Update version to 6.28.2

Summary: Update version to 6.28.2 for bug fix
Update circleci xcode version (#9405 )
2026-11-06 19:12:36 -05:00 · 2022-01-31 15:24:29 -08:00 · 2022-01-31 15:24:29 -08:00 · 2022-01-31 15:24:28 -08:00 · 2022-01-31 10:12:33 -08:00 · 2022-01-31 10:12:33 -08:00
881 changed files with 37979 additions and 69907 deletions
@@ -0,0 +1,54 @@
+#! /bin/bash
+
+# Work around issue with parallel make output causing random error, as in
+# make[1]: write error: stdout
+# Probably due to a kernel bug:
+#   https://bugs.launchpad.net/ubuntu/+source/linux-signed/+bug/1814393
+# Seems to affect image ubuntu-1604:201903-01 and ubuntu-1604:202004-01
+
+cd "$(dirname $0)"
+
+if [ ! -x cat_ignore_eagain.out ]; then
+    cc -x c -o cat_ignore_eagain.out - << EOF
+#include <unistd.h>
+#include <errno.h>
+#include <stdio.h>
+int main() {
+    int n, m, p;
+    char buf[1024];
+    for (;;) {
+        n = read(STDIN_FILENO, buf, 1024);
+        if (n > 0 && n <= 1024) {
+            for (m = 0; m < n;) {
+                p = write(STDOUT_FILENO, buf + m, n - m);
+                if (p < 0) {
+                    if (errno == EAGAIN) {
+                        // ignore but pause a bit
+                        usleep(100);
+                    } else {
+                        perror("write failed");
+                        return 42;
+                    }
+                } else {
+                    m += p;
+                }
+            }
+        } else if (n < 0) {
+            if (errno == EAGAIN) {
+                // ignore but pause a bit
+                usleep(100);
+            } else {
+                // Some non-ignorable error
+                perror("read failed");
+                return 43;
+            }
+        } else {
+            // EOF
+            return 0;
+        }
+    }
+}
+EOF
+fi
+
+exec ./cat_ignore_eagain.out
@@ -32,7 +32,7 @@ jobs:
    - name: Download clang-format-diff.py
      uses: wei/wget@v1
      with:
-        args: https://raw.githubusercontent.com/llvm/llvm-project/release/12.x/clang/tools/clang-format/clang-format-diff.py
+        args: https://raw.githubusercontent.com/llvm/llvm-project/main/clang/tools/clang-format/clang-format-diff.py

    - name: Check format
      run: VERBOSE_CHECK=1 make check-format
@@ -36,6 +36,7 @@ manifest_dump
 sst_dump
 blob_dump
 block_cache_trace_analyzer
+db_with_timestamp_basic_test
 tools/block_cache_analyzer/*.pyc
 column_aware_encoding_exp
 util/build_version.cc
@@ -51,6 +52,7 @@ rocksdb_dump
 rocksdb_undump
 db_test2
 trace_analyzer
+trace_analyzer_test
 block_cache_trace_analyzer
 io_tracer_parser
 .DS_Store
@@ -93,4 +95,3 @@ fuzz/proto/gen/
 fuzz/crash-*

 cmake-build-*
-third-party/folly/
@@ -43,18 +43,29 @@ env:
  - JOB_NAME=cmake-gcc9 # 3-5 minutes
  - JOB_NAME=cmake-gcc9-c++20 # 3-5 minutes
  - JOB_NAME=cmake-mingw # 3 minutes
+  - JOB_NAME=make-gcc4.8
+  - JOB_NAME=status_checked

 matrix:
  exclude:
  - os : linux
    arch: arm64
    env: JOB_NAME=cmake-mingw
+  - os : linux
+    arch: arm64
+    env: JOB_NAME=make-gcc4.8
  - os: linux
    arch: ppc64le
    env: JOB_NAME=cmake-mingw
+  - os: linux
+    arch: ppc64le
+    env: JOB_NAME=make-gcc4.8
  - os: linux
    arch: s390x
    env: JOB_NAME=cmake-mingw
+  - os: linux
+    arch: s390x
+    env: JOB_NAME=make-gcc4.8
  - os: linux
    compiler: clang
  - if: type = pull_request AND commit_message !~ /FULL_CI/
@@ -185,9 +196,20 @@ matrix:
    os: linux
    arch: s390x
    env: JOB_NAME=cmake-gcc9-c++20
+  - if: type = pull_request AND commit_message !~ /FULL_CI/
+    os : linux
+    arch: arm64
+    env: JOB_NAME=status_checked
+  - if: type = pull_request AND commit_message !~ /FULL_CI/
+    os: linux
+    arch: ppc64le
+    env: JOB_NAME=status_checked
+  - if: type = pull_request AND commit_message !~ /FULL_CI/
+    os: linux
+    arch: s390x
+    env: JOB_NAME=status_checked

 install:
-  -  CC=gcc-7 && CXX=g++-7
  - if [ "${JOB_NAME}" == cmake-gcc8 ]; then
      sudo apt-get install -y g++-8 || exit $?;
      CC=gcc-8 && CXX=g++-8;
@@ -199,8 +221,9 @@ install:
  - if [ "${JOB_NAME}" == cmake-mingw ]; then
      sudo apt-get install -y mingw-w64 || exit $?;
    fi
-  - if [ "${CXX}" == "g++-7" ]; then
-      sudo apt-get install -y g++-7 || exit $?;
+  - if [ "${JOB_NAME}" == make-gcc4.8 ]; then
+      sudo apt-get install -y g++-4.8 || exit $?;
+      CC=gcc-4.8 && CXX=g++-4.8;
    fi
  - |
    if [[ "${JOB_NAME}" == cmake* ]]; then
@@ -230,25 +253,21 @@ before_script:
 script:
  - date; ${CXX} --version
  - if [ `command -v ccache` ]; then ccache -C; fi
-  - export MK_PARALLEL=4;
-    if [[ "$TRAVIS_CPU_ARCH" == s390x ]]; then
-      export MK_PARALLEL=1;
-    fi
  - case $TEST_GROUP in
    platform_dependent)
-      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=only make -j$MK_PARALLEL all_but_some_tests check_some
+      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=only make -j4 all_but_some_tests check_some
      ;;
    1)
-      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_END=backup_engine_test make -j$MK_PARALLEL check_some
+      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_END=backupable_db_test make -j4 check_some
      ;;
    2)
-      OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" LIB_MODE=shared V=1 make -j$MK_PARALLEL tools && OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=backup_engine_test ROCKSDBTESTS_END=db_universal_compaction_test make -j$MK_PARALLEL check_some
+      OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" LIB_MODE=shared V=1 make -j4 tools && OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=backupable_db_test ROCKSDBTESTS_END=db_universal_compaction_test make -j4 check_some
      ;;
    3)
-      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=db_universal_compaction_test ROCKSDBTESTS_END=table_properties_collector_test make -j$MK_PARALLEL check_some
+      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=db_universal_compaction_test ROCKSDBTESTS_END=table_properties_collector_test make -j4 check_some
      ;;
    4)
-      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=table_properties_collector_test make -j$MK_PARALLEL check_some
+      OPT=-DTRAVIS LIB_MODE=shared V=1 ROCKSDBTESTS_PLATFORM_DEPENDENT=exclude ROCKSDBTESTS_START=table_properties_collector_test make -j4 check_some
      ;;
    esac
  - case $JOB_NAME in
@@ -256,10 +275,10 @@ script:
      OPT=-DTRAVIS LIB_MODE=shared V=1 make rocksdbjava jtest
      ;;
    lite_build)
-      OPT='-DTRAVIS -DROCKSDB_LITE' LIB_MODE=shared V=1 make -j$MK_PARALLEL all
+      OPT='-DTRAVIS -DROCKSDB_LITE' LIB_MODE=shared V=1 make -j4 all
      ;;
    examples)
-      OPT=-DTRAVIS LIB_MODE=shared V=1 make -j$MK_PARALLEL static_lib && cd examples && make -j$MK_PARALLEL
+      OPT=-DTRAVIS LIB_MODE=shared V=1 make -j4 static_lib && cd examples && make -j4
      ;;
    cmake-mingw)
      sudo update-alternatives --set x86_64-w64-mingw32-g++ /usr/bin/x86_64-w64-mingw32-g++-posix;
@@ -272,7 +291,13 @@ script:
          ;;
      esac

-      mkdir build && cd build && cmake -DCMAKE_BUILD_TYPE=Release -DWITH_TESTS=0 -DWITH_GFLAGS=0 -DWITH_BENCHMARK_TOOLS=0 -DWITH_TOOLS=0 -DWITH_CORE_TOOLS=1 .. && make -j$MK_PARALLEL && cd  .. && rm -rf build && mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_BUILD_TYPE=Release $OPT && make -j$MK_PARALLEL rocksdb rocksdbjni
+      mkdir build && cd build && cmake -DCMAKE_BUILD_TYPE=Release -DWITH_TESTS=0 -DWITH_GFLAGS=0 -DWITH_BENCHMARK_TOOLS=0 -DWITH_TOOLS=0 -DWITH_CORE_TOOLS=1 .. && make -j4 && cd  .. && rm -rf build && mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_BUILD_TYPE=Release $OPT && make -j4 rocksdb rocksdbjni
+      ;;
+    make-gcc4.8)
+      OPT=-DTRAVIS LIB_MODE=shared V=1 SKIP_LINK=1 make -j4 all && [ "Linking broken because libgflags compiled with newer ABI" ]
+      ;;
+    status_checked)
+      OPT=-DTRAVIS LIB_MODE=shared V=1 ASSERT_STATUS_CHECKED=1 make -j4 check_some
      ;;
    esac
 notifications:
@@ -2,7 +2,7 @@
 #     This cmake build is for Windows 64-bit only.
 #
 # Prerequisites:
-#     You must have at least Visual Studio 2019. Start the Developer Command Prompt window that is a part of Visual Studio installation.
+#     You must have at least Visual Studio 2015 Update 3. Start the Developer Command Prompt window that is a part of Visual Studio installation.
 #     Run the build commands from within the Developer Command Prompt window to have paths to the compiler and runtime libraries set.
 #     You must have git.exe in your %PATH% environment variable.
 #
@@ -14,7 +14,7 @@
 #        cd build
 # 3. Run cmake to generate project files for Windows, add more options to enable required third-party libraries.
 #    See thirdparty.inc for more information.
-#        sample command: cmake -G "Visual Studio 16 2019" -DCMAKE_BUILD_TYPE=Release -DWITH_GFLAGS=1 -DWITH_SNAPPY=1 -DWITH_JEMALLOC=1 -DWITH_JNI=1 ..
+#        sample command: cmake -G "Visual Studio 15 Win64" -DCMAKE_BUILD_TYPE=Release -DWITH_GFLAGS=1 -DWITH_SNAPPY=1 -DWITH_JEMALLOC=1 -DWITH_JNI=1 ..
 # 4. Then build the project in debug mode (you may want to add /m[:<N>] flag to run msbuild in <N> parallel threads
 #                                          or simply /m to use all avail cores)
 #        msbuild rocksdb.sln
@@ -27,7 +27,7 @@
 #
 # Linux:
 #
-# 1. Install a recent toolchain if you're on a older distro. C++17 required (GCC >= 7, Clang >= 5)
+# 1. Install a recent toolchain such as devtoolset-3 if you're on a older distro. C++11 required.
 # 2. mkdir build; cd build
 # 3. cmake ..
 # 4. make -j
@@ -40,8 +40,6 @@ include(GoogleTest)
 get_rocksdb_version(rocksdb_VERSION)
 project(rocksdb
  VERSION ${rocksdb_VERSION}
-  DESCRIPTION "An embeddable persistent key-value store for fast storage"
-  HOMEPAGE_URL https://rocksdb.org/
  LANGUAGES CXX C ASM)

 if(POLICY CMP0042)
@@ -80,8 +78,21 @@ if ($ENV{CIRCLECI})
  add_definitions(-DCIRCLECI)
 endif()

+# third-party/folly is only validated to work on Linux and Windows for now.
+# So only turn it on there by default.
+if(CMAKE_SYSTEM_NAME MATCHES "Linux|Windows")
+  if(MSVC AND MSVC_VERSION LESS 1910)
+    # Folly does not compile with MSVC older than VS2017
+    option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
+  else()
+    option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
+  endif()
+else()
+  option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
+endif()
+
 if( NOT DEFINED CMAKE_CXX_STANDARD )
-  set(CMAKE_CXX_STANDARD 17)
+  set(CMAKE_CXX_STANDARD 11)
 endif()

 include(CMakeDependentOption)
@@ -89,11 +100,7 @@ include(CMakeDependentOption)
 if(MSVC)
  option(WITH_GFLAGS "build with GFlags" OFF)
  option(WITH_XPRESS "build with windows built in compression" OFF)
-  option(ROCKSDB_SKIP_THIRDPARTY "skip thirdparty.inc" OFF)
-
-  if(NOT ROCKSDB_SKIP_THIRDPARTY)
-    include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
-  endif()
+  include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
 else()
  if(CMAKE_SYSTEM_NAME MATCHES "FreeBSD" AND NOT CMAKE_SYSTEM_NAME MATCHES "kFreeBSD")
    # FreeBSD has jemalloc as default malloc
@@ -175,6 +182,26 @@ else()
  endif()
 endif()

+string(TIMESTAMP TS "%Y-%m-%d %H:%M:%S" UTC)
+set(BUILD_DATE "${TS}" CACHE STRING "the time we first built rocksdb")
+
+find_package(Git)
+
+if(GIT_FOUND AND EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/.git")
+  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_SHA COMMAND "${GIT_EXECUTABLE}" rev-parse HEAD )
+  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" RESULT_VARIABLE GIT_MOD COMMAND "${GIT_EXECUTABLE}" diff-index HEAD --quiet)
+  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_DATE COMMAND "${GIT_EXECUTABLE}" log -1 --date=format:"%Y-%m-%d %T" --format="%ad")
+  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_TAG RESULT_VARIABLE rv COMMAND "${GIT_EXECUTABLE}" symbolic-ref -q --short HEAD OUTPUT_STRIP_TRAILING_WHITESPACE)
+  if (rv AND NOT rv EQUAL 0)
+    execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_TAG COMMAND "${GIT_EXECUTABLE}" describe --tags --exact-match OUTPUT_STRIP_TRAILING_WHITESPACE)
+  endif()
+else()
+  set(GIT_SHA 0)
+  set(GIT_MOD 1)
+endif()
+string(REGEX REPLACE "[^0-9a-fA-F]+" "" GIT_SHA "${GIT_SHA}")
+string(REGEX REPLACE "[^0-9: /-]+" "" GIT_DATE "${GIT_DATE}")
+
 option(WITH_MD_LIBRARY "build with MD" ON)
 if(WIN32 AND MSVC)
  if(WITH_MD_LIBRARY)
@@ -184,17 +211,20 @@ if(WIN32 AND MSVC)
  endif()
 endif()

+set(BUILD_VERSION_CC ${CMAKE_BINARY_DIR}/build_version.cc)
+configure_file(util/build_version.cc.in ${BUILD_VERSION_CC} @ONLY)
+
 if(MSVC)
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Zi /nologo /EHsc /GS /Gd /GR /GF /fp:precise /Zc:wchar_t /Zc:forScope /errorReport:queue")
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /W4 /wd4127 /wd4800 /wd4996 /wd4351 /wd4100 /wd4204 /wd4324")
 else()
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall -pthread")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers -Wno-strict-aliasing -Wno-invalid-offsetof")
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers -Wno-strict-aliasing")
  if(CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64")
    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Wstrict-prototypes")
  endif()
  if(MINGW)
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format")
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format -fno-asynchronous-unwind-tables")
    add_definitions(-D_POSIX_C_SOURCE=1)
  endif()
  if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
@@ -291,8 +321,7 @@ if(NOT MSVC)
  set(CMAKE_REQUIRED_FLAGS "-msse4.2 -mpclmul")
 endif()

-if (NOT PORTABLE OR FORCE_SSE42)
-  CHECK_CXX_SOURCE_COMPILES("
+CHECK_CXX_SOURCE_COMPILES("
 #include <cstdint>
 #include <nmmintrin.h>
 #include <wmmintrin.h>
@@ -304,17 +333,16 @@ int main() {
  auto d = _mm_cvtsi128_si64(c);
 }
 " HAVE_SSE42)
-  if(HAVE_SSE42)
-    add_definitions(-DHAVE_SSE42)
-    add_definitions(-DHAVE_PCLMUL)
-  elseif(FORCE_SSE42)
-    message(FATAL_ERROR "FORCE_SSE42=ON but unable to compile with SSE4.2 enabled")
-  endif()
+if(HAVE_SSE42)
+  add_definitions(-DHAVE_SSE42)
+  add_definitions(-DHAVE_PCLMUL)
+elseif(FORCE_SSE42)
+  message(FATAL_ERROR "FORCE_SSE42=ON but unable to compile with SSE4.2 enabled")
 endif()

 # Check if -latomic is required or not
 if (NOT MSVC)
-  set(CMAKE_REQUIRED_FLAGS "--std=c++17")
+  set(CMAKE_REQUIRED_FLAGS "--std=c++11")
  CHECK_CXX_SOURCE_COMPILES("
 #include <atomic>
 std::atomic<uint64_t> x(0);
@@ -324,23 +352,44 @@ int main() {
  return 0;
 }
 " BUILTIN_ATOMIC)
-  if (NOT BUILTIN_ATOMIC)
-    #TODO: Check if -latomic exists
-    list(APPEND THIRDPARTY_LIBS atomic)
-  endif()
+if (NOT BUILTIN_ATOMIC)
+  #TODO: Check if -latomic exists
+  list(APPEND THIRDPARTY_LIBS atomic)
+endif()
 endif()

 if (WITH_LIBURING)
-  find_package(uring)
-  if (uring_FOUND)
+  set(CMAKE_REQUIRED_FLAGS "-luring")
+  CHECK_CXX_SOURCE_COMPILES("
+#include <liburing.h>
+int main() {
+  struct io_uring ring;
+  io_uring_queue_init(1, &ring, 0);
+  return 0;
+}
+" HAS_LIBURING)
+  if (HAS_LIBURING)
    add_definitions(-DROCKSDB_IOURING_PRESENT)
-    list(APPEND THIRDPARTY_LIBS uring::uring)
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -luring")
  endif()
 endif()

 # Reset the required flags
 set(CMAKE_REQUIRED_FLAGS ${OLD_CMAKE_REQUIRED_FLAGS})

+CHECK_CXX_SOURCE_COMPILES("
+#if defined(_MSC_VER) && !defined(__thread)
+#define __thread __declspec(thread)
+#endif
+int main() {
+  static __thread int tls;
+  (void)tls;
+}
+" HAVE_THREAD_LOCAL)
+if(HAVE_THREAD_LOCAL)
+  add_definitions(-DROCKSDB_SUPPORT_THREAD_LOCAL)
+endif()
+
 option(WITH_IOSTATS_CONTEXT "Enable IO stats context" ON)
 if (NOT WITH_IOSTATS_CONTEXT)
  add_definitions(-DNIOSTATS_CONTEXT)
@@ -372,7 +421,7 @@ endif()

 option(WITH_TSAN "build with TSAN" OFF)
 if(WITH_TSAN)
-  set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=thread -Wl,-pie")
+  set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=thread -pie")
  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=thread -fPIC")
  set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fsanitize=thread -fPIC")
  if(WITH_JEMALLOC)
@@ -423,32 +472,30 @@ if (ASSERT_STATUS_CHECKED)
  add_definitions(-DROCKSDB_ASSERT_STATUS_CHECKED)
 endif()

-
-# RTTI is by default AUTO which enables it in debug and disables it in release.
-set(USE_RTTI AUTO CACHE STRING "Enable RTTI in builds")
-set_property(CACHE USE_RTTI PROPERTY STRINGS AUTO ON OFF)
-if(USE_RTTI STREQUAL "AUTO")
+if(DEFINED USE_RTTI)
+  if(USE_RTTI)
+    message(STATUS "Enabling RTTI")
+    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
+    set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -DROCKSDB_USE_RTTI")
+  else()
+    if(MSVC)
+      message(STATUS "Disabling RTTI in Release builds. Always on in Debug.")
+      set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
+      set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /GR-")
+    else()
+      message(STATUS "Disabling RTTI in Release builds")
+      set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -fno-rtti")
+      set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -fno-rtti")
+    endif()
+  endif()
+else()
  message(STATUS "Enabling RTTI in Debug builds only (default)")
  set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
  if(MSVC)
-    set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /GR-")
+     set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /GR-")
  else()
    set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -fno-rtti")
  endif()
-elseif(USE_RTTI)
-  message(STATUS "Enabling RTTI in all builds")
-  set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
-  set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -DROCKSDB_USE_RTTI")
-else()
-  if(MSVC)
-    message(STATUS "Disabling RTTI in Release builds. Always on in Debug.")
-    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
-    set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /GR-")
-  else()
-    message(STATUS "Disabling RTTI in all builds")
-    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -fno-rtti")
-    set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -fno-rtti")
-  endif()
 endif()

 # Used to run CI build and tests so we can run faster
@@ -577,17 +624,10 @@ if(HAVE_AUXV_GETAUXVAL)
  add_definitions(-DROCKSDB_AUXV_GETAUXVAL_PRESENT)
 endif()

-check_cxx_symbol_exists(F_FULLFSYNC "fcntl.h" HAVE_FULLFSYNC)
-if(HAVE_FULLFSYNC)
-  add_definitions(-DHAVE_FULLFSYNC)
-endif()
-
 include_directories(${PROJECT_SOURCE_DIR})
 include_directories(${PROJECT_SOURCE_DIR}/include)
-if(USE_FOLLY)
+if(WITH_FOLLY_DISTRIBUTED_MUTEX)
  include_directories(${PROJECT_SOURCE_DIR}/third-party/folly)
-  add_definitions(-DUSE_FOLLY -DFOLLY_NO_CONFIG)
-  list(APPEND THIRDPARTY_LIBS glog)
 endif()
 find_package(Threads REQUIRED)

@@ -599,8 +639,6 @@ set(SOURCES
        cache/cache_key.cc
        cache/cache_reservation_manager.cc
        cache/clock_cache.cc
-        cache/compressed_secondary_cache.cc
-        cache/fast_lru_cache.cc
        cache/lru_cache.cc
        cache/sharded_cache.cc
        db/arena_wrapped_db_iter.cc
@@ -615,7 +653,6 @@ set(SOURCES
        db/blob/blob_log_format.cc
        db/blob/blob_log_sequential_reader.cc
        db/blob/blob_log_writer.cc
-        db/blob/blob_source.cc
        db/blob/prefetch_buffer_collection.cc
        db/builder.cc
        db/c.cc
@@ -677,7 +714,6 @@ set(SOURCES
        db/version_set.cc
        db/wal_edit.cc
        db/wal_manager.cc
-        db/wide/wide_column_serialization.cc
        db/write_batch.cc
        db/write_batch_base.cc
        db/write_controller.cc
@@ -686,6 +722,7 @@ set(SOURCES
        env/env.cc
        env/env_chroot.cc
        env/env_encryption.cc
+        env/env_hdfs.cc
        env/file_system.cc
        env/file_system_tracer.cc
        env/fs_remap.cc
@@ -740,6 +777,7 @@ set(SOURCES
        table/adaptive/adaptive_table_factory.cc
        table/block_based/binary_search_index_reader.cc
        table/block_based/block.cc
+        table/block_based/block_based_filter_block.cc
        table/block_based/block_based_table_builder.cc
        table/block_based/block_based_table_factory.cc
        table/block_based/block_based_table_iterator.cc
@@ -802,12 +840,9 @@ set(SOURCES
        trace_replay/trace_record_result.cc
        trace_replay/trace_record.cc
        trace_replay/trace_replay.cc
-        util/async_file_reader.cc
-        util/cleanable.cc
        util/coding.cc
        util/compaction_job_stats_impl.cc
        util/comparator.cc
-        util/compression.cc
        util/compression_context_cache.cc
        util/concurrent_task_limiter_impl.cc
        util/crc32c.cc
@@ -817,6 +852,7 @@ set(SOURCES
        util/random.cc
        util/rate_limiter.cc
        util/ribbon_config.cc
+        util/regex.cc
        util/slice.cc
        util/file_checksum_helper.cc
        util/status.cc
@@ -824,8 +860,7 @@ set(SOURCES
        util/thread_local.cc
        util/threadpool_imp.cc
        util/xxhash.cc
-        utilities/agg_merge/agg_merge.cc
-        utilities/backup/backup_engine.cc
+        utilities/backupable/backupable_db.cc
        utilities/blob_db/blob_compaction_filter.cc
        utilities/blob_db/blob_db.cc
        utilities/blob_db/blob_db_impl.cc
@@ -840,7 +875,6 @@ set(SOURCES
        utilities/checkpoint/checkpoint_impl.cc
        utilities/compaction_filters.cc
        utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
-        utilities/counted_fs.cc
        utilities/debug.cc
        utilities/env_mirror.cc
        utilities/env_timed.cc
@@ -974,16 +1008,13 @@ else()
    env/io_posix.cc)
 endif()

-if(USE_FOLLY)
+if(WITH_FOLLY_DISTRIBUTED_MUTEX)
  list(APPEND SOURCES
-    third-party/folly/folly/container/detail/F14Table.cpp
    third-party/folly/folly/detail/Futex.cpp
-    third-party/folly/folly/lang/SafeAssert.cpp
-    third-party/folly/folly/lang/ToAscii.cpp
-    third-party/folly/folly/ScopeGuard.cpp
    third-party/folly/folly/synchronization/AtomicNotification.cpp
    third-party/folly/folly/synchronization/DistributedMutex.cpp
-    third-party/folly/folly/synchronization/ParkingLot.cpp)
+    third-party/folly/folly/synchronization/ParkingLot.cpp
+    third-party/folly/folly/synchronization/WaitOptions.cpp)
 endif()

 set(ROCKSDB_STATIC_LIB rocksdb${ARTIFACT_SUFFIX})
@@ -991,6 +1022,12 @@ set(ROCKSDB_SHARED_LIB rocksdb-shared${ARTIFACT_SUFFIX})

 option(ROCKSDB_BUILD_SHARED "Build shared versions of the RocksDB libraries" ON)

+option(WITH_LIBRADOS "Build with librados" OFF)
+if(WITH_LIBRADOS)
+  list(APPEND SOURCES
+    utilities/env_librados.cc)
+  list(APPEND THIRDPARTY_LIBS rados)
+endif()

 if(WIN32)
  set(SYSTEM_LIBS ${SYSTEM_LIBS} shlwapi.lib rpcrt4.lib)
@@ -998,60 +1035,6 @@ else()
  set(SYSTEM_LIBS ${CMAKE_THREAD_LIBS_INIT})
 endif()

-set(ROCKSDB_PLUGIN_EXTERNS "")
-set(ROCKSDB_PLUGIN_BUILTINS "")
-message(STATUS "ROCKSDB PLUGINS TO BUILD ${ROCKSDB_PLUGINS}")
-list(APPEND PLUGINS ${ROCKSDB_PLUGINS})
-foreach(PLUGIN IN LISTS PLUGINS)
-  set(PLUGIN_ROOT "${CMAKE_SOURCE_DIR}/plugin/${PLUGIN}/")
-  message("including rocksb plugin ${PLUGIN_ROOT}")
-  set(PLUGINMKFILE "${PLUGIN_ROOT}${PLUGIN}.mk")
-  if (NOT EXISTS ${PLUGINMKFILE})
-    message(FATAL_ERROR "Missing plugin makefile: ${PLUGINMKFILE}")
-  endif()
-  file(READ ${PLUGINMKFILE} PLUGINMK)
-  string(REGEX MATCH "SOURCES = ([^\n]*)" FOO ${PLUGINMK})
-  set(MK_SOURCES ${CMAKE_MATCH_1})
-  separate_arguments(MK_SOURCES)
-  foreach(MK_FILE IN LISTS MK_SOURCES)
-    list(APPEND SOURCES "${PLUGIN_ROOT}${MK_FILE}")
-  endforeach()
-  string(REGEX MATCH "_FUNC = ([^\n]*)" FOO ${PLUGINMK})
-  if (NOT ${CMAKE_MATCH_1} STREQUAL "")
-    string(APPEND ROCKSDB_PLUGIN_BUILTINS "{\"${PLUGIN}\", " ${CMAKE_MATCH_1} "},")
-    string(APPEND ROCKSDB_PLUGIN_EXTERNS "int " ${CMAKE_MATCH_1} "(ROCKSDB_NAMESPACE::ObjectLibrary&, const std::string&); ")
-  endif()
-  string(REGEX MATCH "_LIBS = ([^\n]*)" FOO ${PLUGINMK})
-  if (NOT ${CMAKE_MATCH_1} STREQUAL "")
-    list(APPEND THIRDPARTY_LIBS "${CMAKE_MATCH_1}")
-  endif()
-  message("THIRDPARTY_LIBS=${THIRDPARTY_LIBS}")
-  #TODO: We need to set any compile/link-time flags and add any link libraries
-endforeach()
-
-string(TIMESTAMP TS "%Y-%m-%d %H:%M:%S" UTC)
-set(BUILD_DATE "${TS}" CACHE STRING "the time we first built rocksdb")
-
-find_package(Git)
-
-if(GIT_FOUND AND EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/.git")
-  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_SHA COMMAND "${GIT_EXECUTABLE}" rev-parse HEAD )
-  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" RESULT_VARIABLE GIT_MOD COMMAND "${GIT_EXECUTABLE}" diff-index HEAD --quiet)
-  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_DATE COMMAND "${GIT_EXECUTABLE}" log -1 --date=format:"%Y-%m-%d %T" --format="%ad")
-  execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_TAG RESULT_VARIABLE rv COMMAND "${GIT_EXECUTABLE}" symbolic-ref -q --short HEAD OUTPUT_STRIP_TRAILING_WHITESPACE)
-  if (rv AND NOT rv EQUAL 0)
-    execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_TAG COMMAND "${GIT_EXECUTABLE}" describe --tags --exact-match OUTPUT_STRIP_TRAILING_WHITESPACE)
-  endif()
-else()
-  set(GIT_SHA 0)
-  set(GIT_MOD 1)
-endif()
-string(REGEX REPLACE "[^0-9a-fA-F]+" "" GIT_SHA "${GIT_SHA}")
-string(REGEX REPLACE "[^0-9: /-]+" "" GIT_DATE "${GIT_DATE}")
-
-set(BUILD_VERSION_CC ${CMAKE_BINARY_DIR}/build_version.cc)
-configure_file(util/build_version.cc.in ${BUILD_VERSION_CC} @ONLY)
-
 add_library(${ROCKSDB_STATIC_LIB} STATIC ${SOURCES} ${BUILD_VERSION_CC})
 target_link_libraries(${ROCKSDB_STATIC_LIB} PRIVATE
  ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
@@ -1131,20 +1114,8 @@ if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
    COMPATIBILITY SameMajorVersion
  )

-  configure_file(
-    ${PROJECT_NAME}.pc.in
-    ${PROJECT_NAME}.pc
-    @ONLY
-  )
-
  install(DIRECTORY include/rocksdb COMPONENT devel DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}")

-  foreach (plugin ${PLUGINS})
-    foreach (header ${${plugin}_HEADERS})
-      install(FILES plugin/${plugin}/${header} DESTINATION ${CMAKE_INSTALL_INCLUDEDIR}/rocksdb/plugin/${plugin})
-    endforeach()
-  endforeach()
-
  install(DIRECTORY "${PROJECT_SOURCE_DIR}/cmake/modules" COMPONENT devel DESTINATION ${package_config_destination})

  install(
@@ -1181,13 +1152,6 @@ if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
    COMPONENT devel
    DESTINATION ${package_config_destination}
  )
-
-  install(
-    FILES
-    ${CMAKE_CURRENT_BINARY_DIR}/${PROJECT_NAME}.pc
-    COMPONENT devel
-    DESTINATION ${CMAKE_INSTALL_LIBDIR}/pkgconfig
-  )
 endif()

 option(WITH_ALL_TESTS "Build all test, rather than a small subset" ON)
@@ -1209,7 +1173,6 @@ if(WITH_TESTS)
    list(APPEND TESTS
        cache/cache_reservation_manager_test.cc
        cache/cache_test.cc
-        cache/compressed_secondary_cache_test.cc
        cache/lru_cache_test.cc
        db/blob/blob_counting_iterator_test.cc
        db/blob/blob_file_addition_test.cc
@@ -1218,7 +1181,6 @@ if(WITH_TESTS)
        db/blob/blob_file_garbage_test.cc
        db/blob/blob_file_reader_test.cc
        db/blob/blob_garbage_meter_test.cc
-        db/blob/blob_source_test.cc
        db/blob/db_blob_basic_test.cc
        db/blob/db_blob_compaction_test.cc
        db/blob/db_blob_corruption_test.cc
@@ -1234,14 +1196,12 @@ if(WITH_TESTS)
        db/comparator_db_test.cc
        db/corruption_test.cc
        db/cuckoo_table_db_test.cc
-        db/db_readonly_with_timestamp_test.cc
        db/db_with_timestamp_basic_test.cc
        db/db_block_cache_test.cc
        db/db_bloom_filter_test.cc
        db/db_compaction_filter_test.cc
        db/db_compaction_test.cc
        db/db_dynamic_level_test.cc
-        db/db_encryption_test.cc
        db/db_flush_test.cc
        db/db_inplace_update_test.cc
        db/db_io_failure_test.cc
@@ -1256,7 +1216,6 @@ if(WITH_TESTS)
        db/db_options_test.cc
        db/db_properties_test.cc
        db/db_range_del_test.cc
-        db/db_rate_limiter_test.cc
        db/db_secondary_test.cc
        db/db_sst_test.cc
        db/db_statistics_test.cc
@@ -1268,7 +1227,6 @@ if(WITH_TESTS)
        db/db_universal_compaction_test.cc
        db/db_wal_test.cc
        db/db_with_timestamp_compaction_test.cc
-        db/db_write_buffer_manager_test.cc
        db/db_write_test.cc
        db/dbformat_test.cc
        db/deletefile_test.cc
@@ -1280,7 +1238,6 @@ if(WITH_TESTS)
        db/file_indexer_test.cc
        db/filename_test.cc
        db/flush_job_test.cc
-        db/import_column_family_test.cc
        db/listener_test.cc
        db/log_test.cc
        db/manual_compaction_test.cc
@@ -1301,7 +1258,6 @@ if(WITH_TESTS)
        db/version_set_test.cc
        db/wal_manager_test.cc
        db/wal_edit_test.cc
-        db/wide/wide_column_serialization_test.cc
        db/write_batch_test.cc
        db/write_callback_test.cc
        db/write_controller_test.cc
@@ -1327,6 +1283,7 @@ if(WITH_TESTS)
        options/customizable_test.cc
        options/options_settable_test.cc
        options/options_test.cc
+        table/block_based/block_based_filter_block_test.cc
        table/block_based/block_based_table_reader_test.cc
        table/block_based/block_test.cc
        table/block_based/data_block_hash_index_test.cc
@@ -1369,15 +1326,13 @@ if(WITH_TESTS)
        util/thread_list_test.cc
        util/thread_local_test.cc
        util/work_queue_test.cc
-        utilities/agg_merge/agg_merge_test.cc
-        utilities/backup/backup_engine_test.cc
+        utilities/backupable/backupable_db_test.cc
        utilities/blob_db/blob_db_test.cc
        utilities/cassandra/cassandra_functional_test.cc
        utilities/cassandra/cassandra_format_test.cc
        utilities/cassandra/cassandra_row_merge_test.cc
        utilities/cassandra/cassandra_serialize_test.cc
        utilities/checkpoint/checkpoint_test.cc
-        utilities/env_timed_test.cc
        utilities/memory/memory_test.cc
        utilities/merge_operators/string_append/stringappend_test.cc
        utilities/object_registry_test.cc
@@ -1391,23 +1346,25 @@ if(WITH_TESTS)
        utilities/transactions/optimistic_transaction_test.cc
        utilities/transactions/transaction_test.cc
        utilities/transactions/lock/point/point_lock_manager_test.cc
-        utilities/transactions/write_committed_transaction_ts_test.cc
        utilities/transactions/write_prepared_transaction_test.cc
        utilities/transactions/write_unprepared_transaction_test.cc
        utilities/transactions/lock/range/range_locking_test.cc
-        utilities/transactions/timestamped_snapshot_test.cc
        utilities/ttl/ttl_test.cc
-        utilities/util_merge_operators_test.cc
        utilities/write_batch_with_index/write_batch_with_index_test.cc
    )
  endif()
+  if(WITH_LIBRADOS)
+    list(APPEND TESTS utilities/env_librados_test.cc)
+  endif()
+
+  if(WITH_FOLLY_DISTRIBUTED_MUTEX)
+    list(APPEND TESTS third-party/folly/folly/synchronization/test/DistributedMutexTest.cpp)
+  endif()

  set(TESTUTIL_SOURCE
      db/db_test_util.cc
-      db/db_with_timestamp_test_util.cc
      monitoring/thread_status_updater_debug.cc
      table/mock_table.cc
-      utilities/agg_merge/test_agg_merge.cc
      utilities/cassandra/test_utils.cc
  )
  enable_testing()
@@ -1438,6 +1395,10 @@ if(WITH_TESTS)
        gtest_discover_tests(${exename} DISCOVERY_TIMEOUT 120)
        add_dependencies(check ${exename}${ARTIFACT_SUFFIX})
      endif()
+      if("${exename}" MATCHES "env_librados_test")
+        # env_librados_test.cc uses librados directly
+        target_link_libraries(${exename}${ARTIFACT_SUFFIX} rados)
+      endif()
  endforeach(sourcefile ${TESTS})

  if(WIN32)
@@ -1,4 +1,4 @@
-# RocksDB default options change log (NO LONGER MAINTAINED)
+# RocksDB default options change log
 ## Unreleased
 * delayed_write_rate takes the rate given by rate_limiter if not specified.

@@ -1,315 +1,15 @@
 # Rocksdb Change Log
-## 7.4.5 (08/02/2022)
-### Bug Fixes
-* Fix a bug starting in 7.4.0 in which some fsync operations might be skipped in a DB after any DropColumnFamily on that DB, until it is re-opened. This can lead to data loss on power loss. (For custom FileSystem implementations, this could lead to `FSDirectory::Fsync` or `FSDirectory::Close` after the first `FSDirectory::Close`; Also, valgrind could report call to `close()` with `fd=-1`.)
-
-## 7.4.4 (07/19/2022)
-### Public API changes
-* Removed Customizable support for RateLimiter and removed its CreateFromString() and Type() functions.
-
-### Bug Fixes
-* Fix a bug where `GenericRateLimiter` could revert the bandwidth set dynamically using `SetBytesPerSecond()` when a user configures a structure enclosing it, e.g., using `GetOptionsFromString()` to configure an `Options` that references an existing `RateLimiter` object.
-
-## 7.4.3 (07/13/2022)
-### Behavior Changes
-* For track_and_verify_wals_in_manifest, revert to the original behavior before #10087: syncing of live WAL file is not tracked, and we track only the synced sizes of **closed** WALs. (PR #10330).
-
-## 7.4.2 (06/30/2022)
-### Bug Fixes
-* Fix a bug in Logger where if dbname and db_log_dir are on different filesystems, dbname creation would fail wrt to db_log_dir path returning an error and fails to open the DB.
-
-## 7.4.1 (06/28/2022)
-### Bug Fixes
-* Pass `rate_limiter_priority` through filter block reader functions to `FileSystem`.
-
-## 7.4.0 (06/19/2022)
-### Bug Fixes
-* Fixed a bug in calculating key-value integrity protection for users of in-place memtable updates. In particular, the affected users would be those who configure `protection_bytes_per_key > 0` on `WriteBatch` or `WriteOptions`, and configure `inplace_callback != nullptr`.
-* Fixed a bug where a snapshot taken during SST file ingestion would be unstable.
-* Fixed a bug for non-TransactionDB with avoid_flush_during_recovery = true and TransactionDB where in case of crash, min_log_number_to_keep may not change on recovery and persisting a new MANIFEST with advanced log_numbers for some column families, results in "column family inconsistency" error on second recovery. As a solution, RocksDB will persist the new MANIFEST after successfully syncing the new WAL. If a future recovery starts from the new MANIFEST, then it means the new WAL is successfully synced. Due to the sentinel empty write batch at the beginning, kPointInTimeRecovery of WAL is guaranteed to go after this point. If future recovery starts from the old MANIFEST, it means the writing the new MANIFEST failed. We won't have the "SST ahead of WAL" error.
-* Fixed a bug where RocksDB DB::Open() may creates and writes to two new MANIFEST files even before recovery succeeds. Now writes to MANIFEST are persisted only after recovery is successful.
-* Fix a race condition in WAL size tracking which is caused by an unsafe iterator access after container is changed.
-* Fix unprotected concurrent accesses to `WritableFileWriter::filesize_` by `DB::SyncWAL()` and `DB::Put()` in two write queue mode.
-* Fix a bug in WAL tracking. Before this PR (#10087), calling `SyncWAL()` on the only WAL file of the db will not log the event in MANIFEST, thus allowing a subsequent `DB::Open` even if the WAL file is missing or corrupted.
-* Fix a bug that could return wrong results with `index_type=kHashSearch` and using `SetOptions` to change the `prefix_extractor`.
-* Fixed a bug in WAL tracking with wal_compression. WAL compression writes a kSetCompressionType record which is not associated with any sequence number. As result, WalManager::GetSortedWalsOfType() will skip these WALs and not return them to caller, e.g. Checkpoint, Backup, causing the operations to fail.
-* Avoid a crash if the IDENTITY file is accidentally truncated to empty. A new DB ID will be written and generated on Open.
-* Fixed a possible corruption for users of `manual_wal_flush` and/or `FlushWAL(true /* sync */)`, together with `track_and_verify_wals_in_manifest == true`. For those users, losing unsynced data (e.g., due to power loss) could make future DB opens fail with a `Status::Corruption` complaining about missing WAL data.
-* Fixed a bug in `WriteBatchInternal::Append()` where WAL termination point in write batch was not considered and the function appends an incorrect number of checksums.
-* Fixed a crash bug introduced in 7.3.0 affecting users of MultiGet with `kDataBlockBinaryAndHash`.
-* Add some fixes in async_io which was doing extra prefetching in shorter scans.
-
-### Public API changes
-* Add new API GetUnixTime in Snapshot class which returns the unix time at which Snapshot is taken.
-* Add transaction `get_pinned` and `multi_get` to C API.
-* Add two-phase commit support to C API.
-* Add `rocksdb_transaction_get_writebatch_wi` and `rocksdb_transaction_rebuild_from_writebatch` to C API.
-* Add `rocksdb_options_get_blob_file_starting_level` and `rocksdb_options_set_blob_file_starting_level` to C API.
-* Add `blobFileStartingLevel` and `setBlobFileStartingLevel` to Java API.
-* Add SingleDelete for DB in C API
-* Add User Defined Timestamp in C API.
-  * `rocksdb_comparator_with_ts_create` to create timestamp aware comparator
-  * Put, Get, Delete, SingleDelete, MultiGet APIs has corresponding timestamp aware APIs with suffix `with_ts`
-  * And Add C API's for Transaction, SstFileWriter, Compaction as mentioned [here](https://github.com/facebook/rocksdb/wiki/User-defined-Timestamp-(Experimental))
-* The contract for implementations of Comparator::IsSameLengthImmediateSuccessor has been updated to work around a design bug in `auto_prefix_mode`.
-* The API documentation for `auto_prefix_mode` now notes some corner cases in which it returns different results than `total_order_seek`, due to design bugs that are not easily fixed. Users using built-in comparators and keys at least the size of a fixed prefix length are not affected.
-* Obsoleted the NUM_DATA_BLOCKS_READ_PER_LEVEL stat and introduced the NUM_LEVEL_READ_PER_MULTIGET and MULTIGET_COROUTINE_COUNT stats
-* Introduced `WriteOptions::protection_bytes_per_key`, which can be used to enable key-value integrity protection for live updates.
-
-### New Features
-* Add FileSystem::ReadAsync API in io_tracing
-* Add blob garbage collection parameters `blob_garbage_collection_policy` and `blob_garbage_collection_age_cutoff` to both force-enable and force-disable GC, as well as selectively override age cutoff when using CompactRange.
-* Add an extra sanity check in `GetSortedWalFiles()` (also used by `GetLiveFilesStorageInfo()`, `BackupEngine`, and `Checkpoint`) to reduce risk of successfully created backup or checkpoint failing to open because of missing WAL file.
-* Add a new column family option `blob_file_starting_level` to enable writing blob files during flushes and compactions starting from the specified LSM tree level.
-* Add support for timestamped snapshots (#9879)
-* Provide support for AbortIO in posix to cancel submitted asynchronous requests using io_uring.
-* Add support for rate-limiting batched `MultiGet()` APIs
-
-### Behavior changes
-* DB::Open(), DB::OpenAsSecondary() will fail if a Logger cannot be created (#9984)
-* Removed support for reading Bloom filters using obsolete block-based filter format. (Support for writing such filters was dropped in 7.0.) For good read performance on old DBs using these filters, a full compaction is required.
-* Per KV checksum in write batch is verified before a write batch is written to WAL to detect any corruption to the write batch (#10114).
-
-### Performance Improvements
-* When compiled with folly (Meta-internal integration; experimental in open source build), improve the locking performance (CPU efficiency) of LRUCache by using folly DistributedMutex in place of standard mutex.
-
-## 7.3.0 (05/20/2022)
-### Bug Fixes
-* Fixed a bug where manual flush would block forever even though flush options had wait=false.
-* Fixed a bug where RocksDB could corrupt DBs with `avoid_flush_during_recovery == true` by removing valid WALs, leading to `Status::Corruption` with message like "SST file is ahead of WALs" when attempting to reopen.
-* Fixed a bug in async_io path where incorrect length of data is read by FilePrefetchBuffer if data is consumed from two populated buffers and request for more data is sent.
-* Fixed a CompactionFilter bug. Compaction filter used to use `Delete` to remove keys, even if the keys should be removed with `SingleDelete`. Mixing `Delete` and `SingleDelete` may cause undefined behavior.
-* Fixed a bug in `WritableFileWriter::WriteDirect` and `WritableFileWriter::WriteDirectWithChecksum`. The rate_limiter_priority specified in ReadOptions was not passed to the RateLimiter when requesting a token.
-* Fixed a bug which might cause process crash when I/O error happens when reading an index block in MultiGet().
-
-### New Features
-* DB::GetLiveFilesStorageInfo is ready for production use.
-* Add new stats PREFETCHED_BYTES_DISCARDED which records number of prefetched bytes discarded by RocksDB FilePrefetchBuffer on destruction and POLL_WAIT_MICROS records wait time for FS::Poll API completion.
-* RemoteCompaction supports table_properties_collector_factories override on compaction worker.
-* Start tracking SST unique id in MANIFEST, which will be used to verify with SST properties during DB open to make sure the SST file is not overwritten or misplaced. A db option `verify_sst_unique_id_in_manifest` is introduced to enable/disable the verification, if enabled all SST files will be opened during DB-open to verify the unique id (default is false), so it's recommended to use it with `max_open_files = -1` to pre-open the files.
-* Added the ability to concurrently read data blocks from multiple files in a level in batched MultiGet. This can be enabled by setting the async_io option in ReadOptions. Using this feature requires a FileSystem that supports ReadAsync (PosixFileSystem is not supported yet for this), and for RocksDB to be compiled with folly and c++20.
-* Charge memory usage of file metadata. RocksDB holds one file metadata structure in-memory per on-disk table file. If an operation reserving memory for file metadata exceeds the avaible space left in the block
-cache at some point (i.e, causing a cache full under `LRUCacheOptions::strict_capacity_limit` = true), creation will fail with `Status::MemoryLimit()`. To opt in this feature,  enable charging `CacheEntryRole::kFileMetadata` in `BlockBasedTableOptions::cache_usage_options`.
-
-### Public API changes
-* Add rollback_deletion_type_callback to TransactionDBOptions so that write-prepared transactions know whether to issue a Delete or SingleDelete to cancel a previous key written during prior prepare phase. The PR aims to prevent mixing SingleDeletes and Deletes for the same key that can lead to undefined behaviors for write-prepared transactions.
-* EXPERIMENTAL: Add new API AbortIO in file_system to abort the read requests submitted asynchronously.
-* CompactionFilter::Decision has a new value: kRemoveWithSingleDelete. If CompactionFilter returns this decision, then CompactionIterator will use `SingleDelete` to mark a key as removed.
-* Renamed CompactionFilter::Decision::kRemoveWithSingleDelete to kPurge since the latter sounds more general and hides the implementation details of how compaction iterator handles keys.
-* Added ability to specify functions for Prepare and Validate to OptionsTypeInfo.  Added methods to OptionTypeInfo to set the functions via an API.  These methods are intended for RocksDB plugin developers for configuration management.
-* Added a new immutable db options, enforce_single_del_contracts. If set to false (default is true), compaction will NOT fail due to a single delete followed by a delete for the same key. The purpose of this temporay option is to help existing use cases migrate.
-* Introduce `BlockBasedTableOptions::cache_usage_options` and use that to replace `BlockBasedTableOptions::reserve_table_builder_memory` and  `BlockBasedTableOptions::reserve_table_reader_memory`.
-* Changed `GetUniqueIdFromTableProperties` to return a 128-bit unique identifier, which will be the standard size now. The old functionality (192-bit) is available from `GetExtendedUniqueIdFromTableProperties`. Both functions are no longer "experimental" and are ready for production use.
-* In IOOptions, mark `prio` as deprecated for future removal.
-* In `file_system.h`, mark `IOPriority` as deprecated for future removal.
-* Add an option, `CompressionOptions::use_zstd_dict_trainer`, to indicate whether zstd dictionary trainer should be used for generating zstd compression dictionaries. The default value of this option is true for backward compatibility. When this option is set to false, zstd API `ZDICT_finalizeDictionary` is used to generate compression dictionaries.
-* Seek API which positions itself every LevelIterator on the correct data block in the correct SST file which can be parallelized if ReadOptions.async_io option is enabled.
-* Add new stat number_async_seek in PerfContext that indicates number of async calls made by seek to prefetch data.
-* Add support for user-defined timestamps to read only DB.
-
-### Bug Fixes
-* RocksDB calls FileSystem::Poll API during FilePrefetchBuffer destruction which impacts performance as it waits for read requets completion which is not needed anymore. Calling FileSystem::AbortIO to abort those requests instead fixes that performance issue.
-* Fixed unnecessary block cache contention when queries within a MultiGet batch and across parallel batches access the same data block, which previously could cause severely degraded performance in this unusual case. (In more typical MultiGet cases, this fix is expected to yield a small or negligible performance improvement.)
-
-### Behavior changes
-* Enforce the existing contract of SingleDelete so that SingleDelete cannot be mixed with Delete because it leads to undefined behavior. Fix a number of unit tests that violate the contract but happen to pass.
-* ldb `--try_load_options` default to true if `--db` is specified and not creating a new DB, the user can still explicitly disable that by `--try_load_options=false` (or explicitly enable that by `--try_load_options`).
-* During Flush write or Compaction write/read, the WriteController is used to determine whether DB writes are stalled or slowed down. The priority (Env::IOPriority) can then be determined accordingly and be passed in IOOptions to the file system.
-
-### Performance Improvements
-* Avoid calling malloc_usable_size() in LRU Cache's mutex.
-* Reduce DB mutex holding time when finding obsolete files to delete. When a file is trivial moved to another level, the internal files will be referenced twice internally and sometimes opened twice too. If a deletion candidate file is not the last reference, we need to destroy the reference and close the file but not deleting the file. Right now we determine it by building a set of all live files. With the improvement, we check the file against all live LSM-tree versions instead.
-
-## 7.2.0 (04/15/2022)
-### Bug Fixes
-* Fixed bug which caused rocksdb failure in the situation when rocksdb was accessible using UNC path
-* Fixed a race condition when 2PC is disabled and WAL tracking in the MANIFEST is enabled. The race condition is between two background flush threads trying to install flush results, causing a WAL deletion not tracked in the MANIFEST. A future DB open may fail.
-* Fixed a heap use-after-free race with DropColumnFamily.
-* Fixed a bug that `rocksdb.read.block.compaction.micros` cannot track compaction stats (#9722).
-* Fixed `file_type`, `relative_filename` and `directory` fields returned by `GetLiveFilesMetaData()`, which were added in inheriting from `FileStorageInfo`.
-* Fixed a bug affecting `track_and_verify_wals_in_manifest`. Without the fix, application may see "open error: Corruption: Missing WAL with log number" while trying to open the db. The corruption is a false alarm but prevents DB open (#9766).
-* Fix segfault in FilePrefetchBuffer with async_io as it doesn't wait for pending jobs to complete on destruction.
-* Fix ERROR_HANDLER_AUTORESUME_RETRY_COUNT stat whose value was set wrong in portal.h
-* Fixed a bug for non-TransactionDB with avoid_flush_during_recovery = true and TransactionDB where in case of crash, min_log_number_to_keep may not change on recovery and persisting a new MANIFEST with advanced log_numbers for some column families, results in "column family inconsistency" error on second recovery. As a solution the corrupted WALs whose numbers are larger than the corrupted wal and smaller than the new WAL will be moved to archive folder.
-* Fixed a bug in RocksDB DB::Open() which may creates and writes to two new MANIFEST files even before recovery succeeds. Now writes to MANIFEST are persisted only after recovery is successful.
-
-### New Features
-* For db_bench when --seed=0 or --seed is not set then it uses the current time as the seed value. Previously it used the value 1000.
-* For db_bench when --benchmark lists multiple tests and each test uses a seed for a RNG then the seeds across tests will no longer be repeated.
-* Added an option to dynamically charge an updating estimated memory usage of block-based table reader to block cache if block cache available. To enable this feature, set `BlockBasedTableOptions::reserve_table_reader_memory = true`.
-* Add new stat ASYNC_READ_BYTES that calculates number of bytes read during async read call and users can check if async code path is being called by RocksDB internal automatic prefetching for sequential reads.
-* Enable async prefetching if ReadOptions.readahead_size is set along with ReadOptions.async_io in FilePrefetchBuffer.
-* Add event listener support on remote compaction compactor side.
-* Added a dedicated integer DB property `rocksdb.live-blob-file-garbage-size` that exposes the total amount of garbage in the blob files in the current version.
-* RocksDB does internal auto prefetching if it notices sequential reads. It starts with readahead size `initial_auto_readahead_size` which now can be configured through BlockBasedTableOptions.
-* Add a merge operator that allows users to register specific aggregation function so that they can does aggregation using different aggregation types for different keys. See comments in include/rocksdb/utilities/agg_merge.h for actual usage. The feature is experimental and the format is subject to change and we won't provide a migration tool.
-* Meta-internal / Experimental: Improve CPU performance by replacing many uses of std::unordered_map with folly::F14FastMap when RocksDB is compiled together with Folly.
-* Experimental: Add CompressedSecondaryCache, a concrete implementation of rocksdb::SecondaryCache, that integrates with compression libraries (e.g. LZ4) to hold compressed blocks.
-
-### Behavior changes
-* Disallow usage of commit-time-write-batch for write-prepared/write-unprepared transactions if TransactionOptions::use_only_the_last_commit_time_batch_for_recovery is false to prevent two (or more) uncommitted versions of the same key in the database. Otherwise, bottommost compaction may violate the internal key uniqueness invariant of SSTs if the sequence numbers of both internal keys are zeroed out (#9794).
-* Make DB::GetUpdatesSince() return NotSupported early for write-prepared/write-unprepared transactions, as the API contract indicates.
-
-### Public API changes
-* Exposed APIs to examine results of block cache stats collections in a structured way. In particular, users of `GetMapProperty()` with property `kBlockCacheEntryStats` can now use the functions in `BlockCacheEntryStatsMapKeys` to find stats in the map.
-* Add `fail_if_not_bottommost_level` to IngestExternalFileOptions so that ingestion will fail if the file(s) cannot be ingested to the bottommost level.
-* Add output parameter `is_in_sec_cache` to `SecondaryCache::Lookup()`. It is to indicate whether the handle is possibly erased from the secondary cache after the Lookup.
-
-## 7.1.0 (03/23/2022)
-### New Features
-* Allow WriteBatchWithIndex to index a WriteBatch that includes keys with user-defined timestamps. The index itself does not have timestamp.
-* Add support for user-defined timestamps to write-committed transaction without API change. The `TransactionDB` layer APIs do not allow timestamps because we require that all user-defined-timestamps-aware operations go through the `Transaction` APIs.
-* Added BlobDB options to `ldb`
-* `BlockBasedTableOptions::detect_filter_construct_corruption` can now be dynamically configured using `DB::SetOptions`.
-* Automatically recover from retryable read IO errors during backgorund flush/compaction.
-* Experimental support for preserving file Temperatures through backup and restore, and for updating DB metadata for outside changes to file Temperature (`UpdateManifestForFilesState` or `ldb update_manifest --update_temperatures`).
-* Experimental support for async_io in ReadOptions which is used by FilePrefetchBuffer to prefetch some of the data asynchronously,  if reads are sequential and auto readahead is enabled by rocksdb internally.
-
-### Bug Fixes
-* Fixed a major performance bug in which Bloom filters generated by pre-7.0 releases are not read by early 7.0.x releases (and vice-versa) due to changes to FilterPolicy::Name() in #9590. This can severely impact read performance and read I/O on upgrade or downgrade with existing DB, but not data correctness.
-* Fixed a data race on `versions_` between `DBImpl::ResumeImpl()` and threads waiting for recovery to complete (#9496)
-* Fixed a bug caused by race among flush, incoming writes and taking snapshots. Queries to snapshots created with these race condition can return incorrect result, e.g. resurfacing deleted data.
-* Fixed a bug that DB flush uses `options.compression` even `options.compression_per_level` is set.
-* Fixed a bug that DisableManualCompaction may assert when disable an unscheduled manual compaction.
-* Fix a race condition when cancel manual compaction with `DisableManualCompaction`. Also DB close can cancel the manual compaction thread.
-* Fixed a potential timer crash when open close DB concurrently.
-* Fixed a race condition for `alive_log_files_` in non-two-write-queues mode. The race is between the write_thread_ in WriteToWAL() and another thread executing `FindObsoleteFiles()`. The race condition will be caught if `__glibcxx_requires_nonempty` is enabled.
-* Fixed a bug that `Iterator::Refresh()` reads stale keys after DeleteRange() performed.
-* Fixed a race condition when disable and re-enable manual compaction.
-* Fixed automatic error recovery failure in atomic flush.
-* Fixed a race condition when mmaping a WritableFile on POSIX.
-
-### Public API changes
-* Added pure virtual FilterPolicy::CompatibilityName(), which is needed for fixing major performance bug involving FilterPolicy naming in SST metadata without affecting Customizable aspect of FilterPolicy. This change only affects those with their own custom or wrapper FilterPolicy classes.
-* `options.compression_per_level` is dynamically changeable with `SetOptions()`.
-* Added `WriteOptions::rate_limiter_priority`. When set to something other than `Env::IO_TOTAL`, the internal rate limiter (`DBOptions::rate_limiter`) will be charged at the specified priority for writes associated with the API to which the `WriteOptions` was provided. Currently the support covers automatic WAL flushes, which happen during live updates (`Put()`, `Write()`, `Delete()`, etc.) when `WriteOptions::disableWAL == false` and `DBOptions::manual_wal_flush == false`.
-* Add DB::OpenAndTrimHistory API. This API will open DB and trim data to the timestamp specified by trim_ts (The data with timestamp larger than specified trim bound will be removed). This API should only be used at a timestamp-enabled column families recovery. If the column family doesn't have timestamp enabled, this API won't trim any data on that column family. This API is not compatible with avoid_flush_during_recovery option.
-* Remove BlockBasedTableOptions.hash_index_allow_collision which already takes no effect.
-
-## 7.0.0 (02/20/2022)
+## 6.28.2 (2022-01-31)
 ### Bug Fixes
 * Fixed a major bug in which batched MultiGet could return old values for keys deleted by DeleteRange when memtable Bloom filter is enabled (memtable_prefix_bloom_size_ratio > 0). (The fix includes a substantial MultiGet performance improvement in the unusual case of both memtable_whole_key_filtering and prefix_extractor.)
-* Fixed more cases of EventListener::OnTableFileCreated called with OK status, file_size==0, and no SST file kept. Now the status is Aborted.
-* Fixed a read-after-free bug in `DB::GetMergeOperands()`.
-* Fix a data loss bug for 2PC write-committed transaction caused by concurrent transaction commit and memtable switch (#9571).
-* Fixed NUM_INDEX_AND_FILTER_BLOCKS_READ_PER_LEVEL, NUM_DATA_BLOCKS_READ_PER_LEVEL, and NUM_SST_READ_PER_LEVEL stats to be reported once per MultiGet batch per level.
-
-### Performance Improvements
-* Mitigated the overhead of building the file location hash table used by the online LSM tree consistency checks, which can improve performance for certain workloads (see #9351).
-* Switched to using a sorted `std::vector` instead of `std::map` for storing the metadata objects for blob files, which can improve performance for certain workloads, especially when the number of blob files is high.
-* DisableManualCompaction() doesn't have to wait scheduled manual compaction to be executed in thread-pool to cancel the job.
-
-### Public API changes
-* Require C++17 compatible compiler (GCC >= 7, Clang >= 5, Visual Studio >= 2017) for compiling RocksDB and any code using RocksDB headers. See #9388.
-* Added `ReadOptions::rate_limiter_priority`. When set to something other than `Env::IO_TOTAL`, the internal rate limiter (`DBOptions::rate_limiter`) will be charged at the specified priority for file reads associated with the API to which the `ReadOptions` was provided.
-* Remove HDFS support from main repo.
-* Remove librados support from main repo.
-* Remove obsolete backupable_db.h and type alias `BackupableDBOptions`. Use backup_engine.h and `BackupEngineOptions`. Similar renamings are in the C and Java APIs.
-* Removed obsolete utility_db.h and `UtilityDB::OpenTtlDB`. Use db_ttl.h and `DBWithTTL::Open`.
-* Remove deprecated API DB::AddFile from main repo.
-* Remove deprecated API ObjectLibrary::Register() and the (now obsolete) Regex public API. Use ObjectLibrary::AddFactory() with PatternEntry instead.
-* Remove deprecated option DBOption::table_cache_remove_scan_count_limit.
-* Remove deprecated API AdvancedColumnFamilyOptions::soft_rate_limit.
-* Remove deprecated API AdvancedColumnFamilyOptions::hard_rate_limit.
-* Remove deprecated API DBOption::base_background_compactions.
-* Remove deprecated API DBOptions::purge_redundant_kvs_while_flush.
-* Remove deprecated overloads of API DB::CompactRange.
-* Remove deprecated option DBOptions::skip_log_error_on_recovery.
-* Remove ReadOptions::iter_start_seqnum which has been deprecated.
-* Remove DBOptions::preserved_deletes and DB::SetPreserveDeletesSequenceNumber().
-* Remove deprecated API AdvancedColumnFamilyOptions::rate_limit_delay_max_milliseconds.
-* Removed timestamp from WriteOptions. Accordingly, added to DB APIs Put, Delete, SingleDelete, etc. accepting an additional argument 'timestamp'. Added Put, Delete, SingleDelete, etc to WriteBatch accepting an additional argument 'timestamp'. Removed WriteBatch::AssignTimestamps(vector<Slice>) API. Renamed WriteBatch::AssignTimestamp() to WriteBatch::UpdateTimestamps() with clarified comments.
-* Changed type of cache buffer passed to `Cache::CreateCallback` from `void*` to `const void*`.
-* Significant updates to FilterPolicy-related APIs and configuration:
-  * Remove public API support for deprecated, inefficient block-based filter (use_block_based_builder=true).
-    * Old code and configuration strings that would enable it now quietly enable full filters instead, though any built-in FilterPolicy can still read block-based filters. This includes changing the longstanding default behavior of the Java API.
-    * Remove deprecated FilterPolicy::CreateFilter() and FilterPolicy::KeyMayMatch()
-    * Remove `rocksdb_filterpolicy_create()` from C API, as the only C API support for custom filter policies is now obsolete.
-    * If temporary memory usage in full filter creation is a problem, consider using partitioned filters, smaller SST files, or setting reserve_table_builder_memory=true.
-  * Remove support for "filter_policy=experimental_ribbon" configuration
-  string. Use something like "filter_policy=ribbonfilter:10" instead.
-  * Allow configuration string like "filter_policy=bloomfilter:10" without
-  bool, to minimize acknowledgement of obsolete block-based filter.
-  * Made FilterPolicy Customizable. Configuration of filter_policy is now accurately saved in OPTIONS file and can be loaded with LoadOptionsFromFile. (Loading an OPTIONS file generated by a previous version only enables reading and using existing filters, not generating new filters. Previously, no filter_policy would be configured from a saved OPTIONS file.)
-  * Change meaning of nullptr return from GetBuilderWithContext() from "use
-    block-based filter" to "generate no filter in this case."
-    * Also, when user specifies bits_per_key < 0.5, we now round this down
-    to "no filter" because we expect a filter with >= 80% FP rate is
-    unlikely to be worth the CPU cost of accessing it (esp with
-    cache_index_and_filter_blocks=1 or partition_filters=1).
-    * bits_per_key >= 0.5 and < 1.0 is still rounded up to 1.0 (for 62% FP
-    rate)
-  * Remove class definitions for FilterBitsBuilder and FilterBitsReader from
-    public API, so these can evolve more easily as implementation details.
-    Custom FilterPolicy can still decide what kind of built-in filter to use
-    under what conditions.
-  * Also removed deprecated functions
-    * FilterPolicy::GetFilterBitsBuilder()
-    * NewExperimentalRibbonFilterPolicy()
-  * Remove default implementations of
-    * FilterPolicy::GetBuilderWithContext()
-* Remove default implementation of Name() from FileSystemWrapper.
-* Rename `SizeApproximationOptions.include_memtabtles` to `SizeApproximationOptions.include_memtables`.
-* Remove deprecated option DBOptions::max_mem_compaction_level.
-* Return Status::InvalidArgument from ObjectRegistry::NewObject if a factory exists but the object ould not be created (returns NotFound if the factory is missing).
-* Remove deprecated overloads of API DB::GetApproximateSizes.
-* Remove deprecated option DBOptions::new_table_reader_for_compaction_inputs.
-* Add Transaction::SetReadTimestampForValidation() and Transaction::SetCommitTimestamp(). Default impl returns NotSupported().
-* Add support for decimal patterns to ObjectLibrary::PatternEntry
-* Remove deprecated remote compaction APIs `CompactionService::Start()` and `CompactionService::WaitForComplete()`. Please use `CompactionService::StartV2()`, `CompactionService::WaitForCompleteV2()` instead, which provides the same information plus extra data like priority, db_id, etc.
-* `ColumnFamilyOptions::OldDefaults` and `DBOptions::OldDefaults` are marked deprecated, as they are no longer maintained.
-* Add subcompaction callback APIs: `OnSubcompactionBegin()` and `OnSubcompactionCompleted()`.
-* Add file Temperature information to `FileOperationInfo` in event listener API.
-* Change the type of SizeApproximationFlags from enum to enum class. Also update the signature of DB::GetApproximateSizes API from uint8_t to SizeApproximationFlags.
-* Add Temperature hints information from RocksDB in API `NewSequentialFile()`. backup and checkpoint operations need to open the source files with `NewSequentialFile()`, which will have the temperature hints. Other operations are not covered.
-
-### Behavior Changes
-* Disallow the combination of DBOptions.use_direct_io_for_flush_and_compaction == true and DBOptions.writable_file_max_buffer_size == 0. This combination can cause WritableFileWriter::Append() to loop forever, and it does not make much sense in direct IO.
-* `ReadOptions::total_order_seek` no longer affects `DB::Get()`. The original motivation for this interaction has been obsolete since RocksDB has been able to detect whether the current prefix extractor is compatible with that used to generate table files, probably RocksDB 5.14.0.
-
-## New Features
-* Introduced an option `BlockBasedTableOptions::detect_filter_construct_corruption` for detecting corruption during Bloom Filter (format_version >= 5) and Ribbon Filter construction.
-* Improved the SstDumpTool to read the comparator from table properties and use it to read the SST File.
-* Extended the column family statistics in the info log so the total amount of garbage in the blob files and the blob file space amplification factor are also logged. Also exposed the blob file space amp via the `rocksdb.blob-stats` DB property.
-* Introduced the API rocksdb_create_dir_if_missing in c.h that calls underlying file system's CreateDirIfMissing API to create the directory.
-* Added last level and non-last level read statistics: `LAST_LEVEL_READ_*`, `NON_LAST_LEVEL_READ_*`.
-* Experimental: Add support for new APIs ReadAsync in FSRandomAccessFile that reads the data asynchronously and Poll API in FileSystem that checks if requested read request has completed or not. ReadAsync takes a callback function. Poll API checks for completion of read IO requests and  should call callback functions to indicate completion of read requests.
-
-## 6.29.0 (01/21/2022)
-Note: The next release will be major release 7.0. See https://github.com/facebook/rocksdb/issues/9390 for more info.
-### Public API change
-* Added values to `TraceFilterType`: `kTraceFilterIteratorSeek`, `kTraceFilterIteratorSeekForPrev`, and `kTraceFilterMultiGet`. They can be set in `TraceOptions` to filter out the operation types after which they are named.
-* Added `TraceOptions::preserve_write_order`. When enabled it  guarantees write records are traced in the same order they are logged to WAL and applied to the DB. By default it is disabled (false) to match the legacy behavior and prevent regression.
-* Made the Env class extend the Customizable class.  Implementations need to be registered with the ObjectRegistry and to implement a Name() method in order to be created via this method.
-* `Options::OldDefaults` is marked deprecated, as it is no longer maintained.
-* Add ObjectLibrary::AddFactory and ObjectLibrary::PatternEntry classes.  This method and associated class are the preferred mechanism for registering factories with the ObjectLibrary going forward.  The ObjectLibrary::Register method, which uses regular expressions and may be problematic, is deprecated and will be in a future release.
-* Changed `BlockBasedTableOptions::block_size` from `size_t` to `uint64_t`.
-* Added API warning against using `Iterator::Refresh()` together with `DB::DeleteRange()`, which are incompatible and have always risked causing the refreshed iterator to return incorrect results.
-* Made `AdvancedColumnFamilyOptions.bottommost_temperature` dynamically changeable with `SetOptions()`.
-
-### Behavior Changes
-* `DB::DestroyColumnFamilyHandle()` will return Status::InvalidArgument() if called with `DB::DefaultColumnFamily()`.
-* On 32-bit platforms, mmap reads are no longer quietly disabled, just discouraged.
-
-### New Features
-* Added `Options::DisableExtraChecks()` that can be used to improve peak write performance by disabling checks that should not be necessary in the absence of software logic errors or CPU+memory hardware errors. (Default options are slowly moving toward some performance overheads for extra correctness checking.)
-
-### Performance Improvements
-* Improved read performance when a prefix extractor is used (Seek, Get, MultiGet), even compared to version 6.25 baseline (see bug fix below), by optimizing the common case of prefix extractor compatible with table file and unchanging.

+## 6.28.1 (2022-01-10)
 ### Bug Fixes
-* Fix a bug that FlushMemTable may return ok even flush not succeed.
-* Fixed a bug of Sync() and Fsync() not using `fcntl(F_FULLFSYNC)` on OS X and iOS.
-* Fixed a significant performance regression in version 6.26 when a prefix extractor is used on the read path (Seek, Get, MultiGet). (Excessive time was spent in SliceTransform::AsString().)
-* Fixed a race condition in SstFileManagerImpl error recovery code that can cause a crash during process shutdown.
-
-### New Features
-* Added RocksJava support for MacOS universal binary (ARM+x86)
+* Fixed compilation errors on newer compiler, e.g. clang-12

 ## 6.28.0 (2021-12-17)
 ### New Features
 * Introduced 'CommitWithTimestamp' as a new tag. Currently, there is no API for user to trigger a write with this tag to the WAL. This is part of the efforts to support write-commited transactions with user-defined timestamps.
-* Introduce SimulatedHybridFileSystem which can help simulating HDD latency in db_bench. Tiered Storage latency simulation can be enabled using -simulate_hybrid_fs_file (note that it doesn't work if db_bench is interrupted in the middle). -simulate_hdd can also be used to simulate all files on HDD.

 ### Bug Fixes
 * Fixed a bug in rocksdb automatic implicit prefetching which got broken because of new feature adaptive_readahead and internal prefetching got disabled when iterator moves from one file to next.
@@ -318,7 +18,6 @@ Note: The next release will be major release 7.0. See https://github.com/faceboo
 * Fixed a bug causing two duplicate entries to be appended to a file opened in non-direct mode and tracked by `FaultInjectionTestFS`.
 * Fixed a bug in TableOptions.prepopulate_block_cache to support block-based filters also.
 * Block cache keys no longer use `FSRandomAccessFile::GetUniqueId()` (previously used when available), so a filesystem recycling unique ids can no longer lead to incorrect result or crash (#7405). For files generated by RocksDB >= 6.24, the cache keys are stable across DB::Open and DB directory move / copy / import / export / migration, etc. Although collisions are still theoretically possible, they are (a) impossible in many common cases, (b) not dependent on environmental factors, and (c) much less likely than a CPU miscalculation while executing RocksDB.
-* Fixed a bug in C bindings causing iterator to return incorrect result (#9343).

 ### Behavior Changes
 * MemTableList::TrimHistory now use allocated bytes when max_write_buffer_size_to_maintain > 0(default in TrasactionDB, introduced in PR#5022) Fix #8371.
@@ -326,8 +25,6 @@ Note: The next release will be major release 7.0. See https://github.com/faceboo
 ### Public API change
 * Extend WriteBatch::AssignTimestamp and AssignTimestamps API so that both functions can accept an optional `checker` argument that performs additional checking on timestamp sizes.
 * Introduce a new EventListener callback that will be called upon the end of automatic error recovery.
-* Add IncreaseFullHistoryTsLow API so users can advance each column family's full_history_ts_low seperately.
-* Add GetFullHistoryTsLow API so users can query current full_history_low value of specified column family.

 ### Performance Improvements
 * Replaced map property `TableProperties::properties_offsets`  with uint64_t property `external_sst_file_global_seqno_offset` to save table properties's memory.
@@ -1814,7 +1511,7 @@ if set to something > 0 user will see 2 changes in iterators behavior 1) only ke
 * Added a new way to report QPS from db_bench (check out --report_file and --report_interval_seconds)
 * Added a cache for individual rows. See DBOptions::row_cache for more info.
 * Several new features on EventListener (see include/rocksdb/listener.h):
- - OnCompactionCompleted() now returns per-compaction job statistics, defined in include/rocksdb/compaction_job_stats.h.
+ - OnCompationCompleted() now returns per-compaction job statistics, defined in include/rocksdb/compaction_job_stats.h.
 - Added OnTableFileCreated() and OnTableFileDeleted().
 * Add compaction_options_universal.enable_trivial_move to true, to allow trivial move while performing universal compaction. Trivial move will happen only when all the input files are non overlapping.

@@ -6,7 +6,7 @@ than release mode.

 RocksDB's library should be able to compile without any dependency installed,
 although we recommend installing some compression libraries (see below).
-We do depend on newer gcc/clang with C++17 support (GCC >= 7, Clang >= 5).
+We do depend on newer gcc/clang with C++11 support.

 There are few options when compiling RocksDB:

@@ -47,12 +47,10 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi

 * If you wish to build the RocksJava static target, then cmake is required for building Snappy.

-* If you wish to run microbench (e.g, `make microbench`, `make ribbon_bench` or `cmake -DWITH_BENCHMARK=1`), Google benchmark >= 1.6.0 is needed.
-
 ## Supported platforms

 * **Linux - Ubuntu**
-    * Upgrade your gcc to version at least 7 to get C++17 support.
+    * Upgrade your gcc to version at least 4.8 to get C++11 support.
    * Install gflags. First, try: `sudo apt-get install libgflags-dev`
      If this doesn't work and you're using Ubuntu, here's a nice tutorial:
      (http://askubuntu.com/questions/312173/installing-gflags-12-04)
@@ -64,7 +62,8 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
    * Install zstandard: `sudo apt-get install libzstd-dev`.

 * **Linux - CentOS / RHEL**
-    * Upgrade your gcc to version at least 7 to get C++17 support
+    * Upgrade your gcc to version at least 4.8 to get C++11 support:
+      `yum install gcc48-c++`
    * Install gflags:

              git clone https://github.com/gflags/gflags.git
@@ -114,11 +113,11 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
              make && sudo make install

 * **OS X**:
-    * Install latest C++ compiler that supports C++ 17:
+    * Install latest C++ compiler that supports C++ 11:
        * Update XCode:  run `xcode-select --install` (or install it from XCode App's settting).
        * Install via [homebrew](http://brew.sh/).
            * If you're first time developer in MacOS, you still need to run: `xcode-select --install` in your command line.
-            * run `brew tap homebrew/versions; brew install gcc7 --use-llvm` to install gcc 7 (or higher).
+            * run `brew tap homebrew/versions; brew install gcc48 --use-llvm` to install gcc 4.8 (or higher).
    * run `brew install rocksdb`

 * **FreeBSD** (11.01):
@@ -161,7 +160,7 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi

    * Install the dependencies for RocksDB:

-        pkg_add gmake gflags snappy bzip2 lz4 zstd git jdk bash findutils gnuwatch
+        pkg_add gmake gflags snappy bzip2 lz4 zstd git jdk bash findutils gnuwatch 

    * Build RocksDB from source:

@@ -180,15 +179,16 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
 * **iOS**:
  * Run: `TARGET_OS=IOS make static_lib`. When building the project which uses rocksdb iOS library, make sure to define two important pre-processing macros: `ROCKSDB_LITE` and `IOS_CROSS_COMPILE`.

-* **Windows** (Visual Studio 2017 to up):
+* **Windows**:
+  * For building with MS Visual Studio 13 you will need Update 4 installed.
  * Read and follow the instructions at CMakeLists.txt
-  * Or install via [vcpkg](https://github.com/microsoft/vcpkg)
+  * Or install via [vcpkg](https://github.com/microsoft/vcpkg) 
       * run `vcpkg install rocksdb:x64-windows`

 * **AIX 6.1**
    * Install AIX Toolbox rpms with gcc
    * Use these environment variables:
-
+  
             export PORTABLE=1
             export CC=gcc
             export AR="ar -X64"
@@ -199,9 +199,9 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
             export LIBPATH=/opt/freeware/lib
             export JAVA_HOME=/usr/java8_64
             export PATH=/opt/freeware/bin:$PATH
-
+  
 * **Solaris Sparc**
-    * Install GCC 7 and higher.
+    * Install GCC 4.8.2 and higher.
    * Use these environment variables:

             export CC=gcc
@@ -210,3 +210,4 @@ to build a portable binary, add `PORTABLE=1` before your make commands, like thi
             export EXTRA_LDFLAGS=-m64
             export PORTABLE=1
             export PLATFORM_LDFLAGS="-static-libstdc++ -static-libgcc"
+
@@ -1,7 +1,4 @@
 This is the list of all known third-party plugins for RocksDB. If something is missing, please open a pull request to add it.

 * [Dedupfs](https://github.com/ajkr/dedupfs): an example for plugin developers to reference
-* [HDFS](https://github.com/riversand963/rocksdb-hdfs-env): an Env used for interacting with HDFS. Migrated from main RocksDB repo
 * [ZenFS](https://github.com/westerndigitalcorporation/zenfs): a file system for zoned block devices
-* [RADOS](https://github.com/riversand963/rocksdb-rados-env): an Env used for interacting with RADOS. Migrated from RocksDB main repo.
-* [PMEM](https://github.com/pmem/pmem-rocksdb-plugin): a collection of plugins to enable Persistent Memory on RocksDB.
@@ -25,7 +25,7 @@ The public interface is in `include/`.  Callers should not include or
 rely on the details of any other header files in this package.  Those
 internal APIs may be changed without warning.

-Questions and discussions are welcome on the [RocksDB Developers Public](https://www.facebook.com/groups/rocksdb.dev/) Facebook group and [email list](https://groups.google.com/g/rocksdb) on Google Groups.
+Design discussions are conducted in https://www.facebook.com/groups/rocksdb.dev/ and https://rocksdb.slack.com/

 ## License

@@ -4,7 +4,7 @@ RocksDBLite is a project focused on mobile use cases, which don't need a lot of

 Some examples of the features disabled by ROCKSDB_LITE:
 * compiled-in support for LDB tool
-* No backup engine
+* No backupable DB
 * No support for replication (which we provide in form of TransactionalIterator)
 * No advanced monitoring tools
 * No special-purpose memtables that are highly optimized for specific use cases
@@ -121,8 +121,6 @@ LzLabs is using RocksDB as a storage engine in their multi-database distributed
 ## Kafka
 [Kafka](https://kafka.apache.org/) is an open-source distributed event streaming platform, it uses RocksDB to store state in Kafka Streams: https://www.confluent.io/blog/how-to-tune-rocksdb-kafka-streams-state-stores-performance/.

