std::string& truth_db_name) {
           FLAGS_rate_limiter_auto_tuned));
     }
 
+    options.listeners.emplace_back(listener_);
     if (FLAGS_num_multi_db <= 1) {
       OpenDb(options, FLAGS_db, &db_);
     } else {
@@ -3745,7 +3809,8 @@ void VerifyDBFromDB(std::string& truth_db_name) {
 
     Duration duration(test_duration, max_ops, ops_per_stage);
     for (size_t i = 0; i < num_key_gens; i++) {
-      key_gens[i].reset(new KeyGenerator(&(thread->rand), write_mode, num_,
+      key_gens[i].reset(new KeyGenerator(&(thread->rand), write_mode,
+                                         num_ + max_num_range_tombstones_,
                                          ops_per_stage));
     }
 
@@ -3826,9 +3891,13 @@ void VerifyDBFromDB(std::string& truth_db_name) {
         bytes += value_size_ + key_size_;
         ++num_written;
         if (writes_per_range_tombstone_ > 0 &&
-            num_written / writes_per_range_tombstone_ <=
+            num_written > writes_before_delete_range_ &&
+            (num_written - writes_before_delete_range_) /
+                    writes_per_range_tombstone_ <=
                 max_num_range_tombstones_ &&
-            num_written % writes_per_range_tombstone_ == 0) {
+            (num_written - writes_before_delete_range_) %
+                    writes_per_range_tombstone_ ==
+                0) {
           int64_t begin_num = key_gens[id]->Next();
           if (FLAGS_expand_range_tombstones) {
             for (int64_t offset = 0; offset < range_tombstone_width_;
@@ -3892,6 +3961,10 @@ void VerifyDBFromDB(std::string& truth_db_name) {
                   NewGenericRateLimiter(write_rate));
         }
       }
+      if (!s.ok()) {
+        s = listener_->WaitForRecovery(600000000) ? Status::OK() : s;
+      }
+
       if (!s.ok()) {
         fprintf(stderr, "put error: %s\n", s.ToString().c_str());
         exit(1);
@@ -4175,7 +4248,7 @@ void VerifyDBFromDB(std::string& truth_db_name) {
         }
         if (levelMeta.level == 0) {
           for (auto& fileMeta : levelMeta.files) {
-            fprintf(stdout, "Level[%d]: %s(size: %" PRIu64 " bytes)\n",
+            fprintf(stdout, "Level[%d]: %s(size: %" ROCKSDB_PRIszt " bytes)\n",
                     levelMeta.level, fileMeta.name.c_str(), fileMeta.size);
           }
         } else {
@@ -4494,9 +4567,31 @@ void VerifyDBFromDB(std::string& truth_db_name) {
     std::unique_ptr<const char[]> key_guard;
     Slice key = AllocateKey(&key_guard);
 
+    std::unique_ptr<const char[]> upper_bound_key_guard;
+    Slice upper_bound = AllocateKey(&upper_bound_key_guard);
+    std::unique_ptr<const char[]> lower_bound_key_guard;
+    Slice lower_bound = AllocateKey(&lower_bound_key_guard);
+
     Duration duration(FLAGS_duration, reads_);
     char value_buffer[256];
     while (!duration.Done(1)) {
+      int64_t seek_pos = thread->rand.Next() % FLAGS_num;
+      GenerateKeyFromInt((uint64_t)seek_pos, FLAGS_num, &key);
+      if (FLAGS_max_scan_distance != 0) {
+        if (FLAGS_reverse_iterator) {
+          GenerateKeyFromInt(
+              (uint64_t)std::max((int64_t)0,
+                                 seek_pos - FLAGS_max_scan_distance),
+              FLAGS_num, &lower_bound);
+          options.iterate_lower_bound = &lower_bound;
+        } else {
+          GenerateKeyFromInt(
+              (uint64_t)std::min(FLAGS_num, seek_pos + FLAGS_max_scan_distance),
+              FLAGS_num, &upper_bound);
+          options.iterate_upper_bound = &upper_bound;
+        }
+      }
+
       if (!FLAGS_use_tailing_iterator) {
         if (db_.db != nullptr) {
           delete single_iter;
@@ -4517,7 +4612,6 @@ void VerifyDBFromDB(std::string& truth_db_name) {
         iter_to_use = multi_iters[thread->rand.Next() % multi_iters.size()];
       }
 
-      GenerateKeyFromInt(thread->rand.Next() % FLAGS_num, FLAGS_num, &key);
       iter_to_use->Seek(key);
       read++;
       if (iter_to_use->Valid() && iter_to_use->key().compare(key) == 0) {
@@ -5614,7 +5708,7 @@ void VerifyDBFromDB(std::string& truth_db_name) {
 
   void Replay(ThreadState* /*thread*/, DBWithColumnFamilies* db_with_cfh) {
     Status s;
-    unique_ptr<TraceReader> trace_reader;
+    std::unique_ptr<TraceReader> trace_reader;
     s = NewFileTraceReader(FLAGS_env, EnvOptions(), FLAGS_trace_file,
                            &trace_reader);
     if (!s.ok()) {
@@ -5742,6 +5836,15 @@ int db_bench_tool(int argc, char** argv) {
 
   rocksdb::Benchmark benchmark;
   benchmark.Run();
+
+#ifndef ROCKSDB_LITE
+  if (FLAGS_print_malloc_stats) {
+    std::string stats_string;
+    rocksdb::DumpMallocStats(&stats_string);
+    fprintf(stdout, "Malloc stats:\n%s\n", stats_string.c_str());
+  }
+#endif  // ROCKSDB_LITE
+
   return 0;
 }
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/tools/db_bench_tool_test.cc b/3rdParty/rocksdb/v5.18.X/tools/db_bench_tool_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/tools/db_bench_tool_test.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/db_bench_tool_test.cc
index 67426066eb..dfc461193c 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/db_bench_tool_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/tools/db_bench_tool_test.cc
@@ -279,7 +279,7 @@ const std::string options_file_content = R"OPTIONS_FILE(
 
 TEST_F(DBBenchTest, OptionsFileFromFile) {
   const std::string kOptionsFileName = test_path_ + "/OPTIONS_flash";
-  unique_ptr<WritableFile> writable;
+  std::unique_ptr<WritableFile> writable;
   ASSERT_OK(Env::Default()->NewWritableFile(kOptionsFileName, &writable,
                                             EnvOptions()));
   ASSERT_OK(writable->Append(options_file_content));
diff --git a/3rdParty/rocksdb/v5.16.X/tools/db_crashtest.py b/3rdParty/rocksdb/v5.18.X/tools/db_crashtest.py
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/tools/db_crashtest.py
rename to 3rdParty/rocksdb/v5.18.X/tools/db_crashtest.py
index d6ae40c28c..0bf43780df 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/db_crashtest.py
+++ b/3rdParty/rocksdb/v5.18.X/tools/db_crashtest.py
@@ -15,6 +15,9 @@ import argparse
 #       default_params < {blackbox,whitebox}_default_params <
 #       simple_default_params <
 #       {blackbox,whitebox}_simple_default_params < args
+#   for enable_atomic_flush:
+#       default_params < {blackbox,whitebox}_default_params <
+#       atomic_flush_params < args
 
 expected_values_file = tempfile.NamedTemporaryFile()
 
@@ -32,6 +35,7 @@ default_params = {
     "destroy_db_initially": 0,
     "enable_pipelined_write": lambda: random.randint(0, 1),
     "expected_values_path": expected_values_file.name,
+    "flush_one_in": 1000000,
     "max_background_compactions": 20,
     "max_bytes_for_level_base": 10485760,
     "max_key": 100000000,
@@ -55,6 +59,7 @@ default_params = {
     "write_buffer_size": 4 * 1024 * 1024,
     "writepercent": 35,
     "format_version": lambda: random.randint(2, 4),
+    "index_block_restart_interval": lambda: random.choice(range(1, 16)),
 }
 
 _TEST_DIR_ENV_VAR = 'TEST_TMPDIR'
@@ -120,6 +125,15 @@ blackbox_simple_default_params = {
 
 whitebox_simple_default_params = {}
 
+atomic_flush_params = {
+    "atomic_flush": 1,
+    "disable_wal": 1,
+    "reopen": 0,
+    # use small value for write_buffer_size so that RocksDB triggers flush
+    # more frequently
+    "write_buffer_size": 1024 * 1024,
+}
+
 
 def finalize_and_sanitize(src_params):
     dest_params = dict([(k,  v() if callable(v) else v)
@@ -150,6 +164,8 @@ def gen_cmd_params(args):
             params.update(blackbox_simple_default_params)
         if args.test_type == 'whitebox':
             params.update(whitebox_simple_default_params)
+    if args.enable_atomic_flush:
+        params.update(atomic_flush_params)
 
     for k, v in vars(args).items():
         if v is not None:
@@ -162,7 +178,7 @@ def gen_cmd(params, unknown_params):
         '--{0}={1}'.format(k, v)
         for k, v in finalize_and_sanitize(params).items()
         if k not in set(['test_type', 'simple', 'duration', 'interval',
-                         'random_kill_odd'])
+                         'random_kill_odd', 'enable_atomic_flush'])
         and v is not None] + unknown_params
     return cmd
 
@@ -354,6 +370,7 @@ def main():
         db_stress multiple times")
     parser.add_argument("test_type", choices=["blackbox", "whitebox"])
     parser.add_argument("--simple", action="store_true")
+    parser.add_argument("--enable_atomic_flush", action='store_true')
 
     all_params = dict(default_params.items()
                       + blackbox_default_params.items()
diff --git a/3rdParty/rocksdb/v5.16.X/tools/db_repl_stress.cc b/3rdParty/rocksdb/v5.18.X/tools/db_repl_stress.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/tools/db_repl_stress.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/db_repl_stress.cc
index 5901b97778..c640b5945b 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/db_repl_stress.cc
+++ b/3rdParty/rocksdb/v5.18.X/tools/db_repl_stress.cc
@@ -67,7 +67,7 @@ struct ReplicationThread {
 static void ReplicationThreadBody(void* arg) {
   ReplicationThread* t = reinterpret_cast<ReplicationThread*>(arg);
   DB* db = t->db;
-  unique_ptr<TransactionLogIterator> iter;
+  std::unique_ptr<TransactionLogIterator> iter;
   SequenceNumber currentSeqNum = 1;
   while (!t->stop.load(std::memory_order_acquire)) {
     iter.reset();
diff --git a/3rdParty/rocksdb/v5.16.X/tools/db_sanity_test.cc b/3rdParty/rocksdb/v5.18.X/tools/db_sanity_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/db_sanity_test.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/db_sanity_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/db_stress.cc b/3rdParty/rocksdb/v5.18.X/tools/db_stress.cc
similarity index 85%
rename from 3rdParty/rocksdb/v5.16.X/tools/db_stress.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/db_stress.cc
index a7cfd51d66..20b2899e95 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/db_stress.cc
+++ b/3rdParty/rocksdb/v5.18.X/tools/db_stress.cc
@@ -133,6 +133,8 @@ DEFINE_bool(test_batches_snapshots, false,
             "\t(b) No long validation at the end (more speed up)\n"
             "\t(c) Test snapshot and atomicity of batch writes");
 
+DEFINE_bool(atomic_flush, false, "If true, the test enables atomic flush\n");
+
 DEFINE_int32(threads, 32, "Number of concurrent threads to run.");
 
 DEFINE_int32(ttl, -1,
@@ -232,6 +234,11 @@ DEFINE_int32(
     static_cast<int32_t>(rocksdb::BlockBasedTableOptions().format_version),
     "Format version of SST files.");
 
+DEFINE_int32(index_block_restart_interval,
+             rocksdb::BlockBasedTableOptions().index_block_restart_interval,
+             "Number of keys between restart points "
+             "for delta encoding of keys in index block.");
+
 DEFINE_int32(max_background_compactions,
              rocksdb::Options().max_background_compactions,
              "The maximum number of concurrent background compactions "
@@ -412,6 +419,10 @@ DEFINE_int32(compact_range_one_in, 0,
              "If non-zero, then CompactRange() will be called once for every N "
              "operations on average.  0 indicates CompactRange() is disabled.");
 
+DEFINE_int32(flush_one_in, 0,
+             "If non-zero, then Flush() will be called once for every N ops "
+             "on average.  0 indicates calls to Flush() are disabled.");
+
 DEFINE_int32(compact_range_width, 10000,
              "The width of the ranges passed to CompactRange().");
 
@@ -419,6 +430,10 @@ DEFINE_int32(acquire_snapshot_one_in, 0,
              "If non-zero, then acquires a snapshot once every N operations on "
              "average.");
 
+DEFINE_bool(compare_full_db_state_snapshot, false,
+            "If set we compare state of entire db (in one of the threads) with"
+            "each snapshot.");
+
 DEFINE_uint64(snapshot_hold_ops, 0,
               "If non-zero, then releases snapshots N operations after they're "
               "acquired.");
@@ -591,7 +606,7 @@ enum RepFactory StringToRepFactory(const char* ctype) {
 #ifdef _MSC_VER
 #pragma warning(push)
 // truncation of constant value on static_cast
-#pragma warning(disable: 4309)
+#pragma warning(disable : 4309)
 #endif
 bool GetNextPrefix(const rocksdb::Slice& src, std::string* v) {
   std::string ret = src.ToString();
@@ -651,6 +666,18 @@ static std::string Key(int64_t val) {
   return big_endian_key;
 }
 
+static bool GetIntVal(std::string big_endian_key, uint64_t *key_p) {
+  unsigned int size_key = sizeof(*key_p);
+  assert(big_endian_key.size() == size_key);
+  std::string little_endian_key;
+  little_endian_key.resize(size_key);
+  for (size_t i = 0 ; i < size_key; ++i) {
+    little_endian_key[i] = big_endian_key[size_key - 1 - i];
+  }
+  Slice little_endian_slice = Slice(little_endian_key);
+  return GetFixed64(&little_endian_slice, key_p);
+}
+
 static std::string StringToHex(const std::string& str) {
   std::string result = "0x";
   result.append(Slice(str).ToString(true));
@@ -765,46 +792,36 @@ class Stats {
     }
   }
 
-  void AddBytesForWrites(int nwrites, size_t nbytes) {
+  void AddBytesForWrites(long nwrites, size_t nbytes) {
     writes_ += nwrites;
     bytes_ += nbytes;
   }
 
-  void AddGets(int ngets, int nfounds) {
+  void AddGets(long ngets, long nfounds) {
     founds_ += nfounds;
     gets_ += ngets;
   }
 
-  void AddPrefixes(int nprefixes, int count) {
+  void AddPrefixes(long nprefixes, long count) {
     prefixes_ += nprefixes;
     iterator_size_sums_ += count;
   }
 
-  void AddIterations(int n) {
-    iterations_ += n;
-  }
+  void AddIterations(long n) { iterations_ += n; }
 
-  void AddDeletes(int n) {
-    deletes_ += n;
-  }
+  void AddDeletes(long n) { deletes_ += n; }
 
   void AddSingleDeletes(size_t n) { single_deletes_ += n; }
 
-  void AddRangeDeletions(int n) {
-    range_deletions_ += n;
-  }
+  void AddRangeDeletions(long n) { range_deletions_ += n; }
 
-  void AddCoveredByRangeDeletions(int n) {
-    covered_by_range_deletions_ += n;
-  }
+  void AddCoveredByRangeDeletions(long n) { covered_by_range_deletions_ += n; }
 
-  void AddErrors(int n) {
-    errors_ += n;
-  }
+  void AddErrors(long n) { errors_ += n; }
 
-  void AddNumCompactFilesSucceed(int n) { num_compact_files_succeed_ += n; }
+  void AddNumCompactFilesSucceed(long n) { num_compact_files_succeed_ += n; }
 
-  void AddNumCompactFilesFailed(int n) { num_compact_files_failed_ += n; }
+  void AddNumCompactFilesFailed(long n) { num_compact_files_failed_ += n; }
 
   void Report(const char* name) {
     std::string extra;
@@ -923,7 +940,7 @@ class SharedState {
       if (status.ok()) {
         status = FLAGS_env->GetFileSize(FLAGS_expected_values_path, &size);
       }
-      unique_ptr<WritableFile> wfile;
+      std::unique_ptr<WritableFile> wfile;
       if (status.ok() && size == 0) {
         const EnvOptions soptions;
         status = FLAGS_env->NewWritableFile(FLAGS_expected_values_path, &wfile,
@@ -1207,6 +1224,8 @@ struct ThreadState {
     Status status;
     // The value of the Get
     std::string value;
+    // optional state of all keys in the db
+    std::vector<bool> *key_vec;
   };
   std::queue<std::pair<uint64_t, SnapshotState> > snapshot_queue;
 
@@ -1219,9 +1238,13 @@ class DbStressListener : public EventListener {
   DbStressListener(const std::string& db_name,
                    const std::vector<DbPath>& db_paths,
                    const std::vector<ColumnFamilyDescriptor>& column_families)
-      : db_name_(db_name), db_paths_(db_paths),
-        column_families_(column_families) {}
-  virtual ~DbStressListener() {}
+      : db_name_(db_name),
+        db_paths_(db_paths),
+        column_families_(column_families),
+        num_pending_file_creations_(0) {}
+  virtual ~DbStressListener() {
+    assert(num_pending_file_creations_ == 0);
+  }
 #ifndef ROCKSDB_LITE
   virtual void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
     assert(IsValidColumnFamilyName(info.cf_name));
@@ -1246,16 +1269,23 @@ class DbStressListener : public EventListener {
         std::chrono::microseconds(Random::GetTLSInstance()->Uniform(5000)));
   }
 
+  virtual void OnTableFileCreationStarted(
+      const TableFileCreationBriefInfo& /*info*/) override {
+    ++num_pending_file_creations_;
+  }
   virtual void OnTableFileCreated(const TableFileCreationInfo& info) override {
     assert(info.db_name == db_name_);
     assert(IsValidColumnFamilyName(info.cf_name));
-    VerifyFilePath(info.file_path);
+    if (info.file_size) {
+      VerifyFilePath(info.file_path);
+    }
     assert(info.job_id > 0 || FLAGS_compact_files_one_in > 0);
     if (info.status.ok() && info.file_size > 0) {
       assert(info.table_properties.data_size > 0);
       assert(info.table_properties.raw_key_size > 0);
       assert(info.table_properties.num_entries > 0);
     }
+    --num_pending_file_creations_;
   }
 
  protected:
@@ -1328,6 +1358,7 @@ class DbStressListener : public EventListener {
   std::string db_name_;
   std::vector<DbPath> db_paths_;
   std::vector<ColumnFamilyDescriptor> column_families_;
+  std::atomic<int> num_pending_file_creations_;
 };
 
 }  // namespace
@@ -1703,6 +1734,24 @@ class StressTest {
                                   ")");
       }
     }
+    if (snap_state.key_vec != nullptr) {
+      // When `prefix_extractor` is set, seeking to beginning and scanning
+      // across prefixes are only supported with `total_order_seek` set.
+      ropt.total_order_seek = true;
+      std::unique_ptr<Iterator> iterator(db->NewIterator(ropt));
+      std::unique_ptr<std::vector<bool>> tmp_bitvec(new std::vector<bool>(FLAGS_max_key));
+      for (iterator->SeekToFirst(); iterator->Valid(); iterator->Next()) {
+        uint64_t key_val;
+        if (GetIntVal(iterator->key().ToString(), &key_val)) {
+          (*tmp_bitvec.get())[key_val] = true;
+        }
+      }
+      if (!std::equal(snap_state.key_vec->begin(),
+                      snap_state.key_vec->end(),
+                      tmp_bitvec.get()->begin())) {
+        return Status::Corruption("Found inconsistent keys at this snapshot");
+      }
+    }
     return Status::OK();
   }
 
@@ -1786,6 +1835,7 @@ class StressTest {
           while (!thread->snapshot_queue.empty()) {
             db_->ReleaseSnapshot(
                 thread->snapshot_queue.front().second.snapshot);
+            delete thread->snapshot_queue.front().second.key_vec;
             thread->snapshot_queue.pop();
           }
           thread->shared->IncVotedReopen();
@@ -1837,27 +1887,6 @@ class StressTest {
         }
       }
 
-      if (FLAGS_backup_one_in > 0 &&
-          thread->rand.Uniform(FLAGS_backup_one_in) == 0) {
-        std::string backup_dir = FLAGS_db + "/.backup" + ToString(thread->tid);
-        BackupableDBOptions backup_opts(backup_dir);
-        BackupEngine* backup_engine = nullptr;
-        Status s = BackupEngine::Open(FLAGS_env, backup_opts, &backup_engine);
-        if (s.ok()) {
-          s = backup_engine->CreateNewBackup(db_);
-        }
-        if (s.ok()) {
-          s = backup_engine->PurgeOldBackups(0 /* num_backups_to_keep */);
-        }
-        if (!s.ok()) {
-          printf("A BackupEngine operation failed with: %s\n",
-                 s.ToString().c_str());
-        }
-        if (backup_engine != nullptr) {
-          delete backup_engine;
-        }
-      }
-
       if (FLAGS_compact_files_one_in > 0 &&
           thread->rand.Uniform(FLAGS_compact_files_one_in) == 0) {
         auto* random_cf =
@@ -1897,8 +1926,8 @@ class StressTest {
                 db_->CompactFiles(CompactionOptions(), random_cf, input_files,
                                   static_cast<int>(output_level));
             if (!s.ok()) {
-              printf("Unable to perform CompactFiles(): %s\n",
-                     s.ToString().c_str());
+              fprintf(stdout, "Unable to perform CompactFiles(): %s\n",
+                      s.ToString().c_str());
               thread->stats.AddNumCompactFilesFailed(1);
             } else {
               thread->stats.AddNumCompactFilesSucceed(1);
@@ -1943,6 +1972,21 @@ class StressTest {
 
       std::vector<int> rand_column_families =
           GenerateColumnFamilies(FLAGS_column_families, rand_column_family);
+
+      if (FLAGS_flush_one_in > 0 &&
+          thread->rand.Uniform(FLAGS_flush_one_in) == 0) {
+        FlushOptions flush_opts;
+        std::vector<ColumnFamilyHandle*> cfhs;
+        std::for_each(
+            rand_column_families.begin(), rand_column_families.end(),
+            [this, &cfhs](int k) { cfhs.push_back(column_families_[k]); });
+        Status status = db_->Flush(flush_opts, cfhs);
+        if (!status.ok()) {
+          fprintf(stdout, "Unable to perform Flush(): %s\n",
+                  status.ToString().c_str());
+        }
+      }
+
       std::vector<int64_t> rand_keys = GenerateKeys(rand_key);
 
       if (FLAGS_ingest_external_file_one_in > 0 &&
@@ -1950,6 +1994,15 @@ class StressTest {
         TestIngestExternalFile(thread, rand_column_families, rand_keys, lock);
       }
 
+      if (FLAGS_backup_one_in > 0 &&
+          thread->rand.Uniform(FLAGS_backup_one_in) == 0) {
+        Status s = TestBackupRestore(thread, rand_column_families, rand_keys);
+        if (!s.ok()) {
+          VerificationAbort(shared, "Backup/restore gave inconsistent state",
+                            s);
+        }
+      }
+
       if (FLAGS_acquire_snapshot_one_in > 0 &&
           thread->rand.Uniform(FLAGS_acquire_snapshot_one_in) == 0) {
         auto snapshot = db_->GetSnapshot();
@@ -1960,9 +2013,26 @@ class StressTest {
         // will later read the same key before releasing the snapshot and verify
         // that the results are the same.
         auto status_at = db_->Get(ropt, column_family, key, &value_at);
+        std::vector<bool> *key_vec = nullptr;
+
+        if (FLAGS_compare_full_db_state_snapshot &&
+            (thread->tid == 0)) {
+          key_vec = new std::vector<bool>(FLAGS_max_key);
+          // When `prefix_extractor` is set, seeking to beginning and scanning
+          // across prefixes are only supported with `total_order_seek` set.
+          ropt.total_order_seek = true;
+          std::unique_ptr<Iterator> iterator(db_->NewIterator(ropt));
+          for (iterator->SeekToFirst(); iterator->Valid(); iterator->Next()) {
+            uint64_t key_val;
+            if (GetIntVal(iterator->key().ToString(), &key_val)) {
+              (*key_vec)[key_val] = true;
+            }
+          }
+        }
+
         ThreadState::SnapshotState snap_state = {
             snapshot, rand_column_family, column_family->GetName(),
-            keystr,   status_at,          value_at};
+            keystr,   status_at,          value_at, key_vec};
         thread->snapshot_queue.emplace(
             std::min(FLAGS_ops_per_thread - 1, i + FLAGS_snapshot_hold_ops),
             snap_state);
@@ -1980,6 +2050,7 @@ class StressTest {
           VerificationAbort(shared, "Snapshot gave inconsistent state", s);
         }
         db_->ReleaseSnapshot(snap_state.snapshot);
+        delete snap_state.key_vec;
         thread->snapshot_queue.pop();
       }
 
@@ -1997,14 +2068,14 @@ class StressTest {
       } else if (prefixBound <= prob_op && prob_op < writeBound) {
         // OPERATION write
         TestPut(thread, write_opts, read_opts, rand_column_families, rand_keys,
-            value, lock);
+                value, lock);
       } else if (writeBound <= prob_op && prob_op < delBound) {
         // OPERATION delete
         TestDelete(thread, write_opts, rand_column_families, rand_keys, lock);
       } else if (delBound <= prob_op && prob_op < delRangeBound) {
         // OPERATION delete range
         TestDeleteRange(thread, write_opts, rand_column_families, rand_keys,
-            lock);
+                        lock);
       } else {
         // OPERATION iterate
         TestIterate(thread, read_opts, rand_column_families, rand_keys);
@@ -2022,8 +2093,7 @@ class StressTest {
   virtual bool ShouldAcquireMutexOnKey() const { return false; }
 
   virtual std::vector<int> GenerateColumnFamilies(
-      const int /* num_column_families */,
-      int rand_column_family) const {
+      const int /* num_column_families */, int rand_column_family) const {
     return {rand_column_family};
   }
 
@@ -2121,6 +2191,106 @@ class StressTest {
     return s;
   }
 
+#ifdef ROCKSDB_LITE
+  virtual Status TestBackupRestore(
+      ThreadState* /* thread */,
+      const std::vector<int>& /* rand_column_families */,
+      const std::vector<int64_t>& /* rand_keys */) {
+    assert(false);
+    fprintf(stderr,
+            "RocksDB lite does not support "
+            "TestBackupRestore\n");
+    std::terminate();
+  }
+#else  // ROCKSDB_LITE
+  virtual Status TestBackupRestore(ThreadState* thread,
+                                   const std::vector<int>& rand_column_families,
+                                   const std::vector<int64_t>& rand_keys) {
+    // Note the column families chosen by `rand_column_families` cannot be
+    // dropped while the locks for `rand_keys` are held. So we should not have
+    // to worry about accessing those column families throughout this function.
+    assert(rand_column_families.size() == rand_keys.size());
+    std::string backup_dir = FLAGS_db + "/.backup" + ToString(thread->tid);
+    std::string restore_dir = FLAGS_db + "/.restore" + ToString(thread->tid);
+    BackupableDBOptions backup_opts(backup_dir);
+    BackupEngine* backup_engine = nullptr;
+    Status s = BackupEngine::Open(FLAGS_env, backup_opts, &backup_engine);
+    if (s.ok()) {
+      s = backup_engine->CreateNewBackup(db_);
+    }
+    if (s.ok()) {
+      delete backup_engine;
+      backup_engine = nullptr;
+      s = BackupEngine::Open(FLAGS_env, backup_opts, &backup_engine);
+    }
+    if (s.ok()) {
+      s = backup_engine->RestoreDBFromLatestBackup(restore_dir /* db_dir */,
+                                                   restore_dir /* wal_dir */);
+    }
+    if (s.ok()) {
+      s = backup_engine->PurgeOldBackups(0 /* num_backups_to_keep */);
+    }
+    DB* restored_db = nullptr;
+    std::vector<ColumnFamilyHandle*> restored_cf_handles;
+    if (s.ok()) {
+      Options restore_options(options_);
+      restore_options.listeners.clear();
+      std::vector<ColumnFamilyDescriptor> cf_descriptors;
+      // TODO(ajkr): `column_family_names_` is not safe to access here when
+      // `clear_column_family_one_in != 0`. But we can't easily switch to
+      // `ListColumnFamilies` to get names because it won't necessarily give
+      // the same order as `column_family_names_`.
+      assert(FLAGS_clear_column_family_one_in == 0);
+      for (auto name : column_family_names_) {
+        cf_descriptors.emplace_back(name, ColumnFamilyOptions(restore_options));
+      }
+      s = DB::Open(DBOptions(restore_options), restore_dir, cf_descriptors,
+                   &restored_cf_handles, &restored_db);
+    }
+    // for simplicity, currently only verifies existence/non-existence of a few
+    // keys
+    for (size_t i = 0; s.ok() && i < rand_column_families.size(); ++i) {
+      std::string key_str = Key(rand_keys[i]);
+      Slice key = key_str;
+      std::string restored_value;
+      Status get_status = restored_db->Get(
+          ReadOptions(), restored_cf_handles[rand_column_families[i]], key,
+          &restored_value);
+      bool exists =
+          thread->shared->Exists(rand_column_families[i], rand_keys[i]);
+      if (get_status.ok()) {
+        if (!exists) {
+          s = Status::Corruption(
+              "key exists in restore but not in original db");
+        }
+      } else if (get_status.IsNotFound()) {
+        if (exists) {
+          s = Status::Corruption(
+              "key exists in original db but not in restore");
+        }
+      } else {
+        s = get_status;
+      }
+    }
+    if (backup_engine != nullptr) {
+      delete backup_engine;
+      backup_engine = nullptr;
+    }
+    if (restored_db != nullptr) {
+      for (auto* cf_handle : restored_cf_handles) {
+        restored_db->DestroyColumnFamilyHandle(cf_handle);
+      }
+      delete restored_db;
+      restored_db = nullptr;
+    }
+    if (!s.ok()) {
+      printf("A backup/restore operation failed with: %s\n",
+             s.ToString().c_str());
+    }
+    return s;
+  }
+#endif  // ROCKSDB_LITE
+
   void VerificationAbort(SharedState* shared, std::string msg, Status s) const {
     printf("Verification failed: %s. Status is %s\n", msg.c_str(),
            s.ToString().c_str());
@@ -2140,6 +2310,8 @@ class StressTest {
     fprintf(stdout, "Format version            : %d\n", FLAGS_format_version);
     fprintf(stdout, "TransactionDB             : %s\n",
             FLAGS_use_txn ? "true" : "false");
+    fprintf(stdout, "Atomic flush              : %s\n",
+            FLAGS_atomic_flush ? "true" : "false");
     fprintf(stdout, "Column families           : %d\n", FLAGS_column_families);
     if (!FLAGS_test_batches_snapshots) {
       fprintf(stdout, "Clear CFs one in          : %d\n",
@@ -2223,6 +2395,8 @@ class StressTest {
       block_based_options.block_size = FLAGS_block_size;
       block_based_options.format_version =
           static_cast<uint32_t>(FLAGS_format_version);
+      block_based_options.index_block_restart_interval =
+          static_cast<int32_t>(FLAGS_index_block_restart_interval);
       block_based_options.filter_policy = filter_policy_;
       options_.table_factory.reset(
           NewBlockBasedTableFactory(block_based_options));
@@ -2283,6 +2457,7 @@ class StressTest {
           FLAGS_universal_max_merge_width;
       options_.compaction_options_universal.max_size_amplification_percent =
           FLAGS_universal_max_size_amplification_percent;
+      options_.atomic_flush = FLAGS_atomic_flush;
     } else {
 #ifdef ROCKSDB_LITE
       fprintf(stderr, "--options_file not supported in lite mode\n");
@@ -2514,7 +2689,7 @@ class NonBatchedOpsStressTest : public StressTest {
       }
       if (!thread->rand.OneIn(2)) {
         // Use iterator to verify this range
-        unique_ptr<Iterator> iter(
+        std::unique_ptr<Iterator> iter(
             db_->NewIterator(options, column_families_[cf]));
         iter->Seek(Key(start));
         for (auto i = start; i < end; i++) {
@@ -2653,16 +2828,15 @@ class NonBatchedOpsStressTest : public StressTest {
     }
 
     Iterator* iter = db_->NewIterator(ro_copy, cfh);
-    int64_t count = 0;
+    long count = 0;
     for (iter->Seek(prefix);
         iter->Valid() && iter->key().starts_with(prefix); iter->Next()) {
       ++count;
     }
-    assert(count <=
-        (static_cast<int64_t>(1) << ((8 - FLAGS_prefix_size) * 8)));
+    assert(count <= (static_cast<long>(1) << ((8 - FLAGS_prefix_size) * 8)));
     Status s = iter->status();
     if (iter->status().ok()) {
-      thread->stats.AddPrefixes(1, static_cast<int>(count));
+      thread->stats.AddPrefixes(1, count);
     } else {
       thread->stats.AddErrors(1);
     }
@@ -3192,7 +3366,7 @@ class BatchedOpsStressTest : public StressTest {
       iters[i]->Seek(prefix_slices[i]);
     }
 
-    int count = 0;
+    long count = 0;
     while (iters[0]->Valid() && iters[0]->key().starts_with(prefix_slices[0])) {
       count++;
       std::string values[10];
@@ -3247,6 +3421,274 @@ class BatchedOpsStressTest : public StressTest {
   virtual void VerifyDb(ThreadState* /* thread */) const {}
 };
 
+class AtomicFlushStressTest : public StressTest {
+ public:
+  AtomicFlushStressTest() : batch_id_(0) {}
+
+  virtual ~AtomicFlushStressTest() {}
+
+  virtual Status TestPut(ThreadState* thread, WriteOptions& write_opts,
+                         const ReadOptions& /* read_opts */,
+                         const std::vector<int>& rand_column_families,
+                         const std::vector<int64_t>& rand_keys,
+                         char (&value)[100],
+                         std::unique_ptr<MutexLock>& /* lock */) {
+    std::string key_str = Key(rand_keys[0]);
+    Slice key = key_str;
+    uint64_t value_base = batch_id_.fetch_add(1);
+    size_t sz =
+        GenerateValue(static_cast<uint32_t>(value_base), value, sizeof(value));
+    Slice v(value, sz);
+    WriteBatch batch;
+    for (auto cf : rand_column_families) {
+      ColumnFamilyHandle* cfh = column_families_[cf];
+      if (FLAGS_use_merge) {
+        batch.Merge(cfh, key, v);
+      } else { /* !FLAGS_use_merge */
+        batch.Put(cfh, key, v);
+      }
+    }
+    Status s = db_->Write(write_opts, &batch);
+    if (!s.ok()) {
+      fprintf(stderr, "multi put or merge error: %s\n", s.ToString().c_str());
+      thread->stats.AddErrors(1);
+    } else {
+      auto num = static_cast<long>(rand_column_families.size());
+      thread->stats.AddBytesForWrites(num, (sz + 1) * num);
+    }
+
+    return s;
+  }
+
+  virtual Status TestDelete(ThreadState* thread, WriteOptions& write_opts,
+                            const std::vector<int>& rand_column_families,
+                            const std::vector<int64_t>& rand_keys,
+                            std::unique_ptr<MutexLock>& /* lock */) {
+    std::string key_str = Key(rand_keys[0]);
+    Slice key = key_str;
+    WriteBatch batch;
+    for (auto cf : rand_column_families) {
+      ColumnFamilyHandle* cfh = column_families_[cf];
+      batch.Delete(cfh, key);
+    }
+    Status s = db_->Write(write_opts, &batch);
+    if (!s.ok()) {
+      fprintf(stderr, "multidel error: %s\n", s.ToString().c_str());
+      thread->stats.AddErrors(1);
+    } else {
+      thread->stats.AddDeletes(static_cast<long>(rand_column_families.size()));
+    }
+    return s;
+  }
+
+  virtual Status TestDeleteRange(ThreadState* thread, WriteOptions& write_opts,
+                                 const std::vector<int>& rand_column_families,
+                                 const std::vector<int64_t>& rand_keys,
+                                 std::unique_ptr<MutexLock>& /* lock */) {
+    int64_t rand_key = rand_keys[0];
+    auto shared = thread->shared;
+    int64_t max_key = shared->GetMaxKey();
+    if (rand_key > max_key - FLAGS_range_deletion_width) {
+      rand_key =
+          thread->rand.Next() % (max_key - FLAGS_range_deletion_width + 1);
+    }
+    std::string key_str = Key(rand_key);
+    Slice key = key_str;
+    std::string end_key_str = Key(rand_key + FLAGS_range_deletion_width);
+    Slice end_key = end_key_str;
+    WriteBatch batch;
+    for (auto cf : rand_column_families) {
+      ColumnFamilyHandle* cfh = column_families_[rand_column_families[cf]];
+      batch.DeleteRange(cfh, key, end_key);
+    }
+    Status s = db_->Write(write_opts, &batch);
+    if (!s.ok()) {
+      fprintf(stderr, "multi del range error: %s\n", s.ToString().c_str());
+      thread->stats.AddErrors(1);
+    } else {
+      thread->stats.AddRangeDeletions(
+          static_cast<long>(rand_column_families.size()));
+    }
+    return s;
+  }
+
+  virtual void TestIngestExternalFile(
+      ThreadState* /* thread */,
+      const std::vector<int>& /* rand_column_families */,
+      const std::vector<int64_t>& /* rand_keys */,
+      std::unique_ptr<MutexLock>& /* lock */) {
+    assert(false);
+    fprintf(stderr,
+            "AtomicFlushStressTest does not support TestIngestExternalFile "
+            "because it's not possible to verify the result\n");
+    std::terminate();
+  }
+
+  virtual Status TestGet(ThreadState* thread, const ReadOptions& readoptions,
+                         const std::vector<int>& rand_column_families,
+                         const std::vector<int64_t>& rand_keys) {
+    std::string key_str = Key(rand_keys[0]);
+    Slice key = key_str;
+    auto cfh =
+        column_families_[rand_column_families[thread->rand.Next() %
+                                              rand_column_families.size()]];
+    std::string from_db;
+    Status s = db_->Get(readoptions, cfh, key, &from_db);
+    if (s.ok()) {
+      thread->stats.AddGets(1, 1);
+    } else if (s.IsNotFound()) {
+      thread->stats.AddGets(1, 0);
+    } else {
+      thread->stats.AddErrors(1);
+    }
+    return s;
+  }
+
+  virtual Status TestPrefixScan(ThreadState* thread,
+                                const ReadOptions& readoptions,
+                                const std::vector<int>& rand_column_families,
+                                const std::vector<int64_t>& rand_keys) {
+    std::string key_str = Key(rand_keys[0]);
+    Slice key = key_str;
+    Slice prefix = Slice(key.data(), FLAGS_prefix_size);
+
+    std::string upper_bound;
+    Slice ub_slice;
+    ReadOptions ro_copy = readoptions;
+    if (thread->rand.OneIn(2) && GetNextPrefix(prefix, &upper_bound)) {
+      ub_slice = Slice(upper_bound);
+      ro_copy.iterate_upper_bound = &ub_slice;
+    }
+    auto cfh =
+        column_families_[rand_column_families[thread->rand.Next() %
+                                              rand_column_families.size()]];
+    Iterator* iter = db_->NewIterator(ro_copy, cfh);
+    long count = 0;
+    for (iter->Seek(prefix); iter->Valid() && iter->key().starts_with(prefix);
+         iter->Next()) {
+      ++count;
+    }
+    assert(count <= (static_cast<long>(1) << ((8 - FLAGS_prefix_size) * 8)));
+    Status s = iter->status();
+    if (s.ok()) {
+      thread->stats.AddPrefixes(1, count);
+    } else {
+      thread->stats.AddErrors(1);
+    }
+    delete iter;
+    return s;
+  }
+
+  virtual void VerifyDb(ThreadState* thread) const {
+    ReadOptions options(FLAGS_verify_checksum, true);
+    // We must set total_order_seek to true because we are doing a SeekToFirst
+    // on a column family whose memtables may support (by default) prefix-based
+    // iterator. In this case, NewIterator with options.total_order_seek being
+    // false returns a prefix-based iterator. Calling SeekToFirst using this
+    // iterator causes the iterator to become invalid. That means we cannot
+    // iterate the memtable using this iterator any more, although the memtable
+    // contains the most up-to-date key-values.
+    options.total_order_seek = true;
+    assert(thread != nullptr);
+    auto shared = thread->shared;
+    std::vector<std::unique_ptr<Iterator> > iters(column_families_.size());
+    for (size_t i = 0; i != column_families_.size(); ++i) {
+      iters[i].reset(db_->NewIterator(options, column_families_[i]));
+    }
+    for (auto& iter : iters) {
+      iter->SeekToFirst();
+    }
+    size_t num = column_families_.size();
+    assert(num == iters.size());
+    std::vector<Status> statuses(num, Status::OK());
+    do {
+      size_t valid_cnt = 0;
+      size_t idx = 0;
+      for (auto& iter : iters) {
+        if (iter->Valid()) {
+          ++valid_cnt;
+        } else {
+          statuses[idx] = iter->status();
+        }
+        ++idx;
+      }
+      if (valid_cnt == 0) {
+        Status status;
+        for (size_t i = 0; i != num; ++i) {
+          const auto& s = statuses[i];
+          if (!s.ok()) {
+            status = s;
+            fprintf(stderr, "Iterator on cf %s has error: %s\n",
+                    column_families_[i]->GetName().c_str(),
+                    s.ToString().c_str());
+            shared->SetVerificationFailure();
+          }
+        }
+        if (status.ok()) {
+          fprintf(stdout, "Finished scanning all column families.\n");
+        }
+        break;
+      } else if (valid_cnt != iters.size()) {
+        for (size_t i = 0; i != num; ++i) {
+          if (!iters[i]->Valid()) {
+            if (statuses[i].ok()) {
+              fprintf(stderr, "Finished scanning cf %s\n",
+                      column_families_[i]->GetName().c_str());
+            } else {
+              fprintf(stderr, "Iterator on cf %s has error: %s\n",
+                      column_families_[i]->GetName().c_str(),
+                      statuses[i].ToString().c_str());
+            }
+          } else {
+            fprintf(stderr, "cf %s has remaining data to scan\n",
+                    column_families_[i]->GetName().c_str());
+          }
+        }
+        shared->SetVerificationFailure();
+        break;
+      }
+      // If the program reaches here, then all column families' iterators are
+      // still valid.
+      Slice key;
+      Slice value;
+      for (size_t i = 0; i != num; ++i) {
+        if (i == 0) {
+          key = iters[i]->key();
+          value = iters[i]->value();
+        } else {
+          if (key.compare(iters[i]->key()) != 0) {
+            fprintf(stderr, "Verification failed\n");
+            fprintf(stderr, "cf%s: %s => %s\n",
+                    column_families_[0]->GetName().c_str(),
+                    key.ToString(true /* hex */).c_str(),
+                    value.ToString(/* hex */).c_str());
+            fprintf(stderr, "cf%s: %s => %s\n",
+                    column_families_[i]->GetName().c_str(),
+                    iters[i]->key().ToString(true /* hex */).c_str(),
+                    iters[i]->value().ToString(true /* hex */).c_str());
+            shared->SetVerificationFailure();
+          }
+        }
+      }
+      for (auto& iter : iters) {
+        iter->Next();
+      }
+    } while (true);
+  }
+
+  virtual std::vector<int> GenerateColumnFamilies(
+      const int /* num_column_families */, int /* rand_column_family */) const {
+    std::vector<int> ret;
+    int num = static_cast<int>(column_families_.size());
+    int k = 0;
+    std::generate_n(back_inserter(ret), num, [&k]() -> int { return k++; });
+    return ret;
+  }
+
+ private:
+  std::atomic<int64_t> batch_id_;
+};
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
@@ -3335,6 +3777,11 @@ int main(int argc, char** argv) {
             "Error: nooverwritepercent must be 0 when using file ingestion\n");
     exit(1);
   }
+  if (FLAGS_clear_column_family_one_in > 0 && FLAGS_backup_one_in > 0) {
+    fprintf(stderr,
+            "Error: clear_column_family_one_in must be 0 when using backup\n");
+    exit(1);
+  }
 
   // Choose a location for the test database if none given with --db=<path>
   if (FLAGS_db.empty()) {
@@ -3348,7 +3795,9 @@ int main(int argc, char** argv) {
   rocksdb_kill_prefix_blacklist = SplitString(FLAGS_kill_prefix_blacklist);
 
   std::unique_ptr<rocksdb::StressTest> stress;
-  if (FLAGS_test_batches_snapshots) {
+  if (FLAGS_atomic_flush) {
+    stress.reset(new rocksdb::AtomicFlushStressTest());
+  } else if (FLAGS_test_batches_snapshots) {
     stress.reset(new rocksdb::BatchedOpsStressTest());
   } else {
     stress.reset(new rocksdb::NonBatchedOpsStressTest());
diff --git a/3rdParty/rocksdb/v5.16.X/tools/dbench_monitor b/3rdParty/rocksdb/v5.18.X/tools/dbench_monitor
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/dbench_monitor
rename to 3rdParty/rocksdb/v5.18.X/tools/dbench_monitor
diff --git a/3rdParty/rocksdb/v5.16.X/tools/dump/db_dump_tool.cc b/3rdParty/rocksdb/v5.18.X/tools/dump/db_dump_tool.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/dump/db_dump_tool.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/dump/db_dump_tool.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/dump/rocksdb_dump.cc b/3rdParty/rocksdb/v5.18.X/tools/dump/rocksdb_dump.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/dump/rocksdb_dump.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/dump/rocksdb_dump.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/dump/rocksdb_undump.cc b/3rdParty/rocksdb/v5.18.X/tools/dump/rocksdb_undump.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/dump/rocksdb_undump.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/dump/rocksdb_undump.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/generate_random_db.sh b/3rdParty/rocksdb/v5.18.X/tools/generate_random_db.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/generate_random_db.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/generate_random_db.sh
diff --git a/3rdParty/rocksdb/v5.18.X/tools/ingest_external_sst.sh b/3rdParty/rocksdb/v5.18.X/tools/ingest_external_sst.sh
new file mode 100755
index 0000000000..54ca3db3b3
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/tools/ingest_external_sst.sh
@@ -0,0 +1,17 @@
+#!/usr/bin/env bash
+#
+#
+
+if [ "$#" -lt 2 ]; then
+  echo "usage: $BASH_SOURCE <DB Path> <External SST Dir>"
+  exit 1
+fi
+
+db_dir=$1
+external_sst_dir=$2
+
+for f in `find $external_sst_dir -name extern_sst*`
+do
+  echo == Ingesting external SST file $f to DB at $db_dir
+  ./ldb --db=$db_dir --create_if_missing ingest_extern_sst $f
+done
diff --git a/3rdParty/rocksdb/v5.16.X/tools/ldb.cc b/3rdParty/rocksdb/v5.18.X/tools/ldb.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/ldb.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/ldb.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/ldb_cmd.cc b/3rdParty/rocksdb/v5.18.X/tools/ldb_cmd.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/tools/ldb_cmd.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/ldb_cmd.cc
index e0e24a73de..997718ef28 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/ldb_cmd.cc
+++ b/3rdParty/rocksdb/v5.18.X/tools/ldb_cmd.cc
@@ -1964,11 +1964,11 @@ void DumpWalFile(std::string wal_file, bool print_header, bool print_values,
                  bool is_write_committed, LDBCommandExecuteResult* exec_state) {
   Env* env_ = Env::Default();
   EnvOptions soptions;
-  unique_ptr<SequentialFileReader> wal_file_reader;
+  std::unique_ptr<SequentialFileReader> wal_file_reader;
 
   Status status;
   {
-    unique_ptr<SequentialFile> file;
+    std::unique_ptr<SequentialFile> file;
     status = env_->NewSequentialFile(wal_file, &file, soptions);
     if (status.ok()) {
       wal_file_reader.reset(
@@ -1999,7 +1999,8 @@ void DumpWalFile(std::string wal_file, bool print_header, bool print_values,
     }
     DBOptions db_options;
     log::Reader reader(db_options.info_log, std::move(wal_file_reader),
-                       &reporter, true, 0, log_number);
+                       &reporter, true /* checksum */, log_number,
+                       false /* retry_after_eof */);
     std::string scratch;
     WriteBatch batch;
     Slice record;
@@ -2844,8 +2845,8 @@ void DumpSstFile(std::string filename, bool output_hex, bool show_properties) {
     return;
   }
   // no verification
-  rocksdb::SstFileReader reader(filename, false, output_hex);
-  Status st = reader.ReadSequential(true, std::numeric_limits<uint64_t>::max(), false,  // has_from
+  rocksdb::SstFileDumper dumper(filename, false, output_hex);
+  Status st = dumper.ReadSequential(true, std::numeric_limits<uint64_t>::max(), false,  // has_from
                                     from_key, false,  // has_to
                                     to_key);
   if (!st.ok()) {
@@ -2859,21 +2860,17 @@ void DumpSstFile(std::string filename, bool output_hex, bool show_properties) {
 
     std::shared_ptr<const rocksdb::TableProperties>
         table_properties_from_reader;
-    st = reader.ReadTableProperties(&table_properties_from_reader);
+    st = dumper.ReadTableProperties(&table_properties_from_reader);
     if (!st.ok()) {
       std::cerr << filename << ": " << st.ToString()
                 << ". Try to use initial table properties" << std::endl;
-      table_properties = reader.GetInitTableProperties();
+      table_properties = dumper.GetInitTableProperties();
     } else {
       table_properties = table_properties_from_reader.get();
     }
     if (table_properties != nullptr) {
       std::cout << std::endl << "Table Properties:" << std::endl;
       std::cout << table_properties->ToString("\n") << std::endl;
-      std::cout << "# deleted keys: "
-                << rocksdb::GetDeletedKeys(
-                       table_properties->user_collected_properties)
-                << std::endl;
     }
   }
 }
diff --git a/3rdParty/rocksdb/v5.16.X/tools/ldb_cmd_impl.h b/3rdParty/rocksdb/v5.18.X/tools/ldb_cmd_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/ldb_cmd_impl.h
rename to 3rdParty/rocksdb/v5.18.X/tools/ldb_cmd_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/tools/ldb_cmd_test.cc b/3rdParty/rocksdb/v5.18.X/tools/ldb_cmd_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/ldb_cmd_test.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/ldb_cmd_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/ldb_test.py b/3rdParty/rocksdb/v5.18.X/tools/ldb_test.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/ldb_test.py
rename to 3rdParty/rocksdb/v5.18.X/tools/ldb_test.py
diff --git a/3rdParty/rocksdb/v5.16.X/tools/ldb_tool.cc b/3rdParty/rocksdb/v5.18.X/tools/ldb_tool.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/ldb_tool.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/ldb_tool.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/pflag b/3rdParty/rocksdb/v5.18.X/tools/pflag
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/pflag
rename to 3rdParty/rocksdb/v5.18.X/tools/pflag
diff --git a/3rdParty/rocksdb/v5.16.X/tools/rdb/.gitignore b/3rdParty/rocksdb/v5.18.X/tools/rdb/.gitignore
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/rdb/.gitignore
rename to 3rdParty/rocksdb/v5.18.X/tools/rdb/.gitignore
diff --git a/3rdParty/rocksdb/v5.16.X/tools/rdb/API.md b/3rdParty/rocksdb/v5.18.X/tools/rdb/API.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/rdb/API.md
rename to 3rdParty/rocksdb/v5.18.X/tools/rdb/API.md
diff --git a/3rdParty/rocksdb/v5.16.X/tools/rdb/README.md b/3rdParty/rocksdb/v5.18.X/tools/rdb/README.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/rdb/README.md
rename to 3rdParty/rocksdb/v5.18.X/tools/rdb/README.md
diff --git a/3rdParty/rocksdb/v5.16.X/tools/rdb/binding.gyp b/3rdParty/rocksdb/v5.18.X/tools/rdb/binding.gyp
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/rdb/binding.gyp
rename to 3rdParty/rocksdb/v5.18.X/tools/rdb/binding.gyp
diff --git a/3rdParty/rocksdb/v5.16.X/tools/rdb/db_wrapper.cc b/3rdParty/rocksdb/v5.18.X/tools/rdb/db_wrapper.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/rdb/db_wrapper.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/rdb/db_wrapper.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/rdb/db_wrapper.h b/3rdParty/rocksdb/v5.18.X/tools/rdb/db_wrapper.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/rdb/db_wrapper.h
rename to 3rdParty/rocksdb/v5.18.X/tools/rdb/db_wrapper.h
diff --git a/3rdParty/rocksdb/v5.16.X/tools/rdb/rdb b/3rdParty/rocksdb/v5.18.X/tools/rdb/rdb
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/rdb/rdb
rename to 3rdParty/rocksdb/v5.18.X/tools/rdb/rdb
diff --git a/3rdParty/rocksdb/v5.16.X/tools/rdb/rdb.cc b/3rdParty/rocksdb/v5.18.X/tools/rdb/rdb.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/rdb/rdb.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/rdb/rdb.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/rdb/unit_test.js b/3rdParty/rocksdb/v5.18.X/tools/rdb/unit_test.js
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/rdb/unit_test.js
rename to 3rdParty/rocksdb/v5.18.X/tools/rdb/unit_test.js
diff --git a/3rdParty/rocksdb/v5.16.X/tools/reduce_levels_test.cc b/3rdParty/rocksdb/v5.18.X/tools/reduce_levels_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/reduce_levels_test.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/reduce_levels_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/regression_test.sh b/3rdParty/rocksdb/v5.18.X/tools/regression_test.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/regression_test.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/regression_test.sh
diff --git a/3rdParty/rocksdb/v5.16.X/tools/report_lite_binary_size.sh b/3rdParty/rocksdb/v5.18.X/tools/report_lite_binary_size.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/report_lite_binary_size.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/report_lite_binary_size.sh
diff --git a/3rdParty/rocksdb/v5.16.X/tools/rocksdb_dump_test.sh b/3rdParty/rocksdb/v5.18.X/tools/rocksdb_dump_test.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/rocksdb_dump_test.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/rocksdb_dump_test.sh
diff --git a/3rdParty/rocksdb/v5.16.X/tools/run_flash_bench.sh b/3rdParty/rocksdb/v5.18.X/tools/run_flash_bench.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/run_flash_bench.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/run_flash_bench.sh
diff --git a/3rdParty/rocksdb/v5.16.X/tools/run_leveldb.sh b/3rdParty/rocksdb/v5.18.X/tools/run_leveldb.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/run_leveldb.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/run_leveldb.sh
diff --git a/3rdParty/rocksdb/v5.16.X/tools/sample-dump.dmp b/3rdParty/rocksdb/v5.18.X/tools/sample-dump.dmp
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/sample-dump.dmp
rename to 3rdParty/rocksdb/v5.18.X/tools/sample-dump.dmp
diff --git a/3rdParty/rocksdb/v5.16.X/tools/sst_dump.cc b/3rdParty/rocksdb/v5.18.X/tools/sst_dump.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/sst_dump.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/sst_dump.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/sst_dump_test.cc b/3rdParty/rocksdb/v5.18.X/tools/sst_dump_test.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/tools/sst_dump_test.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/sst_dump_test.cc
index 17b59fd773..9032123cc6 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/sst_dump_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/tools/sst_dump_test.cc
@@ -43,7 +43,7 @@ void createSST(const std::string& file_name,
   std::shared_ptr<rocksdb::TableFactory> tf;
   tf.reset(new rocksdb::BlockBasedTableFactory(table_options));
 
-  unique_ptr<WritableFile> file;
+  std::unique_ptr<WritableFile> file;
   Env* env = Env::Default();
   EnvOptions env_options;
   ReadOptions read_options;
@@ -51,7 +51,7 @@ void createSST(const std::string& file_name,
   const ImmutableCFOptions imoptions(opts);
   const MutableCFOptions moptions(opts);
   rocksdb::InternalKeyComparator ikc(opts.comparator);
-  unique_ptr<TableBuilder> tb;
+  std::unique_ptr<TableBuilder> tb;
 
   ASSERT_OK(env->NewWritableFile(file_name, &file, env_options));
 
@@ -59,7 +59,7 @@ void createSST(const std::string& file_name,
   std::vector<std::unique_ptr<IntTblPropCollectorFactory> >
       int_tbl_prop_collector_factories;
   std::unique_ptr<WritableFileWriter> file_writer(
-      new WritableFileWriter(std::move(file), EnvOptions()));
+      new WritableFileWriter(std::move(file), file_name, EnvOptions()));
   std::string column_family_name;
   int unknown_level = -1;
   tb.reset(opts.table_factory->NewTableBuilder(
@@ -92,12 +92,11 @@ void cleanup(const std::string& file_name) {
 // Test for sst dump tool "raw" mode
 class SSTDumpToolTest : public testing::Test {
   std::string testDir_;
-public:
+
+ public:
   BlockBasedTableOptions table_options_;
 
-  SSTDumpToolTest() {
-    testDir_ = test::TmpDir();
-  }
+  SSTDumpToolTest() { testDir_ = test::TmpDir(); }
 
   ~SSTDumpToolTest() {}
 
@@ -107,9 +106,9 @@ public:
     return path;
   }
 
-  template<std::size_t N>
+  template <std::size_t N>
   void PopulateCommandArgs(const std::string& file_path, const char* command,
-    char* (&usage)[N]) const {
+                           char* (&usage)[N]) const {
     for (int i = 0; i < static_cast<int>(N); ++i) {
       usage[i] = new char[optLength];
     }
diff --git a/3rdParty/rocksdb/v5.16.X/tools/sst_dump_tool.cc b/3rdParty/rocksdb/v5.18.X/tools/sst_dump_tool.cc
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/tools/sst_dump_tool.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/sst_dump_tool.cc
index f7a097a3a8..25699777e8 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/sst_dump_tool.cc
+++ b/3rdParty/rocksdb/v5.18.X/tools/sst_dump_tool.cc
@@ -43,7 +43,7 @@
 
 namespace rocksdb {
 
-SstFileReader::SstFileReader(const std::string& file_path, bool verify_checksum,
+SstFileDumper::SstFileDumper(const std::string& file_path, bool verify_checksum,
                              bool output_hex)
     : file_name_(file_path),
       read_num_(0),
@@ -74,7 +74,7 @@ static const std::vector<std::pair<CompressionType, const char*>>
         {CompressionType::kXpressCompression, "kXpressCompression"},
         {CompressionType::kZSTD, "kZSTD"}};
 
-Status SstFileReader::GetTableReader(const std::string& file_path) {
+Status SstFileDumper::GetTableReader(const std::string& file_path) {
   // Warning about 'magic_number' being uninitialized shows up only in UBsan
   // builds. Though access is guarded by 's.ok()' checks, fix the issue to
   // avoid any warnings.
@@ -83,7 +83,7 @@ Status SstFileReader::GetTableReader(const std::string& file_path) {
   // read table magic number
   Footer footer;
 
-  unique_ptr<RandomAccessFile> file;
+  std::unique_ptr<RandomAccessFile> file;
   uint64_t file_size = 0;
   Status s = options_.env->NewRandomAccessFile(file_path, &file, soptions_);
   if (s.ok()) {
@@ -123,10 +123,10 @@ Status SstFileReader::GetTableReader(const std::string& file_path) {
   return s;
 }
 
-Status SstFileReader::NewTableReader(
+Status SstFileDumper::NewTableReader(
     const ImmutableCFOptions& /*ioptions*/, const EnvOptions& /*soptions*/,
     const InternalKeyComparator& /*internal_comparator*/, uint64_t file_size,
-    unique_ptr<TableReader>* /*table_reader*/) {
+    std::unique_ptr<TableReader>* /*table_reader*/) {
   // We need to turn off pre-fetching of index and filter nodes for
   // BlockBasedTable
   if (BlockBasedTableFactory::kName == options_.table_factory->Name()) {
@@ -143,12 +143,12 @@ Status SstFileReader::NewTableReader(
       std::move(file_), file_size, &table_reader_);
 }
 
-Status SstFileReader::VerifyChecksum() {
+Status SstFileDumper::VerifyChecksum() {
   return table_reader_->VerifyChecksum();
 }
 
-Status SstFileReader::DumpTable(const std::string& out_filename) {
-  unique_ptr<WritableFile> out_file;
+Status SstFileDumper::DumpTable(const std::string& out_filename) {
+  std::unique_ptr<WritableFile> out_file;
   Env* env = Env::Default();
   env->NewWritableFile(out_filename, &out_file, soptions_);
   Status s = table_reader_->DumpTable(out_file.get(),
@@ -157,22 +157,23 @@ Status SstFileReader::DumpTable(const std::string& out_filename) {
   return s;
 }
 
-uint64_t SstFileReader::CalculateCompressedTableSize(
+uint64_t SstFileDumper::CalculateCompressedTableSize(
     const TableBuilderOptions& tb_options, size_t block_size) {
-  unique_ptr<WritableFile> out_file;
-  unique_ptr<Env> env(NewMemEnv(Env::Default()));
+  std::unique_ptr<WritableFile> out_file;
+  std::unique_ptr<Env> env(NewMemEnv(Env::Default()));
   env->NewWritableFile(testFileName, &out_file, soptions_);
-  unique_ptr<WritableFileWriter> dest_writer;
-  dest_writer.reset(new WritableFileWriter(std::move(out_file), soptions_));
+  std::unique_ptr<WritableFileWriter> dest_writer;
+  dest_writer.reset(
+      new WritableFileWriter(std::move(out_file), testFileName, soptions_));
   BlockBasedTableOptions table_options;
   table_options.block_size = block_size;
   BlockBasedTableFactory block_based_tf(table_options);
-  unique_ptr<TableBuilder> table_builder;
+  std::unique_ptr<TableBuilder> table_builder;
   table_builder.reset(block_based_tf.NewTableBuilder(
       tb_options,
       TablePropertiesCollectorFactory::Context::kUnknownColumnFamily,
       dest_writer.get()));
-  unique_ptr<InternalIterator> iter(table_reader_->NewIterator(
+  std::unique_ptr<InternalIterator> iter(table_reader_->NewIterator(
       ReadOptions(), moptions_.prefix_extractor.get()));
   for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
     if (!iter->status().ok()) {
@@ -191,7 +192,7 @@ uint64_t SstFileReader::CalculateCompressedTableSize(
   return size;
 }
 
-int SstFileReader::ShowAllCompressionSizes(
+int SstFileDumper::ShowAllCompressionSizes(
     size_t block_size,
     const std::vector<std::pair<CompressionType, const char*>>&
         compression_types) {
@@ -225,7 +226,7 @@ int SstFileReader::ShowAllCompressionSizes(
   return 0;
 }
 
-Status SstFileReader::ReadTableProperties(uint64_t table_magic_number,
+Status SstFileDumper::ReadTableProperties(uint64_t table_magic_number,
                                           RandomAccessFileReader* file,
                                           uint64_t file_size) {
   TableProperties* table_properties = nullptr;
@@ -239,7 +240,7 @@ Status SstFileReader::ReadTableProperties(uint64_t table_magic_number,
   return s;
 }
 
-Status SstFileReader::SetTableOptionsByMagicNumber(
+Status SstFileDumper::SetTableOptionsByMagicNumber(
     uint64_t table_magic_number) {
   assert(table_properties_);
   if (table_magic_number == kBlockBasedTableMagicNumber ||
@@ -282,7 +283,7 @@ Status SstFileReader::SetTableOptionsByMagicNumber(
   return Status::OK();
 }
 
-Status SstFileReader::SetOldTableOptions() {
+Status SstFileDumper::SetOldTableOptions() {
   assert(table_properties_ == nullptr);
   options_.table_factory = std::make_shared<BlockBasedTableFactory>();
   fprintf(stdout, "Sst file format: block-based(old version)\n");
@@ -290,7 +291,7 @@ Status SstFileReader::SetOldTableOptions() {
   return Status::OK();
 }
 
-Status SstFileReader::ReadSequential(bool print_kv, uint64_t read_num,
+Status SstFileDumper::ReadSequential(bool print_kv, uint64_t read_num,
                                      bool has_from, const std::string& from_key,
                                      bool has_to, const std::string& to_key,
                                      bool use_from_as_prefix) {
@@ -347,7 +348,7 @@ Status SstFileReader::ReadSequential(bool print_kv, uint64_t read_num,
   return ret;
 }
 
