HISTORY.md update for bzip upgrade (#6767 )

Summary: See https://github.com/facebook/rocksdb/issues/6714 and https://github.com/facebook/rocksdb/issues/6703 Pull Request resolved: https://github.com/facebook/rocksdb/pull/6767 Reviewed By: riversand963 Differential Revision: D21283307 Pulled By: pdillinger fbshipit-source-id: 8463bec725669d13846c728ad4b5bde43f9a84f8
Update RocksJava static version of bzip2 (#6714 )
2026-11-06 02:52:35 -05:00 · 2020-04-28 13:50:06 -07:00 · 2020-04-16 16:01:15 -07:00 · 2020-04-16 16:01:08 -07:00 · 2020-04-15 10:05:11 -07:00 · 2020-04-15 10:04:56 -07:00
441 changed files with 7614 additions and 26752 deletions
@@ -1,56 +0,0 @@
-version: 2.1
-
-orbs:
-  win: circleci/windows@2.4.0
-
-executors:
-  windows-2xlarge:
-    machine:
-      image: 'windows-server-2019-vs2019:stable'
-      resource_class: windows.2xlarge
-      shell: bash.exe
-
-jobs:
-  build:
-    executor: windows-2xlarge
-    
-    environment:
-      THIRDPARTY_HOME: C:/Users/circleci/thirdparty
-      CMAKE_HOME: C:/Users/circleci/thirdparty/cmake-3.16.4-win64-x64
-      CMAKE_BIN: C:/Users/circleci/thirdparty/cmake-3.16.4-win64-x64/bin/cmake.exe
-      CMAKE_GENERATOR: Visual Studio 16 2019
-      SNAPPY_HOME: C:/Users/circleci/thirdparty/snappy-1.1.7
-      SNAPPY_INCLUDE: C:/Users/circleci/thirdparty/snappy-1.1.7;C:/Users/circleci/thirdparty/snappy-1.1.7/build
-      SNAPPY_LIB_DEBUG: C:/Users/circleci/thirdparty/snappy-1.1.7/build/Debug/snappy.lib
-
-    steps:
-      - checkout
-      - run:
-          name: "Install thirdparty dependencies"
-          command: |
-            mkdir ${THIRDPARTY_HOME}
-            cd ${THIRDPARTY_HOME}
-            echo "Installing CMake..."
-            curl --fail --silent --show-error --output cmake-3.16.4-win64-x64.zip --location https://github.com/Kitware/CMake/releases/download/v3.16.4/cmake-3.16.4-win64-x64.zip
-            unzip -q cmake-3.16.4-win64-x64.zip
-            echo "Building Snappy dependency..."
-            curl --fail --silent --show-error --output snappy-1.1.7.zip --location https://github.com/google/snappy/archive/1.1.7.zip
-            unzip -q snappy-1.1.7.zip
-            cd snappy-1.1.7
-            mkdir build
-            cd build
-            ${CMAKE_BIN} -G "${CMAKE_GENERATOR}" ..
-            msbuild.exe Snappy.sln -maxCpuCount -property:Configuration=Debug -property:Platform=x64
-      - run:
-          name: "Build RocksDB"
-          command: |
-            mkdir build
-            cd build
-            ${CMAKE_BIN} -G "${CMAKE_GENERATOR}" -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE=1 -DSNAPPY=1 -DJNI=1 ..
-            cd ..
-            msbuild.exe build/rocksdb.sln -maxCpuCount -property:Configuration=Debug -property:Platform=x64
-      - run:
-          name: "Test RocksDB"
-          shell: powershell.exe
-          command: |
-            build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test,db_test2,env_basic_test,env_test,db_merge_operand_test -Concurrency 16
@@ -1,41 +0,0 @@
-name: Check buck targets and code format
-on: [push, pull_request]
-jobs:
-  check:
-    name: Check TARGETS file and code format
-    runs-on: ubuntu-latest
-    steps:
-    - name: Checkout feature branch
-      uses: actions/checkout@v2
-      with:
-        fetch-depth: 0
-
-    - name: Fetch from upstream
-      run: |
-        git remote add upstream https://github.com/facebook/rocksdb.git && git fetch upstream
-
-    - name: Where am I
-      run: |
-        echo git status && git status
-        echo "git remote -v" && git remote -v
-        echo git branch && git branch
-
-    - name: Setup Python
-      uses: actions/setup-python@v1
-
-    - name: Install Dependencies
-      run: python -m pip install --upgrade pip
-
-    - name: Install argparse
-      run: pip install argparse
-
-    - name: Download clang-format-diff.py
-      uses: wei/wget@v1
-      with:
-        args: https://raw.githubusercontent.com/llvm-mirror/clang/master/tools/clang-format/clang-format-diff.py
-
-    - name: Check format
-      run: make check-format
-
-    - name: Compare buckify output
-      run: make check-buck-targets
@@ -34,7 +34,6 @@ 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
@@ -83,5 +82,3 @@ fbcode/
 fbcode
 buckifier/*.pyc
 buckifier/__pycache__
-
-compile_commands.json
@@ -3,14 +3,12 @@ language: cpp
 os:
  - linux
  - osx
-arch:
-  - amd64
-  - arm64
-  - ppc64le
 compiler:
  - clang
  - gcc
 osx_image: xcode9.4
+jdk:
+  - openjdk7
 cache:
  - ccache

@@ -50,153 +48,26 @@ env:
  - JOB_NAME=examples # 5-7 minutes
  - JOB_NAME=cmake # 3-5 minutes
  - JOB_NAME=cmake-gcc8 # 3-5 minutes
-  - JOB_NAME=cmake-gcc9 # 3-5 minutes
-  - JOB_NAME=cmake-gcc9-c++20 # 3-5 minutes
  - JOB_NAME=cmake-mingw # 3 minutes

 matrix:
  exclude:
+  - os: osx
+    env: TEST_GROUP=1
+  - os: osx
+    env: TEST_GROUP=2
+  - os: osx
+    env: TEST_GROUP=3
+  - os: osx
+    env: TEST_GROUP=4
  - os: osx
    env: JOB_NAME=cmake-gcc8
-  - os: osx
-    env: JOB_NAME=cmake-gcc9
-  - os: osx
-    env: JOB_NAME=cmake-gcc9-c++20
-  - os: osx
+  - os : osx
    env: JOB_NAME=cmake-mingw
-  - os: osx
-    arch: ppc64le
-  - os: osx
-    compiler: gcc
  - os : linux
-    arch: arm64
-    env: JOB_NAME=cmake-mingw
-  - os: linux
-    arch: ppc64le
-    env: JOB_NAME=cmake-mingw
-  - os: linux
    compiler: clang
-  # Exclude all but most unique cmake variants for pull requests, but build all in branches
-  - if: type = pull_request
-    os : linux
-    arch: amd64
-    env: JOB_NAME=cmake
-  - if: type = pull_request
-    os : linux
-    arch: amd64
-    env: JOB_NAME=cmake-gcc8
-  - if: type = pull_request
-    os : linux
-    arch: amd64
-    env: JOB_NAME=cmake-gcc9
-  # Exclude most osx, arm64 and ppc64le tests for pull requests, but build in branches
-  # Temporarily disable ppc64le unit tests in PRs until Travis gets its act together (#6653)
-  - if: type = pull_request
-    os: linux
-    arch: ppc64le
-    env: TEST_GROUP=platform_dependent
-  # NB: the cmake build is a partial java test
-  - if: type = pull_request
-    os: osx
-    env: TEST_GROUP=1
-  - if: type = pull_request
-    os : linux
-    arch: arm64
-    env: TEST_GROUP=1
-  - if: type = pull_request
-    os: linux
-    arch: ppc64le
-    env: TEST_GROUP=1
-  - if: type = pull_request
-    os: osx
-    env: TEST_GROUP=2
-  - if: type = pull_request
-    os : linux
-    arch: arm64
-    env: TEST_GROUP=2
-  - if: type = pull_request
-    os: linux
-    arch: ppc64le
-    env: TEST_GROUP=2
-  - if: type = pull_request
-    os: osx
-    env: TEST_GROUP=3
-  - if: type = pull_request
-    os : linux
-    arch: arm64
-    env: TEST_GROUP=3
-  - if: type = pull_request
-    os: linux
-    arch: ppc64le
-    env: TEST_GROUP=3
-  - if: type = pull_request
-    os: osx
-    env: TEST_GROUP=4
-  - if: type = pull_request
-    os : linux
-    arch: arm64
-    env: TEST_GROUP=4
-  - if: type = pull_request
-    os: linux
-    arch: ppc64le
-    env: TEST_GROUP=4
-  - if: type = pull_request AND commit_message !~ /java/
-    os : osx
-    env: JOB_NAME=java_test
-  - if: type = pull_request AND commit_message !~ /java/
-    os : linux
-    arch: arm64
-    env: JOB_NAME=java_test
-  - if: type = pull_request AND commit_message !~ /java/
-    os: linux
-    arch: ppc64le
-    env: JOB_NAME=java_test
-  - if: type = pull_request
-    os : osx
-    env: JOB_NAME=lite_build
-  - if: type = pull_request
-    os : linux
-    arch: arm64
-    env: JOB_NAME=lite_build
-  - if: type = pull_request
-    os: linux
-    arch: ppc64le
-    env: JOB_NAME=lite_build
-  - if: type = pull_request
-    os : osx
-    env: JOB_NAME=examples
-  - if: type = pull_request
-    os : linux
-    arch: arm64
-    env: JOB_NAME=examples
-  - if: type = pull_request
-    os: linux
-    arch: ppc64le
-    env: JOB_NAME=examples
-  - if: type = pull_request
-    os : linux
-    arch: arm64
-    env: JOB_NAME=cmake-gcc8
-  - if: type = pull_request
-    os: linux
-    arch: ppc64le
-    env: JOB_NAME=cmake-gcc8
-  - if: type = pull_request
-    os : linux
-    arch: arm64
-    env: JOB_NAME=cmake-gcc9
-  - if: type = pull_request
-    os: linux
-    arch: ppc64le
-    env: JOB_NAME=cmake-gcc9
-  - if: type = pull_request
-    os : linux
-    arch: arm64
-    env: JOB_NAME=cmake-gcc9-c++20
-  - if: type = pull_request
-    os: linux
-    arch: ppc64le
-    env: JOB_NAME=cmake-gcc9-c++20
+  - os : osx
+    compiler: gcc

 install:
  - if [ "${TRAVIS_OS_NAME}" == osx ]; then
@@ -206,37 +77,16 @@ install:
      sudo apt-get install -y g++-8;
      CC=gcc-8 && CXX=g++-8;
    fi
-  - if [ "${JOB_NAME}" == cmake-gcc9 ] || [ "${JOB_NAME}" == cmake-gcc9-c++20 ]; then
-      sudo apt-get install -y g++-9;
-      CC=gcc-9 && CXX=g++-9;
-    fi
  - if [ "${JOB_NAME}" == cmake-mingw ]; then
      sudo apt-get install -y mingw-w64 ;
    fi
  - if [[ "${JOB_NAME}" == cmake* ]] && [ "${TRAVIS_OS_NAME}" == linux ]; then
      CMAKE_DIST_URL="https://rocksdb-deps.s3-us-west-2.amazonaws.com/cmake/cmake-3.14.5-Linux-$(uname -m).tar.bz2";
      TAR_OPT="--strip-components=1 -xj";
-      if [ "aarch64" == "$(uname -m)" ]; then
-        sudo apt-get install -y libuv1 librhash0;
-        sudo apt-get upgrade -y libstdc++6;
-      fi;
      mkdir cmake-dist && curl --silent --fail --show-error --location "${CMAKE_DIST_URL}" | tar -C cmake-dist ${TAR_OPT} && export PATH=$PWD/cmake-dist/bin:$PATH;
    fi
-  - |
-    if [[ "${JOB_NAME}" == java_test || "${JOB_NAME}" == cmake* ]]; then
-      # Ensure JDK 8
-      if [ "${TRAVIS_OS_NAME}" == osx ]; then
-        brew tap AdoptOpenJDK/openjdk
-        brew cask install adoptopenjdk8
-        export JAVA_HOME=$(/usr/libexec/java_home)
-      else
-        sudo apt-get install -y openjdk-8-jdk
-        export PATH=/usr/lib/jvm/java-8-openjdk-$(dpkg --print-architecture)/bin:$PATH
-        export JAVA_HOME=/usr/lib/jvm/java-8-openjdk-$(dpkg --print-architecture)
-      fi
-      echo "JAVA_HOME=${JAVA_HOME}"
-      which java && java -version
-      which javac && javac -version
+  - if [[ "${JOB_NAME}" == java_test ]]; then
+      java -version && echo "JAVA_HOME=${JAVA_HOME}";
    fi

 before_script:
@@ -245,7 +95,7 @@ before_script:
  - ulimit -n 8192

 script:
-  - date; ${CXX} --version
+  - ${CXX} --version
  - if [ `command -v ccache` ]; then ccache -C; fi
  - case $TEST_GROUP in
    platform_dependent)
@@ -279,13 +129,7 @@ script:
      mkdir build && cd build && cmake -DJNI=1 -DWITH_GFLAGS=OFF .. -DCMAKE_C_COMPILER=x86_64-w64-mingw32-gcc -DCMAKE_CXX_COMPILER=x86_64-w64-mingw32-g++ -DCMAKE_SYSTEM_NAME=Windows && make -j4 rocksdb rocksdbjni
      ;;
    cmake*)
-      case $JOB_NAME in
-        *-c++20)
-          OPT=-DCMAKE_CXX_STANDARD=20
-          ;;
-      esac
-
-      mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_BUILD_TYPE=Release $OPT && make -j4 rocksdb rocksdbjni
+      mkdir build && cd build && cmake -DJNI=1 .. -DCMAKE_BUILD_TYPE=Release && make -j4 rocksdb rocksdbjni
      ;;
    esac
 notifications:
@@ -83,10 +83,6 @@ else()
  option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
 endif()

-if( NOT DEFINED CMAKE_CXX_STANDARD )
-  set(CMAKE_CXX_STANDARD 11)
-endif()
-
 include(CMakeDependentOption)
 CMAKE_DEPENDENT_OPTION(WITH_GFLAGS "build with GFlags" ON
  "NOT MSVC;NOT MINGW" OFF)
@@ -195,6 +191,7 @@ else()
    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format -fno-asynchronous-unwind-tables")
    add_definitions(-D_POSIX_C_SOURCE=1)
  endif()
+  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
  if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-omit-frame-pointer")
    include(CheckCXXCompilerFlag)
@@ -206,25 +203,16 @@ else()
 endif()

 include(CheckCCompilerFlag)
-if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
-  CHECK_C_COMPILER_FLAG("-mcpu=power9" HAS_POWER9)
-  if(HAS_POWER9)
-    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcpu=power9 -mtune=power9")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=power9 -mtune=power9")
-  else()
-    CHECK_C_COMPILER_FLAG("-mcpu=power8" HAS_POWER8)
-    if(HAS_POWER8)
-      set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcpu=power8 -mtune=power8")
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=power8 -mtune=power8")
-    endif(HAS_POWER8)
-  endif(HAS_POWER9)
+if(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le")
  CHECK_C_COMPILER_FLAG("-maltivec" HAS_ALTIVEC)
  if(HAS_ALTIVEC)
    message(STATUS " HAS_ALTIVEC yes")
    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -maltivec")
    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -maltivec")
+    set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcpu=power8")
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=power8")
  endif(HAS_ALTIVEC)
-endif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
+endif(CMAKE_SYSTEM_PROCESSOR MATCHES "ppc64le")

 if(CMAKE_SYSTEM_PROCESSOR MATCHES "aarch64|AARCH64")
        CHECK_C_COMPILER_FLAG("-march=armv8-a+crc+crypto" HAS_ARMV8_CRC)
@@ -247,7 +235,7 @@ else()
  if(MSVC)
    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
  else()
-    if(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64" AND NOT HAS_ARMV8_CRC)
+    if(NOT HAVE_POWER8 AND NOT HAS_ARMV8_CRC)
      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native")
    endif()
  endif()
@@ -257,7 +245,6 @@ include(CheckCXXSourceCompiles)
 if(NOT MSVC)
  set(CMAKE_REQUIRED_FLAGS "-msse4.2 -mpclmul")
 endif()
-
 CHECK_CXX_SOURCE_COMPILES("
 #include <cstdint>
 #include <nmmintrin.h>
@@ -390,15 +377,7 @@ if(MSVC)
    message(STATUS "Debug optimization is enabled")
    set(CMAKE_CXX_FLAGS_DEBUG "/Oxt")
  else()
-    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1")
-
-    # Minimal Build is deprecated after MSVC 2015
-    if( MSVC_VERSION GREATER 1900 )
-      set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Gm-")
-    else()
-      set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Gm")
-    endif()
-
+    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1 /Gm")
  endif()
  if(WITH_RUNTIME_DEBUG)
    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /${RUNTIME_LIBRARY}d")
@@ -502,11 +481,6 @@ if(HAVE_SCHED_GETCPU)
  add_definitions(-DROCKSDB_SCHED_GETCPU_PRESENT)
 endif()

-check_cxx_symbol_exists(getauxval auvx.h HAVE_AUXV_GETAUXVAL)
-if(HAVE_AUXV_GETAUXVAL)
-  add_definitions(-DROCKSDB_AUXV_GETAUXVAL_PRESENT)
-endif()
-
 include_directories(${PROJECT_SOURCE_DIR})
 include_directories(${PROJECT_SOURCE_DIR}/include)
 include_directories(SYSTEM ${PROJECT_SOURCE_DIR}/third-party/gtest-1.8.1/fused-src)
@@ -518,14 +492,10 @@ find_package(Threads REQUIRED)
 # Main library source code

 set(SOURCES
-        cache/cache.cc
        cache/clock_cache.cc
        cache/lru_cache.cc
        cache/sharded_cache.cc
        db/arena_wrapped_db_iter.cc
-        db/blob/blob_file_addition.cc
-        db/blob/blob_file_garbage.cc
-        db/blob/blob_file_meta.cc
        db/builder.cc
        db/c.cc
        db/column_family.cc
@@ -579,7 +549,6 @@ set(SOURCES
        db/trim_history_scheduler.cc
        db/version_builder.cc
        db/version_edit.cc
-        db/version_edit_handler.cc
        db/version_set.cc
        db/wal_manager.cc
        db/write_batch.cc
@@ -608,7 +577,6 @@ set(SOURCES
        memory/arena.cc
        memory/concurrent_arena.cc
        memory/jemalloc_nodump_allocator.cc
-        memory/memkind_kmem_allocator.cc
        memtable/alloc_tracker.cc
        memtable/hash_linklist_rep.cc
        memtable/hash_skiplist_rep.cc
@@ -633,17 +601,15 @@ set(SOURCES
        options/options.cc
        options/options_helper.cc
        options/options_parser.cc
+        options/options_sanity_check.cc
        port/stack_trace.cc
        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
        table/block_based/block_based_table_reader.cc
        table/block_based/block_builder.cc
-        table/block_based/block_prefetcher.cc
        table/block_based/block_prefix_index.cc
        table/block_based/data_block_hash_index.cc
        table/block_based/data_block_footer.cc
@@ -651,14 +617,9 @@ set(SOURCES
        table/block_based/filter_policy.cc
        table/block_based/flush_block_policy.cc
        table/block_based/full_filter_block.cc
-        table/block_based/hash_index_reader.cc
        table/block_based/index_builder.cc
-        table/block_based/index_reader_common.cc
        table/block_based/parsed_full_filter_block.cc
        table/block_based/partitioned_filter_block.cc
-        table/block_based/partitioned_index_iterator.cc
-        table/block_based/partitioned_index_reader.cc
-        table/block_based/reader_common.cc
        table/block_based/uncompression_dict_reader.cc
        table/block_fetcher.cc
        table/cuckoo/cuckoo_table_builder.cc
@@ -773,11 +734,11 @@ if(HAVE_SSE42 AND NOT MSVC)
    PROPERTIES COMPILE_FLAGS "-msse4.2 -mpclmul")
 endif()

-if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
+if(HAVE_POWER8)
  list(APPEND SOURCES
    util/crc32c_ppc.c
    util/crc32c_ppc_asm.S)
-endif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
+endif(HAVE_POWER8)

 if(HAS_ARMV8_CRC)
  list(APPEND SOURCES
@@ -861,6 +822,7 @@ if(ROCKSDB_BUILD_SHARED)
                          LINKER_LANGUAGE CXX
                          VERSION ${rocksdb_VERSION}
                          SOVERSION ${rocksdb_VERSION_MAJOR}
+                          CXX_STANDARD 11
                          OUTPUT_NAME "rocksdb")
  endif()
 endif()
@@ -957,9 +919,6 @@ if(WITH_TESTS)
  set(TESTS
        cache/cache_test.cc
        cache/lru_cache_test.cc
-        db/blob/blob_file_addition_test.cc
-        db/blob/blob_file_garbage_test.cc
-        db/blob/db_blob_index_test.cc
        db/column_family_test.cc
        db/compact_files_test.cc
        db/compaction/compaction_job_stats_test.cc
@@ -970,7 +929,7 @@ if(WITH_TESTS)
        db/corruption_test.cc
        db/cuckoo_table_db_test.cc
        db/db_basic_test.cc
-        db/db_with_timestamp_basic_test.cc
+        db/db_blob_index_test.cc
        db/db_block_cache_test.cc
        db/db_bloom_filter_test.cc
        db/db_compaction_filter_test.cc
@@ -996,14 +955,12 @@ if(WITH_TESTS)
        db/db_tailing_iter_test.cc
        db/db_test.cc
        db/db_test2.cc
-        db/db_logical_block_size_cache_test.cc
        db/db_universal_compaction_test.cc
        db/db_wal_test.cc
-        db/db_with_timestamp_compaction_test.cc
        db/db_write_test.cc
        db/dbformat_test.cc
        db/deletefile_test.cc
-        db/error_handler_fs_test.cc
+        db/error_handler_test.cc
        db/obsolete_files_test.cc
        db/external_sst_file_basic_test.cc
        db/external_sst_file_test.cc
@@ -1034,15 +991,12 @@ if(WITH_TESTS)
        db/write_controller_test.cc
        env/env_basic_test.cc
        env/env_test.cc
-        env/io_posix_test.cc
        env/mock_env_test.cc
        file/delete_scheduler_test.cc
-        file/random_access_file_reader_test.cc
        logging/auto_roll_logger_test.cc
        logging/env_logger_test.cc
        logging/event_logger_test.cc
        memory/arena_test.cc
-        memory/memkind_kmem_allocator_test.cc
        memtable/inlineskiplist_test.cc
        memtable/skiplist_test.cc
        memtable/write_buffer_manager_test.cc
@@ -1063,7 +1017,6 @@ if(WITH_TESTS)
        table/merger_test.cc
        table/sst_file_reader_test.cc
        table/table_test.cc
-        table/block_fetcher_test.cc
        tools/block_cache_analyzer/block_cache_trace_analyzer_test.cc
        tools/ldb_cmd_test.cc
        tools/reduce_levels_test.cc
@@ -1085,10 +1038,8 @@ if(WITH_TESTS)
        util/slice_test.cc
        util/slice_transform_test.cc
        util/timer_queue_test.cc
-        util/timer_test.cc
        util/thread_list_test.cc
        util/thread_local_test.cc
-        util/work_queue_test.cc
        utilities/backupable/backupable_db_test.cc
        utilities/blob_db/blob_db_test.cc
        utilities/cassandra/cassandra_functional_test.cc
@@ -1108,7 +1059,6 @@ if(WITH_TESTS)
        utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
        utilities/transactions/optimistic_transaction_test.cc
        utilities/transactions/transaction_test.cc
-        utilities/transactions/transaction_lock_mgr_test.cc
        utilities/transactions/write_prepared_transaction_test.cc
        utilities/transactions/write_unprepared_transaction_test.cc
        utilities/ttl/ttl_test.cc
@@ -1127,7 +1077,6 @@ if(WITH_TESTS)
      monitoring/thread_status_updater_debug.cc
      table/mock_table.cc
      test_util/fault_injection_test_env.cc
-      test_util/fault_injection_test_fs.cc
      utilities/cassandra/test_utils.cc
  )
  enable_testing()
@@ -1142,7 +1091,7 @@ if(WITH_TESTS)
        PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
        EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
        EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
-  )
+        )

  foreach(sourcefile ${TESTS})
      get_filename_component(exename ${sourcefile} NAME_WE)
@@ -1152,7 +1101,7 @@ if(WITH_TESTS)
        EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
        EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
        OUTPUT_NAME ${exename}${ARTIFACT_SUFFIX}
-      )
+        )
      target_link_libraries(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} testharness gtest ${ROCKSDB_LIB})
      if(NOT "${exename}" MATCHES "db_sanity_test")
        add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
@@ -1,71 +1,11 @@
 # Rocksdb Change Log
 ## Unreleased
 ### Bug Fixes
-* Fix consistency checking error swallowing in some cases when options.force_consistency_checks = true.
-
-### Public API Change
-* Flush(..., column_family) may return Status::ColumnFamilyDropped() instead of Status::InvalidArgument() if column_family is dropped while processing the flush request.
-* BlobDB now explicitly disallows using the default column family's storage directories as blob directory.
-* DeleteRange now returns `Status::InvalidArgument` if the range's end key comes before its start key according to the user comparator. Previously the behavior was undefined.
-
-## 6.10 (5/2/2020)
-### Bug Fixes
-* Fix wrong result being read from ingested file. May happen when a key in the file happen to be prefix of another key also in the file. The issue can further cause more data corruption. The issue exists with rocksdb >= 5.0.0 since DB::IngestExternalFile() was introduced.
-* Finish implementation of BlockBasedTableOptions::IndexType::kBinarySearchWithFirstKey. It's now ready for use. Significantly reduces read amplification in some setups, especially for iterator seeks.
-* Fix a bug by updating CURRENT file so that it points to the correct MANIFEST file after best-efforts recovery.
-* Fixed a bug where ColumnFamilyHandle objects were not cleaned up in case an error happened during BlobDB's open after the base DB had been opened.
-* Fix a potential undefined behavior caused by trying to dereference nullable pointer (timestamp argument) in DB::MultiGet.
-* Fix a bug caused by not including user timestamp in MultiGet LookupKey construction. This can lead to wrong query result since the trailing bytes of a user key, if not shorter than timestamp, will be mistaken for user timestamp.
-* Fix a bug caused by using wrong compare function when sorting the input keys of MultiGet with timestamps.
 * Upgraded version of bzip library (1.0.6 -> 1.0.8) used with RocksJava to address potential vulnerabilities if an attacker can manipulate compressed data saved and loaded by RocksDB (not normal). See issue #6703.