-## Solana Labs
-[Solana](https://github.com/solana-labs/solana) is a fast, secure, scalable, and decentralized blockchain.  It uses RocksDB as the underlying storage for its ledger store.
-
 ## Others
 More databases using RocksDB can be found at [dbdb.io](https://dbdb.io/browse?embeds=rocksdb).
+
@@ -0,0 +1,77 @@
+version: 1.0.{build}
+
+image: Visual Studio 2019
+
+environment:
+  JAVA_HOME: C:\Program Files\Java\jdk1.8.0
+  THIRDPARTY_HOME: $(APPVEYOR_BUILD_FOLDER)\thirdparty
+  SNAPPY_HOME: $(THIRDPARTY_HOME)\snappy-1.1.7
+  SNAPPY_INCLUDE: $(SNAPPY_HOME);$(SNAPPY_HOME)\build
+  SNAPPY_LIB_DEBUG: $(SNAPPY_HOME)\build\Debug\snappy.lib
+  SNAPPY_LIB_RELEASE: $(SNAPPY_HOME)\build\Release\snappy.lib
+  LZ4_HOME: $(THIRDPARTY_HOME)\lz4-1.8.3
+  LZ4_INCLUDE: $(LZ4_HOME)\lib
+  LZ4_LIB_DEBUG: $(LZ4_HOME)\visual\VS2010\bin\x64_Debug\liblz4_static.lib
+  LZ4_LIB_RELEASE: $(LZ4_HOME)\visual\VS2010\bin\x64_Release\liblz4_static.lib
+  ZSTD_HOME: $(THIRDPARTY_HOME)\zstd-1.4.0
+  ZSTD_INCLUDE: $(ZSTD_HOME)\lib;$(ZSTD_HOME)\lib\dictBuilder
+  ZSTD_LIB_DEBUG: $(ZSTD_HOME)\build\VS2010\bin\x64_Debug\libzstd_static.lib
+  ZSTD_LIB_RELEASE: $(ZSTD_HOME)\build\VS2010\bin\x64_Release\libzstd_static.lib
+  matrix:
+    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2015
+      CMAKE_GENERATOR: Visual Studio 14 Win64
+      DEV_ENV: C:\Program Files (x86)\Microsoft Visual Studio 14.0\Common7\IDE\devenv.com
+    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2017
+      CMAKE_GENERATOR: Visual Studio 15 Win64
+      DEV_ENV: C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com
+
+install:
+  - md %THIRDPARTY_HOME%
+  - echo "Building Snappy dependency..."
+  - cd %THIRDPARTY_HOME%
+  - curl --fail --silent --show-error --output snappy-1.1.7.zip --location https://github.com/google/snappy/archive/1.1.7.zip
+  - unzip snappy-1.1.7.zip
+  - cd snappy-1.1.7
+  - mkdir build
+  - cd build
+  - if DEFINED CMAKE_PLATEFORM_NAME (set "PLATEFORM_OPT=-A %CMAKE_PLATEFORM_NAME%")
+  - cmake .. -G "%CMAKE_GENERATOR%" %PLATEFORM_OPT%
+  - msbuild Snappy.sln /p:Configuration=Debug /p:Platform=x64
+  - msbuild Snappy.sln /p:Configuration=Release /p:Platform=x64
+  - echo "Building LZ4 dependency..."
+  - cd %THIRDPARTY_HOME%
+  - curl --fail --silent --show-error --output lz4-1.8.3.zip --location https://github.com/lz4/lz4/archive/v1.8.3.zip
+  - unzip lz4-1.8.3.zip
+  - cd lz4-1.8.3\visual\VS2010
+  - ps: $CMD="$Env:DEV_ENV"; & $CMD lz4.sln /upgrade
+  - msbuild lz4.sln /p:Configuration=Debug /p:Platform=x64
+  - msbuild lz4.sln /p:Configuration=Release /p:Platform=x64
+  - echo "Building ZStd dependency..."
+  - cd %THIRDPARTY_HOME%
+  - curl --fail --silent --show-error --output zstd-1.4.0.zip --location https://github.com/facebook/zstd/archive/v1.4.0.zip
+  - unzip zstd-1.4.0.zip
+  - cd zstd-1.4.0\build\VS2010
+  - ps: $CMD="$Env:DEV_ENV"; & $CMD zstd.sln /upgrade
+  - msbuild zstd.sln /p:Configuration=Debug /p:Platform=x64
+  - msbuild zstd.sln /p:Configuration=Release /p:Platform=x64
+
+before_build:
+  - md %APPVEYOR_BUILD_FOLDER%\build
+  - cd %APPVEYOR_BUILD_FOLDER%\build
+  - if DEFINED CMAKE_PLATEFORM_NAME (set "PLATEFORM_OPT=-A %CMAKE_PLATEFORM_NAME%")
+  - cmake .. -G "%CMAKE_GENERATOR%" %PLATEFORM_OPT% %CMAKE_OPT% -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE=1 -DSNAPPY=1 -DLZ4=1 -DZSTD=1 -DXPRESS=1 -DJNI=1 -DWITH_ALL_TESTS=0
+  - cd ..
+
+build:
+  project: build\rocksdb.sln
+  parallel: true
+  verbosity: normal
+
+test:
+
+test_script:
+  - ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,env_basic_test -Concurrency 8
+
+on_failure:
+  - cmd: 7z a build-failed.zip %APPVEYOR_BUILD_FOLDER%\build\ && appveyor PushArtifact build-failed.zip
+
@@ -1,4 +1,3 @@
-#!/usr/bin/env python3
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 from __future__ import absolute_import
 from __future__ import division
@@ -144,14 +143,7 @@ def generate_targets(repo_path, deps_map):
        src_mk["LIB_SOURCES"] +
        # always add range_tree, it's only excluded on ppc64, which we don't use internally
        src_mk["RANGE_TREE_SOURCES"] +
-        src_mk["TOOL_LIB_SOURCES"],
-        deps=[
-            "//folly/container:f14_hash",
-            "//folly/experimental/coro:blocking_wait",
-            "//folly/experimental/coro:collect",
-            "//folly/experimental/coro:coroutine",
-            "//folly/experimental/coro:task",
-            "//folly/synchronization:distributed_mutex"])
+        src_mk["TOOL_LIB_SOURCES"])
    # rocksdb_whole_archive_lib
    TARGETS.add_library(
        "rocksdb_whole_archive_lib",
@@ -159,13 +151,7 @@ def generate_targets(repo_path, deps_map):
        # always add range_tree, it's only excluded on ppc64, which we don't use internally
        src_mk["RANGE_TREE_SOURCES"] +
        src_mk["TOOL_LIB_SOURCES"],
-        deps=[
-            "//folly/container:f14_hash",
-            "//folly/experimental/coro:blocking_wait",
-            "//folly/experimental/coro:collect",
-            "//folly/experimental/coro:coroutine",
-            "//folly/experimental/coro:task",
-            "//folly/synchronization:distributed_mutex"],
+        deps=None,
        headers=None,
        extra_external_deps="",
        link_whole=True)
@@ -177,8 +163,9 @@ def generate_targets(repo_path, deps_map):
        src_mk.get("EXP_LIB_SOURCES", []) +
        src_mk.get("ANALYZER_LIB_SOURCES", []),
        [":rocksdb_lib"],
-        extra_test_libs=True
-        )
+        extra_external_deps=""" + [
+        ("googletest", None, "gtest"),
+    ]""")
    # rocksdb_tools_lib
    TARGETS.add_library(
        "rocksdb_tools_lib",
@@ -197,23 +184,12 @@ def generate_targets(repo_path, deps_map):
        src_mk.get("ANALYZER_LIB_SOURCES", [])
        + src_mk.get('STRESS_LIB_SOURCES', [])
        + ["test_util/testutil.cc"])
-    # db_stress binary
-    TARGETS.add_binary("db_stress",
-                       ["db_stress_tool/db_stress.cc"],
-                       [":rocksdb_stress_lib"])
-    # bench binaries
-    for src in src_mk.get("MICROBENCH_SOURCES", []):
-        name =  src.rsplit('/',1)[1].split('.')[0] if '/' in src else src.split('.')[0]
-        TARGETS.add_binary(
-            name,
-            [src],
-            [],
-            extra_bench_libs=True
-            )
+
    print("Extra dependencies:\n{0}".format(json.dumps(deps_map)))

    # Dictionary test executable name -> relative source file path
    test_source_map = {}
+    print(src_mk)

    # c_test.c is added through TARGETS.add_c_test(). If there
    # are more than one .c test file, we need to extend
@@ -224,42 +200,6 @@ def generate_targets(repo_path, deps_map):
            return False
    TARGETS.add_c_test()

-    try:
-        with open(f"{repo_path}/buckifier/bench.json") as json_file:
-            fast_fancy_bench_config_list = json.load(json_file)
-            for config_dict in fast_fancy_bench_config_list:
-                clean_benchmarks = {}
-                benchmarks = config_dict['benchmarks']
-                for binary, benchmark_dict in benchmarks.items():
-                    clean_benchmarks[binary] = {}
-                    for benchmark, overloaded_metric_list in benchmark_dict.items():
-                        clean_benchmarks[binary][benchmark] = []
-                        for metric in overloaded_metric_list:
-                            if not isinstance(metric, dict):
-                                clean_benchmarks[binary][benchmark].append(metric)
-                TARGETS.add_fancy_bench_config(config_dict['name'], clean_benchmarks, False, config_dict['expected_runtime_one_iter'], config_dict['sl_iterations'], config_dict['regression_threshold'])
-
-        with open(f"{repo_path}/buckifier/bench-slow.json") as json_file:
-            slow_fancy_bench_config_list = json.load(json_file)
-            for config_dict in slow_fancy_bench_config_list:
-                clean_benchmarks = {}
-                benchmarks = config_dict['benchmarks']
-                for binary, benchmark_dict in benchmarks.items():
-                    clean_benchmarks[binary] = {}
-                    for benchmark, overloaded_metric_list in benchmark_dict.items():
-                        clean_benchmarks[binary][benchmark] = []
-                        for metric in overloaded_metric_list:
-                            if not isinstance(metric, dict):
-                                clean_benchmarks[binary][benchmark].append(metric)
-            for config_dict in slow_fancy_bench_config_list:
-                TARGETS.add_fancy_bench_config(config_dict['name']+"_slow", clean_benchmarks, True, config_dict['expected_runtime_one_iter'], config_dict['sl_iterations'], config_dict['regression_threshold'])
-    # it is better servicelab experiments break
-    # than rocksdb github ci
-    except Exception:
-        pass
-
-    TARGETS.add_test_header()
-
    for test_src in src_mk.get("TEST_MAIN_SOURCES", []):
        test = test_src.split('.c')[0].strip().split('/')[-1].strip()
        test_source_map[test] = test_src
@@ -273,21 +213,17 @@ def generate_targets(repo_path, deps_map):

            test_target_name = \
                test if not target_alias else test + "_" + target_alias
+            TARGETS.register_test(
+                test_target_name,
+                test_src,
+                test not in non_parallel_tests,
+                json.dumps(deps['extra_deps']),
+                json.dumps(deps['extra_compiler_flags']))

            if test in _EXPORTED_TEST_LIBS:
                test_library = "%s_lib" % test_target_name
-                TARGETS.add_library(test_library, [test_src], deps=[":rocksdb_test_lib"], extra_test_libs=True)
-                TARGETS.register_test(
-                    test_target_name,
-                    test_src,
-                    deps = json.dumps(deps['extra_deps'] + [':'+test_library]),
-                    extra_compiler_flags = json.dumps(deps['extra_compiler_flags']))
-            else:
-                TARGETS.register_test(
-                    test_target_name,
-                    test_src,
-                    deps = json.dumps(deps['extra_deps'] + [":rocksdb_test_lib"] ),
-                    extra_compiler_flags = json.dumps(deps['extra_compiler_flags']))
+                TARGETS.add_library(test_library, [test_src], [":rocksdb_test_lib"])
+    TARGETS.flush_tests()

    print(ColorString.info("Generated TARGETS Summary:"))
    print(ColorString.info("- %d libs" % TARGETS.total_lib))
@@ -10,7 +10,6 @@ except ImportError:
    from __builtin__ import object
    from __builtin__ import str
 import targets_cfg
-import pprint

 def pretty_list(lst, indent=8):
    if lst is None or len(lst) == 0:
@@ -41,73 +40,85 @@ class TARGETSBuilder(object):
        self.targets_file.close()

    def add_library(self, name, srcs, deps=None, headers=None,
-                    extra_external_deps="", link_whole=False,
-                     external_dependencies=None, extra_test_libs=False):
-        if headers is not None:
+                    extra_external_deps="", link_whole=False):
+        headers_attr_prefix = ""
+        if headers is None:
+            headers_attr_prefix = "auto_"
+            headers = "AutoHeaders.RECURSIVE_GLOB"
+        else:
            headers = "[" + pretty_list(headers) + "]"
        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),
            extra_external_deps=extra_external_deps,
-            link_whole=link_whole,
-            external_dependencies=pretty_list(external_dependencies),
-            extra_test_libs=extra_test_libs
-            ).encode("utf-8"))
+            link_whole=link_whole).encode("utf-8"))
        self.total_lib = self.total_lib + 1

-    def add_rocksdb_library(self, name, srcs, headers=None,
-                            external_dependencies=None):
-        if headers is not None:
+    def add_rocksdb_library(self, name, srcs, headers=None):
+        headers_attr_prefix = ""
+        if headers is None:
+            headers_attr_prefix = "auto_"
+            headers = "AutoHeaders.RECURSIVE_GLOB"
+        else:
            headers = "[" + pretty_list(headers) + "]"
        self.targets_file.write(targets_cfg.rocksdb_library_template.format(
            name=name,
            srcs=pretty_list(srcs),
-            headers=headers,
-            external_dependencies=pretty_list(external_dependencies)
-            ).encode("utf-8")
-            )
+            headers_attr_prefix=headers_attr_prefix,
+            headers=headers).encode("utf-8"))
        self.total_lib = self.total_lib + 1

-    def add_binary(self, name, srcs, deps=None, extra_preprocessor_flags=None,extra_bench_libs=False):
+    def add_binary(self, name, srcs, deps=None):
        self.targets_file.write(targets_cfg.binary_template.format(
            name=name,
            srcs=pretty_list(srcs),
-            deps=pretty_list(deps),
-            extra_preprocessor_flags=pretty_list(extra_preprocessor_flags),
-            extra_bench_libs=extra_bench_libs,
-            ).encode("utf-8"))
+            deps=pretty_list(deps)).encode("utf-8"))
        self.total_bin = self.total_bin + 1

    def add_c_test(self):
        self.targets_file.write(b"""
-add_c_test_wrapper()
-""")
+cpp_binary(
+    name = "c_test_bin",
+    srcs = ["db/c_test.c"],
+    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
+    compiler_flags = ROCKSDB_COMPILER_FLAGS,
+    include_paths = ROCKSDB_INCLUDE_PATHS,
+    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
+    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    deps = [":rocksdb_test_lib"],
+) if not is_opt_mode else None

-    def add_test_header(self):
-        self.targets_file.write(b"""
-        # Generate a test rule for each entry in ROCKS_TESTS
-        # Do not build the tests in opt mode, since SyncPoint and other test code
-        # will not be included.
+custom_unittest(
+    name = "c_test",
+    command = [
+        native.package_name() + "/buckifier/rocks_test_runner.sh",
+        "$(location :{})".format("c_test_bin"),
+    ],
+    type = "simple",
+) if not is_opt_mode else None
 """)

-    def add_fancy_bench_config(self, name, bench_config, slow, expected_runtime, sl_iterations, regression_threshold):
-        self.targets_file.write(targets_cfg.fancy_bench_template.format(
-                    name=name,
-                    bench_config=pprint.pformat(bench_config),
-                    slow=slow,
-                    expected_runtime=expected_runtime,
-                    sl_iterations=sl_iterations,
-                    regression_threshold=regression_threshold
-                    ).encode("utf-8"))
-
    def register_test(self,
                      test_name,
                      src,
-                      deps,
+                      is_parallel,
+                      extra_deps,
                      extra_compiler_flags):
+        exec_mode = "serial"
+        if is_parallel:
+            exec_mode = "parallel"
+        self.tests_cfg += targets_cfg.test_cfg_template % (
+            test_name,
+            str(src),
+            str(exec_mode),
+            extra_deps,
+            extra_compiler_flags)

-        self.targets_file.write(targets_cfg.unittests_template.format(test_name=test_name,test_cc=str(src),deps=deps,
-            extra_compiler_flags=extra_compiler_flags).encode("utf-8"))
        self.total_test = self.total_test + 1
+
+    def flush_tests(self):
+        self.targets_file.write(targets_cfg.unittests_template.format(tests=self.tests_cfg).encode("utf-8"))
+        self.tests_cfg = ""
@@ -11,36 +11,220 @@ rocksdb_target_header_template = \
 # This file is a Facebook-specific integration for buck builds, so can
 # only be validated by Facebook employees.
 #
-# @noautodeps @nocodemods
-load("//rocks/buckifier:defs.bzl", "cpp_library_wrapper","rocks_cpp_library_wrapper","cpp_binary_wrapper","cpp_unittest_wrapper","fancy_bench_wrapper","add_c_test_wrapper")
+load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
+load("@fbcode_macros//build_defs:cpp_library.bzl", "cpp_library")
+load(":defs.bzl", "test_binary")

+REPO_PATH = package_name() + "/"
+
+ROCKSDB_COMPILER_FLAGS_0 = [
+    "-fno-builtin-memcmp",
+    # Needed to compile in fbcode
+    "-Wno-expansion-to-defined",
+    # Added missing flags from output of build_detect_platform
+    "-Wnarrowing",
+    "-DROCKSDB_NO_DYNAMIC_EXTENSION",
+]
+
+ROCKSDB_EXTERNAL_DEPS = [
+    ("bzip2", None, "bz2"),
+    ("snappy", None, "snappy"),
+    ("zlib", None, "z"),
+    ("gflags", None, "gflags"),
+    ("lz4", None, "lz4"),
+    ("zstd", None, "zstd"),
+]
+
+ROCKSDB_OS_DEPS_0 = [
+    (
+        "linux",
+        [
+            "third-party//numa:numa",
+            "third-party//liburing:uring",
+            "third-party//tbb:tbb",
+        ],
+    ),
+    (
+        "macos",
+        ["third-party//tbb:tbb"],
+    ),
+]
+
+ROCKSDB_OS_PREPROCESSOR_FLAGS_0 = [
+    (
+        "linux",
+        [
+            "-DOS_LINUX",
+            "-DROCKSDB_FALLOCATE_PRESENT",
+            "-DROCKSDB_MALLOC_USABLE_SIZE",
+            "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
+            "-DROCKSDB_RANGESYNC_PRESENT",
+            "-DROCKSDB_SCHED_GETCPU_PRESENT",
+            "-DROCKSDB_IOURING_PRESENT",
+            "-DHAVE_SSE42",
+            "-DLIBURING",
+            "-DNUMA",
+            "-DROCKSDB_PLATFORM_POSIX",
+            "-DROCKSDB_LIB_IO_POSIX",
+            "-DTBB",
+        ],
+    ),
+    (
+        "macos",
+        [
+            "-DOS_MACOSX",
+            "-DROCKSDB_PLATFORM_POSIX",
+            "-DROCKSDB_LIB_IO_POSIX",
+            "-DTBB",
+        ],
+    ),
+    (
+        "windows",
+        [
+            "-DOS_WIN",
+            "-DWIN32",
+            "-D_MBCS",
+            "-DWIN64",
+            "-DNOMINMAX",
+        ],
+    ),
+]
+
+ROCKSDB_PREPROCESSOR_FLAGS = [
+    "-DROCKSDB_SUPPORT_THREAD_LOCAL",
+
+    # Flags to enable libs we include
+    "-DSNAPPY",
+    "-DZLIB",
+    "-DBZIP2",
+    "-DLZ4",
+    "-DZSTD",
+    "-DZSTD_STATIC_LINKING_ONLY",
+    "-DGFLAGS=gflags",
+
+    # Added missing flags from output of build_detect_platform
+    "-DROCKSDB_BACKTRACE",
+]
+
+# Directories with files for #include
+ROCKSDB_INCLUDE_PATHS = [
+    "",
+    "include",
+]
+
+ROCKSDB_ARCH_PREPROCESSOR_FLAGS = {{
+    "x86_64": [
+        "-DHAVE_PCLMUL",
+    ],
+}}
+
+build_mode = read_config("fbcode", "build_mode")
+
+is_opt_mode = build_mode.startswith("opt")
+
+# -DNDEBUG is added by default in opt mode in fbcode. But adding it twice
+# doesn't harm and avoid forgetting to add it.
+ROCKSDB_COMPILER_FLAGS = ROCKSDB_COMPILER_FLAGS_0 + (["-DNDEBUG"] if is_opt_mode else [])
+
+sanitizer = read_config("fbcode", "sanitizer")
+
+# Do not enable jemalloc if sanitizer presents. RocksDB will further detect
+# whether the binary is linked with jemalloc at runtime.
+ROCKSDB_OS_PREPROCESSOR_FLAGS = ROCKSDB_OS_PREPROCESSOR_FLAGS_0 + ([(
+    "linux",
+    ["-DROCKSDB_JEMALLOC"],
+)] if sanitizer == "" else [])
+
+ROCKSDB_OS_DEPS = ROCKSDB_OS_DEPS_0 + ([(
+    "linux",
+    ["third-party//jemalloc:headers"],
+)] if sanitizer == "" else [])
+
+ROCKSDB_LIB_DEPS = [
+    ":rocksdb_lib",
+    ":rocksdb_test_lib",
+] if not is_opt_mode else [":rocksdb_lib"]
 """


 library_template = """
-cpp_library_wrapper(name="{name}", srcs=[{srcs}], deps=[{deps}], headers={headers}, link_whole={link_whole}, extra_test_libs={extra_test_libs})
+cpp_library(
+    name = "{name}",
+    srcs = [{srcs}],
+    {headers_attr_prefix}headers = {headers},
+    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
+    compiler_flags = ROCKSDB_COMPILER_FLAGS,
+    include_paths = ROCKSDB_INCLUDE_PATHS,
+    link_whole = {link_whole},
+    os_deps = ROCKSDB_OS_DEPS,
+    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
+    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    exported_deps = [{deps}],
+    exported_external_deps = ROCKSDB_EXTERNAL_DEPS{extra_external_deps},
+)
 """

 rocksdb_library_template = """
-rocks_cpp_library_wrapper(name="{name}", srcs=[{srcs}], headers={headers})
-
+cpp_library(
+    name = "{name}",
+    srcs = [{srcs}],
+    {headers_attr_prefix}headers = {headers},
+    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
+    compiler_flags = ROCKSDB_COMPILER_FLAGS,
+    include_paths = ROCKSDB_INCLUDE_PATHS,
+    os_deps = ROCKSDB_OS_DEPS,
+    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
+    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    exported_deps = ROCKSDB_LIB_DEPS,
+    exported_external_deps = ROCKSDB_EXTERNAL_DEPS,
+)
 """

-
-
 binary_template = """
-cpp_binary_wrapper(name="{name}", srcs=[{srcs}], deps=[{deps}], extra_preprocessor_flags=[{extra_preprocessor_flags}], extra_bench_libs={extra_bench_libs})
+cpp_binary(
+    name = "{name}",
+    srcs = [{srcs}],
+    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
+    compiler_flags = ROCKSDB_COMPILER_FLAGS,
+    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+    include_paths = ROCKSDB_INCLUDE_PATHS,
+    deps = [{deps}],
+    external_deps = ROCKSDB_EXTERNAL_DEPS,
+)
+"""
+
+test_cfg_template = """    [
+        "%s",
+        "%s",
+        "%s",
+        %s,
+        %s,
+    ],
 """

 unittests_template = """
-cpp_unittest_wrapper(name="{test_name}",
-            srcs=["{test_cc}"],
-            deps={deps},
-            extra_compiler_flags={extra_compiler_flags})
-
-"""
-
-fancy_bench_template = """
-fancy_bench_wrapper(suite_name="{name}", binary_to_bench_to_metric_list_map={bench_config}, slow={slow}, expected_runtime={expected_runtime}, sl_iterations={sl_iterations}, regression_threshold={regression_threshold})
+# [test_name, test_src, test_type, extra_deps, extra_compiler_flags]
+ROCKS_TESTS = [
+{tests}]

+# Generate a test rule for each entry in ROCKS_TESTS
+# Do not build the tests in opt mode, since SyncPoint and other test code
+# will not be included.
+[
+    cpp_unittest(
+        name = test_name,
+        srcs = [test_cc],
+        arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
+        compiler_flags = ROCKSDB_COMPILER_FLAGS + extra_compiler_flags,
+        include_paths = ROCKSDB_INCLUDE_PATHS,
+        os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
+        preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
+        deps = [":rocksdb_test_lib"] + extra_deps,
+        external_deps = ROCKSDB_EXTERNAL_DEPS + [
+            ("googletest", None, "gtest"),
+        ],
+    )
+    for test_name, test_cc, parallelism, extra_deps, extra_compiler_flags in ROCKS_TESTS
+    if not is_opt_mode
+]
 """
@@ -1,161 +0,0 @@
-#!/usr/bin/env python3
-#  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).
-
-'''Access the results of benchmark runs
-Send these results on to OpenSearch graphing service
-'''
-
-import argparse
-import itertools
-import os
-import re
-import sys
-import requests
-from dateutil import parser
-import logging
-
-logging.basicConfig(level=logging.DEBUG)
-class Configuration:
-    opensearch_user = os.environ['ES_USER']
-    opensearch_pass = os.environ['ES_PASS']
-
-class BenchmarkResultException(Exception):
-    def __init__(self, message, content):
-        super().__init__(self, message)
-        self.content = content
-
-
-class BenchmarkUtils:
-
-    expected_keys = ['ops_sec', 'mb_sec', 'total_size_gb', 'level0_size_gb', 'sum_gb', 'write_amplification',
-                     'write_mbps', 'usec_op', 'percentile_50', 'percentile_75',
-                     'percentile_99', 'percentile_99.9', 'percentile_99.99', 'uptime',
-                     'stall_time', 'stall_percent', 'test_name', 'test_date', 'rocksdb_version',
-                     'job_id', 'timestamp']
-
-    metric_keys = ['ops_sec', 'mb_sec', 'total_size_gb', 'level0_size_gb', 'sum_gb', 'write_amplification',
-                   'write_mbps', 'usec_op', 'percentile_50', 'percentile_75',
-                   'percentile_99', 'percentile_99.9', 'percentile_99.99', 'uptime',
-                   'stall_time', 'stall_percent']
-
-    def sanity_check(row):
-        if not 'test_name' in row:
-            return False
-        if row['test_name'] == '':
-            return False
-        if not 'test_date' in row:
-            return False
-        if not 'ops_sec' in row:
-            return False
-        try:
-            v = int(row['ops_sec'])
-        except (ValueError, TypeError):
-            return False
-        return True
-
-    def conform_opensearch(row):
-        (dt, _) = parser.parse(row['test_date'], fuzzy_with_tokens=True)
-        row['test_date'] = dt.isoformat()
-        return dict((key.replace('.', '_'), value)
-                    for (key, value) in row.items())
-
-
-class ResultParser:
-    def __init__(self, field="(\w|[+-:.])+", intrafield="(\s)+", separator="\t"):
-        self.field = re.compile(field)
-        self.intra = re.compile(intrafield)
-        self.sep = re.compile(separator)
-
-    def line(self, l_in: str):
-        '''Parse a line into items
-        Being clever about separators
-        '''
-        l = l_in
-        row = []
-        while l != '':
-            match_item = self.field.match(l)
-            if match_item:
-                item = match_item.group(0)
-                row.append(item)
-                l = l[len(item):]
-            else:
-                match_intra = self.intra.match(l)
-                if match_intra:
-                    intra = match_intra.group(0)
-                    # Count the separators
-                    # If there are >1 then generate extra blank fields
-                    # White space with no true separators fakes up a single separator
-                    tabbed = self.sep.split(intra)
-                    sep_count = len(tabbed) - 1
-                    if sep_count == 0:
-                        sep_count = 1
-                    for i in range(sep_count-1):
-                        row.append('')
-                    l = l[len(intra):]
-                else:
-                    raise BenchmarkResultException(
-                        'Invalid TSV line', f"{l_in} at {l}")
-        return row
-
-    def parse(self, lines):
-        '''Parse something that iterates lines'''
-        rows = [self.line(line) for line in lines]
-        header = rows[0]
-        width = len(header)
-        records = [{k: v for (k, v) in itertools.zip_longest(
-            header, row[:width])} for row in rows[1:]]
-        return records
-
-
-def load_report_from_tsv(filename: str):
-    file = open(filename, 'r')
-    contents = file.readlines()
-    file.close()
-    parser = ResultParser()
-    report = parser.parse(contents)
-    logging.debug(f"Loaded TSV Report: {report}")
-    return report
-
-
-def push_report_to_opensearch(report, esdocument):
-    sanitized = [BenchmarkUtils.conform_opensearch(row)
-                 for row in report if BenchmarkUtils.sanity_check(row)]
-    logging.debug(f"upload {len(sanitized)} benchmarks to opensearch")
-    for single_benchmark in sanitized:
-        logging.debug(f"upload benchmark: {single_benchmark}")
-        response = requests.post(
-            esdocument,
-            json=single_benchmark, auth=(os.environ['ES_USER'], os.environ['ES_PASS']))
-        logging.debug(
-            f"Sent to OpenSearch, status: {response.status_code}, result: {response.text}")
-        response.raise_for_status()
-
-
-def main():
-    '''Tool for fetching, parsing and uploading benchmark results to OpenSearch / ElasticSearch
-    This tool will
-
-    (1) Open a local tsv benchmark report file
-    (2) Upload to OpenSearch document, via https/JSON
-    '''
-
-    parser = argparse.ArgumentParser(
-        description='CircleCI benchmark scraper.')
-
-    # --tsvfile is the name of the file to read results from
-    # --esdocument is the ElasticSearch document to push these results into
-    #
-    parser.add_argument('--tsvfile', default='build_tools/circle_api_scraper_input.txt',
-                        help='File from which to read tsv report')
-    parser.add_argument('--esdocument', help='ElasticSearch/OpenSearch document URL to upload report into')
-
-    args = parser.parse_args()
-    logging.debug(f"Arguments: {args}")
-    reports = load_report_from_tsv(args.tsvfile)
-    push_report_to_opensearch(reports, args.esdocument)
-
-if __name__ == '__main__':
-    sys.exit(main())
@@ -45,11 +45,11 @@ if test -z "$OUTPUT"; then
  exit 1
 fi

-# we depend on C++17, but should be compatible with newer standards
+# we depend on C++11, but should be compatible with newer standards
 if [ "$ROCKSDB_CXX_STANDARD" ]; then
  PLATFORM_CXXFLAGS="-std=$ROCKSDB_CXX_STANDARD"
 else
-  PLATFORM_CXXFLAGS="-std=c++17"
+  PLATFORM_CXXFLAGS="-std=c++11"
 fi

 # we currently depend on POSIX platform
@@ -58,13 +58,15 @@ COMMON_FLAGS="-DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX"
 # Default to fbcode gcc on internal fb machines
 if [ -z "$ROCKSDB_NO_FBCODE" -a -d /mnt/gvfs/third-party ]; then
    FBCODE_BUILD="true"
-    # If we're compiling with TSAN or shared lib, we need pic build
+    # If we're compiling with TSAN we need pic build
    PIC_BUILD=$COMPILE_WITH_TSAN
-    if [ "$LIB_MODE" == "shared" ]; then
-      PIC_BUILD=1
-    fi
-    if [ -n "$ROCKSDB_FBCODE_BUILD_WITH_PLATFORM010" ]; then
-      source "$PWD/build_tools/fbcode_config_platform010.sh"
+    if [ -n "$ROCKSDB_FBCODE_BUILD_WITH_481" ]; then
+      # we need this to build with MySQL. Don't use for other purposes.
+      source "$PWD/build_tools/fbcode_config4.8.1.sh"
+    elif [ -n "$ROCKSDB_FBCODE_BUILD_WITH_5xx" ]; then
+      source "$PWD/build_tools/fbcode_config.sh"
+    elif [ -n "$ROCKSDB_FBCODE_BUILD_WITH_PLATFORM007" ]; then
+      source "$PWD/build_tools/fbcode_config_platform007.sh"
    elif [ -n "$ROCKSDB_FBCODE_BUILD_WITH_PLATFORM009" ]; then
      source "$PWD/build_tools/fbcode_config_platform009.sh"
    else
@@ -174,7 +176,7 @@ case "$TARGET_OS" in
        fi
        if test "$ROCKSDB_USE_IO_URING" -ne 0; then
            # check for liburing
-            $CXX $PLATFORM_CXXFLAGS -x c++ - -luring -o test.o 2>/dev/null  <<EOF
+            $CXX $PLATFORM_CXXFLAGS -x c++ - -luring -o /dev/null 2>/dev/null  <<EOF
              #include <liburing.h>
              int main() {
                struct io_uring ring;
@@ -269,7 +271,7 @@ esac
 PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS ${CXXFLAGS}"
 JAVA_LDFLAGS="$PLATFORM_LDFLAGS"
 JAVA_STATIC_LDFLAGS="$PLATFORM_LDFLAGS"
-JAVAC_ARGS="-source 8"
+JAVAC_ARGS="-source 7"

 if [ "$CROSS_COMPILE" = "true" -o "$FBCODE_BUILD" = "true" ]; then
    # Cross-compiling; do not try any compilation tests.
@@ -282,7 +284,7 @@ if [ "$CROSS_COMPILE" = "true" -o "$FBCODE_BUILD" = "true" ]; then
 else
    if ! test $ROCKSDB_DISABLE_FALLOCATE; then
        # Test whether fallocate is available
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <fcntl.h>
          #include <linux/falloc.h>
          int main() {
@@ -298,7 +300,7 @@ EOF
    if ! test $ROCKSDB_DISABLE_SNAPPY; then
        # Test whether Snappy library is installed
        # http://code.google.com/p/snappy/
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <snappy.h>
          int main() {}
 EOF
@@ -313,7 +315,7 @@ EOF
        # Test whether gflags library is installed
        # http://gflags.github.io/gflags/
        # check if the namespace is gflags
-        if $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null << EOF
+        if $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
          #include <gflags/gflags.h>
          using namespace GFLAGS_NAMESPACE;
          int main() {}
@@ -322,7 +324,7 @@ EOF
          COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=1"
          PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
        # check if namespace is gflags
-        elif $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null << EOF
+        elif $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
            #include <gflags/gflags.h>
            using namespace gflags;
            int main() {}
@@ -331,7 +333,7 @@ EOF
          COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=1 -DGFLAGS_NAMESPACE=gflags"
          PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
        # check if namespace is google
-        elif $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null << EOF
+        elif $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
            #include <gflags/gflags.h>
            using namespace google;
            int main() {}
@@ -344,7 +346,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_ZLIB; then
        # Test whether zlib library is installed
-        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <zlib.h>
          int main() {}
 EOF
@@ -357,7 +359,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_BZIP; then
        # Test whether bzip library is installed
-        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <bzlib.h>
          int main() {}
 EOF
@@ -370,7 +372,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_LZ4; then
        # Test whether lz4 library is installed
-        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <lz4.h>
          #include <lz4hc.h>
          int main() {}
@@ -397,7 +399,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_NUMA; then
        # Test whether numa is available
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o -lnuma 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null -lnuma 2>/dev/null  <<EOF
          #include <numa.h>
          #include <numaif.h>
          int main() {}
@@ -411,7 +413,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_TBB; then
        # Test whether tbb is available
-        $CXX $PLATFORM_CXXFLAGS $LDFLAGS -x c++ - -o test.o -ltbb 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $LDFLAGS -x c++ - -o /dev/null -ltbb 2>/dev/null  <<EOF
          #include <tbb/tbb.h>
          int main() {}
 EOF
@@ -424,7 +426,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_JEMALLOC; then
        # Test whether jemalloc is available
-        if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o -ljemalloc \
+        if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null -ljemalloc \
          2>/dev/null; then
            # This will enable some preprocessor identifiers in the Makefile
            JEMALLOC=1
@@ -445,7 +447,7 @@ EOF
    fi
    if ! test $JEMALLOC && ! test $ROCKSDB_DISABLE_TCMALLOC; then
        # jemalloc is not available. Let's try tcmalloc
-        if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o \
+        if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null \
          -ltcmalloc 2>/dev/null; then
            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltcmalloc"
            JAVA_LDFLAGS="$JAVA_LDFLAGS -ltcmalloc"
@@ -454,7 +456,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_MALLOC_USABLE_SIZE; then
        # Test whether malloc_usable_size is available
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <malloc.h>
          int main() {
            size_t res = malloc_usable_size(0);
@@ -469,7 +471,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_MEMKIND; then
        # Test whether memkind library is installed
-        $CXX $PLATFORM_CXXFLAGS $LDFLAGS -x c++ - -o test.o -lmemkind 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -lmemkind -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <memkind.h>
          int main() {
            memkind_malloc(MEMKIND_DAX_KMEM, 1024);
@@ -485,7 +487,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_PTHREAD_MUTEX_ADAPTIVE_NP; then
        # Test whether PTHREAD_MUTEX_ADAPTIVE_NP mutex type is available
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <pthread.h>
          int main() {
            int x = PTHREAD_MUTEX_ADAPTIVE_NP;
@@ -500,7 +502,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_BACKTRACE; then
        # Test whether backtrace is available
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <execinfo.h>
          int main() {
            void* frames[1];
@@ -512,7 +514,7 @@ EOF
            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
        else
            # Test whether execinfo library is installed
-            $CXX $PLATFORM_CXXFLAGS -lexecinfo -x c++ - -o test.o 2>/dev/null  <<EOF
+            $CXX $PLATFORM_CXXFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null  <<EOF
              #include <execinfo.h>
              int main() {
                void* frames[1];
@@ -529,7 +531,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_PG; then
        # Test if -pg is supported
-        $CXX $PLATFORM_CXXFLAGS -pg -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -pg -x c++ - -o /dev/null 2>/dev/null  <<EOF
          int main() {
            return 0;
          }
@@ -541,7 +543,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_SYNC_FILE_RANGE; then
        # Test whether sync_file_range is supported for compatibility with an old glibc
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <fcntl.h>
          int main() {
            int fd = open("/dev/null", 0);
@@ -555,7 +557,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_SCHED_GETCPU; then
        # Test whether sched_getcpu is supported
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <sched.h>
          int main() {
            int cpuid = sched_getcpu();
@@ -569,7 +571,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_AUXV_GETAUXVAL; then
        # Test whether getauxval is supported
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
          #include <sys/auxv.h>
          int main() {
            uint64_t auxv = getauxval(AT_HWCAP);
@@ -583,7 +585,7 @@ EOF

    if ! test $ROCKSDB_DISABLE_ALIGNED_NEW; then
        # Test whether c++17 aligned-new is supported
-        $CXX $PLATFORM_CXXFLAGS -faligned-new -x c++ - -o test.o 2>/dev/null <<EOF
+        $CXX $PLATFORM_CXXFLAGS -faligned-new -x c++ - -o /dev/null 2>/dev/null <<EOF
            struct alignas(1024) t {int a;};
            int main() {}
 EOF
@@ -593,7 +595,7 @@ EOF
    fi
    if ! test $ROCKSDB_DISABLE_BENCHMARK; then
        # Test whether google benchmark is available
-        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null -lbenchmark -lpthread 2>/dev/null  <<EOF
+        $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null -lbenchmark 2>/dev/null  <<EOF
          #include <benchmark/benchmark.h>
          int main() {}
 EOF
@@ -607,7 +609,7 @@ fi
 # -Wshorten-64-to-32 breaks compilation on FreeBSD aarch64 and i386
 if ! { [ "$TARGET_OS" = FreeBSD ] && [ "$TARGET_ARCHITECTURE" = arm64 -o "$TARGET_ARCHITECTURE" = i386 ]; }; then
  # Test whether -Wshorten-64-to-32 is available
-  $CXX $PLATFORM_CXXFLAGS -x c++ - -o test.o -Wshorten-64-to-32 2>/dev/null  <<EOF
+  $CXX $PLATFORM_CXXFLAGS -x c++ - -o /dev/null -Wshorten-64-to-32 2>/dev/null  <<EOF
    int main() {}
 EOF
  if [ "$?" = 0 ]; then
@@ -615,6 +617,22 @@ EOF
  fi
 fi

+# shall we use HDFS?
+
+if test "$USE_HDFS"; then
+  if test -z "$JAVA_HOME"; then
+    echo "JAVA_HOME has to be set for HDFS usage." >&2
+    exit 1
+  fi
+  HDFS_CCFLAGS="$HDFS_CCFLAGS -I$JAVA_HOME/include -I$JAVA_HOME/include/linux -DUSE_HDFS -I$HADOOP_HOME/include"
+  HDFS_LDFLAGS="$HDFS_LDFLAGS -lhdfs -L$JAVA_HOME/jre/lib/amd64 -L$HADOOP_HOME/lib/native"
+  HDFS_LDFLAGS="$HDFS_LDFLAGS -L$JAVA_HOME/jre/lib/amd64/server -L$GLIBC_RUNTIME_PATH/lib"
+  HDFS_LDFLAGS="$HDFS_LDFLAGS -ldl -lverify -ljava -ljvm"
+  COMMON_FLAGS="$COMMON_FLAGS $HDFS_CCFLAGS"
+  PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS $HDFS_LDFLAGS"
+  JAVA_LDFLAGS="$JAVA_LDFLAGS $HDFS_LDFLAGS"
+fi
+
 if test "0$PORTABLE" -eq 0; then
  if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
    # Tune for this POWER processor, treating '+' models as base models
@@ -627,15 +645,12 @@ if test "0$PORTABLE" -eq 0; then
    COMMON_FLAGS="$COMMON_FLAGS"
  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
    if echo 'int main() {}' | $CXX $PLATFORM_CXXFLAGS -x c++ \
-      -march=native - -o /dev/null 2>/dev/null; then
+      -fsyntax-only -march=native - -o /dev/null 2>/dev/null; then
      COMMON_FLAGS="$COMMON_FLAGS -march=native "
    else
      COMMON_FLAGS="$COMMON_FLAGS -march=z196 "
    fi
    COMMON_FLAGS="$COMMON_FLAGS"
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^riscv64`"; then
-    RISC_ISA=$(cat /proc/cpuinfo | grep isa | head -1 | cut --delimiter=: -f 2 | cut -b 2-)
-    COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
  elif [ "$TARGET_OS" == "IOS" ]; then
    COMMON_FLAGS="$COMMON_FLAGS"
  elif [ "$TARGET_OS" == "AIX" ] || [ "$TARGET_OS" == "SunOS" ]; then
@@ -656,19 +671,14 @@ else
    COMMON_FLAGS="$COMMON_FLAGS -march=z196 "
  fi

-  if test -n "`echo $TARGET_ARCHITECTURE | grep ^riscv64`"; then
-    RISC_ISA=$(cat /proc/cpuinfo | grep isa | head -1 | cut --delimiter=: -f 2 | cut -b 2-)
-    COMMON_FLAGS="$COMMON_FLAGS -march=${RISC_ISA}"
-  fi
-
  if [[ "${PLATFORM}" == "OS_MACOSX" ]]; then
-    # For portability compile for macOS 10.13 (2017) or newer
-    COMMON_FLAGS="$COMMON_FLAGS -mmacosx-version-min=10.13"
-    PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -mmacosx-version-min=10.13"
+    # For portability compile for macOS 10.12 (2016) or newer
+    COMMON_FLAGS="$COMMON_FLAGS -mmacosx-version-min=10.12"
+    PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -mmacosx-version-min=10.12"
    # -mmacosx-version-min must come first here.
-    PLATFORM_SHARED_LDFLAGS="-mmacosx-version-min=10.13 $PLATFORM_SHARED_LDFLAGS"
-    PLATFORM_CMAKE_FLAGS="-DCMAKE_OSX_DEPLOYMENT_TARGET=10.13"
-    JAVA_STATIC_DEPS_COMMON_FLAGS="-mmacosx-version-min=10.13"
+    PLATFORM_SHARED_LDFLAGS="-mmacosx-version-min=10.12 $PLATFORM_SHARED_LDFLAGS"
+    PLATFORM_CMAKE_FLAGS="-DCMAKE_OSX_DEPLOYMENT_TARGET=10.12"
+    JAVA_STATIC_DEPS_COMMON_FLAGS="-mmacosx-version-min=10.12"
    JAVA_STATIC_DEPS_LDFLAGS="$JAVA_STATIC_DEPS_COMMON_FLAGS"
    JAVA_STATIC_DEPS_CCFLAGS="$JAVA_STATIC_DEPS_COMMON_FLAGS"
    JAVA_STATIC_DEPS_CXXFLAGS="$JAVA_STATIC_DEPS_COMMON_FLAGS"
@@ -713,7 +723,7 @@ if test "$TRY_SSE_ETC"; then
  TRY_LZCNT="-mlzcnt"
 fi

-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_SSE42 -x c++ - -o test.o 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_SSE42 -x c++ - -o /dev/null 2>/dev/null <<EOF
  #include <cstdint>
  #include <nmmintrin.h>
  int main() {
@@ -727,7 +737,7 @@ elif test "$USE_SSE"; then
  echo "warning: USE_SSE specified but compiler could not use SSE intrinsics, disabling" >&2
 fi

-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o test.o 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_PCLMUL -x c++ - -o /dev/null 2>/dev/null <<EOF
  #include <cstdint>
  #include <wmmintrin.h>
  int main() {
@@ -744,7 +754,7 @@ elif test "$USE_SSE"; then
  echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling" >&2
 fi

-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_AVX2 -x c++ - -o test.o 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_AVX2 -x c++ - -o /dev/null 2>/dev/null <<EOF
  #include <cstdint>
  #include <immintrin.h>
  int main() {
@@ -759,7 +769,7 @@ elif test "$USE_SSE"; then
  echo "warning: USE_SSE specified but compiler could not use AVX2 intrinsics, disabling" >&2
 fi

-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_BMI -x c++ - -o test.o 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_BMI -x c++ - -o /dev/null 2>/dev/null <<EOF
  #include <cstdint>
  #include <immintrin.h>
  int main(int argc, char *argv[]) {
@@ -773,7 +783,7 @@ elif test "$USE_SSE"; then
  echo "warning: USE_SSE specified but compiler could not use BMI intrinsics, disabling" >&2
 fi

-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_LZCNT -x c++ - -o test.o 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_LZCNT -x c++ - -o /dev/null 2>/dev/null <<EOF
  #include <cstdint>
  #include <immintrin.h>
  int main(int argc, char *argv[]) {
@@ -787,7 +797,7 @@ elif test "$USE_SSE"; then
  echo "warning: USE_SSE specified but compiler could not use LZCNT intrinsics, disabling" >&2
 fi

-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o test.o 2>/dev/null <<EOF
+$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
  #include <cstdint>
  int main() {
    uint64_t a = 0xffffFFFFffffFFFF;
@@ -800,12 +810,31 @@ if [ "$?" = 0 ]; then
  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_UINT128_EXTENSION"
 fi

+# iOS doesn't support thread-local storage, but this check would erroneously
+# succeed because the cross-compiler flags are added by the Makefile, not this
+# script.
+if [ "$PLATFORM" != IOS ]; then
+  $CXX $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
+  #if defined(_MSC_VER) && !defined(__thread)
+  #define __thread __declspec(thread)
+  #endif
+  int main() {
+    static __thread int tls;
+    (void)tls;
+  }
+EOF
+  if [ "$?" = 0 ]; then
+    COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_SUPPORT_THREAD_LOCAL"
+  fi
+fi
+
+
 if [ "$FBCODE_BUILD" != "true" -a "$PLATFORM" = OS_LINUX ]; then
  $CXX $COMMON_FLAGS $PLATFORM_SHARED_CFLAGS -x c++ -c - -o test_dl.o 2>/dev/null <<EOF
  void dummy_func() {}
 EOF
  if [ "$?" = 0 ]; then
-    $CXX $COMMON_FLAGS $PLATFORM_SHARED_LDFLAGS test_dl.o -o test.o 2>/dev/null
+    $CXX $COMMON_FLAGS $PLATFORM_SHARED_LDFLAGS test_dl.o -o /dev/null 2>/dev/null
    if [ "$?" = 0 ]; then
      EXEC_LDFLAGS+="-ldl"
      rm -f test_dl.o
@@ -813,20 +842,6 @@ EOF
  fi
 fi

-# check for F_FULLFSYNC
-$CXX $PLATFORM_CXXFALGS -x c++ - -o test.o 2>/dev/null  <<EOF
-  #include <fcntl.h>
-  int main() {
-    fcntl(0, F_FULLFSYNC);
-    return 0;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_FULLFSYNC"
-fi
-
-rm -f test.o test_dl.o
-
 PLATFORM_CCFLAGS="$PLATFORM_CCFLAGS $COMMON_FLAGS"
 PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS $COMMON_FLAGS"

@@ -877,8 +892,8 @@ if test -n "$WITH_JEMALLOC_FLAG"; then
  echo "WITH_JEMALLOC_FLAG=$WITH_JEMALLOC_FLAG" >> "$OUTPUT"
 fi
 echo "LUA_PATH=$LUA_PATH" >> "$OUTPUT"
-if test -n "$USE_FOLLY"; then
-  echo "USE_FOLLY=$USE_FOLLY" >> "$OUTPUT"
+if test -n "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
+  echo "USE_FOLLY_DISTRIBUTED_MUTEX=$USE_FOLLY_DISTRIBUTED_MUTEX" >> "$OUTPUT"
 fi
 if test -n "$PPC_LIBC_IS_GNU"; then
  echo "PPC_LIBC_IS_GNU=$PPC_LIBC_IS_GNU" >> "$OUTPUT"
@@ -5,44 +5,24 @@

 BAD=""

-git grep -n 'namespace rocksdb' -- '*.[ch]*'
+git grep 'namespace rocksdb' -- '*.[ch]*'
 if [ "$?" != "1" ]; then
  echo "^^^^^ Do not hardcode namespace rocksdb. Use ROCKSDB_NAMESPACE"
  BAD=1
 fi

-git grep -n -i 'nocommit' -- ':!build_tools/check-sources.sh'
+git grep -i 'nocommit' -- ':!build_tools/check-sources.sh'
 if [ "$?" != "1" ]; then
  echo "^^^^^ Code was not intended to be committed"
  BAD=1
 fi

-git grep -n 'include <rocksdb/' -- ':!build_tools/check-sources.sh'
+git grep '<rocksdb/' -- ':!build_tools/check-sources.sh'
 if [ "$?" != "1" ]; then
  echo '^^^^^ Use double-quotes as in #include "rocksdb/something.h"'
  BAD=1
 fi

-git grep -n 'include "include/rocksdb/' -- ':!build_tools/check-sources.sh'
-if [ "$?" != "1" ]; then
-  echo '^^^^^ Use #include "rocksdb/something.h" instead of #include "include/rocksdb/something.h"'
-  BAD=1
-fi
-
-git grep -n 'using namespace' -- ':!build_tools' ':!docs' \
-    ':!third-party/folly/folly/lang/Align.h' \
-    ':!third-party/gtest-1.8.1/fused-src/gtest/gtest.h'
-if [ "$?" != "1" ]; then
-  echo '^^^^ Do not use "using namespace"'
-  BAD=1
-fi
-
-git grep -n -P "[\x80-\xFF]" -- ':!docs' ':!*.md'
-if [ "$?" != "1" ]; then
-  echo '^^^^ Use only ASCII characters in source files'
-  BAD=1
-fi
-
 if [ "$BAD" ]; then
  exit 1
 fi
@@ -0,0 +1,19 @@
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/5.x/centos7-native/c447969
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/1bd23f9917738974ad0ff305aa23eb5f93f18305/9.0.0/centos7-native/c9f9104
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/5.x/gcc-5-glibc-2.23/339d858
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.23/gcc-5-glibc-2.23/ca1d1c0
+SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/gcc-5-glibc-2.23/9bc6787
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/gcc-5-glibc-2.23/9bc6787
+BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/gcc-5-glibc-2.23/9bc6787
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/gcc-5-glibc-2.23/9bc6787
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/gcc-5-glibc-2.23/03859b5
+GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/gcc-5-glibc-2.23/9bc6787
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/gcc-5-glibc-2.23/0c8f76d
+NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/gcc-5-glibc-2.23/9bc6787
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/gcc-5-glibc-2.23/b443de1
+TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/gcc-5-glibc-2.23/9bc6787
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/2e3cb7d119b3cea5f1e738cc13a1ac69f49eb875/2.29.1/centos7-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/gcc-5-glibc-2.23/9bc6787
+LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.2.3/gcc-5-glibc-2.23/65372bd
@@ -0,0 +1,20 @@
+# shellcheck disable=SC2148
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+GCC_BASE=/mnt/gvfs/third-party2/gcc/cf7d14c625ce30bae1a4661c2319c5a283e4dd22/4.8.1/centos6-native/cc6c9dc
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/8598c375b0e94e1448182eb3df034704144a838d/stable/centos6-native/3f16ddd
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/d6e0a7da6faba45f5e5b1638f9edd7afc2f34e7d/4.8.1/gcc-4.8.1-glibc-2.17/8aac7fc
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/d282e6e8f3d20f4e40a516834847bdc038e07973/2.17/gcc-4.8.1-glibc-2.17/99df8fc
+SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/8c38a4c1e52b4c2cc8a9cdc31b9c947ed7dbfcb4/1.1.3/gcc-4.8.1-glibc-2.17/c3f970a
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/0882df3713c7a84f15abe368dc004581f20b39d7/1.2.8/gcc-4.8.1-glibc-2.17/c3f970a
+BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/740325875f6729f42d28deaa2147b0854f3a347e/1.0.6/gcc-4.8.1-glibc-2.17/c3f970a
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/0e790b441e2d9acd68d51e1d2e028f88c6a79ddf/r131/gcc-4.8.1-glibc-2.17/c3f970a
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/9455f75ff7f4831dc9fda02a6a0f8c68922fad8f/1.0.0/gcc-4.8.1-glibc-2.17/c3f970a
+GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/f001a51b2854957676d07306ef3abf67186b5c8b/2.1.1/gcc-4.8.1-glibc-2.17/c3f970a
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/fc8a13ca1fffa4d0765c716c5a0b49f0c107518f/master/gcc-4.8.1-glibc-2.17/8d31e51
+NUMA_BASE=/mnt/gvfs/third-party2/numa/17c514c4d102a25ca15f4558be564eeed76f4b6a/2.0.8/gcc-4.8.1-glibc-2.17/c3f970a
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/ad576de2a1ea560c4d3434304f0fc4e079bede42/trunk/gcc-4.8.1-glibc-2.17/675d945
+TBB_BASE=/mnt/gvfs/third-party2/tbb/9d9a554877d0c5bef330fe818ab7178806dd316a/4.0_update2/gcc-4.8.1-glibc-2.17/c3f970a
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/7c111ff27e0c466235163f00f280a9d617c3d2ec/4.0.9-36_fbk5_2933_gd092e3f/gcc-4.8.1-glibc-2.17/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/b7fd454c4b10c6a81015d4524ed06cdeab558490/2.26/centos6-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d7f4d4d86674a57668e3a96f76f0e17dd0eb8765/3.8.1/gcc-4.8.1-glibc-2.17/c3f970a
+LUA_BASE=/mnt/gvfs/third-party2/lua/61e4abf5813bbc39bc4f548757ccfcadde175a48/5.2.3/centos6-native/730f94e
@@ -0,0 +1,20 @@
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/7.x/centos7-native/b2ef2b6
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/963d9aeda70cc4779885b1277484fe7544a04e3e/9.0.0/platform007/9e92d53/
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/7.x/platform007/5620abc
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.26/platform007/f259413
+SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/platform007/ca4da3d
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/platform007/ca4da3d
+BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/platform007/ca4da3d
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/platform007/ca4da3d
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/platform007/15a3614
+GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/platform007/ca4da3d
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/platform007/c26c002
+NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/platform007/ca4da3d
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/platform007/6f3e0a9
+TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/platform007/ca4da3d
+LIBURING_BASE=/mnt/gvfs/third-party2/liburing/79427253fd0d42677255aacfe6d13bfe63f752eb/20190828/platform007/ca4da3d
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/fb/platform007/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/ab9f09bba370e7066cafd4eb59752db93f2e8312/2.29.1/platform007/15a3614
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/platform007/ca4da3d
+LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.3.4/platform007/5007832
@@ -9,7 +9,7 @@ BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/73a237ac5bc0a5f5d67b39b8d253cfebaab88684
 LZ4_BASE=/mnt/gvfs/third-party2/lz4/ec6573523b0ce55ef6373a4801189027cf07bb2c/1.9.1/platform009/7f3b187
 ZSTD_BASE=/mnt/gvfs/third-party2/zstd/64c58a207d2495e83abc57a500a956df09b79a7c/1.4.x/platform009/ba86d1f
 GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/824d0a8a5abb5b121afd1b35fc3896407ea50092/2.2.0/platform009/7f3b187
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/b62912d333ef33f9760efa6219dbe3fe6abb3b0e/master/platform009/c305944
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/d9aef9feb850b168a68736420f217b01cce11a89/master/platform009/c305944
 NUMA_BASE=/mnt/gvfs/third-party2/numa/0af65f71e23a67bf65dc91b11f95caa39325c432/2.0.11/platform009/7f3b187
 LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/02486dac347645d31dce116f44e1de3177315be2/1.4/platform009/5191652
 TBB_BASE=/mnt/gvfs/third-party2/tbb/2e0ec671e550bfca347300bf3f789d9c0fff24ad/2018_U5/platform009/7f3b187
@@ -18,9 +18,4 @@ KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/32b8a2407b634df3f8f948
 BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/08634589372fa5f237bfd374e8c644a8364e78c1/2.32/platform009/ba86d1f/
 VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/6ae525939ad02e5e676855082fbbc7828dbafeac/3.15.0/platform009/7f3b187
 LUA_BASE=/mnt/gvfs/third-party2/lua/162efd9561a3d21f6869f4814011e9cf1b3ff4dc/5.3.4/platform009/a6271c4
-BENCHMARK_BASE=/mnt/gvfs/third-party2/benchmark/30bf49ad6414325e17f3425b0edcb64239427ae3/1.6.1/platform009/7f3b187
-BOOST_BASE=/mnt/gvfs/third-party2/boost/201b7d74941e54b436dfa364a063aa6d2cd7de4c/1.69.0/platform009/8a7ffdf
-GLOG_BASE=/mnt/gvfs/third-party2/glog/32d751bd5673375b438158717ab6a57c1cc57e3d/0.3.2_fb/platform009/10a364d/
-FMT_BASE=/mnt/gvfs/third-party2/fmt/ce0c25f67165f4d2c22a29b8ef50f5600d7873ca/6.1.1/platform009/7f3b187/
-DBL_CONV_BASE=/mnt/gvfs/third-party2/double_conversion/109b3d9696d71f1048678cd7da1e22505470543d/20141126/platform009/7f3b187/
-LIBEVENT_BASE=/mnt/gvfs/third-party2/libevent/4a4d3a79a76c2439b6bd471bf3586b3481dde75e/1.4.14b_hphp/platform009/7f3b187/
+BENCHMARK_BASE=/mnt/gvfs/third-party2/benchmark/bce8d9564eaf161700aa3a20b1051564acf555fb/1.5.5/platform009/7f3b187
@@ -1,22 +0,0 @@
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-# The file is generated using update_dependencies.sh.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/e40bde78650fa91b8405a857e3f10bf336633fb0/11.x/centos7-native/886b5eb
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/2043340983c032915adbb6f78903dc855b65aee8/12/platform010/9520e0f
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/c00dcc6a3e4125c7e8b248e9a79c14b78ac9e0ca/11.x/platform010/5684a5a
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/0b9c8e4b060eda62f3bc1c6127bbe1256697569b/2.34/platform010/f259413
-SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/bc9647f7912b131315827d65cb6189c21f381d05/1.1.3/platform010/76ebdda
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/a6f5f3f1d063d2d00cd02fc12f0f05fc3ab3a994/1.2.11/platform010/76ebdda
-BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/09703139cfc376bd8a82642385a0e97726b28287/1.0.6/platform010/76ebdda
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/60220d6a5bf7722b9cc239a1368c596619b12060/1.9.1/platform010/76ebdda
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/50eace8143eaaea9473deae1f3283e0049e05633/1.4.x/platform010/64091f4
-GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/5d27e5919771603da06000a027b12f799e58a4f7/2.2.0/platform010/76ebdda
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/b62912d333ef33f9760efa6219dbe3fe6abb3b0e/master/platform010/f57cc4a
-NUMA_BASE=/mnt/gvfs/third-party2/numa/6b412770957aa3c8a87e5e0dcd8cc2f45f393bc0/2.0.11/platform010/76ebdda
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/52f69816e936e147664ad717eb71a1a0e9dc973a/1.4/platform010/5074a48
-TBB_BASE=/mnt/gvfs/third-party2/tbb/c9cc192099fa84c0dcd0ffeedd44a373ad6e4925/2018_U5/platform010/76ebdda
-LIBURING_BASE=/mnt/gvfs/third-party2/liburing/a98e2d137007e3ebf7f33bd6f99c2c56bdaf8488/20210212/platform010/76ebdda
-BENCHMARK_BASE=/mnt/gvfs/third-party2/benchmark/780c7a0f9cf0967961e69ad08e61cddd85d61821/trunk/platform010/76ebdda
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/02d9f76aaaba580611cf75e741753c800c7fdc12/fb/platform010/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/938dc3f064ef3a48c0446f5b11d788d50b3eb5ee/2.37/centos7-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/429a6b3203eb415f1599bd15183659153129188e/3.15.0/platform010/76ebdda
-LUA_BASE=/mnt/gvfs/third-party2/lua/363787fa5cac2a8aa20638909210443278fa138e/5.3.4/platform010/9079c97
@@ -21,48 +21,38 @@ LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"
 GLIBC_INCLUDE="$GLIBC_BASE/include"
 GLIBC_LIBS=" -L $GLIBC_BASE/lib"

-if ! test $ROCKSDB_DISABLE_SNAPPY; then
-  # snappy
-  SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
-  if test -z $PIC_BUILD; then
-    SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy.a"
-  else
-    SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy_pic.a"
-  fi
-  CFLAGS+=" -DSNAPPY"
+# snappy
+SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
+if test -z $PIC_BUILD; then
+  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy.a"
+else
+  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy_pic.a"
 fi
+CFLAGS+=" -DSNAPPY"

 if test -z $PIC_BUILD; then
-  if ! test $ROCKSDB_DISABLE_ZLIB; then
-    # location of zlib headers and libraries
-    ZLIB_INCLUDE=" -I $ZLIB_BASE/include/"
-    ZLIB_LIBS=" $ZLIB_BASE/lib/libz.a"
-    CFLAGS+=" -DZLIB"
-  fi
+  # location of zlib headers and libraries
+  ZLIB_INCLUDE=" -I $ZLIB_BASE/include/"
+  ZLIB_LIBS=" $ZLIB_BASE/lib/libz.a"
+  CFLAGS+=" -DZLIB"

-  if ! test $ROCKSDB_DISABLE_BZIP; then
-    # location of bzip headers and libraries
-    BZIP_INCLUDE=" -I $BZIP2_BASE/include/"
-    BZIP_LIBS=" $BZIP2_BASE/lib/libbz2.a"
-    CFLAGS+=" -DBZIP2"
-  fi
+  # location of bzip headers and libraries
+  BZIP_INCLUDE=" -I $BZIP2_BASE/include/"
+  BZIP_LIBS=" $BZIP2_BASE/lib/libbz2.a"
+  CFLAGS+=" -DBZIP2"

-  if ! test $ROCKSDB_DISABLE_LZ4; then
-    LZ4_INCLUDE=" -I $LZ4_BASE/include/"
-    LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
-    CFLAGS+=" -DLZ4"
-  fi
+  LZ4_INCLUDE=" -I $LZ4_BASE/include/"
+  LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
+  CFLAGS+=" -DLZ4"
 fi

-if ! test $ROCKSDB_DISABLE_ZSTD; then
-  ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
-  if test -z $PIC_BUILD; then
-    ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
-  else
-    ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd_pic.a"
-  fi
-  CFLAGS+=" -DZSTD -DZSTD_STATIC_LINKING_ONLY"
+ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
+if test -z $PIC_BUILD; then
+  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
+else
+  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd_pic.a"
 fi
+CFLAGS+=" -DZSTD -DZSTD_STATIC_LINKING_ONLY"

 # location of gflags headers and libraries
 GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
@@ -147,7 +137,7 @@ else
 fi

 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DHAVE_SSE42"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42"
 CXXFLAGS+=" $CFLAGS"

 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"
@@ -172,4 +162,6 @@ else
  LUA_LIB=" $LUA_PATH/lib/liblua_pic.a"
 fi

+USE_FOLLY_DISTRIBUTED_MUTEX=1
+
 export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD LUA_PATH LUA_LIB
@@ -0,0 +1,120 @@
+#!/bin/sh
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+#
+# Set environment variables so that we can compile rocksdb using
+# fbcode settings.  It uses the latest g++ compiler and also
+# uses jemalloc
+
+BASEDIR=`dirname $BASH_SOURCE`
+source "$BASEDIR/dependencies_4.8.1.sh"
+
+# location of libgcc
+LIBGCC_INCLUDE="$LIBGCC_BASE/include"
+LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"
+
+# location of glibc
+GLIBC_INCLUDE="$GLIBC_BASE/include"
+GLIBC_LIBS=" -L $GLIBC_BASE/lib"
+
+# location of snappy headers and libraries
+SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include"
+SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy.a"
+
+# location of zlib headers and libraries
+ZLIB_INCLUDE=" -I $ZLIB_BASE/include"
+ZLIB_LIBS=" $ZLIB_BASE/lib/libz.a"
+
+# location of bzip headers and libraries
+BZIP2_INCLUDE=" -I $BZIP2_BASE/include/"
+BZIP2_LIBS=" $BZIP2_BASE/lib/libbz2.a"
+
+LZ4_INCLUDE=" -I $LZ4_BASE/include"
+LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
+
+ZSTD_INCLUDE=" -I $ZSTD_BASE/include"
+ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
+
+# location of gflags headers and libraries
+GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
+GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags.a"
+
+# location of jemalloc
+JEMALLOC_INCLUDE=" -I $JEMALLOC_BASE/include"
+JEMALLOC_LIB="$JEMALLOC_BASE/lib/libjemalloc.a"
+
+# location of numa
+NUMA_INCLUDE=" -I $NUMA_BASE/include/"
+NUMA_LIB=" $NUMA_BASE/lib/libnuma.a"
+
+# location of libunwind
+LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
+
+# location of tbb
+TBB_INCLUDE=" -isystem $TBB_BASE/include/"
+TBB_LIBS="$TBB_BASE/lib/libtbb.a"
+
+test "$USE_SSE" || USE_SSE=1
+export USE_SSE
+test "$PORTABLE" || PORTABLE=1
+export PORTABLE
+
+BINUTILS="$BINUTILS_BASE/bin"
+AR="$BINUTILS/ar"
+
+DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP2_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE"
+
+STDLIBS="-L $GCC_BASE/lib64"
+
+if [ -z "$USE_CLANG" ]; then
+  # gcc
+  CC="$GCC_BASE/bin/gcc"
+  CXX="$GCC_BASE/bin/g++"
+  CXX="$GCC_BASE/bin/gcc-ar"
+
+  CFLAGS="-B$BINUTILS/gold -m64 -mtune=generic"
+  CFLAGS+=" -isystem $GLIBC_INCLUDE"
+  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
+  JEMALLOC=1
+else
+  # clang
+  CLANG_BIN="$CLANG_BASE/bin"
+  CLANG_LIB="$CLANG_BASE/lib"
+  CLANG_INCLUDE="$CLANG_LIB/clang/*/include"
+  CC="$CLANG_BIN/clang"
+  CXX="$CLANG_BIN/clang++"
+  AR="$CLANG_BIN/llvm-ar"
+
+  KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include/"
+
+  CFLAGS="-B$BINUTILS/gold -nostdinc -nostdlib"
+  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/4.8.1 "
+  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/4.8.1/x86_64-facebook-linux "
+  CFLAGS+=" -isystem $GLIBC_INCLUDE"
+  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
+  CFLAGS+=" -isystem $CLANG_INCLUDE"
+  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
+  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
+  CXXFLAGS="-nostdinc++"
+fi
+
+CFLAGS+=" $DEPS_INCLUDE"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42"
+CFLAGS+=" -DSNAPPY -DGFLAGS=google -DZLIB -DBZIP2 -DLZ4 -DZSTD -DNUMA -DTBB"
+CXXFLAGS+=" $CFLAGS"
+
+EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP2_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"
+EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/gcc-4.8.1-glibc-2.17/lib/ld.so"
+EXEC_LDFLAGS+=" $LIBUNWIND"
+EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/gcc-4.8.1-glibc-2.17/lib"
+# required by libtbb
+EXEC_LDFLAGS+=" -ldl"
+
+PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
+
+EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP2_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS"
+
+VALGRIND_VER="$VALGRIND_BASE/bin/"
+
+LUA_PATH="$LUA_BASE"
+
+export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE LUA_PATH
@@ -0,0 +1,170 @@
+#!/bin/sh
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+#
+# Set environment variables so that we can compile rocksdb using
+# fbcode settings.  It uses the latest g++ and clang compilers and also
+# uses jemalloc
+# Environment variables that change the behavior of this script:
+# PIC_BUILD -- if true, it will only take pic versions of libraries from fbcode. libraries that don't have pic variant will not be included
+
+
+BASEDIR=`dirname $BASH_SOURCE`
+source "$BASEDIR/dependencies_platform007.sh"
+
+CFLAGS=""
+
+# libgcc
+LIBGCC_INCLUDE="$LIBGCC_BASE/include/c++/7.3.0"
+LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"
+
+# glibc
+GLIBC_INCLUDE="$GLIBC_BASE/include"
+GLIBC_LIBS=" -L $GLIBC_BASE/lib"
+
+# snappy
+SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
+if test -z $PIC_BUILD; then
+  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy.a"
+else
+  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy_pic.a"
+fi
+CFLAGS+=" -DSNAPPY"
+
+if test -z $PIC_BUILD; then
+  # location of zlib headers and libraries
+  ZLIB_INCLUDE=" -I $ZLIB_BASE/include/"
+  ZLIB_LIBS=" $ZLIB_BASE/lib/libz.a"
+  CFLAGS+=" -DZLIB"
+
+  # location of bzip headers and libraries
+  BZIP_INCLUDE=" -I $BZIP2_BASE/include/"
+  BZIP_LIBS=" $BZIP2_BASE/lib/libbz2.a"
+  CFLAGS+=" -DBZIP2"
+
+  LZ4_INCLUDE=" -I $LZ4_BASE/include/"
+  LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
+  CFLAGS+=" -DLZ4"
+fi
+
+ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
+if test -z $PIC_BUILD; then
+  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
+else
+  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd_pic.a"
+fi
+CFLAGS+=" -DZSTD"
+
+# location of gflags headers and libraries
+GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
+if test -z $PIC_BUILD; then
+  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags.a"
+else
+  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags_pic.a"
+fi
+CFLAGS+=" -DGFLAGS=gflags"
+
+# location of jemalloc
+JEMALLOC_INCLUDE=" -I $JEMALLOC_BASE/include/"
+JEMALLOC_LIB=" $JEMALLOC_BASE/lib/libjemalloc.a"
+
+if test -z $PIC_BUILD; then
+  # location of numa
+  NUMA_INCLUDE=" -I $NUMA_BASE/include/"
+  NUMA_LIB=" $NUMA_BASE/lib/libnuma.a"
+  CFLAGS+=" -DNUMA"
+
+  # location of libunwind
+  LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
+fi
+
+# location of TBB
+TBB_INCLUDE=" -isystem $TBB_BASE/include/"
+if test -z $PIC_BUILD; then
+  TBB_LIBS="$TBB_BASE/lib/libtbb.a"
+else
+  TBB_LIBS="$TBB_BASE/lib/libtbb_pic.a"
+fi
+CFLAGS+=" -DTBB"
+
+# location of LIBURING
+LIBURING_INCLUDE=" -isystem $LIBURING_BASE/include/"
+if test -z $PIC_BUILD; then
+  LIBURING_LIBS="$LIBURING_BASE/lib/liburing.a"
+else
+  LIBURING_LIBS="$LIBURING_BASE/lib/liburing_pic.a"
+fi
+CFLAGS+=" -DLIBURING"
+
+test "$USE_SSE" || USE_SSE=1
+export USE_SSE
+test "$PORTABLE" || PORTABLE=1
+export PORTABLE
+
+BINUTILS="$BINUTILS_BASE/bin"
+AR="$BINUTILS/ar"
+
+DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE $LIBURING_INCLUDE"
+
+STDLIBS="-L $GCC_BASE/lib64"
+
+CLANG_BIN="$CLANG_BASE/bin"
+CLANG_LIB="$CLANG_BASE/lib"
+CLANG_SRC="$CLANG_BASE/../../src"
+
+CLANG_ANALYZER="$CLANG_BIN/clang++"
+CLANG_SCAN_BUILD="$CLANG_SRC/llvm/tools/clang/tools/scan-build/bin/scan-build"
+
+if [ -z "$USE_CLANG" ]; then
+  # gcc
+  CC="$GCC_BASE/bin/gcc"
+  CXX="$GCC_BASE/bin/g++"
+  AR="$GCC_BASE/bin/gcc-ar"
+
+  CFLAGS+=" -B$BINUTILS/gold"
+  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
+  CFLAGS+=" -isystem $GLIBC_INCLUDE"
+  JEMALLOC=1
+else
+  # clang
+  CLANG_INCLUDE="$CLANG_LIB/clang/stable/include"
+  CC="$CLANG_BIN/clang"
+  CXX="$CLANG_BIN/clang++"
+  AR="$CLANG_BIN/llvm-ar"
+
+  KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include"
+
+  CFLAGS+=" -B$BINUTILS/gold -nostdinc -nostdlib"
+  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/7.x "
+  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/7.x/x86_64-facebook-linux "
+  CFLAGS+=" -isystem $GLIBC_INCLUDE"
+  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
+  CFLAGS+=" -isystem $CLANG_INCLUDE"
+  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
+  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
+  CFLAGS+=" -Wno-expansion-to-defined "
+  CXXFLAGS="-nostdinc++"
+fi
+
+CFLAGS+=" $DEPS_INCLUDE"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42 -DROCKSDB_IOURING_PRESENT"
+CXXFLAGS+=" $CFLAGS"
+
+EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS $LIBURING_LIBS"
+EXEC_LDFLAGS+=" -B$BINUTILS/gold"
+EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/platform007/lib/ld.so"
+EXEC_LDFLAGS+=" $LIBUNWIND"
+EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/platform007/lib"
+# required by libtbb
+EXEC_LDFLAGS+=" -ldl"
+
+PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
+
+EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $TBB_LIBS $LIBURING_LIBS"
+
+VALGRIND_VER="$VALGRIND_BASE/bin/"
+
+# lua not supported because it's on track for deprecation, I think
+LUA_PATH=
+LUA_LIB=
+
+export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD LUA_PATH LUA_LIB
@@ -14,94 +14,92 @@ source "$BASEDIR/dependencies_platform009.sh"
 CFLAGS=""

 # libgcc
-LIBGCC_INCLUDE="$LIBGCC_BASE/include/c++/9.3.0 -I $LIBGCC_BASE/include/c++/9.3.0/backward"
+LIBGCC_INCLUDE="$LIBGCC_BASE/include/c++/9.3.0"
 LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"

 # glibc
 GLIBC_INCLUDE="$GLIBC_BASE/include"
 GLIBC_LIBS=" -L $GLIBC_BASE/lib"

+# snappy
+SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
 if test -z $PIC_BUILD; then
-  MAYBE_PIC=
+  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy.a"
 else
-  MAYBE_PIC=_pic
+  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy_pic.a"
 fi
+CFLAGS+=" -DSNAPPY"

-if ! test $ROCKSDB_DISABLE_SNAPPY; then
-  # snappy
-  SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
-  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy${MAYBE_PIC}.a"
-  CFLAGS+=" -DSNAPPY"
-fi
-
-if ! test $ROCKSDB_DISABLE_ZLIB; then
+if test -z $PIC_BUILD; then
  # location of zlib headers and libraries
  ZLIB_INCLUDE=" -I $ZLIB_BASE/include/"
-  ZLIB_LIBS=" $ZLIB_BASE/lib/libz${MAYBE_PIC}.a"
+  ZLIB_LIBS=" $ZLIB_BASE/lib/libz.a"
  CFLAGS+=" -DZLIB"
-fi

-if ! test $ROCKSDB_DISABLE_BZIP; then
  # location of bzip headers and libraries
  BZIP_INCLUDE=" -I $BZIP2_BASE/include/"
-  BZIP_LIBS=" $BZIP2_BASE/lib/libbz2${MAYBE_PIC}.a"
+  BZIP_LIBS=" $BZIP2_BASE/lib/libbz2.a"
  CFLAGS+=" -DBZIP2"
-fi

-if ! test $ROCKSDB_DISABLE_LZ4; then
  LZ4_INCLUDE=" -I $LZ4_BASE/include/"
-  LZ4_LIBS=" $LZ4_BASE/lib/liblz4${MAYBE_PIC}.a"
+  LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
  CFLAGS+=" -DLZ4"
 fi

-if ! test $ROCKSDB_DISABLE_ZSTD; then
-  ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
-  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd${MAYBE_PIC}.a"
-  CFLAGS+=" -DZSTD"
+ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
+if test -z $PIC_BUILD; then
+  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
+else
+  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd_pic.a"
 fi
+CFLAGS+=" -DZSTD"

 # location of gflags headers and libraries
 GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
-GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags${MAYBE_PIC}.a"
+if test -z $PIC_BUILD; then
+  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags.a"
+else
+  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags_pic.a"
+fi
 CFLAGS+=" -DGFLAGS=gflags"

 BENCHMARK_INCLUDE=" -I $BENCHMARK_BASE/include/"
-BENCHMARK_LIBS=" $BENCHMARK_BASE/lib/libbenchmark${MAYBE_PIC}.a"
-
-BOOST_INCLUDE=" -I $BOOST_BASE/include/"
-
-GLOG_INCLUDE=" -I $GLOG_BASE/include/"
-GLOG_LIBS=" $GLOG_BASE/lib/libglog${MAYBE_PIC}.a"
-
-FMT_INCLUDE=" -I $FMT_BASE/include/"
-FMT_LIBS=" $FMT_BASE/lib/libfmt${MAYBE_PIC}.a"
-
-DBL_CONV_INCLUDE=" -I $DBL_CONV_BASE/include/"
-DBL_CONV_LIBS=" $DBL_CONV_BASE/lib/libdouble-conversion${MAYBE_PIC}.a"
-
-LIBEVENT_INCLUDE=" -I $LIBEVENT_BASE/include/"
-LIBEVENT_LIBS=" $LIBEVENT_BASE/lib/libevent${MAYBE_PIC}.a"
+if test -z $PIC_BUILD; then
+  BENCHMARK_LIBS=" $BENCHMARK_BASE/lib/libbenchmark.a"
+else
+  BENCHMARK_LIBS=" $BENCHMARK_BASE/lib/libbenchmark_pic.a"
+fi

 # location of jemalloc
 JEMALLOC_INCLUDE=" -I $JEMALLOC_BASE/include/"
-JEMALLOC_LIB=" $JEMALLOC_BASE/lib/libjemalloc${MAYBE_PIC}.a"
+JEMALLOC_LIB=" $JEMALLOC_BASE/lib/libjemalloc.a"

-# location of numa
-NUMA_INCLUDE=" -I $NUMA_BASE/include/"
-NUMA_LIB=" $NUMA_BASE/lib/libnuma${MAYBE_PIC}.a"
-CFLAGS+=" -DNUMA"
+if test -z $PIC_BUILD; then
+  # location of numa
+  NUMA_INCLUDE=" -I $NUMA_BASE/include/"
+  NUMA_LIB=" $NUMA_BASE/lib/libnuma.a"
+  CFLAGS+=" -DNUMA"

-# location of libunwind
-LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind${MAYBE_PIC}.a"
+  # location of libunwind
+  LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
+fi

 # location of TBB
 TBB_INCLUDE=" -isystem $TBB_BASE/include/"
-TBB_LIBS="$TBB_BASE/lib/libtbb${MAYBE_PIC}.a"
+if test -z $PIC_BUILD; then
+  TBB_LIBS="$TBB_BASE/lib/libtbb.a"
+else
+  TBB_LIBS="$TBB_BASE/lib/libtbb_pic.a"
+fi
 CFLAGS+=" -DTBB"

 # location of LIBURING
 LIBURING_INCLUDE=" -isystem $LIBURING_BASE/include/"
-LIBURING_LIBS="$LIBURING_BASE/lib/liburing${MAYBE_PIC}.a"
+if test -z $PIC_BUILD; then
+  LIBURING_LIBS="$LIBURING_BASE/lib/liburing.a"
+else
+  LIBURING_LIBS="$LIBURING_BASE/lib/liburing_pic.a"
+fi
 CFLAGS+=" -DLIBURING"

 test "$USE_SSE" || USE_SSE=1
@@ -113,7 +111,7 @@ BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
 AS="$BINUTILS/as"

-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE $LIBURING_INCLUDE $BENCHMARK_INCLUDE $BOOST_INCLUDE $GLOG_INCLUDE $FMT_INCLUDE $DBL_CONV_INCLUDE $LIBEVENT_INCLUDE"
+DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE $LIBURING_INCLUDE $BENCHMARK_INCLUDE"

 STDLIBS="-L $GCC_BASE/lib64"

@@ -156,7 +154,7 @@ else
 fi

 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DHAVE_SSE42 -DROCKSDB_IOURING_PRESENT"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42 -DROCKSDB_IOURING_PRESENT"
 CXXFLAGS+=" $CFLAGS"

 EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS $LIBURING_LIBS $BENCHMARK_LIBS"
@@ -1,175 +0,0 @@
-#!/bin/sh
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-#
-# Set environment variables so that we can compile rocksdb using
-# fbcode settings.  It uses the latest g++ and clang compilers and also
-# uses jemalloc
-# Environment variables that change the behavior of this script:
-# PIC_BUILD -- if true, it will only take pic versions of libraries from fbcode. libraries that don't have pic variant will not be included
-
-
-BASEDIR=`dirname $BASH_SOURCE`
-source "$BASEDIR/dependencies_platform010.sh"
-
-# Disallow using libraries from default locations as they might not be compatible with platform010 libraries.
-CFLAGS=" --sysroot=/DOES/NOT/EXIST"
-
-# libgcc
-LIBGCC_INCLUDE="$LIBGCC_BASE/include/c++/trunk"
-LIBGCC_LIBS=" -L $LIBGCC_BASE/lib -B$LIBGCC_BASE/lib/gcc/x86_64-facebook-linux/trunk/"
-
-# glibc
-GLIBC_INCLUDE="$GLIBC_BASE/include"
-GLIBC_LIBS=" -L $GLIBC_BASE/lib"
-GLIBC_LIBS+=" -B$GLIBC_BASE/lib"
-
-if test -z $PIC_BUILD; then
-  MAYBE_PIC=
-else
-  MAYBE_PIC=_pic
-fi
-
-if ! test $ROCKSDB_DISABLE_SNAPPY; then
-  # snappy
-  SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
-  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy${MAYBE_PIC}.a"
-  CFLAGS+=" -DSNAPPY"
-fi
-
-if ! test $ROCKSDB_DISABLE_ZLIB; then
-  # location of zlib headers and libraries
-  ZLIB_INCLUDE=" -I $ZLIB_BASE/include/"
-  ZLIB_LIBS=" $ZLIB_BASE/lib/libz${MAYBE_PIC}.a"
-  CFLAGS+=" -DZLIB"
-fi
-
-if ! test $ROCKSDB_DISABLE_BZIP; then
-  # location of bzip headers and libraries
-  BZIP_INCLUDE=" -I $BZIP2_BASE/include/"
-  BZIP_LIBS=" $BZIP2_BASE/lib/libbz2${MAYBE_PIC}.a"
-  CFLAGS+=" -DBZIP2"
-fi
-
-if ! test $ROCKSDB_DISABLE_LZ4; then
-  LZ4_INCLUDE=" -I $LZ4_BASE/include/"
-  LZ4_LIBS=" $LZ4_BASE/lib/liblz4${MAYBE_PIC}.a"
-  CFLAGS+=" -DLZ4"
-fi
-
-if ! test $ROCKSDB_DISABLE_ZSTD; then
-  ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
-  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd${MAYBE_PIC}.a"
-  CFLAGS+=" -DZSTD"
-fi
-
-# location of gflags headers and libraries
-GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
-GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags${MAYBE_PIC}.a"
-CFLAGS+=" -DGFLAGS=gflags"
-
-BENCHMARK_INCLUDE=" -I $BENCHMARK_BASE/include/"
-BENCHMARK_LIBS=" $BENCHMARK_BASE/lib/libbenchmark${MAYBE_PIC}.a"
-
-# location of jemalloc
-JEMALLOC_INCLUDE=" -I $JEMALLOC_BASE/include/"
-JEMALLOC_LIB=" $JEMALLOC_BASE/lib/libjemalloc${MAYBE_PIC}.a"
-
-# location of numa
-NUMA_INCLUDE=" -I $NUMA_BASE/include/"
-NUMA_LIB=" $NUMA_BASE/lib/libnuma${MAYBE_PIC}.a"
-CFLAGS+=" -DNUMA"
-
-# location of libunwind
-LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind${MAYBE_PIC}.a"
-
-# location of TBB
-TBB_INCLUDE=" -isystem $TBB_BASE/include/"
-TBB_LIBS="$TBB_BASE/lib/libtbb${MAYBE_PIC}.a"
-CFLAGS+=" -DTBB"
-
-# location of LIBURING
-LIBURING_INCLUDE=" -isystem $LIBURING_BASE/include/"
-LIBURING_LIBS="$LIBURING_BASE/lib/liburing${MAYBE_PIC}.a"
-CFLAGS+=" -DLIBURING"
-
-test "$USE_SSE" || USE_SSE=1
-export USE_SSE
-test "$PORTABLE" || PORTABLE=1
-export PORTABLE
-
-BINUTILS="$BINUTILS_BASE/bin"
-AR="$BINUTILS/ar"
-AS="$BINUTILS/as"
-
-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE $LIBURING_INCLUDE $BENCHMARK_INCLUDE"
-
-STDLIBS="-L $GCC_BASE/lib64"
-
-CLANG_BIN="$CLANG_BASE/bin"
-CLANG_LIB="$CLANG_BASE/lib"
-CLANG_SRC="$CLANG_BASE/../../src"
-
-CLANG_ANALYZER="$CLANG_BIN/clang++"
-CLANG_SCAN_BUILD="$CLANG_SRC/llvm/clang/tools/scan-build/bin/scan-build"
-
-if [ -z "$USE_CLANG" ]; then
-  # gcc
-  CC="$GCC_BASE/bin/gcc"
-  CXX="$GCC_BASE/bin/g++"
-  AR="$GCC_BASE/bin/gcc-ar"
-
-  CFLAGS+=" -B$BINUTILS -nostdinc -nostdlib"
-  CFLAGS+=" -I$GCC_BASE/include"
-  CFLAGS+=" -isystem $GCC_BASE/lib/gcc/x86_64-redhat-linux-gnu/11.2.1/include"
-  CFLAGS+=" -isystem $GCC_BASE/lib/gcc/x86_64-redhat-linux-gnu/11.2.1/install-tools/include"
-  CFLAGS+=" -isystem $GCC_BASE/lib/gcc/x86_64-redhat-linux-gnu/11.2.1/include-fixed/"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
-  CFLAGS+=" -I$GLIBC_INCLUDE"
-  CFLAGS+=" -I$LIBGCC_BASE/include"
-  CFLAGS+=" -I$LIBGCC_BASE/include/c++/11.x/"
-  CFLAGS+=" -I$LIBGCC_BASE/include/c++/11.x/x86_64-facebook-linux/"
-  CFLAGS+=" -I$LIBGCC_BASE/include/c++/11.x/backward"
-  CFLAGS+=" -isystem $GLIBC_INCLUDE -I$GLIBC_INCLUDE"
-  JEMALLOC=1
-else
-  # clang
-  CLANG_INCLUDE="$CLANG_LIB/clang/stable/include"
-  CC="$CLANG_BIN/clang"
-  CXX="$CLANG_BIN/clang++"
-  AR="$CLANG_BIN/llvm-ar"
-
-  CFLAGS+=" -B$BINUTILS -nostdinc -nostdlib"
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/trunk "
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/trunk/x86_64-facebook-linux "
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  CFLAGS+=" -isystem $CLANG_INCLUDE"
-  CFLAGS+=" -Wno-expansion-to-defined "
-  CXXFLAGS="-nostdinc++"
-fi
-
-KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include"
-CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
-CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
-
-CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DHAVE_SSE42 -DROCKSDB_IOURING_PRESENT"
-CXXFLAGS+=" $CFLAGS"
-
-EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS $LIBURING_LIBS $BENCHMARK_LIBS"
-EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/platform010/lib/ld.so"
-EXEC_LDFLAGS+=" $LIBUNWIND"
-EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/platform010/lib"
-EXEC_LDFLAGS+=" -Wl,-rpath=$GCC_BASE/lib64"
-# required by libtbb
-EXEC_LDFLAGS+=" -ldl"
-
-PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
-PLATFORM_LDFLAGS+=" -B$BINUTILS"
-
-EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $TBB_LIBS $LIBURING_LIBS $BENCHMARK_LIBS"
-
-VALGRIND_VER="$VALGRIND_BASE/bin/"
-
-export CC CXX AR AS CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD LUA_PATH LUA_LIB
@@ -1561,7 +1561,7 @@ sub save_stdin_stdout_stderr {
 	::die_bug("Can't dup STDERR: $!");
    open $Global::original_stdin, "<&", "STDIN" or
 	::die_bug("Can't dup STDIN: $!");
-    $Global::is_terminal = (-t $Global::original_stderr) && !$ENV{'CIRCLECI'} && !$ENV{'TRAVIS'};
+    $Global::is_terminal = (-t $Global::original_stderr);
 }

 sub enough_file_handles {
@@ -0,0 +1,209 @@
+#!/usr/bin/env python2.7
+# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
+
+from __future__ import absolute_import
+from __future__ import division
+from __future__ import print_function
+from __future__ import unicode_literals
+import argparse
+import commands
+import subprocess
+import sys
+import re
+import os
+import time
+
+
+#
+# Simple logger
+#
+
+class Log:
+
+    def __init__(self, filename):
+        self.filename = filename
+        self.f = open(self.filename, 'w+', 0)
+
+    def caption(self, str):
+        line = "\n##### %s #####\n" % str
+        if self.f:
+            self.f.write("%s \n" % line)
+        else:
+            print(line)
+
+    def error(self, str):
+        data = "\n\n##### ERROR ##### %s" % str
+        if self.f:
+            self.f.write("%s \n" % data)
+        else:
+            print(data)
+
+    def log(self, str):
+        if self.f:
+            self.f.write("%s \n" % str)
+        else:
+            print(str)
+
+#
+# Shell Environment
+#
+
+
+class Env(object):
+
+    def __init__(self, logfile, tests):
+        self.tests = tests
+        self.log = Log(logfile)
+
+    def shell(self, cmd, path=os.getcwd()):
+        if path:
+            os.chdir(path)
+
+        self.log.log("==== shell session ===========================")
+        self.log.log("%s> %s" % (path, cmd))
+        status = subprocess.call("cd %s; %s" % (path, cmd), shell=True,
+                                 stdout=self.log.f, stderr=self.log.f)
+        self.log.log("status = %s" % status)
+        self.log.log("============================================== \n\n")
+        return status
+
+    def GetOutput(self, cmd, path=os.getcwd()):
+        if path:
+            os.chdir(path)
+
+        self.log.log("==== shell session ===========================")
+        self.log.log("%s> %s" % (path, cmd))
+        status, out = commands.getstatusoutput(cmd)
+        self.log.log("status = %s" % status)
+        self.log.log("out = %s" % out)
+        self.log.log("============================================== \n\n")
+        return status, out
+
+#
+# Pre-commit checker
+#
+
+
+class PreCommitChecker(Env):
+
+    def __init__(self, args):
+        Env.__init__(self, args.logfile, args.tests)
+        self.ignore_failure = args.ignore_failure
+
+    #
+    #   Get commands for a given job from the determinator file
+    #
+    def get_commands(self, test):
+        status, out = self.GetOutput(
+            "RATIO=1 build_tools/rocksdb-lego-determinator %s" % test, ".")
+        return status, out
+
+    #
+    # Run a specific CI job
+    #
+    def run_test(self, test):
+        self.log.caption("Running test %s locally" % test)
+
+        # get commands for the CI job determinator
+        status, cmds = self.get_commands(test)
+        if status != 0:
+            self.log.error("Error getting commands for test %s" % test)
+            return False
+
+        # Parse the JSON to extract the commands to run
+        cmds = re.findall("'shell':'([^\']*)'", cmds)
+
+        if len(cmds) == 0:
+            self.log.log("No commands found")
+            return False
+
+        # Run commands
+        for cmd in cmds:
+            # Replace J=<..> with the local environment variable
+            if "J" in os.environ:
+                cmd = cmd.replace("J=1", "J=%s" % os.environ["J"])
+                cmd = cmd.replace("make ", "make -j%s " % os.environ["J"])
+            # Run the command
+            status = self.shell(cmd, ".")
+            if status != 0:
+                self.log.error("Error running command %s for test %s"
+                               % (cmd, test))
+                return False
+
+        return True
+
+    #
+    # Run specified CI jobs
+    #
+    def run_tests(self):
+        if not self.tests:
+            self.log.error("Invalid args. Please provide tests")
+            return False
+
+        self.print_separator()
+        self.print_row("TEST", "RESULT")
+        self.print_separator()
+
+        result = True
+        for test in self.tests:
+            start_time = time.time()
+            self.print_test(test)
+            result = self.run_test(test)
+            elapsed_min = (time.time() - start_time) / 60
+            if not result:
+                self.log.error("Error running test %s" % test)
+                self.print_result("FAIL (%dm)" % elapsed_min)
+                if not self.ignore_failure:
+                    return False
+                result = False
+            else:
+                self.print_result("PASS (%dm)" % elapsed_min)
+
+        self.print_separator()
+        return result
+
+    #
+    # Print a line
+    #
+    def print_separator(self):
+        print("".ljust(60, "-"))
+
+    #
+    # Print two colums
+    #
+    def print_row(self, c0, c1):
+        print("%s%s" % (c0.ljust(40), c1.ljust(20)))
+
+    def print_test(self, test):
+        print(test.ljust(40), end="")
+        sys.stdout.flush()
+
+    def print_result(self, result):
+        print(result.ljust(20))
+
+#
+# Main
+#
+parser = argparse.ArgumentParser(description='RocksDB pre-commit checker.')
+
+# --log <logfile>
+parser.add_argument('--logfile', default='/tmp/precommit-check.log',
+                    help='Log file. Default is /tmp/precommit-check.log')
+# --ignore_failure
+parser.add_argument('--ignore_failure', action='store_true', default=False,
+                    help='Stop when an error occurs')
+# <test ....>
+parser.add_argument('tests', nargs='+',
+                    help='CI test(s) to run. e.g: unit punit asan tsan ubsan')
+
+args = parser.parse_args()
+checker = PreCommitChecker(args)
+
+print("Please follow log %s" % checker.log.filename)
+
+if not checker.run_tests():
+    print("Error running tests. Please check log file %s"
+          % checker.log.filename)
+    sys.exit(1)
+
+sys.exit(0)
@@ -258,6 +258,7 @@ common_in_mem_args="--db=/dev/shm/rocksdb \
    --value_size=100 \
    --compression_type=none \
    --compression_ratio=1 \
+    --hard_rate_limit=2 \
    --write_buffer_size=134217728 \
    --max_write_buffer_number=4 \
    --level0_file_num_compaction_trigger=8 \
@@ -42,7 +42,7 @@ $RunOnly.Add("c_test") | Out-Null
 $RunOnly.Add("compact_on_deletion_collector_test") | Out-Null
 $RunOnly.Add("merge_test") | Out-Null
 $RunOnly.Add("stringappend_test") | Out-Null # Apparently incorrectly written
-$RunOnly.Add("backup_engine_test") | Out-Null # Disabled
+$RunOnly.Add("backupable_db_test") | Out-Null # Disabled
 $RunOnly.Add("timer_queue_test") | Out-Null # Not a gtest

 if($RunAll -and $SuiteRun -ne "") {
@@ -491,3 +491,5 @@ if(!$script:success) {
 }

 exit 0
+
+
@@ -9,7 +9,6 @@ OUTPUT=""
 function log_header()
 {
  echo "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved." >> "$OUTPUT"
-  echo "# The file is generated using update_dependencies.sh." >> "$OUTPUT"
 }