-Status SstFileReader::ReadTableProperties(
+Status SstFileDumper::ReadTableProperties(
     std::shared_ptr<const TableProperties>* table_properties) {
   if (!table_reader_) {
     return init_result_;
@@ -569,16 +570,16 @@ int SSTDumpTool::Run(int argc, char** argv) {
       filename = std::string(dir_or_file) + "/" + filename;
     }
 
-    rocksdb::SstFileReader reader(filename, verify_checksum,
+    rocksdb::SstFileDumper dumper(filename, verify_checksum,
                                   output_hex);
-    if (!reader.getStatus().ok()) {
+    if (!dumper.getStatus().ok()) {
       fprintf(stderr, "%s: %s\n", filename.c_str(),
-              reader.getStatus().ToString().c_str());
+              dumper.getStatus().ToString().c_str());
       continue;
     }
 
     if (command == "recompress") {
-      reader.ShowAllCompressionSizes(
+      dumper.ShowAllCompressionSizes(
           set_block_size ? block_size : 16384,
           compression_types.empty() ? kCompressions : compression_types);
       return 0;
@@ -588,7 +589,7 @@ int SSTDumpTool::Run(int argc, char** argv) {
       std::string out_filename = filename.substr(0, filename.length() - 4);
       out_filename.append("_dump.txt");
 
-      st = reader.DumpTable(out_filename);
+      st = dumper.DumpTable(out_filename);
       if (!st.ok()) {
         fprintf(stderr, "%s: %s\n", filename.c_str(), st.ToString().c_str());
         exit(1);
@@ -600,7 +601,7 @@ int SSTDumpTool::Run(int argc, char** argv) {
 
     // scan all files in give file path.
     if (command == "" || command == "scan" || command == "check") {
-      st = reader.ReadSequential(
+      st = dumper.ReadSequential(
           command == "scan", read_num > 0 ? (read_num - total_read) : read_num,
           has_from || use_from_as_prefix, from_key, has_to, to_key,
           use_from_as_prefix);
@@ -608,14 +609,14 @@ int SSTDumpTool::Run(int argc, char** argv) {
         fprintf(stderr, "%s: %s\n", filename.c_str(),
             st.ToString().c_str());
       }
-      total_read += reader.GetReadNumber();
+      total_read += dumper.GetReadNumber();
       if (read_num > 0 && total_read > read_num) {
         break;
       }
     }
 
     if (command == "verify") {
-      st = reader.VerifyChecksum();
+      st = dumper.VerifyChecksum();
       if (!st.ok()) {
         fprintf(stderr, "%s is corrupted: %s\n", filename.c_str(),
                 st.ToString().c_str());
@@ -630,11 +631,11 @@ int SSTDumpTool::Run(int argc, char** argv) {
 
       std::shared_ptr<const rocksdb::TableProperties>
           table_properties_from_reader;
-      st = reader.ReadTableProperties(&table_properties_from_reader);
+      st = dumper.ReadTableProperties(&table_properties_from_reader);
       if (!st.ok()) {
         fprintf(stderr, "%s: %s\n", filename.c_str(), st.ToString().c_str());
         fprintf(stderr, "Try to use initial table properties\n");
-        table_properties = reader.GetInitTableProperties();
+        table_properties = dumper.GetInitTableProperties();
       } else {
         table_properties = table_properties_from_reader.get();
       }
@@ -645,19 +646,6 @@ int SSTDumpTool::Run(int argc, char** argv) {
                   "------------------------------\n"
                   "  %s",
                   table_properties->ToString("\n  ", ": ").c_str());
-          fprintf(stdout, "# deleted keys: %" PRIu64 "\n",
-                  rocksdb::GetDeletedKeys(
-                      table_properties->user_collected_properties));
-
-          bool property_present;
-          uint64_t merge_operands = rocksdb::GetMergeOperands(
-              table_properties->user_collected_properties, &property_present);
-          if (property_present) {
-            fprintf(stdout, "  # merge operands: %" PRIu64 "\n",
-                    merge_operands);
-          } else {
-            fprintf(stdout, "  # merge operands: UNKNOWN\n");
-          }
         }
         total_num_files += 1;
         total_num_data_blocks += table_properties->num_data_blocks;
diff --git a/3rdParty/rocksdb/v5.16.X/tools/sst_dump_tool_imp.h b/3rdParty/rocksdb/v5.18.X/tools/sst_dump_tool_imp.h
similarity index 89%
rename from 3rdParty/rocksdb/v5.16.X/tools/sst_dump_tool_imp.h
rename to 3rdParty/rocksdb/v5.18.X/tools/sst_dump_tool_imp.h
index ca60dd93c9..9e83d8d040 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/sst_dump_tool_imp.h
+++ b/3rdParty/rocksdb/v5.18.X/tools/sst_dump_tool_imp.h
@@ -15,9 +15,9 @@
 
 namespace rocksdb {
 
-class SstFileReader {
+class SstFileDumper {
  public:
-  explicit SstFileReader(const std::string& file_name, bool verify_checksum,
+  explicit SstFileDumper(const std::string& file_name, bool verify_checksum,
                          bool output_hex);
 
   Status ReadSequential(bool print_kv, uint64_t read_num, bool has_from,
@@ -57,7 +57,7 @@ class SstFileReader {
                         const EnvOptions& soptions,
                         const InternalKeyComparator& internal_comparator,
                         uint64_t file_size,
-                        unique_ptr<TableReader>* table_reader);
+                        std::unique_ptr<TableReader>* table_reader);
 
   std::string file_name_;
   uint64_t read_num_;
@@ -70,13 +70,13 @@ class SstFileReader {
   Options options_;
 
   Status init_result_;
-  unique_ptr<TableReader> table_reader_;
-  unique_ptr<RandomAccessFileReader> file_;
+  std::unique_ptr<TableReader> table_reader_;
+  std::unique_ptr<RandomAccessFileReader> file_;
 
   const ImmutableCFOptions ioptions_;
   const MutableCFOptions moptions_;
   InternalKeyComparator internal_comparator_;
-  unique_ptr<TableProperties> table_properties_;
+  std::unique_ptr<TableProperties> table_properties_;
 };
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/tools/trace_analyzer.cc b/3rdParty/rocksdb/v5.18.X/tools/trace_analyzer.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/trace_analyzer.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/trace_analyzer.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/trace_analyzer_test.cc b/3rdParty/rocksdb/v5.18.X/tools/trace_analyzer_test.cc
similarity index 75%
rename from 3rdParty/rocksdb/v5.16.X/tools/trace_analyzer_test.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/trace_analyzer_test.cc
index 49cd31ba3b..768f789cc8 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/trace_analyzer_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/tools/trace_analyzer_test.cc
@@ -37,7 +37,7 @@ namespace rocksdb {
 namespace {
 static const int kMaxArgCount = 100;
 static const size_t kArgBufferSize = 100000;
-}
+}  // namespace
 
 // The helper functions for the test
 class TraceAnalyzerTest : public testing::Test {
@@ -62,6 +62,7 @@ class TraceAnalyzerTest : public testing::Test {
     DB* db_ = nullptr;
     std::string value;
     std::unique_ptr<TraceWriter> trace_writer;
+    Iterator* single_iter = nullptr;
 
     ASSERT_OK(
         NewFileTraceWriter(env_, env_options_, trace_path, &trace_writer));
@@ -77,7 +78,12 @@ class TraceAnalyzerTest : public testing::Test {
     ASSERT_OK(db_->Write(wo, &batch));
 
     ASSERT_OK(db_->Get(ro, "a", &value));
+    single_iter = db_->NewIterator(ro);
+    single_iter->Seek("a");
+    single_iter->SeekForPrev("b");
+    delete single_iter;
     std::this_thread::sleep_for (std::chrono::seconds(1));
+
     db_->Get(ro, "g", &value);
 
     ASSERT_OK(db_->EndTrace());
@@ -141,6 +147,30 @@ class TraceAnalyzerTest : public testing::Test {
     return;
   }
 
+  void AnalyzeTrace(std::vector<std::string>& paras_diff,
+                    std::string output_path, std::string trace_path) {
+    std::vector<std::string> paras = {"./trace_analyzer",
+                                      "-convert_to_human_readable_trace",
+                                      "-output_key_stats",
+                                      "-output_access_count_stats",
+                                      "-output_prefix=test",
+                                      "-output_prefix_cut=1",
+                                      "-output_time_series",
+                                      "-output_value_distribution",
+                                      "-output_qps_stats",
+                                      "-no_key",
+                                      "-no_print"};
+    for (auto& para : paras_diff) {
+      paras.push_back(para);
+    }
+    Status s = env_->FileExists(trace_path);
+    if (!s.ok()) {
+      GenerateTrace(trace_path);
+    }
+    env_->CreateDir(output_path);
+    RunTraceAnalyzer(paras);
+  }
+
   rocksdb::Env* env_;
   EnvOptions env_options_;
   std::string test_path_;
@@ -152,28 +182,11 @@ TEST_F(TraceAnalyzerTest, Get) {
   std::string trace_path = test_path_ + "/trace";
   std::string output_path = test_path_ + "/get";
   std::string file_path;
-  std::vector<std::string> paras = {"./trace_analyzer",
-                                    "-analyze_get",
-                                    "-convert_to_human_readable_trace",
-                                    "-output_key_stats",
-                                    "-output_access_count_stats",
-                                    "-output_prefix=test",
-                                    "-output_prefix_cut=1",
-                                    "-output_time_series",
-                                    "-output_value_distribution",
-                                    "-output_qps_stats",
-                                    "-no_key",
-                                    "-no_print"};
-  Status s = env_->FileExists(trace_path);
-  if (!s.ok()) {
-    GenerateTrace(trace_path);
-  }
+  std::vector<std::string> paras = {"-analyze_get"};
   paras.push_back("-output_dir=" + output_path);
   paras.push_back("-trace_path=" + trace_path);
   paras.push_back("-key_space_dir=" + test_path_);
-
-  env_->CreateDir(output_path);
-  RunTraceAnalyzer(paras);
+  AnalyzeTrace(paras, output_path, trace_path);
 
   // check the key_stats file
   std::vector<std::string> k_stats = {"0 10 0 1 1.000000", "0 10 1 1 1.000000"};
@@ -186,7 +199,8 @@ TEST_F(TraceAnalyzerTest, Get) {
   CheckFileContent(k_dist, file_path, true);
 
   // Check the trace sequence
-  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4", "0", "0"};
+  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4",
+                                         "0", "6", "7", "0"};
   file_path = output_path + "/test-human_readable_trace.txt";
   CheckFileContent(k_sequence, file_path, false);
 
@@ -234,29 +248,11 @@ TEST_F(TraceAnalyzerTest, Put) {
   std::string trace_path = test_path_ + "/trace";
   std::string output_path = test_path_ + "/put";
   std::string file_path;
-  std::vector<std::string> paras = {"./trace_analyzer",
-                                    "-analyze_get",
-                                    "-analyze_put",
-                                    "-convert_to_human_readable_trace",
-                                    "-output_key_stats",
-                                    "-output_access_count_stats",
-                                    "-output_prefix=test",
-                                    "-output_prefix_cut=1",
-                                    "-output_time_series",
-                                    "-output_value_distribution",
-                                    "-output_qps_stats",
-                                    "-no_key",
-                                    "-no_print"};
-  Status s = env_->FileExists(trace_path);
-  if (!s.ok()) {
-    GenerateTrace(trace_path);
-  }
+  std::vector<std::string> paras = {"-analyze_put"};
   paras.push_back("-output_dir=" + output_path);
   paras.push_back("-trace_path=" + trace_path);
   paras.push_back("-key_space_dir=" + test_path_);
-
-  env_->CreateDir(output_path);
-  RunTraceAnalyzer(paras);
+  AnalyzeTrace(paras, output_path, trace_path);
 
   // check the key_stats file
   std::vector<std::string> k_stats = {"0 9 0 1 1.000000"};
@@ -269,7 +265,8 @@ TEST_F(TraceAnalyzerTest, Put) {
   CheckFileContent(k_dist, file_path, true);
 
   // Check the trace sequence
-  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4", "0", "0"};
+  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4",
+                                         "0", "6", "7", "0"};
   file_path = output_path + "/test-human_readable_trace.txt";
   CheckFileContent(k_sequence, file_path, false);
 
@@ -299,7 +296,7 @@ TEST_F(TraceAnalyzerTest, Put) {
   file_path = output_path + "/test-qps_stats.txt";
   CheckFileContent(all_qps, file_path, true);
 
-  // Check the qps of get
+  // Check the qps of Put
   std::vector<std::string> get_qps = {"1"};
   file_path = output_path + "/test-put-0-qps_stats.txt";
   CheckFileContent(get_qps, file_path, true);
@@ -322,30 +319,11 @@ TEST_F(TraceAnalyzerTest, Delete) {
   std::string trace_path = test_path_ + "/trace";
   std::string output_path = test_path_ + "/delete";
   std::string file_path;
-  std::vector<std::string> paras = {"./trace_analyzer",
-                                    "-analyze_get",
-                                    "-analyze_put",
-                                    "-analyze_delete",
-                                    "-convert_to_human_readable_trace",
-                                    "-output_key_stats",
-                                    "-output_access_count_stats",
-                                    "-output_prefix=test",
-                                    "-output_prefix_cut=1",
-                                    "-output_time_series",
-                                    "-output_value_distribution",
-                                    "-output_qps_stats",
-                                    "-no_key",
-                                    "-no_print"};
-  Status s = env_->FileExists(trace_path);
-  if (!s.ok()) {
-    GenerateTrace(trace_path);
-  }
+  std::vector<std::string> paras = {"-analyze_delete"};
   paras.push_back("-output_dir=" + output_path);
   paras.push_back("-trace_path=" + trace_path);
   paras.push_back("-key_space_dir=" + test_path_);
-
-  env_->CreateDir(output_path);
-  RunTraceAnalyzer(paras);
+  AnalyzeTrace(paras, output_path, trace_path);
 
   // check the key_stats file
   std::vector<std::string> k_stats = {"0 0 0 1 1.000000"};
@@ -359,7 +337,8 @@ TEST_F(TraceAnalyzerTest, Delete) {
   CheckFileContent(k_dist, file_path, true);
 
   // Check the trace sequence
-  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4", "0", "0"};
+  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4",
+                                         "0", "6", "7", "0"};
   file_path = output_path + "/test-human_readable_trace.txt";
   CheckFileContent(k_sequence, file_path, false);
 
@@ -389,7 +368,7 @@ TEST_F(TraceAnalyzerTest, Delete) {
   file_path = output_path + "/test-qps_stats.txt";
   CheckFileContent(all_qps, file_path, true);
 
-  // Check the qps of get
+  // Check the qps of Delete
   std::vector<std::string> get_qps = {"1"};
   file_path = output_path + "/test-delete-0-qps_stats.txt";
   CheckFileContent(get_qps, file_path, true);
@@ -406,31 +385,11 @@ TEST_F(TraceAnalyzerTest, Merge) {
   std::string trace_path = test_path_ + "/trace";
   std::string output_path = test_path_ + "/merge";
   std::string file_path;
-  std::vector<std::string> paras = {"./trace_analyzer",
-                                    "-analyze_get",
-                                    "-analyze_put",
-                                    "-analyze_delete",
-                                    "-analyze_merge",
-                                    "-convert_to_human_readable_trace",
-                                    "-output_key_stats",
-                                    "-output_access_count_stats",
-                                    "-output_prefix=test",
-                                    "-output_prefix_cut=1",
-                                    "-output_time_series",
-                                    "-output_value_distribution",
-                                    "-output_qps_stats",
-                                    "-no_key",
-                                    "-no_print"};
-  Status s = env_->FileExists(trace_path);
-  if (!s.ok()) {
-    GenerateTrace(trace_path);
-  }
+  std::vector<std::string> paras = {"-analyze_merge"};
   paras.push_back("-output_dir=" + output_path);
   paras.push_back("-trace_path=" + trace_path);
   paras.push_back("-key_space_dir=" + test_path_);
-
-  env_->CreateDir(output_path);
-  RunTraceAnalyzer(paras);
+  AnalyzeTrace(paras, output_path, trace_path);
 
   // check the key_stats file
   std::vector<std::string> k_stats = {"0 20 0 1 1.000000"};
@@ -443,7 +402,8 @@ TEST_F(TraceAnalyzerTest, Merge) {
   CheckFileContent(k_dist, file_path, true);
 
   // Check the trace sequence
-  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4", "0", "0"};
+  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4",
+                                         "0", "6", "7", "0"};
   file_path = output_path + "/test-human_readable_trace.txt";
   CheckFileContent(k_sequence, file_path, false);
 
@@ -473,7 +433,7 @@ TEST_F(TraceAnalyzerTest, Merge) {
   file_path = output_path + "/test-qps_stats.txt";
   CheckFileContent(all_qps, file_path, true);
 
-  // Check the qps of get
+  // Check the qps of Merge
   std::vector<std::string> get_qps = {"1"};
   file_path = output_path + "/test-merge-0-qps_stats.txt";
   CheckFileContent(get_qps, file_path, true);
@@ -497,32 +457,11 @@ TEST_F(TraceAnalyzerTest, SingleDelete) {
   std::string trace_path = test_path_ + "/trace";
   std::string output_path = test_path_ + "/single_delete";
   std::string file_path;
-  std::vector<std::string> paras = {"./trace_analyzer",
-                                    "-analyze_get",
-                                    "-analyze_put",
-                                    "-analyze_delete",
-                                    "-analyze_merge",
-                                    "-analyze_single_delete",
-                                    "-convert_to_human_readable_trace",
-                                    "-output_key_stats",
-                                    "-output_access_count_stats",
-                                    "-output_prefix=test",
-                                    "-output_prefix_cut=1",
-                                    "-output_time_series",
-                                    "-output_value_distribution",
-                                    "-output_qps_stats",
-                                    "-no_key",
-                                    "-no_print"};
-  Status s = env_->FileExists(trace_path);
-  if (!s.ok()) {
-    GenerateTrace(trace_path);
-  }
+  std::vector<std::string> paras = {"-analyze_single_delete"};
   paras.push_back("-output_dir=" + output_path);
   paras.push_back("-trace_path=" + trace_path);
   paras.push_back("-key_space_dir=" + test_path_);
-
-  env_->CreateDir(output_path);
-  RunTraceAnalyzer(paras);
+  AnalyzeTrace(paras, output_path, trace_path);
 
   // check the key_stats file
   std::vector<std::string> k_stats = {"0 0 0 1 1.000000"};
@@ -536,7 +475,8 @@ TEST_F(TraceAnalyzerTest, SingleDelete) {
   CheckFileContent(k_dist, file_path, true);
 
   // Check the trace sequence
-  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4", "0", "0"};
+  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4",
+                                         "0", "6", "7", "0"};
   file_path = output_path + "/test-human_readable_trace.txt";
   CheckFileContent(k_sequence, file_path, false);
 
@@ -566,7 +506,7 @@ TEST_F(TraceAnalyzerTest, SingleDelete) {
   file_path = output_path + "/test-qps_stats.txt";
   CheckFileContent(all_qps, file_path, true);
 
-  // Check the qps of get
+  // Check the qps of SingleDelete
   std::vector<std::string> get_qps = {"1"};
   file_path = output_path + "/test-single_delete-0-qps_stats.txt";
   CheckFileContent(get_qps, file_path, true);
@@ -584,33 +524,11 @@ TEST_F(TraceAnalyzerTest, DeleteRange) {
   std::string trace_path = test_path_ + "/trace";
   std::string output_path = test_path_ + "/range_delete";
   std::string file_path;
-  std::vector<std::string> paras = {"./trace_analyzer",
-                                    "-analyze_get",
-                                    "-analyze_put",
-                                    "-analyze_delete",
-                                    "-analyze_merge",
-                                    "-analyze_single_delete",
-                                    "-analyze_range_delete",
-                                    "-convert_to_human_readable_trace",
-                                    "-output_key_stats",
-                                    "-output_access_count_stats",
-                                    "-output_prefix=test",
-                                    "-output_prefix_cut=1",
-                                    "-output_time_series",
-                                    "-output_value_distribution",
-                                    "-output_qps_stats",
-                                    "-no_key",
-                                    "-no_print"};
-  Status s = env_->FileExists(trace_path);
-  if (!s.ok()) {
-    GenerateTrace(trace_path);
-  }
+  std::vector<std::string> paras = {"-analyze_range_delete"};
   paras.push_back("-output_dir=" + output_path);
   paras.push_back("-trace_path=" + trace_path);
   paras.push_back("-key_space_dir=" + test_path_);
-
-  env_->CreateDir(output_path);
-  RunTraceAnalyzer(paras);
+  AnalyzeTrace(paras, output_path, trace_path);
 
   // check the key_stats file
   std::vector<std::string> k_stats = {"0 0 0 1 1.000000", "0 0 1 1 1.000000"};
@@ -624,7 +542,8 @@ TEST_F(TraceAnalyzerTest, DeleteRange) {
   CheckFileContent(k_dist, file_path, true);
 
   // Check the trace sequence
-  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4", "0", "0"};
+  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4",
+                                         "0", "6", "7", "0"};
   file_path = output_path + "/test-human_readable_trace.txt";
   CheckFileContent(k_sequence, file_path, false);
 
@@ -655,7 +574,7 @@ TEST_F(TraceAnalyzerTest, DeleteRange) {
   file_path = output_path + "/test-qps_stats.txt";
   CheckFileContent(all_qps, file_path, true);
 
-  // Check the qps of get
+  // Check the qps of DeleteRange
   std::vector<std::string> get_qps = {"2"};
   file_path = output_path + "/test-range_delete-0-qps_stats.txt";
   CheckFileContent(get_qps, file_path, true);
@@ -669,6 +588,121 @@ TEST_F(TraceAnalyzerTest, DeleteRange) {
   CheckFileContent(top_qps, file_path, true);
 }
 
+// Test analyzing of Iterator
+TEST_F(TraceAnalyzerTest, Iterator) {
+  std::string trace_path = test_path_ + "/trace";
+  std::string output_path = test_path_ + "/iterator";
+  std::string file_path;
+  std::vector<std::string> paras = {"-analyze_iterator"};
+  paras.push_back("-output_dir=" + output_path);
+  paras.push_back("-trace_path=" + trace_path);
+  paras.push_back("-key_space_dir=" + test_path_);
+  AnalyzeTrace(paras, output_path, trace_path);
+
+  // Check the output of Seek
+  // check the key_stats file
+  std::vector<std::string> k_stats = {"0 0 0 1 1.000000"};
+  file_path = output_path + "/test-iterator_Seek-0-accessed_key_stats.txt";
+  CheckFileContent(k_stats, file_path, true);
+
+  // Check the access count distribution
+  std::vector<std::string> k_dist = {"access_count: 1 num: 1"};
+  file_path =
+      output_path + "/test-iterator_Seek-0-accessed_key_count_distribution.txt";
+  CheckFileContent(k_dist, file_path, true);
+
+  // Check the trace sequence
+  std::vector<std::string> k_sequence = {"1", "5", "2", "3", "4",
+                                         "0", "6", "7", "0"};
+  file_path = output_path + "/test-human_readable_trace.txt";
+  CheckFileContent(k_sequence, file_path, false);
+
+  // Check the prefix
+  std::vector<std::string> k_prefix = {"0 0 0 0.000000 0.000000 0x30"};
+  file_path = output_path + "/test-iterator_Seek-0-accessed_key_prefix_cut.txt";
+  CheckFileContent(k_prefix, file_path, true);
+
+  // Check the time series
+  std::vector<std::string> k_series = {"6 1 0"};
+  file_path = output_path + "/test-iterator_Seek-0-time_series.txt";
+  CheckFileContent(k_series, file_path, false);
+
+  // Check the accessed key in whole key space
+  std::vector<std::string> k_whole_access = {"0 1"};
+  file_path = output_path + "/test-iterator_Seek-0-whole_key_stats.txt";
+  CheckFileContent(k_whole_access, file_path, true);
+
+  // Check the whole key prefix cut
+  std::vector<std::string> k_whole_prefix = {"0 0x61", "1 0x62", "2 0x63",
+                                             "3 0x64", "4 0x65", "5 0x66"};
+  file_path = output_path + "/test-iterator_Seek-0-whole_key_prefix_cut.txt";
+  CheckFileContent(k_whole_prefix, file_path, true);
+
+  // Check the overall qps
+  std::vector<std::string> all_qps = {"1 1 1 1 2 1 1 1 9"};
+  file_path = output_path + "/test-qps_stats.txt";
+  CheckFileContent(all_qps, file_path, true);
+
+  // Check the qps of Iterator_Seek
+  std::vector<std::string> get_qps = {"1"};
+  file_path = output_path + "/test-iterator_Seek-0-qps_stats.txt";
+  CheckFileContent(get_qps, file_path, true);
+
+  // Check the top k qps prefix cut
+  std::vector<std::string> top_qps = {"At time: 0 with QPS: 1",
+                                      "The prefix: 0x61 Access count: 1"};
+  file_path =
+      output_path + "/test-iterator_Seek-0-accessed_top_k_qps_prefix_cut.txt";
+  CheckFileContent(top_qps, file_path, true);
+
+  // Check the output of SeekForPrev
+  // check the key_stats file
+  k_stats = {"0 0 0 1 1.000000"};
+  file_path =
+      output_path + "/test-iterator_SeekForPrev-0-accessed_key_stats.txt";
+  CheckFileContent(k_stats, file_path, true);
+
+  // Check the access count distribution
+  k_dist = {"access_count: 1 num: 1"};
+  file_path =
+      output_path +
+      "/test-iterator_SeekForPrev-0-accessed_key_count_distribution.txt";
+  CheckFileContent(k_dist, file_path, true);
+
+  // Check the prefix
+  k_prefix = {"0 0 0 0.000000 0.000000 0x30"};
+  file_path =
+      output_path + "/test-iterator_SeekForPrev-0-accessed_key_prefix_cut.txt";
+  CheckFileContent(k_prefix, file_path, true);
+
+  // Check the time series
+  k_series = {"7 0 0"};
+  file_path = output_path + "/test-iterator_SeekForPrev-0-time_series.txt";
+  CheckFileContent(k_series, file_path, false);
+
+  // Check the accessed key in whole key space
+  k_whole_access = {"1 1"};
+  file_path = output_path + "/test-iterator_SeekForPrev-0-whole_key_stats.txt";
+  CheckFileContent(k_whole_access, file_path, true);
+
+  // Check the whole key prefix cut
+  k_whole_prefix = {"0 0x61", "1 0x62", "2 0x63", "3 0x64", "4 0x65", "5 0x66"};
+  file_path =
+      output_path + "/test-iterator_SeekForPrev-0-whole_key_prefix_cut.txt";
+  CheckFileContent(k_whole_prefix, file_path, true);
+
+  // Check the qps of Iterator_SeekForPrev
+  get_qps = {"1"};
+  file_path = output_path + "/test-iterator_SeekForPrev-0-qps_stats.txt";
+  CheckFileContent(get_qps, file_path, true);
+
+  // Check the top k qps prefix cut
+  top_qps = {"At time: 0 with QPS: 1", "The prefix: 0x62 Access count: 1"};
+  file_path = output_path +
+              "/test-iterator_SeekForPrev-0-accessed_top_k_qps_prefix_cut.txt";
+  CheckFileContent(top_qps, file_path, true);
+}
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
diff --git a/3rdParty/rocksdb/v5.16.X/tools/trace_analyzer_tool.cc b/3rdParty/rocksdb/v5.18.X/tools/trace_analyzer_tool.cc
similarity index 88%
rename from 3rdParty/rocksdb/v5.16.X/tools/trace_analyzer_tool.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/trace_analyzer_tool.cc
index fc95b6a08f..49f2175a39 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/trace_analyzer_tool.cc
+++ b/3rdParty/rocksdb/v5.18.X/tools/trace_analyzer_tool.cc
@@ -63,36 +63,36 @@ DEFINE_string(output_prefix, "trace",
 DEFINE_bool(output_key_stats, false,
             "Output the key access count statistics to file\n"
             "for accessed keys:\n"
-            "file name: <prefix>-<query type>-<cf_id>-accessed_key_stats.txt\n"
+            "file name: <prefix>-<query_type>-<cf_id>-accessed_key_stats.txt\n"
             "Format:[cf_id value_size access_keyid access_count]\n"
             "for the whole key space keys:\n"
-            "File name: <prefix>-<query type>-<cf_id>-whole_key_stats.txt\n"
+            "File name: <prefix>-<query_type>-<cf_id>-whole_key_stats.txt\n"
             "Format:[whole_key_space_keyid access_count]");
 DEFINE_bool(output_access_count_stats, false,
             "Output the access count distribution statistics to file.\n"
-            "File name:  <prefix>-<query type>-<cf_id>-accessed_"
+            "File name:  <prefix>-<query_type>-<cf_id>-accessed_"
             "key_count_distribution.txt \n"
             "Format:[access_count number_of_access_count]");
 DEFINE_bool(output_time_series, false,
             "Output the access time in second of each key, "
             "such that we can have the time series data of the queries \n"
-            "File name: <prefix>-<query type>-<cf_id>-time_series.txt\n"
+            "File name: <prefix>-<query_type>-<cf_id>-time_series.txt\n"
             "Format:[type_id time_in_sec access_keyid].");
 DEFINE_int32(output_prefix_cut, 0,
              "The number of bytes as prefix to cut the keys.\n"
-             "if it is enabled, it will generate the following:\n"
-             "for accessed keys:\n"
-             "File name: <prefix>-<query type>-<cf_id>-"
+             "If it is enabled, it will generate the following:\n"
+             "For accessed keys:\n"
+             "File name: <prefix>-<query_type>-<cf_id>-"
              "accessed_key_prefix_cut.txt \n"
              "Format:[acessed_keyid access_count_of_prefix "
              "number_of_keys_in_prefix average_key_access "
              "prefix_succ_ratio prefix]\n"
-             "for whole key space keys:\n"
-             "File name: <prefix>-<query type>-<cf_id>"
+             "For whole key space keys:\n"
+             "File name: <prefix>-<query_type>-<cf_id>"
              "-whole_key_prefix_cut.txt\n"
              "Format:[start_keyid_in_whole_keyspace prefix]\n"
              "if 'output_qps_stats' and 'top_k' are enabled, it will output:\n"
-             "File name: <prefix>-<query type>-<cf_id>"
+             "File name: <prefix>-<query_type>-<cf_id>"
              "-accessed_top_k_qps_prefix_cut.txt\n"
              "Format:[the_top_ith_qps_time QPS], [prefix qps_of_this_second].");
 DEFINE_bool(convert_to_human_readable_trace, false,
@@ -101,7 +101,7 @@ DEFINE_bool(convert_to_human_readable_trace, false,
             "This file will be extremely large "
             "(similar size as the original binary trace file). "
             "You can specify 'no_key' to reduce the size, if key is not "
-            "needed in the next step\n"
+            "needed in the next step.\n"
             "File name: <prefix>_human_readable_trace.txt\n"
             "Format:[type_id cf_id value_size time_in_micorsec <key>].");
 DEFINE_bool(output_qps_stats, false,
@@ -110,8 +110,8 @@ DEFINE_bool(output_qps_stats, false,
             "The time is started from the first trace record\n"
             "File name: <prefix>_qps_stats.txt\n"
             "Format: [qps_type_1 qps_type_2 ...... overall_qps]\n"
-            "For each cf and query, it will have its own qps output\n"
-            "File name: <prefix>-<query type>-<cf_id>_qps_stats.txt \n"
+            "For each cf and query, it will have its own qps output.\n"
+            "File name: <prefix>-<query_type>-<cf_id>_qps_stats.txt \n"
             "Format:[query_count_in_this_second].");
 DEFINE_bool(no_print, false, "Do not print out any result");
 DEFINE_string(
@@ -122,7 +122,7 @@ DEFINE_string(
     "get, put, delete, single_delete, rangle_delete, merge. No space "
     "between the pairs separated by commar. Example: =[get,get]... "
     "It will print out the number of pairs of 'A after B' and "
-    "the average time interval between the two query");
+    "the average time interval between the two query.");
 DEFINE_string(key_space_dir, "",
               "<the directory stores full key space files> \n"
               "The key space files should be: <column family id>.txt");
@@ -139,11 +139,11 @@ DEFINE_bool(no_key, false,
 DEFINE_bool(print_overall_stats, true,
             " Print the stats of the whole trace, "
             "like total requests, keys, and etc.");
-DEFINE_bool(print_key_distribution, false, "Print the key size distribution.");
+DEFINE_bool(output_key_distribution, false, "Print the key size distribution.");
 DEFINE_bool(
     output_value_distribution, false,
     "Out put the value size distribution, only available for Put and Merge.\n"
-    "File name: <prefix>-<query type>-<cf_id>"
+    "File name: <prefix>-<query_type>-<cf_id>"
     "-accessed_value_size_distribution.txt\n"
     "Format:[Number_of_value_size_between x and "
     "x+value_interval is: <the count>]");
@@ -158,6 +158,9 @@ DEFINE_int32(value_interval, 8,
              "To output the value distribution, we need to set the value "
              "intervals and make the statistic of the value size distribution "
              "in different intervals. The default is 8.");
+DEFINE_double(sample_ratio, 1.0,
+              "If the trace size is extremely huge or user want to sample "
+              "the trace when analyzing, sample ratio can be set (0, 1.0]");
 
 namespace rocksdb {
 
@@ -185,7 +188,7 @@ uint64_t MultiplyCheckOverflow(uint64_t op1, uint64_t op2) {
   return (op1 * op2);
 }
 
-void DecodeCFAndKey(std::string& buffer, uint32_t* cf_id, Slice* key) {
+void DecodeCFAndKeyFromString(std::string& buffer, uint32_t* cf_id, Slice* key) {
   Slice buf(buffer);
   GetFixed32(&buf, cf_id);
   GetLengthPrefixedSlice(&buf, key);
@@ -276,9 +279,17 @@ TraceAnalyzer::TraceAnalyzer(std::string& trace_path, std::string& output_path,
   total_access_keys_ = 0;
   total_gets_ = 0;
   total_writes_ = 0;
+  trace_create_time_ = 0;
   begin_time_ = 0;
   end_time_ = 0;
   time_series_start_ = 0;
+  cur_time_sec_ = 0;
+  if (FLAGS_sample_ratio > 1.0 || FLAGS_sample_ratio <= 0) {
+    sample_max_ = 1;
+  } else {
+    sample_max_ = static_cast<uint32_t>(1.0 / FLAGS_sample_ratio);
+  }
+
   ta_.resize(kTaTypeNum);
   ta_[0].type_name = "get";
   if (FLAGS_analyze_get) {
@@ -328,6 +339,9 @@ TraceAnalyzer::TraceAnalyzer(std::string& trace_path, std::string& output_path,
   } else {
     ta_[7].enabled = false;
   }
+  for (int i = 0; i < kTaTypeNum; i++) {
+    ta_[i].sample_count = 0;
+  }
 }
 
 TraceAnalyzer::~TraceAnalyzer() {}
@@ -363,6 +377,13 @@ Status TraceAnalyzer::PrepareProcessing() {
     if (!s.ok()) {
       return s;
     }
+
+    qps_stats_name =
+        output_path_ + "/" + FLAGS_output_prefix + "-cf_qps_stats.txt";
+    s = env_->NewWritableFile(qps_stats_name, &cf_qps_f_, env_options_);
+    if (!s.ok()) {
+      return s;
+    }
   }
   return Status::OK();
 }
@@ -422,6 +443,7 @@ Status TraceAnalyzer::StartProcessing() {
     fprintf(stderr, "Cannot read the header\n");
     return s;
   }
+  trace_create_time_ = header.ts;
   if (FLAGS_output_time_series) {
     time_series_start_ = header.ts;
   }
@@ -459,7 +481,7 @@ Status TraceAnalyzer::StartProcessing() {
     } else if (trace.type == kTraceGet) {
       uint32_t cf_id = 0;
       Slice key;
-      DecodeCFAndKey(trace.payload, &cf_id, &key);
+      DecodeCFAndKeyFromString(trace.payload, &cf_id, &key);
       total_gets_++;
 
       s = HandleGet(cf_id, key.ToString(), trace.ts, 1);
@@ -471,7 +493,7 @@ Status TraceAnalyzer::StartProcessing() {
                trace.type == kTraceIteratorSeekForPrev) {
       uint32_t cf_id = 0;
       Slice key;
-      DecodeCFAndKey(trace.payload, &cf_id, &key);
+      DecodeCFAndKeyFromString(trace.payload, &cf_id, &key);
       s = HandleIter(cf_id, key.ToString(), trace.ts, trace.type);
       if (!s.ok()) {
         fprintf(stderr, "Cannot process the iterator in the trace\n");
@@ -521,7 +543,7 @@ Status TraceAnalyzer::MakeStatistics() {
         }
 
         // Generate the key size distribution data
-        if (FLAGS_print_key_distribution) {
+        if (FLAGS_output_key_distribution) {
           if (stat.second.a_key_size_stats.find(record.first.size()) ==
               stat.second.a_key_size_stats.end()) {
             stat.second.a_key_size_stats[record.first.size()] = 1;
@@ -565,17 +587,31 @@ Status TraceAnalyzer::MakeStatistics() {
 
       // find the medium of the key size
       uint64_t k_count = 0;
+      bool get_mid = false;
       for (auto& record : stat.second.a_key_size_stats) {
         k_count += record.second;
-        if (k_count >= stat.second.a_key_mid) {
+        if (!get_mid && k_count >= stat.second.a_key_mid) {
           stat.second.a_key_mid = record.first;
-          break;
+          get_mid = true;
+        }
+        if (FLAGS_output_key_distribution && stat.second.a_key_size_f) {
+          ret = sprintf(buffer_, "%" PRIu64 " %" PRIu64 "\n", record.first,
+                        record.second);
+          if (ret < 0) {
+            return Status::IOError("Format output failed");
+          }
+          std::string printout(buffer_);
+          s = stat.second.a_key_size_f->Append(printout);
+          if (!s.ok()) {
+            fprintf(stderr, "Write key size distribution file failed\n");
+            return s;
+          }
         }
       }
 
       // output the value size distribution
       uint64_t v_begin = 0, v_end = 0, v_count = 0;
-      bool get_mid = false;
+      get_mid = false;
       for (auto& record : stat.second.a_value_size_stats) {
         v_begin = v_end;
         v_end = (record.first + 1) * FLAGS_value_interval;
@@ -740,7 +776,11 @@ Status TraceAnalyzer::MakeStatisticCorrelation(TraceStats& stats,
 
 // Process the statistics of QPS
 Status TraceAnalyzer::MakeStatisticQPS() {
-  uint32_t duration = static_cast<uint32_t>((end_time_ - begin_time_) / 1000000);
+  if(begin_time_ == 0) {
+    begin_time_ = trace_create_time_;
+  }
+  uint32_t duration =
+      static_cast<uint32_t>((end_time_ - begin_time_) / 1000000);
   int ret;
   Status s;
   std::vector<std::vector<uint32_t>> type_qps(
@@ -817,6 +857,32 @@ Status TraceAnalyzer::MakeStatisticQPS() {
         stat.second.a_ave_qps = (static_cast<double>(cf_qps_sum)) / duration;
       }
 
+      // Output the accessed unique key number change overtime
+      if (stat.second.a_key_num_f) {
+        uint64_t cur_uni_key =
+            static_cast<uint64_t>(stat.second.a_key_stats.size());
+        double cur_ratio = 0.0;
+        uint64_t cur_num = 0;
+        for (uint32_t i = 0; i < duration; i++) {
+          auto find_time = stat.second.uni_key_num.find(i);
+          if (find_time != stat.second.uni_key_num.end()) {
+            cur_ratio = (static_cast<double>(find_time->second)) / cur_uni_key;
+            cur_num = find_time->second;
+          }
+          ret = sprintf(buffer_, "%" PRIu64 " %.12f\n", cur_num, cur_ratio);
+          if (ret < 0) {
+            return Status::IOError("Format the output failed");
+          }
+          std::string printout(buffer_);
+          s = stat.second.a_key_num_f->Append(printout);
+          if (!s.ok()) {
+            fprintf(stderr,
+                    "Write accessed unique key number change file failed\n");
+            return s;
+          }
+        }
+      }
+
       // output the prefix of top k access peak
       if (FLAGS_output_prefix_cut > 0 && stat.second.a_top_qps_prefix_f) {
         while (!stat.second.top_k_qps_sec.empty()) {
@@ -881,6 +947,33 @@ Status TraceAnalyzer::MakeStatisticQPS() {
     }
   }
 
+  if (cf_qps_f_) {
+    int cfs_size = static_cast<uint32_t>(cfs_.size());
+    uint32_t v;
+    for (uint32_t i = 0; i < duration; i++) {
+      for (int cf = 0; cf < cfs_size; cf++) {
+        if (cfs_[cf].cf_qps.find(i) != cfs_[cf].cf_qps.end()) {
+          v = cfs_[cf].cf_qps[i];
+        } else {
+          v = 0;
+        }
+        if (cf < cfs_size - 1) {
+          ret = sprintf(buffer_, "%u ", v);
+        } else {
+          ret = sprintf(buffer_, "%u\n", v);
+        }
+        if (ret < 0) {
+          return Status::IOError("Format the output failed");
+        }
+        std::string printout(buffer_);
+        s = cf_qps_f_->Append(printout);
+        if (!s.ok()) {
+          return s;
+        }
+      }
+    }
+  }
+
   qps_peak_ = qps_peak;
   for (int type = 0; type <= kTaTypeNum; type++) {
     if (duration == 0) {
@@ -1009,7 +1102,7 @@ Status TraceAnalyzer::ReProcessing() {
           }
 
           // Make the statistics fo the key size distribution
-          if (FLAGS_print_key_distribution) {
+          if (FLAGS_output_key_distribution) {
             if (cfs_[cf_id].w_key_size_stats.find(input_key.size()) ==
                 cfs_[cf_id].w_key_size_stats.end()) {
               cfs_[cf_id].w_key_size_stats[input_key.size()] = 1;
@@ -1128,6 +1221,11 @@ Status TraceAnalyzer::KeyStatsInsertion(const uint32_t& type,
       tmp_qps_map[prefix] = 1;
       ta_[type].stats[cf_id].a_qps_prefix_stats[time_in_sec] = tmp_qps_map;
     }
+    if (time_in_sec != cur_time_sec_) {
+      ta_[type].stats[cf_id].uni_key_num[cur_time_sec_] =
+          static_cast<uint64_t>(ta_[type].stats[cf_id].a_key_stats.size());
+      cur_time_sec_ = time_in_sec;
+    }
   } else {
     found_stats->second.a_count++;
     found_stats->second.a_key_size_sqsum += MultiplyCheckOverflow(
@@ -1148,6 +1246,11 @@ Status TraceAnalyzer::KeyStatsInsertion(const uint32_t& type,
         s = StatsUnitCorrelationUpdate(found_key->second, type, ts, key);
       }
     }
+    if (time_in_sec != cur_time_sec_) {
+      found_stats->second.uni_key_num[cur_time_sec_] =
+          static_cast<uint64_t>(found_stats->second.a_key_stats.size());
+      cur_time_sec_ = time_in_sec;
+    }
 
     auto found_value =
         found_stats->second.a_value_size_stats.find(dist_value_size);
@@ -1188,6 +1291,10 @@ Status TraceAnalyzer::KeyStatsInsertion(const uint32_t& type,
     cfs_[cf_id] = cf_unit;
   }
 
+  if (FLAGS_output_qps_stats) {
+    cfs_[cf_id].cf_qps[time_in_sec]++;
+  }
+
   if (FLAGS_output_time_series) {
     TraceUnit trace_u;
     trace_u.type = type;
@@ -1250,6 +1357,9 @@ Status TraceAnalyzer::OpenStatsOutputFiles(const std::string& type,
   if (FLAGS_output_key_stats) {
     s = CreateOutputFile(type, new_stats.cf_name, "accessed_key_stats.txt",
                          &new_stats.a_key_f);
+    s = CreateOutputFile(type, new_stats.cf_name,
+                         "accessed_unique_key_num_change.txt",
+                         &new_stats.a_key_num_f);
     if (!FLAGS_key_space_dir.empty()) {
       s = CreateOutputFile(type, new_stats.cf_name, "whole_key_stats.txt",
                            &new_stats.w_key_f);
@@ -1288,6 +1398,12 @@ Status TraceAnalyzer::OpenStatsOutputFiles(const std::string& type,
                          &new_stats.a_value_size_f);
   }
 
+  if (FLAGS_output_key_distribution) {
+    s = CreateOutputFile(type, new_stats.cf_name,
+                         "accessed_key_size_distribution.txt",
+                         &new_stats.a_key_size_f);
+  }
+
   if (FLAGS_output_qps_stats) {
     s = CreateOutputFile(type, new_stats.cf_name, "qps_stats.txt",
                          &new_stats.a_qps_f);
@@ -1327,6 +1443,10 @@ void TraceAnalyzer::CloseOutputFiles() {
         stat.second.a_key_f->Close();
       }
 
+      if (stat.second.a_key_num_f) {
+        stat.second.a_key_num_f->Close();
+      }
+
       if (stat.second.a_count_dist_f) {
         stat.second.a_count_dist_f->Close();
       }
@@ -1339,6 +1459,10 @@ void TraceAnalyzer::CloseOutputFiles() {
         stat.second.a_value_size_f->Close();
       }
 
+      if (stat.second.a_key_size_f) {
+        stat.second.a_key_size_f->Close();
+      }
+
       if (stat.second.a_qps_f) {
         stat.second.a_qps_f->Close();
       }
@@ -1372,6 +1496,15 @@ Status TraceAnalyzer::HandleGet(uint32_t column_family_id,
     }
   }
 
+  if (ta_[TraceOperationType::kGet].sample_count >= sample_max_) {
+    ta_[TraceOperationType::kGet].sample_count = 0;
+  }
+  if (ta_[TraceOperationType::kGet].sample_count > 0) {
+    ta_[TraceOperationType::kGet].sample_count++;
+    return Status::OK();
+  }
+  ta_[TraceOperationType::kGet].sample_count++;
+
   if (!ta_[TraceOperationType::kGet].enabled) {
     return Status::OK();
   }
@@ -1399,6 +1532,15 @@ Status TraceAnalyzer::HandlePut(uint32_t column_family_id, const Slice& key,
     }
   }
 
+  if (ta_[TraceOperationType::kPut].sample_count >= sample_max_) {
+    ta_[TraceOperationType::kPut].sample_count = 0;
+  }
+  if (ta_[TraceOperationType::kPut].sample_count > 0) {
+    ta_[TraceOperationType::kPut].sample_count++;
+    return Status::OK();
+  }
+  ta_[TraceOperationType::kPut].sample_count++;
+
   if (!ta_[TraceOperationType::kPut].enabled) {
     return Status::OK();
   }
@@ -1423,6 +1565,15 @@ Status TraceAnalyzer::HandleDelete(uint32_t column_family_id,
     }
   }
 
+  if (ta_[TraceOperationType::kDelete].sample_count >= sample_max_) {
+    ta_[TraceOperationType::kDelete].sample_count = 0;
+  }
+  if (ta_[TraceOperationType::kDelete].sample_count > 0) {
+    ta_[TraceOperationType::kDelete].sample_count++;
+    return Status::OK();
+  }
+  ta_[TraceOperationType::kDelete].sample_count++;
+
   if (!ta_[TraceOperationType::kDelete].enabled) {
     return Status::OK();
   }
@@ -1447,6 +1598,15 @@ Status TraceAnalyzer::HandleSingleDelete(uint32_t column_family_id,
     }
   }
 
+  if (ta_[TraceOperationType::kSingleDelete].sample_count >= sample_max_) {
+    ta_[TraceOperationType::kSingleDelete].sample_count = 0;
+  }
+  if (ta_[TraceOperationType::kSingleDelete].sample_count > 0) {
+    ta_[TraceOperationType::kSingleDelete].sample_count++;
+    return Status::OK();
+  }
+  ta_[TraceOperationType::kSingleDelete].sample_count++;
+
   if (!ta_[TraceOperationType::kSingleDelete].enabled) {
     return Status::OK();
   }
@@ -1472,6 +1632,15 @@ Status TraceAnalyzer::HandleDeleteRange(uint32_t column_family_id,
     }
   }
 
+  if (ta_[TraceOperationType::kRangeDelete].sample_count >= sample_max_) {
+    ta_[TraceOperationType::kRangeDelete].sample_count = 0;
+  }
+  if (ta_[TraceOperationType::kRangeDelete].sample_count > 0) {
+    ta_[TraceOperationType::kRangeDelete].sample_count++;
+    return Status::OK();
+  }
+  ta_[TraceOperationType::kRangeDelete].sample_count++;
+
   if (!ta_[TraceOperationType::kRangeDelete].enabled) {
     return Status::OK();
   }
@@ -1498,6 +1667,15 @@ Status TraceAnalyzer::HandleMerge(uint32_t column_family_id, const Slice& key,
     }
   }
 
+  if (ta_[TraceOperationType::kMerge].sample_count >= sample_max_) {
+    ta_[TraceOperationType::kMerge].sample_count = 0;
+  }
+  if (ta_[TraceOperationType::kMerge].sample_count > 0) {
+    ta_[TraceOperationType::kMerge].sample_count++;
+    return Status::OK();
+  }
+  ta_[TraceOperationType::kMerge].sample_count++;
+
   if (!ta_[TraceOperationType::kMerge].enabled) {
     return Status::OK();
   }
@@ -1534,6 +1712,15 @@ Status TraceAnalyzer::HandleIter(uint32_t column_family_id,
     }
   }
 
+  if (ta_[type].sample_count >= sample_max_) {
+    ta_[type].sample_count = 0;
+  }
+  if (ta_[type].sample_count > 0) {
+    ta_[type].sample_count++;
+    return Status::OK();
+  }
+  ta_[type].sample_count++;
+
   if (!ta_[type].enabled) {
     return Status::OK();
   }
@@ -1595,6 +1782,8 @@ void TraceAnalyzer::PrintStatistics() {
       ta_[type].total_succ_access += stat.a_succ_count;
       printf("*********************************************************\n");
       printf("colume family id: %u\n", stat.cf_id);
+      printf("Total number of queries to this cf by %s: %" PRIu64 "\n",
+             ta_[type].type_name.c_str(), stat.a_count);
       printf("Total unique keys in this cf: %" PRIu64 "\n", total_a_keys);
       printf("Average key size: %f key size medium: %" PRIu64
              " Key size Variation: %f\n",
@@ -1641,15 +1830,6 @@ void TraceAnalyzer::PrintStatistics() {
         }
       }
 
-      // print the key size distribution
-      if (FLAGS_print_key_distribution) {
-        printf("The key size distribution\n");
-        for (auto& record : stat.a_key_size_stats) {
-          printf("key_size %" PRIu64 " nums: %" PRIu64 "\n", record.first,
-                 record.second);
-        }
-      }
-
       // print the operation correlations
       if (!FLAGS_print_correlation.empty()) {
         for (int correlation = 0;
@@ -1699,6 +1879,8 @@ void TraceAnalyzer::PrintStatistics() {
       printf("Average QPS per second: %f Peak QPS: %u\n", qps_ave_[kTaTypeNum],
              qps_peak_[kTaTypeNum]);
     }
+    printf("The statistics related to query number need to times: %u\n",
+           sample_max_);
     printf("Total_requests: %" PRIu64 " Total_accessed_keys: %" PRIu64
            " Total_gets: %" PRIu64 " Total_write_batch: %" PRIu64 "\n",
            total_requests_, total_access_keys_, total_gets_, total_writes_);
@@ -1794,5 +1976,5 @@ int trace_analyzer_tool(int argc, char** argv) {
 }
 }  // namespace rocksdb
 
-#endif // Endif of Gflag
-#endif // RocksDB LITE
+#endif  // Endif of Gflag
+#endif  // RocksDB LITE
diff --git a/3rdParty/rocksdb/v5.16.X/tools/trace_analyzer_tool.h b/3rdParty/rocksdb/v5.18.X/tools/trace_analyzer_tool.h
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/tools/trace_analyzer_tool.h
rename to 3rdParty/rocksdb/v5.18.X/tools/trace_analyzer_tool.h
index 12a0020849..be96f5005d 100644
--- a/3rdParty/rocksdb/v5.16.X/tools/trace_analyzer_tool.h
+++ b/3rdParty/rocksdb/v5.18.X/tools/trace_analyzer_tool.h
@@ -115,12 +115,15 @@ struct TraceStats {
       top_k_qps_sec;
   std::list<TraceUnit> time_series;
   std::vector<std::pair<uint64_t, uint64_t>> correlation_output;
+  std::map<uint32_t, uint64_t> uni_key_num;
 
   std::unique_ptr<rocksdb::WritableFile> time_series_f;
   std::unique_ptr<rocksdb::WritableFile> a_key_f;
   std::unique_ptr<rocksdb::WritableFile> a_count_dist_f;
   std::unique_ptr<rocksdb::WritableFile> a_prefix_cut_f;
   std::unique_ptr<rocksdb::WritableFile> a_value_size_f;
+  std::unique_ptr<rocksdb::WritableFile> a_key_size_f;
+  std::unique_ptr<rocksdb::WritableFile> a_key_num_f;
   std::unique_ptr<rocksdb::WritableFile> a_qps_f;
   std::unique_ptr<rocksdb::WritableFile> a_top_qps_prefix_f;
   std::unique_ptr<rocksdb::WritableFile> w_key_f;
@@ -128,6 +131,10 @@ struct TraceStats {
 
   TraceStats();
   ~TraceStats();
+  TraceStats(const TraceStats&) = delete;
+  TraceStats& operator=(const TraceStats&) = delete;
+  TraceStats(TraceStats&&) = default;
+  TraceStats& operator=(TraceStats&&) = default;
 };
 
 struct TypeUnit {
@@ -136,7 +143,14 @@ struct TypeUnit {
   uint64_t total_keys;
   uint64_t total_access;
   uint64_t total_succ_access;
+  uint32_t sample_count;
   std::map<uint32_t, TraceStats> stats;
+  TypeUnit() = default;
+  ~TypeUnit() = default;
+  TypeUnit(const TypeUnit&) = delete;
+  TypeUnit& operator=(const TypeUnit&) = delete;
+  TypeUnit(TypeUnit&&) = default;
+  TypeUnit& operator=(TypeUnit&&) = default;
 };
 
 struct CfUnit {
@@ -145,6 +159,7 @@ struct CfUnit {
   uint64_t a_count;  // the total keys in this cf that are accessed
   std::map<uint64_t, uint64_t> w_key_size_stats;  // whole key space key size
                                                   // statistic this cf
+  std::map<uint32_t, uint32_t> cf_qps;
 };
 
 class TraceAnalyzer {
@@ -194,11 +209,15 @@ class TraceAnalyzer {
   uint64_t total_access_keys_;
   uint64_t total_gets_;
   uint64_t total_writes_;
+  uint64_t trace_create_time_;
   uint64_t begin_time_;
   uint64_t end_time_;
   uint64_t time_series_start_;
+  uint32_t sample_max_;
+  uint32_t cur_time_sec_;
   std::unique_ptr<rocksdb::WritableFile> trace_sequence_f_;  // readable trace
   std::unique_ptr<rocksdb::WritableFile> qps_f_;             // overall qps
+  std::unique_ptr<rocksdb::WritableFile> cf_qps_f_;  // The qps of each CF>
   std::unique_ptr<rocksdb::SequentialFile> wkey_input_f_;
   std::vector<TypeUnit> ta_;  // The main statistic collecting data structure
   std::map<uint32_t, CfUnit> cfs_;  // All the cf_id appears in this trace;
diff --git a/3rdParty/rocksdb/v5.16.X/tools/verify_random_db.sh b/3rdParty/rocksdb/v5.18.X/tools/verify_random_db.sh
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/verify_random_db.sh
rename to 3rdParty/rocksdb/v5.18.X/tools/verify_random_db.sh
diff --git a/3rdParty/rocksdb/v5.18.X/tools/write_external_sst.sh b/3rdParty/rocksdb/v5.18.X/tools/write_external_sst.sh
new file mode 100755
index 0000000000..6efc300202
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/tools/write_external_sst.sh
@@ -0,0 +1,25 @@
+#!/usr/bin/env bash
+#
+#
+#
+
+if [ "$#" -lt 3 ]; then
+  echo "usage: $BASH_SOURCE <input_data_path> <DB Path> <extern SST dir>"
+  exit 1
+fi
+
+input_data_dir=$1
+db_dir=$2
+extern_sst_dir=$3
+rm -rf $db_dir
+
+set -e
+
+n=0
+
+for f in `find $input_data_dir -name sorted_data*`
+do
+  echo == Writing external SST file $f to $extern_sst_dir/extern_sst${n}
+  ./ldb --db=$db_dir --create_if_missing write_extern_sst $extern_sst_dir/extern_sst${n} < $f
+  let "n = n + 1"
+done
diff --git a/3rdParty/rocksdb/v5.16.X/tools/write_stress.cc b/3rdParty/rocksdb/v5.18.X/tools/write_stress.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/write_stress.cc
rename to 3rdParty/rocksdb/v5.18.X/tools/write_stress.cc
diff --git a/3rdParty/rocksdb/v5.16.X/tools/write_stress_runner.py b/3rdParty/rocksdb/v5.18.X/tools/write_stress_runner.py
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/tools/write_stress_runner.py
rename to 3rdParty/rocksdb/v5.18.X/tools/write_stress_runner.py
diff --git a/3rdParty/rocksdb/v5.16.X/util/aligned_buffer.h b/3rdParty/rocksdb/v5.18.X/util/aligned_buffer.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/aligned_buffer.h
rename to 3rdParty/rocksdb/v5.18.X/util/aligned_buffer.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/allocator.h b/3rdParty/rocksdb/v5.18.X/util/allocator.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/allocator.h
rename to 3rdParty/rocksdb/v5.18.X/util/allocator.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/arena.cc b/3rdParty/rocksdb/v5.18.X/util/arena.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/arena.cc
rename to 3rdParty/rocksdb/v5.18.X/util/arena.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/arena.h b/3rdParty/rocksdb/v5.18.X/util/arena.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/arena.h
rename to 3rdParty/rocksdb/v5.18.X/util/arena.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/arena_test.cc b/3rdParty/rocksdb/v5.18.X/util/arena_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/arena_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/arena_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/auto_roll_logger.cc b/3rdParty/rocksdb/v5.18.X/util/auto_roll_logger.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/auto_roll_logger.cc
rename to 3rdParty/rocksdb/v5.18.X/util/auto_roll_logger.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/auto_roll_logger.h b/3rdParty/rocksdb/v5.18.X/util/auto_roll_logger.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/auto_roll_logger.h
rename to 3rdParty/rocksdb/v5.18.X/util/auto_roll_logger.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/auto_roll_logger_test.cc b/3rdParty/rocksdb/v5.18.X/util/auto_roll_logger_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/util/auto_roll_logger_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/auto_roll_logger_test.cc
index 5a6b3abc11..284a981521 100644
--- a/3rdParty/rocksdb/v5.16.X/util/auto_roll_logger_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/auto_roll_logger_test.cc
@@ -230,7 +230,7 @@ TEST_F(AutoRollLoggerTest, CompositeRollByTimeAndSizeLogger) {
 TEST_F(AutoRollLoggerTest, CreateLoggerFromOptions) {
   DBOptions options;
   NoSleepEnv nse(Env::Default());
-  shared_ptr<Logger> logger;
+  std::shared_ptr<Logger> logger;
 
   // Normal logger
   ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
@@ -273,7 +273,7 @@ TEST_F(AutoRollLoggerTest, CreateLoggerFromOptions) {
 
 TEST_F(AutoRollLoggerTest, LogFlushWhileRolling) {
   DBOptions options;
-  shared_ptr<Logger> logger;
+  std::shared_ptr<Logger> logger;
 
   InitTestDb();
   options.max_log_file_size = 1024 * 5;
diff --git a/3rdParty/rocksdb/v5.16.X/util/autovector.h b/3rdParty/rocksdb/v5.18.X/util/autovector.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/util/autovector.h
rename to 3rdParty/rocksdb/v5.18.X/util/autovector.h
index b5c8471245..97348d818a 100644
--- a/3rdParty/rocksdb/v5.16.X/util/autovector.h
+++ b/3rdParty/rocksdb/v5.18.X/util/autovector.h
@@ -271,7 +271,12 @@ class autovector {
 
   template <class... Args>
   void emplace_back(Args&&... args) {
-    push_back(value_type(args...));
+    if (num_stack_items_ < kSize) {
+      values_[num_stack_items_++] =
+          std::move(value_type(std::forward<Args>(args)...));
+    } else {
+      vect_.emplace_back(std::forward<Args>(args)...);
+    }
   }
 
   void pop_back() {
diff --git a/3rdParty/rocksdb/v5.16.X/util/autovector_test.cc b/3rdParty/rocksdb/v5.18.X/util/autovector_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/autovector_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/autovector_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/bloom.cc b/3rdParty/rocksdb/v5.18.X/util/bloom.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/bloom.cc
rename to 3rdParty/rocksdb/v5.18.X/util/bloom.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/bloom_test.cc b/3rdParty/rocksdb/v5.18.X/util/bloom_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/bloom_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/bloom_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/build_version.cc.in b/3rdParty/rocksdb/v5.18.X/util/build_version.cc.in
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/build_version.cc.in
rename to 3rdParty/rocksdb/v5.18.X/util/build_version.cc.in
diff --git a/3rdParty/rocksdb/v5.16.X/util/build_version.h b/3rdParty/rocksdb/v5.18.X/util/build_version.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/build_version.h
rename to 3rdParty/rocksdb/v5.18.X/util/build_version.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/cast_util.h b/3rdParty/rocksdb/v5.18.X/util/cast_util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/cast_util.h
rename to 3rdParty/rocksdb/v5.18.X/util/cast_util.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/channel.h b/3rdParty/rocksdb/v5.18.X/util/channel.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/channel.h
rename to 3rdParty/rocksdb/v5.18.X/util/channel.h
index 1b030192cf..0225482c00 100644
--- a/3rdParty/rocksdb/v5.16.X/util/channel.h
+++ b/3rdParty/rocksdb/v5.18.X/util/channel.h
@@ -3,13 +3,13 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
+#pragma once
+
 #include <condition_variable>
 #include <mutex>
 #include <queue>
 #include <utility>
 
-#pragma once
-
 namespace rocksdb {
 
 template <class T>
diff --git a/3rdParty/rocksdb/v5.16.X/util/coding.cc b/3rdParty/rocksdb/v5.18.X/util/coding.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/coding.cc
rename to 3rdParty/rocksdb/v5.18.X/util/coding.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/coding.h b/3rdParty/rocksdb/v5.18.X/util/coding.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/util/coding.h
rename to 3rdParty/rocksdb/v5.18.X/util/coding.h
index 27a638347f..4046a2b60b 100644
--- a/3rdParty/rocksdb/v5.16.X/util/coding.h
+++ b/3rdParty/rocksdb/v5.18.X/util/coding.h
@@ -64,7 +64,8 @@ extern Slice GetLengthPrefixedSlice(const char* data);
 
 extern Slice GetSliceUntil(Slice* slice, char delimiter);
 