-### Public API Change
-* Add a ConfigOptions argument to the APIs dealing with converting options to and from strings and files.  The ConfigOptions is meant to replace some of the options (such as input_strings_escaped and ignore_unknown_options) and allow for more parameters to be passed in the future without changing the function signature.
-* Add NewFileChecksumGenCrc32cFactory to the file checksum public API, such that the builtin Crc32c based file checksum generator factory can be used by applications.
-* Add IsDirectory to Env and FS to indicate if a path is a directory.
-
-### New Features
-* Added support for pipelined & parallel compression optimization for `BlockBasedTableBuilder`. This optimization makes block building, block compression and block appending a pipeline, and uses multiple threads to accelerate block compression. Users can set `CompressionOptions::parallel_threads` greater than 1 to enable compression parallelism. This feature is experimental for now.
-* Provide an allocator for memkind to be used with block cache. This is to work with memory technologies (Intel DCPMM is one such technology currently available) that require different libraries for allocation and management (such as PMDK and memkind). The high capacities available make it possible to provision large caches (up to several TBs in size) beyond what is achievable with DRAM.
-* Option `max_background_flushes` can be set dynamically using DB::SetDBOptions().
-* Added functionality in sst_dump tool to check the compressed file size for different compression levels and print the time spent on compressing files with each compression type. Added arguments `--compression_level_from` and `--compression_level_to` to report size of all compression levels and one compression_type must be specified with it so that it will report compressed sizes of one compression type with different levels.
-* Added statistics for redundant insertions into block cache: rocksdb.block.cache.*add.redundant. (There is currently no coordination to ensure that only one thread loads a table block when many threads are trying to access that same table block.)
-
-### Bug Fixes
-* Fix a bug when making options.bottommost_compression, options.compression_opts and options.bottommost_compression_opts dynamically changeable: the modified values are not written to option files or returned back to users when being queried.
-* Fix a bug where index key comparisons were unaccounted in `PerfContext::user_key_comparison_count` for lookups in files written with `format_version >= 3`.
-* Fix many bloom.filter statistics not being updated in batch MultiGet.
-
-### Performance Improvements
-* Improve performance of batch MultiGet with partitioned filters, by sharing block cache lookups to applicable filter blocks.
-* Reduced memory copies when fetching and uncompressing compressed blocks from sst files.
-
-## 6.9.0 (03/29/2020)
+## 6.8.1 (03/30/2020)
 ### Behavior changes
-* Since RocksDB 6.8, ttl-based FIFO compaction can drop a file whose oldest key becomes older than options.ttl while others have not. This fix reverts this and makes ttl-based FIFO compaction use the file's flush time as the criterion. This fix also requires that max_open_files = -1 and compaction_options_fifo.allow_compaction = false to function properly.
-
-### Public API Change
-* Fix spelling so that API now has correctly spelled transaction state name `COMMITTED`, while the old misspelled `COMMITED` is still available as an alias.
-* Updated default format_version in BlockBasedTableOptions from 2 to 4. SST files generated with the new default can be read by RocksDB versions 5.16 and newer, and use more efficient encoding of keys in index blocks.
-* A new parameter `CreateBackupOptions` is added to both `BackupEngine::CreateNewBackup` and `BackupEngine::CreateNewBackupWithMetadata`, you can decrease CPU priority of `BackupEngine`'s background threads by setting `decrease_background_thread_cpu_priority` and `background_thread_cpu_priority` in `CreateBackupOptions`.
-* Updated the public API of SST file checksum. Introduce the FileChecksumGenFactory to create the FileChecksumGenerator for each SST file, such that the FileChecksumGenerator is not shared and it can be more general for checksum implementations. Changed the FileChecksumGenerator interface from Value, Extend, and GetChecksum to Update, Finalize, and GetChecksum. Finalize should be only called once after all data is processed to generate the final checksum. Temproal data should be maintained by the FileChecksumGenerator object itself and finally it can return the checksum string.
-
-### Bug Fixes
-* Fix a bug where range tombstone blocks in ingested files were cached incorrectly during ingestion. If range tombstones were read from those incorrectly cached blocks, the keys they covered would be exposed.
-* Fix a data race that might cause crash when calling DB::GetCreationTimeOfOldestFile() by a small chance. The bug was introduced in 6.6 Release.
-* Fix a bug where a boolean value optimize_filters_for_hits was for max threads when calling load table handles after a flush or compaction. The value is correct to 1. The bug should not cause user visible problems.
-* Fix a bug which might crash the service when write buffer manager fails to insert the dummy handle to the block cache.
-
-### Performance Improvements
-* In CompactRange, for levels starting from 0, if the level does not have any file with any key falling in the specified range, the level is skipped. So instead of always compacting from level 0, the compaction starts from the first level with keys in the specified range until the last such level.
-* Reduced memory copy when reading sst footer and blobdb in direct IO mode.
-* When restarting a database with large numbers of sst files, large amount of CPU time is spent on getting logical block size of the sst files, which slows down the starting progress, this inefficiency is optimized away with an internal cache for the logical block sizes.
-
-### New Features
-* Basic support for user timestamp in iterator. Seek/SeekToFirst/Next and lower/upper bounds are supported. Reverse iteration is not supported. Merge is not considered.
-* When file lock failure when the lock is held by the current process, return acquiring time and thread ID in the error message.
-* Added a new option, best_efforts_recovery (default: false), to allow database to open in a db dir with missing table files. During best efforts recovery, missing table files are ignored, and database recovers to the most recent state without missing table file. Cross-column-family consistency is not guaranteed even if WAL is enabled.
-* options.bottommost_compression, options.compression_opts and options.bottommost_compression_opts are now dynamically changeable.
+* Since RocksDB 6.8.0, ttl-based FIFO compaction can drop a file whose oldest key becomes older than options.ttl while others have not. This fix reverts this and makes ttl-based FIFO compaction use the file's flush time as the criterion. This fix also requires that max_open_files = -1 and compaction_options_fifo.allow_compaction = false to function properly.

 ## 6.8.0 (02/24/2020)
 ### Java API Changes
@@ -8,7 +8,6 @@

 BASH_EXISTS := $(shell which bash)
 SHELL := $(shell which bash)
-PYTHON?=$(shell which python)

 CLEAN_FILES = # deliberately empty, so we can append below.
 CFLAGS += ${EXTRA_CFLAGS}
@@ -204,20 +203,10 @@ LDFLAGS += -lrados
 endif

 AM_LINK = $(AM_V_CCLD)$(CXX) $^ $(EXEC_LDFLAGS) -o $@ $(LDFLAGS) $(COVERAGEFLAGS)
-# Detect what platform we're building on.
-# Export some common variables that might have been passed as Make variables
-# instead of environment variables.
-dummy := $(shell (export ROCKSDB_ROOT="$(CURDIR)"; \
-                  export COMPILE_WITH_ASAN="$(COMPILE_WITH_ASAN)"; \
-                  export COMPILE_WITH_TSAN="$(COMPILE_WITH_TSAN)"; \
-                  export COMPILE_WITH_UBSAN="$(COMPILE_WITH_UBSAN)"; \
-                  export PORTABLE="$(PORTABLE)"; \
-                  export ROCKSDB_NO_FBCODE="$(ROCKSDB_NO_FBCODE)"; \
-                  export USE_CLANG="$(USE_CLANG)"; \
-                  "$(CURDIR)/build_tools/build_detect_platform" "$(CURDIR)/make_config.mk"))
+# detect what platform we're building on
+dummy := $(shell (export ROCKSDB_ROOT="$(CURDIR)"; export PORTABLE="$(PORTABLE)"; "$(CURDIR)/build_tools/build_detect_platform" "$(CURDIR)/make_config.mk"))
 # this file is generated by the previous line to set build flags and sources
 include make_config.mk
-export JAVAC_ARGS
 CLEAN_FILES += make_config.mk

 missing_make_config_paths := $(shell				\
@@ -227,7 +216,7 @@ missing_make_config_paths := $(shell				\
 	done | sort | uniq)

 $(foreach path, $(missing_make_config_paths), \
-	$(warning Warning: $(path) does not exist))
+	$(warning Warning: $(path) dont exist))

 ifeq ($(PLATFORM), OS_AIX)
 # no debug info
@@ -450,18 +439,12 @@ BENCHTOOLOBJECTS = $(BENCH_LIB_SOURCES:.cc=.o) $(LIBOBJECTS) $(TESTUTIL)

 ANALYZETOOLOBJECTS = $(ANALYZER_LIB_SOURCES:.cc=.o)

-ifeq ($(DEBUG_LEVEL),0)
 STRESSTOOLOBJECTS = $(STRESS_LIB_SOURCES:.cc=.o) $(LIBOBJECTS) $(TESTUTIL)
-else
-STRESSTOOLOBJECTS = $(STRESS_LIB_SOURCES:.cc=.o) $(LIBOBJECTS) $(TESTUTIL) \
-	$(TESTHARNESS)
-endif

 EXPOBJECTS = $(LIBOBJECTS) $(TESTUTIL)

 TESTS = \
 	db_basic_test \
-	db_with_timestamp_basic_test \
 	db_encryption_test \
 	db_test2 \
 	external_sst_file_basic_test \
@@ -476,18 +459,15 @@ TESTS = \
 	env_basic_test \
 	env_test \
 	env_logger_test \
-	io_posix_test \
 	hash_test \
 	random_test \
 	thread_local_test \
-	work_queue_test \
 	rate_limiter_test \
 	perf_context_test \
 	iostats_context_test \
 	db_wal_test \
 	db_block_cache_test \
 	db_test \
-	db_logical_block_size_cache_test \
 	db_blob_index_test \
 	db_iter_test \
 	db_iter_stress_test \
@@ -512,14 +492,13 @@ TESTS = \
 	db_table_properties_test \
 	db_statistics_test \
 	db_write_test \
-	error_handler_fs_test \
+	error_handler_test \
 	autovector_test \
 	blob_db_test \
 	cleanable_test \
 	column_family_test \
 	table_properties_collector_test \
 	arena_test \
-	memkind_kmem_allocator_test \
 	block_test \
 	data_block_hash_index_test \
 	cache_test \
@@ -530,7 +509,6 @@ TESTS = \
 	fault_injection_test \
 	filelock_test \
 	filename_test \
-	random_access_file_reader_test \
 	file_reader_writer_test \
 	block_based_filter_block_test \
 	full_filter_block_test \
@@ -575,7 +553,6 @@ TESTS = \
 	deletefile_test \
 	obsolete_files_test \
 	table_test \
-	block_fetcher_test \
 	delete_scheduler_test \
 	options_test \
 	options_settable_test \
@@ -600,7 +577,6 @@ TESTS = \
 	compaction_job_stats_test \
 	option_change_migration_test \
 	transaction_test \
-	transaction_lock_mgr_test \
 	ldb_cmd_test \
 	persistent_cache_test \
 	statistics_test \
@@ -621,10 +597,6 @@ TESTS = \
 	block_cache_tracer_test \
 	block_cache_trace_analyzer_test \
 	defer_test \
-	blob_file_addition_test \
-	blob_file_garbage_test \
-	timer_test \
-	db_with_timestamp_compaction_test \

 ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
 	TESTS += folly_synchronization_distributed_mutex_test
@@ -649,7 +621,6 @@ PARALLEL_TEST = \
 	persistent_cache_test \
 	table_test \
 	transaction_test \
-	transaction_lock_mgr_test \
 	write_prepared_transaction_test \
 	write_unprepared_transaction_test \

@@ -966,26 +937,24 @@ check: all
 	    $(MAKE) T="$$t" TMPD=$(TMPD) check_0;                       \
 	else                                                            \
 	    for t in $(TESTS); do                                       \
-	      echo "===== Running $$t (`date`)"; ./$$t || exit 1; done;          \
+	      echo "===== Running $$t"; ./$$t || exit 1; done;          \
 	fi
 	rm -rf $(TMPD)
 ifneq ($(PLATFORM), OS_AIX)
-	$(PYTHON) tools/check_all_python.py
+	python tools/check_all_python.py
 ifeq ($(filter -DROCKSDB_LITE,$(OPT)),)
-	$(PYTHON) tools/ldb_test.py
+	python tools/ldb_test.py
 	sh tools/rocksdb_dump_test.sh
 endif
 endif
-	$(MAKE) check-format
-	$(MAKE) check-buck-targets

 # TODO add ldb_tests
 check_some: $(SUBSET)
-	for t in $(SUBSET); do echo "===== Running $$t (`date`)"; ./$$t || exit 1; done
+	for t in $(SUBSET); do echo "===== Running $$t"; ./$$t || exit 1; done

 .PHONY: ldb_tests
 ldb_tests: ldb
-	$(PYTHON) tools/ldb_test.py
+	python tools/ldb_test.py

 crash_test: whitebox_crash_test blackbox_crash_test

@@ -994,31 +963,31 @@ crash_test_with_atomic_flush: whitebox_crash_test_with_atomic_flush blackbox_cra
 crash_test_with_txn: whitebox_crash_test_with_txn blackbox_crash_test_with_txn

 blackbox_crash_test: db_stress
-	$(PYTHON) -u tools/db_crashtest.py --simple blackbox $(CRASH_TEST_EXT_ARGS)
-	$(PYTHON) -u tools/db_crashtest.py blackbox $(CRASH_TEST_EXT_ARGS)
+	python -u tools/db_crashtest.py --simple blackbox $(CRASH_TEST_EXT_ARGS)
+	python -u tools/db_crashtest.py blackbox $(CRASH_TEST_EXT_ARGS)

 blackbox_crash_test_with_atomic_flush: db_stress
-	$(PYTHON) -u tools/db_crashtest.py --cf_consistency blackbox $(CRASH_TEST_EXT_ARGS)
+	python -u tools/db_crashtest.py --cf_consistency blackbox $(CRASH_TEST_EXT_ARGS)

 blackbox_crash_test_with_txn: db_stress
-	$(PYTHON) -u tools/db_crashtest.py --txn blackbox $(CRASH_TEST_EXT_ARGS)
+	python -u tools/db_crashtest.py --txn blackbox $(CRASH_TEST_EXT_ARGS)

 ifeq ($(CRASH_TEST_KILL_ODD),)
  CRASH_TEST_KILL_ODD=888887
 endif

 whitebox_crash_test: db_stress
-	$(PYTHON) -u tools/db_crashtest.py --simple whitebox --random_kill_odd \
+	python -u tools/db_crashtest.py --simple whitebox --random_kill_odd \
      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
-	$(PYTHON) -u tools/db_crashtest.py whitebox  --random_kill_odd \
+	python -u tools/db_crashtest.py whitebox  --random_kill_odd \
      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)

 whitebox_crash_test_with_atomic_flush: db_stress
-	$(PYTHON) -u tools/db_crashtest.py --cf_consistency whitebox  --random_kill_odd \
+	python -u tools/db_crashtest.py --cf_consistency whitebox  --random_kill_odd \
      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)

 whitebox_crash_test_with_txn: db_stress
-	$(PYTHON) -u tools/db_crashtest.py --txn whitebox --random_kill_odd \
+	python -u tools/db_crashtest.py --txn whitebox --random_kill_odd \
      $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)

 asan_check:
@@ -1087,7 +1056,7 @@ ifneq ($(PAR_TEST),)
 parloop:
 	ret_bad=0;							\
 	for t in $(PAR_TEST); do		\
-		echo "===== Running $$t in parallel $(NUM_PAR) (`date`)";\
+		echo "===== Running $$t in parallel $(NUM_PAR)";\
 		if [ $(db_test) -eq 1 ]; then \
 			seq $(J) | v="$$t" build_tools/gnu_parallel --gnu --plain 's=$(TMPD)/rdb-{};  export TEST_TMPDIR=$$s;' \
 				'timeout 2m ./db_test --gtest_filter=$$v >> $$s/log-{} 2>1'; \
@@ -1198,12 +1167,6 @@ tags0:
 format:
 	build_tools/format-diff.sh

-check-format:
-	build_tools/format-diff.sh -c
-
-check-buck-targets:
-	buckifier/check_buck_targets.sh
-
 package:
 	bash build_tools/make_package.sh $(SHARED_MAJOR).$(SHARED_MINOR)

@@ -1266,9 +1229,6 @@ db_repl_stress: tools/db_repl_stress.o $(LIBOBJECTS) $(TESTUTIL)

 arena_test: memory/arena_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
-	
-memkind_kmem_allocator_test: memory/memkind_kmem_allocator_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)	

 autovector_test: util/autovector_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
@@ -1327,9 +1287,6 @@ histogram_test: monitoring/histogram_test.o $(LIBOBJECTS) $(TESTHARNESS)
 thread_local_test: util/thread_local_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-work_queue_test: util/work_queue_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 corruption_test: db/corruption_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1345,12 +1302,6 @@ slice_transform_test: util/slice_transform_test.o $(LIBOBJECTS) $(TESTHARNESS)
 db_basic_test: db/db_basic_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-db_with_timestamp_basic_test: db/db_with_timestamp_basic_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-db_with_timestamp_compaction_test: db/db_with_timestamp_compaction_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 db_encryption_test: db/db_encryption_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1360,10 +1311,7 @@ db_test: db/db_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 db_test2: db/db_test2.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-db_logical_block_size_cache_test: db/db_logical_block_size_cache_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-db_blob_index_test: db/blob/db_blob_index_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+db_blob_index_test: db/db_blob_index_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 db_block_cache_test: db/db_block_cache_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1417,7 +1365,7 @@ db_statistics_test: db/db_statistics_test.o db/db_test_util.o $(LIBOBJECTS) $(TE
 db_write_test: db/db_write_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-error_handler_fs_test: db/error_handler_fs_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+error_handler_test: db/error_handler_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

 external_sst_file_basic_test: db/external_sst_file_basic_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
@@ -1530,9 +1478,6 @@ env_basic_test: env/env_basic_test.o $(LIBOBJECTS) $(TESTHARNESS)
 env_test: env/env_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-io_posix_test: env/io_posix_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 fault_injection_test: db/fault_injection_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1545,9 +1490,6 @@ delete_scheduler_test: file/delete_scheduler_test.o $(LIBOBJECTS) $(TESTHARNESS)
 filename_test: db/filename_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-random_access_file_reader_test: file/random_access_file_reader_test.o $(LIBOBJECTS) $(TESTHARNESS) $(TESTUTIL)
-	$(AM_LINK)
-
 file_reader_writer_test: util/file_reader_writer_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1569,9 +1511,6 @@ cleanable_test: table/cleanable_test.o $(LIBOBJECTS) $(TESTHARNESS)
 table_test: table/table_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-block_fetcher_test: table/block_fetcher_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 block_test: table/block_based/block_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1710,9 +1649,6 @@ write_callback_test: db/write_callback_test.o $(LIBOBJECTS) $(TESTHARNESS)
 heap_test: util/heap_test.o $(GTEST)
 	$(AM_LINK)

-transaction_lock_mgr_test: utilities/transactions/transaction_lock_mgr_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 transaction_test: utilities/transactions/transaction_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

@@ -1782,15 +1718,6 @@ block_cache_trace_analyzer_test: tools/block_cache_analyzer/block_cache_trace_an
 defer_test: util/defer_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)

-blob_file_addition_test: db/blob/blob_file_addition_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-blob_file_garbage_test: db/blob/blob_file_garbage_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
-timer_test: util/timer_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 #-------------------------------------------------
 # make install related stuff
 INSTALL_PATH ?= /usr/local
@@ -2141,7 +2068,7 @@ jtest_run:

 jtest: rocksdbjava
 	cd java;$(MAKE) sample;$(MAKE) test;
-	$(PYTHON) tools/check_all_python.py # TODO peterd: find a better place for this check in CI targets
+	python tools/check_all_python.py # TODO peterd: find a better place for this check in CI targets

 jdb_bench:
 	cd java;$(MAKE) db_bench;
@@ -24,7 +24,7 @@ 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.