@@ -19,7 +18,7 @@ function log_variable()
 }


-TP2_LATEST="/data/users/$USER/fbsource/fbcode/third-party2/"
+TP2_LATEST="/mnt/vol/engshare/fbcode/third-party2"
 ## $1 => lib name
 ## $2 => lib version (if not provided, will try to pick latest)
 ## $3 => platform (if not provided, will try to pick latest gcc)
@@ -51,8 +50,6 @@ function get_lib_base()
  fi
  
  result=`ls -1d $result/*/ | head -n1`
-
-  echo Finding link $result
  
  # lib_name => LIB_NAME_BASE
  local __res_var=${lib_name^^}"_BASE"
@@ -64,10 +61,10 @@ function get_lib_base()
 }

 ###########################################################
-#                platform010 dependencies                 #
+#                platform007 dependencies                 #
 ###########################################################

-OUTPUT="$BASEDIR/dependencies_platform010.sh"
+OUTPUT="$BASEDIR/dependencies_platform007.sh"

 rm -f "$OUTPUT"
 touch "$OUTPUT"
@@ -75,42 +72,40 @@ touch "$OUTPUT"
 echo "Writing dependencies to $OUTPUT"

 # Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/11.x/centos7-native/*/`
-CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/12/platform010/*/`
+GCC_BASE=`readlink -f $TP2_LATEST/gcc/7.x/centos7-native/*/`
+CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`

 log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE

 # Libraries locations
-get_lib_base libgcc     11.x    platform010
-get_lib_base glibc      2.34    platform010
-get_lib_base snappy     LATEST  platform010
-get_lib_base zlib       LATEST  platform010
-get_lib_base bzip2      LATEST  platform010
-get_lib_base lz4        LATEST  platform010
-get_lib_base zstd       LATEST  platform010
-get_lib_base gflags     LATEST  platform010
-get_lib_base jemalloc   LATEST  platform010
-get_lib_base numa       LATEST  platform010
-get_lib_base libunwind  LATEST  platform010
-get_lib_base tbb        2018_U5 platform010
-get_lib_base liburing   LATEST  platform010
-get_lib_base benchmark  LATEST  platform010
+get_lib_base libgcc     7.x     platform007
+get_lib_base glibc      2.26    platform007
+get_lib_base snappy     LATEST  platform007
+get_lib_base zlib       LATEST  platform007
+get_lib_base bzip2      LATEST  platform007
+get_lib_base lz4        LATEST  platform007
+get_lib_base zstd       LATEST  platform007
+get_lib_base gflags     LATEST  platform007
+get_lib_base jemalloc   LATEST  platform007
+get_lib_base numa       LATEST  platform007
+get_lib_base libunwind  LATEST  platform007
+get_lib_base tbb        LATEST  platform007
+get_lib_base liburing   LATEST  platform007

-get_lib_base kernel-headers fb platform010
+get_lib_base kernel-headers fb platform007
 get_lib_base binutils   LATEST centos7-native
-get_lib_base valgrind   LATEST platform010
-get_lib_base lua        5.3.4  platform010
+get_lib_base valgrind   LATEST platform007
+get_lib_base lua        5.3.4  platform007

 git diff $OUTPUT

-
 ###########################################################
-#                platform009 dependencies                 #
+#                   5.x dependencies                      #
 ###########################################################

-OUTPUT="$BASEDIR/dependencies_platform009.sh"
+OUTPUT="$BASEDIR/dependencies.sh"

 rm -f "$OUTPUT"
 touch "$OUTPUT"
@@ -118,32 +113,70 @@ touch "$OUTPUT"
 echo "Writing dependencies to $OUTPUT"

 # Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/9.x/centos7-native/*/`
-CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/9.0.0/platform009/*/`
+GCC_BASE=`readlink -f $TP2_LATEST/gcc/5.x/centos7-native/*/`
+CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`

 log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE

 # Libraries locations
-get_lib_base libgcc     9.x     platform009
-get_lib_base glibc      2.30    platform009
-get_lib_base snappy     LATEST  platform009
-get_lib_base zlib       LATEST  platform009
-get_lib_base bzip2      LATEST  platform009
-get_lib_base lz4        LATEST  platform009
-get_lib_base zstd       LATEST  platform009
-get_lib_base gflags     LATEST  platform009
-get_lib_base jemalloc   LATEST  platform009
-get_lib_base numa       LATEST  platform009
-get_lib_base libunwind  LATEST  platform009
-get_lib_base tbb        2018_U5 platform009
-get_lib_base liburing   LATEST  platform009
-get_lib_base benchmark  LATEST  platform009
+get_lib_base libgcc     5.x     gcc-5-glibc-2.23
+get_lib_base glibc      2.23    gcc-5-glibc-2.23
+get_lib_base snappy     LATEST  gcc-5-glibc-2.23
+get_lib_base zlib       LATEST  gcc-5-glibc-2.23
+get_lib_base bzip2      LATEST  gcc-5-glibc-2.23
+get_lib_base lz4        LATEST  gcc-5-glibc-2.23
+get_lib_base zstd       LATEST  gcc-5-glibc-2.23
+get_lib_base gflags     LATEST  gcc-5-glibc-2.23
+get_lib_base jemalloc   LATEST  gcc-5-glibc-2.23
+get_lib_base numa       LATEST  gcc-5-glibc-2.23
+get_lib_base libunwind  LATEST  gcc-5-glibc-2.23
+get_lib_base tbb        LATEST  gcc-5-glibc-2.23

-get_lib_base kernel-headers fb platform009
+get_lib_base kernel-headers 4.0.9-36_fbk5_2933_gd092e3f gcc-5-glibc-2.23
 get_lib_base binutils   LATEST centos7-native
-get_lib_base valgrind   LATEST platform009
-get_lib_base lua        5.3.4  platform009
+get_lib_base valgrind   LATEST gcc-5-glibc-2.23
+get_lib_base lua        5.2.3 gcc-5-glibc-2.23
+
+git diff $OUTPUT
+
+###########################################################
+#                   4.8.1 dependencies                    #
+###########################################################
+
+OUTPUT="$BASEDIR/dependencies_4.8.1.sh"
+
+rm -f "$OUTPUT"
+touch "$OUTPUT"
+
+echo "Writing 4.8.1 dependencies to $OUTPUT"
+
+# Compilers locations
+GCC_BASE=`readlink -f $TP2_LATEST/gcc/4.8.1/centos6-native/*/`
+CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`
+
+log_header
+log_variable GCC_BASE
+log_variable CLANG_BASE
+
+# Libraries locations
+get_lib_base libgcc     4.8.1  gcc-4.8.1-glibc-2.17
+get_lib_base glibc      2.17   gcc-4.8.1-glibc-2.17  
+get_lib_base snappy     LATEST gcc-4.8.1-glibc-2.17
+get_lib_base zlib       LATEST gcc-4.8.1-glibc-2.17
+get_lib_base bzip2      LATEST gcc-4.8.1-glibc-2.17
+get_lib_base lz4        LATEST gcc-4.8.1-glibc-2.17
+get_lib_base zstd       LATEST gcc-4.8.1-glibc-2.17
+get_lib_base gflags     LATEST gcc-4.8.1-glibc-2.17
+get_lib_base jemalloc   LATEST gcc-4.8.1-glibc-2.17
+get_lib_base numa       LATEST gcc-4.8.1-glibc-2.17
+get_lib_base libunwind  LATEST gcc-4.8.1-glibc-2.17
+get_lib_base tbb        4.0_update2 gcc-4.8.1-glibc-2.17
+
+get_lib_base kernel-headers LATEST gcc-4.8.1-glibc-2.17 
+get_lib_base binutils   LATEST centos6-native 
+get_lib_base valgrind   3.8.1  gcc-4.8.1-glibc-2.17
+get_lib_base lua        5.2.3 centos6-native

 git diff $OUTPUT
@@ -34,61 +34,13 @@ static std::unordered_map<std::string, OptionTypeInfo>
          OptionType::kDouble, OptionVerificationType::kNormal,
          OptionTypeFlags::kMutable}},
 };
-
-static std::unordered_map<std::string, OptionTypeInfo>
-    comp_sec_cache_options_type_info = {
-        {"capacity",
-         {offsetof(struct CompressedSecondaryCacheOptions, capacity),
-          OptionType::kSizeT, OptionVerificationType::kNormal,
-          OptionTypeFlags::kMutable}},
-        {"num_shard_bits",
-         {offsetof(struct CompressedSecondaryCacheOptions, num_shard_bits),
-          OptionType::kInt, OptionVerificationType::kNormal,
-          OptionTypeFlags::kMutable}},
-        {"compression_type",
-         {offsetof(struct CompressedSecondaryCacheOptions, compression_type),
-          OptionType::kCompressionType, OptionVerificationType::kNormal,
-          OptionTypeFlags::kMutable}},
-        {"compress_format_version",
-         {offsetof(struct CompressedSecondaryCacheOptions,
-                   compress_format_version),
-          OptionType::kUInt32T, OptionVerificationType::kNormal,
-          OptionTypeFlags::kMutable}},
-};
 #endif  // ROCKSDB_LITE

 Status SecondaryCache::CreateFromString(
    const ConfigOptions& config_options, const std::string& value,
    std::shared_ptr<SecondaryCache>* result) {
-  if (value.find("compressed_secondary_cache://") == 0) {
-    std::string args = value;
-    args.erase(0, std::strlen("compressed_secondary_cache://"));
-    Status status;
-    std::shared_ptr<SecondaryCache> sec_cache;
-
-#ifndef ROCKSDB_LITE
-    CompressedSecondaryCacheOptions sec_cache_opts;
-    status = OptionTypeInfo::ParseStruct(config_options, "",
-                                         &comp_sec_cache_options_type_info, "",
-                                         args, &sec_cache_opts);
-    if (status.ok()) {
-      sec_cache = NewCompressedSecondaryCache(sec_cache_opts);
-    }
-
-#else
-    (void)config_options;
-    status = Status::NotSupported(
-        "Cannot load compressed secondary cache in LITE mode ", args);
-#endif  //! ROCKSDB_LITE
-
-    if (status.ok()) {
-      result->swap(sec_cache);
-    }
-    return status;
-  } else {
-    return LoadSharedObject<SecondaryCache>(config_options, value, nullptr,
-                                            result);
-  }
+  return LoadSharedObject<SecondaryCache>(config_options, value, nullptr,
+                                          result);
 }

 Status Cache::CreateFromString(const ConfigOptions& config_options,
@@ -12,7 +12,6 @@
 #include <set>
 #include <sstream>

-#include "cache/fast_lru_cache.h"
 #include "db/db_impl/db_impl.h"
 #include "monitoring/histogram.h"
 #include "port/port.h"
@@ -26,7 +25,6 @@
 #include "table/block_based/block_based_table_reader.h"
 #include "table/block_based/cachable_entry.h"
 #include "util/coding.h"
-#include "util/distributed_mutex.h"
 #include "util/gflags_compat.h"
 #include "util/hash.h"
 #include "util/mutexlock.h"
@@ -78,55 +76,34 @@ DEFINE_string(secondary_cache_uri, "",
 static class std::shared_ptr<ROCKSDB_NAMESPACE::SecondaryCache> secondary_cache;
 #endif  // ROCKSDB_LITE

-DEFINE_string(cache_type, "lru_cache", "Type of block cache.");
+DEFINE_bool(use_clock_cache, false, "");

 // ## BEGIN stress_cache_key sub-tool options ##
-// See class StressCacheKey below.
 DEFINE_bool(stress_cache_key, false,
            "If true, run cache key stress test instead");
-DEFINE_uint32(
-    sck_files_per_day, 2500000,
-    "(-stress_cache_key) Simulated files generated per simulated day");
-// NOTE: Giving each run a specified lifetime, rather than e.g. "until
-// first collision" ensures equal skew from start-up, when collisions are
-// less likely.
-DEFINE_uint32(sck_days_per_run, 90,
+DEFINE_uint32(sck_files_per_day, 2500000,
+              "(-stress_cache_key) Simulated files generated per day");
+DEFINE_uint32(sck_duration, 90,
              "(-stress_cache_key) Number of days to simulate in each run");
-// NOTE: The number of observed collisions directly affects the relative
-// accuracy of the predicted probabilities. 15 observations should be well
-// within factor-of-2 accuracy.
 DEFINE_uint32(
    sck_min_collision, 15,
    "(-stress_cache_key) Keep running until this many collisions seen");
-// sck_file_size_mb can be thought of as average file size. The simulation is
-// not precise enough to care about the distribution of file sizes; other
-// simulations (https://github.com/pdillinger/unique_id/tree/main/monte_carlo)
-// indicate the distribution only makes a small difference (e.g. < 2x factor)
 DEFINE_uint32(
    sck_file_size_mb, 32,
    "(-stress_cache_key) Simulated file size in MiB, for accounting purposes");
 DEFINE_uint32(sck_reopen_nfiles, 100,
-              "(-stress_cache_key) Simulate DB re-open average every n files");
-DEFINE_uint32(sck_restarts_per_day, 24,
-              "(-stress_cache_key) Average simulated process restarts per day "
-              "(across DBs)");
+              "(-stress_cache_key) Re-opens DB average every n files");
 DEFINE_uint32(
-    sck_db_count, 100,
-    "(-stress_cache_key) Parallel DBs in simulation sharing a block cache");
-DEFINE_uint32(
-    sck_table_bits, 20,
-    "(-stress_cache_key) Log2 number of tracked (live) files (across DBs)");
-// sck_keep_bits being well below full 128 bits amplifies the collision
-// probability so that the true probability can be estimated through observed
-// collisions. (More explanation below.)
-DEFINE_uint32(
-    sck_keep_bits, 50,
-    "(-stress_cache_key) Number of bits to keep from each cache key (<= 64)");
-// sck_randomize is used to validate whether cache key is performing "better
-// than random." Even with this setting, file offsets are not randomized.
+    sck_restarts_per_day, 24,
+    "(-stress_cache_key) Simulated process restarts per day (across DBs)");
+DEFINE_uint32(sck_db_count, 100,
+              "(-stress_cache_key) Parallel DBs in operation");
+DEFINE_uint32(sck_table_bits, 20,
+              "(-stress_cache_key) Log2 number of tracked files");
+DEFINE_uint32(sck_keep_bits, 50,
+              "(-stress_cache_key) Number of cache key bits to keep");
 DEFINE_bool(sck_randomize, false,
            "(-stress_cache_key) Randomize (hash) cache key");
-// See https://github.com/facebook/rocksdb/pull/9058
 DEFINE_bool(sck_footer_unique_id, false,
            "(-stress_cache_key) Simulate using proposed footer unique id");
 // ## END stress_cache_key sub-tool options ##
@@ -281,17 +258,13 @@ class CacheBench {
      if (max_key > (static_cast<uint64_t>(1) << max_log_)) max_log_++;
    }

-    if (FLAGS_cache_type == "clock_cache") {
+    if (FLAGS_use_clock_cache) {
      cache_ = NewClockCache(FLAGS_cache_size, FLAGS_num_shard_bits);
      if (!cache_) {
        fprintf(stderr, "Clock cache not supported.\n");
        exit(1);
      }
-    } else if (FLAGS_cache_type == "fast_lru_cache") {
-      cache_ = NewFastLRUCache(
-          FLAGS_cache_size, FLAGS_value_bytes, FLAGS_num_shard_bits,
-          false /*strict_capacity_limit*/, kDefaultCacheMetadataChargePolicy);
-    } else if (FLAGS_cache_type == "lru_cache") {
+    } else {
      LRUCacheOptions opts(FLAGS_cache_size, FLAGS_num_shard_bits, false, 0.5);
 #ifndef ROCKSDB_LITE
      if (!FLAGS_secondary_cache_uri.empty()) {
@@ -309,9 +282,6 @@ class CacheBench {
 #endif  // ROCKSDB_LITE

      cache_ = NewLRUCache(opts);
-    } else {
-      fprintf(stderr, "Cache type not supported.");
-      exit(1);
    }
  }

@@ -519,9 +489,8 @@ class CacheBench {
      timer.Start();
      Slice key = gen.GetRand(thread->rnd, max_key_, max_log_);
      uint64_t random_op = thread->rnd.Next();
-      Cache::CreateCallback create_cb = [](const void* buf, size_t size,
-                                           void** out_obj,
-                                           size_t* charge) -> Status {
+      Cache::CreateCallback create_cb =
+          [](void* buf, size_t size, void** out_obj, size_t* charge) -> Status {
        *out_obj = reinterpret_cast<void*>(new char[size]);
        memcpy(*out_obj, buf, size);
        *charge = size;
@@ -588,15 +557,7 @@ class CacheBench {
  }

  void PrintEnv() const {
-#if defined(__GNUC__) && !defined(__OPTIMIZE__)
-    printf(
-        "WARNING: Optimization is disabled: benchmarks unnecessarily slow\n");
-#endif
-#ifndef NDEBUG
-    printf("WARNING: Assertions are enabled; benchmarks unnecessarily slow\n");
-#endif
    printf("RocksDB version     : %d.%d\n", kMajorVersion, kMinorVersion);
-    printf("DMutex impl name    : %s\n", DMutex::kName());
    printf("Number of threads   : %u\n", FLAGS_threads);
    printf("Ops per thread      : %" PRIu64 "\n", FLAGS_ops_per_thread);
    printf("Cache size          : %s\n",
@@ -622,97 +583,20 @@ class CacheBench {
  }
 };

-// cache_bench -stress_cache_key is an independent embedded tool for
-// estimating the probability of CacheKey collisions through simulation.
-// At a high level, it simulates generating SST files over many months,
-// keeping them in the DB and/or cache for some lifetime while staying
-// under resource caps, and checking for any cache key collisions that
-// arise among the set of live files. For efficient simulation, we make
-// some simplifying "pessimistic" assumptions (that only increase the
-// chance of the simulation reporting a collision relative to the chance
-// of collision in practice):
-// * Every generated file has a cache entry for every byte offset in the
-// file (contiguous range of cache keys)
-// * All of every file is cached for its entire lifetime. (Here "lifetime"
-// is technically the union of DB and Cache lifetime, though we only
-// model a generous DB lifetime, where space usage is always maximized.
-// In a effective Cache, lifetime in cache can only substantially exceed
-// lifetime in DB if there is little cache activity; cache activity is
-// required to hit cache key collisions.)
-//
-// It would be possible to track an exact set of cache key ranges for the
-// set of live files, but we would have no hope of observing collisions
-// (overlap in live files) in our simulation. We need to employ some way
-// of amplifying collision probability that allows us to predict the real
-// collision probability by extrapolation from observed collisions. Our
-// basic approach is to reduce each cache key range down to some smaller
-// number of bits, and limiting to bits that are shared over the whole
-// range.  Now we can observe collisions using a set of smaller stripped-down
-// (reduced) cache keys. Let's do some case analysis to understand why this
-// works:
-// * No collision in reduced key - because the reduction is a pure function
-// this implies no collision in the full keys
-// * Collision detected between two reduced keys - either
-//   * The reduction has dropped some structured uniqueness info (from one of
-// session counter or file number; file offsets are never materialized here).
-// This can only artificially inflate the observed and extrapolated collision
-// probabilities. We only have to worry about this in designing the reduction.
-//   * The reduction has preserved all the structured uniqueness in the cache
-// key, which means either
-//     * REJECTED: We have a uniqueness bug in generating cache keys, where
-// structured uniqueness info should have been different but isn't. In such a
-// case, increasing by 1 the number of bits kept after reduction would not
-// reduce observed probabilities by half. (In our observations, the
-// probabilities are reduced approximately by half.)
-//     * ACCEPTED: The lost unstructured uniqueness in the key determines the
-// probability that an observed collision would imply an overlap in ranges.
-// In short, dropping n bits from key would increase collision probability by
-// 2**n, assuming those n bits have full entropy in unstructured uniqueness.
-//
-// But we also have to account for the key ranges based on file size. If file
-// sizes are roughly 2**b offsets, using XOR in 128-bit cache keys for
-// "ranges", we know from other simulations (see
-// https://github.com/pdillinger/unique_id/) that that's roughly equivalent to
-// (less than 2x higher collision probability) using a cache key of size
-// 128 - b bits for the whole file. (This is the only place we make an
-// "optimistic" assumption, which is more than offset by the real
-// implementation stripping off 2 lower bits from block byte offsets for cache
-// keys. The simulation assumes byte offsets, which is net pessimistic.)
-//
-// So to accept the extrapolation as valid, we need to be confident that all
-// "lost" bits, excluding those covered by file offset, are full entropy.
-// Recall that we have assumed (verifiably, safely) that other structured data
-// (file number and session counter) are kept, not lost. Based on the
-// implementation comments for OffsetableCacheKey, the only potential hole here
-// is that we only have ~103 bits of entropy in "all new" session IDs, and in
-// extreme cases, there might be only 1 DB ID. However, because the upper ~39
-// bits of session ID are hashed, the combination of file number and file
-// offset only has to add to 25 bits (or more) to ensure full entropy in
-// unstructured uniqueness lost in the reduction. Typical file size of 32MB
-// suffices (at least for simulation purposes where we assume each file offset
-// occupies a cache key).
-//
-// Example results in comments on OffsetableCacheKey.
+// TODO: better description (see PR #9126 for some info)
 class StressCacheKey {
 public:
  void Run() {
    if (FLAGS_sck_footer_unique_id) {
-      // Proposed footer unique IDs are DB-independent and session-independent
-      // (but process-dependent) which is most easily simulated here by
-      // assuming 1 DB and (later below) no session resets without process
-      // reset.
      FLAGS_sck_db_count = 1;
    }

-    // Describe the simulated workload
    uint64_t mb_per_day =
        uint64_t{FLAGS_sck_files_per_day} * FLAGS_sck_file_size_mb;
    printf("Total cache or DBs size: %gTiB  Writing %g MiB/s or %gTiB/day\n",
           FLAGS_sck_file_size_mb / 1024.0 / 1024.0 *
               std::pow(2.0, FLAGS_sck_table_bits),
           mb_per_day / 86400.0, mb_per_day / 1024.0 / 1024.0);
-    // For extrapolating probability of any collisions from a number of
-    // observed collisions
    multiplier_ = std::pow(2.0, 128 - FLAGS_sck_keep_bits) /
                  (FLAGS_sck_file_size_mb * 1024.0 * 1024.0);
    printf(
@@ -722,9 +606,6 @@ class StressCacheKey {
    restart_nfiles_ = FLAGS_sck_files_per_day / FLAGS_sck_restarts_per_day;
    double without_ejection =
        std::pow(1.414214, FLAGS_sck_keep_bits) / FLAGS_sck_files_per_day;
-    // This should be a lower bound for -sck_randomize, usually a terribly
-    // rough lower bound.
-    // If observation is worse than this, then something has gone wrong.
    printf(
        "Without ejection, expect random collision after %g days (%g "
        "corrected)\n",
@@ -732,36 +613,30 @@ class StressCacheKey {
    double with_full_table =
        std::pow(2.0, FLAGS_sck_keep_bits - FLAGS_sck_table_bits) /
        FLAGS_sck_files_per_day;
-    // This is an alternate lower bound for -sck_randomize, usually pretty
-    // accurate. Our cache keys should usually perform "better than random"
-    // but always no worse. (If observation is substantially worse than this,
-    // then something has gone wrong.)
    printf(
        "With ejection and full table, expect random collision after %g "
        "days (%g corrected)\n",
        with_full_table, with_full_table * multiplier_);
    collisions_ = 0;

-    // Run until sufficient number of observed collisions.
    for (int i = 1; collisions_ < FLAGS_sck_min_collision; i++) {
      RunOnce();
      if (collisions_ == 0) {
        printf(
            "No collisions after %d x %u days                              "
            "                   \n",
-            i, FLAGS_sck_days_per_run);
+            i, FLAGS_sck_duration);
      } else {
-        double est = 1.0 * i * FLAGS_sck_days_per_run / collisions_;
+        double est = 1.0 * i * FLAGS_sck_duration / collisions_;
        printf("%" PRIu64
               " collisions after %d x %u days, est %g days between (%g "
               "corrected)        \n",
-               collisions_, i, FLAGS_sck_days_per_run, est, est * multiplier_);
+               collisions_, i, FLAGS_sck_duration, est, est * multiplier_);
      }
    }
  }

  void RunOnce() {
-    // Re-initialized simulated state
    const size_t db_count = FLAGS_sck_db_count;
    dbs_.reset(new TableProperties[db_count]{});
    const size_t table_mask = (size_t{1} << FLAGS_sck_table_bits) - 1;
@@ -769,11 +644,7 @@ class StressCacheKey {
    if (FLAGS_sck_keep_bits > 64) {
      FLAGS_sck_keep_bits = 64;
    }
-
-    // Details of which bits are dropped in reduction
    uint32_t shift_away = 64 - FLAGS_sck_keep_bits;
-    // Shift away fewer potential file number bits (b) than potential
-    // session counter bits (a).
    uint32_t shift_away_b = shift_away / 3;
    uint32_t shift_away_a = shift_away - shift_away_b;

@@ -784,78 +655,62 @@ class StressCacheKey {
    Random64 r{std::random_device{}()};

    uint64_t max_file_count =
-        uint64_t{FLAGS_sck_files_per_day} * FLAGS_sck_days_per_run;
-    uint64_t file_size = FLAGS_sck_file_size_mb * uint64_t{1024} * 1024U;
+        uint64_t{FLAGS_sck_files_per_day} * FLAGS_sck_duration;
+    uint64_t file_count = 0;
    uint32_t report_count = 0;
    uint32_t collisions_this_run = 0;
-    size_t db_i = 0;
-
-    for (uint64_t file_count = 1; file_count <= max_file_count;
-         ++file_count, ++db_i) {
-      // Round-robin through DBs (this faster than %)
+    // Round robin through DBs
+    for (size_t db_i = 0;; ++db_i) {
      if (db_i >= db_count) {
        db_i = 0;
      }
-      // Any other periodic actions before simulating next file
+      if (file_count >= max_file_count) {
+        break;
+      }
      if (!FLAGS_sck_footer_unique_id && r.OneIn(FLAGS_sck_reopen_nfiles)) {
        ResetSession(db_i);
      } else if (r.OneIn(restart_nfiles_)) {
        ResetProcess();
      }
-      // Simulate next file
      OffsetableCacheKey ock;
      dbs_[db_i].orig_file_number += 1;
-      // skip some file numbers for other file kinds, except in footer unique
-      // ID, orig_file_number here tracks process-wide generated SST file
-      // count.
-      if (!FLAGS_sck_footer_unique_id) {
+      // skip some file numbers, unless 1 DB so that that can simulate
+      // better (DB-independent) unique IDs
+      if (db_count > 1) {
        dbs_[db_i].orig_file_number += (r.Next() & 3);
      }
-      bool is_stable;
-      BlockBasedTable::SetupBaseCacheKey(&dbs_[db_i], /* ignored */ "",
-                                         /* ignored */ 42, file_size, &ock,
-                                         &is_stable);
-      assert(is_stable);
-      // Get a representative cache key, which later we analytically generalize
-      // to a range.
+      BlockBasedTable::SetupBaseCacheKey(&dbs_[db_i], "", 42, 42, &ock);
      CacheKey ck = ock.WithOffset(0);
-      uint64_t reduced_key;
+      uint64_t stripped;
      if (FLAGS_sck_randomize) {
-        reduced_key = GetSliceHash64(ck.AsSlice()) >> shift_away;
+        stripped = GetSliceHash64(ck.AsSlice()) >> shift_away;
      } else if (FLAGS_sck_footer_unique_id) {
-        // Special case: keep only file number, not session counter
        uint32_t a = DecodeFixed32(ck.AsSlice().data() + 4) >> shift_away_a;
        uint32_t b = DecodeFixed32(ck.AsSlice().data() + 12) >> shift_away_b;
-        reduced_key = (uint64_t{a} << 32) + b;
+        stripped = (uint64_t{a} << 32) + b;
      } else {
-        // Try to keep file number and session counter (shift away other bits)
        uint32_t a = DecodeFixed32(ck.AsSlice().data()) << shift_away_a;
        uint32_t b = DecodeFixed32(ck.AsSlice().data() + 12) >> shift_away_b;
-        reduced_key = (uint64_t{a} << 32) + b;
+        stripped = (uint64_t{a} << 32) + b;
      }
-      if (reduced_key == 0) {
-        // Unlikely, but we need to exclude tracking this value because we
-        // use it to mean "empty" in table. This case is OK as long as we
-        // don't hit it often.
+      if (stripped == 0) {
+        // Unlikely, but we need to exclude tracking this value
        printf("Hit Zero!                                                  \n");
-        file_count--;
        continue;
      }
-      uint64_t h =
-          NPHash64(reinterpret_cast<char*>(&reduced_key), sizeof(reduced_key));
-      // Skew expected lifetimes, for high variance (super-Poisson) variance
-      // in actual lifetimes.
+      file_count++;
+      uint64_t h = NPHash64(reinterpret_cast<char*>(&stripped), 8);
+      // Skew lifetimes
      size_t pos =
          std::min(Lower32of64(h) & table_mask, Upper32of64(h) & table_mask);
-      if (table_[pos] == reduced_key) {
+      if (table_[pos] == stripped) {
        collisions_this_run++;
-        // Our goal is to predict probability of no collisions, not expected
-        // number of collisions. To make the distinction, we have to get rid
-        // of observing correlated collisions, which this takes care of:
+        // To predict probability of no collisions, we have to get rid of
+        // correlated collisions, which this takes care of:
        ResetProcess();
      } else {
-        // Replace (end of lifetime for file that was in this slot)
-        table_[pos] = reduced_key;
+        // Replace
+        table_[pos] = stripped;
      }

      if (++report_count == FLAGS_sck_files_per_day) {
@@ -893,8 +748,6 @@ class StressCacheKey {
      ResetSession(i);
    }
    if (FLAGS_sck_footer_unique_id) {
-      // For footer unique ID, this tracks process-wide generated SST file
-      // count.
      dbs_[0].orig_file_number = 0;
    }
  }
@@ -11,7 +11,7 @@

 namespace ROCKSDB_NAMESPACE {

-std::array<std::string, kNumCacheEntryRoles> kCacheEntryRoleToCamelString{{
+std::array<const char*, kNumCacheEntryRoles> kCacheEntryRoleToCamelString{{
    "DataBlock",
    "FilterBlock",
    "FilterMetaBlock",
@@ -21,12 +21,10 @@ std::array<std::string, kNumCacheEntryRoles> kCacheEntryRoleToCamelString{{
    "WriteBuffer",
    "CompressionDictionaryBuildingBuffer",
    "FilterConstruction",
-    "BlockBasedTableReader",
-    "FileMetadata",
    "Misc",
 }};

-std::array<std::string, kNumCacheEntryRoles> kCacheEntryRoleToHyphenString{{
+std::array<const char*, kNumCacheEntryRoles> kCacheEntryRoleToHyphenString{{
    "data-block",
    "filter-block",
    "filter-meta-block",
@@ -36,77 +34,19 @@ std::array<std::string, kNumCacheEntryRoles> kCacheEntryRoleToHyphenString{{
    "write-buffer",
    "compression-dictionary-building-buffer",
    "filter-construction",
-    "block-based-table-reader",
-    "file-metadata",
    "misc",
 }};

-const std::string& GetCacheEntryRoleName(CacheEntryRole role) {
-  return kCacheEntryRoleToHyphenString[static_cast<size_t>(role)];
-}
-
-const std::string& BlockCacheEntryStatsMapKeys::CacheId() {
-  static const std::string kCacheId = "id";
-  return kCacheId;
-}
-
-const std::string& BlockCacheEntryStatsMapKeys::CacheCapacityBytes() {
-  static const std::string kCacheCapacityBytes = "capacity";
-  return kCacheCapacityBytes;
-}
-
-const std::string&
-BlockCacheEntryStatsMapKeys::LastCollectionDurationSeconds() {
-  static const std::string kLastCollectionDurationSeconds =
-      "secs_for_last_collection";
-  return kLastCollectionDurationSeconds;
-}
-
-const std::string& BlockCacheEntryStatsMapKeys::LastCollectionAgeSeconds() {
-  static const std::string kLastCollectionAgeSeconds =
-      "secs_since_last_collection";
-  return kLastCollectionAgeSeconds;
-}
-
-namespace {
-
-std::string GetPrefixedCacheEntryRoleName(const std::string& prefix,
-                                          CacheEntryRole role) {
-  const std::string& role_name = GetCacheEntryRoleName(role);
-  std::string prefixed_role_name;
-  prefixed_role_name.reserve(prefix.size() + role_name.size());
-  prefixed_role_name.append(prefix);
-  prefixed_role_name.append(role_name);
-  return prefixed_role_name;
-}
-
-}  // namespace
-
-std::string BlockCacheEntryStatsMapKeys::EntryCount(CacheEntryRole role) {
-  const static std::string kPrefix = "count.";
-  return GetPrefixedCacheEntryRoleName(kPrefix, role);
-}
-
-std::string BlockCacheEntryStatsMapKeys::UsedBytes(CacheEntryRole role) {
-  const static std::string kPrefix = "bytes.";
-  return GetPrefixedCacheEntryRoleName(kPrefix, role);
-}
-
-std::string BlockCacheEntryStatsMapKeys::UsedPercent(CacheEntryRole role) {
-  const static std::string kPrefix = "percent.";
-  return GetPrefixedCacheEntryRoleName(kPrefix, role);
-}
-
 namespace {

 struct Registry {
  std::mutex mutex;
-  UnorderedMap<Cache::DeleterFn, CacheEntryRole> role_map;
+  std::unordered_map<Cache::DeleterFn, CacheEntryRole> role_map;
  void Register(Cache::DeleterFn fn, CacheEntryRole role) {
    std::lock_guard<std::mutex> lock(mutex);
    role_map[fn] = role;
  }
-  UnorderedMap<Cache::DeleterFn, CacheEntryRole> Copy() {
+  std::unordered_map<Cache::DeleterFn, CacheEntryRole> Copy() {
    std::lock_guard<std::mutex> lock(mutex);
    return role_map;
  }
@@ -123,7 +63,7 @@ void RegisterCacheDeleterRole(Cache::DeleterFn fn, CacheEntryRole role) {
  GetRegistry().Register(fn, role);
 }

-UnorderedMap<Cache::DeleterFn, CacheEntryRole> CopyCacheDeleterRoleMap() {
+std::unordered_map<Cache::DeleterFn, CacheEntryRole> CopyCacheDeleterRoleMap() {
  return GetRegistry().Copy();
 }

@@ -9,15 +9,46 @@
 #include <cstdint>
 #include <memory>
 #include <type_traits>
+#include <unordered_map>

 #include "rocksdb/cache.h"
-#include "util/hash_containers.h"

 namespace ROCKSDB_NAMESPACE {

-extern std::array<std::string, kNumCacheEntryRoles>
+// Classifications of block cache entries, for reporting statistics
+// Adding new enum to this class requires corresponding updates to
+// kCacheEntryRoleToCamelString and kCacheEntryRoleToHyphenString
+enum class CacheEntryRole {
+  // Block-based table data block
+  kDataBlock,
+  // Block-based table filter block (full or partitioned)
+  kFilterBlock,
+  // Block-based table metadata block for partitioned filter
+  kFilterMetaBlock,
+  // Block-based table deprecated filter block (old "block-based" filter)
+  kDeprecatedFilterBlock,
+  // Block-based table index block
+  kIndexBlock,
+  // Other kinds of block-based table block
+  kOtherBlock,
+  // WriteBufferManager reservations to account for memtable usage
+  kWriteBuffer,
+  // BlockBasedTableBuilder reservations to account for
+  // compression dictionary building buffer's memory usage
+  kCompressionDictionaryBuildingBuffer,
+  // Filter reservations to account for
+  // (new) bloom and ribbon filter construction's memory usage
+  kFilterConstruction,
+  // Default bucket, for miscellaneous cache entries. Do not use for
+  // entries that could potentially add up to large usage.
+  kMisc,
+};
+constexpr uint32_t kNumCacheEntryRoles =
+    static_cast<uint32_t>(CacheEntryRole::kMisc) + 1;
+
+extern std::array<const char*, kNumCacheEntryRoles>
    kCacheEntryRoleToCamelString;
-extern std::array<std::string, kNumCacheEntryRoles>
+extern std::array<const char*, kNumCacheEntryRoles>
    kCacheEntryRoleToHyphenString;

 // To associate cache entries with their role, we use a hack on the
@@ -44,7 +75,7 @@ void RegisterCacheDeleterRole(Cache::DeleterFn fn, CacheEntryRole role);
 // * This is suitable for preparing for batch operations, like with
 // CacheEntryStatsCollector.
 // * The number of mappings should be sufficiently small (dozens).
-UnorderedMap<Cache::DeleterFn, CacheEntryRole> CopyCacheDeleterRoleMap();
+std::unordered_map<Cache::DeleterFn, CacheEntryRole> CopyCacheDeleterRoleMap();

 // ************************************************************** //
 // An automatic registration infrastructure. This enables code
@@ -35,8 +35,7 @@ CacheKey CacheKey::CreateUniqueForCacheLifetime(Cache *cache) {
 CacheKey CacheKey::CreateUniqueForProcessLifetime() {
  // To avoid colliding with CreateUniqueForCacheLifetime, assuming
  // Cache::NewId counts up from zero, here we count down from UINT64_MAX.
-  // If this ever becomes a point of contention, we could sub-divide the
-  // space and use CoreLocalArray.
+  // If this ever becomes a point of contention, we could use CoreLocalArray.
  static std::atomic<uint64_t> counter{UINT64_MAX};
  uint64_t id = counter.fetch_sub(1, std::memory_order_relaxed);
  // Ensure we don't collide with CreateUniqueForCacheLifetime
@@ -119,10 +118,9 @@ CacheKey CacheKey::CreateUniqueForProcessLifetime() {
 // "structured" uniqueness hasn't been cloned. Using a static
 // SemiStructuredUniqueIdGen for db_session_ids, this means we only get an
 // "all new" session id when a new process uses RocksDB. (Between processes,
-// we don't know if a DB or other persistent storage has been cloned. We
-// assume that if VM hot cloning is used, subsequently generated SST files
-// do not interact.) Within a process, only the session_lower of the
-// db_session_id changes incrementally ("structured" uniqueness).
+// we don't know if a DB or other persistent storage has been cloned.) Within
+// a process, only the session_lower of the db_session_id changes
+// incrementally ("structured" uniqueness).
 //
 // This basically means that our offsets, counters and file numbers allow us
 // to do somewhat "better than random" (birthday paradox) while in the
@@ -170,83 +168,12 @@ CacheKey CacheKey::CreateUniqueForProcessLifetime() {
 // data from the last 180 days is in cache, but NOT the other assumption
 // for the 1 in a trillion estimate above).
 //
+// Conclusion: Burning through session IDs, particularly "all new" IDs that
+// only arise when a new process is started, is the only way to have a
+// plausible chance of cache key collision. When processes live for hours
+// or days, the chance of a cache key collision seems more plausibly due
+// to bad hardware than to bad luck in random session ID data.
 //
-// Collision probability estimation through simulation:
-// A tool ./cache_bench -stress_cache_key broadly simulates host-wide cache
-// activity over many months, by making some pessimistic simplifying
-// assumptions. See class StressCacheKey in cache_bench_tool.cc for details.
-// Here is some sample output with
-// `./cache_bench -stress_cache_key -sck_keep_bits=40`:
-//
-//   Total cache or DBs size: 32TiB  Writing 925.926 MiB/s or 76.2939TiB/day
-//   Multiply by 9.22337e+18 to correct for simulation losses (but still
-//   assume whole file cached)
-//
-// These come from default settings of 2.5M files per day of 32 MB each, and
-// `-sck_keep_bits=40` means that to represent a single file, we are only
-// keeping 40 bits of the 128-bit (base) cache key.  With file size of 2**25
-// contiguous keys (pessimistic), our simulation is about 2\*\*(128-40-25) or
-// about 9 billion billion times more prone to collision than reality.
-//
-// More default assumptions, relatively pessimistic:
-// * 100 DBs in same process (doesn't matter much)
-// * Re-open DB in same process (new session ID related to old session ID) on
-// average every 100 files generated
-// * Restart process (all new session IDs unrelated to old) 24 times per day
-//
-// After enough data, we get a result at the end (-sck_keep_bits=40):
-//
-//   (keep 40 bits)  17 collisions after 2 x 90 days, est 10.5882 days between
-//                   (9.76592e+19 corrected)
-//
-// If we believe the (pessimistic) simulation and the mathematical
-// extrapolation, we would need to run a billion machines all for 97 billion
-// days to expect a cache key collision. To help verify that our extrapolation
-// ("corrected") is robust, we can make our simulation more precise with
-// `-sck_keep_bits=41` and `42`, which takes more running time to get enough
-// collision data:
-//
-//   (keep 41 bits)  16 collisions after 4 x 90 days, est 22.5 days between
-//                   (1.03763e+20 corrected)
-//   (keep 42 bits)  19 collisions after 10 x 90 days, est 47.3684 days between
-//                   (1.09224e+20 corrected)
-//
-// The extrapolated prediction is very close. If anything, we might have some
-// very small losses of structured data (see class StressCacheKey in
-// cache_bench_tool.cc) leading to more accurate & more attractive prediction
-// with more bits kept.
-//
-// With the `-sck_randomize` option, we can see that typical workloads like
-// above have lower collision probability than "random" cache keys (note:
-// offsets still non-randomized) by a modest amount (roughly 20x less collision
-// prone than random), which should make us reasonably comfortable even in
-// "degenerate" cases (e.g. repeatedly launch a process to generate 1 file
-// with SstFileWriter):
-//
-//   (rand 40 bits) 197 collisions after 1 x 90 days, est 0.456853 days between
-//                  (4.21372e+18 corrected)
-//
-// We can see that with more frequent process restarts (all new session IDs),
-// we get closer to the "random" cache key performance:
-//
-//   (-sck_restarts_per_day=5000): 140 collisions after 1 x 90 days, ...
-//                  (5.92931e+18 corrected)
-//
-// Other tests have been run to validate other conditions behave as expected,
-// never behaving "worse than random" unless we start chopping off structured
-// data.
-//
-//
-// Conclusion: Even in extreme cases, rapidly burning through "all new" IDs
-// that only arise when a new process is started, the chance of any cache key
-// collisions in a giant fleet of machines is negligible. Especially when
-// processes live for hours or days, the chance of a cache key collision is
-// likely more plausibly due to bad hardware than to bad luck in random
-// session ID data. Software defects are surely more likely to cause corruption
-// than both of those.
-//
-// TODO: Nevertheless / regardless, an efficient way to detect (and thus
-// quantify) block cache corruptions, including collisions, should be added.
 OffsetableCacheKey::OffsetableCacheKey(const std::string &db_id,
                                       const std::string &db_session_id,
                                       uint64_t file_number,
@@ -17,30 +17,12 @@
 #include "rocksdb/cache.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/status.h"
-#include "table/block_based/reader_common.h"
+#include "table/block_based/block_based_table_reader.h"
 #include "util/coding.h"

 namespace ROCKSDB_NAMESPACE {
-
-template <CacheEntryRole R>
-CacheReservationManagerImpl<R>::CacheReservationHandle::CacheReservationHandle(
-    std::size_t incremental_memory_used,
-    std::shared_ptr<CacheReservationManagerImpl> cache_res_mgr)
-    : incremental_memory_used_(incremental_memory_used) {
-  assert(cache_res_mgr);
-  cache_res_mgr_ = cache_res_mgr;
-}
-
-template <CacheEntryRole R>
-CacheReservationManagerImpl<
-    R>::CacheReservationHandle::~CacheReservationHandle() {
-  Status s = cache_res_mgr_->ReleaseCacheReservation(incremental_memory_used_);
-  s.PermitUncheckedError();
-}
-
-template <CacheEntryRole R>
-CacheReservationManagerImpl<R>::CacheReservationManagerImpl(
-    std::shared_ptr<Cache> cache, bool delayed_decrease)
+CacheReservationManager::CacheReservationManager(std::shared_ptr<Cache> cache,
+                                                 bool delayed_decrease)
    : delayed_decrease_(delayed_decrease),
      cache_allocated_size_(0),
      memory_used_(0) {
@@ -48,15 +30,14 @@ CacheReservationManagerImpl<R>::CacheReservationManagerImpl(
  cache_ = cache;
 }

-template <CacheEntryRole R>
-CacheReservationManagerImpl<R>::~CacheReservationManagerImpl() {
+CacheReservationManager::~CacheReservationManager() {
  for (auto* handle : dummy_handles_) {
    cache_->Release(handle, true);
  }
 }

 template <CacheEntryRole R>
-Status CacheReservationManagerImpl<R>::UpdateCacheReservation(
+Status CacheReservationManager::UpdateCacheReservation(
    std::size_t new_mem_used) {
  memory_used_ = new_mem_used;
  std::size_t cur_cache_allocated_size =
@@ -64,7 +45,7 @@ Status CacheReservationManagerImpl<R>::UpdateCacheReservation(
  if (new_mem_used == cur_cache_allocated_size) {
    return Status::OK();
  } else if (new_mem_used > cur_cache_allocated_size) {
-    Status s = IncreaseCacheReservation(new_mem_used);
+    Status s = IncreaseCacheReservation<R>(new_mem_used);
    return s;
  } else {
    // In delayed decrease mode, we don't decrease cache reservation
@@ -85,32 +66,41 @@ Status CacheReservationManagerImpl<R>::UpdateCacheReservation(
  }
 }

+// Explicitly instantiate templates for "CacheEntryRole" values we use.
+// This makes it possible to keep the template definitions in the .cc file.
+template Status CacheReservationManager::UpdateCacheReservation<
+    CacheEntryRole::kWriteBuffer>(std::size_t new_mem_used);
+template Status CacheReservationManager::UpdateCacheReservation<
+    CacheEntryRole::kCompressionDictionaryBuildingBuffer>(
+    std::size_t new_mem_used);
+// For cache reservation manager unit tests
+template Status CacheReservationManager::UpdateCacheReservation<
+    CacheEntryRole::kMisc>(std::size_t new_mem_used);
+
 template <CacheEntryRole R>
-Status CacheReservationManagerImpl<R>::MakeCacheReservation(
+Status CacheReservationManager::MakeCacheReservation(
    std::size_t incremental_memory_used,
-    std::unique_ptr<CacheReservationManager::CacheReservationHandle>* handle) {
-  assert(handle);
+    std::unique_ptr<CacheReservationHandle<R>>* handle) {
+  assert(handle != nullptr);
  Status s =
-      UpdateCacheReservation(GetTotalMemoryUsed() + incremental_memory_used);
-  (*handle).reset(new CacheReservationManagerImpl::CacheReservationHandle(
-      incremental_memory_used,
-      std::enable_shared_from_this<
-          CacheReservationManagerImpl<R>>::shared_from_this()));
+      UpdateCacheReservation<R>(GetTotalMemoryUsed() + incremental_memory_used);
+  (*handle).reset(new CacheReservationHandle<R>(incremental_memory_used,
+                                                shared_from_this()));
  return s;
 }

-template <CacheEntryRole R>
-Status CacheReservationManagerImpl<R>::ReleaseCacheReservation(
-    std::size_t incremental_memory_used) {
-  assert(GetTotalMemoryUsed() >= incremental_memory_used);
-  std::size_t updated_total_mem_used =
-      GetTotalMemoryUsed() - incremental_memory_used;
-  Status s = UpdateCacheReservation(updated_total_mem_used);
-  return s;
-}
+template Status
+CacheReservationManager::MakeCacheReservation<CacheEntryRole::kMisc>(
+    std::size_t incremental_memory_used,
+    std::unique_ptr<CacheReservationHandle<CacheEntryRole::kMisc>>* handle);
+template Status CacheReservationManager::MakeCacheReservation<
+    CacheEntryRole::kFilterConstruction>(
+    std::size_t incremental_memory_used,
+    std::unique_ptr<
+        CacheReservationHandle<CacheEntryRole::kFilterConstruction>>* handle);

 template <CacheEntryRole R>
-Status CacheReservationManagerImpl<R>::IncreaseCacheReservation(
+Status CacheReservationManager::IncreaseCacheReservation(
    std::size_t new_mem_used) {
  Status return_status = Status::OK();
  while (new_mem_used > cache_allocated_size_.load(std::memory_order_relaxed)) {
@@ -128,8 +118,7 @@ Status CacheReservationManagerImpl<R>::IncreaseCacheReservation(
  return return_status;
 }

-template <CacheEntryRole R>
-Status CacheReservationManagerImpl<R>::DecreaseCacheReservation(
+Status CacheReservationManager::DecreaseCacheReservation(
    std::size_t new_mem_used) {
  Status return_status = Status::OK();

@@ -148,18 +137,15 @@ Status CacheReservationManagerImpl<R>::DecreaseCacheReservation(
  return return_status;
 }

-template <CacheEntryRole R>
-std::size_t CacheReservationManagerImpl<R>::GetTotalReservedCacheSize() {
+std::size_t CacheReservationManager::GetTotalReservedCacheSize() {
  return cache_allocated_size_.load(std::memory_order_relaxed);
 }

-template <CacheEntryRole R>
-std::size_t CacheReservationManagerImpl<R>::GetTotalMemoryUsed() {
+std::size_t CacheReservationManager::GetTotalMemoryUsed() {
  return memory_used_;
 }

-template <CacheEntryRole R>
-Slice CacheReservationManagerImpl<R>::GetNextCacheKey() {
+Slice CacheReservationManager::GetNextCacheKey() {
  // Calling this function will have the side-effect of changing the
  // underlying cache_key_ that is shared among other keys generated from this
  // fucntion. Therefore please make sure the previous keys are saved/copied
@@ -169,16 +155,34 @@ Slice CacheReservationManagerImpl<R>::GetNextCacheKey() {
 }

 template <CacheEntryRole R>
-Cache::DeleterFn CacheReservationManagerImpl<R>::TEST_GetNoopDeleterForRole() {
+Cache::DeleterFn CacheReservationManager::TEST_GetNoopDeleterForRole() {
  return GetNoopDeleterForRole<R>();
 }

-template class CacheReservationManagerImpl<
-    CacheEntryRole::kBlockBasedTableReader>;
-template class CacheReservationManagerImpl<
-    CacheEntryRole::kCompressionDictionaryBuildingBuffer>;
-template class CacheReservationManagerImpl<CacheEntryRole::kFilterConstruction>;
-template class CacheReservationManagerImpl<CacheEntryRole::kMisc>;
-template class CacheReservationManagerImpl<CacheEntryRole::kWriteBuffer>;
-template class CacheReservationManagerImpl<CacheEntryRole::kFileMetadata>;
+template Cache::DeleterFn CacheReservationManager::TEST_GetNoopDeleterForRole<
+    CacheEntryRole::kFilterConstruction>();
+
+template <CacheEntryRole R>
+CacheReservationHandle<R>::CacheReservationHandle(
+    std::size_t incremental_memory_used,
+    std::shared_ptr<CacheReservationManager> cache_res_mgr)
+    : incremental_memory_used_(incremental_memory_used) {
+  assert(cache_res_mgr != nullptr);
+  cache_res_mgr_ = cache_res_mgr;
+}
+
+template <CacheEntryRole R>
+CacheReservationHandle<R>::~CacheReservationHandle() {
+  assert(cache_res_mgr_ != nullptr);
+  assert(cache_res_mgr_->GetTotalMemoryUsed() >= incremental_memory_used_);
+
+  Status s = cache_res_mgr_->UpdateCacheReservation<R>(
+      cache_res_mgr_->GetTotalMemoryUsed() - incremental_memory_used_);
+  s.PermitUncheckedError();
+}
+
+// Explicitly instantiate templates for "CacheEntryRole" values we use.
+// This makes it possible to keep the template definitions in the .cc file.
+template class CacheReservationHandle<CacheEntryRole::kMisc>;
+template class CacheReservationHandle<CacheEntryRole::kFilterConstruction>;
 }  // namespace ROCKSDB_NAMESPACE
@@ -13,96 +13,54 @@
 #include <cstddef>
 #include <cstdint>
 #include <memory>
-#include <mutex>
 #include <vector>

 #include "cache/cache_entry_roles.h"
-#include "cache/cache_key.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/slice.h"
 #include "rocksdb/status.h"
+#include "table/block_based/block_based_table_reader.h"
 #include "util/coding.h"

 namespace ROCKSDB_NAMESPACE {
-// CacheReservationManager is an interface for reserving cache space for the
-// memory used
-class CacheReservationManager {
- public:
-  // CacheReservationHandle is for managing the lifetime of a cache reservation
-  // for an incremental amount of memory used (i.e, incremental_memory_used)
-  class CacheReservationHandle {
-   public:
-    virtual ~CacheReservationHandle() {}
-  };
-  virtual ~CacheReservationManager() {}
-  virtual Status UpdateCacheReservation(std::size_t new_memory_used) = 0;
-  // TODO(hx235): replace the usage of
-  // `UpdateCacheReservation(memory_used_delta, increase)` with
-  // `UpdateCacheReservation(new_memory_used)` so that we only have one
-  // `UpdateCacheReservation` function
-  virtual Status UpdateCacheReservation(std::size_t memory_used_delta,
-                                        bool increase) = 0;
-  virtual Status MakeCacheReservation(
-      std::size_t incremental_memory_used,
-      std::unique_ptr<CacheReservationManager::CacheReservationHandle>
-          *handle) = 0;
-  virtual std::size_t GetTotalReservedCacheSize() = 0;
-  virtual std::size_t GetTotalMemoryUsed() = 0;
-};

-// CacheReservationManagerImpl implements interface CacheReservationManager
-// for reserving cache space for the memory used by inserting/releasing dummy
-// entries in the cache.
+template <CacheEntryRole R>
+class CacheReservationHandle;
+
+// CacheReservationManager is for reserving cache space for the memory used
+// through inserting/releasing dummy entries in the cache.
 //
 // This class is NOT thread-safe, except that GetTotalReservedCacheSize()
 // can be called without external synchronization.
-template <CacheEntryRole R>
-class CacheReservationManagerImpl
-    : public CacheReservationManager,
-      public std::enable_shared_from_this<CacheReservationManagerImpl<R>> {
+class CacheReservationManager
+    : public std::enable_shared_from_this<CacheReservationManager> {
 public:
-  class CacheReservationHandle
-      : public CacheReservationManager::CacheReservationHandle {
-   public:
-    CacheReservationHandle(
-        std::size_t incremental_memory_used,
-        std::shared_ptr<CacheReservationManagerImpl> cache_res_mgr);
-    ~CacheReservationHandle() override;
-
-   private:
-    std::size_t incremental_memory_used_;
-    std::shared_ptr<CacheReservationManagerImpl> cache_res_mgr_;
-  };
-
-  // Construct a CacheReservationManagerImpl
+  // Construct a CacheReservationManager
  // @param cache The cache where dummy entries are inserted and released for
  // reserving cache space
  // @param delayed_decrease If set true, then dummy entries won't be released
-  //                         immediately when memory usage decreases.
+  // immediately when memory usage decreases.
  //                         Instead, it will be released when the memory usage
  //                         decreases to 3/4 of what we have reserved so far.
  //                         This is for saving some future dummy entry
  //                         insertion when memory usage increases are likely to
  //                         happen in the near future.
-  //
-  // REQUIRED: cache is not nullptr
-  explicit CacheReservationManagerImpl(std::shared_ptr<Cache> cache,
-                                       bool delayed_decrease = false);
+  explicit CacheReservationManager(std::shared_ptr<Cache> cache,
+                                   bool delayed_decrease = false);

  // no copy constructor, copy assignment, move constructor, move assignment
-  CacheReservationManagerImpl(const CacheReservationManagerImpl &) = delete;
-  CacheReservationManagerImpl &operator=(const CacheReservationManagerImpl &) =
-      delete;
-  CacheReservationManagerImpl(CacheReservationManagerImpl &&) = delete;
-  CacheReservationManagerImpl &operator=(CacheReservationManagerImpl &&) =
-      delete;
+  CacheReservationManager(const CacheReservationManager &) = delete;
+  CacheReservationManager &operator=(const CacheReservationManager &) = delete;
+  CacheReservationManager(CacheReservationManager &&) = delete;
+  CacheReservationManager &operator=(CacheReservationManager &&) = delete;

-  ~CacheReservationManagerImpl() override;
+  ~CacheReservationManager();

-  // One of the two ways of reserving/releasing cache space,
-  // see MakeCacheReservation() for the other.
-  //
-  // Use ONLY one of these two ways to prevent unexpected behavior.
+  template <CacheEntryRole R>
+
+  // One of the two ways of reserving/releasing cache,
+  // see CacheReservationManager::MakeCacheReservation() for the other.
+  // Use ONLY one of them to prevent unexpected behavior.
  //
  // Insert and release dummy entries in the cache to
  // match the size of total dummy entries with the least multiple of
@@ -132,18 +90,11 @@ class CacheReservationManagerImpl
  //         Otherwise, it returns the first non-ok status;
  //         On releasing dummy entries, it always returns Status::OK().
  //         On keeping dummy entries the same, it always returns Status::OK().
-  Status UpdateCacheReservation(std::size_t new_memory_used) override;
+  Status UpdateCacheReservation(std::size_t new_memory_used);

-  Status UpdateCacheReservation(std::size_t /* memory_used_delta */,
-                                bool /* increase */) override {
-    return Status::NotSupported();
-  }
-
-  // One of the two ways of reserving cache space and releasing is done through
-  // destruction of CacheReservationHandle.
-  // See UpdateCacheReservation() for the other way.
-  //
-  // Use ONLY one of these two ways to prevent unexpected behavior.
+  // One of the two ways of reserving/releasing cache,
+  // see CacheReservationManager::UpdateCacheReservation() for the other.
+  // Use ONLY one of them to prevent unexpected behavior.
  //
  // Insert dummy entries in the cache for the incremental memory usage
  // to match the size of total dummy entries with the least multiple of
@@ -167,19 +118,21 @@ class CacheReservationManagerImpl
  //        calling MakeCacheReservation() is needed if you want
  //        GetTotalMemoryUsed() indeed returns the latest memory used.
  //
-  // @param handle An pointer to std::unique_ptr<CacheReservationHandle> that
-  //        manages the lifetime of the cache reservation represented by the
-  //        handle.
+  // @param handle An pointer to std::unique_ptr<CacheReservationHandle<R>> that
+  //        manages the lifetime of the handle and its cache reservation.
  //
  // @return It returns Status::OK() if all dummy
  //         entry insertions succeed.
  //         Otherwise, it returns the first non-ok status;
  //
  // REQUIRES: handle != nullptr
+  // REQUIRES: The CacheReservationManager object is NOT managed by
+  //           std::unique_ptr as CacheReservationHandle needs to
+  //           shares ownership to the CacheReservationManager object.
+  template <CacheEntryRole R>
  Status MakeCacheReservation(
      std::size_t incremental_memory_used,
-      std::unique_ptr<CacheReservationManager::CacheReservationHandle> *handle)
-      override;
+      std::unique_ptr<CacheReservationHandle<R>> *handle);

  // Return the size of the cache (which is a multiple of kSizeDummyEntry)
  // successfully reserved by calling UpdateCacheReservation().
@@ -189,25 +142,25 @@ class CacheReservationManagerImpl
  // smaller number than the actual reserved cache size due to
  // the returned number will always be a multiple of kSizeDummyEntry
  // and cache full might happen in the middle of inserting a dummy entry.
-  std::size_t GetTotalReservedCacheSize() override;
+  std::size_t GetTotalReservedCacheSize();

  // Return the latest total memory used indicated by the most recent call of
  // UpdateCacheReservation(std::size_t new_memory_used);
-  std::size_t GetTotalMemoryUsed() override;
+  std::size_t GetTotalMemoryUsed();

  static constexpr std::size_t GetDummyEntrySize() { return kSizeDummyEntry; }

  // For testing only - it is to help ensure the NoopDeleterForRole<R>
-  // accessed from CacheReservationManagerImpl and the one accessed from the
-  // test are from the same translation units
+  // accessed from CacheReservationManager and the one accessed from the test
+  // are from the same translation units
+  template <CacheEntryRole R>
  static Cache::DeleterFn TEST_GetNoopDeleterForRole();

 private:
  static constexpr std::size_t kSizeDummyEntry = 256 * 1024;

  Slice GetNextCacheKey();
-
-  Status ReleaseCacheReservation(std::size_t incremental_memory_used);
+  template <CacheEntryRole R>
  Status IncreaseCacheReservation(std::size_t new_mem_used);
  Status DecreaseCacheReservation(std::size_t new_mem_used);

@@ -219,98 +172,20 @@ class CacheReservationManagerImpl
  CacheKey cache_key_;
 };

-class ConcurrentCacheReservationManager
-    : public CacheReservationManager,
-      public std::enable_shared_from_this<ConcurrentCacheReservationManager> {
+// CacheReservationHandle is for managing the lifetime of a cache reservation
+// This class is NOT thread-safe
+template <CacheEntryRole R>
+class CacheReservationHandle {
 public:
-  class CacheReservationHandle
-      : public CacheReservationManager::CacheReservationHandle {
-   public:
-    CacheReservationHandle(
-        std::shared_ptr<ConcurrentCacheReservationManager> cache_res_mgr,
-        std::unique_ptr<CacheReservationManager::CacheReservationHandle>
-            cache_res_handle) {
-      assert(cache_res_mgr && cache_res_handle);
-      cache_res_mgr_ = cache_res_mgr;
-      cache_res_handle_ = std::move(cache_res_handle);
-    }
-
-    ~CacheReservationHandle() override {
-      std::lock_guard<std::mutex> lock(cache_res_mgr_->cache_res_mgr_mu_);
-      cache_res_handle_.reset();
-    }
-
-   private:
-    std::shared_ptr<ConcurrentCacheReservationManager> cache_res_mgr_;
-    std::unique_ptr<CacheReservationManager::CacheReservationHandle>
-        cache_res_handle_;
-  };
-
-  explicit ConcurrentCacheReservationManager(
-      std::shared_ptr<CacheReservationManager> cache_res_mgr) {
-    cache_res_mgr_ = std::move(cache_res_mgr);
-  }
-  ConcurrentCacheReservationManager(const ConcurrentCacheReservationManager &) =
-      delete;
-  ConcurrentCacheReservationManager &operator=(
-      const ConcurrentCacheReservationManager &) = delete;
-  ConcurrentCacheReservationManager(ConcurrentCacheReservationManager &&) =
-      delete;
-  ConcurrentCacheReservationManager &operator=(
-      ConcurrentCacheReservationManager &&) = delete;
-
-  ~ConcurrentCacheReservationManager() override {}
-
-  inline Status UpdateCacheReservation(std::size_t new_memory_used) override {
-    std::lock_guard<std::mutex> lock(cache_res_mgr_mu_);
-    return cache_res_mgr_->UpdateCacheReservation(new_memory_used);
-  }
-
-  inline Status UpdateCacheReservation(std::size_t memory_used_delta,
-                                       bool increase) override {
-    std::lock_guard<std::mutex> lock(cache_res_mgr_mu_);
-    std::size_t total_mem_used = cache_res_mgr_->GetTotalMemoryUsed();
-    Status s;
-    if (!increase) {
-      assert(total_mem_used >= memory_used_delta);
-      s = cache_res_mgr_->UpdateCacheReservation(total_mem_used -
-                                                 memory_used_delta);
-    } else {
-      s = cache_res_mgr_->UpdateCacheReservation(total_mem_used +
-                                                 memory_used_delta);
-    }
-    return s;
-  }
-
-  inline Status MakeCacheReservation(
+  // REQUIRES: cache_res_mgr != nullptr
+  explicit CacheReservationHandle(
      std::size_t incremental_memory_used,
-      std::unique_ptr<CacheReservationManager::CacheReservationHandle> *handle)
-      override {
-    std::unique_ptr<CacheReservationManager::CacheReservationHandle>
-        wrapped_handle;
-    Status s;
-    {
-      std::lock_guard<std::mutex> lock(cache_res_mgr_mu_);
-      s = cache_res_mgr_->MakeCacheReservation(incremental_memory_used,
-                                               &wrapped_handle);
-    }
-    (*handle).reset(
-        new ConcurrentCacheReservationManager::CacheReservationHandle(
-            std::enable_shared_from_this<
-                ConcurrentCacheReservationManager>::shared_from_this(),
-            std::move(wrapped_handle)));
-    return s;
-  }
-  inline std::size_t GetTotalReservedCacheSize() override {
-    return cache_res_mgr_->GetTotalReservedCacheSize();
-  }
-  inline std::size_t GetTotalMemoryUsed() override {
-    std::lock_guard<std::mutex> lock(cache_res_mgr_mu_);
-    return cache_res_mgr_->GetTotalMemoryUsed();
-  }
+      std::shared_ptr<CacheReservationManager> cache_res_mgr);
+
+  ~CacheReservationHandle();

 private:
-  std::mutex cache_res_mgr_mu_;
+  std::size_t incremental_memory_used_;
  std::shared_ptr<CacheReservationManager> cache_res_mgr_;
 };
 }  // namespace ROCKSDB_NAMESPACE
@@ -15,6 +15,7 @@
 #include "cache/cache_entry_roles.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/slice.h"
+#include "table/block_based/block_based_table_reader.h"
 #include "test_util/testharness.h"
 #include "util/coding.h"

@@ -22,24 +23,25 @@ namespace ROCKSDB_NAMESPACE {
 class CacheReservationManagerTest : public ::testing::Test {
 protected:
  static constexpr std::size_t kSizeDummyEntry =
-      CacheReservationManagerImpl<CacheEntryRole::kMisc>::GetDummyEntrySize();
+      CacheReservationManager::GetDummyEntrySize();
  static constexpr std::size_t kCacheCapacity = 4096 * kSizeDummyEntry;
  static constexpr int kNumShardBits = 0;  // 2^0 shard
  static constexpr std::size_t kMetaDataChargeOverhead = 10000;

  std::shared_ptr<Cache> cache = NewLRUCache(kCacheCapacity, kNumShardBits);
-  std::shared_ptr<CacheReservationManager> test_cache_rev_mng;
+  std::unique_ptr<CacheReservationManager> test_cache_rev_mng;

  CacheReservationManagerTest() {
-    test_cache_rev_mng =
-        std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
-            cache);
+    test_cache_rev_mng.reset(new CacheReservationManager(cache));
  }
 };

 TEST_F(CacheReservationManagerTest, GenerateCacheKey) {
  std::size_t new_mem_used = 1 * kSizeDummyEntry;
-  Status s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  Status s =
+      test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  ASSERT_EQ(s, Status::OK());
  ASSERT_GE(cache->GetPinnedUsage(), 1 * kSizeDummyEntry);
  ASSERT_LT(cache->GetPinnedUsage(),
@@ -47,14 +49,13 @@ TEST_F(CacheReservationManagerTest, GenerateCacheKey) {

  // Next unique Cache key
  CacheKey ckey = CacheKey::CreateUniqueForCacheLifetime(cache.get());
-  // Get to the underlying values
-  using PairU64 = std::array<uint64_t, 2>;
-  auto& ckey_pair = *reinterpret_cast<PairU64*>(&ckey);
  // Back it up to the one used by CRM (using CacheKey implementation details)
-  ckey_pair[1]--;
+  using PairU64 = std::pair<uint64_t, uint64_t>;
+  auto& ckey_pair = *reinterpret_cast<PairU64*>(&ckey);
+  ckey_pair.second--;

  // Specific key (subject to implementation details)
-  EXPECT_EQ(ckey_pair, PairU64({0, 2}));
+  EXPECT_EQ(ckey_pair, PairU64(0, 2));

  Cache::Handle* handle = cache->Lookup(ckey.AsSlice());
  EXPECT_NE(handle, nullptr)
@@ -65,7 +66,10 @@ TEST_F(CacheReservationManagerTest, GenerateCacheKey) {

 TEST_F(CacheReservationManagerTest, KeepCacheReservationTheSame) {
  std::size_t new_mem_used = 1 * kSizeDummyEntry;
-  Status s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  Status s =
+      test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  ASSERT_EQ(s, Status::OK());
  ASSERT_EQ(test_cache_rev_mng->GetTotalReservedCacheSize(),
            1 * kSizeDummyEntry);
@@ -75,7 +79,9 @@ TEST_F(CacheReservationManagerTest, KeepCacheReservationTheSame) {
  ASSERT_LT(initial_pinned_usage,
            1 * kSizeDummyEntry + kMetaDataChargeOverhead);

-  s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  s = test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::OK())
      << "Failed to keep cache reservation the same when new_mem_used equals "
         "to current cache reservation";
@@ -94,7 +100,10 @@ TEST_F(CacheReservationManagerTest, KeepCacheReservationTheSame) {
 TEST_F(CacheReservationManagerTest,
       IncreaseCacheReservationByMultiplesOfDummyEntrySize) {
  std::size_t new_mem_used = 2 * kSizeDummyEntry;
-  Status s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  Status s =
+      test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::OK())
      << "Failed to increase cache reservation correctly";
  EXPECT_EQ(test_cache_rev_mng->GetTotalReservedCacheSize(),
@@ -112,7 +121,10 @@ TEST_F(CacheReservationManagerTest,
 TEST_F(CacheReservationManagerTest,
       IncreaseCacheReservationNotByMultiplesOfDummyEntrySize) {
  std::size_t new_mem_used = 2 * kSizeDummyEntry + kSizeDummyEntry / 2;
-  Status s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  Status s =
+      test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::OK())
      << "Failed to increase cache reservation correctly";
  EXPECT_EQ(test_cache_rev_mng->GetTotalReservedCacheSize(),
@@ -131,7 +143,7 @@ TEST(CacheReservationManagerIncreaseReservcationOnFullCacheTest,
     IncreaseCacheReservationOnFullCache) {
  ;
  constexpr std::size_t kSizeDummyEntry =
-      CacheReservationManagerImpl<CacheEntryRole::kMisc>::GetDummyEntrySize();
+      CacheReservationManager::GetDummyEntrySize();
  constexpr std::size_t kSmallCacheCapacity = 4 * kSizeDummyEntry;
  constexpr std::size_t kBigCacheCapacity = 4096 * kSizeDummyEntry;
  constexpr std::size_t kMetaDataChargeOverhead = 10000;
@@ -141,12 +153,14 @@ TEST(CacheReservationManagerIncreaseReservcationOnFullCacheTest,
  lo.num_shard_bits = 0;  // 2^0 shard
  lo.strict_capacity_limit = true;
  std::shared_ptr<Cache> cache = NewLRUCache(lo);
-  std::shared_ptr<CacheReservationManager> test_cache_rev_mng =
-      std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
-          cache);
+  std::unique_ptr<CacheReservationManager> test_cache_rev_mng(
+      new CacheReservationManager(cache));

  std::size_t new_mem_used = kSmallCacheCapacity + 1;
-  Status s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  Status s =
+      test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::Incomplete())
      << "Failed to return status to indicate failure of dummy entry insertion "
         "during cache reservation on full cache";
@@ -169,7 +183,9 @@ TEST(CacheReservationManagerIncreaseReservcationOnFullCacheTest,
         "encountering cache resevation failure due to full cache";

  new_mem_used = kSmallCacheCapacity / 2;  // 2 dummy entries
-  s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  s = test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::OK())
      << "Failed to decrease cache reservation after encountering cache "
         "reservation failure due to full cache";
@@ -191,7 +207,9 @@ TEST(CacheReservationManagerIncreaseReservcationOnFullCacheTest,

  // Create cache full again for subsequent tests
  new_mem_used = kSmallCacheCapacity + 1;
-  s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  s = test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::Incomplete())
      << "Failed to return status to indicate failure of dummy entry insertion "
         "during cache reservation on full cache";
@@ -217,7 +235,9 @@ TEST(CacheReservationManagerIncreaseReservcationOnFullCacheTest,
  // succeed
  cache->SetCapacity(kBigCacheCapacity);
  new_mem_used = kSmallCacheCapacity + 1;
-  s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  s = test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::OK())
      << "Failed to increase cache reservation after increasing cache capacity "
         "and mitigating cache full error";
@@ -239,7 +259,10 @@ TEST(CacheReservationManagerIncreaseReservcationOnFullCacheTest,
 TEST_F(CacheReservationManagerTest,
       DecreaseCacheReservationByMultiplesOfDummyEntrySize) {
  std::size_t new_mem_used = 2 * kSizeDummyEntry;
-  Status s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  Status s =
+      test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  ASSERT_EQ(s, Status::OK());
  ASSERT_EQ(test_cache_rev_mng->GetTotalReservedCacheSize(),
            2 * kSizeDummyEntry);
@@ -249,7 +272,9 @@ TEST_F(CacheReservationManagerTest,
            2 * kSizeDummyEntry + kMetaDataChargeOverhead);

  new_mem_used = 1 * kSizeDummyEntry;
-  s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  s = test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::OK())
      << "Failed to decrease cache reservation correctly";
  EXPECT_EQ(test_cache_rev_mng->GetTotalReservedCacheSize(),
@@ -267,7 +292,10 @@ TEST_F(CacheReservationManagerTest,
 TEST_F(CacheReservationManagerTest,
       DecreaseCacheReservationNotByMultiplesOfDummyEntrySize) {
  std::size_t new_mem_used = 2 * kSizeDummyEntry;
-  Status s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  Status s =
+      test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  ASSERT_EQ(s, Status::OK());
  ASSERT_EQ(test_cache_rev_mng->GetTotalReservedCacheSize(),
            2 * kSizeDummyEntry);
@@ -277,7 +305,9 @@ TEST_F(CacheReservationManagerTest,
            2 * kSizeDummyEntry + kMetaDataChargeOverhead);

  new_mem_used = kSizeDummyEntry / 2;
-  s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  s = test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::OK())
      << "Failed to decrease cache reservation correctly";
  EXPECT_EQ(test_cache_rev_mng->GetTotalReservedCacheSize(),
@@ -295,7 +325,7 @@ TEST_F(CacheReservationManagerTest,
 TEST(CacheReservationManagerWithDelayedDecreaseTest,
     DecreaseCacheReservationWithDelayedDecrease) {
  constexpr std::size_t kSizeDummyEntry =
-      CacheReservationManagerImpl<CacheEntryRole::kMisc>::GetDummyEntrySize();
+      CacheReservationManager::GetDummyEntrySize();
  constexpr std::size_t kCacheCapacity = 4096 * kSizeDummyEntry;
  constexpr std::size_t kMetaDataChargeOverhead = 10000;

@@ -303,12 +333,14 @@ TEST(CacheReservationManagerWithDelayedDecreaseTest,
  lo.capacity = kCacheCapacity;
  lo.num_shard_bits = 0;
  std::shared_ptr<Cache> cache = NewLRUCache(lo);
-  std::shared_ptr<CacheReservationManager> test_cache_rev_mng =
-      std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
-          cache, true /* delayed_decrease */);
+  std::unique_ptr<CacheReservationManager> test_cache_rev_mng(
+      new CacheReservationManager(cache, true /* delayed_decrease */));

  std::size_t new_mem_used = 8 * kSizeDummyEntry;
-  Status s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  Status s =
+      test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  ASSERT_EQ(s, Status::OK());
  ASSERT_EQ(test_cache_rev_mng->GetTotalReservedCacheSize(),
            8 * kSizeDummyEntry);
@@ -319,7 +351,9 @@ TEST(CacheReservationManagerWithDelayedDecreaseTest,
            8 * kSizeDummyEntry + kMetaDataChargeOverhead);

  new_mem_used = 6 * kSizeDummyEntry;
-  s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  s = test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::OK()) << "Failed to delay decreasing cache reservation";
  EXPECT_EQ(test_cache_rev_mng->GetTotalReservedCacheSize(),
            8 * kSizeDummyEntry)
@@ -331,7 +365,9 @@ TEST(CacheReservationManagerWithDelayedDecreaseTest,
      << "Failed to delay decreasing underlying dummy entries in cache";

  new_mem_used = 7 * kSizeDummyEntry;
-  s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  s = test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::OK()) << "Failed to delay decreasing cache reservation";
  EXPECT_EQ(test_cache_rev_mng->GetTotalReservedCacheSize(),
            8 * kSizeDummyEntry)
@@ -343,7 +379,9 @@ TEST(CacheReservationManagerWithDelayedDecreaseTest,
      << "Failed to delay decreasing underlying dummy entries in cache";

  new_mem_used = 6 * kSizeDummyEntry - 1;
-  s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+  s = test_cache_rev_mng
+          ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+              new_mem_used);
  EXPECT_EQ(s, Status::OK())
      << "Failed to decrease cache reservation correctly when new_mem_used < "
         "GetTotalReservedCacheSize() * 3 / 4 on delayed decrease mode";
@@ -367,7 +405,7 @@ TEST(CacheReservationManagerWithDelayedDecreaseTest,
 TEST(CacheReservationManagerDestructorTest,
     ReleaseRemainingDummyEntriesOnDestruction) {
  constexpr std::size_t kSizeDummyEntry =
-      CacheReservationManagerImpl<CacheEntryRole::kMisc>::GetDummyEntrySize();
+      CacheReservationManager::GetDummyEntrySize();
  constexpr std::size_t kCacheCapacity = 4096 * kSizeDummyEntry;
  constexpr std::size_t kMetaDataChargeOverhead = 10000;

@@ -376,11 +414,13 @@ TEST(CacheReservationManagerDestructorTest,
  lo.num_shard_bits = 0;
  std::shared_ptr<Cache> cache = NewLRUCache(lo);
  {
-    std::shared_ptr<CacheReservationManager> test_cache_rev_mng =
-        std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
-            cache);
+    std::unique_ptr<CacheReservationManager> test_cache_rev_mng(
+        new CacheReservationManager(cache));
    std::size_t new_mem_used = 1 * kSizeDummyEntry;
-    Status s = test_cache_rev_mng->UpdateCacheReservation(new_mem_used);
+    Status s =
+        test_cache_rev_mng
+            ->UpdateCacheReservation<ROCKSDB_NAMESPACE::CacheEntryRole::kMisc>(
+                new_mem_used);
    ASSERT_EQ(s, Status::OK());
    ASSERT_GE(cache->GetPinnedUsage(), 1 * kSizeDummyEntry);
    ASSERT_LT(cache->GetPinnedUsage(),
@@ -402,19 +442,18 @@ TEST(CacheReservationHandleTest, HandleTest) {
  std::shared_ptr<Cache> cache = NewLRUCache(lo);

  std::shared_ptr<CacheReservationManager> test_cache_rev_mng(
-      std::make_shared<CacheReservationManagerImpl<CacheEntryRole::kMisc>>(
-          cache));
+      std::make_shared<CacheReservationManager>(cache));

  std::size_t mem_used = 0;
  const std::size_t incremental_mem_used_handle_1 = 1 * kSizeDummyEntry;
  const std::size_t incremental_mem_used_handle_2 = 2 * kSizeDummyEntry;
-  std::unique_ptr<CacheReservationManager::CacheReservationHandle> handle_1,
+  std::unique_ptr<CacheReservationHandle<CacheEntryRole::kMisc>> handle_1,
      handle_2;

  // To test consecutive CacheReservationManager::MakeCacheReservation works
  // correctly in terms of returning the handle as well as updating cache
  // reservation and the latest total memory used
-  Status s = test_cache_rev_mng->MakeCacheReservation(
+  Status s = test_cache_rev_mng->MakeCacheReservation<CacheEntryRole::kMisc>(
      incremental_mem_used_handle_1, &handle_1);
  mem_used = mem_used + incremental_mem_used_handle_1;
  ASSERT_EQ(s, Status::OK());
@@ -424,8 +463,8 @@ TEST(CacheReservationHandleTest, HandleTest) {
  EXPECT_GE(cache->GetPinnedUsage(), mem_used);
  EXPECT_LT(cache->GetPinnedUsage(), mem_used + kMetaDataChargeOverhead);

-  s = test_cache_rev_mng->MakeCacheReservation(incremental_mem_used_handle_2,
-                                               &handle_2);
+  s = test_cache_rev_mng->MakeCacheReservation<CacheEntryRole::kMisc>(
+      incremental_mem_used_handle_2, &handle_2);
  mem_used = mem_used + incremental_mem_used_handle_2;
  ASSERT_EQ(s, Status::OK());
  EXPECT_TRUE(handle_2 != nullptr);
@@ -434,9 +473,8 @@ TEST(CacheReservationHandleTest, HandleTest) {
  EXPECT_GE(cache->GetPinnedUsage(), mem_used);
  EXPECT_LT(cache->GetPinnedUsage(), mem_used + kMetaDataChargeOverhead);

-  // To test
-  // CacheReservationManager::CacheReservationHandle::~CacheReservationHandle()
-  // works correctly in releasing the cache reserved for the handle
+  // To test CacheReservationHandle::~CacheReservationHandle() works correctly
+  // in releasing the cache reserved for the handle
  handle_1.reset();
  EXPECT_TRUE(handle_1 == nullptr);
  mem_used = mem_used - incremental_mem_used_handle_1;
@@ -14,53 +14,31 @@
 #include <iostream>
 #include <string>
 #include <vector>
-
 #include "cache/clock_cache.h"
-#include "cache/fast_lru_cache.h"
 #include "cache/lru_cache.h"
-#include "port/stack_trace.h"
 #include "test_util/testharness.h"
 #include "util/coding.h"
 #include "util/string_util.h"

 namespace ROCKSDB_NAMESPACE {

-namespace {
-
 // Conversions between numeric keys/values and the types expected by Cache.
-std::string EncodeKey16Bytes(int k) {
-  std::string result;
-  PutFixed32(&result, k);
-  result.append(std::string(12, 'a'));  // Because we need a 16B output, we
-                                        // add a 12-byte padding.
-  return result;
-}
-
-int DecodeKey16Bytes(const Slice& k) {
-  assert(k.size() == 16);
-  return DecodeFixed32(k.data());  // Decodes only the first 4 bytes of k.
-}
-
-std::string EncodeKey32Bits(int k) {
+static std::string EncodeKey(int k) {
  std::string result;
  PutFixed32(&result, k);
  return result;
 }
-
-int DecodeKey32Bits(const Slice& k) {
+static int DecodeKey(const Slice& k) {
  assert(k.size() == 4);
  return DecodeFixed32(k.data());
 }
-
-void* EncodeValue(uintptr_t v) { return reinterpret_cast<void*>(v); }
-
-int DecodeValue(void* v) {
+static void* EncodeValue(uintptr_t v) { return reinterpret_cast<void*>(v); }
+static int DecodeValue(void* v) {
  return static_cast<int>(reinterpret_cast<uintptr_t>(v));
 }

 const std::string kLRU = "lru";
 const std::string kClock = "clock";
-const std::string kFast = "fast";

 void dumbDeleter(const Slice& /*key*/, void* /*value*/) {}

@@ -69,19 +47,12 @@ void eraseDeleter(const Slice& /*key*/, void* value) {
  cache->Erase("foo");
 }

-}  // anonymous namespace
-
 class CacheTest : public testing::TestWithParam<std::string> {
 public:
  static CacheTest* current_;
-  static std::string type_;

  static void Deleter(const Slice& key, void* v) {
-    if (type_ == kFast) {
-      current_->deleted_keys_.push_back(DecodeKey16Bytes(key));
-    } else {
-      current_->deleted_keys_.push_back(DecodeKey32Bits(key));
-    }
+    current_->deleted_keys_.push_back(DecodeKey(key));
    current_->deleted_values_.push_back(DecodeValue(v));
  }

@@ -100,7 +71,6 @@ class CacheTest : public testing::TestWithParam<std::string> {
      : cache_(NewCache(kCacheSize, kNumShardBits, false)),
        cache2_(NewCache(kCacheSize2, kNumShardBits2, false)) {
    current_ = this;
-    type_ = GetParam();
  }

  ~CacheTest() override {}
@@ -113,11 +83,6 @@ class CacheTest : public testing::TestWithParam<std::string> {
    if (type == kClock) {
      return NewClockCache(capacity);
    }
-    if (type == kFast) {
-      return NewFastLRUCache(
-          capacity, 1 /*estimated_value_size*/, -1 /*num_shard_bits*/,
-          false /*strict_capacity_limit*/, kDefaultCacheMetadataChargePolicy);
-    }
    return nullptr;
  }

@@ -138,35 +103,9 @@ class CacheTest : public testing::TestWithParam<std::string> {
      return NewClockCache(capacity, num_shard_bits, strict_capacity_limit,
                           charge_policy);
    }
-    if (type == kFast) {
-      return NewFastLRUCache(capacity, 1 /*estimated_value_size*/,
-                             num_shard_bits, strict_capacity_limit,
-                             charge_policy);
-    }
    return nullptr;
  }

-  // These functions encode/decode keys in tests cases that use
-  // int keys.
-  // Currently, FastLRUCache requires keys to be 16B long, whereas
-  // LRUCache and ClockCache don't, so the encoding depends on
-  // the cache type.
-  std::string EncodeKey(int k) {
-    if (GetParam() == kFast) {
-      return EncodeKey16Bytes(k);
-    } else {
-      return EncodeKey32Bits(k);
-    }
-  }
-
-  int DecodeKey(const Slice& k) {
-    if (GetParam() == kFast) {
-      return DecodeKey16Bytes(k);
-    } else {
-      return DecodeKey32Bits(k);
-    }
-  }
-
  int Lookup(std::shared_ptr<Cache> cache, int key) {
    Cache::Handle* handle = cache->Lookup(EncodeKey(key));
    const int r = (handle == nullptr) ? -1 : DecodeValue(cache->Value(handle));
@@ -210,18 +149,11 @@ class CacheTest : public testing::TestWithParam<std::string> {
    Erase(cache2_, key);
  }
 };
-
 CacheTest* CacheTest::current_;
-std::string CacheTest::type_;

 class LRUCacheTest : public CacheTest {};

 TEST_P(CacheTest, UsageTest) {
-  if (GetParam() == kFast) {
-    ROCKSDB_GTEST_BYPASS("FastLRUCache requires 16 byte keys.");
-    return;
-  }
-
  // cache is std::shared_ptr and will be automatically cleaned up.
  const uint64_t kCapacity = 100000;
  auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
@@ -251,7 +183,7 @@ TEST_P(CacheTest, UsageTest) {

  // make sure the cache will be overloaded
  for (uint64_t i = 1; i < kCapacity; ++i) {
-    auto key = std::to_string(i);
+    auto key = ToString(i);
    ASSERT_OK(cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
                            dumbDeleter));
    ASSERT_OK(precise_cache->Insert(key, reinterpret_cast<void*>(value),
@@ -266,11 +198,6 @@ TEST_P(CacheTest, UsageTest) {
 }

 TEST_P(CacheTest, PinnedUsageTest) {
-  if (GetParam() == kFast) {
-    ROCKSDB_GTEST_BYPASS("FastLRUCache requires 16 byte keys.");
-    return;
-  }
-
  // cache is std::shared_ptr and will be automatically cleaned up.
  const uint64_t kCapacity = 200000;
  auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
@@ -328,7 +255,7 @@ TEST_P(CacheTest, PinnedUsageTest) {