-// Borrowed from https://github.com/facebook/fbthrift/blob/449a5f77f9f9bae72c9eb5e78093247eef185c04/thrift/lib/cpp/util/VarintUtils-inl.h#L202-L208
+// Borrowed from
+// https://github.com/facebook/fbthrift/blob/449a5f77f9f9bae72c9eb5e78093247eef185c04/thrift/lib/cpp/util/VarintUtils-inl.h#L202-L208
 constexpr inline uint64_t i64ToZigzag(const int64_t l) {
   return (static_cast<uint64_t>(l) << 1) ^ static_cast<uint64_t>(l >> 63);
 }
diff --git a/3rdParty/rocksdb/v5.16.X/util/coding_test.cc b/3rdParty/rocksdb/v5.18.X/util/coding_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/coding_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/coding_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/compaction_job_stats_impl.cc b/3rdParty/rocksdb/v5.18.X/util/compaction_job_stats_impl.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/compaction_job_stats_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/util/compaction_job_stats_impl.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/comparator.cc b/3rdParty/rocksdb/v5.18.X/util/comparator.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/comparator.cc
rename to 3rdParty/rocksdb/v5.18.X/util/comparator.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/compression.h b/3rdParty/rocksdb/v5.18.X/util/compression.h
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/util/compression.h
rename to 3rdParty/rocksdb/v5.18.X/util/compression.h
index 3a980a5d88..e91faeac65 100644
--- a/3rdParty/rocksdb/v5.16.X/util/compression.h
+++ b/3rdParty/rocksdb/v5.18.X/util/compression.h
@@ -14,8 +14,10 @@
 #include <string>
 
 #include "rocksdb/options.h"
+#include "rocksdb/table.h"
 #include "util/coding.h"
 #include "util/compression_context_cache.h"
+#include "util/memory_allocator.h"
 
 #ifdef SNAPPY
 #include <snappy.h>
@@ -36,9 +38,9 @@
 
 #if defined(ZSTD)
 #include <zstd.h>
-#if ZSTD_VERSION_NUMBER >= 800  // v0.8.0+
+#if ZSTD_VERSION_NUMBER >= 10103  // v1.1.3+
 #include <zdict.h>
-#endif  // ZSTD_VERSION_NUMBER >= 800
+#endif  // ZSTD_VERSION_NUMBER >= 10103
 namespace rocksdb {
 // Need this for the context allocation override
 // On windows we need to do this explicitly
@@ -495,11 +497,10 @@ inline bool Zlib_Compress(const CompressionContext& ctx,
 // header in varint32 format
 // @param compression_dict Data for presetting the compression library's
 //    dictionary.
-inline char* Zlib_Uncompress(const UncompressionContext& ctx,
-                             const char* input_data, size_t input_length,
-                             int* decompress_size,
-                             uint32_t compress_format_version,
-                             int windowBits = -14) {
+inline CacheAllocationPtr Zlib_Uncompress(
+    const UncompressionContext& ctx, const char* input_data,
+    size_t input_length, int* decompress_size, uint32_t compress_format_version,
+    MemoryAllocator* allocator = nullptr, int windowBits = -14) {
 #ifdef ZLIB
   uint32_t output_len = 0;
   if (compress_format_version == 2) {
@@ -541,9 +542,9 @@ inline char* Zlib_Uncompress(const UncompressionContext& ctx,
   _stream.next_in = (Bytef*)input_data;
   _stream.avail_in = static_cast<unsigned int>(input_length);
 
-  char* output = new char[output_len];
+  auto output = AllocateBlock(output_len, allocator);
 
-  _stream.next_out = (Bytef*)output;
+  _stream.next_out = (Bytef*)output.get();
   _stream.avail_out = static_cast<unsigned int>(output_len);
 
   bool done = false;
@@ -561,19 +562,17 @@ inline char* Zlib_Uncompress(const UncompressionContext& ctx,
         size_t old_sz = output_len;
         uint32_t output_len_delta = output_len / 5;
         output_len += output_len_delta < 10 ? 10 : output_len_delta;
-        char* tmp = new char[output_len];
-        memcpy(tmp, output, old_sz);
-        delete[] output;
-        output = tmp;
+        auto tmp = AllocateBlock(output_len, allocator);
+        memcpy(tmp.get(), output.get(), old_sz);
+        output = std::move(tmp);
 
         // Set more output.
-        _stream.next_out = (Bytef*)(output + old_sz);
+        _stream.next_out = (Bytef*)(output.get() + old_sz);
         _stream.avail_out = static_cast<unsigned int>(output_len - old_sz);
         break;
       }
       case Z_BUF_ERROR:
       default:
-        delete[] output;
         inflateEnd(&_stream);
         return nullptr;
     }
@@ -590,6 +589,7 @@ inline char* Zlib_Uncompress(const UncompressionContext& ctx,
   (void)input_length;
   (void)decompress_size;
   (void)compress_format_version;
+  (void)allocator;
   (void)windowBits;
   return nullptr;
 #endif
@@ -660,9 +660,9 @@ inline bool BZip2_Compress(const CompressionContext& /*ctx*/,
 // block header
 // compress_format_version == 2 -- decompressed size is included in the block
 // header in varint32 format
-inline char* BZip2_Uncompress(const char* input_data, size_t input_length,
-                              int* decompress_size,
-                              uint32_t compress_format_version) {
+inline CacheAllocationPtr BZip2_Uncompress(
+    const char* input_data, size_t input_length, int* decompress_size,
+    uint32_t compress_format_version, MemoryAllocator* allocator = nullptr) {
 #ifdef BZIP2
   uint32_t output_len = 0;
   if (compress_format_version == 2) {
@@ -690,9 +690,9 @@ inline char* BZip2_Uncompress(const char* input_data, size_t input_length,
   _stream.next_in = (char*)input_data;
   _stream.avail_in = static_cast<unsigned int>(input_length);
 
-  char* output = new char[output_len];
+  auto output = AllocateBlock(output_len, allocator);
 
-  _stream.next_out = (char*)output;
+  _stream.next_out = (char*)output.get();
   _stream.avail_out = static_cast<unsigned int>(output_len);
 
   bool done = false;
@@ -709,18 +709,16 @@ inline char* BZip2_Uncompress(const char* input_data, size_t input_length,
         assert(compress_format_version != 2);
         uint32_t old_sz = output_len;
         output_len = output_len * 1.2;
-        char* tmp = new char[output_len];
-        memcpy(tmp, output, old_sz);
-        delete[] output;
-        output = tmp;
+        auto tmp = AllocateBlock(output_len, allocator);
+        memcpy(tmp.get(), output.get(), old_sz);
+        output = std::move(tmp);
 
         // Set more output.
-        _stream.next_out = (char*)(output + old_sz);
+        _stream.next_out = (char*)(output.get() + old_sz);
         _stream.avail_out = static_cast<unsigned int>(output_len - old_sz);
         break;
       }
       default:
-        delete[] output;
         BZ2_bzDecompressEnd(&_stream);
         return nullptr;
     }
@@ -736,6 +734,7 @@ inline char* BZip2_Uncompress(const char* input_data, size_t input_length,
   (void)input_length;
   (void)decompress_size;
   (void)compress_format_version;
+  (void)allocator;
   return nullptr;
 #endif
 }
@@ -791,6 +790,7 @@ inline bool LZ4_Compress(const CompressionContext& ctx,
 #else   // up to r123
   outlen = LZ4_compress_limitedOutput(input, &(*output)[output_header_len],
                                       static_cast<int>(length), compress_bound);
+  (void)ctx;
 #endif  // LZ4_VERSION_NUMBER >= 10400
 
   if (outlen == 0) {
@@ -814,10 +814,12 @@ inline bool LZ4_Compress(const CompressionContext& ctx,
 // header in varint32 format
 // @param compression_dict Data for presetting the compression library's
 //    dictionary.
-inline char* LZ4_Uncompress(const UncompressionContext& ctx,
-                            const char* input_data, size_t input_length,
-                            int* decompress_size,
-                            uint32_t compress_format_version) {
+inline CacheAllocationPtr LZ4_Uncompress(const UncompressionContext& ctx,
+                                         const char* input_data,
+                                         size_t input_length,
+                                         int* decompress_size,
+                                         uint32_t compress_format_version,
+                                         MemoryAllocator* allocator = nullptr) {
 #ifdef LZ4
   uint32_t output_len = 0;
   if (compress_format_version == 2) {
@@ -837,7 +839,7 @@ inline char* LZ4_Uncompress(const UncompressionContext& ctx,
     input_data += 8;
   }
 
-  char* output = new char[output_len];
+  auto output = AllocateBlock(output_len, allocator);
 #if LZ4_VERSION_NUMBER >= 10400  // r124+
   LZ4_streamDecode_t* stream = LZ4_createStreamDecode();
   if (ctx.dict().size()) {
@@ -845,17 +847,17 @@ inline char* LZ4_Uncompress(const UncompressionContext& ctx,
                         static_cast<int>(ctx.dict().size()));
   }
   *decompress_size = LZ4_decompress_safe_continue(
-      stream, input_data, output, static_cast<int>(input_length),
+      stream, input_data, output.get(), static_cast<int>(input_length),
       static_cast<int>(output_len));
   LZ4_freeStreamDecode(stream);
 #else   // up to r123
-  *decompress_size =
-      LZ4_decompress_safe(input_data, output, static_cast<int>(input_length),
-                          static_cast<int>(output_len));
+  *decompress_size = LZ4_decompress_safe(input_data, output.get(),
+                                         static_cast<int>(input_length),
+                                         static_cast<int>(output_len));
+  (void)ctx;
 #endif  // LZ4_VERSION_NUMBER >= 10400
 
   if (*decompress_size < 0) {
-    delete[] output;
     return nullptr;
   }
   assert(*decompress_size == static_cast<int>(output_len));
@@ -866,6 +868,7 @@ inline char* LZ4_Uncompress(const UncompressionContext& ctx,
   (void)input_length;
   (void)decompress_size;
   (void)compress_format_version;
+  (void)allocator;
   return nullptr;
 #endif
 }
@@ -1028,9 +1031,10 @@ inline bool ZSTD_Compress(const CompressionContext& ctx, const char* input,
 
 // @param compression_dict Data for presetting the compression library's
 //    dictionary.
-inline char* ZSTD_Uncompress(const UncompressionContext& ctx,
-                             const char* input_data, size_t input_length,
-                             int* decompress_size) {
+inline CacheAllocationPtr ZSTD_Uncompress(
+    const UncompressionContext& ctx, const char* input_data,
+    size_t input_length, int* decompress_size,
+    MemoryAllocator* allocator = nullptr) {
 #ifdef ZSTD
   uint32_t output_len = 0;
   if (!compression::GetDecompressedSizeInfo(&input_data, &input_length,
@@ -1038,17 +1042,17 @@ inline char* ZSTD_Uncompress(const UncompressionContext& ctx,
     return nullptr;
   }
 
-  char* output = new char[output_len];
+  auto output = AllocateBlock(output_len, allocator);
   size_t actual_output_length;
 #if ZSTD_VERSION_NUMBER >= 500  // v0.5.0+
   ZSTD_DCtx* context = ctx.GetZSTDContext();
   assert(context != nullptr);
   actual_output_length = ZSTD_decompress_usingDict(
-      context, output, output_len, input_data, input_length, ctx.dict().data(),
-      ctx.dict().size());
+      context, output.get(), output_len, input_data, input_length,
+      ctx.dict().data(), ctx.dict().size());
 #else   // up to v0.4.x
   actual_output_length =
-      ZSTD_decompress(output, output_len, input_data, input_length);
+      ZSTD_decompress(output.get(), output_len, input_data, input_length);
 #endif  // ZSTD_VERSION_NUMBER >= 500
   assert(actual_output_length == output_len);
   *decompress_size = static_cast<int>(actual_output_length);
@@ -1058,6 +1062,7 @@ inline char* ZSTD_Uncompress(const UncompressionContext& ctx,
   (void)input_data;
   (void)input_length;
   (void)decompress_size;
+  (void)allocator;
   return nullptr;
 #endif
 }
@@ -1065,9 +1070,10 @@ inline char* ZSTD_Uncompress(const UncompressionContext& ctx,
 inline std::string ZSTD_TrainDictionary(const std::string& samples,
                                         const std::vector<size_t>& sample_lens,
                                         size_t max_dict_bytes) {
-  // Dictionary trainer is available since v0.6.1, but ZSTD was marked stable
-  // only since v0.8.0. For now we enable the feature in stable versions only.
-#if ZSTD_VERSION_NUMBER >= 800  // v0.8.0+
+  // Dictionary trainer is available since v0.6.1 for static linking, but not
+  // available for dynamic linking until v1.1.3. For now we enable the feature
+  // in v1.1.3+ only.
+#if ZSTD_VERSION_NUMBER >= 10103  // v1.1.3+
   std::string dict_data(max_dict_bytes, '\0');
   size_t dict_len = ZDICT_trainFromBuffer(
       &dict_data[0], max_dict_bytes, &samples[0], &sample_lens[0],
@@ -1078,13 +1084,13 @@ inline std::string ZSTD_TrainDictionary(const std::string& samples,
   assert(dict_len <= max_dict_bytes);
   dict_data.resize(dict_len);
   return dict_data;
-#else   // up to v0.7.x
+#else   // up to v1.1.2
   assert(false);
   (void)samples;
   (void)sample_lens;
   (void)max_dict_bytes;
   return "";
-#endif  // ZSTD_VERSION_NUMBER >= 800
+#endif  // ZSTD_VERSION_NUMBER >= 10103
 }
 
 inline std::string ZSTD_TrainDictionary(const std::string& samples,
@@ -1092,18 +1098,18 @@ inline std::string ZSTD_TrainDictionary(const std::string& samples,
                                         size_t max_dict_bytes) {
   // Dictionary trainer is available since v0.6.1, but ZSTD was marked stable
   // only since v0.8.0. For now we enable the feature in stable versions only.
-#if ZSTD_VERSION_NUMBER >= 800  // v0.8.0+
+#if ZSTD_VERSION_NUMBER >= 10103  // v1.1.3+
   // skips potential partial sample at the end of "samples"
   size_t num_samples = samples.size() >> sample_len_shift;
   std::vector<size_t> sample_lens(num_samples, size_t(1) << sample_len_shift);
   return ZSTD_TrainDictionary(samples, sample_lens, max_dict_bytes);
-#else   // up to v0.7.x
+#else   // up to v1.1.2
   assert(false);
   (void)samples;
   (void)sample_len_shift;
   (void)max_dict_bytes;
   return "";
-#endif  // ZSTD_VERSION_NUMBER >= 800
+#endif  // ZSTD_VERSION_NUMBER >= 10103
 }
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/util/compression_context_cache.cc b/3rdParty/rocksdb/v5.18.X/util/compression_context_cache.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/compression_context_cache.cc
rename to 3rdParty/rocksdb/v5.18.X/util/compression_context_cache.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/compression_context_cache.h b/3rdParty/rocksdb/v5.18.X/util/compression_context_cache.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/compression_context_cache.h
rename to 3rdParty/rocksdb/v5.18.X/util/compression_context_cache.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/concurrent_arena.cc b/3rdParty/rocksdb/v5.18.X/util/concurrent_arena.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/concurrent_arena.cc
rename to 3rdParty/rocksdb/v5.18.X/util/concurrent_arena.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/concurrent_arena.h b/3rdParty/rocksdb/v5.18.X/util/concurrent_arena.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/concurrent_arena.h
rename to 3rdParty/rocksdb/v5.18.X/util/concurrent_arena.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/core_local.h b/3rdParty/rocksdb/v5.18.X/util/core_local.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/core_local.h
rename to 3rdParty/rocksdb/v5.18.X/util/core_local.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/crc32c.cc b/3rdParty/rocksdb/v5.18.X/util/crc32c.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/crc32c.cc
rename to 3rdParty/rocksdb/v5.18.X/util/crc32c.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/crc32c.h b/3rdParty/rocksdb/v5.18.X/util/crc32c.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/crc32c.h
rename to 3rdParty/rocksdb/v5.18.X/util/crc32c.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/crc32c_ppc.c b/3rdParty/rocksdb/v5.18.X/util/crc32c_ppc.c
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/crc32c_ppc.c
rename to 3rdParty/rocksdb/v5.18.X/util/crc32c_ppc.c
diff --git a/3rdParty/rocksdb/v5.16.X/util/crc32c_ppc.h b/3rdParty/rocksdb/v5.18.X/util/crc32c_ppc.h
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/util/crc32c_ppc.h
rename to 3rdParty/rocksdb/v5.18.X/util/crc32c_ppc.h
index b52ad9b2a4..3bcaecfe82 100644
--- a/3rdParty/rocksdb/v5.16.X/util/crc32c_ppc.h
+++ b/3rdParty/rocksdb/v5.18.X/util/crc32c_ppc.h
@@ -6,8 +6,7 @@
 //  This source code is also licensed under the GPLv2 license found in the
 //  COPYING file in the root directory of this source tree.
 
-#ifndef CRC32C_PPC_H
-#define CRC32C_PPC_H
+#pragma once
 
 #ifdef __cplusplus
 extern "C" {
@@ -19,5 +18,3 @@ extern uint32_t crc32c_ppc(uint32_t crc, unsigned char const *buffer,
 #ifdef __cplusplus
 }
 #endif
-
-#endif
diff --git a/3rdParty/rocksdb/v5.16.X/util/crc32c_ppc_asm.S b/3rdParty/rocksdb/v5.18.X/util/crc32c_ppc_asm.S
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/crc32c_ppc_asm.S
rename to 3rdParty/rocksdb/v5.18.X/util/crc32c_ppc_asm.S
diff --git a/3rdParty/rocksdb/v5.16.X/util/crc32c_ppc_constants.h b/3rdParty/rocksdb/v5.18.X/util/crc32c_ppc_constants.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/util/crc32c_ppc_constants.h
rename to 3rdParty/rocksdb/v5.18.X/util/crc32c_ppc_constants.h
index 1206a957a7..57d6630322 100644
--- a/3rdParty/rocksdb/v5.16.X/util/crc32c_ppc_constants.h
+++ b/3rdParty/rocksdb/v5.18.X/util/crc32c_ppc_constants.h
@@ -5,8 +5,9 @@
 //  of patent rights can be found in the PATENTS file in the same directory.
 //  This source code is also licensed under the GPLv2 license found in the
 //  COPYING file in the root directory of this source tree.
-#ifndef CRC32C_PPC_CONST_H
-#define CRC32C_PPC_CONST_H
+
+#pragma once
+
 #define CRC 0x1edc6f41
 #define REFLECT
 #define CRC_XOR
@@ -898,5 +899,3 @@ static const unsigned int crc_table[] = {
         /* 33 bit reflected Barrett constant n */
         .octa 0x00000000000000000000000105ec76f1
 #endif
-
-#endif
diff --git a/3rdParty/rocksdb/v5.16.X/util/crc32c_test.cc b/3rdParty/rocksdb/v5.18.X/util/crc32c_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/crc32c_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/crc32c_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/delete_scheduler.cc b/3rdParty/rocksdb/v5.18.X/util/delete_scheduler.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/util/delete_scheduler.cc
rename to 3rdParty/rocksdb/v5.18.X/util/delete_scheduler.cc
index 1d51055a3b..a8078b94a1 100644
--- a/3rdParty/rocksdb/v5.16.X/util/delete_scheduler.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/delete_scheduler.cc
@@ -275,7 +275,7 @@ Status DeleteScheduler::DeleteTrashFile(const std::string& path_in_trash,
       Status my_status = env_->NumFileLinks(path_in_trash, &num_hard_links);
       if (my_status.ok()) {
         if (num_hard_links == 1) {
-          unique_ptr<WritableFile> wf;
+          std::unique_ptr<WritableFile> wf;
           my_status =
               env_->ReopenWritableFile(path_in_trash, &wf, EnvOptions());
           if (my_status.ok()) {
diff --git a/3rdParty/rocksdb/v5.16.X/util/delete_scheduler.h b/3rdParty/rocksdb/v5.18.X/util/delete_scheduler.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/delete_scheduler.h
rename to 3rdParty/rocksdb/v5.18.X/util/delete_scheduler.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/delete_scheduler_test.cc b/3rdParty/rocksdb/v5.18.X/util/delete_scheduler_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/util/delete_scheduler_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/delete_scheduler_test.cc
index 6c33f03daa..bfd9954deb 100644
--- a/3rdParty/rocksdb/v5.16.X/util/delete_scheduler_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/delete_scheduler_test.cc
@@ -89,7 +89,7 @@ class DeleteSchedulerTest : public testing::Test {
     std::string data(size, 'A');
     EXPECT_OK(f->Append(data));
     EXPECT_OK(f->Close());
-    sst_file_mgr_->OnAddFile(file_path);
+    sst_file_mgr_->OnAddFile(file_path, false);
     return file_path;
   }
 
diff --git a/3rdParty/rocksdb/v5.16.X/util/duplicate_detector.h b/3rdParty/rocksdb/v5.18.X/util/duplicate_detector.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/duplicate_detector.h
rename to 3rdParty/rocksdb/v5.18.X/util/duplicate_detector.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/dynamic_bloom.cc b/3rdParty/rocksdb/v5.18.X/util/dynamic_bloom.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/dynamic_bloom.cc
rename to 3rdParty/rocksdb/v5.18.X/util/dynamic_bloom.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/dynamic_bloom.h b/3rdParty/rocksdb/v5.18.X/util/dynamic_bloom.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/dynamic_bloom.h
rename to 3rdParty/rocksdb/v5.18.X/util/dynamic_bloom.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/dynamic_bloom_test.cc b/3rdParty/rocksdb/v5.18.X/util/dynamic_bloom_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/dynamic_bloom_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/dynamic_bloom_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/event_logger.cc b/3rdParty/rocksdb/v5.18.X/util/event_logger.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/event_logger.cc
rename to 3rdParty/rocksdb/v5.18.X/util/event_logger.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/event_logger.h b/3rdParty/rocksdb/v5.18.X/util/event_logger.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/event_logger.h
rename to 3rdParty/rocksdb/v5.18.X/util/event_logger.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/event_logger_test.cc b/3rdParty/rocksdb/v5.18.X/util/event_logger_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/event_logger_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/event_logger_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/fault_injection_test_env.cc b/3rdParty/rocksdb/v5.18.X/util/fault_injection_test_env.cc
similarity index 84%
rename from 3rdParty/rocksdb/v5.16.X/util/fault_injection_test_env.cc
rename to 3rdParty/rocksdb/v5.18.X/util/fault_injection_test_env.cc
index 46e1e0d773..64e9da1aac 100644
--- a/3rdParty/rocksdb/v5.16.X/util/fault_injection_test_env.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/fault_injection_test_env.cc
@@ -29,12 +29,12 @@ std::string GetDirName(const std::string filename) {
 
 // A basic file truncation function suitable for this test.
 Status Truncate(Env* env, const std::string& filename, uint64_t length) {
-  unique_ptr<SequentialFile> orig_file;
+  std::unique_ptr<SequentialFile> orig_file;
   const EnvOptions options;
   Status s = env->NewSequentialFile(filename, &orig_file, options);
   if (!s.ok()) {
-    fprintf(stderr, "Cannot truncate file %s: %s\n", filename.c_str(),
-            s.ToString().c_str());
+    fprintf(stderr, "Cannot open file %s for truncation: %s\n",
+            filename.c_str(), s.ToString().c_str());
     return s;
   }
 
@@ -46,7 +46,7 @@ Status Truncate(Env* env, const std::string& filename, uint64_t length) {
 #endif
   if (s.ok()) {
     std::string tmp_name = GetDirName(filename) + "/truncate.tmp";
-    unique_ptr<WritableFile> tmp_file;
+    std::unique_ptr<WritableFile> tmp_file;
     s = env->NewWritableFile(tmp_name, &tmp_file, options);
     if (s.ok()) {
       s = tmp_file->Append(result);
@@ -103,7 +103,7 @@ Status TestDirectory::Fsync() {
 }
 
 TestWritableFile::TestWritableFile(const std::string& fname,
-                                   unique_ptr<WritableFile>&& f,
+                                   std::unique_ptr<WritableFile>&& f,
                                    FaultInjectionTestEnv* env)
     : state_(fname),
       target_(std::move(f)),
@@ -157,8 +157,8 @@ Status TestWritableFile::Sync() {
 }
 
 Status FaultInjectionTestEnv::NewDirectory(const std::string& name,
-                                           unique_ptr<Directory>* result) {
-  unique_ptr<Directory> r;
+                                           std::unique_ptr<Directory>* result) {
+  std::unique_ptr<Directory> r;
   Status s = target()->NewDirectory(name, &r);
   assert(s.ok());
   if (!s.ok()) {
@@ -168,9 +168,9 @@ Status FaultInjectionTestEnv::NewDirectory(const std::string& name,
   return Status::OK();
 }
 
-Status FaultInjectionTestEnv::NewWritableFile(const std::string& fname,
-                                              unique_ptr<WritableFile>* result,
-                                              const EnvOptions& soptions) {
+Status FaultInjectionTestEnv::NewWritableFile(
+    const std::string& fname, std::unique_ptr<WritableFile>* result,
+    const EnvOptions& soptions) {
   if (!IsFilesystemActive()) {
     return GetError();
   }
@@ -197,6 +197,36 @@ Status FaultInjectionTestEnv::NewWritableFile(const std::string& fname,
   return s;
 }
 
+Status FaultInjectionTestEnv::ReopenWritableFile(
+    const std::string& fname, std::unique_ptr<WritableFile>* result,
+    const EnvOptions& soptions) {
+  if (!IsFilesystemActive()) {
+    return GetError();
+  }
+  Status s = target()->ReopenWritableFile(fname, result, soptions);
+  if (s.ok()) {
+    result->reset(new TestWritableFile(fname, std::move(*result), this));
+    // WritableFileWriter* file is opened
+    // again then it will be truncated - so forget our saved state.
+    UntrackFile(fname);
+    MutexLock l(&mutex_);
+    open_files_.insert(fname);
+    auto dir_and_name = GetDirAndName(fname);
+    auto& list = dir_to_new_files_since_last_sync_[dir_and_name.first];
+    list.insert(dir_and_name.second);
+  }
+  return s;
+}
+
+Status FaultInjectionTestEnv::NewRandomAccessFile(
+    const std::string& fname, std::unique_ptr<RandomAccessFile>* result,
+    const EnvOptions& soptions) {
+  if (!IsFilesystemActive()) {
+    return GetError();
+  }
+  return target()->NewRandomAccessFile(fname, result, soptions);
+}
+
 Status FaultInjectionTestEnv::DeleteFile(const std::string& f) {
   if (!IsFilesystemActive()) {
     return GetError();
diff --git a/3rdParty/rocksdb/v5.16.X/util/fault_injection_test_env.h b/3rdParty/rocksdb/v5.18.X/util/fault_injection_test_env.h
similarity index 83%
rename from 3rdParty/rocksdb/v5.16.X/util/fault_injection_test_env.h
rename to 3rdParty/rocksdb/v5.18.X/util/fault_injection_test_env.h
index 1a62c619e8..d3775d3a3f 100644
--- a/3rdParty/rocksdb/v5.16.X/util/fault_injection_test_env.h
+++ b/3rdParty/rocksdb/v5.18.X/util/fault_injection_test_env.h
@@ -11,8 +11,7 @@
 // the last "sync". It then checks for data loss errors by purposely dropping
 // file data (or entire files) not protected by a "sync".
 
-#ifndef UTIL_FAULT_INJECTION_TEST_ENV_H_
-#define UTIL_FAULT_INJECTION_TEST_ENV_H_
+#pragma once
 
 #include <map>
 #include <set>
@@ -57,7 +56,7 @@ struct FileState {
 class TestWritableFile : public WritableFile {
  public:
   explicit TestWritableFile(const std::string& fname,
-                            unique_ptr<WritableFile>&& f,
+                            std::unique_ptr<WritableFile>&& f,
                             FaultInjectionTestEnv* env);
   virtual ~TestWritableFile();
   virtual Status Append(const Slice& data) override;
@@ -78,7 +77,7 @@ class TestWritableFile : public WritableFile {
 
  private:
   FileState state_;
-  unique_ptr<WritableFile> target_;
+  std::unique_ptr<WritableFile> target_;
   bool writable_file_opened_;
   FaultInjectionTestEnv* env_;
 };
@@ -95,7 +94,7 @@ class TestDirectory : public Directory {
  private:
   FaultInjectionTestEnv* env_;
   std::string dirname_;
-  unique_ptr<Directory> dir_;
+  std::unique_ptr<Directory> dir_;
 };
 
 class FaultInjectionTestEnv : public EnvWrapper {
@@ -105,17 +104,35 @@ class FaultInjectionTestEnv : public EnvWrapper {
   virtual ~FaultInjectionTestEnv() {}
 
   Status NewDirectory(const std::string& name,
-                      unique_ptr<Directory>* result) override;
+                      std::unique_ptr<Directory>* result) override;
 
   Status NewWritableFile(const std::string& fname,
-                         unique_ptr<WritableFile>* result,
+                         std::unique_ptr<WritableFile>* result,
                          const EnvOptions& soptions) override;
 
+  Status ReopenWritableFile(const std::string& fname,
+                            std::unique_ptr<WritableFile>* result,
+                            const EnvOptions& soptions) override;
+
+  Status NewRandomAccessFile(const std::string& fname,
+                             std::unique_ptr<RandomAccessFile>* result,
+                             const EnvOptions& soptions) override;
+
   virtual Status DeleteFile(const std::string& f) override;
 
   virtual Status RenameFile(const std::string& s,
                             const std::string& t) override;
 
+  virtual Status GetFreeSpace(const std::string& path,
+                              uint64_t* disk_free) override {
+    if (!IsFilesystemActive() && error_ == Status::NoSpace()) {
+      *disk_free = 0;
+      return Status::OK();
+    } else {
+      return target()->GetFreeSpace(path, disk_free);
+    }
+  }
+
   void WritableFileClosed(const FileState& state);
 
   // For every file that is not fully synced, make a call to `func` with
@@ -171,5 +188,3 @@ class FaultInjectionTestEnv : public EnvWrapper {
 };
 
 }  // namespace rocksdb
-
-#endif  // UTIL_FAULT_INJECTION_TEST_ENV_H_
diff --git a/3rdParty/rocksdb/v5.16.X/util/file_reader_writer.cc b/3rdParty/rocksdb/v5.18.X/util/file_reader_writer.cc
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/util/file_reader_writer.cc
rename to 3rdParty/rocksdb/v5.18.X/util/file_reader_writer.cc
index f0bbb52829..821d657b0a 100644
--- a/3rdParty/rocksdb/v5.16.X/util/file_reader_writer.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/file_reader_writer.cc
@@ -62,7 +62,7 @@ Status SequentialFileReader::Read(size_t n, Slice* result, char* scratch) {
 Status SequentialFileReader::Skip(uint64_t n) {
 #ifndef ROCKSDB_LITE
   if (use_direct_io()) {
-    offset_ += n;
+    offset_ += static_cast<size_t>(n);
     return Status::OK();
   }
 #endif  // !ROCKSDB_LITE
@@ -81,9 +81,9 @@ Status RandomAccessFileReader::Read(uint64_t offset, size_t n, Slice* result,
     if (use_direct_io()) {
 #ifndef ROCKSDB_LITE
       size_t alignment = file_->GetRequiredBufferAlignment();
-      size_t aligned_offset = TruncateToPageBoundary(alignment, offset);
-      size_t offset_advance = offset - aligned_offset;
-      size_t read_size = Roundup(offset + n, alignment) - aligned_offset;
+      size_t aligned_offset = TruncateToPageBoundary(alignment, static_cast<size_t>(offset));
+      size_t offset_advance = static_cast<size_t>(offset) - aligned_offset;
+      size_t read_size = Roundup(static_cast<size_t>(offset + n), alignment) - aligned_offset;
       AlignedBuffer buf;
       buf.Alignment(alignment);
       buf.AllocateNewBuffer(read_size);
@@ -98,8 +98,20 @@ Status RandomAccessFileReader::Read(uint64_t offset, size_t n, Slice* result,
           allowed = read_size;
         }
         Slice tmp;
+
+        time_t start_ts = 0;
+        uint64_t orig_offset = 0;
+        if (ShouldNotifyListeners()) {
+          start_ts = std::chrono::system_clock::to_time_t(
+              std::chrono::system_clock::now());
+          orig_offset = aligned_offset + buf.CurrentSize();
+        }
         s = file_->Read(aligned_offset + buf.CurrentSize(), allowed, &tmp,
                         buf.Destination());
+        if (ShouldNotifyListeners()) {
+          NotifyOnFileReadFinish(orig_offset, tmp.size(), start_ts, s);
+        }
+
         buf.Size(buf.CurrentSize() + tmp.size());
         if (!s.ok() || tmp.size() < allowed) {
           break;
@@ -131,7 +143,21 @@ Status RandomAccessFileReader::Read(uint64_t offset, size_t n, Slice* result,
           allowed = n;
         }
         Slice tmp_result;
+
+#ifndef ROCKSDB_LITE
+        time_t start_ts = 0;
+        if (ShouldNotifyListeners()) {
+          start_ts = std::chrono::system_clock::to_time_t(
+              std::chrono::system_clock::now());
+        }
+#endif
         s = file_->Read(offset + pos, allowed, &tmp_result, scratch + pos);
+#ifndef ROCKSDB_LITE
+        if (ShouldNotifyListeners()) {
+          NotifyOnFileReadFinish(offset + pos, tmp_result.size(), start_ts, s);
+        }
+#endif
+
         if (res_scratch == nullptr) {
           // we can't simply use `scratch` because reads of mmap'd files return
           // data in a different buffer.
@@ -414,7 +440,22 @@ Status WritableFileWriter::WriteBuffered(const char* data, size_t size) {
     {
       IOSTATS_TIMER_GUARD(write_nanos);
       TEST_SYNC_POINT("WritableFileWriter::Flush:BeforeAppend");
+
+#ifndef ROCKSDB_LITE
+      time_t start_ts = 0;
+      uint64_t old_size = writable_file_->GetFileSize();
+      if (ShouldNotifyListeners()) {
+        start_ts = std::chrono::system_clock::to_time_t(
+            std::chrono::system_clock::now());
+        old_size = next_write_offset_;
+      }
+#endif
       s = writable_file_->Append(Slice(src, allowed));
+#ifndef ROCKSDB_LITE
+      if (ShouldNotifyListeners()) {
+        NotifyOnFileWriteFinish(old_size, allowed, start_ts, s);
+      }
+#endif
       if (!s.ok()) {
         return s;
       }
@@ -477,8 +518,16 @@ Status WritableFileWriter::WriteDirect() {
     {
       IOSTATS_TIMER_GUARD(write_nanos);
       TEST_SYNC_POINT("WritableFileWriter::Flush:BeforeAppend");
+      time_t start_ts(0);
+      if (ShouldNotifyListeners()) {
+        start_ts = std::chrono::system_clock::to_time_t(
+            std::chrono::system_clock::now());
+      }
       // direct writes must be positional
       s = writable_file_->PositionedAppend(Slice(src, size), write_offset);
+      if (ShouldNotifyListeners()) {
+        NotifyOnFileWriteFinish(write_offset, size, start_ts, s);
+      }
       if (!s.ok()) {
         buf_.Size(file_advance + leftover_tail);
         return s;
@@ -673,7 +722,7 @@ Status FilePrefetchBuffer::Prefetch(RandomAccessFileReader* reader,
       // Only a few requested bytes are in the buffer. memmove those chunk of
       // bytes to the beginning, and memcpy them back into the new buffer if a
       // new buffer is created.
-      chunk_offset_in_buffer = Rounddown(offset - buffer_offset_, alignment);
+      chunk_offset_in_buffer = Rounddown(static_cast<size_t>(offset - buffer_offset_), alignment);
       chunk_len = buffer_.CurrentSize() - chunk_offset_in_buffer;
       assert(chunk_offset_in_buffer % alignment == 0);
       assert(chunk_len % alignment == 0);
@@ -694,11 +743,11 @@ Status FilePrefetchBuffer::Prefetch(RandomAccessFileReader* reader,
     buffer_.Alignment(alignment);
     buffer_.AllocateNewBuffer(static_cast<size_t>(roundup_len),
                               copy_data_to_new_buffer, chunk_offset_in_buffer,
-                              chunk_len);
+                              static_cast<size_t>(chunk_len));
   } else if (chunk_len > 0) {
     // New buffer not needed. But memmove bytes from tail to the beginning since
     // chunk_len is greater than 0.
-    buffer_.RefitTail(chunk_offset_in_buffer, chunk_len);
+    buffer_.RefitTail(static_cast<size_t>(chunk_offset_in_buffer), static_cast<size_t>(chunk_len));
   }
 
   Slice result;
@@ -707,7 +756,7 @@ Status FilePrefetchBuffer::Prefetch(RandomAccessFileReader* reader,
                    buffer_.BufferStart() + chunk_len);
   if (s.ok()) {
     buffer_offset_ = rounddown_offset;
-    buffer_.Size(chunk_len + result.size());
+    buffer_.Size(static_cast<size_t>(chunk_len) + result.size());
   }
   return s;
 }
@@ -715,7 +764,7 @@ Status FilePrefetchBuffer::Prefetch(RandomAccessFileReader* reader,
 bool FilePrefetchBuffer::TryReadFromCache(uint64_t offset, size_t n,
                                           Slice* result) {
   if (track_min_offset_ && offset < min_offset_read_) {
-    min_offset_read_ = offset;
+    min_offset_read_ = static_cast<size_t>(offset);
   }
   if (!enable_ || offset < buffer_offset_) {
     return false;
@@ -753,7 +802,7 @@ std::unique_ptr<RandomAccessFile> NewReadaheadRandomAccessFile(
 }
 
 Status NewWritableFile(Env* env, const std::string& fname,
-                       unique_ptr<WritableFile>* result,
+                       std::unique_ptr<WritableFile>* result,
                        const EnvOptions& options) {
   Status s = env->NewWritableFile(fname, result, options);
   TEST_KILL_RANDOM("NewWritableFile:0", rocksdb_kill_odds * REDUCE_ODDS2);
diff --git a/3rdParty/rocksdb/v5.16.X/util/file_reader_writer.h b/3rdParty/rocksdb/v5.18.X/util/file_reader_writer.h
similarity index 72%
rename from 3rdParty/rocksdb/v5.16.X/util/file_reader_writer.h
rename to 3rdParty/rocksdb/v5.18.X/util/file_reader_writer.h
index 93155fa3c5..ec7acebcc4 100644
--- a/3rdParty/rocksdb/v5.16.X/util/file_reader_writer.h
+++ b/3rdParty/rocksdb/v5.18.X/util/file_reader_writer.h
@@ -12,6 +12,7 @@
 #include <string>
 #include "port/port.h"
 #include "rocksdb/env.h"
+#include "rocksdb/listener.h"
 #include "rocksdb/rate_limiter.h"
 #include "util/aligned_buffer.h"
 #include "util/sync_point.h"
@@ -62,6 +63,26 @@ class SequentialFileReader {
 
 class RandomAccessFileReader {
  private:
+#ifndef ROCKSDB_LITE
+  void NotifyOnFileReadFinish(uint64_t offset, size_t length, time_t start_ts,
+                              const Status& status) const {
+    FileOperationInfo info(file_name_);
+    info.offset = offset;
+    info.length = length;
+    info.start_timestamp = start_ts;
+    time_t finish_ts =
+        std::chrono::system_clock::to_time_t(std::chrono::system_clock::now());
+    info.finish_timestamp = finish_ts;
+    info.status = status;
+
+    for (auto& listener : listeners_) {
+      listener->OnFileReadFinish(info);
+    }
+  }
+#endif  // ROCKSDB_LITE
+
+  bool ShouldNotifyListeners() const { return !listeners_.empty(); }
+
   std::unique_ptr<RandomAccessFile> file_;
   std::string     file_name_;
   Env*            env_;
@@ -70,16 +91,15 @@ class RandomAccessFileReader {
   HistogramImpl*  file_read_hist_;
   RateLimiter* rate_limiter_;
   bool for_compaction_;
+  std::vector<std::shared_ptr<EventListener>> listeners_;
 
  public:
-  explicit RandomAccessFileReader(std::unique_ptr<RandomAccessFile>&& raf,
-                                  std::string _file_name,
-                                  Env* env = nullptr,
-                                  Statistics* stats = nullptr,
-                                  uint32_t hist_type = 0,
-                                  HistogramImpl* file_read_hist = nullptr,
-                                  RateLimiter* rate_limiter = nullptr,
-                                  bool for_compaction = false)
+  explicit RandomAccessFileReader(
+      std::unique_ptr<RandomAccessFile>&& raf, std::string _file_name,
+      Env* env = nullptr, Statistics* stats = nullptr, uint32_t hist_type = 0,
+      HistogramImpl* file_read_hist = nullptr,
+      RateLimiter* rate_limiter = nullptr, bool for_compaction = false,
+      const std::vector<std::shared_ptr<EventListener>>& listeners = {})
       : file_(std::move(raf)),
         file_name_(std::move(_file_name)),
         env_(env),
@@ -87,7 +107,19 @@ class RandomAccessFileReader {
         hist_type_(hist_type),
         file_read_hist_(file_read_hist),
         rate_limiter_(rate_limiter),
-        for_compaction_(for_compaction) {}
+        for_compaction_(for_compaction),
+        listeners_() {
+#ifndef ROCKSDB_LITE
+    std::for_each(listeners.begin(), listeners.end(),
+                  [this](const std::shared_ptr<EventListener>& e) {
+                    if (e->ShouldBeNotifiedOnFileIO()) {
+                      listeners_.emplace_back(e);
+                    }
+                  });
+#else  // !ROCKSDB_LITE
+    (void)listeners;
+#endif
+  }
 
   RandomAccessFileReader(RandomAccessFileReader&& o) ROCKSDB_NOEXCEPT {
     *this = std::move(o);
@@ -124,7 +156,28 @@ class RandomAccessFileReader {
 // Use posix write to write data to a file.
 class WritableFileWriter {
  private:
+#ifndef ROCKSDB_LITE
+  void NotifyOnFileWriteFinish(uint64_t offset, size_t length, time_t start_ts,
+                               const Status& status) {
+    FileOperationInfo info(file_name_);
+    info.offset = offset;
+    info.length = length;
+    info.start_timestamp = start_ts;
+    time_t finish_ts =
+        std::chrono::system_clock::to_time_t(std::chrono::system_clock::now());
+    info.finish_timestamp = finish_ts;
+    info.status = status;
+
+    for (auto& listener : listeners_) {
+      listener->OnFileWriteFinish(info);
+    }
+  }
+#endif  // ROCKSDB_LITE
+
+  bool ShouldNotifyListeners() const { return !listeners_.empty(); }
+
   std::unique_ptr<WritableFile> writable_file_;
+  std::string file_name_;
   AlignedBuffer           buf_;
   size_t                  max_buffer_size_;
   // Actually written data size can be used for truncate
@@ -141,11 +194,15 @@ class WritableFileWriter {
   uint64_t                bytes_per_sync_;
   RateLimiter*            rate_limiter_;
   Statistics* stats_;
+  std::vector<std::shared_ptr<EventListener>> listeners_;
 
  public:
-  WritableFileWriter(std::unique_ptr<WritableFile>&& file,
-                     const EnvOptions& options, Statistics* stats = nullptr)
+  WritableFileWriter(
+      std::unique_ptr<WritableFile>&& file, const std::string& _file_name,
+      const EnvOptions& options, Statistics* stats = nullptr,
+      const std::vector<std::shared_ptr<EventListener>>& listeners = {})
       : writable_file_(std::move(file)),
+        file_name_(_file_name),
         buf_(),
         max_buffer_size_(options.writable_file_max_buffer_size),
         filesize_(0),
@@ -156,11 +213,22 @@ class WritableFileWriter {
         last_sync_size_(0),
         bytes_per_sync_(options.bytes_per_sync),
         rate_limiter_(options.rate_limiter),
-        stats_(stats) {
+        stats_(stats),
+        listeners_() {
     TEST_SYNC_POINT_CALLBACK("WritableFileWriter::WritableFileWriter:0",
                              reinterpret_cast<void*>(max_buffer_size_));
     buf_.Alignment(writable_file_->GetRequiredBufferAlignment());
     buf_.AllocateNewBuffer(std::min((size_t)65536, max_buffer_size_));
+#ifndef ROCKSDB_LITE
+    std::for_each(listeners.begin(), listeners.end(),
+                  [this](const std::shared_ptr<EventListener>& e) {
+                    if (e->ShouldBeNotifiedOnFileIO()) {
+                      listeners_.emplace_back(e);
+                    }
+                  });
+#else  // !ROCKSDB_LITE
+    (void)listeners;
+#endif
   }
 
   WritableFileWriter(const WritableFileWriter&) = delete;
@@ -169,6 +237,8 @@ class WritableFileWriter {
 
   ~WritableFileWriter() { Close(); }
 
+  std::string file_name() const { return file_name_; }
+
   Status Append(const Slice& data);
 
   Status Pad(const size_t pad_bytes);
@@ -249,7 +319,7 @@ class FilePrefetchBuffer {
 };
 
 extern Status NewWritableFile(Env* env, const std::string& fname,
-                              unique_ptr<WritableFile>* result,
+                              std::unique_ptr<WritableFile>* result,
                               const EnvOptions& options);
 bool ReadOneLine(std::istringstream* iss, SequentialFile* seq_file,
                  std::string* output, bool* has_data, Status* result);
diff --git a/3rdParty/rocksdb/v5.16.X/util/file_reader_writer_test.cc b/3rdParty/rocksdb/v5.18.X/util/file_reader_writer_test.cc
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/util/file_reader_writer_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/file_reader_writer_test.cc
index 4425f87a0a..72dd625c1f 100644
--- a/3rdParty/rocksdb/v5.16.X/util/file_reader_writer_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/file_reader_writer_test.cc
@@ -71,9 +71,9 @@ TEST_F(WritableFileWriterTest, RangeSync) {
 
   EnvOptions env_options;
   env_options.bytes_per_sync = kMb;
-  unique_ptr<FakeWF> wf(new FakeWF);
-  unique_ptr<WritableFileWriter> writer(
-      new WritableFileWriter(std::move(wf), env_options));
+  std::unique_ptr<FakeWF> wf(new FakeWF);
+  std::unique_ptr<WritableFileWriter> writer(
+      new WritableFileWriter(std::move(wf), "" /* don't care */, env_options));
   Random r(301);
   std::unique_ptr<char[]> large_buf(new char[10 * kMb]);
   for (int i = 0; i < 1000; i++) {
@@ -147,15 +147,15 @@ TEST_F(WritableFileWriterTest, IncrementalBuffer) {
     env_options.writable_file_max_buffer_size =
         (attempt < kNumAttempts / 2) ? 512 * 1024 : 700 * 1024;
     std::string actual;
-    unique_ptr<FakeWF> wf(new FakeWF(&actual,
+    std::unique_ptr<FakeWF> wf(new FakeWF(&actual,
 #ifndef ROCKSDB_LITE
-                                     attempt % 2 == 1,
+                                          attempt % 2 == 1,
 #else
-                                     false,
+                                          false,
 #endif
-                                     no_flush));
-    unique_ptr<WritableFileWriter> writer(
-        new WritableFileWriter(std::move(wf), env_options));
+                                          no_flush));
+    std::unique_ptr<WritableFileWriter> writer(new WritableFileWriter(
+        std::move(wf), "" /* don't care */, env_options));
 
     std::string target;
     for (int i = 0; i < 20; i++) {
@@ -206,10 +206,10 @@ TEST_F(WritableFileWriterTest, AppendStatusReturn) {
     bool use_direct_io_;
     bool io_error_;
   };
-  unique_ptr<FakeWF> wf(new FakeWF());
+  std::unique_ptr<FakeWF> wf(new FakeWF());
   wf->Setuse_direct_io(true);
-  unique_ptr<WritableFileWriter> writer(
-      new WritableFileWriter(std::move(wf), EnvOptions()));
+  std::unique_ptr<WritableFileWriter> writer(
+      new WritableFileWriter(std::move(wf), "" /* don't care */, EnvOptions()));
 
   ASSERT_OK(writer->Append(std::string(2 * kMb, 'a')));
 
@@ -238,8 +238,9 @@ class ReadaheadRandomAccessFileTest
     return std::string(result.data(), result.size());
   }
   void ResetSourceStr(const std::string& str = "") {
-    auto write_holder = std::unique_ptr<WritableFileWriter>(
-        test::GetWritableFileWriter(new test::StringSink(&control_contents_)));
+    auto write_holder =
+        std::unique_ptr<WritableFileWriter>(test::GetWritableFileWriter(
+            new test::StringSink(&control_contents_), "" /* don't care */));
     write_holder->Append(Slice(str));
     write_holder->Flush();
     auto read_holder = std::unique_ptr<RandomAccessFile>(
diff --git a/3rdParty/rocksdb/v5.16.X/util/file_util.cc b/3rdParty/rocksdb/v5.18.X/util/file_util.cc
similarity index 78%
rename from 3rdParty/rocksdb/v5.16.X/util/file_util.cc
rename to 3rdParty/rocksdb/v5.18.X/util/file_util.cc
index ee8b3fb537..bf56592efc 100644
--- a/3rdParty/rocksdb/v5.16.X/util/file_util.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/file_util.cc
@@ -19,16 +19,16 @@ Status CopyFile(Env* env, const std::string& source,
                 const std::string& destination, uint64_t size, bool use_fsync) {
   const EnvOptions soptions;
   Status s;
-  unique_ptr<SequentialFileReader> src_reader;
-  unique_ptr<WritableFileWriter> dest_writer;
+  std::unique_ptr<SequentialFileReader> src_reader;
+  std::unique_ptr<WritableFileWriter> dest_writer;
 
   {
-    unique_ptr<SequentialFile> srcfile;
+    std::unique_ptr<SequentialFile> srcfile;
     s = env->NewSequentialFile(source, &srcfile, soptions);
     if (!s.ok()) {
       return s;
     }
-    unique_ptr<WritableFile> destfile;
+    std::unique_ptr<WritableFile> destfile;
     s = env->NewWritableFile(destination, &destfile, soptions);
     if (!s.ok()) {
       return s;
@@ -42,7 +42,8 @@ Status CopyFile(Env* env, const std::string& source,
       }
     }
     src_reader.reset(new SequentialFileReader(std::move(srcfile), source));
-    dest_writer.reset(new WritableFileWriter(std::move(destfile), soptions));
+    dest_writer.reset(
+        new WritableFileWriter(std::move(destfile), destination, soptions));
   }
 
   char buffer[4096];
@@ -67,18 +68,23 @@ Status CopyFile(Env* env, const std::string& source,
 
 // Utility function to create a file with the provided contents
 Status CreateFile(Env* env, const std::string& destination,
-                  const std::string& contents) {
+                  const std::string& contents, bool use_fsync) {
   const EnvOptions soptions;
   Status s;
-  unique_ptr<WritableFileWriter> dest_writer;
+  std::unique_ptr<WritableFileWriter> dest_writer;
 
-  unique_ptr<WritableFile> destfile;
+  std::unique_ptr<WritableFile> destfile;
   s = env->NewWritableFile(destination, &destfile, soptions);
   if (!s.ok()) {
     return s;
   }
-  dest_writer.reset(new WritableFileWriter(std::move(destfile), soptions));
-  return dest_writer->Append(Slice(contents));
+  dest_writer.reset(
+      new WritableFileWriter(std::move(destfile), destination, soptions));
+  s = dest_writer->Append(Slice(contents));
+  if (!s.ok()) {
+    return s;
+  }
+  return dest_writer->Sync(use_fsync);
 }
 
 Status DeleteSSTFile(const ImmutableDBOptions* db_options,
diff --git a/3rdParty/rocksdb/v5.16.X/util/file_util.h b/3rdParty/rocksdb/v5.18.X/util/file_util.h
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/util/file_util.h
rename to 3rdParty/rocksdb/v5.18.X/util/file_util.h
index 4df597275b..5c05c9def6 100644
--- a/3rdParty/rocksdb/v5.16.X/util/file_util.h
+++ b/3rdParty/rocksdb/v5.18.X/util/file_util.h
@@ -19,7 +19,7 @@ extern Status CopyFile(Env* env, const std::string& source,
                        bool use_fsync);
 
 extern Status CreateFile(Env* env, const std::string& destination,
-                         const std::string& contents);
+                         const std::string& contents, bool use_fsync);
 
 extern Status DeleteSSTFile(const ImmutableDBOptions* db_options,
                             const std::string& fname,
diff --git a/3rdParty/rocksdb/v5.16.X/util/filelock_test.cc b/3rdParty/rocksdb/v5.18.X/util/filelock_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/filelock_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/filelock_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/filename.cc b/3rdParty/rocksdb/v5.18.X/util/filename.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/util/filename.cc
rename to 3rdParty/rocksdb/v5.18.X/util/filename.cc
index 759b22a16c..32289aecb4 100644
--- a/3rdParty/rocksdb/v5.16.X/util/filename.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/filename.cc
@@ -80,6 +80,13 @@ std::string BlobFileName(const std::string& blobdirname, uint64_t number) {
   return MakeFileName(blobdirname, number, kRocksDBBlobFileExt.c_str());
 }
 
+std::string BlobFileName(const std::string& dbname, const std::string& blob_dir,
+                         uint64_t number) {
+  assert(number > 0);
+  return MakeFileName(dbname + "/" + blob_dir, number,
+                      kRocksDBBlobFileExt.c_str());
+}
+
 std::string ArchivalDirectory(const std::string& dir) {
   return dir + "/" + ARCHIVAL_DIR;
 }
diff --git a/3rdParty/rocksdb/v5.16.X/util/filename.h b/3rdParty/rocksdb/v5.18.X/util/filename.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/util/filename.h
rename to 3rdParty/rocksdb/v5.18.X/util/filename.h
index 0d4bacf536..eea6b1b02f 100644
--- a/3rdParty/rocksdb/v5.16.X/util/filename.h
+++ b/3rdParty/rocksdb/v5.18.X/util/filename.h
@@ -49,6 +49,9 @@ extern std::string LogFileName(const std::string& dbname, uint64_t number);
 
 extern std::string BlobFileName(const std::string& bdirname, uint64_t number);
 
+extern std::string BlobFileName(const std::string& dbname,
+                                const std::string& blob_dir, uint64_t number);
+
 static const std::string ARCHIVAL_DIR = "archive";
 
 extern std::string ArchivalDirectory(const std::string& dbname);
diff --git a/3rdParty/rocksdb/v5.16.X/util/filter_policy.cc b/3rdParty/rocksdb/v5.18.X/util/filter_policy.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/filter_policy.cc
rename to 3rdParty/rocksdb/v5.18.X/util/filter_policy.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/gflags_compat.h b/3rdParty/rocksdb/v5.18.X/util/gflags_compat.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/gflags_compat.h
rename to 3rdParty/rocksdb/v5.18.X/util/gflags_compat.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/hash.cc b/3rdParty/rocksdb/v5.18.X/util/hash.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/hash.cc
rename to 3rdParty/rocksdb/v5.18.X/util/hash.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/hash.h b/3rdParty/rocksdb/v5.18.X/util/hash.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/hash.h
rename to 3rdParty/rocksdb/v5.18.X/util/hash.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/hash_map.h b/3rdParty/rocksdb/v5.18.X/util/hash_map.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/hash_map.h
rename to 3rdParty/rocksdb/v5.18.X/util/hash_map.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/hash_test.cc b/3rdParty/rocksdb/v5.18.X/util/hash_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/hash_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/hash_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/heap.h b/3rdParty/rocksdb/v5.18.X/util/heap.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/util/heap.h
rename to 3rdParty/rocksdb/v5.18.X/util/heap.h
index 4d5894134f..6093c20e2b 100644
--- a/3rdParty/rocksdb/v5.16.X/util/heap.h
+++ b/3rdParty/rocksdb/v5.18.X/util/heap.h
@@ -92,9 +92,9 @@ class BinaryHeap {
     reset_root_cmp_cache();
   }
 