-Design discussions are conducted in https://www.facebook.com/groups/rocksdb.dev/ and https://rocksdb.slack.com/
+Design discussions are conducted in https://www.facebook.com/groups/rocksdb.dev/

 ## License

@@ -112,14 +112,10 @@ ROCKSDB_OS_DEPS += ([(
 cpp_library(
    name = "rocksdb_lib",
    srcs = [
-        "cache/cache.cc",
        "cache/clock_cache.cc",
        "cache/lru_cache.cc",
        "cache/sharded_cache.cc",
        "db/arena_wrapped_db_iter.cc",
-        "db/blob/blob_file_addition.cc",
-        "db/blob/blob_file_garbage.cc",
-        "db/blob/blob_file_meta.cc",
        "db/builder.cc",
        "db/c.cc",
        "db/column_family.cc",
@@ -173,7 +169,6 @@ cpp_library(
        "db/trim_history_scheduler.cc",
        "db/version_builder.cc",
        "db/version_edit.cc",
-        "db/version_edit_handler.cc",
        "db/version_set.cc",
        "db/wal_manager.cc",
        "db/write_batch.cc",
@@ -205,7 +200,6 @@ cpp_library(
        "memory/arena.cc",
        "memory/concurrent_arena.cc",
        "memory/jemalloc_nodump_allocator.cc",
-        "memory/memkind_kmem_allocator.cc",
        "memtable/alloc_tracker.cc",
        "memtable/hash_linklist_rep.cc",
        "memtable/hash_skiplist_rep.cc",
@@ -231,18 +225,16 @@ cpp_library(
        "options/options.cc",
        "options/options_helper.cc",
        "options/options_parser.cc",
+        "options/options_sanity_check.cc",
        "port/port_posix.cc",
        "port/stack_trace.cc",
        "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",
        "table/block_based/block_based_table_reader.cc",
        "table/block_based/block_builder.cc",
-        "table/block_based/block_prefetcher.cc",
        "table/block_based/block_prefix_index.cc",
        "table/block_based/data_block_footer.cc",
        "table/block_based/data_block_hash_index.cc",
@@ -250,14 +242,9 @@ cpp_library(
        "table/block_based/filter_policy.cc",
        "table/block_based/flush_block_policy.cc",
        "table/block_based/full_filter_block.cc",
-        "table/block_based/hash_index_reader.cc",
        "table/block_based/index_builder.cc",
-        "table/block_based/index_reader_common.cc",
        "table/block_based/parsed_full_filter_block.cc",
        "table/block_based/partitioned_filter_block.cc",
-        "table/block_based/partitioned_index_iterator.cc",
-        "table/block_based/partitioned_index_reader.cc",
-        "table/block_based/reader_common.cc",
        "table/block_based/uncompression_dict_reader.cc",
        "table/block_fetcher.cc",
        "table/cuckoo/cuckoo_table_builder.cc",
@@ -380,7 +367,6 @@ cpp_library(
        "db/db_test_util.cc",
        "table/mock_table.cc",
        "test_util/fault_injection_test_env.cc",
-        "test_util/fault_injection_test_fs.cc",
        "test_util/testharness.cc",
        "test_util/testutil.cc",
        "tools/block_cache_analyzer/block_cache_trace_analyzer.cc",
@@ -437,10 +423,7 @@ cpp_library(
    os_deps = ROCKSDB_OS_DEPS,
    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
-    deps = [
-        ":rocksdb_lib",
-        ":rocksdb_test_lib",
-    ],
+    deps = [":rocksdb_lib"],
    external_deps = ROCKSDB_EXTERNAL_DEPS,
 )

@@ -494,20 +477,6 @@ ROCKS_TESTS = [
        [],
        [],
    ],
-    [
-        "blob_file_addition_test",
-        "db/blob/blob_file_addition_test.cc",
-        "serial",
-        [],
-        [],
-    ],
-    [
-        "blob_file_garbage_test",
-        "db/blob/blob_file_garbage_test.cc",
-        "serial",
-        [],
-        [],
-    ],
    [
        "block_based_filter_block_test",
        "table/block_based/block_based_filter_block_test.cc",
@@ -529,13 +498,6 @@ ROCKS_TESTS = [
        [],
        [],
    ],
-    [
-        "block_fetcher_test",
-        "table/block_fetcher_test.cc",
-        "serial",
-        [],
-        [],
-    ],
    [
        "block_test",
        "table/block_based/block_test.cc",
@@ -727,7 +689,7 @@ ROCKS_TESTS = [
    ],
    [
        "db_blob_index_test",
-        "db/blob/db_blob_index_test.cc",
+        "db/db_blob_index_test.cc",
        "serial",
        [],
        [],
@@ -823,13 +785,6 @@ ROCKS_TESTS = [
        [],
        [],
    ],
-    [
-        "db_logical_block_size_cache_test",
-        "db/db_logical_block_size_cache_test.cc",
-        "serial",
-        [],
-        [],
-    ],
    [
        "db_memtable_test",
        "db/db_memtable_test.cc",
@@ -935,20 +890,6 @@ ROCKS_TESTS = [
        [],
        [],
    ],
-    [
-        "db_with_timestamp_basic_test",
-        "db/db_with_timestamp_basic_test.cc",
-        "serial",
-        [],
-        [],
-    ],
-    [
-        "db_with_timestamp_compaction_test",
-        "db/db_with_timestamp_compaction_test.cc",
-        "serial",
-        [],
-        [],
-    ],
    [
        "db_write_test",
        "db/db_write_test.cc",
@@ -1020,8 +961,8 @@ ROCKS_TESTS = [
        [],
    ],
    [
-        "error_handler_fs_test",
-        "db/error_handler_fs_test.cc",
+        "error_handler_test",
+        "db/error_handler_test.cc",
        "serial",
        [],
        [],
@@ -1138,13 +1079,6 @@ ROCKS_TESTS = [
        [],
        [],
    ],
-    [
-        "io_posix_test",
-        "env/io_posix_test.cc",
-        "serial",
-        [],
-        [],
-    ],
    [
        "iostats_context_test",
        "monitoring/iostats_context_test.cc",
@@ -1187,13 +1121,6 @@ ROCKS_TESTS = [
        [],
        [],
    ],
-    [
-        "memkind_kmem_allocator_test",
-        "memory/memkind_kmem_allocator_test.cc",
-        "serial",
-        [],
-        [],
-    ],
    [
        "memory_test",
        "utilities/memory/memory_test.cc",
@@ -1327,13 +1254,6 @@ ROCKS_TESTS = [
        [],
        [],
    ],
-    [
-        "random_access_file_reader_test",
-        "file/random_access_file_reader_test.cc",
-        "serial",
-        [],
-        [],
-    ],
    [
        "random_test",
        "util/random_test.cc",
@@ -1481,13 +1401,6 @@ ROCKS_TESTS = [
        [],
        [],
    ],
-    [
-        "timer_test",
-        "util/timer_test.cc",
-        "serial",
-        [],
-        [],
-    ],
    [
        "trace_analyzer_test",
        "tools/trace_analyzer_test.cc",
@@ -1495,13 +1408,6 @@ ROCKS_TESTS = [
        [],
        [],
    ],
-    [
-        "transaction_lock_mgr_test",
-        "utilities/transactions/transaction_lock_mgr_test.cc",
-        "parallel",
-        [],
-        [],
-    ],
    [
        "transaction_test",
        "utilities/transactions/transaction_test.cc",
@@ -1551,13 +1457,6 @@ ROCKS_TESTS = [
        [],
        [],
    ],
-    [
-        "work_queue_test",
-        "util/work_queue_test.cc",
-        "serial",
-        [],
-        [],
-    ],
    [
        "write_batch_test",
        "db/write_batch_test.cc",
@@ -106,6 +106,3 @@ LzLabs is using RocksDB as a storage engine in their multi-database distributed
 ## Nebula Graph

 [Nebula Graph](https://github.com/vesoft-inc/nebula) is a distributed, scalable, lightning-fast, open source graph database capable of hosting super large scale graphs with dozens of billions of vertices (nodes) and trillions of edges, with milliseconds of latency.
-
-## YugabyteDB
-[YugabyteDB](https://www.yugabyte.com/) is an open source, high performance, distributed SQL database that uses RocksDB as its storage layer. For more information, please see https://github.com/yugabyte/yugabyte-db/.
@@ -1,6 +1,6 @@
 version: 1.0.{build}

-image: Visual Studio 2019
+image: Visual Studio 2017

 environment:
  JAVA_HOME: C:\Program Files\Java\jdk1.8.0
@@ -24,15 +24,6 @@ environment:
    - 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
-    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2019
-      CMAKE_GENERATOR: Visual Studio 16
-      CMAKE_PLATEFORM_NAME: x64
-      DEV_ENV: C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\Common7\IDE\devenv.com
-    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2019
-      CMAKE_GENERATOR: Visual Studio 16
-      CMAKE_PLATEFORM_NAME: x64
-      CMAKE_OPT: -DCMAKE_CXX_STANDARD=20
-      DEV_ENV: C:\Program Files (x86)\Microsoft Visual Studio\2019\Community\Common7\IDE\devenv.com

 install:
  - md %THIRDPARTY_HOME%
@@ -43,8 +34,7 @@ install:
  - 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%
+  - cmake -G "%CMAKE_GENERATOR%" ..
  - msbuild Snappy.sln /p:Configuration=Debug /p:Platform=x64
  - msbuild Snappy.sln /p:Configuration=Release /p:Platform=x64
  - echo "Building LZ4 dependency..."
@@ -67,8 +57,7 @@ install:
 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
+  - cmake -G "%CMAKE_GENERATOR%" -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE=1 -DSNAPPY=1 -DLZ4=1 -DZSTD=1 -DXPRESS=1 -DJNI=1 ..
  - cd ..

 build:
@@ -79,7 +68,7 @@ build:
 test:

 test_script:
-  - ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_with_timestamp_basic_test,db_test2,db_test,env_basic_test,env_test,db_merge_operand_test -Concurrency 8
+  - ps: build_tools\run_ci_db_test.ps1 -SuiteRun db_basic_test,db_test2,db_test,env_basic_test,env_test,db_merge_operand_test -Concurrency 8

 on_failure:
  - cmd: 7z a build-failed.zip %APPVEYOR_BUILD_FOLDER%\build\ && appveyor PushArtifact build-failed.zip
@@ -173,7 +173,7 @@ def generate_targets(repo_path, deps_map):
        src_mk.get("ANALYZER_LIB_SOURCES", [])
        + src_mk.get('STRESS_LIB_SOURCES', [])
        + ["test_util/testutil.cc"],
-        [":rocksdb_lib", ":rocksdb_test_lib"])
+        [":rocksdb_lib"])

    print("Extra dependencies:\n{0}".format(str(deps_map)))
    # test for every test we found in the Makefile
@@ -1,31 +0,0 @@
-#!/usr/bin/env bash
-# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-# If clang_format_diff.py command is not specfied, we assume we are able to
-# access directly without any path.
-
-TGT_DIFF=`git diff TARGETS | head -n 1`
-
-if [ ! -z "$TGT_DIFF" ]
-then
-  echo "TARGETS file has uncommitted changes. Skip this check."
-  exit 0
-fi
-
-echo Backup original TARGETS file.
-
-cp TARGETS TARGETS.bkp
-
-python buckifier/buckify_rocksdb.py
-
-TGT_DIFF=`git diff TARGETS | head -n 1`
-
-if [ -z "$TGT_DIFF" ]
-then
-  mv TARGETS.bkp TARGETS
-  exit 0
-else
-  echo "Please run 'python buckifier/buckify_rocksdb.py' to update TARGETS file."
-  echo "Do not manually update TARGETS file."
-  mv TARGETS.bkp TARGETS
-  exit 1
-fi
@@ -9,7 +9,6 @@
 #   PLATFORM_LDFLAGS            Linker flags
 #   JAVA_LDFLAGS                Linker flags for RocksDBJava
 #   JAVA_STATIC_LDFLAGS         Linker flags for RocksDBJava static build
-#   JAVAC_ARGS                  Arguments for javac
 #   PLATFORM_SHARED_EXT         Extension for shared libraries
 #   PLATFORM_SHARED_LDFLAGS     Flags for building shared library
 #   PLATFORM_SHARED_CFLAGS      Flags for compiling objects for shared library
@@ -28,7 +27,6 @@
 #       -DZSTD                      if the ZSTD library is present
 #       -DNUMA                      if the NUMA library is present
 #       -DTBB                       if the TBB library is present
-#       -DMEMKIND                   if the memkind library is present
 #
 # Using gflags in rocksdb:
 # Our project depends on gflags, which requires users to take some extra steps
@@ -241,15 +239,10 @@ esac
 PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS ${CXXFLAGS}"
 JAVA_LDFLAGS="$PLATFORM_LDFLAGS"
 JAVA_STATIC_LDFLAGS="$PLATFORM_LDFLAGS"
-JAVAC_ARGS="-source 7"

 if [ "$CROSS_COMPILE" = "true" -o "$FBCODE_BUILD" = "true" ]; then
    # Cross-compiling; do not try any compilation tests.
    # Also don't need any compilation tests if compiling on fbcode
-    if [ "$FBCODE_BUILD" = "true" ]; then
-      # Enable backtrace on fbcode since the necessary libraries are present
-      COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
-    fi
    true
 else
    if ! test $ROCKSDB_DISABLE_FALLOCATE; then
@@ -430,23 +423,7 @@ EOF
            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_MALLOC_USABLE_SIZE"
        fi
    fi
-    
-    if ! test $ROCKSDB_DISABLE_MEMKIND; then
-        # Test whether memkind library is installed
-        $CXX $CFLAGS $COMMON_FLAGS -lmemkind -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <memkind.h>
-          int main() {
-            memkind_malloc(MEMKIND_DAX_KMEM, 1024);
-            return 0;
-          }
-EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DMEMKIND"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lmemkind"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -lmemkind"
-        fi
-    fi
-    
+
    if ! test $ROCKSDB_DISABLE_PTHREAD_MUTEX_ADAPTIVE_NP; then
        # Test whether PTHREAD_MUTEX_ADAPTIVE_NP mutex type is available
        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
@@ -531,20 +508,6 @@ EOF
        fi
    fi

-    if ! test $ROCKSDB_DISABLE_AUXV_GETAUXVAL; then
-        # Test whether getauxval is supported
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <sys/auxv.h>
-          int main() {
-            uint64_t auxv = getauxval(AT_HWCAP);
-            (void)auxv;
-          }
-EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_AUXV_GETAUXVAL_PRESENT"
-        fi
-    fi
-
    if ! test $ROCKSDB_DISABLE_ALIGNED_NEW; then
        # Test whether c++17 aligned-new is supported
        $CXX $PLATFORM_CXXFLAGS -faligned-new -x c++ - -o /dev/null 2>/dev/null <<EOF
@@ -705,7 +668,6 @@ EOF
  fi
 fi

-
 if [ "$FBCODE_BUILD" != "true" -a "$PLATFORM" = OS_LINUX ]; then
  $CXX $COMMON_FLAGS $PLATFORM_SHARED_CFLAGS -x c++ -c - -o test_dl.o 2>/dev/null <<EOF
  void dummy_func() {}
@@ -734,7 +696,6 @@ echo "PLATFORM=$PLATFORM" >> "$OUTPUT"
 echo "PLATFORM_LDFLAGS=$PLATFORM_LDFLAGS" >> "$OUTPUT"
 echo "JAVA_LDFLAGS=$JAVA_LDFLAGS" >> "$OUTPUT"
 echo "JAVA_STATIC_LDFLAGS=$JAVA_STATIC_LDFLAGS" >> "$OUTPUT"
-echo "JAVAC_ARGS=$JAVAC_ARGS" >> "$OUTPUT"
 echo "VALGRIND_VER=$VALGRIND_VER" >> "$OUTPUT"
 echo "PLATFORM_CCFLAGS=$PLATFORM_CCFLAGS" >> "$OUTPUT"
 echo "PLATFORM_CXXFLAGS=$PLATFORM_CXXFLAGS" >> "$OUTPUT"
@@ -2,30 +2,6 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 # If clang_format_diff.py command is not specfied, we assume we are able to
 # access directly without any path.
-
-print_usage () {
-  echo "Usage:"
-  echo "format-diff.sh [OPTIONS]"
-  echo "-c: check only."
-  echo "-h: print this message."
-}
-
-while getopts ':ch' OPTION; do
-  case "$OPTION" in
-    c)
-      CHECK_ONLY=1
-      ;;
-    h)
-      print_usage
-      exit 1
-      ;;
-    ?)
-      print_usage
-      exit 1
-      ;;
-  esac
-done
-
 if [ -z $CLANG_FORMAT_DIFF ]
 then
 CLANG_FORMAT_DIFF="clang-format-diff.py"
@@ -34,28 +10,18 @@ fi
 # Check clang-format-diff.py
 if ! which $CLANG_FORMAT_DIFF &> /dev/null
 then
-  if [ ! -f ./clang-format-diff.py ]
-  then
-    echo "You didn't have clang-format-diff.py and/or clang-format available in your computer!"
-    echo "You can download clang-format-diff.py by running: "
-    echo "    curl --location http://goo.gl/iUW1u2 -o ${CLANG_FORMAT_DIFF}"
-    echo "You can download clang-format by running:"
-    echo "    brew install clang-format"
-    echo "  Or"
-    echo "    apt install clang-format"
-    echo "  This might work too:"
-    echo "    yum install git-clang-format"
-    echo "Then, move both files (i.e. ${CLANG_FORMAT_DIFF} and clang-format) to some directory within PATH=${PATH}"
-    echo "and make sure ${CLANG_FORMAT_DIFF} is executable."
-    exit 128
-  else
-    if [ -x ./clang-format-diff.py ]
-    then
-      PATH=$PATH:.
-    else
-      CLANG_FORMAT_DIFF="python ./clang-format-diff.py"
-    fi
-  fi
+  echo "You didn't have clang-format-diff.py and/or clang-format available in your computer!"
+  echo "You can download clang-format-diff.py by running: "
+  echo "    curl --location http://goo.gl/iUW1u2 -o ${CLANG_FORMAT_DIFF}"
+  echo "You can download clang-format by running:"
+  echo "    brew install clang-format"
+  echo "  Or"
+  echo "    apt install clang-format"
+  echo "  This might work too:"
+  echo "    yum install git-clang-format"
+  echo "Then, move both files (i.e. ${CLANG_FORMAT_DIFF} and clang-format) to some directory within PATH=${PATH}"
+  echo "and make sure ${CLANG_FORMAT_DIFF} is executable."
+  exit 128
 fi

 # Check argparse, a library that clang-format-diff.py requires.
@@ -121,10 +87,6 @@ if [ -z "$diffs" ]
 then
  echo "Nothing needs to be reformatted!"
  exit 0
-elif [ $CHECK_ONLY ]
-then
-  echo "Your change has unformatted code. Please run make format!"
-  exit 1
 fi

 # Highlight the insertion/deletion from the clang-format-diff.py's output
@@ -159,7 +121,7 @@ if [ -z "$uncommitted_code" ]
 then
  git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -i -p 1
 else
-  git diff -U0 HEAD | $CLANG_FORMAT_DIFF -i -p 1
+  git diff -U0 HEAD^ | $CLANG_FORMAT_DIFF -i -p 1
 fi
 echo "Files reformatted!"

@@ -5801,7 +5801,7 @@ sub workdir {
 		    . "-" . $self->seq();
 	    } else {
 		$workdir = $opt::workdir;
-		# Rsync treats /./ special. We don't want that
+		# Rsync treats /./ special. We dont want that
 		$workdir =~ s:/\./:/:g; # Remove /./
 		$workdir =~ s:/+$::; # Remove ending / if any
 		$workdir =~ s:^\./::g; # Remove starting ./ if any
@@ -818,8 +818,6 @@ run_format_compatible()
  rm -rf /dev/shm/rocksdb
  mkdir /dev/shm/rocksdb

-  export https_proxy="fwdproxy:8080"
-  
  tools/check_format_compatible.sh
 }

@@ -1,9 +1,9 @@
 #!/bin/bash
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-set -ex
+set -e

-ROCKSDB_VERSION="6.7.3"
-ZSTD_VERSION="1.4.4"
+ROCKSDB_VERSION="5.10.3"
+ZSTD_VERSION="1.1.3"

 echo "This script configures CentOS with everything needed to build and run RocksDB"

@@ -40,6 +40,5 @@ cd /usr/local/rocksdb
 chown -R vagrant:vagrant /usr/local/rocksdb/
 sudo -u vagrant make static_lib
 cd examples/
-sudo -u vagrant LD_LIBRARY_PATH=/usr/local/lib/ make all
-sudo -u vagrant LD_LIBRARY_PATH=/usr/local/lib/ ./c_simple_example
-
+sudo -u vagrant make all
+sudo -u vagrant ./c_simple_example
@@ -1,41 +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 "rocksdb/cache.h"
-
-#include "cache/lru_cache.h"
-#include "options/options_helper.h"
-#include "util/string_util.h"
-
-namespace ROCKSDB_NAMESPACE {
-Status Cache::CreateFromString(const ConfigOptions& /*opts*/,
-                               const std::string& value,
-                               std::shared_ptr<Cache>* result) {
-  Status status;
-  std::shared_ptr<Cache> cache;
-  if (value.find('=') == std::string::npos) {
-    cache = NewLRUCache(ParseSizeT(value));
-  } else {
-#ifndef ROCKSDB_LITE
-    LRUCacheOptions cache_opts;
-    if (!ParseOptionHelper(reinterpret_cast<char*>(&cache_opts),
-                           OptionType::kLRUCacheOptions, value)) {
-      status = Status::InvalidArgument("Invalid cache options");
-    }
-    cache = NewLRUCache(cache_opts);
-#else
-    status = Status::NotSupported("Cannot load cache in LITE mode ", value);
-#endif  //! ROCKSDB_LITE
-  }
-  if (status.ok()) {
-    result->swap(cache);
-  }
-  return status;
-}
-}  // namespace ROCKSDB_NAMESPACE
@@ -14,47 +14,34 @@ int main() {
 #include <stdio.h>
 #include <sys/types.h>
 #include <cinttypes>
-#include <limits>

 #include "port/port.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "util/coding.h"
 #include "util/gflags_compat.h"
-#include "util/hash.h"
 #include "util/mutexlock.h"
 #include "util/random.h"

 using GFLAGS_NAMESPACE::ParseCommandLineFlags;

-static constexpr uint32_t KiB = uint32_t{1} << 10;
-static constexpr uint32_t MiB = KiB << 10;
-static constexpr uint64_t GiB = MiB << 10;
+static const uint32_t KB = 1024;

-DEFINE_uint32(threads, 16, "Number of concurrent threads to run.");
-DEFINE_uint64(cache_size, 1 * GiB,
-              "Number of bytes to use as a cache of uncompressed data.");
-DEFINE_uint32(num_shard_bits, 6, "shard_bits.");
+DEFINE_int32(threads, 16, "Number of concurrent threads to run.");
+DEFINE_int64(cache_size, 8 * KB * KB,
+             "Number of bytes to use as a cache of uncompressed data.");
+DEFINE_int32(num_shard_bits, 4, "shard_bits.");

-DEFINE_double(resident_ratio, 0.25,
-              "Ratio of keys fitting in cache to keyspace.");
-DEFINE_uint64(ops_per_thread, 0,
-              "Number of operations per thread. (Default: 5 * keyspace size)");
-DEFINE_uint32(value_bytes, 8 * KiB, "Size of each value added.");
+DEFINE_int64(max_key, 1 * KB * KB * KB, "Max number of key to place in cache");
+DEFINE_uint64(ops_per_thread, 1200000, "Number of operations per thread.");

-DEFINE_uint32(skew, 5, "Degree of skew in key selection");
-DEFINE_bool(populate_cache, true, "Populate cache before operations");
-
-DEFINE_uint32(lookup_insert_percent, 87,
-              "Ratio of lookup (+ insert on not found) to total workload "
-              "(expressed as a percentage)");
-DEFINE_uint32(insert_percent, 2,
-              "Ratio of insert to total workload (expressed as a percentage)");
-DEFINE_uint32(lookup_percent, 10,
-              "Ratio of lookup to total workload (expressed as a percentage)");
-DEFINE_uint32(erase_percent, 1,
-              "Ratio of erase to total workload (expressed as a percentage)");
+DEFINE_bool(populate_cache, false, "Populate cache before operations");
+DEFINE_int32(insert_percent, 40,
+             "Ratio of insert to total workload (expressed as a percentage)");
+DEFINE_int32(lookup_percent, 50,
+             "Ratio of lookup to total workload (expressed as a percentage)");
+DEFINE_int32(erase_percent, 10,
+             "Ratio of erase to total workload (expressed as a percentage)");

 DEFINE_bool(use_clock_cache, false, "");

@@ -62,15 +49,21 @@ namespace ROCKSDB_NAMESPACE {

 class CacheBench;
 namespace {
+void deleter(const Slice& /*key*/, void* value) {
+    delete reinterpret_cast<char *>(value);
+}
+
 // State shared by all concurrent executions of the same benchmark.
 class SharedState {
 public:
  explicit SharedState(CacheBench* cache_bench)
      : cv_(&mu_),
+        num_threads_(FLAGS_threads),
        num_initialized_(0),
        start_(false),
        num_done_(0),
-        cache_bench_(cache_bench) {}
+        cache_bench_(cache_bench) {
+  }

  ~SharedState() {}

@@ -94,9 +87,13 @@ class SharedState {
    num_done_++;
  }

-  bool AllInitialized() const { return num_initialized_ >= FLAGS_threads; }
+  bool AllInitialized() const {
+    return num_initialized_ >= num_threads_;
+  }

-  bool AllDone() const { return num_done_ >= FLAGS_threads; }
+  bool AllDone() const {
+    return num_done_ >= num_threads_;
+  }

  void SetStart() {
    start_ = true;
@@ -110,6 +107,7 @@ class SharedState {
  port::Mutex mu_;
  port::CondVar cv_;

+  const uint64_t num_threads_;
  uint64_t num_initialized_;
  bool start_;
  uint64_t num_done_;
@@ -120,69 +118,17 @@ class SharedState {
 // Per-thread state for concurrent executions of the same benchmark.
 struct ThreadState {
  uint32_t tid;
-  Random64 rnd;
+  Random rnd;
  SharedState* shared;