  // check that overloading the cache does not change the pinned usage
  for (uint64_t i = 1; i < 2 * kCapacity; ++i) {
-    auto key = std::to_string(i);
+    auto key = ToString(i);
    ASSERT_OK(cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
                            dumbDeleter));
    ASSERT_OK(precise_cache->Insert(key, reinterpret_cast<void*>(value),
@@ -523,22 +450,12 @@ TEST_P(CacheTest, EvictionPolicyRef) {
 }

 TEST_P(CacheTest, EvictEmptyCache) {
-  if (GetParam() == kFast) {
-    ROCKSDB_GTEST_BYPASS("FastLRUCache requires 16 byte keys.");
-    return;
-  }
-
  // Insert item large than capacity to trigger eviction on empty cache.
  auto cache = NewCache(1, 0, false);
  ASSERT_OK(cache->Insert("foo", nullptr, 10, dumbDeleter));
 }

 TEST_P(CacheTest, EraseFromDeleter) {
-  if (GetParam() == kFast) {
-    ROCKSDB_GTEST_BYPASS("FastLRUCache requires 16 byte keys.");
-    return;
-  }
-
  // Have deleter which will erase item from cache, which will re-enter
  // the cache at that point.
  std::shared_ptr<Cache> cache = NewCache(10, 0, false);
@@ -607,9 +524,9 @@ TEST_P(CacheTest, NewId) {

 class Value {
 public:
-  explicit Value(int v) : v_(v) {}
+  explicit Value(size_t v) : v_(v) { }

-  int v_;
+  size_t v_;
 };

 namespace {
@@ -657,8 +574,8 @@ TEST_P(CacheTest, SetCapacity) {
  std::shared_ptr<Cache> cache = NewCache(5, 0, false);
  std::vector<Cache::Handle*> handles(10);
  // Insert 5 entries, but not releasing.
-  for (int i = 0; i < 5; i++) {
-    std::string key = EncodeKey(i + 1);
+  for (size_t i = 0; i < 5; i++) {
+    std::string key = ToString(i+1);
    Status s = cache->Insert(key, new Value(i + 1), 1, &deleter, &handles[i]);
    ASSERT_TRUE(s.ok());
  }
@@ -672,14 +589,14 @@ TEST_P(CacheTest, SetCapacity) {
  // insert 5 more elements to cache, then release 5,
  // then decrease capacity to 7, final capacity should be 7
  // and usage should be 7
-  for (int i = 5; i < 10; i++) {
-    std::string key = EncodeKey(i + 1);
+  for (size_t i = 5; i < 10; i++) {
+    std::string key = ToString(i+1);
    Status s = cache->Insert(key, new Value(i + 1), 1, &deleter, &handles[i]);
    ASSERT_TRUE(s.ok());
  }
  ASSERT_EQ(10U, cache->GetCapacity());
  ASSERT_EQ(10U, cache->GetUsage());
-  for (int i = 0; i < 5; i++) {
+  for (size_t i = 0; i < 5; i++) {
    cache->Release(handles[i]);
  }
  ASSERT_EQ(10U, cache->GetCapacity());
@@ -689,7 +606,7 @@ TEST_P(CacheTest, SetCapacity) {
  ASSERT_EQ(7, cache->GetUsage());

  // release remaining 5 to keep valgrind happy
-  for (int i = 5; i < 10; i++) {
+  for (size_t i = 5; i < 10; i++) {
    cache->Release(handles[i]);
  }

@@ -703,8 +620,8 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
  std::shared_ptr<Cache> cache = NewCache(5, 0, false);
  std::vector<Cache::Handle*> handles(10);
  Status s;
-  for (int i = 0; i < 10; i++) {
-    std::string key = EncodeKey(i + 1);
+  for (size_t i = 0; i < 10; i++) {
+    std::string key = ToString(i + 1);
    s = cache->Insert(key, new Value(i + 1), 1, &deleter, &handles[i]);
    ASSERT_OK(s);
    ASSERT_NE(nullptr, handles[i]);
@@ -712,7 +629,7 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
  ASSERT_EQ(10, cache->GetUsage());

  // test2: set the flag to true. Insert and check if it fails.
-  std::string extra_key = EncodeKey(100);
+  std::string extra_key = "extra";
  Value* extra_value = new Value(0);
  cache->SetStrictCapacityLimit(true);
  Cache::Handle* handle;
@@ -721,14 +638,14 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
  ASSERT_EQ(nullptr, handle);
  ASSERT_EQ(10, cache->GetUsage());

-  for (int i = 0; i < 10; i++) {
+  for (size_t i = 0; i < 10; i++) {
    cache->Release(handles[i]);
  }

  // test3: init with flag being true.
  std::shared_ptr<Cache> cache2 = NewCache(5, 0, true);
-  for (int i = 0; i < 5; i++) {
-    std::string key = EncodeKey(i + 1);
+  for (size_t i = 0; i < 5; i++) {
+    std::string key = ToString(i + 1);
    s = cache2->Insert(key, new Value(i + 1), 1, &deleter, &handles[i]);
    ASSERT_OK(s);
    ASSERT_NE(nullptr, handles[i]);
@@ -743,7 +660,7 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
  ASSERT_EQ(5, cache2->GetUsage());
  ASSERT_EQ(nullptr, cache2->Lookup(extra_key));

-  for (int i = 0; i < 5; i++) {
+  for (size_t i = 0; i < 5; i++) {
    cache2->Release(handles[i]);
  }
 }
@@ -757,15 +674,15 @@ TEST_P(CacheTest, OverCapacity) {
  std::vector<Cache::Handle*> handles(n+1);

  // Insert n+1 entries, but not releasing.
-  for (int i = 0; i < static_cast<int>(n + 1); i++) {
-    std::string key = EncodeKey(i + 1);
+  for (size_t i = 0; i < n + 1; i++) {
+    std::string key = ToString(i+1);
    Status s = cache->Insert(key, new Value(i + 1), 1, &deleter, &handles[i]);
    ASSERT_TRUE(s.ok());
  }

  // Guess what's in the cache now?
-  for (int i = 0; i < static_cast<int>(n + 1); i++) {
-    std::string key = EncodeKey(i + 1);
+  for (size_t i = 0; i < n + 1; i++) {
+    std::string key = ToString(i+1);
    auto h = cache->Lookup(key);
    ASSERT_TRUE(h != nullptr);
    if (h) cache->Release(h);
@@ -773,7 +690,7 @@ TEST_P(CacheTest, OverCapacity) {

  // the cache is over capacity since nothing could be evicted
  ASSERT_EQ(n + 1U, cache->GetUsage());
-  for (int i = 0; i < static_cast<int>(n + 1); i++) {
+  for (size_t i = 0; i < n + 1; i++) {
    cache->Release(handles[i]);
  }
  // Make sure eviction is triggered.
@@ -785,14 +702,14 @@ TEST_P(CacheTest, OverCapacity) {
  // element 0 is evicted and the rest is there
  // This is consistent with the LRU policy since the element 0
  // was released first
-  for (int i = 0; i < static_cast<int>(n + 1); i++) {
-    std::string key = EncodeKey(i + 1);
+  for (size_t i = 0; i < n + 1; i++) {
+    std::string key = ToString(i+1);
    auto h = cache->Lookup(key);
    if (h) {
-      ASSERT_NE(static_cast<size_t>(i), 0U);
+      ASSERT_NE(i, 0U);
      cache->Release(h);
    } else {
-      ASSERT_EQ(static_cast<size_t>(i), 0U);
+      ASSERT_EQ(i, 0U);
    }
  }
 }
@@ -818,7 +735,7 @@ TEST_P(CacheTest, ApplyToAllCacheEntriesTest) {
  std::sort(inserted.begin(), inserted.end());
  std::sort(legacy_callback_state.begin(), legacy_callback_state.end());
  ASSERT_EQ(inserted.size(), legacy_callback_state.size());
-  for (int i = 0; i < static_cast<int>(inserted.size()); ++i) {
+  for (size_t i = 0; i < inserted.size(); ++i) {
    EXPECT_EQ(inserted[i], legacy_callback_state[i]);
  }
 }
@@ -827,9 +744,9 @@ TEST_P(CacheTest, ApplyToAllEntriesTest) {
  std::vector<std::string> callback_state;
  const auto callback = [&](const Slice& key, void* value, size_t charge,
                            Cache::DeleterFn deleter) {
-    callback_state.push_back(std::to_string(DecodeKey(key)) + "," +
-                             std::to_string(DecodeValue(value)) + "," +
-                             std::to_string(charge));
+    callback_state.push_back(ToString(DecodeKey(key)) + "," +
+                             ToString(DecodeValue(value)) + "," +
+                             ToString(charge));
    assert(deleter == &CacheTest::Deleter);
  };

@@ -838,15 +755,15 @@ TEST_P(CacheTest, ApplyToAllEntriesTest) {

  for (int i = 0; i < 10; ++i) {
    Insert(i, i * 2, i + 1);
-    inserted.push_back(std::to_string(i) + "," + std::to_string(i * 2) + "," +
-                       std::to_string(i + 1));
+    inserted.push_back(ToString(i) + "," + ToString(i * 2) + "," +
+                       ToString(i + 1));
  }
  cache_->ApplyToAllEntries(callback, /*opts*/ {});

  std::sort(inserted.begin(), inserted.end());
  std::sort(callback_state.begin(), callback_state.end());
  ASSERT_EQ(inserted.size(), callback_state.size());
-  for (int i = 0; i < static_cast<int>(inserted.size()); ++i) {
+  for (size_t i = 0; i < inserted.size(); ++i) {
    EXPECT_EQ(inserted[i], callback_state[i]);
  }
 }
@@ -861,10 +778,8 @@ TEST_P(CacheTest, ApplyToAllEntriesDuringResize) {
  constexpr int kSpecialCharge = 2;
  constexpr int kNotSpecialCharge = 1;
  constexpr int kSpecialCount = 100;
-  size_t expected_usage = 0;
  for (int i = 0; i < kSpecialCount; ++i) {
    Insert(i, i * 2, kSpecialCharge);
-    expected_usage += kSpecialCharge;
  }

  // For callback
@@ -885,17 +800,12 @@ TEST_P(CacheTest, ApplyToAllEntriesDuringResize) {
  });

  // In parallel, add more entries, enough to cause resize but not enough
-  // to cause ejections. (Note: if any cache shard is over capacity, there
-  // will be ejections)
-  for (int i = kSpecialCount * 1; i < kSpecialCount * 5; ++i) {
+  // to cause ejections
+  for (int i = kSpecialCount * 1; i < kSpecialCount * 6; ++i) {
    Insert(i, i * 2, kNotSpecialCharge);
-    expected_usage += kNotSpecialCharge;
  }

  apply_thread.join();
-  // verify no evictions
-  ASSERT_EQ(cache_->GetUsage(), expected_usage);
-  // verify everything seen in ApplyToAllEntries
  ASSERT_EQ(special_count, kSpecialCount);
 }

@@ -928,18 +838,15 @@ TEST_P(CacheTest, GetChargeAndDeleter) {
 std::shared_ptr<Cache> (*new_clock_cache_func)(
    size_t, int, bool, CacheMetadataChargePolicy) = NewClockCache;
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
-                        testing::Values(kLRU, kClock, kFast));
+                        testing::Values(kLRU, kClock));
 #else
-INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
-                        testing::Values(kLRU, kFast));
+INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest, testing::Values(kLRU));
 #endif  // SUPPORT_CLOCK_CACHE
-INSTANTIATE_TEST_CASE_P(CacheTestInstance, LRUCacheTest,
-                        testing::Values(kLRU, kFast));
+INSTANTIATE_TEST_CASE_P(CacheTestInstance, LRUCacheTest, testing::Values(kLRU));

 }  // namespace ROCKSDB_NAMESPACE

 int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
  ::testing::InitGoogleTest(&argc, argv);
  return RUN_ALL_TESTS();
 }
@@ -39,7 +39,7 @@ std::shared_ptr<Cache> NewClockCache(
 #include "port/port.h"
 #include "tbb/concurrent_hash_map.h"
 #include "util/autovector.h"
-#include "util/distributed_mutex.h"
+#include "util/mutexlock.h"

 namespace ROCKSDB_NAMESPACE {

@@ -286,8 +286,8 @@ class ClockCacheShard final : public CacheShard {
    return Lookup(key, hash);
  }
  bool Release(Cache::Handle* handle, bool /*useful*/,
-               bool erase_if_last_ref) override {
-    return Release(handle, erase_if_last_ref);
+               bool force_erase) override {
+    return Release(handle, force_erase);
  }
  bool IsReady(Cache::Handle* /*handle*/) override { return true; }
  void Wait(Cache::Handle* /*handle*/) override {}
@@ -297,7 +297,7 @@ class ClockCacheShard final : public CacheShard {
  //
  // Not necessary to hold mutex_ before being called.
  bool Ref(Cache::Handle* handle) override;
-  bool Release(Cache::Handle* handle, bool erase_if_last_ref = false) override;
+  bool Release(Cache::Handle* handle, bool force_erase = false) override;
  void Erase(const Slice& key, uint32_t hash) override;
  bool EraseAndConfirm(const Slice& key, uint32_t hash,
                       CleanupContext* context);
@@ -368,7 +368,7 @@ class ClockCacheShard final : public CacheShard {

  // Guards list_, head_, and recycle_. In addition, updating table_ also has
  // to hold the mutex, to avoid the cache being in inconsistent state.
-  mutable DMutex mutex_;
+  mutable port::Mutex mutex_;

  // The circular list of cache handles. Initially the list is empty. Once a
  // handle is needed by insertion, and no more handles are available in
@@ -431,7 +431,7 @@ void ClockCacheShard::ApplyToSomeEntries(
                             DeleterFn deleter)>& callback,
    uint32_t average_entries_per_lock, uint32_t* state) {
  assert(average_entries_per_lock > 0);
-  DMutexLock l(mutex_);
+  MutexLock lock(&mutex_);

  // Figure out the range to iterate, update `state`
  size_t list_size = list_.size();
@@ -532,7 +532,7 @@ bool ClockCacheShard::Unref(CacheHandle* handle, bool set_usage,
    pinned_usage_.fetch_sub(total_charge, std::memory_order_relaxed);
    // Cleanup if it is the last reference.
    if (!InCache(flags)) {
-      DMutexLock l(mutex_);
+      MutexLock l(&mutex_);
      RecycleHandle(handle, context);
    }
  }
@@ -598,7 +598,7 @@ bool ClockCacheShard::EvictFromCache(size_t charge, CleanupContext* context) {
 void ClockCacheShard::SetCapacity(size_t capacity) {
  CleanupContext context;
  {
-    DMutexLock l(mutex_);
+    MutexLock l(&mutex_);
    capacity_.store(capacity, std::memory_order_relaxed);
    EvictFromCache(0, &context);
  }
@@ -618,7 +618,7 @@ CacheHandle* ClockCacheShard::Insert(
  uint32_t meta_charge =
      CacheHandle::CalcMetadataCharge(key, metadata_charge_policy_);
  size_t total_charge = charge + meta_charge;
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  bool success = EvictFromCache(total_charge, context);
  bool strict = strict_capacity_limit_.load(std::memory_order_relaxed);
  if (!success && (strict || !hold_reference)) {
@@ -687,7 +687,7 @@ Status ClockCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
  Status s;
  if (out_handle != nullptr) {
    if (handle == nullptr) {
-      s = Status::Incomplete("Insert failed due to CLOCK cache being full.");
+      s = Status::Incomplete("Insert failed due to LRU cache being full.");
    } else {
      *out_handle = reinterpret_cast<Cache::Handle*>(handle);
    }
@@ -725,11 +725,11 @@ Cache::Handle* ClockCacheShard::Lookup(const Slice& key, uint32_t hash) {
  return reinterpret_cast<Cache::Handle*>(handle);
 }

-bool ClockCacheShard::Release(Cache::Handle* h, bool erase_if_last_ref) {
+bool ClockCacheShard::Release(Cache::Handle* h, bool force_erase) {
  CleanupContext context;
  CacheHandle* handle = reinterpret_cast<CacheHandle*>(h);
  bool erased = Unref(handle, true, &context);
-  if (erase_if_last_ref && !erased) {
+  if (force_erase && !erased) {
    erased = EraseAndConfirm(handle->key, handle->hash, &context);
  }
  Cleanup(context);
@@ -744,7 +744,7 @@ void ClockCacheShard::Erase(const Slice& key, uint32_t hash) {

 bool ClockCacheShard::EraseAndConfirm(const Slice& key, uint32_t hash,
                                      CleanupContext* context) {
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  HashTable::accessor accessor;
  bool erased = false;
  if (table_.find(accessor, ClockCacheKey(key, hash))) {
@@ -758,7 +758,7 @@ bool ClockCacheShard::EraseAndConfirm(const Slice& key, uint32_t hash,
 void ClockCacheShard::EraseUnRefEntries() {
  CleanupContext context;
  {
-    DMutexLock l(mutex_);
+    MutexLock l(&mutex_);
    table_.clear();
    for (auto& handle : list_) {
      UnsetInCache(&handle, &context);
@@ -1,171 +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 "cache/compressed_secondary_cache.h"
-
-#include <memory>
-
-#include "memory/memory_allocator.h"
-#include "util/compression.h"
-#include "util/string_util.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-namespace {
-
-void DeletionCallback(const Slice& /*key*/, void* obj) {
-  delete reinterpret_cast<CacheAllocationPtr*>(obj);
-  obj = nullptr;
-}
-
-}  // namespace
-
-CompressedSecondaryCache::CompressedSecondaryCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy,
-    CompressionType compression_type, uint32_t compress_format_version)
-    : cache_options_(capacity, num_shard_bits, strict_capacity_limit,
-                     high_pri_pool_ratio, memory_allocator, use_adaptive_mutex,
-                     metadata_charge_policy, compression_type,
-                     compress_format_version) {
-  cache_ = NewLRUCache(capacity, num_shard_bits, strict_capacity_limit,
-                       high_pri_pool_ratio, memory_allocator,
-                       use_adaptive_mutex, metadata_charge_policy);
-}
-
-CompressedSecondaryCache::~CompressedSecondaryCache() { cache_.reset(); }
-
-std::unique_ptr<SecondaryCacheResultHandle> CompressedSecondaryCache::Lookup(
-    const Slice& key, const Cache::CreateCallback& create_cb, bool /*wait*/,
-    bool& is_in_sec_cache) {
-  std::unique_ptr<SecondaryCacheResultHandle> handle;
-  is_in_sec_cache = false;
-  Cache::Handle* lru_handle = cache_->Lookup(key);
-  if (lru_handle == nullptr) {
-    return handle;
-  }
-
-  CacheAllocationPtr* ptr =
-      reinterpret_cast<CacheAllocationPtr*>(cache_->Value(lru_handle));
-  void* value = nullptr;
-  size_t charge = 0;
-  Status s;
-
-  if (cache_options_.compression_type == kNoCompression) {
-    s = create_cb(ptr->get(), cache_->GetCharge(lru_handle), &value, &charge);
-  } else {
-    UncompressionContext uncompression_context(cache_options_.compression_type);
-    UncompressionInfo uncompression_info(uncompression_context,
-                                         UncompressionDict::GetEmptyDict(),
-                                         cache_options_.compression_type);
-
-    size_t uncompressed_size = 0;
-    CacheAllocationPtr uncompressed;
-    uncompressed = UncompressData(
-        uncompression_info, (char*)ptr->get(), cache_->GetCharge(lru_handle),
-        &uncompressed_size, cache_options_.compress_format_version,
-        cache_options_.memory_allocator.get());
-
-    if (!uncompressed) {
-      cache_->Release(lru_handle, /* erase_if_last_ref */ true);
-      return handle;
-    }
-    s = create_cb(uncompressed.get(), uncompressed_size, &value, &charge);
-  }
-
-  if (!s.ok()) {
-    cache_->Release(lru_handle, /* erase_if_last_ref */ true);
-    return handle;
-  }
-
-  cache_->Release(lru_handle, /* erase_if_last_ref */ true);
-  handle.reset(new CompressedSecondaryCacheResultHandle(value, charge));
-
-  return handle;
-}
-
-Status CompressedSecondaryCache::Insert(const Slice& key, void* value,
-                                        const Cache::CacheItemHelper* helper) {
-  size_t size = (*helper->size_cb)(value);
-  CacheAllocationPtr ptr =
-      AllocateBlock(size, cache_options_.memory_allocator.get());
-
-  Status s = (*helper->saveto_cb)(value, 0, size, ptr.get());
-  if (!s.ok()) {
-    return s;
-  }
-  Slice val(ptr.get(), size);
-
-  std::string compressed_val;
-  if (cache_options_.compression_type != kNoCompression) {
-    CompressionOptions compression_opts;
-    CompressionContext compression_context(cache_options_.compression_type);
-    uint64_t sample_for_compression = 0;
-    CompressionInfo compression_info(
-        compression_opts, compression_context, CompressionDict::GetEmptyDict(),
-        cache_options_.compression_type, sample_for_compression);
-
-    bool success =
-        CompressData(val, compression_info,
-                     cache_options_.compress_format_version, &compressed_val);
-
-    if (!success) {
-      return Status::Corruption("Error compressing value.");
-    }
-
-    val = Slice(compressed_val);
-    size = compressed_val.size();
-    ptr = AllocateBlock(size, cache_options_.memory_allocator.get());
-    memcpy(ptr.get(), compressed_val.data(), size);
-  }
-
-  CacheAllocationPtr* buf = new CacheAllocationPtr(std::move(ptr));
-
-  return cache_->Insert(key, buf, size, DeletionCallback);
-}
-
-void CompressedSecondaryCache::Erase(const Slice& key) { cache_->Erase(key); }
-
-std::string CompressedSecondaryCache::GetPrintableOptions() const {
-  std::string ret;
-  ret.reserve(20000);
-  const int kBufferSize = 200;
-  char buffer[kBufferSize];
-  ret.append(cache_->GetPrintableOptions());
-  snprintf(buffer, kBufferSize, "    compression_type : %s\n",
-           CompressionTypeToString(cache_options_.compression_type).c_str());
-  ret.append(buffer);
-  snprintf(buffer, kBufferSize, "    compression_type : %d\n",
-           cache_options_.compress_format_version);
-  ret.append(buffer);
-  return ret;
-}
-
-std::shared_ptr<SecondaryCache> NewCompressedSecondaryCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy,
-    CompressionType compression_type, uint32_t compress_format_version) {
-  return std::make_shared<CompressedSecondaryCache>(
-      capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
-      memory_allocator, use_adaptive_mutex, metadata_charge_policy,
-      compression_type, compress_format_version);
-}
-
-std::shared_ptr<SecondaryCache> NewCompressedSecondaryCache(
-    const CompressedSecondaryCacheOptions& opts) {
-  // The secondary_cache is disabled for this LRUCache instance.
-  assert(opts.secondary_cache == nullptr);
-  return NewCompressedSecondaryCache(
-      opts.capacity, opts.num_shard_bits, opts.strict_capacity_limit,
-      opts.high_pri_pool_ratio, opts.memory_allocator, opts.use_adaptive_mutex,
-      opts.metadata_charge_policy, opts.compression_type,
-      opts.compress_format_version);
-}
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,86 +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
-
-#include <memory>
-
-#include "cache/lru_cache.h"
-#include "memory/memory_allocator.h"
-#include "rocksdb/secondary_cache.h"
-#include "rocksdb/slice.h"
-#include "rocksdb/status.h"
-#include "util/compression.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class CompressedSecondaryCacheResultHandle : public SecondaryCacheResultHandle {
- public:
-  CompressedSecondaryCacheResultHandle(void* value, size_t size)
-      : value_(value), size_(size) {}
-  virtual ~CompressedSecondaryCacheResultHandle() override = default;
-
-  CompressedSecondaryCacheResultHandle(
-      const CompressedSecondaryCacheResultHandle&) = delete;
-  CompressedSecondaryCacheResultHandle& operator=(
-      const CompressedSecondaryCacheResultHandle&) = delete;
-
-  bool IsReady() override { return true; }
-
-  void Wait() override {}
-
-  void* Value() override { return value_; }
-
-  size_t Size() override { return size_; }
-
- private:
-  void* value_;
-  size_t size_;
-};
-
-// The CompressedSecondaryCache is a concrete implementation of
-// rocksdb::SecondaryCache.
-//
-// Users can also cast a pointer to it and call methods on
-// it directly, especially custom methods that may be added
-// in the future.  For example -
-// std::unique_ptr<rocksdb::SecondaryCache> cache =
-//      NewCompressedSecondaryCache(opts);
-// static_cast<CompressedSecondaryCache*>(cache.get())->Erase(key);
-
-class CompressedSecondaryCache : public SecondaryCache {
- public:
-  CompressedSecondaryCache(
-      size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-      double high_pri_pool_ratio,
-      std::shared_ptr<MemoryAllocator> memory_allocator = nullptr,
-      bool use_adaptive_mutex = kDefaultToAdaptiveMutex,
-      CacheMetadataChargePolicy metadata_charge_policy =
-          kDontChargeCacheMetadata,
-      CompressionType compression_type = CompressionType::kLZ4Compression,
-      uint32_t compress_format_version = 2);
-  virtual ~CompressedSecondaryCache() override;
-
-  const char* Name() const override { return "CompressedSecondaryCache"; }
-
-  Status Insert(const Slice& key, void* value,
-                const Cache::CacheItemHelper* helper) override;
-
-  std::unique_ptr<SecondaryCacheResultHandle> Lookup(
-      const Slice& key, const Cache::CreateCallback& create_cb, bool /*wait*/,
-      bool& is_in_sec_cache) override;
-
-  void Erase(const Slice& key) override;
-
-  void WaitAll(std::vector<SecondaryCacheResultHandle*> /*handles*/) override {}
-
-  std::string GetPrintableOptions() const override;
-
- private:
-  std::shared_ptr<Cache> cache_;
-  CompressedSecondaryCacheOptions cache_options_;
-};
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,647 +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 "cache/compressed_secondary_cache.h"
-
-#include <algorithm>
-#include <cstdint>
-
-#include "memory/jemalloc_nodump_allocator.h"
-#include "memory/memory_allocator.h"
-#include "rocksdb/convenience.h"
-#include "rocksdb/secondary_cache.h"
-#include "test_util/testharness.h"
-#include "test_util/testutil.h"
-#include "util/compression.h"
-#include "util/random.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class CompressedSecondaryCacheTest : public testing::Test {
- public:
-  CompressedSecondaryCacheTest() : fail_create_(false) {}
-  ~CompressedSecondaryCacheTest() {}
-
- protected:
-  class TestItem {
-   public:
-    TestItem(const char* buf, size_t size) : buf_(new char[size]), size_(size) {
-      memcpy(buf_.get(), buf, size);
-    }
-    ~TestItem() {}
-
-    char* Buf() { return buf_.get(); }
-    size_t Size() { return size_; }
-
-   private:
-    std::unique_ptr<char[]> buf_;
-    size_t size_;
-  };
-
-  static size_t SizeCallback(void* obj) {
-    return reinterpret_cast<TestItem*>(obj)->Size();
-  }
-
-  static Status SaveToCallback(void* from_obj, size_t from_offset,
-                               size_t length, void* out) {
-    TestItem* item = reinterpret_cast<TestItem*>(from_obj);
-    const char* buf = item->Buf();
-    EXPECT_EQ(length, item->Size());
-    EXPECT_EQ(from_offset, 0);
-    memcpy(out, buf, length);
-    return Status::OK();
-  }
-
-  static void DeletionCallback(const Slice& /*key*/, void* obj) {
-    delete reinterpret_cast<TestItem*>(obj);
-    obj = nullptr;
-  }
-
-  static Cache::CacheItemHelper helper_;
-
-  static Status SaveToCallbackFail(void* /*obj*/, size_t /*offset*/,
-                                   size_t /*size*/, void* /*out*/) {
-    return Status::NotSupported();
-  }
-
-  static Cache::CacheItemHelper helper_fail_;
-
-  Cache::CreateCallback test_item_creator = [&](const void* buf, size_t size,
-                                                void** out_obj,
-                                                size_t* charge) -> Status {
-    if (fail_create_) {
-      return Status::NotSupported();
-    }
-    *out_obj = reinterpret_cast<void*>(new TestItem((char*)buf, size));
-    *charge = size;
-    return Status::OK();
-  };
-
-  void SetFailCreate(bool fail) { fail_create_ = fail; }
-
-  void BasicTestHelper(std::shared_ptr<SecondaryCache> sec_cache) {
-    bool is_in_sec_cache{true};
-    // Lookup an non-existent key.
-    std::unique_ptr<SecondaryCacheResultHandle> handle0 =
-        sec_cache->Lookup("k0", test_item_creator, true, is_in_sec_cache);
-    ASSERT_EQ(handle0, nullptr);
-
-    Random rnd(301);
-    // Insert and Lookup the first item.
-    std::string str1;
-    test::CompressibleString(&rnd, 0.25, 1000, &str1);
-    TestItem item1(str1.data(), str1.length());
-    ASSERT_OK(sec_cache->Insert("k1", &item1,
-                                &CompressedSecondaryCacheTest::helper_));
-
-    std::unique_ptr<SecondaryCacheResultHandle> handle1 =
-        sec_cache->Lookup("k1", test_item_creator, true, is_in_sec_cache);
-    ASSERT_NE(handle1, nullptr);
-    ASSERT_FALSE(is_in_sec_cache);
-
-    std::unique_ptr<TestItem> val1 =
-        std::unique_ptr<TestItem>(static_cast<TestItem*>(handle1->Value()));
-    ASSERT_NE(val1, nullptr);
-    ASSERT_EQ(memcmp(val1->Buf(), item1.Buf(), item1.Size()), 0);
-
-    // Lookup the first item again.
-    std::unique_ptr<SecondaryCacheResultHandle> handle1_1 =
-        sec_cache->Lookup("k1", test_item_creator, true, is_in_sec_cache);
-    ASSERT_EQ(handle1_1, nullptr);
-
-    // Insert and Lookup the second item.
-    std::string str2;
-    test::CompressibleString(&rnd, 0.5, 1000, &str2);
-    TestItem item2(str2.data(), str2.length());
-    ASSERT_OK(sec_cache->Insert("k2", &item2,
-                                &CompressedSecondaryCacheTest::helper_));
-    std::unique_ptr<SecondaryCacheResultHandle> handle2 =
-        sec_cache->Lookup("k2", test_item_creator, true, is_in_sec_cache);
-    ASSERT_NE(handle2, nullptr);
-    std::unique_ptr<TestItem> val2 =
-        std::unique_ptr<TestItem>(static_cast<TestItem*>(handle2->Value()));
-    ASSERT_NE(val2, nullptr);
-    ASSERT_EQ(memcmp(val2->Buf(), item2.Buf(), item2.Size()), 0);
-
-    std::vector<SecondaryCacheResultHandle*> handles = {handle1.get(),
-                                                        handle2.get()};
-    sec_cache->WaitAll(handles);
-
-    sec_cache.reset();
-  }
-
-  void BasicTest(bool sec_cache_is_compressed, bool use_jemalloc) {
-    CompressedSecondaryCacheOptions opts;
-    opts.capacity = 2048;
-    opts.num_shard_bits = 0;
-    opts.metadata_charge_policy = kDontChargeCacheMetadata;
-
-    if (sec_cache_is_compressed) {
-      if (!LZ4_Supported()) {
-        ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-        opts.compression_type = CompressionType::kNoCompression;
-      }
-    } else {
-      opts.compression_type = CompressionType::kNoCompression;
-    }
-
-    if (use_jemalloc) {
-      JemallocAllocatorOptions jopts;
-      std::shared_ptr<MemoryAllocator> allocator;
-      std::string msg;
-      if (JemallocNodumpAllocator::IsSupported(&msg)) {
-        Status s = NewJemallocNodumpAllocator(jopts, &allocator);
-        if (s.ok()) {
-          opts.memory_allocator = allocator;
-        }
-      } else {
-        ROCKSDB_GTEST_BYPASS("JEMALLOC not supported");
-      }
-    }
-    std::shared_ptr<SecondaryCache> sec_cache =
-        NewCompressedSecondaryCache(opts);
-  }
-
-  void FailsTest(bool sec_cache_is_compressed) {
-    CompressedSecondaryCacheOptions secondary_cache_opts;
-    if (sec_cache_is_compressed) {
-      if (!LZ4_Supported()) {
-        ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-        secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-      }
-    } else {
-      secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-    }
-
-    secondary_cache_opts.capacity = 1100;
-    secondary_cache_opts.num_shard_bits = 0;
-    secondary_cache_opts.metadata_charge_policy = kDontChargeCacheMetadata;
-    std::shared_ptr<SecondaryCache> sec_cache =
-        NewCompressedSecondaryCache(secondary_cache_opts);
-
-    // Insert and Lookup the first item.
-    Random rnd(301);
-    std::string str1(rnd.RandomString(1000));
-    TestItem item1(str1.data(), str1.length());
-    ASSERT_OK(sec_cache->Insert("k1", &item1,
-                                &CompressedSecondaryCacheTest::helper_));
-
-    // Insert and Lookup the second item.
-    std::string str2(rnd.RandomString(200));
-    TestItem item2(str2.data(), str2.length());
-    // k1 is evicted.
-    ASSERT_OK(sec_cache->Insert("k2", &item2,
-                                &CompressedSecondaryCacheTest::helper_));
-    bool is_in_sec_cache{false};
-    std::unique_ptr<SecondaryCacheResultHandle> handle1_1 =
-        sec_cache->Lookup("k1", test_item_creator, true, is_in_sec_cache);
-    ASSERT_EQ(handle1_1, nullptr);
-    std::unique_ptr<SecondaryCacheResultHandle> handle2 =
-        sec_cache->Lookup("k2", test_item_creator, true, is_in_sec_cache);
-    ASSERT_NE(handle2, nullptr);
-    std::unique_ptr<TestItem> val2 =
-        std::unique_ptr<TestItem>(static_cast<TestItem*>(handle2->Value()));
-    ASSERT_NE(val2, nullptr);
-    ASSERT_EQ(memcmp(val2->Buf(), item2.Buf(), item2.Size()), 0);
-
-    // Create Fails.
-    SetFailCreate(true);
-    std::unique_ptr<SecondaryCacheResultHandle> handle2_1 =
-        sec_cache->Lookup("k2", test_item_creator, true, is_in_sec_cache);
-    ASSERT_EQ(handle2_1, nullptr);
-
-    // Save Fails.
-    std::string str3 = rnd.RandomString(10);
-    TestItem item3(str3.data(), str3.length());
-    ASSERT_NOK(sec_cache->Insert("k3", &item3,
-                                 &CompressedSecondaryCacheTest::helper_fail_));
-
-    sec_cache.reset();
-  }
-
-  void BasicIntegrationTest(bool sec_cache_is_compressed) {
-    CompressedSecondaryCacheOptions secondary_cache_opts;
-
-    if (sec_cache_is_compressed) {
-      if (!LZ4_Supported()) {
-        ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-        secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-      }
-    } else {
-      secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-    }
-
-    secondary_cache_opts.capacity = 2300;
-    secondary_cache_opts.num_shard_bits = 0;
-    secondary_cache_opts.metadata_charge_policy = kDontChargeCacheMetadata;
-    std::shared_ptr<SecondaryCache> secondary_cache =
-        NewCompressedSecondaryCache(secondary_cache_opts);
-    LRUCacheOptions lru_cache_opts(1024, 0, false, 0.5, nullptr,
-                                   kDefaultToAdaptiveMutex,
-                                   kDontChargeCacheMetadata);
-    lru_cache_opts.secondary_cache = secondary_cache;
-    std::shared_ptr<Cache> cache = NewLRUCache(lru_cache_opts);
-    std::shared_ptr<Statistics> stats = CreateDBStatistics();
-
-    Random rnd(301);
-
-    std::string str1 = rnd.RandomString(1010);
-    std::string str1_clone{str1};
-    TestItem* item1 = new TestItem(str1.data(), str1.length());
-    ASSERT_OK(cache->Insert("k1", item1, &CompressedSecondaryCacheTest::helper_,
-                            str1.length()));
-
-    std::string str2 = rnd.RandomString(1020);
-    TestItem* item2 = new TestItem(str2.data(), str2.length());
-    // After Insert, lru cache contains k2 and secondary cache contains k1.
-    ASSERT_OK(cache->Insert("k2", item2, &CompressedSecondaryCacheTest::helper_,
-                            str2.length()));
-
-    std::string str3 = rnd.RandomString(1020);
-    TestItem* item3 = new TestItem(str3.data(), str3.length());
-    // After Insert, lru cache contains k3 and secondary cache contains k1 and
-    // k2
-    ASSERT_OK(cache->Insert("k3", item3, &CompressedSecondaryCacheTest::helper_,
-                            str3.length()));
-
-    Cache::Handle* handle;
-    handle = cache->Lookup("k3", &CompressedSecondaryCacheTest::helper_,
-                           test_item_creator, Cache::Priority::LOW, true,
-                           stats.get());
-    ASSERT_NE(handle, nullptr);
-    TestItem* val3 = static_cast<TestItem*>(cache->Value(handle));
-    ASSERT_NE(val3, nullptr);
-    ASSERT_EQ(memcmp(val3->Buf(), item3->Buf(), item3->Size()), 0);
-    cache->Release(handle);
-
-    // Lookup an non-existent key.
-    handle = cache->Lookup("k0", &CompressedSecondaryCacheTest::helper_,
-                           test_item_creator, Cache::Priority::LOW, true,
-                           stats.get());
-    ASSERT_EQ(handle, nullptr);
-
-    // This Lookup should promote k1 and erase k1 from the secondary cache,
-    // then k3 is demoted. So k2 and k3 are in the secondary cache.
-    handle = cache->Lookup("k1", &CompressedSecondaryCacheTest::helper_,
-                           test_item_creator, Cache::Priority::LOW, true,
-                           stats.get());
-
-    ASSERT_NE(handle, nullptr);
-    TestItem* val1_1 = static_cast<TestItem*>(cache->Value(handle));
-    ASSERT_NE(val1_1, nullptr);
-    ASSERT_EQ(memcmp(val1_1->Buf(), str1_clone.data(), str1_clone.size()), 0);
-    cache->Release(handle);
-
-    handle = cache->Lookup("k2", &CompressedSecondaryCacheTest::helper_,
-                           test_item_creator, Cache::Priority::LOW, true,
-                           stats.get());
-    ASSERT_NE(handle, nullptr);
-    cache->Release(handle);
-
-    cache.reset();
-    secondary_cache.reset();
-  }
-
-  void BasicIntegrationFailTest(bool sec_cache_is_compressed) {
-    CompressedSecondaryCacheOptions secondary_cache_opts;
-
-    if (sec_cache_is_compressed) {
-      if (!LZ4_Supported()) {
-        ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-        secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-      }
-    } else {
-      secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-    }
-
-    secondary_cache_opts.capacity = 2048;
-    secondary_cache_opts.num_shard_bits = 0;
-    secondary_cache_opts.metadata_charge_policy = kDontChargeCacheMetadata;
-    std::shared_ptr<SecondaryCache> secondary_cache =
-        NewCompressedSecondaryCache(secondary_cache_opts);
-
-    LRUCacheOptions opts(1024, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
-                         kDontChargeCacheMetadata);
-    opts.secondary_cache = secondary_cache;
-    std::shared_ptr<Cache> cache = NewLRUCache(opts);
-
-    Random rnd(301);
-    std::string str1 = rnd.RandomString(1020);
-    auto item1 =
-        std::unique_ptr<TestItem>(new TestItem(str1.data(), str1.length()));
-    ASSERT_NOK(cache->Insert("k1", item1.get(), nullptr, str1.length()));
-    ASSERT_OK(cache->Insert("k1", item1.get(),
-                            &CompressedSecondaryCacheTest::helper_,
-                            str1.length()));
-    item1.release();  // Appease clang-analyze "potential memory leak"
-
-    Cache::Handle* handle;
-    handle = cache->Lookup("k2", nullptr, test_item_creator,
-                           Cache::Priority::LOW, true);
-    ASSERT_EQ(handle, nullptr);
-    handle = cache->Lookup("k2", &CompressedSecondaryCacheTest::helper_,
-                           test_item_creator, Cache::Priority::LOW, false);
-    ASSERT_EQ(handle, nullptr);
-
-    cache.reset();
-    secondary_cache.reset();
-  }
-
-  void IntegrationSaveFailTest(bool sec_cache_is_compressed) {
-    CompressedSecondaryCacheOptions secondary_cache_opts;
-
-    if (sec_cache_is_compressed) {
-      if (!LZ4_Supported()) {
-        ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-        secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-      }
-    } else {
-      secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-    }
-
-    secondary_cache_opts.capacity = 2048;
-    secondary_cache_opts.num_shard_bits = 0;
-    secondary_cache_opts.metadata_charge_policy = kDontChargeCacheMetadata;
-
-    std::shared_ptr<SecondaryCache> secondary_cache =
-        NewCompressedSecondaryCache(secondary_cache_opts);
-
-    LRUCacheOptions opts(1024, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
-                         kDontChargeCacheMetadata);
-    opts.secondary_cache = secondary_cache;
-    std::shared_ptr<Cache> cache = NewLRUCache(opts);
-
-    Random rnd(301);
-    std::string str1 = rnd.RandomString(1020);
-    TestItem* item1 = new TestItem(str1.data(), str1.length());
-    ASSERT_OK(cache->Insert("k1", item1,
-                            &CompressedSecondaryCacheTest::helper_fail_,
-                            str1.length()));
-    std::string str2 = rnd.RandomString(1020);
-    TestItem* item2 = new TestItem(str2.data(), str2.length());
-    // k1 should be demoted to the secondary cache.
-    ASSERT_OK(cache->Insert("k2", item2,
-                            &CompressedSecondaryCacheTest::helper_fail_,
-                            str2.length()));
-
-    Cache::Handle* handle;
-    handle = cache->Lookup("k2", &CompressedSecondaryCacheTest::helper_fail_,
-                           test_item_creator, Cache::Priority::LOW, true);
-    ASSERT_NE(handle, nullptr);
-    cache->Release(handle);
-    // This lookup should fail, since k1 demotion would have failed
-    handle = cache->Lookup("k1", &CompressedSecondaryCacheTest::helper_fail_,
-                           test_item_creator, Cache::Priority::LOW, true);
-    ASSERT_EQ(handle, nullptr);
-    // Since k1 didn't get promoted, k2 should still be in cache
-    handle = cache->Lookup("k2", &CompressedSecondaryCacheTest::helper_fail_,
-                           test_item_creator, Cache::Priority::LOW, true);
-    ASSERT_NE(handle, nullptr);
-    cache->Release(handle);
-
-    cache.reset();
-    secondary_cache.reset();
-  }
-
-  void IntegrationCreateFailTest(bool sec_cache_is_compressed) {
-    CompressedSecondaryCacheOptions secondary_cache_opts;
-
-    if (sec_cache_is_compressed) {
-      if (!LZ4_Supported()) {
-        ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-        secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-      }
-    } else {
-      secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-    }
-
-    secondary_cache_opts.capacity = 2048;
-    secondary_cache_opts.num_shard_bits = 0;
-    secondary_cache_opts.metadata_charge_policy = kDontChargeCacheMetadata;
-
-    std::shared_ptr<SecondaryCache> secondary_cache =
-        NewCompressedSecondaryCache(secondary_cache_opts);
-
-    LRUCacheOptions opts(1024, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
-                         kDontChargeCacheMetadata);
-    opts.secondary_cache = secondary_cache;
-    std::shared_ptr<Cache> cache = NewLRUCache(opts);
-
-    Random rnd(301);
-    std::string str1 = rnd.RandomString(1020);
-    TestItem* item1 = new TestItem(str1.data(), str1.length());
-    ASSERT_OK(cache->Insert("k1", item1, &CompressedSecondaryCacheTest::helper_,
-                            str1.length()));
-
-    std::string str2 = rnd.RandomString(1020);
-    TestItem* item2 = new TestItem(str2.data(), str2.length());
-    // k1 should be demoted to the secondary cache.
-    ASSERT_OK(cache->Insert("k2", item2, &CompressedSecondaryCacheTest::helper_,
-                            str2.length()));
-
-    Cache::Handle* handle;
-    SetFailCreate(true);
-    handle = cache->Lookup("k2", &CompressedSecondaryCacheTest::helper_,
-                           test_item_creator, Cache::Priority::LOW, true);
-    ASSERT_NE(handle, nullptr);
-    cache->Release(handle);
-    // This lookup should fail, since k1 creation would have failed
-    handle = cache->Lookup("k1", &CompressedSecondaryCacheTest::helper_,
-                           test_item_creator, Cache::Priority::LOW, true);
-    ASSERT_EQ(handle, nullptr);
-    // Since k1 didn't get promoted, k2 should still be in cache
-    handle = cache->Lookup("k2", &CompressedSecondaryCacheTest::helper_,
-                           test_item_creator, Cache::Priority::LOW, true);
-    ASSERT_NE(handle, nullptr);
-    cache->Release(handle);
-
-    cache.reset();
-    secondary_cache.reset();
-  }
-
-  void IntegrationFullCapacityTest(bool sec_cache_is_compressed) {
-    CompressedSecondaryCacheOptions secondary_cache_opts;
-
-    if (sec_cache_is_compressed) {
-      if (!LZ4_Supported()) {
-        ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-        secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-      }
-    } else {
-      secondary_cache_opts.compression_type = CompressionType::kNoCompression;
-    }
-
-    secondary_cache_opts.capacity = 2048;
-    secondary_cache_opts.num_shard_bits = 0;
-    secondary_cache_opts.metadata_charge_policy = kDontChargeCacheMetadata;
-
-    std::shared_ptr<SecondaryCache> secondary_cache =
-        NewCompressedSecondaryCache(secondary_cache_opts);
-
-    LRUCacheOptions opts(1024, 0, /*_strict_capacity_limit=*/true, 0.5, nullptr,
-                         kDefaultToAdaptiveMutex, kDontChargeCacheMetadata);
-    opts.secondary_cache = secondary_cache;
-    std::shared_ptr<Cache> cache = NewLRUCache(opts);
-
-    Random rnd(301);
-    std::string str1 = rnd.RandomString(1020);
-    TestItem* item1 = new TestItem(str1.data(), str1.length());
-    ASSERT_OK(cache->Insert("k1", item1, &CompressedSecondaryCacheTest::helper_,
-                            str1.length()));
-    std::string str2 = rnd.RandomString(1020);
-    TestItem* item2 = new TestItem(str2.data(), str2.length());
-    // k1 should be demoted to the secondary cache.
-    ASSERT_OK(cache->Insert("k2", item2, &CompressedSecondaryCacheTest::helper_,
-                            str2.length()));
-
-    Cache::Handle* handle2;
-    handle2 = cache->Lookup("k2", &CompressedSecondaryCacheTest::helper_,
-                            test_item_creator, Cache::Priority::LOW, true);
-    ASSERT_NE(handle2, nullptr);
-    cache->Release(handle2);
-    // k1 promotion should fail due to the block cache being at capacity,
-    // but the lookup should still succeed
-    Cache::Handle* handle1;
-    handle1 = cache->Lookup("k1", &CompressedSecondaryCacheTest::helper_,
-                            test_item_creator, Cache::Priority::LOW, true);
-    ASSERT_NE(handle1, nullptr);
-    cache->Release(handle1);
-
-    // Since k1 didn't get inserted, k2 should still be in cache
-    handle2 = cache->Lookup("k2", &CompressedSecondaryCacheTest::helper_,
-                            test_item_creator, Cache::Priority::LOW, true);
-    ASSERT_NE(handle2, nullptr);
-    cache->Release(handle2);
-
-    cache.reset();
-    secondary_cache.reset();
-  }
-
- private:
-  bool fail_create_;
-};
-
-Cache::CacheItemHelper CompressedSecondaryCacheTest::helper_(
-    CompressedSecondaryCacheTest::SizeCallback,
-    CompressedSecondaryCacheTest::SaveToCallback,
-    CompressedSecondaryCacheTest::DeletionCallback);
-
-Cache::CacheItemHelper CompressedSecondaryCacheTest::helper_fail_(
-    CompressedSecondaryCacheTest::SizeCallback,
-    CompressedSecondaryCacheTest::SaveToCallbackFail,
-    CompressedSecondaryCacheTest::DeletionCallback);
-
-TEST_F(CompressedSecondaryCacheTest, BasicTestWithNoCompression) {
-  BasicTest(false, false);
-}
-
-TEST_F(CompressedSecondaryCacheTest,
-       BasicTestWithMemoryAllocatorAndNoCompression) {
-  BasicTest(false, true);
-}
-
-TEST_F(CompressedSecondaryCacheTest, BasicTestWithCompression) {
-  BasicTest(true, false);
-}
-
-TEST_F(CompressedSecondaryCacheTest,
-       BasicTestWithMemoryAllocatorAndCompression) {
-  BasicTest(true, true);
-}
-
-#ifndef ROCKSDB_LITE
-
-TEST_F(CompressedSecondaryCacheTest, BasicTestFromStringWithNoCompression) {
-  std::string sec_cache_uri =
-      "compressed_secondary_cache://"
-      "capacity=2048;num_shard_bits=0;compression_type=kNoCompression";
-  std::shared_ptr<SecondaryCache> sec_cache;
-  Status s = SecondaryCache::CreateFromString(ConfigOptions(), sec_cache_uri,
-                                              &sec_cache);
-  EXPECT_OK(s);
-  BasicTestHelper(sec_cache);
-}
-
-TEST_F(CompressedSecondaryCacheTest, BasicTestFromStringWithCompression) {
-  std::string sec_cache_uri;
-  if (LZ4_Supported()) {
-    sec_cache_uri =
-        "compressed_secondary_cache://"
-        "capacity=2048;num_shard_bits=0;compression_type=kLZ4Compression;"
-        "compress_format_version=2";
-  } else {
-    ROCKSDB_GTEST_SKIP("This test requires LZ4 support.");
-    sec_cache_uri =
-        "compressed_secondary_cache://"
-        "capacity=2048;num_shard_bits=0;compression_type=kNoCompression";
-  }
-
-  std::shared_ptr<SecondaryCache> sec_cache;
-  Status s = SecondaryCache::CreateFromString(ConfigOptions(), sec_cache_uri,
-                                              &sec_cache);
-  EXPECT_OK(s);
-  BasicTestHelper(sec_cache);
-}
-
-#endif  // ROCKSDB_LITE
-
-TEST_F(CompressedSecondaryCacheTest, FailsTestWithNoCompression) {
-  FailsTest(false);
-}
-
-TEST_F(CompressedSecondaryCacheTest, FailsTestWithCompression) {
-  FailsTest(true);
-}
-
-TEST_F(CompressedSecondaryCacheTest, BasicIntegrationTestWithNoCompression) {
-  BasicIntegrationTest(false);
-}
-
-TEST_F(CompressedSecondaryCacheTest, BasicIntegrationTestWithCompression) {
-  BasicIntegrationTest(true);
-}
-
-TEST_F(CompressedSecondaryCacheTest,
-       BasicIntegrationFailTestWithNoCompression) {
-  BasicIntegrationFailTest(false);
-}
-
-TEST_F(CompressedSecondaryCacheTest, BasicIntegrationFailTestWithCompression) {
-  BasicIntegrationFailTest(true);
-}
-
-TEST_F(CompressedSecondaryCacheTest, IntegrationSaveFailTestWithNoCompression) {
-  IntegrationSaveFailTest(false);
-}
-
-TEST_F(CompressedSecondaryCacheTest, IntegrationSaveFailTestWithCompression) {
-  IntegrationSaveFailTest(true);
-}
-
-TEST_F(CompressedSecondaryCacheTest,
-       IntegrationCreateFailTestWithNoCompression) {
-  IntegrationCreateFailTest(false);
-}
-
-TEST_F(CompressedSecondaryCacheTest, IntegrationCreateFailTestWithCompression) {
-  IntegrationCreateFailTest(true);
-}
-
-TEST_F(CompressedSecondaryCacheTest,
-       IntegrationFullCapacityTestWithNoCompression) {
-  IntegrationFullCapacityTest(false);
-}
-
-TEST_F(CompressedSecondaryCacheTest,
-       IntegrationFullCapacityTestWithCompression) {
-  IntegrationFullCapacityTest(true);
-}
-
-}  // namespace ROCKSDB_NAMESPACE
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
@@ -1,500 +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 "cache/fast_lru_cache.h"
-
-#include <cassert>
-#include <cstdint>
-#include <cstdio>
-
-#include "monitoring/perf_context_imp.h"
-#include "monitoring/statistics.h"
-#include "port/lang.h"
-#include "util/distributed_mutex.h"
-
-#define KEY_LENGTH \
-  16  // TODO(guido) Make use of this symbol in other parts of the source code
-      // (e.g., cache_key.h, cache_test.cc, etc.)
-
-namespace ROCKSDB_NAMESPACE {
-
-namespace fast_lru_cache {
-
-LRUHandleTable::LRUHandleTable(int hash_bits)
-    : length_bits_(hash_bits),
-      list_(new LRUHandle* [size_t{1} << length_bits_] {}) {}
-
-LRUHandleTable::~LRUHandleTable() {
-  ApplyToEntriesRange(
-      [](LRUHandle* h) {
-        if (!h->HasRefs()) {
-          h->Free();
-        }
-      },
-      0, uint32_t{1} << length_bits_);
-}
-
-LRUHandle* LRUHandleTable::Lookup(const Slice& key, uint32_t hash) {
-  return *FindPointer(key, hash);
-}
-
-inline LRUHandle** LRUHandleTable::Head(uint32_t hash) {
-  return &list_[hash >> (32 - length_bits_)];
-}
-
-LRUHandle* LRUHandleTable::Insert(LRUHandle* h) {
-  LRUHandle** ptr = FindPointer(h->key(), h->hash);
-  LRUHandle* old = *ptr;
-  h->next_hash = (old == nullptr ? nullptr : old->next_hash);
-  *ptr = h;
-  return old;
-}
-
-LRUHandle* LRUHandleTable::Remove(const Slice& key, uint32_t hash) {
-  LRUHandle** ptr = FindPointer(key, hash);
-  LRUHandle* result = *ptr;
-  if (result != nullptr) {
-    *ptr = result->next_hash;
-  }
-  return result;
-}
-
-LRUHandle** LRUHandleTable::FindPointer(const Slice& key, uint32_t hash) {
-  LRUHandle** ptr = &list_[hash >> (32 - length_bits_)];
-  while (*ptr != nullptr && ((*ptr)->hash != hash || key != (*ptr)->key())) {
-    ptr = &(*ptr)->next_hash;
-  }
-  return ptr;
-}
-
-LRUCacheShard::LRUCacheShard(size_t capacity, size_t estimated_value_size,
-                             bool strict_capacity_limit,
-                             CacheMetadataChargePolicy metadata_charge_policy)
-    : capacity_(0),
-      strict_capacity_limit_(strict_capacity_limit),
-      table_(
-          GetHashBits(capacity, estimated_value_size, metadata_charge_policy)),
-      usage_(0),
-      lru_usage_(0) {
-  set_metadata_charge_policy(metadata_charge_policy);
-  // Make empty circular linked list.
-  lru_.next = &lru_;
-  lru_.prev = &lru_;
-  lru_low_pri_ = &lru_;
-  SetCapacity(capacity);
-}
-
-void LRUCacheShard::EraseUnRefEntries() {
-  autovector<LRUHandle*> last_reference_list;
-  {
-    DMutexLock l(mutex_);
-    while (lru_.next != &lru_) {
-      LRUHandle* old = lru_.next;
-      // LRU list contains only elements which can be evicted.
-      assert(old->InCache() && !old->HasRefs());
-      LRU_Remove(old);
-      table_.Remove(old->key(), old->hash);
-      old->SetInCache(false);
-      assert(usage_ >= old->total_charge);
-      usage_ -= old->total_charge;
-      last_reference_list.push_back(old);
-    }
-  }
-
-  // Free the entries here outside of mutex for performance reasons.
-  for (auto entry : last_reference_list) {
-    entry->Free();
-  }
-}
-
-void LRUCacheShard::ApplyToSomeEntries(
-    const std::function<void(const Slice& key, void* value, size_t charge,
-                             DeleterFn deleter)>& callback,
-    uint32_t average_entries_per_lock, uint32_t* state) {
-  // The state is essentially going to be the starting hash, which works
-  // nicely even if we resize between calls because we use upper-most
-  // hash bits for table indexes.
-  DMutexLock l(mutex_);
-  uint32_t length_bits = table_.GetLengthBits();
-  uint32_t length = uint32_t{1} << length_bits;
-
-  assert(average_entries_per_lock > 0);
-  // Assuming we are called with same average_entries_per_lock repeatedly,
-  // this simplifies some logic (index_end will not overflow).
-  assert(average_entries_per_lock < length || *state == 0);
-
-  uint32_t index_begin = *state >> (32 - length_bits);
-  uint32_t index_end = index_begin + average_entries_per_lock;
-  if (index_end >= length) {
-    // Going to end
-    index_end = length;
-    *state = UINT32_MAX;
-  } else {
-    *state = index_end << (32 - length_bits);
-  }
-
-  table_.ApplyToEntriesRange(
-      [callback,
-       metadata_charge_policy = metadata_charge_policy_](LRUHandle* h) {
-        callback(h->key(), h->value, h->GetCharge(metadata_charge_policy),
-                 h->deleter);
-      },
-      index_begin, index_end);
-}
-
-void LRUCacheShard::LRU_Remove(LRUHandle* e) {
-  assert(e->next != nullptr);
-  assert(e->prev != nullptr);
-  e->next->prev = e->prev;
-  e->prev->next = e->next;
-  e->prev = e->next = nullptr;
-  assert(lru_usage_ >= e->total_charge);
-  lru_usage_ -= e->total_charge;
-}
-
-void LRUCacheShard::LRU_Insert(LRUHandle* e) {
-  assert(e->next == nullptr);
-  assert(e->prev == nullptr);
-  // Inset "e" to head of LRU list.
-  e->next = &lru_;
-  e->prev = lru_.prev;
-  e->prev->next = e;
-  e->next->prev = e;
-  lru_usage_ += e->total_charge;
-}
-
-void LRUCacheShard::EvictFromLRU(size_t charge,
-                                 autovector<LRUHandle*>* deleted) {
-  while ((usage_ + charge) > capacity_ && lru_.next != &lru_) {
-    LRUHandle* old = lru_.next;
-    // LRU list contains only elements which can be evicted.
-    assert(old->InCache() && !old->HasRefs());
-    LRU_Remove(old);
-    table_.Remove(old->key(), old->hash);
-    old->SetInCache(false);
-    assert(usage_ >= old->total_charge);
-    usage_ -= old->total_charge;
-    deleted->push_back(old);
-  }
-}
-
-int LRUCacheShard::GetHashBits(
-    size_t capacity, size_t estimated_value_size,
-    CacheMetadataChargePolicy metadata_charge_policy) {
-  LRUHandle* e = reinterpret_cast<LRUHandle*>(
-      new char[sizeof(LRUHandle) - 1 + KEY_LENGTH]);
-  e->key_length = KEY_LENGTH;
-  e->deleter = nullptr;
-  e->refs = 0;
-  e->flags = 0;
-  e->refs = 0;
-
-  e->CalcTotalCharge(estimated_value_size, metadata_charge_policy);
-  size_t num_entries = capacity / e->total_charge;
-  e->Free();
-  int num_hash_bits = 0;
-  while (num_entries >>= 1) {
-    ++num_hash_bits;
-  }
-  return num_hash_bits;
-}
-
-void LRUCacheShard::SetCapacity(size_t capacity) {
-  autovector<LRUHandle*> last_reference_list;
-  {
-    DMutexLock l(mutex_);
-    capacity_ = capacity;
-    EvictFromLRU(0, &last_reference_list);
-  }
-
-  // Free the entries here outside of mutex for performance reasons.
-  for (auto entry : last_reference_list) {
-    entry->Free();
-  }
-}
-
-void LRUCacheShard::SetStrictCapacityLimit(bool strict_capacity_limit) {
-  DMutexLock l(mutex_);
-  strict_capacity_limit_ = strict_capacity_limit;
-}
-
-Status LRUCacheShard::InsertItem(LRUHandle* e, Cache::Handle** handle,
-                                 bool free_handle_on_fail) {
-  Status s = Status::OK();
-  autovector<LRUHandle*> last_reference_list;
-  {
-    DMutexLock l(mutex_);
-
-    // Free the space following strict LRU policy until enough space
-    // is freed or the lru list is empty.
-    EvictFromLRU(e->total_charge, &last_reference_list);
-
-    if ((usage_ + e->total_charge) > capacity_ &&
-        (strict_capacity_limit_ || handle == nullptr)) {
-      e->SetInCache(false);
-      if (handle == nullptr) {
-        // Don't insert the entry but still return ok, as if the entry inserted
-        // into cache and get evicted immediately.
-        last_reference_list.push_back(e);
-      } else {
-        if (free_handle_on_fail) {
-          delete[] reinterpret_cast<char*>(e);
-          *handle = nullptr;
-        }
-        s = Status::Incomplete("Insert failed due to LRU cache being full.");
-      }
-    } else {
-      // Insert into the cache. Note that the cache might get larger than its
-      // capacity if not enough space was freed up.
-      LRUHandle* old = table_.Insert(e);
-      usage_ += e->total_charge;
-      if (old != nullptr) {
-        s = Status::OkOverwritten();
-        assert(old->InCache());
-        old->SetInCache(false);
-        if (!old->HasRefs()) {
-          // old is on LRU because it's in cache and its reference count is 0.
-          LRU_Remove(old);
-          assert(usage_ >= old->total_charge);
-          usage_ -= old->total_charge;
-          last_reference_list.push_back(old);
-        }
-      }
-      if (handle == nullptr) {
-        LRU_Insert(e);
-      } else {
-        // If caller already holds a ref, no need to take one here.
-        if (!e->HasRefs()) {
-          e->Ref();
-        }
-        *handle = reinterpret_cast<Cache::Handle*>(e);
-      }
-    }
-  }
-
-  // Free the entries here outside of mutex for performance reasons.
-  for (auto entry : last_reference_list) {
-    entry->Free();
-  }
-
-  return s;
-}
-
-Cache::Handle* LRUCacheShard::Lookup(const Slice& key, uint32_t hash) {
-  LRUHandle* e = nullptr;
-  {
-    DMutexLock l(mutex_);
-    e = table_.Lookup(key, hash);
-    if (e != nullptr) {
-      assert(e->InCache());
-      if (!e->HasRefs()) {
-        // The entry is in LRU since it's in hash and has no external references
-        LRU_Remove(e);
-      }
-      e->Ref();
-    }
-  }
-  return reinterpret_cast<Cache::Handle*>(e);
-}
-
-bool LRUCacheShard::Ref(Cache::Handle* h) {
-  LRUHandle* e = reinterpret_cast<LRUHandle*>(h);
-  DMutexLock l(mutex_);
-  // To create another reference - entry must be already externally referenced.
-  assert(e->HasRefs());
-  e->Ref();
-  return true;
-}
-
-bool LRUCacheShard::Release(Cache::Handle* handle, bool erase_if_last_ref) {
-  if (handle == nullptr) {
-    return false;
-  }
-  LRUHandle* e = reinterpret_cast<LRUHandle*>(handle);
-  bool last_reference = false;
-  {
-    DMutexLock l(mutex_);
-    last_reference = e->Unref();
-    if (last_reference && e->InCache()) {
-      // The item is still in cache, and nobody else holds a reference to it.
-      if (usage_ > capacity_ || erase_if_last_ref) {
-        // The LRU list must be empty since the cache is full.
-        assert(lru_.next == &lru_ || erase_if_last_ref);
-        // Take this opportunity and remove the item.
-        table_.Remove(e->key(), e->hash);
-        e->SetInCache(false);
-      } else {
-        // Put the item back on the LRU list, and don't free it.
-        LRU_Insert(e);
-        last_reference = false;
-      }
-    }
-    // If it was the last reference, then decrement the cache usage.
-    if (last_reference) {
-      assert(usage_ >= e->total_charge);
-      usage_ -= e->total_charge;
-    }
-  }
-
-  // Free the entry here outside of mutex for performance reasons.
-  if (last_reference) {
-    e->Free();
-  }
-  return last_reference;
-}
-
-Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
-                             size_t charge, Cache::DeleterFn deleter,
-                             Cache::Handle** handle,
-                             Cache::Priority /*priority*/) {
-  if (key.size() != KEY_LENGTH) {
-    return Status::NotSupported("FastLRUCache only supports key size " +
-                                std::to_string(KEY_LENGTH) + "B");
-  }
-
-  // Allocate the memory here outside of the mutex.
-  // If the cache is full, we'll have to release it.
-  // It shouldn't happen very often though.
-  LRUHandle* e = reinterpret_cast<LRUHandle*>(
-      new char[sizeof(LRUHandle) - 1 + key.size()]);
-
-  e->value = value;
-  e->flags = 0;
-  e->deleter = deleter;
-  e->key_length = key.size();
-  e->hash = hash;
-  e->refs = 0;
-  e->next = e->prev = nullptr;
-  e->SetInCache(true);
-  e->CalcTotalCharge(charge, metadata_charge_policy_);
-  memcpy(e->key_data, key.data(), key.size());
-
-  return InsertItem(e, handle, /* free_handle_on_fail */ true);
-}
-
-void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
-  LRUHandle* e;
-  bool last_reference = false;
-  {
-    DMutexLock l(mutex_);
-    e = table_.Remove(key, hash);
-    if (e != nullptr) {
-      assert(e->InCache());
-      e->SetInCache(false);
-      if (!e->HasRefs()) {
-        // The entry is in LRU since it's in hash and has no external references
-        LRU_Remove(e);
-        assert(usage_ >= e->total_charge);
-        usage_ -= e->total_charge;
-        last_reference = true;
-      }
-    }
-  }
-
-  // Free the entry here outside of mutex for performance reasons.
-  // last_reference will only be true if e != nullptr.
-  if (last_reference) {
-    e->Free();
-  }
-}
-
-size_t LRUCacheShard::GetUsage() const {
-  DMutexLock l(mutex_);
-  return usage_;
-}
-
-size_t LRUCacheShard::GetPinnedUsage() const {
-  DMutexLock l(mutex_);
-  assert(usage_ >= lru_usage_);
-  return usage_ - lru_usage_;
-}
-
-std::string LRUCacheShard::GetPrintableOptions() const { return std::string{}; }
-
-LRUCache::LRUCache(size_t capacity, size_t estimated_value_size,
-                   int num_shard_bits, bool strict_capacity_limit,
-                   CacheMetadataChargePolicy metadata_charge_policy)
-    : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
-  num_shards_ = 1 << num_shard_bits;
-  shards_ = reinterpret_cast<LRUCacheShard*>(
-      port::cacheline_aligned_alloc(sizeof(LRUCacheShard) * num_shards_));
-  size_t per_shard = (capacity + (num_shards_ - 1)) / num_shards_;
-  for (int i = 0; i < num_shards_; i++) {
-    new (&shards_[i])
-        LRUCacheShard(per_shard, estimated_value_size, strict_capacity_limit,
-                      metadata_charge_policy);
-  }
-}
-
-LRUCache::~LRUCache() {
-  if (shards_ != nullptr) {
-    assert(num_shards_ > 0);
-    for (int i = 0; i < num_shards_; i++) {
-      shards_[i].~LRUCacheShard();
-    }
-    port::cacheline_aligned_free(shards_);
-  }
-}
-
-CacheShard* LRUCache::GetShard(uint32_t shard) {
-  return reinterpret_cast<CacheShard*>(&shards_[shard]);
-}
-
-const CacheShard* LRUCache::GetShard(uint32_t shard) const {
-  return reinterpret_cast<CacheShard*>(&shards_[shard]);
-}
-
-void* LRUCache::Value(Handle* handle) {
-  return reinterpret_cast<const LRUHandle*>(handle)->value;
-}
-
-size_t LRUCache::GetCharge(Handle* handle) const {
-  CacheMetadataChargePolicy metadata_charge_policy = kDontChargeCacheMetadata;
-  if (num_shards_ > 0) {
-    metadata_charge_policy = shards_[0].metadata_charge_policy_;
-  }
-  return reinterpret_cast<const LRUHandle*>(handle)->GetCharge(
-      metadata_charge_policy);
-}
-
-Cache::DeleterFn LRUCache::GetDeleter(Handle* handle) const {
-  auto h = reinterpret_cast<const LRUHandle*>(handle);
-  return h->deleter;
-}
-
-uint32_t LRUCache::GetHash(Handle* handle) const {
-  return reinterpret_cast<const LRUHandle*>(handle)->hash;
-}
-
-void LRUCache::DisownData() {
-  // Leak data only if that won't generate an ASAN/valgrind warning.
-  if (!kMustFreeHeapAllocations) {
-    shards_ = nullptr;
-    num_shards_ = 0;
-  }
-}
-
-}  // namespace fast_lru_cache
-
-std::shared_ptr<Cache> NewFastLRUCache(
-    size_t capacity, size_t estimated_value_size, int num_shard_bits,
-    bool strict_capacity_limit,
-    CacheMetadataChargePolicy metadata_charge_policy) {
-  if (num_shard_bits >= 20) {
-    return nullptr;  // The cache cannot be sharded into too many fine pieces.
-  }
-  if (num_shard_bits < 0) {
-    num_shard_bits = GetDefaultCacheShardBits(capacity);
-  }
-  return std::make_shared<fast_lru_cache::LRUCache>(
-      capacity, estimated_value_size, num_shard_bits, strict_capacity_limit,
-      metadata_charge_policy);
-}
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,311 +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.
-#pragma once
-
-#include <memory>
-#include <string>
-
-#include "cache/sharded_cache.h"
-#include "port/lang.h"
-#include "port/malloc.h"
-#include "port/port.h"
-#include "rocksdb/secondary_cache.h"
-#include "util/autovector.h"
-#include "util/distributed_mutex.h"
-
-namespace ROCKSDB_NAMESPACE {
-namespace fast_lru_cache {
-
-// An experimental (under development!) alternative to LRUCache
-
-struct LRUHandle {
-  void* value;
-  Cache::DeleterFn deleter;
-  LRUHandle* next_hash;
-  LRUHandle* next;
-  LRUHandle* prev;
-  size_t total_charge;  // TODO(opt): Only allow uint32_t?
-  size_t key_length;
-  // The hash of key(). Used for fast sharding and comparisons.
-  uint32_t hash;
-  // The number of external refs to this entry. The cache itself is not counted.
-  uint32_t refs;
-
-  enum Flags : uint8_t {
-    // Whether this entry is referenced by the hash table.
-    IN_CACHE = (1 << 0),
-  };
-  uint8_t flags;
-
-  // Beginning of the key (MUST BE THE LAST FIELD IN THIS STRUCT!)
-  char key_data[1];
-
-  Slice key() const { return Slice(key_data, key_length); }
-
-  // Increase the reference count by 1.
-  void Ref() { refs++; }
-
-  // Just reduce the reference count by 1. Return true if it was last reference.
-  bool Unref() {
-    assert(refs > 0);
-    refs--;
-    return refs == 0;
-  }
-
-  // Return true if there are external refs, false otherwise.
-  bool HasRefs() const { return refs > 0; }
-
-  bool InCache() const { return flags & IN_CACHE; }
-
-  void SetInCache(bool in_cache) {
-    if (in_cache) {
-      flags |= IN_CACHE;
-    } else {
-      flags &= ~IN_CACHE;
-    }
-  }
-
-  void Free() {
-    assert(refs == 0);
-    if (deleter) {
-      (*deleter)(key(), value);
-    }
-    delete[] reinterpret_cast<char*>(this);
-  }
-
-  // Calculate the memory usage by metadata.
-  inline size_t CalcMetaCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) const {
-    if (metadata_charge_policy != kFullChargeCacheMetadata) {
-      return 0;
-    } else {
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-      return malloc_usable_size(
-          const_cast<void*>(static_cast<const void*>(this)));
-#else
-      // This is the size that is used when a new handle is created.
-      return sizeof(LRUHandle) - 1 + key_length;
-#endif
-    }
-  }
-
-  inline void CalcTotalCharge(
-      size_t charge, CacheMetadataChargePolicy metadata_charge_policy) {
-    total_charge = charge + CalcMetaCharge(metadata_charge_policy);
-  }
-
-  inline size_t GetCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) const {
-    size_t meta_charge = CalcMetaCharge(metadata_charge_policy);
-    assert(total_charge >= meta_charge);
-    return total_charge - meta_charge;
-  }
-};
-
-// We provide our own simple hash table since it removes a whole bunch
-// of porting hacks and is also faster than some of the built-in hash
-// table implementations in some of the compiler/runtime combinations
-// we have tested.  E.g., readrandom speeds up by ~5% over the g++
-// 4.4.3's builtin hashtable.
-class LRUHandleTable {
- public:
-  explicit LRUHandleTable(int hash_bits);
-  ~LRUHandleTable();
-
-  LRUHandle* Lookup(const Slice& key, uint32_t hash);
-  LRUHandle* Insert(LRUHandle* h);
-  LRUHandle* Remove(const Slice& key, uint32_t hash);
-
-  template <typename T>
-  void ApplyToEntriesRange(T func, uint32_t index_begin, uint32_t index_end) {
-    for (uint32_t i = index_begin; i < index_end; i++) {
-      LRUHandle* h = list_[i];
-      while (h != nullptr) {
-        auto n = h->next_hash;
-        assert(h->InCache());
-        func(h);
-        h = n;
-      }
-    }
-  }
-
-  int GetLengthBits() const { return length_bits_; }
-
-  // Return the address of the head of the chain in the bucket given
-  // by the hash.
-  inline LRUHandle** Head(uint32_t hash);
-
- private:
-  // Return a pointer to slot that points to a cache entry that
-  // matches key/hash.  If there is no such cache entry, return a
-  // pointer to the trailing slot in the corresponding linked list.
-  LRUHandle** FindPointer(const Slice& key, uint32_t hash);
-
-  // Number of hash bits (upper because lower bits used for sharding)
-  // used for table index. Length == 1 << length_bits_
-  int length_bits_;
-
-  // The table consists of an array of buckets where each bucket is
-  // a linked list of cache entries that hash into the bucket.
-  std::unique_ptr<LRUHandle*[]> list_;
-};
-
-// A single shard of sharded cache.
-class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
- public:
-  LRUCacheShard(size_t capacity, size_t estimated_value_size,
-                bool strict_capacity_limit,
-                CacheMetadataChargePolicy metadata_charge_policy);
-  ~LRUCacheShard() override = default;
-
-  // Separate from constructor so caller can easily make an array of LRUCache
-  // if current usage is more than new capacity, the function will attempt to
-  // free the needed space.
-  void SetCapacity(size_t capacity) override;
-
-  // Set the flag to reject insertion if cache if full.
-  void SetStrictCapacityLimit(bool strict_capacity_limit) override;
-
-  // Like Cache methods, but with an extra "hash" parameter.
-  Status Insert(const Slice& key, uint32_t hash, void* value, size_t charge,
-                Cache::DeleterFn deleter, Cache::Handle** handle,
-                Cache::Priority priority) override;
-
-  Status Insert(const Slice& key, uint32_t hash, void* value,
-                const Cache::CacheItemHelper* helper, size_t charge,
-                Cache::Handle** handle, Cache::Priority priority) override {
-    return Insert(key, hash, value, charge, helper->del_cb, handle, priority);
-  }
-
-  Cache::Handle* Lookup(const Slice& key, uint32_t hash,
-                        const Cache::CacheItemHelper* /*helper*/,
-                        const Cache::CreateCallback& /*create_cb*/,
-                        Cache::Priority /*priority*/, bool /*wait*/,
-                        Statistics* /*stats*/) override {
-    return Lookup(key, hash);
-  }
-  Cache::Handle* Lookup(const Slice& key, uint32_t hash) override;
-
-  bool Release(Cache::Handle* handle, bool /*useful*/,
-               bool erase_if_last_ref) override {
-    return Release(handle, erase_if_last_ref);
-  }
-  bool IsReady(Cache::Handle* /*handle*/) override { return true; }
-  void Wait(Cache::Handle* /*handle*/) override {}
-
-  bool Ref(Cache::Handle* handle) override;
-  bool Release(Cache::Handle* handle, bool erase_if_last_ref = false) override;
-  void Erase(const Slice& key, uint32_t hash) override;
-
-  size_t GetUsage() const override;
-  size_t GetPinnedUsage() const override;
-
-  void ApplyToSomeEntries(
-      const std::function<void(const Slice& key, void* value, size_t charge,
-                               DeleterFn deleter)>& callback,
-      uint32_t average_entries_per_lock, uint32_t* state) override;
-
-  void EraseUnRefEntries() override;
-
-  std::string GetPrintableOptions() const override;
-
- private:
-  friend class LRUCache;
-  // Insert an item into the hash table and, if handle is null, insert into
-  // the LRU list. Older items are evicted as necessary. If the cache is full
-  // and free_handle_on_fail is true, the item is deleted and handle is set to
-  // nullptr.
-  Status InsertItem(LRUHandle* item, Cache::Handle** handle,
-                    bool free_handle_on_fail);
-
-  void LRU_Remove(LRUHandle* e);
-  void LRU_Insert(LRUHandle* e);
-
-  // Free some space following strict LRU policy until enough space
-  // to hold (usage_ + charge) is freed or the lru list is empty
-  // This function is not thread safe - it needs to be executed while
-  // holding the mutex_.
-  void EvictFromLRU(size_t charge, autovector<LRUHandle*>* deleted);
-
-  // Returns the number of bits used to hash an element in the per-shard
-  // table.
-  static int GetHashBits(size_t capacity, size_t estimated_value_size,
-                         CacheMetadataChargePolicy metadata_charge_policy);
-
-  // Initialized before use.
-  size_t capacity_;
-
-  // Whether to reject insertion if cache reaches its full capacity.
-  bool strict_capacity_limit_;
-
-  // Dummy head of LRU list.
-  // lru.prev is newest entry, lru.next is oldest entry.
-  // LRU contains items which can be evicted, ie reference only by cache
-  LRUHandle lru_;
-
-  // Pointer to head of low-pri pool in LRU list.
-  LRUHandle* lru_low_pri_;
-
-  // ------------^^^^^^^^^^^^^-----------
-  // Not frequently modified data members
-  // ------------------------------------
-  //
-  // We separate data members that are updated frequently from the ones that
-  // are not frequently updated so that they don't share the same cache line
-  // which will lead into false cache sharing
-  //
-  // ------------------------------------
-  // Frequently modified data members
-  // ------------vvvvvvvvvvvvv-----------
-  LRUHandleTable table_;
-
-  // Memory size for entries residing in the cache.
-  size_t usage_;
-
-  // Memory size for entries residing only in the LRU list.
-  size_t lru_usage_;
-
-  // mutex_ protects the following state.
-  // We don't count mutex_ as the cache's internal state so semantically we
-  // don't mind mutex_ invoking the non-const actions.
-  mutable DMutex mutex_;
-};
-
-class LRUCache
-#ifdef NDEBUG
-    final
-#endif
-    : public ShardedCache {
- public:
-  LRUCache(size_t capacity, size_t estimated_value_size, int num_shard_bits,
-           bool strict_capacity_limit,
-           CacheMetadataChargePolicy metadata_charge_policy =
-               kDontChargeCacheMetadata);
-  ~LRUCache() override;
-  const char* Name() const override { return "LRUCache"; }
-  CacheShard* GetShard(uint32_t shard) override;
-  const CacheShard* GetShard(uint32_t shard) const override;
-  void* Value(Handle* handle) override;
-  size_t GetCharge(Handle* handle) const override;
-  uint32_t GetHash(Handle* handle) const override;
-  DeleterFn GetDeleter(Handle* handle) const override;
-  void DisownData() override;
-
- private:
-  LRUCacheShard* shards_ = nullptr;
-  int num_shards_ = 0;
-};
-}  // namespace fast_lru_cache
-
-std::shared_ptr<Cache> NewFastLRUCache(
-    size_t capacity, size_t estimated_value_size, int num_shard_bits,
-    bool strict_capacity_limit,
-    CacheMetadataChargePolicy metadata_charge_policy);
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -16,10 +16,9 @@
 #include "monitoring/perf_context_imp.h"
 #include "monitoring/statistics.h"
 #include "port/lang.h"
-#include "util/distributed_mutex.h"
+#include "util/mutexlock.h"

 namespace ROCKSDB_NAMESPACE {
-namespace lru_cache {

 LRUHandleTable::LRUHandleTable(int max_upper_hash_bits)
    : length_bits_(/* historical starting size*/ 4),
@@ -77,12 +76,13 @@ LRUHandle** LRUHandleTable::FindPointer(const Slice& key, uint32_t hash) {

 void LRUHandleTable::Resize() {
  if (length_bits_ >= max_length_bits_) {
-    // Due to reaching limit of hash information, if we made the table bigger,
-    // we would allocate more addresses but only the same number would be used.
+    // Due to reaching limit of hash information, if we made the table
+    // bigger, we would allocate more addresses but only the same
+    // number would be used.
    return;
  }
  if (length_bits_ >= 31) {
-    // Avoid undefined behavior shifting uint32_t by 32.
+    // Avoid undefined behavior shifting uint32_t by 32
    return;
  }

@@ -125,7 +125,7 @@ LRUCacheShard::LRUCacheShard(
      mutex_(use_adaptive_mutex),
      secondary_cache_(secondary_cache) {
  set_metadata_charge_policy(metadata_charge_policy);
-  // Make empty circular linked list.
+  // Make empty circular linked list
  lru_.next = &lru_;
  lru_.prev = &lru_;
  lru_low_pri_ = &lru_;
@@ -135,16 +135,17 @@ LRUCacheShard::LRUCacheShard(
 void LRUCacheShard::EraseUnRefEntries() {
  autovector<LRUHandle*> last_reference_list;
  {
-    DMutexLock l(mutex_);
+    MutexLock l(&mutex_);
    while (lru_.next != &lru_) {
      LRUHandle* old = lru_.next;
-      // LRU list contains only elements which can be evicted.
+      // LRU list contains only elements which can be evicted
      assert(old->InCache() && !old->HasRefs());
      LRU_Remove(old);
      table_.Remove(old->key(), old->hash);
      old->SetInCache(false);
-      assert(usage_ >= old->total_charge);
-      usage_ -= old->total_charge;
+      size_t total_charge = old->CalcTotalCharge(metadata_charge_policy_);
+      assert(usage_ >= total_charge);
+      usage_ -= total_charge;
      last_reference_list.push_back(old);
    }
  }
@@ -161,13 +162,13 @@ void LRUCacheShard::ApplyToSomeEntries(
  // The state is essentially going to be the starting hash, which works
  // nicely even if we resize between calls because we use upper-most
  // hash bits for table indexes.
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  uint32_t length_bits = table_.GetLengthBits();
  uint32_t length = uint32_t{1} << length_bits;

  assert(average_entries_per_lock > 0);
  // Assuming we are called with same average_entries_per_lock repeatedly,
-  // this simplifies some logic (index_end will not overflow).
+  // this simplifies some logic (index_end will not overflow)
  assert(average_entries_per_lock < length || *state == 0);

  uint32_t index_begin = *state >> (32 - length_bits);
@@ -181,25 +182,23 @@ void LRUCacheShard::ApplyToSomeEntries(
  }

  table_.ApplyToEntriesRange(
-      [callback,
-       metadata_charge_policy = metadata_charge_policy_](LRUHandle* h) {
+      [callback](LRUHandle* h) {
        DeleterFn deleter = h->IsSecondaryCacheCompatible()
                                ? h->info_.helper->del_cb
                                : h->info_.deleter;
-        callback(h->key(), h->value, h->GetCharge(metadata_charge_policy),
-                 deleter);
+        callback(h->key(), h->value, h->charge, deleter);
      },
      index_begin, index_end);
 }

 void LRUCacheShard::TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri) {
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  *lru = &lru_;
  *lru_low_pri = lru_low_pri_;
 }

 size_t LRUCacheShard::TEST_GetLRUSize() {
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  LRUHandle* lru_handle = lru_.next;
  size_t lru_size = 0;
  while (lru_handle != &lru_) {
@@ -210,7 +209,7 @@ size_t LRUCacheShard::TEST_GetLRUSize() {
 }

 double LRUCacheShard::GetHighPriPoolRatio() {
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  return high_pri_pool_ratio_;
 }

@@ -223,17 +222,19 @@ void LRUCacheShard::LRU_Remove(LRUHandle* e) {
  e->next->prev = e->prev;
  e->prev->next = e->next;
  e->prev = e->next = nullptr;
-  assert(lru_usage_ >= e->total_charge);
-  lru_usage_ -= e->total_charge;
+  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
+  assert(lru_usage_ >= total_charge);
+  lru_usage_ -= total_charge;
  if (e->InHighPriPool()) {
-    assert(high_pri_pool_usage_ >= e->total_charge);
-    high_pri_pool_usage_ -= e->total_charge;
+    assert(high_pri_pool_usage_ >= total_charge);
+    high_pri_pool_usage_ -= total_charge;
  }
 }

 void LRUCacheShard::LRU_Insert(LRUHandle* e) {
  assert(e->next == nullptr);
  assert(e->prev == nullptr);
+  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
  if (high_pri_pool_ratio_ > 0 && (e->IsHighPri() || e->HasHit())) {
    // Inset "e" to head of LRU list.
    e->next = &lru_;
@@ -241,7 +242,7 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
    e->prev->next = e;
    e->next->prev = e;
    e->SetInHighPriPool(true);
-    high_pri_pool_usage_ += e->total_charge;
+    high_pri_pool_usage_ += total_charge;
    MaintainPoolSize();
  } else {
    // Insert "e" to the head of low-pri pool. Note that when
@@ -253,7 +254,7 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
    e->SetInHighPriPool(false);
    lru_low_pri_ = e;
  }
-  lru_usage_ += e->total_charge;
+  lru_usage_ += total_charge;
 }

 void LRUCacheShard::MaintainPoolSize() {
@@ -262,8 +263,10 @@ void LRUCacheShard::MaintainPoolSize() {
    lru_low_pri_ = lru_low_pri_->next;
    assert(lru_low_pri_ != &lru_);
    lru_low_pri_->SetInHighPriPool(false);
-    assert(high_pri_pool_usage_ >= lru_low_pri_->total_charge);
-    high_pri_pool_usage_ -= lru_low_pri_->total_charge;
+    size_t total_charge =
+        lru_low_pri_->CalcTotalCharge(metadata_charge_policy_);
+    assert(high_pri_pool_usage_ >= total_charge);
+    high_pri_pool_usage_ -= total_charge;
  }
 }

@@ -271,13 +274,14 @@ void LRUCacheShard::EvictFromLRU(size_t charge,
                                 autovector<LRUHandle*>* deleted) {
  while ((usage_ + charge) > capacity_ && lru_.next != &lru_) {
    LRUHandle* old = lru_.next;
-    // LRU list contains only elements which can be evicted.
+    // LRU list contains only elements which can be evicted
    assert(old->InCache() && !old->HasRefs());
    LRU_Remove(old);
    table_.Remove(old->key(), old->hash);
    old->SetInCache(false);
-    assert(usage_ >= old->total_charge);
-    usage_ -= old->total_charge;
+    size_t old_total_charge = old->CalcTotalCharge(metadata_charge_policy_);
+    assert(usage_ >= old_total_charge);
+    usage_ -= old_total_charge;
    deleted->push_back(old);
  }
 }
@@ -285,17 +289,17 @@ void LRUCacheShard::EvictFromLRU(size_t charge,
 void LRUCacheShard::SetCapacity(size_t capacity) {
  autovector<LRUHandle*> last_reference_list;
  {
-    DMutexLock l(mutex_);
+    MutexLock l(&mutex_);
    capacity_ = capacity;
    high_pri_pool_capacity_ = capacity_ * high_pri_pool_ratio_;
    EvictFromLRU(0, &last_reference_list);
  }

-  // Try to insert the evicted entries into tiered cache.
-  // Free the entries outside of mutex for performance reasons.
+  // Try to insert the evicted entries into tiered cache
+  // Free the entries outside of mutex for performance reasons
  for (auto entry : last_reference_list) {
    if (secondary_cache_ && entry->IsSecondaryCacheCompatible() &&
-        !entry->IsInSecondaryCache()) {
+        !entry->IsPromoted()) {
      secondary_cache_->Insert(entry->key(), entry->value, entry->info_.helper)
          .PermitUncheckedError();
    }
@@ -304,7 +308,7 @@ void LRUCacheShard::SetCapacity(size_t capacity) {
 }

 void LRUCacheShard::SetStrictCapacityLimit(bool strict_capacity_limit) {
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  strict_capacity_limit_ = strict_capacity_limit;
 }