-  bool empty() const {
-    return data_.empty();
-  }
+  bool empty() const { return data_.empty(); }
+
+  size_t size() const { return data_.size(); }
 
   void reset_root_cmp_cache() { root_cmp_cache_ = port::kMaxSizet; }
 
diff --git a/3rdParty/rocksdb/v5.16.X/util/heap_test.cc b/3rdParty/rocksdb/v5.18.X/util/heap_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/heap_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/heap_test.cc
diff --git a/3rdParty/rocksdb/v5.18.X/util/jemalloc_nodump_allocator.cc b/3rdParty/rocksdb/v5.18.X/util/jemalloc_nodump_allocator.cc
new file mode 100644
index 0000000000..1db939b4f8
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/util/jemalloc_nodump_allocator.cc
@@ -0,0 +1,202 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "util/jemalloc_nodump_allocator.h"
+
+#include <string>
+#include <thread>
+
+#include "port/likely.h"
+#include "port/port.h"
+#include "util/string_util.h"
+
+namespace rocksdb {
+
+#ifdef ROCKSDB_JEMALLOC_NODUMP_ALLOCATOR
+
+std::atomic<extent_alloc_t*> JemallocNodumpAllocator::original_alloc_{nullptr};
+
+JemallocNodumpAllocator::JemallocNodumpAllocator(
+    JemallocAllocatorOptions& options,
+    std::unique_ptr<extent_hooks_t>&& arena_hooks, unsigned arena_index)
+    : options_(options),
+      arena_hooks_(std::move(arena_hooks)),
+      arena_index_(arena_index),
+      tcache_(&JemallocNodumpAllocator::DestroyThreadSpecificCache) {}
+
+int JemallocNodumpAllocator::GetThreadSpecificCache(size_t size) {
+  // We always enable tcache. The only corner case is when there are a ton of
+  // threads accessing with low frequency, then it could consume a lot of
+  // memory (may reach # threads * ~1MB) without bringing too much benefit.
+  if (options_.limit_tcache_size && (size <= options_.tcache_size_lower_bound ||
+                                     size > options_.tcache_size_upper_bound)) {
+    return MALLOCX_TCACHE_NONE;
+  }
+  unsigned* tcache_index = reinterpret_cast<unsigned*>(tcache_.Get());
+  if (UNLIKELY(tcache_index == nullptr)) {
+    // Instantiate tcache.
+    tcache_index = new unsigned(0);
+    size_t tcache_index_size = sizeof(unsigned);
+    int ret =
+        mallctl("tcache.create", tcache_index, &tcache_index_size, nullptr, 0);
+    if (ret != 0) {
+      // No good way to expose the error. Silently disable tcache.
+      delete tcache_index;
+      return MALLOCX_TCACHE_NONE;
+    }
+    tcache_.Reset(static_cast<void*>(tcache_index));
+  }
+  return MALLOCX_TCACHE(*tcache_index);
+}
+
+void* JemallocNodumpAllocator::Allocate(size_t size) {
+  int tcache_flag = GetThreadSpecificCache(size);
+  return mallocx(size, MALLOCX_ARENA(arena_index_) | tcache_flag);
+}
+
+void JemallocNodumpAllocator::Deallocate(void* p) {
+  // Obtain tcache.
+  size_t size = 0;
+  if (options_.limit_tcache_size) {
+    size = malloc_usable_size(p);
+  }
+  int tcache_flag = GetThreadSpecificCache(size);
+  // No need to pass arena index to dallocx(). Jemalloc will find arena index
+  // from its own metadata.
+  dallocx(p, tcache_flag);
+}
+
+void* JemallocNodumpAllocator::Alloc(extent_hooks_t* extent, void* new_addr,
+                                     size_t size, size_t alignment, bool* zero,
+                                     bool* commit, unsigned arena_ind) {
+  extent_alloc_t* original_alloc =
+      original_alloc_.load(std::memory_order_relaxed);
+  assert(original_alloc != nullptr);
+  void* result = original_alloc(extent, new_addr, size, alignment, zero, commit,
+                                arena_ind);
+  if (result != nullptr) {
+    int ret = madvise(result, size, MADV_DONTDUMP);
+    if (ret != 0) {
+      fprintf(
+          stderr,
+          "JemallocNodumpAllocator failed to set MADV_DONTDUMP, error code: %d",
+          ret);
+      assert(false);
+    }
+  }
+  return result;
+}
+
+Status JemallocNodumpAllocator::DestroyArena(unsigned arena_index) {
+  assert(arena_index != 0);
+  std::string key = "arena." + ToString(arena_index) + ".destroy";
+  int ret = mallctl(key.c_str(), nullptr, 0, nullptr, 0);
+  if (ret != 0) {
+    return Status::Incomplete("Failed to destroy jemalloc arena, error code: " +
+                              ToString(ret));
+  }
+  return Status::OK();
+}
+
+void JemallocNodumpAllocator::DestroyThreadSpecificCache(void* ptr) {
+  assert(ptr != nullptr);
+  unsigned* tcache_index = static_cast<unsigned*>(ptr);
+  size_t tcache_index_size = sizeof(unsigned);
+  int ret __attribute__((__unused__)) =
+      mallctl("tcache.destroy", nullptr, 0, tcache_index, tcache_index_size);
+  // Silently ignore error.
+  assert(ret == 0);
+  delete tcache_index;
+}
+
+JemallocNodumpAllocator::~JemallocNodumpAllocator() {
+  // Destroy tcache before destroying arena.
+  autovector<void*> tcache_list;
+  tcache_.Scrape(&tcache_list, nullptr);
+  for (void* tcache_index : tcache_list) {
+    DestroyThreadSpecificCache(tcache_index);
+  }
+  // Destroy arena. Silently ignore error.
+  Status s __attribute__((__unused__)) = DestroyArena(arena_index_);
+  assert(s.ok());
+}
+
+size_t JemallocNodumpAllocator::UsableSize(void* p,
+                                           size_t /*allocation_size*/) const {
+  return malloc_usable_size(static_cast<void*>(p));
+}
+#endif  // ROCKSDB_JEMALLOC_NODUMP_ALLOCATOR
+
+Status NewJemallocNodumpAllocator(
+    JemallocAllocatorOptions& options,
+    std::shared_ptr<MemoryAllocator>* memory_allocator) {
+  *memory_allocator = nullptr;
+#ifndef ROCKSDB_JEMALLOC_NODUMP_ALLOCATOR
+  (void) options;
+  return Status::NotSupported(
+      "JemallocNodumpAllocator only available with jemalloc version >= 5 "
+      "and MADV_DONTDUMP is available.");
+#else
+  if (memory_allocator == nullptr) {
+    return Status::InvalidArgument("memory_allocator must be non-null.");
+  }
+  if (options.limit_tcache_size &&
+      options.tcache_size_lower_bound >= options.tcache_size_upper_bound) {
+    return Status::InvalidArgument(
+        "tcache_size_lower_bound larger or equal to tcache_size_upper_bound.");
+  }
+
+  // Create arena.
+  unsigned arena_index = 0;
+  size_t arena_index_size = sizeof(arena_index);
+  int ret =
+      mallctl("arenas.create", &arena_index, &arena_index_size, nullptr, 0);
+  if (ret != 0) {
+    return Status::Incomplete("Failed to create jemalloc arena, error code: " +
+                              ToString(ret));
+  }
+  assert(arena_index != 0);
+
+  // Read existing hooks.
+  std::string key = "arena." + ToString(arena_index) + ".extent_hooks";
+  extent_hooks_t* hooks;
+  size_t hooks_size = sizeof(hooks);
+  ret = mallctl(key.c_str(), &hooks, &hooks_size, nullptr, 0);
+  if (ret != 0) {
+    JemallocNodumpAllocator::DestroyArena(arena_index);
+    return Status::Incomplete("Failed to read existing hooks, error code: " +
+                              ToString(ret));
+  }
+
+  // Store existing alloc.
+  extent_alloc_t* original_alloc = hooks->alloc;
+  extent_alloc_t* expected = nullptr;
+  bool success =
+      JemallocNodumpAllocator::original_alloc_.compare_exchange_strong(
+          expected, original_alloc);
+  if (!success && original_alloc != expected) {
+    JemallocNodumpAllocator::DestroyArena(arena_index);
+    return Status::Incomplete("Original alloc conflict.");
+  }
+
+  // Set the custom hook.
+  std::unique_ptr<extent_hooks_t> new_hooks(new extent_hooks_t(*hooks));
+  new_hooks->alloc = &JemallocNodumpAllocator::Alloc;
+  extent_hooks_t* hooks_ptr = new_hooks.get();
+  ret = mallctl(key.c_str(), nullptr, nullptr, &hooks_ptr, sizeof(hooks_ptr));
+  if (ret != 0) {
+    JemallocNodumpAllocator::DestroyArena(arena_index);
+    return Status::Incomplete("Failed to set custom hook, error code: " +
+                              ToString(ret));
+  }
+
+  // Create cache allocator.
+  memory_allocator->reset(
+      new JemallocNodumpAllocator(options, std::move(new_hooks), arena_index));
+  return Status::OK();
+#endif  // ROCKSDB_JEMALLOC_NODUMP_ALLOCATOR
+}
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.18.X/util/jemalloc_nodump_allocator.h b/3rdParty/rocksdb/v5.18.X/util/jemalloc_nodump_allocator.h
new file mode 100644
index 0000000000..914088de18
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/util/jemalloc_nodump_allocator.h
@@ -0,0 +1,79 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include <atomic>
+#include <vector>
+
+#include "port/port.h"
+#include "rocksdb/memory_allocator.h"
+#include "util/core_local.h"
+#include "util/thread_local.h"
+
+#if defined(ROCKSDB_JEMALLOC) && defined(ROCKSDB_PLATFORM_POSIX)
+
+#include <jemalloc/jemalloc.h>
+#include <sys/mman.h>
+
+#if (JEMALLOC_VERSION_MAJOR >= 5) && defined(MADV_DONTDUMP)
+#define ROCKSDB_JEMALLOC_NODUMP_ALLOCATOR
+
+namespace rocksdb {
+
+class JemallocNodumpAllocator : public MemoryAllocator {
+ public:
+  JemallocNodumpAllocator(JemallocAllocatorOptions& options,
+                          std::unique_ptr<extent_hooks_t>&& arena_hooks,
+                          unsigned arena_index);
+  ~JemallocNodumpAllocator();
+
+  const char* Name() const override { return "JemallocNodumpAllocator"; }
+  void* Allocate(size_t size) override;
+  void Deallocate(void* p) override;
+  size_t UsableSize(void* p, size_t allocation_size) const override;
+
+ private:
+  friend Status NewJemallocNodumpAllocator(
+      JemallocAllocatorOptions& options,
+      std::shared_ptr<MemoryAllocator>* memory_allocator);
+
+  // Custom alloc hook to replace jemalloc default alloc.
+  static void* Alloc(extent_hooks_t* extent, void* new_addr, size_t size,
+                     size_t alignment, bool* zero, bool* commit,
+                     unsigned arena_ind);
+
+  // Destroy arena on destruction of the allocator, or on failure.
+  static Status DestroyArena(unsigned arena_index);
+
+  // Destroy tcache on destruction of the allocator, or thread exit.
+  static void DestroyThreadSpecificCache(void* ptr);
+
+  // Get or create tcache. Return flag suitable to use with `mallocx`:
+  // either MALLOCX_TCACHE_NONE or MALLOCX_TCACHE(tc).
+  int GetThreadSpecificCache(size_t size);
+
+  // A function pointer to jemalloc default alloc. Use atomic to make sure
+  // NewJemallocNodumpAllocator is thread-safe.
+  //
+  // Hack: original_alloc_ needs to be static for Alloc() to access it.
+  // alloc needs to be static to pass to jemalloc as function pointer.
+  static std::atomic<extent_alloc_t*> original_alloc_;
+
+  const JemallocAllocatorOptions options_;
+
+  // Custom hooks has to outlive corresponding arena.
+  const std::unique_ptr<extent_hooks_t> arena_hooks_;
+
+  // Arena index.
+  const unsigned arena_index_;
+
+  // Hold thread-local tcache index.
+  ThreadLocalPtr tcache_;
+};
+
+}  // namespace rocksdb
+#endif  // (JEMALLOC_VERSION_MAJOR >= 5) && MADV_DONTDUMP
+#endif  // ROCKSDB_JEMALLOC && ROCKSDB_PLATFORM_POSIX
diff --git a/3rdParty/rocksdb/v5.16.X/util/kv_map.h b/3rdParty/rocksdb/v5.18.X/util/kv_map.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/kv_map.h
rename to 3rdParty/rocksdb/v5.18.X/util/kv_map.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/log_buffer.cc b/3rdParty/rocksdb/v5.18.X/util/log_buffer.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/log_buffer.cc
rename to 3rdParty/rocksdb/v5.18.X/util/log_buffer.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/log_buffer.h b/3rdParty/rocksdb/v5.18.X/util/log_buffer.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/log_buffer.h
rename to 3rdParty/rocksdb/v5.18.X/util/log_buffer.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/log_write_bench.cc b/3rdParty/rocksdb/v5.18.X/util/log_write_bench.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/util/log_write_bench.cc
rename to 3rdParty/rocksdb/v5.18.X/util/log_write_bench.cc
index b4e12b948c..5c9b3e84bf 100644
--- a/3rdParty/rocksdb/v5.16.X/util/log_write_bench.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/log_write_bench.cc
@@ -35,9 +35,9 @@ void RunBenchmark() {
   Env* env = Env::Default();
   EnvOptions env_options = env->OptimizeForLogWrite(EnvOptions());
   env_options.bytes_per_sync = FLAGS_bytes_per_sync;
-  unique_ptr<WritableFile> file;
+  std::unique_ptr<WritableFile> file;
   env->NewWritableFile(file_name, &file, env_options);
-  unique_ptr<WritableFileWriter> writer;
+  std::unique_ptr<WritableFileWriter> writer;
   writer.reset(new WritableFileWriter(std::move(file), env_options));
 
   std::string record;
diff --git a/3rdParty/rocksdb/v5.18.X/util/logging.h b/3rdParty/rocksdb/v5.18.X/util/logging.h
new file mode 100644
index 0000000000..f605d36a5a
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/util/logging.h
@@ -0,0 +1,57 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file. See the AUTHORS file for names of contributors.
+//
+// Must not be included from any .h files to avoid polluting the namespace
+// with macros.
+
+#pragma once
+
+// Helper macros that include information about file name and line number
+#define ROCKS_LOG_STRINGIFY(x) #x
+#define ROCKS_LOG_TOSTRING(x) ROCKS_LOG_STRINGIFY(x)
+#define ROCKS_LOG_PREPEND_FILE_LINE(FMT) ("[%s:" ROCKS_LOG_TOSTRING(__LINE__) "] " FMT)
+
+inline const char* RocksLogShorterFileName(const char* file)
+{
+  // 15 is the length of "util/logging.h".
+  // If the name of this file changed, please change this number, too.
+  return file + (sizeof(__FILE__) > 15 ? sizeof(__FILE__) - 15 : 0);
+}
+
+// Don't inclide file/line info in HEADER level
+#define ROCKS_LOG_HEADER(LGR, FMT, ...)                                          \
+  rocksdb::Log(InfoLogLevel::HEADER_LEVEL, LGR, FMT, ##__VA_ARGS__)
+
+#define ROCKS_LOG_DEBUG(LGR, FMT, ...)                                           \
+  rocksdb::Log(InfoLogLevel::DEBUG_LEVEL, LGR, ROCKS_LOG_PREPEND_FILE_LINE(FMT), \
+               RocksLogShorterFileName(__FILE__), ##__VA_ARGS__)
+
+#define ROCKS_LOG_INFO(LGR, FMT, ...)                                            \
+  rocksdb::Log(InfoLogLevel::INFO_LEVEL, LGR, ROCKS_LOG_PREPEND_FILE_LINE(FMT),  \
+               RocksLogShorterFileName(__FILE__), ##__VA_ARGS__)
+
+#define ROCKS_LOG_WARN(LGR, FMT, ...)                                            \
+  rocksdb::Log(InfoLogLevel::WARN_LEVEL, LGR, ROCKS_LOG_PREPEND_FILE_LINE(FMT),  \
+               RocksLogShorterFileName(__FILE__), ##__VA_ARGS__)
+
+#define ROCKS_LOG_ERROR(LGR, FMT, ...)                                           \
+  rocksdb::Log(InfoLogLevel::ERROR_LEVEL, LGR, ROCKS_LOG_PREPEND_FILE_LINE(FMT), \
+               RocksLogShorterFileName(__FILE__), ##__VA_ARGS__)
+
+#define ROCKS_LOG_FATAL(LGR, FMT, ...)                                           \
+  rocksdb::Log(InfoLogLevel::FATAL_LEVEL, LGR, ROCKS_LOG_PREPEND_FILE_LINE(FMT), \
+               RocksLogShorterFileName(__FILE__), ##__VA_ARGS__)
+
+#define ROCKS_LOG_BUFFER(LOG_BUF, FMT, ...)                                      \
+  rocksdb::LogToBuffer(LOG_BUF, ROCKS_LOG_PREPEND_FILE_LINE(FMT),                \
+                       RocksLogShorterFileName(__FILE__), ##__VA_ARGS__)
+
+#define ROCKS_LOG_BUFFER_MAX_SZ(LOG_BUF, MAX_LOG_SIZE, FMT, ...)                 \
+  rocksdb::LogToBuffer(LOG_BUF, MAX_LOG_SIZE, ROCKS_LOG_PREPEND_FILE_LINE(FMT),  \
+                       RocksLogShorterFileName(__FILE__), ##__VA_ARGS__)
diff --git a/3rdParty/rocksdb/v5.18.X/util/memory_allocator.h b/3rdParty/rocksdb/v5.18.X/util/memory_allocator.h
new file mode 100644
index 0000000000..99a7241d0a
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/util/memory_allocator.h
@@ -0,0 +1,38 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+//
+
+#pragma once
+
+#include "rocksdb/memory_allocator.h"
+
+namespace rocksdb {
+
+struct CustomDeleter {
+  CustomDeleter(MemoryAllocator* a = nullptr) : allocator(a) {}
+
+  void operator()(char* ptr) const {
+    if (allocator) {
+      allocator->Deallocate(reinterpret_cast<void*>(ptr));
+    } else {
+      delete[] ptr;
+    }
+  }
+
+  MemoryAllocator* allocator;
+};
+
+using CacheAllocationPtr = std::unique_ptr<char[], CustomDeleter>;
+
+inline CacheAllocationPtr AllocateBlock(size_t size,
+                                        MemoryAllocator* allocator) {
+  if (allocator) {
+    auto block = reinterpret_cast<char*>(allocator->Allocate(size));
+    return CacheAllocationPtr(block, allocator);
+  }
+  return CacheAllocationPtr(new char[size]);
+}
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/util/memory_usage.h b/3rdParty/rocksdb/v5.18.X/util/memory_usage.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/memory_usage.h
rename to 3rdParty/rocksdb/v5.18.X/util/memory_usage.h
diff --git a/3rdParty/rocksdb/v5.18.X/util/mock_time_env.h b/3rdParty/rocksdb/v5.18.X/util/mock_time_env.h
new file mode 100644
index 0000000000..c6ab8a7483
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/util/mock_time_env.h
@@ -0,0 +1,43 @@
+// Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include "rocksdb/env.h"
+
+namespace rocksdb {
+
+class MockTimeEnv : public EnvWrapper {
+ public:
+  explicit MockTimeEnv(Env* base) : EnvWrapper(base) {}
+
+  virtual Status GetCurrentTime(int64_t* time) override {
+    assert(time != nullptr);
+    assert(current_time_ <=
+           static_cast<uint64_t>(std::numeric_limits<int64_t>::max()));
+    *time = static_cast<int64_t>(current_time_);
+    return Status::OK();
+  }
+
+  virtual uint64_t NowMicros() override {
+    assert(current_time_ <= std::numeric_limits<uint64_t>::max() / 1000000);
+    return current_time_ * 1000000;
+  }
+
+  virtual uint64_t NowNanos() override {
+    assert(current_time_ <= std::numeric_limits<uint64_t>::max() / 1000000000);
+    return current_time_ * 1000000000;
+  }
+
+  void set_current_time(uint64_t time) {
+    assert(time >= current_time_);
+    current_time_ = time;
+  }
+
+ private:
+  std::atomic<uint64_t> current_time_{0};
+};
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/util/murmurhash.cc b/3rdParty/rocksdb/v5.18.X/util/murmurhash.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/murmurhash.cc
rename to 3rdParty/rocksdb/v5.18.X/util/murmurhash.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/murmurhash.h b/3rdParty/rocksdb/v5.18.X/util/murmurhash.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/murmurhash.h
rename to 3rdParty/rocksdb/v5.18.X/util/murmurhash.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/mutexlock.h b/3rdParty/rocksdb/v5.18.X/util/mutexlock.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/mutexlock.h
rename to 3rdParty/rocksdb/v5.18.X/util/mutexlock.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/ppc-opcode.h b/3rdParty/rocksdb/v5.18.X/util/ppc-opcode.h
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/util/ppc-opcode.h
rename to 3rdParty/rocksdb/v5.18.X/util/ppc-opcode.h
index eeb0ae08ff..554fa50a89 100644
--- a/3rdParty/rocksdb/v5.16.X/util/ppc-opcode.h
+++ b/3rdParty/rocksdb/v5.18.X/util/ppc-opcode.h
@@ -6,8 +6,7 @@
 //  This source code is also licensed under the GPLv2 license found in the
 //  COPYING file in the root directory of this source tree.
 
-#ifndef __OPCODES_H
-#define __OPCODES_H
+#pragma once
 
 #define __PPC_RA(a) (((a)&0x1f) << 16)
 #define __PPC_RB(b) (((b)&0x1f) << 11)
@@ -27,5 +26,3 @@
 #define VPMSUMD(t, a, b) .long PPC_INST_VPMSUMD | VSX_XX3((t), a, b)
 #define MFVRD(a, t) .long PPC_INST_MFVSRD | VSX_XX1((t) + 32, a, 0)
 #define MTVRD(t, a) .long PPC_INST_MTVSRD | VSX_XX1((t) + 32, a, 0)
-
-#endif
diff --git a/3rdParty/rocksdb/v5.16.X/util/random.cc b/3rdParty/rocksdb/v5.18.X/util/random.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/random.cc
rename to 3rdParty/rocksdb/v5.18.X/util/random.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/random.h b/3rdParty/rocksdb/v5.18.X/util/random.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/random.h
rename to 3rdParty/rocksdb/v5.18.X/util/random.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/rate_limiter.cc b/3rdParty/rocksdb/v5.18.X/util/rate_limiter.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/rate_limiter.cc
rename to 3rdParty/rocksdb/v5.18.X/util/rate_limiter.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/rate_limiter.h b/3rdParty/rocksdb/v5.18.X/util/rate_limiter.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/rate_limiter.h
rename to 3rdParty/rocksdb/v5.18.X/util/rate_limiter.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/rate_limiter_test.cc b/3rdParty/rocksdb/v5.18.X/util/rate_limiter_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/rate_limiter_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/rate_limiter_test.cc
diff --git a/3rdParty/rocksdb/v5.18.X/util/repeatable_thread.h b/3rdParty/rocksdb/v5.18.X/util/repeatable_thread.h
new file mode 100644
index 0000000000..3506234f9e
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/util/repeatable_thread.h
@@ -0,0 +1,153 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#pragma once
+
+#include <functional>
+#include <string>
+
+#include "port/port.h"
+#include "rocksdb/env.h"
+#include "util/mock_time_env.h"
+#include "util/mutexlock.h"
+
+namespace rocksdb {
+
+class RepeatableThread {
+ public:
+  RepeatableThread(std::function<void()> function,
+                   const std::string& thread_name, Env* env, uint64_t delay_us,
+                   uint64_t initial_delay_us = 0)
+      : function_(function),
+        thread_name_("rocksdb:" + thread_name),
+        env_(env),
+        delay_us_(delay_us),
+        initial_delay_us_(initial_delay_us),
+        cond_var_(&mutex_),
+        running_(true),
+#ifndef NDEBUG
+        waiting_(false),
+        run_count_(0),
+#endif
+        thread_([this] { thread(); }) {
+  }
+
+  void cancel() {
+    {
+      MutexLock l(&mutex_);
+      if (!running_) {
+        return;
+      }
+      running_ = false;
+      cond_var_.SignalAll();
+    }
+    thread_.join();
+  }
+
+  ~RepeatableThread() { cancel(); }
+
+#ifndef NDEBUG
+  // Wait until RepeatableThread starting waiting, call the optional callback,
+  // then wait for one run of RepeatableThread. Tests can use provide a
+  // custom env object to mock time, and use the callback here to bump current
+  // time and trigger RepeatableThread. See repeatable_thread_test for example.
+  //
+  // Note: only support one caller of this method.
+  void TEST_WaitForRun(std::function<void()> callback = nullptr) {
+    MutexLock l(&mutex_);
+    while (!waiting_) {
+      cond_var_.Wait();
+    }
+    uint64_t prev_count = run_count_;
+    if (callback != nullptr) {
+      callback();
+    }
+    cond_var_.SignalAll();
+    while (!(run_count_ > prev_count)) {
+      cond_var_.Wait();
+    }
+  }
+#endif
+
+ private:
+  bool wait(uint64_t delay) {
+    MutexLock l(&mutex_);
+    if (running_ && delay > 0) {
+      uint64_t wait_until = env_->NowMicros() + delay;
+#ifndef NDEBUG
+      waiting_ = true;
+      cond_var_.SignalAll();
+#endif
+      while (running_) {
+#ifndef NDEBUG
+        if (dynamic_cast<MockTimeEnv*>(env_) != nullptr) {
+          // MockTimeEnv is used. Since it is not easy to mock TimedWait,
+          // we wait without timeout to wait for TEST_WaitForRun to wake us up.
+          cond_var_.Wait();
+        } else {
+          cond_var_.TimedWait(wait_until);
+        }
+#else
+        cond_var_.TimedWait(wait_until);
+#endif
+        if (env_->NowMicros() >= wait_until) {
+          break;
+        }
+      }
+#ifndef NDEBUG
+      waiting_ = false;
+#endif
+    }
+    return running_;
+  }
+
+  void thread() {
+#if defined(_GNU_SOURCE) && defined(__GLIBC_PREREQ)
+#if __GLIBC_PREREQ(2, 12)
+    // Set thread name.
+    auto thread_handle = thread_.native_handle();
+    int ret __attribute__((__unused__)) =
+        pthread_setname_np(thread_handle, thread_name_.c_str());
+    assert(ret == 0);
+#endif
+#endif
+
+    assert(delay_us_ > 0);
+    if (!wait(initial_delay_us_)) {
+      return;
+    }
+    do {
+      function_();
+#ifndef NDEBUG
+      {
+        MutexLock l(&mutex_);
+        run_count_++;
+        cond_var_.SignalAll();
+      }
+#endif
+    } while (wait(delay_us_));
+  }
+
+  const std::function<void()> function_;
+  const std::string thread_name_;
+  Env* const env_;
+  const uint64_t delay_us_;
+  const uint64_t initial_delay_us_;
+
+  // Mutex lock should be held when accessing running_, waiting_
+  // and run_count_.
+  port::Mutex mutex_;
+  port::CondVar cond_var_;
+  bool running_;
+#ifndef NDEBUG
+  // RepeatableThread waiting for timeout.
+  bool waiting_;
+  // Times function_ had run.
+  uint64_t run_count_;
+#endif
+  port::Thread thread_;
+};
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.18.X/util/repeatable_thread_test.cc b/3rdParty/rocksdb/v5.18.X/util/repeatable_thread_test.cc
new file mode 100644
index 0000000000..dec437da32
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/util/repeatable_thread_test.cc
@@ -0,0 +1,76 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include <atomic>
+#include <memory>
+
+#include "db/db_test_util.h"
+#include "util/repeatable_thread.h"
+#include "util/testharness.h"
+
+class RepeatableThreadTest : public testing::Test {
+ public:
+  RepeatableThreadTest()
+      : mock_env_(new rocksdb::MockTimeEnv(rocksdb::Env::Default())) {}
+
+ protected:
+  std::unique_ptr<rocksdb::MockTimeEnv> mock_env_;
+};
+
+TEST_F(RepeatableThreadTest, TimedTest) {
+  constexpr uint64_t kSecond = 1000000;  // 1s = 1000000us
+  constexpr int kIteration = 3;
+  rocksdb::Env* env = rocksdb::Env::Default();
+  rocksdb::port::Mutex mutex;
+  rocksdb::port::CondVar test_cv(&mutex);
+  int count = 0;
+  uint64_t prev_time = env->NowMicros();
+  rocksdb::RepeatableThread thread(
+      [&] {
+        rocksdb::MutexLock l(&mutex);
+        count++;
+        uint64_t now = env->NowMicros();
+        assert(count == 1 || prev_time + 1 * kSecond <= now);
+        prev_time = now;
+        if (count >= kIteration) {
+          test_cv.SignalAll();
+        }
+      },
+      "rt_test", env, 1 * kSecond);
+  // Wait for execution finish.
+  {
+    rocksdb::MutexLock l(&mutex);
+    while (count < kIteration) {
+      test_cv.Wait();
+    }
+  }
+
+  // Test cancel
+  thread.cancel();
+}
+
+TEST_F(RepeatableThreadTest, MockEnvTest) {
+  constexpr uint64_t kSecond = 1000000;  // 1s = 1000000us
+  constexpr int kIteration = 3;
+  mock_env_->set_current_time(0);  // in seconds
+  std::atomic<int> count{0};
+  rocksdb::RepeatableThread thread([&] { count++; }, "rt_test", mock_env_.get(),
+                                   1 * kSecond, 1 * kSecond);
+  for (int i = 1; i <= kIteration; i++) {
+    // Bump current time
+    thread.TEST_WaitForRun([&] { mock_env_->set_current_time(i); });
+  }
+  // Test function should be exectued exactly kIteraion times.
+  ASSERT_EQ(kIteration, count.load());
+
+  // Test cancel
+  thread.cancel();
+}
+
+int main(int argc, char** argv) {
+  ::testing::InitGoogleTest(&argc, argv);
+
+  return RUN_ALL_TESTS();
+}
diff --git a/3rdParty/rocksdb/v5.16.X/util/set_comparator.h b/3rdParty/rocksdb/v5.18.X/util/set_comparator.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/set_comparator.h
rename to 3rdParty/rocksdb/v5.18.X/util/set_comparator.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/slice.cc b/3rdParty/rocksdb/v5.18.X/util/slice.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/slice.cc
rename to 3rdParty/rocksdb/v5.18.X/util/slice.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/slice_transform_test.cc b/3rdParty/rocksdb/v5.18.X/util/slice_transform_test.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/util/slice_transform_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/slice_transform_test.cc
index ddbb9f4bfa..2eb56af6d6 100644
--- a/3rdParty/rocksdb/v5.16.X/util/slice_transform_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/slice_transform_test.cc
@@ -24,7 +24,7 @@ TEST_F(SliceTransformTest, CapPrefixTransform) {
   std::string s;
   s = "abcdefge";
 
-  unique_ptr<const SliceTransform> transform;
+  std::unique_ptr<const SliceTransform> transform;
 
   transform.reset(NewCappedPrefixTransform(6));
   ASSERT_EQ(transform->Transform(s).ToString(), "abcdef");
@@ -115,7 +115,7 @@ TEST_F(SliceTransformDBTest, CapPrefix) {
   ASSERT_OK(db()->Put(wo, "foo3", "bar3"));
   ASSERT_OK(db()->Flush(fo));
 
-  unique_ptr<Iterator> iter(db()->NewIterator(ro));
+  std::unique_ptr<Iterator> iter(db()->NewIterator(ro));
 
   iter->Seek("foo");
   ASSERT_OK(iter->status());
diff --git a/3rdParty/rocksdb/v5.18.X/util/sst_file_manager_impl.cc b/3rdParty/rocksdb/v5.18.X/util/sst_file_manager_impl.cc
new file mode 100644
index 0000000000..ee1394bc91
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/util/sst_file_manager_impl.cc
@@ -0,0 +1,511 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#include "util/sst_file_manager_impl.h"
+
+#include <vector>
+
+#include "db/db_impl.h"
+#include "port/port.h"
+#include "rocksdb/env.h"
+#include "rocksdb/sst_file_manager.h"
+#include "util/mutexlock.h"
+#include "util/sync_point.h"
+
+namespace rocksdb {
+
+#ifndef ROCKSDB_LITE
+SstFileManagerImpl::SstFileManagerImpl(Env* env, std::shared_ptr<Logger> logger,
+                                       int64_t rate_bytes_per_sec,
+                                       double max_trash_db_ratio,
+                                       uint64_t bytes_max_delete_chunk)
+    : env_(env),
+      logger_(logger),
+      total_files_size_(0),
+      in_progress_files_size_(0),
+      compaction_buffer_size_(0),
+      cur_compactions_reserved_size_(0),
+      max_allowed_space_(0),
+      delete_scheduler_(env, rate_bytes_per_sec, logger.get(), this,
+                        max_trash_db_ratio, bytes_max_delete_chunk),
+      cv_(&mu_),
+      closing_(false),
+      bg_thread_(nullptr),
+      reserved_disk_buffer_(0),
+      free_space_trigger_(0),
+      cur_instance_(nullptr) {
+}
+
+SstFileManagerImpl::~SstFileManagerImpl() {
+  Close();
+}
+
+void SstFileManagerImpl::Close() {
+  {
+    MutexLock l(&mu_);
+    if (closing_) {
+      return;
+    }
+    closing_ = true;
+    cv_.SignalAll();
+  }
+  if (bg_thread_) {
+    bg_thread_->join();
+  }
+}
+
+Status SstFileManagerImpl::OnAddFile(const std::string& file_path,
+                                     bool compaction) {
+  uint64_t file_size;
+  Status s = env_->GetFileSize(file_path, &file_size);
+  if (s.ok()) {
+    MutexLock l(&mu_);
+    OnAddFileImpl(file_path, file_size, compaction);
+  }
+  TEST_SYNC_POINT("SstFileManagerImpl::OnAddFile");
+  return s;
+}
+
+Status SstFileManagerImpl::OnDeleteFile(const std::string& file_path) {
+  {
+    MutexLock l(&mu_);
+    OnDeleteFileImpl(file_path);
+  }
+  TEST_SYNC_POINT("SstFileManagerImpl::OnDeleteFile");
+  return Status::OK();
+}
+
+void SstFileManagerImpl::OnCompactionCompletion(Compaction* c) {
+  MutexLock l(&mu_);
+  uint64_t size_added_by_compaction = 0;
+  for (size_t i = 0; i < c->num_input_levels(); i++) {
+    for (size_t j = 0; j < c->num_input_files(i); j++) {
+      FileMetaData* filemeta = c->input(i, j);
+      size_added_by_compaction += filemeta->fd.GetFileSize();
+    }
+  }
+  cur_compactions_reserved_size_ -= size_added_by_compaction;
+
+  auto new_files = c->edit()->GetNewFiles();
+  for (auto& new_file : new_files) {
+    auto fn = TableFileName(c->immutable_cf_options()->cf_paths,
+                            new_file.second.fd.GetNumber(),
+                            new_file.second.fd.GetPathId());
+    if (in_progress_files_.find(fn) != in_progress_files_.end()) {
+      auto tracked_file = tracked_files_.find(fn);
+      assert(tracked_file != tracked_files_.end());
+      in_progress_files_size_ -= tracked_file->second;
+      in_progress_files_.erase(fn);
+    }
+  }
+}
+
+Status SstFileManagerImpl::OnMoveFile(const std::string& old_path,
+                                      const std::string& new_path,
+                                      uint64_t* file_size) {
+  {
+    MutexLock l(&mu_);
+    if (file_size != nullptr) {
+      *file_size = tracked_files_[old_path];
+    }
+    OnAddFileImpl(new_path, tracked_files_[old_path], false);
+    OnDeleteFileImpl(old_path);
+  }
+  TEST_SYNC_POINT("SstFileManagerImpl::OnMoveFile");
+  return Status::OK();
+}
+
+void SstFileManagerImpl::SetMaxAllowedSpaceUsage(uint64_t max_allowed_space) {
+  MutexLock l(&mu_);
+  max_allowed_space_ = max_allowed_space;
+}
+
+void SstFileManagerImpl::SetCompactionBufferSize(
+    uint64_t compaction_buffer_size) {
+  MutexLock l(&mu_);
+  compaction_buffer_size_ = compaction_buffer_size;
+}
+
+bool SstFileManagerImpl::IsMaxAllowedSpaceReached() {
+  MutexLock l(&mu_);
+  if (max_allowed_space_ <= 0) {
+    return false;
+  }
+  return total_files_size_ >= max_allowed_space_;
+}
+
+bool SstFileManagerImpl::IsMaxAllowedSpaceReachedIncludingCompactions() {
+  MutexLock l(&mu_);
+  if (max_allowed_space_ <= 0) {
+    return false;
+  }
+  return total_files_size_ + cur_compactions_reserved_size_ >=
+         max_allowed_space_;
+}
+
+bool SstFileManagerImpl::EnoughRoomForCompaction(
+    ColumnFamilyData* cfd, const std::vector<CompactionInputFiles>& inputs,
+    Status bg_error) {
+  MutexLock l(&mu_);
+  uint64_t size_added_by_compaction = 0;
+  // First check if we even have the space to do the compaction
+  for (size_t i = 0; i < inputs.size(); i++) {
+    for (size_t j = 0; j < inputs[i].size(); j++) {
+      FileMetaData* filemeta = inputs[i][j];
+      size_added_by_compaction += filemeta->fd.GetFileSize();
+    }
+  }
+
+  // Update cur_compactions_reserved_size_ so concurrent compaction
+  // don't max out space
+  size_t needed_headroom =
+      cur_compactions_reserved_size_ + size_added_by_compaction +
+      compaction_buffer_size_;
+  if (max_allowed_space_ != 0 &&
+      (needed_headroom + total_files_size_ > max_allowed_space_)) {
+    return false;
+  }
+
+  // Implement more aggressive checks only if this DB instance has already
+  // seen a NoSpace() error. This is tin order to contain a single potentially
+  // misbehaving DB instance and prevent it from slowing down compactions of
+  // other DB instances
+  if (CheckFreeSpace() && bg_error == Status::NoSpace()) {
+    auto fn =
+        TableFileName(cfd->ioptions()->cf_paths, inputs[0][0]->fd.GetNumber(),
+                      inputs[0][0]->fd.GetPathId());
+    uint64_t free_space = 0;
+    env_->GetFreeSpace(fn, &free_space);
+    // needed_headroom is based on current size reserved by compactions,
+    // minus any files created by running compactions as they would count
+    // against the reserved size. If user didn't specify any compaction
+    // buffer, add reserved_disk_buffer_ that's calculated by default so the
+    // compaction doesn't end up leaving nothing for logs and flush SSTs
+    if (compaction_buffer_size_ == 0) {
+      needed_headroom += reserved_disk_buffer_;
+    }
+    needed_headroom -= in_progress_files_size_;
+    if (free_space < needed_headroom + size_added_by_compaction) {
+      // We hit the condition of not enough disk space
+      ROCKS_LOG_ERROR(logger_, "free space [%d bytes] is less than "
+          "needed headroom [%d bytes]\n", free_space, needed_headroom);
+      return false;
+    }
+  }
+
+  cur_compactions_reserved_size_ += size_added_by_compaction;
+  // Take a snapshot of cur_compactions_reserved_size_ for when we encounter
+  // a NoSpace error.
+  free_space_trigger_ = cur_compactions_reserved_size_;
+  return true;
+}
+
+uint64_t SstFileManagerImpl::GetCompactionsReservedSize() {
+  MutexLock l(&mu_);
+  return cur_compactions_reserved_size_;
+}
+
+uint64_t SstFileManagerImpl::GetTotalSize() {
+  MutexLock l(&mu_);
+  return total_files_size_;
+}
+
+std::unordered_map<std::string, uint64_t>
+SstFileManagerImpl::GetTrackedFiles() {
+  MutexLock l(&mu_);
+  return tracked_files_;
+}
+
+int64_t SstFileManagerImpl::GetDeleteRateBytesPerSecond() {
+  return delete_scheduler_.GetRateBytesPerSecond();
+}
+
+void SstFileManagerImpl::SetDeleteRateBytesPerSecond(int64_t delete_rate) {
+  return delete_scheduler_.SetRateBytesPerSecond(delete_rate);
+}
+
+double SstFileManagerImpl::GetMaxTrashDBRatio() {
+  return delete_scheduler_.GetMaxTrashDBRatio();
+}
+
+void SstFileManagerImpl::SetMaxTrashDBRatio(double r) {
+  return delete_scheduler_.SetMaxTrashDBRatio(r);
+}
+
+uint64_t SstFileManagerImpl::GetTotalTrashSize() {
+  return delete_scheduler_.GetTotalTrashSize();
+}
+
+void SstFileManagerImpl::ReserveDiskBuffer(uint64_t size,
+                                           const std::string& path) {
+  MutexLock l(&mu_);
+
+  reserved_disk_buffer_ += size;
+  if (path_.empty()) {
+    path_ = path;
+  }
+}
+
+void SstFileManagerImpl::ClearError() {
+  while (true) {
+    MutexLock l(&mu_);
+
+    if (closing_) {
+      return;
+    }
+
+    uint64_t free_space;
+    Status s = env_->GetFreeSpace(path_, &free_space);
+    if (s.ok()) {
+      // In case of multi-DB instances, some of them may have experienced a
+      // soft error and some a hard error. In the SstFileManagerImpl, a hard
+      // error will basically override previously reported soft errors. Once
+      // we clear the hard error, we don't keep track of previous errors for
+      // now
+      if (bg_err_.severity() == Status::Severity::kHardError) {
+        if (free_space < reserved_disk_buffer_) {
+          ROCKS_LOG_ERROR(logger_, "free space [%d bytes] is less than "
+              "required disk buffer [%d bytes]\n", free_space,
+              reserved_disk_buffer_);
+          ROCKS_LOG_ERROR(logger_, "Cannot clear hard error\n");
+          s = Status::NoSpace();
+        }
+      } else if (bg_err_.severity() == Status::Severity::kSoftError) {
+        if (free_space < free_space_trigger_) {
+          ROCKS_LOG_WARN(logger_, "free space [%d bytes] is less than "
+              "free space for compaction trigger [%d bytes]\n", free_space,
+              free_space_trigger_);
+          ROCKS_LOG_WARN(logger_, "Cannot clear soft error\n");
+          s = Status::NoSpace();
+        }
+      }
+    }
+
+    // Someone could have called CancelErrorRecovery() and the list could have
+    // become empty, so check again here
+    if (s.ok() && !error_handler_list_.empty()) {
+      auto error_handler = error_handler_list_.front();
+      // Since we will release the mutex, set cur_instance_ to signal to the
+      // shutdown thread, if it calls // CancelErrorRecovery() the meantime,
+      // to indicate that this DB instance is busy. The DB instance is
+      // guaranteed to not be deleted before RecoverFromBGError() returns,
+      // since the ErrorHandler::recovery_in_prog_ flag would be true
+      cur_instance_ = error_handler;
+      mu_.Unlock();
+      s = error_handler->RecoverFromBGError();
+      mu_.Lock();
+      // The DB instance might have been deleted while we were
+      // waiting for the mutex, so check cur_instance_ to make sure its
+      // still non-null
+      if (cur_instance_) {
+        // Check for error again, since the instance may have recovered but
+        // immediately got another error. If that's the case, and the new
+        // error is also a NoSpace() non-fatal error, leave the instance in
+        // the list
+        Status err = cur_instance_->GetBGError();
+        if (s.ok() && err == Status::NoSpace() &&
+            err.severity() < Status::Severity::kFatalError) {
+          s = err;
+        }
+        cur_instance_ = nullptr;
+      }
+
+      if (s.ok() || s.IsShutdownInProgress() ||
+          (!s.ok() && s.severity() >= Status::Severity::kFatalError)) {
+        // If shutdown is in progress, abandon this handler instance
+        // and continue with the others
+        error_handler_list_.pop_front();
+      }
+    }
+
+    if (!error_handler_list_.empty()) {
+      // If there are more instances to be recovered, reschedule after 5
+      // seconds
+      int64_t wait_until = env_->NowMicros() + 5000000;
+      cv_.TimedWait(wait_until);
+    }
+
+    // Check again for error_handler_list_ empty, as a DB instance shutdown
+    // could have removed it from the queue while we were in timed wait
+    if (error_handler_list_.empty()) {
+      ROCKS_LOG_INFO(logger_, "Clearing error\n");
+      bg_err_ = Status::OK();
+      return;
+    }
+  }
+}
+
+void SstFileManagerImpl::StartErrorRecovery(ErrorHandler* handler,
+                                            Status bg_error) {
+  MutexLock l(&mu_);
+  if (bg_error.severity() == Status::Severity::kSoftError) {
+    if (bg_err_.ok()) {
+      // Setting bg_err_ basically means we're in degraded mode
+      // Assume that all pending compactions will fail similarly. The trigger
+      // for clearing this condition is set to current compaction reserved
+      // size, so we stop checking disk space available in
+      // EnoughRoomForCompaction once this much free space is available
+      bg_err_ = bg_error;
+    }
+  } else if (bg_error.severity() == Status::Severity::kHardError) {
+    bg_err_ = bg_error;
+  } else {
+    assert(false);
+  }
+
+  // If this is the first instance of this error, kick of a thread to poll
+  // and recover from this condition
+  if (error_handler_list_.empty()) {
+    error_handler_list_.push_back(handler);
+    // Release lock before calling join. Its ok to do so because
+    // error_handler_list_ is now non-empty, so no other invocation of this
+    // function will execute this piece of code
+    mu_.Unlock();
+    if (bg_thread_) {
+      bg_thread_->join();
+    }
+    // Start a new thread. The previous one would have exited.
+    bg_thread_.reset(new port::Thread(&SstFileManagerImpl::ClearError, this));
+    mu_.Lock();
+  } else {
+    // Check if this DB instance is already in the list
+    for (auto iter = error_handler_list_.begin();
+         iter != error_handler_list_.end(); ++iter) {
+      if ((*iter) == handler) {
+        return;
+      }
+    }
+    error_handler_list_.push_back(handler);
+  }
+}
+
+bool SstFileManagerImpl::CancelErrorRecovery(ErrorHandler* handler) {
+  MutexLock l(&mu_);
+
+  if (cur_instance_ == handler) {
+    // This instance is currently busy attempting to recover
+    // Nullify it so the recovery thread doesn't attempt to access it again
+    cur_instance_ = nullptr;
+    return false;
+  }
+
+  for (auto iter = error_handler_list_.begin();
+       iter != error_handler_list_.end(); ++iter) {
+    if ((*iter) == handler) {
+      error_handler_list_.erase(iter);
+      return true;
+    }
+  }
+  return false;
+}
+
+Status SstFileManagerImpl::ScheduleFileDeletion(
+    const std::string& file_path, const std::string& path_to_sync) {
+  return delete_scheduler_.DeleteFile(file_path, path_to_sync);
+}
+
+void SstFileManagerImpl::WaitForEmptyTrash() {
+  delete_scheduler_.WaitForEmptyTrash();
+}
+
+void SstFileManagerImpl::OnAddFileImpl(const std::string& file_path,
+                                       uint64_t file_size, bool compaction) {
+  auto tracked_file = tracked_files_.find(file_path);
+  if (tracked_file != tracked_files_.end()) {
+    // File was added before, we will just update the size
+    assert(!compaction);
+    total_files_size_ -= tracked_file->second;
+    total_files_size_ += file_size;
+    cur_compactions_reserved_size_ -= file_size;
+  } else {
+    total_files_size_ += file_size;
+    if (compaction) {
+      // Keep track of the size of files created by in-progress compactions.
+      // When calculating whether there's enough headroom for new compactions,
+      // this will be subtracted from cur_compactions_reserved_size_.
+      // Otherwise, compactions will be double counted.
+      in_progress_files_size_ += file_size;
+      in_progress_files_.insert(file_path);
+    }
+  }
+  tracked_files_[file_path] = file_size;
+}
+
+void SstFileManagerImpl::OnDeleteFileImpl(const std::string& file_path) {
+  auto tracked_file = tracked_files_.find(file_path);
+  if (tracked_file == tracked_files_.end()) {
+    // File is not tracked
+    assert(in_progress_files_.find(file_path) == in_progress_files_.end());
+    return;
+  }
+
+  total_files_size_ -= tracked_file->second;
+  // Check if it belonged to an in-progress compaction
+  if (in_progress_files_.find(file_path) != in_progress_files_.end()) {
+    in_progress_files_size_ -= tracked_file->second;
+    in_progress_files_.erase(file_path);
+  }
+  tracked_files_.erase(tracked_file);
+}
+
+SstFileManager* NewSstFileManager(Env* env, std::shared_ptr<Logger> info_log,
+                                  std::string trash_dir,
+                                  int64_t rate_bytes_per_sec,
+                                  bool delete_existing_trash, Status* status,
+                                  double max_trash_db_ratio,
+                                  uint64_t bytes_max_delete_chunk) {
+  SstFileManagerImpl* res =
+      new SstFileManagerImpl(env, info_log, rate_bytes_per_sec,
+                             max_trash_db_ratio, bytes_max_delete_chunk);
+
+  // trash_dir is deprecated and not needed anymore, but if user passed it
+  // we will still remove files in it.
+  Status s;
+  if (delete_existing_trash && trash_dir != "") {
+    std::vector<std::string> files_in_trash;
+    s = env->GetChildren(trash_dir, &files_in_trash);
+    if (s.ok()) {
+      for (const std::string& trash_file : files_in_trash) {
+        if (trash_file == "." || trash_file == "..") {
+          continue;
+        }
+
+        std::string path_in_trash = trash_dir + "/" + trash_file;
+        res->OnAddFile(path_in_trash);
+        Status file_delete =
+            res->ScheduleFileDeletion(path_in_trash, trash_dir);
+        if (s.ok() && !file_delete.ok()) {
+          s = file_delete;
+        }
+      }
+    }
+  }
+
+  if (status) {
+    *status = s;
+  }
+
+  return res;
+}
+
+#else
+
+SstFileManager* NewSstFileManager(Env* /*env*/,
+                                  std::shared_ptr<Logger> /*info_log*/,
+                                  std::string /*trash_dir*/,
+                                  int64_t /*rate_bytes_per_sec*/,
+                                  bool /*delete_existing_trash*/,
+                                  Status* status, double /*max_trash_db_ratio*/,
+                                  uint64_t /*bytes_max_delete_chunk*/) {
+  if (status) {
+    *status =
+        Status::NotSupported("SstFileManager is not supported in ROCKSDB_LITE");
+  }
+  return nullptr;
+}
+
+#endif  // ROCKSDB_LITE
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/util/sst_file_manager_impl.h b/3rdParty/rocksdb/v5.18.X/util/sst_file_manager_impl.h
similarity index 67%
rename from 3rdParty/rocksdb/v5.16.X/util/sst_file_manager_impl.h
rename to 3rdParty/rocksdb/v5.18.X/util/sst_file_manager_impl.h
index 90815d44f2..d11035df80 100644
--- a/3rdParty/rocksdb/v5.16.X/util/sst_file_manager_impl.h
+++ b/3rdParty/rocksdb/v5.18.X/util/sst_file_manager_impl.h
@@ -12,6 +12,7 @@
 #include "port/port.h"
 
 #include "db/compaction.h"
+#include "db/error_handler.h"
 #include "rocksdb/sst_file_manager.h"
 #include "util/delete_scheduler.h"
 
@@ -33,7 +34,7 @@ class SstFileManagerImpl : public SstFileManager {
   ~SstFileManagerImpl();
 
   // DB will call OnAddFile whenever a new sst file is added.
-  Status OnAddFile(const std::string& file_path);
+  Status OnAddFile(const std::string& file_path, bool compaction = false);
 
   // DB will call OnDeleteFile whenever an sst file is deleted.
   Status OnDeleteFile(const std::string& file_path);
@@ -67,7 +68,9 @@ class SstFileManagerImpl : public SstFileManager {
   // estimates how much space is currently being used by compactions (i.e.
   // if a compaction has started, this function bumps the used space by
   // the full compaction size).
-  bool EnoughRoomForCompaction(const std::vector<CompactionInputFiles>& inputs);
+  bool EnoughRoomForCompaction(ColumnFamilyData* cfd,
+                               const std::vector<CompactionInputFiles>& inputs,
+                               Status bg_error);
 
   // Bookkeeping so total_file_sizes_ goes back to normal after compaction
   // finishes
@@ -96,6 +99,18 @@ class SstFileManagerImpl : public SstFileManager {
   // Return the total size of trash files
   uint64_t GetTotalTrashSize() override;
 
+  // Called by each DB instance using this sst file manager to reserve
+  // disk buffer space for recovery from out of space errors
+  void ReserveDiskBuffer(uint64_t buffer, const std::string& path);
+
+  // Set a flag upon encountering disk full. May enqueue the ErrorHandler
+  // instance for background polling and recovery
+  void StartErrorRecovery(ErrorHandler* db, Status bg_error);
+
+  // Remove the given Errorhandler instance from the recovery queue. Its
+  // not guaranteed
+  bool CancelErrorRecovery(ErrorHandler* db);
+
   // Mark file as trash and schedule it's deletion.
   virtual Status ScheduleFileDeletion(const std::string& file_path,
                                       const std::string& dir_to_sync);
@@ -106,18 +121,30 @@ class SstFileManagerImpl : public SstFileManager {
 
   DeleteScheduler* delete_scheduler() { return &delete_scheduler_; }
 
+  // Stop the error recovery background thread. This should be called only
+  // once in the object's lifetime, and before the destructor
+  void Close();
+
  private:
   // REQUIRES: mutex locked
-  void OnAddFileImpl(const std::string& file_path, uint64_t file_size);
+  void OnAddFileImpl(const std::string& file_path, uint64_t file_size,
+                     bool compaction);
   // REQUIRES: mutex locked
   void OnDeleteFileImpl(const std::string& file_path);
 
+  void ClearError();
+  bool CheckFreeSpace() {
+    return bg_err_.severity() == Status::Severity::kSoftError;
+  }
+
   Env* env_;
   std::shared_ptr<Logger> logger_;
   // Mutex to protect tracked_files_, total_files_size_
   port::Mutex mu_;
   // The summation of the sizes of all files in tracked_files_ map
   uint64_t total_files_size_;
+  // The summation of all output files of in-progress compactions
+  uint64_t in_progress_files_size_;
   // Compactions should only execute if they can leave at least
   // this amount of buffer space for logs and flushes
   uint64_t compaction_buffer_size_;
@@ -126,10 +153,32 @@ class SstFileManagerImpl : public SstFileManager {
   // A map containing all tracked files and there sizes
   //  file_path => file_size
   std::unordered_map<std::string, uint64_t> tracked_files_;
+  // A set of files belonging to in-progress compactions
+  std::unordered_set<std::string> in_progress_files_;
   // The maximum allowed space (in bytes) for sst files.
   uint64_t max_allowed_space_;
   // DeleteScheduler used to throttle file deletition.
   DeleteScheduler delete_scheduler_;
+  port::CondVar cv_;
+  // Flag to force error recovery thread to exit
+  bool closing_;
+  // Background error recovery thread
+  std::unique_ptr<port::Thread> bg_thread_;
+  // A path in the filesystem corresponding to this SFM. This is used for
+  // calling Env::GetFreeSpace. Posix requires a path in the filesystem
+  std::string path_;
+  // Save the current background error
+  Status bg_err_;
+  // Amount of free disk headroom before allowing recovery from hard errors
+  uint64_t reserved_disk_buffer_;
+  // For soft errors, amount of free disk space before we can allow
+  // compactions to run full throttle. If disk space is below this trigger,
+  // compactions will be gated by free disk space > input size
+  uint64_t free_space_trigger_;
+  // List of database error handler instances tracked by this sst file manager
+  std::list<ErrorHandler*> error_handler_list_;
+  // Pointer to ErrorHandler instance that is currently processing recovery
+  ErrorHandler* cur_instance_;
 };
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/util/status.cc b/3rdParty/rocksdb/v5.18.X/util/status.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/status.cc
rename to 3rdParty/rocksdb/v5.18.X/util/status.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/stderr_logger.h b/3rdParty/rocksdb/v5.18.X/util/stderr_logger.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/stderr_logger.h
rename to 3rdParty/rocksdb/v5.18.X/util/stderr_logger.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/stop_watch.h b/3rdParty/rocksdb/v5.18.X/util/stop_watch.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/stop_watch.h
rename to 3rdParty/rocksdb/v5.18.X/util/stop_watch.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/string_util.cc b/3rdParty/rocksdb/v5.18.X/util/string_util.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/string_util.cc
rename to 3rdParty/rocksdb/v5.18.X/util/string_util.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/string_util.h b/3rdParty/rocksdb/v5.18.X/util/string_util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/string_util.h
rename to 3rdParty/rocksdb/v5.18.X/util/string_util.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/sync_point.cc b/3rdParty/rocksdb/v5.18.X/util/sync_point.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/util/sync_point.cc
rename to 3rdParty/rocksdb/v5.18.X/util/sync_point.cc
index ce0fa0a972..4599c256d9 100644
--- a/3rdParty/rocksdb/v5.16.X/util/sync_point.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/sync_point.cc
@@ -17,9 +17,7 @@ SyncPoint* SyncPoint::GetInstance() {
   return &sync_point;
 }
 
-SyncPoint::SyncPoint() : 
-  impl_(new Data) {
-}
+SyncPoint::SyncPoint() : impl_(new Data) {}
 
 SyncPoint:: ~SyncPoint() {
   delete impl_;
diff --git a/3rdParty/rocksdb/v5.16.X/util/sync_point.h b/3rdParty/rocksdb/v5.18.X/util/sync_point.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/sync_point.h
rename to 3rdParty/rocksdb/v5.18.X/util/sync_point.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/sync_point_impl.cc b/3rdParty/rocksdb/v5.18.X/util/sync_point_impl.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/sync_point_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/util/sync_point_impl.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/sync_point_impl.h b/3rdParty/rocksdb/v5.18.X/util/sync_point_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/sync_point_impl.h
rename to 3rdParty/rocksdb/v5.18.X/util/sync_point_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/testharness.cc b/3rdParty/rocksdb/v5.18.X/util/testharness.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/testharness.cc
rename to 3rdParty/rocksdb/v5.18.X/util/testharness.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/testharness.h b/3rdParty/rocksdb/v5.18.X/util/testharness.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/testharness.h
rename to 3rdParty/rocksdb/v5.18.X/util/testharness.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/testutil.cc b/3rdParty/rocksdb/v5.18.X/util/testutil.cc
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/util/testutil.cc
rename to 3rdParty/rocksdb/v5.18.X/util/testutil.cc
index 6094d7ba0a..2f8e31cd57 100644
--- a/3rdParty/rocksdb/v5.16.X/util/testutil.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/testutil.cc
@@ -124,20 +124,21 @@ const Comparator* Uint64Comparator() {
   return &uint64comp;
 }
 
-WritableFileWriter* GetWritableFileWriter(WritableFile* wf) {
-  unique_ptr<WritableFile> file(wf);
-  return new WritableFileWriter(std::move(file), EnvOptions());
+WritableFileWriter* GetWritableFileWriter(WritableFile* wf,
+                                          const std::string& fname) {
+  std::unique_ptr<WritableFile> file(wf);
+  return new WritableFileWriter(std::move(file), fname, EnvOptions());
 }
 
 RandomAccessFileReader* GetRandomAccessFileReader(RandomAccessFile* raf) {
-  unique_ptr<RandomAccessFile> file(raf);
+  std::unique_ptr<RandomAccessFile> file(raf);
   return new RandomAccessFileReader(std::move(file),
                                     "[test RandomAccessFileReader]");
 }
 
 SequentialFileReader* GetSequentialFileReader(SequentialFile* se,
                                               const std::string& fname) {
-  unique_ptr<SequentialFile> file(se);
+  std::unique_ptr<SequentialFile> file(se);
   return new SequentialFileReader(std::move(file), fname);
 }
 
@@ -400,5 +401,21 @@ Status DestroyDir(Env* env, const std::string& dir) {
   return s;
 }
 
+bool IsDirectIOSupported(Env* env, const std::string& dir) {
+  EnvOptions env_options;
+  env_options.use_mmap_writes = false;
+  env_options.use_direct_writes = true;
+  std::string tmp = TempFileName(dir, 999);
+  Status s;
+  {
+    std::unique_ptr<WritableFile> file;
+    s = env->NewWritableFile(tmp, &file, env_options);
+  }
+  if (s.ok()) {
+    s = env->DeleteFile(tmp);
+  }
+  return s.ok();
+}
+
 }  // namespace test
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/util/testutil.h b/3rdParty/rocksdb/v5.18.X/util/testutil.h
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/util/testutil.h
rename to 3rdParty/rocksdb/v5.18.X/util/testutil.h
index ffdaa5ad60..2aab3df72c 100644
--- a/3rdParty/rocksdb/v5.16.X/util/testutil.h
+++ b/3rdParty/rocksdb/v5.18.X/util/testutil.h
@@ -64,7 +64,7 @@ class ErrorEnv : public EnvWrapper {
                num_writable_file_errors_(0) { }
 
   virtual Status NewWritableFile(const std::string& fname,
-                                 unique_ptr<WritableFile>* result,
+                                 std::unique_ptr<WritableFile>* result,
                                  const EnvOptions& soptions) override {
     result->reset();
     if (writable_file_error_) {
@@ -183,7 +183,8 @@ class VectorIterator : public InternalIterator {
   std::vector<std::string> values_;
   size_t current_;
 };
-extern WritableFileWriter* GetWritableFileWriter(WritableFile* wf);
+extern WritableFileWriter* GetWritableFileWriter(WritableFile* wf,
+                                                 const std::string& fname);
 
 extern RandomAccessFileReader* GetRandomAccessFileReader(RandomAccessFile* raf);
 
@@ -249,7 +250,7 @@ class RandomRWStringSink : public RandomRWFile {
 
   Status Write(uint64_t offset, const Slice& data) override {
     if (offset + data.size() > ss_->contents_.size()) {
-      ss_->contents_.resize(offset + data.size(), '\0');
+      ss_->contents_.resize(static_cast<size_t>(offset) + data.size(), '\0');
     }
 
     char* pos = const_cast<char*>(ss_->contents_.data() + offset);
@@ -517,7 +518,7 @@ class StringEnv : public EnvWrapper {
             "Attemp to read when it already reached eof.");
       }
       // TODO(yhchiang): Currently doesn't handle the overflow case.
-      offset_ += n;
+      offset_ += static_cast<size_t>(n);
       return Status::OK();
     }
 
@@ -531,7 +532,7 @@ class StringEnv : public EnvWrapper {
     explicit StringSink(std::string* contents)
         : WritableFile(), contents_(contents) {}
     virtual Status Truncate(uint64_t size) override {
-      contents_->resize(size);
+      contents_->resize(static_cast<size_t>(size));
       return Status::OK();
     }
     virtual Status Close() override { return Status::OK(); }
@@ -553,7 +554,7 @@ class StringEnv : public EnvWrapper {
 
   const Status WriteToNewFile(const std::string& file_name,
                               const std::string& content) {
-    unique_ptr<WritableFile> r;
+    std::unique_ptr<WritableFile> r;
     auto s = NewWritableFile(file_name, &r, EnvOptions());
     if (!s.ok()) {
       return s;
@@ -566,7 +567,8 @@ class StringEnv : public EnvWrapper {
   }
 
   // The following text is boilerplate that forwards all methods to target()
-  Status NewSequentialFile(const std::string& f, unique_ptr<SequentialFile>* r,
+  Status NewSequentialFile(const std::string& f,
+                           std::unique_ptr<SequentialFile>* r,
                            const EnvOptions& /*options*/) override {
     auto iter = files_.find(f);
     if (iter == files_.end()) {
@@ -576,11 +578,11 @@ class StringEnv : public EnvWrapper {
     return Status::OK();
   }
   Status NewRandomAccessFile(const std::string& /*f*/,
-                             unique_ptr<RandomAccessFile>* /*r*/,
+                             std::unique_ptr<RandomAccessFile>* /*r*/,
                              const EnvOptions& /*options*/) override {
     return Status::NotSupported();
   }
-  Status NewWritableFile(const std::string& f, unique_ptr<WritableFile>* r,
+  Status NewWritableFile(const std::string& f, std::unique_ptr<WritableFile>* r,
                          const EnvOptions& /*options*/) override {
     auto iter = files_.find(f);
     if (iter != files_.end()) {
@@ -590,7 +592,7 @@ class StringEnv : public EnvWrapper {
     return Status::OK();
   }
   virtual Status NewDirectory(const std::string& /*name*/,
-                              unique_ptr<Directory>* /*result*/) override {
+                              std::unique_ptr<Directory>* /*result*/) override {
     return Status::NotSupported();
   }
   Status FileExists(const std::string& f) override {
@@ -746,5 +748,7 @@ std::string RandomName(Random* rnd, const size_t len);
 
 Status DestroyDir(Env* env, const std::string& dir);
 
+bool IsDirectIOSupported(Env* env, const std::string& dir);
+
 }  // namespace test
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/util/thread_list_test.cc b/3rdParty/rocksdb/v5.18.X/util/thread_list_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/thread_list_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/thread_list_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/thread_local.cc b/3rdParty/rocksdb/v5.18.X/util/thread_local.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/util/thread_local.cc
rename to 3rdParty/rocksdb/v5.18.X/util/thread_local.cc
index dea2002a02..7346eff11e 100644
--- a/3rdParty/rocksdb/v5.16.X/util/thread_local.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/thread_local.cc
@@ -204,7 +204,7 @@ extern "C" {
 // The linker must not discard thread_callback_on_exit.  (We force a reference
 // to this variable with a linker /include:symbol pragma to ensure that.) If
 // this variable is discarded, the OnThreadExit function will never be called.
-#ifdef _WIN64
+#ifndef _X86_
 
 // .CRT section is merged with .rdata on x64 so it must be constant data.
 #pragma const_seg(".CRT$XLB")
@@ -219,7 +219,7 @@ const PIMAGE_TLS_CALLBACK p_thread_callback_on_exit =
 #pragma comment(linker, "/include:_tls_used")
 #pragma comment(linker, "/include:p_thread_callback_on_exit")
 
-#else  // _WIN64
+#else  // _X86_
 
 #pragma data_seg(".CRT$XLB")
 PIMAGE_TLS_CALLBACK p_thread_callback_on_exit = wintlscleanup::WinOnThreadExit;
@@ -229,7 +229,7 @@ PIMAGE_TLS_CALLBACK p_thread_callback_on_exit = wintlscleanup::WinOnThreadExit;
 #pragma comment(linker, "/INCLUDE:__tls_used")
 #pragma comment(linker, "/INCLUDE:_p_thread_callback_on_exit")
 
-#endif  // _WIN64
+#endif  // _X86_
 
 #else
 // https://github.com/couchbase/gperftools/blob/master/src/windows/port.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/thread_local.h b/3rdParty/rocksdb/v5.18.X/util/thread_local.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/thread_local.h
rename to 3rdParty/rocksdb/v5.18.X/util/thread_local.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/thread_local_test.cc b/3rdParty/rocksdb/v5.18.X/util/thread_local_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/thread_local_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/thread_local_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/thread_operation.h b/3rdParty/rocksdb/v5.18.X/util/thread_operation.h
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/util/thread_operation.h
rename to 3rdParty/rocksdb/v5.18.X/util/thread_operation.h
index 025392b59d..f1827da0a0 100644
--- a/3rdParty/rocksdb/v5.16.X/util/thread_operation.h
+++ b/3rdParty/rocksdb/v5.18.X/util/thread_operation.h
@@ -70,7 +70,7 @@ static OperationStageInfo global_op_stage_table[] = {
   {ThreadStatus::STAGE_MEMTABLE_ROLLBACK,
       "MemTableList::RollbackMemtableFlush"},
   {ThreadStatus::STAGE_MEMTABLE_INSTALL_FLUSH_RESULTS,
-      "MemTableList::InstallMemtableFlushResults"},
+      "MemTableList::TryInstallMemtableFlushResults"},
 };
 
 // The structure that describes a state.
diff --git a/3rdParty/rocksdb/v5.16.X/util/threadpool_imp.cc b/3rdParty/rocksdb/v5.18.X/util/threadpool_imp.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/util/threadpool_imp.cc
rename to 3rdParty/rocksdb/v5.18.X/util/threadpool_imp.cc
index 3b1f762b8f..b431830ee6 100644
--- a/3rdParty/rocksdb/v5.16.X/util/threadpool_imp.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/threadpool_imp.cc
@@ -188,7 +188,7 @@ void ThreadPoolImpl::Impl::BGThread(size_t thread_id) {
   bool low_cpu_priority = false;
 
   while (true) {
-// Wait until there is an item that is ready to run
+    // Wait until there is an item that is ready to run
     std::unique_lock<std::mutex> lock(mu_);
     // Stop waiting if the thread needs to do work or needs to terminate.
     while (!exit_all_threads_ && !IsLastExcessiveThread(thread_id) &&
@@ -198,7 +198,7 @@ void ThreadPoolImpl::Impl::BGThread(size_t thread_id) {
 
     if (exit_all_threads_) {  // mechanism to let BG threads exit safely
 
-      if(!wait_for_jobs_to_complete_ ||
+      if (!wait_for_jobs_to_complete_ ||
           queue_.empty()) {
         break;
        }
@@ -469,16 +469,12 @@ void ThreadPoolImpl::SubmitJob(std::function<void()>&& job) {
 
 void ThreadPoolImpl::Schedule(void(*function)(void* arg1), void* arg,
   void* tag, void(*unschedFunction)(void* arg)) {
-
-  std::function<void()> fn = [arg, function] { function(arg); };
-
-  std::function<void()> unfn;
-  if (unschedFunction != nullptr) {
-    auto uf = [arg, unschedFunction] { unschedFunction(arg); };
-    unfn = std::move(uf);
+  if (unschedFunction == nullptr) {
+    impl_->Submit(std::bind(function, arg), std::function<void()>(), tag);
+  } else {
+    impl_->Submit(std::bind(function, arg), std::bind(unschedFunction, arg),
+                  tag);
   }
-
-  impl_->Submit(std::move(fn), std::move(unfn), tag);
 }
 
 int ThreadPoolImpl::UnSchedule(void* arg) {
diff --git a/3rdParty/rocksdb/v5.16.X/util/threadpool_imp.h b/3rdParty/rocksdb/v5.18.X/util/threadpool_imp.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/threadpool_imp.h
rename to 3rdParty/rocksdb/v5.18.X/util/threadpool_imp.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/timer_queue.h b/3rdParty/rocksdb/v5.18.X/util/timer_queue.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/timer_queue.h
rename to 3rdParty/rocksdb/v5.18.X/util/timer_queue.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/timer_queue_test.cc b/3rdParty/rocksdb/v5.18.X/util/timer_queue_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/timer_queue_test.cc
rename to 3rdParty/rocksdb/v5.18.X/util/timer_queue_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/util/trace_replay.cc b/3rdParty/rocksdb/v5.18.X/util/trace_replay.cc
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/util/trace_replay.cc
rename to 3rdParty/rocksdb/v5.18.X/util/trace_replay.cc
index cd2e3ee95e..5b9bec651e 100644
--- a/3rdParty/rocksdb/v5.16.X/util/trace_replay.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/trace_replay.cc
@@ -16,6 +16,8 @@
 
 namespace rocksdb {
 
+const std::string kTraceMagic = "feedcafedeadbeef";
+
 namespace {
 void EncodeCFAndKey(std::string* dst, uint32_t cf_id, const Slice& key) {
   PutFixed32(dst, cf_id);
@@ -29,14 +31,20 @@ void DecodeCFAndKey(std::string& buffer, uint32_t* cf_id, Slice* key) {
 }
 }  // namespace
 
-Tracer::Tracer(Env* env, std::unique_ptr<TraceWriter>&& trace_writer)
-    : env_(env), trace_writer_(std::move(trace_writer)) {
+Tracer::Tracer(Env* env, const TraceOptions& trace_options,
+               std::unique_ptr<TraceWriter>&& trace_writer)
+    : env_(env),
+      trace_options_(trace_options),
+      trace_writer_(std::move(trace_writer)) {
   WriteHeader();
 }
 
 Tracer::~Tracer() { trace_writer_.reset(); }
 
 Status Tracer::Write(WriteBatch* write_batch) {
+  if (IsTraceFileOverMax()) {
+    return Status::OK();
+  }
   Trace trace;
   trace.ts = env_->NowMicros();
   trace.type = kTraceWrite;
@@ -45,6 +53,9 @@ Status Tracer::Write(WriteBatch* write_batch) {
 }
 