  ThreadState(uint32_t index, SharedState* _shared)
      : tid(index), rnd(1000 + index), shared(_shared) {}
 };
-
-struct KeyGen {
-  char key_data[27];
-
-  Slice GetRand(Random64& rnd, uint64_t max_key) {
-    uint64_t raw = rnd.Next();
-    // Skew according to setting
-    for (uint32_t i = 0; i < FLAGS_skew; ++i) {
-      raw = std::min(raw, rnd.Next());
-    }
-    uint64_t key = fastrange64(raw, max_key);
-    // Variable size and alignment
-    size_t off = key % 8;
-    key_data[0] = char{42};
-    EncodeFixed64(key_data + 1, key);
-    key_data[9] = char{11};
-    EncodeFixed64(key_data + 10, key);
-    key_data[18] = char{4};
-    EncodeFixed64(key_data + 19, key);
-    return Slice(&key_data[off], sizeof(key_data) - off);
-  }
-};
-
-char* createValue(Random64& rnd) {
-  char* rv = new char[FLAGS_value_bytes];
-  // Fill with some filler data, and take some CPU time
-  for (uint32_t i = 0; i < FLAGS_value_bytes; i += 8) {
-    EncodeFixed64(rv + i, rnd.Next());
-  }
-  return rv;
-}
-
-void deleter(const Slice& /*key*/, void* value) {
-  delete[] static_cast<char*>(value);
-}
 }  // namespace

 class CacheBench {
-  static constexpr uint64_t kHundredthUint64 =
-      std::numeric_limits<uint64_t>::max() / 100U;
-
 public:
-  CacheBench()
-      : max_key_(static_cast<uint64_t>(FLAGS_cache_size / FLAGS_resident_ratio /
-                                       FLAGS_value_bytes)),
-        lookup_insert_threshold_(kHundredthUint64 *
-                                 FLAGS_lookup_insert_percent),
-        insert_threshold_(lookup_insert_threshold_ +
-                          kHundredthUint64 * FLAGS_insert_percent),
-        lookup_threshold_(insert_threshold_ +
-                          kHundredthUint64 * FLAGS_lookup_percent),
-        erase_threshold_(lookup_threshold_ +
-                         kHundredthUint64 * FLAGS_erase_percent) {
-    if (erase_threshold_ != 100U * kHundredthUint64) {
-      fprintf(stderr, "Percentages must add to 100.\n");
-      exit(1);
-    }
+  CacheBench() : num_threads_(FLAGS_threads) {
    if (FLAGS_use_clock_cache) {
      cache_ = NewClockCache(FLAGS_cache_size, FLAGS_num_shard_bits);
      if (!cache_) {
@@ -192,19 +138,18 @@ class CacheBench {
    } else {
      cache_ = NewLRUCache(FLAGS_cache_size, FLAGS_num_shard_bits);
    }
-    if (FLAGS_ops_per_thread == 0) {
-      FLAGS_ops_per_thread = 5 * max_key_;
-    }
  }

  ~CacheBench() {}

  void PopulateCache() {
-    Random64 rnd(1);
-    KeyGen keygen;
-    for (uint64_t i = 0; i < 2 * FLAGS_cache_size; i += FLAGS_value_bytes) {
-      cache_->Insert(keygen.GetRand(rnd, max_key_), createValue(rnd),
-                     FLAGS_value_bytes, &deleter);
+    Random rnd(1);
+    for (int64_t i = 0; i < FLAGS_cache_size; i++) {
+      uint64_t rand_key = rnd.Next() % FLAGS_max_key;
+      // Cast uint64* to be char*, data would be copied to cache
+      Slice key(reinterpret_cast<char*>(&rand_key), 8);
+      // do insert
+      cache_->Insert(key, new char[10], 1, &deleter);
    }
  }

@@ -213,10 +158,10 @@ class CacheBench {

    PrintEnv();
    SharedState shared(this);
-    std::vector<std::unique_ptr<ThreadState> > threads(FLAGS_threads);
-    for (uint32_t i = 0; i < FLAGS_threads; i++) {
-      threads[i].reset(new ThreadState(i, &shared));
-      env->StartThread(ThreadBody, threads[i].get());
+    std::vector<ThreadState*> threads(num_threads_);
+    for (uint32_t i = 0; i < num_threads_; i++) {
+      threads[i] = new ThreadState(i, &shared);
+      env->StartThread(ThreadBody, threads[i]);
    }
    {
      MutexLock l(shared.GetMutex());
@@ -247,15 +192,10 @@ class CacheBench {

 private:
  std::shared_ptr<Cache> cache_;
-  const uint64_t max_key_;
-  // Cumulative thresholds in the space of a random uint64_t
-  const uint64_t lookup_insert_threshold_;
-  const uint64_t insert_threshold_;
-  const uint64_t lookup_threshold_;
-  const uint64_t erase_threshold_;
+  uint32_t num_threads_;

  static void ThreadBody(void* v) {
-    ThreadState* thread = static_cast<ThreadState*>(v);
+    ThreadState* thread = reinterpret_cast<ThreadState*>(v);
    SharedState* shared = thread->shared;

    {
@@ -280,78 +220,40 @@ class CacheBench {
  }

  void OperateCache(ThreadState* thread) {
-    // To use looked-up values
-    uint64_t result = 0;
-    // To hold handles for a non-trivial amount of time
-    Cache::Handle* handle = nullptr;
-    KeyGen gen;
    for (uint64_t i = 0; i < FLAGS_ops_per_thread; i++) {
-      Slice key = gen.GetRand(thread->rnd, max_key_);
-      uint64_t random_op = thread->rnd.Next();
-      if (random_op < lookup_insert_threshold_) {
-        if (handle) {
-          cache_->Release(handle);
-          handle = nullptr;
-        }
-        // do lookup
-        handle = cache_->Lookup(key);
-        if (handle) {
-          // do something with the data
-          result += NPHash64(static_cast<char*>(cache_->Value(handle)),
-                             FLAGS_value_bytes);
-        } else {
-          // do insert
-          cache_->Insert(key, createValue(thread->rnd), FLAGS_value_bytes,
-                         &deleter, &handle);
-        }
-      } else if (random_op < insert_threshold_) {
-        if (handle) {
-          cache_->Release(handle);
-          handle = nullptr;
-        }
+      uint64_t rand_key = thread->rnd.Next() % FLAGS_max_key;
+      // Cast uint64* to be char*, data would be copied to cache
+      Slice key(reinterpret_cast<char*>(&rand_key), 8);
+      int32_t prob_op = thread->rnd.Uniform(100);
+      if (prob_op >= 0 && prob_op < FLAGS_insert_percent) {
        // do insert
-        cache_->Insert(key, createValue(thread->rnd), FLAGS_value_bytes,
-                       &deleter, &handle);
-      } else if (random_op < lookup_threshold_) {
+        cache_->Insert(key, new char[10], 1, &deleter);
+      } else if (prob_op -= FLAGS_insert_percent &&
+                 prob_op < FLAGS_lookup_percent) {
+        // do lookup
+        auto handle = cache_->Lookup(key);
        if (handle) {
          cache_->Release(handle);
-          handle = nullptr;
        }
-        // do lookup
-        handle = cache_->Lookup(key);
-        if (handle) {
-          // do something with the data
-          result += NPHash64(static_cast<char*>(cache_->Value(handle)),
-                             FLAGS_value_bytes);
-        }
-      } else if (random_op < erase_threshold_) {
+      } else if (prob_op -= FLAGS_lookup_percent &&
+                 prob_op < FLAGS_erase_percent) {
        // do erase
        cache_->Erase(key);
-      } else {
-        // Should be extremely unlikely (noop)
-        assert(random_op >= kHundredthUint64 * 100U);
      }
    }
-    if (handle) {
-      cache_->Release(handle);
-      handle = nullptr;
-    }
  }

  void PrintEnv() const {
    printf("RocksDB version     : %d.%d\n", kMajorVersion, kMinorVersion);
-    printf("Number of threads   : %u\n", FLAGS_threads);
+    printf("Number of threads   : %d\n", FLAGS_threads);
    printf("Ops per thread      : %" PRIu64 "\n", FLAGS_ops_per_thread);
    printf("Cache size          : %" PRIu64 "\n", FLAGS_cache_size);
-    printf("Num shard bits      : %u\n", FLAGS_num_shard_bits);
-    printf("Max key             : %" PRIu64 "\n", max_key_);
-    printf("Resident ratio      : %g\n", FLAGS_resident_ratio);
-    printf("Skew degree         : %u\n", FLAGS_skew);
-    printf("Populate cache      : %d\n", int{FLAGS_populate_cache});
-    printf("Lookup+Insert pct   : %u%%\n", FLAGS_lookup_insert_percent);
-    printf("Insert percentage   : %u%%\n", FLAGS_insert_percent);
-    printf("Lookup percentage   : %u%%\n", FLAGS_lookup_percent);
-    printf("Erase percentage    : %u%%\n", FLAGS_erase_percent);
+    printf("Num shard bits      : %d\n", FLAGS_num_shard_bits);
+    printf("Max key             : %" PRIu64 "\n", FLAGS_max_key);
+    printf("Populate cache      : %d\n", FLAGS_populate_cache);
+    printf("Insert percentage   : %d%%\n", FLAGS_insert_percent);
+    printf("Lookup percentage   : %d%%\n", FLAGS_lookup_percent);
+    printf("Erase percentage    : %d%%\n", FLAGS_erase_percent);
    printf("----------------------------\n");
  }
 };
@@ -368,8 +270,6 @@ int main(int argc, char** argv) {
  ROCKSDB_NAMESPACE::CacheBench bench;
  if (FLAGS_populate_cache) {
    bench.PopulateCache();
-    printf("Population complete\n");
-    printf("----------------------------\n");
  }
  if (bench.Run()) {
    return 0;
@@ -341,8 +341,7 @@ class ClockCacheShard final : public CacheShard {
  CacheHandle* Insert(const Slice& key, uint32_t hash, void* value,
                      size_t change,
                      void (*deleter)(const Slice& key, void* value),
-                      bool hold_reference, CleanupContext* context,
-                      bool* overwritten);
+                      bool hold_reference, CleanupContext* context);

  // Guards list_, head_, and recycle_. In addition, updating table_ also has
  // to hold the mutex, to avoid the cache being in inconsistent state.
@@ -565,8 +564,7 @@ void ClockCacheShard::SetStrictCapacityLimit(bool strict_capacity_limit) {
 CacheHandle* ClockCacheShard::Insert(
    const Slice& key, uint32_t hash, void* value, size_t charge,
    void (*deleter)(const Slice& key, void* value), bool hold_reference,
-    CleanupContext* context, bool* overwritten) {
-  assert(overwritten != nullptr && *overwritten == false);
+    CleanupContext* context) {
  size_t total_charge =
      CacheHandle::CalcTotalCharge(key, charge, metadata_charge_policy_);
  MutexLock l(&mutex_);
@@ -599,7 +597,6 @@ CacheHandle* ClockCacheShard::Insert(
  handle->flags.store(flags, std::memory_order_relaxed);
  HashTable::accessor accessor;
  if (table_.find(accessor, CacheKey(key, hash))) {
-    *overwritten = true;
    CacheHandle* existing_handle = accessor->second;
    table_.erase(accessor);
    UnsetInCache(existing_handle, context);
@@ -622,9 +619,8 @@ Status ClockCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
  char* key_data = new char[key.size()];
  memcpy(key_data, key.data(), key.size());
  Slice key_copy(key_data, key.size());
-  bool overwritten = false;
  CacheHandle* handle = Insert(key_copy, hash, value, charge, deleter,
-                               out_handle != nullptr, &context, &overwritten);
+                               out_handle != nullptr, &context);
  Status s;
  if (out_handle != nullptr) {
    if (handle == nullptr) {
@@ -633,10 +629,6 @@ Status ClockCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
      *out_handle = reinterpret_cast<Cache::Handle*>(handle);
    }
  }
-  if (overwritten) {
-    assert(s.ok());
-    s = Status::OkOverwritten();
-  }
  Cleanup(context);
  return s;
 }
@@ -386,7 +386,6 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
      LRUHandle* old = table_.Insert(e);
      usage_ += total_charge;
      if (old != nullptr) {
-        s = Status::OkOverwritten();
        assert(old->InCache());
        old->SetInCache(false);
        if (!old->HasRefs()) {
@@ -1,7 +0,0 @@
-macro(get_cxx_std_flags FLAGS_VARIABLE)
-  if( CMAKE_CXX_STANDARD_REQUIRED )
-    set(${FLAGS_VARIABLE} ${CMAKE_CXX${CMAKE_CXX_STANDARD}_STANDARD_COMPILE_OPTION})
-  else()
-    set(${FLAGS_VARIABLE} ${CMAKE_CXX${CMAKE_CXX_STANDARD}_EXTENSION_COMPILE_OPTION})
-  endif()
-endmacro()
@@ -17,19 +17,16 @@ if [ -d /mnt/gvfs/third-party -a -z "$CXX" ]; then
 else
  GCOV=$(which gcov)
 fi
-echo -e "Using $GCOV"

 COVERAGE_DIR="$PWD/COVERAGE_REPORT"
 mkdir -p $COVERAGE_DIR

 # Find all gcno files to generate the coverage report

-PYTHON=${1:-`which python`}
-echo -e "Using $PYTHON"
 GCNO_FILES=`find $ROOT -name "*.gcno"`
 $GCOV --preserve-paths --relative-only --no-output $GCNO_FILES 2>/dev/null |
  # Parse the raw gcov report to more human readable form.
-  $PYTHON $ROOT/coverage/parse_gcov_output.py |
+  python $ROOT/coverage/parse_gcov_output.py |
  # Write the output to both stdout and report file.
  tee $COVERAGE_DIR/coverage_report_all.txt &&
 echo -e "Generated coverage report for all files: $COVERAGE_DIR/coverage_report_all.txt\n"
@@ -44,7 +41,7 @@ RECENT_REPORT=$COVERAGE_DIR/coverage_report_recent.txt

 echo -e "Recently updated files: $LATEST_FILES\n" > $RECENT_REPORT
 $GCOV --preserve-paths --relative-only --no-output $GCNO_FILES 2>/dev/null |
-  $PYTHON $ROOT/coverage/parse_gcov_output.py -interested-files $LATEST_FILES |
+  python $ROOT/coverage/parse_gcov_output.py -interested-files $LATEST_FILES |
  tee -a $RECENT_REPORT &&
 echo -e "Generated coverage report for recently updated files: $RECENT_REPORT\n"

@@ -1,12 +1,10 @@
-#!/usr/bin/env python
+#!/usr/bin/env python2
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-
-from __future__ import print_function
-
-import optparse
 import re
 import sys

+from optparse import OptionParser
+
 # the gcov report follows certain pattern. Each file will have two lines
 # of report, from which we can extract the file name, total lines and coverage
 # percentage.
@@ -50,7 +48,7 @@ def parse_gcov_report(gcov_input):
 def get_option_parser():
    usage = "Parse the gcov output and generate more human-readable code " +\
            "coverage report."
-    parser = optparse.OptionParser(usage)
+    parser = OptionParser(usage)

    parser.add_option(
        "--interested-files", "-i",
@@ -75,8 +73,8 @@ def display_file_coverage(per_file_coverage, total_coverage):
    header_template = \
        "%" + str(max_file_name_length) + "s\t%s\t%s"
    separator = "-" * (max_file_name_length + 10 + 20)
-    print(header_template % ("Filename", "Coverage", "Lines"))  # noqa: E999 T25377293 Grandfathered in
-    print(separator)
+    print header_template % ("Filename", "Coverage", "Lines")  # noqa: E999 T25377293 Grandfathered in
+    print separator

    # -- Print body
    # template for printing coverage report for each file.
@@ -84,12 +82,12 @@ def display_file_coverage(per_file_coverage, total_coverage):

    for fname, coverage_info in per_file_coverage.items():
        coverage, lines = coverage_info
-        print(record_template % (fname, coverage, lines))
+        print record_template % (fname, coverage, lines)

    # -- Print footer
    if total_coverage:
-        print(separator)
-        print(record_template % ("Total", total_coverage[0], total_coverage[1]))
+        print separator
+        print record_template % ("Total", total_coverage[0], total_coverage[1])

 def report_coverage():
    parser = get_option_parser()
@@ -113,7 +111,7 @@ def report_coverage():
        total_coverage = None

    if not len(per_file_coverage):
-        print("Cannot find coverage info for the given files.", file=sys.stderr)
+        print >> sys.stderr, "Cannot find coverage info for the given files."
        return
    display_file_coverage(per_file_coverage, total_coverage)

@@ -75,7 +75,7 @@ Status ArenaWrappedDBIter::Refresh() {

    InternalIterator* internal_iter = db_impl_->NewInternalIterator(
        read_options_, cfd_, sv, &arena_, db_iter_->GetRangeDelAggregator(),
-        latest_seq, /* allow_unprepared_value */ true);
+        latest_seq);
    SetIterUnderDBIter(internal_iter);
  } else {
    db_iter_->set_sequence(latest_seq);
@@ -51,8 +51,6 @@ class ArenaWrappedDBIter : public Iterator {
  bool Valid() const override { return db_iter_->Valid(); }
  void SeekToFirst() override { db_iter_->SeekToFirst(); }
  void SeekToLast() override { db_iter_->SeekToLast(); }
-  // 'target' does not contain timestamp, even if user timestamp feature is
-  // enabled.
  void Seek(const Slice& target) override { db_iter_->Seek(target); }
  void SeekForPrev(const Slice& target) override {
    db_iter_->SeekForPrev(target);
@@ -62,7 +60,6 @@ class ArenaWrappedDBIter : public Iterator {
  Slice key() const override { return db_iter_->key(); }
  Slice value() const override { return db_iter_->value(); }
  Status status() const override { return db_iter_->status(); }
-  Slice timestamp() const override { return db_iter_->timestamp(); }
  bool IsBlob() const { return db_iter_->IsBlob(); }