@@ -312,15 +316,16 @@ Status LRUCacheShard::InsertItem(LRUHandle* e, Cache::Handle** handle,
                                 bool free_handle_on_fail) {
  Status s = Status::OK();
  autovector<LRUHandle*> last_reference_list;
+  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);

  {
-    DMutexLock l(mutex_);
+    MutexLock l(&mutex_);

    // Free the space following strict LRU policy until enough space
-    // is freed or the lru list is empty.
-    EvictFromLRU(e->total_charge, &last_reference_list);
+    // is freed or the lru list is empty
+    EvictFromLRU(total_charge, &last_reference_list);

-    if ((usage_ + e->total_charge) > capacity_ &&
+    if ((usage_ + total_charge) > capacity_ &&
        (strict_capacity_limit_ || handle == nullptr)) {
      e->SetInCache(false);
      if (handle == nullptr) {
@@ -338,23 +343,25 @@ Status LRUCacheShard::InsertItem(LRUHandle* e, Cache::Handle** handle,
      // Insert into the cache. Note that the cache might get larger than its
      // capacity if not enough space was freed up.
      LRUHandle* old = table_.Insert(e);
-      usage_ += e->total_charge;
+      usage_ += total_charge;
      if (old != nullptr) {
        s = Status::OkOverwritten();
        assert(old->InCache());
        old->SetInCache(false);
        if (!old->HasRefs()) {
-          // old is on LRU because it's in cache and its reference count is 0.
+          // old is on LRU because it's in cache and its reference count is 0
          LRU_Remove(old);
-          assert(usage_ >= old->total_charge);
-          usage_ -= old->total_charge;
+          size_t old_total_charge =
+              old->CalcTotalCharge(metadata_charge_policy_);
+          assert(usage_ >= old_total_charge);
+          usage_ -= old_total_charge;
          last_reference_list.push_back(old);
        }
      }
      if (handle == nullptr) {
        LRU_Insert(e);
      } else {
-        // If caller already holds a ref, no need to take one here.
+        // If caller already holds a ref, no need to take one here
        if (!e->HasRefs()) {
          e->Ref();
        }
@@ -363,11 +370,11 @@ Status LRUCacheShard::InsertItem(LRUHandle* e, Cache::Handle** handle,
    }
  }

-  // Try to insert the evicted entries into the secondary cache.
-  // Free the entries here outside of mutex for performance reasons.
+  // Try to insert the evicted entries into the secondary cache
+  // Free the entries here outside of mutex for performance reasons
  for (auto entry : last_reference_list) {
    if (secondary_cache_ && entry->IsSecondaryCacheCompatible() &&
-        !entry->IsInSecondaryCache()) {
+        !entry->IsPromoted()) {
      secondary_cache_->Insert(entry->key(), entry->value, entry->info_.helper)
          .PermitUncheckedError();
    }
@@ -383,8 +390,9 @@ void LRUCacheShard::Promote(LRUHandle* e) {
  assert(secondary_handle->IsReady());
  e->SetIncomplete(false);
  e->SetInCache(true);
+  e->SetPromoted(true);
  e->value = secondary_handle->Value();
-  e->CalcTotalCharge(secondary_handle->Size(), metadata_charge_policy_);
+  e->charge = secondary_handle->Size();
  delete secondary_handle;

  // This call could fail if the cache is over capacity and
@@ -396,15 +404,14 @@ void LRUCacheShard::Promote(LRUHandle* e) {
    Status s = InsertItem(e, &handle, /*free_handle_on_fail=*/false);
    if (!s.ok()) {
      // Item is in memory, but not accounted against the cache capacity.
-      // When the handle is released, the item should get deleted.
+      // When the handle is released, the item should get deleted
      assert(!e->InCache());
    }
  } else {
    // Since the secondary cache lookup failed, mark the item as not in cache
    // Don't charge the cache as its only metadata that'll shortly be released
-    DMutexLock l(mutex_);
-    // TODO
-    e->CalcTotalCharge(0, metadata_charge_policy_);
+    MutexLock l(&mutex_);
+    e->charge = 0;
    e->SetInCache(false);
  }
 }
@@ -416,7 +423,7 @@ Cache::Handle* LRUCacheShard::Lookup(
    bool wait, Statistics* stats) {
  LRUHandle* e = nullptr;
  {
-    DMutexLock l(mutex_);
+    MutexLock l(&mutex_);
    e = table_.Lookup(key, hash);
    if (e != nullptr) {
      assert(e->InCache());
@@ -430,8 +437,8 @@ Cache::Handle* LRUCacheShard::Lookup(
  }

  // If handle table lookup failed, then allocate a handle outside the
-  // mutex if we're going to lookup in the secondary cache.
-  // Only support synchronous for now.
+  // mutex if we're going to lookup in the secondary cache
+  // Only support synchronous for now
  // TODO: Support asynchronous lookup in secondary cache
  if (!e && secondary_cache_ && helper && helper->saveto_cb) {
    // For objects from the secondary cache, we expect the caller to provide
@@ -440,9 +447,8 @@ Cache::Handle* LRUCacheShard::Lookup(
    // accounting purposes, which we won't demote to the secondary cache
    // anyway.
    assert(create_cb && helper->del_cb);
-    bool is_in_sec_cache{false};
    std::unique_ptr<SecondaryCacheResultHandle> secondary_handle =
-        secondary_cache_->Lookup(key, create_cb, wait, is_in_sec_cache);
+        secondary_cache_->Lookup(key, create_cb, wait);
    if (secondary_handle != nullptr) {
      e = reinterpret_cast<LRUHandle*>(
          new char[sizeof(LRUHandle) - 1 + key.size()]);
@@ -462,9 +468,8 @@ Cache::Handle* LRUCacheShard::Lookup(

      if (wait) {
        Promote(e);
-        e->SetIsInSecondaryCache(is_in_sec_cache);
        if (!e->value) {
-          // The secondary cache returned a handle, but the lookup failed.
+          // The secondary cache returned a handle, but the lookup failed
          e->Unref();
          e->Free();
          e = nullptr;
@@ -474,9 +479,8 @@ Cache::Handle* LRUCacheShard::Lookup(
        }
      } else {
        // If wait is false, we always return a handle and let the caller
-        // release the handle after checking for success or failure.
+        // release the handle after checking for success or failure
        e->SetIncomplete(true);
-        e->SetIsInSecondaryCache(is_in_sec_cache);
        // This may be slightly inaccurate, if the lookup eventually fails.
        // But the probability is very low.
        PERF_COUNTER_ADD(secondary_cache_hit_count, 1);
@@ -489,39 +493,39 @@ Cache::Handle* LRUCacheShard::Lookup(

 bool LRUCacheShard::Ref(Cache::Handle* h) {
  LRUHandle* e = reinterpret_cast<LRUHandle*>(h);
-  DMutexLock l(mutex_);
-  // To create another reference - entry must be already externally referenced.
+  MutexLock l(&mutex_);
+  // To create another reference - entry must be already externally referenced
  assert(e->HasRefs());
  e->Ref();
  return true;
 }

 void LRUCacheShard::SetHighPriorityPoolRatio(double high_pri_pool_ratio) {
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  high_pri_pool_ratio_ = high_pri_pool_ratio;
  high_pri_pool_capacity_ = capacity_ * high_pri_pool_ratio_;
  MaintainPoolSize();
 }

-bool LRUCacheShard::Release(Cache::Handle* handle, bool erase_if_last_ref) {
+bool LRUCacheShard::Release(Cache::Handle* handle, bool force_erase) {
  if (handle == nullptr) {
    return false;
  }
  LRUHandle* e = reinterpret_cast<LRUHandle*>(handle);
  bool last_reference = false;
  {
-    DMutexLock l(mutex_);
+    MutexLock l(&mutex_);
    last_reference = e->Unref();
    if (last_reference && e->InCache()) {
-      // The item is still in cache, and nobody else holds a reference to it.
-      if (usage_ > capacity_ || erase_if_last_ref) {
-        // The LRU list must be empty since the cache is full.
-        assert(lru_.next == &lru_ || erase_if_last_ref);
-        // Take this opportunity and remove the item.
+      // The item is still in cache, and nobody else holds a reference to it
+      if (usage_ > capacity_ || force_erase) {
+        // The LRU list must be empty since the cache is full
+        assert(lru_.next == &lru_ || force_erase);
+        // Take this opportunity and remove the item
        table_.Remove(e->key(), e->hash);
        e->SetInCache(false);
      } else {
-        // Put the item back on the LRU list, and don't free it.
+        // Put the item back on the LRU list, and don't free it
        LRU_Insert(e);
        last_reference = false;
      }
@@ -532,12 +536,13 @@ bool LRUCacheShard::Release(Cache::Handle* handle, bool erase_if_last_ref) {
    // usage. If value is null in the latter case, taht means the lookup
    // failed and we didn't charge the cache.
    if (last_reference && (!e->IsSecondaryCacheCompatible() || e->value)) {
-      assert(usage_ >= e->total_charge);
-      usage_ -= e->total_charge;
+      size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
+      assert(usage_ >= total_charge);
+      usage_ -= total_charge;
    }
  }

-  // Free the entry here outside of mutex for performance reasons.
+  // Free the entry here outside of mutex for performance reasons
  if (last_reference) {
    e->Free();
  }
@@ -549,8 +554,8 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
                             void (*deleter)(const Slice& key, void* value),
                             const Cache::CacheItemHelper* helper,
                             Cache::Handle** handle, Cache::Priority priority) {
-  // Allocate the memory here outside of the mutex.
-  // If the cache is full, we'll have to release it.
+  // Allocate the memory here outside of the mutex
+  // If the cache is full, we'll have to release it
  // It shouldn't happen very often though.
  LRUHandle* e = reinterpret_cast<LRUHandle*>(
      new char[sizeof(LRUHandle) - 1 + key.size()]);
@@ -566,6 +571,7 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
 #endif  // __SANITIZE_THREAD__
    e->info_.deleter = deleter;
  }
+  e->charge = charge;
  e->key_length = key.size();
  e->hash = hash;
  e->refs = 0;
@@ -573,7 +579,6 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
  e->SetInCache(true);
  e->SetPriority(priority);
  memcpy(e->key_data, key.data(), key.size());
-  e->CalcTotalCharge(charge, metadata_charge_policy_);

  return InsertItem(e, handle, /* free_handle_on_fail */ true);
 }
@@ -582,7 +587,7 @@ void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
  LRUHandle* e;
  bool last_reference = false;
  {
-    DMutexLock l(mutex_);
+    MutexLock l(&mutex_);
    e = table_.Remove(key, hash);
    if (e != nullptr) {
      assert(e->InCache());
@@ -590,15 +595,16 @@ void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
      if (!e->HasRefs()) {
        // The entry is in LRU since it's in hash and has no external references
        LRU_Remove(e);
-        assert(usage_ >= e->total_charge);
-        usage_ -= e->total_charge;
+        size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
+        assert(usage_ >= total_charge);
+        usage_ -= total_charge;
        last_reference = true;
      }
    }
  }

-  // Free the entry here outside of mutex for performance reasons.
-  // last_reference will only be true if e != nullptr.
+  // Free the entry here outside of mutex for performance reasons
+  // last_reference will only be true if e != nullptr
  if (last_reference) {
    e->Free();
  }
@@ -606,7 +612,7 @@ void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {

 bool LRUCacheShard::IsReady(Cache::Handle* handle) {
  LRUHandle* e = reinterpret_cast<LRUHandle*>(handle);
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  bool ready = true;
  if (e->IsPending()) {
    assert(secondary_cache_);
@@ -617,12 +623,12 @@ bool LRUCacheShard::IsReady(Cache::Handle* handle) {
 }

 size_t LRUCacheShard::GetUsage() const {
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  return usage_;
 }

 size_t LRUCacheShard::GetPinnedUsage() const {
-  DMutexLock l(mutex_);
+  MutexLock l(&mutex_);
  assert(usage_ >= lru_usage_);
  return usage_ - lru_usage_;
 }
@@ -631,7 +637,7 @@ std::string LRUCacheShard::GetPrintableOptions() const {
  const int kBufferSize = 200;
  char buffer[kBufferSize];
  {
-    DMutexLock l(mutex_);
+    MutexLock l(&mutex_);
    snprintf(buffer, kBufferSize, "    high_pri_pool_ratio: %.3lf\n",
             high_pri_pool_ratio_);
  }
@@ -682,12 +688,7 @@ void* LRUCache::Value(Handle* handle) {
 }

 size_t LRUCache::GetCharge(Handle* handle) const {
-  CacheMetadataChargePolicy metadata_charge_policy = kDontChargeCacheMetadata;
-  if (num_shards_ > 0) {
-    metadata_charge_policy = shards_[0].metadata_charge_policy_;
-  }
-  return reinterpret_cast<const LRUHandle*>(handle)->GetCharge(
-      metadata_charge_policy);
+  return reinterpret_cast<const LRUHandle*>(handle)->charge;
 }

 Cache::DeleterFn LRUCache::GetDeleter(Handle* handle) const {
@@ -704,7 +705,7 @@ uint32_t LRUCache::GetHash(Handle* handle) const {
 }

 void LRUCache::DisownData() {
-  // Leak data only if that won't generate an ASAN/valgrind warning.
+  // Leak data only if that won't generate an ASAN/valgrind warning
  if (!kMustFreeHeapAllocations) {
    shards_ = nullptr;
    num_shards_ = 0;
@@ -757,8 +758,6 @@ void LRUCache::WaitAll(std::vector<Handle*>& handles) {
  }
 }

-}  // namespace lru_cache
-
 std::shared_ptr<Cache> NewLRUCache(
    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
    double high_pri_pool_ratio,
@@ -766,10 +765,10 @@ std::shared_ptr<Cache> NewLRUCache(
    CacheMetadataChargePolicy metadata_charge_policy,
    const std::shared_ptr<SecondaryCache>& secondary_cache) {
  if (num_shard_bits >= 20) {
-    return nullptr;  // The cache cannot be sharded into too many fine pieces.
+    return nullptr;  // the cache cannot be sharded into too many fine pieces
  }
  if (high_pri_pool_ratio < 0.0 || high_pri_pool_ratio > 1.0) {
-    // Invalid high_pri_pool_ratio
+    // invalid high_pri_pool_ratio
    return nullptr;
  }
  if (num_shard_bits < 0) {
@@ -17,10 +17,8 @@
 #include "port/port.h"
 #include "rocksdb/secondary_cache.h"
 #include "util/autovector.h"
-#include "util/distributed_mutex.h"

 namespace ROCKSDB_NAMESPACE {
-namespace lru_cache {

 // LRU cache implementation. This class is not thread-safe.

@@ -67,7 +65,7 @@ struct LRUHandle {
  };
  LRUHandle* next;
  LRUHandle* prev;
-  size_t total_charge;  // TODO(opt): Only allow uint32_t?
+  size_t charge;  // TODO(opt): Only allow uint32_t?
  size_t key_length;
  // The hash of key(). Used for fast sharding and comparisons.
  uint32_t hash;
@@ -83,12 +81,12 @@ struct LRUHandle {
    IN_HIGH_PRI_POOL = (1 << 2),
    // Whether this entry has had any lookups (hits).
    HAS_HIT = (1 << 3),
-    // Can this be inserted into the secondary cache.
+    // Can this be inserted into the secondary cache
    IS_SECONDARY_CACHE_COMPATIBLE = (1 << 4),
-    // Is the handle still being read from a lower tier.
+    // Is the handle still being read from a lower tier
    IS_PENDING = (1 << 5),
-    // Whether this handle is still in a lower tier
-    IS_IN_SECONDARY_CACHE = (1 << 6),
+    // Has the item been promoted from a lower tier
+    IS_PROMOTED = (1 << 6),
  };

  uint8_t flags;
@@ -131,7 +129,7 @@ struct LRUHandle {
 #endif  // __SANITIZE_THREAD__
  }
  bool IsPending() const { return flags & IS_PENDING; }
-  bool IsInSecondaryCache() const { return flags & IS_IN_SECONDARY_CACHE; }
+  bool IsPromoted() const { return flags & IS_PROMOTED; }

  void SetInCache(bool in_cache) {
    if (in_cache) {
@@ -178,11 +176,11 @@ struct LRUHandle {
    }
  }

-  void SetIsInSecondaryCache(bool is_in_secondary_cache) {
-    if (is_in_secondary_cache) {
-      flags |= IS_IN_SECONDARY_CACHE;
+  void SetPromoted(bool promoted) {
+    if (promoted) {
+      flags |= IS_PROMOTED;
    } else {
-      flags &= ~IS_IN_SECONDARY_CACHE;
+      flags &= ~IS_PROMOTED;
    }
  }

@@ -210,32 +208,19 @@ struct LRUHandle {
    delete[] reinterpret_cast<char*>(this);
  }

-  inline size_t CalcuMetaCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) const {
-    if (metadata_charge_policy != kFullChargeCacheMetadata) {
-      return 0;
-    } else {
+  // Calculate the memory usage by metadata
+  inline size_t CalcTotalCharge(
+      CacheMetadataChargePolicy metadata_charge_policy) {
+    size_t meta_charge = 0;
+    if (metadata_charge_policy == kFullChargeCacheMetadata) {
 #ifdef ROCKSDB_MALLOC_USABLE_SIZE
-      return malloc_usable_size(
-          const_cast<void*>(static_cast<const void*>(this)));
+      meta_charge += malloc_usable_size(static_cast<void*>(this));
 #else
-      // This is the size that is used when a new handle is created.
-      return sizeof(LRUHandle) - 1 + key_length;
+      // This is the size that is used when a new handle is created
+      meta_charge += sizeof(LRUHandle) - 1 + key_length;
 #endif
    }
-  }
-
-  // Calculate the memory usage by metadata.
-  inline void CalcTotalCharge(
-      size_t charge, CacheMetadataChargePolicy metadata_charge_policy) {
-    total_charge = charge + CalcuMetaCharge(metadata_charge_policy);
-  }
-
-  inline size_t GetCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) const {
-    size_t meta_charge = CalcuMetaCharge(metadata_charge_policy);
-    assert(total_charge >= meta_charge);
-    return total_charge - meta_charge;
+    return charge + meta_charge;
  }
 };

@@ -287,10 +272,10 @@ class LRUHandleTable {
  // a linked list of cache entries that hash into the bucket.
  std::unique_ptr<LRUHandle*[]> list_;

-  // Number of elements currently in the table.
+  // Number of elements currently in the table
  uint32_t elems_;

-  // Set from max_upper_hash_bits (see constructor).
+  // Set from max_upper_hash_bits (see constructor)
  const int max_length_bits_;
 };

@@ -306,7 +291,7 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {

  // Separate from constructor so caller can easily make an array of LRUCache
  // if current usage is more than new capacity, the function will attempt to
-  // free the needed space.
+  // free the needed space
  virtual void SetCapacity(size_t capacity) override;

  // Set the flag to reject insertion if cache if full.
@@ -329,7 +314,8 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
    assert(helper);
    return Insert(key, hash, value, charge, nullptr, helper, handle, priority);
  }
-  // If helper_cb is null, the values of the following arguments don't matter.
+  // If helper_cb is null, the values of the following arguments don't
+  // matter
  virtual Cache::Handle* Lookup(const Slice& key, uint32_t hash,
                                const ShardedCache::CacheItemHelper* helper,
                                const ShardedCache::CreateCallback& create_cb,
@@ -340,14 +326,14 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
                  nullptr);
  }
  virtual bool Release(Cache::Handle* handle, bool /*useful*/,
-                       bool erase_if_last_ref) override {
-    return Release(handle, erase_if_last_ref);
+                       bool force_erase) override {
+    return Release(handle, force_erase);
  }
  virtual bool IsReady(Cache::Handle* /*handle*/) override;
  virtual void Wait(Cache::Handle* /*handle*/) override {}
  virtual bool Ref(Cache::Handle* handle) override;
  virtual bool Release(Cache::Handle* handle,
-                       bool erase_if_last_ref = false) override;
+                       bool force_erase = false) override;
  virtual void Erase(const Slice& key, uint32_t hash) override;

  // Although in some platforms the update of size_t is atomic, to make sure
@@ -368,8 +354,8 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {

  void TEST_GetLRUList(LRUHandle** lru, LRUHandle** lru_low_pri);

-  //  Retrieves number of elements in LRU, for unit test purpose only.
-  //  Not threadsafe.
+  //  Retrieves number of elements in LRU, for unit test purpose only
+  //  not threadsafe
  size_t TEST_GetLRUSize();

  //  Retrieves high pri pool ratio
@@ -379,16 +365,14 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
  friend class LRUCache;
  // Insert an item into the hash table and, if handle is null, insert into
  // the LRU list. Older items are evicted as necessary. If the cache is full
-  // and free_handle_on_fail is true, the item is deleted and handle is set to
-  // nullptr.
+  // and free_handle_on_fail is true, the item is deleted and handle is set to.
  Status InsertItem(LRUHandle* item, Cache::Handle** handle,
                    bool free_handle_on_fail);
  Status Insert(const Slice& key, uint32_t hash, void* value, size_t charge,
                DeleterFn deleter, const Cache::CacheItemHelper* helper,
                Cache::Handle** handle, Cache::Priority priority);
-  // Promote an item looked up from the secondary cache to the LRU cache.
-  // The item may be still in the secondary cache.
-  // It is only inserted into the hash table and not the LRU list, and only
+  // Promote an item looked up from the secondary cache to the LRU cache. The
+  // item is only inserted into the hash table and not the LRU list, and only
  // if the cache is not at full capacity, as is the case during Insert.  The
  // caller should hold a reference on the LRUHandle. When the caller releases
  // the last reference, the item is added to the LRU list.
@@ -405,7 +389,7 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
  // Free some space following strict LRU policy until enough space
  // to hold (usage_ + charge) is freed or the lru list is empty
  // This function is not thread safe - it needs to be executed while
-  // holding the mutex_.
+  // holding the mutex_
  void EvictFromLRU(size_t charge, autovector<LRUHandle*>* deleted);

  // Initialized before use.
@@ -445,16 +429,16 @@ class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
  // ------------vvvvvvvvvvvvv-----------
  LRUHandleTable table_;

-  // Memory size for entries residing in the cache.
+  // Memory size for entries residing in the cache
  size_t usage_;

-  // Memory size for entries residing only in the LRU list.
+  // Memory size for entries residing only in the LRU list
  size_t lru_usage_;

  // mutex_ protects the following state.
  // We don't count mutex_ as the cache's internal state so semantically we
  // don't mind mutex_ invoking the non-const actions.
-  mutable DMutex mutex_;
+  mutable port::Mutex mutex_;

  std::shared_ptr<SecondaryCache> secondary_cache_;
 };
@@ -483,9 +467,9 @@ class LRUCache
  virtual void DisownData() override;
  virtual void WaitAll(std::vector<Handle*>& handles) override;

-  //  Retrieves number of elements in LRU, for unit test purpose only.
+  //  Retrieves number of elements in LRU, for unit test purpose only
  size_t TEST_GetLRUSize();
-  //  Retrieves high pri pool ratio.
+  //  Retrieves high pri pool ratio
  double GetHighPriPoolRatio();

 private:
@@ -494,10 +478,4 @@ class LRUCache
  std::shared_ptr<SecondaryCache> secondary_cache_;
 };

-}  // namespace lru_cache
-
-using LRUCache = lru_cache::LRUCache;
-using LRUHandle = lru_cache::LRUHandle;
-using LRUCacheShard = lru_cache::LRUCacheShard;
-
 }  // namespace ROCKSDB_NAMESPACE
@@ -9,7 +9,6 @@
 #include <vector>

 #include "cache/cache_key.h"
-#include "cache/fast_lru_cache.h"
 #include "db/db_test_util.h"
 #include "file/sst_file_manager_impl.h"
 #include "port/port.h"
@@ -206,53 +205,6 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
  ValidateLRUList({"e", "f", "g", "Z", "d"}, 2);
 }

-// TODO(guido) Consolidate the following FastLRUCache tests with
-// that of LRUCache.
-class FastLRUCacheTest : public testing::Test {
- public:
-  FastLRUCacheTest() {}
-  ~FastLRUCacheTest() override { DeleteCache(); }
-
-  void DeleteCache() {
-    if (cache_ != nullptr) {
-      cache_->~LRUCacheShard();
-      port::cacheline_aligned_free(cache_);
-      cache_ = nullptr;
-    }
-  }
-
-  void NewCache(size_t capacity) {
-    DeleteCache();
-    cache_ = reinterpret_cast<fast_lru_cache::LRUCacheShard*>(
-        port::cacheline_aligned_alloc(sizeof(fast_lru_cache::LRUCacheShard)));
-    new (cache_) fast_lru_cache::LRUCacheShard(
-        capacity, 1 /*estimated_value_size*/, false /*strict_capacity_limit*/,
-        kDontChargeCacheMetadata);
-  }
-
-  Status Insert(const std::string& key) {
-    return cache_->Insert(key, 0 /*hash*/, nullptr /*value*/, 1 /*charge*/,
-                          nullptr /*deleter*/, nullptr /*handle*/,
-                          Cache::Priority::LOW);
-  }
-
-  Status Insert(char key, size_t len) { return Insert(std::string(len, key)); }
-
- private:
-  fast_lru_cache::LRUCacheShard* cache_ = nullptr;
-};
-
-TEST_F(FastLRUCacheTest, ValidateKeySize) {
-  NewCache(3);
-  EXPECT_OK(Insert('a', 16));
-  EXPECT_NOK(Insert('b', 15));
-  EXPECT_OK(Insert('b', 16));
-  EXPECT_NOK(Insert('c', 17));
-  EXPECT_NOK(Insert('d', 1000));
-  EXPECT_NOK(Insert('e', 11));
-  EXPECT_NOK(Insert('f', 0));
-}
-
 class TestSecondaryCache : public SecondaryCache {
 public:
  // Specifies what action to take on a lookup for a particular key
@@ -314,13 +266,12 @@ class TestSecondaryCache : public SecondaryCache {
  }

  std::unique_ptr<SecondaryCacheResultHandle> Lookup(
-      const Slice& key, const Cache::CreateCallback& create_cb, bool /*wait*/,
-      bool& is_in_sec_cache) override {
+      const Slice& key, const Cache::CreateCallback& create_cb,
+      bool /*wait*/) override {
    std::string key_str = key.ToString();
    TEST_SYNC_POINT_CALLBACK("TestSecondaryCache::Lookup", &key_str);

    std::unique_ptr<SecondaryCacheResultHandle> secondary_handle;
-    is_in_sec_cache = false;
    ResultType type = ResultType::SUCCESS;
    auto iter = result_map_.find(key.ToString());
    if (iter != result_map_.end()) {
@@ -345,7 +296,6 @@ class TestSecondaryCache : public SecondaryCache {
      if (s.ok()) {
        secondary_handle.reset(new TestSecondaryCacheResultHandle(
            cache_.get(), handle, value, charge, type));
-        is_in_sec_cache = true;
      } else {
        cache_->Release(handle);
      }
@@ -433,10 +383,10 @@ class DBSecondaryCacheTest : public DBTestBase {
  std::unique_ptr<Env> fault_env_;
 };

-class LRUCacheSecondaryCacheTest : public LRUCacheTest {
+class LRUSecondaryCacheTest : public LRUCacheTest {
 public:
-  LRUCacheSecondaryCacheTest() : fail_create_(false) {}
-  ~LRUCacheSecondaryCacheTest() {}
+  LRUSecondaryCacheTest() : fail_create_(false) {}
+  ~LRUSecondaryCacheTest() {}

 protected:
  class TestItem {
@@ -482,9 +432,8 @@ class LRUCacheSecondaryCacheTest : public LRUCacheTest {

  static Cache::CacheItemHelper helper_fail_;

-  Cache::CreateCallback test_item_creator = [&](const void* buf, size_t size,
-                                                void** out_obj,
-                                                size_t* charge) -> Status {
+  Cache::CreateCallback test_item_creator =
+      [&](void* buf, size_t size, void** out_obj, size_t* charge) -> Status {
    if (fail_create_) {
      return Status::NotSupported();
    }
@@ -499,17 +448,16 @@ class LRUCacheSecondaryCacheTest : public LRUCacheTest {
  bool fail_create_;
 };

-Cache::CacheItemHelper LRUCacheSecondaryCacheTest::helper_(
-    LRUCacheSecondaryCacheTest::SizeCallback,
-    LRUCacheSecondaryCacheTest::SaveToCallback,
-    LRUCacheSecondaryCacheTest::DeletionCallback);
+Cache::CacheItemHelper LRUSecondaryCacheTest::helper_(
+    LRUSecondaryCacheTest::SizeCallback, LRUSecondaryCacheTest::SaveToCallback,
+    LRUSecondaryCacheTest::DeletionCallback);

-Cache::CacheItemHelper LRUCacheSecondaryCacheTest::helper_fail_(
-    LRUCacheSecondaryCacheTest::SizeCallback,
-    LRUCacheSecondaryCacheTest::SaveToCallbackFail,
-    LRUCacheSecondaryCacheTest::DeletionCallback);
+Cache::CacheItemHelper LRUSecondaryCacheTest::helper_fail_(
+    LRUSecondaryCacheTest::SizeCallback,
+    LRUSecondaryCacheTest::SaveToCallbackFail,
+    LRUSecondaryCacheTest::DeletionCallback);

-TEST_F(LRUCacheSecondaryCacheTest, BasicTest) {
+TEST_F(LRUSecondaryCacheTest, BasicTest) {
  LRUCacheOptions opts(1024, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
                       kDontChargeCacheMetadata);
  std::shared_ptr<TestSecondaryCache> secondary_cache =
@@ -521,25 +469,25 @@ TEST_F(LRUCacheSecondaryCacheTest, BasicTest) {
  Random rnd(301);
  std::string str1 = rnd.RandomString(1020);
  TestItem* item1 = new TestItem(str1.data(), str1.length());
-  ASSERT_OK(cache->Insert("k1", item1, &LRUCacheSecondaryCacheTest::helper_,
+  ASSERT_OK(cache->Insert("k1", item1, &LRUSecondaryCacheTest::helper_,
                          str1.length()));
  std::string str2 = rnd.RandomString(1020);
  TestItem* item2 = new TestItem(str2.data(), str2.length());
  // k1 should be demoted to NVM
-  ASSERT_OK(cache->Insert("k2", item2, &LRUCacheSecondaryCacheTest::helper_,
+  ASSERT_OK(cache->Insert("k2", item2, &LRUSecondaryCacheTest::helper_,
                          str2.length()));

  get_perf_context()->Reset();
  Cache::Handle* handle;
  handle =
-      cache->Lookup("k2", &LRUCacheSecondaryCacheTest::helper_,
-                    test_item_creator, Cache::Priority::LOW, true, stats.get());
+      cache->Lookup("k2", &LRUSecondaryCacheTest::helper_, test_item_creator,
+                    Cache::Priority::LOW, true, stats.get());
  ASSERT_NE(handle, nullptr);
  cache->Release(handle);
  // This lookup should promote k1 and demote k2
  handle =
-      cache->Lookup("k1", &LRUCacheSecondaryCacheTest::helper_,
-                    test_item_creator, Cache::Priority::LOW, true, stats.get());
+      cache->Lookup("k1", &LRUSecondaryCacheTest::helper_, test_item_creator,
+                    Cache::Priority::LOW, true, stats.get());
  ASSERT_NE(handle, nullptr);
  cache->Release(handle);
  ASSERT_EQ(secondary_cache->num_inserts(), 2u);
@@ -553,7 +501,7 @@ TEST_F(LRUCacheSecondaryCacheTest, BasicTest) {
  secondary_cache.reset();
 }

-TEST_F(LRUCacheSecondaryCacheTest, BasicFailTest) {
+TEST_F(LRUSecondaryCacheTest, BasicFailTest) {
  LRUCacheOptions opts(1024, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
                       kDontChargeCacheMetadata);
  std::shared_ptr<TestSecondaryCache> secondary_cache =
@@ -563,18 +511,16 @@ TEST_F(LRUCacheSecondaryCacheTest, BasicFailTest) {

  Random rnd(301);
  std::string str1 = rnd.RandomString(1020);
-  auto item1 = std::make_unique<TestItem>(str1.data(), str1.length());
-  ASSERT_TRUE(cache->Insert("k1", item1.get(), nullptr, str1.length())
-                  .IsInvalidArgument());
-  ASSERT_OK(cache->Insert("k1", item1.get(),
-                          &LRUCacheSecondaryCacheTest::helper_, str1.length()));
-  item1.release();  // Appease clang-analyze "potential memory leak"
+  TestItem* item1 = new TestItem(str1.data(), str1.length());
+  ASSERT_NOK(cache->Insert("k1", item1, nullptr, str1.length()));
+  ASSERT_OK(cache->Insert("k1", item1, &LRUSecondaryCacheTest::helper_,
+                          str1.length()));

  Cache::Handle* handle;
  handle = cache->Lookup("k2", nullptr, test_item_creator, Cache::Priority::LOW,
                         true);
  ASSERT_EQ(handle, nullptr);
-  handle = cache->Lookup("k2", &LRUCacheSecondaryCacheTest::helper_,
+  handle = cache->Lookup("k2", &LRUSecondaryCacheTest::helper_,
                         test_item_creator, Cache::Priority::LOW, false);
  ASSERT_EQ(handle, nullptr);

@@ -582,7 +528,7 @@ TEST_F(LRUCacheSecondaryCacheTest, BasicFailTest) {
  secondary_cache.reset();
 }

-TEST_F(LRUCacheSecondaryCacheTest, SaveFailTest) {
+TEST_F(LRUSecondaryCacheTest, SaveFailTest) {
  LRUCacheOptions opts(1024, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
                       kDontChargeCacheMetadata);
  std::shared_ptr<TestSecondaryCache> secondary_cache =
@@ -593,66 +539,25 @@ TEST_F(LRUCacheSecondaryCacheTest, SaveFailTest) {
  Random rnd(301);
  std::string str1 = rnd.RandomString(1020);
  TestItem* item1 = new TestItem(str1.data(), str1.length());
-  ASSERT_OK(cache->Insert(
-      "k1", item1, &LRUCacheSecondaryCacheTest::helper_fail_, str1.length()));
-  std::string str2 = rnd.RandomString(1020);
-  TestItem* item2 = new TestItem(str2.data(), str2.length());
-  // k1 should be demoted to NVM
-  ASSERT_OK(cache->Insert(
-      "k2", item2, &LRUCacheSecondaryCacheTest::helper_fail_, str2.length()));
-
-  Cache::Handle* handle;
-  handle = cache->Lookup("k2", &LRUCacheSecondaryCacheTest::helper_fail_,
-                         test_item_creator, Cache::Priority::LOW, true);
-  ASSERT_NE(handle, nullptr);
-  cache->Release(handle);
-  // This lookup should fail, since k1 demotion would have failed
-  handle = cache->Lookup("k1", &LRUCacheSecondaryCacheTest::helper_fail_,
-                         test_item_creator, Cache::Priority::LOW, true);
-  ASSERT_EQ(handle, nullptr);
-  // Since k1 didn't get promoted, k2 should still be in cache
-  handle = cache->Lookup("k2", &LRUCacheSecondaryCacheTest::helper_fail_,
-                         test_item_creator, Cache::Priority::LOW, true);
-  ASSERT_NE(handle, nullptr);
-  cache->Release(handle);
-  ASSERT_EQ(secondary_cache->num_inserts(), 1u);
-  ASSERT_EQ(secondary_cache->num_lookups(), 1u);
-
-  cache.reset();
-  secondary_cache.reset();
-}
-
-TEST_F(LRUCacheSecondaryCacheTest, CreateFailTest) {
-  LRUCacheOptions opts(1024, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
-                       kDontChargeCacheMetadata);
-  std::shared_ptr<TestSecondaryCache> secondary_cache =
-      std::make_shared<TestSecondaryCache>(2048);
-  opts.secondary_cache = secondary_cache;
-  std::shared_ptr<Cache> cache = NewLRUCache(opts);
-
-  Random rnd(301);
-  std::string str1 = rnd.RandomString(1020);
-  TestItem* item1 = new TestItem(str1.data(), str1.length());
-  ASSERT_OK(cache->Insert("k1", item1, &LRUCacheSecondaryCacheTest::helper_,
+  ASSERT_OK(cache->Insert("k1", item1, &LRUSecondaryCacheTest::helper_fail_,
                          str1.length()));
  std::string str2 = rnd.RandomString(1020);
  TestItem* item2 = new TestItem(str2.data(), str2.length());
  // k1 should be demoted to NVM
-  ASSERT_OK(cache->Insert("k2", item2, &LRUCacheSecondaryCacheTest::helper_,
+  ASSERT_OK(cache->Insert("k2", item2, &LRUSecondaryCacheTest::helper_fail_,
                          str2.length()));

  Cache::Handle* handle;
-  SetFailCreate(true);
-  handle = cache->Lookup("k2", &LRUCacheSecondaryCacheTest::helper_,
+  handle = cache->Lookup("k2", &LRUSecondaryCacheTest::helper_fail_,
                         test_item_creator, Cache::Priority::LOW, true);
  ASSERT_NE(handle, nullptr);
  cache->Release(handle);
-  // This lookup should fail, since k1 creation would have failed
-  handle = cache->Lookup("k1", &LRUCacheSecondaryCacheTest::helper_,
+  // This lookup should fail, since k1 demotion would have failed
+  handle = cache->Lookup("k1", &LRUSecondaryCacheTest::helper_fail_,
                         test_item_creator, Cache::Priority::LOW, true);
  ASSERT_EQ(handle, nullptr);
  // Since k1 didn't get promoted, k2 should still be in cache
-  handle = cache->Lookup("k2", &LRUCacheSecondaryCacheTest::helper_,
+  handle = cache->Lookup("k2", &LRUSecondaryCacheTest::helper_fail_,
                         test_item_creator, Cache::Priority::LOW, true);
  ASSERT_NE(handle, nullptr);
  cache->Release(handle);
@@ -663,7 +568,48 @@ TEST_F(LRUCacheSecondaryCacheTest, CreateFailTest) {
  secondary_cache.reset();
 }

-TEST_F(LRUCacheSecondaryCacheTest, FullCapacityTest) {
+TEST_F(LRUSecondaryCacheTest, CreateFailTest) {
+  LRUCacheOptions opts(1024, 0, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
+                       kDontChargeCacheMetadata);
+  std::shared_ptr<TestSecondaryCache> secondary_cache =
+      std::make_shared<TestSecondaryCache>(2048);
+  opts.secondary_cache = secondary_cache;
+  std::shared_ptr<Cache> cache = NewLRUCache(opts);
+
+  Random rnd(301);
+  std::string str1 = rnd.RandomString(1020);
+  TestItem* item1 = new TestItem(str1.data(), str1.length());
+  ASSERT_OK(cache->Insert("k1", item1, &LRUSecondaryCacheTest::helper_,
+                          str1.length()));
+  std::string str2 = rnd.RandomString(1020);
+  TestItem* item2 = new TestItem(str2.data(), str2.length());
+  // k1 should be demoted to NVM
+  ASSERT_OK(cache->Insert("k2", item2, &LRUSecondaryCacheTest::helper_,
+                          str2.length()));
+
+  Cache::Handle* handle;
+  SetFailCreate(true);
+  handle = cache->Lookup("k2", &LRUSecondaryCacheTest::helper_,
+                         test_item_creator, Cache::Priority::LOW, true);
+  ASSERT_NE(handle, nullptr);
+  cache->Release(handle);
+  // This lookup should fail, since k1 creation would have failed
+  handle = cache->Lookup("k1", &LRUSecondaryCacheTest::helper_,
+                         test_item_creator, Cache::Priority::LOW, true);
+  ASSERT_EQ(handle, nullptr);
+  // Since k1 didn't get promoted, k2 should still be in cache
+  handle = cache->Lookup("k2", &LRUSecondaryCacheTest::helper_,
+                         test_item_creator, Cache::Priority::LOW, true);
+  ASSERT_NE(handle, nullptr);
+  cache->Release(handle);
+  ASSERT_EQ(secondary_cache->num_inserts(), 1u);
+  ASSERT_EQ(secondary_cache->num_lookups(), 1u);
+
+  cache.reset();
+  secondary_cache.reset();
+}
+
+TEST_F(LRUSecondaryCacheTest, FullCapacityTest) {
  LRUCacheOptions opts(1024, 0, /*_strict_capacity_limit=*/true, 0.5, nullptr,
                       kDefaultToAdaptiveMutex, kDontChargeCacheMetadata);
  std::shared_ptr<TestSecondaryCache> secondary_cache =
@@ -674,28 +620,28 @@ TEST_F(LRUCacheSecondaryCacheTest, FullCapacityTest) {
  Random rnd(301);
  std::string str1 = rnd.RandomString(1020);
  TestItem* item1 = new TestItem(str1.data(), str1.length());
-  ASSERT_OK(cache->Insert("k1", item1, &LRUCacheSecondaryCacheTest::helper_,
+  ASSERT_OK(cache->Insert("k1", item1, &LRUSecondaryCacheTest::helper_,
                          str1.length()));
  std::string str2 = rnd.RandomString(1020);
  TestItem* item2 = new TestItem(str2.data(), str2.length());
  // k1 should be demoted to NVM
-  ASSERT_OK(cache->Insert("k2", item2, &LRUCacheSecondaryCacheTest::helper_,
+  ASSERT_OK(cache->Insert("k2", item2, &LRUSecondaryCacheTest::helper_,
                          str2.length()));

  Cache::Handle* handle;
-  handle = cache->Lookup("k2", &LRUCacheSecondaryCacheTest::helper_,
+  handle = cache->Lookup("k2", &LRUSecondaryCacheTest::helper_,
                         test_item_creator, Cache::Priority::LOW, true);
  ASSERT_NE(handle, nullptr);
  // k1 promotion should fail due to the block cache being at capacity,
  // but the lookup should still succeed
  Cache::Handle* handle2;
-  handle2 = cache->Lookup("k1", &LRUCacheSecondaryCacheTest::helper_,
+  handle2 = cache->Lookup("k1", &LRUSecondaryCacheTest::helper_,
                          test_item_creator, Cache::Priority::LOW, true);
  ASSERT_NE(handle2, nullptr);
  // Since k1 didn't get inserted, k2 should still be in cache
  cache->Release(handle);
  cache->Release(handle2);
-  handle = cache->Lookup("k2", &LRUCacheSecondaryCacheTest::helper_,
+  handle = cache->Lookup("k2", &LRUSecondaryCacheTest::helper_,
                         test_item_creator, Cache::Priority::LOW, true);
  ASSERT_NE(handle, nullptr);
  cache->Release(handle);
@@ -1097,7 +1043,7 @@ TEST_F(DBSecondaryCacheTest, SecondaryCacheFailureTest) {
  Destroy(options);
 }

-TEST_F(LRUCacheSecondaryCacheTest, BasicWaitAllTest) {
+TEST_F(LRUSecondaryCacheTest, BasicWaitAllTest) {
  LRUCacheOptions opts(1024, 2, false, 0.5, nullptr, kDefaultToAdaptiveMutex,
                       kDontChargeCacheMetadata);
  std::shared_ptr<TestSecondaryCache> secondary_cache =
@@ -1113,8 +1059,7 @@ TEST_F(LRUCacheSecondaryCacheTest, BasicWaitAllTest) {
    values.emplace_back(str);
    TestItem* item = new TestItem(str.data(), str.length());
    ASSERT_OK(cache->Insert("k" + std::to_string(i), item,
-                            &LRUCacheSecondaryCacheTest::helper_,
-                            str.length()));
+                            &LRUSecondaryCacheTest::helper_, str.length()));
  }
  // Force all entries to be evicted to the secondary cache
  cache->SetCapacity(0);
@@ -1127,9 +1072,9 @@ TEST_F(LRUCacheSecondaryCacheTest, BasicWaitAllTest) {
       {"k5", TestSecondaryCache::ResultType::FAIL}});
  std::vector<Cache::Handle*> results;
  for (int i = 0; i < 6; ++i) {
-    results.emplace_back(cache->Lookup(
-        "k" + std::to_string(i), &LRUCacheSecondaryCacheTest::helper_,
-        test_item_creator, Cache::Priority::LOW, false));
+    results.emplace_back(
+        cache->Lookup("k" + std::to_string(i), &LRUSecondaryCacheTest::helper_,
+                      test_item_creator, Cache::Priority::LOW, false));
  }
  cache->WaitAll(results);
  for (int i = 0; i < 6; ++i) {
@@ -104,15 +104,14 @@ bool ShardedCache::Ref(Handle* handle) {
  return GetShard(Shard(hash))->Ref(handle);
 }

-bool ShardedCache::Release(Handle* handle, bool erase_if_last_ref) {
+bool ShardedCache::Release(Handle* handle, bool force_erase) {
  uint32_t hash = GetHash(handle);
-  return GetShard(Shard(hash))->Release(handle, erase_if_last_ref);
+  return GetShard(Shard(hash))->Release(handle, force_erase);
 }

-bool ShardedCache::Release(Handle* handle, bool useful,
-                           bool erase_if_last_ref) {
+bool ShardedCache::Release(Handle* handle, bool useful, bool force_erase) {
  uint32_t hash = GetHash(handle);
-  return GetShard(Shard(hash))->Release(handle, useful, erase_if_last_ref);
+  return GetShard(Shard(hash))->Release(handle, useful, force_erase);
 }

 void ShardedCache::Erase(const Slice& key) {
@@ -37,11 +37,11 @@ class CacheShard {
                                Cache::Priority priority, bool wait,
                                Statistics* stats) = 0;
  virtual bool Release(Cache::Handle* handle, bool useful,
-                       bool erase_if_last_ref) = 0;
+                       bool force_erase) = 0;
  virtual bool IsReady(Cache::Handle* handle) = 0;
  virtual void Wait(Cache::Handle* handle) = 0;
  virtual bool Ref(Cache::Handle* handle) = 0;
-  virtual bool Release(Cache::Handle* handle, bool erase_if_last_ref) = 0;
+  virtual bool Release(Cache::Handle* handle, bool force_erase) = 0;
  virtual void Erase(const Slice& key, uint32_t hash) = 0;
  virtual void SetCapacity(size_t capacity) = 0;
  virtual void SetStrictCapacityLimit(bool strict_capacity_limit) = 0;
@@ -94,11 +94,11 @@ class ShardedCache : public Cache {
                         const CreateCallback& create_cb, Priority priority,
                         bool wait, Statistics* stats = nullptr) override;
  virtual bool Release(Handle* handle, bool useful,
-                       bool erase_if_last_ref = false) override;
+                       bool force_erase = false) override;
  virtual bool IsReady(Handle* handle) override;
  virtual void Wait(Handle* handle) override;
  virtual bool Ref(Handle* handle) override;
-  virtual bool Release(Handle* handle, bool erase_if_last_ref = false) override;
+  virtual bool Release(Handle* handle, bool force_erase = false) override;
  virtual void Erase(const Slice& key) override;
  virtual uint64_t NewId() override;
  virtual size_t GetCapacity() const override;
@@ -1,26 +0,0 @@
-# - Find liburing
-#
-# uring_INCLUDE_DIR - Where to find liburing.h
-# uring_LIBRARIES - List of libraries when using uring.
-# uring_FOUND - True if uring found.
-
-find_path(uring_INCLUDE_DIR
-  NAMES liburing.h)
-find_library(uring_LIBRARIES
-  NAMES liburing.a liburing)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(uring
-  DEFAULT_MSG uring_LIBRARIES uring_INCLUDE_DIR)
-
-mark_as_advanced(
-  uring_INCLUDE_DIR
-  uring_LIBRARIES)
-
-if(uring_FOUND AND NOT TARGET uring::uring)
-  add_library(uring::uring UNKNOWN IMPORTED)
-  set_target_properties(uring::uring PROPERTIES
-    INTERFACE_INCLUDE_DIRECTORIES "${uring_INCLUDE_DIR}"
-    IMPORTED_LINK_INTERFACE_LANGUAGES "C"
-    IMPORTED_LOCATION "${uring_LIBRARIES}")
-endif()
@@ -1,30 +0,0 @@
-ifndef PYTHON
-
-# Default to python3. Some distros like CentOS 8 do not have `python`.
-ifeq ($(origin PYTHON), undefined)
-	PYTHON := $(shell which python3 || which python || echo python3)
-endif
-export PYTHON
-
-endif
-
-# To setup tmp directory, first recognize some old variables for setting
-# test tmp directory or base tmp directory. TEST_TMPDIR is usually read
-# by RocksDB tools though Env/FileSystem::GetTestDirectory.
-ifeq ($(TEST_TMPDIR),)
-TEST_TMPDIR := $(TMPD)
-endif
-ifeq ($(TEST_TMPDIR),)
-ifeq ($(BASE_TMPDIR),)
-BASE_TMPDIR :=$(TMPDIR)
-endif
-ifeq ($(BASE_TMPDIR),)
-BASE_TMPDIR :=/tmp
-endif
-# Use /dev/shm if it has the sticky bit set (otherwise, /tmp or other
-# base dir), and create a randomly-named rocksdb.XXXX directory therein.
-TEST_TMPDIR := $(shell f=/dev/shm; test -k $$f || f=$(BASE_TMPDIR); \
-  perl -le 'use File::Temp "tempdir";'	                            \
-    -e 'print tempdir("'$$f'/rocksdb.XXXX", CLEANUP => 0)')
-endif
-export TEST_TMPDIR
@@ -12,7 +12,7 @@ fi
 ROOT=".."
 # Fetch right version of gcov
 if [ -d /mnt/gvfs/third-party -a -z "$CXX" ]; then
-  source $ROOT/build_tools/fbcode_config_platform009.sh
+  source $ROOT/build_tools/fbcode_config_platform007.sh
  GCOV=$GCC_BASE/bin/gcov
 else
  GCOV=$(which gcov)
@@ -1,93 +0,0 @@
-# This file is used by Meta-internal infrastructure as well as by Makefile
-
-# When included from Makefile, there are rules to build DB_STRESS_CMD. When
-# used directly with `make -f crashtest.mk ...` there will be no rules to
-# build DB_STRESS_CMD so it must exist prior.
-DB_STRESS_CMD?=./db_stress
-
-include common.mk
-
-CRASHTEST_MAKE=$(MAKE) -f crash_test.mk
-CRASHTEST_PY=$(PYTHON) -u tools/db_crashtest.py --stress_cmd=$(DB_STRESS_CMD)
-
-.PHONY: crash_test crash_test_with_atomic_flush crash_test_with_txn \
-	crash_test_with_best_efforts_recovery crash_test_with_ts \
-	blackbox_crash_test blackbox_crash_test_with_atomic_flush \
-	blackbox_crash_test_with_txn blackbox_crash_test_with_ts \
-	blackbox_crash_test_with_best_efforts_recovery \
-	whitebox_crash_test whitebox_crash_test_with_atomic_flush \
-	whitebox_crash_test_with_txn whitebox_crash_test_with_ts \
-	blackbox_crash_test_with_multiops_wc_txn \
-	blackbox_crash_test_with_multiops_wp_txn
-
-crash_test: $(DB_STRESS_CMD)
-# Do not parallelize
-	$(CRASHTEST_MAKE) whitebox_crash_test
-	$(CRASHTEST_MAKE) blackbox_crash_test
-
-crash_test_with_atomic_flush: $(DB_STRESS_CMD)
-# Do not parallelize
-	$(CRASHTEST_MAKE) whitebox_crash_test_with_atomic_flush
-	$(CRASHTEST_MAKE) blackbox_crash_test_with_atomic_flush
-
-crash_test_with_txn: $(DB_STRESS_CMD)
-# Do not parallelize
-	$(CRASHTEST_MAKE) whitebox_crash_test_with_txn
-	$(CRASHTEST_MAKE) blackbox_crash_test_with_txn
-
-crash_test_with_best_efforts_recovery: blackbox_crash_test_with_best_efforts_recovery
-
-crash_test_with_ts: $(DB_STRESS_CMD)
-# Do not parallelize
-	$(CRASHTEST_MAKE) whitebox_crash_test_with_ts
-	$(CRASHTEST_MAKE) blackbox_crash_test_with_ts
-
-crash_test_with_multiops_wc_txn: $(DB_STRESS_CMD)
-	$(CRASHTEST_MAKE) blackbox_crash_test_with_multiops_wc_txn
-
-crash_test_with_multiops_wp_txn: $(DB_STRESS_CMD)
-	$(CRASHTEST_MAKE) blackbox_crash_test_with_multiops_wp_txn
-
-blackbox_crash_test: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --simple blackbox $(CRASH_TEST_EXT_ARGS)
-	$(CRASHTEST_PY) blackbox $(CRASH_TEST_EXT_ARGS)
-
-blackbox_crash_test_with_atomic_flush: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --cf_consistency blackbox $(CRASH_TEST_EXT_ARGS)
-
-blackbox_crash_test_with_txn: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --txn blackbox $(CRASH_TEST_EXT_ARGS)
-
-blackbox_crash_test_with_best_efforts_recovery: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --test_best_efforts_recovery blackbox $(CRASH_TEST_EXT_ARGS)
-
-blackbox_crash_test_with_ts: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --enable_ts blackbox $(CRASH_TEST_EXT_ARGS)
-
-blackbox_crash_test_with_multiops_wc_txn: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --test_multiops_txn --write_policy write_committed blackbox $(CRASH_TEST_EXT_ARGS)
-
-blackbox_crash_test_with_multiops_wp_txn: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --test_multiops_txn --write_policy write_prepared blackbox $(CRASH_TEST_EXT_ARGS)
-
-ifeq ($(CRASH_TEST_KILL_ODD),)
-  CRASH_TEST_KILL_ODD=888887
-endif
-
-whitebox_crash_test: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --simple whitebox --random_kill_odd \
-      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
-	$(CRASHTEST_PY) whitebox  --random_kill_odd \
-      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
-
-whitebox_crash_test_with_atomic_flush: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --cf_consistency whitebox  --random_kill_odd \
-      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
-
-whitebox_crash_test_with_txn: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --txn whitebox --random_kill_odd \
-      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
-
-whitebox_crash_test_with_ts: $(DB_STRESS_CMD)
-	$(CRASHTEST_PY) --enable_ts whitebox --random_kill_odd \
-      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
@@ -23,7 +23,7 @@ Status ArenaWrappedDBIter::GetProperty(std::string prop_name,
  if (prop_name == "rocksdb.iterator.super-version-number") {
    // First try to pass the value returned from inner iterator.
    if (!db_iter_->GetProperty(prop_name, prop).ok()) {
-      *prop = std::to_string(sv_number_);
+      *prop = ToString(sv_number_);
    }
    return Status::OK();
  }
@@ -58,55 +58,30 @@ Status ArenaWrappedDBIter::Refresh() {
  uint64_t cur_sv_number = cfd_->GetSuperVersionNumber();
  TEST_SYNC_POINT("ArenaWrappedDBIter::Refresh:1");
  TEST_SYNC_POINT("ArenaWrappedDBIter::Refresh:2");
-  while (true) {
-    if (sv_number_ != cur_sv_number) {
-      Env* env = db_iter_->env();
-      db_iter_->~DBIter();
-      arena_.~Arena();
-      new (&arena_) Arena();
+  if (sv_number_ != cur_sv_number) {
+    Env* env = db_iter_->env();
+    db_iter_->~DBIter();
+    arena_.~Arena();
+    new (&arena_) Arena();

-      SuperVersion* sv = cfd_->GetReferencedSuperVersion(db_impl_);
-      SequenceNumber latest_seq = db_impl_->GetLatestSequenceNumber();
-      if (read_callback_) {
-        read_callback_->Refresh(latest_seq);
-      }
-      Init(env, read_options_, *(cfd_->ioptions()), sv->mutable_cf_options,
-           sv->current, latest_seq,
-           sv->mutable_cf_options.max_sequential_skip_in_iterations,
-           cur_sv_number, read_callback_, db_impl_, cfd_, expose_blob_index_,
-           allow_refresh_);
-
-      InternalIterator* internal_iter = db_impl_->NewInternalIterator(
-          read_options_, cfd_, sv, &arena_, db_iter_->GetRangeDelAggregator(),
-          latest_seq, /* allow_unprepared_value */ true);
-      SetIterUnderDBIter(internal_iter);
-      break;
-    } else {
-      SequenceNumber latest_seq = db_impl_->GetLatestSequenceNumber();
-      // Refresh range-tombstones in MemTable
-      if (!read_options_.ignore_range_deletions) {
-        SuperVersion* sv = cfd_->GetThreadLocalSuperVersion(db_impl_);
-        ReadRangeDelAggregator* range_del_agg =
-            db_iter_->GetRangeDelAggregator();
-        std::unique_ptr<FragmentedRangeTombstoneIterator> range_del_iter;
-        range_del_iter.reset(
-            sv->mem->NewRangeTombstoneIterator(read_options_, latest_seq));
-        range_del_agg->AddTombstones(std::move(range_del_iter));
-        cfd_->ReturnThreadLocalSuperVersion(sv);
-      }
-      // Refresh latest sequence number
-      db_iter_->set_sequence(latest_seq);
-      db_iter_->set_valid(false);
-      // Check again if the latest super version number is changed
-      uint64_t latest_sv_number = cfd_->GetSuperVersionNumber();
-      if (latest_sv_number != cur_sv_number) {
-        // If the super version number is changed after refreshing,
-        // fallback to Re-Init the InternalIterator
-        cur_sv_number = latest_sv_number;
-        continue;
-      }
-      break;
+    SuperVersion* sv = cfd_->GetReferencedSuperVersion(db_impl_);
+    SequenceNumber latest_seq = db_impl_->GetLatestSequenceNumber();
+    if (read_callback_) {
+      read_callback_->Refresh(latest_seq);
    }
+    Init(env, read_options_, *(cfd_->ioptions()), sv->mutable_cf_options,
+         sv->current, latest_seq,
+         sv->mutable_cf_options.max_sequential_skip_in_iterations,
+         cur_sv_number, read_callback_, db_impl_, cfd_, expose_blob_index_,
+         allow_refresh_);
+
+    InternalIterator* internal_iter = db_impl_->NewInternalIterator(
+        read_options_, cfd_, sv, &arena_, db_iter_->GetRangeDelAggregator(),
+        latest_seq, /* allow_unprepared_value */ true);
+    SetIterUnderDBIter(internal_iter);
+  } else {
+    db_iter_->set_sequence(db_impl_->GetLatestSequenceNumber());
+    db_iter_->set_valid(false);
  }
  return Status::OK();
 }
@@ -148,10 +148,9 @@ Status BlobFileReader::ReadHeader(const RandomAccessFileReader* file_reader,
    constexpr uint64_t read_offset = 0;
    constexpr size_t read_size = BlobLogHeader::kSize;

-    // TODO: rate limit reading headers from blob files.
-    const Status s = ReadFromFile(file_reader, read_offset, read_size,
-                                  statistics, &header_slice, &buf, &aligned_buf,
-                                  Env::IO_TOTAL /* rate_limiter_priority */);
+    const Status s =
+        ReadFromFile(file_reader, read_offset, read_size, statistics,
+                     &header_slice, &buf, &aligned_buf);
    if (!s.ok()) {
      return s;
    }
@@ -199,10 +198,9 @@ Status BlobFileReader::ReadFooter(const RandomAccessFileReader* file_reader,
    const uint64_t read_offset = file_size - BlobLogFooter::kSize;
    constexpr size_t read_size = BlobLogFooter::kSize;

-    // TODO: rate limit reading footers from blob files.
-    const Status s = ReadFromFile(file_reader, read_offset, read_size,
-                                  statistics, &footer_slice, &buf, &aligned_buf,
-                                  Env::IO_TOTAL /* rate_limiter_priority */);
+    const Status s =
+        ReadFromFile(file_reader, read_offset, read_size, statistics,
+                     &footer_slice, &buf, &aligned_buf);
    if (!s.ok()) {
      return s;
    }
@@ -232,8 +230,7 @@ Status BlobFileReader::ReadFooter(const RandomAccessFileReader* file_reader,
 Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
                                    uint64_t read_offset, size_t read_size,
                                    Statistics* statistics, Slice* slice,
-                                    Buffer* buf, AlignedBuf* aligned_buf,
-                                    Env::IOPriority rate_limiter_priority) {
+                                    Buffer* buf, AlignedBuf* aligned_buf) {
  assert(slice);
  assert(buf);
  assert(aligned_buf);
@@ -248,13 +245,13 @@ Status BlobFileReader::ReadFromFile(const RandomAccessFileReader* file_reader,
    constexpr char* scratch = nullptr;

    s = file_reader->Read(IOOptions(), read_offset, read_size, slice, scratch,
-                          aligned_buf, rate_limiter_priority);
+                          aligned_buf);
  } else {
    buf->reset(new char[read_size]);
    constexpr AlignedBuf* aligned_scratch = nullptr;

    s = file_reader->Read(IOOptions(), read_offset, read_size, slice,
-                          buf->get(), aligned_scratch, rate_limiter_priority);
+                          buf->get(), aligned_scratch);
  }

  if (!s.ok()) {
@@ -326,8 +323,7 @@ Status BlobFileReader::GetBlob(const ReadOptions& read_options,

    prefetched = prefetch_buffer->TryReadFromCache(
        IOOptions(), file_reader_.get(), record_offset,
-        static_cast<size_t>(record_size), &record_slice, &s,
-        read_options.rate_limiter_priority, for_compaction);
+        static_cast<size_t>(record_size), &record_slice, &s, for_compaction);
    if (!s.ok()) {
      return s;
    }
@@ -338,8 +334,7 @@ Status BlobFileReader::GetBlob(const ReadOptions& read_options,

    const Status s = ReadFromFile(file_reader_.get(), record_offset,
                                  static_cast<size_t>(record_size), statistics_,
-                                  &record_slice, &buf, &aligned_buf,
-                                  read_options.rate_limiter_priority);
+                                  &record_slice, &buf, &aligned_buf);
    if (!s.ok()) {
      return s;
    }
@@ -429,8 +424,7 @@ void BlobFileReader::MultiGetBlob(
  }
  TEST_SYNC_POINT("BlobFileReader::MultiGetBlob:ReadFromFile");
  s = file_reader_->MultiRead(IOOptions(), read_reqs.data(), read_reqs.size(),
-                              direct_io ? &aligned_buf : nullptr,
-                              read_options.rate_limiter_priority);
+                              direct_io ? &aligned_buf : nullptr);
  if (!s.ok()) {
    for (auto& req : read_reqs) {
      req.status.PermitUncheckedError();
@@ -83,8 +83,7 @@ class BlobFileReader {
  static Status ReadFromFile(const RandomAccessFileReader* file_reader,
                             uint64_t read_offset, size_t read_size,
                             Statistics* statistics, Slice* slice, Buffer* buf,
-                             AlignedBuf* aligned_buf,
-                             Env::IOPriority rate_limiter_priority);
+                             AlignedBuf* aligned_buf);

  static Status VerifyBlob(const Slice& record_slice, const Slice& user_key,
                           uint64_t value_size);
@@ -96,9 +96,9 @@ class BlobIndex {
    assert(slice.size() > 0);
    type_ = static_cast<Type>(*slice.data());
    if (type_ >= Type::kUnknown) {
-      return Status::Corruption(kErrorMessage,
-                                "Unknown blob index type: " +
-                                    std::to_string(static_cast<char>(type_)));
+      return Status::Corruption(
+          kErrorMessage,
+          "Unknown blob index type: " + ToString(static_cast<char>(type_)));
    }
    slice = Slice(slice.data() + 1, slice.size() - 1);
    if (HasTTL()) {
@@ -28,10 +28,8 @@ Status BlobLogSequentialReader::ReadSlice(uint64_t size, Slice* slice,
  assert(file_);

  StopWatch read_sw(clock_, statistics_, BLOB_DB_BLOB_FILE_READ_MICROS);
-  // TODO: rate limit `BlobLogSequentialReader` reads (it appears unused?)
-  Status s =
-      file_->Read(IOOptions(), next_byte_, static_cast<size_t>(size), slice,
-                  buf, nullptr, Env::IO_TOTAL /* rate_limiter_priority */);
+  Status s = file_->Read(IOOptions(), next_byte_, static_cast<size_t>(size),
+                         slice, buf, nullptr);
  next_byte_ += size;
  if (!s.ok()) {
    return s;
@@ -1,169 +0,0 @@
-//  Copyright (c) Meta Platforms, Inc. and affiliates.
-//  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/blob/blob_source.h"
-
-#include <cassert>
-#include <string>
-
-#include "db/blob/blob_file_reader.h"
-#include "options/cf_options.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-BlobSource::BlobSource(const ImmutableOptions* immutable_options,
-                       const std::string& db_id,
-                       const std::string& db_session_id,
-                       BlobFileCache* blob_file_cache)
-    : db_id_(db_id),
-      db_session_id_(db_session_id),
-      statistics_(immutable_options->statistics.get()),
-      blob_file_cache_(blob_file_cache),
-      blob_cache_(immutable_options->blob_cache) {}
-
-BlobSource::~BlobSource() = default;
-
-Status BlobSource::GetBlobFromCache(const Slice& cache_key,
-                                    CachableEntry<std::string>* blob) const {
-  assert(blob);
-  assert(blob->IsEmpty());
-  assert(blob_cache_);
-  assert(!cache_key.empty());
-
-  Cache::Handle* cache_handle = nullptr;
-  cache_handle = GetEntryFromCache(cache_key);
-  if (cache_handle != nullptr) {
-    blob->SetCachedValue(
-        static_cast<std::string*>(blob_cache_->Value(cache_handle)),
-        blob_cache_.get(), cache_handle);
-    return Status::OK();
-  }
-
-  assert(blob->IsEmpty());
-
-  return Status::NotFound("Blob not found in cache");
-}
-
-Status BlobSource::PutBlobIntoCache(const Slice& cache_key,
-                                    CachableEntry<std::string>* cached_blob,
-                                    PinnableSlice* blob) const {
-  assert(blob);
-  assert(!cache_key.empty());
-  assert(blob_cache_);
-
-  Status s;
-  const Cache::Priority priority = Cache::Priority::LOW;
-
-  // Objects to be put into the cache have to be heap-allocated and
-  // self-contained, i.e. own their contents. The Cache has to be able to take
-  // unique ownership of them. Therefore, we copy the blob into a string
-  // directly, and insert that into the cache.
-  std::string* buf = new std::string();
-  buf->assign(blob->data(), blob->size());
-
-  // TODO: support custom allocators and provide a better estimated memory
-  // usage using malloc_usable_size.
-  Cache::Handle* cache_handle = nullptr;
-  s = InsertEntryIntoCache(cache_key, buf, buf->size(), &cache_handle,
-                           priority);
-  if (s.ok()) {
-    assert(cache_handle != nullptr);
-    cached_blob->SetCachedValue(buf, blob_cache_.get(), cache_handle);
-  }
-
-  return s;
-}
-
-Status BlobSource::GetBlob(const ReadOptions& read_options,
-                           const Slice& user_key, uint64_t file_number,
-                           uint64_t offset, uint64_t file_size,
-                           uint64_t value_size,
-                           CompressionType compression_type,
-                           FilePrefetchBuffer* prefetch_buffer,
-                           PinnableSlice* value, uint64_t* bytes_read) {
-  assert(value);
-
-  Status s;
-
-  const CacheKey cache_key = GetCacheKey(file_number, file_size, offset);
-
-  CachableEntry<std::string> blob_entry;
-
-  // First, try to get the blob from the cache
-  //
-  // If blob cache is enabled, we'll try to read from it.
-  if (blob_cache_) {
-    Slice key = cache_key.AsSlice();
-    s = GetBlobFromCache(key, &blob_entry);
-    if (s.ok() && blob_entry.GetValue()) {
-      assert(blob_entry.GetValue()->size() == value_size);
-      if (bytes_read) {
-        *bytes_read = value_size;
-      }
-      value->PinSelf(*blob_entry.GetValue());
-      return s;
-    }
-  }
-
-  assert(blob_entry.IsEmpty());
-
-  const bool no_io = read_options.read_tier == kBlockCacheTier;
-  if (no_io) {
-    return Status::Incomplete("Cannot read blob(s): no disk I/O allowed");
-  }
-
-  // Can't find the blob from the cache. Since I/O is allowed, read from the
-  // file.
-  {
-    CacheHandleGuard<BlobFileReader> blob_file_reader;
-    s = blob_file_cache_->GetBlobFileReader(file_number, &blob_file_reader);
-    if (!s.ok()) {
-      return s;
-    }
-
-    assert(blob_file_reader.GetValue());
-
-    if (compression_type != blob_file_reader.GetValue()->GetCompressionType()) {
-      return Status::Corruption("Compression type mismatch when reading blob");
-    }
-
-    s = blob_file_reader.GetValue()->GetBlob(
-        read_options, user_key, offset, value_size, compression_type,
-        prefetch_buffer, value, bytes_read);
-    if (!s.ok()) {
-      return s;
-    }
-  }
-
-  if (blob_cache_ && read_options.fill_cache) {
-    // If filling cache is allowed and a cache is configured, try to put the
-    // blob to the cache.
-    Slice key = cache_key.AsSlice();
-    s = PutBlobIntoCache(key, &blob_entry, value);
-    if (!s.ok()) {
-      return s;
-    }
-  }
-
-  assert(s.ok());
-  return s;
-}
-
-bool BlobSource::TEST_BlobInCache(uint64_t file_number, uint64_t file_size,
-                                  uint64_t offset) const {
-  const CacheKey cache_key = GetCacheKey(file_number, file_size, offset);
-  const Slice key = cache_key.AsSlice();
-
-  CachableEntry<std::string> blob_entry;
-  const Status s = GetBlobFromCache(key, &blob_entry);
-
-  if (s.ok() && blob_entry.GetValue() != nullptr) {
-    return true;
-  }
-
-  return false;
-}
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,88 +0,0 @@
-//  Copyright (c) Meta Platforms, Inc. and affiliates.
-//  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 <cinttypes>
-
-#include "cache/cache_helpers.h"
-#include "cache/cache_key.h"
-#include "db/blob/blob_file_cache.h"
-#include "rocksdb/cache.h"
-#include "rocksdb/rocksdb_namespace.h"
-#include "table/block_based/cachable_entry.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-struct ImmutableOptions;
-class Status;
-class FilePrefetchBuffer;
-class Slice;
-
-// BlobSource is a class that provides universal access to blobs, regardless of
-// whether they are in the blob cache, secondary cache, or (remote) storage.
-// Depending on user settings, it always fetch blobs from multi-tier cache and
-// storage with minimal cost.
-class BlobSource {
- public:
-  BlobSource(const ImmutableOptions* immutable_options,
-             const std::string& db_id, const std::string& db_session_id,
-             BlobFileCache* blob_file_cache);
-
-  BlobSource(const BlobSource&) = delete;
-  BlobSource& operator=(const BlobSource&) = delete;
-
-  ~BlobSource();
-
-  Status GetBlob(const ReadOptions& read_options, const Slice& user_key,
-                 uint64_t file_number, uint64_t offset, uint64_t file_size,
-                 uint64_t value_size, CompressionType compression_type,
-                 FilePrefetchBuffer* prefetch_buffer, PinnableSlice* value,
-                 uint64_t* bytes_read);
-
-  bool TEST_BlobInCache(uint64_t file_number, uint64_t file_size,
-                        uint64_t offset) const;
-
- private:
-  Status GetBlobFromCache(const Slice& cache_key,
-                          CachableEntry<std::string>* blob) const;
-
-  Status PutBlobIntoCache(const Slice& cache_key,
-                          CachableEntry<std::string>* cached_blob,
-                          PinnableSlice* blob) const;
-
-  inline CacheKey GetCacheKey(uint64_t file_number, uint64_t file_size,
-                              uint64_t offset) const {
-    OffsetableCacheKey base_cache_key(db_id_, db_session_id_, file_number,
-                                      file_size);
-    return base_cache_key.WithOffset(offset);
-  }
-
-  inline Cache::Handle* GetEntryFromCache(const Slice& key) const {
-    return blob_cache_->Lookup(key, statistics_);
-  }
-
-  inline Status InsertEntryIntoCache(const Slice& key, std::string* value,
-                                     size_t charge,
-                                     Cache::Handle** cache_handle,
-                                     Cache::Priority priority) const {
-    return blob_cache_->Insert(key, value, charge,
-                               &DeleteCacheEntry<std::string>, cache_handle,
-                               priority);
-  }
-
-  const std::string db_id_;
-  const std::string db_session_id_;
-
-  Statistics* statistics_;
-
-  // A cache to store blob file reader.
-  BlobFileCache* blob_file_cache_;
-
-  // A cache to store uncompressed blobs.
-  std::shared_ptr<Cache> blob_cache_;
-};
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,298 +0,0 @@
-//  Copyright (c) Meta Platforms, Inc. and affiliates.
-//  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/blob/blob_source.h"
-
-#include <cassert>
-#include <cstdint>
-#include <cstdio>
-#include <memory>
-#include <string>
-
-#include "db/blob/blob_file_cache.h"
-#include "db/blob/blob_log_format.h"
-#include "db/blob/blob_log_writer.h"
-#include "db/db_test_util.h"
-#include "file/filename.h"
-#include "file/read_write_util.h"
-#include "options/cf_options.h"
-#include "rocksdb/options.h"
-#include "util/compression.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-namespace {
-
-// Creates a test blob file with `num` blobs in it.
-void WriteBlobFile(const ImmutableOptions& immutable_options,
-                   uint32_t column_family_id, bool has_ttl,
-                   const ExpirationRange& expiration_range_header,
-                   const ExpirationRange& expiration_range_footer,
-                   uint64_t blob_file_number, const std::vector<Slice>& keys,
-                   const std::vector<Slice>& blobs, CompressionType compression,
-                   std::vector<uint64_t>& blob_offsets,
-                   std::vector<uint64_t>& blob_sizes) {
-  assert(!immutable_options.cf_paths.empty());
-  size_t num = keys.size();
-  assert(num == blobs.size());
-  assert(num == blob_offsets.size());
-  assert(num == blob_sizes.size());
-
-  const std::string blob_file_path =
-      BlobFileName(immutable_options.cf_paths.front().path, blob_file_number);
-  std::unique_ptr<FSWritableFile> file;
-  ASSERT_OK(NewWritableFile(immutable_options.fs.get(), blob_file_path, &file,
-                            FileOptions()));
-
-  std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
-      std::move(file), blob_file_path, FileOptions(), immutable_options.clock));
-
-  constexpr Statistics* statistics = nullptr;
-  constexpr bool use_fsync = false;
-  constexpr bool do_flush = false;
-
-  BlobLogWriter blob_log_writer(std::move(file_writer), immutable_options.clock,
-                                statistics, blob_file_number, use_fsync,
-                                do_flush);
-
-  BlobLogHeader header(column_family_id, compression, has_ttl,
-                       expiration_range_header);
-
-  ASSERT_OK(blob_log_writer.WriteHeader(header));
-
-  std::vector<std::string> compressed_blobs(num);
-  std::vector<Slice> blobs_to_write(num);
-  if (kNoCompression == compression) {
-    for (size_t i = 0; i < num; ++i) {
-      blobs_to_write[i] = blobs[i];
-      blob_sizes[i] = blobs[i].size();
-    }
-  } else {
-    CompressionOptions opts;
-    CompressionContext context(compression);
-    constexpr uint64_t sample_for_compression = 0;
-    CompressionInfo info(opts, context, CompressionDict::GetEmptyDict(),
-                         compression, sample_for_compression);
-
-    constexpr uint32_t compression_format_version = 2;
-
-    for (size_t i = 0; i < num; ++i) {
-      ASSERT_TRUE(CompressData(blobs[i], info, compression_format_version,
-                               &compressed_blobs[i]));
-      blobs_to_write[i] = compressed_blobs[i];
-      blob_sizes[i] = compressed_blobs[i].size();
-    }
-  }
-
-  for (size_t i = 0; i < num; ++i) {
-    uint64_t key_offset = 0;
-    ASSERT_OK(blob_log_writer.AddRecord(keys[i], blobs_to_write[i], &key_offset,
-                                        &blob_offsets[i]));
-  }
-
-  BlobLogFooter footer;
-  footer.blob_count = num;
-  footer.expiration_range = expiration_range_footer;
-
-  std::string checksum_method;
-  std::string checksum_value;
-  ASSERT_OK(
-      blob_log_writer.AppendFooter(footer, &checksum_method, &checksum_value));
-}
-
-}  // anonymous namespace
-
-class BlobSourceTest : public DBTestBase {
- protected:
- public:
-  explicit BlobSourceTest()
-      : DBTestBase("blob_source_test", /*env_do_fsync=*/true) {}
-};
-
-TEST_F(BlobSourceTest, GetBlobsFromCache) {
-  Options options;
-  options.env = env_;
-  options.cf_paths.emplace_back(
-      test::PerThreadDBPath(env_, "BlobSourceTest_GetBlobsFromCache"), 0);
-  options.enable_blob_files = true;
-
-  LRUCacheOptions co;
-  co.capacity = 2048;
-  co.num_shard_bits = 2;
-  co.metadata_charge_policy = kDontChargeCacheMetadata;
-  options.blob_cache = NewLRUCache(co);
-  options.lowest_used_cache_tier = CacheTier::kVolatileTier;
-
-  Reopen(options);
-
-  std::string db_id;
-  ASSERT_OK(db_->GetDbIdentity(db_id));
-
-  std::string db_session_id;
-  ASSERT_OK(db_->GetDbSessionId(db_session_id));
-
-  ImmutableOptions immutable_options(options);
-
-  constexpr uint32_t column_family_id = 1;
-  constexpr bool has_ttl = false;
-  constexpr ExpirationRange expiration_range;
-  constexpr uint64_t blob_file_number = 1;
-  constexpr size_t num_blobs = 16;
-
-  std::vector<std::string> key_strs;
-  std::vector<std::string> blob_strs;
-
-  for (size_t i = 0; i < num_blobs; ++i) {
-    key_strs.push_back("key" + std::to_string(i));
-    blob_strs.push_back("blob" + std::to_string(i));
-  }
-
-  std::vector<Slice> keys;
-  std::vector<Slice> blobs;
-
-  uint64_t file_size = BlobLogHeader::kSize;
-  for (size_t i = 0; i < num_blobs; ++i) {
-    keys.push_back({key_strs[i]});
-    blobs.push_back({blob_strs[i]});
-    file_size += BlobLogRecord::kHeaderSize + keys[i].size() + blobs[i].size();
-  }
-  file_size += BlobLogFooter::kSize;
-
-  std::vector<uint64_t> blob_offsets(keys.size());
-  std::vector<uint64_t> blob_sizes(keys.size());
-
-  WriteBlobFile(immutable_options, column_family_id, has_ttl, expiration_range,
-                expiration_range, blob_file_number, keys, blobs, kNoCompression,
-                blob_offsets, blob_sizes);
-
-  constexpr size_t capacity = 1024;
-  std::shared_ptr<Cache> backing_cache =
-      NewLRUCache(capacity);  // Blob file cache
-
-  FileOptions file_options;
-  constexpr HistogramImpl* blob_file_read_hist = nullptr;
-
-  std::unique_ptr<BlobFileCache> blob_file_cache(new BlobFileCache(
-      backing_cache.get(), &immutable_options, &file_options, column_family_id,
-      blob_file_read_hist, nullptr /*IOTracer*/));
-
-  BlobSource blob_source(&immutable_options, db_id, db_session_id,
-                         blob_file_cache.get());
-
-  ReadOptions read_options;
-  read_options.verify_checksums = true;
-
-  constexpr FilePrefetchBuffer* prefetch_buffer = nullptr;
-
-  {
-    // GetBlob
-    std::vector<PinnableSlice> values(keys.size());
-    uint64_t bytes_read = 0;
-
-    read_options.fill_cache = false;
-
-    for (size_t i = 0; i < num_blobs; ++i) {
-      ASSERT_FALSE(blob_source.TEST_BlobInCache(blob_file_number, file_size,
-                                                blob_offsets[i]));
-
-      ASSERT_OK(blob_source.GetBlob(read_options, keys[i], blob_file_number,
-                                    blob_offsets[i], file_size, blob_sizes[i],
-                                    kNoCompression, prefetch_buffer, &values[i],
-                                    &bytes_read));
-      ASSERT_EQ(values[i], blobs[i]);
-      ASSERT_EQ(bytes_read,
-                blob_sizes[i] + keys[i].size() + BlobLogRecord::kHeaderSize);
-
-      ASSERT_FALSE(blob_source.TEST_BlobInCache(blob_file_number, file_size,
-                                                blob_offsets[i]));
-    }
-
-    read_options.fill_cache = true;
-
-    for (size_t i = 0; i < num_blobs; ++i) {
-      ASSERT_FALSE(blob_source.TEST_BlobInCache(blob_file_number, file_size,
-                                                blob_offsets[i]));
-
-      ASSERT_OK(blob_source.GetBlob(read_options, keys[i], blob_file_number,
-                                    blob_offsets[i], file_size, blob_sizes[i],
-                                    kNoCompression, prefetch_buffer, &values[i],
-                                    &bytes_read));
-      ASSERT_EQ(values[i], blobs[i]);
-      ASSERT_EQ(bytes_read,
-                blob_sizes[i] + keys[i].size() + BlobLogRecord::kHeaderSize);
-
-      ASSERT_TRUE(blob_source.TEST_BlobInCache(blob_file_number, file_size,
-                                               blob_offsets[i]));
-    }
-
-    read_options.fill_cache = true;
-
-    for (size_t i = 0; i < num_blobs; ++i) {
-      ASSERT_TRUE(blob_source.TEST_BlobInCache(blob_file_number, file_size,
-                                               blob_offsets[i]));
-
-      ASSERT_OK(blob_source.GetBlob(read_options, keys[i], blob_file_number,
-                                    blob_offsets[i], file_size, blob_sizes[i],
-                                    kNoCompression, prefetch_buffer, &values[i],
-                                    &bytes_read));
-      ASSERT_EQ(values[i], blobs[i]);
-      ASSERT_EQ(bytes_read, blob_sizes[i]);
-
-      ASSERT_TRUE(blob_source.TEST_BlobInCache(blob_file_number, file_size,
-                                               blob_offsets[i]));
-    }
-
-    // Cache-only GetBlob
-    read_options.read_tier = ReadTier::kBlockCacheTier;
-
-    for (size_t i = 0; i < num_blobs; ++i) {
-      ASSERT_TRUE(blob_source.TEST_BlobInCache(blob_file_number, file_size,
-                                               blob_offsets[i]));
-
-      ASSERT_OK(blob_source.GetBlob(read_options, keys[i], blob_file_number,
-                                    blob_offsets[i], file_size, blob_sizes[i],
-                                    kNoCompression, prefetch_buffer, &values[i],
-                                    &bytes_read));
-      ASSERT_EQ(values[i], blobs[i]);
-      ASSERT_EQ(bytes_read, blob_sizes[i]);
-
-      ASSERT_TRUE(blob_source.TEST_BlobInCache(blob_file_number, file_size,
-                                               blob_offsets[i]));
-    }
-  }
-
-  options.blob_cache->EraseUnRefEntries();
-
-  {
-    // Cache-only GetBlob
-    std::vector<PinnableSlice> values(keys.size());
-    uint64_t bytes_read = 0;
-
-    read_options.read_tier = ReadTier::kBlockCacheTier;
-    read_options.fill_cache = true;
-
-    for (size_t i = 0; i < num_blobs; ++i) {
-      ASSERT_FALSE(blob_source.TEST_BlobInCache(blob_file_number, file_size,
-                                                blob_offsets[i]));
-
-      ASSERT_NOK(blob_source.GetBlob(read_options, keys[i], blob_file_number,
-                                     blob_offsets[i], file_size, blob_sizes[i],
-                                     kNoCompression, prefetch_buffer,
-                                     &values[i], &bytes_read));
-      ASSERT_TRUE(values[i].empty());
-      ASSERT_EQ(bytes_read, 0);
-
-      ASSERT_FALSE(blob_source.TEST_BlobInCache(blob_file_number, file_size,
-                                                blob_offsets[i]));
-    }
-  }
-}
-
-}  // namespace ROCKSDB_NAMESPACE
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
@@ -366,26 +366,19 @@ TEST_F(DBBlobBasicTest, GetBlob_CorruptIndex) {
  Reopen(options);

  constexpr char key[] = "key";
-  constexpr char blob[] = "blob";

-  ASSERT_OK(Put(key, blob));
+  // Fake a corrupt blob index.
+  const std::string blob_index("foobar");
+
+  WriteBatch batch;
+  ASSERT_OK(WriteBatchInternal::PutBlobIndex(&batch, 0, key, blob_index));
+  ASSERT_OK(db_->Write(WriteOptions(), &batch));
+
  ASSERT_OK(Flush());

-  SyncPoint::GetInstance()->SetCallBack(
-      "Version::Get::TamperWithBlobIndex", [](void* arg) {
-        Slice* const blob_index = static_cast<Slice*>(arg);
-        assert(blob_index);
-        assert(!blob_index->empty());
-        blob_index->remove_prefix(1);
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
  PinnableSlice result;
  ASSERT_TRUE(db_->Get(ReadOptions(), db_->DefaultColumnFamily(), key, &result)
                  .IsCorruption());
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
 }

 TEST_F(DBBlobBasicTest, MultiGetBlob_CorruptIndex) {
@@ -408,27 +401,17 @@ TEST_F(DBBlobBasicTest, MultiGetBlob_CorruptIndex) {
  }

  constexpr char key[] = "key";
-  constexpr char blob[] = "blob";
-  ASSERT_OK(Put(key, blob));
-  keys[kNumOfKeys] = key;
+  {
+    // Fake a corrupt blob index.
+    const std::string blob_index("foobar");
+    WriteBatch batch;
+    ASSERT_OK(WriteBatchInternal::PutBlobIndex(&batch, 0, key, blob_index));
+    ASSERT_OK(db_->Write(WriteOptions(), &batch));
+    keys[kNumOfKeys] = Slice(static_cast<const char*>(key), sizeof(key) - 1);
+  }

  ASSERT_OK(Flush());

-  SyncPoint::GetInstance()->SetCallBack(
-      "Version::MultiGet::TamperWithBlobIndex", [&key](void* arg) {
-        KeyContext* const key_context = static_cast<KeyContext*>(arg);
-        assert(key_context);
-        assert(key_context->key);
-
-        if (*(key_context->key) == key) {
-          Slice* const blob_index = key_context->value;
-          assert(blob_index);
-          assert(!blob_index->empty());
-          blob_index->remove_prefix(1);
-        }
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
  std::array<PinnableSlice, kNumOfKeys + 1> values;
  std::array<Status, kNumOfKeys + 1> statuses;
  db_->MultiGet(ReadOptions(), dbfull()->DefaultColumnFamily(), kNumOfKeys + 1,
@@ -442,9 +425,6 @@ TEST_F(DBBlobBasicTest, MultiGetBlob_CorruptIndex) {
      ASSERT_TRUE(statuses[i].IsCorruption());
    }
  }
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
 }

 TEST_F(DBBlobBasicTest, MultiGetBlob_ExceedSoftLimit) {
@@ -714,21 +694,18 @@ TEST_F(DBBlobBasicTest, Properties) {
  constexpr char key3[] = "key3";
  constexpr size_t key3_size = sizeof(key3) - 1;

-  constexpr char blob[] = "00000000000000";
+  constexpr char blob[] = "0000000000";
  constexpr size_t blob_size = sizeof(blob) - 1;

-  constexpr char longer_blob[] = "00000000000000000000";
-  constexpr size_t longer_blob_size = sizeof(longer_blob) - 1;
-
  ASSERT_OK(Put(key1, blob));
-  ASSERT_OK(Put(key2, longer_blob));
+  ASSERT_OK(Put(key2, blob));
  ASSERT_OK(Flush());

  constexpr size_t first_blob_file_expected_size =
      BlobLogHeader::kSize +
      BlobLogRecord::CalculateAdjustmentForRecordHeader(key1_size) + blob_size +
-      BlobLogRecord::CalculateAdjustmentForRecordHeader(key2_size) +
-      longer_blob_size + BlobLogFooter::kSize;
+      BlobLogRecord::CalculateAdjustmentForRecordHeader(key2_size) + blob_size +
+      BlobLogFooter::kSize;

  ASSERT_OK(Put(key3, blob));
  ASSERT_OK(Flush());
@@ -753,14 +730,6 @@ TEST_F(DBBlobBasicTest, Properties) {
                                  &live_blob_file_size));
  ASSERT_EQ(live_blob_file_size, total_expected_size);