 Status Tracer::Get(ColumnFamilyHandle* column_family, const Slice& key) {
+  if (IsTraceFileOverMax()) {
+    return Status::OK();
+  }
   Trace trace;
   trace.ts = env_->NowMicros();
   trace.type = kTraceGet;
@@ -53,6 +64,9 @@ Status Tracer::Get(ColumnFamilyHandle* column_family, const Slice& key) {
 }
 
 Status Tracer::IteratorSeek(const uint32_t& cf_id, const Slice& key) {
+  if (IsTraceFileOverMax()) {
+    return Status::OK();
+  }
   Trace trace;
   trace.ts = env_->NowMicros();
   trace.type = kTraceIteratorSeek;
@@ -61,6 +75,9 @@ Status Tracer::IteratorSeek(const uint32_t& cf_id, const Slice& key) {
 }
 
 Status Tracer::IteratorSeekForPrev(const uint32_t& cf_id, const Slice& key) {
+  if (IsTraceFileOverMax()) {
+    return Status::OK();
+  }
   Trace trace;
   trace.ts = env_->NowMicros();
   trace.type = kTraceIteratorSeekForPrev;
@@ -68,6 +85,11 @@ Status Tracer::IteratorSeekForPrev(const uint32_t& cf_id, const Slice& key) {
   return WriteTrace(trace);
 }
 
+bool Tracer::IsTraceFileOverMax() {
+  uint64_t trace_file_size = trace_writer_->GetFileSize();
+  return (trace_file_size > trace_options_.max_trace_file_size);
+}
+
 Status Tracer::WriteHeader() {
   std::ostringstream s;
   s << kTraceMagic << "\t"
@@ -103,7 +125,7 @@ Status Tracer::WriteTrace(const Trace& trace) {
 Status Tracer::Close() { return WriteFooter(); }
 
 Replayer::Replayer(DB* db, const std::vector<ColumnFamilyHandle*>& handles,
-                   unique_ptr<TraceReader>&& reader)
+                   std::unique_ptr<TraceReader>&& reader)
     : trace_reader_(std::move(reader)) {
   assert(db != nullptr);
   db_ = static_cast<DBImpl*>(db->GetRootDB());
diff --git a/3rdParty/rocksdb/v5.16.X/util/trace_replay.h b/3rdParty/rocksdb/v5.18.X/util/trace_replay.h
similarity index 88%
rename from 3rdParty/rocksdb/v5.16.X/util/trace_replay.h
rename to 3rdParty/rocksdb/v5.18.X/util/trace_replay.h
index b324696f01..d935f65ce7 100644
--- a/3rdParty/rocksdb/v5.16.X/util/trace_replay.h
+++ b/3rdParty/rocksdb/v5.18.X/util/trace_replay.h
@@ -10,6 +10,7 @@
 #include <utility>
 
 #include "rocksdb/env.h"
+#include "rocksdb/options.h"
 #include "rocksdb/trace_reader_writer.h"
 
 namespace rocksdb {
@@ -21,7 +22,7 @@ class DBImpl;
 class Slice;
 class WriteBatch;
 
-const std::string kTraceMagic = "feedcafedeadbeef";
+extern const std::string kTraceMagic;
 const unsigned int kTraceTimestampSize = 8;
 const unsigned int kTraceTypeSize = 1;
 const unsigned int kTracePayloadLengthSize = 4;
@@ -55,13 +56,15 @@ struct Trace {
 // Trace RocksDB operations using a TraceWriter.
 class Tracer {
  public:
-  Tracer(Env* env, std::unique_ptr<TraceWriter>&& trace_writer);
+  Tracer(Env* env, const TraceOptions& trace_options,
+         std::unique_ptr<TraceWriter>&& trace_writer);
   ~Tracer();
 
   Status Write(WriteBatch* write_batch);
   Status Get(ColumnFamilyHandle* cfname, const Slice& key);
   Status IteratorSeek(const uint32_t& cf_id, const Slice& key);
   Status IteratorSeekForPrev(const uint32_t& cf_id, const Slice& key);
+  bool IsTraceFileOverMax();
 
   Status Close();
 
@@ -71,7 +74,8 @@ class Tracer {
   Status WriteTrace(const Trace& trace);
 
   Env* env_;
-  unique_ptr<TraceWriter> trace_writer_;
+  TraceOptions trace_options_;
+  std::unique_ptr<TraceWriter> trace_writer_;
 };
 
 // Replay RocksDB operations from a trace.
diff --git a/3rdParty/rocksdb/v5.16.X/util/transaction_test_util.cc b/3rdParty/rocksdb/v5.18.X/util/transaction_test_util.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/util/transaction_test_util.cc
rename to 3rdParty/rocksdb/v5.18.X/util/transaction_test_util.cc
index 19d27b1a14..58d95b2ae1 100644
--- a/3rdParty/rocksdb/v5.16.X/util/transaction_test_util.cc
+++ b/3rdParty/rocksdb/v5.18.X/util/transaction_test_util.cc
@@ -13,6 +13,7 @@
 #include <inttypes.h>
 #include <algorithm>
 #include <numeric>
+#include <random>
 #include <string>
 #include <thread>
 
@@ -135,8 +136,8 @@ bool RandomTransactionInserter::DoInsert(DB* db, Transaction* txn,
 
   std::vector<uint16_t> set_vec(num_sets_);
   std::iota(set_vec.begin(), set_vec.end(), static_cast<uint16_t>(0));
-  std::random_shuffle(set_vec.begin(), set_vec.end(),
-                      [&](uint64_t r) { return rand_->Uniform(r); });
+  std::shuffle(set_vec.begin(), set_vec.end(), std::random_device{});
+
   // For each set, pick a key at random and increment it
   for (uint16_t set_i : set_vec) {
     uint64_t int_value = 0;
@@ -257,10 +258,8 @@ Status RandomTransactionInserter::Verify(DB* db, uint16_t num_sets,
 
   std::vector<uint16_t> set_vec(num_sets);
   std::iota(set_vec.begin(), set_vec.end(), static_cast<uint16_t>(0));
-  if (rand) {
-    std::random_shuffle(set_vec.begin(), set_vec.end(),
-                        [&](uint64_t r) { return rand->Uniform(r); });
-  }
+  std::shuffle(set_vec.begin(), set_vec.end(), std::random_device{});
+
   // For each set of keys with the same prefix, sum all the values
   for (uint16_t set_i : set_vec) {
     // Five digits (since the largest uint16_t is 65535) plus the NUL
diff --git a/3rdParty/rocksdb/v5.16.X/util/transaction_test_util.h b/3rdParty/rocksdb/v5.18.X/util/transaction_test_util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/transaction_test_util.h
rename to 3rdParty/rocksdb/v5.18.X/util/transaction_test_util.h
diff --git a/3rdParty/rocksdb/v5.16.X/util/util.h b/3rdParty/rocksdb/v5.18.X/util/util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/util/util.h
rename to 3rdParty/rocksdb/v5.18.X/util/util.h
diff --git a/3rdParty/rocksdb/v5.18.X/util/vector_iterator.h b/3rdParty/rocksdb/v5.18.X/util/vector_iterator.h
new file mode 100644
index 0000000000..da60eb229c
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/util/vector_iterator.h
@@ -0,0 +1,100 @@
+#pragma once
+
+#include <algorithm>
+#include <string>
+#include <vector>
+
+#include "db/dbformat.h"
+#include "rocksdb/iterator.h"
+#include "rocksdb/slice.h"
+#include "table/internal_iterator.h"
+
+namespace rocksdb {
+
+// Iterator over a vector of keys/values
+class VectorIterator : public InternalIterator {
+ public:
+  VectorIterator(std::vector<std::string> keys, std::vector<std::string> values,
+                 const InternalKeyComparator* icmp)
+      : keys_(std::move(keys)),
+        values_(std::move(values)),
+        indexed_cmp_(icmp, &keys_),
+        current_(keys.size()) {
+    assert(keys_.size() == values_.size());
+
+    indices_.reserve(keys_.size());
+    for (size_t i = 0; i < keys_.size(); i++) {
+      indices_.push_back(i);
+    }
+    std::sort(indices_.begin(), indices_.end(), indexed_cmp_);
+  }
+
+  virtual bool Valid() const override {
+    return !indices_.empty() && current_ < indices_.size();
+  }
+
+  virtual void SeekToFirst() override { current_ = 0; }
+  virtual void SeekToLast() override { current_ = indices_.size() - 1; }
+
+  virtual void Seek(const Slice& target) override {
+    current_ = std::lower_bound(indices_.begin(), indices_.end(), target,
+                                indexed_cmp_) -
+               indices_.begin();
+  }
+
+  virtual void SeekForPrev(const Slice& target) override {
+    current_ = std::lower_bound(indices_.begin(), indices_.end(), target,
+                                indexed_cmp_) -
+               indices_.begin();
+    if (!Valid()) {
+      SeekToLast();
+    } else {
+      Prev();
+    }
+  }
+
+  virtual void Next() override { current_++; }
+  virtual void Prev() override { current_--; }
+
+  virtual Slice key() const override {
+    return Slice(keys_[indices_[current_]]);
+  }
+  virtual Slice value() const override {
+    return Slice(values_[indices_[current_]]);
+  }
+
+  virtual Status status() const override { return Status::OK(); }
+
+  virtual bool IsKeyPinned() const override { return true; }
+  virtual bool IsValuePinned() const override { return true; }
+
+ private:
+  struct IndexedKeyComparator {
+    IndexedKeyComparator(const InternalKeyComparator* c,
+                         const std::vector<std::string>* ks)
+        : cmp(c), keys(ks) {}
+
+    bool operator()(size_t a, size_t b) const {
+      return cmp->Compare((*keys)[a], (*keys)[b]) < 0;
+    }
+
+    bool operator()(size_t a, const Slice& b) const {
+      return cmp->Compare((*keys)[a], b) < 0;
+    }
+
+    bool operator()(const Slice& a, size_t b) const {
+      return cmp->Compare(a, (*keys)[b]) < 0;
+    }
+
+    const InternalKeyComparator* cmp;
+    const std::vector<std::string>* keys;
+  };
+
+  std::vector<std::string> keys_;
+  std::vector<std::string> values_;
+  IndexedKeyComparator indexed_cmp_;
+  std::vector<size_t> indices_;
+  size_t current_;
+};
+
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.18.X/util/xxhash.cc b/3rdParty/rocksdb/v5.18.X/util/xxhash.cc
new file mode 100644
index 0000000000..2ec95a636e
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/util/xxhash.cc
@@ -0,0 +1,1074 @@
+/*
+xxHash - Fast Hash algorithm
+Copyright (C) 2012-2014, Yann Collet.
+BSD 2-Clause License (http://www.opensource.org/licenses/bsd-license.php)
+
+Redistribution and use in source and binary forms, with or without
+modification, are permitted provided that the following conditions are
+met:
+
+* Redistributions of source code must retain the above copyright
+notice, this list of conditions and the following disclaimer.
+* Redistributions in binary form must reproduce the above
+copyright notice, this list of conditions and the following disclaimer
+in the documentation and/or other materials provided with the
+distribution.
+
+THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
+"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
+LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
+A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
+OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
+SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
+LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
+DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
+THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
+(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
+OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
+
+You can contact the author at :
+- xxHash source repository : http://code.google.com/p/xxhash/
+*/
+
+
+//**************************************
+// Tuning parameters
+//**************************************
+/*!XXH_FORCE_MEMORY_ACCESS :
+ * By default, access to unaligned memory is controlled by `memcpy()`, which is
+ * safe and portable. Unfortunately, on some target/compiler combinations, the
+ * generated assembly is sub-optimal. The below switch allow to select different
+ * access method for improved performance. Method 0 (default) : use `memcpy()`.
+ * Safe and portable. Method 1 : `__packed` statement. It depends on compiler
+ * extension (ie, not portable). This method is safe if your compiler supports
+ * it, and *generally* as fast or faster than `memcpy`. Method 2 : direct
+ * access. This method doesn't depend on compiler but violate C standard. It can
+ * generate buggy code on targets which do not support unaligned memory
+ * accesses. But in some circumstances, it's the only known way to get the most
+ * performance (ie GCC + ARMv6) See http://stackoverflow.com/a/32095106/646947
+ * for details. Prefer these methods in priority order (0 > 1 > 2)
+ */
+
+#include "util/util.h"
+
+#ifndef XXH_FORCE_MEMORY_ACCESS /* can be defined externally, on command line \
+                                   for example */
+#if defined(__GNUC__) &&                                     \
+    (defined(__ARM_ARCH_6__) || defined(__ARM_ARCH_6J__) ||  \
+     defined(__ARM_ARCH_6K__) || defined(__ARM_ARCH_6Z__) || \
+     defined(__ARM_ARCH_6ZK__) || defined(__ARM_ARCH_6T2__))
+#define XXH_FORCE_MEMORY_ACCESS 2
+#elif (defined(__INTEL_COMPILER) && !defined(_WIN32)) ||      \
+    (defined(__GNUC__) &&                                     \
+     (defined(__ARM_ARCH_7__) || defined(__ARM_ARCH_7A__) ||  \
+      defined(__ARM_ARCH_7R__) || defined(__ARM_ARCH_7M__) || \
+      defined(__ARM_ARCH_7S__)))
+#define XXH_FORCE_MEMORY_ACCESS 1
+#endif
+#endif
+
+// Unaligned memory access is automatically enabled for "common" CPU, such as x86.
+// For others CPU, the compiler will be more cautious, and insert extra code to ensure aligned access is respected.
+// If you know your target CPU supports unaligned memory access, you want to force this option manually to improve performance.
+// You can also enable this parameter if you know your input data will always be aligned (boundaries of 4, for U32).
+#if defined(__ARM_FEATURE_UNALIGNED) || defined(__i386) || defined(_M_IX86) || defined(__x86_64__) || defined(_M_X64)
+#  define XXH_USE_UNALIGNED_ACCESS 1
+#endif
+
+// XXH_ACCEPT_NULL_INPUT_POINTER :
+// If the input pointer is a null pointer, xxHash default behavior is to trigger a memory access error, since it is a bad pointer.
+// When this option is enabled, xxHash output for null input pointers will be the same as a null-length input.
+// This option has a very small performance cost (only measurable on small inputs).
+// By default, this option is disabled. To enable it, uncomment below define :
+//#define XXH_ACCEPT_NULL_INPUT_POINTER 1
+
+// XXH_FORCE_NATIVE_FORMAT :
+// By default, xxHash library provides endian-independent Hash values, based on little-endian convention.
+// Results are therefore identical for little-endian and big-endian CPU.
+// This comes at a performance cost for big-endian CPU, since some swapping is required to emulate little-endian format.
+// Should endian-independence be of no importance for your application, you may set the #define below to 1.
+// It will improve speed for Big-endian CPU.
+// This option has no impact on Little_Endian CPU.
+#define XXH_FORCE_NATIVE_FORMAT 0
+
+/*!XXH_FORCE_ALIGN_CHECK :
+ * This is a minor performance trick, only useful with lots of very small keys.
+ * It means : check for aligned/unaligned input.
+ * The check costs one initial branch per hash;
+ * set it to 0 when the input is guaranteed to be aligned,
+ * or when alignment doesn't matter for performance.
+ */
+#ifndef XXH_FORCE_ALIGN_CHECK /* can be defined externally */
+#if defined(__i386) || defined(_M_IX86) || defined(__x86_64__) || \
+    defined(_M_X64)
+#define XXH_FORCE_ALIGN_CHECK 0
+#else
+#define XXH_FORCE_ALIGN_CHECK 1
+#endif
+#endif
+
+//**************************************
+// Compiler Specific Options
+//**************************************
+// Disable some Visual warning messages
+#ifdef _MSC_VER  // Visual Studio
+#  pragma warning(disable : 4127)      // disable: C4127: conditional expression is constant
+#  pragma warning(disable : 4804)      // disable: C4804: 'operation' : unsafe use of type 'bool' in operation (static assert line 313)
+#endif
+
+#ifdef _MSC_VER    // Visual Studio
+#  define FORCE_INLINE static __forceinline
+#else
+#  ifdef __GNUC__
+#    define FORCE_INLINE static inline __attribute__((always_inline))
+#  else
+#    define FORCE_INLINE static inline
+#  endif
+#endif
+
+
+//**************************************
+// Includes & Memory related functions
+//**************************************
+#include "xxhash.h"
+// Modify the local functions below should you wish to use some other memory related routines
+// for malloc(), free()
+#include <stdlib.h>
+FORCE_INLINE void* XXH_malloc(size_t s) { return malloc(s); }
+FORCE_INLINE void  XXH_free  (void* p)  { free(p); }
+// for memcpy()
+#include <string.h>
+FORCE_INLINE void* XXH_memcpy(void* dest, const void* src, size_t size) { return memcpy(dest,src,size); }
+#include <assert.h> /* assert */
+
+namespace rocksdb {
+//**************************************
+// Basic Types
+//**************************************
+#if defined (__STDC_VERSION__) && __STDC_VERSION__ >= 199901L   // C99
+# include <stdint.h>
+  typedef uint8_t  BYTE;
+  typedef uint16_t U16;
+  typedef uint32_t U32;
+  typedef  int32_t S32;
+  typedef uint64_t U64;
+#else
+  typedef unsigned char      BYTE;
+  typedef unsigned short     U16;
+  typedef unsigned int       U32;
+  typedef   signed int       S32;
+  typedef unsigned long long U64;
+#endif
+
+#if defined(__GNUC__)  && !defined(XXH_USE_UNALIGNED_ACCESS)
+#  define _PACKED __attribute__ ((packed))
+#else
+#  define _PACKED
+#endif
+
+#if !defined(XXH_USE_UNALIGNED_ACCESS) && !defined(__GNUC__)
+#  ifdef __IBMC__
+#    pragma pack(1)
+#  else
+#    pragma pack(push, 1)
+#  endif
+#endif
+
+typedef struct _U32_S { U32 v; } _PACKED U32_S;
+
+#if !defined(XXH_USE_UNALIGNED_ACCESS) && !defined(__GNUC__)
+#  pragma pack(pop)
+#endif
+
+#define A32(x) (((U32_S *)(x))->v)
+
+#if (defined(XXH_FORCE_MEMORY_ACCESS) && (XXH_FORCE_MEMORY_ACCESS == 2))
+
+/* Force direct memory access. Only works on CPU which support unaligned memory
+ * access in hardware */
+static U32 XXH_read32(const void* memPtr) { return *(const U32*)memPtr; }
+
+#elif (defined(XXH_FORCE_MEMORY_ACCESS) && (XXH_FORCE_MEMORY_ACCESS == 1))
+
+/* __pack instructions are safer, but compiler specific, hence potentially
+ * problematic for some compilers */
+/* currently only defined for gcc and icc */
+typedef union {
+  U32 u32;
+} __attribute__((packed)) unalign;
+static U32 XXH_read32(const void* ptr) { return ((const unalign*)ptr)->u32; }
+
+#else
+
+/* portable and safe solution. Generally efficient.
+ * see : http://stackoverflow.com/a/32095106/646947
+ */
+static U32 XXH_read32(const void* memPtr) {
+  U32 val;
+  memcpy(&val, memPtr, sizeof(val));
+  return val;
+}
+
+#endif /* XXH_FORCE_DIRECT_MEMORY_ACCESS */
+
+//***************************************
+// Compiler-specific Functions and Macros
+//***************************************
+#define GCC_VERSION (__GNUC__ * 100 + __GNUC_MINOR__)
+
+// Note : although _rotl exists for minGW (GCC under windows), performance seems poor
+#if defined(_MSC_VER)
+#  define XXH_rotl32(x,r) _rotl(x,r)
+#define XXH_rotl64(x, r) _rotl64(x, r)
+#else
+#  define XXH_rotl32(x,r) ((x << r) | (x >> (32 - r)))
+#define XXH_rotl64(x, r) ((x << r) | (x >> (64 - r)))
+#endif
+
+#if defined(_MSC_VER)     // Visual Studio
+#  define XXH_swap32 _byteswap_ulong
+#elif GCC_VERSION >= 403
+#  define XXH_swap32 __builtin_bswap32
+#else
+static inline U32 XXH_swap32 (U32 x) {
+    return  ((x << 24) & 0xff000000 ) |
+        ((x <<  8) & 0x00ff0000 ) |
+        ((x >>  8) & 0x0000ff00 ) |
+        ((x >> 24) & 0x000000ff );}
+#endif
+
+
+//**************************************
+// Constants
+//**************************************
+#define PRIME32_1   2654435761U
+#define PRIME32_2   2246822519U
+#define PRIME32_3   3266489917U
+#define PRIME32_4    668265263U
+#define PRIME32_5    374761393U
+
+
+//**************************************
+// Architecture Macros
+//**************************************
+typedef enum { XXH_bigEndian=0, XXH_littleEndian=1 } XXH_endianess;
+#ifndef XXH_CPU_LITTLE_ENDIAN   // It is possible to define XXH_CPU_LITTLE_ENDIAN externally, for example using a compiler switch
+    static const int one = 1;
+#   define XXH_CPU_LITTLE_ENDIAN   (*(char*)(&one))
+#endif
+
+
+//**************************************
+// Macros
+//**************************************
+#define XXH_STATIC_ASSERT(c)   { enum { XXH_static_assert = 1/(!!(c)) }; }    // use only *after* variable declarations
+
+
+//****************************
+// Memory reads
+//****************************
+typedef enum { XXH_aligned, XXH_unaligned } XXH_alignment;
+
+FORCE_INLINE U32 XXH_readLE32_align(const U32* ptr, XXH_endianess endian, XXH_alignment align)
+{
+    if (align==XXH_unaligned)
+        return endian==XXH_littleEndian ? A32(ptr) : XXH_swap32(A32(ptr));
+    else
+        return endian==XXH_littleEndian ? *ptr : XXH_swap32(*ptr);
+}
+
+FORCE_INLINE U32 XXH_readLE32_align(const void* ptr, XXH_endianess endian,
+                                    XXH_alignment align) {
+  if (align == XXH_unaligned)
+    return endian == XXH_littleEndian ? XXH_read32(ptr)
+                                      : XXH_swap32(XXH_read32(ptr));
+  else
+    return endian == XXH_littleEndian ? *(const U32*)ptr
+                                      : XXH_swap32(*(const U32*)ptr);
+}
+
+FORCE_INLINE U32 XXH_readLE32(const U32* ptr, XXH_endianess endian) {
+  return XXH_readLE32_align(ptr, endian, XXH_unaligned);
+}
+
+//****************************
+// Simple Hash Functions
+//****************************
+#define XXH_get32bits(p) XXH_readLE32_align(p, endian, align)
+
+FORCE_INLINE U32 XXH32_endian_align(const void* input, int len, U32 seed, XXH_endianess endian, XXH_alignment align)
+{
+    const BYTE* p = (const BYTE*)input;
+    const BYTE* const bEnd = p + len;
+    U32 h32;
+
+#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
+    if (p==NULL) { len=0; p=(const BYTE*)(size_t)16; }
+#endif
+
+    if (len>=16)
+    {
+        const BYTE* const limit = bEnd - 16;
+        U32 v1 = seed + PRIME32_1 + PRIME32_2;
+        U32 v2 = seed + PRIME32_2;
+        U32 v3 = seed + 0;
+        U32 v4 = seed - PRIME32_1;
+
+        do
+        {
+            v1 += XXH_readLE32_align((const U32*)p, endian, align) * PRIME32_2; v1 = XXH_rotl32(v1, 13); v1 *= PRIME32_1; p+=4;
+            v2 += XXH_readLE32_align((const U32*)p, endian, align) * PRIME32_2; v2 = XXH_rotl32(v2, 13); v2 *= PRIME32_1; p+=4;
+            v3 += XXH_readLE32_align((const U32*)p, endian, align) * PRIME32_2; v3 = XXH_rotl32(v3, 13); v3 *= PRIME32_1; p+=4;
+            v4 += XXH_readLE32_align((const U32*)p, endian, align) * PRIME32_2; v4 = XXH_rotl32(v4, 13); v4 *= PRIME32_1; p+=4;
+        } while (p<=limit);
+
+        h32 = XXH_rotl32(v1, 1) + XXH_rotl32(v2, 7) + XXH_rotl32(v3, 12) + XXH_rotl32(v4, 18);
+    }
+    else
+    {
+        h32  = seed + PRIME32_5;
+    }
+
+    h32 += (U32) len;
+
+    while (p<=bEnd-4)
+    {
+        h32 += XXH_readLE32_align((const U32*)p, endian, align) * PRIME32_3;
+        h32  = XXH_rotl32(h32, 17) * PRIME32_4 ;
+        p+=4;
+    }
+
+    while (p<bEnd)
+    {
+        h32 += (*p) * PRIME32_5;
+        h32 = XXH_rotl32(h32, 11) * PRIME32_1 ;
+        p++;
+    }
+
+    h32 ^= h32 >> 15;
+    h32 *= PRIME32_2;
+    h32 ^= h32 >> 13;
+    h32 *= PRIME32_3;
+    h32 ^= h32 >> 16;
+
+    return h32;
+}
+
+
+U32 XXH32(const void* input, int len, U32 seed)
+{
+#if 0
+    // Simple version, good for code maintenance, but unfortunately slow for small inputs
+    void* state = XXH32_init(seed);
+    XXH32_update(state, input, len);
+    return XXH32_digest(state);
+#else
+    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
+
+#  if !defined(XXH_USE_UNALIGNED_ACCESS)
+    if ((((size_t)input) & 3))   // Input is aligned, let's leverage the speed advantage
+    {
+        if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
+            return XXH32_endian_align(input, len, seed, XXH_littleEndian, XXH_aligned);
+        else
+            return XXH32_endian_align(input, len, seed, XXH_bigEndian, XXH_aligned);
+    }
+#  endif
+
+    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
+        return XXH32_endian_align(input, len, seed, XXH_littleEndian, XXH_unaligned);
+    else
+        return XXH32_endian_align(input, len, seed, XXH_bigEndian, XXH_unaligned);
+#endif
+}
+
+
+//****************************
+// Advanced Hash Functions
+//****************************
+
+struct XXH_state32_t
+{
+    U64 total_len;
+    U32 seed;
+    U32 v1;
+    U32 v2;
+    U32 v3;
+    U32 v4;
+    int memsize;
+    char memory[16];
+};
+
+
+int XXH32_sizeofState()
+{
+    XXH_STATIC_ASSERT(XXH32_SIZEOFSTATE >= sizeof(struct XXH_state32_t));   // A compilation error here means XXH32_SIZEOFSTATE is not large enough
+    return sizeof(struct XXH_state32_t);
+}
+
+
+XXH_errorcode XXH32_resetState(void* state_in, U32 seed)
+{
+    struct XXH_state32_t * state = (struct XXH_state32_t *) state_in;
+    state->seed = seed;
+    state->v1 = seed + PRIME32_1 + PRIME32_2;
+    state->v2 = seed + PRIME32_2;
+    state->v3 = seed + 0;
+    state->v4 = seed - PRIME32_1;
+    state->total_len = 0;
+    state->memsize = 0;
+    return XXH_OK;
+}
+
+
+void* XXH32_init (U32 seed)
+{
+    void* state = XXH_malloc (sizeof(struct XXH_state32_t));
+    XXH32_resetState(state, seed);
+    return state;
+}
+
+
+FORCE_INLINE XXH_errorcode XXH32_update_endian (void* state_in, const void* input, int len, XXH_endianess endian)
+{
+    struct XXH_state32_t * state = (struct XXH_state32_t *) state_in;
+    const BYTE* p = (const BYTE*)input;
+    const BYTE* const bEnd = p + len;
+
+#ifdef XXH_ACCEPT_NULL_INPUT_POINTER
+    if (input==NULL) return XXH_ERROR;
+#endif
+
+    state->total_len += len;
+
+    if (state->memsize + len < 16)   // fill in tmp buffer
+    {
+        XXH_memcpy(state->memory + state->memsize, input, len);
+        state->memsize +=  len;
+        return XXH_OK;
+    }
+
+    if (state->memsize)   // some data left from previous update
+    {
+        XXH_memcpy(state->memory + state->memsize, input, 16-state->memsize);
+        {
+            const U32* p32 = (const U32*)state->memory;
+            state->v1 += XXH_readLE32(p32, endian) * PRIME32_2; state->v1 = XXH_rotl32(state->v1, 13); state->v1 *= PRIME32_1; p32++;
+            state->v2 += XXH_readLE32(p32, endian) * PRIME32_2; state->v2 = XXH_rotl32(state->v2, 13); state->v2 *= PRIME32_1; p32++;
+            state->v3 += XXH_readLE32(p32, endian) * PRIME32_2; state->v3 = XXH_rotl32(state->v3, 13); state->v3 *= PRIME32_1; p32++;
+            state->v4 += XXH_readLE32(p32, endian) * PRIME32_2; state->v4 = XXH_rotl32(state->v4, 13); state->v4 *= PRIME32_1; p32++;
+        }
+        p += 16-state->memsize;
+        state->memsize = 0;
+    }
+
+    if (p <= bEnd-16)
+    {
+        const BYTE* const limit = bEnd - 16;
+        U32 v1 = state->v1;
+        U32 v2 = state->v2;
+        U32 v3 = state->v3;
+        U32 v4 = state->v4;
+
+        do
+        {
+            v1 += XXH_readLE32((const U32*)p, endian) * PRIME32_2; v1 = XXH_rotl32(v1, 13); v1 *= PRIME32_1; p+=4;
+            v2 += XXH_readLE32((const U32*)p, endian) * PRIME32_2; v2 = XXH_rotl32(v2, 13); v2 *= PRIME32_1; p+=4;
+            v3 += XXH_readLE32((const U32*)p, endian) * PRIME32_2; v3 = XXH_rotl32(v3, 13); v3 *= PRIME32_1; p+=4;
+            v4 += XXH_readLE32((const U32*)p, endian) * PRIME32_2; v4 = XXH_rotl32(v4, 13); v4 *= PRIME32_1; p+=4;
+        } while (p<=limit);
+
+        state->v1 = v1;
+        state->v2 = v2;
+        state->v3 = v3;
+        state->v4 = v4;
+    }
+
+    if (p < bEnd)
+    {
+        XXH_memcpy(state->memory, p, bEnd-p);
+        state->memsize = (int)(bEnd-p);
+    }
+
+    return XXH_OK;
+}
+
+XXH_errorcode XXH32_update (void* state_in, const void* input, int len)
+{
+    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
+
+    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
+        return XXH32_update_endian(state_in, input, len, XXH_littleEndian);
+    else
+        return XXH32_update_endian(state_in, input, len, XXH_bigEndian);
+}
+
+
+
+FORCE_INLINE U32 XXH32_intermediateDigest_endian (void* state_in, XXH_endianess endian)
+{
+    struct XXH_state32_t * state = (struct XXH_state32_t *) state_in;
+    const BYTE * p = (const BYTE*)state->memory;
+    BYTE* bEnd = (BYTE*)state->memory + state->memsize;
+    U32 h32;
+
+    if (state->total_len >= 16)
+    {
+        h32 = XXH_rotl32(state->v1, 1) + XXH_rotl32(state->v2, 7) + XXH_rotl32(state->v3, 12) + XXH_rotl32(state->v4, 18);
+    }
+    else
+    {
+        h32  = state->seed + PRIME32_5;
+    }
+
+    h32 += (U32) state->total_len;
+
+    while (p<=bEnd-4)
+    {
+        h32 += XXH_readLE32((const U32*)p, endian) * PRIME32_3;
+        h32  = XXH_rotl32(h32, 17) * PRIME32_4;
+        p+=4;
+    }
+
+    while (p<bEnd)
+    {
+        h32 += (*p) * PRIME32_5;
+        h32 = XXH_rotl32(h32, 11) * PRIME32_1;
+        p++;
+    }
+
+    h32 ^= h32 >> 15;
+    h32 *= PRIME32_2;
+    h32 ^= h32 >> 13;
+    h32 *= PRIME32_3;
+    h32 ^= h32 >> 16;
+
+    return h32;
+}
+
+
+U32 XXH32_intermediateDigest (void* state_in)
+{
+    XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
+
+    if ((endian_detected==XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
+        return XXH32_intermediateDigest_endian(state_in, XXH_littleEndian);
+    else
+        return XXH32_intermediateDigest_endian(state_in, XXH_bigEndian);
+}
+
+
+U32 XXH32_digest (void* state_in)
+{
+    U32 h32 = XXH32_intermediateDigest(state_in);
+
+    XXH_free(state_in);
+
+    return h32;
+}
+
+/* *******************************************************************
+ *  64-bit hash functions
+ *********************************************************************/
+
+ #if (defined(XXH_FORCE_MEMORY_ACCESS) && (XXH_FORCE_MEMORY_ACCESS==2))
+
+ /* Force direct memory access. Only works on CPU which support unaligned memory access in hardware */
+ static U64 XXH_read64(const void* memPtr) { return *(const U64*) memPtr; }
+
+ #elif (defined(XXH_FORCE_MEMORY_ACCESS) && (XXH_FORCE_MEMORY_ACCESS==1))
+
+ /* __pack instructions are safer, but compiler specific, hence potentially problematic for some compilers */
+ /* currently only defined for gcc and icc */
+ typedef union { U32 u32; U64 u64; } __attribute__((packed)) unalign64;
+ static U64 XXH_read64(const void* ptr) { return ((const unalign64*)ptr)->u64; }
+
+ #else
+
+ /* portable and safe solution. Generally efficient.
+  * see : http://stackoverflow.com/a/32095106/646947
+  */
+
+ static U64 XXH_read64(const void* memPtr)
+ {
+     U64 val;
+     memcpy(&val, memPtr, sizeof(val));
+     return val;
+ }
+#endif   /* XXH_FORCE_DIRECT_MEMORY_ACCESS */
+
+#if defined(_MSC_VER) /* Visual Studio */
+#define XXH_swap64 _byteswap_uint64
+#elif XXH_GCC_VERSION >= 403
+#define XXH_swap64 __builtin_bswap64
+#else
+static U64 XXH_swap64(U64 x) {
+  return ((x << 56) & 0xff00000000000000ULL) |
+         ((x << 40) & 0x00ff000000000000ULL) |
+         ((x << 24) & 0x0000ff0000000000ULL) |
+         ((x << 8) & 0x000000ff00000000ULL) |
+         ((x >> 8) & 0x00000000ff000000ULL) |
+         ((x >> 24) & 0x0000000000ff0000ULL) |
+         ((x >> 40) & 0x000000000000ff00ULL) |
+         ((x >> 56) & 0x00000000000000ffULL);
+}
+#endif
+
+FORCE_INLINE U64 XXH_readLE64_align(const void* ptr, XXH_endianess endian,
+                                    XXH_alignment align) {
+  if (align == XXH_unaligned)
+    return endian == XXH_littleEndian ? XXH_read64(ptr)
+                                      : XXH_swap64(XXH_read64(ptr));
+  else
+    return endian == XXH_littleEndian ? *(const U64*)ptr
+                                      : XXH_swap64(*(const U64*)ptr);
+}
+
+FORCE_INLINE U64 XXH_readLE64(const void* ptr, XXH_endianess endian) {
+  return XXH_readLE64_align(ptr, endian, XXH_unaligned);
+}
+
+static U64 XXH_readBE64(const void* ptr) {
+  return XXH_CPU_LITTLE_ENDIAN ? XXH_swap64(XXH_read64(ptr)) : XXH_read64(ptr);
+}
+
+/*======   xxh64   ======*/
+
+static const U64 PRIME64_1 =
+    11400714785074694791ULL; /* 0b1001111000110111011110011011000110000101111010111100101010000111
+                              */
+static const U64 PRIME64_2 =
+    14029467366897019727ULL; /* 0b1100001010110010101011100011110100100111110101001110101101001111
+                              */
+static const U64 PRIME64_3 =
+    1609587929392839161ULL; /* 0b0001011001010110011001111011000110011110001101110111100111111001
+                             */
+static const U64 PRIME64_4 =
+    9650029242287828579ULL; /* 0b1000010111101011110010100111011111000010101100101010111001100011
+                             */
+static const U64 PRIME64_5 =
+    2870177450012600261ULL; /* 0b0010011111010100111010110010111100010110010101100110011111000101
+                             */
+
+static U64 XXH64_round(U64 acc, U64 input) {
+  acc += input * PRIME64_2;
+  acc = XXH_rotl64(acc, 31);
+  acc *= PRIME64_1;
+  return acc;
+}
+
+static U64 XXH64_mergeRound(U64 acc, U64 val) {
+  val = XXH64_round(0, val);
+  acc ^= val;
+  acc = acc * PRIME64_1 + PRIME64_4;
+  return acc;
+}
+
+static U64 XXH64_avalanche(U64 h64) {
+  h64 ^= h64 >> 33;
+  h64 *= PRIME64_2;
+  h64 ^= h64 >> 29;
+  h64 *= PRIME64_3;
+  h64 ^= h64 >> 32;
+  return h64;
+}
+
+#define XXH_get64bits(p) XXH_readLE64_align(p, endian, align)
+
+static U64 XXH64_finalize(U64 h64, const void* ptr, size_t len,
+                          XXH_endianess endian, XXH_alignment align) {
+  const BYTE* p = (const BYTE*)ptr;
+
+#define PROCESS1_64          \
+  h64 ^= (*p++) * PRIME64_5; \
+  h64 = XXH_rotl64(h64, 11) * PRIME64_1;
+
+#define PROCESS4_64                           \
+  h64 ^= (U64)(XXH_get32bits(p)) * PRIME64_1; \
+  p += 4;                                     \
+  h64 = XXH_rotl64(h64, 23) * PRIME64_2 + PRIME64_3;
+
+#define PROCESS8_64                                    \
+  {                                                    \
+    U64 const k1 = XXH64_round(0, XXH_get64bits(p));   \
+    p += 8;                                            \
+    h64 ^= k1;                                         \
+    h64 = XXH_rotl64(h64, 27) * PRIME64_1 + PRIME64_4; \
+  }
+
+  switch (len & 31) {
+    case 24:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 16:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 8:
+      PROCESS8_64;
+      return XXH64_avalanche(h64);
+
+    case 28:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 20:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 12:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 4:
+      PROCESS4_64;
+      return XXH64_avalanche(h64);
+
+    case 25:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 17:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 9:
+      PROCESS8_64;
+      PROCESS1_64;
+      return XXH64_avalanche(h64);
+
+    case 29:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 21:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 13:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 5:
+      PROCESS4_64;
+      PROCESS1_64;
+      return XXH64_avalanche(h64);
+
+    case 26:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 18:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 10:
+      PROCESS8_64;
+      PROCESS1_64;
+      PROCESS1_64;
+      return XXH64_avalanche(h64);
+
+    case 30:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 22:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 14:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 6:
+      PROCESS4_64;
+      PROCESS1_64;
+      PROCESS1_64;
+      return XXH64_avalanche(h64);
+
+    case 27:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 19:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 11:
+      PROCESS8_64;
+      PROCESS1_64;
+      PROCESS1_64;
+      PROCESS1_64;
+      return XXH64_avalanche(h64);
+
+    case 31:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 23:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 15:
+      PROCESS8_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 7:
+      PROCESS4_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 3:
+      PROCESS1_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 2:
+      PROCESS1_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 1:
+      PROCESS1_64;
+      FALLTHROUGH_INTENDED;
+      /* fallthrough */
+    case 0:
+      return XXH64_avalanche(h64);
+  }
+
+  /* impossible to reach */
+  assert(0);
+  return 0; /* unreachable, but some compilers complain without it */
+}
+
+FORCE_INLINE U64 XXH64_endian_align(const void* input, size_t len, U64 seed,
+                                    XXH_endianess endian, XXH_alignment align) {
+  const BYTE* p = (const BYTE*)input;
+  const BYTE* bEnd = p + len;
+  U64 h64;
+
+#if defined(XXH_ACCEPT_NULL_INPUT_POINTER) && \
+    (XXH_ACCEPT_NULL_INPUT_POINTER >= 1)
+  if (p == NULL) {
+    len = 0;
+    bEnd = p = (const BYTE*)(size_t)32;
+  }
+#endif
+
+  if (len >= 32) {
+    const BYTE* const limit = bEnd - 32;
+    U64 v1 = seed + PRIME64_1 + PRIME64_2;
+    U64 v2 = seed + PRIME64_2;
+    U64 v3 = seed + 0;
+    U64 v4 = seed - PRIME64_1;
+
+    do {
+      v1 = XXH64_round(v1, XXH_get64bits(p));
+      p += 8;
+      v2 = XXH64_round(v2, XXH_get64bits(p));
+      p += 8;
+      v3 = XXH64_round(v3, XXH_get64bits(p));
+      p += 8;
+      v4 = XXH64_round(v4, XXH_get64bits(p));
+      p += 8;
+    } while (p <= limit);
+
+    h64 = XXH_rotl64(v1, 1) + XXH_rotl64(v2, 7) + XXH_rotl64(v3, 12) +
+          XXH_rotl64(v4, 18);
+    h64 = XXH64_mergeRound(h64, v1);
+    h64 = XXH64_mergeRound(h64, v2);
+    h64 = XXH64_mergeRound(h64, v3);
+    h64 = XXH64_mergeRound(h64, v4);
+
+  } else {
+    h64 = seed + PRIME64_5;
+  }
+
+  h64 += (U64)len;
+
+  return XXH64_finalize(h64, p, len, endian, align);
+}
+
+unsigned long long XXH64(const void* input, size_t len,
+                         unsigned long long seed) {
+#if 0
+    /* Simple version, good for code maintenance, but unfortunately slow for small inputs */
+    XXH64_state_t state;
+    XXH64_reset(&state, seed);
+    XXH64_update(&state, input, len);
+    return XXH64_digest(&state);
+#else
+  XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
+
+  if (XXH_FORCE_ALIGN_CHECK) {
+    if ((((size_t)input) & 7) ==
+        0) { /* Input is aligned, let's leverage the speed advantage */
+      if ((endian_detected == XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
+        return XXH64_endian_align(input, len, seed, XXH_littleEndian,
+                                  XXH_aligned);
+      else
+        return XXH64_endian_align(input, len, seed, XXH_bigEndian, XXH_aligned);
+    }
+  }
+
+  if ((endian_detected == XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
+    return XXH64_endian_align(input, len, seed, XXH_littleEndian,
+                              XXH_unaligned);
+  else
+    return XXH64_endian_align(input, len, seed, XXH_bigEndian, XXH_unaligned);
+#endif
+}
+
+/*======   Hash Streaming   ======*/
+
+XXH64_state_t* XXH64_createState(void) {
+  return (XXH64_state_t*)XXH_malloc(sizeof(XXH64_state_t));
+}
+XXH_errorcode XXH64_freeState(XXH64_state_t* statePtr) {
+  XXH_free(statePtr);
+  return XXH_OK;
+}
+
+void XXH64_copyState(XXH64_state_t* dstState, const XXH64_state_t* srcState) {
+  memcpy(dstState, srcState, sizeof(*dstState));
+}
+
+XXH_errorcode XXH64_reset(XXH64_state_t* statePtr, unsigned long long seed) {
+  XXH64_state_t state; /* using a local state to memcpy() in order to avoid
+                          strict-aliasing warnings */
+  memset(&state, 0, sizeof(state));
+  state.v1 = seed + PRIME64_1 + PRIME64_2;
+  state.v2 = seed + PRIME64_2;
+  state.v3 = seed + 0;
+  state.v4 = seed - PRIME64_1;
+  /* do not write into reserved, planned to be removed in a future version */
+  memcpy(statePtr, &state, sizeof(state) - sizeof(state.reserved));
+  return XXH_OK;
+}
+
+FORCE_INLINE XXH_errorcode XXH64_update_endian(XXH64_state_t* state,
+                                               const void* input, size_t len,
+                                               XXH_endianess endian) {
+  if (input == NULL)
+#if defined(XXH_ACCEPT_NULL_INPUT_POINTER) && \
+    (XXH_ACCEPT_NULL_INPUT_POINTER >= 1)
+    return XXH_OK;
+#else
+    return XXH_ERROR;
+#endif
+
+  {
+    const BYTE* p = (const BYTE*)input;
+    const BYTE* const bEnd = p + len;
+
+    state->total_len += len;
+
+    if (state->memsize + len < 32) { /* fill in tmp buffer */
+      XXH_memcpy(((BYTE*)state->mem64) + state->memsize, input, len);
+      state->memsize += (U32)len;
+      return XXH_OK;
+    }
+
+    if (state->memsize) { /* tmp buffer is full */
+      XXH_memcpy(((BYTE*)state->mem64) + state->memsize, input,
+                 32 - state->memsize);
+      state->v1 =
+          XXH64_round(state->v1, XXH_readLE64(state->mem64 + 0, endian));
+      state->v2 =
+          XXH64_round(state->v2, XXH_readLE64(state->mem64 + 1, endian));
+      state->v3 =
+          XXH64_round(state->v3, XXH_readLE64(state->mem64 + 2, endian));
+      state->v4 =
+          XXH64_round(state->v4, XXH_readLE64(state->mem64 + 3, endian));
+      p += 32 - state->memsize;
+      state->memsize = 0;
+    }
+
+    if (p + 32 <= bEnd) {
+      const BYTE* const limit = bEnd - 32;
+      U64 v1 = state->v1;
+      U64 v2 = state->v2;
+      U64 v3 = state->v3;
+      U64 v4 = state->v4;
+
+      do {
+        v1 = XXH64_round(v1, XXH_readLE64(p, endian));
+        p += 8;
+        v2 = XXH64_round(v2, XXH_readLE64(p, endian));
+        p += 8;
+        v3 = XXH64_round(v3, XXH_readLE64(p, endian));
+        p += 8;
+        v4 = XXH64_round(v4, XXH_readLE64(p, endian));
+        p += 8;
+      } while (p <= limit);
+
+      state->v1 = v1;
+      state->v2 = v2;
+      state->v3 = v3;
+      state->v4 = v4;
+    }
+
+    if (p < bEnd) {
+      XXH_memcpy(state->mem64, p, (size_t)(bEnd - p));
+      state->memsize = (unsigned)(bEnd - p);
+    }
+  }
+
+  return XXH_OK;
+}
+
+XXH_errorcode XXH64_update(XXH64_state_t* state_in, const void* input,
+                           size_t len) {
+  XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
+
+  if ((endian_detected == XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
+    return XXH64_update_endian(state_in, input, len, XXH_littleEndian);
+  else
+    return XXH64_update_endian(state_in, input, len, XXH_bigEndian);
+}
+
+FORCE_INLINE U64 XXH64_digest_endian(const XXH64_state_t* state,
+                                     XXH_endianess endian) {
+  U64 h64;
+
+  if (state->total_len >= 32) {
+    U64 const v1 = state->v1;
+    U64 const v2 = state->v2;
+    U64 const v3 = state->v3;
+    U64 const v4 = state->v4;
+
+    h64 = XXH_rotl64(v1, 1) + XXH_rotl64(v2, 7) + XXH_rotl64(v3, 12) +
+          XXH_rotl64(v4, 18);
+    h64 = XXH64_mergeRound(h64, v1);
+    h64 = XXH64_mergeRound(h64, v2);
+    h64 = XXH64_mergeRound(h64, v3);
+    h64 = XXH64_mergeRound(h64, v4);
+  } else {
+    h64 = state->v3 /*seed*/ + PRIME64_5;
+  }
+
+  h64 += (U64)state->total_len;
+
+  return XXH64_finalize(h64, state->mem64, (size_t)state->total_len, endian,
+                        XXH_aligned);
+}
+
+unsigned long long XXH64_digest(const XXH64_state_t* state_in) {
+  XXH_endianess endian_detected = (XXH_endianess)XXH_CPU_LITTLE_ENDIAN;
+
+  if ((endian_detected == XXH_littleEndian) || XXH_FORCE_NATIVE_FORMAT)
+    return XXH64_digest_endian(state_in, XXH_littleEndian);
+  else
+    return XXH64_digest_endian(state_in, XXH_bigEndian);
+}
+
+/*====== Canonical representation   ======*/
+
+void XXH64_canonicalFromHash(XXH64_canonical_t* dst, XXH64_hash_t hash) {
+  XXH_STATIC_ASSERT(sizeof(XXH64_canonical_t) == sizeof(XXH64_hash_t));
+  if (XXH_CPU_LITTLE_ENDIAN) hash = XXH_swap64(hash);
+  memcpy(dst, &hash, sizeof(*dst));
+}
+
+XXH64_hash_t XXH64_hashFromCanonical(const XXH64_canonical_t* src) {
+  return XXH_readBE64(src);
+}
+}  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/util/xxhash.h b/3rdParty/rocksdb/v5.18.X/util/xxhash.h
similarity index 70%
rename from 3rdParty/rocksdb/v5.16.X/util/xxhash.h
rename to 3rdParty/rocksdb/v5.18.X/util/xxhash.h
index 3343e3488f..88352ac75f 100644
--- a/3rdParty/rocksdb/v5.16.X/util/xxhash.h
+++ b/3rdParty/rocksdb/v5.18.X/util/xxhash.h
@@ -59,6 +59,14 @@ It depends on successfully passing SMHasher test set.
 
 #pragma once
 
+#include <stdlib.h>
+
+#if !defined(__VMS) &&       \
+    (defined(__cplusplus) || \
+     (defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */))
+#include <stdint.h>
+#endif
+
 #if defined (__cplusplus)
 namespace rocksdb {
 #endif
@@ -67,6 +75,7 @@ namespace rocksdb {
 //****************************
 // Type
 //****************************
+/* size_t */
 typedef enum { XXH_OK=0, XXH_ERROR } XXH_errorcode;
 
 
@@ -157,7 +166,74 @@ To free memory context, use XXH32_digest(), or free().
 #define XXH32_result XXH32_digest
 #define XXH32_getIntermediateResult XXH32_intermediateDigest
 
+/*-**********************************************************************
+ *  64-bit hash
+ ************************************************************************/
+typedef unsigned long long XXH64_hash_t;
 
+/*! XXH64() :
+    Calculate the 64-bit hash of sequence of length "len" stored at memory
+   address "input". "seed" can be used to alter the result predictably. This
+   function runs faster on 64-bit systems, but slower on 32-bit systems (see
+   benchmark).
+*/
+XXH64_hash_t XXH64(const void* input, size_t length, unsigned long long seed);
+
+/*======   Streaming   ======*/
+typedef struct XXH64_state_s XXH64_state_t; /* incomplete type */
+XXH64_state_t* XXH64_createState(void);
+XXH_errorcode XXH64_freeState(XXH64_state_t* statePtr);
+void XXH64_copyState(XXH64_state_t* dst_state, const XXH64_state_t* src_state);
+
+XXH_errorcode XXH64_reset(XXH64_state_t* statePtr, unsigned long long seed);
+XXH_errorcode XXH64_update(XXH64_state_t* statePtr, const void* input,
+                           size_t length);
+XXH64_hash_t XXH64_digest(const XXH64_state_t* statePtr);
+
+/*======   Canonical representation   ======*/
+typedef struct {
+  unsigned char digest[8];
+} XXH64_canonical_t;
+void XXH64_canonicalFromHash(XXH64_canonical_t* dst, XXH64_hash_t hash);
+XXH64_hash_t XXH64_hashFromCanonical(const XXH64_canonical_t* src);
+
+/* These definitions are only present to allow
+ * static allocation of XXH state, on stack or in a struct for example.
+ * Never **ever** use members directly. */
+
+#if !defined(__VMS) &&       \
+    (defined(__cplusplus) || \
+     (defined(__STDC_VERSION__) && (__STDC_VERSION__ >= 199901L) /* C99 */))
+
+struct XXH64_state_s {
+  uint64_t total_len;
+  uint64_t v1;
+  uint64_t v2;
+  uint64_t v3;
+  uint64_t v4;
+  uint64_t mem64[4];
+  uint32_t memsize;
+  uint32_t reserved[2]; /* never read nor write, might be removed in a future
+                           version */
+};                      /* typedef'd to XXH64_state_t */
+
+#else
+
+#ifndef XXH_NO_LONG_LONG /* remove 64-bit support */
+struct XXH64_state_s {
+  unsigned long long total_len;
+  unsigned long long v1;
+  unsigned long long v2;
+  unsigned long long v3;
+  unsigned long long v4;
+  unsigned long long mem64[4];
+  unsigned memsize;
+  unsigned reserved[2]; /* never read nor write, might be removed in a future
+                           version */
+};                      /* typedef'd to XXH64_state_t */
+#endif
+
+#endif
 
 #if defined (__cplusplus)
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/backupable/backupable_db.cc b/3rdParty/rocksdb/v5.18.X/utilities/backupable/backupable_db.cc
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/utilities/backupable/backupable_db.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/backupable/backupable_db.cc
index 75a65c89a3..78def188cf 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/backupable/backupable_db.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/backupable/backupable_db.cc
@@ -305,16 +305,16 @@ class BackupEngineImpl : public BackupEngine {
   // @param contents If non-empty, the file will be created with these contents.
   Status CopyOrCreateFile(const std::string& src, const std::string& dst,
                           const std::string& contents, Env* src_env,
-                          Env* dst_env, bool sync, RateLimiter* rate_limiter,
+                          Env* dst_env, const EnvOptions& src_env_options,
+                          bool sync, RateLimiter* rate_limiter,
                           uint64_t* size = nullptr,
                           uint32_t* checksum_value = nullptr,
                           uint64_t size_limit = 0,
                           std::function<void()> progress_callback = []() {});
 
-  Status CalculateChecksum(const std::string& src,
-                           Env* src_env,
-                           uint64_t size_limit,
-                           uint32_t* checksum_value);
+  Status CalculateChecksum(const std::string& src, Env* src_env,
+                           const EnvOptions& src_env_options,
+                           uint64_t size_limit, uint32_t* checksum_value);
 
   struct CopyOrCreateResult {
     uint64_t size;
@@ -331,6 +331,7 @@ class BackupEngineImpl : public BackupEngine {
     std::string contents;
     Env* src_env;
     Env* dst_env;
+    EnvOptions src_env_options;
     bool sync;
     RateLimiter* rate_limiter;
     uint64_t size_limit;
@@ -338,14 +339,15 @@ class BackupEngineImpl : public BackupEngine {
     std::function<void()> progress_callback;
 
     CopyOrCreateWorkItem()
-      : src_path(""),
-        dst_path(""),
-        contents(""),
-        src_env(nullptr),
-        dst_env(nullptr),
-        sync(false),
-        rate_limiter(nullptr),
-        size_limit(0) {}
+        : src_path(""),
+          dst_path(""),
+          contents(""),
+          src_env(nullptr),
+          dst_env(nullptr),
+          src_env_options(),
+          sync(false),
+          rate_limiter(nullptr),
+          size_limit(0) {}
 
     CopyOrCreateWorkItem(const CopyOrCreateWorkItem&) = delete;
     CopyOrCreateWorkItem& operator=(const CopyOrCreateWorkItem&) = delete;
@@ -360,6 +362,7 @@ class BackupEngineImpl : public BackupEngine {
       contents = std::move(o.contents);
       src_env = o.src_env;
       dst_env = o.dst_env;
+      src_env_options = std::move(o.src_env_options);
       sync = o.sync;
       rate_limiter = o.rate_limiter;
       size_limit = o.size_limit;
@@ -370,14 +373,15 @@ class BackupEngineImpl : public BackupEngine {
 
     CopyOrCreateWorkItem(std::string _src_path, std::string _dst_path,
                          std::string _contents, Env* _src_env, Env* _dst_env,
-                         bool _sync, RateLimiter* _rate_limiter,
-                         uint64_t _size_limit,
+                         EnvOptions _src_env_options, bool _sync,
+                         RateLimiter* _rate_limiter, uint64_t _size_limit,
                          std::function<void()> _progress_callback = []() {})
         : src_path(std::move(_src_path)),
           dst_path(std::move(_dst_path)),
           contents(std::move(_contents)),
           src_env(_src_env),
           dst_env(_dst_env),
+          src_env_options(std::move(_src_env_options)),
           sync(_sync),
           rate_limiter(_rate_limiter),
           size_limit(_size_limit),
@@ -471,7 +475,8 @@ class BackupEngineImpl : public BackupEngine {
       std::vector<BackupAfterCopyOrCreateWorkItem>& backup_items_to_finish,
       BackupID backup_id, bool shared, const std::string& src_dir,
       const std::string& fname,  // starts with "/"
-      RateLimiter* rate_limiter, uint64_t size_bytes, uint64_t size_limit = 0,
+      const EnvOptions& src_env_options, RateLimiter* rate_limiter,
+      uint64_t size_bytes, uint64_t size_limit = 0,
       bool shared_checksum = false,
       std::function<void()> progress_callback = []() {},
       const std::string& contents = std::string());
@@ -479,9 +484,9 @@ class BackupEngineImpl : public BackupEngine {
   // backup state data
   BackupID latest_backup_id_;
   BackupID latest_valid_backup_id_;
-  std::map<BackupID, unique_ptr<BackupMeta>> backups_;
-  std::map<BackupID,
-           std::pair<Status, unique_ptr<BackupMeta>>> corrupt_backups_;
+  std::map<BackupID, std::unique_ptr<BackupMeta>> backups_;
+  std::map<BackupID, std::pair<Status, std::unique_ptr<BackupMeta>>>
+      corrupt_backups_;
   std::unordered_map<std::string,
                      std::shared_ptr<FileInfo>> backuped_file_infos_;
   std::atomic<bool> stop_backup_;
@@ -492,10 +497,10 @@ class BackupEngineImpl : public BackupEngine {
   Env* backup_env_;
 
   // directories
-  unique_ptr<Directory> backup_directory_;
-  unique_ptr<Directory> shared_directory_;
-  unique_ptr<Directory> meta_directory_;
-  unique_ptr<Directory> private_directory_;
+  std::unique_ptr<Directory> backup_directory_;
+  std::unique_ptr<Directory> shared_directory_;
+  std::unique_ptr<Directory> meta_directory_;
+  std::unique_ptr<Directory> private_directory_;
 
   static const size_t kDefaultCopyFileBufferSize = 5 * 1024 * 1024LL;  // 5MB
   size_t copy_file_buffer_size_;
@@ -616,7 +621,7 @@ Status BackupEngineImpl::Initialize() {
     }
     assert(backups_.find(backup_id) == backups_.end());
     backups_.insert(std::make_pair(
-        backup_id, unique_ptr<BackupMeta>(new BackupMeta(
+        backup_id, std::unique_ptr<BackupMeta>(new BackupMeta(
                        GetBackupMetaFile(backup_id, false /* tmp */),
                        GetBackupMetaFile(backup_id, true /* tmp */),
                        &backuped_file_infos_, backup_env_))));
@@ -723,9 +728,10 @@ Status BackupEngineImpl::Initialize() {
         CopyOrCreateResult result;
         result.status = CopyOrCreateFile(
             work_item.src_path, work_item.dst_path, work_item.contents,
-            work_item.src_env, work_item.dst_env, work_item.sync,
-            work_item.rate_limiter, &result.size, &result.checksum_value,
-            work_item.size_limit, work_item.progress_callback);
+            work_item.src_env, work_item.dst_env, work_item.src_env_options,
+            work_item.sync, work_item.rate_limiter, &result.size,
+            &result.checksum_value, work_item.size_limit,
+            work_item.progress_callback);
         work_item.result.set_value(std::move(result));
       }
     });
@@ -761,7 +767,7 @@ Status BackupEngineImpl::CreateNewBackupWithMetadata(
   }
 
   auto ret = backups_.insert(std::make_pair(
-      new_backup_id, unique_ptr<BackupMeta>(new BackupMeta(
+      new_backup_id, std::unique_ptr<BackupMeta>(new BackupMeta(
                          GetBackupMetaFile(new_backup_id, false /* tmp */),
                          GetBackupMetaFile(new_backup_id, true /* tmp */),
                          &backuped_file_infos_, backup_env_))));
@@ -781,7 +787,7 @@ Status BackupEngineImpl::CreateNewBackupWithMetadata(
 
   RateLimiter* rate_limiter = options_.backup_rate_limiter.get();
   if (rate_limiter) {
-    copy_file_buffer_size_ = rate_limiter->GetSingleBurstBytes();
+    copy_file_buffer_size_ = static_cast<size_t>(rate_limiter->GetSingleBurstBytes());
   }
 
   // A set into which we will insert the dst_paths that are calculated for live
@@ -796,8 +802,10 @@ Status BackupEngineImpl::CreateNewBackupWithMetadata(
   if (s.ok()) {
     CheckpointImpl checkpoint(db);
     uint64_t sequence_number = 0;
+    DBOptions db_options = db->GetDBOptions();
+    EnvOptions src_raw_env_options(db_options);
     s = checkpoint.CreateCustomCheckpoint(
-        db->GetDBOptions(),
+        db_options,
         [&](const std::string& /*src_dirname*/, const std::string& /*fname*/,
             FileType) {
           // custom checkpoint will switch to calling copy_file_cb after it sees
@@ -815,11 +823,33 @@ Status BackupEngineImpl::CreateNewBackupWithMetadata(
           if (type == kTableFile) {
             st = db_env_->GetFileSize(src_dirname + fname, &size_bytes);
           }
+          EnvOptions src_env_options;
+          switch (type) {
+            case kLogFile:
+              src_env_options =
+                  db_env_->OptimizeForLogRead(src_raw_env_options);
+              break;
+            case kTableFile:
+              src_env_options = db_env_->OptimizeForCompactionTableRead(
+                  src_raw_env_options, ImmutableDBOptions(db_options));
+              break;
+            case kDescriptorFile:
+              src_env_options =
+                  db_env_->OptimizeForManifestRead(src_raw_env_options);
+              break;
+            default:
+              // Other backed up files (like options file) are not read by live
+              // DB, so don't need to worry about avoiding mixing buffered and
+              // direct I/O. Just use plain defaults.
+              src_env_options = src_raw_env_options;
+              break;
+          }
           if (st.ok()) {
             st = AddBackupFileWorkItem(
                 live_dst_paths, backup_items_to_finish, new_backup_id,
                 options_.share_table_files && type == kTableFile, src_dirname,
-                fname, rate_limiter, size_bytes, size_limit_bytes,
+                fname, src_env_options, rate_limiter, size_bytes,
+                size_limit_bytes,
                 options_.share_files_with_checksum && type == kTableFile,
                 progress_callback);
           }
@@ -829,8 +859,9 @@ Status BackupEngineImpl::CreateNewBackupWithMetadata(
           Log(options_.info_log, "add file for backup %s", fname.c_str());
           return AddBackupFileWorkItem(
               live_dst_paths, backup_items_to_finish, new_backup_id,
-              false /* shared */, "" /* src_dir */, fname, rate_limiter,
-              contents.size(), 0 /* size_limit */, false /* shared_checksum */,
+              false /* shared */, "" /* src_dir */, fname,
+              EnvOptions() /* src_env_options */, rate_limiter, contents.size(),
+              0 /* size_limit */, false /* shared_checksum */,
               progress_callback, contents);
         } /* create_file_cb */,
         &sequence_number, flush_before_backup ? 0 : port::kMaxUint64);
@@ -869,7 +900,7 @@ Status BackupEngineImpl::CreateNewBackupWithMetadata(
     s = new_backup->StoreToFile(options_.sync);
   }
   if (s.ok() && options_.sync) {
-    unique_ptr<Directory> backup_private_directory;
+    std::unique_ptr<Directory> backup_private_directory;
     backup_env_->NewDirectory(
         GetAbsolutePath(GetPrivateFileRel(new_backup_id, false)),
         &backup_private_directory);
@@ -1078,7 +1109,7 @@ Status BackupEngineImpl::RestoreDBFromBackup(
 
   RateLimiter* rate_limiter = options_.restore_rate_limiter.get();
   if (rate_limiter) {
-    copy_file_buffer_size_ = rate_limiter->GetSingleBurstBytes();
+    copy_file_buffer_size_ = static_cast<size_t>(rate_limiter->GetSingleBurstBytes());
   }
   Status s;
   std::vector<RestoreAfterCopyOrCreateWorkItem> restore_items_to_finish;
@@ -1114,7 +1145,8 @@ Status BackupEngineImpl::RestoreDBFromBackup(
                    dst.c_str());
     CopyOrCreateWorkItem copy_or_create_work_item(
         GetAbsolutePath(file), dst, "" /* contents */, backup_env_, db_env_,
-        false, rate_limiter, 0 /* size_limit */);
+        EnvOptions() /* src_env_options */, false, rate_limiter,
+        0 /* size_limit */);
     RestoreAfterCopyOrCreateWorkItem after_copy_or_create_work_item(
         copy_or_create_work_item.result.get_future(),
         file_info->checksum_value);
@@ -1183,15 +1215,15 @@ Status BackupEngineImpl::VerifyBackup(BackupID backup_id) {
 