  Status GetProperty(std::string prop_name, std::string* prop) override;
@@ -1,16 +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 <cstdint>
-
-#include "rocksdb/rocksdb_namespace.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-constexpr uint64_t kInvalidBlobFileNumber = 0;
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,154 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#include "db/blob/blob_file_addition.h"
-
-#include <ostream>
-#include <sstream>
-
-#include "logging/event_logger.h"
-#include "rocksdb/slice.h"
-#include "rocksdb/status.h"
-#include "test_util/sync_point.h"
-#include "util/coding.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-// Tags for custom fields. Note that these get persisted in the manifest,
-// so existing tags should not be modified.
-enum BlobFileAddition::CustomFieldTags : uint32_t {
-  kEndMarker,
-
-  // Add forward compatible fields here
-
-  /////////////////////////////////////////////////////////////////////
-
-  kForwardIncompatibleMask = 1 << 6,
-
-  // Add forward incompatible fields here
-};
-
-void BlobFileAddition::EncodeTo(std::string* output) const {
-  PutVarint64(output, blob_file_number_);
-  PutVarint64(output, total_blob_count_);
-  PutVarint64(output, total_blob_bytes_);
-  PutLengthPrefixedSlice(output, checksum_method_);
-  PutLengthPrefixedSlice(output, checksum_value_);
-
-  // Encode any custom fields here. The format to use is a Varint32 tag (see
-  // CustomFieldTags above) followed by a length prefixed slice. Unknown custom
-  // fields will be ignored during decoding unless they're in the forward
-  // incompatible range.
-
-  TEST_SYNC_POINT_CALLBACK("BlobFileAddition::EncodeTo::CustomFields", output);
-
-  PutVarint32(output, kEndMarker);
-}
-
-Status BlobFileAddition::DecodeFrom(Slice* input) {
-  constexpr char class_name[] = "BlobFileAddition";
-
-  if (!GetVarint64(input, &blob_file_number_)) {
-    return Status::Corruption(class_name, "Error decoding blob file number");
-  }
-
-  if (!GetVarint64(input, &total_blob_count_)) {
-    return Status::Corruption(class_name, "Error decoding total blob count");
-  }
-
-  if (!GetVarint64(input, &total_blob_bytes_)) {
-    return Status::Corruption(class_name, "Error decoding total blob bytes");
-  }
-
-  Slice checksum_method;
-  if (!GetLengthPrefixedSlice(input, &checksum_method)) {
-    return Status::Corruption(class_name, "Error decoding checksum method");
-  }
-  checksum_method_ = checksum_method.ToString();
-
-  Slice checksum_value;
-  if (!GetLengthPrefixedSlice(input, &checksum_value)) {
-    return Status::Corruption(class_name, "Error decoding checksum value");
-  }
-  checksum_value_ = checksum_value.ToString();
-
-  while (true) {
-    uint32_t custom_field_tag = 0;
-    if (!GetVarint32(input, &custom_field_tag)) {
-      return Status::Corruption(class_name, "Error decoding custom field tag");
-    }
-
-    if (custom_field_tag == kEndMarker) {
-      break;
-    }
-
-    if (custom_field_tag & kForwardIncompatibleMask) {
-      return Status::Corruption(
-          class_name, "Forward incompatible custom field encountered");
-    }
-
-    Slice custom_field_value;
-    if (!GetLengthPrefixedSlice(input, &custom_field_value)) {
-      return Status::Corruption(class_name,
-                                "Error decoding custom field value");
-    }
-  }
-
-  return Status::OK();
-}
-
-std::string BlobFileAddition::DebugString() const {
-  std::ostringstream oss;
-
-  oss << *this;
-
-  return oss.str();
-}
-
-std::string BlobFileAddition::DebugJSON() const {
-  JSONWriter jw;
-
-  jw << *this;
-
-  jw.EndObject();
-
-  return jw.Get();
-}
-
-bool operator==(const BlobFileAddition& lhs, const BlobFileAddition& rhs) {
-  return lhs.GetBlobFileNumber() == rhs.GetBlobFileNumber() &&
-         lhs.GetTotalBlobCount() == rhs.GetTotalBlobCount() &&
-         lhs.GetTotalBlobBytes() == rhs.GetTotalBlobBytes() &&
-         lhs.GetChecksumMethod() == rhs.GetChecksumMethod() &&
-         lhs.GetChecksumValue() == rhs.GetChecksumValue();
-}
-
-bool operator!=(const BlobFileAddition& lhs, const BlobFileAddition& rhs) {
-  return !(lhs == rhs);
-}
-
-std::ostream& operator<<(std::ostream& os,
-                         const BlobFileAddition& blob_file_addition) {
-  os << "blob_file_number: " << blob_file_addition.GetBlobFileNumber()
-     << " total_blob_count: " << blob_file_addition.GetTotalBlobCount()
-     << " total_blob_bytes: " << blob_file_addition.GetTotalBlobBytes()
-     << " checksum_method: " << blob_file_addition.GetChecksumMethod()
-     << " checksum_value: " << blob_file_addition.GetChecksumValue();
-
-  return os;
-}
-
-JSONWriter& operator<<(JSONWriter& jw,
-                       const BlobFileAddition& blob_file_addition) {
-  jw << "BlobFileNumber" << blob_file_addition.GetBlobFileNumber()
-     << "TotalBlobCount" << blob_file_addition.GetTotalBlobCount()
-     << "TotalBlobBytes" << blob_file_addition.GetTotalBlobBytes()
-     << "ChecksumMethod" << blob_file_addition.GetChecksumMethod()
-     << "ChecksumValue" << blob_file_addition.GetChecksumValue();
-
-  return jw;
-}
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,67 +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 <cassert>
-#include <cstdint>
-#include <iosfwd>
-#include <string>
-
-#include "db/blob/blob_constants.h"
-#include "rocksdb/rocksdb_namespace.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class JSONWriter;
-class Slice;
-class Status;
-
-class BlobFileAddition {
- public:
-  BlobFileAddition() = default;
-
-  BlobFileAddition(uint64_t blob_file_number, uint64_t total_blob_count,
-                   uint64_t total_blob_bytes, std::string checksum_method,
-                   std::string checksum_value)
-      : blob_file_number_(blob_file_number),
-        total_blob_count_(total_blob_count),
-        total_blob_bytes_(total_blob_bytes),
-        checksum_method_(std::move(checksum_method)),
-        checksum_value_(std::move(checksum_value)) {
-    assert(checksum_method_.empty() == checksum_value_.empty());
-  }
-
-  uint64_t GetBlobFileNumber() const { return blob_file_number_; }
-  uint64_t GetTotalBlobCount() const { return total_blob_count_; }
-  uint64_t GetTotalBlobBytes() const { return total_blob_bytes_; }
-  const std::string& GetChecksumMethod() const { return checksum_method_; }
-  const std::string& GetChecksumValue() const { return checksum_value_; }
-
-  void EncodeTo(std::string* output) const;
-  Status DecodeFrom(Slice* input);
-
-  std::string DebugString() const;
-  std::string DebugJSON() const;
-
- private:
-  enum CustomFieldTags : uint32_t;
-
-  uint64_t blob_file_number_ = kInvalidBlobFileNumber;
-  uint64_t total_blob_count_ = 0;
-  uint64_t total_blob_bytes_ = 0;
-  std::string checksum_method_;
-  std::string checksum_value_;
-};
-
-bool operator==(const BlobFileAddition& lhs, const BlobFileAddition& rhs);
-bool operator!=(const BlobFileAddition& lhs, const BlobFileAddition& rhs);
-
-std::ostream& operator<<(std::ostream& os,
-                         const BlobFileAddition& blob_file_addition);
-JSONWriter& operator<<(JSONWriter& jw,
-                       const BlobFileAddition& blob_file_addition);
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,206 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#include "db/blob/blob_file_addition.h"
-
-#include <cstdint>
-#include <cstring>
-#include <string>
-
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "util/coding.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class BlobFileAdditionTest : public testing::Test {
- public:
-  static void TestEncodeDecode(const BlobFileAddition& blob_file_addition) {
-    std::string encoded;
-    blob_file_addition.EncodeTo(&encoded);
-
-    BlobFileAddition decoded;
-    Slice input(encoded);
-    ASSERT_OK(decoded.DecodeFrom(&input));
-
-    ASSERT_EQ(blob_file_addition, decoded);
-  }
-};
-
-TEST_F(BlobFileAdditionTest, Empty) {
-  BlobFileAddition blob_file_addition;
-
-  ASSERT_EQ(blob_file_addition.GetBlobFileNumber(), kInvalidBlobFileNumber);
-  ASSERT_EQ(blob_file_addition.GetTotalBlobCount(), 0);
-  ASSERT_EQ(blob_file_addition.GetTotalBlobBytes(), 0);
-  ASSERT_TRUE(blob_file_addition.GetChecksumMethod().empty());
-  ASSERT_TRUE(blob_file_addition.GetChecksumValue().empty());
-
-  TestEncodeDecode(blob_file_addition);
-}
-
-TEST_F(BlobFileAdditionTest, NonEmpty) {
-  constexpr uint64_t blob_file_number = 123;
-  constexpr uint64_t total_blob_count = 2;
-  constexpr uint64_t total_blob_bytes = 123456;
-  const std::string checksum_method("SHA1");
-  const std::string checksum_value("bdb7f34a59dfa1592ce7f52e99f98c570c525cbd");
-
-  BlobFileAddition blob_file_addition(blob_file_number, total_blob_count,
-                                      total_blob_bytes, checksum_method,
-                                      checksum_value);
-
-  ASSERT_EQ(blob_file_addition.GetBlobFileNumber(), blob_file_number);
-  ASSERT_EQ(blob_file_addition.GetTotalBlobCount(), total_blob_count);
-  ASSERT_EQ(blob_file_addition.GetTotalBlobBytes(), total_blob_bytes);
-  ASSERT_EQ(blob_file_addition.GetChecksumMethod(), checksum_method);
-  ASSERT_EQ(blob_file_addition.GetChecksumValue(), checksum_value);
-
-  TestEncodeDecode(blob_file_addition);
-}
-
-TEST_F(BlobFileAdditionTest, DecodeErrors) {
-  std::string str;
-  Slice slice(str);
-
-  BlobFileAddition blob_file_addition;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "blob file number"));
-  }
-
-  constexpr uint64_t blob_file_number = 123;
-  PutVarint64(&str, blob_file_number);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "total blob count"));
-  }
-
-  constexpr uint64_t total_blob_count = 4567;
-  PutVarint64(&str, total_blob_count);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "total blob bytes"));
-  }
-
-  constexpr uint64_t total_blob_bytes = 12345678;
-  PutVarint64(&str, total_blob_bytes);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "checksum method"));
-  }
-
-  constexpr char checksum_method[] = "SHA1";
-  PutLengthPrefixedSlice(&str, checksum_method);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "checksum value"));
-  }
-
-  constexpr char checksum_value[] = "bdb7f34a59dfa1592ce7f52e99f98c570c525cbd";
-  PutLengthPrefixedSlice(&str, checksum_value);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "custom field tag"));
-  }
-
-  constexpr uint32_t custom_tag = 2;
-  PutVarint32(&str, custom_tag);
-  slice = str;
-
-  {
-    const Status s = blob_file_addition.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "custom field value"));
-  }
-}
-
-TEST_F(BlobFileAdditionTest, ForwardCompatibleCustomField) {
-  SyncPoint::GetInstance()->SetCallBack(
-      "BlobFileAddition::EncodeTo::CustomFields", [&](void* arg) {
-        std::string* output = static_cast<std::string*>(arg);
-
-        constexpr uint32_t forward_compatible_tag = 2;
-        PutVarint32(output, forward_compatible_tag);
-
-        PutLengthPrefixedSlice(output, "deadbeef");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  constexpr uint64_t blob_file_number = 678;
-  constexpr uint64_t total_blob_count = 9999;
-  constexpr uint64_t total_blob_bytes = 100000000;
-  const std::string checksum_method("CRC32");
-  const std::string checksum_value("3d87ff57");
-
-  BlobFileAddition blob_file_addition(blob_file_number, total_blob_count,
-                                      total_blob_bytes, checksum_method,
-                                      checksum_value);
-
-  TestEncodeDecode(blob_file_addition);
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-TEST_F(BlobFileAdditionTest, ForwardIncompatibleCustomField) {
-  SyncPoint::GetInstance()->SetCallBack(
-      "BlobFileAddition::EncodeTo::CustomFields", [&](void* arg) {
-        std::string* output = static_cast<std::string*>(arg);
-
-        constexpr uint32_t forward_incompatible_tag = (1 << 6) + 1;
-        PutVarint32(output, forward_incompatible_tag);
-
-        PutLengthPrefixedSlice(output, "foobar");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  constexpr uint64_t blob_file_number = 456;
-  constexpr uint64_t total_blob_count = 100;
-  constexpr uint64_t total_blob_bytes = 2000000;
-  const std::string checksum_method("CRC32B");
-  const std::string checksum_value("6dbdf23a");
-
-  BlobFileAddition blob_file_addition(blob_file_number, total_blob_count,
-                                      total_blob_bytes, checksum_method,
-                                      checksum_value);
-
-  std::string encoded;
-  blob_file_addition.EncodeTo(&encoded);
-
-  BlobFileAddition decoded_blob_file_addition;
-  Slice input(encoded);
-  const Status s = decoded_blob_file_addition.DecodeFrom(&input);
-
-  ASSERT_TRUE(s.IsCorruption());
-  ASSERT_TRUE(std::strstr(s.getState(), "Forward incompatible"));
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-}  // namespace ROCKSDB_NAMESPACE
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
@@ -1,134 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#include "db/blob/blob_file_garbage.h"
-
-#include <ostream>
-#include <sstream>
-
-#include "logging/event_logger.h"
-#include "rocksdb/slice.h"
-#include "rocksdb/status.h"
-#include "test_util/sync_point.h"
-#include "util/coding.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-// Tags for custom fields. Note that these get persisted in the manifest,
-// so existing tags should not be modified.
-enum BlobFileGarbage::CustomFieldTags : uint32_t {
-  kEndMarker,
-
-  // Add forward compatible fields here
-
-  /////////////////////////////////////////////////////////////////////
-
-  kForwardIncompatibleMask = 1 << 6,
-
-  // Add forward incompatible fields here
-};
-
-void BlobFileGarbage::EncodeTo(std::string* output) const {
-  PutVarint64(output, blob_file_number_);
-  PutVarint64(output, garbage_blob_count_);
-  PutVarint64(output, garbage_blob_bytes_);
-
-  // Encode any custom fields here. The format to use is a Varint32 tag (see
-  // CustomFieldTags above) followed by a length prefixed slice. Unknown custom
-  // fields will be ignored during decoding unless they're in the forward
-  // incompatible range.
-
-  TEST_SYNC_POINT_CALLBACK("BlobFileGarbage::EncodeTo::CustomFields", output);
-
-  PutVarint32(output, kEndMarker);
-}
-
-Status BlobFileGarbage::DecodeFrom(Slice* input) {
-  constexpr char class_name[] = "BlobFileGarbage";
-
-  if (!GetVarint64(input, &blob_file_number_)) {
-    return Status::Corruption(class_name, "Error decoding blob file number");
-  }
-
-  if (!GetVarint64(input, &garbage_blob_count_)) {
-    return Status::Corruption(class_name, "Error decoding garbage blob count");
-  }
-
-  if (!GetVarint64(input, &garbage_blob_bytes_)) {
-    return Status::Corruption(class_name, "Error decoding garbage blob bytes");
-  }
-
-  while (true) {
-    uint32_t custom_field_tag = 0;
-    if (!GetVarint32(input, &custom_field_tag)) {
-      return Status::Corruption(class_name, "Error decoding custom field tag");
-    }
-
-    if (custom_field_tag == kEndMarker) {
-      break;
-    }
-
-    if (custom_field_tag & kForwardIncompatibleMask) {
-      return Status::Corruption(
-          class_name, "Forward incompatible custom field encountered");
-    }
-
-    Slice custom_field_value;
-    if (!GetLengthPrefixedSlice(input, &custom_field_value)) {
-      return Status::Corruption(class_name,
-                                "Error decoding custom field value");
-    }
-  }
-
-  return Status::OK();
-}
-
-std::string BlobFileGarbage::DebugString() const {
-  std::ostringstream oss;
-
-  oss << *this;
-
-  return oss.str();
-}
-
-std::string BlobFileGarbage::DebugJSON() const {
-  JSONWriter jw;
-
-  jw << *this;
-
-  jw.EndObject();
-
-  return jw.Get();
-}
-
-bool operator==(const BlobFileGarbage& lhs, const BlobFileGarbage& rhs) {
-  return lhs.GetBlobFileNumber() == rhs.GetBlobFileNumber() &&
-         lhs.GetGarbageBlobCount() == rhs.GetGarbageBlobCount() &&
-         lhs.GetGarbageBlobBytes() == rhs.GetGarbageBlobBytes();
-}
-
-bool operator!=(const BlobFileGarbage& lhs, const BlobFileGarbage& rhs) {
-  return !(lhs == rhs);
-}
-
-std::ostream& operator<<(std::ostream& os,
-                         const BlobFileGarbage& blob_file_garbage) {
-  os << "blob_file_number: " << blob_file_garbage.GetBlobFileNumber()
-     << " garbage_blob_count: " << blob_file_garbage.GetGarbageBlobCount()
-     << " garbage_blob_bytes: " << blob_file_garbage.GetGarbageBlobBytes();
-
-  return os;
-}
-
-JSONWriter& operator<<(JSONWriter& jw,
-                       const BlobFileGarbage& blob_file_garbage) {
-  jw << "BlobFileNumber" << blob_file_garbage.GetBlobFileNumber()
-     << "GarbageBlobCount" << blob_file_garbage.GetGarbageBlobCount()
-     << "GarbageBlobBytes" << blob_file_garbage.GetGarbageBlobBytes();
-
-  return jw;
-}
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,57 +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 <cstdint>
-#include <iosfwd>
-#include <string>
-
-#include "db/blob/blob_constants.h"
-#include "rocksdb/rocksdb_namespace.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class JSONWriter;
-class Slice;
-class Status;
-
-class BlobFileGarbage {
- public:
-  BlobFileGarbage() = default;
-
-  BlobFileGarbage(uint64_t blob_file_number, uint64_t garbage_blob_count,
-                  uint64_t garbage_blob_bytes)
-      : blob_file_number_(blob_file_number),
-        garbage_blob_count_(garbage_blob_count),
-        garbage_blob_bytes_(garbage_blob_bytes) {}
-
-  uint64_t GetBlobFileNumber() const { return blob_file_number_; }
-  uint64_t GetGarbageBlobCount() const { return garbage_blob_count_; }
-  uint64_t GetGarbageBlobBytes() const { return garbage_blob_bytes_; }
-
-  void EncodeTo(std::string* output) const;
-  Status DecodeFrom(Slice* input);
-
-  std::string DebugString() const;
-  std::string DebugJSON() const;
-
- private:
-  enum CustomFieldTags : uint32_t;
-
-  uint64_t blob_file_number_ = kInvalidBlobFileNumber;
-  uint64_t garbage_blob_count_ = 0;
-  uint64_t garbage_blob_bytes_ = 0;
-};
-
-bool operator==(const BlobFileGarbage& lhs, const BlobFileGarbage& rhs);
-bool operator!=(const BlobFileGarbage& lhs, const BlobFileGarbage& rhs);
-
-std::ostream& operator<<(std::ostream& os,
-                         const BlobFileGarbage& blob_file_garbage);
-JSONWriter& operator<<(JSONWriter& jw,
-                       const BlobFileGarbage& blob_file_garbage);
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,173 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#include "db/blob/blob_file_garbage.h"
-
-#include <cstdint>
-#include <cstring>
-#include <string>
-
-#include "test_util/sync_point.h"
-#include "test_util/testharness.h"
-#include "util/coding.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class BlobFileGarbageTest : public testing::Test {
- public:
-  static void TestEncodeDecode(const BlobFileGarbage& blob_file_garbage) {
-    std::string encoded;
-    blob_file_garbage.EncodeTo(&encoded);
-
-    BlobFileGarbage decoded;
-    Slice input(encoded);
-    ASSERT_OK(decoded.DecodeFrom(&input));
-
-    ASSERT_EQ(blob_file_garbage, decoded);
-  }
-};
-
-TEST_F(BlobFileGarbageTest, Empty) {
-  BlobFileGarbage blob_file_garbage;
-
-  ASSERT_EQ(blob_file_garbage.GetBlobFileNumber(), kInvalidBlobFileNumber);
-  ASSERT_EQ(blob_file_garbage.GetGarbageBlobCount(), 0);
-  ASSERT_EQ(blob_file_garbage.GetGarbageBlobBytes(), 0);
-
-  TestEncodeDecode(blob_file_garbage);
-}
-
-TEST_F(BlobFileGarbageTest, NonEmpty) {
-  constexpr uint64_t blob_file_number = 123;
-  constexpr uint64_t garbage_blob_count = 1;
-  constexpr uint64_t garbage_blob_bytes = 9876;
-
-  BlobFileGarbage blob_file_garbage(blob_file_number, garbage_blob_count,
-                                    garbage_blob_bytes);
-
-  ASSERT_EQ(blob_file_garbage.GetBlobFileNumber(), blob_file_number);
-  ASSERT_EQ(blob_file_garbage.GetGarbageBlobCount(), garbage_blob_count);
-  ASSERT_EQ(blob_file_garbage.GetGarbageBlobBytes(), garbage_blob_bytes);
-
-  TestEncodeDecode(blob_file_garbage);
-}
-
-TEST_F(BlobFileGarbageTest, DecodeErrors) {
-  std::string str;
-  Slice slice(str);
-
-  BlobFileGarbage blob_file_garbage;
-
-  {
-    const Status s = blob_file_garbage.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "blob file number"));
-  }
-
-  constexpr uint64_t blob_file_number = 123;
-  PutVarint64(&str, blob_file_number);
-  slice = str;
-
-  {
-    const Status s = blob_file_garbage.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "garbage blob count"));
-  }
-
-  constexpr uint64_t garbage_blob_count = 4567;
-  PutVarint64(&str, garbage_blob_count);
-  slice = str;
-
-  {
-    const Status s = blob_file_garbage.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "garbage blob bytes"));
-  }
-
-  constexpr uint64_t garbage_blob_bytes = 12345678;
-  PutVarint64(&str, garbage_blob_bytes);
-  slice = str;
-
-  {
-    const Status s = blob_file_garbage.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "custom field tag"));
-  }
-
-  constexpr uint32_t custom_tag = 2;
-  PutVarint32(&str, custom_tag);
-  slice = str;
-
-  {
-    const Status s = blob_file_garbage.DecodeFrom(&slice);
-    ASSERT_TRUE(s.IsCorruption());
-    ASSERT_TRUE(std::strstr(s.getState(), "custom field value"));
-  }
-}
-
-TEST_F(BlobFileGarbageTest, ForwardCompatibleCustomField) {
-  SyncPoint::GetInstance()->SetCallBack(
-      "BlobFileGarbage::EncodeTo::CustomFields", [&](void* arg) {
-        std::string* output = static_cast<std::string*>(arg);
-
-        constexpr uint32_t forward_compatible_tag = 2;
-        PutVarint32(output, forward_compatible_tag);
-
-        PutLengthPrefixedSlice(output, "deadbeef");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  constexpr uint64_t blob_file_number = 678;
-  constexpr uint64_t garbage_blob_count = 9999;
-  constexpr uint64_t garbage_blob_bytes = 100000000;
-
-  BlobFileGarbage blob_file_garbage(blob_file_number, garbage_blob_count,
-                                    garbage_blob_bytes);
-
-  TestEncodeDecode(blob_file_garbage);
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-TEST_F(BlobFileGarbageTest, ForwardIncompatibleCustomField) {
-  SyncPoint::GetInstance()->SetCallBack(
-      "BlobFileGarbage::EncodeTo::CustomFields", [&](void* arg) {
-        std::string* output = static_cast<std::string*>(arg);
-
-        constexpr uint32_t forward_incompatible_tag = (1 << 6) + 1;
-        PutVarint32(output, forward_incompatible_tag);
-
-        PutLengthPrefixedSlice(output, "foobar");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  constexpr uint64_t blob_file_number = 456;
-  constexpr uint64_t garbage_blob_count = 100;
-  constexpr uint64_t garbage_blob_bytes = 2000000;
-
-  BlobFileGarbage blob_file_garbage(blob_file_number, garbage_blob_count,
-                                    garbage_blob_bytes);
-
-  std::string encoded;
-  blob_file_garbage.EncodeTo(&encoded);
-
-  BlobFileGarbage decoded_blob_file_addition;
-  Slice input(encoded);
-  const Status s = decoded_blob_file_addition.DecodeFrom(&input);
-
-  ASSERT_TRUE(s.IsCorruption());
-  ASSERT_TRUE(std::strstr(s.getState(), "Forward incompatible"));
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-}  // namespace ROCKSDB_NAMESPACE
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
@@ -1,48 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-
-#include "db/blob/blob_file_meta.h"
-
-#include <ostream>
-#include <sstream>
-
-namespace ROCKSDB_NAMESPACE {
-
-std::string SharedBlobFileMetaData::DebugString() const {
-  std::ostringstream oss;
-  oss << (*this);
-
-  return oss.str();
-}
-
-std::ostream& operator<<(std::ostream& os,
-                         const SharedBlobFileMetaData& shared_meta) {
-  os << "blob_file_number: " << shared_meta.GetBlobFileNumber()
-     << " total_blob_count: " << shared_meta.GetTotalBlobCount()
-     << " total_blob_bytes: " << shared_meta.GetTotalBlobBytes()
-     << " checksum_method: " << shared_meta.GetChecksumMethod()
-     << " checksum_value: " << shared_meta.GetChecksumValue();
-
-  return os;
-}
-
-std::string BlobFileMetaData::DebugString() const {
-  std::ostringstream oss;
-  oss << (*this);
-
-  return oss.str();
-}
-
-std::ostream& operator<<(std::ostream& os, const BlobFileMetaData& meta) {
-  const auto& shared_meta = meta.GetSharedMeta();
-  assert(shared_meta);
-
-  os << (*shared_meta) << " garbage_blob_count: " << meta.GetGarbageBlobCount()
-     << " garbage_blob_bytes: " << meta.GetGarbageBlobBytes();
-
-  return os;
-}
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -1,154 +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 "rocksdb/rocksdb_namespace.h"
-
-#include <cassert>
-#include <iosfwd>
-#include <memory>
-#include <string>
-
-namespace ROCKSDB_NAMESPACE {
-
-// SharedBlobFileMetaData represents the immutable part of blob files' metadata,
-// like the blob file number, total number and size of blobs, or checksum
-// method and value. There is supposed to be one object of this class per blob
-// file (shared across all versions that include the blob file in question);
-// hence, the type is neither copyable nor movable. A blob file can be marked
-// obsolete when the corresponding SharedBlobFileMetaData object is destroyed.
-
-class SharedBlobFileMetaData {
- public:
-  static std::shared_ptr<SharedBlobFileMetaData> Create(
-      uint64_t blob_file_number, uint64_t total_blob_count,
-      uint64_t total_blob_bytes, std::string checksum_method,
-      std::string checksum_value) {
-    return std::shared_ptr<SharedBlobFileMetaData>(new SharedBlobFileMetaData(
-        blob_file_number, total_blob_count, total_blob_bytes,
-        std::move(checksum_method), std::move(checksum_value)));
-  }
-
-  template <typename Deleter>
-  static std::shared_ptr<SharedBlobFileMetaData> Create(
-      uint64_t blob_file_number, uint64_t total_blob_count,
-      uint64_t total_blob_bytes, std::string checksum_method,
-      std::string checksum_value, Deleter deleter) {
-    return std::shared_ptr<SharedBlobFileMetaData>(
-        new SharedBlobFileMetaData(blob_file_number, total_blob_count,
-                                   total_blob_bytes, std::move(checksum_method),
-                                   std::move(checksum_value)),
-        deleter);
-  }
-
-  SharedBlobFileMetaData(const SharedBlobFileMetaData&) = delete;
-  SharedBlobFileMetaData& operator=(const SharedBlobFileMetaData&) = delete;
-
-  SharedBlobFileMetaData(SharedBlobFileMetaData&&) = delete;
-  SharedBlobFileMetaData& operator=(SharedBlobFileMetaData&&) = delete;
-
-  uint64_t GetBlobFileNumber() const { return blob_file_number_; }
-  uint64_t GetTotalBlobCount() const { return total_blob_count_; }
-  uint64_t GetTotalBlobBytes() const { return total_blob_bytes_; }
-  const std::string& GetChecksumMethod() const { return checksum_method_; }
-  const std::string& GetChecksumValue() const { return checksum_value_; }
-
-  std::string DebugString() const;
-
- private:
-  SharedBlobFileMetaData(uint64_t blob_file_number, uint64_t total_blob_count,
-                         uint64_t total_blob_bytes, std::string checksum_method,
-                         std::string checksum_value)
-      : blob_file_number_(blob_file_number),
-        total_blob_count_(total_blob_count),
-        total_blob_bytes_(total_blob_bytes),
-        checksum_method_(std::move(checksum_method)),
-        checksum_value_(std::move(checksum_value)) {
-    assert(checksum_method_.empty() == checksum_value_.empty());
-  }
-
-  uint64_t blob_file_number_;
-  uint64_t total_blob_count_;
-  uint64_t total_blob_bytes_;
-  std::string checksum_method_;
-  std::string checksum_value_;
-};
-
-std::ostream& operator<<(std::ostream& os,
-                         const SharedBlobFileMetaData& shared_meta);
-
-// BlobFileMetaData contains the part of the metadata for blob files that can
-// vary across versions, like the amount of garbage in the blob file. In
-// addition, BlobFileMetaData objects point to and share the ownership of the
-// SharedBlobFileMetaData object for the corresponding blob file. Similarly to
-// SharedBlobFileMetaData, BlobFileMetaData are not copyable or movable. They
-// are meant to be jointly owned by the versions in which the blob file has the
-// same (immutable *and* mutable) state.
-
-class BlobFileMetaData {
- public:
-  static std::shared_ptr<BlobFileMetaData> Create(
-      std::shared_ptr<SharedBlobFileMetaData> shared_meta,
-      uint64_t garbage_blob_count, uint64_t garbage_blob_bytes) {
-    return std::shared_ptr<BlobFileMetaData>(new BlobFileMetaData(
-        std::move(shared_meta), garbage_blob_count, garbage_blob_bytes));
-  }
-
-  BlobFileMetaData(const BlobFileMetaData&) = delete;
-  BlobFileMetaData& operator=(const BlobFileMetaData&) = delete;
-
-  BlobFileMetaData(BlobFileMetaData&&) = delete;
-  BlobFileMetaData& operator=(BlobFileMetaData&&) = delete;
-
-  const std::shared_ptr<SharedBlobFileMetaData>& GetSharedMeta() const {
-    return shared_meta_;
-  }
-
-  uint64_t GetBlobFileNumber() const {
-    assert(shared_meta_);
-    return shared_meta_->GetBlobFileNumber();
-  }
-  uint64_t GetTotalBlobCount() const {
-    assert(shared_meta_);
-    return shared_meta_->GetTotalBlobCount();
-  }
-  uint64_t GetTotalBlobBytes() const {
-    assert(shared_meta_);
-    return shared_meta_->GetTotalBlobBytes();
-  }
-  const std::string& GetChecksumMethod() const {
-    assert(shared_meta_);
-    return shared_meta_->GetChecksumMethod();
-  }
-  const std::string& GetChecksumValue() const {
-    assert(shared_meta_);
-    return shared_meta_->GetChecksumValue();
-  }
-
-  uint64_t GetGarbageBlobCount() const { return garbage_blob_count_; }
-  uint64_t GetGarbageBlobBytes() const { return garbage_blob_bytes_; }
-
-  std::string DebugString() const;
-
- private:
-  BlobFileMetaData(std::shared_ptr<SharedBlobFileMetaData> shared_meta,
-                   uint64_t garbage_blob_count, uint64_t garbage_blob_bytes)
-      : shared_meta_(std::move(shared_meta)),
-        garbage_blob_count_(garbage_blob_count),
-        garbage_blob_bytes_(garbage_blob_bytes) {
-    assert(shared_meta_);
-    assert(garbage_blob_count_ <= shared_meta_->GetTotalBlobCount());
-    assert(garbage_blob_bytes_ <= shared_meta_->GetTotalBlobBytes());
-  }
-
-  std::shared_ptr<SharedBlobFileMetaData> shared_meta_;
-  uint64_t garbage_blob_count_;
-  uint64_t garbage_blob_bytes_;
-};
-
-std::ostream& operator<<(std::ostream& os, const BlobFileMetaData& meta);
-
-}  // namespace ROCKSDB_NAMESPACE
@@ -81,11 +81,10 @@ Status BuildTable(
    SnapshotChecker* snapshot_checker, const CompressionType compression,
    uint64_t sample_for_compression, const CompressionOptions& compression_opts,
    bool paranoid_file_checks, InternalStats* internal_stats,
-    TableFileCreationReason reason, IOStatus* io_status,
-    EventLogger* event_logger, int job_id, const Env::IOPriority io_priority,
-    TableProperties* table_properties, int level, const uint64_t creation_time,
-    const uint64_t oldest_key_time, Env::WriteLifeTimeHint write_hint,
-    const uint64_t file_creation_time) {
+    TableFileCreationReason reason, EventLogger* event_logger, int job_id,
+    const Env::IOPriority io_priority, TableProperties* table_properties,
+    int level, const uint64_t creation_time, const uint64_t oldest_key_time,
+    Env::WriteLifeTimeHint write_hint, const uint64_t file_creation_time) {
  assert((column_family_id ==
          TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
         column_family_name.empty());
@@ -134,7 +133,7 @@ Status BuildTable(

      file_writer.reset(new WritableFileWriter(
          std::move(file), fname, file_options, env, ioptions.statistics,
-          ioptions.listeners, ioptions.file_checksum_gen_factory));
+          ioptions.listeners, ioptions.sst_file_checksum_func));

      builder = NewTableBuilder(
          ioptions, mutable_cf_options, internal_comparator,
@@ -183,15 +182,14 @@ Status BuildTable(
    }