-  // Total amount of garbage in live blob files
-  {
-    uint64_t live_blob_file_garbage_size = 0;
-    ASSERT_TRUE(db_->GetIntProperty(DB::Properties::kLiveBlobFileGarbageSize,
-                                    &live_blob_file_garbage_size));
-    ASSERT_EQ(live_blob_file_garbage_size, 0);
-  }
-
  // Total size of all blob files across all versions
  // Note: this should be the same as above since we only have one
  // version at this point.
@@ -778,12 +747,7 @@ TEST_F(DBBlobBasicTest, Properties) {
  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), begin, end));

  constexpr size_t expected_garbage_size =
-      BlobLogRecord::CalculateAdjustmentForRecordHeader(key2_size) +
-      longer_blob_size;
-
-  constexpr double expected_space_amp =
-      static_cast<double>(total_expected_size) /
-      (total_expected_size - expected_garbage_size);
+      BlobLogRecord::CalculateAdjustmentForRecordHeader(key2_size) + blob_size;

  // Blob file stats
  std::string blob_stats;
@@ -793,17 +757,9 @@ TEST_F(DBBlobBasicTest, Properties) {
  oss << "Number of blob files: 2\nTotal size of blob files: "
      << total_expected_size
      << "\nTotal size of garbage in blob files: " << expected_garbage_size
-      << "\nBlob file space amplification: " << expected_space_amp << '\n';
+      << '\n';

  ASSERT_EQ(blob_stats, oss.str());
-
-  // Total amount of garbage in live blob files
-  {
-    uint64_t live_blob_file_garbage_size = 0;
-    ASSERT_TRUE(db_->GetIntProperty(DB::Properties::kLiveBlobFileGarbageSize,
-                                    &live_blob_file_garbage_size));
-    ASSERT_EQ(live_blob_file_garbage_size, expected_garbage_size);
-  }
 }

 TEST_F(DBBlobBasicTest, PropertiesMultiVersion) {
@@ -243,84 +243,6 @@ TEST_F(DBBlobCompactionTest, FilterByKeyLength) {
  Close();
 }

-#ifndef ROCKSDB_LITE
-TEST_F(DBBlobCompactionTest, BlobCompactWithStartingLevel) {
-  Options options = GetDefaultOptions();
-
-  options.enable_blob_files = true;
-  options.min_blob_size = 1000;
-  options.blob_file_starting_level = 5;
-  options.create_if_missing = true;
-
-  // Open DB with fixed-prefix sst-partitioner so that compaction will cut
-  // new table file when encountering a new key whose 1-byte prefix changes.
-  constexpr size_t key_len = 1;
-  options.sst_partitioner_factory =
-      NewSstPartitionerFixedPrefixFactory(key_len);
-
-  ASSERT_OK(TryReopen(options));
-
-  constexpr size_t blob_size = 3000;
-
-  constexpr char first_key[] = "a";
-  const std::string first_blob(blob_size, 'a');
-  ASSERT_OK(Put(first_key, first_blob));
-
-  constexpr char second_key[] = "b";
-  const std::string second_blob(2 * blob_size, 'b');
-  ASSERT_OK(Put(second_key, second_blob));
-
-  constexpr char third_key[] = "d";
-  const std::string third_blob(blob_size, 'd');
-  ASSERT_OK(Put(third_key, third_blob));
-
-  ASSERT_OK(Flush());
-
-  constexpr char fourth_key[] = "c";
-  const std::string fourth_blob(blob_size, 'c');
-  ASSERT_OK(Put(fourth_key, fourth_blob));
-
-  ASSERT_OK(Flush());
-
-  ASSERT_EQ(0, GetBlobFileNumbers().size());
-  ASSERT_EQ(2, NumTableFilesAtLevel(/*level=*/0));
-  ASSERT_EQ(0, NumTableFilesAtLevel(/*level=*/1));
-
-  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
-                              /*end=*/nullptr));
-
-  // No blob file should be created since blob_file_starting_level is 5.
-  ASSERT_EQ(0, GetBlobFileNumbers().size());
-  ASSERT_EQ(0, NumTableFilesAtLevel(/*level=*/0));
-  ASSERT_EQ(4, NumTableFilesAtLevel(/*level=*/1));
-
-  {
-    options.blob_file_starting_level = 1;
-    DestroyAndReopen(options);
-
-    ASSERT_OK(Put(first_key, first_blob));
-    ASSERT_OK(Put(second_key, second_blob));
-    ASSERT_OK(Put(third_key, third_blob));
-    ASSERT_OK(Flush());
-    ASSERT_OK(Put(fourth_key, fourth_blob));
-    ASSERT_OK(Flush());
-
-    ASSERT_EQ(0, GetBlobFileNumbers().size());
-    ASSERT_EQ(2, NumTableFilesAtLevel(/*level=*/0));
-    ASSERT_EQ(0, NumTableFilesAtLevel(/*level=*/1));
-
-    ASSERT_OK(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
-                                /*end=*/nullptr));
-    // The compaction's output level equals to blob_file_starting_level.
-    ASSERT_EQ(1, GetBlobFileNumbers().size());
-    ASSERT_EQ(0, NumTableFilesAtLevel(/*level=*/0));
-    ASSERT_EQ(4, NumTableFilesAtLevel(/*level=*/1));
-  }
-
-  Close();
-}
-#endif
-
 TEST_F(DBBlobCompactionTest, BlindWriteFilter) {
  Options options = GetDefaultOptions();
  options.enable_blob_files = true;
@@ -493,30 +415,16 @@ TEST_F(DBBlobCompactionTest, CorruptedBlobIndex) {
      new ValueMutationFilter(""));
  options.compaction_filter = compaction_filter_guard.get();
  DestroyAndReopen(options);
-
+  // Mock a corrupted blob index
  constexpr char key[] = "key";
-  constexpr char blob[] = "blob";
-
-  ASSERT_OK(Put(key, blob));
+  std::string blob_idx("blob_idx");
+  WriteBatch write_batch;
+  ASSERT_OK(WriteBatchInternal::PutBlobIndex(&write_batch, 0, key, blob_idx));
+  ASSERT_OK(db_->Write(WriteOptions(), &write_batch));
  ASSERT_OK(Flush());
-
-  SyncPoint::GetInstance()->SetCallBack(
-      "CompactionIterator::InvokeFilterIfNeeded::TamperWithBlobIndex",
-      [](void* arg) {
-        Slice* const blob_index = static_cast<Slice*>(arg);
-        assert(blob_index);
-        assert(!blob_index->empty());
-        blob_index->remove_prefix(1);
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
  ASSERT_TRUE(db_->CompactRange(CompactRangeOptions(), /*begin=*/nullptr,
                                /*end=*/nullptr)
                  .IsCorruption());
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-
  Close();
 }

@@ -604,7 +512,8 @@ TEST_F(DBBlobCompactionTest, TrackGarbage) {
  ASSERT_EQ(blob_files.size(), 2);

  {
-    const auto& meta = blob_files.front();
+    auto it = blob_files.begin();
+    const auto& meta = it->second;
    assert(meta);

    constexpr uint64_t first_expected_bytes =
@@ -634,7 +543,8 @@ TEST_F(DBBlobCompactionTest, TrackGarbage) {
  }

  {
-    const auto& meta = blob_files.back();
+    auto it = blob_files.rbegin();
+    const auto& meta = it->second;
    assert(meta);

    constexpr uint64_t new_first_expected_bytes =
@@ -13,7 +13,6 @@
 #include <vector>

 #include "db/arena_wrapped_db_iter.h"
-#include "db/blob/blob_index.h"
 #include "db/column_family.h"
 #include "db/db_iter.h"
 #include "db/db_test_util.h"
@@ -139,39 +138,20 @@ class DBBlobIndexTest : public DBTestBase {
  }
 };

-// Note: the following test case pertains to the StackableDB-based BlobDB
-// implementation. We should be able to write kTypeBlobIndex to memtables and
-// SST files.
+// Should be able to write kTypeBlobIndex to memtables and SST files.
 TEST_F(DBBlobIndexTest, Write) {
  for (auto tier : kAllTiers) {
    DestroyAndReopen(GetTestOptions());
-
-    std::vector<std::pair<std::string, std::string>> key_values;
-
-    constexpr size_t num_key_values = 5;
-
-    key_values.reserve(num_key_values);
-
-    for (size_t i = 1; i <= num_key_values; ++i) {
-      std::string key = "key" + std::to_string(i);
-
-      std::string blob_index;
-      BlobIndex::EncodeInlinedTTL(&blob_index, /* expiration */ 9876543210,
-                                  "blob" + std::to_string(i));
-
-      key_values.emplace_back(std::move(key), std::move(blob_index));
-    }
-
-    for (const auto& key_value : key_values) {
+    for (int i = 1; i <= 5; i++) {
+      std::string index = ToString(i);
      WriteBatch batch;
-      ASSERT_OK(PutBlobIndex(&batch, key_value.first, key_value.second));
+      ASSERT_OK(PutBlobIndex(&batch, "key" + index, "blob" + index));
      ASSERT_OK(Write(&batch));
    }
-
    MoveDataTo(tier);
-
-    for (const auto& key_value : key_values) {
-      ASSERT_EQ(GetBlobIndex(key_value.first), key_value.second);
+    for (int i = 1; i <= 5; i++) {
+      std::string index = ToString(i);
+      ASSERT_EQ("blob" + index, GetBlobIndex("key" + index));
    }
  }
 }
@@ -184,19 +164,13 @@ TEST_F(DBBlobIndexTest, Write) {
 // accidentally opening the base DB of a stacked BlobDB and actual corruption
 // when using the integrated BlobDB.
 TEST_F(DBBlobIndexTest, Get) {
-  std::string blob_index;
-  BlobIndex::EncodeInlinedTTL(&blob_index, /* expiration */ 9876543210, "blob");
-
  for (auto tier : kAllTiers) {
    DestroyAndReopen(GetTestOptions());
-
    WriteBatch batch;
    ASSERT_OK(batch.Put("key", "value"));
-    ASSERT_OK(PutBlobIndex(&batch, "blob_key", blob_index));
+    ASSERT_OK(PutBlobIndex(&batch, "blob_key", "blob_index"));
    ASSERT_OK(Write(&batch));
-
    MoveDataTo(tier);
-
    // Verify normal value
    bool is_blob_index = false;
    PinnableSlice value;
@@ -204,7 +178,6 @@ TEST_F(DBBlobIndexTest, Get) {
    ASSERT_EQ("value", GetImpl("key"));
    ASSERT_EQ("value", GetImpl("key", &is_blob_index));
    ASSERT_FALSE(is_blob_index);
-
    // Verify blob index
    if (tier <= kImmutableMemtables) {
      ASSERT_TRUE(Get("blob_key", &value).IsNotSupported());
@@ -213,7 +186,7 @@ TEST_F(DBBlobIndexTest, Get) {
      ASSERT_TRUE(Get("blob_key", &value).IsCorruption());
      ASSERT_EQ("CORRUPTION", GetImpl("blob_key"));
    }
-    ASSERT_EQ(blob_index, GetImpl("blob_key", &is_blob_index));
+    ASSERT_EQ("blob_index", GetImpl("blob_key", &is_blob_index));
    ASSERT_TRUE(is_blob_index);
  }
 }
@@ -223,14 +196,11 @@ TEST_F(DBBlobIndexTest, Get) {
 // if blob index is updated with a normal value. See the test case above for
 // more details.
 TEST_F(DBBlobIndexTest, Updated) {
-  std::string blob_index;
-  BlobIndex::EncodeInlinedTTL(&blob_index, /* expiration */ 9876543210, "blob");
-
  for (auto tier : kAllTiers) {
    DestroyAndReopen(GetTestOptions());
    WriteBatch batch;
    for (int i = 0; i < 10; i++) {
-      ASSERT_OK(PutBlobIndex(&batch, "key" + std::to_string(i), blob_index));
+      ASSERT_OK(PutBlobIndex(&batch, "key" + ToString(i), "blob_index"));
    }
    ASSERT_OK(Write(&batch));
    // Avoid blob values from being purged.
@@ -248,7 +218,7 @@ TEST_F(DBBlobIndexTest, Updated) {
    ASSERT_OK(dbfull()->DeleteRange(WriteOptions(), cfh(), "key6", "key9"));
    MoveDataTo(tier);
    for (int i = 0; i < 10; i++) {
-      ASSERT_EQ(blob_index, GetBlobIndex("key" + std::to_string(i), snapshot));
+      ASSERT_EQ("blob_index", GetBlobIndex("key" + ToString(i), snapshot));
    }
    ASSERT_EQ("new_value", Get("key1"));
    if (tier <= kImmutableMemtables) {
@@ -260,9 +230,9 @@ TEST_F(DBBlobIndexTest, Updated) {
    ASSERT_EQ("NOT_FOUND", Get("key4"));
    ASSERT_EQ("a,b,c", GetImpl("key5"));
    for (int i = 6; i < 9; i++) {
-      ASSERT_EQ("NOT_FOUND", Get("key" + std::to_string(i)));
+      ASSERT_EQ("NOT_FOUND", Get("key" + ToString(i)));
    }
-    ASSERT_EQ(blob_index, GetBlobIndex("key9"));
+    ASSERT_EQ("blob_index", GetBlobIndex("key9"));
    dbfull()->ReleaseSnapshot(snapshot);
  }
 }
@@ -301,7 +271,7 @@ TEST_F(DBBlobIndexTest, Iterate) {
  };

  auto get_value = [&](int index, int version) {
-    return get_key(index) + "_value" + std::to_string(version);
+    return get_key(index) + "_value" + ToString(version);
  };

  auto check_iterator = [&](Iterator* iterator, Status::Code expected_status,
@@ -501,7 +471,7 @@ TEST_F(DBBlobIndexTest, IntegratedBlobIterate) {
  auto get_key = [](size_t index) { return ("key" + std::to_string(index)); };

  auto get_value = [&](size_t index, size_t version) {
-    return get_key(index) + "_value" + std::to_string(version);
+    return get_key(index) + "_value" + ToString(version);
  };

  auto check_iterator = [&](Iterator* iterator, Status expected_status,
@@ -37,7 +37,6 @@
 #include "table/block_based/block_based_table_builder.h"
 #include "table/format.h"
 #include "table/internal_iterator.h"
-#include "table/unique_id_impl.h"
 #include "test_util/sync_point.h"
 #include "util/stop_watch.h"

@@ -63,9 +62,9 @@ Status BuildTable(
    FileMetaData* meta, std::vector<BlobFileAddition>* blob_file_additions,
    std::vector<SequenceNumber> snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
-    SequenceNumber job_snapshot, SnapshotChecker* snapshot_checker,
-    bool paranoid_file_checks, InternalStats* internal_stats,
-    IOStatus* io_status, const std::shared_ptr<IOTracer>& io_tracer,
+    SnapshotChecker* snapshot_checker, bool paranoid_file_checks,
+    InternalStats* internal_stats, IOStatus* io_status,
+    const std::shared_ptr<IOTracer>& io_tracer,
    BlobFileCreationReason blob_creation_reason, EventLogger* event_logger,
    int job_id, const Env::IOPriority io_priority,
    TableProperties* table_properties, Env::WriteLifeTimeHint write_hint,
@@ -116,7 +115,6 @@ Status BuildTable(
  assert(fs);

  TableProperties tp;
-  bool table_file_created = false;
  if (iter->Valid() || !range_del_agg->IsEmpty()) {
    std::unique_ptr<CompactionFilter> compaction_filter;
    if (ioptions.compaction_filter_factory != nullptr &&
@@ -160,8 +158,6 @@ Status BuildTable(
            file_checksum_func_name);
        return s;
      }
-
-      table_file_created = true;
      FileTypeSet tmp_set = ioptions.checksum_handoff_file_types;
      file->SetIOPriority(io_priority);
      file->SetWriteLifeTimeHint(write_hint);
@@ -181,10 +177,7 @@ Status BuildTable(
        snapshots.empty() ? 0 : snapshots.back(), snapshot_checker);

    std::unique_ptr<BlobFileBuilder> blob_file_builder(
-        (mutable_cf_options.enable_blob_files &&
-         tboptions.level_at_creation >=
-             mutable_cf_options.blob_file_starting_level &&
-         blob_file_additions)
+        (mutable_cf_options.enable_blob_files && blob_file_additions)
            ? new BlobFileBuilder(
                  versions, fs, &ioptions, &mutable_cf_options, &file_options,
                  job_id, tboptions.column_family_id,
@@ -193,18 +186,17 @@ Status BuildTable(
                  &blob_file_paths, blob_file_additions)
            : nullptr);

-    const std::atomic<bool> kManualCompactionCanceledFalse{false};
    CompactionIterator c_iter(
        iter, tboptions.internal_comparator.user_comparator(), &merge,
        kMaxSequenceNumber, &snapshots, earliest_write_conflict_snapshot,
-        job_snapshot, snapshot_checker, env,
-        ShouldReportDetailedTime(env, ioptions.stats),
+        snapshot_checker, env, ShouldReportDetailedTime(env, ioptions.stats),
        true /* internal key corruption is not ok */, range_del_agg.get(),
        blob_file_builder.get(), ioptions.allow_data_in_errors,
-        ioptions.enforce_single_del_contracts,
-        /*manual_compaction_canceled=*/kManualCompactionCanceledFalse,
        /*compaction=*/nullptr, compaction_filter.get(),
-        /*shutting_down=*/nullptr, db_options.info_log, full_history_ts_low);
+        /*shutting_down=*/nullptr,
+        /*preserve_deletes_seqnum=*/0, /*manual_compaction_paused=*/nullptr,
+        /*manual_compaction_canceled=*/nullptr, db_options.info_log,
+        full_history_ts_low);

    c_iter.SeekToFirst();
    for (; c_iter.Valid(); c_iter.Next()) {
@@ -219,11 +211,7 @@ Status BuildTable(
        break;
      }
      builder->Add(key, value);
-
-      s = meta->UpdateBoundaries(key, value, ikey.sequence, ikey.type);
-      if (!s.ok()) {
-        break;
-      }
+      meta->UpdateBoundaries(key, value, ikey.sequence, ikey.type);

      // TODO(noetzli): Update stats after flush, too.
      if (io_priority == Env::IO_HIGH &&
@@ -313,15 +301,6 @@ Status BuildTable(
      meta->file_checksum_func_name = file_writer->GetFileChecksumFuncName();
      file_checksum = meta->file_checksum;
      file_checksum_func_name = meta->file_checksum_func_name;
-      // Set unique_id only if db_id and db_session_id exist
-      if (!tboptions.db_id.empty() && !tboptions.db_session_id.empty()) {
-        if (!GetSstInternalUniqueId(tboptions.db_id, tboptions.db_session_id,
-                                    meta->fd.GetNumber(), &(meta->unique_id))
-                 .ok()) {
-          // if failed to get unique id, just set it Null
-          meta->unique_id = kNullUniqueId64x2;
-        }
-      }
    }

    if (s.ok()) {
@@ -339,18 +318,18 @@ Status BuildTable(

    // TODO Also check the IO status when create the Iterator.

-    TEST_SYNC_POINT("BuildTable:BeforeOutputValidation");
    if (s.ok() && !empty) {
      // Verify that the table is usable
      // We set for_compaction to false and don't OptimizeForCompactionTableRead
-      // here because this is a special case after we finish the table building.
+      // here because this is a special case after we finish the table building
      // No matter whether use_direct_io_for_flush_and_compaction is true,
-      // the goal is to cache it here for further user reads.
+      // we will regrad this verification as user reads since the goal is
+      // to cache it here for further user reads
      ReadOptions read_options;
      std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
          read_options, file_options, tboptions.internal_comparator, *meta,
-          nullptr /* range_del_agg */, mutable_cf_options.prefix_extractor,
-          nullptr,
+          nullptr /* range_del_agg */,
+          mutable_cf_options.prefix_extractor.get(), nullptr,
          (internal_stats == nullptr) ? nullptr
                                      : internal_stats->GetFileReadHist(0),
          TableReaderCaller::kFlush, /*arena=*/nullptr,
@@ -386,17 +365,15 @@ Status BuildTable(

    constexpr IODebugContext* dbg = nullptr;

-    if (table_file_created) {
-      Status ignored = fs->DeleteFile(fname, IOOptions(), dbg);
-      ignored.PermitUncheckedError();
-    }
+    Status ignored = fs->DeleteFile(fname, IOOptions(), dbg);
+    ignored.PermitUncheckedError();

    assert(blob_file_additions || blob_file_paths.empty());

    if (blob_file_additions) {
      for (const std::string& blob_file_path : blob_file_paths) {
-        Status ignored = DeleteDBFile(&db_options, blob_file_path, dbname,
-                                      /*force_bg=*/false, /*force_fg=*/false);
+        ignored = DeleteDBFile(&db_options, blob_file_path, dbname,
+                               /*force_bg=*/false, /*force_fg=*/false);
        ignored.PermitUncheckedError();
        TEST_SYNC_POINT("BuildTable::AfterDeleteFile");
      }
@@ -57,9 +57,9 @@ extern Status BuildTable(
    FileMetaData* meta, std::vector<BlobFileAddition>* blob_file_additions,
    std::vector<SequenceNumber> snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
-    SequenceNumber job_snapshot, SnapshotChecker* snapshot_checker,
-    bool paranoid_file_checks, InternalStats* internal_stats,
-    IOStatus* io_status, const std::shared_ptr<IOTracer>& io_tracer,
+    SnapshotChecker* snapshot_checker, bool paranoid_file_checks,
+    InternalStats* internal_stats, IOStatus* io_status,
+    const std::shared_ptr<IOTracer>& io_tracer,
    BlobFileCreationReason blob_creation_reason,
    EventLogger* event_logger = nullptr, int job_id = 0,
    const Env::IOPriority io_priority = Env::IO_HIGH,
@@ -7,13 +7,12 @@

 #ifndef ROCKSDB_LITE  // Lite does not support C API

-#include <assert.h>
+#include "rocksdb/c.h"
+
 #include <stddef.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
-
-#include "rocksdb/c.h"
 #ifndef OS_WIN
 #include <unistd.h>
 #endif
@@ -33,6 +32,11 @@ int geteuid() {
  return result;
 }

+// VS < 2015
+#if defined(_MSC_VER) && (_MSC_VER < 1900)
+#define snprintf _snprintf
+#endif
+
 #endif

 const char* phase = "";
@@ -85,8 +89,10 @@ static void CheckEqual(const char* expected, const char* v, size_t n) {
    // ok
    return;
  } else {
-    fprintf(stderr, "%s: expected '%s', got '%s'\n", phase,
-            (expected ? expected : "(null)"), (v ? v : "(null)"));
+    fprintf(stderr, "%s: expected '%s', got '%s'\n",
+            phase,
+            (expected ? expected : "(null)"),
+            (v ? v : "(null"));
    abort();
  }
 }
@@ -164,16 +170,6 @@ static void CheckPinGetCF(rocksdb_t* db, const rocksdb_readoptions_t* options,
  rocksdb_pinnableslice_destroy(p);
 }

-static void CheckMultiGetValues(size_t num_keys, char** values,
-                                size_t* values_sizes, char** errs,
-                                const char** expected) {
-  for (size_t i = 0; i < num_keys; i++) {
-    CheckNoError(errs[i]);
-    CheckEqual(expected[i], values[i], values_sizes[i]);
-    Free(&values[i]);
-  }
-}
-
 static void CheckIter(rocksdb_iterator_t* iter,
                      const char* key, const char* val) {
  size_t len;
@@ -230,6 +226,39 @@ static const char* CmpName(void* arg) {
  return "foo";
 }

+// Custom filter policy
+static unsigned char fake_filter_result = 1;
+static void FilterDestroy(void* arg) { (void)arg; }
+static const char* FilterName(void* arg) {
+  (void)arg;
+  return "TestFilter";
+}
+static char* FilterCreate(
+    void* arg,
+    const char* const* key_array, const size_t* key_length_array,
+    int num_keys,
+    size_t* filter_length) {
+  (void)arg;
+  (void)key_array;
+  (void)key_length_array;
+  (void)num_keys;
+  *filter_length = 4;
+  char* result = malloc(4);
+  memcpy(result, "fake", 4);
+  return result;
+}
+static unsigned char FilterKeyMatch(
+    void* arg,
+    const char* key, size_t length,
+    const char* filter, size_t filter_length) {
+  (void)arg;
+  (void)key;
+  (void)length;
+  CheckCondition(filter_length == 4);
+  CheckCondition(memcmp(filter, "fake", 4) == 0);
+  return fake_filter_result;
+}
+
 // Custom compaction filter
 static void CFilterDestroy(void* arg) { (void)arg; }
 static const char* CFilterName(void* arg) {
@@ -288,16 +317,6 @@ static rocksdb_t* CheckCompaction(rocksdb_t* db, rocksdb_options_t* options,
  CheckNoError(err);
  CheckGet(db, roptions, "baz", "bazvalue");

-  // Disable compaction
-  rocksdb_disable_manual_compaction(db);
-  rocksdb_compact_range(db, NULL, 0, NULL, 0);
-  // should not filter anything when disabled
-  CheckGet(db, roptions, "foo", "foovalue");
-  CheckGet(db, roptions, "bar", "barvalue");
-  CheckGet(db, roptions, "baz", "bazvalue");
-  // Reenable compaction
-  rocksdb_enable_manual_compaction(db);
-
  // Force compaction
  rocksdb_compact_range(db, NULL, 0, NULL, 0);
  // should have filtered bar, but not foo
@@ -381,49 +400,18 @@ static void CheckTxnGetCF(rocksdb_transaction_t* txn,
  Free(&val);
 }

-static void CheckTxnPinGet(rocksdb_transaction_t* txn,
-                           const rocksdb_readoptions_t* options,
-                           const char* key, const char* expected) {
-  rocksdb_pinnableslice_t* p = NULL;
-  const char* val = NULL;
-  char* err = NULL;
-  size_t val_len;
-  p = rocksdb_transaction_get_pinned(txn, options, key, strlen(key), &err);
-  CheckNoError(err);
-  val = rocksdb_pinnableslice_value(p, &val_len);
-  CheckEqual(expected, val, val_len);
-  rocksdb_pinnableslice_destroy(p);
-}
-
-static void CheckTxnPinGetCF(rocksdb_transaction_t* txn,
-                             const rocksdb_readoptions_t* options,
-                             rocksdb_column_family_handle_t* column_family,
-                             const char* key, const char* expected) {
-  rocksdb_pinnableslice_t* p = NULL;
-  const char* val = NULL;
-  char* err = NULL;
-  size_t val_len;
-  p = rocksdb_transaction_get_pinned_cf(txn, options, column_family, key,
-                                        strlen(key), &err);
-  CheckNoError(err);
-  val = rocksdb_pinnableslice_value(p, &val_len);
-  CheckEqual(expected, val, val_len);
-  rocksdb_pinnableslice_destroy(p);
-}
-
 static void CheckTxnDBGet(
        rocksdb_transactiondb_t* txn_db,
        const rocksdb_readoptions_t* options,
        const char* key,
        const char* expected) {
-  char* err = NULL;
-  size_t val_len;
-  char* val;
-  val = rocksdb_transactiondb_get(txn_db, options, key, strlen(key), &val_len,
-                                  &err);
-  CheckNoError(err);
-  CheckEqual(expected, val, val_len);
-  Free(&val);
+        char* err = NULL;
+        size_t val_len;
+        char* val;
+        val = rocksdb_transactiondb_get(txn_db, options, key, strlen(key), &val_len, &err);
+        CheckNoError(err);
+        CheckEqual(expected, val, val_len);
+        Free(&val);
 }

 static void CheckTxnDBGetCF(rocksdb_transactiondb_t* txn_db,
@@ -440,36 +428,6 @@ static void CheckTxnDBGetCF(rocksdb_transactiondb_t* txn_db,
  Free(&val);
 }

-static void CheckTxnDBPinGet(rocksdb_transactiondb_t* txn_db,
-                             const rocksdb_readoptions_t* options,
-                             const char* key, const char* expected) {
-  rocksdb_pinnableslice_t* p = NULL;
-  const char* val = NULL;
-  char* err = NULL;
-  size_t val_len;
-  p = rocksdb_transactiondb_get_pinned(txn_db, options, key, strlen(key), &err);
-  CheckNoError(err);
-  val = rocksdb_pinnableslice_value(p, &val_len);
-  CheckEqual(expected, val, val_len);
-  rocksdb_pinnableslice_destroy(p);
-}
-
-static void CheckTxnDBPinGetCF(rocksdb_transactiondb_t* txn_db,
-                               const rocksdb_readoptions_t* options,
-                               rocksdb_column_family_handle_t* column_family,
-                               const char* key, const char* expected) {
-  rocksdb_pinnableslice_t* p = NULL;
-  const char* val = NULL;
-  char* err = NULL;
-  size_t val_len;
-  p = rocksdb_transactiondb_get_pinned_cf(txn_db, options, column_family, key,
-                                          strlen(key), &err);
-  CheckNoError(err);
-  val = rocksdb_pinnableslice_value(p, &val_len);
-  CheckEqual(expected, val, val_len);
-  rocksdb_pinnableslice_destroy(p);
-}
-
 int main(int argc, char** argv) {
  (void)argc;
  (void)argv;
@@ -522,10 +480,6 @@ int main(int argc, char** argv) {
  cmp = rocksdb_comparator_create(NULL, CmpDestroy, CmpCompare, CmpName);
  dbpath = rocksdb_dbpath_create(dbpathname, 1024 * 1024);
  env = rocksdb_create_default_env();
-
-  rocksdb_create_dir_if_missing(env, GetTempDir(), &err);
-  CheckNoError(err);
-
  cache = rocksdb_cache_create_lru(100000);

  options = rocksdb_options_create();
@@ -536,6 +490,7 @@ int main(int argc, char** argv) {
  rocksdb_options_set_write_buffer_size(options, 100000);
  rocksdb_options_set_paranoid_checks(options, 1);
  rocksdb_options_set_max_open_files(options, 10);
+  rocksdb_options_set_base_background_compactions(options, 1);

  table_options = rocksdb_block_based_options_create();
  rocksdb_block_based_options_set_block_cache(table_options, cache);
@@ -990,9 +945,24 @@ int main(int argc, char** argv) {
    char* vals[3];
    size_t vals_sizes[3];
    char* errs[3];
-    const char* expected[3] = {"c", "hello", NULL};
    rocksdb_multi_get(db, roptions, 3, keys, keys_sizes, vals, vals_sizes, errs);
-    CheckMultiGetValues(3, vals, vals_sizes, errs, expected);
+
+    int i;
+    for (i = 0; i < 3; i++) {
+      CheckEqual(NULL, errs[i], 0);
+      switch (i) {
+      case 0:
+        CheckEqual("c", vals[i], vals_sizes[i]);
+        break;
+      case 1:
+        CheckEqual("hello", vals[i], vals_sizes[i]);
+        break;
+      case 2:
+        CheckEqual(NULL, vals[i], vals_sizes[i]);
+        break;
+      }
+      Free(&vals[i]);
+    }
  }

  StartPhase("pin_get");
@@ -1049,36 +1019,7 @@ int main(int argc, char** argv) {
    CheckGet(db, roptions, "foo", NULL);
    rocksdb_release_snapshot(db, snap);
  }
-  StartPhase("snapshot_with_memtable_inplace_update");
-  {
-    rocksdb_close(db);
-    const rocksdb_snapshot_t* snap = NULL;
-    const char* s_key = "foo_snap";
-    const char* value1 = "hello_s1";
-    const char* value2 = "hello_s2";
-    rocksdb_options_set_allow_concurrent_memtable_write(options, 0);
-    rocksdb_options_set_inplace_update_support(options, 1);
-    rocksdb_options_set_error_if_exists(options, 0);
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_put(db, woptions, s_key, 8, value1, 8, &err);
-    snap = rocksdb_create_snapshot(db);
-    assert(snap != NULL);
-    rocksdb_put(db, woptions, s_key, 8, value2, 8, &err);
-    CheckNoError(err);
-    rocksdb_readoptions_set_snapshot(roptions, snap);
-    CheckGet(db, roptions, "foo", NULL);
-    // snapshot syntax is invalid, because of inplace update supported is set
-    CheckGet(db, roptions, s_key, value2);
-    // restore the data and options
-    rocksdb_delete(db, woptions, s_key, 8, &err);
-    CheckGet(db, roptions, s_key, NULL);
-    rocksdb_release_snapshot(db, snap);
-    rocksdb_readoptions_set_snapshot(roptions, NULL);
-    rocksdb_options_set_inplace_update_support(options, 0);
-    rocksdb_options_set_allow_concurrent_memtable_write(options, 1);
-    rocksdb_options_set_error_if_exists(options, 1);
-  }
+
  StartPhase("repair");
  {
    // If we do not compact here, then the lazy deletion of
@@ -1102,15 +1043,18 @@ int main(int argc, char** argv) {
  }

  StartPhase("filter");
-  for (run = 1; run <= 4; run++) {
-    // run=0 uses custom filter (not currently supported)
+  for (run = 0; run <= 4; run++) {
+    // run=0 uses custom filter
    // run=1 uses old block-based bloom filter
    // run=2 run uses full bloom filter
    // run=3 uses Ribbon
    // run=4 uses Ribbon-Bloom hybrid configuration
    CheckNoError(err);
    rocksdb_filterpolicy_t* policy;
-    if (run == 1) {
+    if (run == 0) {
+      policy = rocksdb_filterpolicy_create(NULL, FilterDestroy, FilterCreate,
+                                           FilterKeyMatch, NULL, FilterName);
+    } else if (run == 1) {
      policy = rocksdb_filterpolicy_create_bloom(8.0);
    } else if (run == 2) {
      policy = rocksdb_filterpolicy_create_bloom_full(8.0);
@@ -1145,8 +1089,19 @@ int main(int argc, char** argv) {
    }
    rocksdb_compact_range(db, NULL, 0, NULL, 0);

+    fake_filter_result = 1;
    CheckGet(db, roptions, "foo", "foovalue");
    CheckGet(db, roptions, "bar", "barvalue");
+    if (run == 0) {
+      // Must not find value when custom filter returns false
+      fake_filter_result = 0;
+      CheckGet(db, roptions, "foo", NULL);
+      CheckGet(db, roptions, "bar", NULL);
+      fake_filter_result = 1;
+
+      CheckGet(db, roptions, "foo", "foovalue");
+      CheckGet(db, roptions, "bar", "barvalue");
+    }

    {
      // Query some keys not added to identify Bloom filter implementation
@@ -1159,6 +1114,7 @@ int main(int argc, char** argv) {
      int i;
      char keybuf[100];
      for (i = 0; i < keys_to_query; i++) {
+        fake_filter_result = i % 2;
        snprintf(keybuf, sizeof(keybuf), "no%020d", i);
        CheckGet(db, roptions, keybuf, NULL);
      }
@@ -1168,10 +1124,10 @@ int main(int argc, char** argv) {
      if (run == 0) {
        // Due to half true, half false with fake filter result
        CheckCondition(hits == keys_to_query / 2);
-      } else if (run == 1 || run == 2 || run == 4) {
-        // For run == 1, block-based Bloom is no longer available in public
-        // API; attempting to enable it enables full Bloom instead.
-        //
+      } else if (run == 1) {
+        // Essentially a fingerprint of the block-based Bloom schema
+        CheckCondition(hits == 241);
+      } else if (run == 2 || run == 4) {
        // Essentially a fingerprint of full Bloom schema, format_version=5
        CheckCondition(hits == 188);
      } else {
@@ -1321,18 +1277,15 @@ int main(int argc, char** argv) {
    rocksdb_writebatch_clear(wb);
    rocksdb_writebatch_put_cf(wb, handles[1], "bar", 3, "b", 1);
    rocksdb_writebatch_put_cf(wb, handles[1], "box", 3, "c", 1);
-    rocksdb_writebatch_put_cf(wb, handles[1], "buff", 4, "rocksdb", 7);
    rocksdb_writebatch_delete_cf(wb, handles[1], "bar", 3);
    rocksdb_write(db, woptions, wb, &err);
    CheckNoError(err);
    CheckGetCF(db, roptions, handles[1], "baz", NULL);
    CheckGetCF(db, roptions, handles[1], "bar", NULL);
    CheckGetCF(db, roptions, handles[1], "box", "c");
-    CheckGetCF(db, roptions, handles[1], "buff", "rocksdb");
    CheckPinGetCF(db, roptions, handles[1], "baz", NULL);
    CheckPinGetCF(db, roptions, handles[1], "bar", NULL);
    CheckPinGetCF(db, roptions, handles[1], "box", "c");
-    CheckPinGetCF(db, roptions, handles[1], "buff", "rocksdb");
    rocksdb_writebatch_destroy(wb);

    rocksdb_flush_wal(db, 1, &err);
@@ -1363,26 +1316,6 @@ int main(int argc, char** argv) {
      Free(&vals[i]);
    }

-    {
-      const char* batched_keys[4] = {"box", "buff", "barfooxx", "box"};
-      const size_t batched_keys_sizes[4] = {3, 4, 8, 3};
-      const char* expected_value[4] = {"c", "rocksdb", NULL, "c"};
-      char* batched_errs[4];
-
-      rocksdb_pinnableslice_t* pvals[4];
-      rocksdb_batched_multi_get_cf(db, roptions, handles[1], 4, batched_keys,
-                                   batched_keys_sizes, pvals, batched_errs,
-                                   false);
-      const char* val;
-      size_t val_len;
-      for (i = 0; i < 4; ++i) {
-        val = rocksdb_pinnableslice_value(pvals[i], &val_len);
-        CheckNoError(batched_errs[i]);
-        CheckEqual(expected_value[i], val, val_len);
-        rocksdb_pinnableslice_destroy(pvals[i]);
-      }
-    }
-
    {
      unsigned char value_found = 0;

@@ -1414,7 +1347,7 @@ int main(int argc, char** argv) {
    for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
      i++;
    }
-    CheckCondition(i == 4);
+    CheckCondition(i == 3);
    rocksdb_iter_get_error(iter, &err);
    CheckNoError(err);
    rocksdb_iter_destroy(iter);
@@ -1438,7 +1371,7 @@ int main(int argc, char** argv) {
    for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
      i++;
    }
-    CheckCondition(i == 4);
+    CheckCondition(i == 3);
    rocksdb_iter_get_error(iter, &err);
    CheckNoError(err);
    rocksdb_iter_destroy(iter);
@@ -1680,6 +1613,9 @@ int main(int argc, char** argv) {
    rocksdb_options_set_max_background_compactions(o, 3);
    CheckCondition(3 == rocksdb_options_get_max_background_compactions(o));

+    rocksdb_options_set_base_background_compactions(o, 4);
+    CheckCondition(4 == rocksdb_options_get_base_background_compactions(o));
+
    rocksdb_options_set_max_background_flushes(o, 5);
    CheckCondition(5 == rocksdb_options_get_max_background_flushes(o));

@@ -1695,6 +1631,12 @@ int main(int argc, char** argv) {
    rocksdb_options_set_recycle_log_file_num(o, 9);
    CheckCondition(9 == rocksdb_options_get_recycle_log_file_num(o));

+    rocksdb_options_set_soft_rate_limit(o, 2.0);
+    CheckCondition(2.0 == rocksdb_options_get_soft_rate_limit(o));
+
+    rocksdb_options_set_hard_rate_limit(o, 4.0);
+    CheckCondition(4.0 == rocksdb_options_get_hard_rate_limit(o));
+
    rocksdb_options_set_soft_pending_compaction_bytes_limit(o, 10);
    CheckCondition(10 ==
                   rocksdb_options_get_soft_pending_compaction_bytes_limit(o));
@@ -1703,6 +1645,10 @@ int main(int argc, char** argv) {
    CheckCondition(11 ==
                   rocksdb_options_get_hard_pending_compaction_bytes_limit(o));

+    rocksdb_options_set_rate_limit_delay_max_milliseconds(o, 1);
+    CheckCondition(1 ==
+                   rocksdb_options_get_rate_limit_delay_max_milliseconds(o));
+
    rocksdb_options_set_max_manifest_file_size(o, 12);
    CheckCondition(12 == rocksdb_options_get_max_manifest_file_size(o));

@@ -1740,6 +1686,9 @@ int main(int argc, char** argv) {
    rocksdb_options_set_is_fd_close_on_exec(o, 1);
    CheckCondition(1 == rocksdb_options_get_is_fd_close_on_exec(o));

+    rocksdb_options_set_skip_log_error_on_recovery(o, 1);
+    CheckCondition(1 == rocksdb_options_get_skip_log_error_on_recovery(o));
+
    rocksdb_options_set_stats_dump_period_sec(o, 18);
    CheckCondition(18 == rocksdb_options_get_stats_dump_period_sec(o));

@@ -1828,9 +1777,6 @@ int main(int argc, char** argv) {
    rocksdb_options_set_manual_wal_flush(o, 1);
    CheckCondition(1 == rocksdb_options_get_manual_wal_flush(o));

-    rocksdb_options_set_wal_compression(o, 1);
-    CheckCondition(1 == rocksdb_options_get_wal_compression(o));
-
    /* Blob Options */
    rocksdb_options_set_enable_blob_files(o, 1);
    CheckCondition(1 == rocksdb_options_get_enable_blob_files(o));
@@ -1857,9 +1803,6 @@ int main(int argc, char** argv) {
    CheckCondition(262144 ==
                   rocksdb_options_get_blob_compaction_readahead_size(o));

-    rocksdb_options_set_blob_file_starting_level(o, 5);
-    CheckCondition(5 == rocksdb_options_get_blob_file_starting_level(o));
-
    // Create a copy that should be equal to the original.
    rocksdb_options_t* copy;
    copy = rocksdb_options_create_copy(o);
@@ -1905,15 +1848,20 @@ int main(int argc, char** argv) {
    CheckCondition(123456 == rocksdb_options_get_max_subcompactions(copy));
    CheckCondition(2 == rocksdb_options_get_max_background_jobs(copy));
    CheckCondition(3 == rocksdb_options_get_max_background_compactions(copy));
+    CheckCondition(4 == rocksdb_options_get_base_background_compactions(copy));
    CheckCondition(5 == rocksdb_options_get_max_background_flushes(copy));
    CheckCondition(6 == rocksdb_options_get_max_log_file_size(copy));
    CheckCondition(7 == rocksdb_options_get_log_file_time_to_roll(copy));
    CheckCondition(8 == rocksdb_options_get_keep_log_file_num(copy));
    CheckCondition(9 == rocksdb_options_get_recycle_log_file_num(copy));
+    CheckCondition(2.0 == rocksdb_options_get_soft_rate_limit(copy));
+    CheckCondition(4.0 == rocksdb_options_get_hard_rate_limit(copy));
    CheckCondition(
        10 == rocksdb_options_get_soft_pending_compaction_bytes_limit(copy));
    CheckCondition(
        11 == rocksdb_options_get_hard_pending_compaction_bytes_limit(copy));
+    CheckCondition(1 ==
+                   rocksdb_options_get_rate_limit_delay_max_milliseconds(copy));
    CheckCondition(12 == rocksdb_options_get_max_manifest_file_size(copy));
    CheckCondition(13 == rocksdb_options_get_table_cache_numshardbits(copy));
    CheckCondition(14 == rocksdb_options_get_arena_block_size(copy));
@@ -1927,6 +1875,7 @@ int main(int argc, char** argv) {
    CheckCondition(
        1 == rocksdb_options_get_use_direct_io_for_flush_and_compaction(copy));
    CheckCondition(1 == rocksdb_options_get_is_fd_close_on_exec(copy));
+    CheckCondition(1 == rocksdb_options_get_skip_log_error_on_recovery(copy));
    CheckCondition(18 == rocksdb_options_get_stats_dump_period_sec(copy));
    CheckCondition(5 == rocksdb_options_get_stats_persist_period_sec(copy));
    CheckCondition(1 == rocksdb_options_get_advise_random_on_open(copy));
@@ -2107,6 +2056,10 @@ int main(int argc, char** argv) {
    CheckCondition(13 == rocksdb_options_get_max_background_compactions(copy));
    CheckCondition(3 == rocksdb_options_get_max_background_compactions(o));

+    rocksdb_options_set_base_background_compactions(copy, 14);
+    CheckCondition(14 == rocksdb_options_get_base_background_compactions(copy));
+    CheckCondition(4 == rocksdb_options_get_base_background_compactions(o));
+
    rocksdb_options_set_max_background_flushes(copy, 15);
    CheckCondition(15 == rocksdb_options_get_max_background_flushes(copy));
    CheckCondition(5 == rocksdb_options_get_max_background_flushes(o));
@@ -2127,6 +2080,14 @@ int main(int argc, char** argv) {
    CheckCondition(19 == rocksdb_options_get_recycle_log_file_num(copy));
    CheckCondition(9 == rocksdb_options_get_recycle_log_file_num(o));

+    rocksdb_options_set_soft_rate_limit(copy, 4.0);
+    CheckCondition(4.0 == rocksdb_options_get_soft_rate_limit(copy));
+    CheckCondition(2.0 == rocksdb_options_get_soft_rate_limit(o));
+
+    rocksdb_options_set_hard_rate_limit(copy, 2.0);
+    CheckCondition(2.0 == rocksdb_options_get_hard_rate_limit(copy));
+    CheckCondition(4.0 == rocksdb_options_get_hard_rate_limit(o));
+
    rocksdb_options_set_soft_pending_compaction_bytes_limit(copy, 110);
    CheckCondition(
        110 == rocksdb_options_get_soft_pending_compaction_bytes_limit(copy));
@@ -2139,6 +2100,12 @@ int main(int argc, char** argv) {
    CheckCondition(11 ==
                   rocksdb_options_get_hard_pending_compaction_bytes_limit(o));

+    rocksdb_options_set_rate_limit_delay_max_milliseconds(copy, 0);
+    CheckCondition(0 ==
+                   rocksdb_options_get_rate_limit_delay_max_milliseconds(copy));
+    CheckCondition(1 ==
+                   rocksdb_options_get_rate_limit_delay_max_milliseconds(o));
+
    rocksdb_options_set_max_manifest_file_size(copy, 112);
    CheckCondition(112 == rocksdb_options_get_max_manifest_file_size(copy));
    CheckCondition(12 == rocksdb_options_get_max_manifest_file_size(o));
@@ -2190,6 +2157,10 @@ int main(int argc, char** argv) {
    CheckCondition(0 == rocksdb_options_get_is_fd_close_on_exec(copy));
    CheckCondition(1 == rocksdb_options_get_is_fd_close_on_exec(o));

+    rocksdb_options_set_skip_log_error_on_recovery(copy, 0);
+    CheckCondition(0 == rocksdb_options_get_skip_log_error_on_recovery(copy));
+    CheckCondition(1 == rocksdb_options_get_skip_log_error_on_recovery(o));
+
    rocksdb_options_set_stats_dump_period_sec(copy, 218);
    CheckCondition(218 == rocksdb_options_get_stats_dump_period_sec(copy));
    CheckCondition(18 == rocksdb_options_get_stats_dump_period_sec(o));
@@ -2535,53 +2506,53 @@ int main(int argc, char** argv) {
    rocksdb_fifo_compaction_options_destroy(fco);
  }

-  StartPhase("backup_engine_option");
+  StartPhase("backupable_db_option");
  {
-    rocksdb_backup_engine_options_t* bdo;
-    bdo = rocksdb_backup_engine_options_create("path");
+    rocksdb_backupable_db_options_t* bdo;
+    bdo = rocksdb_backupable_db_options_create("path");

-    rocksdb_backup_engine_options_set_share_table_files(bdo, 1);
+    rocksdb_backupable_db_options_set_share_table_files(bdo, 1);
    CheckCondition(1 ==
-                   rocksdb_backup_engine_options_get_share_table_files(bdo));
+                   rocksdb_backupable_db_options_get_share_table_files(bdo));

-    rocksdb_backup_engine_options_set_sync(bdo, 1);
-    CheckCondition(1 == rocksdb_backup_engine_options_get_sync(bdo));
+    rocksdb_backupable_db_options_set_sync(bdo, 1);
+    CheckCondition(1 == rocksdb_backupable_db_options_get_sync(bdo));

-    rocksdb_backup_engine_options_set_destroy_old_data(bdo, 1);
+    rocksdb_backupable_db_options_set_destroy_old_data(bdo, 1);
    CheckCondition(1 ==
-                   rocksdb_backup_engine_options_get_destroy_old_data(bdo));
+                   rocksdb_backupable_db_options_get_destroy_old_data(bdo));

-    rocksdb_backup_engine_options_set_backup_log_files(bdo, 1);
+    rocksdb_backupable_db_options_set_backup_log_files(bdo, 1);
    CheckCondition(1 ==
-                   rocksdb_backup_engine_options_get_backup_log_files(bdo));
+                   rocksdb_backupable_db_options_get_backup_log_files(bdo));

-    rocksdb_backup_engine_options_set_backup_rate_limit(bdo, 123);
+    rocksdb_backupable_db_options_set_backup_rate_limit(bdo, 123);
    CheckCondition(123 ==
-                   rocksdb_backup_engine_options_get_backup_rate_limit(bdo));
+                   rocksdb_backupable_db_options_get_backup_rate_limit(bdo));

-    rocksdb_backup_engine_options_set_restore_rate_limit(bdo, 37);
+    rocksdb_backupable_db_options_set_restore_rate_limit(bdo, 37);
    CheckCondition(37 ==
-                   rocksdb_backup_engine_options_get_restore_rate_limit(bdo));
+                   rocksdb_backupable_db_options_get_restore_rate_limit(bdo));

-    rocksdb_backup_engine_options_set_max_background_operations(bdo, 20);
+    rocksdb_backupable_db_options_set_max_background_operations(bdo, 20);
    CheckCondition(
-        20 == rocksdb_backup_engine_options_get_max_background_operations(bdo));
+        20 == rocksdb_backupable_db_options_get_max_background_operations(bdo));

-    rocksdb_backup_engine_options_set_callback_trigger_interval_size(bdo, 9000);
+    rocksdb_backupable_db_options_set_callback_trigger_interval_size(bdo, 9000);
    CheckCondition(
        9000 ==
-        rocksdb_backup_engine_options_get_callback_trigger_interval_size(bdo));
+        rocksdb_backupable_db_options_get_callback_trigger_interval_size(bdo));

-    rocksdb_backup_engine_options_set_max_valid_backups_to_open(bdo, 40);
+    rocksdb_backupable_db_options_set_max_valid_backups_to_open(bdo, 40);
    CheckCondition(
-        40 == rocksdb_backup_engine_options_get_max_valid_backups_to_open(bdo));
+        40 == rocksdb_backupable_db_options_get_max_valid_backups_to_open(bdo));

-    rocksdb_backup_engine_options_set_share_files_with_checksum_naming(bdo, 2);
+    rocksdb_backupable_db_options_set_share_files_with_checksum_naming(bdo, 2);
    CheckCondition(
-        2 == rocksdb_backup_engine_options_get_share_files_with_checksum_naming(
+        2 == rocksdb_backupable_db_options_get_share_files_with_checksum_naming(
                 bdo));

-    rocksdb_backup_engine_options_destroy(bdo);
+    rocksdb_backupable_db_options_destroy(bdo);
  }

  StartPhase("compression_options");
@@ -2603,9 +2574,6 @@ int main(int argc, char** argv) {
        200 ==
        rocksdb_options_get_compression_options_max_dict_buffer_bytes(co));

-    rocksdb_options_set_compression_options_use_zstd_dict_trainer(co, 0);
-    CheckCondition(
-        0 == rocksdb_options_get_compression_options_use_zstd_dict_trainer(co));
    rocksdb_options_destroy(co);
  }

@@ -2687,13 +2655,11 @@ int main(int argc, char** argv) {
    rocksdb_transactiondb_put(txn_db, woptions, "foo", 3, "hello", 5, &err);
    CheckNoError(err);
    CheckTxnDBGet(txn_db, roptions, "foo", "hello");
-    CheckTxnDBPinGet(txn_db, roptions, "foo", "hello");

    // delete from outside transaction
    rocksdb_transactiondb_delete(txn_db, woptions, "foo", 3, &err);
    CheckNoError(err);
    CheckTxnDBGet(txn_db, roptions, "foo", NULL);
-    CheckTxnDBPinGet(txn_db, roptions, "foo", NULL);

    // write batch into TransactionDB
    rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
@@ -2705,63 +2671,24 @@ int main(int argc, char** argv) {
    rocksdb_transactiondb_write(txn_db, woptions, wb, &err);
    rocksdb_writebatch_destroy(wb);
    CheckTxnDBGet(txn_db, roptions, "box", "c");
-    CheckTxnDBPinGet(txn_db, roptions, "box", "c");
    CheckNoError(err);

-    // multi get
-    {
-      const char* keys[3] = {"box", "foo", "notfound"};
-      const size_t keys_sizes[3] = {3, 3, 8};
-      char* vals[3];
-      size_t vals_sizes[3];
-      char* errs[3];
-      const char* expected[3] = {"c", NULL, NULL};
-      rocksdb_transactiondb_multi_get(txn_db, roptions, 3, keys, keys_sizes,
-                                      vals, vals_sizes, errs);
-      CheckMultiGetValues(3, vals, vals_sizes, errs, expected);
-    }
-
    // begin a transaction
    txn = rocksdb_transaction_begin(txn_db, woptions, txn_options, NULL);
    // put
    rocksdb_transaction_put(txn, "foo", 3, "hello", 5, &err);
    CheckNoError(err);
    CheckTxnGet(txn, roptions, "foo", "hello");
-    CheckTxnPinGet(txn, roptions, "foo", "hello");
-    {
-      const char* keys[3] = {"box", "foo", "notfound"};
-      const size_t keys_sizes[3] = {3, 3, 8};
-      char* vals[3];
-      size_t vals_sizes[3];
-      char* errs[3];
-      const char* expected[3] = {"c", "hello", NULL};
-      rocksdb_transaction_multi_get(txn, roptions, 3, keys, keys_sizes, vals,
-                                    vals_sizes, errs);
-      CheckMultiGetValues(3, vals, vals_sizes, errs, expected);
-    }
    // delete
    rocksdb_transaction_delete(txn, "foo", 3, &err);
    CheckNoError(err);
    CheckTxnGet(txn, roptions, "foo", NULL);
-    CheckTxnPinGet(txn, roptions, "foo", NULL);

    rocksdb_transaction_put(txn, "foo", 3, "hello", 5, &err);
    CheckNoError(err);

    // read from outside transaction, before commit
    CheckTxnDBGet(txn_db, roptions, "foo", NULL);
-    CheckTxnDBPinGet(txn_db, roptions, "foo", NULL);
-    {
-      const char* keys[3] = {"box", "foo", "notfound"};
-      const size_t keys_sizes[3] = {3, 3, 8};
-      char* vals[3];
-      size_t vals_sizes[3];
-      char* errs[3];
-      const char* expected[3] = {"c", NULL, NULL};
-      rocksdb_transactiondb_multi_get(txn_db, roptions, 3, keys, keys_sizes,
-                                      vals, vals_sizes, errs);
-      CheckMultiGetValues(3, vals, vals_sizes, errs, expected);
-    }

    // commit
    rocksdb_transaction_commit(txn, &err);
@@ -2769,18 +2696,6 @@ int main(int argc, char** argv) {

    // read from outside transaction, after commit
    CheckTxnDBGet(txn_db, roptions, "foo", "hello");
-    CheckTxnDBPinGet(txn_db, roptions, "foo", "hello");
-    {
-      const char* keys[3] = {"box", "foo", "notfound"};
-      const size_t keys_sizes[3] = {3, 3, 8};
-      char* vals[3];
-      size_t vals_sizes[3];
-      char* errs[3];
-      const char* expected[3] = {"c", "hello", NULL};
-      rocksdb_transactiondb_multi_get(txn_db, roptions, 3, keys, keys_sizes,
-                                      vals, vals_sizes, errs);
-      CheckMultiGetValues(3, vals, vals_sizes, errs, expected);
-    }

    // reuse old transaction
    txn = rocksdb_transaction_begin(txn_db, woptions, txn_options, txn);
@@ -2794,11 +2709,9 @@ int main(int argc, char** argv) {
    CheckNoError(err);

    CheckTxnDBGet(txn_db, roptions, "foo", "hello");
-    CheckTxnDBPinGet(txn_db, roptions, "foo", "hello");
    rocksdb_readoptions_set_snapshot(roptions, NULL);
    rocksdb_transactiondb_release_snapshot(txn_db, snapshot);
    CheckTxnDBGet(txn_db, roptions, "foo", "hey");
-    CheckTxnDBPinGet(txn_db, roptions, "foo", "hey");

    // iterate
    rocksdb_transaction_put(txn, "bar", 3, "hi", 2, &err);
@@ -2815,34 +2728,25 @@ int main(int argc, char** argv) {
    rocksdb_transaction_rollback(txn, &err);
    CheckNoError(err);
    CheckTxnDBGet(txn_db, roptions, "bar", NULL);
-    CheckTxnDBPinGet(txn_db, roptions, "bar", NULL);

    // save point
    rocksdb_transaction_put(txn, "foo1", 4, "hi1", 3, &err);
    rocksdb_transaction_set_savepoint(txn);
    CheckTxnGet(txn, roptions, "foo1", "hi1");
-    CheckTxnPinGet(txn, roptions, "foo1", "hi1");
    rocksdb_transaction_put(txn, "foo2", 4, "hi2", 3, &err);
    CheckTxnGet(txn, roptions, "foo2", "hi2");
-    CheckTxnPinGet(txn, roptions, "foo2", "hi2");

    // rollback to savepoint
    rocksdb_transaction_rollback_to_savepoint(txn, &err);
    CheckNoError(err);
    CheckTxnGet(txn, roptions, "foo2", NULL);
    CheckTxnGet(txn, roptions, "foo1", "hi1");
-    CheckTxnPinGet(txn, roptions, "foo2", NULL);
-    CheckTxnPinGet(txn, roptions, "foo1", "hi1");
    CheckTxnDBGet(txn_db, roptions, "foo1", NULL);
    CheckTxnDBGet(txn_db, roptions, "foo2", NULL);
-    CheckTxnDBPinGet(txn_db, roptions, "foo1", NULL);
-    CheckTxnDBPinGet(txn_db, roptions, "foo2", NULL);
    rocksdb_transaction_commit(txn, &err);
    CheckNoError(err);
    CheckTxnDBGet(txn_db, roptions, "foo1", "hi1");
    CheckTxnDBGet(txn_db, roptions, "foo2", NULL);
-    CheckTxnDBPinGet(txn_db, roptions, "foo1", "hi1");
-    CheckTxnDBPinGet(txn_db, roptions, "foo2", NULL);

    // Column families.
    rocksdb_column_family_handle_t* cfh;
@@ -2854,130 +2758,15 @@ int main(int argc, char** argv) {
                                 8, &err);
    CheckNoError(err);
    CheckTxnDBGetCF(txn_db, roptions, cfh, "cf_foo", "cf_hello");
-    CheckTxnDBPinGetCF(txn_db, roptions, cfh, "cf_foo", "cf_hello");
-    {
-      const rocksdb_column_family_handle_t* get_handles[2] = {cfh, cfh};
-      const char* keys[2] = {"cf_foo", "notfound"};
-      const size_t keys_sizes[2] = {6, 8};
-      char* vals[2];
-      size_t vals_sizes[2];
-      char* errs[2];
-      const char* expected[2] = {"cf_hello", NULL};
-      rocksdb_transactiondb_multi_get_cf(txn_db, roptions, get_handles, 2, keys,
-                                         keys_sizes, vals, vals_sizes, errs);
-      CheckMultiGetValues(2, vals, vals_sizes, errs, expected);
-    }

    rocksdb_transactiondb_delete_cf(txn_db, woptions, cfh, "cf_foo", 6, &err);
    CheckNoError(err);
    CheckTxnDBGetCF(txn_db, roptions, cfh, "cf_foo", NULL);
-    CheckTxnDBPinGetCF(txn_db, roptions, cfh, "cf_foo", NULL);

-    // flush
-    rocksdb_flushoptions_t* flush_options = rocksdb_flushoptions_create();
-    rocksdb_flushoptions_set_wait(flush_options, 1);
-    rocksdb_transactiondb_flush_wal(txn_db, 1, &err);
-    CheckNoError(err);
-    rocksdb_transactiondb_flush_cf(txn_db, flush_options, cfh, &err);
-    CheckNoError(err);
-    rocksdb_transactiondb_flush(txn_db, flush_options, &err);
-    CheckNoError(err);
-    rocksdb_flushoptions_destroy(flush_options);
-
-    // close and destroy
    rocksdb_column_family_handle_destroy(cfh);
-    rocksdb_transaction_destroy(txn);
-    rocksdb_transactiondb_close(txn_db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_transaction_options_destroy(txn_options);
-    rocksdb_transactiondb_options_destroy(txn_db_options);
-  }
-
-  StartPhase("two-phase commit");
-  {
-    // open a TransactionDB
-    txn_db_options = rocksdb_transactiondb_options_create();
-    txn_options = rocksdb_transaction_options_create();
-    rocksdb_options_set_create_if_missing(options, 1);
-    txn_db = rocksdb_transactiondb_open(options, txn_db_options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_transaction_options_set_skip_prepare(txn_options, 0);
-    txn = rocksdb_transaction_begin(txn_db, woptions, txn_options, NULL);
-    rocksdb_transaction_commit(txn, &err);
-    CheckCondition(err != NULL);
-    Free(&err);
-    err = NULL;
-    rocksdb_transaction_prepare(txn, &err);
-    CheckCondition(err != NULL);
-    Free(&err);
-    err = NULL;
-    rocksdb_transaction_set_name(txn, "txn1", 4, &err);
-    CheckNoError(err);
-    rocksdb_transaction_prepare(txn, &err);
-    CheckNoError(err);
-    rocksdb_transaction_commit(txn, &err);
-    CheckNoError(err);
-    rocksdb_transaction_destroy(txn);
-
-    // prepare 2 transactions and close db.
-    rocksdb_transaction_t* txn1 =
-        rocksdb_transaction_begin(txn_db, woptions, txn_options, NULL);
-    rocksdb_transaction_put(txn1, "bar1", 4, "1", 1, &err);
-    CheckNoError(err);
-    rocksdb_transaction_set_name(txn1, "txn1", 4, &err);
-    CheckNoError(err);
-    rocksdb_transaction_prepare(txn1, &err);
-    CheckNoError(err);
-    rocksdb_transaction_t* txn2 =
-        rocksdb_transaction_begin(txn_db, woptions, txn_options, NULL);
-    rocksdb_transaction_put(txn2, "bar2", 4, "2", 1, &err);
-    CheckNoError(err);
-    rocksdb_transaction_set_name(txn2, "txn2", 4, &err);
-    CheckNoError(err);
-    rocksdb_transaction_prepare(txn2, &err);
-    CheckNoError(err);
-    rocksdb_transaction_destroy(txn1);
-    rocksdb_transaction_destroy(txn2);
-    rocksdb_transactiondb_close(txn_db);
-    rocksdb_transaction_options_destroy(txn_options);
-    rocksdb_transactiondb_options_destroy(txn_db_options);
-
-    // reopen db and get all prepared.
-    txn_db_options = rocksdb_transactiondb_options_create();
-    txn_options = rocksdb_transaction_options_create();
-    rocksdb_options_set_error_if_exists(options, 0);
-    txn_db = rocksdb_transactiondb_open(options, txn_db_options, dbname, &err);
-    CheckNoError(err);
-    CheckTxnDBPinGet(txn_db, roptions, "bar1", NULL);
-    CheckTxnDBPinGet(txn_db, roptions, "bar2", NULL);
-    size_t cnt;
-    rocksdb_transaction_t** txns =
-        rocksdb_transactiondb_get_prepared_transactions(txn_db, &cnt);
-    CheckCondition(cnt == 2);
-    size_t i;
-    for (i = 0; i < cnt; i++) {
-      txn = txns[i];
-      size_t name_len = 0;
-      char* name = rocksdb_transaction_get_name(txn, &name_len);
-      CheckCondition(name_len == 4);
-      if (strncmp(name, "txn1", name_len) == 0) {
-        rocksdb_transaction_commit(txn, &err);
-      } else if (strncmp(name, "txn2", name_len) == 0) {
-        rocksdb_transaction_rollback(txn, &err);
-      }
-      rocksdb_free(name);
-      CheckNoError(err);
-      rocksdb_transaction_destroy(txn);
-    }
-    rocksdb_free(txns);
-    CheckTxnDBGet(txn_db, roptions, "bar1", "1");
-    CheckTxnDBGet(txn_db, roptions, "bar2", NULL);
-    rocksdb_transactiondb_put(txn_db, woptions, "bar2", 4, "2", 1, &err);
-    CheckNoError(err);

    // close and destroy
+    rocksdb_transaction_destroy(txn);
    rocksdb_transactiondb_close(txn_db);
    rocksdb_destroy_db(options, dbname, &err);
    CheckNoError(err);
@@ -3001,7 +2790,6 @@ int main(int argc, char** argv) {
    rocksdb_transaction_put(txn2, "key1", 4, "value1", 6, &err);
    CheckNoError(err);
    CheckTxnGet(txn1, roptions, "key", "value");
-    CheckTxnPinGet(txn1, roptions, "key", "value");
    rocksdb_transaction_commit(txn1, &err);
    CheckNoError(err);
    rocksdb_transaction_commit(txn2, &err);
@@ -3028,19 +2816,6 @@ int main(int argc, char** argv) {
                                              txn);
    CheckGetCF(db, roptions, cfh1, "key_cf1", "val_cf1");
    CheckTxnGetCF(txn, roptions, cfh1, "key_cf1", "val_cf1");
-    CheckTxnPinGetCF(txn, roptions, cfh1, "key_cf1", "val_cf1");
-    {
-      const rocksdb_column_family_handle_t* get_handles[3] = {cfh1, cfh2, cfh2};
-      const char* keys[3] = {"key_cf1", "key_cf2", "notfound"};
-      const size_t keys_sizes[3] = {7, 7, 8};
-      char* vals[3];
-      size_t vals_sizes[3];
-      char* errs[3];
-      const char* expected[3] = {"val_cf1", "val_cf2", NULL};
-      rocksdb_transaction_multi_get_cf(txn, roptions, get_handles, 3, keys,
-                                       keys_sizes, vals, vals_sizes, errs);
-      CheckMultiGetValues(3, vals, vals_sizes, errs, expected);
-    }

    // Check iterator with column family
    rocksdb_transaction_put_cf(txn, cfh1, "key1_cf", 7, "val1_cf", 7, &err);
@@ -3086,9 +2861,6 @@ int main(int argc, char** argv) {
    CheckTxnGetCF(txn_cf, roptions, cf_handles[0], "key", "value");
    CheckTxnGetCF(txn_cf, roptions, cf_handles[1], "key_cf1", "val_cf1");
    CheckTxnGetCF(txn_cf, roptions, cf_handles[2], "key_cf2", "val_cf2");
-    CheckTxnPinGetCF(txn_cf, roptions, cf_handles[0], "key", "value");
-    CheckTxnPinGetCF(txn_cf, roptions, cf_handles[1], "key_cf1", "val_cf1");
-    CheckTxnPinGetCF(txn_cf, roptions, cf_handles[2], "key_cf2", "val_cf2");
    rocksdb_transaction_destroy(txn_cf);
    rocksdb_options_destroy(cf_options);
    rocksdb_column_family_handle_destroy(cf_handles[0]);
@@ -3184,51 +2956,6 @@ int main(int argc, char** argv) {
    CheckNoError(err);
  }

-  StartPhase("filter_with_prefix_seek");
-  {
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_options_set_prefix_extractor(
-        options, rocksdb_slicetransform_create_fixed_prefix(1));
-    rocksdb_filterpolicy_t* filter_policy =
-        rocksdb_filterpolicy_create_bloom_full(8.0);
-    rocksdb_block_based_options_set_filter_policy(table_options, filter_policy);
-    rocksdb_options_set_block_based_table_factory(options, table_options);
-
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-
-    int i;
-    for (i = 0; i < 10; ++i) {
-      char key = '0' + (char)i;
-      rocksdb_put(db, woptions, &key, 1, "", 1, &err);
-      CheckNoError(err);
-    }
-
-    // Flush to generate an L0 so that filter will be used later.
-    rocksdb_flushoptions_t* flush_options = rocksdb_flushoptions_create();
-    rocksdb_flushoptions_set_wait(flush_options, 1);
-    rocksdb_flush(db, flush_options, &err);
-    rocksdb_flushoptions_destroy(flush_options);
-    CheckNoError(err);
-
-    rocksdb_readoptions_t* ropts = rocksdb_readoptions_create();
-    rocksdb_iterator_t* iter = rocksdb_create_iterator(db, ropts);
-
-    rocksdb_iter_seek(iter, "0", 1);
-    int cnt = 0;
-    while (rocksdb_iter_valid(iter)) {
-      ++cnt;
-      rocksdb_iter_next(iter);
-    }
-    CheckCondition(10 == cnt);
-
-    rocksdb_iter_destroy(iter);
-    rocksdb_readoptions_destroy(ropts);
-  }
-
  StartPhase("cancel_all_background_work");
  rocksdb_cancel_all_background_work(db, 1);

@@ -136,15 +136,9 @@ Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options) {
    }
  }
  if (cf_options.compression_opts.zstd_max_train_bytes > 0) {
-    if (cf_options.compression_opts.use_zstd_dict_trainer) {
-      if (!ZSTD_TrainDictionarySupported()) {
-        return Status::InvalidArgument(
-            "zstd dictionary trainer cannot be used because ZSTD 1.1.3+ "
-            "is not linked with the binary.");
-      }
-    } else if (!ZSTD_FinalizeDictionarySupported()) {
+    if (!ZSTD_TrainDictionarySupported()) {
      return Status::InvalidArgument(
-          "zstd finalizeDictionary cannot be used because ZSTD 1.4.5+ "
+          "zstd dictionary trainer cannot be used because ZSTD 1.1.3+ "
          "is not linked with the binary.");
    }
    if (cf_options.compression_opts.max_dict_bytes == 0) {
@@ -507,8 +501,7 @@ std::vector<std::string> ColumnFamilyData::GetDbPaths() const {
  return paths;
 }

-const uint32_t ColumnFamilyData::kDummyColumnFamilyDataId =
-    std::numeric_limits<uint32_t>::max();
+const uint32_t ColumnFamilyData::kDummyColumnFamilyDataId = port::kMaxUint32;

 ColumnFamilyData::ColumnFamilyData(
    uint32_t id, const std::string& name, Version* _dummy_versions,
@@ -619,26 +612,6 @@ ColumnFamilyData::ColumnFamilyData(
  }

  RecalculateWriteStallConditions(mutable_cf_options_);
-
-  if (cf_options.table_factory->IsInstanceOf(
-          TableFactory::kBlockBasedTableName()) &&
-      cf_options.table_factory->GetOptions<BlockBasedTableOptions>()) {
-    const BlockBasedTableOptions* bbto =
-        cf_options.table_factory->GetOptions<BlockBasedTableOptions>();
-    const auto& options_overrides = bbto->cache_usage_options.options_overrides;
-    const auto file_metadata_charged =
-        options_overrides.at(CacheEntryRole::kFileMetadata).charged;
-    if (bbto->block_cache &&
-        file_metadata_charged == CacheEntryRoleOptions::Decision::kEnabled) {
-      // TODO(hx235): Add a `ConcurrentCacheReservationManager` at DB scope
-      // responsible for reservation of `ObsoleteFileInfo` so that we can keep
-      // this `file_metadata_cache_res_mgr_` nonconcurrent
-      file_metadata_cache_res_mgr_.reset(new ConcurrentCacheReservationManager(
-          std::make_shared<
-              CacheReservationManagerImpl<CacheEntryRole::kFileMetadata>>(
-              bbto->block_cache)));
-    }
-  }
 }

 // DB mutex held
@@ -853,8 +826,8 @@ int GetL0ThresholdSpeedupCompaction(int level0_file_num_compaction_trigger,
  // condition.
  // Or twice as compaction trigger, if it is smaller.
  int64_t res = std::min(twice_level0_trigger, one_fourth_trigger_slowdown);
-  if (res >= std::numeric_limits<int32_t>::max()) {
-    return std::numeric_limits<int32_t>::max();
+  if (res >= port::kMaxInt32) {
+    return port::kMaxInt32;
  } else {
    // res fits in int
    return static_cast<int>(res);
@@ -1191,12 +1164,12 @@ Compaction* ColumnFamilyData::CompactRange(
    int output_level, const CompactRangeOptions& compact_range_options,
    const InternalKey* begin, const InternalKey* end,
    InternalKey** compaction_end, bool* conflict,
-    uint64_t max_file_num_to_ignore, const std::string& trim_ts) {
+    uint64_t max_file_num_to_ignore) {
  auto* result = compaction_picker_->CompactRange(
      GetName(), mutable_cf_options, mutable_db_options,
      current_->storage_info(), input_level, output_level,
      compact_range_options, begin, end, compaction_end, conflict,
-      max_file_num_to_ignore, trim_ts);
+      max_file_num_to_ignore);
  if (result != nullptr) {
    result->SetInputVersion(current_);
  }
@@ -1589,6 +1562,20 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
  return new_cfd;
 }

+// REQUIRES: DB mutex held
+void ColumnFamilySet::FreeDeadColumnFamilies() {
+  autovector<ColumnFamilyData*> to_delete;
+  for (auto cfd = dummy_cfd_->next_; cfd != dummy_cfd_; cfd = cfd->next_) {
+    if (cfd->refs_.load(std::memory_order_relaxed) == 0) {
+      to_delete.push_back(cfd);
+    }
+  }
+  for (auto cfd : to_delete) {
+    // this is very rare, so it's not a problem that we do it under a mutex
+    delete cfd;
+  }
+}
+
 // under a DB mutex AND from a write thread
 void ColumnFamilySet::RemoveColumnFamily(ColumnFamilyData* cfd) {
  auto cfd_iter = column_family_data_.find(cfd->GetID());
@@ -9,12 +9,11 @@

 #pragma once

-#include <atomic>
-#include <string>
 #include <unordered_map>
+#include <string>
 #include <vector>
+#include <atomic>

-#include "cache/cache_reservation_manager.h"
 #include "db/memtable_list.h"
 #include "db/table_cache.h"
 #include "db/table_properties_collector.h"
@@ -26,7 +25,6 @@
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
 #include "trace_replay/block_cache_tracer.h"
-#include "util/hash_containers.h"
 #include "util/thread_local.h"

 namespace ROCKSDB_NAMESPACE {
@@ -415,8 +413,7 @@ class ColumnFamilyData {
                           const CompactRangeOptions& compact_range_options,
                           const InternalKey* begin, const InternalKey* end,
                           InternalKey** compaction_end, bool* manual_conflict,
-                           uint64_t max_file_num_to_ignore,
-                           const std::string& trim_ts);
+                           uint64_t max_file_num_to_ignore);

  CompactionPicker* compaction_picker() { return compaction_picker_.get(); }
  // thread-safe
@@ -521,15 +518,10 @@ class ColumnFamilyData {

  ThreadLocalPtr* TEST_GetLocalSV() { return local_sv_.get(); }
  WriteBufferManager* write_buffer_mgr() { return write_buffer_manager_; }
-  std::shared_ptr<CacheReservationManager>
-  GetFileMetadataCacheReservationManager() {
-    return file_metadata_cache_res_mgr_;
-  }
-
-  static const uint32_t kDummyColumnFamilyDataId;

 private:
  friend class ColumnFamilySet;
+  static const uint32_t kDummyColumnFamilyDataId;
  ColumnFamilyData(uint32_t id, const std::string& name,
                   Version* dummy_versions, Cache* table_cache,
                   WriteBufferManager* write_buffer_manager,
@@ -623,10 +615,6 @@ class ColumnFamilyData {
  bool db_paths_registered_;

  std::string full_history_ts_low_;
-
-  // For charging memory usage of file metadata created for newly added files to
-  // a Version associated with this CFD
-  std::shared_ptr<CacheReservationManager> file_metadata_cache_res_mgr_;
 };

 // ColumnFamilySet has interesting thread-safety requirements
@@ -639,8 +627,10 @@ class ColumnFamilyData {
 // held and it needs to be executed from the write thread. SetDropped() also
 // guarantees that it will be called only from single-threaded LogAndApply(),
 // but this condition is not that important.
-// * Iteration -- hold DB mutex. If you want to release the DB mutex in the
-// body of the iteration, wrap in a RefedColumnFamilySet.
+// * Iteration -- hold DB mutex, but you can release it in the body of
+// iteration. If you release DB mutex in body, reference the column
+// family before the mutex and unreference after you unlock, since the column
+// family might get dropped when the DB mutex is released
 // * GetDefault() -- thread safe
 // * GetColumnFamily() -- either inside of DB mutex or from a write thread
 // * GetNextColumnFamilyID(), GetMaxColumnFamily(), UpdateMaxColumnFamily(),
@@ -652,12 +642,17 @@ class ColumnFamilySet {
   public:
    explicit iterator(ColumnFamilyData* cfd)
        : current_(cfd) {}
-    // NOTE: minimum operators for for-loop iteration
    iterator& operator++() {
-      current_ = current_->next_;
+      // dropped column families might still be included in this iteration
+      // (we're only removing them when client drops the last reference to the
+      // column family).
+      // dummy is never dead, so this will never be infinite
+      do {
+        current_ = current_->next_;
+      } while (current_->refs_.load(std::memory_order_relaxed) == 0);
      return *this;
    }
-    bool operator!=(const iterator& other) const {
+    bool operator!=(const iterator& other) {
      return this->current_ != other.current_;
    }
    ColumnFamilyData* operator*() { return current_; }
@@ -696,6 +691,10 @@ class ColumnFamilySet {
  iterator begin() { return iterator(dummy_cfd_->next_); }
  iterator end() { return iterator(dummy_cfd_); }

+  // REQUIRES: DB mutex held
+  // Don't call while iterating over ColumnFamilySet
+  void FreeDeadColumnFamilies();
+
  Cache* get_table_cache() { return table_cache_; }

  WriteBufferManager* write_buffer_manager() { return write_buffer_manager_; }
@@ -715,8 +714,8 @@ class ColumnFamilySet {
  // * when reading, at least one condition needs to be satisfied:
  // 1. DB mutex locked
  // 2. accessed from a single-threaded write thread
-  UnorderedMap<std::string, uint32_t> column_families_;
-  UnorderedMap<uint32_t, ColumnFamilyData*> column_family_data_;
+  std::unordered_map<std::string, uint32_t> column_families_;
+  std::unordered_map<uint32_t, ColumnFamilyData*> column_family_data_;

  uint32_t max_column_family_;
  const FileOptions file_options_;
@@ -738,55 +737,6 @@ class ColumnFamilySet {
  std::string db_session_id_;
 };

-// A wrapper for ColumnFamilySet that supports releasing DB mutex during each
-// iteration over the iterator, because the cfd is Refed and Unrefed during
-// each iteration to prevent concurrent CF drop from destroying it (until
-// Unref).
-class RefedColumnFamilySet {
- public:
-  explicit RefedColumnFamilySet(ColumnFamilySet* cfs) : wrapped_(cfs) {}
-
-  class iterator {
-   public:
-    explicit iterator(ColumnFamilySet::iterator wrapped) : wrapped_(wrapped) {
-      MaybeRef(*wrapped_);
-    }
-    ~iterator() { MaybeUnref(*wrapped_); }
-    inline void MaybeRef(ColumnFamilyData* cfd) {
-      if (cfd->GetID() != ColumnFamilyData::kDummyColumnFamilyDataId) {
-        cfd->Ref();
-      }
-    }
-    inline void MaybeUnref(ColumnFamilyData* cfd) {
-      if (cfd->GetID() != ColumnFamilyData::kDummyColumnFamilyDataId) {
-        cfd->UnrefAndTryDelete();
-      }
-    }
-    // NOTE: minimum operators for for-loop iteration
-    inline iterator& operator++() {
-      ColumnFamilyData* old = *wrapped_;
-      ++wrapped_;
-      // Can only unref & potentially free cfd after accessing its next_
-      MaybeUnref(old);
-      MaybeRef(*wrapped_);
-      return *this;
-    }
-    inline bool operator!=(const iterator& other) const {
-      return this->wrapped_ != other.wrapped_;
-    }
-    inline ColumnFamilyData* operator*() { return *wrapped_; }
-
-   private:
-    ColumnFamilySet::iterator wrapped_;
-  };
-
-  iterator begin() { return iterator(wrapped_->begin()); }
-  iterator end() { return iterator(wrapped_->end()); }
-
- private:
-  ColumnFamilySet* wrapped_;
-};
-
 // We use ColumnFamilyMemTablesImpl to provide WriteBatch a way to access
 // memtables of different column families (specified by ID in the write batch)
 class ColumnFamilyMemTablesImpl : public ColumnFamilyMemTables {
@@ -383,7 +383,7 @@ class ColumnFamilyTestBase : public testing::Test {

  int NumTableFilesAtLevel(int level, int cf) {
    return GetProperty(cf,
-                       "rocksdb.num-files-at-level" + std::to_string(level));
+                       "rocksdb.num-files-at-level" + ToString(level));
  }

 #ifndef ROCKSDB_LITE
@@ -783,7 +783,7 @@ TEST_P(ColumnFamilyTest, BulkAddDrop) {
  std::vector<std::string> cf_names;
  std::vector<ColumnFamilyHandle*> cf_handles;
  for (int i = 1; i <= kNumCF; i++) {
-    cf_names.push_back("cf1-" + std::to_string(i));
+    cf_names.push_back("cf1-" + ToString(i));
  }
  ASSERT_OK(db_->CreateColumnFamilies(cf_options, cf_names, &cf_handles));
  for (int i = 1; i <= kNumCF; i++) {
@@ -796,8 +796,7 @@ TEST_P(ColumnFamilyTest, BulkAddDrop) {
  }
  cf_handles.clear();
  for (int i = 1; i <= kNumCF; i++) {
-    cf_descriptors.emplace_back("cf2-" + std::to_string(i),
-                                ColumnFamilyOptions());
+    cf_descriptors.emplace_back("cf2-" + ToString(i), ColumnFamilyOptions());
  }
  ASSERT_OK(db_->CreateColumnFamilies(cf_descriptors, &cf_handles));
  for (int i = 1; i <= kNumCF; i++) {
@@ -821,7 +820,7 @@ TEST_P(ColumnFamilyTest, DropTest) {
    Open({"default"});
    CreateColumnFamiliesAndReopen({"pikachu"});
    for (int i = 0; i < 100; ++i) {
-      ASSERT_OK(Put(1, std::to_string(i), "bar" + std::to_string(i)));
+      ASSERT_OK(Put(1, ToString(i), "bar" + ToString(i)));
    }
    ASSERT_OK(Flush(1));

@@ -1345,7 +1344,7 @@ TEST_P(ColumnFamilyTest, DifferentCompactionStyles) {
    PutRandomData(1, 10, 12000);
    PutRandomData(1, 1, 10);
    WaitForFlush(1);
-    AssertFilesPerLevel(std::to_string(i + 1), 1);
+    AssertFilesPerLevel(ToString(i + 1), 1);
  }

  // SETUP column family "two" -- level style with 4 levels
@@ -1353,7 +1352,7 @@ TEST_P(ColumnFamilyTest, DifferentCompactionStyles) {
    PutRandomData(2, 10, 12000);
    PutRandomData(2, 1, 10);
    WaitForFlush(2);
-    AssertFilesPerLevel(std::to_string(i + 1), 2);
+    AssertFilesPerLevel(ToString(i + 1), 2);
  }

  // TRIGGER compaction "one"
@@ -1417,17 +1416,18 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
    PutRandomData(1, 10, 12000, true);
    PutRandomData(1, 1, 10, true);
    WaitForFlush(1);
-    AssertFilesPerLevel(std::to_string(i + 1), 1);
+    AssertFilesPerLevel(ToString(i + 1), 1);
  }
-  std::atomic_bool cf_1_1{true};
+  bool cf_1_1 = true;
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
      {{"ColumnFamilyTest::MultiManual:4", "ColumnFamilyTest::MultiManual:1"},
       {"ColumnFamilyTest::MultiManual:2", "ColumnFamilyTest::MultiManual:5"},
       {"ColumnFamilyTest::MultiManual:2", "ColumnFamilyTest::MultiManual:3"}});
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
-        if (cf_1_1.exchange(false)) {
+        if (cf_1_1) {
          TEST_SYNC_POINT("ColumnFamilyTest::MultiManual:4");
+          cf_1_1 = false;
          TEST_SYNC_POINT("ColumnFamilyTest::MultiManual:3");
        }
      });
@@ -1446,7 +1446,7 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
    PutRandomData(2, 10, 12000);
    PutRandomData(2, 1, 10);
    WaitForFlush(2);
-    AssertFilesPerLevel(std::to_string(i + 1), 2);
+    AssertFilesPerLevel(ToString(i + 1), 2);
  }
  threads.emplace_back([&] {
    TEST_SYNC_POINT("ColumnFamilyTest::MultiManual:1");
@@ -1514,14 +1514,15 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
  auto stop_token =
      dbfull()->TEST_write_controler().GetCompactionPressureToken();

-  std::atomic_bool cf_1_1{true};
+  bool cf_1_1 = true;
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
      {{"ColumnFamilyTest::AutoManual:4", "ColumnFamilyTest::AutoManual:1"},
       {"ColumnFamilyTest::AutoManual:2", "ColumnFamilyTest::AutoManual:5"},
       {"ColumnFamilyTest::AutoManual:2", "ColumnFamilyTest::AutoManual:3"}});
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
-        if (cf_1_1.exchange(false)) {
+        if (cf_1_1) {
+          cf_1_1 = false;
          TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:4");
          TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:3");
        }
@@ -1532,7 +1533,7 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
    PutRandomData(1, 10, 12000, true);
    PutRandomData(1, 1, 10, true);
    WaitForFlush(1);
-    AssertFilesPerLevel(std::to_string(i + 1), 1);
+    AssertFilesPerLevel(ToString(i + 1), 1);
  }

  TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:1");
@@ -1542,7 +1543,7 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
    PutRandomData(2, 10, 12000);
    PutRandomData(2, 1, 10);
    WaitForFlush(2);
-    AssertFilesPerLevel(std::to_string(i + 1), 2);
+    AssertFilesPerLevel(ToString(i + 1), 2);
  }
  ROCKSDB_NAMESPACE::port::Thread threads([&] {
    CompactRangeOptions compact_options;
@@ -1614,21 +1615,23 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
    PutRandomData(1, 10, 12000, true);
    PutRandomData(1, 1, 10, true);
    WaitForFlush(1);
-    AssertFilesPerLevel(std::to_string(i + 1), 1);
+    AssertFilesPerLevel(ToString(i + 1), 1);
  }
-  std::atomic_bool cf_1_1{true};
-  std::atomic_bool cf_1_2{true};
+  bool cf_1_1 = true;
+  bool cf_1_2 = true;
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
      {{"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:1"},
       {"ColumnFamilyTest::ManualAuto:5", "ColumnFamilyTest::ManualAuto:2"},
       {"ColumnFamilyTest::ManualAuto:2", "ColumnFamilyTest::ManualAuto:3"}});
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
-        if (cf_1_1.exchange(false)) {
+        if (cf_1_1) {
          TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:4");
+          cf_1_1 = false;
          TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:3");
-        } else if (cf_1_2.exchange(false)) {
+        } else if (cf_1_2) {
          TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:2");
+          cf_1_2 = false;
        }
      });

@@ -1647,7 +1650,7 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
    PutRandomData(2, 10, 12000);
    PutRandomData(2, 1, 10);
    WaitForFlush(2);
-    AssertFilesPerLevel(std::to_string(i + 1), 2);
+    AssertFilesPerLevel(ToString(i + 1), 2);
  }
  TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:5");
  threads.join();
@@ -1706,10 +1709,10 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
    PutRandomData(1, 10, 12000, true);
    PutRandomData(1, 1, 10, true);
    WaitForFlush(1);
-    AssertFilesPerLevel(std::to_string(i + 1), 1);
+    AssertFilesPerLevel(ToString(i + 1), 1);
  }
-  std::atomic_bool cf_1_1{true};
-  std::atomic_bool cf_1_2{true};
+  bool cf_1_1 = true;
+  bool cf_1_2 = true;
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
      {{"ColumnFamilyTest::ManualManual:4", "ColumnFamilyTest::ManualManual:2"},
       {"ColumnFamilyTest::ManualManual:4", "ColumnFamilyTest::ManualManual:5"},
@@ -1718,11 +1721,13 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
        "ColumnFamilyTest::ManualManual:3"}});
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
-        if (cf_1_1.exchange(false)) {
+        if (cf_1_1) {
          TEST_SYNC_POINT("ColumnFamilyTest::ManualManual:4");
+          cf_1_1 = false;
          TEST_SYNC_POINT("ColumnFamilyTest::ManualManual:3");
-        } else if (cf_1_2.exchange(false)) {
+        } else if (cf_1_2) {
          TEST_SYNC_POINT("ColumnFamilyTest::ManualManual:2");
+          cf_1_2 = false;
        }
      });