 Status BackupEngineImpl::CopyOrCreateFile(
     const std::string& src, const std::string& dst, const std::string& contents,
-    Env* src_env, Env* dst_env, bool sync, RateLimiter* rate_limiter,
-    uint64_t* size, uint32_t* checksum_value, uint64_t size_limit,
-    std::function<void()> progress_callback) {
+    Env* src_env, Env* dst_env, const EnvOptions& src_env_options, bool sync,
+    RateLimiter* rate_limiter, uint64_t* size, uint32_t* checksum_value,
+    uint64_t size_limit, std::function<void()> progress_callback) {
   assert(src.empty() != contents.empty());
   Status s;
-  unique_ptr<WritableFile> dst_file;
-  unique_ptr<SequentialFile> src_file;
-  EnvOptions env_options;
-  env_options.use_mmap_writes = false;
+  std::unique_ptr<WritableFile> dst_file;
+  std::unique_ptr<SequentialFile> src_file;
+  EnvOptions dst_env_options;
+  dst_env_options.use_mmap_writes = false;
   // TODO:(gzh) maybe use direct reads/writes here if possible
   if (size != nullptr) {
     *size = 0;
@@ -1205,18 +1237,18 @@ Status BackupEngineImpl::CopyOrCreateFile(
     size_limit = std::numeric_limits<uint64_t>::max();
   }
 
-  s = dst_env->NewWritableFile(dst, &dst_file, env_options);
+  s = dst_env->NewWritableFile(dst, &dst_file, dst_env_options);
   if (s.ok() && !src.empty()) {
-    s = src_env->NewSequentialFile(src, &src_file, env_options);
+    s = src_env->NewSequentialFile(src, &src_file, src_env_options);
   }
   if (!s.ok()) {
     return s;
   }
 
-  unique_ptr<WritableFileWriter> dest_writer(
-      new WritableFileWriter(std::move(dst_file), env_options));
-  unique_ptr<SequentialFileReader> src_reader;
-  unique_ptr<char[]> buf;
+  std::unique_ptr<WritableFileWriter> dest_writer(
+      new WritableFileWriter(std::move(dst_file), dst, dst_env_options));
+  std::unique_ptr<SequentialFileReader> src_reader;
+  std::unique_ptr<char[]> buf;
   if (!src.empty()) {
     src_reader.reset(new SequentialFileReader(std::move(src_file), src));
     buf.reset(new char[copy_file_buffer_size_]);
@@ -1231,7 +1263,7 @@ Status BackupEngineImpl::CopyOrCreateFile(
     if (!src.empty()) {
       size_t buffer_to_read = (copy_file_buffer_size_ < size_limit)
                                   ? copy_file_buffer_size_
-                                  : size_limit;
+                                  : static_cast<size_t>(size_limit);
       s = src_reader->Read(buffer_to_read, &data, buf.get());
       processed_buffer_size += buffer_to_read;
     } else {
@@ -1276,9 +1308,10 @@ Status BackupEngineImpl::AddBackupFileWorkItem(
     std::unordered_set<std::string>& live_dst_paths,
     std::vector<BackupAfterCopyOrCreateWorkItem>& backup_items_to_finish,
     BackupID backup_id, bool shared, const std::string& src_dir,
-    const std::string& fname, RateLimiter* rate_limiter, uint64_t size_bytes,
-    uint64_t size_limit, bool shared_checksum,
-    std::function<void()> progress_callback, const std::string& contents) {
+    const std::string& fname, const EnvOptions& src_env_options,
+    RateLimiter* rate_limiter, uint64_t size_bytes, uint64_t size_limit,
+    bool shared_checksum, std::function<void()> progress_callback,
+    const std::string& contents) {
   assert(!fname.empty() && fname[0] == '/');
   assert(contents.empty() != src_dir.empty());
 
@@ -1289,7 +1322,7 @@ Status BackupEngineImpl::AddBackupFileWorkItem(
 
   if (shared && shared_checksum) {
     // add checksum and file length to the file name
-    s = CalculateChecksum(src_dir + fname, db_env_, size_limit,
+    s = CalculateChecksum(src_dir + fname, db_env_, src_env_options, size_limit,
                           &checksum_value);
     if (!s.ok()) {
       return s;
@@ -1365,8 +1398,8 @@ Status BackupEngineImpl::AddBackupFileWorkItem(
       // the file is present and referenced by a backup
       ROCKS_LOG_INFO(options_.info_log,
                      "%s already present, calculate checksum", fname.c_str());
-      s = CalculateChecksum(src_dir + fname, db_env_, size_limit,
-                            &checksum_value);
+      s = CalculateChecksum(src_dir + fname, db_env_, src_env_options,
+                            size_limit, &checksum_value);
     }
   }
   live_dst_paths.insert(final_dest_path);
@@ -1376,8 +1409,8 @@ Status BackupEngineImpl::AddBackupFileWorkItem(
                    copy_dest_path->c_str());
     CopyOrCreateWorkItem copy_or_create_work_item(
         src_dir.empty() ? "" : src_dir + fname, *copy_dest_path, contents,
-        db_env_, backup_env_, options_.sync, rate_limiter, size_limit,
-        progress_callback);
+        db_env_, backup_env_, src_env_options, options_.sync, rate_limiter,
+        size_limit, progress_callback);
     BackupAfterCopyOrCreateWorkItem after_copy_or_create_work_item(
         copy_or_create_work_item.result.get_future(), shared, need_to_copy,
         backup_env_, temp_dest_path, final_dest_path, dst_relative);
@@ -1399,6 +1432,7 @@ Status BackupEngineImpl::AddBackupFileWorkItem(
 }
 
 Status BackupEngineImpl::CalculateChecksum(const std::string& src, Env* src_env,
+                                           const EnvOptions& src_env_options,
                                            uint64_t size_limit,
                                            uint32_t* checksum_value) {
   *checksum_value = 0;
@@ -1406,17 +1440,13 @@ Status BackupEngineImpl::CalculateChecksum(const std::string& src, Env* src_env,
     size_limit = std::numeric_limits<uint64_t>::max();
   }
 
-  EnvOptions env_options;
-  env_options.use_mmap_writes = false;
-  env_options.use_direct_reads = false;
-
   std::unique_ptr<SequentialFile> src_file;
-  Status s = src_env->NewSequentialFile(src, &src_file, env_options);
+  Status s = src_env->NewSequentialFile(src, &src_file, src_env_options);
   if (!s.ok()) {
     return s;
   }
 
-  unique_ptr<SequentialFileReader> src_reader(
+  std::unique_ptr<SequentialFileReader> src_reader(
       new SequentialFileReader(std::move(src_file), src));
   std::unique_ptr<char[]> buf(new char[copy_file_buffer_size_]);
   Slice data;
@@ -1426,7 +1456,7 @@ Status BackupEngineImpl::CalculateChecksum(const std::string& src, Env* src_env,
       return Status::Incomplete("Backup stopped");
     }
     size_t buffer_to_read = (copy_file_buffer_size_ < size_limit) ?
-      copy_file_buffer_size_ : size_limit;
+      copy_file_buffer_size_ : static_cast<size_t>(size_limit);
     s = src_reader->Read(buffer_to_read, &data, buf.get());
 
     if (!s.ok()) {
@@ -1634,15 +1664,15 @@ Status BackupEngineImpl::BackupMeta::LoadFromFile(
     const std::unordered_map<std::string, uint64_t>& abs_path_to_size) {
   assert(Empty());
   Status s;
-  unique_ptr<SequentialFile> backup_meta_file;
+  std::unique_ptr<SequentialFile> backup_meta_file;
   s = env_->NewSequentialFile(meta_filename_, &backup_meta_file, EnvOptions());
   if (!s.ok()) {
     return s;
   }
 
-  unique_ptr<SequentialFileReader> backup_meta_reader(
+  std::unique_ptr<SequentialFileReader> backup_meta_reader(
       new SequentialFileReader(std::move(backup_meta_file), meta_filename_));
-  unique_ptr<char[]> buf(new char[max_backup_meta_file_size_ + 1]);
+  std::unique_ptr<char[]> buf(new char[max_backup_meta_file_size_ + 1]);
   Slice data;
   s = backup_meta_reader->Read(max_backup_meta_file_size_, &data, buf.get());
 
@@ -1736,7 +1766,7 @@ Status BackupEngineImpl::BackupMeta::LoadFromFile(
 
 Status BackupEngineImpl::BackupMeta::StoreToFile(bool sync) {
   Status s;
-  unique_ptr<WritableFile> backup_meta_file;
+  std::unique_ptr<WritableFile> backup_meta_file;
   EnvOptions env_options;
   env_options.use_mmap_writes = false;
   env_options.use_direct_writes = false;
@@ -1745,7 +1775,7 @@ Status BackupEngineImpl::BackupMeta::StoreToFile(bool sync) {
     return s;
   }
 
-  unique_ptr<char[]> buf(new char[max_backup_meta_file_size_]);
+  std::unique_ptr<char[]> buf(new char[max_backup_meta_file_size_]);
   size_t len = 0, buf_size = max_backup_meta_file_size_;
   len += snprintf(buf.get(), buf_size, "%" PRId64 "\n", timestamp_);
   len += snprintf(buf.get() + len, buf_size - len, "%" PRIu64 "\n",
@@ -1762,7 +1792,8 @@ Status BackupEngineImpl::BackupMeta::StoreToFile(bool sync) {
     else if (len + hex_meta_strlen >= buf_size) {
       backup_meta_file->Append(Slice(buf.get(), len));
       buf.reset();
-      unique_ptr<char[]> new_reset_buf(new char[max_backup_meta_file_size_]);
+      std::unique_ptr<char[]> new_reset_buf(
+          new char[max_backup_meta_file_size_]);
       buf.swap(new_reset_buf);
       len = 0;
     }
@@ -1776,7 +1807,7 @@ Status BackupEngineImpl::BackupMeta::StoreToFile(bool sync) {
                      "%" ROCKSDB_PRIszt "\n", files_.size()) >= buf_size) {
     backup_meta_file->Append(Slice(buf.get(), len));
     buf.reset();
-    unique_ptr<char[]> new_reset_buf(new char[max_backup_meta_file_size_]);
+    std::unique_ptr<char[]> new_reset_buf(new char[max_backup_meta_file_size_]);
     buf.swap(new_reset_buf);
     len = 0;
   }
@@ -1794,7 +1825,8 @@ Status BackupEngineImpl::BackupMeta::StoreToFile(bool sync) {
     if (newlen >= buf_size) {
       backup_meta_file->Append(Slice(buf.get(), len));
       buf.reset();
-      unique_ptr<char[]> new_reset_buf(new char[max_backup_meta_file_size_]);
+      std::unique_ptr<char[]> new_reset_buf(
+          new char[max_backup_meta_file_size_]);
       buf.swap(new_reset_buf);
       len = 0;
     }
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/backupable/backupable_db_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/backupable/backupable_db_test.cc
similarity index 92%
rename from 3rdParty/rocksdb/v5.16.X/utilities/backupable/backupable_db_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/backupable/backupable_db_test.cc
index 9fdc058fd0..26ff00e91a 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/backupable/backupable_db_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/backupable/backupable_db_test.cc
@@ -179,7 +179,8 @@ class TestEnv : public EnvWrapper {
     bool fail_reads_;
   };
 
-  Status NewSequentialFile(const std::string& f, unique_ptr<SequentialFile>* r,
+  Status NewSequentialFile(const std::string& f,
+                           std::unique_ptr<SequentialFile>* r,
                            const EnvOptions& options) override {
     MutexLock l(&mutex_);
     if (dummy_sequential_file_) {
@@ -187,11 +188,18 @@ class TestEnv : public EnvWrapper {
           new TestEnv::DummySequentialFile(dummy_sequential_file_fail_reads_));
       return Status::OK();
     } else {
-      return EnvWrapper::NewSequentialFile(f, r, options);
+      Status s = EnvWrapper::NewSequentialFile(f, r, options);
+      if (s.ok()) {
+        if ((*r)->use_direct_io()) {
+          ++num_direct_seq_readers_;
+        }
+        ++num_seq_readers_;
+      }
+      return s;
     }
   }
 
-  Status NewWritableFile(const std::string& f, unique_ptr<WritableFile>* r,
+  Status NewWritableFile(const std::string& f, std::unique_ptr<WritableFile>* r,
                          const EnvOptions& options) override {
     MutexLock l(&mutex_);
     written_files_.push_back(f);
@@ -199,7 +207,28 @@ class TestEnv : public EnvWrapper {
       return Status::NotSupported("Sorry, can't do this");
     }
     limit_written_files_--;
-    return EnvWrapper::NewWritableFile(f, r, options);
+    Status s = EnvWrapper::NewWritableFile(f, r, options);
+    if (s.ok()) {
+      if ((*r)->use_direct_io()) {
+        ++num_direct_writers_;
+      }
+      ++num_writers_;
+    }
+    return s;
+  }
+
+  virtual Status NewRandomAccessFile(const std::string& fname,
+                                     unique_ptr<RandomAccessFile>* result,
+                                     const EnvOptions& options) override {
+    MutexLock l(&mutex_);
+    Status s = EnvWrapper::NewRandomAccessFile(fname, result, options);
+    if (s.ok()) {
+      if ((*result)->use_direct_io()) {
+        ++num_direct_rand_readers_;
+      }
+      ++num_rand_readers_;
+    }
+    return s;
   }
 
   virtual Status DeleteFile(const std::string& fname) override {
@@ -308,13 +337,30 @@ class TestEnv : public EnvWrapper {
 
   void SetNewDirectoryFailure(bool fail) { new_directory_failure_ = fail; }
   virtual Status NewDirectory(const std::string& name,
-                              unique_ptr<Directory>* result) override {
+                              std::unique_ptr<Directory>* result) override {
     if (new_directory_failure_) {
       return Status::IOError("SimulatedFailure");
     }
     return EnvWrapper::NewDirectory(name, result);
   }
 
+  void ClearFileOpenCounters() {
+    MutexLock l(&mutex_);
+    num_rand_readers_ = 0;
+    num_direct_rand_readers_ = 0;
+    num_seq_readers_ = 0;
+    num_direct_seq_readers_ = 0;
+    num_writers_ = 0;
+    num_direct_writers_ = 0;
+  }
+
+  int num_rand_readers() { return num_rand_readers_; }
+  int num_direct_rand_readers() { return num_direct_rand_readers_; }
+  int num_seq_readers() { return num_seq_readers_; }
+  int num_direct_seq_readers() { return num_direct_seq_readers_; }
+  int num_writers() { return num_writers_; }
+  int num_direct_writers() { return num_direct_writers_; }
+
  private:
   port::Mutex mutex_;
   bool dummy_sequential_file_ = false;
@@ -328,6 +374,15 @@ class TestEnv : public EnvWrapper {
   bool get_children_failure_ = false;
   bool create_dir_if_missing_failure_ = false;
   bool new_directory_failure_ = false;
+
+  // Keeps track of how many files of each type were successfully opened, and
+  // out of those, how many were opened with direct I/O.
+  std::atomic<int> num_rand_readers_;
+  std::atomic<int> num_direct_rand_readers_;
+  std::atomic<int> num_seq_readers_;
+  std::atomic<int> num_direct_seq_readers_;
+  std::atomic<int> num_writers_;
+  std::atomic<int> num_direct_writers_;
 };  // TestEnv
 
 class FileManager : public EnvWrapper {
@@ -427,7 +482,7 @@ class FileManager : public EnvWrapper {
   }
 
   Status WriteToFile(const std::string& fname, const std::string& data) {
-    unique_ptr<WritableFile> file;
+    std::unique_ptr<WritableFile> file;
     EnvOptions env_options;
     env_options.use_mmap_writes = false;
     Status s = EnvWrapper::NewWritableFile(fname, &file, env_options);
@@ -620,22 +675,22 @@ class BackupableDBTest : public testing::Test {
   std::shared_ptr<Logger> logger_;
 
   // envs
-  unique_ptr<Env> db_chroot_env_;
-  unique_ptr<Env> backup_chroot_env_;
-  unique_ptr<TestEnv> test_db_env_;
-  unique_ptr<TestEnv> test_backup_env_;
-  unique_ptr<FileManager> file_manager_;
+  std::unique_ptr<Env> db_chroot_env_;
+  std::unique_ptr<Env> backup_chroot_env_;
+  std::unique_ptr<TestEnv> test_db_env_;
+  std::unique_ptr<TestEnv> test_backup_env_;
+  std::unique_ptr<FileManager> file_manager_;
 
   // all the dbs!
   DummyDB* dummy_db_; // BackupableDB owns dummy_db_
-  unique_ptr<DB> db_;
-  unique_ptr<BackupEngine> backup_engine_;
+  std::unique_ptr<DB> db_;
+  std::unique_ptr<BackupEngine> backup_engine_;
 
   // options
   Options options_;
 
  protected:
-  unique_ptr<BackupableDBOptions> backupable_options_;
+  std::unique_ptr<BackupableDBOptions> backupable_options_;
 }; // BackupableDBTest
 
 void AppendPath(const std::string& path, std::vector<std::string>& v) {
@@ -1633,6 +1688,59 @@ TEST_F(BackupableDBTest, WriteOnlyEngineNoSharedFileDeletion) {
     AssertBackupConsistency(i + 1, 0, (i + 1) * kNumKeys);
   }
 }
+
+TEST_P(BackupableDBTestWithParam, BackupUsingDirectIO) {
+  // Tests direct I/O on the backup engine's reads and writes on the DB env and
+  // backup env
+  // We use ChrootEnv underneath so the below line checks for direct I/O support
+  // in the chroot directory, not the true filesystem root.
+  if (!test::IsDirectIOSupported(test_db_env_.get(), "/")) {
+    return;
+  }
+  const int kNumKeysPerBackup = 100;
+  const int kNumBackups = 3;
+  options_.use_direct_reads = true;
+  OpenDBAndBackupEngine(true /* destroy_old_data */);
+  for (int i = 0; i < kNumBackups; ++i) {
+    FillDB(db_.get(), i * kNumKeysPerBackup /* from */,
+           (i + 1) * kNumKeysPerBackup /* to */);
+    ASSERT_OK(db_->Flush(FlushOptions()));
+
+    // Clear the file open counters and then do a bunch of backup engine ops.
+    // For all ops, files should be opened in direct mode.
+    test_backup_env_->ClearFileOpenCounters();
+    test_db_env_->ClearFileOpenCounters();
+    CloseBackupEngine();
+    OpenBackupEngine();
+    ASSERT_OK(backup_engine_->CreateNewBackup(db_.get(),
+                                              false /* flush_before_backup */));
+    ASSERT_OK(backup_engine_->VerifyBackup(i + 1));
+    CloseBackupEngine();
+    OpenBackupEngine();
+    std::vector<BackupInfo> backup_infos;
+    backup_engine_->GetBackupInfo(&backup_infos);
+    ASSERT_EQ(static_cast<size_t>(i + 1), backup_infos.size());
+
+    // Verify backup engine always opened files with direct I/O
+    ASSERT_EQ(0, test_db_env_->num_writers());
+    ASSERT_EQ(0, test_db_env_->num_rand_readers());
+    ASSERT_GT(test_db_env_->num_direct_seq_readers(), 0);
+    // Currently the DB doesn't support reading WALs or manifest with direct
+    // I/O, so subtract two.
+    ASSERT_EQ(test_db_env_->num_seq_readers() - 2,
+              test_db_env_->num_direct_seq_readers());
+    ASSERT_EQ(0, test_db_env_->num_rand_readers());
+  }
+  CloseDBAndBackupEngine();
+
+  for (int i = 0; i < kNumBackups; ++i) {
+    AssertBackupConsistency(i + 1 /* backup_id */,
+                            i * kNumKeysPerBackup /* start_exist */,
+                            (i + 1) * kNumKeysPerBackup /* end_exist */,
+                            (i + 2) * kNumKeysPerBackup /* end */);
+  }
+}
+
 }  // anon namespace
 
 } //  namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_compaction_filter.cc b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_compaction_filter.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_compaction_filter.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_compaction_filter.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_compaction_filter.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_compaction_filter.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_compaction_filter.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_compaction_filter.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db.cc b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_impl.cc b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_impl.cc
similarity index 87%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_impl.cc
index 06ef0ed3c4..bdec654628 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_impl.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_impl.cc
@@ -304,13 +304,17 @@ void BlobDBImpl::CloseRandomAccessLocked(
   open_file_count_--;
 }
 
-std::shared_ptr<RandomAccessFileReader> BlobDBImpl::GetOrOpenRandomAccessReader(
-    const std::shared_ptr<BlobFile>& bfile, Env* env,
-    const EnvOptions& env_options) {
+Status BlobDBImpl::GetBlobFileReader(
+    const std::shared_ptr<BlobFile>& blob_file,
+    std::shared_ptr<RandomAccessFileReader>* reader) {
+  assert(reader != nullptr);
   bool fresh_open = false;
-  auto rar = bfile->GetOrOpenRandomAccessReader(env, env_options, &fresh_open);
-  if (fresh_open) open_file_count_++;
-  return rar;
+  Status s = blob_file->GetReader(env_, env_options_, reader, &fresh_open);
+  if (s.ok() && fresh_open) {
+    assert(*reader != nullptr);
+    open_file_count_++;
+  }
+  return s;
 }
 
 std::shared_ptr<BlobFile> BlobDBImpl::NewBlobFile(const std::string& reason) {
@@ -338,7 +342,7 @@ Status BlobDBImpl::CreateWriterLocked(const std::shared_ptr<BlobFile>& bfile) {
   }
 
   std::unique_ptr<WritableFileWriter> fwriter;
-  fwriter.reset(new WritableFileWriter(std::move(wfile), env_options_));
+  fwriter.reset(new WritableFileWriter(std::move(wfile), fpath, env_options_));
 
   uint64_t boffset = bfile->GetFileSize();
   if (debug_level_ >= 2 && boffset) {
@@ -400,82 +404,91 @@ std::shared_ptr<BlobFile> BlobDBImpl::FindBlobFileLocked(
   return (b1 || b2) ? nullptr : (*finditr);
 }
 
-std::shared_ptr<Writer> BlobDBImpl::CheckOrCreateWriterLocked(
-    const std::shared_ptr<BlobFile>& bfile) {
-  std::shared_ptr<Writer> writer = bfile->GetWriter();
-  if (writer) return writer;
-
-  Status s = CreateWriterLocked(bfile);
-  if (!s.ok()) return nullptr;
-
-  writer = bfile->GetWriter();
-  return writer;
+Status BlobDBImpl::CheckOrCreateWriterLocked(
+    const std::shared_ptr<BlobFile>& blob_file,
+    std::shared_ptr<Writer>* writer) {
+  assert(writer != nullptr);
+  *writer = blob_file->GetWriter();
+  if (*writer != nullptr) {
+    return Status::OK();
+  }
+  Status s = CreateWriterLocked(blob_file);
+  if (s.ok()) {
+    *writer = blob_file->GetWriter();
+  }
+  return s;
 }
 
-std::shared_ptr<BlobFile> BlobDBImpl::SelectBlobFile() {
+Status BlobDBImpl::SelectBlobFile(std::shared_ptr<BlobFile>* blob_file) {
+  assert(blob_file != nullptr);
   {
     ReadLock rl(&mutex_);
     if (open_non_ttl_file_ != nullptr) {
-      return open_non_ttl_file_;
+      *blob_file = open_non_ttl_file_;
+      return Status::OK();
     }
   }
 
   // CHECK again
   WriteLock wl(&mutex_);
   if (open_non_ttl_file_ != nullptr) {
-    return open_non_ttl_file_;
+    *blob_file = open_non_ttl_file_;
+    return Status::OK();
   }
 
-  std::shared_ptr<BlobFile> bfile = NewBlobFile("SelectBlobFile");
-  assert(bfile);
+  *blob_file = NewBlobFile("SelectBlobFile");
+  assert(*blob_file != nullptr);
 
   // file not visible, hence no lock
-  std::shared_ptr<Writer> writer = CheckOrCreateWriterLocked(bfile);
-  if (!writer) {
+  std::shared_ptr<Writer> writer;
+  Status s = CheckOrCreateWriterLocked(*blob_file, &writer);
+  if (!s.ok()) {
     ROCKS_LOG_ERROR(db_options_.info_log,
-                    "Failed to get writer from blob file: %s",
-                    bfile->PathName().c_str());
-    return nullptr;
+                    "Failed to get writer from blob file: %s, error: %s",
+                    (*blob_file)->PathName().c_str(), s.ToString().c_str());
+    return s;
   }
 
-  bfile->file_size_ = BlobLogHeader::kSize;
-  bfile->header_.compression = bdb_options_.compression;
-  bfile->header_.has_ttl = false;
-  bfile->header_.column_family_id =
+  (*blob_file)->file_size_ = BlobLogHeader::kSize;
+  (*blob_file)->header_.compression = bdb_options_.compression;
+  (*blob_file)->header_.has_ttl = false;
+  (*blob_file)->header_.column_family_id =
       reinterpret_cast<ColumnFamilyHandleImpl*>(DefaultColumnFamily())->GetID();
-  bfile->header_valid_ = true;
-  bfile->SetColumnFamilyId(bfile->header_.column_family_id);
-  bfile->SetHasTTL(false);
-  bfile->SetCompression(bdb_options_.compression);
+  (*blob_file)->header_valid_ = true;
+  (*blob_file)->SetColumnFamilyId((*blob_file)->header_.column_family_id);
+  (*blob_file)->SetHasTTL(false);
+  (*blob_file)->SetCompression(bdb_options_.compression);
 
-  Status s = writer->WriteHeader(bfile->header_);
+  s = writer->WriteHeader((*blob_file)->header_);
   if (!s.ok()) {
     ROCKS_LOG_ERROR(db_options_.info_log,
                     "Failed to write header to new blob file: %s"
                     " status: '%s'",
-                    bfile->PathName().c_str(), s.ToString().c_str());
-    return nullptr;
+                    (*blob_file)->PathName().c_str(), s.ToString().c_str());
+    return s;
   }
 
-  blob_files_.insert(std::make_pair(bfile->BlobFileNumber(), bfile));
-  open_non_ttl_file_ = bfile;
+  blob_files_.insert(
+      std::make_pair((*blob_file)->BlobFileNumber(), *blob_file));
+  open_non_ttl_file_ = *blob_file;
   total_blob_size_ += BlobLogHeader::kSize;
-  return bfile;
+  return s;
 }
 
-std::shared_ptr<BlobFile> BlobDBImpl::SelectBlobFileTTL(uint64_t expiration) {
+Status BlobDBImpl::SelectBlobFileTTL(uint64_t expiration,
+                                     std::shared_ptr<BlobFile>* blob_file) {
+  assert(blob_file != nullptr);
   assert(expiration != kNoExpiration);
   uint64_t epoch_read = 0;
-  std::shared_ptr<BlobFile> bfile;
   {
     ReadLock rl(&mutex_);
-    bfile = FindBlobFileLocked(expiration);
+    *blob_file = FindBlobFileLocked(expiration);
     epoch_read = epoch_of_.load();
   }
 
-  if (bfile) {
-    assert(!bfile->Immutable());
-    return bfile;
+  if (*blob_file != nullptr) {
+    assert(!(*blob_file)->Immutable());
+    return Status::OK();
   }
 
   uint64_t exp_low =
@@ -483,61 +496,66 @@ std::shared_ptr<BlobFile> BlobDBImpl::SelectBlobFileTTL(uint64_t expiration) {
   uint64_t exp_high = exp_low + bdb_options_.ttl_range_secs;
   ExpirationRange expiration_range = std::make_pair(exp_low, exp_high);
 
-  bfile = NewBlobFile("SelectBlobFileTTL");
-  assert(bfile);
+  *blob_file = NewBlobFile("SelectBlobFileTTL");
+  assert(*blob_file != nullptr);
 
   ROCKS_LOG_INFO(db_options_.info_log, "New blob file TTL range: %s %d %d",
-                 bfile->PathName().c_str(), exp_low, exp_high);
+                 (*blob_file)->PathName().c_str(), exp_low, exp_high);
   LogFlush(db_options_.info_log);
 
   // we don't need to take lock as no other thread is seeing bfile yet
-  std::shared_ptr<Writer> writer = CheckOrCreateWriterLocked(bfile);
-  if (!writer) {
-    ROCKS_LOG_ERROR(db_options_.info_log,
-                    "Failed to get writer from blob file with TTL: %s",
-                    bfile->PathName().c_str());
-    return nullptr;
+  std::shared_ptr<Writer> writer;
+  Status s = CheckOrCreateWriterLocked(*blob_file, &writer);
+  if (!s.ok()) {
+    ROCKS_LOG_ERROR(
+        db_options_.info_log,
+        "Failed to get writer from blob file with TTL: %s, error: %s",
+        (*blob_file)->PathName().c_str(), s.ToString().c_str());
+    return s;
   }
 
-  bfile->header_.expiration_range = expiration_range;
-  bfile->header_.compression = bdb_options_.compression;
-  bfile->header_.has_ttl = true;
-  bfile->header_.column_family_id =
+  (*blob_file)->header_.expiration_range = expiration_range;
+  (*blob_file)->header_.compression = bdb_options_.compression;
+  (*blob_file)->header_.has_ttl = true;
+  (*blob_file)->header_.column_family_id =
       reinterpret_cast<ColumnFamilyHandleImpl*>(DefaultColumnFamily())->GetID();
-  ;
-  bfile->header_valid_ = true;
-  bfile->SetColumnFamilyId(bfile->header_.column_family_id);
-  bfile->SetHasTTL(true);
-  bfile->SetCompression(bdb_options_.compression);
-  bfile->file_size_ = BlobLogHeader::kSize;
+  (*blob_file)->header_valid_ = true;
+  (*blob_file)->SetColumnFamilyId((*blob_file)->header_.column_family_id);
+  (*blob_file)->SetHasTTL(true);
+  (*blob_file)->SetCompression(bdb_options_.compression);
+  (*blob_file)->file_size_ = BlobLogHeader::kSize;
 
   // set the first value of the range, since that is
   // concrete at this time.  also necessary to add to open_ttl_files_
-  bfile->expiration_range_ = expiration_range;
+  (*blob_file)->expiration_range_ = expiration_range;
 
   WriteLock wl(&mutex_);
   // in case the epoch has shifted in the interim, then check
   // check condition again - should be rare.
   if (epoch_of_.load() != epoch_read) {
-    auto bfile2 = FindBlobFileLocked(expiration);
-    if (bfile2) return bfile2;
+    std::shared_ptr<BlobFile> blob_file2 = FindBlobFileLocked(expiration);
+    if (blob_file2 != nullptr) {
+      *blob_file = std::move(blob_file2);
+      return Status::OK();
+    }
   }
 
-  Status s = writer->WriteHeader(bfile->header_);
+  s = writer->WriteHeader((*blob_file)->header_);
   if (!s.ok()) {
     ROCKS_LOG_ERROR(db_options_.info_log,
                     "Failed to write header to new blob file: %s"
                     " status: '%s'",
-                    bfile->PathName().c_str(), s.ToString().c_str());
-    return nullptr;
+                    (*blob_file)->PathName().c_str(), s.ToString().c_str());
+    return s;
   }
 
-  blob_files_.insert(std::make_pair(bfile->BlobFileNumber(), bfile));
-  open_ttl_files_.insert(bfile);
+  blob_files_.insert(
+      std::make_pair((*blob_file)->BlobFileNumber(), *blob_file));
+  open_ttl_files_.insert(*blob_file);
   total_blob_size_ += BlobLogHeader::kSize;
   epoch_of_++;
 
-  return bfile;
+  return s;
 }
 
 class BlobDBImpl::BlobInserter : public WriteBatch::Handler {
@@ -562,8 +580,8 @@ class BlobDBImpl::BlobInserter : public WriteBatch::Handler {
       return Status::NotSupported(
           "Blob DB doesn't support non-default column family.");
     }
-    Status s = blob_db_impl_->PutBlobValue(options_, key, value,
-                                           kNoExpiration, &batch_);
+    Status s = blob_db_impl_->PutBlobValue(options_, key, value, kNoExpiration,
+                                           &batch_);
     return s;
   }
 
@@ -621,39 +639,6 @@ Status BlobDBImpl::Write(const WriteOptions& options, WriteBatch* updates) {
   return db_->Write(options, blob_inserter.batch());
 }
 
-Status BlobDBImpl::GetLiveFiles(std::vector<std::string>& ret,
-                                uint64_t* manifest_file_size,
-                                bool flush_memtable) {
-  // Hold a lock in the beginning to avoid updates to base DB during the call
-  ReadLock rl(&mutex_);
-  Status s = db_->GetLiveFiles(ret, manifest_file_size, flush_memtable);
-  if (!s.ok()) {
-    return s;
-  }
-  ret.reserve(ret.size() + blob_files_.size());
-  for (auto bfile_pair : blob_files_) {
-    auto blob_file = bfile_pair.second;
-    ret.emplace_back(blob_file->PathName());
-  }
-  return Status::OK();
-}
-
-void BlobDBImpl::GetLiveFilesMetaData(std::vector<LiveFileMetaData>* metadata) {
-  // Hold a lock in the beginning to avoid updates to base DB during the call
-  ReadLock rl(&mutex_);
-  db_->GetLiveFilesMetaData(metadata);
-  for (auto bfile_pair : blob_files_) {
-    auto blob_file = bfile_pair.second;
-    LiveFileMetaData filemetadata;
-    filemetadata.size = blob_file->GetFileSize();
-    filemetadata.name = blob_file->PathName();
-    auto cfh =
-        reinterpret_cast<ColumnFamilyHandleImpl*>(DefaultColumnFamily());
-    filemetadata.column_family_name = cfh->GetName();
-    metadata->emplace_back(filemetadata);
-  }
-}
-
 Status BlobDBImpl::Put(const WriteOptions& options, const Slice& key,
                        const Slice& value) {
   return PutUntil(options, key, value, kNoExpiration);
@@ -724,36 +709,41 @@ Status BlobDBImpl::PutBlobValue(const WriteOptions& /*options*/,
       return s;
     }
 
-    std::shared_ptr<BlobFile> bfile = (expiration != kNoExpiration)
-                                          ? SelectBlobFileTTL(expiration)
-                                          : SelectBlobFile();
-    assert(bfile != nullptr);
-    assert(bfile->compression() == bdb_options_.compression);
-
-    s = AppendBlob(bfile, headerbuf, key, value_compressed, expiration,
-                   &index_entry);
-    if (expiration == kNoExpiration) {
-      RecordTick(statistics_, BLOB_DB_WRITE_BLOB);
+    std::shared_ptr<BlobFile> blob_file;
+    if (expiration != kNoExpiration) {
+      s = SelectBlobFileTTL(expiration, &blob_file);
     } else {
-      RecordTick(statistics_, BLOB_DB_WRITE_BLOB_TTL);
+      s = SelectBlobFile(&blob_file);
+    }
+    if (s.ok()) {
+      assert(blob_file != nullptr);
+      assert(blob_file->compression() == bdb_options_.compression);
+      s = AppendBlob(blob_file, headerbuf, key, value_compressed, expiration,
+                     &index_entry);
     }
-
     if (s.ok()) {
       if (expiration != kNoExpiration) {
-        bfile->ExtendExpirationRange(expiration);
+        blob_file->ExtendExpirationRange(expiration);
       }
-      s = CloseBlobFileIfNeeded(bfile);
-      if (s.ok()) {
-        s = WriteBatchInternal::PutBlobIndex(batch, column_family_id, key,
-                                             index_entry);
+      s = CloseBlobFileIfNeeded(blob_file);
+    }
+    if (s.ok()) {
+      s = WriteBatchInternal::PutBlobIndex(batch, column_family_id, key,
+                                           index_entry);
+    }
+    if (s.ok()) {
+      if (expiration == kNoExpiration) {
+        RecordTick(statistics_, BLOB_DB_WRITE_BLOB);
+      } else {
+        RecordTick(statistics_, BLOB_DB_WRITE_BLOB_TTL);
       }
     } else {
       ROCKS_LOG_ERROR(db_options_.info_log,
                       "Failed to append blob to FILE: %s: KEY: %s VALSZ: %d"
                       " status: '%s' blob_file: '%s'",
-                      bfile->PathName().c_str(), key.ToString().c_str(),
+                      blob_file->PathName().c_str(), key.ToString().c_str(),
                       value.size(), s.ToString().c_str(),
-                      bfile->DumpState().c_str());
+                      blob_file->DumpState().c_str());
     }
   }
 
@@ -896,9 +886,10 @@ Status BlobDBImpl::AppendBlob(const std::shared_ptr<BlobFile>& bfile,
   uint64_t key_offset = 0;
   {
     WriteLock lockbfile_w(&bfile->mutex_);
-    std::shared_ptr<Writer> writer = CheckOrCreateWriterLocked(bfile);
-    if (!writer) {
-      return Status::IOError("Failed to create blob writer");
+    std::shared_ptr<Writer> writer;
+    s = CheckOrCreateWriterLocked(bfile, &writer);
+    if (!s.ok()) {
+      return s;
     }
 
     // write the blob to the blob log.
@@ -1031,22 +1022,25 @@ Status BlobDBImpl::GetBlobValue(const Slice& key, const Slice& index_entry,
   }
 
   // takes locks when called
-  std::shared_ptr<RandomAccessFileReader> reader =
-      GetOrOpenRandomAccessReader(bfile, env_, env_options_);
+  std::shared_ptr<RandomAccessFileReader> reader;
+  s = GetBlobFileReader(bfile, &reader);
+  if (!s.ok()) {
+    return s;
+  }
 
   assert(blob_index.offset() > key.size() + sizeof(uint32_t));
   uint64_t record_offset = blob_index.offset() - key.size() - sizeof(uint32_t);
   uint64_t record_size = sizeof(uint32_t) + key.size() + blob_index.size();
 
   // Allocate the buffer. This is safe in C++11
-  std::string buffer_str(record_size, static_cast<char>(0));
+  std::string buffer_str(static_cast<size_t>(record_size), static_cast<char>(0));
   char* buffer = &buffer_str[0];
 
   // A partial blob record contain checksum, key and value.
   Slice blob_record;
   {
     StopWatch read_sw(env_, statistics_, BLOB_DB_BLOB_FILE_READ_MICROS);
-    s = reader->Read(record_offset, record_size, &blob_record, buffer);
+    s = reader->Read(record_offset, static_cast<size_t>(record_size), &blob_record, buffer);
     RecordTick(statistics_, BLOB_DB_BLOB_FILE_BYTES_READ, blob_record.size());
   }
   if (!s.ok()) {
@@ -1072,7 +1066,7 @@ Status BlobDBImpl::GetBlobValue(const Slice& key, const Slice& index_entry,
   }
   Slice crc_slice(blob_record.data(), sizeof(uint32_t));
   Slice blob_value(blob_record.data() + sizeof(uint32_t) + key.size(),
-                   blob_index.size());
+                   static_cast<size_t>(blob_index.size()));
   uint32_t crc_exp;
   if (!GetFixed32(&crc_slice, &crc_exp)) {
     ROCKS_LOG_DEBUG(db_options_.info_log,
@@ -1144,9 +1138,10 @@ Status BlobDBImpl::GetImpl(const ReadOptions& read_options,
   ReadOptions ro(read_options);
   bool snapshot_created = SetSnapshotIfNeeded(&ro);
 
+  PinnableSlice index_entry;
   Status s;
   bool is_blob_index = false;
-  s = db_impl_->GetImpl(ro, column_family, key, value,
+  s = db_impl_->GetImpl(ro, column_family, key, &index_entry,
                         nullptr /*value_found*/, nullptr /*read_callback*/,
                         &is_blob_index);
   TEST_SYNC_POINT("BlobDBImpl::Get:AfterIndexEntryGet:1");
@@ -1154,27 +1149,30 @@ Status BlobDBImpl::GetImpl(const ReadOptions& read_options,
   if (expiration != nullptr) {
     *expiration = kNoExpiration;
   }
-  if (s.ok() && is_blob_index) {
-    std::string index_entry = value->ToString();
-    value->Reset();
-    s = GetBlobValue(key, index_entry, value, expiration);
+  RecordTick(statistics_, BLOB_DB_NUM_KEYS_READ);
+  if (s.ok()) {
+    if (is_blob_index) {
+      s = GetBlobValue(key, index_entry, value, expiration);
+    } else {
+      // The index entry is the value itself in this case.
+      value->PinSelf(index_entry);
+    }
+    RecordTick(statistics_, BLOB_DB_BYTES_READ, value->size());
   }
   if (snapshot_created) {
     db_->ReleaseSnapshot(ro.snapshot);
   }
-  RecordTick(statistics_, BLOB_DB_NUM_KEYS_READ);
-  RecordTick(statistics_, BLOB_DB_BYTES_READ, value->size());
   return s;
 }
 
 std::pair<bool, int64_t> BlobDBImpl::SanityCheck(bool aborted) {
-  if (aborted) return std::make_pair(false, -1);
+  if (aborted) {
+    return std::make_pair(false, -1);
+  }
 
   ROCKS_LOG_INFO(db_options_.info_log, "Starting Sanity Check");
-
   ROCKS_LOG_INFO(db_options_.info_log, "Number of files %" PRIu64,
                  blob_files_.size());
-
   ROCKS_LOG_INFO(db_options_.info_log, "Number of open files %" PRIu64,
                  open_ttl_files_.size());
 
@@ -1182,14 +1180,33 @@ std::pair<bool, int64_t> BlobDBImpl::SanityCheck(bool aborted) {
     assert(!bfile->Immutable());
   }
 
-  uint64_t epoch_now = EpochNow();
+  uint64_t now = EpochNow();
 
-  for (auto bfile_pair : blob_files_) {
-    auto bfile = bfile_pair.second;
-    ROCKS_LOG_INFO(
-        db_options_.info_log, "Blob File %s %" PRIu64 " %" PRIu64 " %" PRIu64,
-        bfile->PathName().c_str(), bfile->GetFileSize(), bfile->BlobCount(),
-        (bfile->expiration_range_.second - epoch_now));
+  for (auto blob_file_pair : blob_files_) {
+    auto blob_file = blob_file_pair.second;
+    char buf[1000];
+    int pos = snprintf(buf, sizeof(buf),
+                       "Blob file %" PRIu64 ", size %" PRIu64
+                       ", blob count %" PRIu64 ", immutable %d",
+                       blob_file->BlobFileNumber(), blob_file->GetFileSize(),
+                       blob_file->BlobCount(), blob_file->Immutable());
+    if (blob_file->HasTTL()) {
+      auto expiration_range = blob_file->GetExpirationRange();
+      pos += snprintf(buf + pos, sizeof(buf) - pos,
+                      ", expiration range (%" PRIu64 ", %" PRIu64 ")",
+                      expiration_range.first, expiration_range.second);
+      if (!blob_file->Obsolete()) {
+        pos += snprintf(buf + pos, sizeof(buf) - pos,
+                        ", expire in %" PRIu64 " seconds",
+                        expiration_range.second - now);
+      }
+    }
+    if (blob_file->Obsolete()) {
+      pos += snprintf(buf + pos, sizeof(buf) - pos, ", obsolete at %" PRIu64,
+                      blob_file->GetObsoleteSequence());
+    }
+    snprintf(buf + pos, sizeof(buf) - pos, ".");
+    ROCKS_LOG_INFO(db_options_.info_log, "%s", buf);
   }
 
   // reschedule
@@ -1279,7 +1296,14 @@ bool BlobDBImpl::VisibleToActiveSnapshot(
       oldest_snapshot = snapshots.oldest()->GetSequenceNumber();
     }
   }
-  return oldest_snapshot < obsolete_sequence;
+  bool visible = oldest_snapshot < obsolete_sequence;
+  if (visible) {
+    ROCKS_LOG_INFO(db_options_.info_log,
+                   "Obsolete blob file %" PRIu64 " (obsolete at %" PRIu64
+                   ") visible to oldest snapshot %" PRIu64 ".",
+                   bfile->BlobFileNumber(), obsolete_sequence, oldest_snapshot);
+  }
+  return visible;
 }
 
 std::pair<bool, int64_t> BlobDBImpl::EvictExpiredFiles(bool aborted) {
@@ -1455,8 +1479,7 @@ Status BlobDBImpl::GCFileAndUpdateLSM(const std::shared_ptr<BlobFile>& bfptr,
     return s;
   }
 
-  auto* cfh =
-      db_impl_->GetColumnFamilyHandleUnlocked(bfptr->column_family_id());
+  auto cfh = db_impl_->DefaultColumnFamily();
   auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh)->cfd();
   auto column_family_id = cfd->GetID();
   bool has_ttl = header.has_ttl;
@@ -1571,7 +1594,13 @@ Status BlobDBImpl::GCFileAndUpdateLSM(const std::shared_ptr<BlobFile>& bfptr,
       reason += bfptr->PathName();
       newfile = NewBlobFile(reason);
 
-      new_writer = CheckOrCreateWriterLocked(newfile);
+      s = CheckOrCreateWriterLocked(newfile, &new_writer);
+      if (!s.ok()) {
+        ROCKS_LOG_ERROR(db_options_.info_log,
+                        "Failed to open file %s for writer, error: %s",
+                        newfile->PathName().c_str(), s.ToString().c_str());
+        break;
+      }
       // Can't use header beyond this point
       newfile->header_ = std::move(header);
       newfile->header_valid_ = true;
@@ -1680,16 +1709,21 @@ Status BlobDBImpl::GCFileAndUpdateLSM(const std::shared_ptr<BlobFile>& bfptr,
 }
 
 std::pair<bool, int64_t> BlobDBImpl::DeleteObsoleteFiles(bool aborted) {
-  if (aborted) return std::make_pair(false, -1);
+  if (aborted) {
+    return std::make_pair(false, -1);
+  }
 
-  {
-    ReadLock rl(&mutex_);
-    if (obsolete_files_.empty()) return std::make_pair(true, -1);
+  MutexLock delete_file_lock(&delete_file_mutex_);
+  if (disable_file_deletions_ > 0) {
+    return std::make_pair(true, -1);
   }
 
   std::list<std::shared_ptr<BlobFile>> tobsolete;
   {
     WriteLock wl(&mutex_);
+    if (obsolete_files_.empty()) {
+      return std::make_pair(true, -1);
+    }
     tobsolete.swap(obsolete_files_);
   }
 
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_impl.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_impl.h
similarity index 88%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_impl.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_impl.h
index 0579a9ab42..8d5148def6 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_impl.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_impl.h
@@ -155,12 +155,6 @@ class BlobDBImpl : public BlobDB {
 
   virtual Status Close() override;
 
-  virtual Status GetLiveFiles(std::vector<std::string>&,
-                              uint64_t* manifest_file_size,
-                              bool flush_memtable = true) override;
-  virtual void GetLiveFilesMetaData(
-      std::vector<LiveFileMetaData>* ) override;
-
   using BlobDB::PutWithTTL;
   Status PutWithTTL(const WriteOptions& options, const Slice& key,
                     const Slice& value, uint64_t ttl) override;
@@ -175,6 +169,15 @@ class BlobDBImpl : public BlobDB {
              const DBOptions& db_options,
              const ColumnFamilyOptions& cf_options);
 
+  virtual Status DisableFileDeletions() override;
+
+  virtual Status EnableFileDeletions(bool force) override;
+
+  virtual Status GetLiveFiles(std::vector<std::string>&,
+                              uint64_t* manifest_file_size,
+                              bool flush_memtable = true) override;
+  virtual void GetLiveFilesMetaData(std::vector<LiveFileMetaData>*) override;
+
   ~BlobDBImpl();
 
   Status Open(std::vector<ColumnFamilyHandle*>* handles);
@@ -252,10 +255,11 @@ class BlobDBImpl : public BlobDB {
 
   // find an existing blob log file based on the expiration unix epoch
   // if such a file does not exist, return nullptr
-  std::shared_ptr<BlobFile> SelectBlobFileTTL(uint64_t expiration);
+  Status SelectBlobFileTTL(uint64_t expiration,
+                           std::shared_ptr<BlobFile>* blob_file);
 
   // find an existing blob log file to append the value to
-  std::shared_ptr<BlobFile> SelectBlobFile();
+  Status SelectBlobFile(std::shared_ptr<BlobFile>* blob_file);
 
   std::shared_ptr<BlobFile> FindBlobFileLocked(uint64_t expiration) const;
 
@@ -293,11 +297,8 @@ class BlobDBImpl : public BlobDB {
   // Open all blob files found in blob_dir.
   Status OpenAllBlobFiles();
 
-  // hold write mutex on file and call
-  // creates a Random Access reader for GET call
-  std::shared_ptr<RandomAccessFileReader> GetOrOpenRandomAccessReader(
-      const std::shared_ptr<BlobFile>& bfile, Env* env,
-      const EnvOptions& env_options);
+  Status GetBlobFileReader(const std::shared_ptr<BlobFile>& blob_file,
+                           std::shared_ptr<RandomAccessFileReader>* reader);
 
   // hold write mutex on file and call.
   // Close the above Random Access reader
@@ -309,8 +310,8 @@ class BlobDBImpl : public BlobDB {
 
   // returns a Writer object for the file. If writer is not
   // already present, creates one. Needs Write Mutex to be held
-  std::shared_ptr<Writer> CheckOrCreateWriterLocked(
-      const std::shared_ptr<BlobFile>& bfile);
+  Status CheckOrCreateWriterLocked(const std::shared_ptr<BlobFile>& blob_file,
+                                   std::shared_ptr<Writer>* writer);
 
   // Iterate through keys and values on Blob and write into
   // separate file the remaining blobs and delete/update pointers
@@ -347,7 +348,8 @@ class BlobDBImpl : public BlobDB {
   ColumnFamilyOptions cf_options_;
   EnvOptions env_options_;
 
-  // Raw pointer of statistic. db_options_ has a shared_ptr to hold ownership.
+  // Raw pointer of statistic. db_options_ has a std::shared_ptr to hold
+  // ownership.
   Statistics* statistics_;
 
   // by default this is "blob_dir" under dbname_
@@ -408,6 +410,26 @@ class BlobDBImpl : public BlobDB {
 
   std::list<std::shared_ptr<BlobFile>> obsolete_files_;
 
+  // DeleteObsoleteFiles, DiableFileDeletions and EnableFileDeletions block
+  // on the mutex to avoid contention.
+  //
+  // While DeleteObsoleteFiles hold both mutex_ and delete_file_mutex_, note
+  // the difference. mutex_ only needs to be held when access the
+  // data-structure, and delete_file_mutex_ needs to be held the whole time
+  // during DeleteObsoleteFiles to avoid being run simultaneously with
+  // DisableFileDeletions.
+  //
+  // If both of mutex_ and delete_file_mutex_ needs to be held, it is adviced
+  // to hold delete_file_mutex_ first to avoid deadlock.
+  mutable port::Mutex delete_file_mutex_;
+
+  // Each call of DisableFileDeletions will increase disable_file_deletion_
+  // by 1. EnableFileDeletions will either decrease the count by 1 or reset
+  // it to zeor, depending on the force flag.
+  //
+  // REQUIRES: access with delete_file_mutex_ held.
+  int disable_file_deletions_ = 0;
+
   uint32_t debug_level_;
 };
 
diff --git a/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_impl_filesnapshot.cc b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_impl_filesnapshot.cc
new file mode 100644
index 0000000000..8effe88c0a
--- /dev/null
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_impl_filesnapshot.cc
@@ -0,0 +1,108 @@
+//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under both the GPLv2 (found in the
+//  COPYING file in the root directory) and Apache 2.0 License
+//  (found in the LICENSE.Apache file in the root directory).
+
+#ifndef ROCKSDB_LITE
+
+#include "utilities/blob_db/blob_db_impl.h"
+
+#include "util/filename.h"
+#include "util/logging.h"
+#include "util/mutexlock.h"
+
+// BlobDBImpl methods to get snapshot of files, e.g. for replication.
+
+namespace rocksdb {
+namespace blob_db {
+
+Status BlobDBImpl::DisableFileDeletions() {
+  // Disable base DB file deletions.
+  Status s = db_impl_->DisableFileDeletions();
+  if (!s.ok()) {
+    return s;
+  }
+
+  int count = 0;
+  {
+    // Hold delete_file_mutex_ to make sure no DeleteObsoleteFiles job
+    // is running.
+    MutexLock l(&delete_file_mutex_);
+    count = ++disable_file_deletions_;
+  }
+
+  ROCKS_LOG_INFO(db_options_.info_log,
+                 "Disalbed blob file deletions. count: %d", count);
+  return Status::OK();
+}
+
+Status BlobDBImpl::EnableFileDeletions(bool force) {
+  // Enable base DB file deletions.
+  Status s = db_impl_->EnableFileDeletions(force);
+  if (!s.ok()) {
+    return s;
+  }
+
+  int count = 0;
+  {
+    MutexLock l(&delete_file_mutex_);
+    if (force) {
+      disable_file_deletions_ = 0;
+    } else if (disable_file_deletions_ > 0) {
+      count = --disable_file_deletions_;
+    }
+    assert(count >= 0);
+  }
+
+  ROCKS_LOG_INFO(db_options_.info_log, "Enabled blob file deletions. count: %d",
+                 count);
+  // Consider trigger DeleteobsoleteFiles once after re-enabled, if we are to
+  // make DeleteobsoleteFiles re-run interval configuration.
+  return Status::OK();
+}
+
+Status BlobDBImpl::GetLiveFiles(std::vector<std::string>& ret,
+                                uint64_t* manifest_file_size,
+                                bool flush_memtable) {
+  if (!bdb_options_.path_relative) {
+    return Status::NotSupported(
+        "Not able to get relative blob file path from absolute blob_dir.");
+  }
+  // Hold a lock in the beginning to avoid updates to base DB during the call
+  ReadLock rl(&mutex_);
+  Status s = db_->GetLiveFiles(ret, manifest_file_size, flush_memtable);
+  if (!s.ok()) {
+    return s;
+  }
+  ret.reserve(ret.size() + blob_files_.size());
+  for (auto bfile_pair : blob_files_) {
+    auto blob_file = bfile_pair.second;
+    // Path should be relative to db_name, but begin with slash.
+    ret.emplace_back(
+        BlobFileName("", bdb_options_.blob_dir, blob_file->BlobFileNumber()));
+  }
+  return Status::OK();
+}
+
+void BlobDBImpl::GetLiveFilesMetaData(std::vector<LiveFileMetaData>* metadata) {
+  // Path should be relative to db_name.
+  assert(bdb_options_.path_relative);
+  // Hold a lock in the beginning to avoid updates to base DB during the call
+  ReadLock rl(&mutex_);
+  db_->GetLiveFilesMetaData(metadata);
+  for (auto bfile_pair : blob_files_) {
+    auto blob_file = bfile_pair.second;
+    LiveFileMetaData filemetadata;
+    filemetadata.size = static_cast<size_t>(blob_file->GetFileSize());
+    // Path should be relative to db_name, but begin with slash.
+    filemetadata.name =
+        BlobFileName("", bdb_options_.blob_dir, blob_file->BlobFileNumber());
+    auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(DefaultColumnFamily());
+    filemetadata.column_family_name = cfh->GetName();
+    metadata->emplace_back(filemetadata);
+  }
+}
+
+}  // namespace blob_db
+}  // namespace rocksdb
+#endif  // !ROCKSDB_LITE
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_iterator.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_iterator.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_iterator.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_iterator.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_listener.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_listener.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_listener.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_listener.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_test.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_test.cc
index 99a2cb1acc..1c1867e4e2 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_db_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_db_test.cc
@@ -16,6 +16,7 @@
 #include "port/port.h"
 #include "rocksdb/utilities/debug.h"
 #include "util/cast_util.h"
+#include "util/fault_injection_test_env.h"
 #include "util/random.h"
 #include "util/string_util.h"
 #include "util/sync_point.h"
@@ -40,6 +41,7 @@ class BlobDBTest : public testing::Test {
   BlobDBTest()
       : dbname_(test::PerThreadDBPath("blob_db_test")),
         mock_env_(new MockTimeEnv(Env::Default())),
+        fault_injection_env_(new FaultInjectionTestEnv(Env::Default())),
         blob_db_(nullptr) {
     Status s = DestroyBlobDB(dbname_, Options(), BlobDBOptions());
     assert(s.ok());
@@ -236,6 +238,7 @@ class BlobDBTest : public testing::Test {
 
   const std::string dbname_;
   std::unique_ptr<MockTimeEnv> mock_env_;
+  std::unique_ptr<FaultInjectionTestEnv> fault_injection_env_;
   BlobDB *blob_db_;
 };  // class BlobDBTest
 
@@ -354,6 +357,36 @@ TEST_F(BlobDBTest, GetExpiration) {
   ASSERT_EQ(300 /* = 100 + 200 */, expiration);
 }
 
+TEST_F(BlobDBTest, GetIOError) {
+  Options options;
+  options.env = fault_injection_env_.get();
+  BlobDBOptions bdb_options;
+  bdb_options.min_blob_size = 0;  // Make sure value write to blob file
+  bdb_options.disable_background_tasks = true;
+  Open(bdb_options, options);
+  ColumnFamilyHandle *column_family = blob_db_->DefaultColumnFamily();
+  PinnableSlice value;
+  ASSERT_OK(Put("foo", "bar"));
+  fault_injection_env_->SetFilesystemActive(false, Status::IOError());
+  Status s = blob_db_->Get(ReadOptions(), column_family, "foo", &value);
+  ASSERT_TRUE(s.IsIOError());
+  // Reactivate file system to allow test to close DB.
+  fault_injection_env_->SetFilesystemActive(true);
+}
+
+TEST_F(BlobDBTest, PutIOError) {
+  Options options;
+  options.env = fault_injection_env_.get();
+  BlobDBOptions bdb_options;
+  bdb_options.min_blob_size = 0;  // Make sure value write to blob file
+  bdb_options.disable_background_tasks = true;
+  Open(bdb_options, options);
+  fault_injection_env_->SetFilesystemActive(false, Status::IOError());
+  ASSERT_TRUE(Put("foo", "v1").IsIOError());
+  fault_injection_env_->SetFilesystemActive(true, Status::IOError());
+  ASSERT_OK(Put("bar", "v1"));
+}
+
 TEST_F(BlobDBTest, WriteBatch) {
   Random rnd(301);
   BlobDBOptions bdb_options;
@@ -461,7 +494,6 @@ TEST_F(BlobDBTest, DecompressAfterReopen) {
   Reopen(bdb_options);
   VerifyDB(data);
 }
-
 #endif
 
 TEST_F(BlobDBTest, MultipleWriters) {
@@ -834,6 +866,8 @@ TEST_F(BlobDBTest, ColumnFamilyNotSupported) {
 TEST_F(BlobDBTest, GetLiveFilesMetaData) {
   Random rnd(301);
   BlobDBOptions bdb_options;
+  bdb_options.blob_dir = "blob_dir";
+  bdb_options.path_relative = true;
   bdb_options.min_blob_size = 0;
   bdb_options.disable_background_tasks = true;
   Open(bdb_options);
@@ -841,16 +875,16 @@ TEST_F(BlobDBTest, GetLiveFilesMetaData) {
   for (size_t i = 0; i < 100; i++) {
     PutRandom("key" + ToString(i), &rnd, &data);
   }
-  auto *bdb_impl = static_cast<BlobDBImpl *>(blob_db_);
   std::vector<LiveFileMetaData> metadata;
-  bdb_impl->GetLiveFilesMetaData(&metadata);
+  blob_db_->GetLiveFilesMetaData(&metadata);
   ASSERT_EQ(1U, metadata.size());
-  std::string filename = dbname_ + "/blob_dir/000001.blob";
+  // Path should be relative to db_name, but begin with slash.
+  std::string filename = "/blob_dir/000001.blob";
   ASSERT_EQ(filename, metadata[0].name);
   ASSERT_EQ("default", metadata[0].column_family_name);
   std::vector<std::string> livefile;
   uint64_t mfs;
-  bdb_impl->GetLiveFiles(livefile, &mfs, false);
+  ASSERT_OK(blob_db_->GetLiveFiles(livefile, &mfs, false));
   ASSERT_EQ(4U, livefile.size());
   ASSERT_EQ(filename, livefile[3]);
   VerifyDB(data);
@@ -1413,6 +1447,52 @@ TEST_F(BlobDBTest, EvictExpiredFile) {
   blob_db_impl()->TEST_DeleteObsoleteFiles();
   ASSERT_EQ(0, blob_db_impl()->TEST_GetBlobFiles().size());
   ASSERT_EQ(0, blob_db_impl()->TEST_GetObsoleteFiles().size());
+  // Make sure we don't return garbage value after blob file being evicted,
+  // but the blob index still exists in the LSM tree.
+  std::string val = "";
+  ASSERT_TRUE(blob_db_->Get(ReadOptions(), "foo", &val).IsNotFound());
+  ASSERT_EQ("", val);
+}
+
+TEST_F(BlobDBTest, DisableFileDeletions) {
+  BlobDBOptions bdb_options;
+  bdb_options.disable_background_tasks = true;
+  Open(bdb_options);
+  std::map<std::string, std::string> data;
+  for (bool force : {true, false}) {
+    ASSERT_OK(Put("foo", "v", &data));
+    auto blob_files = blob_db_impl()->TEST_GetBlobFiles();
+    ASSERT_EQ(1, blob_files.size());
+    auto blob_file = blob_files[0];
+    ASSERT_OK(blob_db_impl()->TEST_CloseBlobFile(blob_file));
+    blob_db_impl()->TEST_ObsoleteBlobFile(blob_file);
+    ASSERT_EQ(1, blob_db_impl()->TEST_GetBlobFiles().size());
+    ASSERT_EQ(1, blob_db_impl()->TEST_GetObsoleteFiles().size());
+    // Call DisableFileDeletions twice.
+    ASSERT_OK(blob_db_->DisableFileDeletions());
+    ASSERT_OK(blob_db_->DisableFileDeletions());
+    // File deletions should be disabled.
+    blob_db_impl()->TEST_DeleteObsoleteFiles();
+    ASSERT_EQ(1, blob_db_impl()->TEST_GetBlobFiles().size());
+    ASSERT_EQ(1, blob_db_impl()->TEST_GetObsoleteFiles().size());
+    VerifyDB(data);
+    // Enable file deletions once. If force=true, file deletion is enabled.
+    // Otherwise it needs to enable it for a second time.
+    ASSERT_OK(blob_db_->EnableFileDeletions(force));
+    blob_db_impl()->TEST_DeleteObsoleteFiles();
+    if (!force) {
+      ASSERT_EQ(1, blob_db_impl()->TEST_GetBlobFiles().size());
+      ASSERT_EQ(1, blob_db_impl()->TEST_GetObsoleteFiles().size());
+      VerifyDB(data);
+      // Call EnableFileDeletions a second time.
+      ASSERT_OK(blob_db_->EnableFileDeletions(false));
+      blob_db_impl()->TEST_DeleteObsoleteFiles();
+    }
+    // Regardless of value of `force`, file should be deleted by now.
+    ASSERT_EQ(0, blob_db_impl()->TEST_GetBlobFiles().size());
+    ASSERT_EQ(0, blob_db_impl()->TEST_GetObsoleteFiles().size());
+    VerifyDB({});
+  }
 }
 