    // Finish and check for builder errors
-    bool empty = builder->IsEmpty();
+    tp = builder->GetTableProperties();
+    bool empty = builder->NumEntries() == 0 && tp.num_range_deletions == 0;
    s = c_iter.status();
-    TEST_SYNC_POINT("BuildTable:BeforeFinishBuildTable");
    if (!s.ok() || empty) {
      builder->Abandon();
    } else {
      s = builder->Finish();
    }
-    *io_status = builder->io_status();

    if (s.ok() && !empty) {
      uint64_t file_size = builder->FileSize();
@@ -202,28 +200,20 @@ Status BuildTable(
      if (table_properties) {
        *table_properties = tp;
      }
+      // Add the checksum information to file metadata.
+      meta->file_checksum = builder->GetFileChecksum();
+      meta->file_checksum_func_name = builder->GetFileChecksumFuncName();
    }
    delete builder;

    // Finish and check for file errors
    if (s.ok() && !empty) {
      StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
-      *io_status = file_writer->Sync(ioptions.use_fsync);
+      s = file_writer->Sync(ioptions.use_fsync);
    }
-    if (io_status->ok() && !empty) {
-      *io_status = file_writer->Close();
+    if (s.ok() && !empty) {
+      s = file_writer->Close();
    }
-    if (io_status->ok() && !empty) {
-      // Add the checksum information to file metadata.
-      meta->file_checksum = file_writer->GetFileChecksum();
-      meta->file_checksum_func_name = file_writer->GetFileChecksumFuncName();
-    }
-
-    if (!io_status->ok()) {
-      s = *io_status;
-    }
-
-    // TODO Also check the IO status when create the Iterator.

    if (s.ok() && !empty) {
      // Verify that the table is usable
@@ -240,8 +230,7 @@ Status BuildTable(
                                      : internal_stats->GetFileReadHist(0),
          TableReaderCaller::kFlush, /*arena=*/nullptr,
          /*skip_filter=*/false, level, /*smallest_compaction_key=*/nullptr,
-          /*largest_compaction_key*/ nullptr,
-          /*allow_unprepared_value*/ false));
+          /*largest_compaction_key*/ nullptr));
      s = it->status();
      if (s.ok() && paranoid_file_checks) {
        for (it->SeekToFirst(); it->Valid(); it->Next()) {
@@ -78,7 +78,7 @@ extern Status BuildTable(
    const uint64_t sample_for_compression,
    const CompressionOptions& compression_opts, bool paranoid_file_checks,
    InternalStats* internal_stats, TableFileCreationReason reason,
-    IOStatus* io_status, EventLogger* event_logger = nullptr, int job_id = 0,
+    EventLogger* event_logger = nullptr, int job_id = 0,
    const Env::IOPriority io_priority = Env::IO_HIGH,
    TableProperties* table_properties = nullptr, int level = -1,
    const uint64_t creation_time = 0, const uint64_t oldest_key_time = 0,
@@ -4441,16 +4441,6 @@ uint64_t rocksdb_approximate_memory_usage_get_cache_total(
  return memory_usage->cache_total;
 }

-void rocksdb_options_set_dump_malloc_stats(rocksdb_options_t* opt,
-                                           unsigned char val) {
-  opt->rep.dump_malloc_stats = val;
-}
-
-void rocksdb_options_set_memtable_whole_key_filtering(rocksdb_options_t* opt,
-                                                      unsigned char val) {
-  opt->rep.memtable_whole_key_filtering = val;
-}
-
 // deletes container with memory usage estimates
 void rocksdb_approximate_memory_usage_destroy(rocksdb_memory_usage_t* usage) {
  delete usage;
@@ -471,17 +471,6 @@ void SuperVersionUnrefHandle(void* ptr) {
 }
 }  // anonymous namespace

-std::vector<std::string> ColumnFamilyData::GetDbPaths() const {
-  std::vector<std::string> paths;
-  paths.reserve(ioptions_.cf_paths.size());
-  for (const DbPath& db_path : ioptions_.cf_paths) {
-    paths.emplace_back(db_path.path);
-  }
-  return paths;
-}
-
-const uint32_t ColumnFamilyData::kDummyColumnFamilyDataId = port::kMaxUint32;
-
 ColumnFamilyData::ColumnFamilyData(
    uint32_t id, const std::string& name, Version* _dummy_versions,
    Cache* _table_cache, WriteBufferManager* write_buffer_manager,
@@ -518,23 +507,7 @@ ColumnFamilyData::ColumnFamilyData(
      queued_for_compaction_(false),
      prev_compaction_needed_bytes_(0),
      allow_2pc_(db_options.allow_2pc),
-      last_memtable_id_(0),
-      db_paths_registered_(false) {
-  if (id_ != kDummyColumnFamilyDataId) {
-    // TODO(cc): RegisterDbPaths can be expensive, considering moving it
-    // outside of this constructor which might be called with db mutex held.
-    // TODO(cc): considering using ioptions_.fs, currently some tests rely on
-    // EnvWrapper, that's the main reason why we use env here.
-    Status s = ioptions_.env->RegisterDbPaths(GetDbPaths());
-    if (s.ok()) {
-      db_paths_registered_ = true;
-    } else {
-      ROCKS_LOG_ERROR(
-          ioptions_.info_log,
-          "Failed to register data paths of column family (id: %d, name: %s)",
-          id_, name_.c_str());
-    }
-  }
+      last_memtable_id_(0) {
  Ref();

  // Convert user defined table properties collector factories to internal ones.
@@ -628,18 +601,6 @@ ColumnFamilyData::~ColumnFamilyData() {
  for (MemTable* m : to_delete) {
    delete m;
  }
-
-  if (db_paths_registered_) {
-    // TODO(cc): considering using ioptions_.fs, currently some tests rely on
-    // EnvWrapper, that's the main reason why we use env here.
-    Status s = ioptions_.env->UnregisterDbPaths(GetDbPaths());
-    if (!s.ok()) {
-      ROCKS_LOG_ERROR(
-          ioptions_.info_log,
-          "Failed to unregister data paths of column family (id: %d, name: %s)",
-          id_, name_.c_str());
-    }
-  }
 }

 bool ColumnFamilyData::UnrefAndTryDelete() {
@@ -1360,7 +1321,7 @@ Env::WriteLifeTimeHint ColumnFamilyData::CalculateSSTWriteHint(int level) {
 }

 Status ColumnFamilyData::AddDirectories(
-    std::map<std::string, std::shared_ptr<FSDirectory>>* created_dirs) {
+    std::map<std::string, std::shared_ptr<Directory>>* created_dirs) {
  Status s;
  assert(created_dirs != nullptr);
  assert(data_dirs_.empty());
@@ -1368,8 +1329,8 @@ Status ColumnFamilyData::AddDirectories(
    auto existing_dir = created_dirs->find(p.path);

    if (existing_dir == created_dirs->end()) {
-      std::unique_ptr<FSDirectory> path_directory;
-      s = DBImpl::CreateAndNewDirectory(ioptions_.fs, p.path, &path_directory);
+      std::unique_ptr<Directory> path_directory;
+      s = DBImpl::CreateAndNewDirectory(ioptions_.env, p.path, &path_directory);
      if (!s.ok()) {
        return s;
      }
@@ -1384,7 +1345,7 @@ Status ColumnFamilyData::AddDirectories(
  return s;
 }

-FSDirectory* ColumnFamilyData::GetDataDir(size_t path_id) const {
+Directory* ColumnFamilyData::GetDataDir(size_t path_id) const {
  if (data_dirs_.empty()) {
    return nullptr;
  }
@@ -1397,21 +1358,20 @@ ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
                                 const ImmutableDBOptions* db_options,
                                 const FileOptions& file_options,
                                 Cache* table_cache,
-                                 WriteBufferManager* _write_buffer_manager,
-                                 WriteController* _write_controller,
+                                 WriteBufferManager* write_buffer_manager,
+                                 WriteController* write_controller,
                                 BlockCacheTracer* const block_cache_tracer)
    : max_column_family_(0),
      dummy_cfd_(new ColumnFamilyData(
-          ColumnFamilyData::kDummyColumnFamilyDataId, "", nullptr, nullptr,
-          nullptr, ColumnFamilyOptions(), *db_options, file_options, nullptr,
-          block_cache_tracer)),
+          0, "", nullptr, nullptr, nullptr, ColumnFamilyOptions(), *db_options,
+          file_options, nullptr, block_cache_tracer)),
      default_cfd_cache_(nullptr),
      db_name_(dbname),
      db_options_(db_options),
      file_options_(file_options),
      table_cache_(table_cache),
-      write_buffer_manager_(_write_buffer_manager),
-      write_controller_(_write_controller),
+      write_buffer_manager_(write_buffer_manager),
+      write_controller_(write_controller),
      block_cache_tracer_(block_cache_tracer) {
  // initialize linked list
  dummy_cfd_->prev_ = dummy_cfd_;
@@ -500,15 +500,14 @@ class ColumnFamilyData {
  // created_dirs remembers directory created, so that we don't need to call
  // the same data creation operation again.
  Status AddDirectories(
-      std::map<std::string, std::shared_ptr<FSDirectory>>* created_dirs);
+      std::map<std::string, std::shared_ptr<Directory>>* created_dirs);

-  FSDirectory* GetDataDir(size_t path_id) const;
+  Directory* GetDataDir(size_t path_id) const;

  ThreadLocalPtr* TEST_GetLocalSV() { return local_sv_.get(); }

 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,
@@ -518,8 +517,6 @@ class ColumnFamilyData {
                   ColumnFamilySet* column_family_set,
                   BlockCacheTracer* const block_cache_tracer);

-  std::vector<std::string> GetDbPaths() const;
-
  uint32_t id_;
  const std::string name_;
  Version* dummy_versions_;  // Head of circular doubly-linked list of versions.
@@ -595,9 +592,7 @@ class ColumnFamilyData {
  std::atomic<uint64_t> last_memtable_id_;

  // Directories corresponding to cf_paths.
-  std::vector<std::shared_ptr<FSDirectory>> data_dirs_;
-
-  bool db_paths_registered_;
+  std::vector<std::shared_ptr<Directory>> data_dirs_;
 };

 // ColumnFamilySet has interesting thread-safety requirements
@@ -647,8 +642,8 @@ class ColumnFamilySet {
  ColumnFamilySet(const std::string& dbname,
                  const ImmutableDBOptions* db_options,
                  const FileOptions& file_options, Cache* table_cache,
-                  WriteBufferManager* _write_buffer_manager,
-                  WriteController* _write_controller,
+                  WriteBufferManager* write_buffer_manager,
+                  WriteController* write_controller,
                  BlockCacheTracer* const block_cache_tracer);
  ~ColumnFamilySet();

@@ -678,10 +673,6 @@ class ColumnFamilySet {

  Cache* get_table_cache() { return table_cache_; }

-  WriteBufferManager* write_buffer_manager() { return write_buffer_manager_; }
-
-  WriteController* write_controller() { return write_controller_; }
-
 private:
  friend class ColumnFamilyData;
  // helper function that gets called from cfd destructor
@@ -8,16 +8,16 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

 #include <algorithm>
+#include <vector>
 #include <string>
 #include <thread>
-#include <vector>

 #include "db/db_impl/db_impl.h"
 #include "db/db_test_util.h"
+#include "memtable/hash_skiplist_rep.h"
 #include "options/options_parser.h"
 #include "port/port.h"
 #include "port/stack_trace.h"
-#include "rocksdb/convenience.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/iterator.h"
@@ -287,9 +287,7 @@ class ColumnFamilyTestBase : public testing::Test {
      // Verify the CF options of the returned CF handle.
      ColumnFamilyDescriptor desc;
      ASSERT_OK(handles_[cfi]->GetDescriptor(&desc));
-      RocksDBOptionsParser::VerifyCFOptions(ConfigOptions(), desc.options,
-                                            current_cf_opt);
-
+      RocksDBOptionsParser::VerifyCFOptions(desc.options, current_cf_opt);
 #endif  // !ROCKSDB_LITE
      cfi++;
    }
@@ -823,7 +821,7 @@ TEST_P(ColumnFamilyTest, BulkAddDrop) {
 }

 TEST_P(ColumnFamilyTest, DropTest) {
-  // first iteration - don't reopen DB before dropping
+  // first iteration - dont reopen DB before dropping
  // second iteration - reopen DB before dropping
  for (int iter = 0; iter < 2; ++iter) {
    Open({"default"});
@@ -37,7 +37,7 @@ Status CompactedDBImpl::Get(const ReadOptions& options, ColumnFamilyHandle*,
                            const Slice& key, PinnableSlice* value) {
  GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                         GetContext::kNotFound, key, value, nullptr, nullptr,
-                         nullptr, true, nullptr, nullptr);
+                         true, nullptr, nullptr);
  LookupKey lkey(key, kMaxSequenceNumber);
  files_.files[FindFile(key)].fd.table_reader->Get(options, lkey.internal_key(),
                                                   &get_context, nullptr);
@@ -70,7 +70,7 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
      std::string& value = (*values)[idx];
      GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                             GetContext::kNotFound, keys[idx], &pinnable_val,
-                             nullptr, nullptr, nullptr, true, nullptr, nullptr);
+                             nullptr, nullptr, true, nullptr, nullptr);
      LookupKey lkey(keys[idx], kMaxSequenceNumber);
      r->Get(options, lkey.internal_key(), &get_context, nullptr);
      value.assign(pinnable_val.data(), pinnable_val.size());
@@ -23,7 +23,7 @@ const uint64_t kRangeTombstoneSentinel =

 int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
                      const InternalKey& b) {
-  auto c = user_cmp->CompareWithoutTimestamp(a.user_key(), b.user_key());
+  auto c = user_cmp->Compare(a.user_key(), b.user_key());
  if (c != 0) {
    return c;
  }
@@ -298,7 +298,7 @@ CompactionJob::CompactionJob(
    const FileOptions& file_options, VersionSet* versions,
    const std::atomic<bool>* shutting_down,
    const SequenceNumber preserve_deletes_seqnum, LogBuffer* log_buffer,
-    FSDirectory* db_directory, FSDirectory* output_directory, Statistics* stats,
+    Directory* db_directory, Directory* output_directory, Statistics* stats,
    InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
    std::vector<SequenceNumber> existing_snapshots,
    SequenceNumber earliest_write_conflict_snapshot,
@@ -613,13 +613,8 @@ Status CompactionJob::Run() {
    }
  }

-  IOStatus io_s;
  if (status.ok() && output_directory_) {
-    io_s = output_directory_->Fsync(IOOptions(), nullptr);
-  }
-  if (!io_s.ok()) {
-    io_status_ = io_s;
-    status = io_s;
+    status = output_directory_->Fsync();
  }

  if (status.ok()) {
@@ -655,8 +650,7 @@ Status CompactionJob::Run() {
            TableReaderCaller::kCompactionRefill, /*arena=*/nullptr,
            /*skip_filters=*/false, compact_->compaction->output_level(),
            /*smallest_compaction_key=*/nullptr,
-            /*largest_compaction_key=*/nullptr,
-            /*allow_unprepared_value=*/false);
+            /*largest_compaction_key=*/nullptr);
        auto s = iter->status();

        if (s.ok() && paranoid_file_checks_) {
@@ -719,13 +713,9 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
  cfd->internal_stats()->AddCompactionStats(
      compact_->compaction->output_level(), thread_pri_, compaction_stats_);

-  versions_->SetIOStatusOK();
  if (status.ok()) {
    status = InstallCompactionResults(mutable_cf_options);
  }
-  if (!versions_->io_status().ok()) {
-    io_status_ = versions_->io_status();
-  }
  VersionStorageInfo::LevelSummaryStorage tmp;
  auto vstorage = cfd->current()->storage_info();
  const auto& stats = compaction_stats_;
@@ -938,8 +928,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
    assert(sub_compact->builder != nullptr);
    assert(sub_compact->current_output() != nullptr);
    sub_compact->builder->Add(key, value);
-    sub_compact->current_output_file_size =
-        sub_compact->builder->EstimatedFileSize();
+    sub_compact->current_output_file_size = sub_compact->builder->FileSize();
    const ParsedInternalKey& ikey = c_iter->ikey();
    sub_compact->current_output()->meta.UpdateBoundaries(
        key, value, ikey.sequence, ikey.type);
@@ -1305,35 +1294,25 @@ Status CompactionJob::FinishCompactionOutputFile(
  } else {
    sub_compact->builder->Abandon();
  }
-  if (!sub_compact->builder->io_status().ok()) {
-    io_status_ = sub_compact->builder->io_status();
-    s = io_status_;
-  }
  const uint64_t current_bytes = sub_compact->builder->FileSize();
  if (s.ok()) {
+    // Add the checksum information to file metadata.
+    meta->file_checksum = sub_compact->builder->GetFileChecksum();
+    meta->file_checksum_func_name =
+        sub_compact->builder->GetFileChecksumFuncName();
+
    meta->fd.file_size = current_bytes;
  }
  sub_compact->current_output()->finished = true;
  sub_compact->total_bytes += current_bytes;

  // Finish and check for file errors
-  IOStatus io_s;
  if (s.ok()) {
    StopWatch sw(env_, stats_, COMPACTION_OUTFILE_SYNC_MICROS);
-    io_s = sub_compact->outfile->Sync(db_options_.use_fsync);
+    s = sub_compact->outfile->Sync(db_options_.use_fsync);
  }
-  if (io_s.ok()) {
-    io_s = sub_compact->outfile->Close();
-  }
-  if (io_s.ok()) {
-    // Add the checksum information to file metadata.
-    meta->file_checksum = sub_compact->outfile->GetFileChecksum();
-    meta->file_checksum_func_name =
-        sub_compact->outfile->GetFileChecksumFuncName();
-  }
-  if (!io_s.ok()) {
-    io_status_ = io_s;
-    s = io_s;
+  if (s.ok()) {
+    s = sub_compact->outfile->Close();
  }
  sub_compact->outfile.reset();

@@ -1535,7 +1514,7 @@ Status CompactionJob::OpenCompactionOutputFile(
  sub_compact->outfile.reset(
      new WritableFileWriter(std::move(writable_file), fname, file_options_,
                             env_, db_options_.statistics.get(), listeners,
-                             db_options_.file_checksum_gen_factory.get()));
+                             db_options_.sst_file_checksum_func.get()));

  // If the Column family flag is to only optimize filters for hits,
  // we can skip creating filters if this is the bottommost_level where
@@ -67,8 +67,8 @@ class CompactionJob {
                const FileOptions& file_options, VersionSet* versions,
                const std::atomic<bool>* shutting_down,
                const SequenceNumber preserve_deletes_seqnum,
-                LogBuffer* log_buffer, FSDirectory* db_directory,
-                FSDirectory* output_directory, Statistics* stats,
+                LogBuffer* log_buffer, Directory* db_directory,
+                Directory* output_directory, Statistics* stats,
                InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
                std::vector<SequenceNumber> existing_snapshots,
                SequenceNumber earliest_write_conflict_snapshot,
@@ -100,9 +100,6 @@ class CompactionJob {
  // Add compaction input/output to the current version
  Status Install(const MutableCFOptions& mutable_cf_options);

-  // Return the IO status
-  IOStatus io_status() const { return io_status_; }
-
 private:
  struct SubcompactionState;

@@ -164,8 +161,8 @@ class CompactionJob {
  const std::atomic<bool>* manual_compaction_paused_;
  const SequenceNumber preserve_deletes_seqnum_;
  LogBuffer* log_buffer_;
-  FSDirectory* db_directory_;
-  FSDirectory* output_directory_;
+  Directory* db_directory_;
+  Directory* output_directory_;
  Statistics* stats_;
  InstrumentedMutex* db_mutex_;
  ErrorHandler* db_error_handler_;
@@ -196,7 +193,6 @@ class CompactionJob {
  std::vector<uint64_t> sizes_;
  Env::WriteLifeTimeHint write_hint_;
  Env::Priority thread_pri_;
-  IOStatus io_status_;
 };

 }  // namespace ROCKSDB_NAMESPACE
@@ -12,7 +12,7 @@
 #include <string>
 #include <tuple>

-#include "db/blob/blob_index.h"
+#include "db/blob_index.h"
 #include "db/column_family.h"
 #include "db/compaction/compaction_job.h"
 #include "db/db_impl/db_impl.h"
@@ -281,7 +281,7 @@ class CompactionJobTest : public testing::Test {
    }
    ASSERT_OK(s);
    // Make "CURRENT" file that points to the new manifest file.
-    s = SetCurrentFile(fs_.get(), dbname_, 1, nullptr);
+    s = SetCurrentFile(env_, dbname_, 1, nullptr);

    std::vector<ColumnFamilyDescriptor> column_families;
    cf_options_.table_factory = mock_table_factory_;
@@ -314,11 +314,11 @@ class CompactionJobTest : public testing::Test {
      num_input_files += level_files.size();
    }

-    Compaction compaction(
-        cfd->current()->storage_info(), *cfd->ioptions(),
-        *cfd->GetLatestMutableCFOptions(), compaction_input_files, output_level,
-        1024 * 1024, 10 * 1024 * 1024, 0, kNoCompression,
-        cfd->GetLatestMutableCFOptions()->compression_opts, 0, {}, true);
+    Compaction compaction(cfd->current()->storage_info(), *cfd->ioptions(),
+                          *cfd->GetLatestMutableCFOptions(),
+                          compaction_input_files, output_level, 1024 * 1024,
+                          10 * 1024 * 1024, 0, kNoCompression,
+                          cfd->ioptions()->compression_opts, 0, {}, true);
    compaction.SetInputVersion(cfd->current());

    LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, db_options_.info_log.get());
@@ -110,9 +110,9 @@ CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,