@@ -1743,8 +1748,8 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
    PutRandomData(1, 10, 12000, true);
    PutRandomData(1, 1, 10, true);
    WaitForFlush(1);
-    AssertFilesPerLevel(
-        std::to_string(one.level0_file_num_compaction_trigger + i), 1);
+    AssertFilesPerLevel(ToString(one.level0_file_num_compaction_trigger + i),
+                        1);
  }

  ROCKSDB_NAMESPACE::port::Thread threads1([&] {
@@ -1806,10 +1811,10 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
    PutRandomData(1, 10, 12000, true);
    PutRandomData(1, 1, 10, true);
    WaitForFlush(1);
-    AssertFilesPerLevel(std::to_string(i + 1), 1);
+    AssertFilesPerLevel(ToString(i + 1), 1);
  }
-  std::atomic_bool cf_1_1{true};
-  std::atomic_bool cf_1_2{true};
+  bool cf_1_1 = true;
+  bool cf_1_2 = true;
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
      {{"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:2"},
       {"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:5"},
@@ -1817,11 +1822,13 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
       {"ColumnFamilyTest::ManualAuto:1", "ColumnFamilyTest::ManualAuto:3"}});
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
-        if (cf_1_1.exchange(false)) {
+        if (cf_1_1) {
          TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:4");
+          cf_1_1 = false;
          TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:3");
-        } else if (cf_1_2.exchange(false)) {
+        } else if (cf_1_2) {
          TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:2");
+          cf_1_2 = false;
        }
      });

@@ -1842,8 +1849,8 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
    PutRandomData(1, 10, 12000, true);
    PutRandomData(1, 1, 10, true);
    WaitForFlush(1);
-    AssertFilesPerLevel(
-        std::to_string(one.level0_file_num_compaction_trigger + i), 1);
+    AssertFilesPerLevel(ToString(one.level0_file_num_compaction_trigger + i),
+                        1);
  }

  TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:1");
@@ -1897,10 +1904,10 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
    PutRandomData(1, 10, 12000, true);
    PutRandomData(1, 1, 10, true);
    WaitForFlush(1);
-    AssertFilesPerLevel(std::to_string(i + 1), 1);
+    AssertFilesPerLevel(ToString(i + 1), 1);
  }
-  std::atomic_bool cf_1_1{true};
-  std::atomic_bool cf_1_2{true};
+  bool cf_1_1 = true;
+  bool cf_1_2 = true;
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
      {{"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:2"},
       {"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:5"},
@@ -1910,11 +1917,13 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
       {"ColumnFamilyTest::ManualAuto:1", "ColumnFamilyTest::ManualAuto:3"}});
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
-        if (cf_1_1.exchange(false)) {
+        if (cf_1_1) {
          TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:4");
+          cf_1_1 = false;
          TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:3");
-        } else if (cf_1_2.exchange(false)) {
+        } else if (cf_1_2) {
          TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:2");
+          cf_1_2 = false;
        }
      });

@@ -1933,8 +1942,8 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
    PutRandomData(1, 10, 12000, true);
    PutRandomData(1, 1, 10, true);
    WaitForFlush(1);
-    AssertFilesPerLevel(
-        std::to_string(one.level0_file_num_compaction_trigger + i), 1);
+    AssertFilesPerLevel(ToString(one.level0_file_num_compaction_trigger + i),
+                        1);
  }

  TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:1");
@@ -1989,8 +1998,8 @@ TEST_P(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
  auto stop_token =
      dbfull()->TEST_write_controler().GetCompactionPressureToken();

-  std::atomic_bool cf_1_1{true};
-  std::atomic_bool cf_1_2{true};
+  bool cf_1_1 = true;
+  bool cf_1_2 = true;
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
      {{"ColumnFamilyTest::AutoManual:4", "ColumnFamilyTest::AutoManual:2"},
       {"ColumnFamilyTest::AutoManual:4", "ColumnFamilyTest::AutoManual:5"},
@@ -1998,11 +2007,13 @@ TEST_P(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
        "ColumnFamilyTest::AutoManual:3"}});
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
-        if (cf_1_1.exchange(false)) {
+        if (cf_1_1) {
          TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:4");
+          cf_1_1 = false;
          TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:3");
-        } else if (cf_1_2.exchange(false)) {
+        } else if (cf_1_2) {
          TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:2");
+          cf_1_2 = false;
        }
      });

@@ -2013,7 +2024,7 @@ TEST_P(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
    PutRandomData(1, 10, 12000, true);
    PutRandomData(1, 1, 10, true);
    WaitForFlush(1);
-    AssertFilesPerLevel(std::to_string(i + 1), 1);
+    AssertFilesPerLevel(ToString(i + 1), 1);
  }

  TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:5");
@@ -91,8 +91,8 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
  // create couple files
  // Background compaction starts and waits in BackgroundCallCompaction:0
  for (int i = 0; i < kLevel0Trigger * 4; ++i) {
-    ASSERT_OK(db->Put(WriteOptions(), std::to_string(i), ""));
-    ASSERT_OK(db->Put(WriteOptions(), std::to_string(100 - i), ""));
+    ASSERT_OK(db->Put(WriteOptions(), ToString(i), ""));
+    ASSERT_OK(db->Put(WriteOptions(), ToString(100 - i), ""));
    ASSERT_OK(db->Flush(FlushOptions()));
  }

@@ -136,20 +136,17 @@ TEST_F(CompactFilesTest, MultipleLevel) {
  // create couple files in L0, L3, L4 and L5
  for (int i = 5; i > 2; --i) {
    collector->ClearFlushedFiles();
-    ASSERT_OK(db->Put(WriteOptions(), std::to_string(i), ""));
+    ASSERT_OK(db->Put(WriteOptions(), ToString(i), ""));
    ASSERT_OK(db->Flush(FlushOptions()));
-    // Ensure background work is fully finished including listener callbacks
-    // before accessing listener state.
-    ASSERT_OK(static_cast_with_check<DBImpl>(db)->TEST_WaitForBackgroundWork());
    auto l0_files = collector->GetFlushedFiles();
    ASSERT_OK(db->CompactFiles(CompactionOptions(), l0_files, i));

    std::string prop;
-    ASSERT_TRUE(db->GetProperty(
-        "rocksdb.num-files-at-level" + std::to_string(i), &prop));
+    ASSERT_TRUE(
+        db->GetProperty("rocksdb.num-files-at-level" + ToString(i), &prop));
    ASSERT_EQ("1", prop);
  }
-  ASSERT_OK(db->Put(WriteOptions(), std::to_string(0), ""));
+  ASSERT_OK(db->Put(WriteOptions(), ToString(0), ""));
  ASSERT_OK(db->Flush(FlushOptions()));

  ColumnFamilyMetaData meta;
@@ -218,7 +215,7 @@ TEST_F(CompactFilesTest, ObsoleteFiles) {

  // create couple files
  for (int i = 1000; i < 2000; ++i) {
-    ASSERT_OK(db->Put(WriteOptions(), std::to_string(i),
+    ASSERT_OK(db->Put(WriteOptions(), ToString(i),
                      std::string(kWriteBufferSize / 10, 'a' + (i % 26))));
  }

@@ -257,14 +254,14 @@ TEST_F(CompactFilesTest, NotCutOutputOnLevel0) {

  // create couple files
  for (int i = 0; i < 500; ++i) {
-    ASSERT_OK(db->Put(WriteOptions(), std::to_string(i),
+    ASSERT_OK(db->Put(WriteOptions(), ToString(i),
                      std::string(1000, 'a' + (i % 26))));
  }
  ASSERT_OK(static_cast_with_check<DBImpl>(db)->TEST_WaitForFlushMemTable());
  auto l0_files_1 = collector->GetFlushedFiles();
  collector->ClearFlushedFiles();
  for (int i = 0; i < 500; ++i) {
-    ASSERT_OK(db->Put(WriteOptions(), std::to_string(i),
+    ASSERT_OK(db->Put(WriteOptions(), ToString(i),
                      std::string(1000, 'a' + (i % 26))));
  }
  ASSERT_OK(static_cast_with_check<DBImpl>(db)->TEST_WaitForFlushMemTable());
@@ -295,13 +292,10 @@ TEST_F(CompactFilesTest, CapturingPendingFiles) {

  // Create 5 files.
  for (int i = 0; i < 5; ++i) {
-    ASSERT_OK(db->Put(WriteOptions(), "key" + std::to_string(i), "value"));
+    ASSERT_OK(db->Put(WriteOptions(), "key" + ToString(i), "value"));
    ASSERT_OK(db->Flush(FlushOptions()));
  }

-  // Ensure background work is fully finished including listener callbacks
-  // before accessing listener state.
-  ASSERT_OK(static_cast_with_check<DBImpl>(db)->TEST_WaitForBackgroundWork());
  auto l0_files = collector->GetFlushedFiles();
  EXPECT_EQ(5, l0_files.size());

@@ -420,9 +414,6 @@ TEST_F(CompactFilesTest, SentinelCompressionType) {
    ASSERT_OK(db->Put(WriteOptions(), "key", "val"));
    ASSERT_OK(db->Flush(FlushOptions()));

-    // Ensure background work is fully finished including listener callbacks
-    // before accessing listener state.
-    ASSERT_OK(static_cast_with_check<DBImpl>(db)->TEST_WaitForBackgroundWork());
    auto l0_files = collector->GetFlushedFiles();
    ASSERT_EQ(1, l0_files.size());

@@ -465,7 +456,7 @@ TEST_F(CompactFilesTest, GetCompactionJobInfo) {

  // create couple files
  for (int i = 0; i < 500; ++i) {
-    ASSERT_OK(db->Put(WriteOptions(), std::to_string(i),
+    ASSERT_OK(db->Put(WriteOptions(), ToString(i),
                      std::string(1000, 'a' + (i % 26))));
  }
  ASSERT_OK(static_cast_with_check<DBImpl>(db)->TEST_WaitForFlushMemTable());
@@ -213,10 +213,8 @@ Compaction::Compaction(
    uint32_t _output_path_id, CompressionType _compression,
    CompressionOptions _compression_opts, Temperature _output_temperature,
    uint32_t _max_subcompactions, std::vector<FileMetaData*> _grandparents,
-    bool _manual_compaction, const std::string& _trim_ts, double _score,
-    bool _deletion_compaction, CompactionReason _compaction_reason,
-    BlobGarbageCollectionPolicy _blob_garbage_collection_policy,
-    double _blob_garbage_collection_age_cutoff)
+    bool _manual_compaction, double _score, bool _deletion_compaction,
+    CompactionReason _compaction_reason)
    : input_vstorage_(vstorage),
      start_level_(_inputs[0].level),
      output_level_(_output_level),
@@ -239,22 +237,9 @@ Compaction::Compaction(
      bottommost_level_(IsBottommostLevel(output_level_, vstorage, inputs_)),
      is_full_compaction_(IsFullCompaction(vstorage, inputs_)),
      is_manual_compaction_(_manual_compaction),
-      trim_ts_(_trim_ts),
      is_trivial_move_(false),
      compaction_reason_(_compaction_reason),
-      notify_on_compaction_completion_(false),
-      enable_blob_garbage_collection_(
-          _blob_garbage_collection_policy == BlobGarbageCollectionPolicy::kForce
-              ? true
-              : (_blob_garbage_collection_policy ==
-                         BlobGarbageCollectionPolicy::kDisable
-                     ? false
-                     : mutable_cf_options()->enable_blob_garbage_collection)),
-      blob_garbage_collection_age_cutoff_(
-          _blob_garbage_collection_age_cutoff < 0 ||
-                  _blob_garbage_collection_age_cutoff > 1
-              ? mutable_cf_options()->blob_garbage_collection_age_cutoff
-              : _blob_garbage_collection_age_cutoff) {
+      notify_on_compaction_completion_(false) {
  MarkFilesBeingCompacted(true);
  if (is_manual_compaction_) {
    compaction_reason_ = CompactionReason::kManualCompaction;
@@ -292,9 +277,9 @@ Compaction::~Compaction() {

 bool Compaction::InputCompressionMatchesOutput() const {
  int base_level = input_vstorage_->base_level();
-  bool matches =
-      (GetCompressionType(input_vstorage_, mutable_cf_options_, start_level_,
-                          base_level) == output_compression_);
+  bool matches = (GetCompressionType(immutable_options_, input_vstorage_,
+                                     mutable_cf_options_, start_level_,
+                                     base_level) == output_compression_);
  if (matches) {
    TEST_SYNC_POINT("Compaction::InputCompressionMatchesOutput:Matches");
    return true;
@@ -333,14 +318,13 @@ bool Compaction::IsTrivialMove() const {
  // Used in universal compaction, where trivial move can be done if the
  // input files are non overlapping
  if ((mutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
-      (output_level_ != 0) &&
-      (cfd_->ioptions()->compaction_style == kCompactionStyleUniversal)) {
+      (output_level_ != 0)) {
    return is_trivial_move_;
  }

  if (!(start_level_ != output_level_ && num_input_levels() == 1 &&
-        input(0, 0)->fd.GetPathId() == output_path_id() &&
-        InputCompressionMatchesOutput())) {
+          input(0, 0)->fd.GetPathId() == output_path_id() &&
+          InputCompressionMatchesOutput())) {
    return false;
  }

@@ -532,7 +516,7 @@ uint64_t Compaction::OutputFilePreallocationSize() const {
    }
  }

-  if (max_output_file_size_ != std::numeric_limits<uint64_t>::max() &&
+  if (max_output_file_size_ != port::kMaxUint64 &&
      (immutable_options_.compaction_style == kCompactionStyleLevel ||
       output_level() > 0)) {
    preallocation_size = std::min(max_output_file_size_, preallocation_size);
@@ -630,7 +614,7 @@ bool Compaction::DoesInputReferenceBlobFiles() const {

 uint64_t Compaction::MinInputFileOldestAncesterTime(
    const InternalKey* start, const InternalKey* end) const {
-  uint64_t min_oldest_ancester_time = std::numeric_limits<uint64_t>::max();
+  uint64_t min_oldest_ancester_time = port::kMaxUint64;
  const InternalKeyComparator& icmp =
      column_family_data()->internal_comparator();
  for (const auto& level_files : inputs_) {
@@ -79,12 +79,9 @@ class Compaction {
             CompressionOptions compression_opts,
             Temperature output_temperature, uint32_t max_subcompactions,
             std::vector<FileMetaData*> grandparents,
-             bool manual_compaction = false, const std::string& trim_ts = "",
-             double score = -1, bool deletion_compaction = false,
-             CompactionReason compaction_reason = CompactionReason::kUnknown,
-             BlobGarbageCollectionPolicy blob_garbage_collection_policy =
-                 BlobGarbageCollectionPolicy::kUseDefault,
-             double blob_garbage_collection_age_cutoff = -1);
+             bool manual_compaction = false, double score = -1,
+             bool deletion_compaction = false,
+             CompactionReason compaction_reason = CompactionReason::kUnknown);

  // No copying allowed
  Compaction(const Compaction&) = delete;
@@ -211,8 +208,6 @@ class Compaction {
  // Was this compaction triggered manually by the client?
  bool is_manual_compaction() const { return is_manual_compaction_; }

-  std::string trim_ts() const { return trim_ts_; }
-
  // Used when allow_trivial_move option is set in
  // Universal compaction. If all the input files are
  // non overlapping, then is_trivial_move_ variable
@@ -297,7 +292,7 @@ class Compaction {

  int GetInputBaseLevel() const;

-  CompactionReason compaction_reason() const { return compaction_reason_; }
+  CompactionReason compaction_reason() { return compaction_reason_; }

  const std::vector<FileMetaData*>& grandparents() const {
    return grandparents_;
@@ -309,14 +304,6 @@ class Compaction {

  uint32_t max_subcompactions() const { return max_subcompactions_; }

-  bool enable_blob_garbage_collection() const {
-    return enable_blob_garbage_collection_;
-  }
-
-  double blob_garbage_collection_age_cutoff() const {
-    return blob_garbage_collection_age_cutoff_;
-  }
-
  // start and end are sub compact range. Null if no boundary.
  // This is used to filter out some input files' ancester's time range.
  uint64_t MinInputFileOldestAncesterTime(const InternalKey* start,
@@ -343,9 +330,8 @@ class Compaction {

  // 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.
+  // 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);

@@ -360,7 +346,7 @@ class Compaction {

  VersionStorageInfo* input_vstorage_;

-  const int start_level_;   // the lowest level to be compacted
+  const int start_level_;    // the lowest level to be compacted
  const int output_level_;  // levels to which output files are stored
  uint64_t max_output_file_size_;
  uint64_t max_compaction_bytes_;
@@ -371,7 +357,7 @@ class Compaction {
  VersionEdit edit_;
  const int number_levels_;
  ColumnFamilyData* cfd_;
-  Arena arena_;  // Arena used to allocate space for file_levels_
+  Arena arena_;          // Arena used to allocate space for file_levels_

  const uint32_t output_path_id_;
  CompressionType output_compression_;
@@ -389,7 +375,7 @@ class Compaction {
  // State used to check for number of overlapping grandparent files
  // (grandparent == "output_level_ + 1")
  std::vector<FileMetaData*> grandparents_;
-  const double score_;  // score that was used to pick this compaction.
+  const double score_;         // score that was used to pick this compaction.

  // Is this compaction creating a file in the bottom most level?
  const bool bottommost_level_;
@@ -399,9 +385,6 @@ class Compaction {
  // Is this compaction requested by the client?
  const bool is_manual_compaction_;

-  // The data with timestamp > trim_ts_ will be removed
-  const std::string trim_ts_;
-
  // True if we can do trivial move in Universal multi level
  // compaction
  bool is_trivial_move_;
@@ -424,12 +407,6 @@ class Compaction {
  // Notify on compaction completion only if listener was notified on compaction
  // begin.
  bool notify_on_compaction_completion_;
-
-  // Enable/disable GC collection for blobs during compaction.
-  bool enable_blob_garbage_collection_;
-
-  // Blob garbage collection age cutoff.
-  double blob_garbage_collection_age_cutoff_;
 };

 // Return sum of sizes of all files in `files`.
@@ -24,39 +24,42 @@ CompactionIterator::CompactionIterator(
    InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
    SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
-    SequenceNumber job_snapshot, const SnapshotChecker* snapshot_checker,
-    Env* env, bool report_detailed_time, bool expect_valid_internal_key,
+    const SnapshotChecker* snapshot_checker, Env* env,
+    bool report_detailed_time, bool expect_valid_internal_key,
    CompactionRangeDelAggregator* range_del_agg,
    BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
-    bool enforce_single_del_contracts,
-    const std::atomic<bool>& manual_compaction_canceled,
    const Compaction* compaction, const CompactionFilter* compaction_filter,
    const std::atomic<bool>* shutting_down,
+    const SequenceNumber preserve_deletes_seqnum,
+    const std::atomic<int>* manual_compaction_paused,
+    const std::atomic<bool>* manual_compaction_canceled,
    const std::shared_ptr<Logger> info_log,
    const std::string* full_history_ts_low)
    : CompactionIterator(
          input, cmp, merge_helper, last_sequence, snapshots,
-          earliest_write_conflict_snapshot, job_snapshot, snapshot_checker, env,
+          earliest_write_conflict_snapshot, snapshot_checker, env,
          report_detailed_time, expect_valid_internal_key, range_del_agg,
-          blob_file_builder, allow_data_in_errors, enforce_single_del_contracts,
-          manual_compaction_canceled,
+          blob_file_builder, allow_data_in_errors,
          std::unique_ptr<CompactionProxy>(
              compaction ? new RealCompaction(compaction) : nullptr),
-          compaction_filter, shutting_down, info_log, full_history_ts_low) {}
+          compaction_filter, shutting_down, preserve_deletes_seqnum,
+          manual_compaction_paused, manual_compaction_canceled, info_log,
+          full_history_ts_low) {}

 CompactionIterator::CompactionIterator(
    InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
    SequenceNumber /*last_sequence*/, std::vector<SequenceNumber>* snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
-    SequenceNumber job_snapshot, const SnapshotChecker* snapshot_checker,
-    Env* env, bool report_detailed_time, bool expect_valid_internal_key,
+    const SnapshotChecker* snapshot_checker, Env* env,
+    bool report_detailed_time, bool expect_valid_internal_key,
    CompactionRangeDelAggregator* range_del_agg,
    BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
-    bool enforce_single_del_contracts,
-    const std::atomic<bool>& manual_compaction_canceled,
    std::unique_ptr<CompactionProxy> compaction,
    const CompactionFilter* compaction_filter,
    const std::atomic<bool>* shutting_down,
+    const SequenceNumber preserve_deletes_seqnum,
+    const std::atomic<int>* manual_compaction_paused,
+    const std::atomic<bool>* manual_compaction_canceled,
    const std::shared_ptr<Logger> info_log,
    const std::string* full_history_ts_low)
    : input_(input, cmp,
@@ -65,7 +68,6 @@ CompactionIterator::CompactionIterator(
      merge_helper_(merge_helper),
      snapshots_(snapshots),
      earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
-      job_snapshot_(job_snapshot),
      snapshot_checker_(snapshot_checker),
      env_(env),
      clock_(env_->GetSystemClock().get()),
@@ -76,10 +78,11 @@ CompactionIterator::CompactionIterator(
      compaction_(std::move(compaction)),
      compaction_filter_(compaction_filter),
      shutting_down_(shutting_down),
+      manual_compaction_paused_(manual_compaction_paused),
      manual_compaction_canceled_(manual_compaction_canceled),
+      preserve_deletes_seqnum_(preserve_deletes_seqnum),
      info_log_(info_log),
      allow_data_in_errors_(allow_data_in_errors),
-      enforce_single_del_contracts_(enforce_single_del_contracts),
      timestamp_size_(cmp_ ? cmp_->timestamp_size() : 0),
      full_history_ts_low_(full_history_ts_low),
      current_user_key_sequence_(0),
@@ -157,12 +160,10 @@ void CompactionIterator::Next() {
      Status s = ParseInternalKey(key_, &ikey_, allow_data_in_errors_);
      // MergeUntil stops when it encounters a corrupt key and does not
      // include them in the result, so we expect the keys here to be valid.
+      assert(s.ok());
      if (!s.ok()) {
-        ROCKS_LOG_FATAL(
-            info_log_, "Invalid ikey %s in compaction. %s",
-            allow_data_in_errors_ ? key_.ToString(true).c_str() : "hidden",
-            s.getState());
-        assert(false);
+        ROCKS_LOG_FATAL(info_log_, "Invalid key in compaction. %s",
+                        s.getState());
      }

      // Keep current_key_ in sync.
@@ -236,10 +237,6 @@ bool CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
          return false;
        }

-        TEST_SYNC_POINT_CALLBACK(
-            "CompactionIterator::InvokeFilterIfNeeded::TamperWithBlobIndex",
-            &value_);
-
        // For integrated BlobDB impl, CompactionIterator reads blob value.
        // For Stacked BlobDB impl, the corresponding CompactionFilter's
        // FilterV2 method should read the blob value.
@@ -309,14 +306,6 @@ bool CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
    // no value associated with delete
    value_.clear();
    iter_stats_.num_record_drop_user++;
-  } else if (filter == CompactionFilter::Decision::kPurge) {
-    // convert the current key to a single delete; key_ is pointing into
-    // current_key_ at this point, so updating current_key_ updates key()
-    ikey_.type = kTypeSingleDeletion;
-    current_key_.UpdateInternalKey(ikey_.sequence, kTypeSingleDeletion);
-    // no value associated with single delete
-    value_.clear();
-    iter_stats_.num_record_drop_user++;
  } else if (filter == CompactionFilter::Decision::kChangeValue) {
    if (ikey_.type == kTypeBlobIndex) {
      // value transfer from blob file to inlined data
@@ -519,18 +508,18 @@ void CompactionIterator::NextFromInput() {
      // In the previous iteration we encountered a single delete that we could
      // not compact out.  We will keep this Put, but can drop it's data.
      // (See Optimization 3, below.)
+      assert(ikey_.type == kTypeValue || ikey_.type == kTypeBlobIndex);
      if (ikey_.type != kTypeValue && ikey_.type != kTypeBlobIndex) {
-        ROCKS_LOG_FATAL(info_log_, "Unexpected key %s for compaction output",
-                        ikey_.DebugString(allow_data_in_errors_, true).c_str());
-        assert(false);
+        ROCKS_LOG_FATAL(info_log_,
+                        "Unexpected key type %d for compaction output",
+                        ikey_.type);
      }
+      assert(current_user_key_snapshot_ >= last_snapshot);
      if (current_user_key_snapshot_ < last_snapshot) {
        ROCKS_LOG_FATAL(info_log_,
-                        "key %s, current_user_key_snapshot_ (%" PRIu64
+                        "current_user_key_snapshot_ (%" PRIu64
                        ") < last_snapshot (%" PRIu64 ")",
-                        ikey_.DebugString(allow_data_in_errors_, true).c_str(),
                        current_user_key_snapshot_, last_snapshot);
-        assert(false);
      }

      if (ikey_.type == kTypeBlobIndex) {
@@ -635,39 +624,24 @@ void CompactionIterator::NextFromInput() {

          TEST_SYNC_POINT_CALLBACK(
              "CompactionIterator::NextFromInput:SingleDelete:2", nullptr);
-          if (next_ikey.type == kTypeSingleDeletion) {
+          if (next_ikey.type == kTypeSingleDeletion ||
+              next_ikey.type == kTypeDeletion) {
            // We encountered two SingleDeletes for same key in a row. This
            // could be due to unexpected user input. If write-(un)prepared
            // transaction is used, this could also be due to releasing an old
            // snapshot between a Put and its matching SingleDelete.
+            // Furthermore, if write-(un)prepared transaction is rolled back
+            // after prepare, we will write a Delete to cancel a prior Put. If
+            // old snapshot is released between a later Put and its matching
+            // SingleDelete, we will end up with a Delete followed by
+            // SingleDelete.
            // Skip the first SingleDelete and let the next iteration decide
-            // how to handle the second SingleDelete.
+            // how to handle the second SingleDelete or Delete.

            // First SingleDelete has been skipped since we already called
            // input_.Next().
            ++iter_stats_.num_record_drop_obsolete;
            ++iter_stats_.num_single_del_mismatch;
-          } else if (next_ikey.type == kTypeDeletion) {
-            std::ostringstream oss;
-            oss << "Found SD and type: " << static_cast<int>(next_ikey.type)
-                << " on the same key, violating the contract "
-                   "of SingleDelete. Check your application to make sure the "
-                   "application does not mix SingleDelete and Delete for "
-                   "the same key. If you are using "
-                   "write-prepared/write-unprepared transactions, and use "
-                   "SingleDelete to delete certain keys, then make sure "
-                   "TransactionDBOptions::rollback_deletion_type_callback is "
-                   "configured properly. Mixing SD and DEL can lead to "
-                   "undefined behaviors";
-            ++iter_stats_.num_record_drop_obsolete;
-            ++iter_stats_.num_single_del_mismatch;
-            if (enforce_single_del_contracts_) {
-              ROCKS_LOG_ERROR(info_log_, "%s", oss.str().c_str());
-              valid_ = false;
-              status_ = Status::Corruption(oss.str());
-              return;
-            }
-            ROCKS_LOG_WARN(info_log_, "%s", oss.str().c_str());
          } else if (!is_timestamp_eligible_for_gc) {
            // We cannot drop the SingleDelete as timestamp is enabled, and
            // timestamp of this key is greater than or equal to
@@ -769,13 +743,12 @@ void CompactionIterator::NextFromInput() {
      // Note: Dropping this key will not affect TransactionDB write-conflict
      // checking since there has already been a record returned for this key
      // in this snapshot.
+      assert(last_sequence >= current_user_key_sequence_);
      if (last_sequence < current_user_key_sequence_) {
        ROCKS_LOG_FATAL(info_log_,
-                        "key %s, last_sequence (%" PRIu64
+                        "last_sequence (%" PRIu64
                        ") < current_user_key_sequence_ (%" PRIu64 ")",
-                        ikey_.DebugString(allow_data_in_errors_, true).c_str(),
                        last_sequence, current_user_key_sequence_);
-        assert(false);
      }

      ++iter_stats_.num_record_drop_hidden;  // rule (A)
@@ -785,6 +758,7 @@ void CompactionIterator::NextFromInput() {
                (ikey_.type == kTypeDeletionWithTimestamp &&
                 cmp_with_history_ts_low_ < 0)) &&
               DefinitelyInSnapshot(ikey_.sequence, earliest_snapshot_) &&
+               ikeyNotNeededForIncrementalSnapshot() &&
               compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
                                                          &level_ptrs_)) {
      // TODO(noetzli): This is the only place where we use compaction_
@@ -818,7 +792,7 @@ void CompactionIterator::NextFromInput() {
    } else if ((ikey_.type == kTypeDeletion ||
                (ikey_.type == kTypeDeletionWithTimestamp &&
                 cmp_with_history_ts_low_ < 0)) &&
-               bottommost_level_) {
+               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
@@ -887,12 +861,10 @@ void CompactionIterator::NextFromInput() {
        pik_status = ParseInternalKey(key_, &ikey_, allow_data_in_errors_);
        // MergeUntil stops when it encounters a corrupt key and does not
        // include them in the result, so we expect the keys here to valid.
+        assert(pik_status.ok());
        if (!pik_status.ok()) {
-          ROCKS_LOG_FATAL(
-              info_log_, "Invalid key %s in compaction. %s",
-              allow_data_in_errors_ ? key_.ToString(true).c_str() : "hidden",
-              pik_status.getState());
-          assert(false);
+          ROCKS_LOG_FATAL(info_log_, "Invalid key in compaction. %s",
+                          pik_status.getState());
        }
        // Keep current_key_ in sync.
        current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
@@ -982,10 +954,6 @@ void CompactionIterator::GarbageCollectBlobIfNeeded() {

  // GC for integrated BlobDB
  if (compaction_->enable_blob_garbage_collection()) {
-    TEST_SYNC_POINT_CALLBACK(
-        "CompactionIterator::GarbageCollectBlobIfNeeded::TamperWithBlobIndex",
-        &value_);
-
    BlobIndex blob_index;

    {
@@ -1092,25 +1060,19 @@ void CompactionIterator::PrepareOutput() {
    // Can we do the same for levels above bottom level as long as
    // KeyNotExistsBeyondOutputLevel() return true?
    if (valid_ && compaction_ != nullptr &&
-        !compaction_->allow_ingest_behind() && bottommost_level_ &&
+        !compaction_->allow_ingest_behind() &&
+        ikeyNotNeededForIncrementalSnapshot() && bottommost_level_ &&
        DefinitelyInSnapshot(ikey_.sequence, earliest_snapshot_) &&
-        ikey_.type != kTypeMerge && current_key_committed_) {
+        ikey_.type != kTypeMerge) {
+      assert(ikey_.type != kTypeDeletion);
+      assert(ikey_.type != kTypeSingleDeletion ||
+             (timestamp_size_ || full_history_ts_low_));
      if (ikey_.type == kTypeDeletion ||
-          (ikey_.type == kTypeSingleDeletion && timestamp_size_ == 0)) {
-        ROCKS_LOG_FATAL(
-            info_log_,
-            "Unexpected key %s for seq-zero optimization. "
-            "earliest_snapshot %" PRIu64
-            ", earliest_write_conflict_snapshot %" PRIu64
-            " job_snapshot %" PRIu64
-            ". timestamp_size: %d full_history_ts_low_ %s",
-            ikey_.DebugString(allow_data_in_errors_, true).c_str(),
-            earliest_snapshot_, earliest_write_conflict_snapshot_,
-            job_snapshot_, static_cast<int>(timestamp_size_),
-            full_history_ts_low_ != nullptr
-                ? Slice(*full_history_ts_low_).ToString(true).c_str()
-                : "null");
-        assert(false);
+          (ikey_.type == kTypeSingleDeletion &&
+           (!timestamp_size_ || !full_history_ts_low_))) {
+        ROCKS_LOG_FATAL(info_log_,
+                        "Unexpected key type %d for seq-zero optimization",
+                        ikey_.type);
      }
      ikey_.sequence = 0;
      last_key_seq_zeroed_ = true;
@@ -1141,17 +1103,14 @@ inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
  }
  auto snapshots_iter = std::lower_bound(
      snapshots_->begin(), snapshots_->end(), in);
-  assert(prev_snapshot != nullptr);
  if (snapshots_iter == snapshots_->begin()) {
    *prev_snapshot = 0;
  } else {
    *prev_snapshot = *std::prev(snapshots_iter);
+    assert(*prev_snapshot < in);
    if (*prev_snapshot >= in) {
      ROCKS_LOG_FATAL(info_log_,
-                      "*prev_snapshot (%" PRIu64 ") >= in (%" PRIu64
-                      ") in findEarliestVisibleSnapshot",
-                      *prev_snapshot, in);
-      assert(false);
+                      "*prev_snapshot >= in in findEarliestVisibleSnapshot");
    }
  }
  if (snapshot_checker_ == nullptr) {
@@ -1161,12 +1120,9 @@ inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
  bool has_released_snapshot = !released_snapshots_.empty();
  for (; snapshots_iter != snapshots_->end(); ++snapshots_iter) {
    auto cur = *snapshots_iter;
+    assert(in <= cur);
    if (in > cur) {
-      ROCKS_LOG_FATAL(info_log_,
-                      "in (%" PRIu64 ") > cur (%" PRIu64
-                      ") in findEarliestVisibleSnapshot",
-                      in, cur);
-      assert(false);
+      ROCKS_LOG_FATAL(info_log_, "in > cur in findEarliestVisibleSnapshot");
    }
    // Skip if cur is in released_snapshots.
    if (has_released_snapshot && released_snapshots_.count(cur) > 0) {
@@ -1183,6 +1139,13 @@ inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
  return kMaxSequenceNumber;
 }

+// used in 2 places - prevents deletion markers to be dropped if they may be
+// needed and disables seqnum zero-out in PrepareOutput for recent keys.
+inline bool CompactionIterator::ikeyNotNeededForIncrementalSnapshot() {
+  return (!compaction_->preserve_deletes()) ||
+         (ikey_.sequence < preserve_deletes_seqnum_);
+}
+
 uint64_t CompactionIterator::ComputeBlobGarbageCollectionCutoffFileNumber(
    const CompactionProxy* compaction) {
  if (!compaction) {
@@ -1201,17 +1164,12 @@ uint64_t CompactionIterator::ComputeBlobGarbageCollectionCutoffFileNumber(

  const auto& blob_files = storage_info->GetBlobFiles();

-  const size_t cutoff_index = static_cast<size_t>(
-      compaction->blob_garbage_collection_age_cutoff() * blob_files.size());
+  auto it = blob_files.begin();
+  std::advance(
+      it, compaction->blob_garbage_collection_age_cutoff() * blob_files.size());

-  if (cutoff_index >= blob_files.size()) {
-    return std::numeric_limits<uint64_t>::max();
-  }
-
-  const auto& meta = blob_files[cutoff_index];
-  assert(meta);
-
-  return meta->GetBlobFileNumber();
+  return it != blob_files.end() ? it->first
+                                : std::numeric_limits<uint64_t>::max();
 }

 std::unique_ptr<BlobFetcher> CompactionIterator::CreateBlobFetcherIfNeeded(
@@ -92,6 +92,8 @@ class CompactionIterator {

    virtual bool allow_ingest_behind() const = 0;

+    virtual bool preserve_deletes() const = 0;
+
    virtual bool allow_mmap_reads() const = 0;

    virtual bool enable_blob_garbage_collection() const = 0;
@@ -137,16 +139,21 @@ class CompactionIterator {
      return compaction_->immutable_options()->allow_ingest_behind;
    }

+    bool preserve_deletes() const override {
+      return compaction_->immutable_options()->preserve_deletes;
+    }
+
    bool allow_mmap_reads() const override {
      return compaction_->immutable_options()->allow_mmap_reads;
    }

    bool enable_blob_garbage_collection() const override {
-      return compaction_->enable_blob_garbage_collection();
+      return compaction_->mutable_cf_options()->enable_blob_garbage_collection;
    }

    double blob_garbage_collection_age_cutoff() const override {
-      return compaction_->blob_garbage_collection_age_cutoff();
+      return compaction_->mutable_cf_options()
+          ->blob_garbage_collection_age_cutoff;
    }

    uint64_t blob_compaction_readahead_size() const override {
@@ -167,42 +174,40 @@ class CompactionIterator {
    const Compaction* compaction_;
  };

-  CompactionIterator(InternalIterator* input, const Comparator* cmp,
-                     MergeHelper* merge_helper, SequenceNumber last_sequence,
-                     std::vector<SequenceNumber>* snapshots,
-                     SequenceNumber earliest_write_conflict_snapshot,
-                     SequenceNumber job_snapshot,
-                     const SnapshotChecker* snapshot_checker, Env* env,
-                     bool report_detailed_time, bool expect_valid_internal_key,
-                     CompactionRangeDelAggregator* range_del_agg,
-                     BlobFileBuilder* blob_file_builder,
-                     bool allow_data_in_errors,
-                     bool enforce_single_del_contracts,
-                     const std::atomic<bool>& manual_compaction_canceled,
-                     const Compaction* compaction = nullptr,
-                     const CompactionFilter* compaction_filter = nullptr,
-                     const std::atomic<bool>* shutting_down = nullptr,
-                     const std::shared_ptr<Logger> info_log = nullptr,
-                     const std::string* full_history_ts_low = nullptr);
+  CompactionIterator(
+      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
+      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
+      SequenceNumber earliest_write_conflict_snapshot,
+      const SnapshotChecker* snapshot_checker, Env* env,
+      bool report_detailed_time, bool expect_valid_internal_key,
+      CompactionRangeDelAggregator* range_del_agg,
+      BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
+      const Compaction* compaction = nullptr,
+      const CompactionFilter* compaction_filter = nullptr,
+      const std::atomic<bool>* shutting_down = nullptr,
+      const SequenceNumber preserve_deletes_seqnum = 0,
+      const std::atomic<int>* manual_compaction_paused = nullptr,
+      const std::atomic<bool>* manual_compaction_canceled = nullptr,
+      const std::shared_ptr<Logger> info_log = nullptr,
+      const std::string* full_history_ts_low = nullptr);

  // Constructor with custom CompactionProxy, used for tests.
-  CompactionIterator(InternalIterator* input, const Comparator* cmp,
-                     MergeHelper* merge_helper, SequenceNumber last_sequence,
-                     std::vector<SequenceNumber>* snapshots,
-                     SequenceNumber earliest_write_conflict_snapshot,
-                     SequenceNumber job_snapshot,
-                     const SnapshotChecker* snapshot_checker, Env* env,
-                     bool report_detailed_time, bool expect_valid_internal_key,
-                     CompactionRangeDelAggregator* range_del_agg,
-                     BlobFileBuilder* blob_file_builder,
-                     bool allow_data_in_errors,
-                     bool enforce_single_del_contracts,
-                     const std::atomic<bool>& manual_compaction_canceled,
-                     std::unique_ptr<CompactionProxy> compaction,
-                     const CompactionFilter* compaction_filter = nullptr,
-                     const std::atomic<bool>* shutting_down = nullptr,
-                     const std::shared_ptr<Logger> info_log = nullptr,
-                     const std::string* full_history_ts_low = nullptr);
+  CompactionIterator(
+      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
+      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
+      SequenceNumber earliest_write_conflict_snapshot,
+      const SnapshotChecker* snapshot_checker, Env* env,
+      bool report_detailed_time, bool expect_valid_internal_key,
+      CompactionRangeDelAggregator* range_del_agg,
+      BlobFileBuilder* blob_file_builder, bool allow_data_in_errors,
+      std::unique_ptr<CompactionProxy> compaction,
+      const CompactionFilter* compaction_filter = nullptr,
+      const std::atomic<bool>* shutting_down = nullptr,
+      const SequenceNumber preserve_deletes_seqnum = 0,
+      const std::atomic<int>* manual_compaction_paused = nullptr,
+      const std::atomic<bool>* manual_compaction_canceled = nullptr,
+      const std::shared_ptr<Logger> info_log = nullptr,
+      const std::string* full_history_ts_low = nullptr);

  ~CompactionIterator();

@@ -269,9 +274,14 @@ class CompactionIterator {
  inline SequenceNumber findEarliestVisibleSnapshot(
      SequenceNumber in, SequenceNumber* prev_snapshot);

+  // Checks whether the currently seen ikey_ is needed for
+  // incremental (differential) snapshot and hence can't be dropped
+  // or seqnum be zero-ed out even if all other conditions for it are met.
+  inline bool ikeyNotNeededForIncrementalSnapshot();
+
  inline bool KeyCommitted(SequenceNumber sequence) {
    return snapshot_checker_ == nullptr ||
-           snapshot_checker_->CheckInSnapshot(sequence, job_snapshot_) ==
+           snapshot_checker_->CheckInSnapshot(sequence, kMaxSequenceNumber) ==
               SnapshotCheckerResult::kInSnapshot;
  }

@@ -312,7 +322,6 @@ class CompactionIterator {
  std::unordered_set<SequenceNumber> released_snapshots_;
  std::vector<SequenceNumber>::const_iterator earliest_snapshot_iter_;
  const SequenceNumber earliest_write_conflict_snapshot_;
-  const SequenceNumber job_snapshot_;
  const SnapshotChecker* const snapshot_checker_;
  Env* env_;
  SystemClock* clock_;
@@ -323,7 +332,9 @@ class CompactionIterator {
  std::unique_ptr<CompactionProxy> compaction_;
  const CompactionFilter* compaction_filter_;
  const std::atomic<bool>* shutting_down_;
-  const std::atomic<bool>& manual_compaction_canceled_;
+  const std::atomic<int>* manual_compaction_paused_;
+  const std::atomic<bool>* manual_compaction_canceled_;
+  const SequenceNumber preserve_deletes_seqnum_;
  bool bottommost_level_;
  bool valid_ = false;
  bool visible_at_tip_;
@@ -334,8 +345,6 @@ class CompactionIterator {

  bool allow_data_in_errors_;

-  const bool enforce_single_del_contracts_;
-
  // Comes from comparator.
  const size_t timestamp_size_;

@@ -428,7 +437,10 @@ class CompactionIterator {

  bool IsPausingManualCompaction() {
    // This is a best-effort facility, so memory_order_relaxed is sufficient.
-    return manual_compaction_canceled_.load(std::memory_order_relaxed);
+    return (manual_compaction_paused_ &&
+            manual_compaction_paused_->load(std::memory_order_relaxed) > 0) ||
+           (manual_compaction_canceled_ &&
+            manual_compaction_canceled_->load(std::memory_order_relaxed));
  }
 };

@@ -166,6 +166,8 @@ class FakeCompaction : public CompactionIterator::CompactionProxy {

  bool allow_ingest_behind() const override { return is_allow_ingest_behind; }

+  bool preserve_deletes() const override { return false; }
+
  bool allow_mmap_reads() const override { return false; }

  bool enable_blob_garbage_collection() const override { return false; }
@@ -275,13 +277,13 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
    iter_->SeekToFirst();
    c_iter_.reset(new CompactionIterator(
        iter_.get(), cmp_, merge_helper_.get(), last_sequence, &snapshots_,
-        earliest_write_conflict_snapshot, kMaxSequenceNumber,
-        snapshot_checker_.get(), Env::Default(),
-        false /* report_detailed_time */, false, range_del_agg_.get(),
-        nullptr /* blob_file_builder */, true /*allow_data_in_errors*/,
-        true /*enforce_single_del_contracts*/,
-        /*manual_compaction_canceled=*/kManualCompactionCanceledFalse_,
-        std::move(compaction), filter, &shutting_down_, /*info_log=*/nullptr,
+        earliest_write_conflict_snapshot, snapshot_checker_.get(),
+        Env::Default(), false /* report_detailed_time */, false,
+        range_del_agg_.get(), nullptr /* blob_file_builder */,
+        true /*allow_data_in_errors*/, std::move(compaction), filter,
+        &shutting_down_, /*preserve_deletes_seqnum=*/0,
+        /*manual_compaction_paused=*/nullptr,
+        /*manual_compaction_canceled=*/nullptr, /*info_log=*/nullptr,
        full_history_ts_low));
  }

@@ -313,7 +315,7 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
                  key_not_exists_beyond_output_level, full_history_ts_low);
    c_iter_->SeekToFirst();
    for (size_t i = 0; i < expected_keys.size(); i++) {
-      std::string info = "i = " + std::to_string(i);
+      std::string info = "i = " + ToString(i);
      ASSERT_TRUE(c_iter_->Valid()) << info;
      ASSERT_OK(c_iter_->status()) << info;
      ASSERT_EQ(expected_keys[i], c_iter_->key().ToString()) << info;
@@ -340,7 +342,6 @@ class CompactionIteratorTest : public testing::TestWithParam<bool> {
  std::unique_ptr<CompactionRangeDelAggregator> range_del_agg_;
  std::unique_ptr<SnapshotChecker> snapshot_checker_;
  std::atomic<bool> shutting_down_{false};
-  const std::atomic<bool> kManualCompactionCanceledFalse_{false};
  FakeCompaction* compaction_proxy_;
 };

@@ -1078,7 +1079,7 @@ INSTANTIATE_TEST_CASE_P(CompactionIteratorWithAllowIngestBehindTestInstance,
 class CompactionIteratorTsGcTest : public CompactionIteratorTest {
 public:
  CompactionIteratorTsGcTest()
-      : CompactionIteratorTest(test::BytewiseComparatorWithU64TsWrapper()) {}
+      : CompactionIteratorTest(test::ComparatorWithU64Ts()) {}
 };

 TEST_P(CompactionIteratorTsGcTest, NoKeyEligibleForGC) {
@@ -31,7 +31,6 @@
 #include "db/dbformat.h"
 #include "db/error_handler.h"
 #include "db/event_helpers.h"
-#include "db/history_trimming_iterator.h"
 #include "db/log_reader.h"
 #include "db/log_writer.h"
 #include "db/memtable.h"
@@ -64,7 +63,6 @@
 #include "table/block_based/block_based_table_factory.h"
 #include "table/merging_iterator.h"
 #include "table/table_builder.h"
-#include "table/unique_id_impl.h"
 #include "test_util/sync_point.h"
 #include "util/coding.h"
 #include "util/hash.h"
@@ -197,10 +195,6 @@ struct CompactionJob::SubcompactionState {
  // within the same compaction job.
  const uint32_t sub_job_id;

-  // Notify on sub-compaction completion only if listener was notified on
-  // sub-compaction begin.
-  bool notify_on_subcompaction_completion = false;
-
  SubcompactionState(Compaction* c, Slice* _start, Slice* _end, uint64_t size,
                     uint32_t _sub_job_id)
      : compaction(c),
@@ -418,21 +412,20 @@ CompactionJob::CompactionJob(
    int job_id, Compaction* compaction, const ImmutableDBOptions& db_options,
    const MutableDBOptions& mutable_db_options, const FileOptions& file_options,
    VersionSet* versions, const std::atomic<bool>* shutting_down,
-    LogBuffer* log_buffer, FSDirectory* db_directory,
-    FSDirectory* output_directory, FSDirectory* blob_output_directory,
-    Statistics* stats, InstrumentedMutex* db_mutex,
-    ErrorHandler* db_error_handler,
+    const SequenceNumber preserve_deletes_seqnum, LogBuffer* log_buffer,
+    FSDirectory* db_directory, FSDirectory* output_directory,
+    FSDirectory* blob_output_directory, Statistics* stats,
+    InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
    std::vector<SequenceNumber> existing_snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
-    const SnapshotChecker* snapshot_checker, JobContext* job_context,
-    std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
-    bool paranoid_file_checks, bool measure_io_stats, const std::string& dbname,
-    CompactionJobStats* compaction_job_stats, Env::Priority thread_pri,
-    const std::shared_ptr<IOTracer>& io_tracer,
-    const std::atomic<bool>& manual_compaction_canceled,
+    const SnapshotChecker* snapshot_checker, std::shared_ptr<Cache> table_cache,
+    EventLogger* event_logger, bool paranoid_file_checks, bool measure_io_stats,
+    const std::string& dbname, CompactionJobStats* compaction_job_stats,
+    Env::Priority thread_pri, const std::shared_ptr<IOTracer>& io_tracer,
+    const std::atomic<int>* manual_compaction_paused,
+    const std::atomic<bool>* manual_compaction_canceled,
    const std::string& db_id, const std::string& db_session_id,
-    std::string full_history_ts_low, std::string trim_ts,
-    BlobFileCompletionCallback* blob_callback)
+    std::string full_history_ts_low, BlobFileCompletionCallback* blob_callback)
    : compact_(new CompactionState(compaction)),
      compaction_stats_(compaction->compaction_reason(), 1),
      db_options_(db_options),
@@ -455,7 +448,9 @@ CompactionJob::CompactionJob(
          fs_->OptimizeForCompactionTableRead(file_options, db_options_)),
      versions_(versions),
      shutting_down_(shutting_down),
+      manual_compaction_paused_(manual_compaction_paused),
      manual_compaction_canceled_(manual_compaction_canceled),
+      preserve_deletes_seqnum_(preserve_deletes_seqnum),
      db_directory_(db_directory),
      blob_output_directory_(blob_output_directory),
      db_mutex_(db_mutex),
@@ -463,14 +458,12 @@ CompactionJob::CompactionJob(
      existing_snapshots_(std::move(existing_snapshots)),
      earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
      snapshot_checker_(snapshot_checker),
-      job_context_(job_context),
      table_cache_(std::move(table_cache)),
      event_logger_(event_logger),
      paranoid_file_checks_(paranoid_file_checks),
      measure_io_stats_(measure_io_stats),
      thread_pri_(thread_pri),
      full_history_ts_low_(std::move(full_history_ts_low)),
-      trim_ts_(std::move(trim_ts)),
      blob_callback_(blob_callback) {
  assert(compaction_job_stats_ != nullptr);
  assert(log_buffer_ != nullptr);
@@ -797,8 +790,8 @@ Status CompactionJob::Run() {
      }
    }
    ColumnFamilyData* cfd = compact_->compaction->column_family_data();
-    auto& prefix_extractor =
-        compact_->compaction->mutable_cf_options()->prefix_extractor;
+    auto prefix_extractor =
+        compact_->compaction->mutable_cf_options()->prefix_extractor.get();
    std::atomic<size_t> next_file_idx(0);
    auto verify_table = [&](Status& output_status) {
      while (true) {
@@ -970,14 +963,11 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {

  const auto& blob_files = vstorage->GetBlobFiles();
  if (!blob_files.empty()) {
-    assert(blob_files.front());
-    assert(blob_files.back());
-
-    ROCKS_LOG_BUFFER(
-        log_buffer_,
-        "[%s] Blob file summary: head=%" PRIu64 ", tail=%" PRIu64 "\n",
-        column_family_name.c_str(), blob_files.front()->GetBlobFileNumber(),
-        blob_files.back()->GetBlobFileNumber());
+    ROCKS_LOG_BUFFER(log_buffer_,
+                     "[%s] Blob file summary: head=%" PRIu64 ", tail=%" PRIu64
+                     "\n",
+                     column_family_name.c_str(), blob_files.begin()->first,
+                     blob_files.rbegin()->first);
  }

  UpdateCompactionJobStats(stats);
@@ -1024,11 +1014,8 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
  stream.EndArray();

  if (!blob_files.empty()) {
-    assert(blob_files.front());
-    stream << "blob_file_head" << blob_files.front()->GetBlobFileNumber();
-
-    assert(blob_files.back());
-    stream << "blob_file_tail" << blob_files.back()->GetBlobFileNumber();
+    stream << "blob_file_head" << blob_files.begin()->first;
+    stream << "blob_file_tail" << blob_files.rbegin()->first;
  }

  CleanupCompaction();
@@ -1046,7 +1033,6 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
  const Compaction* compaction = sub_compact->compaction;
  CompactionServiceInput compaction_input;
  compaction_input.output_level = compaction->output_level();
-  compaction_input.db_id = db_id_;

  const std::vector<CompactionInputFiles>& inputs =
      *(compact_->compaction->inputs());
@@ -1208,7 +1194,6 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
    meta.oldest_ancester_time = file.oldest_ancester_time;
    meta.file_creation_time = file.file_creation_time;
    meta.marked_for_compaction = file.marked_for_compaction;
-    meta.unique_id = file.unique_id;

    auto cfd = compaction->column_family_data();
    sub_compact->outputs.emplace_back(std::move(meta),
@@ -1224,82 +1209,8 @@ CompactionJob::ProcessKeyValueCompactionWithCompactionService(
             compaction_result.bytes_written);
  return CompactionServiceJobStatus::kSuccess;
 }
-
-void CompactionJob::BuildSubcompactionJobInfo(
-    SubcompactionState* sub_compact,
-    SubcompactionJobInfo* subcompaction_job_info) const {
-  Compaction* c = compact_->compaction;
-  ColumnFamilyData* cfd = c->column_family_data();
-
-  subcompaction_job_info->cf_id = cfd->GetID();
-  subcompaction_job_info->cf_name = cfd->GetName();
-  subcompaction_job_info->status = sub_compact->status;
-  subcompaction_job_info->thread_id = env_->GetThreadID();
-  subcompaction_job_info->job_id = job_id_;
-  subcompaction_job_info->subcompaction_job_id = sub_compact->sub_job_id;
-  subcompaction_job_info->base_input_level = c->start_level();
-  subcompaction_job_info->output_level = c->output_level();
-  subcompaction_job_info->stats = sub_compact->compaction_job_stats;
-}
 #endif  // !ROCKSDB_LITE

-void CompactionJob::NotifyOnSubcompactionBegin(
-    SubcompactionState* sub_compact) {
-#ifndef ROCKSDB_LITE
-  Compaction* c = compact_->compaction;
-
-  if (db_options_.listeners.empty()) {
-    return;
-  }
-  if (shutting_down_->load(std::memory_order_acquire)) {
-    return;
-  }
-  if (c->is_manual_compaction() &&
-      manual_compaction_canceled_.load(std::memory_order_acquire)) {
-    return;
-  }
-
-  sub_compact->notify_on_subcompaction_completion = true;
-
-  SubcompactionJobInfo info{};
-  BuildSubcompactionJobInfo(sub_compact, &info);
-
-  for (auto listener : db_options_.listeners) {
-    listener->OnSubcompactionBegin(info);
-  }
-  info.status.PermitUncheckedError();
-
-#else
-  (void)sub_compact;
-#endif  // ROCKSDB_LITE
-}
-
-void CompactionJob::NotifyOnSubcompactionCompleted(
-    SubcompactionState* sub_compact) {
-#ifndef ROCKSDB_LITE
-
-  if (db_options_.listeners.empty()) {
-    return;
-  }
-  if (shutting_down_->load(std::memory_order_acquire)) {
-    return;
-  }
-
-  if (sub_compact->notify_on_subcompaction_completion == false) {
-    return;
-  }
-
-  SubcompactionJobInfo info{};
-  BuildSubcompactionJobInfo(sub_compact, &info);
-
-  for (auto listener : db_options_.listeners) {
-    listener->OnSubcompactionCompleted(info);
-  }
-#else
-  (void)sub_compact;
-#endif  // ROCKSDB_LITE
-}
-
 void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  assert(sub_compact);
  assert(sub_compact->compaction);
@@ -1317,7 +1228,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  }
 #endif  // !ROCKSDB_LITE

-  uint64_t prev_cpu_micros = db_options_.clock->CPUMicros();
+  uint64_t prev_cpu_micros = db_options_.clock->CPUNanos() / 1000;

  ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();

@@ -1338,20 +1249,15 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
    return;
  }

-  NotifyOnSubcompactionBegin(sub_compact);
-
  CompactionRangeDelAggregator range_del_agg(&cfd->internal_comparator(),
                                             existing_snapshots_);

-  // TODO: since we already use C++17, should use
-  // std::optional<const Slice> instead.
  const Slice* const start = sub_compact->start;
  const Slice* const end = sub_compact->end;

  ReadOptions read_options;
  read_options.verify_checksums = true;
  read_options.fill_cache = false;
-  read_options.rate_limiter_priority = GetRateLimiterPriority();
  // Compaction iterators shouldn't be confined to a single prefix.
  // Compactions use Seek() for
  // (a) concurrent compactions,
@@ -1366,13 +1272,9 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {

  // 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> raw_input(versions_->MakeInputIterator(
-      read_options, sub_compact->compaction, &range_del_agg,
-      file_options_for_read_,
-      (start == nullptr) ? std::optional<const Slice>{}
-                         : std::optional<const Slice>{*start},
-      (end == nullptr) ? std::optional<const Slice>{}
-                       : std::optional<const Slice>{*end}));
+  std::unique_ptr<InternalIterator> raw_input(
+      versions_->MakeInputIterator(read_options, sub_compact->compaction,
+                                   &range_del_agg, file_options_for_read_));
  InternalIterator* input = raw_input.get();

  IterKey start_ikey;
@@ -1391,28 +1293,21 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {

  std::unique_ptr<InternalIterator> clip;
  if (start || end) {
-    clip = std::make_unique<ClippingIterator>(
+    clip.reset(new ClippingIterator(
        raw_input.get(), start ? &start_slice : nullptr,
-        end ? &end_slice : nullptr, &cfd->internal_comparator());
+        end ? &end_slice : nullptr, &cfd->internal_comparator()));
    input = clip.get();
  }

  std::unique_ptr<InternalIterator> blob_counter;

  if (sub_compact->compaction->DoesInputReferenceBlobFiles()) {
-    sub_compact->blob_garbage_meter = std::make_unique<BlobGarbageMeter>();
-    blob_counter = std::make_unique<BlobCountingIterator>(
-        input, sub_compact->blob_garbage_meter.get());
+    sub_compact->blob_garbage_meter.reset(new BlobGarbageMeter);
+    blob_counter.reset(
+        new BlobCountingIterator(input, sub_compact->blob_garbage_meter.get()));
    input = blob_counter.get();
  }

-  std::unique_ptr<InternalIterator> trim_history_iter;
-  if (cfd->user_comparator()->timestamp_size() > 0 && !trim_ts_.empty()) {
-    trim_history_iter = std::make_unique<HistoryTrimmingIterator>(
-        input, cfd->user_comparator(), trim_ts_);
-    input = trim_history_iter.get();
-  }
-
  input->SeekToFirst();

  AutoThreadOperationStageUpdater stage_updater(
@@ -1452,9 +1347,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  std::vector<std::string> blob_file_paths;

  std::unique_ptr<BlobFileBuilder> blob_file_builder(
-      (mutable_cf_options->enable_blob_files &&
-       sub_compact->compaction->output_level() >=
-           mutable_cf_options->blob_file_starting_level)
+      mutable_cf_options->enable_blob_files
          ? new BlobFileBuilder(
                versions_, fs_.get(),
                sub_compact->compaction->immutable_options(),
@@ -1468,23 +1361,20 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  TEST_SYNC_POINT_CALLBACK(
      "CompactionJob::Run():PausingManualCompaction:1",
      reinterpret_cast<void*>(
-          const_cast<std::atomic<bool>*>(&manual_compaction_canceled_)));
+          const_cast<std::atomic<int>*>(manual_compaction_paused_)));

  Status status;
  const std::string* const full_history_ts_low =
      full_history_ts_low_.empty() ? nullptr : &full_history_ts_low_;
-  const SequenceNumber job_snapshot_seq =
-      job_context_ ? job_context_->GetJobSnapshotSequence()
-                   : kMaxSequenceNumber;
  sub_compact->c_iter.reset(new CompactionIterator(
      input, cfd->user_comparator(), &merge, versions_->LastSequence(),
-      &existing_snapshots_, earliest_write_conflict_snapshot_, job_snapshot_seq,
+      &existing_snapshots_, earliest_write_conflict_snapshot_,
      snapshot_checker_, env_, ShouldReportDetailedTime(env_, stats_),
      /*expect_valid_internal_key=*/true, &range_del_agg,
      blob_file_builder.get(), db_options_.allow_data_in_errors,
-      db_options_.enforce_single_del_contracts, manual_compaction_canceled_,
      sub_compact->compaction, compaction_filter, shutting_down_,
-      db_options_.info_log, full_history_ts_low));
+      preserve_deletes_seqnum_, manual_compaction_paused_,
+      manual_compaction_canceled_, db_options_.info_log, full_history_ts_low));
  auto c_iter = sub_compact->c_iter.get();
  c_iter->SeekToFirst();
  if (c_iter->Valid() && sub_compact->compaction->output_level() != 0) {
@@ -1536,15 +1426,11 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
      break;
    }

-    const ParsedInternalKey& ikey = c_iter->ikey();
-    status = sub_compact->current_output()->meta.UpdateBoundaries(
-        key, value, ikey.sequence, ikey.type);
-    if (!status.ok()) {
-      break;
-    }
-
    sub_compact->current_output_file_size =
        sub_compact->builder->EstimatedFileSize();
+    const ParsedInternalKey& ikey = c_iter->ikey();
+    sub_compact->current_output()->meta.UpdateBoundaries(
+        key, value, ikey.sequence, ikey.type);
    sub_compact->num_output_records++;

    // Close output file if it is big enough. Two possibilities determine it's
@@ -1566,7 +1452,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
    TEST_SYNC_POINT_CALLBACK(
        "CompactionJob::Run():PausingManualCompaction:2",
        reinterpret_cast<void*>(
-            const_cast<std::atomic<bool>*>(&manual_compaction_canceled_)));
+            const_cast<std::atomic<int>*>(manual_compaction_paused_)));
    if (partitioner.get()) {
      last_key_for_partitioner.assign(c_iter->user_key().data_,
                                      c_iter->user_key().size_);
@@ -1645,7 +1531,10 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
    status = Status::ShutdownInProgress("Database shutdown");
  }
  if ((status.ok() || status.IsColumnFamilyDropped()) &&
-      (manual_compaction_canceled_.load(std::memory_order_relaxed))) {
+      ((manual_compaction_paused_ &&
+        manual_compaction_paused_->load(std::memory_order_relaxed) > 0) ||
+       (manual_compaction_canceled_ &&
+        manual_compaction_canceled_->load(std::memory_order_relaxed)))) {
    status = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
  }
  if (status.ok()) {
@@ -1683,7 +1572,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  }

  sub_compact->compaction_job_stats.cpu_micros =
-      db_options_.clock->CPUMicros() - prev_cpu_micros;
+      db_options_.clock->CPUNanos() / 1000 - prev_cpu_micros;

  if (measure_io_stats_) {
    sub_compact->compaction_job_stats.file_write_nanos +=
@@ -1718,7 +1607,6 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
  clip.reset();
  raw_input.reset();
  sub_compact->status = status;
-  NotifyOnSubcompactionCompleted(sub_compact);
 }

 uint64_t CompactionJob::GetCompactionId(SubcompactionState* sub_compact) {
@@ -1974,8 +1862,7 @@ Status CompactionJob::FinishCompactionOutputFile(
        refined_oldest_ancester_time =
            sub_compact->compaction->MinInputFileOldestAncesterTime(
                &(meta->smallest), &(meta->largest));
-        if (refined_oldest_ancester_time !=
-            std::numeric_limits<uint64_t>::max()) {
+        if (refined_oldest_ancester_time != port::kMaxUint64) {
          meta->oldest_ancester_time = refined_oldest_ancester_time;
        }
      }
@@ -2057,21 +1944,17 @@ Status CompactionJob::FinishCompactionOutputFile(
  std::string fname;
  FileDescriptor output_fd;
  uint64_t oldest_blob_file_number = kInvalidBlobFileNumber;
-  Status status_for_listener = s;
  if (meta != nullptr) {
    fname = GetTableFileName(meta->fd.GetNumber());
    output_fd = meta->fd;
    oldest_blob_file_number = meta->oldest_blob_file_number;
  } else {
    fname = "(nil)";
-    if (s.ok()) {
-      status_for_listener = Status::Aborted("Empty SST file not kept");
-    }
  }
  EventHelpers::LogAndNotifyTableFileCreationFinished(
      event_logger_, cfd->ioptions()->listeners, dbname_, cfd->GetName(), fname,
      job_id_, output_fd, oldest_blob_file_number, tp,
-      TableFileCreationReason::kCompaction, status_for_listener, file_checksum,
+      TableFileCreationReason::kCompaction, s, file_checksum,
      file_checksum_func_name);

 #ifndef ROCKSDB_LITE
@@ -2112,11 +1995,11 @@ Status CompactionJob::InstallCompactionResults(

  {
    Compaction::InputLevelSummaryBuffer inputs_summary;
-    ROCKS_LOG_BUFFER(log_buffer_,
-                     "[%s] [JOB %d] Compacted %s => %" PRIu64 " bytes",
-                     compaction->column_family_data()->GetName().c_str(),
-                     job_id_, compaction->InputLevelSummary(&inputs_summary),
-                     compact_->total_bytes + compact_->total_blob_bytes);
+    ROCKS_LOG_INFO(db_options_.info_log,
+                   "[%s] [JOB %d] Compacted %s => %" PRIu64 " bytes",
+                   compaction->column_family_data()->GetName().c_str(), job_id_,
+                   compaction->InputLevelSummary(&inputs_summary),
+                   compact_->total_bytes + compact_->total_blob_bytes);
  }

  VersionEdit* const edit = compaction->edit();
@@ -2265,7 +2148,7 @@ Status CompactionJob::OpenCompactionOutputFile(
      sub_compact->compaction->MinInputFileOldestAncesterTime(
          (sub_compact->start != nullptr) ? &tmp_start : nullptr,
          (sub_compact->end != nullptr) ? &tmp_end : nullptr);
-  if (oldest_ancester_time == std::numeric_limits<uint64_t>::max()) {
+  if (oldest_ancester_time == port::kMaxUint64) {
    oldest_ancester_time = current_time;
  }

@@ -2277,18 +2160,6 @@ Status CompactionJob::OpenCompactionOutputFile(
    meta.oldest_ancester_time = oldest_ancester_time;
    meta.file_creation_time = current_time;
    meta.temperature = temperature;
-    assert(!db_id_.empty());
-    assert(!db_session_id_.empty());
-    s = GetSstInternalUniqueId(db_id_, db_session_id_, meta.fd.GetNumber(),
-                               &meta.unique_id);
-    if (!s.ok()) {
-      ROCKS_LOG_ERROR(db_options_.info_log,
-                      "[%s] [JOB %d] file #%" PRIu64
-                      " failed to generate unique id: %s.",
-                      cfd->GetName().c_str(), job_id_, meta.fd.GetNumber(),
-                      s.ToString().c_str());
-      return s;
-    }
    sub_compact->outputs.emplace_back(
        std::move(meta), cfd->internal_comparator(),
        /*enable_order_check=*/
@@ -2297,7 +2168,7 @@ Status CompactionJob::OpenCompactionOutputFile(
        /*enable_hash=*/paranoid_file_checks_);
  }

-  writable_file->SetIOPriority(GetRateLimiterPriority());
+  writable_file->SetIOPriority(Env::IOPriority::IO_LOW);
  writable_file->SetWriteLifeTimeHint(write_hint_);
  FileTypeSet tmp_set = db_options_.checksum_handoff_file_types;
  writable_file->SetPreallocationBlockSize(static_cast<size_t>(
@@ -2305,8 +2176,9 @@ Status CompactionJob::OpenCompactionOutputFile(
  const auto& listeners =
      sub_compact->compaction->immutable_options()->listeners;
  sub_compact->outfile.reset(new WritableFileWriter(
-      std::move(writable_file), fname, fo_copy, db_options_.clock, io_tracer_,
-      db_options_.stats, listeners, db_options_.file_checksum_gen_factory.get(),
+      std::move(writable_file), fname, file_options_, db_options_.clock,
+      io_tracer_, db_options_.stats, listeners,
+      db_options_.file_checksum_gen_factory.get(),
      tmp_set.Contains(FileType::kTableFile), false));

  TableBuilderOptions tboptions(
@@ -2471,7 +2343,7 @@ void CompactionJob::LogCompaction() {
           << "compaction_reason"
           << GetCompactionReasonString(compaction->compaction_reason());
    for (size_t i = 0; i < compaction->num_input_levels(); ++i) {
-      stream << ("files_L" + std::to_string(compaction->level(i)));
+      stream << ("files_L" + ToString(compaction->level(i)));
      stream.StartArray();
      for (auto f : *compaction->inputs(i)) {
        stream << f->fd.GetNumber();
@@ -2488,19 +2360,6 @@ std::string CompactionJob::GetTableFileName(uint64_t file_number) {
                       file_number, compact_->compaction->output_path_id());
 }

-Env::IOPriority CompactionJob::GetRateLimiterPriority() {
-  if (versions_ && versions_->GetColumnFamilySet() &&
-      versions_->GetColumnFamilySet()->write_controller()) {
-    WriteController* write_controller =
-        versions_->GetColumnFamilySet()->write_controller();
-    if (write_controller->NeedsDelay() || write_controller->IsStopped()) {
-      return Env::IO_USER;
-    }
-  }
-
-  return Env::IO_LOW;
-}
-
 #ifndef ROCKSDB_LITE
 std::string CompactionServiceCompactionJob::GetTableFileName(
    uint64_t file_number) {
@@ -2522,20 +2381,19 @@ CompactionServiceCompactionJob::CompactionServiceCompactionJob(
    std::vector<SequenceNumber> existing_snapshots,
    std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
    const std::string& dbname, const std::shared_ptr<IOTracer>& io_tracer,
-    const std::atomic<bool>& manual_compaction_canceled,
    const std::string& db_id, const std::string& db_session_id,
    const std::string& output_path,
    const CompactionServiceInput& compaction_service_input,
    CompactionServiceResult* compaction_service_result)
    : CompactionJob(
          job_id, compaction, db_options, mutable_db_options, file_options,
-          versions, shutting_down, log_buffer, nullptr, output_directory,
+          versions, shutting_down, 0, log_buffer, nullptr, output_directory,
          nullptr, stats, db_mutex, db_error_handler, existing_snapshots,
-          kMaxSequenceNumber, nullptr, nullptr, table_cache, event_logger,
+          kMaxSequenceNumber, nullptr, table_cache, event_logger,
          compaction->mutable_cf_options()->paranoid_file_checks,
          compaction->mutable_cf_options()->report_bg_io_stats, dbname,
          &(compaction_service_result->stats), Env::Priority::USER, io_tracer,
-          manual_compaction_canceled, db_id, db_session_id,
+          nullptr, nullptr, db_id, db_session_id,
          compaction->column_family_data()->GetFullHistoryTsLow()),
      output_path_(output_path),
      compaction_input_(compaction_service_input),
@@ -2621,7 +2479,7 @@ Status CompactionServiceCompactionJob::Run() {
        meta.fd.largest_seqno, meta.smallest.Encode().ToString(),
        meta.largest.Encode().ToString(), meta.oldest_ancester_time,
        meta.file_creation_time, output_file.validator.GetHash(),
-        meta.marked_for_compaction, meta.unique_id);
+        meta.marked_for_compaction);
  }
  compaction_result_->num_output_records = sub_compact->num_output_records;
  compaction_result_->total_bytes = sub_compact->total_bytes;
@@ -2638,14 +2496,34 @@ enum BinaryFormatVersion : uint32_t {
  kOptionsString = 1,  // Use string format similar to Option string format
 };

+// offset_of is used to get the offset of a class data member
+// ex: offset_of(&ColumnFamilyDescriptor::options)
+// This call will return the offset of options in ColumnFamilyDescriptor class
+//
+// This is the same as offsetof() but allow us to work with non standard-layout
+// classes and structures
+// refs:
+// http://en.cppreference.com/w/cpp/concept/StandardLayoutType
+// https://gist.github.com/graphitemaster/494f21190bb2c63c5516
+static ColumnFamilyDescriptor dummy_cfd("", ColumnFamilyOptions());
+template <typename T1>
+int offset_of(T1 ColumnFamilyDescriptor::*member) {
+  return int(size_t(&(dummy_cfd.*member)) - size_t(&dummy_cfd));
+}
+
+static CompactionServiceInput dummy_cs_input;
+template <typename T1>
+int offset_of(T1 CompactionServiceInput::*member) {
+  return int(size_t(&(dummy_cs_input.*member)) - size_t(&dummy_cs_input));
+}
+
 static std::unordered_map<std::string, OptionTypeInfo> cfd_type_info = {
    {"name",
-     {offsetof(struct ColumnFamilyDescriptor, name), OptionType::kEncodedString,
+     {offset_of(&ColumnFamilyDescriptor::name), OptionType::kEncodedString,
      OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
    {"options",
-     {offsetof(struct ColumnFamilyDescriptor, options),
-      OptionType::kConfigurable, OptionVerificationType::kNormal,
-      OptionTypeFlags::kNone,
+     {offset_of(&ColumnFamilyDescriptor::options), OptionType::kConfigurable,
+      OptionVerificationType::kNormal, OptionTypeFlags::kNone,
      [](const ConfigOptions& opts, const std::string& /*name*/,
         const std::string& value, void* addr) {
        auto cf_options = static_cast<ColumnFamilyOptions*>(addr);
@@ -2679,14 +2557,13 @@ static std::unordered_map<std::string, OptionTypeInfo> cfd_type_info = {

 static std::unordered_map<std::string, OptionTypeInfo> cs_input_type_info = {
    {"column_family",
-     OptionTypeInfo::Struct(
-         "column_family", &cfd_type_info,
-         offsetof(struct CompactionServiceInput, column_family),
-         OptionVerificationType::kNormal, OptionTypeFlags::kNone)},
+     OptionTypeInfo::Struct("column_family", &cfd_type_info,
+                            offset_of(&CompactionServiceInput::column_family),
+                            OptionVerificationType::kNormal,
+                            OptionTypeFlags::kNone)},
    {"db_options",
-     {offsetof(struct CompactionServiceInput, db_options),
-      OptionType::kConfigurable, OptionVerificationType::kNormal,
-      OptionTypeFlags::kNone,
+     {offset_of(&CompactionServiceInput::db_options), OptionType::kConfigurable,
+      OptionVerificationType::kNormal, OptionTypeFlags::kNone,
      [](const ConfigOptions& opts, const std::string& /*name*/,
         const std::string& value, void* addr) {
        auto options = static_cast<DBOptions*>(addr);
@@ -2715,36 +2592,31 @@ static std::unordered_map<std::string, OptionTypeInfo> cs_input_type_info = {
        return result;
      }}},
    {"snapshots", OptionTypeInfo::Vector<uint64_t>(
-                      offsetof(struct CompactionServiceInput, snapshots),
+                      offset_of(&CompactionServiceInput::snapshots),
                      OptionVerificationType::kNormal, OptionTypeFlags::kNone,
                      {0, OptionType::kUInt64T})},
    {"input_files", OptionTypeInfo::Vector<std::string>(
-                        offsetof(struct CompactionServiceInput, input_files),
+                        offset_of(&CompactionServiceInput::input_files),
                        OptionVerificationType::kNormal, OptionTypeFlags::kNone,
                        {0, OptionType::kEncodedString})},
    {"output_level",
-     {offsetof(struct CompactionServiceInput, output_level), OptionType::kInt,
+     {offset_of(&CompactionServiceInput::output_level), OptionType::kInt,
      OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
-    {"db_id",
-     {offsetof(struct CompactionServiceInput, db_id),
-      OptionType::kEncodedString}},
    {"has_begin",
-     {offsetof(struct CompactionServiceInput, has_begin), OptionType::kBoolean,
+     {offset_of(&CompactionServiceInput::has_begin), OptionType::kBoolean,
      OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
    {"begin",
-     {offsetof(struct CompactionServiceInput, begin),
-      OptionType::kEncodedString, OptionVerificationType::kNormal,
-      OptionTypeFlags::kNone}},
+     {offset_of(&CompactionServiceInput::begin), OptionType::kEncodedString,
+      OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
    {"has_end",
-     {offsetof(struct CompactionServiceInput, has_end), OptionType::kBoolean,
+     {offset_of(&CompactionServiceInput::has_end), OptionType::kBoolean,
      OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
    {"end",
-     {offsetof(struct CompactionServiceInput, end), OptionType::kEncodedString,
+     {offset_of(&CompactionServiceInput::end), OptionType::kEncodedString,
      OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
    {"approx_size",
-     {offsetof(struct CompactionServiceInput, approx_size),
-      OptionType::kUInt64T, OptionVerificationType::kNormal,
-      OptionTypeFlags::kNone}},
+     {offset_of(&CompactionServiceInput::approx_size), OptionType::kUInt64T,
+      OptionVerificationType::kNormal, OptionTypeFlags::kNone}},
 };

 static std::unordered_map<std::string, OptionTypeInfo>
@@ -2785,11 +2657,6 @@ static std::unordered_map<std::string, OptionTypeInfo>
         {offsetof(struct CompactionServiceOutputFile, marked_for_compaction),
          OptionType::kBoolean, OptionVerificationType::kNormal,
          OptionTypeFlags::kNone}},
-        {"unique_id",
-         OptionTypeInfo::Array<uint64_t, 2>(
-             offsetof(struct CompactionServiceOutputFile, unique_id),
-             OptionVerificationType::kNormal, OptionTypeFlags::kNone,
-             {0, OptionType::kUInt64T})},
 };

 static std::unordered_map<std::string, OptionTypeInfo>
@@ -2985,7 +2852,6 @@ static std::unordered_map<std::string, OptionTypeInfo> cs_result_type_info = {
         const void* addr1, const void* addr2, std::string* mismatch) {
        const auto status1 = static_cast<const Status*>(addr1);
        const auto status2 = static_cast<const Status*>(addr2);
-
        StatusSerializationAdapter adatper1(*status1);
        StatusSerializationAdapter adapter2(*status2);
        return OptionTypeInfo::TypesAreEqual(opts, status_adapter_type_info,
@@ -3043,7 +2909,7 @@ Status CompactionServiceInput::Read(const std::string& data_str,
  } else {
    return Status::NotSupported(
        "Compaction Service Input data version not supported: " +
-        std::to_string(format_version));
+        ToString(format_version));
  }
 }

@@ -3072,7 +2938,7 @@ Status CompactionServiceResult::Read(const std::string& data_str,
  } else {
    return Status::NotSupported(
        "Compaction Service Result data version not supported: " +
-        std::to_string(format_version));
+        ToString(format_version));
  }
 }

@@ -67,20 +67,22 @@ class CompactionJob {
      int job_id, Compaction* compaction, const ImmutableDBOptions& db_options,
      const MutableDBOptions& mutable_db_options,
      const FileOptions& file_options, VersionSet* versions,
-      const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
+      const std::atomic<bool>* shutting_down,
+      const SequenceNumber preserve_deletes_seqnum, LogBuffer* log_buffer,
      FSDirectory* db_directory, FSDirectory* output_directory,
      FSDirectory* blob_output_directory, Statistics* stats,
      InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
      std::vector<SequenceNumber> existing_snapshots,
      SequenceNumber earliest_write_conflict_snapshot,
-      const SnapshotChecker* snapshot_checker, JobContext* job_context,
+      const SnapshotChecker* snapshot_checker,
      std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
      bool paranoid_file_checks, bool measure_io_stats,
      const std::string& dbname, CompactionJobStats* compaction_job_stats,
      Env::Priority thread_pri, const std::shared_ptr<IOTracer>& io_tracer,
-      const std::atomic<bool>& manual_compaction_canceled,
+      const std::atomic<int>* manual_compaction_paused = nullptr,
+      const std::atomic<bool>* manual_compaction_canceled = nullptr,
      const std::string& db_id = "", const std::string& db_session_id = "",
-      std::string full_history_ts_low = "", std::string trim_ts = "",
+      std::string full_history_ts_low = "",
      BlobFileCompletionCallback* blob_callback = nullptr);

  virtual ~CompactionJob();
@@ -136,8 +138,6 @@ class CompactionJob {
  IOStatus io_status_;

 private:
-  friend class CompactionJobTestBase;
-
  // Generates a histogram representing potential divisions of key ranges from
  // the input. It adds the starting and/or ending keys of certain input files
  // to the working set and then finds the approximate size of data in between
@@ -167,16 +167,6 @@ class CompactionJob {
  void UpdateCompactionInputStatsHelper(
      int* num_files, uint64_t* bytes_read, int input_level);

-#ifndef ROCKSDB_LITE
-  void BuildSubcompactionJobInfo(
-      SubcompactionState* sub_compact,
-      SubcompactionJobInfo* subcompaction_job_info) const;
-#endif  // ROCKSDB_LITE
-
-  void NotifyOnSubcompactionBegin(SubcompactionState* sub_compact);
-
-  void NotifyOnSubcompactionCompleted(SubcompactionState* sub_compact);
-
  uint32_t job_id_;

  CompactionJobStats* compaction_job_stats_;
@@ -194,7 +184,9 @@ class CompactionJob {
  FileOptions file_options_for_read_;
  VersionSet* versions_;
  const std::atomic<bool>* shutting_down_;
-  const std::atomic<bool>& manual_compaction_canceled_;
+  const std::atomic<int>* manual_compaction_paused_;
+  const std::atomic<bool>* manual_compaction_canceled_;
+  const SequenceNumber preserve_deletes_seqnum_;
  FSDirectory* db_directory_;
  FSDirectory* blob_output_directory_;
  InstrumentedMutex* db_mutex_;
@@ -212,8 +204,6 @@ class CompactionJob {

  const SnapshotChecker* const snapshot_checker_;

-  JobContext* job_context_;
-
  std::shared_ptr<Cache> table_cache_;

  EventLogger* event_logger_;
@@ -226,7 +216,6 @@ class CompactionJob {
  std::vector<uint64_t> sizes_;
  Env::Priority thread_pri_;
  std::string full_history_ts_low_;
-  std::string trim_ts_;
  BlobFileCompletionCallback* blob_callback_;

  uint64_t GetCompactionId(SubcompactionState* sub_compact);
@@ -234,10 +223,6 @@ class CompactionJob {
  // Get table file name in where it's outputting to, which should also be in
  // `output_directory_`.
  virtual std::string GetTableFileName(uint64_t file_number);
-  // The rate limiter priority (io_priority) is determined dynamically here.
-  // The Compaction Read and Write priorities are the same for different
-  // scenarios, such as write stalled.
-  Env::IOPriority GetRateLimiterPriority();
 };

 // CompactionServiceInput is used the pass compaction information between two
@@ -257,9 +242,6 @@ struct CompactionServiceInput {
  std::vector<std::string> input_files;
  int output_level;

-  // db_id is used to generate unique id of sst on the remote compactor
-  std::string db_id;
-
  // information for subcompaction
  bool has_begin = false;
  std::string begin;
@@ -291,15 +273,13 @@ struct CompactionServiceOutputFile {
  uint64_t file_creation_time;
  uint64_t paranoid_hash;
  bool marked_for_compaction;
-  UniqueId64x2 unique_id;

  CompactionServiceOutputFile() = default;
  CompactionServiceOutputFile(
      const std::string& name, SequenceNumber smallest, SequenceNumber largest,
      std::string _smallest_internal_key, std::string _largest_internal_key,
      uint64_t _oldest_ancester_time, uint64_t _file_creation_time,
-      uint64_t _paranoid_hash, bool _marked_for_compaction,
-      UniqueId64x2 _unique_id)
+      uint64_t _paranoid_hash, bool _marked_for_compaction)
      : file_name(name),
        smallest_seqno(smallest),
        largest_seqno(largest),
@@ -308,8 +288,7 @@ struct CompactionServiceOutputFile {
        oldest_ancester_time(_oldest_ancester_time),
        file_creation_time(_file_creation_time),
        paranoid_hash(_paranoid_hash),
-        marked_for_compaction(_marked_for_compaction),
-        unique_id(std::move(_unique_id)) {}
+        marked_for_compaction(_marked_for_compaction) {}
 };

 // CompactionServiceResult contains the compaction result from a different db
@@ -355,7 +334,6 @@ class CompactionServiceCompactionJob : private CompactionJob {
      std::vector<SequenceNumber> existing_snapshots,
      std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
      const std::string& dbname, const std::shared_ptr<IOTracer>& io_tracer,
-      const std::atomic<bool>& manual_compaction_canceled,
      const std::string& db_id, const std::string& db_session_id,
      const std::string& output_path,
      const CompactionServiceInput& compaction_service_input,
@@ -268,10 +268,10 @@ class CompactionJobStatsTest : public testing::Test,
    if (cf == 0) {
      // default cfd
      EXPECT_TRUE(db_->GetProperty(
-          "rocksdb.num-files-at-level" + std::to_string(level), &property));
+          "rocksdb.num-files-at-level" + ToString(level), &property));
    } else {
      EXPECT_TRUE(db_->GetProperty(
-          handles_[cf], "rocksdb.num-files-at-level" + std::to_string(level),
+          handles_[cf], "rocksdb.num-files-at-level" + ToString(level),
          &property));
    }
    return atoi(property.c_str());
@@ -672,7 +672,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
      snprintf(buf, kBufSize, "%d", ++num_L0_files);
      ASSERT_EQ(std::string(buf), FilesPerLevel(1));
    }
-    ASSERT_EQ(std::to_string(num_L0_files), FilesPerLevel(1));
+    ASSERT_EQ(ToString(num_L0_files), FilesPerLevel(1));

    // 2nd Phase: perform L0 -> L1 compaction.
    int L0_compaction_count = 6;
@@ -27,7 +27,6 @@
 #include "rocksdb/options.h"
 #include "rocksdb/write_buffer_manager.h"
 #include "table/mock_table.h"
-#include "table/unique_id_impl.h"
 #include "test_util/testharness.h"
 #include "test_util/testutil.h"
 #include "util/string_util.h"
@@ -69,138 +68,12 @@ void VerifyInitializationOfCompactionJobStats(
 #endif  // !defined(IOS_CROSS_COMPILE)
 }