 }  //  namespace blob_db
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_dump_tool.cc b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_dump_tool.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_dump_tool.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_dump_tool.cc
index e75ec18598..7ce0697e3b 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_dump_tool.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_dump_tool.cc
@@ -199,7 +199,7 @@ Status BlobDumpTool::DumpRecord(DisplayType show_key, DisplayType show_blob,
     fprintf(stdout, "  expiration : %" PRIu64 "\n", record.expiration);
   }
   *offset += BlobLogRecord::kHeaderSize;
-  s = Read(*offset, key_size + value_size, &slice);
+  s = Read(*offset, static_cast<size_t>(key_size + value_size), &slice);
   if (!s.ok()) {
     return s;
   }
@@ -210,8 +210,8 @@ Status BlobDumpTool::DumpRecord(DisplayType show_key, DisplayType show_blob,
     BlockContents contents;
     UncompressionContext uncompression_ctx(compression);
     s = UncompressBlockContentsForCompressionType(
-        uncompression_ctx, slice.data() + key_size, value_size, &contents,
-        2 /*compress_format_version*/, ImmutableCFOptions(Options()));
+        uncompression_ctx, slice.data() + key_size, static_cast<size_t>(value_size),
+        &contents, 2 /*compress_format_version*/, ImmutableCFOptions(Options()));
     if (!s.ok()) {
       return s;
     }
@@ -219,10 +219,10 @@ Status BlobDumpTool::DumpRecord(DisplayType show_key, DisplayType show_blob,
   }
   if (show_key != DisplayType::kNone) {
     fprintf(stdout, "  key        : ");
-    DumpSlice(Slice(slice.data(), key_size), show_key);
+    DumpSlice(Slice(slice.data(), static_cast<size_t>(key_size)), show_key);
     if (show_blob != DisplayType::kNone) {
       fprintf(stdout, "  blob       : ");
-      DumpSlice(Slice(slice.data() + key_size, value_size), show_blob);
+      DumpSlice(Slice(slice.data() + static_cast<size_t>(key_size), static_cast<size_t>(value_size)), show_blob);
     }
     if (show_uncompressed_blob != DisplayType::kNone) {
       fprintf(stdout, "  raw blob   : ");
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_dump_tool.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_dump_tool.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_dump_tool.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_dump_tool.h
index e91feffa79..ff4672fd3f 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_dump_tool.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_dump_tool.h
@@ -33,7 +33,7 @@ class BlobDumpTool {
 
  private:
   std::unique_ptr<RandomAccessFileReader> reader_;
-  std::unique_ptr<char> buffer_;
+  std::unique_ptr<char[]> buffer_;
   size_t buffer_size_;
 
   Status Read(uint64_t offset, size_t size, Slice* result);
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_file.cc b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_file.cc
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_file.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_file.cc
index c34ad9098b..6e70bdcb0a 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_file.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_file.cc
@@ -191,36 +191,48 @@ void BlobFile::CloseRandomAccessLocked() {
   last_access_ = -1;
 }
 
-std::shared_ptr<RandomAccessFileReader> BlobFile::GetOrOpenRandomAccessReader(
-    Env* env, const EnvOptions& env_options, bool* fresh_open) {
+Status BlobFile::GetReader(Env* env, const EnvOptions& env_options,
+                           std::shared_ptr<RandomAccessFileReader>* reader,
+                           bool* fresh_open) {
+  assert(reader != nullptr);
+  assert(fresh_open != nullptr);
   *fresh_open = false;
   int64_t current_time = 0;
   env->GetCurrentTime(&current_time);
   last_access_.store(current_time);
+  Status s;
 
   {
     ReadLock lockbfile_r(&mutex_);
-    if (ra_file_reader_) return ra_file_reader_;
+    if (ra_file_reader_) {
+      *reader = ra_file_reader_;
+      return s;
+    }
   }
 
   WriteLock lockbfile_w(&mutex_);
-  if (ra_file_reader_) return ra_file_reader_;
+  // Double check.
+  if (ra_file_reader_) {
+    *reader = ra_file_reader_;
+    return s;
+  }
 
   std::unique_ptr<RandomAccessFile> rfile;
-  Status s = env->NewRandomAccessFile(PathName(), &rfile, env_options);
+  s = env->NewRandomAccessFile(PathName(), &rfile, env_options);
   if (!s.ok()) {
     ROCKS_LOG_ERROR(info_log_,
                     "Failed to open blob file for random-read: %s status: '%s'"
                     " exists: '%s'",
                     PathName().c_str(), s.ToString().c_str(),
                     env->FileExists(PathName()).ToString().c_str());
-    return nullptr;
+    return s;
   }
 
   ra_file_reader_ = std::make_shared<RandomAccessFileReader>(std::move(rfile),
                                                              PathName());
+  *reader = ra_file_reader_;
   *fresh_open = true;
-  return ra_file_reader_;
+  return s;
 }
 
 Status BlobFile::ReadMetadata(Env* env, const EnvOptions& env_options) {
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_file.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_file.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_file.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_file.h
index 288523e773..668a037228 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_file.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_file.h
@@ -181,6 +181,10 @@ class BlobFile {
   // footer_valid_ to false and return Status::OK.
   Status ReadMetadata(Env* env, const EnvOptions& env_options);
 
+  Status GetReader(Env* env, const EnvOptions& env_options,
+                   std::shared_ptr<RandomAccessFileReader>* reader,
+                   bool* fresh_open);
+
  private:
   std::shared_ptr<Reader> OpenRandomAccessReader(
       Env* env, const DBOptions& db_options,
@@ -190,9 +194,6 @@ class BlobFile {
 
   Status WriteFooterAndCloseLocked();
 
-  std::shared_ptr<RandomAccessFileReader> GetOrOpenRandomAccessReader(
-      Env* env, const EnvOptions& env_options, bool* fresh_open);
-
   void CloseRandomAccessLocked();
 
   // this is used, when you are reading only the footer of a
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_index.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_index.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_index.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_index.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_format.cc b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_format.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_format.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_format.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_format.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_format.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_format.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_format.h
index 3e1b686aa1..fcc042f06d 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_format.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_format.h
@@ -10,7 +10,9 @@
 #ifndef ROCKSDB_LITE
 
 #include <limits>
+#include <memory>
 #include <utility>
+
 #include "rocksdb/options.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/status.h"
@@ -106,8 +108,8 @@ struct BlobLogRecord {
   uint32_t blob_crc = 0;
   Slice key;
   Slice value;
-  std::string key_buf;
-  std::string value_buf;
+  std::unique_ptr<char[]> key_buf;
+  std::unique_ptr<char[]> value_buf;
 
   uint64_t record_size() const { return kHeaderSize + key_size + value_size; }
 
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_reader.cc b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_reader.cc
similarity index 75%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_reader.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_reader.cc
index c2ba214571..0f098f2d45 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_reader.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_reader.cc
@@ -24,10 +24,9 @@ Reader::Reader(unique_ptr<RandomAccessFileReader>&& file_reader, Env* env,
       buffer_(),
       next_byte_(0) {}
 
-Status Reader::ReadSlice(uint64_t size, Slice* slice, std::string* buf) {
+Status Reader::ReadSlice(uint64_t size, Slice* slice, char* buf) {
   StopWatch read_sw(env_, statistics_, BLOB_DB_BLOB_FILE_READ_MICROS);
-  buf->reserve(size);
-  Status s = file_->Read(next_byte_, size, slice, &(*buf)[0]);
+  Status s = file_->Read(next_byte_, static_cast<size_t>(size), slice, buf);
   next_byte_ += size;
   if (!s.ok()) {
     return s;
@@ -42,7 +41,7 @@ Status Reader::ReadSlice(uint64_t size, Slice* slice, std::string* buf) {
 Status Reader::ReadHeader(BlobLogHeader* header) {
   assert(file_.get() != nullptr);
   assert(next_byte_ == 0);
-  Status s = ReadSlice(BlobLogHeader::kSize, &buffer_, &backing_store_);
+  Status s = ReadSlice(BlobLogHeader::kSize, &buffer_, header_buf_);
   if (!s.ok()) {
     return s;
   }
@@ -56,7 +55,7 @@ Status Reader::ReadHeader(BlobLogHeader* header) {
 
 Status Reader::ReadRecord(BlobLogRecord* record, ReadLevel level,
                           uint64_t* blob_offset) {
-  Status s = ReadSlice(BlobLogRecord::kHeaderSize, &buffer_, &backing_store_);
+  Status s = ReadSlice(BlobLogRecord::kHeaderSize, &buffer_, header_buf_);
   if (!s.ok()) {
     return s;
   }
@@ -80,14 +79,18 @@ Status Reader::ReadRecord(BlobLogRecord* record, ReadLevel level,
       break;
 
     case kReadHeaderKey:
-      s = ReadSlice(record->key_size, &record->key, &record->key_buf);
+      record->key_buf.reset(new char[record->key_size]);
+      s = ReadSlice(record->key_size, &record->key, record->key_buf.get());
       next_byte_ += record->value_size;
       break;
 
     case kReadHeaderKeyBlob:
-      s = ReadSlice(record->key_size, &record->key, &record->key_buf);
+      record->key_buf.reset(new char[record->key_size]);
+      s = ReadSlice(record->key_size, &record->key, record->key_buf.get());
       if (s.ok()) {
-        s = ReadSlice(record->value_size, &record->value, &record->value_buf);
+        record->value_buf.reset(new char[record->value_size]);
+        s = ReadSlice(record->value_size, &record->value,
+                      record->value_buf.get());
       }
       if (s.ok()) {
         s = record->CheckBlobCRC();
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_reader.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_reader.h
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_reader.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_reader.h
index 4b780decd5..45e2e95514 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_reader.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_reader.h
@@ -60,19 +60,19 @@ class Reader {
   Status ReadRecord(BlobLogRecord* record, ReadLevel level = kReadHeader,
                     uint64_t* blob_offset = nullptr);
 
-  Status ReadSlice(uint64_t size, Slice* slice, std::string* buf);
-
   void ResetNextByte() { next_byte_ = 0; }
 
   uint64_t GetNextByte() const { return next_byte_; }
 
  private:
+  Status ReadSlice(uint64_t size, Slice* slice, char* buf);
+
   const std::unique_ptr<RandomAccessFileReader> file_;
   Env* env_;
   Statistics* statistics_;
 
-  std::string backing_store_;
   Slice buffer_;
+  char header_buf_[BlobLogRecord::kHeaderSize];
 
   // which byte to read next. For asserting proper usage
   uint64_t next_byte_;
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_writer.cc b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_writer.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_writer.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_writer.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_writer.h b/3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_writer.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/blob_db/blob_log_writer.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/blob_db/blob_log_writer.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_compaction_filter.cc b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_compaction_filter.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_compaction_filter.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_compaction_filter.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_compaction_filter.h b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_compaction_filter.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_compaction_filter.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_compaction_filter.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_format_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_format_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_format_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_format_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_functional_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_functional_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_functional_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_functional_test.cc
index 3e612b3ad6..653e6da72b 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_functional_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_functional_test.cc
@@ -101,7 +101,7 @@ public:
 
  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
      const CompactionFilter::Context& /*context*/) override {
-   return unique_ptr<CompactionFilter>(new CassandraCompactionFilter(
+   return std::unique_ptr<CompactionFilter>(new CassandraCompactionFilter(
        purge_ttl_on_expiration_, gc_grace_period_in_seconds_));
   }
 
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_row_merge_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_row_merge_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_row_merge_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_row_merge_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_serialize_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_serialize_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/cassandra_serialize_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/cassandra_serialize_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/format.cc b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/format.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/format.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/format.cc
index 4a22658de1..42cd7206b6 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/format.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/format.cc
@@ -266,7 +266,7 @@ RowValue RowValue::ConvertExpiredColumnsToTombstones(bool* changed) const {
         std::static_pointer_cast<ExpiringColumn>(column);
 
       if(expiring_column->Expired()) {
-        shared_ptr<Tombstone> tombstone = expiring_column->ToTombstone();
+        std::shared_ptr<Tombstone> tombstone = expiring_column->ToTombstone();
         new_columns.push_back(tombstone);
         *changed = true;
         continue;
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/format.h b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/format.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/format.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/format.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/merge_operator.cc b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/merge_operator.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/merge_operator.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/merge_operator.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/merge_operator.h b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/merge_operator.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/merge_operator.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/merge_operator.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/serialize.h b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/serialize.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/serialize.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/serialize.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/test_utils.cc b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/test_utils.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/test_utils.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/test_utils.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/cassandra/test_utils.h b/3rdParty/rocksdb/v5.18.X/utilities/cassandra/test_utils.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/cassandra/test_utils.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/cassandra/test_utils.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/checkpoint/checkpoint_impl.cc b/3rdParty/rocksdb/v5.18.X/utilities/checkpoint/checkpoint_impl.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/checkpoint/checkpoint_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/checkpoint/checkpoint_impl.cc
index fc8efe8836..9863ac1d56 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/checkpoint/checkpoint_impl.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/checkpoint/checkpoint_impl.cc
@@ -120,7 +120,8 @@ Status CheckpointImpl::CreateCheckpoint(const std::string& checkpoint_dir,
         } /* copy_file_cb */,
         [&](const std::string& fname, const std::string& contents, FileType) {
           ROCKS_LOG_INFO(db_options.info_log, "Creating %s", fname.c_str());
-          return CreateFile(db_->GetEnv(), full_private_path + fname, contents);
+          return CreateFile(db_->GetEnv(), full_private_path + fname, contents,
+                            db_options.use_fsync);
         } /* create_file_cb */,
         &sequence_number, log_size_for_flush);
     // we copied all the files, enable file deletions
@@ -132,7 +133,7 @@ Status CheckpointImpl::CreateCheckpoint(const std::string& checkpoint_dir,
     s = db_->GetEnv()->RenameFile(full_private_path, checkpoint_dir);
   }
   if (s.ok()) {
-    unique_ptr<Directory> checkpoint_directory;
+    std::unique_ptr<Directory> checkpoint_directory;
     db_->GetEnv()->NewDirectory(checkpoint_dir, &checkpoint_directory);
     if (checkpoint_directory != nullptr) {
       s = checkpoint_directory->Fsync();
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/checkpoint/checkpoint_impl.h b/3rdParty/rocksdb/v5.18.X/utilities/checkpoint/checkpoint_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/checkpoint/checkpoint_impl.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/checkpoint/checkpoint_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/checkpoint/checkpoint_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/checkpoint/checkpoint_test.cc
similarity index 95%
rename from 3rdParty/rocksdb/v5.16.X/utilities/checkpoint/checkpoint_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/checkpoint/checkpoint_test.cc
index b47f240c33..62c78faa8b 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/checkpoint/checkpoint_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/checkpoint/checkpoint_test.cc
@@ -17,12 +17,13 @@
 #include <thread>
 #include <utility>
 #include "db/db_impl.h"
-#include "port/stack_trace.h"
 #include "port/port.h"
+#include "port/stack_trace.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/utilities/checkpoint.h"
 #include "rocksdb/utilities/transaction_db.h"
+#include "util/fault_injection_test_env.h"
 #include "util/sync_point.h"
 #include "util/testharness.h"
 
@@ -585,6 +586,32 @@ TEST_F(CheckpointTest, CheckpointWithParallelWrites) {
   thread.join();
 }
 
+TEST_F(CheckpointTest, CheckpointWithUnsyncedDataDropped) {
+  Options options = CurrentOptions();
+  std::unique_ptr<FaultInjectionTestEnv> env(new FaultInjectionTestEnv(env_));
+  options.env = env.get();
+  Reopen(options);
+  ASSERT_OK(Put("key1", "val1"));
+  Checkpoint* checkpoint;
+  ASSERT_OK(Checkpoint::Create(db_, &checkpoint));
+  ASSERT_OK(checkpoint->CreateCheckpoint(snapshot_name_));
+  delete checkpoint;
+  env->DropUnsyncedFileData();
+
+  // make sure it's openable even though whatever data that wasn't synced got
+  // dropped.
+  options.env = env_;
+  DB* snapshot_db;
+  ASSERT_OK(DB::Open(options, snapshot_name_, &snapshot_db));
+  ReadOptions read_opts;
+  std::string get_result;
+  ASSERT_OK(snapshot_db->Get(read_opts, "key1", &get_result));
+  ASSERT_EQ("val1", get_result);
+  delete snapshot_db;
+  delete db_;
+  db_ = nullptr;
+}
+
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/col_buf_decoder.cc b/3rdParty/rocksdb/v5.18.X/utilities/col_buf_decoder.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/utilities/col_buf_decoder.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/col_buf_decoder.cc
index 3fb31794f7..8f9fa74abd 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/col_buf_decoder.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/col_buf_decoder.cc
@@ -147,7 +147,7 @@ size_t FixedLengthColBufDecoder::Decode(const char* src, char** dest) {
              col_compression_type_ == kColDict) {
     uint64_t dict_val = read_val;
     assert(dict_val < dict_vec_.size());
-    write_val = dict_vec_[dict_val];
+    write_val = dict_vec_[static_cast<size_t>(dict_val)];
   }
 
   // dest->append(reinterpret_cast<char*>(&write_val), size_);
@@ -222,7 +222,7 @@ size_t VariableChunkColBufDecoder::Decode(const char* src, char** dest) {
       uint64_t dict_val;
       ReadVarint64(&src, &dict_val);
       assert(dict_val < dict_vec_.size());
-      chunk_buf = dict_vec_[dict_val];
+      chunk_buf = dict_vec_[static_cast<size_t>(dict_val)];
     } else {
       memcpy(&chunk_buf, src, chunk_size);
       src += chunk_size;
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/col_buf_decoder.h b/3rdParty/rocksdb/v5.18.X/utilities/col_buf_decoder.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/col_buf_decoder.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/col_buf_decoder.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/col_buf_encoder.cc b/3rdParty/rocksdb/v5.18.X/utilities/col_buf_encoder.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/col_buf_encoder.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/col_buf_encoder.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/col_buf_encoder.h b/3rdParty/rocksdb/v5.18.X/utilities/col_buf_encoder.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/col_buf_encoder.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/col_buf_encoder.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/column_aware_encoding_exp.cc b/3rdParty/rocksdb/v5.18.X/utilities/column_aware_encoding_exp.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/utilities/column_aware_encoding_exp.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/column_aware_encoding_exp.cc
index 988a59b3c7..c251c985ec 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/column_aware_encoding_exp.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/column_aware_encoding_exp.cc
@@ -88,7 +88,7 @@ class ColumnAwareEncodingExp {
     EnvOptions env_options;
     if (CompressionTypeSupported(compression_type)) {
       fprintf(stdout, "[%s]\n", FLAGS_compression_type.c_str());
-      unique_ptr<WritableFile> encoded_out_file;
+      std::unique_ptr<WritableFile> encoded_out_file;
 
       std::unique_ptr<Env> env(NewMemEnv(Env::Default()));
       if (!FLAGS_encoded_file.empty()) {
@@ -116,7 +116,7 @@ class ColumnAwareEncodingExp {
       uint64_t encode_time = sw.ElapsedNanosSafe(false /* reset */);
       fprintf(stdout, "Encode time: %" PRIu64 "\n", encode_time);
       if (decode) {
-        unique_ptr<WritableFile> decoded_out_file;
+        std::unique_ptr<WritableFile> decoded_out_file;
         if (!FLAGS_decoded_file.empty()) {
           env->NewWritableFile(FLAGS_decoded_file, &decoded_out_file,
                                env_options);
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/column_aware_encoding_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/column_aware_encoding_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/column_aware_encoding_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/column_aware_encoding_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/column_aware_encoding_util.cc b/3rdParty/rocksdb/v5.18.X/utilities/column_aware_encoding_util.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/utilities/column_aware_encoding_util.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/column_aware_encoding_util.cc
index 45dedca08f..222ee46803 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/column_aware_encoding_util.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/column_aware_encoding_util.cc
@@ -100,7 +100,7 @@ void ColumnAwareEncodingReader::DecodeBlocks(
 
     size_t num_kv_pairs;
     const char* header_content_ptr = content_ptr;
-    num_kv_pairs = DecodeFixed64(header_content_ptr);
+    num_kv_pairs = static_cast<size_t>(DecodeFixed64(header_content_ptr));
 
     header_content_ptr += sizeof(size_t);
     size_t num_key_columns = key_col_bufs.size();
@@ -118,7 +118,7 @@ void ColumnAwareEncodingReader::DecodeBlocks(
       key_content_ptr[i] = col_content_ptr;
       key_content_ptr[i] += key_col_bufs[i]->Init(key_content_ptr[i]);
       size_t offset;
-      offset = DecodeFixed64(header_content_ptr);
+      offset = static_cast<size_t>(DecodeFixed64(header_content_ptr));
       header_content_ptr += sizeof(size_t);
       col_content_ptr += offset;
     }
@@ -126,7 +126,7 @@ void ColumnAwareEncodingReader::DecodeBlocks(
       value_content_ptr[i] = col_content_ptr;
       value_content_ptr[i] += value_col_bufs[i]->Init(value_content_ptr[i]);
       size_t offset;
-      offset = DecodeFixed64(header_content_ptr);
+      offset = static_cast<size_t>(DecodeFixed64(header_content_ptr));
       header_content_ptr += sizeof(size_t);
       col_content_ptr += offset;
     }
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/column_aware_encoding_util.h b/3rdParty/rocksdb/v5.18.X/utilities/column_aware_encoding_util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/column_aware_encoding_util.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/column_aware_encoding_util.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc b/3rdParty/rocksdb/v5.18.X/utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/compaction_filters/remove_emptyvalue_compactionfilter.h b/3rdParty/rocksdb/v5.18.X/utilities/compaction_filters/remove_emptyvalue_compactionfilter.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/compaction_filters/remove_emptyvalue_compactionfilter.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/compaction_filters/remove_emptyvalue_compactionfilter.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/convenience/info_log_finder.cc b/3rdParty/rocksdb/v5.18.X/utilities/convenience/info_log_finder.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/convenience/info_log_finder.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/convenience/info_log_finder.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/date_tiered/date_tiered_db_impl.cc b/3rdParty/rocksdb/v5.18.X/utilities/date_tiered/date_tiered_db_impl.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/date_tiered/date_tiered_db_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/date_tiered/date_tiered_db_impl.cc
index 978bfb2e49..2574d379f2 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/date_tiered/date_tiered_db_impl.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/date_tiered/date_tiered_db_impl.cc
@@ -389,7 +389,7 @@ Iterator* DateTieredDBImpl::NewIterator(const ReadOptions& opts) {
   for (auto& item : handle_map_) {
     auto handle = item.second;
     builder.AddIterator(db_impl->NewInternalIterator(
-        arena, db_iter->GetRangeDelAggregator(), handle));
+        arena, db_iter->GetRangeDelAggregator(), kMaxSequenceNumber, handle));
   }
   auto internal_iter = builder.Finish();
   db_iter->SetIterUnderDBIter(internal_iter);
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/date_tiered/date_tiered_db_impl.h b/3rdParty/rocksdb/v5.18.X/utilities/date_tiered/date_tiered_db_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/date_tiered/date_tiered_db_impl.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/date_tiered/date_tiered_db_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/date_tiered/date_tiered_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/date_tiered/date_tiered_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/date_tiered/date_tiered_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/date_tiered/date_tiered_test.cc
index 8e7fced58a..35f15584e5 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/date_tiered/date_tiered_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/date_tiered/date_tiered_test.cc
@@ -13,6 +13,7 @@
 
 #include "rocksdb/compaction_filter.h"
 #include "rocksdb/utilities/date_tiered_db.h"
+#include "port/port.h"
 #include "util/logging.h"
 #include "util/string_util.h"
 #include "util/testharness.h"
@@ -131,7 +132,7 @@ class DateTieredTest : public testing::Test {
   Options options_;
   KVMap::iterator kv_it_;
   const std::string kNewValue_ = "new_value";
-  unique_ptr<CompactionFilter> test_comp_filter_;
+  std::unique_ptr<CompactionFilter> test_comp_filter_;
 };
 
 // Puts a set of values and checks its presence using Get during ttl
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/debug.cc b/3rdParty/rocksdb/v5.18.X/utilities/debug.cc
similarity index 88%
rename from 3rdParty/rocksdb/v5.16.X/utilities/debug.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/debug.cc
index e0c5f5566e..3dfde980ec 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/debug.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/debug.cc
@@ -19,9 +19,11 @@ Status GetAllKeyVersions(DB* db, Slice begin_key, Slice end_key,
 
   DBImpl* idb = static_cast<DBImpl*>(db->GetRootDB());
   auto icmp = InternalKeyComparator(idb->GetOptions().comparator);
-  RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
+  ReadRangeDelAggregatorV2 range_del_agg(&icmp,
+                                         kMaxSequenceNumber /* upper_bound */);
   Arena arena;
-  ScopedArenaIterator iter(idb->NewInternalIterator(&arena, &range_del_agg));
+  ScopedArenaIterator iter(
+      idb->NewInternalIterator(&arena, &range_del_agg, kMaxSequenceNumber));
 
   if (!begin_key.empty()) {
     InternalKey ikey;
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/document/document_db.cc b/3rdParty/rocksdb/v5.18.X/utilities/document/document_db.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/document/document_db.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/document/document_db.cc
index 939327ed1b..279e4cb4da 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/document/document_db.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/document/document_db.cc
@@ -1155,10 +1155,10 @@ Options GetRocksDBOptionsFromOptions(const DocumentDBOptions& options) {
   Options rocksdb_options;
   rocksdb_options.max_background_compactions = options.background_threads - 1;
   rocksdb_options.max_background_flushes = 1;
-  rocksdb_options.write_buffer_size = options.memtable_size;
+  rocksdb_options.write_buffer_size = static_cast<size_t>(options.memtable_size);
   rocksdb_options.max_write_buffer_number = 6;
   BlockBasedTableOptions table_options;
-  table_options.block_cache = NewLRUCache(options.cache_size);
+  table_options.block_cache = NewLRUCache(static_cast<size_t>(options.cache_size));
   rocksdb_options.table_factory.reset(NewBlockBasedTableFactory(table_options));
   return rocksdb_options;
 }
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/document/document_db_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/document/document_db_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/document/document_db_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/document/document_db_test.cc
index 652f1e4558..3ee560db12 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/document/document_db_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/document/document_db_test.cc
@@ -75,8 +75,10 @@ TEST_F(DocumentDBTest, SimpleQueryTest) {
   ASSERT_OK(DocumentDB::Open(options, dbname_, {}, &db_));
   CreateIndexes({index});
   delete db_;
+  db_ = nullptr;
   // now there is index present
   ASSERT_OK(DocumentDB::Open(options, dbname_, {index}, &db_));
+  assert(db_ != nullptr);
   delete index.description;
 
   std::vector<std::string> json_objects = {
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/document/json_document.cc b/3rdParty/rocksdb/v5.18.X/utilities/document/json_document.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/document/json_document.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/document/json_document.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/document/json_document_builder.cc b/3rdParty/rocksdb/v5.18.X/utilities/document/json_document_builder.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/document/json_document_builder.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/document/json_document_builder.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/document/json_document_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/document/json_document_test.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/utilities/document/json_document_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/document/json_document_test.cc
index 977905b915..9d79c41cf5 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/document/json_document_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/document/json_document_test.cc
@@ -249,21 +249,23 @@ TEST_F(JSONDocumentTest, OperatorEqualsTest) {
   ASSERT_TRUE(JSONDocument(static_cast<int64_t>(15)) ==
               JSONDocument(static_cast<int64_t>(15)));
 
-  unique_ptr<JSONDocument> arrayWithInt8Doc(JSONDocument::ParseJSON("[8]"));
+  std::unique_ptr<JSONDocument> arrayWithInt8Doc(
+      JSONDocument::ParseJSON("[8]"));
   ASSERT_TRUE(arrayWithInt8Doc != nullptr);
   ASSERT_TRUE(arrayWithInt8Doc->IsArray());
   ASSERT_TRUE((*arrayWithInt8Doc)[0].IsInt64());
   ASSERT_TRUE((*arrayWithInt8Doc)[0] == JSONDocument(static_cast<int64_t>(8)));
 
-  unique_ptr<JSONDocument> arrayWithInt16Doc(JSONDocument::ParseJSON("[512]"));
+  std::unique_ptr<JSONDocument> arrayWithInt16Doc(
+      JSONDocument::ParseJSON("[512]"));
   ASSERT_TRUE(arrayWithInt16Doc != nullptr);
   ASSERT_TRUE(arrayWithInt16Doc->IsArray());
   ASSERT_TRUE((*arrayWithInt16Doc)[0].IsInt64());
   ASSERT_TRUE((*arrayWithInt16Doc)[0] ==
               JSONDocument(static_cast<int64_t>(512)));
 
-  unique_ptr<JSONDocument> arrayWithInt32Doc(
-    JSONDocument::ParseJSON("[1000000]"));
+  std::unique_ptr<JSONDocument> arrayWithInt32Doc(
+      JSONDocument::ParseJSON("[1000000]"));
   ASSERT_TRUE(arrayWithInt32Doc != nullptr);
   ASSERT_TRUE(arrayWithInt32Doc->IsArray());
   ASSERT_TRUE((*arrayWithInt32Doc)[0].IsInt64());
@@ -277,8 +279,8 @@ TEST_F(JSONDocumentTest, OperatorEqualsTest) {
 }
 
 TEST_F(JSONDocumentTest, JSONDocumentBuilderTest) {
-  unique_ptr<JSONDocument> parsedArray(
-    JSONDocument::ParseJSON("[1, [123, \"a\", \"b\"], {\"b\":\"c\"}]"));
+  std::unique_ptr<JSONDocument> parsedArray(
+      JSONDocument::ParseJSON("[1, [123, \"a\", \"b\"], {\"b\":\"c\"}]"));
   ASSERT_TRUE(parsedArray != nullptr);
 
   JSONDocumentBuilder builder;
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/env_librados.cc b/3rdParty/rocksdb/v5.18.X/utilities/env_librados.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/env_librados.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/env_librados.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/env_librados.md b/3rdParty/rocksdb/v5.18.X/utilities/env_librados.md
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/env_librados.md
rename to 3rdParty/rocksdb/v5.18.X/utilities/env_librados.md
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/env_librados_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/env_librados_test.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/utilities/env_librados_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/env_librados_test.cc
index 7d9b252ea4..fb10224e7d 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/env_librados_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/env_librados_test.cc
@@ -108,7 +108,7 @@ public:
 
 TEST_F(EnvLibradosTest, Basics) {
   uint64_t file_size;
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   std::vector<std::string> children;
 
   ASSERT_OK(env_->CreateDir("/dir"));
@@ -150,8 +150,8 @@ TEST_F(EnvLibradosTest, Basics) {
   ASSERT_EQ(3U, file_size);
 
   // Check that opening non-existent file fails.
-  unique_ptr<SequentialFile> seq_file;
-  unique_ptr<RandomAccessFile> rand_file;
+  std::unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<RandomAccessFile> rand_file;
   ASSERT_TRUE(
     !env_->NewSequentialFile("/dir/non_existent", &seq_file, soptions_).ok());
   ASSERT_TRUE(!seq_file);
@@ -169,9 +169,9 @@ TEST_F(EnvLibradosTest, Basics) {
 }
 
 TEST_F(EnvLibradosTest, ReadWrite) {
-  unique_ptr<WritableFile> writable_file;
-  unique_ptr<SequentialFile> seq_file;
-  unique_ptr<RandomAccessFile> rand_file;
+  std::unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<RandomAccessFile> rand_file;
   Slice result;
   char scratch[100];
 
@@ -210,7 +210,7 @@ TEST_F(EnvLibradosTest, ReadWrite) {
 
 TEST_F(EnvLibradosTest, Locks) {
   FileLock* lock = nullptr;
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
 
   ASSERT_OK(env_->CreateDir("/dir"));
 
@@ -229,7 +229,7 @@ TEST_F(EnvLibradosTest, Misc) {
   ASSERT_OK(env_->GetTestDirectory(&test_dir));
   ASSERT_TRUE(!test_dir.empty());
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   ASSERT_TRUE(!env_->NewWritableFile("/a/b", &writable_file, soptions_).ok());
 
   ASSERT_OK(env_->NewWritableFile("/a", &writable_file, soptions_));
@@ -249,14 +249,14 @@ TEST_F(EnvLibradosTest, LargeWrite) {
     write_data.append(1, 'h');
   }
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   ASSERT_OK(env_->CreateDir("/dir"));
   ASSERT_OK(env_->NewWritableFile("/dir/g", &writable_file, soptions_));
   ASSERT_OK(writable_file->Append("foo"));
   ASSERT_OK(writable_file->Append(write_data));
   writable_file.reset();
 
-  unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<SequentialFile> seq_file;
   Slice result;
   ASSERT_OK(env_->NewSequentialFile("/dir/g", &seq_file, soptions_));
   ASSERT_OK(seq_file->Read(3, &result, scratch));  // Read "foo".
@@ -282,7 +282,7 @@ TEST_F(EnvLibradosTest, FrequentlySmallWrite) {
     write_data.append(1, 'h');
   }
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   ASSERT_OK(env_->CreateDir("/dir"));
   ASSERT_OK(env_->NewWritableFile("/dir/g", &writable_file, soptions_));
   ASSERT_OK(writable_file->Append("foo"));
@@ -292,7 +292,7 @@ TEST_F(EnvLibradosTest, FrequentlySmallWrite) {
   }
   writable_file.reset();
 
-  unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<SequentialFile> seq_file;
   Slice result;
   ASSERT_OK(env_->NewSequentialFile("/dir/g", &seq_file, soptions_));
   ASSERT_OK(seq_file->Read(3, &result, scratch));  // Read "foo".
@@ -317,7 +317,7 @@ TEST_F(EnvLibradosTest, Truncate) {
     write_data.append(1, 'h');
   }
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   ASSERT_OK(env_->CreateDir("/dir"));
   ASSERT_OK(env_->NewWritableFile("/dir/g", &writable_file, soptions_));
   ASSERT_OK(writable_file->Append(write_data));
@@ -801,7 +801,7 @@ public:
 
 TEST_F(EnvLibradosMutipoolTest, Basics) {
   uint64_t file_size;
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   std::vector<std::string> children;
   std::vector<std::string> v = {"/tmp/dir1", "/tmp/dir2", "/tmp/dir3", "/tmp/dir4", "dir"};
 
@@ -850,8 +850,8 @@ TEST_F(EnvLibradosMutipoolTest, Basics) {
     ASSERT_EQ(3U, file_size);
 
     // Check that opening non-existent file fails.
-    unique_ptr<SequentialFile> seq_file;
-    unique_ptr<RandomAccessFile> rand_file;
+    std::unique_ptr<SequentialFile> seq_file;
+    std::unique_ptr<RandomAccessFile> rand_file;
     ASSERT_TRUE(
       !env_->NewSequentialFile(dir_non_existent.c_str(), &seq_file, soptions_).ok());
     ASSERT_TRUE(!seq_file);
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/env_mirror.cc b/3rdParty/rocksdb/v5.18.X/utilities/env_mirror.cc
similarity index 93%
rename from 3rdParty/rocksdb/v5.16.X/utilities/env_mirror.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/env_mirror.cc
index e4da918346..327d8e1622 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/env_mirror.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/env_mirror.cc
@@ -16,7 +16,7 @@ namespace rocksdb {
 // Env's.  This is useful for debugging purposes.
 class SequentialFileMirror : public SequentialFile {
  public:
-  unique_ptr<SequentialFile> a_, b_;
+  std::unique_ptr<SequentialFile> a_, b_;
   std::string fname;
   explicit SequentialFileMirror(std::string f) : fname(f) {}
 
@@ -60,11 +60,12 @@ class SequentialFileMirror : public SequentialFile {
 
 class RandomAccessFileMirror : public RandomAccessFile {
  public:
-  unique_ptr<RandomAccessFile> a_, b_;
+  std::unique_ptr<RandomAccessFile> a_, b_;
   std::string fname;
   explicit RandomAccessFileMirror(std::string f) : fname(f) {}
 
-  Status Read(uint64_t offset, size_t n, Slice* result, char* scratch) const override {
+  Status Read(uint64_t offset, size_t n, Slice* result,
+              char* scratch) const override {
     Status as = a_->Read(offset, n, result, scratch);
     if (as == Status::OK()) {
       char* bscratch = new char[n];
@@ -94,7 +95,7 @@ class RandomAccessFileMirror : public RandomAccessFile {
 
 class WritableFileMirror : public WritableFile {
  public:
-  unique_ptr<WritableFile> a_, b_;
+  std::unique_ptr<WritableFile> a_, b_;
   std::string fname;
   explicit WritableFileMirror(std::string f) : fname(f) {}
 
@@ -190,7 +191,7 @@ class WritableFileMirror : public WritableFile {
 };
 
 Status EnvMirror::NewSequentialFile(const std::string& f,
-                                    unique_ptr<SequentialFile>* r,
+                                    std::unique_ptr<SequentialFile>* r,
                                     const EnvOptions& options) {
   if (f.find("/proc/") == 0) {
     return a_->NewSequentialFile(f, r, options);
@@ -207,7 +208,7 @@ Status EnvMirror::NewSequentialFile(const std::string& f,
 }
 
 Status EnvMirror::NewRandomAccessFile(const std::string& f,
-                                      unique_ptr<RandomAccessFile>* r,
+                                      std::unique_ptr<RandomAccessFile>* r,
                                       const EnvOptions& options) {
   if (f.find("/proc/") == 0) {
     return a_->NewRandomAccessFile(f, r, options);
@@ -224,7 +225,7 @@ Status EnvMirror::NewRandomAccessFile(const std::string& f,
 }
 
 Status EnvMirror::NewWritableFile(const std::string& f,
-                                  unique_ptr<WritableFile>* r,
+                                  std::unique_ptr<WritableFile>* r,
                                   const EnvOptions& options) {
   if (f.find("/proc/") == 0) return a_->NewWritableFile(f, r, options);
   WritableFileMirror* mf = new WritableFileMirror(f);
@@ -240,7 +241,7 @@ Status EnvMirror::NewWritableFile(const std::string& f,
 
 Status EnvMirror::ReuseWritableFile(const std::string& fname,
                                     const std::string& old_fname,
-                                    unique_ptr<WritableFile>* r,
+                                    std::unique_ptr<WritableFile>* r,
                                     const EnvOptions& options) {
   if (fname.find("/proc/") == 0)
     return a_->ReuseWritableFile(fname, old_fname, r, options);
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/env_mirror_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/env_mirror_test.cc
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/utilities/env_mirror_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/env_mirror_test.cc
index 2bf8ec8583..812595ca1e 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/env_mirror_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/env_mirror_test.cc
@@ -32,7 +32,7 @@ class EnvMirrorTest : public testing::Test {
 
 TEST_F(EnvMirrorTest, Basics) {
   uint64_t file_size;
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   std::vector<std::string> children;
 
   ASSERT_OK(env_->CreateDir("/dir"));
@@ -91,8 +91,8 @@ TEST_F(EnvMirrorTest, Basics) {
   ASSERT_EQ(3U, file_size);
 
   // Check that opening non-existent file fails.
-  unique_ptr<SequentialFile> seq_file;
-  unique_ptr<RandomAccessFile> rand_file;
+  std::unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<RandomAccessFile> rand_file;
   ASSERT_TRUE(
       !env_->NewSequentialFile("/dir/non_existent", &seq_file, soptions_).ok());
   ASSERT_TRUE(!seq_file);
@@ -110,9 +110,9 @@ TEST_F(EnvMirrorTest, Basics) {
 }
 
 TEST_F(EnvMirrorTest, ReadWrite) {
-  unique_ptr<WritableFile> writable_file;
-  unique_ptr<SequentialFile> seq_file;
-  unique_ptr<RandomAccessFile> rand_file;
+  std::unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<RandomAccessFile> rand_file;
   Slice result;
   char scratch[100];
 
@@ -162,7 +162,7 @@ TEST_F(EnvMirrorTest, Misc) {
   ASSERT_OK(env_->GetTestDirectory(&test_dir));
   ASSERT_TRUE(!test_dir.empty());
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   ASSERT_OK(env_->NewWritableFile("/a/b", &writable_file, soptions_));
 
   // These are no-ops, but we test they return success.
@@ -181,13 +181,13 @@ TEST_F(EnvMirrorTest, LargeWrite) {
     write_data.append(1, static_cast<char>(i));
   }
 
-  unique_ptr<WritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
   ASSERT_OK(env_->NewWritableFile("/dir/f", &writable_file, soptions_));
   ASSERT_OK(writable_file->Append("foo"));
   ASSERT_OK(writable_file->Append(write_data));
   writable_file.reset();
 
-  unique_ptr<SequentialFile> seq_file;
+  std::unique_ptr<SequentialFile> seq_file;
   Slice result;
   ASSERT_OK(env_->NewSequentialFile("/dir/f", &seq_file, soptions_));
   ASSERT_OK(seq_file->Read(3, &result, scratch));  // Read "foo".
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/env_timed.cc b/3rdParty/rocksdb/v5.18.X/utilities/env_timed.cc
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/utilities/env_timed.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/env_timed.cc
index 6afd45bf99..86455ee65c 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/env_timed.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/env_timed.cc
@@ -18,21 +18,21 @@ class TimedEnv : public EnvWrapper {
   explicit TimedEnv(Env* base_env) : EnvWrapper(base_env) {}
 
   virtual Status NewSequentialFile(const std::string& fname,
-                                   unique_ptr<SequentialFile>* result,
+                                   std::unique_ptr<SequentialFile>* result,
                                    const EnvOptions& options) override {
     PERF_TIMER_GUARD(env_new_sequential_file_nanos);
     return EnvWrapper::NewSequentialFile(fname, result, options);
   }
 
   virtual Status NewRandomAccessFile(const std::string& fname,
-                                     unique_ptr<RandomAccessFile>* result,
+                                     std::unique_ptr<RandomAccessFile>* result,
                                      const EnvOptions& options) override {
     PERF_TIMER_GUARD(env_new_random_access_file_nanos);
     return EnvWrapper::NewRandomAccessFile(fname, result, options);
   }
 
   virtual Status NewWritableFile(const std::string& fname,
-                                 unique_ptr<WritableFile>* result,
+                                 std::unique_ptr<WritableFile>* result,
                                  const EnvOptions& options) override {
     PERF_TIMER_GUARD(env_new_writable_file_nanos);
     return EnvWrapper::NewWritableFile(fname, result, options);
@@ -40,21 +40,21 @@ class TimedEnv : public EnvWrapper {
 
   virtual Status ReuseWritableFile(const std::string& fname,
                                    const std::string& old_fname,
-                                   unique_ptr<WritableFile>* result,
+                                   std::unique_ptr<WritableFile>* result,
                                    const EnvOptions& options) override {
     PERF_TIMER_GUARD(env_reuse_writable_file_nanos);
     return EnvWrapper::ReuseWritableFile(fname, old_fname, result, options);
   }
 
   virtual Status NewRandomRWFile(const std::string& fname,
-                                 unique_ptr<RandomRWFile>* result,
+                                 std::unique_ptr<RandomRWFile>* result,
                                  const EnvOptions& options) override {
     PERF_TIMER_GUARD(env_new_random_rw_file_nanos);
     return EnvWrapper::NewRandomRWFile(fname, result, options);
   }
 
   virtual Status NewDirectory(const std::string& name,
-                              unique_ptr<Directory>* result) override {
+                              std::unique_ptr<Directory>* result) override {
     PERF_TIMER_GUARD(env_new_directory_nanos);
     return EnvWrapper::NewDirectory(name, result);
   }
@@ -131,7 +131,7 @@ class TimedEnv : public EnvWrapper {
   }
 
   virtual Status NewLogger(const std::string& fname,
-                           shared_ptr<Logger>* result) override {
+                           std::shared_ptr<Logger>* result) override {
     PERF_TIMER_GUARD(env_new_logger_nanos);
     return EnvWrapper::NewLogger(fname, result);
   }
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/env_timed_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/env_timed_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/env_timed_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/env_timed_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/geodb/geodb_impl.cc b/3rdParty/rocksdb/v5.18.X/utilities/geodb/geodb_impl.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/geodb/geodb_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/geodb/geodb_impl.cc
index 97c4da0f73..9150b16b2c 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/geodb/geodb_impl.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/geodb/geodb_impl.cc
@@ -222,7 +222,7 @@ GeoIterator* GeoDBImpl::SearchRadial(const GeoPosition& pos,
   Iterator* iter = db_->NewIterator(ReadOptions());
 
   // Process each prospective quadkey
-  for (std::string qid : qids) {
+  for (const std::string& qid : qids) {
     // The user is interested in only these many objects.
     if (number_of_values == 0) {
       break;
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/geodb/geodb_impl.h b/3rdParty/rocksdb/v5.18.X/utilities/geodb/geodb_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/geodb/geodb_impl.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/geodb/geodb_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/geodb/geodb_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/geodb/geodb_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/geodb/geodb_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/geodb/geodb_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/leveldb_options/leveldb_options.cc b/3rdParty/rocksdb/v5.18.X/utilities/leveldb_options/leveldb_options.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/leveldb_options/leveldb_options.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/leveldb_options/leveldb_options.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/lua/rocks_lua_compaction_filter.cc b/3rdParty/rocksdb/v5.18.X/utilities/lua/rocks_lua_compaction_filter.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/lua/rocks_lua_compaction_filter.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/lua/rocks_lua_compaction_filter.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/lua/rocks_lua_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/lua/rocks_lua_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/lua/rocks_lua_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/lua/rocks_lua_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/memory/memory_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/memory/memory_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/memory/memory_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/memory/memory_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/memory/memory_util.cc b/3rdParty/rocksdb/v5.18.X/utilities/memory/memory_util.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/memory/memory_util.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/memory/memory_util.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators.h b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/bytesxor.cc b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/bytesxor.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators/bytesxor.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators/bytesxor.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/bytesxor.h b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/bytesxor.h
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators/bytesxor.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators/bytesxor.h
index 1562ca852a..762e372445 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/bytesxor.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/bytesxor.h
@@ -3,8 +3,7 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#ifndef UTILITIES_MERGE_OPERATORS_BYTESXOR_H_
-#define UTILITIES_MERGE_OPERATORS_BYTESXOR_H_
+#pragma once
 
 #include <algorithm>
 #include <memory>
@@ -38,5 +37,3 @@ class BytesXOROperator : public AssociativeMergeOperator {
 };
 
 }  // namespace rocksdb
-
-#endif  // UTILITIES_MERGE_OPERATORS_BYTESXOR_H_
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/max.cc b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/max.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators/max.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators/max.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/put.cc b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/put.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators/put.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators/put.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/string_append/stringappend.cc b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/string_append/stringappend.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators/string_append/stringappend.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators/string_append/stringappend.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/string_append/stringappend.h b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/string_append/stringappend.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators/string_append/stringappend.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators/string_append/stringappend.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/string_append/stringappend2.cc b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/string_append/stringappend2.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators/string_append/stringappend2.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators/string_append/stringappend2.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/string_append/stringappend2.h b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/string_append/stringappend2.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators/string_append/stringappend2.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators/string_append/stringappend2.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/string_append/stringappend_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/string_append/stringappend_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators/string_append/stringappend_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators/string_append/stringappend_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/merge_operators/uint64add.cc b/3rdParty/rocksdb/v5.18.X/utilities/merge_operators/uint64add.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/merge_operators/uint64add.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/merge_operators/uint64add.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/object_registry_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/object_registry_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/object_registry_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/object_registry_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/option_change_migration/option_change_migration.cc b/3rdParty/rocksdb/v5.18.X/utilities/option_change_migration/option_change_migration.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/option_change_migration/option_change_migration.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/option_change_migration/option_change_migration.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/option_change_migration/option_change_migration_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/option_change_migration/option_change_migration_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/option_change_migration/option_change_migration_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/option_change_migration/option_change_migration_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/options/options_util.cc b/3rdParty/rocksdb/v5.18.X/utilities/options/options_util.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/options/options_util.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/options/options_util.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/options/options_util_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/options/options_util_test.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/utilities/options/options_util_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/options/options_util_test.cc
index bf830190c6..4c12f1a67d 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/options/options_util_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/options/options_util_test.cc
@@ -104,8 +104,8 @@ class DummyTableFactory : public TableFactory {
 
   virtual Status NewTableReader(
       const TableReaderOptions& /*table_reader_options*/,
-      unique_ptr<RandomAccessFileReader>&& /*file*/, uint64_t /*file_size*/,
-      unique_ptr<TableReader>* /*table_reader*/,
+      std::unique_ptr<RandomAccessFileReader>&& /*file*/,
+      uint64_t /*file_size*/, std::unique_ptr<TableReader>* /*table_reader*/,
       bool /*prefetch_index_and_filter_in_cache*/) const override {
     return Status::NotSupported();
   }
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier.cc b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier.cc
index 1ebf8ae6b3..f7f72df6df 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier.cc
@@ -263,7 +263,7 @@ Status BlockCacheTier::InsertImpl(const Slice& key, const Slice& data) {
   return Status::OK();
 }
 
-Status BlockCacheTier::Lookup(const Slice& key, unique_ptr<char[]>* val,
+Status BlockCacheTier::Lookup(const Slice& key, std::unique_ptr<char[]>* val,
                               size_t* size) {
   StopWatchNano timer(opt_.env, /*auto_start=*/ true);
 
@@ -287,7 +287,7 @@ Status BlockCacheTier::Lookup(const Slice& key, unique_ptr<char[]>* val,
 
   assert(file->refs_);
 
-  unique_ptr<char[]> scratch(new char[lba.size_]);
+  std::unique_ptr<char[]> scratch(new char[lba.size_]);
   Slice blk_key;
   Slice blk_val;
 
@@ -369,7 +369,7 @@ bool BlockCacheTier::Reserve(const size_t size) {
 
   const double retain_fac = (100 - kEvictPct) / static_cast<double>(100);
   while (size + size_ > opt_.cache_size * retain_fac) {
-    unique_ptr<BlockCacheFile> f(metadata_.Evict());
+    std::unique_ptr<BlockCacheFile> f(metadata_.Evict());
     if (!f) {
       // nothing is evictable
       return false;
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier.h
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier.h
index dcb97258b4..2b2c0ef4f1 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier.h
@@ -44,9 +44,9 @@ class BlockCacheTier : public PersistentCacheTier {
  public:
   explicit BlockCacheTier(const PersistentCacheConfig& opt)
       : opt_(opt),
-        insert_ops_(opt_.max_write_pipeline_backlog_size),
+        insert_ops_(static_cast<size_t>(opt_.max_write_pipeline_backlog_size)),
         buffer_allocator_(opt.write_buffer_size, opt.write_buffer_count()),
-        writer_(this, opt_.writer_qdepth, opt_.writer_dispatch_size) {
+        writer_(this, opt_.writer_qdepth, static_cast<size_t>(opt_.writer_dispatch_size)) {
     Info(opt_.log, "Initializing allocator. size=%d B count=%d",
          opt_.write_buffer_size, opt_.write_buffer_count());
   }
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_file.cc b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_file.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_file.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_file.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_file.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_file.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_file.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_file.h
index ef5dbab040..e38b6c9a1d 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_file.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_file.h
@@ -149,7 +149,7 @@ class RandomAccessCacheFile : public BlockCacheFile {
  public:
   explicit RandomAccessCacheFile(Env* const env, const std::string& dir,
                                  const uint32_t cache_id,
-                                 const shared_ptr<Logger>& log)
+                                 const std::shared_ptr<Logger>& log)
       : BlockCacheFile(env, dir, cache_id), log_(log) {}
 
   virtual ~RandomAccessCacheFile() {}
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_file_buffer.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_file_buffer.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_file_buffer.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_file_buffer.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_metadata.cc b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_metadata.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_metadata.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_metadata.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_metadata.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_metadata.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/block_cache_tier_metadata.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/block_cache_tier_metadata.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/hash_table.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/hash_table.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/hash_table.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/hash_table.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/hash_table_bench.cc b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/hash_table_bench.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/hash_table_bench.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/hash_table_bench.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/hash_table_evictable.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/hash_table_evictable.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/hash_table_evictable.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/hash_table_evictable.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/hash_table_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/hash_table_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/hash_table_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/hash_table_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/lrulist.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/lrulist.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/lrulist.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/lrulist.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_bench.cc b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_bench.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_bench.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_bench.cc
index 7d26c3a7de..64d75c7a51 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_bench.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_bench.cc
@@ -251,7 +251,7 @@ class CacheTierBenchmark {
 
   // create data for a key by filling with a certain pattern
   std::unique_ptr<char[]> NewBlock(const uint64_t val) {
-    unique_ptr<char[]> data(new char[FLAGS_iosize]);
+    std::unique_ptr<char[]> data(new char[FLAGS_iosize]);
     memset(data.get(), val % 255, FLAGS_iosize);
     return data;
   }
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_test.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_test.h
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_test.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_test.h
index 37e842f2e2..ad99ea864b 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_test.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_test.h
@@ -157,7 +157,7 @@ class PersistentCacheTierTest : public testing::Test {
       memset(edata, '0' + (i % 10), sizeof(edata));
       auto k = prefix + PaddedNumber(i, /*count=*/8);
       Slice key(k);
-      unique_ptr<char[]> block;
+      std::unique_ptr<char[]> block;
       size_t block_size;
 
       if (eviction_enabled) {
@@ -210,7 +210,7 @@ class PersistentCacheTierTest : public testing::Test {
   }
 
   const std::string path_;
-  shared_ptr<Logger> log_;
+  std::shared_ptr<Logger> log_;
   std::shared_ptr<PersistentCacheTier> cache_;
   std::atomic<size_t> key_{0};
   size_t max_keys_ = 0;
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_tier.cc b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_tier.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_tier.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_tier.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_tier.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_tier.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_tier.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_tier.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_util.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/persistent_cache_util.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/persistent_cache_util.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/volatile_tier_impl.cc b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/volatile_tier_impl.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/volatile_tier_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/volatile_tier_impl.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/volatile_tier_impl.h b/3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/volatile_tier_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/persistent_cache/volatile_tier_impl.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/persistent_cache/volatile_tier_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/redis/README b/3rdParty/rocksdb/v5.18.X/utilities/redis/README
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/redis/README
rename to 3rdParty/rocksdb/v5.18.X/utilities/redis/README
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/redis/redis_list_exception.h b/3rdParty/rocksdb/v5.18.X/utilities/redis/redis_list_exception.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/redis/redis_list_exception.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/redis/redis_list_exception.h
index f93bcbb190..bc2b39a310 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/redis/redis_list_exception.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/redis/redis_list_exception.h
@@ -5,8 +5,8 @@
  * Copyright 2013 Facebook
  */
 
-#ifndef ROCKSDB_LITE
 #pragma once
+#ifndef ROCKSDB_LITE
 #include <exception>
 
 namespace rocksdb {
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/redis/redis_list_iterator.h b/3rdParty/rocksdb/v5.18.X/utilities/redis/redis_list_iterator.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/redis/redis_list_iterator.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/redis/redis_list_iterator.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/redis/redis_lists.cc b/3rdParty/rocksdb/v5.18.X/utilities/redis/redis_lists.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/redis/redis_lists.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/redis/redis_lists.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/redis/redis_lists.h b/3rdParty/rocksdb/v5.18.X/utilities/redis/redis_lists.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/redis/redis_lists.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/redis/redis_lists.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/redis/redis_lists_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/redis/redis_lists_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/redis/redis_lists_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/redis/redis_lists_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/simulator_cache/sim_cache.cc b/3rdParty/rocksdb/v5.18.X/utilities/simulator_cache/sim_cache.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/simulator_cache/sim_cache.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/simulator_cache/sim_cache.cc
index e7750dd5e2..bdf6c5aa87 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/simulator_cache/sim_cache.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/simulator_cache/sim_cache.cc
@@ -46,7 +46,8 @@ class CacheActivityLogger {
     if (!status.ok()) {
       return status;
     }
-    file_writer_.reset(new WritableFileWriter(std::move(log_file), env_opts));
+    file_writer_.reset(new WritableFileWriter(std::move(log_file),
+                                              activity_log_file, env_opts));
 
     max_logging_size_ = max_logging_size;
     activity_logging_enabled_.store(true);
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/simulator_cache/sim_cache_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/simulator_cache/sim_cache_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/simulator_cache/sim_cache_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/simulator_cache/sim_cache_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/spatialdb/spatial_db.cc b/3rdParty/rocksdb/v5.18.X/utilities/spatialdb/spatial_db.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/utilities/spatialdb/spatial_db.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/spatialdb/spatial_db.cc
index a9b990ee20..b34976eb81 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/spatialdb/spatial_db.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/spatialdb/spatial_db.cc
@@ -354,8 +354,8 @@ class SpatialIndexCursor : public Cursor {
       : value_getter_(value_getter), valid_(true) {
     // calculate quad keys we'll need to query
     std::vector<uint64_t> quad_keys;
-    quad_keys.reserve((tile_bbox.max_x - tile_bbox.min_x + 1) *
-                      (tile_bbox.max_y - tile_bbox.min_y + 1));
+    quad_keys.reserve(static_cast<size_t>((tile_bbox.max_x - tile_bbox.min_x + 1) *
+                      (tile_bbox.max_y - tile_bbox.min_y + 1)));
     for (uint64_t x = tile_bbox.min_x; x <= tile_bbox.max_x; ++x) {
       for (uint64_t y = tile_bbox.min_y; y <= tile_bbox.max_y; ++y) {
         quad_keys.push_back(GetQuadKeyFromTile(x, y, tile_bits));
@@ -473,7 +473,7 @@ class SpatialIndexCursor : public Cursor {
 
   }
 
-  unique_ptr<ValueGetter> value_getter_;
+  std::unique_ptr<ValueGetter> value_getter_;
   bool valid_;
   Status status_;
 
@@ -791,7 +791,7 @@ Status SpatialDB::Create(
   db_options.create_missing_column_families = true;
   db_options.error_if_exists = true;
 
-  auto block_cache = NewLRUCache(options.cache_size);
+  auto block_cache = NewLRUCache(static_cast<size_t>(options.cache_size));
   ColumnFamilyOptions column_family_options =
       GetColumnFamilyOptions(options, block_cache);
 
@@ -832,7 +832,7 @@ Status SpatialDB::Create(
 Status SpatialDB::Open(const SpatialDBOptions& options, const std::string& name,
                        SpatialDB** db, bool read_only) {
   DBOptions db_options = GetDBOptionsFromSpatialDBOptions(options);
-  auto block_cache = NewLRUCache(options.cache_size);
+  auto block_cache = NewLRUCache(static_cast<size_t>(options.cache_size));
   ColumnFamilyOptions column_family_options =
       GetColumnFamilyOptions(options, block_cache);
 
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/spatialdb/spatial_db_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/spatialdb/spatial_db_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/spatialdb/spatial_db_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/spatialdb/spatial_db_test.cc
index 783b347d0a..cb92af8b1a 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/spatialdb/spatial_db_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/spatialdb/spatial_db_test.cc
@@ -94,7 +94,7 @@ TEST_F(SpatialDBTest, FeatureSetSerializeTest) {
   ASSERT_EQ(deserialized.Get("m").get_double(), 3.25);
 
   // corrupted serialization
-  serialized = serialized.substr(0, serialized.size() - 4);
+  serialized = serialized.substr(0, serialized.size() - 1);
   deserialized.Clear();
   ASSERT_TRUE(!deserialized.Deserialize(serialized));
 }
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/spatialdb/utils.h b/3rdParty/rocksdb/v5.18.X/utilities/spatialdb/utils.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/spatialdb/utils.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/spatialdb/utils.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/table_properties_collectors/compact_on_deletion_collector.cc b/3rdParty/rocksdb/v5.18.X/utilities/table_properties_collectors/compact_on_deletion_collector.cc
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/utilities/table_properties_collectors/compact_on_deletion_collector.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/table_properties_collectors/compact_on_deletion_collector.cc
index fdb7389a7a..eaf2c501d1 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/table_properties_collectors/compact_on_deletion_collector.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/table_properties_collectors/compact_on_deletion_collector.cc
@@ -20,7 +20,6 @@ CompactOnDeletionCollector::CompactOnDeletionCollector(
       deletion_trigger_(deletion_trigger),
       need_compaction_(false),
       finished_(false) {
-  assert(bucket_size_ > 0U);
   memset(num_deletions_in_buckets_, 0, sizeof(size_t) * kNumBuckets);
 }
 
@@ -35,6 +34,11 @@ Status CompactOnDeletionCollector::AddUserKey(const Slice& /*key*/,
                                               SequenceNumber /*seq*/,
                                               uint64_t /*file_size*/) {
   assert(!finished_);
+  if (bucket_size_ == 0) {
+    // This collector is effectively disabled
+    return Status::OK();
+  }
+
   if (need_compaction_) {
     // If the output file already needs to be compacted, skip the check.
     return Status::OK();
@@ -71,14 +75,14 @@ TablePropertiesCollector*
 CompactOnDeletionCollectorFactory::CreateTablePropertiesCollector(
     TablePropertiesCollectorFactory::Context /*context*/) {
   return new CompactOnDeletionCollector(
-      sliding_window_size_, deletion_trigger_);
+      sliding_window_size_.load(), deletion_trigger_.load());
 }
 
-std::shared_ptr<TablePropertiesCollectorFactory>
+std::shared_ptr<CompactOnDeletionCollectorFactory>
     NewCompactOnDeletionCollectorFactory(
         size_t sliding_window_size,
         size_t deletion_trigger) {
-  return std::shared_ptr<TablePropertiesCollectorFactory>(
+  return std::shared_ptr<CompactOnDeletionCollectorFactory>(
       new CompactOnDeletionCollectorFactory(
           sliding_window_size, deletion_trigger));
 }
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/table_properties_collectors/compact_on_deletion_collector.h b/3rdParty/rocksdb/v5.18.X/utilities/table_properties_collectors/compact_on_deletion_collector.h
similarity index 69%
rename from 3rdParty/rocksdb/v5.16.X/utilities/table_properties_collectors/compact_on_deletion_collector.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/table_properties_collectors/compact_on_deletion_collector.h
index 5406ecea28..96c8db896f 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/table_properties_collectors/compact_on_deletion_collector.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/table_properties_collectors/compact_on_deletion_collector.h
@@ -9,38 +9,6 @@
 #include "rocksdb/utilities/table_properties_collectors.h"
 namespace rocksdb {
 
-// A factory of a table property collector that marks a SST
-// file as need-compaction when it observe at least "D" deletion
-// entries in any "N" consecutive entires.
-class CompactOnDeletionCollectorFactory
-    : public TablePropertiesCollectorFactory {
- public:
-  // A factory of a table property collector that marks a SST
-  // file as need-compaction when it observe at least "D" deletion
-  // entries in any "N" consecutive entires.
-  //
-  // @param sliding_window_size "N"
-  // @param deletion_trigger "D"
-  CompactOnDeletionCollectorFactory(
-      size_t sliding_window_size,
-      size_t deletion_trigger) :
-          sliding_window_size_(sliding_window_size),
-          deletion_trigger_(deletion_trigger) {}
-
-  virtual ~CompactOnDeletionCollectorFactory() {}
-
-  virtual TablePropertiesCollector* CreateTablePropertiesCollector(
-      TablePropertiesCollectorFactory::Context context) override;
-
-  virtual const char* Name() const override {
-    return "CompactOnDeletionCollector";
-  }
-
- private:
-  size_t sliding_window_size_;
-  size_t deletion_trigger_;
-};
-
 class CompactOnDeletionCollector : public TablePropertiesCollector {
  public:
   CompactOnDeletionCollector(
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/table_properties_collectors/compact_on_deletion_collector_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/trace/file_trace_reader_writer.cc b/3rdParty/rocksdb/v5.18.X/utilities/trace/file_trace_reader_writer.cc
similarity index 90%
rename from 3rdParty/rocksdb/v5.16.X/utilities/trace/file_trace_reader_writer.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/trace/file_trace_reader_writer.cc
index dde36aa93c..4a81516a8b 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/trace/file_trace_reader_writer.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/trace/file_trace_reader_writer.cc
@@ -83,16 +83,18 @@ Status FileTraceWriter::Write(const Slice& data) {
   return file_writer_->Append(data);
 }
 
+uint64_t FileTraceWriter::GetFileSize() { return file_writer_->GetFileSize(); }
+
 Status NewFileTraceReader(Env* env, const EnvOptions& env_options,
                           const std::string& trace_filename,
                           std::unique_ptr<TraceReader>* trace_reader) {
-  unique_ptr<RandomAccessFile> trace_file;
+  std::unique_ptr<RandomAccessFile> trace_file;
   Status s = env->NewRandomAccessFile(trace_filename, &trace_file, env_options);
   if (!s.ok()) {
     return s;
   }
 