  // If bottommost_compression is set and we are compacting to the
  // bottommost level then we should use it.
-  if (mutable_cf_options.bottommost_compression != kDisableCompressionOption &&
+  if (ioptions.bottommost_compression != kDisableCompressionOption &&
      level >= (vstorage->num_non_empty_levels() - 1)) {
-    return mutable_cf_options.bottommost_compression;
+    return ioptions.bottommost_compression;
  }
  // If the user has specified a different compression level for each level,
  // then pick the compression for that level.
@@ -132,22 +132,22 @@ CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
  }
 }

-CompressionOptions GetCompressionOptions(const MutableCFOptions& cf_options,
+CompressionOptions GetCompressionOptions(const ImmutableCFOptions& ioptions,
                                         const VersionStorageInfo* vstorage,
                                         int level,
                                         const bool enable_compression) {
  if (!enable_compression) {
-    return cf_options.compression_opts;
+    return ioptions.compression_opts;
  }
  // If bottommost_compression is set and we are compacting to the
  // bottommost level then we should use the specified compression options
  // for the bottmomost_compression.
-  if (cf_options.bottommost_compression != kDisableCompressionOption &&
+  if (ioptions.bottommost_compression != kDisableCompressionOption &&
      level >= (vstorage->num_non_empty_levels() - 1) &&
-      cf_options.bottommost_compression_opts.enabled) {
-    return cf_options.bottommost_compression_opts;
+      ioptions.bottommost_compression_opts.enabled) {
+    return ioptions.bottommost_compression_opts;
  }
-  return cf_options.compression_opts;
+  return ioptions.compression_opts;
 }

 CompactionPicker::CompactionPicker(const ImmutableCFOptions& ioptions,
@@ -359,7 +359,7 @@ Compaction* CompactionPicker::CompactFiles(
      vstorage, ioptions_, mutable_cf_options, input_files, output_level,
      compact_options.output_file_size_limit,
      mutable_cf_options.max_compaction_bytes, output_path_id, compression_type,
-      GetCompressionOptions(mutable_cf_options, vstorage, output_level),
+      GetCompressionOptions(ioptions_, vstorage, output_level),
      compact_options.max_subcompactions,
      /* grandparents */ {}, true);
  RegisterCompaction(c);
@@ -634,7 +634,7 @@ Compaction* CompactionPicker::CompactRange(
        compact_range_options.target_path_id,
        GetCompressionType(ioptions_, vstorage, mutable_cf_options,
                           output_level, 1),
-        GetCompressionOptions(mutable_cf_options, vstorage, output_level),
+        GetCompressionOptions(ioptions_, vstorage, output_level),
        compact_range_options.max_subcompactions, /* grandparents */ {},
        /* is manual */ true);
    RegisterCompaction(c);
@@ -787,7 +787,7 @@ Compaction* CompactionPicker::CompactRange(
      compact_range_options.target_path_id,
      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
                         vstorage->base_level()),
-      GetCompressionOptions(mutable_cf_options, vstorage, output_level),
+      GetCompressionOptions(ioptions_, vstorage, output_level),
      compact_range_options.max_subcompactions, std::move(grandparents),
      /* is manual compaction */ true);

@@ -305,9 +305,9 @@ CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
                                   int level, int base_level,
                                   const bool enable_compression = true);

-CompressionOptions GetCompressionOptions(
-    const MutableCFOptions& mutable_cf_options,
-    const VersionStorageInfo* vstorage, int level,
-    const bool enable_compression = true);
+CompressionOptions GetCompressionOptions(const ImmutableCFOptions& ioptions,
+                                         const VersionStorageInfo* vstorage,
+                                         int level,
+                                         const bool enable_compression = true);

 }  // namespace ROCKSDB_NAMESPACE
@@ -71,7 +71,6 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
  if (current_time > mutable_cf_options.ttl) {
    for (auto ritr = level_files.rbegin(); ritr != level_files.rend(); ++ritr) {
      FileMetaData* f = *ritr;
-      assert(f);
      if (f->fd.table_reader && f->fd.table_reader->GetTableProperties()) {
        uint64_t creation_time =
            f->fd.table_reader->GetTableProperties()->creation_time;
@@ -79,9 +78,9 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
            creation_time >= (current_time - mutable_cf_options.ttl)) {
          break;
        }
+        total_size -= f->compensated_file_size;
+        inputs[0].files.push_back(f);
      }
-      total_size -= f->compensated_file_size;
-      inputs[0].files.push_back(f);
    }
  }

@@ -97,8 +96,7 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(

  for (const auto& f : inputs[0].files) {
    uint64_t creation_time = 0;
-    assert(f);
-    if (f->fd.table_reader && f->fd.table_reader->GetTableProperties()) {
+    if (f && f->fd.table_reader && f->fd.table_reader->GetTableProperties()) {
      creation_time = f->fd.table_reader->GetTableProperties()->creation_time;
    }
    ROCKS_LOG_BUFFER(log_buffer,
@@ -109,9 +107,8 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(

  Compaction* c = new Compaction(
      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
-      kNoCompression, mutable_cf_options.compression_opts,
-      /* max_subcompactions */ 0, {}, /* is manual */ false,
-      vstorage->CompactionScore(0),
+      kNoCompression, ioptions_.compression_opts, /* max_subcompactions */ 0,
+      {}, /* is manual */ false, vstorage->CompactionScore(0),
      /* is deletion compaction */ true, CompactionReason::kFIFOTtl);
  return c;
 }
@@ -151,7 +148,7 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(
            16 * 1024 * 1024 /* output file size limit */,
            0 /* max compaction bytes, not applicable */,
            0 /* output path ID */, mutable_cf_options.compression,
-            mutable_cf_options.compression_opts, 0 /* max_subcompactions */, {},
+            ioptions_.compression_opts, 0 /* max_subcompactions */, {},
            /* is manual */ false, vstorage->CompactionScore(0),
            /* is deletion compaction */ false,
            CompactionReason::kFIFOReduceNumFiles);
@@ -199,9 +196,8 @@ Compaction* FIFOCompactionPicker::PickSizeCompaction(

  Compaction* c = new Compaction(
      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
-      kNoCompression, mutable_cf_options.compression_opts,
-      /* max_subcompactions */ 0, {}, /* is manual */ false,
-      vstorage->CompactionScore(0),
+      kNoCompression, ioptions_.compression_opts, /* max_subcompactions */ 0,
+      {}, /* is manual */ false, vstorage->CompactionScore(0),
      /* is deletion compaction */ true, CompactionReason::kFIFOMaxSize);
  return c;
 }
@@ -93,13 +93,9 @@ class LevelCompactionBuilder {
  // otherwise, returns false.
  bool PickIntraL0Compaction();

-  // Picks a file from level_files to compact.
-  // level_files is a vector of (level, file metadata) in ascending order of
-  // level. If compact_to_next_level is true, compact the file to the next
-  // level, otherwise, compact to the same level as the input file.
-  void PickFileToCompact(
-      const autovector<std::pair<int, FileMetaData*>>& level_files,
-      bool compact_to_next_level);
+  void PickExpiredTtlFiles();
+
+  void PickFilesMarkedForPeriodicCompaction();

  const std::string& cf_name_;
  VersionStorageInfo* vstorage_;
@@ -128,34 +124,72 @@ class LevelCompactionBuilder {
  static const int kMinFilesForIntraL0Compaction = 4;
 };

-void LevelCompactionBuilder::PickFileToCompact(
-    const autovector<std::pair<int, FileMetaData*>>& level_files,
-    bool compact_to_next_level) {
-  for (auto& level_file : level_files) {
+void LevelCompactionBuilder::PickExpiredTtlFiles() {
+  if (vstorage_->ExpiredTtlFiles().empty()) {
+    return;
+  }
+
+  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
    // If it's being compacted it has nothing to do here.
    // If this assert() fails that means that some function marked some
    // files as being_compacted, but didn't call ComputeCompactionScore()
    assert(!level_file.second->being_compacted);
    start_level_ = level_file.first;
-    if ((compact_to_next_level &&
-         start_level_ == vstorage_->num_non_empty_levels() - 1) ||
+    output_level_ =
+        (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
+
+    if ((start_level_ == vstorage_->num_non_empty_levels() - 1) ||
        (start_level_ == 0 &&
         !compaction_picker_->level0_compactions_in_progress()->empty())) {
-      continue;
-    }
-    if (compact_to_next_level) {
-      output_level_ =
-          (start_level_ == 0) ? vstorage_->base_level() : start_level_ + 1;
-    } else {
-      output_level_ = start_level_;
+      return false;
    }
+
    start_level_inputs_.files = {level_file.second};
    start_level_inputs_.level = start_level_;
-    if (compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
-                                                   &start_level_inputs_)) {
+    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                      &start_level_inputs_);
+  };
+
+  for (auto& level_file : vstorage_->ExpiredTtlFiles()) {
+    if (continuation(level_file)) {
+      // found the compaction!
      return;
    }
  }
+
+  start_level_inputs_.files.clear();
+}
+
+void LevelCompactionBuilder::PickFilesMarkedForPeriodicCompaction() {
+  if (vstorage_->FilesMarkedForPeriodicCompaction().empty()) {
+    return;
+  }
+
+  auto continuation = [&](std::pair<int, FileMetaData*> level_file) {
+    // If it's being compacted it has nothing to do here.
+    // If this assert() fails that means that some function marked some
+    // files as being_compacted, but didn't call ComputeCompactionScore()
+    assert(!level_file.second->being_compacted);
+    output_level_ = start_level_ = level_file.first;
+
+    if (start_level_ == 0 &&
+        !compaction_picker_->level0_compactions_in_progress()->empty()) {
+      return false;
+    }
+
+    start_level_inputs_.files = {level_file.second};
+    start_level_inputs_.level = start_level_;
+    return compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                      &start_level_inputs_);
+  };
+
+  for (auto& level_file : vstorage_->FilesMarkedForPeriodicCompaction()) {
+    if (continuation(level_file)) {
+      // found the compaction!
+      return;
+    }
+  }
+
  start_level_inputs_.files.clear();
 }

@@ -204,46 +238,64 @@ void LevelCompactionBuilder::SetupInitialFiles() {
          }
        }
      }
-    } else {
-      // Compaction scores are sorted in descending order, no further scores
-      // will be >= 1.
-      break;
    }
  }
-  if (!start_level_inputs_.empty()) {
-    return;
-  }

  // if we didn't find a compaction, check if there are any files marked for
  // compaction
-  parent_index_ = base_index_ = -1;
+  if (start_level_inputs_.empty()) {
+    parent_index_ = base_index_ = -1;

-  compaction_picker_->PickFilesMarkedForCompaction(
-      cf_name_, vstorage_, &start_level_, &output_level_, &start_level_inputs_);
-  if (!start_level_inputs_.empty()) {
-    compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
-    return;
+    compaction_picker_->PickFilesMarkedForCompaction(
+        cf_name_, vstorage_, &start_level_, &output_level_,
+        &start_level_inputs_);
+    if (!start_level_inputs_.empty()) {
+      is_manual_ = true;
+      compaction_reason_ = CompactionReason::kFilesMarkedForCompaction;
+      return;
+    }
  }

  // Bottommost Files Compaction on deleting tombstones
-  PickFileToCompact(vstorage_->BottommostFilesMarkedForCompaction(), false);
-  if (!start_level_inputs_.empty()) {
-    compaction_reason_ = CompactionReason::kBottommostFiles;
-    return;
+  if (start_level_inputs_.empty()) {
+    size_t i;
+    for (i = 0; i < vstorage_->BottommostFilesMarkedForCompaction().size();
+         ++i) {
+      auto& level_and_file = vstorage_->BottommostFilesMarkedForCompaction()[i];
+      assert(!level_and_file.second->being_compacted);
+      start_level_inputs_.level = output_level_ = start_level_ =
+          level_and_file.first;
+      start_level_inputs_.files = {level_and_file.second};
+      if (compaction_picker_->ExpandInputsToCleanCut(cf_name_, vstorage_,
+                                                     &start_level_inputs_)) {
+        break;
+      }
+    }
+    if (i == vstorage_->BottommostFilesMarkedForCompaction().size()) {
+      start_level_inputs_.clear();
+    } else {
+      assert(!start_level_inputs_.empty());
+      compaction_reason_ = CompactionReason::kBottommostFiles;
+      return;
+    }
  }

  // TTL Compaction
-  PickFileToCompact(vstorage_->ExpiredTtlFiles(), true);
-  if (!start_level_inputs_.empty()) {
-    compaction_reason_ = CompactionReason::kTtl;
-    return;
+  if (start_level_inputs_.empty()) {
+    PickExpiredTtlFiles();
+    if (!start_level_inputs_.empty()) {
+      compaction_reason_ = CompactionReason::kTtl;
+      return;
+    }
  }

  // Periodic Compaction
-  PickFileToCompact(vstorage_->FilesMarkedForPeriodicCompaction(), false);
-  if (!start_level_inputs_.empty()) {
-    compaction_reason_ = CompactionReason::kPeriodicCompaction;
-    return;
+  if (start_level_inputs_.empty()) {
+    PickFilesMarkedForPeriodicCompaction();
+    if (!start_level_inputs_.empty()) {
+      compaction_reason_ = CompactionReason::kPeriodicCompaction;
+      return;
+    }
  }
 }

@@ -332,7 +384,7 @@ Compaction* LevelCompactionBuilder::GetCompaction() {
      GetPathId(ioptions_, mutable_cf_options_, output_level_),
      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
                         output_level_, vstorage_->base_level()),
-      GetCompressionOptions(mutable_cf_options_, vstorage_, output_level_),
+      GetCompressionOptions(ioptions_, vstorage_, output_level_),
      /* max_subcompactions */ 0, std::move(grandparents_), is_manual_,
      start_level_score_, false /* deletion_compaction */, compaction_reason_);

@@ -389,7 +389,7 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
  VersionStorageInfo::LevelSummaryStorage tmp;
  ROCKS_LOG_BUFFER_MAX_SZ(
      log_buffer_, 3072,
-      "[%s] Universal: sorted runs: %" ROCKSDB_PRIszt " files: %s\n",
+      "[%s] Universal: sorted runs files(%" ROCKSDB_PRIszt "): %s\n",
      cf_name_.c_str(), sorted_runs_.size(), vstorage_->LevelSummary(&tmp));

  Compaction* c = nullptr;
@@ -751,7 +751,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
      LLONG_MAX, path_id,
      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_, start_level,
                         1, enable_compression),
-      GetCompressionOptions(mutable_cf_options_, vstorage_, start_level,
+      GetCompressionOptions(ioptions_, vstorage_, start_level,
                            enable_compression),
      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
      score_, false /* deletion_compaction */, compaction_reason);
@@ -959,8 +959,8 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
      /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_,
                         output_level, 1),
-      GetCompressionOptions(mutable_cf_options_, vstorage_, output_level),
-      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
+      GetCompressionOptions(ioptions_, vstorage_, output_level),
+      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ true,
      score_, false /* deletion_compaction */,
      CompactionReason::kFilesMarkedForCompaction);
 }
@@ -1029,7 +1029,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionToOldest(
      LLONG_MAX, path_id,
      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_, start_level,
                         1, true /* enable_compression */),
-      GetCompressionOptions(mutable_cf_options_, vstorage_, start_level,
+      GetCompressionOptions(ioptions_, vstorage_, start_level,
                            true /* enable_compression */),
      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
      score_, false /* deletion_compaction */, compaction_reason);
@@ -14,7 +14,7 @@
 namespace ROCKSDB_NAMESPACE {

 void CancelAllBackgroundWork(DB* db, bool wait) {
-  (static_cast_with_check<DBImpl>(db->GetRootDB()))
+  (static_cast_with_check<DBImpl, DB>(db->GetRootDB()))
      ->CancelAllBackgroundWork(wait);
 }

@@ -28,7 +28,7 @@ Status DeleteFilesInRange(DB* db, ColumnFamilyHandle* column_family,
 Status DeleteFilesInRanges(DB* db, ColumnFamilyHandle* column_family,
                           const RangePtr* ranges, size_t n,
                           bool include_end) {
-  return (static_cast_with_check<DBImpl>(db->GetRootDB()))
+  return (static_cast_with_check<DBImpl, DB>(db->GetRootDB()))
      ->DeleteFilesInRanges(column_family, ranges, n, include_end);
 }

@@ -190,6 +190,7 @@ class CorruptionTest : public testing::Test {
    ASSERT_TRUE(s.ok()) << s.ToString();
    Options options;
    EnvOptions env_options;
+    options.file_system.reset(new LegacyFileSystemWrapper(options.env));
    ASSERT_NOK(VerifySstFileChecksum(options, env_options, fname));
  }

@@ -517,139 +517,6 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksCachePriority) {
  }
 }

-namespace {
-
-// An LRUCache wrapper that can falsely report "not found" on Lookup.
-// This allows us to manipulate BlockBasedTableReader into thinking
-// another thread inserted the data in between Lookup and Insert,
-// while mostly preserving the LRUCache interface/behavior.
-class LookupLiarCache : public CacheWrapper {
-  int nth_lookup_not_found_ = 0;
-
- public:
-  explicit LookupLiarCache(std::shared_ptr<Cache> target)
-      : CacheWrapper(std::move(target)) {}
-
-  Handle* Lookup(const Slice& key, Statistics* stats) override {
-    if (nth_lookup_not_found_ == 1) {
-      nth_lookup_not_found_ = 0;
-      return nullptr;
-    }
-    if (nth_lookup_not_found_ > 1) {
-      --nth_lookup_not_found_;
-    }
-    return CacheWrapper::Lookup(key, stats);
-  }
-
-  // 1 == next lookup, 2 == after next, etc.
-  void SetNthLookupNotFound(int n) { nth_lookup_not_found_ = n; }
-};
-
-}  // anonymous namespace
-
-TEST_F(DBBlockCacheTest, AddRedundantStats) {
-  const size_t capacity = size_t{1} << 25;
-  const int num_shard_bits = 0;  // 1 shard
-  int iterations_tested = 0;
-  for (std::shared_ptr<Cache> base_cache :
-       {NewLRUCache(capacity, num_shard_bits),
-        NewClockCache(capacity, num_shard_bits)}) {
-    if (!base_cache) {
-      // Skip clock cache when not supported
-      continue;
-    }
-    ++iterations_tested;
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-
-    std::shared_ptr<LookupLiarCache> cache =
-        std::make_shared<LookupLiarCache>(base_cache);
-
-    BlockBasedTableOptions table_options;
-    table_options.cache_index_and_filter_blocks = true;
-    table_options.block_cache = cache;
-    table_options.filter_policy.reset(NewBloomFilterPolicy(50));
-    options.table_factory.reset(new BlockBasedTableFactory(table_options));
-    DestroyAndReopen(options);
-
-    // Create a new table.
-    ASSERT_OK(Put("foo", "value"));
-    ASSERT_OK(Put("bar", "value"));
-    ASSERT_OK(Flush());
-    ASSERT_EQ(1, NumTableFilesAtLevel(0));
-
-    // Normal access filter+index+data.
-    ASSERT_EQ("value", Get("foo"));
-
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_ADD));
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_ADD));
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_DATA_ADD));
-    // --------
-    ASSERT_EQ(3, TestGetTickerCount(options, BLOCK_CACHE_ADD));
-
-    ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_INDEX_ADD_REDUNDANT));
-    ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_FILTER_ADD_REDUNDANT));
-    ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_DATA_ADD_REDUNDANT));
-    // --------
-    ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_ADD_REDUNDANT));
-
-    // Againt access filter+index+data, but force redundant load+insert on index
-    cache->SetNthLookupNotFound(2);
-    ASSERT_EQ("value", Get("bar"));
-
-    ASSERT_EQ(2, TestGetTickerCount(options, BLOCK_CACHE_INDEX_ADD));
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_ADD));
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_DATA_ADD));
-    // --------
-    ASSERT_EQ(4, TestGetTickerCount(options, BLOCK_CACHE_ADD));
-
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_ADD_REDUNDANT));
-    ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_FILTER_ADD_REDUNDANT));
-    ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_DATA_ADD_REDUNDANT));
-    // --------
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_ADD_REDUNDANT));
-
-    // Access just filter (with high probability), and force redundant
-    // load+insert
-    cache->SetNthLookupNotFound(1);
-    ASSERT_EQ("NOT_FOUND", Get("this key was not added"));
-
-    EXPECT_EQ(2, TestGetTickerCount(options, BLOCK_CACHE_INDEX_ADD));
-    EXPECT_EQ(2, TestGetTickerCount(options, BLOCK_CACHE_FILTER_ADD));
-    EXPECT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_DATA_ADD));
-    // --------
-    EXPECT_EQ(5, TestGetTickerCount(options, BLOCK_CACHE_ADD));
-
-    EXPECT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_ADD_REDUNDANT));
-    EXPECT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_ADD_REDUNDANT));
-    EXPECT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_DATA_ADD_REDUNDANT));
-    // --------
-    EXPECT_EQ(2, TestGetTickerCount(options, BLOCK_CACHE_ADD_REDUNDANT));
-
-    // Access just data, forcing redundant load+insert
-    ReadOptions read_options;
-    std::unique_ptr<Iterator> iter{db_->NewIterator(read_options)};
-    cache->SetNthLookupNotFound(1);
-    iter->SeekToFirst();
-    ASSERT_TRUE(iter->Valid());
-    ASSERT_EQ(iter->key(), "bar");
-
-    EXPECT_EQ(2, TestGetTickerCount(options, BLOCK_CACHE_INDEX_ADD));
-    EXPECT_EQ(2, TestGetTickerCount(options, BLOCK_CACHE_FILTER_ADD));
-    EXPECT_EQ(2, TestGetTickerCount(options, BLOCK_CACHE_DATA_ADD));
-    // --------
-    EXPECT_EQ(6, TestGetTickerCount(options, BLOCK_CACHE_ADD));
-
-    EXPECT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_ADD_REDUNDANT));
-    EXPECT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_ADD_REDUNDANT));
-    EXPECT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_DATA_ADD_REDUNDANT));
-    // --------
-    EXPECT_EQ(3, TestGetTickerCount(options, BLOCK_CACHE_ADD_REDUNDANT));
-  }
-  EXPECT_GE(iterations_tested, 1);
-}
-
 TEST_F(DBBlockCacheTest, ParanoidFileChecks) {
  Options options = CurrentOptions();
  options.create_if_missing = true;
@@ -8,7 +8,6 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.