-// Mock FSWritableFile for testing io priority.
-// Only override the essential functions for testing compaction io priority.
-class MockTestWritableFile : public FSWritableFileOwnerWrapper {
- public:
-  MockTestWritableFile(std::unique_ptr<FSWritableFile>&& file,
-                       Env::IOPriority io_priority)
-      : FSWritableFileOwnerWrapper(std::move(file)),
-        write_io_priority_(io_priority) {}
-  IOStatus Append(const Slice& data, const IOOptions& options,
-                  IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, write_io_priority_);
-    return target()->Append(data, options, dbg);
-  }
-  IOStatus Append(const Slice& data, const IOOptions& options,
-                  const DataVerificationInfo& verification_info,
-                  IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, write_io_priority_);
-    return target()->Append(data, options, verification_info, dbg);
-  }
-  IOStatus Close(const IOOptions& options, IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, write_io_priority_);
-    return target()->Close(options, dbg);
-  }
-  IOStatus Flush(const IOOptions& options, IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, write_io_priority_);
-    return target()->Flush(options, dbg);
-  }
-  IOStatus Sync(const IOOptions& options, IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, write_io_priority_);
-    return target()->Sync(options, dbg);
-  }
-  IOStatus Fsync(const IOOptions& options, IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, write_io_priority_);
-    return target()->Fsync(options, dbg);
-  }
-  uint64_t GetFileSize(const IOOptions& options, IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, write_io_priority_);
-    return target()->GetFileSize(options, dbg);
-  }
-  IOStatus RangeSync(uint64_t offset, uint64_t nbytes, const IOOptions& options,
-                     IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, write_io_priority_);
-    return target()->RangeSync(offset, nbytes, options, dbg);
-  }
-
-  void PrepareWrite(size_t offset, size_t len, const IOOptions& options,
-                    IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, write_io_priority_);
-    target()->PrepareWrite(offset, len, options, dbg);
-  }
-
-  IOStatus Allocate(uint64_t offset, uint64_t len, const IOOptions& options,
-                    IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, write_io_priority_);
-    return target()->Allocate(offset, len, options, dbg);
-  }
-
- private:
-  Env::IOPriority write_io_priority_;
-};
-
-// Mock FSRandomAccessFile for testing io priority.
-// Only override the essential functions for testing compaction io priority.
-class MockTestRandomAccessFile : public FSRandomAccessFileOwnerWrapper {
- public:
-  MockTestRandomAccessFile(std::unique_ptr<FSRandomAccessFile>&& file,
-                           Env::IOPriority io_priority)
-      : FSRandomAccessFileOwnerWrapper(std::move(file)),
-        read_io_priority_(io_priority) {}
-
-  IOStatus Read(uint64_t offset, size_t n, const IOOptions& options,
-                Slice* result, char* scratch,
-                IODebugContext* dbg) const override {
-    EXPECT_EQ(options.rate_limiter_priority, read_io_priority_);
-    return target()->Read(offset, n, options, result, scratch, dbg);
-  }
-  IOStatus Prefetch(uint64_t offset, size_t n, const IOOptions& options,
-                    IODebugContext* dbg) override {
-    EXPECT_EQ(options.rate_limiter_priority, read_io_priority_);
-    return target()->Prefetch(offset, n, options, dbg);
-  }
-
- private:
-  Env::IOPriority read_io_priority_;
-};
-
-// Mock FileSystem for testing io priority.
-class MockTestFileSystem : public FileSystemWrapper {
- public:
-  explicit MockTestFileSystem(const std::shared_ptr<FileSystem>& base,
-                              Env::IOPriority read_io_priority,
-                              Env::IOPriority write_io_priority)
-      : FileSystemWrapper(base),
-        read_io_priority_(read_io_priority),
-        write_io_priority_(write_io_priority) {}
-
-  static const char* kClassName() { return "MockTestFileSystem"; }
-  const char* Name() const override { return kClassName(); }
-
-  IOStatus NewRandomAccessFile(const std::string& fname,
-                               const FileOptions& file_opts,
-                               std::unique_ptr<FSRandomAccessFile>* result,
-                               IODebugContext* dbg) override {
-    IOStatus s = target()->NewRandomAccessFile(fname, file_opts, result, dbg);
-    EXPECT_OK(s);
-    result->reset(
-        new MockTestRandomAccessFile(std::move(*result), read_io_priority_));
-    return s;
-  }
-  IOStatus NewWritableFile(const std::string& fname,
-                           const FileOptions& file_opts,
-                           std::unique_ptr<FSWritableFile>* result,
-                           IODebugContext* dbg) override {
-    IOStatus s = target()->NewWritableFile(fname, file_opts, result, dbg);
-    EXPECT_OK(s);
-    result->reset(
-        new MockTestWritableFile(std::move(*result), write_io_priority_));
-    return s;
-  }
-
- private:
-  Env::IOPriority read_io_priority_;
-  Env::IOPriority write_io_priority_;
-};
-
 }  // namespace

 class CompactionJobTestBase : public testing::Test {
 protected:
  CompactionJobTestBase(std::string dbname, const Comparator* ucmp,
-                        std::function<std::string(uint64_t)> encode_u64_ts,
-                        bool test_io_priority)
+                        std::function<std::string(uint64_t)> encode_u64_ts)
      : dbname_(std::move(dbname)),
        ucmp_(ucmp),
        db_options_(),
@@ -214,10 +87,10 @@ class CompactionJobTestBase : public testing::Test {
                                 /*block_cache_tracer=*/nullptr,
                                 /*io_tracer=*/nullptr, /*db_session_id*/ "")),
        shutting_down_(false),
+        preserve_deletes_seqnum_(0),
        mock_table_factory_(new mock::MockTableFactory()),
        error_handler_(nullptr, db_options_, &mutex_),
-        encode_u64_ts_(std::move(encode_u64_ts)),
-        test_io_priority_(test_io_priority) {
+        encode_u64_ts_(std::move(encode_u64_ts)) {
    Env* base_env = Env::Default();
    EXPECT_OK(
        test::CreateEnvFromSystem(ConfigOptions(), &base_env, &env_guard_));
@@ -232,12 +105,7 @@ class CompactionJobTestBase : public testing::Test {
    db_options_.db_paths.emplace_back(dbname_,
                                      std::numeric_limits<uint64_t>::max());
    cf_options_.comparator = ucmp_;
-    if (test_io_priority_) {
-      BlockBasedTableOptions table_options;
-      cf_options_.table_factory.reset(NewBlockBasedTableFactory(table_options));
-    } else {
-      cf_options_.table_factory = mock_table_factory_;
-    }
+    cf_options_.table_factory = mock_table_factory_;
  }

  std::string GenerateFileName(uint64_t file_number) {
@@ -277,33 +145,6 @@ class CompactionJobTestBase : public testing::Test {
    return blob_index;
  }

-  // Creates a table with the specificied key value pairs.
-  void CreateTable(const std::string& table_name,
-                   const mock::KVVector& contents, uint64_t& file_size) {
-    std::unique_ptr<WritableFileWriter> file_writer;
-    Status s = WritableFileWriter::Create(fs_, table_name, FileOptions(),
-                                          &file_writer, nullptr);
-    ASSERT_OK(s);
-    std::unique_ptr<TableBuilder> table_builder(
-        cf_options_.table_factory->NewTableBuilder(
-            TableBuilderOptions(*cfd_->ioptions(), mutable_cf_options_,
-                                cfd_->internal_comparator(),
-                                cfd_->int_tbl_prop_collector_factories(),
-                                CompressionType::kNoCompression,
-                                CompressionOptions(), 0 /* column_family_id */,
-                                kDefaultColumnFamilyName, -1 /* level */),
-            file_writer.get()));
-    // Build table.
-    for (auto kv : contents) {
-      std::string key;
-      std::string value;
-      std::tie(key, value) = kv;
-      table_builder->Add(key, value);
-    }
-    ASSERT_OK(table_builder->Finish());
-    file_size = table_builder->FileSize();
-  }
-
  void AddMockFile(const mock::KVVector& contents, int level = 0) {
    assert(contents.size() > 0);

@@ -357,23 +198,16 @@ class CompactionJobTestBase : public testing::Test {
    }

    uint64_t file_number = versions_->NewFileNumber();
-
-    uint64_t file_size;
-    if (test_io_priority_) {
-      CreateTable(GenerateFileName(file_number), contents, file_size);
-    } else {
-      file_size = 10;
-      EXPECT_OK(mock_table_factory_->CreateMockTable(
-          env_, GenerateFileName(file_number), std::move(contents)));
-    }
+    EXPECT_OK(mock_table_factory_->CreateMockTable(
+        env_, GenerateFileName(file_number), std::move(contents)));

    VersionEdit edit;
-    edit.AddFile(level, file_number, 0, file_size, smallest_key, largest_key,
+    edit.AddFile(level, file_number, 0, 10, smallest_key, largest_key,
                 smallest_seqno, largest_seqno, false, Temperature::kUnknown,
                 oldest_blob_file_number, kUnknownOldestAncesterTime,
                 kUnknownFileCreationTime, kUnknownFileChecksum,
                 kUnknownFileChecksumFuncName, kDisableUserTimestamp,
-                 kDisableUserTimestamp, kNullUniqueId64x2);
+                 kDisableUserTimestamp);

    mutex_.Lock();
    EXPECT_OK(
@@ -403,8 +237,8 @@ class CompactionJobTestBase : public testing::Test {
    for (int i = 0; i < 2; ++i) {
      auto contents = mock::MakeMockFile();
      for (int k = 0; k < kKeysPerFile; ++k) {
-        auto key = std::to_string(i * kMatchingKeys + k);
-        auto value = std::to_string(i * kKeysPerFile + k);
+        auto key = ToString(i * kMatchingKeys + k);
+        auto value = ToString(i * kKeysPerFile + k);
        InternalKey internal_key(key, ++sequence_number, kTypeValue);

        // This is how the key will look like once it's written in bottommost
@@ -488,16 +322,7 @@ class CompactionJobTestBase : public testing::Test {
      const std::vector<SequenceNumber>& snapshots = {},
      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber,
      int output_level = 1, bool verify = true,
-      uint64_t expected_oldest_blob_file_number = kInvalidBlobFileNumber,
-      bool check_get_priority = false,
-      Env::IOPriority read_io_priority = Env::IO_TOTAL,
-      Env::IOPriority write_io_priority = Env::IO_TOTAL) {
-    // For compaction, set fs as MockTestFileSystem to check the io_priority.
-    if (test_io_priority_) {
-      db_options_.fs.reset(
-          new MockTestFileSystem(fs_, read_io_priority, write_io_priority));
-    }
-
+      uint64_t expected_oldest_blob_file_number = kInvalidBlobFileNumber) {
    auto cfd = versions_->GetColumnFamilySet()->GetDefault();

    size_t num_input_files = 0;
@@ -527,17 +352,16 @@ class CompactionJobTestBase : public testing::Test {
    SnapshotChecker* snapshot_checker = nullptr;
    ASSERT_TRUE(full_history_ts_low_.empty() ||
                ucmp_->timestamp_size() == full_history_ts_low_.size());
-    const std::atomic<bool> kManualCompactionCanceledFalse{false};
    CompactionJob compaction_job(
        0, &compaction, db_options_, mutable_db_options_, env_options_,
-        versions_.get(), &shutting_down_, &log_buffer, nullptr, nullptr,
-        nullptr, nullptr, &mutex_, &error_handler_, snapshots,
-        earliest_write_conflict_snapshot, snapshot_checker, nullptr,
-        table_cache_, &event_logger, false, false, dbname_,
-        &compaction_job_stats_, Env::Priority::USER, nullptr /* IOTracer */,
-        /*manual_compaction_canceled=*/kManualCompactionCanceledFalse,
-        env_->GenerateUniqueId(), DBImpl::GenerateDbSessionId(nullptr),
-        full_history_ts_low_);
+        versions_.get(), &shutting_down_, preserve_deletes_seqnum_, &log_buffer,
+        nullptr, nullptr, nullptr, nullptr, &mutex_, &error_handler_, snapshots,
+        earliest_write_conflict_snapshot, snapshot_checker, table_cache_,
+        &event_logger, false, false, dbname_, &compaction_job_stats_,
+        Env::Priority::USER, nullptr /* IOTracer */,
+        /*manual_compaction_paused=*/nullptr,
+        /*manual_compaction_canceled=*/nullptr, /*db_id=*/"",
+        /*db_session_id=*/"", full_history_ts_low_);
    VerifyInitializationOfCompactionJobStats(compaction_job_stats_);

    compaction_job.Prepare();
@@ -567,32 +391,6 @@ class CompactionJobTestBase : public testing::Test {
                  expected_oldest_blob_file_number);
      }
    }
-
-    if (check_get_priority) {
-      CheckGetRateLimiterPriority(compaction_job);
-    }
-  }
-
-  void CheckGetRateLimiterPriority(CompactionJob& compaction_job) {
-    // When the state from WriteController is normal.
-    ASSERT_EQ(compaction_job.GetRateLimiterPriority(), Env::IO_LOW);
-
-    WriteController* write_controller =
-        compaction_job.versions_->GetColumnFamilySet()->write_controller();
-
-    {
-      // When the state from WriteController is Delayed.
-      std::unique_ptr<WriteControllerToken> delay_token =
-          write_controller->GetDelayToken(1000000);
-      ASSERT_EQ(compaction_job.GetRateLimiterPriority(), Env::IO_USER);
-    }
-
-    {
-      // When the state from WriteController is Stopped.
-      std::unique_ptr<WriteControllerToken> stop_token =
-          write_controller->GetStopToken();
-      ASSERT_EQ(compaction_job.GetRateLimiterPriority(), Env::IO_USER);
-    }
  }

  std::shared_ptr<Env> env_guard_;
@@ -611,6 +409,7 @@ class CompactionJobTestBase : public testing::Test {
  std::unique_ptr<VersionSet> versions_;
  InstrumentedMutex mutex_;
  std::atomic<bool> shutting_down_;
+  SequenceNumber preserve_deletes_seqnum_;
  std::shared_ptr<mock::MockTableFactory> mock_table_factory_;
  CompactionJobStats compaction_job_stats_;
  ColumnFamilyData* cfd_;
@@ -619,16 +418,15 @@ class CompactionJobTestBase : public testing::Test {
  ErrorHandler error_handler_;
  std::string full_history_ts_low_;
  const std::function<std::string(uint64_t)> encode_u64_ts_;
-  bool test_io_priority_;
 };

 // TODO(icanadi) Make it simpler once we mock out VersionSet
 class CompactionJobTest : public CompactionJobTestBase {
 public:
  CompactionJobTest()
-      : CompactionJobTestBase(
-            test::PerThreadDBPath("compaction_job_test"), BytewiseComparator(),
-            [](uint64_t /*ts*/) { return ""; }, false) {}
+      : CompactionJobTestBase(test::PerThreadDBPath("compaction_job_test"),
+                              BytewiseComparator(),
+                              [](uint64_t /*ts*/) { return ""; }) {}
 };

 TEST_F(CompactionJobTest, Simple) {
@@ -1094,10 +892,10 @@ TEST_F(CompactionJobTest, MultiSingleDelete) {
  //      -> Snapshot Put
  // K: SDel SDel Put SDel Put Put Snapshot SDel Put SDel SDel Put SDel
  //      -> Snapshot Put Snapshot SDel
-  // L: SDel Put SDel Put SDel Snapshot SDel Put SDel SDel Put SDel
-  //      -> Snapshot SDel Put SDel
-  // M: (Put) SDel Put SDel Put SDel Snapshot Put SDel SDel Put SDel SDel
-  //      -> SDel Snapshot Put SDel
+  // L: SDel Put Del Put SDel Snapshot Del Put Del SDel Put SDel
+  //      -> Snapshot SDel
+  // M: (Put) SDel Put Del Put SDel Snapshot Put Del SDel Put SDel Del
+  //      -> SDel Snapshot Del
  NewDB();

  auto file1 = mock::MakeMockFile({
@@ -1128,14 +926,14 @@ TEST_F(CompactionJobTest, MultiSingleDelete) {
      {KeyStr("L", 16U, kTypeSingleDeletion), ""},
      {KeyStr("L", 15U, kTypeValue), "val"},
      {KeyStr("L", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("L", 13U, kTypeSingleDeletion), ""},
+      {KeyStr("L", 13U, kTypeDeletion), ""},
      {KeyStr("L", 12U, kTypeValue), "val"},
-      {KeyStr("L", 11U, kTypeSingleDeletion), ""},
-      {KeyStr("M", 16U, kTypeSingleDeletion), ""},
+      {KeyStr("L", 11U, kTypeDeletion), ""},
+      {KeyStr("M", 16U, kTypeDeletion), ""},
      {KeyStr("M", 15U, kTypeSingleDeletion), ""},
      {KeyStr("M", 14U, kTypeValue), "val"},
      {KeyStr("M", 13U, kTypeSingleDeletion), ""},
-      {KeyStr("M", 12U, kTypeSingleDeletion), ""},
+      {KeyStr("M", 12U, kTypeDeletion), ""},
      {KeyStr("M", 11U, kTypeValue), "val"},
  });
  AddMockFile(file1);
@@ -1176,12 +974,12 @@ TEST_F(CompactionJobTest, MultiSingleDelete) {
      {KeyStr("K", 1U, kTypeSingleDeletion), ""},
      {KeyStr("L", 5U, kTypeSingleDeletion), ""},
      {KeyStr("L", 4U, kTypeValue), "val"},
-      {KeyStr("L", 3U, kTypeSingleDeletion), ""},
+      {KeyStr("L", 3U, kTypeDeletion), ""},
      {KeyStr("L", 2U, kTypeValue), "val"},
      {KeyStr("L", 1U, kTypeSingleDeletion), ""},
      {KeyStr("M", 10U, kTypeSingleDeletion), ""},
      {KeyStr("M", 7U, kTypeValue), "val"},
-      {KeyStr("M", 5U, kTypeSingleDeletion), ""},
+      {KeyStr("M", 5U, kTypeDeletion), ""},
      {KeyStr("M", 4U, kTypeValue), "val"},
      {KeyStr("M", 3U, kTypeSingleDeletion), ""},
  });
@@ -1223,9 +1021,7 @@ TEST_F(CompactionJobTest, MultiSingleDelete) {
                          {KeyStr("K", 8U, kTypeValue), "val3"},
                          {KeyStr("L", 16U, kTypeSingleDeletion), ""},
                          {KeyStr("L", 15U, kTypeValue), ""},
-                          {KeyStr("L", 11U, kTypeSingleDeletion), ""},
-                          {KeyStr("M", 15U, kTypeSingleDeletion), ""},
-                          {KeyStr("M", 14U, kTypeValue), ""},
+                          {KeyStr("M", 16U, kTypeDeletion), ""},
                          {KeyStr("M", 3U, kTypeSingleDeletion), ""}});

  SetLastSequence(22U);
@@ -1311,21 +1107,6 @@ TEST_F(CompactionJobTest, OldestBlobFileNumber) {
                /* expected_oldest_blob_file_number */ 19);
 }

-TEST_F(CompactionJobTest, NoEnforceSingleDeleteContract) {
-  db_options_.enforce_single_del_contracts = false;
-  NewDB();
-
-  auto file =
-      mock::MakeMockFile({{KeyStr("a", 4U, kTypeSingleDeletion), ""},
-                          {KeyStr("a", 3U, kTypeDeletion), "dontcare"}});
-  AddMockFile(file);
-  SetLastSequence(4U);
-
-  auto expected_results = mock::MakeMockFile();
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-}
-
 TEST_F(CompactionJobTest, InputSerialization) {
  // Setup a random CompactionServiceInput
  CompactionServiceInput input;
@@ -1431,14 +1212,13 @@ TEST_F(CompactionJobTest, ResultSerialization) {
  result.status =
      status_list.at(rnd.Uniform(static_cast<int>(status_list.size())));
  while (!rnd.OneIn(10)) {
-    UniqueId64x2 id{rnd64.Uniform(UINT64_MAX), rnd64.Uniform(UINT64_MAX)};
    result.output_files.emplace_back(
        rnd.RandomString(rnd.Uniform(kStrMaxLen)), rnd64.Uniform(UINT64_MAX),
        rnd64.Uniform(UINT64_MAX),
        rnd.RandomBinaryString(rnd.Uniform(kStrMaxLen)),
        rnd.RandomBinaryString(rnd.Uniform(kStrMaxLen)),
        rnd64.Uniform(UINT64_MAX), rnd64.Uniform(UINT64_MAX),
-        rnd64.Uniform(UINT64_MAX), rnd.OneIn(2), id);
+        rnd64.Uniform(UINT64_MAX), rnd.OneIn(2));
  }
  result.output_level = rnd.Uniform(10);
  result.output_path = rnd.RandomString(rnd.Uniform(kStrMaxLen));
@@ -1466,16 +1246,6 @@ TEST_F(CompactionJobTest, ResultSerialization) {
  ASSERT_FALSE(deserialized1.TEST_Equals(&result, &mismatch));
  ASSERT_EQ(mismatch, "stats.num_input_files");

-  // Test unique id mismatch
-  if (!result.output_files.empty()) {
-    CompactionServiceResult deserialized_tmp;
-    ASSERT_OK(CompactionServiceResult::Read(output, &deserialized_tmp));
-    deserialized_tmp.output_files[0].unique_id[0] += 1;
-    ASSERT_FALSE(deserialized_tmp.TEST_Equals(&result, &mismatch));
-    ASSERT_EQ(mismatch, "output_files.unique_id");
-    deserialized_tmp.status.PermitUncheckedError();
-  }
-
  // Test unknown field
  CompactionServiceResult deserialized2;
  output.clear();
@@ -1518,13 +1288,11 @@ TEST_F(CompactionJobTest, ResultSerialization) {
  }
 }

-
 class CompactionJobTimestampTest : public CompactionJobTestBase {
 public:
  CompactionJobTimestampTest()
      : CompactionJobTestBase(test::PerThreadDBPath("compaction_job_ts_test"),
-                              test::BytewiseComparatorWithU64TsWrapper(),
-                              test::EncodeInt, false) {}
+                              test::ComparatorWithU64Ts(), test::EncodeInt) {}
 };

 TEST_F(CompactionJobTimestampTest, GCDisabled) {
@@ -1640,69 +1408,6 @@ TEST_F(CompactionJobTimestampTest, SomeKeysExpired) {
  RunCompaction({files}, expected_results);
 }

-// The io priority of the compaction reads and writes are different from
-// other DB reads and writes. To prepare the compaction input files, use the
-// default filesystem from Env. To test the io priority of the compaction
-// reads and writes, db_options_.fs is set as MockTestFileSystem.
-class CompactionJobIOPriorityTest : public CompactionJobTestBase {
- public:
-  CompactionJobIOPriorityTest()
-      : CompactionJobTestBase(
-            test::PerThreadDBPath("compaction_job_io_priority_test"),
-            BytewiseComparator(), [](uint64_t /*ts*/) { return ""; }, true) {}
-};
-
-TEST_F(CompactionJobIOPriorityTest, WriteControllerStateNormal) {
-  // When the state from WriteController is normal.
-  NewDB();
-  mock::KVVector expected_results = CreateTwoFiles(false);
-  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-  auto files = cfd->current()->storage_info()->LevelFiles(0);
-  ASSERT_EQ(2U, files.size());
-  RunCompaction({files}, expected_results, {}, kMaxSequenceNumber, 1, false,
-                kInvalidBlobFileNumber, false, Env::IO_LOW, Env::IO_LOW);
-}
-
-TEST_F(CompactionJobIOPriorityTest, WriteControllerStateDelayed) {
-  // When the state from WriteController is Delayed.
-  NewDB();
-  mock::KVVector expected_results = CreateTwoFiles(false);
-  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-  auto files = cfd->current()->storage_info()->LevelFiles(0);
-  ASSERT_EQ(2U, files.size());
-  {
-    std::unique_ptr<WriteControllerToken> delay_token =
-        write_controller_.GetDelayToken(1000000);
-    RunCompaction({files}, expected_results, {}, kMaxSequenceNumber, 1, false,
-                  kInvalidBlobFileNumber, false, Env::IO_USER, Env::IO_USER);
-  }
-}
-
-TEST_F(CompactionJobIOPriorityTest, WriteControllerStateStalled) {
-  // When the state from WriteController is Stalled.
-  NewDB();
-  mock::KVVector expected_results = CreateTwoFiles(false);
-  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-  auto files = cfd->current()->storage_info()->LevelFiles(0);
-  ASSERT_EQ(2U, files.size());
-  {
-    std::unique_ptr<WriteControllerToken> stop_token =
-        write_controller_.GetStopToken();
-    RunCompaction({files}, expected_results, {}, kMaxSequenceNumber, 1, false,
-                  kInvalidBlobFileNumber, false, Env::IO_USER, Env::IO_USER);
-  }
-}
-
-TEST_F(CompactionJobIOPriorityTest, GetRateLimiterPriority) {
-  NewDB();
-  mock::KVVector expected_results = CreateTwoFiles(false);
-  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-  auto files = cfd->current()->storage_info()->LevelFiles(0);
-  ASSERT_EQ(2U, files.size());
-  RunCompaction({files}, expected_results, {}, kMaxSequenceNumber, 1, false,
-                kInvalidBlobFileNumber, true, Env::IO_LOW, Env::IO_LOW);
-}
-
 }  // namespace ROCKSDB_NAMESPACE

 int main(int argc, char** argv) {
@@ -65,7 +65,7 @@ bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
  size_t compact_bytes = static_cast<size_t>(level_files[start]->fd.file_size);
  uint64_t compensated_compact_bytes =
      level_files[start]->compensated_file_size;
-  size_t compact_bytes_per_del_file = std::numeric_limits<size_t>::max();
+  size_t compact_bytes_per_del_file = port::kMaxSizet;
  // Compaction range will be [start, limit).
  size_t limit;
  // Pull in files until the amount of compaction work per deleted file begins
@@ -100,7 +100,8 @@ bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
 // If enable_compression is false, then compression is always disabled no
 // matter what the values of the other two parameters are.
 // Otherwise, the compression type is determined based on options and level.
-CompressionType GetCompressionType(const VersionStorageInfo* vstorage,
+CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
+                                   const VersionStorageInfo* vstorage,
                                   const MutableCFOptions& mutable_cf_options,
                                   int level, int base_level,
                                   const bool enable_compression) {
@@ -117,19 +118,17 @@ CompressionType GetCompressionType(const VersionStorageInfo* vstorage,
  }
  // If the user has specified a different compression level for each level,
  // then pick the compression for that level.
-  if (!mutable_cf_options.compression_per_level.empty()) {
+  if (!ioptions.compression_per_level.empty()) {
    assert(level == 0 || level >= base_level);
    int idx = (level == 0) ? 0 : level - base_level + 1;

-    const int n =
-        static_cast<int>(mutable_cf_options.compression_per_level.size()) - 1;
+    const int n = static_cast<int>(ioptions.compression_per_level.size()) - 1;
    // It is possible for level_ to be -1; in that case, we use level
    // 0's compression.  This occurs mostly in backwards compatibility
    // situations when the builder doesn't know what level the file
    // belongs to.  Likewise, if level is beyond the end of the
    // specified compression levels, use the last value.
-    return mutable_cf_options
-        .compression_per_level[std::max(0, std::min(idx, n))];
+    return ioptions.compression_per_level[std::max(0, std::min(idx, n))];
  } else {
    return mutable_cf_options.compression;
  }
@@ -348,8 +347,9 @@ Compaction* CompactionPicker::CompactFiles(
    } else {
      base_level = 1;
    }
-    compression_type = GetCompressionType(vstorage, mutable_cf_options,
-                                          output_level, base_level);
+    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.
@@ -401,7 +401,7 @@ Status CompactionPicker::GetCompactionInputsFromFileNumbers(
        "Cannot find matched SST files for the following file numbers:");
    for (auto fn : *input_set) {
      message += " ";
-      message += std::to_string(fn);
+      message += ToString(fn);
    }
    return Status::InvalidArgument(message);
  }
@@ -571,7 +571,7 @@ Compaction* CompactionPicker::CompactRange(
    int input_level, int output_level,
    const CompactRangeOptions& compact_range_options, const InternalKey* begin,
    const InternalKey* end, InternalKey** compaction_end, bool* manual_conflict,
-    uint64_t max_file_num_to_ignore, const std::string& trim_ts) {
+    uint64_t max_file_num_to_ignore) {
  // CompactionPickerFIFO has its own implementation of compact range
  assert(ioptions_.compaction_style != kCompactionStyleFIFO);

@@ -637,14 +637,12 @@ Compaction* CompactionPicker::CompactRange(
                            ioptions_.compaction_style),
        /* max_compaction_bytes */ LLONG_MAX,
        compact_range_options.target_path_id,
-        GetCompressionType(vstorage, mutable_cf_options, output_level, 1),
+        GetCompressionType(ioptions_, vstorage, mutable_cf_options,
+                           output_level, 1),
        GetCompressionOptions(mutable_cf_options, vstorage, output_level),
        Temperature::kUnknown, compact_range_options.max_subcompactions,
-        /* grandparents */ {}, /* is manual */ true, trim_ts, /* score */ -1,
-        /* deletion_compaction */ false, CompactionReason::kUnknown,
-        compact_range_options.blob_garbage_collection_policy,
-        compact_range_options.blob_garbage_collection_age_cutoff);
-
+        /* grandparents */ {},
+        /* is manual */ true);
    RegisterCompaction(c);
    vstorage->ComputeCompactionScore(ioptions_, mutable_cf_options);
    return c;
@@ -721,7 +719,7 @@ Compaction* CompactionPicker::CompactRange(
  // files that are created during the current compaction.
  if (compact_range_options.bottommost_level_compaction ==
          BottommostLevelCompaction::kForceOptimized &&
-      max_file_num_to_ignore != std::numeric_limits<uint64_t>::max()) {
+      max_file_num_to_ignore != port::kMaxUint64) {
    assert(input_level == output_level);
    // inputs_shrunk holds a continuous subset of input files which were all
    // created before the current manual compaction
@@ -818,14 +816,12 @@ Compaction* CompactionPicker::CompactRange(
                          ioptions_.level_compaction_dynamic_level_bytes),
      mutable_cf_options.max_compaction_bytes,
      compact_range_options.target_path_id,
-      GetCompressionType(vstorage, mutable_cf_options, output_level,
+      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
                         vstorage->base_level()),
      GetCompressionOptions(mutable_cf_options, vstorage, output_level),
      Temperature::kUnknown, compact_range_options.max_subcompactions,
-      std::move(grandparents), /* is manual */ true, trim_ts, /* score */ -1,
-      /* deletion_compaction */ false, CompactionReason::kUnknown,
-      compact_range_options.blob_garbage_collection_policy,
-      compact_range_options.blob_garbage_collection_age_cutoff);
+      std::move(grandparents),
+      /* is manual compaction */ true);

  TEST_SYNC_POINT_CALLBACK("CompactionPicker::CompactRange:Return", compaction);
  RegisterCompaction(compaction);
@@ -1010,14 +1006,14 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
    return Status::InvalidArgument(
        "Output level for column family " + cf_meta.name +
        " must between [0, " +
-        std::to_string(cf_meta.levels[cf_meta.levels.size() - 1].level) + "].");
+        ToString(cf_meta.levels[cf_meta.levels.size() - 1].level) + "].");
  }

  if (output_level > MaxOutputLevel()) {
    return Status::InvalidArgument(
        "Exceed the maximum output level defined by "
        "the current compaction algorithm --- " +
-        std::to_string(MaxOutputLevel()));
+        ToString(MaxOutputLevel()));
  }

  if (output_level < 0) {
@@ -1067,8 +1063,8 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
      return Status::InvalidArgument(
          "Cannot compact file to up level, input file: " +
          MakeTableFileName("", file_num) + " level " +
-          std::to_string(input_file_level) + " > output level " +
-          std::to_string(output_level));
+          ToString(input_file_level) + " > output level " +
+          ToString(output_level));
    }
  }

@@ -78,7 +78,7 @@ class CompactionPicker {
      const CompactRangeOptions& compact_range_options,
      const InternalKey* begin, const InternalKey* end,
      InternalKey** compaction_end, bool* manual_conflict,
-      uint64_t max_file_num_to_ignore, const std::string& trim_ts);
+      uint64_t max_file_num_to_ignore);

  // The maximum allowed output level.  Default value is NumberLevels() - 1.
  virtual int MaxOutputLevel() const { return NumberLevels() - 1; }
@@ -270,8 +270,7 @@ class NullCompactionPicker : public CompactionPicker {
                           const InternalKey* /*end*/,
                           InternalKey** /*compaction_end*/,
                           bool* /*manual_conflict*/,
-                           uint64_t /*max_file_num_to_ignore*/,
-                           const std::string& /*trim_ts*/) override {
+                           uint64_t /*max_file_num_to_ignore*/) override {
    return nullptr;
  }

@@ -305,7 +304,8 @@ bool FindIntraL0Compaction(
    CompactionInputFiles* comp_inputs,
    SequenceNumber earliest_mem_seqno = kMaxSequenceNumber);

-CompressionType GetCompressionType(const VersionStorageInfo* vstorage,
+CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
+                                   const VersionStorageInfo* vstorage,
                                   const MutableCFOptions& mutable_cf_options,
                                   int level, int base_level,
                                   const bool enable_compression = true);
@@ -115,7 +115,7 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
      std::move(inputs), 0, 0, 0, 0, kNoCompression,
      mutable_cf_options.compression_opts, Temperature::kUnknown,
      /* max_subcompactions */ 0, {}, /* is manual */ false,
-      /* trim_ts */ "", vstorage->CompactionScore(0),
+      vstorage->CompactionScore(0),
      /* is deletion compaction */ true, CompactionReason::kFIFOTtl);
  return c;
 }
@@ -157,8 +157,8 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
            0 /* max compaction bytes, not applicable */,
            0 /* output path ID */, mutable_cf_options.compression,
            mutable_cf_options.compression_opts, Temperature::kUnknown,
-            0 /* max_subcompactions */, {}, /* is manual */ false,
-            /* trim_ts */ "", vstorage->CompactionScore(0),
+            0 /* max_subcompactions */, {},
+            /* is manual */ false, vstorage->CompactionScore(0),
            /* is deletion compaction */ false,
            CompactionReason::kFIFOReduceNumFiles);
        return c;
@@ -208,7 +208,7 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
      std::move(inputs), 0, 0, 0, 0, kNoCompression,
      mutable_cf_options.compression_opts, Temperature::kUnknown,
      /* max_subcompactions */ 0, {}, /* is manual */ false,
-      /* trim_ts */ "", vstorage->CompactionScore(0),
+      vstorage->CompactionScore(0),
      /* is deletion compaction */ true, CompactionReason::kFIFOMaxSize);
  return c;
 }
@@ -313,7 +313,7 @@ Compaction* FIFOCompactionPicker::PickCompactionToWarm(
      0 /* max compaction bytes, not applicable */, 0 /* output path ID */,
      mutable_cf_options.compression, mutable_cf_options.compression_opts,
      Temperature::kWarm,
-      /* max_subcompactions */ 0, {}, /* is manual */ false, /* trim_ts */ "",
+      /* max_subcompactions */ 0, {}, /* is manual */ false,
      vstorage->CompactionScore(0),
      /* is deletion compaction */ false, CompactionReason::kChangeTemperature);
  return c;
@@ -349,7 +349,7 @@ Compaction* FIFOCompactionPicker::CompactRange(
    const CompactRangeOptions& /*compact_range_options*/,
    const InternalKey* /*begin*/, const InternalKey* /*end*/,
    InternalKey** compaction_end, bool* /*manual_conflict*/,
-    uint64_t /*max_file_num_to_ignore*/, const std::string& /*trim_ts*/) {
+    uint64_t /*max_file_num_to_ignore*/) {
 #ifdef NDEBUG
  (void)input_level;
  (void)output_level;
@@ -32,7 +32,7 @@ class FIFOCompactionPicker : public CompactionPicker {
      const CompactRangeOptions& compact_range_options,
      const InternalKey* begin, const InternalKey* end,
      InternalKey** compaction_end, bool* manual_conflict,
-      uint64_t max_file_num_to_ignore, const std::string& trim_ts) override;
+      uint64_t max_file_num_to_ignore) override;

  // The maximum allowed output level.  Always returns 0.
  virtual int MaxOutputLevel() const override { return 0; }
@@ -343,13 +343,12 @@ Compaction* LevelCompactionBuilder::GetCompaction() {
                          ioptions_.level_compaction_dynamic_level_bytes),
      mutable_cf_options_.max_compaction_bytes,
      GetPathId(ioptions_, mutable_cf_options_, output_level_),
-      GetCompressionType(vstorage_, mutable_cf_options_, output_level_,
-                         vstorage_->base_level()),
+      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
+                         output_level_, vstorage_->base_level()),
      GetCompressionOptions(mutable_cf_options_, vstorage_, output_level_),
      Temperature::kUnknown,
      /* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
-      /* trim_ts */ "", start_level_score_, false /* deletion_compaction */,
-      compaction_reason_);
+      start_level_score_, false /* deletion_compaction */, compaction_reason_);

  // If it's level 0 compaction, make sure we don't execute any other level 0
  // compactions in parallel
@@ -504,7 +503,7 @@ bool LevelCompactionBuilder::PickIntraL0Compaction() {
    return false;
  }
  return FindIntraL0Compaction(level_files, kMinFilesForIntraL0Compaction,
-                               std::numeric_limits<uint64_t>::max(),
+                               port::kMaxUint64,
                               mutable_cf_options_.max_compaction_bytes,
                               &start_level_inputs_, earliest_mem_seqno_);
 }
@@ -12,7 +12,6 @@
 #include "db/compaction/compaction_picker_level.h"
 #include "db/compaction/compaction_picker_universal.h"
 #include "db/compaction/file_pri.h"
-#include "table/unique_id_impl.h"
 #include "test_util/testharness.h"
 #include "test_util/testutil.h"
 #include "util/string_util.h"
@@ -77,7 +76,7 @@ class CompactionPickerTest : public testing::Test {
    options_.num_levels = num_levels;
    vstorage_.reset(new VersionStorageInfo(&icmp_, ucmp_, options_.num_levels,
                                           style, nullptr, false));
-    vstorage_->PrepareForVersionAppend(ioptions_, mutable_cf_options_);
+    vstorage_->CalculateBaseBytes(ioptions_, mutable_cf_options_);
  }

  // Create a new VersionStorageInfo object so we can add mode files and then
@@ -116,7 +115,7 @@ class CompactionPickerTest : public testing::Test {
        largest_seq, marked_for_compact, temperature, kInvalidBlobFileNumber,
        kUnknownOldestAncesterTime, kUnknownFileCreationTime,
        kUnknownFileChecksum, kUnknownFileChecksumFuncName,
-        kDisableUserTimestamp, kDisableUserTimestamp, kNullUniqueId64x2);
+        kDisableUserTimestamp, kDisableUserTimestamp);
    f->compensated_file_size =
        (compensated_file_size != 0) ? compensated_file_size : file_size;
    f->oldest_ancester_time = oldest_ancestor_time;
@@ -149,10 +148,35 @@ class CompactionPickerTest : public testing::Test {
      ASSERT_OK(builder.SaveTo(temp_vstorage_.get()));
      vstorage_ = std::move(temp_vstorage_);
    }
-    vstorage_->PrepareForVersionAppend(ioptions_, mutable_cf_options_);
+    vstorage_->CalculateBaseBytes(ioptions_, mutable_cf_options_);
+    vstorage_->UpdateFilesByCompactionPri(ioptions_, mutable_cf_options_);
+    vstorage_->UpdateNumNonEmptyLevels();
+    vstorage_->GenerateFileIndexer();
+    vstorage_->GenerateLevelFilesBrief();
    vstorage_->ComputeCompactionScore(ioptions_, mutable_cf_options_);
+    vstorage_->GenerateLevel0NonOverlapping();
+    vstorage_->ComputeFilesMarkedForCompaction();
    vstorage_->SetFinalized();
  }
+  void AddFileToVersionStorage(int level, uint32_t file_number,
+                               const char* smallest, const char* largest,
+                               uint64_t file_size = 1, uint32_t path_id = 0,
+                               SequenceNumber smallest_seq = 100,
+                               SequenceNumber largest_seq = 100,
+                               size_t compensated_file_size = 0,
+                               bool marked_for_compact = false) {
+    VersionStorageInfo* base_vstorage = vstorage_.release();
+    vstorage_.reset(new VersionStorageInfo(&icmp_, ucmp_, options_.num_levels,
+                                           kCompactionStyleUniversal,
+                                           base_vstorage, false));
+    Add(level, file_number, smallest, largest, file_size, path_id, smallest_seq,
+        largest_seq, compensated_file_size, marked_for_compact);
+
+    VersionBuilder builder(FileOptions(), &ioptions_, nullptr, base_vstorage,
+                           nullptr);
+    builder.SaveTo(vstorage_.get());
+    UpdateVersionStorageInfo();
+  }

 private:
  std::unique_ptr<VersionStorageInfo> temp_vstorage_;
@@ -274,9 +298,9 @@ TEST_F(CompactionPickerTest, NeedsCompactionLevel) {
      // start a brand new version in each test.
      NewVersionStorage(kLevels, kCompactionStyleLevel);
      for (int i = 0; i < file_count; ++i) {
-        Add(level, i, std::to_string((i + 100) * 1000).c_str(),
-            std::to_string((i + 100) * 1000 + 999).c_str(), file_size, 0,
-            i * 100, i * 100 + 99);
+        Add(level, i, ToString((i + 100) * 1000).c_str(),
+            ToString((i + 100) * 1000 + 999).c_str(),
+            file_size, 0, i * 100, i * 100 + 99);
      }
      UpdateVersionStorageInfo();
      ASSERT_EQ(vstorage_->CompactionScoreLevel(0), level);
@@ -440,8 +464,8 @@ TEST_F(CompactionPickerTest, NeedsCompactionUniversal) {
  for (int i = 1;
       i <= mutable_cf_options_.level0_file_num_compaction_trigger * 2; ++i) {
    NewVersionStorage(1, kCompactionStyleUniversal);
-    Add(0, i, std::to_string((i + 100) * 1000).c_str(),
-        std::to_string((i + 100) * 1000 + 999).c_str(), 1000000, 0, i * 100,
+    Add(0, i, ToString((i + 100) * 1000).c_str(),
+        ToString((i + 100) * 1000 + 999).c_str(), 1000000, 0, i * 100,
        i * 100 + 99);
    UpdateVersionStorageInfo();
    ASSERT_EQ(level_compaction_picker.NeedsCompaction(vstorage_.get()),
@@ -853,17 +877,17 @@ TEST_F(CompactionPickerTest, UniversalIncrementalSpace4) {
  // L3: (1101, 1180) (1201, 1280) ... (7901, 7908)
  // L4: (1130, 1150) (1160, 1210) (1230, 1250) (1260 1310) ... (7960, 8010)
  for (int i = 11; i < 79; i++) {
-    Add(3, 100 + i * 3, std::to_string(i * 100).c_str(),
-        std::to_string(i * 100 + 80).c_str(), kFileSize, 0, 200, 251);
+    Add(3, 100 + i * 3, ToString(i * 100).c_str(),
+        ToString(i * 100 + 80).c_str(), kFileSize, 0, 200, 251);
    // Add a tie breaker
    if (i == 66) {
      Add(3, 10000U, "6690", "6699", kFileSize, 0, 200, 251);
    }

-    Add(4, 100 + i * 3 + 1, std::to_string(i * 100 + 30).c_str(),
-        std::to_string(i * 100 + 50).c_str(), kFileSize, 0, 200, 251);
-    Add(4, 100 + i * 3 + 2, std::to_string(i * 100 + 60).c_str(),
-        std::to_string(i * 100 + 110).c_str(), kFileSize, 0, 200, 251);
+    Add(4, 100 + i * 3 + 1, ToString(i * 100 + 30).c_str(),
+        ToString(i * 100 + 50).c_str(), kFileSize, 0, 200, 251);
+    Add(4, 100 + i * 3 + 2, ToString(i * 100 + 60).c_str(),
+        ToString(i * 100 + 110).c_str(), kFileSize, 0, 200, 251);
  }
  UpdateVersionStorageInfo();

@@ -900,14 +924,14 @@ TEST_F(CompactionPickerTest, UniversalIncrementalSpace5) {
  // L3: (1101, 1180) (1201, 1280) ... (7901, 7908)
  // L4: (1130, 1150) (1160, 1210) (1230, 1250) (1260 1310) ... (7960, 8010)
  for (int i = 11; i < 70; i++) {
-    Add(3, 100 + i * 3, std::to_string(i * 100).c_str(),
-        std::to_string(i * 100 + 80).c_str(),
+    Add(3, 100 + i * 3, ToString(i * 100).c_str(),
+        ToString(i * 100 + 80).c_str(),
        i % 10 == 9 ? kFileSize * 100 : kFileSize, 0, 200, 251);

-    Add(4, 100 + i * 3 + 1, std::to_string(i * 100 + 30).c_str(),
-        std::to_string(i * 100 + 50).c_str(), kFileSize, 0, 200, 251);
-    Add(4, 100 + i * 3 + 2, std::to_string(i * 100 + 60).c_str(),
-        std::to_string(i * 100 + 110).c_str(), kFileSize, 0, 200, 251);
+    Add(4, 100 + i * 3 + 1, ToString(i * 100 + 30).c_str(),
+        ToString(i * 100 + 50).c_str(), kFileSize, 0, 200, 251);
+    Add(4, 100 + i * 3 + 2, ToString(i * 100 + 60).c_str(),
+        ToString(i * 100 + 110).c_str(), kFileSize, 0, 200, 251);
  }
  UpdateVersionStorageInfo();

@@ -940,11 +964,13 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {

  // verify whether compaction is needed based on the current
  // size of L0 files.
+  uint64_t current_size = 0;
  for (int i = 1; i <= kFileCount; ++i) {
    NewVersionStorage(1, kCompactionStyleFIFO);
-    Add(0, i, std::to_string((i + 100) * 1000).c_str(),
-        std::to_string((i + 100) * 1000 + 999).c_str(), kFileSize, 0, i * 100,
-        i * 100 + 99);
+    Add(0, i, ToString((i + 100) * 1000).c_str(),
+        ToString((i + 100) * 1000 + 999).c_str(),
+        kFileSize, 0, i * 100, i * 100 + 99);
+    current_size += kFileSize;
    UpdateVersionStorageInfo();
    ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()),
              vstorage_->CompactionScore(0) >= 1);
@@ -2649,13 +2675,12 @@ TEST_F(CompactionPickerTest, UniversalMarkedManualCompaction) {
  ASSERT_EQ(3U, vstorage_->FilesMarkedForCompaction().size());

  bool manual_conflict = false;
-  InternalKey* manual_end = nullptr;
+  InternalKey* manual_end = NULL;
  std::unique_ptr<Compaction> compaction(
      universal_compaction_picker.CompactRange(
          cf_name_, mutable_cf_options_, mutable_db_options_, vstorage_.get(),
-          ColumnFamilyData::kCompactAllLevels, 6, CompactRangeOptions(),
-          nullptr, nullptr, &manual_end, &manual_conflict,
-          std::numeric_limits<uint64_t>::max(), ""));
+          ColumnFamilyData::kCompactAllLevels, 6, CompactRangeOptions(), NULL,
+          NULL, &manual_end, &manual_conflict, port::kMaxUint64));

  ASSERT_TRUE(compaction);

@@ -746,19 +746,19 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
  } else {
    compaction_reason = CompactionReason::kUniversalSortedRunNum;
  }
-  return new Compaction(vstorage_, ioptions_, mutable_cf_options_,
-                        mutable_db_options_, std::move(inputs), output_level,
-                        MaxFileSizeForLevel(mutable_cf_options_, output_level,
-                                            kCompactionStyleUniversal),
-                        GetMaxOverlappingBytes(), path_id,
-                        GetCompressionType(vstorage_, mutable_cf_options_,
-                                           start_level, 1, enable_compression),
-                        GetCompressionOptions(mutable_cf_options_, vstorage_,
-                                              start_level, enable_compression),
-                        Temperature::kUnknown,
-                        /* max_subcompactions */ 0, grandparents,
-                        /* is manual */ false, /* trim_ts */ "", score_,
-                        false /* deletion_compaction */, compaction_reason);
+  return new Compaction(
+      vstorage_, ioptions_, mutable_cf_options_, mutable_db_options_,
+      std::move(inputs), output_level,
+      MaxFileSizeForLevel(mutable_cf_options_, output_level,
+                          kCompactionStyleUniversal),
+      GetMaxOverlappingBytes(), path_id,
+      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_, start_level,
+                         1, enable_compression),
+      GetCompressionOptions(mutable_cf_options_, vstorage_, start_level,
+                            enable_compression),
+      Temperature::kUnknown,
+      /* max_subcompactions */ 0, grandparents, /* is manual */ false, score_,
+      false /* deletion_compaction */, compaction_reason);
 }

 // Look at overall size amplification. If size amplification
@@ -1076,13 +1076,13 @@ Compaction* UniversalCompactionBuilder::PickIncrementalForReduceSizeAmp(
      MaxFileSizeForLevel(mutable_cf_options_, output_level,
                          kCompactionStyleUniversal),
      GetMaxOverlappingBytes(), path_id,
-      GetCompressionType(vstorage_, mutable_cf_options_, output_level, 1,
-                         true /* enable_compression */),
+      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
+                         output_level, 1, true /* enable_compression */),
      GetCompressionOptions(mutable_cf_options_, vstorage_, output_level,
                            true /* enable_compression */),
      Temperature::kUnknown,
      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
-      /* trim_ts */ "", score_, false /* deletion_compaction */,
+      score_, false /* deletion_compaction */,
      CompactionReason::kUniversalSizeAmplification);
 }

@@ -1220,11 +1220,12 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
      MaxFileSizeForLevel(mutable_cf_options_, output_level,
                          kCompactionStyleUniversal),
      /* max_grandparent_overlap_bytes */ GetMaxOverlappingBytes(), path_id,
-      GetCompressionType(vstorage_, mutable_cf_options_, output_level, 1),
+      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
+                         output_level, 1),
      GetCompressionOptions(mutable_cf_options_, vstorage_, output_level),
      Temperature::kUnknown,
-      /* max_subcompactions */ 0, grandparents, /* is manual */ false,
-      /* trim_ts */ "", score_, false /* deletion_compaction */,
+      /* max_subcompactions */ 0, grandparents, /* is manual */ false, score_,
+      false /* deletion_compaction */,
      CompactionReason::kFilesMarkedForCompaction);
 }

@@ -1293,14 +1294,13 @@ Compaction* UniversalCompactionBuilder::PickCompactionToOldest(
      MaxFileSizeForLevel(mutable_cf_options_, output_level,
                          kCompactionStyleUniversal),
      GetMaxOverlappingBytes(), path_id,
-      GetCompressionType(vstorage_, mutable_cf_options_, output_level, 1,
-                         true /* enable_compression */),
+      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
+                         output_level, 1, true /* enable_compression */),
      GetCompressionOptions(mutable_cf_options_, vstorage_, output_level,
                            true /* enable_compression */),
      Temperature::kUnknown,
      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
-      /* trim_ts */ "", score_, false /* deletion_compaction */,
-      compaction_reason);
+      score_, false /* deletion_compaction */, compaction_reason);
 }

 Compaction* UniversalCompactionBuilder::PickPeriodicCompaction() {
@@ -1371,7 +1371,7 @@ Compaction* UniversalCompactionBuilder::PickPeriodicCompaction() {

 uint64_t UniversalCompactionBuilder::GetMaxOverlappingBytes() const {
  if (!mutable_cf_options_.compaction_options_universal.incremental) {
-    return std::numeric_limits<uint64_t>::max();
+    return port::kMaxUint64;
  } else {
    // Try to align cutting boundary with files at the next level if the
    // file isn't end up with 1/2 of target size, or it would overlap
@@ -7,26 +7,137 @@

 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
-#include "table/unique_id_impl.h"

 namespace ROCKSDB_NAMESPACE {

-class MyTestCompactionService : public CompactionService {
+class TestCompactionServiceBase {
 public:
-  MyTestCompactionService(
-      std::string db_path, Options& options,
-      std::shared_ptr<Statistics>& statistics,
-      std::vector<std::shared_ptr<EventListener>>& listeners,
-      std::vector<std::shared_ptr<TablePropertiesCollectorFactory>>
-          table_properties_collector_factories)
+  virtual int GetCompactionNum() = 0;
+
+  void OverrideStartStatus(CompactionServiceJobStatus s) {
+    is_override_start_status = true;
+    override_start_status = s;
+  }
+
+  void OverrideWaitStatus(CompactionServiceJobStatus s) {
+    is_override_wait_status = true;
+    override_wait_status = s;
+  }
+
+  void OverrideWaitResult(std::string str) {
+    is_override_wait_result = true;
+    override_wait_result = std::move(str);
+  }
+
+  void ResetOverride() {
+    is_override_wait_result = false;
+    is_override_start_status = false;
+    is_override_wait_status = false;
+  }
+
+  virtual ~TestCompactionServiceBase() = default;
+
+ protected:
+  bool is_override_start_status = false;
+  CompactionServiceJobStatus override_start_status =
+      CompactionServiceJobStatus::kFailure;
+  bool is_override_wait_status = false;
+  CompactionServiceJobStatus override_wait_status =
+      CompactionServiceJobStatus::kFailure;
+  bool is_override_wait_result = false;
+  std::string override_wait_result;
+};
+
+class MyTestCompactionServiceLegacy : public CompactionService,
+                                      public TestCompactionServiceBase {
+ public:
+  MyTestCompactionServiceLegacy(std::string db_path, Options& options,
+                                std::shared_ptr<Statistics>& statistics)
+      : db_path_(std::move(db_path)),
+        options_(options),
+        statistics_(statistics) {}
+
+  static const char* kClassName() { return "MyTestCompactionServiceLegacy"; }
+
+  const char* Name() const override { return kClassName(); }
+
+  CompactionServiceJobStatus Start(const std::string& compaction_service_input,
+                                   uint64_t job_id) override {
+    InstrumentedMutexLock l(&mutex_);
+    jobs_.emplace(job_id, compaction_service_input);
+    CompactionServiceJobStatus s = CompactionServiceJobStatus::kSuccess;
+    if (is_override_start_status) {
+      return override_start_status;
+    }
+    return s;
+  }
+
+  CompactionServiceJobStatus WaitForComplete(
+      uint64_t job_id, std::string* compaction_service_result) override {
+    std::string compaction_input;
+    {
+      InstrumentedMutexLock l(&mutex_);
+      auto i = jobs_.find(job_id);
+      if (i == jobs_.end()) {
+        return CompactionServiceJobStatus::kFailure;
+      }
+      compaction_input = std::move(i->second);
+      jobs_.erase(i);
+    }
+
+    if (is_override_wait_status) {
+      return override_wait_status;
+    }
+
+    CompactionServiceOptionsOverride options_override;
+    options_override.env = options_.env;
+    options_override.file_checksum_gen_factory =
+        options_.file_checksum_gen_factory;
+    options_override.comparator = options_.comparator;
+    options_override.merge_operator = options_.merge_operator;
+    options_override.compaction_filter = options_.compaction_filter;
+    options_override.compaction_filter_factory =
+        options_.compaction_filter_factory;
+    options_override.prefix_extractor = options_.prefix_extractor;
+    options_override.table_factory = options_.table_factory;
+    options_override.sst_partitioner_factory = options_.sst_partitioner_factory;
+    options_override.statistics = statistics_;
+
+    Status s = DB::OpenAndCompact(
+        db_path_, db_path_ + "/" + ROCKSDB_NAMESPACE::ToString(job_id),
+        compaction_input, compaction_service_result, options_override);
+    if (is_override_wait_result) {
+      *compaction_service_result = override_wait_result;
+    }
+    compaction_num_.fetch_add(1);
+    if (s.ok()) {
+      return CompactionServiceJobStatus::kSuccess;
+    } else {
+      return CompactionServiceJobStatus::kFailure;
+    }
+  }
+
+  int GetCompactionNum() override { return compaction_num_.load(); }
+
+ private:
+  InstrumentedMutex mutex_;
+  std::atomic_int compaction_num_{0};
+  std::map<uint64_t, std::string> jobs_;
+  const std::string db_path_;
+  Options options_;
+  std::shared_ptr<Statistics> statistics_;
+};
+
+class MyTestCompactionService : public CompactionService,
+                                public TestCompactionServiceBase {
+ public:
+  MyTestCompactionService(std::string db_path, Options& options,
+                          std::shared_ptr<Statistics>& statistics)
      : db_path_(std::move(db_path)),
        options_(options),
        statistics_(statistics),
        start_info_("na", "na", "na", 0, Env::TOTAL),
-        wait_info_("na", "na", "na", 0, Env::TOTAL),
-        listeners_(listeners),
-        table_properties_collector_factories_(
-            std::move(table_properties_collector_factories)) {}
+        wait_info_("na", "na", "na", 0, Env::TOTAL) {}

  static const char* kClassName() { return "MyTestCompactionService"; }

@@ -40,8 +151,8 @@ class MyTestCompactionService : public CompactionService {
    assert(info.db_name == db_path_);
    jobs_.emplace(info.job_id, compaction_service_input);
    CompactionServiceJobStatus s = CompactionServiceJobStatus::kSuccess;
-    if (is_override_start_status_) {
-      return override_start_status_;
+    if (is_override_start_status) {
+      return override_start_status;
    }
    return s;
  }
@@ -62,8 +173,8 @@ class MyTestCompactionService : public CompactionService {
      jobs_.erase(i);
    }

-    if (is_override_wait_status_) {
-      return override_wait_status_;
+    if (is_override_wait_status) {
+      return override_wait_status;
    }

    CompactionServiceOptionsOverride options_override;
@@ -79,23 +190,12 @@ class MyTestCompactionService : public CompactionService {
    options_override.table_factory = options_.table_factory;
    options_override.sst_partitioner_factory = options_.sst_partitioner_factory;
    options_override.statistics = statistics_;
-    if (!listeners_.empty()) {
-      options_override.listeners = listeners_;
-    }
-
-    if (!table_properties_collector_factories_.empty()) {
-      options_override.table_properties_collector_factories =
-          table_properties_collector_factories_;
-    }
-
-    OpenAndCompactOptions options;
-    options.canceled = &canceled_;

    Status s = DB::OpenAndCompact(
-        options, db_path_, db_path_ + "/" + std::to_string(info.job_id),
+        db_path_, db_path_ + "/" + ROCKSDB_NAMESPACE::ToString(info.job_id),
        compaction_input, compaction_service_result, options_override);
-    if (is_override_wait_result_) {
-      *compaction_service_result = override_wait_result_;
+    if (is_override_wait_result) {
+      *compaction_service_result = override_wait_result;
    }
    compaction_num_.fetch_add(1);
    if (s.ok()) {
@@ -105,34 +205,11 @@ class MyTestCompactionService : public CompactionService {
    }
  }

-  int GetCompactionNum() { return compaction_num_.load(); }
+  int GetCompactionNum() override { return compaction_num_.load(); }

  CompactionServiceJobInfo GetCompactionInfoForStart() { return start_info_; }
  CompactionServiceJobInfo GetCompactionInfoForWait() { return wait_info_; }

-  void OverrideStartStatus(CompactionServiceJobStatus s) {
-    is_override_start_status_ = true;
-    override_start_status_ = s;
-  }
-
-  void OverrideWaitStatus(CompactionServiceJobStatus s) {
-    is_override_wait_status_ = true;
-    override_wait_status_ = s;
-  }
-
-  void OverrideWaitResult(std::string str) {
-    is_override_wait_result_ = true;
-    override_wait_result_ = std::move(str);
-  }
-
-  void ResetOverride() {
-    is_override_wait_result_ = false;
-    is_override_start_status_ = false;
-    is_override_wait_status_ = false;
-  }
-
-  void SetCanceled(bool canceled) { canceled_ = canceled; }
-
 private:
  InstrumentedMutex mutex_;
  std::atomic_int compaction_num_{0};
@@ -142,21 +219,17 @@ class MyTestCompactionService : public CompactionService {
  std::shared_ptr<Statistics> statistics_;
  CompactionServiceJobInfo start_info_;
  CompactionServiceJobInfo wait_info_;
-  bool is_override_start_status_ = false;
-  CompactionServiceJobStatus override_start_status_ =
-      CompactionServiceJobStatus::kFailure;
-  bool is_override_wait_status_ = false;
-  CompactionServiceJobStatus override_wait_status_ =
-      CompactionServiceJobStatus::kFailure;
-  bool is_override_wait_result_ = false;
-  std::string override_wait_result_;
-  std::vector<std::shared_ptr<EventListener>> listeners_;
-  std::vector<std::shared_ptr<TablePropertiesCollectorFactory>>
-      table_properties_collector_factories_;
-  std::atomic_bool canceled_{false};
 };

-class CompactionServiceTest : public DBTestBase {
+// This is only for listing test classes
+enum TestCompactionServiceType {
+  MyTestCompactionServiceType,
+  MyTestCompactionServiceLegacyType,
+};
+
+class CompactionServiceTest
+    : public DBTestBase,
+      public testing::WithParamInterface<TestCompactionServiceType> {
 public:
  explicit CompactionServiceTest()
      : DBTestBase("compaction_service_test", true) {}
@@ -167,10 +240,19 @@ class CompactionServiceTest : public DBTestBase {
    primary_statistics_ = CreateDBStatistics();
    options->statistics = primary_statistics_;
    compactor_statistics_ = CreateDBStatistics();
-
-    compaction_service_ = std::make_shared<MyTestCompactionService>(
-        dbname_, *options, compactor_statistics_, remote_listeners,
-        remote_table_properties_collector_factories);
+    TestCompactionServiceType cs_type = GetParam();
+    switch (cs_type) {
+      case MyTestCompactionServiceType:
+        compaction_service_ = std::make_shared<MyTestCompactionService>(
+            dbname_, *options, compactor_statistics_);
+        break;
+      case MyTestCompactionServiceLegacyType:
+        compaction_service_ = std::make_shared<MyTestCompactionServiceLegacy>(
+            dbname_, *options, compactor_statistics_);
+        break;
+      default:
+        assert(false);
+    }
    options->compaction_service = compaction_service_;
    DestroyAndReopen(*options);
  }
@@ -179,9 +261,9 @@ class CompactionServiceTest : public DBTestBase {

  Statistics* GetPrimaryStatistics() { return primary_statistics_.get(); }

-  MyTestCompactionService* GetCompactionService() {
+  TestCompactionServiceBase* GetCompactionService() {
    CompactionService* cs = compaction_service_.get();
-    return static_cast_with_check<MyTestCompactionService>(cs);
+    return dynamic_cast<TestCompactionServiceBase*>(cs);
  }

  void GenerateTestData() {
@@ -189,7 +271,7 @@ class CompactionServiceTest : public DBTestBase {
    for (int i = 0; i < 20; i++) {
      for (int j = 0; j < 10; j++) {
        int key_id = i * 10 + j;
-        ASSERT_OK(Put(Key(key_id), "value" + std::to_string(key_id)));
+        ASSERT_OK(Put(Key(key_id), "value" + ToString(key_id)));
      }
      ASSERT_OK(Flush());
    }
@@ -199,7 +281,7 @@ class CompactionServiceTest : public DBTestBase {
    for (int i = 0; i < 10; i++) {
      for (int j = 0; j < 10; j++) {
        int key_id = i * 20 + j * 2;
-        ASSERT_OK(Put(Key(key_id), "value_new" + std::to_string(key_id)));
+        ASSERT_OK(Put(Key(key_id), "value_new" + ToString(key_id)));
      }
      ASSERT_OK(Flush());
    }
@@ -211,24 +293,20 @@ class CompactionServiceTest : public DBTestBase {
    for (int i = 0; i < 200; i++) {
      auto result = Get(Key(i));
      if (i % 2) {
-        ASSERT_EQ(result, "value" + std::to_string(i));
+        ASSERT_EQ(result, "value" + ToString(i));
      } else {
-        ASSERT_EQ(result, "value_new" + std::to_string(i));
+        ASSERT_EQ(result, "value_new" + ToString(i));
      }
    }
  }

-  std::vector<std::shared_ptr<EventListener>> remote_listeners;
-  std::vector<std::shared_ptr<TablePropertiesCollectorFactory>>
-      remote_table_properties_collector_factories;
-
 private:
  std::shared_ptr<Statistics> compactor_statistics_;
  std::shared_ptr<Statistics> primary_statistics_;
  std::shared_ptr<CompactionService> compaction_service_;
 };

-TEST_F(CompactionServiceTest, BasicCompactions) {
+TEST_P(CompactionServiceTest, BasicCompactions) {
  Options options = CurrentOptions();
  ReopenWithCompactionService(&options);

@@ -238,7 +316,7 @@ TEST_F(CompactionServiceTest, BasicCompactions) {
  for (int i = 0; i < 20; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 10 + j;
-      ASSERT_OK(Put(Key(key_id), "value" + std::to_string(key_id)));
+      ASSERT_OK(Put(Key(key_id), "value" + ToString(key_id)));
    }
    ASSERT_OK(Flush());
  }
@@ -246,7 +324,7 @@ TEST_F(CompactionServiceTest, BasicCompactions) {
  for (int i = 0; i < 10; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 20 + j * 2;
-      ASSERT_OK(Put(Key(key_id), "value_new" + std::to_string(key_id)));
+      ASSERT_OK(Put(Key(key_id), "value_new" + ToString(key_id)));
    }
    ASSERT_OK(Flush());
  }
@@ -256,9 +334,9 @@ TEST_F(CompactionServiceTest, BasicCompactions) {
  for (int i = 0; i < 200; i++) {
    auto result = Get(Key(i));
    if (i % 2) {
-      ASSERT_EQ(result, "value" + std::to_string(i));
+      ASSERT_EQ(result, "value" + ToString(i));
    } else {
-      ASSERT_EQ(result, "value_new" + std::to_string(i));
+      ASSERT_EQ(result, "value_new" + ToString(i));
    }
  }
  auto my_cs = GetCompactionService();
@@ -289,23 +367,13 @@ TEST_F(CompactionServiceTest, BasicCompactions) {
        auto s = static_cast<Status*>(status);
        *s = Status::Aborted("MyTestCompactionService failed to compact!");
      });
-
-  // tracking success unique id verification
-  std::atomic_int verify_passed{0};
-  SyncPoint::GetInstance()->SetCallBack(
-      "Version::VerifySstUniqueIds::Passed", [&](void* arg) {
-        // override job status
-        auto id = static_cast<UniqueId64x2*>(arg);
-        assert(*id != kNullUniqueId64x2);
-        verify_passed++;
-      });
  SyncPoint::GetInstance()->EnableProcessing();

  Status s;
  for (int i = 0; i < 10; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 20 + j * 2;
-      s = Put(Key(key_id), "value_new" + std::to_string(key_id));
+      s = Put(Key(key_id), "value_new" + ToString(key_id));
      if (s.IsAborted()) {
        break;
      }
@@ -323,15 +391,9 @@ TEST_F(CompactionServiceTest, BasicCompactions) {
    }
  }
  ASSERT_TRUE(s.IsAborted());
-
-  // Test verification
-  ASSERT_EQ(verify_passed, 0);
-  options.verify_sst_unique_id_in_manifest = true;
-  Reopen(options);
-  ASSERT_GT(verify_passed, 0);
 }

-TEST_F(CompactionServiceTest, ManualCompaction) {
+TEST_P(CompactionServiceTest, ManualCompaction) {
  Options options = CurrentOptions();
  options.disable_auto_compactions = true;
  ReopenWithCompactionService(&options);
@@ -368,52 +430,7 @@ TEST_F(CompactionServiceTest, ManualCompaction) {
  VerifyTestData();
 }

-TEST_F(CompactionServiceTest, CancelCompactionOnRemoteSide) {
-  Options options = CurrentOptions();
-  options.disable_auto_compactions = true;
-  ReopenWithCompactionService(&options);
-  GenerateTestData();
-
-  auto my_cs = GetCompactionService();
-
-  std::string start_str = Key(15);
-  std::string end_str = Key(45);
-  Slice start(start_str);
-  Slice end(end_str);
-  uint64_t comp_num = my_cs->GetCompactionNum();
-
-  // Test cancel compaction at the beginning
-  my_cs->SetCanceled(true);
-  auto s = db_->CompactRange(CompactRangeOptions(), &start, &end);
-  ASSERT_TRUE(s.IsIncomplete());
-  // compaction number is not increased
-  ASSERT_GE(my_cs->GetCompactionNum(), comp_num);
-  VerifyTestData();
-
-  // Test cancel compaction in progress
-  ReopenWithCompactionService(&options);
-  GenerateTestData();
-  my_cs = GetCompactionService();
-  my_cs->SetCanceled(false);
-
-  std::atomic_bool cancel_issued{false};
-  SyncPoint::GetInstance()->SetCallBack("CompactionJob::Run():Inprogress",
-                                        [&](void* /*arg*/) {
-                                          cancel_issued = true;
-                                          my_cs->SetCanceled(true);
-                                        });
-
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  s = db_->CompactRange(CompactRangeOptions(), &start, &end);
-  ASSERT_TRUE(s.IsIncomplete());
-  ASSERT_TRUE(cancel_issued);
-  // compaction number is not increased
-  ASSERT_GE(my_cs->GetCompactionNum(), comp_num);
-  VerifyTestData();
-}
-
-TEST_F(CompactionServiceTest, FailedToStart) {
+TEST_P(CompactionServiceTest, FailedToStart) {
  Options options = CurrentOptions();
  options.disable_auto_compactions = true;
  ReopenWithCompactionService(&options);
@@ -431,7 +448,7 @@ TEST_F(CompactionServiceTest, FailedToStart) {
  ASSERT_TRUE(s.IsIncomplete());
 }

-TEST_F(CompactionServiceTest, InvalidResult) {
+TEST_P(CompactionServiceTest, InvalidResult) {
  Options options = CurrentOptions();
  options.disable_auto_compactions = true;
  ReopenWithCompactionService(&options);
@@ -449,7 +466,7 @@ TEST_F(CompactionServiceTest, InvalidResult) {
  ASSERT_FALSE(s.ok());
 }

-TEST_F(CompactionServiceTest, SubCompaction) {
+TEST_P(CompactionServiceTest, SubCompaction) {
  Options options = CurrentOptions();
  options.max_subcompactions = 10;
  options.target_file_size_base = 1 << 10;  // 1KB
@@ -488,7 +505,7 @@ class PartialDeleteCompactionFilter : public CompactionFilter {
  const char* Name() const override { return "PartialDeleteCompactionFilter"; }
 };

-TEST_F(CompactionServiceTest, CompactionFilter) {
+TEST_P(CompactionServiceTest, CompactionFilter) {
  Options options = CurrentOptions();
  std::unique_ptr<CompactionFilter> delete_comp_filter(
      new PartialDeleteCompactionFilter());
@@ -498,7 +515,7 @@ TEST_F(CompactionServiceTest, CompactionFilter) {
  for (int i = 0; i < 20; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 10 + j;
-      ASSERT_OK(Put(Key(key_id), "value" + std::to_string(key_id)));
+      ASSERT_OK(Put(Key(key_id), "value" + ToString(key_id)));
    }
    ASSERT_OK(Flush());
  }
@@ -506,7 +523,7 @@ TEST_F(CompactionServiceTest, CompactionFilter) {
  for (int i = 0; i < 10; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 20 + j * 2;
-      ASSERT_OK(Put(Key(key_id), "value_new" + std::to_string(key_id)));
+      ASSERT_OK(Put(Key(key_id), "value_new" + ToString(key_id)));
    }
    ASSERT_OK(Flush());
  }
@@ -520,16 +537,16 @@ TEST_F(CompactionServiceTest, CompactionFilter) {
    if (i > 5 && i <= 105) {
      ASSERT_EQ(result, "NOT_FOUND");
    } else if (i % 2) {
-      ASSERT_EQ(result, "value" + std::to_string(i));
+      ASSERT_EQ(result, "value" + ToString(i));
    } else {
-      ASSERT_EQ(result, "value_new" + std::to_string(i));
+      ASSERT_EQ(result, "value_new" + ToString(i));
    }
  }
  auto my_cs = GetCompactionService();
  ASSERT_GE(my_cs->GetCompactionNum(), 1);
 }

-TEST_F(CompactionServiceTest, Snapshot) {
+TEST_P(CompactionServiceTest, Snapshot) {
  Options options = CurrentOptions();
  ReopenWithCompactionService(&options);

@@ -550,7 +567,7 @@ TEST_F(CompactionServiceTest, Snapshot) {
  db_->ReleaseSnapshot(s1);
 }

-TEST_F(CompactionServiceTest, ConcurrentCompaction) {
+TEST_P(CompactionServiceTest, ConcurrentCompaction) {
  Options options = CurrentOptions();
  options.level0_file_num_compaction_trigger = 100;
  options.max_background_jobs = 20;
@@ -562,7 +579,7 @@ TEST_F(CompactionServiceTest, ConcurrentCompaction) {

  std::vector<std::thread> threads;
  for (const auto& file : meta.levels[1].files) {
-    threads.emplace_back(std::thread([&]() {
+    threads.push_back(std::thread([&]() {
      std::string fname = file.db_path + "/" + file.name;
      ASSERT_OK(db_->CompactFiles(CompactionOptions(), {fname}, 2));
    }));
@@ -577,9 +594,9 @@ TEST_F(CompactionServiceTest, ConcurrentCompaction) {
  for (int i = 0; i < 200; i++) {
    auto result = Get(Key(i));
    if (i % 2) {
-      ASSERT_EQ(result, "value" + std::to_string(i));
+      ASSERT_EQ(result, "value" + ToString(i));
    } else {
-      ASSERT_EQ(result, "value_new" + std::to_string(i));
+      ASSERT_EQ(result, "value_new" + ToString(i));
    }
  }
  auto my_cs = GetCompactionService();
@@ -587,14 +604,19 @@ TEST_F(CompactionServiceTest, ConcurrentCompaction) {
  ASSERT_EQ(FilesPerLevel(), "0,0,10");
 }

-TEST_F(CompactionServiceTest, CompactionInfo) {
+TEST_P(CompactionServiceTest, CompactionInfo) {
+  // only test compaction info for new compaction service interface
+  if (GetParam() != MyTestCompactionServiceType) {
+    return;
+  }
+
  Options options = CurrentOptions();
  ReopenWithCompactionService(&options);

  for (int i = 0; i < 20; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 10 + j;
-      ASSERT_OK(Put(Key(key_id), "value" + std::to_string(key_id)));
+      ASSERT_OK(Put(Key(key_id), "value" + ToString(key_id)));
    }
    ASSERT_OK(Flush());
  }
@@ -602,7 +624,7 @@ TEST_F(CompactionServiceTest, CompactionInfo) {
  for (int i = 0; i < 10; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 20 + j * 2;
-      ASSERT_OK(Put(Key(key_id), "value_new" + std::to_string(key_id)));
+      ASSERT_OK(Put(Key(key_id), "value_new" + ToString(key_id)));
    }
    ASSERT_OK(Flush());
  }
@@ -647,7 +669,7 @@ TEST_F(CompactionServiceTest, CompactionInfo) {
  for (int i = 0; i < 20; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 10 + j;
-      ASSERT_OK(Put(Key(key_id), "value" + std::to_string(key_id)));
+      ASSERT_OK(Put(Key(key_id), "value" + ToString(key_id)));
    }
    ASSERT_OK(Flush());
  }
@@ -655,7 +677,7 @@ TEST_F(CompactionServiceTest, CompactionInfo) {
  for (int i = 0; i < 4; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 20 + j * 2;
-      ASSERT_OK(Put(Key(key_id), "value_new" + std::to_string(key_id)));
+      ASSERT_OK(Put(Key(key_id), "value_new" + ToString(key_id)));
    }
    ASSERT_OK(Flush());
  }
@@ -666,7 +688,7 @@ TEST_F(CompactionServiceTest, CompactionInfo) {
  ASSERT_EQ(Env::BOTTOM, info.priority);
 }

-TEST_F(CompactionServiceTest, FallbackLocalAuto) {
+TEST_P(CompactionServiceTest, FallbackLocalAuto) {
  Options options = CurrentOptions();
  ReopenWithCompactionService(&options);

@@ -683,7 +705,7 @@ TEST_F(CompactionServiceTest, FallbackLocalAuto) {
  for (int i = 0; i < 20; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 10 + j;
-      ASSERT_OK(Put(Key(key_id), "value" + std::to_string(key_id)));
+      ASSERT_OK(Put(Key(key_id), "value" + ToString(key_id)));
    }
    ASSERT_OK(Flush());
  }
@@ -691,7 +713,7 @@ TEST_F(CompactionServiceTest, FallbackLocalAuto) {
  for (int i = 0; i < 10; i++) {
    for (int j = 0; j < 10; j++) {
      int key_id = i * 20 + j * 2;
-      ASSERT_OK(Put(Key(key_id), "value_new" + std::to_string(key_id)));
+      ASSERT_OK(Put(Key(key_id), "value_new" + ToString(key_id)));
    }
    ASSERT_OK(Flush());
  }
@@ -701,9 +723,9 @@ TEST_F(CompactionServiceTest, FallbackLocalAuto) {
  for (int i = 0; i < 200; i++) {
    auto result = Get(Key(i));
    if (i % 2) {
-      ASSERT_EQ(result, "value" + std::to_string(i));
+      ASSERT_EQ(result, "value" + ToString(i));
    } else {
-      ASSERT_EQ(result, "value_new" + std::to_string(i));
+      ASSERT_EQ(result, "value_new" + ToString(i));
    }
  }

@@ -718,7 +740,7 @@ TEST_F(CompactionServiceTest, FallbackLocalAuto) {
  ASSERT_EQ(primary_statistics->getTickerCount(REMOTE_COMPACT_WRITE_BYTES), 0);
 }

-TEST_F(CompactionServiceTest, FallbackLocalManual) {
+TEST_P(CompactionServiceTest, FallbackLocalManual) {
  Options options = CurrentOptions();
  options.disable_auto_compactions = true;
  ReopenWithCompactionService(&options);
@@ -776,177 +798,11 @@ TEST_F(CompactionServiceTest, FallbackLocalManual) {
  VerifyTestData();
 }

-TEST_F(CompactionServiceTest, RemoteEventListener) {
-  class RemoteEventListenerTest : public EventListener {
-   public:
-    const char* Name() const override { return "RemoteEventListenerTest"; }
-
-    void OnSubcompactionBegin(const SubcompactionJobInfo& info) override {
-      auto result = on_going_compactions.emplace(info.job_id);
-      ASSERT_TRUE(result.second);  // make sure there's no duplication
-      compaction_num++;
-      EventListener::OnSubcompactionBegin(info);
-    }
-    void OnSubcompactionCompleted(const SubcompactionJobInfo& info) override {
-      auto num = on_going_compactions.erase(info.job_id);
-      ASSERT_TRUE(num == 1);  // make sure the compaction id exists
-      EventListener::OnSubcompactionCompleted(info);
-    }
-    void OnTableFileCreated(const TableFileCreationInfo& info) override {
-      ASSERT_EQ(on_going_compactions.count(info.job_id), 1);
-      file_created++;
-      EventListener::OnTableFileCreated(info);
-    }
-    void OnTableFileCreationStarted(
-        const TableFileCreationBriefInfo& info) override {
-      ASSERT_EQ(on_going_compactions.count(info.job_id), 1);
-      file_creation_started++;
-      EventListener::OnTableFileCreationStarted(info);
-    }
-
-    bool ShouldBeNotifiedOnFileIO() override {
-      file_io_notified++;
-      return EventListener::ShouldBeNotifiedOnFileIO();
-    }
-
-    std::atomic_uint64_t file_io_notified{0};
-    std::atomic_uint64_t file_creation_started{0};
-    std::atomic_uint64_t file_created{0};
-
-    std::set<int> on_going_compactions;  // store the job_id
-    std::atomic_uint64_t compaction_num{0};
-  };
-
-  auto listener = new RemoteEventListenerTest();
-  remote_listeners.emplace_back(listener);
-
-  Options options = CurrentOptions();
-  ReopenWithCompactionService(&options);
-
-  for (int i = 0; i < 20; i++) {
-    for (int j = 0; j < 10; j++) {
-      int key_id = i * 10 + j;
-      ASSERT_OK(Put(Key(key_id), "value" + std::to_string(key_id)));
-    }
-    ASSERT_OK(Flush());
-  }
-
-  for (int i = 0; i < 10; i++) {
-    for (int j = 0; j < 10; j++) {
-      int key_id = i * 20 + j * 2;
-      ASSERT_OK(Put(Key(key_id), "value_new" + std::to_string(key_id)));
-    }
-    ASSERT_OK(Flush());
-  }
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-
-  // check the events are triggered
-  ASSERT_TRUE(listener->file_io_notified > 0);
-  ASSERT_TRUE(listener->file_creation_started > 0);
-  ASSERT_TRUE(listener->file_created > 0);
-  ASSERT_TRUE(listener->compaction_num > 0);
-  ASSERT_TRUE(listener->on_going_compactions.empty());
-
-  // verify result
-  for (int i = 0; i < 200; i++) {
-    auto result = Get(Key(i));
-    if (i % 2) {
-      ASSERT_EQ(result, "value" + std::to_string(i));
-    } else {
-      ASSERT_EQ(result, "value_new" + std::to_string(i));
-    }
-  }
-}
-
-TEST_F(CompactionServiceTest, TablePropertiesCollector) {
-  const static std::string kUserPropertyName = "TestCount";
-
-  class TablePropertiesCollectorTest : public TablePropertiesCollector {
-   public:
-    Status Finish(UserCollectedProperties* properties) override {
-      *properties = UserCollectedProperties{
-          {kUserPropertyName, std::to_string(count_)},
-      };
-      return Status::OK();
-    }
-
-    UserCollectedProperties GetReadableProperties() const override {
-      return UserCollectedProperties();
-    }
-
-    const char* Name() const override { return "TablePropertiesCollectorTest"; }
-
-    Status AddUserKey(const Slice& /*user_key*/, const Slice& /*value*/,
-                      EntryType /*type*/, SequenceNumber /*seq*/,
-                      uint64_t /*file_size*/) override {
-      count_++;
-      return Status::OK();
-    }
-
-   private:
-    uint32_t count_ = 0;
-  };
-
-  class TablePropertiesCollectorFactoryTest
-      : public TablePropertiesCollectorFactory {
-   public:
-    TablePropertiesCollector* CreateTablePropertiesCollector(
-        TablePropertiesCollectorFactory::Context /*context*/) override {
-      return new TablePropertiesCollectorTest();
-    }
-
-    const char* Name() const override {
-      return "TablePropertiesCollectorFactoryTest";
-    }
-  };
-
-  auto factory = new TablePropertiesCollectorFactoryTest();
-  remote_table_properties_collector_factories.emplace_back(factory);
-
-  const int kNumSst = 3;
-  const int kLevel0Trigger = 4;
-  Options options = CurrentOptions();
-  options.level0_file_num_compaction_trigger = kLevel0Trigger;
-  ReopenWithCompactionService(&options);
-
-  // generate a few SSTs locally which should not have user property
-  for (int i = 0; i < kNumSst; i++) {
-    for (int j = 0; j < 100; j++) {
-      ASSERT_OK(Put(Key(i * 10 + j), "value"));
-    }
-    ASSERT_OK(Flush());
-  }
-
-  TablePropertiesCollection fname_to_props;
-  ASSERT_OK(db_->GetPropertiesOfAllTables(&fname_to_props));
-  for (const auto& file_props : fname_to_props) {
-    auto properties = file_props.second->user_collected_properties;
-    auto it = properties.find(kUserPropertyName);
-    ASSERT_EQ(it, properties.end());
-  }
-
-  // trigger compaction
-  for (int i = kNumSst; i < kLevel0Trigger; i++) {
-    for (int j = 0; j < 100; j++) {
-      ASSERT_OK(Put(Key(i * 10 + j), "value"));
-    }
-    ASSERT_OK(Flush());
-  }
-  ASSERT_OK(dbfull()->TEST_WaitForCompact(true));
-
-  ASSERT_OK(db_->GetPropertiesOfAllTables(&fname_to_props));
-
-  bool has_user_property = false;
-  for (const auto& file_props : fname_to_props) {
-    auto properties = file_props.second->user_collected_properties;
-    auto it = properties.find(kUserPropertyName);
-    if (it != properties.end()) {
-      has_user_property = true;
-      ASSERT_GT(std::stoi(it->second), 0);
-    }
-  }
-  ASSERT_TRUE(has_user_property);
-}
+INSTANTIATE_TEST_CASE_P(
+    CompactionServiceTest, CompactionServiceTest,
+    ::testing::Values(
+        TestCompactionServiceType::MyTestCompactionServiceType,
+        TestCompactionServiceType::MyTestCompactionServiceLegacyType));

 }  // namespace ROCKSDB_NAMESPACE
Author	SHA1	Message	Date
Peter Dillinger	df4d3cf6fd	Update version to 6.28.2 Summary: Update version to 6.28.2 for bug fix	2022-01-31 15:24:29 -08:00
Jay Zhuang	70a68ddc06	Update circleci xcode version (#9405 ) Summary: xcode 11.3.1 is deprecated https://circleci.com/docs/2.0/testing-ios/ , jobs are failing: ``` failed to create host: Image xcode:11.3.0 is not supported ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9405 Test Plan: CI Reviewed By: ajkr, hx235 Differential Revision: D33674462 Pulled By: jay-zhuang fbshipit-source-id: 85dd27aad84d26eaaa5c5375015344182b2c50b9	2022-01-31 15:24:29 -08:00
Peter Dillinger	c79005a6b6	Pick in install-jdk8-on-macos from `5602b1d3d9`	2022-01-31 15:24:28 -08:00
Peter Dillinger	0500c49f62	Fix^2 prefix extractor testing in crash test (#9463 ) Summary: Even after https://github.com/facebook/rocksdb/issues/9461 could see ``` Error: please specify prefix_size for test_batches_snapshots test! ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9463 Test Plan: run `make blackbox_crashtest` for a long time. (Unfortunately, it's taking a long time to reproduce these failures) Reviewed By: akankshamahajan15 Differential Revision: D33838152 Pulled By: pdillinger fbshipit-source-id: b9a73c5bbb68df53f14c22b9b52f61d1f7ef38af	2022-01-31 10:12:33 -08:00
Peter Dillinger	0cf2c6aa3b	Fix/expand prefix extractor testing in crash test (#9461 ) Summary: Changes in https://github.com/facebook/rocksdb/issues/9453 could trigger ``` stderr: Error: prefixpercent is non-zero while prefix_size is not positive! ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/9461 Test Plan: run `make blackbox_crashtest` for a long time Reviewed By: ajkr Differential Revision: D33830751 Pulled By: pdillinger fbshipit-source-id: be88377dcaa47e4bb7adb0347762639eff8f1476	2022-01-31 10:12:33 -08:00
Peter Dillinger	b0e248e2a4	Fix major bug with MultiGet, DeleteRange, and memtable Bloom (#9453 ) Summary: MemTable::MultiGet was not considering range tombstones before querying Bloom filter. This means range tombstones would be skipped for keys (or prefixes) with no other entries in the memtable. This could cause old values for a key (in SST files) to still show up until the range tombstone covering it has been flushed. This is fixed by essentially disabling the memtable Bloom filter when there are any range tombstones. (This could be better optimized in the future, but good enough for now.) Did some other cleanup/optimization in the same code to (more than) offset the cost of checking on range tombstones in more cases. There is now notable improvement when memtable_whole_key_filtering and prefix_extractor are used together (unusual), and this makes MultiGet closer to the Get implementation. Pull Request resolved: https://github.com/facebook/rocksdb/pull/9453 Test Plan: new unit test added. Added memtable Bloom to crash test. Performance testing -------------------- Build WAL-only DB (recovers to memtable): ``` TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -benchmarks=fillrandom -num=1000000 -write_buffer_size=250000000 ``` Query test command, to maximize sensitivity to the changed code: ``` TEST_TMPDIR=/dev/shm/rocksdb ./db_bench -use_existing_db -readonly -benchmarks=multireadrandom -num=10000000 -write_buffer_size=250000000 -memtable_bloom_size_ratio=0.015 -multiread_batched -batch_size=24 -threads=8 -memtable_whole_key_filtering=$MWKF -prefix_size=$PXS ``` (Note -num here is 10x larger for mostly memtable misses) Before & after run simultaneously, average over 10 iterations per data point, ops/sec. MWKF=0 PXS=0 (Bloom disabled) Before: 5724844 After: 6722066 MWKF=0 PXS=7 (prefixes hardly unique; Bloom not useful) Before: 9981319 After: 10237990 MWKF=0 PXS=8 (prefixes unique; Bloom useful) Before: 12081715 After: 12117603 MWKF=1 PXS=0 (whole key Bloom useful) Before: 11944354 After: 12096085 MWKF=1 PXS=7 (whole key Bloom useful in new version; prefixes not useful in old version) Before: 9444299 After: 11826029 MWKF=1 PXS=7 (whole key Bloom useful in new version; prefixes useful in old version) Before: 11784465 After: 11778591 Only in this last case is the 'before' slightly faster, perhaps because hashing prefixes is slightly faster than hashing whole keys. Otherwise, 'after' is faster. Reviewed By: ajkr Differential Revision: D33805025 Pulled By: pdillinger fbshipit-source-id: 597523cae4f4eafdf6ae6bb2bc6cb46f83b017bf	2022-01-31 10:12:30 -08:00
Yanqin Jin	fdb3125547	Update HISTORY and bump version	2022-01-10 11:31:18 -08:00
Yanqin Jin	128e36ca53	Make RocksDB codebase compatible with newer compilers like clang-12 (#9370 ) Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/9370 GCC and newer clang, e.g. clang-12 treat `std::unique_ptr` slightly differently. For the following code ``` #include <iostream> #include <memory> #include <type_traits> struct A { std::unique_ptr<int> m1; }; int main() { std::cout << std::boolalpha; std::cout << std::is_standard_layout<A>::value << '\n'; return 0; } ``` GCC11(C++20) (tested on https://en.cppreference.com/w/cpp/types/is_standard_layout) will print "true", while newer clang, e.g. clang-12 will print "false". This breaks the usage of `offsetof()` on structs with non-static members of type `std::unique_ptr`. Fixing this by replacing the builtin `offsetof` with a trick documented at https://gist.github.com/graphitemaster/494f21190bb2c63c5516. Reviewed By: jay-zhuang Differential Revision: D33420840 fbshipit-source-id: 02bde281dfa28809bec787ad0f7019e85dd9c607	2022-01-10 11:27:59 -08:00