-  unique_ptr<RandomAccessFileReader> file_reader;
+  std::unique_ptr<RandomAccessFileReader> file_reader;
   file_reader.reset(
       new RandomAccessFileReader(std::move(trace_file), trace_filename));
   trace_reader->reset(new FileTraceReader(std::move(file_reader)));
@@ -102,14 +104,15 @@ Status NewFileTraceReader(Env* env, const EnvOptions& env_options,
 Status NewFileTraceWriter(Env* env, const EnvOptions& env_options,
                           const std::string& trace_filename,
                           std::unique_ptr<TraceWriter>* trace_writer) {
-  unique_ptr<WritableFile> trace_file;
+  std::unique_ptr<WritableFile> trace_file;
   Status s = env->NewWritableFile(trace_filename, &trace_file, env_options);
   if (!s.ok()) {
     return s;
   }
 
-  unique_ptr<WritableFileWriter> file_writer;
-  file_writer.reset(new WritableFileWriter(std::move(trace_file), env_options));
+  std::unique_ptr<WritableFileWriter> file_writer;
+  file_writer.reset(new WritableFileWriter(std::move(trace_file),
+                                           trace_filename, env_options));
   trace_writer->reset(new FileTraceWriter(std::move(file_writer)));
   return s;
 }
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/trace/file_trace_reader_writer.h b/3rdParty/rocksdb/v5.18.X/utilities/trace/file_trace_reader_writer.h
similarity index 88%
rename from 3rdParty/rocksdb/v5.16.X/utilities/trace/file_trace_reader_writer.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/trace/file_trace_reader_writer.h
index b363a3f09f..863f5d9d06 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/trace/file_trace_reader_writer.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/trace/file_trace_reader_writer.h
@@ -22,7 +22,7 @@ class FileTraceReader : public TraceReader {
   virtual Status Close() override;
 
  private:
-  unique_ptr<RandomAccessFileReader> file_reader_;
+  std::unique_ptr<RandomAccessFileReader> file_reader_;
   Slice result_;
   size_t offset_;
   char* const buffer_;
@@ -39,9 +39,10 @@ class FileTraceWriter : public TraceWriter {
 
   virtual Status Write(const Slice& data) override;
   virtual Status Close() override;
+  virtual uint64_t GetFileSize() override;
 
  private:
-  unique_ptr<WritableFileWriter> file_writer_;
+  std::unique_ptr<WritableFileWriter> file_writer_;
 };
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/optimistic_transaction.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/optimistic_transaction.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/optimistic_transaction.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/optimistic_transaction.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/optimistic_transaction.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/optimistic_transaction.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/optimistic_transaction.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/optimistic_transaction.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/optimistic_transaction_db_impl.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/optimistic_transaction_db_impl.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/optimistic_transaction_db_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/optimistic_transaction_db_impl.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/optimistic_transaction_db_impl.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/optimistic_transaction_db_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/optimistic_transaction_db_impl.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/optimistic_transaction_db_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/optimistic_transaction_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/optimistic_transaction_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/optimistic_transaction_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/optimistic_transaction_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction.cc
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction.cc
index 65487ea505..d895d9d935 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction.cc
@@ -46,7 +46,8 @@ PessimisticTransaction::PessimisticTransaction(
       waiting_key_(nullptr),
       lock_timeout_(0),
       deadlock_detect_(false),
-      deadlock_detect_depth_(0) {
+      deadlock_detect_depth_(0),
+      skip_concurrency_control_(false) {
   txn_db_impl_ =
       static_cast_with_check<PessimisticTransactionDB, TransactionDB>(txn_db);
   db_impl_ = static_cast_with_check<DBImpl, DB>(db_);
@@ -61,6 +62,7 @@ void PessimisticTransaction::Initialize(const TransactionOptions& txn_options) {
   deadlock_detect_ = txn_options.deadlock_detect;
   deadlock_detect_depth_ = txn_options.deadlock_detect_depth;
   write_batch_.SetMaxBytes(txn_options.max_write_batch_size);
+  skip_concurrency_control_ = txn_options.skip_concurrency_control;
 
   lock_timeout_ = txn_options.lock_timeout * 1000;
   if (lock_timeout_ < 0) {
@@ -125,8 +127,7 @@ bool PessimisticTransaction::IsExpired() const {
 WriteCommittedTxn::WriteCommittedTxn(TransactionDB* txn_db,
                                      const WriteOptions& write_options,
                                      const TransactionOptions& txn_options)
-    : PessimisticTransaction(txn_db, write_options, txn_options),
-      _commited_seq_nr(0) {};
+    : PessimisticTransaction(txn_db, write_options, txn_options){};
 
 Status PessimisticTransaction::CommitBatch(WriteBatch* batch) {
   TransactionKeyMap keys_to_unlock;
@@ -229,15 +230,10 @@ Status WriteCommittedTxn::PrepareInternal() {
   WriteOptions write_options = write_options_;
   write_options.disableWAL = false;
   WriteBatchInternal::MarkEndPrepare(GetWriteBatch()->GetWriteBatch(), name_);
-  uint64_t seq_used = kMaxSequenceNumber;
   Status s =
       db_impl_->WriteImpl(write_options, GetWriteBatch()->GetWriteBatch(),
-                          /*callback*/ nullptr, &log_number_, /*log ref*/ 0,
-                          /*disable_memtable*/ true, &seq_used);
-  assert(!s.ok() || seq_used != kMaxSequenceNumber);
-  if (s.ok()) {
-    _commited_seq_nr = seq_used;
-  }
+                          /*callback*/ nullptr, &log_number_, /*log_ref*/ 0,
+                          /* disable_memtable*/ true);
   return s;
 }
 
@@ -327,18 +323,26 @@ Status PessimisticTransaction::Commit() {
 
 Status WriteCommittedTxn::CommitWithoutPrepareInternal() {
   uint64_t seq_used = kMaxSequenceNumber;
-  auto s = db_impl_->WriteImpl(write_options_, GetWriteBatch()->GetWriteBatch(),
-                               /*callback*/ nullptr, /*log nr*/ nullptr,
-                               /*log ref*/ 0, /*disable_memtable*/ false, &seq_used);
+  auto s =
+      db_impl_->WriteImpl(write_options_, GetWriteBatch()->GetWriteBatch(),
+                          /*callback*/ nullptr, /*log_used*/ nullptr,
+                          /*log_ref*/ 0, /*disable_memtable*/ false, &seq_used);
   assert(!s.ok() || seq_used != kMaxSequenceNumber);
   if (s.ok()) {
-    _commited_seq_nr = seq_used;
+    SetId(seq_used);
   }
   return s;
 }
 
 Status WriteCommittedTxn::CommitBatchInternal(WriteBatch* batch, size_t) {
-  Status s = db_->Write(write_options_, batch);
+  uint64_t seq_used = kMaxSequenceNumber;
+  auto s = db_impl_->WriteImpl(write_options_, batch, /*callback*/ nullptr,
+                               /*log_used*/ nullptr, /*log_ref*/ 0,
+                               /*disable_memtable*/ false, &seq_used);
+  assert(!s.ok() || seq_used != kMaxSequenceNumber);
+  if (s.ok()) {
+    SetId(seq_used);
+  }
   return s;
 }
 
@@ -356,8 +360,15 @@ Status WriteCommittedTxn::CommitInternal() {
   // in non recovery mode and simply insert the values
   WriteBatchInternal::Append(working_batch, GetWriteBatch()->GetWriteBatch());
 
-  auto s = db_impl_->WriteImpl(write_options_, working_batch, nullptr, nullptr,
-                               log_number_);
+  uint64_t seq_used = kMaxSequenceNumber;
+  auto s =
+      db_impl_->WriteImpl(write_options_, working_batch, /*callback*/ nullptr,
+                          /*log_used*/ nullptr, /*log_ref*/ log_number_,
+                          /*disable_memtable*/ false, &seq_used);  
+  assert(!s.ok() || seq_used != kMaxSequenceNumber);
+  if (s.ok()) {
+    SetId(seq_used);
+  }
   return s;
 }
 
@@ -505,11 +516,14 @@ Status PessimisticTransaction::LockBatch(WriteBatch* batch,
 Status PessimisticTransaction::TryLock(ColumnFamilyHandle* column_family,
                                        const Slice& key, bool read_only,
                                        bool exclusive, bool skip_validate) {
+  Status s;
+  if (UNLIKELY(skip_concurrency_control_)) {
+    return s;
+  }
   uint32_t cfh_id = GetColumnFamilyID(column_family);
   std::string key_str = key.ToString();
   bool previously_locked;
   bool lock_upgrade = false;
-  Status s;
 
   // lock this key if this transactions hasn't already locked it
   SequenceNumber tracked_at_seq = kMaxSequenceNumber;
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction.h
index 899441d62f..145d561fb1 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction.h
@@ -183,6 +183,9 @@ class PessimisticTransaction : public TransactionBaseImpl {
   // Whether to perform deadlock detection or not.
   int64_t deadlock_detect_depth_;
 
+  // Refer to TransactionOptions::skip_concurrency_control
+  bool skip_concurrency_control_;
+
   virtual Status ValidateSnapshot(ColumnFamilyHandle* column_family,
                                   const Slice& key,
                                   SequenceNumber* tracked_at_seq);
@@ -201,11 +204,6 @@ class WriteCommittedTxn : public PessimisticTransaction {
                     const TransactionOptions& txn_options);
 
   virtual ~WriteCommittedTxn() {}
-  
-  SequenceNumber GetCommitedSeqNumber() const override {
-    assert(txn_state_ == COMMITED);
-    return _commited_seq_nr;
-  }
 
  private:
   Status PrepareInternal() override;
@@ -221,10 +219,6 @@ class WriteCommittedTxn : public PessimisticTransaction {
   // No copying allowed
   WriteCommittedTxn(const WriteCommittedTxn&);
   void operator=(const WriteCommittedTxn&);
-  
- protected:
-  // seq_nr of WriteBatch in WAL
-  SequenceNumber _commited_seq_nr;
 };
 
 }  // namespace rocksdb
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction_db.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction_db.cc
similarity index 96%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction_db.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction_db.cc
index 0f1d9b41e0..8eb21777a9 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction_db.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction_db.cc
@@ -133,12 +133,22 @@ Status PessimisticTransactionDB::Initialize(
     WriteOptions w_options;
     w_options.sync = true;
     TransactionOptions t_options;
+    // This would help avoiding deadlock for keys that although exist in the WAL
+    // did not go through concurrency control. This includes the merge that
+    // MyRocks uses for auto-inc columns. It is safe to do so, since (i) if
+    // there is a conflict between the keys of two transactions that must be
+    // avoided, it is already avoided by the application, MyRocks, before the
+    // restart (ii) application, MyRocks, guarntees to rollback/commit the
+    // recovered transactions before new transactions start.
+    t_options.skip_concurrency_control = true;
 
     Transaction* real_trx = BeginTransaction(w_options, t_options, nullptr);
     assert(real_trx);
     real_trx->SetLogNumber(batch_info.log_number_);
     assert(seq != kMaxSequenceNumber);
-    real_trx->SetId(seq);
+    if (GetTxnDBOptions().write_policy != WRITE_COMMITTED) {
+      real_trx->SetId(seq);
+    }
 
     s = real_trx->SetName(recovered_trx->name_);
     if (!s.ok()) {
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction_db.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction_db.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/pessimistic_transaction_db.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/pessimistic_transaction_db.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/snapshot_checker.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/snapshot_checker.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/snapshot_checker.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/snapshot_checker.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_base.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_base.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_base.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_base.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_base.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_base.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_base.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_base.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_db_mutex_impl.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_db_mutex_impl.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_db_mutex_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_db_mutex_impl.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_db_mutex_impl.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_db_mutex_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_db_mutex_impl.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_db_mutex_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_lock_mgr.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_lock_mgr.cc
similarity index 98%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_lock_mgr.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_lock_mgr.cc
index 19321de485..8086f7c7c0 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_lock_mgr.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_lock_mgr.cc
@@ -104,7 +104,7 @@ void DeadlockInfoBuffer::AddNewPath(DeadlockPath path) {
     return;
   }
 
-  paths_buffer_[buffer_idx_] = path;
+  paths_buffer_[buffer_idx_] = std::move(path);
   buffer_idx_ = (buffer_idx_ + 1) % paths_buffer_.size();
 }
 
@@ -222,9 +222,9 @@ void TransactionLockMgr::RemoveColumnFamily(uint32_t column_family_id) {
   }
 }
 
-// Look up the LockMap shared_ptr for a given column_family_id.
+// Look up the LockMap std::shared_ptr for a given column_family_id.
 // Note:  The LockMap is only valid as long as the caller is still holding on
-//   to the returned shared_ptr.
+//   to the returned std::shared_ptr.
 std::shared_ptr<LockMap> TransactionLockMgr::GetLockMap(
     uint32_t column_family_id) {
   // First check thread-local cache
@@ -446,8 +446,8 @@ bool TransactionLockMgr::IncrementWaiters(
     const autovector<TransactionID>& wait_ids, const std::string& key,
     const uint32_t& cf_id, const bool& exclusive, Env* const env) {
   auto id = txn->GetID();
-  std::vector<int> queue_parents(txn->GetDeadlockDetectDepth());
-  std::vector<TransactionID> queue_values(txn->GetDeadlockDetectDepth());
+  std::vector<int> queue_parents(static_cast<size_t>(txn->GetDeadlockDetectDepth()));
+  std::vector<TransactionID> queue_values(static_cast<size_t>(txn->GetDeadlockDetectDepth()));
   std::lock_guard<std::mutex> lock(wait_txn_map_mutex_);
   assert(!wait_txn_map_.Contains(id));
 
@@ -494,8 +494,8 @@ bool TransactionLockMgr::IncrementWaiters(
 
         auto extracted_info = wait_txn_map_.Get(queue_values[head]);
         path.push_back({queue_values[head], extracted_info.m_cf_id,
-                        extracted_info.m_waiting_key,
-                        extracted_info.m_exclusive});
+                        extracted_info.m_exclusive,
+                        extracted_info.m_waiting_key});
         head = queue_parents[head];
       }
       env->GetCurrentTime(&deadlock_time);
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_lock_mgr.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_lock_mgr.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_lock_mgr.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_lock_mgr.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_test.cc
index 44c6e35964..0968b9a349 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_test.cc
@@ -606,6 +606,7 @@ TEST_P(TransactionTest, DeadlockCycleShared) {
   }
 }
 
+#ifndef ROCKSDB_VALGRIND_RUN
 TEST_P(TransactionStressTest, DeadlockCycle) {
   WriteOptions write_options;
   ReadOptions read_options;
@@ -768,6 +769,7 @@ TEST_P(TransactionStressTest, DeadlockStress) {
     t.join();
   }
 }
+#endif  // ROCKSDB_VALGRIND_RUN
 
 TEST_P(TransactionTest, CommitTimeBatchFailTest) {
   WriteOptions write_options;
@@ -796,6 +798,7 @@ TEST_P(TransactionTest, LogMarkLeakTest) {
   WriteOptions write_options;
   options.write_buffer_size = 1024;
   ASSERT_OK(ReOpenNoDelete());
+  assert(db != nullptr);
   Random rnd(47);
   std::vector<Transaction*> txns;
   DBImpl* db_impl = reinterpret_cast<DBImpl*>(db->GetRootDB());
@@ -1096,6 +1099,7 @@ TEST_P(TransactionTest, TwoPhaseEmptyWriteTest) {
   }
 }
 
+#ifndef ROCKSDB_VALGRIND_RUN
 TEST_P(TransactionStressTest, TwoPhaseExpirationTest) {
   Status s;
 
@@ -1254,6 +1258,7 @@ TEST_P(TransactionTest, PersistentTwoPhaseTransactionTest) {
   reinterpret_cast<PessimisticTransactionDB*>(db)->TEST_Crash();
   s = ReOpenNoDelete();
   ASSERT_OK(s);
+  assert(db != nullptr);
   db_impl = reinterpret_cast<DBImpl*>(db->GetRootDB());
 
   // find trans in list of prepared transactions
@@ -1332,6 +1337,7 @@ TEST_P(TransactionTest, PersistentTwoPhaseTransactionTest) {
   // deleting transaction should unregister transaction
   ASSERT_EQ(db->GetTransactionByName("xid"), nullptr);
 }
+#endif  // ROCKSDB_VALGRIND_RUN
 
 // TODO this test needs to be updated with serial commits
 TEST_P(TransactionTest, DISABLED_TwoPhaseMultiThreadTest) {
@@ -1717,7 +1723,7 @@ TEST_P(TransactionTest, TwoPhaseLogRollingTest) {
   }
 
   // flush only cfa memtable
-  s = db_impl->TEST_FlushMemTable(true, cfa);
+  s = db_impl->TEST_FlushMemTable(true, false, cfa);
   ASSERT_OK(s);
 
   switch (txn_db_options.write_policy) {
@@ -1736,7 +1742,7 @@ TEST_P(TransactionTest, TwoPhaseLogRollingTest) {
   }
 
   // flush only cfb memtable
-  s = db_impl->TEST_FlushMemTable(true, cfb);
+  s = db_impl->TEST_FlushMemTable(true, false, cfb);
   ASSERT_OK(s);
 
   // should show not dependency on logs
@@ -3786,7 +3792,7 @@ TEST_P(TransactionTest, SavepointTest3) {
 
   s = txn1->Put("A", "");
   ASSERT_OK(s);
-  
+
   s = txn1->PopSavePoint();  // Still no SavePoint present
   ASSERT_TRUE(s.IsNotFound());
 
@@ -3796,21 +3802,21 @@ TEST_P(TransactionTest, SavepointTest3) {
   ASSERT_OK(s);
 
   s = txn1->PopSavePoint();  // Remove 1
-  ASSERT_TRUE(txn1->RollbackToSavePoint().IsNotFound()); 
+  ASSERT_TRUE(txn1->RollbackToSavePoint().IsNotFound());
 
-  // Verify that "A" is still locked 
+  // Verify that "A" is still locked
   Transaction* txn2 = db->BeginTransaction(write_options, txn_options);
   ASSERT_TRUE(txn2);
 
   s = txn2->Put("A", "a2");
   ASSERT_TRUE(s.IsTimedOut());
   delete txn2;
-  
+
   txn1->SetSavePoint();  // 2
 
   s = txn1->Put("B", "b");
   ASSERT_OK(s);
-  
+
   txn1->SetSavePoint();  // 3
 
   s = txn1->Put("B", "b2");
@@ -3820,7 +3826,7 @@ TEST_P(TransactionTest, SavepointTest3) {
 
   s = txn1->PopSavePoint();
   ASSERT_OK(s);
-  
+
   s = txn1->PopSavePoint();
   ASSERT_TRUE(s.IsNotFound());
 
@@ -3834,12 +3840,12 @@ TEST_P(TransactionTest, SavepointTest3) {
   s = db->Get(read_options, "A", &value);
   ASSERT_OK(s);
   ASSERT_EQ("a", value);
-  
+
   // tnx1 should have set "B" to just "b"
   s = db->Get(read_options, "B", &value);
   ASSERT_OK(s);
   ASSERT_EQ("b", value);
-  
+
   s = db->Get(read_options, "C", &value);
   ASSERT_TRUE(s.IsNotFound());
 }
@@ -5511,7 +5517,7 @@ TEST_P(TransactionTest, DuplicateKeys) {
     db->FlushWAL(true);
     // Flush only cf 1
     reinterpret_cast<DBImpl*>(db->GetRootDB())
-        ->TEST_FlushMemTable(true, handles[1]);
+        ->TEST_FlushMemTable(true, false, handles[1]);
     reinterpret_cast<PessimisticTransactionDB*>(db)->TEST_Crash();
     ASSERT_OK(ReOpenNoDelete(cfds, &handles));
     txn0 = db->GetTransactionByName("xid");
@@ -5549,7 +5555,7 @@ TEST_P(TransactionTest, DuplicateKeys) {
     ASSERT_OK(db->FlushWAL(true));
     // Flush only cf 1
     reinterpret_cast<DBImpl*>(db->GetRootDB())
-        ->TEST_FlushMemTable(true, handles[1]);
+        ->TEST_FlushMemTable(true, false, handles[1]);
     reinterpret_cast<PessimisticTransactionDB*>(db)->TEST_Crash();
     ASSERT_OK(ReOpenNoDelete(cfds, &handles));
     txn0 = db->GetTransactionByName("xid");
@@ -5582,7 +5588,7 @@ TEST_P(TransactionTest, DuplicateKeys) {
     ASSERT_OK(db->FlushWAL(true));
     // Flush only cf 1
     reinterpret_cast<DBImpl*>(db->GetRootDB())
-        ->TEST_FlushMemTable(true, handles[1]);
+        ->TEST_FlushMemTable(true, false, handles[1]);
     reinterpret_cast<PessimisticTransactionDB*>(db)->TEST_Crash();
     ASSERT_OK(ReOpenNoDelete(cfds, &handles));
     txn0 = db->GetTransactionByName("xid");
@@ -5609,7 +5615,7 @@ TEST_P(TransactionTest, DuplicateKeys) {
     ASSERT_OK(db->FlushWAL(true));
     // Flush only cf 1
     reinterpret_cast<DBImpl*>(db->GetRootDB())
-        ->TEST_FlushMemTable(true, handles[1]);
+        ->TEST_FlushMemTable(true, false, handles[1]);
     reinterpret_cast<PessimisticTransactionDB*>(db)->TEST_Crash();
     ASSERT_OK(ReOpenNoDelete(cfds, &handles));
     txn0 = db->GetTransactionByName("xid");
@@ -5636,7 +5642,7 @@ TEST_P(TransactionTest, DuplicateKeys) {
     ASSERT_OK(db->FlushWAL(true));
     // Flush only cf 1
     reinterpret_cast<DBImpl*>(db->GetRootDB())
-        ->TEST_FlushMemTable(true, handles[1]);
+        ->TEST_FlushMemTable(true, false, handles[1]);
     reinterpret_cast<PessimisticTransactionDB*>(db)->TEST_Crash();
     ASSERT_OK(ReOpenNoDelete(cfds, &handles));
     txn0 = db->GetTransactionByName("xid");
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_test.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_test.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_test.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_test.h
index d024cecb21..cdc014acb2 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_test.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_test.h
@@ -100,6 +100,7 @@ class TransactionTestBase : public ::testing::Test {
     } else {
       s = OpenWithStackableDB();
     }
+    assert(!s.ok() || db != nullptr);
     return s;
   }
 
@@ -121,6 +122,7 @@ class TransactionTestBase : public ::testing::Test {
     } else {
       s = OpenWithStackableDB(cfs, handles);
     }
+    assert(db != nullptr);
     return s;
   }
 
@@ -134,6 +136,7 @@ class TransactionTestBase : public ::testing::Test {
     } else {
       s = OpenWithStackableDB();
     }
+    assert(db != nullptr);
     return s;
   }
 
@@ -184,15 +187,17 @@ class TransactionTestBase : public ::testing::Test {
         txn_db_options.write_policy == WRITE_PREPARED;
     Status s = DBImpl::Open(options_copy, dbname, column_families, &handles,
                             &root_db, use_seq_per_batch, use_batch_per_txn);
-    StackableDB* stackable_db = new StackableDB(root_db);
-    if (s.ok()) {
-      assert(root_db != nullptr);
-      assert(handles.size() == 1);
-      s = TransactionDB::WrapStackableDB(stackable_db, txn_db_options,
-                                         compaction_enabled_cf_indices, handles,
-                                         &db);
-      delete handles[0];
+    if (!s.ok()) {
+      delete root_db;
+      return s;
     }
+    StackableDB* stackable_db = new StackableDB(root_db);
+    assert(root_db != nullptr);
+    assert(handles.size() == 1);
+    s = TransactionDB::WrapStackableDB(stackable_db, txn_db_options,
+                                       compaction_enabled_cf_indices, handles,
+                                       &db);
+    delete handles[0];
     if (!s.ok()) {
       delete stackable_db;
       // just in case it was not deleted (and not set to nullptr).
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_util.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_util.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_util.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_util.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_util.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_util.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/transaction_util.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/transaction_util.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_transaction_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_transaction_test.cc
similarity index 94%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_transaction_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_transaction_test.cc
index 391d58defd..1d645d237f 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_transaction_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_transaction_test.cc
@@ -731,6 +731,71 @@ TEST_P(WritePreparedTransactionTest, MaybeUpdateOldCommitMap) {
   MaybeUpdateOldCommitMapTestWithNext(p, c, s, ns, false);
 }
 
+// Reproduce the bug with two snapshots with the same seuqence number and test
+// that the release of the first snapshot will not affect the reads by the other
+// snapshot
+TEST_P(WritePreparedTransactionTest, DoubleSnapshot) {
+  TransactionOptions txn_options;
+  Status s;
+
+  // Insert initial value
+  ASSERT_OK(db->Put(WriteOptions(), "key", "value1"));
+
+  WritePreparedTxnDB* wp_db = dynamic_cast<WritePreparedTxnDB*>(db);
+  Transaction* txn =
+      wp_db->BeginTransaction(WriteOptions(), txn_options, nullptr);
+  ASSERT_OK(txn->SetName("txn"));
+  ASSERT_OK(txn->Put("key", "value2"));
+  ASSERT_OK(txn->Prepare());
+  // Three snapshots with the same seq number
+  const Snapshot* snapshot0 = wp_db->GetSnapshot();
+  const Snapshot* snapshot1 = wp_db->GetSnapshot();
+  const Snapshot* snapshot2 = wp_db->GetSnapshot();
+  ASSERT_OK(txn->Commit());
+  SequenceNumber cache_size = wp_db->COMMIT_CACHE_SIZE;
+  SequenceNumber overlap_seq = txn->GetId() + cache_size;
+  delete txn;
+
+  // 4th snapshot with a larger seq
+  const Snapshot* snapshot3 = wp_db->GetSnapshot();
+  // Cause an eviction to advance max evicted seq number
+  // This also fetches the 4 snapshots from db since their seq is lower than the
+  // new max
+  wp_db->AddCommitted(overlap_seq, overlap_seq);
+
+  ReadOptions ropt;
+  // It should see the value before commit
+  ropt.snapshot = snapshot2;
+  PinnableSlice pinnable_val;
+  s = wp_db->Get(ropt, wp_db->DefaultColumnFamily(), "key", &pinnable_val);
+  ASSERT_OK(s);
+  ASSERT_TRUE(pinnable_val == "value1");
+  pinnable_val.Reset();
+
+  wp_db->ReleaseSnapshot(snapshot1);
+
+  // It should still see the value before commit
+  s = wp_db->Get(ropt, wp_db->DefaultColumnFamily(), "key", &pinnable_val);
+  ASSERT_OK(s);
+  ASSERT_TRUE(pinnable_val == "value1");
+  pinnable_val.Reset();
+
+  // Cause an eviction to advance max evicted seq number and trigger updating
+  // the snapshot list
+  overlap_seq += cache_size;
+  wp_db->AddCommitted(overlap_seq, overlap_seq);
+
+  // It should still see the value before commit
+  s = wp_db->Get(ropt, wp_db->DefaultColumnFamily(), "key", &pinnable_val);
+  ASSERT_OK(s);
+  ASSERT_TRUE(pinnable_val == "value1");
+  pinnable_val.Reset();
+
+  wp_db->ReleaseSnapshot(snapshot0);
+  wp_db->ReleaseSnapshot(snapshot2);
+  wp_db->ReleaseSnapshot(snapshot3);
+}
+
 // Test that the entries in old_commit_map_ get garbage collected properly
 TEST_P(WritePreparedTransactionTest, OldCommitMapGC) {
   const size_t snapshot_cache_bits = 0;
@@ -816,6 +881,7 @@ TEST_P(WritePreparedTransactionTest, CheckAgainstSnapshotsTest) {
   std::vector<SequenceNumber> snapshots = {100l, 200l, 300l, 400l, 500l,
                                            600l, 700l, 800l, 900l};
   const size_t snapshot_cache_bits = 2;
+  const uint64_t cache_size = 1ul << snapshot_cache_bits;
   // Safety check to express the intended size in the test. Can be adjusted if
   // the snapshots lists changed.
   assert((1ul << snapshot_cache_bits) * 2 + 1 == snapshots.size());
@@ -843,6 +909,57 @@ TEST_P(WritePreparedTransactionTest, CheckAgainstSnapshotsTest) {
                          commit_entry.prep_seq <= snapshots.back();
     ASSERT_EQ(expect_update, !wp_db->old_commit_map_empty_);
   }
+
+  // Test that search will include multiple snapshot from snapshot cache
+  {
+    // exclude first and last item in the cache
+    CommitEntry commit_entry = {snapshots.front() + 1,
+                                snapshots[cache_size - 1] - 1};
+    wp_db->old_commit_map_empty_ = true;  // reset
+    wp_db->old_commit_map_.clear();
+    wp_db->CheckAgainstSnapshots(commit_entry);
+    ASSERT_EQ(wp_db->old_commit_map_.size(), cache_size - 2);
+  }
+
+  // Test that search will include multiple snapshot from old snapshots
+  {
+    // include two in the middle
+    CommitEntry commit_entry = {snapshots[cache_size] + 1,
+                                snapshots[cache_size + 2] + 1};
+    wp_db->old_commit_map_empty_ = true;  // reset
+    wp_db->old_commit_map_.clear();
+    wp_db->CheckAgainstSnapshots(commit_entry);
+    ASSERT_EQ(wp_db->old_commit_map_.size(), 2);
+  }
+
+  // Test that search will include both snapshot cache and old snapshots
+  // Case 1: includes all in snapshot cache
+  {
+    CommitEntry commit_entry = {snapshots.front() - 1, snapshots.back() + 1};
+    wp_db->old_commit_map_empty_ = true;  // reset
+    wp_db->old_commit_map_.clear();
+    wp_db->CheckAgainstSnapshots(commit_entry);
+    ASSERT_EQ(wp_db->old_commit_map_.size(), snapshots.size());
+  }
+
+  // Case 2: includes all snapshot caches except the smallest
+  {
+    CommitEntry commit_entry = {snapshots.front() + 1, snapshots.back() + 1};
+    wp_db->old_commit_map_empty_ = true;  // reset
+    wp_db->old_commit_map_.clear();
+    wp_db->CheckAgainstSnapshots(commit_entry);
+    ASSERT_EQ(wp_db->old_commit_map_.size(), snapshots.size() - 1);
+  }
+
+  // Case 3: includes only the largest of snapshot cache
+  {
+    CommitEntry commit_entry = {snapshots[cache_size - 1] - 1,
+                                snapshots.back() + 1};
+    wp_db->old_commit_map_empty_ = true;  // reset
+    wp_db->old_commit_map_.clear();
+    wp_db->CheckAgainstSnapshots(commit_entry);
+    ASSERT_EQ(wp_db->old_commit_map_.size(), snapshots.size() - cache_size + 1);
+  }
 }
 
 // This test is too slow for travis
@@ -1015,6 +1132,7 @@ TEST_P(WritePreparedTransactionTest, AdvanceMaxEvictedSeqWithDuplicatesTest) {
   wp_db->db_impl_->FlushWAL(true);
   wp_db->TEST_Crash();
   ReOpenNoDelete();
+  assert(db != nullptr);
   wp_db = dynamic_cast<WritePreparedTxnDB*>(db);
   wp_db->AdvanceMaxEvictedSeq(0, new_max);
   s = db->Get(ropt, db->DefaultColumnFamily(), "key", &pinnable_val);
@@ -1146,6 +1264,7 @@ TEST_P(SeqAdvanceConcurrentTest, SeqAdvanceConcurrentTest) {
     // Check if recovery preserves the last sequence number
     db_impl->FlushWAL(true);
     ReOpenNoDelete();
+    assert(db != nullptr);
     db_impl = reinterpret_cast<DBImpl*>(db->GetRootDB());
     seq = db_impl->TEST_GetLastVisibleSequence();
     ASSERT_EQ(exp_seq, seq);
@@ -1158,6 +1277,7 @@ TEST_P(SeqAdvanceConcurrentTest, SeqAdvanceConcurrentTest) {
     // Check if recovery after flush preserves the last sequence number
     db_impl->FlushWAL(true);
     ReOpenNoDelete();
+    assert(db != nullptr);
     db_impl = reinterpret_cast<DBImpl*>(db->GetRootDB());
     seq = db_impl->GetLatestSequenceNumber();
     ASSERT_EQ(exp_seq, seq);
@@ -1212,6 +1332,7 @@ TEST_P(WritePreparedTransactionTest, BasicRecoveryTest) {
   wp_db->db_impl_->FlushWAL(true);
   wp_db->TEST_Crash();
   ReOpenNoDelete();
+  assert(db != nullptr);
   wp_db = dynamic_cast<WritePreparedTxnDB*>(db);
   // After recovery, all the uncommitted txns (0 and 1) should be inserted into
   // delayed_prepared_
@@ -1256,6 +1377,7 @@ TEST_P(WritePreparedTransactionTest, BasicRecoveryTest) {
   wp_db->db_impl_->FlushWAL(true);
   wp_db->TEST_Crash();
   ReOpenNoDelete();
+  assert(db != nullptr);
   wp_db = dynamic_cast<WritePreparedTxnDB*>(db);
   ASSERT_TRUE(wp_db->prepared_txns_.empty());
   ASSERT_FALSE(wp_db->delayed_prepared_empty_);
@@ -1290,6 +1412,7 @@ TEST_P(WritePreparedTransactionTest, BasicRecoveryTest) {
   delete txn2;
   wp_db->db_impl_->FlushWAL(true);
   ReOpenNoDelete();
+  assert(db != nullptr);
   wp_db = dynamic_cast<WritePreparedTxnDB*>(db);
   ASSERT_TRUE(wp_db->prepared_txns_.empty());
   ASSERT_TRUE(wp_db->delayed_prepared_empty_);
@@ -1301,55 +1424,6 @@ TEST_P(WritePreparedTransactionTest, BasicRecoveryTest) {
   pinnable_val.Reset();
 }
 
-// After recovery the new transactions should still conflict with recovered
-// transactions.
-TEST_P(WritePreparedTransactionTest, ConflictDetectionAfterRecoveryTest) {
-  options.disable_auto_compactions = true;
-  ReOpen();
-
-  TransactionOptions txn_options;
-  WriteOptions write_options;
-  size_t index = 0;
-  Transaction* txn0 = db->BeginTransaction(write_options, txn_options);
-  auto istr0 = std::to_string(index);
-  auto s = txn0->SetName("xid" + istr0);
-  ASSERT_OK(s);
-  s = txn0->Put(Slice("key" + istr0), Slice("bar0" + istr0));
-  ASSERT_OK(s);
-  s = txn0->Prepare();
-
-  // With the same index 0 and key prefix, txn_t0 should conflict with txn0
-  txn_t0_with_status(0, Status::TimedOut());
-  delete txn0;
-
-  auto db_impl = reinterpret_cast<DBImpl*>(db->GetRootDB());
-  db_impl->FlushWAL(true);
-  dynamic_cast<WritePreparedTxnDB*>(db)->TEST_Crash();
-  ReOpenNoDelete();
-
-  // It should still conflict after the recovery
-  txn_t0_with_status(0, Status::TimedOut());
-
-  db_impl = reinterpret_cast<DBImpl*>(db->GetRootDB());
-  db_impl->FlushWAL(true);
-  ReOpenNoDelete();
-
-  // Check that a recovered txn will still cause conflicts after 2nd recovery
-  txn_t0_with_status(0, Status::TimedOut());
-
-  txn0 = db->GetTransactionByName("xid" + istr0);
-  ASSERT_NE(txn0, nullptr);
-  txn0->Commit();
-  delete txn0;
-
-  db_impl = reinterpret_cast<DBImpl*>(db->GetRootDB());
-  db_impl->FlushWAL(true);
-  ReOpenNoDelete();
-
-  // tnx0 is now committed and should no longer cause a conflict
-  txn_t0_with_status(0, Status::OK());
-}
-
 // After recovery the commit map is empty while the max is set. The code would
 // go through a different path which requires a separate test.
 TEST_P(WritePreparedTransactionTest, IsInSnapshotEmptyMapTest) {
@@ -1590,6 +1664,7 @@ TEST_P(WritePreparedTransactionTest, RollbackTest) {
           db_impl->FlushWAL(true);
           dynamic_cast<WritePreparedTxnDB*>(db)->TEST_Crash();
           ReOpenNoDelete();
+          assert(db != nullptr);
           wp_db = dynamic_cast<WritePreparedTxnDB*>(db);
           txn = db->GetTransactionByName("xid0");
           ASSERT_FALSE(wp_db->delayed_prepared_empty_);
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_txn.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_txn.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_txn.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_txn.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_txn.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_txn.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_txn.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_txn.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_txn_db.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_txn_db.cc
similarity index 91%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_txn_db.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_txn_db.cc
index 34ed04aa67..ca728d5071 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_txn_db.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_txn_db.cc
@@ -379,9 +379,9 @@ void WritePreparedTxnDB::Init(const TransactionDBOptions& /* unused */) {
   // around.
   INC_STEP_FOR_MAX_EVICTED =
       std::max(COMMIT_CACHE_SIZE / 100, static_cast<size_t>(1));
-  snapshot_cache_ = unique_ptr<std::atomic<SequenceNumber>[]>(
+  snapshot_cache_ = std::unique_ptr<std::atomic<SequenceNumber>[]>(
       new std::atomic<SequenceNumber>[SNAPSHOT_CACHE_SIZE] {});
-  commit_cache_ = unique_ptr<std::atomic<CommitEntry64b>[]>(
+  commit_cache_ = std::unique_ptr<std::atomic<CommitEntry64b>[]>(
       new std::atomic<CommitEntry64b>[COMMIT_CACHE_SIZE] {});
 }
 
@@ -460,7 +460,7 @@ void WritePreparedTxnDB::RemovePrepared(const uint64_t prepare_seq,
 bool WritePreparedTxnDB::GetCommitEntry(const uint64_t indexed_seq,
                                         CommitEntry64b* entry_64b,
                                         CommitEntry* entry) const {
-  *entry_64b = commit_cache_[indexed_seq].load(std::memory_order_acquire);
+  *entry_64b = commit_cache_[static_cast<size_t>(indexed_seq)].load(std::memory_order_acquire);
   bool valid = entry_64b->Parse(indexed_seq, entry, FORMAT);
   return valid;
 }
@@ -469,7 +469,7 @@ bool WritePreparedTxnDB::AddCommitEntry(const uint64_t indexed_seq,
                                         const CommitEntry& new_entry,
                                         CommitEntry* evicted_entry) {
   CommitEntry64b new_entry_64b(new_entry, FORMAT);
-  CommitEntry64b evicted_entry_64b = commit_cache_[indexed_seq].exchange(
+  CommitEntry64b evicted_entry_64b = commit_cache_[static_cast<size_t>(indexed_seq)].exchange(
       new_entry_64b, std::memory_order_acq_rel);
   bool valid = evicted_entry_64b.Parse(indexed_seq, evicted_entry, FORMAT);
   return valid;
@@ -478,7 +478,7 @@ bool WritePreparedTxnDB::AddCommitEntry(const uint64_t indexed_seq,
 bool WritePreparedTxnDB::ExchangeCommitEntry(const uint64_t indexed_seq,
                                              CommitEntry64b& expected_entry_64b,
                                              const CommitEntry& new_entry) {
-  auto& atomic_entry = commit_cache_[indexed_seq];
+  auto& atomic_entry = commit_cache_[static_cast<size_t>(indexed_seq)];
   CommitEntry64b new_entry_64b(new_entry, FORMAT);
   bool succ = atomic_entry.compare_exchange_strong(
       expected_entry_64b, new_entry_64b, std::memory_order_acq_rel,
@@ -554,12 +554,6 @@ const std::vector<SequenceNumber> WritePreparedTxnDB::GetSnapshotListFromDB(
   return db_impl_->snapshots().GetAll(nullptr, max);
 }
 
-void WritePreparedTxnDB::ReleaseSnapshot(const Snapshot* snapshot) {
-  auto snap_seq = snapshot->GetSequenceNumber();
-  ReleaseSnapshotInternal(snap_seq);
-  db_impl_->ReleaseSnapshot(snapshot);
-}
-
 void WritePreparedTxnDB::ReleaseSnapshotInternal(
     const SequenceNumber snap_seq) {
   // relax is enough since max increases monotonically, i.e., if snap_seq <
@@ -572,14 +566,16 @@ void WritePreparedTxnDB::ReleaseSnapshotInternal(
     bool need_gc = false;
     {
       WPRecordTick(TXN_OLD_COMMIT_MAP_MUTEX_OVERHEAD);
-      ROCKS_LOG_WARN(info_log_, "old_commit_map_mutex_ overhead");
+      ROCKS_LOG_WARN(info_log_, "old_commit_map_mutex_ overhead for %" PRIu64,
+                     snap_seq);
       ReadLock rl(&old_commit_map_mutex_);
       auto prep_set_entry = old_commit_map_.find(snap_seq);
       need_gc = prep_set_entry != old_commit_map_.end();
     }
     if (need_gc) {
       WPRecordTick(TXN_OLD_COMMIT_MAP_MUTEX_OVERHEAD);
-      ROCKS_LOG_WARN(info_log_, "old_commit_map_mutex_ overhead");
+      ROCKS_LOG_WARN(info_log_, "old_commit_map_mutex_ overhead for %" PRIu64,
+                     snap_seq);
       WriteLock wl(&old_commit_map_mutex_);
       old_commit_map_.erase(snap_seq);
       old_commit_map_empty_.store(old_commit_map_.empty(),
@@ -588,6 +584,33 @@ void WritePreparedTxnDB::ReleaseSnapshotInternal(
   }
 }
 
+void WritePreparedTxnDB::CleanupReleasedSnapshots(
+    const std::vector<SequenceNumber>& new_snapshots,
+    const std::vector<SequenceNumber>& old_snapshots) {
+  auto newi = new_snapshots.begin();
+  auto oldi = old_snapshots.begin();
+  for (; newi != new_snapshots.end() && oldi != old_snapshots.end();) {
+    assert(*newi >= *oldi);  // cannot have new snapshots with lower seq
+    if (*newi == *oldi) {    // still not released
+      auto value = *newi;
+      while (newi != new_snapshots.end() && *newi == value) {
+        newi++;
+      }
+      while (oldi != old_snapshots.end() && *oldi == value) {
+        oldi++;
+      }
+    } else {
+      assert(*newi > *oldi);  // *oldi is released
+      ReleaseSnapshotInternal(*oldi);
+      oldi++;
+    }
+  }
+  // Everything remained in old_snapshots is released and must be cleaned up
+  for (; oldi != old_snapshots.end(); oldi++) {
+    ReleaseSnapshotInternal(*oldi);
+  }
+}
+
 void WritePreparedTxnDB::UpdateSnapshots(
     const std::vector<SequenceNumber>& snapshots,
     const SequenceNumber& version) {
@@ -636,6 +659,12 @@ void WritePreparedTxnDB::UpdateSnapshots(
   // Update the size at the end. Otherwise a parallel reader might read
   // items that are not set yet.
   snapshots_total_.store(snapshots.size(), std::memory_order_release);
+
+  // Note: this must be done after the snapshots data structures are updated
+  // with the new list of snapshots.
+  CleanupReleasedSnapshots(snapshots, snapshots_all_);
+  snapshots_all_ = snapshots;
+
   TEST_SYNC_POINT("WritePreparedTxnDB::UpdateSnapshots:p:end");
   TEST_SYNC_POINT("WritePreparedTxnDB::UpdateSnapshots:s:end");
 }
@@ -654,13 +683,20 @@ void WritePreparedTxnDB::CheckAgainstSnapshots(const CommitEntry& evicted) {
   // place before gets overwritten the reader that reads bottom-up will
   // eventully see it.
   const bool next_is_larger = true;
-  SequenceNumber snapshot_seq = kMaxSequenceNumber;
+  // We will set to true if the border line snapshot suggests that.
+  bool search_larger_list = false;
   size_t ip1 = std::min(cnt, SNAPSHOT_CACHE_SIZE);
   for (; 0 < ip1; ip1--) {
-    snapshot_seq = snapshot_cache_[ip1 - 1].load(std::memory_order_acquire);
+    SequenceNumber snapshot_seq =
+        snapshot_cache_[ip1 - 1].load(std::memory_order_acquire);
     TEST_IDX_SYNC_POINT("WritePreparedTxnDB::CheckAgainstSnapshots:p:",
                         ++sync_i);
     TEST_IDX_SYNC_POINT("WritePreparedTxnDB::CheckAgainstSnapshots:s:", sync_i);
+    if (ip1 == SNAPSHOT_CACHE_SIZE) {  // border line snapshot
+      // snapshot_seq < commit_seq => larger_snapshot_seq <= commit_seq
+      // then later also continue the search to larger snapshots
+      search_larger_list = snapshot_seq < evicted.commit_seq;
+    }
     if (!MaybeUpdateOldCommitMap(evicted.prep_seq, evicted.commit_seq,
                                  snapshot_seq, !next_is_larger)) {
       break;
@@ -675,17 +711,20 @@ void WritePreparedTxnDB::CheckAgainstSnapshots(const CommitEntry& evicted) {
 #endif
   TEST_SYNC_POINT("WritePreparedTxnDB::CheckAgainstSnapshots:p:end");
   TEST_SYNC_POINT("WritePreparedTxnDB::CheckAgainstSnapshots:s:end");
-  if (UNLIKELY(SNAPSHOT_CACHE_SIZE < cnt && ip1 == SNAPSHOT_CACHE_SIZE &&
-               snapshot_seq < evicted.prep_seq)) {
+  if (UNLIKELY(SNAPSHOT_CACHE_SIZE < cnt && search_larger_list)) {
     // Then access the less efficient list of snapshots_
     WPRecordTick(TXN_SNAPSHOT_MUTEX_OVERHEAD);
-    ROCKS_LOG_WARN(info_log_, "snapshots_mutex_ overhead");
+    ROCKS_LOG_WARN(info_log_,
+                   "snapshots_mutex_ overhead for <%" PRIu64 ",%" PRIu64
+                   "> with %" ROCKSDB_PRIszt " snapshots",
+                   evicted.prep_seq, evicted.commit_seq, cnt);
     ReadLock rl(&snapshots_mutex_);
     // Items could have moved from the snapshots_ to snapshot_cache_ before
     // accquiring the lock. To make sure that we do not miss a valid snapshot,
     // read snapshot_cache_ again while holding the lock.
     for (size_t i = 0; i < SNAPSHOT_CACHE_SIZE; i++) {
-      snapshot_seq = snapshot_cache_[i].load(std::memory_order_acquire);
+      SequenceNumber snapshot_seq =
+          snapshot_cache_[i].load(std::memory_order_acquire);
       if (!MaybeUpdateOldCommitMap(evicted.prep_seq, evicted.commit_seq,
                                    snapshot_seq, next_is_larger)) {
         break;
@@ -713,7 +752,10 @@ bool WritePreparedTxnDB::MaybeUpdateOldCommitMap(
   // then snapshot_seq < commit_seq
   if (prep_seq <= snapshot_seq) {  // overlapping range
     WPRecordTick(TXN_OLD_COMMIT_MAP_MUTEX_OVERHEAD);
-    ROCKS_LOG_WARN(info_log_, "old_commit_map_mutex_ overhead");
+    ROCKS_LOG_WARN(info_log_,
+                   "old_commit_map_mutex_ overhead for %" PRIu64
+                   " commit entry: <%" PRIu64 ",%" PRIu64 ">",
+                   snapshot_seq, prep_seq, commit_seq);
     WriteLock wl(&old_commit_map_mutex_);
     old_commit_map_empty_.store(false, std::memory_order_release);
     auto& vec = old_commit_map_[snapshot_seq];
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_txn_db.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_txn_db.h
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_txn_db.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_txn_db.h
index ec76e27163..e0263d4f7b 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_prepared_txn_db.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_prepared_txn_db.h
@@ -112,8 +112,6 @@ class WritePreparedTxnDB : public PessimisticTransactionDB {
       const std::vector<ColumnFamilyHandle*>& column_families,
       std::vector<Iterator*>* iterators) override;
 
-  virtual void ReleaseSnapshot(const Snapshot* snapshot) override;
-
   // Check whether the transaction that wrote the value with sequence number seq
   // is visible to the snapshot with sequence number snapshot_seq.
   // Returns true if commit_seq <= snapshot_seq
@@ -222,7 +220,6 @@ class WritePreparedTxnDB : public PessimisticTransactionDB {
       // rare case and it is ok to pay the cost of mutex ReadLock for such old,
       // reading transactions.
       WPRecordTick(TXN_OLD_COMMIT_MAP_MUTEX_OVERHEAD);
-      ROCKS_LOG_WARN(info_log_, "old_commit_map_mutex_ overhead");
       ReadLock rl(&old_commit_map_mutex_);
       auto prep_set_entry = old_commit_map_.find(snapshot_seq);
       bool found = prep_set_entry != old_commit_map_.end();
@@ -380,6 +377,7 @@ class WritePreparedTxnDB : public PessimisticTransactionDB {
   friend class
       WritePreparedTransactionTest_AdvanceMaxEvictedSeqWithDuplicatesTest_Test;
   friend class WritePreparedTransactionTest_BasicRecoveryTest_Test;
+  friend class WritePreparedTransactionTest_DoubleSnapshot_Test;
   friend class WritePreparedTransactionTest_IsInSnapshotEmptyMapTest_Test;
   friend class WritePreparedTransactionTest_OldCommitMapGC_Test;
   friend class WritePreparedTransactionTest_RollbackTest_Test;
@@ -519,6 +517,11 @@ class WritePreparedTxnDB : public PessimisticTransactionDB {
   // version value.
   void UpdateSnapshots(const std::vector<SequenceNumber>& snapshots,
                        const SequenceNumber& version);
+  // Check the new list of new snapshots against the old one to see  if any of
+  // the snapshots are released and to do the cleanup for the released snapshot.
+  void CleanupReleasedSnapshots(
+      const std::vector<SequenceNumber>& new_snapshots,
+      const std::vector<SequenceNumber>& old_snapshots);
 
   // Check an evicted entry against live snapshots to see if it should be kept
   // around or it can be safely discarded (and hence assume committed for all
@@ -549,10 +552,14 @@ class WritePreparedTxnDB : public PessimisticTransactionDB {
   static const size_t DEF_SNAPSHOT_CACHE_BITS = static_cast<size_t>(7);
   const size_t SNAPSHOT_CACHE_BITS;
   const size_t SNAPSHOT_CACHE_SIZE;
-  unique_ptr<std::atomic<SequenceNumber>[]> snapshot_cache_;
+  std::unique_ptr<std::atomic<SequenceNumber>[]> snapshot_cache_;
   // 2nd list for storing snapshots. The list sorted in ascending order.
   // Thread-safety is provided with snapshots_mutex_.
   std::vector<SequenceNumber> snapshots_;
+  // The list of all snapshots: snapshots_ + snapshot_cache_. This list although
+  // redundant but simplifies CleanupOldSnapshots implementation.
+  // Thread-safety is provided with snapshots_mutex_.
+  std::vector<SequenceNumber> snapshots_all_;
   // The version of the latest list of snapshots. This can be used to avoid
   // rewriting a list that is concurrently updated with a more recent version.
   SequenceNumber snapshots_version_ = 0;
@@ -567,7 +574,7 @@ class WritePreparedTxnDB : public PessimisticTransactionDB {
   const CommitEntry64bFormat FORMAT;
   // commit_cache_ must be initialized to zero to tell apart an empty index from
   // a filled one. Thread-safety is provided with commit_cache_mutex_.
-  unique_ptr<std::atomic<CommitEntry64b>[]> commit_cache_;
+  std::unique_ptr<std::atomic<CommitEntry64b>[]> commit_cache_;
   // The largest evicted *commit* sequence number from the commit_cache_. If a
   // seq is smaller than max_evicted_seq_ is might or might not be present in
   // commit_cache_. So commit_cache_ must first be checked before consulting
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_transaction_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_transaction_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_transaction_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_transaction_test.cc
index 8ec7f6bfba..009991bb7c 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_transaction_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_transaction_test.cc
@@ -250,7 +250,7 @@ TEST_P(WriteUnpreparedTransactionTest, RecoveryTest) {
           wup_db->db_impl_->FlushWAL(true);
           wup_db->TEST_Crash();
           ReOpenNoDelete();
-          wup_db = dynamic_cast<WriteUnpreparedTxnDB*>(db);
+          assert(db != nullptr);
 
           db->GetAllPreparedTransactions(&prepared_trans);
           ASSERT_EQ(prepared_trans.size(), a == UNPREPARED ? 0 : 1);
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_txn.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_txn.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_txn.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_txn.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_txn.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_txn.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_txn.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_txn.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_txn_db.cc b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_txn_db.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_txn_db.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_txn_db.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_txn_db.h b/3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_txn_db.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/transactions/write_unprepared_txn_db.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/transactions/write_unprepared_txn_db.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/ttl/db_ttl_impl.cc b/3rdParty/rocksdb/v5.18.X/utilities/ttl/db_ttl_impl.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/ttl/db_ttl_impl.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/ttl/db_ttl_impl.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/ttl/db_ttl_impl.h b/3rdParty/rocksdb/v5.18.X/utilities/ttl/db_ttl_impl.h
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/ttl/db_ttl_impl.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/ttl/db_ttl_impl.h
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/ttl/ttl_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/ttl/ttl_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/ttl/ttl_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/ttl/ttl_test.cc
index ee7b317aaf..f434d18570 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/ttl/ttl_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/ttl/ttl_test.cc
@@ -370,14 +370,14 @@ class TtlTest : public testing::Test {
   static const int64_t kSampleSize_ = 100;
   std::string dbname_;
   DBWithTTL* db_ttl_;
-  unique_ptr<SpecialTimeEnv> env_;
+  std::unique_ptr<SpecialTimeEnv> env_;
 
  private:
   Options options_;
   KVMap kvmap_;
   KVMap::iterator kv_it_;
   const std::string kNewValue_ = "new_value";
-  unique_ptr<CompactionFilter> test_comp_filter_;
+  std::unique_ptr<CompactionFilter> test_comp_filter_;
 }; // class TtlTest
 
 // If TTL is non positive or not provided, the behaviour is TTL = infinity
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/util_merge_operators_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/util_merge_operators_test.cc
similarity index 100%
rename from 3rdParty/rocksdb/v5.16.X/utilities/util_merge_operators_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/util_merge_operators_test.cc
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index.cc b/3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index.cc
similarity index 97%
rename from 3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index.cc
index 52eb700246..2202d6baf7 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index.cc
@@ -352,14 +352,16 @@ class WBWIIteratorImpl : public WBWIIterator {
   }
 
   virtual void SeekToFirst() override {
-    WriteBatchIndexEntry search_entry(WriteBatchIndexEntry::kFlagMin,
-                                      column_family_id_, 0, 0);
+    WriteBatchIndexEntry search_entry(
+        nullptr /* search_key */, column_family_id_,
+        true /* is_forward_direction */, true /* is_seek_to_first */);
     skip_list_iter_.Seek(&search_entry);
   }
 
   virtual void SeekToLast() override {
-    WriteBatchIndexEntry search_entry(WriteBatchIndexEntry::kFlagMin,
-                                      column_family_id_ + 1, 0, 0);
+    WriteBatchIndexEntry search_entry(
+        nullptr /* search_key */, column_family_id_ + 1,
+        true /* is_forward_direction */, true /* is_seek_to_first */);
     skip_list_iter_.Seek(&search_entry);
     if (!skip_list_iter_.Valid()) {
       skip_list_iter_.SeekToLast();
@@ -369,12 +371,16 @@ class WBWIIteratorImpl : public WBWIIterator {
   }
 
   virtual void Seek(const Slice& key) override {
-    WriteBatchIndexEntry search_entry(&key, column_family_id_);
+    WriteBatchIndexEntry search_entry(&key, column_family_id_,
+                                      true /* is_forward_direction */,
+                                      false /* is_seek_to_first */);
     skip_list_iter_.Seek(&search_entry);
   }
 
   virtual void SeekForPrev(const Slice& key) override {
-    WriteBatchIndexEntry search_entry(&key, column_family_id_);
+    WriteBatchIndexEntry search_entry(&key, column_family_id_,
+                                      false /* is_forward_direction */,
+                                      false /* is_seek_to_first */);
     skip_list_iter_.SeekForPrev(&search_entry);
   }
 
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index_internal.cc b/3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index_internal.cc
similarity index 89%
rename from 3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index_internal.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index_internal.cc
index 14e5f2147d..243672ce4d 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index_internal.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index_internal.cc
@@ -85,6 +85,20 @@ Status ReadableWriteBatch::GetEntryFromDataOffset(size_t data_offset,
   return Status::OK();
 }
 
+// If both of `entry1` and `entry2` point to real entry in write batch, we
+// compare the entries as following:
+// 1. first compare the column family, the one with larger CF will be larger;
+// 2. Inside the same CF, we first decode the entry to find the key of the entry
+//    and the entry with larger key will be larger;
+// 3. If two entries are of the same CF and offset, the one with larger offset
+//    will be larger.
+// Some times either `entry1` or `entry2` is dummy entry, which is actually
+// a search key. In this case, in step 2, we don't go ahead and decode the
+// entry but use the value in WriteBatchIndexEntry::search_key.
+// One special case is WriteBatchIndexEntry::key_size is kFlagMinInCf.
+// This indicate that we are going to seek to the first of the column family.
+// Once we see this, this entry will be smaller than all the real entries of
+// the column family.
 int WriteBatchEntryComparator::operator()(
     const WriteBatchIndexEntry* entry1,
     const WriteBatchIndexEntry* entry2) const {
@@ -94,9 +108,10 @@ int WriteBatchEntryComparator::operator()(
     return -1;
   }
 
-  if (entry1->offset == WriteBatchIndexEntry::kFlagMin) {
+  // Deal with special case of seeking to the beginning of a column family
+  if (entry1->is_min_in_cf()) {
     return -1;
-  } else if (entry2->offset == WriteBatchIndexEntry::kFlagMin) {
+  } else if (entry2->is_min_in_cf()) {
     return 1;
   }
 
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index_internal.h b/3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index_internal.h
similarity index 61%
rename from 3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index_internal.h
rename to 3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index_internal.h
index ac20f1b862..3eed7c724c 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index_internal.h
+++ b/3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index_internal.h
@@ -31,21 +31,52 @@ struct WriteBatchIndexEntry {
         key_offset(ko),
         key_size(ksz),
         search_key(nullptr) {}
-  WriteBatchIndexEntry(const Slice* sk, uint32_t c)
-      : offset(0),
-        column_family(c),
+  // Create a dummy entry as the search key. This index entry won't be backed
+  // by an entry from the write batch, but a pointer to the search key. Or a
+  // special flag of offset can indicate we are seek to first.
+  // @_search_key: the search key
+  // @_column_family: column family
+  // @is_forward_direction: true for Seek(). False for SeekForPrev()
+  // @is_seek_to_first: true if we seek to the beginning of the column family
+  //                    _search_key should be null in this case.
+  WriteBatchIndexEntry(const Slice* _search_key, uint32_t _column_family,
+                       bool is_forward_direction, bool is_seek_to_first)
+      // For SeekForPrev(), we need to make the dummy entry larger than any
+      // entry who has the same search key. Otherwise, we'll miss those entries.
+      : offset(is_forward_direction ? 0 : port::kMaxSizet),
+        column_family(_column_family),
         key_offset(0),
-        key_size(0),
-        search_key(sk) {}
+        key_size(is_seek_to_first ? kFlagMinInCf : 0),
+        search_key(_search_key) {
+    assert(_search_key != nullptr || is_seek_to_first);
+  }
 
-  // If this flag appears in the offset, it indicates a key that is smaller
-  // than any other entry for the same column family
-  static const size_t kFlagMin = port::kMaxSizet;
+  // If this flag appears in the key_size, it indicates a
+  // key that is smaller than any other entry for the same column family.
+  static const size_t kFlagMinInCf = port::kMaxSizet;
 
-  size_t offset;           // offset of an entry in write batch's string buffer.
-  uint32_t column_family;  // column family of the entry.
+  bool is_min_in_cf() const {
+    assert(key_size != kFlagMinInCf ||
+           (key_offset == 0 && search_key == nullptr));
+    return key_size == kFlagMinInCf;
+  }
+
+  // offset of an entry in write batch's string buffer. If this is a dummy
+  // lookup key, in which case search_key != nullptr, offset is set to either
+  // 0 or max, only for comparison purpose. Because when entries have the same
+  // key, the entry with larger offset is larger, offset = 0 will make a seek
+  // key small or equal than all the entries with the seek key, so that Seek()
+  // will find all the entries of the same key. Similarly, offset = MAX will
+  // make the entry just larger than all entries with the search key so
+  // SeekForPrev() will see all the keys with the same key.
+  size_t offset;
+  uint32_t column_family;  // c1olumn family of the entry.
   size_t key_offset;       // offset of the key in write batch's string buffer.
-  size_t key_size;         // size of the key.
+  size_t key_size;         // size of the key. kFlagMinInCf indicates
+                           // that this is a dummy look up entry for
+                           // SeekToFirst() to the beginning of the column
+                           // family. We use the flag here to save a boolean
+                           // in the struct.
 
   const Slice* search_key;  // if not null, instead of reading keys from
                             // write batch, use it to compare. This is used
diff --git a/3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index_test.cc b/3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index_test.cc
similarity index 99%
rename from 3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index_test.cc
rename to 3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index_test.cc
index aa484cde99..d477968ca9 100644
--- a/3rdParty/rocksdb/v5.16.X/utilities/write_batch_with_index/write_batch_with_index_test.cc
+++ b/3rdParty/rocksdb/v5.18.X/utilities/write_batch_with_index/write_batch_with_index_test.cc
@@ -621,7 +621,7 @@ TEST_F(WriteBatchWithIndexTest, TestRandomIteraratorWithBase) {
     for (int i = 0; i < 128; i++) {
       // Random walk and make sure iter and result_iter returns the
       // same key and value
-      int type = rnd.Uniform(5);
+      int type = rnd.Uniform(6);
       ASSERT_OK(iter->status());
       switch (type) {
         case 0:
@@ -642,7 +642,15 @@ TEST_F(WriteBatchWithIndexTest, TestRandomIteraratorWithBase) {
           result_iter->Seek(key);
           break;
         }
-        case 3:
+        case 3: {
+          // SeekForPrev to random key
+          auto key_idx = rnd.Uniform(static_cast<int>(source_strings.size()));
+          auto key = source_strings[key_idx];
+          iter->SeekForPrev(key);
+          result_iter->SeekForPrev(key);
+          break;
+        }
+        case 4:
           // Next
           if (is_valid) {
             iter->Next();
@@ -652,7 +660,7 @@ TEST_F(WriteBatchWithIndexTest, TestRandomIteraratorWithBase) {
           }
           break;
         default:
-          assert(type == 4);
+          assert(type == 5);
           // Prev
           if (is_valid) {
             iter->Prev();
diff --git a/arangod/RocksDBEngine/RocksDBTransactionState.cpp b/arangod/RocksDBEngine/RocksDBTransactionState.cpp
index 2be51a4a46..0a81430675 100644
--- a/arangod/RocksDBEngine/RocksDBTransactionState.cpp
+++ b/arangod/RocksDBEngine/RocksDBTransactionState.cpp
@@ -327,7 +327,8 @@ arangodb::Result RocksDBTransactionState::internalCommit() {
     
     if (result.ok()) {
       TRI_ASSERT(numOps > 0); // simon: should hold unless we're being stupid
-      rocksdb::SequenceNumber postCommitSeq = _rocksTransaction->GetCommitedSeqNumber();
+      rocksdb::SequenceNumber postCommitSeq = _rocksTransaction->GetId();
+      TRI_ASSERT(postCommitSeq != 0);
       if (ADB_LIKELY(numOps > 0)) {
         postCommitSeq += numOps - 1; // add to get to the next batch
       }