 #include "db/db_test_util.h"
-#include "options/options_helper.h"
 #include "port/stack_trace.h"
 #include "rocksdb/perf_context.h"
 #include "table/block_based/filter_policy_internal.h"
@@ -1030,206 +1029,6 @@ TEST_F(DBBloomFilterTest, MemtablePrefixBloomOutOfDomain) {
  ASSERT_EQ(kKey, iter->key());
 }

-class DBBloomFilterTestVaryPrefixAndFormatVer
-    : public DBTestBase,
-      public testing::WithParamInterface<std::tuple<bool, uint32_t>> {
- protected:
-  bool use_prefix_;
-  uint32_t format_version_;
-
- public:
-  DBBloomFilterTestVaryPrefixAndFormatVer()
-      : DBTestBase("/db_bloom_filter_tests") {}
-
-  ~DBBloomFilterTestVaryPrefixAndFormatVer() override {}
-
-  void SetUp() override {
-    use_prefix_ = std::get<0>(GetParam());
-    format_version_ = std::get<1>(GetParam());
-  }
-
-  static std::string UKey(uint32_t i) { return Key(static_cast<int>(i)); }
-};
-
-TEST_P(DBBloomFilterTestVaryPrefixAndFormatVer, PartitionedMultiGet) {
-  Options options = CurrentOptions();
-  if (use_prefix_) {
-    // Entire key from UKey()
-    options.prefix_extractor.reset(NewCappedPrefixTransform(9));
-  }
-  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-  BlockBasedTableOptions bbto;
-  bbto.filter_policy.reset(NewBloomFilterPolicy(20));
-  bbto.partition_filters = true;
-  bbto.index_type = BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
-  bbto.whole_key_filtering = !use_prefix_;
-  bbto.metadata_block_size = 128;
-  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-  DestroyAndReopen(options);
-  ReadOptions ropts;
-
-  constexpr uint32_t N = 10000;
-  // Add N/2 evens
-  for (uint32_t i = 0; i < N; i += 2) {
-    ASSERT_OK(Put(UKey(i), UKey(i)));
-  }
-  ASSERT_OK(Flush());
-#ifndef ROCKSDB_LITE
-  ASSERT_EQ(TotalTableFiles(), 1);
-#endif
-
-  constexpr uint32_t Q = 29;
-  // MultiGet In
-  std::array<std::string, Q> keys;
-  std::array<Slice, Q> key_slices;
-  std::array<ColumnFamilyHandle*, Q> column_families;
-  // MultiGet Out
-  std::array<Status, Q> statuses;
-  std::array<PinnableSlice, Q> values;
-
-  TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_HIT);
-  TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_MISS);
-  TestGetAndResetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL);
-  TestGetAndResetTickerCount(options, BLOOM_FILTER_USEFUL);
-  TestGetAndResetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED);
-  TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_POSITIVE);
-  TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_TRUE_POSITIVE);
-
-  // Check that initial clump of keys only loads one partition filter from
-  // block cache.
-  // And that spread out keys load many partition filters.
-  // In both cases, mix present vs. not present keys.
-  for (uint32_t stride : {uint32_t{1}, (N / Q) | 1}) {
-    for (uint32_t i = 0; i < Q; ++i) {
-      keys[i] = UKey(i * stride);
-      key_slices[i] = Slice(keys[i]);
-      column_families[i] = db_->DefaultColumnFamily();
-      statuses[i] = Status();
-      values[i] = PinnableSlice();
-    }
-
-    db_->MultiGet(ropts, Q, &column_families[0], &key_slices[0], &values[0],
-                  /*timestamps=*/nullptr, &statuses[0], true);
-
-    // Confirm correct status results
-    uint32_t number_not_found = 0;
-    for (uint32_t i = 0; i < Q; ++i) {
-      if ((i * stride % 2) == 0) {
-        ASSERT_OK(statuses[i]);
-      } else {
-        ASSERT_TRUE(statuses[i].IsNotFound());
-        ++number_not_found;
-      }
-    }
-
-    // Confirm correct Bloom stats (no FPs)
-    uint64_t filter_useful = TestGetAndResetTickerCount(
-        options,
-        use_prefix_ ? BLOOM_FILTER_PREFIX_USEFUL : BLOOM_FILTER_USEFUL);
-    uint64_t filter_checked =
-        TestGetAndResetTickerCount(options, use_prefix_
-                                                ? BLOOM_FILTER_PREFIX_CHECKED
-                                                : BLOOM_FILTER_FULL_POSITIVE) +
-        (use_prefix_ ? 0 : filter_useful);
-    EXPECT_EQ(filter_useful, number_not_found);
-    EXPECT_EQ(filter_checked, Q);
-    if (!use_prefix_) {
-      EXPECT_EQ(
-          TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_TRUE_POSITIVE),
-          Q - number_not_found);
-    }
-
-    // Confirm no duplicate loading same filter partition
-    uint64_t filter_accesses =
-        TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_HIT) +
-        TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_MISS);
-    if (stride == 1) {
-      EXPECT_EQ(filter_accesses, 1);
-    } else {
-      // for large stride
-      EXPECT_GE(filter_accesses, Q / 2 + 1);
-    }
-  }
-
-  // Check that a clump of keys (present and not) works when spanning
-  // two partitions
-  int found_spanning = 0;
-  for (uint32_t start = 0; start < N / 2;) {
-    for (uint32_t i = 0; i < Q; ++i) {
-      keys[i] = UKey(start + i);
-      key_slices[i] = Slice(keys[i]);
-      column_families[i] = db_->DefaultColumnFamily();
-      statuses[i] = Status();
-      values[i] = PinnableSlice();
-    }
-
-    db_->MultiGet(ropts, Q, &column_families[0], &key_slices[0], &values[0],
-                  /*timestamps=*/nullptr, &statuses[0], true);
-
-    // Confirm correct status results
-    uint32_t number_not_found = 0;
-    for (uint32_t i = 0; i < Q; ++i) {
-      if (((start + i) % 2) == 0) {
-        ASSERT_OK(statuses[i]);
-      } else {
-        ASSERT_TRUE(statuses[i].IsNotFound());
-        ++number_not_found;
-      }
-    }
-
-    // Confirm correct Bloom stats (might see some FPs)
-    uint64_t filter_useful = TestGetAndResetTickerCount(
-        options,
-        use_prefix_ ? BLOOM_FILTER_PREFIX_USEFUL : BLOOM_FILTER_USEFUL);
-    uint64_t filter_checked =
-        TestGetAndResetTickerCount(options, use_prefix_
-                                                ? BLOOM_FILTER_PREFIX_CHECKED
-                                                : BLOOM_FILTER_FULL_POSITIVE) +
-        (use_prefix_ ? 0 : filter_useful);
-    EXPECT_GE(filter_useful, number_not_found - 2);  // possible FP
-    EXPECT_EQ(filter_checked, Q);
-    if (!use_prefix_) {
-      EXPECT_EQ(
-          TestGetAndResetTickerCount(options, BLOOM_FILTER_FULL_TRUE_POSITIVE),
-          Q - number_not_found);
-    }
-
-    // Confirm no duplicate loading of same filter partition
-    uint64_t filter_accesses =
-        TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_HIT) +
-        TestGetAndResetTickerCount(options, BLOCK_CACHE_FILTER_MISS);
-    if (filter_accesses == 2) {
-      // Spanned across partitions.
-      ++found_spanning;
-      if (found_spanning >= 2) {
-        break;
-      } else {
-        // Ensure that at least once we have at least one present and
-        // one non-present key on both sides of partition boundary.
-        start += 2;
-      }
-    } else {
-      EXPECT_EQ(filter_accesses, 1);
-      // See explanation at "start += 2"
-      start += Q - 4;
-    }
-  }
-  EXPECT_TRUE(found_spanning >= 2);
-}
-
-INSTANTIATE_TEST_CASE_P(DBBloomFilterTestVaryPrefixAndFormatVer,
-                        DBBloomFilterTestVaryPrefixAndFormatVer,
-                        ::testing::Values(
-                            // (use_prefix, format_version)
-                            std::make_tuple(false, 2),
-                            std::make_tuple(false, 3),
-                            std::make_tuple(false, 4),
-                            std::make_tuple(false, 5),
-                            std::make_tuple(true, 2),
-                            std::make_tuple(true, 3),
-                            std::make_tuple(true, 4),
-                            std::make_tuple(true, 5)));
-
 #ifndef ROCKSDB_LITE
 namespace {
 namespace BFP2 {
@@ -1544,7 +1343,8 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
  for (int i = 0; i < numkeys; i += 2) {
    keys.push_back(i);
  }
-  RandomShuffle(std::begin(keys), std::end(keys));
+  std::random_shuffle(std::begin(keys), std::end(keys));
+
  int num_inserted = 0;
  for (int key : keys) {
    ASSERT_OK(Put(1, Key(key), "val"));
@@ -157,21 +157,21 @@ Options DeletionTriggerOptions(Options options) {
 bool HaveOverlappingKeyRanges(
    const Comparator* c,
    const SstFileMetaData& a, const SstFileMetaData& b) {
-  if (c->CompareWithoutTimestamp(a.smallestkey, b.smallestkey) >= 0) {
-    if (c->CompareWithoutTimestamp(a.smallestkey, b.largestkey) <= 0) {
+  if (c->Compare(a.smallestkey, b.smallestkey) >= 0) {
+    if (c->Compare(a.smallestkey, b.largestkey) <= 0) {
      // b.smallestkey <= a.smallestkey <= b.largestkey
      return true;
    }
-  } else if (c->CompareWithoutTimestamp(a.largestkey, b.smallestkey) >= 0) {
+  } else if (c->Compare(a.largestkey, b.smallestkey) >= 0) {
    // a.smallestkey < b.smallestkey <= a.largestkey
    return true;
  }
-  if (c->CompareWithoutTimestamp(a.largestkey, b.largestkey) <= 0) {
-    if (c->CompareWithoutTimestamp(a.largestkey, b.smallestkey) >= 0) {
+  if (c->Compare(a.largestkey, b.largestkey) <= 0) {
+    if (c->Compare(a.largestkey, b.smallestkey) >= 0) {
      // b.smallestkey <= a.largestkey <= b.largestkey
      return true;
    }
-  } else if (c->CompareWithoutTimestamp(a.smallestkey, b.largestkey) <= 0) {
+  } else if (c->Compare(a.smallestkey, b.largestkey) <= 0) {
    // a.smallestkey <= b.largestkey < a.largestkey
    return true;
  }
@@ -593,72 +593,6 @@ TEST_P(DBCompactionTestWithParam, CompactionDeletionTriggerReopen) {
  }
 }

-TEST_F(DBCompactionTest, CompactRangeBottomPri) {
-  ASSERT_OK(Put(Key(50), ""));
-  ASSERT_OK(Flush());
-  ASSERT_OK(Put(Key(100), ""));
-  ASSERT_OK(Flush());
-  ASSERT_OK(Put(Key(200), ""));
-  ASSERT_OK(Flush());
-
-  {
-    CompactRangeOptions cro;
-    cro.change_level = true;
-    cro.target_level = 2;
-    dbfull()->CompactRange(cro, nullptr, nullptr);
-  }
-  ASSERT_EQ("0,0,3", FilesPerLevel(0));
-
-  ASSERT_OK(Put(Key(1), ""));
-  ASSERT_OK(Put(Key(199), ""));
-  ASSERT_OK(Flush());
-  ASSERT_OK(Put(Key(2), ""));
-  ASSERT_OK(Put(Key(199), ""));
-  ASSERT_OK(Flush());
-  ASSERT_EQ("2,0,3", FilesPerLevel(0));
-
-  // Now we have 2 L0 files, and 3 L2 files, and a manual compaction will
-  // be triggered.
-  // Two compaction jobs will run. One compacts 2 L0 files in Low Pri Pool
-  // and one compact to L2 in bottom pri pool.
-  int low_pri_count = 0;
-  int bottom_pri_count = 0;
-  SyncPoint::GetInstance()->SetCallBack(
-      "ThreadPoolImpl::Impl::BGThread:BeforeRun", [&](void* arg) {
-        Env::Priority* pri = reinterpret_cast<Env::Priority*>(arg);
-        // First time is low pri pool in the test case.
-        if (low_pri_count == 0 && bottom_pri_count == 0) {
-          ASSERT_EQ(Env::Priority::LOW, *pri);
-        }
-        if (*pri == Env::Priority::LOW) {
-          low_pri_count++;
-        } else {
-          bottom_pri_count++;
-        }
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-  env_->SetBackgroundThreads(1, Env::Priority::BOTTOM);
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  ASSERT_EQ(1, low_pri_count);
-  ASSERT_EQ(1, bottom_pri_count);
-  ASSERT_EQ("0,0,2", FilesPerLevel(0));
-
-  // Recompact bottom most level uses bottom pool
-  CompactRangeOptions cro;
-  cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
-  dbfull()->CompactRange(cro, nullptr, nullptr);
-  ASSERT_EQ(1, low_pri_count);
-  ASSERT_EQ(2, bottom_pri_count);
-
-  env_->SetBackgroundThreads(0, Env::Priority::BOTTOM);
-  dbfull()->CompactRange(cro, nullptr, nullptr);
-  // Low pri pool is used if bottom pool has size 0.
-  ASSERT_EQ(2, low_pri_count);
-  ASSERT_EQ(2, bottom_pri_count);
-
-  SyncPoint::GetInstance()->DisableProcessing();
-}
-
 TEST_F(DBCompactionTest, DisableStatsUpdateReopen) {
  uint64_t db_size[3];
  for (int test = 0; test < 2; ++test) {
@@ -2525,7 +2459,7 @@ TEST_P(DBCompactionTestWithParam, ManualCompaction) {
    ASSERT_EQ("1,1,1", FilesPerLevel(1));

    // Compaction range overlaps files
-    Compact(1, "p", "q");
+    Compact(1, "p1", "p9");
    ASSERT_EQ("0,0,1", FilesPerLevel(1));

    // Populate a different range
@@ -2592,7 +2526,7 @@ TEST_P(DBCompactionTestWithParam, ManualLevelCompactionOutputPathId) {
    ASSERT_EQ("3", FilesPerLevel(1));

    // Compaction range overlaps files
-    Compact(1, "p", "q", 1);
+    Compact(1, "p1", "p9", 1);
    ASSERT_OK(dbfull()->TEST_WaitForCompact());
    ASSERT_EQ("0,1", FilesPerLevel(1));
    ASSERT_EQ(1, GetSstFileCount(options.db_paths[1].path));
@@ -4721,7 +4655,7 @@ TEST_P(DBCompactionDirectIOTest, DirectIO) {
  CreateAndReopenWithCF({"pikachu"}, options);
  MakeTables(3, "p", "q", 1);
  ASSERT_EQ("1,1,1", FilesPerLevel(1));
-  Compact(1, "p", "q");
+  Compact(1, "p1", "p9");
  ASSERT_EQ(readahead, options.use_direct_reads);
  ASSERT_EQ("0,0,1", FilesPerLevel(1));
  Destroy(options);
@@ -4762,7 +4696,7 @@ TEST_P(CompactionPriTest, Test) {
  for (int i = 0; i < kNKeys; i++) {
    keys[i] = i;
  }
-  RandomShuffle(std::begin(keys), std::end(keys), rnd.Next());
+  std::random_shuffle(std::begin(keys), std::end(keys));

  for (int i = 0; i < kNKeys; i++) {
    ASSERT_OK(Put(Key(keys[i]), RandomString(&rnd, 102)));
@@ -5024,11 +4958,10 @@ TEST_P(DBCompactionTestWithParam, FixFileIngestionCompactionDeadlock) {

 TEST_F(DBCompactionTest, ConsistencyFailTest) {
  Options options = CurrentOptions();
-  options.force_consistency_checks = true;
  DestroyAndReopen(options);

  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "VersionBuilder::CheckConsistency0", [&](void* arg) {
+      "VersionBuilder::CheckConsistency", [&](void* arg) {
        auto p =
            reinterpret_cast<std::pair<FileMetaData**, FileMetaData**>*>(arg);
        // just swap the two FileMetaData so that we hit error
@@ -5047,48 +4980,6 @@ TEST_F(DBCompactionTest, ConsistencyFailTest) {

  ASSERT_NOK(Put("foo", "bar"));
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
-TEST_F(DBCompactionTest, ConsistencyFailTest2) {
-  Options options = CurrentOptions();
-  options.force_consistency_checks = true;
-  options.target_file_size_base = 1000;
-  options.level0_file_num_compaction_trigger = 2;
-  BlockBasedTableOptions bbto;
-  bbto.block_size = 400;  // small block size
-  options.table_factory.reset(new BlockBasedTableFactory(bbto));
-  DestroyAndReopen(options);
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "VersionBuilder::CheckConsistency1", [&](void* arg) {
-        auto p =
-            reinterpret_cast<std::pair<FileMetaData**, FileMetaData**>*>(arg);
-        // just swap the two FileMetaData so that we hit error
-        // in CheckConsistency funcion
-        FileMetaData* temp = *(p->first);
-        *(p->first) = *(p->second);
-        *(p->second) = temp;
-      });
-
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-
-  Random rnd(301);
-  std::string value = RandomString(&rnd, 1000);
-
-  ASSERT_OK(Put("foo1", value));
-  ASSERT_OK(Put("z", ""));
-  Flush();
-  ASSERT_OK(Put("foo2", value));
-  ASSERT_OK(Put("z", ""));
-  Flush();
-
-  // This probably returns non-OK, but we rely on the next Put()
-  // to determine the DB is frozen.
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_NOK(Put("foo", "bar"));
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
 }

 void IngestOneKeyValue(DBImpl* db, const std::string& key,
@@ -50,7 +50,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase) {
      keys[i] = i;
    }
    if (ordered_insert == 0) {
-      RandomShuffle(std::begin(keys), std::end(keys), rnd.Next());
+      std::random_shuffle(std::begin(keys), std::end(keys));
    }
    for (int max_background_compactions = 1; max_background_compactions < 4;
         max_background_compactions += 2) {
@@ -90,9 +90,6 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
      mutex_.Unlock();
      status = AtomicFlushMemTables(cfds, FlushOptions(),
                                    FlushReason::kGetLiveFiles);
-      if (status.IsColumnFamilyDropped()) {
-        status = Status::OK();
-      }
      mutex_.Lock();
    } else {
      for (auto cfd : *versions_->GetColumnFamilySet()) {
@@ -106,10 +103,8 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
        TEST_SYNC_POINT("DBImpl::GetLiveFiles:2");
        mutex_.Lock();
        cfd->UnrefAndTryDelete();
-        if (!status.ok() && !status.IsColumnFamilyDropped()) {
+        if (!status.ok()) {
          break;
-        } else if (status.IsColumnFamilyDropped()) {
-          status = Status::OK();
        }
      }
    }
@@ -123,33 +118,27 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
    }
  }

-  // Make a set of all of the live table and blob files
-  std::vector<uint64_t> live_table_files;
-  std::vector<uint64_t> live_blob_files;
+  // Make a set of all of the live *.sst files
+  std::vector<FileDescriptor> live;
  for (auto cfd : *versions_->GetColumnFamilySet()) {
    if (cfd->IsDropped()) {
      continue;
    }
-    cfd->current()->AddLiveFiles(&live_table_files, &live_blob_files);
+    cfd->current()->AddLiveFiles(&live);
  }

  ret.clear();
-  ret.reserve(live_table_files.size() + live_blob_files.size() +
-              3);  // for CURRENT + MANIFEST + OPTIONS
+  ret.reserve(live.size() + 3);  // *.sst + CURRENT + MANIFEST + OPTIONS

  // create names of the live files. The names are not absolute
  // paths, instead they are relative to dbname_;
-  for (const auto& table_file_number : live_table_files) {
-    ret.emplace_back(MakeTableFileName("", table_file_number));
+  for (const auto& live_file : live) {
+    ret.push_back(MakeTableFileName("", live_file.GetNumber()));
  }

-  for (const auto& blob_file_number : live_blob_files) {
-    ret.emplace_back(BlobFileName("", blob_file_number));
-  }
-
-  ret.emplace_back(CurrentFileName(""));
-  ret.emplace_back(DescriptorFileName("", versions_->manifest_file_number()));
-  ret.emplace_back(OptionsFileName("", versions_->options_file_number()));
+  ret.push_back(CurrentFileName(""));
+  ret.push_back(DescriptorFileName("", versions_->manifest_file_number()));
+  ret.push_back(OptionsFileName("", versions_->options_file_number()));

  // find length of manifest file while holding the mutex lock
  *manifest_file_size = versions_->manifest_file_size();
@@ -21,6 +21,7 @@
 #include <stdexcept>
 #include <string>
 #include <unordered_map>
+#include <unordered_set>
 #include <utility>
 #include <vector>

@@ -150,7 +151,7 @@ DBImpl::DBImpl(const DBOptions& options, const std::string& dbname,
      own_info_log_(options.info_log == nullptr),
      initial_db_options_(SanitizeOptions(dbname, options)),
      env_(initial_db_options_.env),
-      fs_(initial_db_options_.env->GetFileSystem()),
+      fs_(initial_db_options_.file_system),
      immutable_db_options_(initial_db_options_),
      mutable_db_options_(initial_db_options_),
      stats_(immutable_db_options_.statistics.get()),
@@ -311,11 +312,6 @@ Status DBImpl::ResumeImpl() {
    s = bg_error;
  }

-  // Make sure the IO Status stored in version set is set to OK.
-  if (s.ok()) {
-    versions_->SetIOStatusOK();
-  }
-
  // We cannot guarantee consistency of the WAL. So force flush Memtables of
  // all the column families
  if (s.ok()) {
@@ -870,7 +866,9 @@ void DBImpl::DumpStats() {
 Status DBImpl::TablesRangeTombstoneSummary(ColumnFamilyHandle* column_family,
                                           int max_entries_to_print,
                                           std::string* out_str) {
-  auto* cfh = static_cast_with_check<ColumnFamilyHandleImpl>(column_family);
+  auto* cfh =
+      static_cast_with_check<ColumnFamilyHandleImpl, ColumnFamilyHandle>(
+          column_family);
  ColumnFamilyData* cfd = cfh->cfd();

  SuperVersion* super_version = cfd->GetReferencedSuperVersion(this);
@@ -892,9 +890,9 @@ void DBImpl::ScheduleBgLogWriterClose(JobContext* job_context) {
  }
 }

-FSDirectory* DBImpl::GetDataDir(ColumnFamilyData* cfd, size_t path_id) const {
+Directory* DBImpl::GetDataDir(ColumnFamilyData* cfd, size_t path_id) const {
  assert(cfd);
-  FSDirectory* ret_dir = cfd->GetDataDir(path_id);
+  Directory* ret_dir = cfd->GetDataDir(path_id);
  if (ret_dir == nullptr) {
    return directories_.GetDataDir(path_id);
  }
@@ -1008,12 +1006,12 @@ Status DBImpl::SetDBOptions(
    }
    if (s.ok()) {
      const BGJobLimits current_bg_job_limits =
-          GetBGJobLimits(mutable_db_options_.max_background_flushes,
+          GetBGJobLimits(immutable_db_options_.max_background_flushes,
                         mutable_db_options_.max_background_compactions,
                         mutable_db_options_.max_background_jobs,
                         /* parallelize_compactions */ true);
      const BGJobLimits new_bg_job_limits = GetBGJobLimits(
-          new_options.max_background_flushes,
+          immutable_db_options_.max_background_flushes,
          new_options.max_background_compactions,
          new_options.max_background_jobs, /* parallelize_compactions */ true);

@@ -1149,25 +1147,25 @@ int DBImpl::FindMinimumEmptyLevelFitting(

 Status DBImpl::FlushWAL(bool sync) {
  if (manual_wal_flush_) {
-    IOStatus io_s;
+    Status s;
    {
      // We need to lock log_write_mutex_ since logs_ might change concurrently
      InstrumentedMutexLock wl(&log_write_mutex_);
      log::Writer* cur_log_writer = logs_.back().writer;
-      io_s = cur_log_writer->WriteBuffer();
+      s = cur_log_writer->WriteBuffer();
    }
-    if (!io_s.ok()) {
+    if (!s.ok()) {
      ROCKS_LOG_ERROR(immutable_db_options_.info_log, "WAL flush error %s",
-                      io_s.ToString().c_str());
+                      s.ToString().c_str());
      // In case there is a fs error we should set it globally to prevent the
      // future writes
-      IOStatusCheck(io_s);
+      WriteStatusCheck(s);
      // whether sync or not, we should abort the rest of function upon error
-      return std::move(io_s);
+      return s;
    }
    if (!sync) {
      ROCKS_LOG_DEBUG(immutable_db_options_.info_log, "FlushWAL sync=false");
-      return std::move(io_s);
+      return s;
    }
  }
  if (!sync) {
@@ -1219,23 +1217,14 @@ Status DBImpl::SyncWAL() {
  TEST_SYNC_POINT("DBWALTest::SyncWALNotWaitWrite:1");
  RecordTick(stats_, WAL_FILE_SYNCED);
  Status status;
-  IOStatus io_s;
  for (log::Writer* log : logs_to_sync) {
-    io_s = log->file()->SyncWithoutFlush(immutable_db_options_.use_fsync);
-    if (!io_s.ok()) {
-      status = io_s;
+    status = log->file()->SyncWithoutFlush(immutable_db_options_.use_fsync);
+    if (!status.ok()) {
      break;
    }
  }
-  if (!io_s.ok()) {
-    ROCKS_LOG_ERROR(immutable_db_options_.info_log, "WAL Sync error %s",
-                    io_s.ToString().c_str());
-    // In case there is a fs error we should set it globally to prevent the
-    // future writes
-    IOStatusCheck(io_s);
-  }
  if (status.ok() && need_log_dir_sync) {
-    status = directories_.GetWalDir()->Fsync(IOOptions(), nullptr);
+    status = directories_.GetWalDir()->Fsync();
  }
  TEST_SYNC_POINT("DBWALTest::SyncWALNotWaitWrite:2");

@@ -1260,7 +1249,7 @@ Status DBImpl::LockWAL() {
    // future writes
    WriteStatusCheck(status);
  }
-  return std::move(status);
+  return status;
 }

 Status DBImpl::UnlockWAL() {
@@ -1311,7 +1300,7 @@ bool DBImpl::SetPreserveDeletesSequenceNumber(SequenceNumber seqnum) {

 InternalIterator* DBImpl::NewInternalIterator(
    Arena* arena, RangeDelAggregator* range_del_agg, SequenceNumber sequence,
-    ColumnFamilyHandle* column_family, bool allow_unprepared_value) {
+    ColumnFamilyHandle* column_family) {
  ColumnFamilyData* cfd;
  if (column_family == nullptr) {
    cfd = default_cf_handle_->cfd();
@@ -1325,7 +1314,7 @@ InternalIterator* DBImpl::NewInternalIterator(
  mutex_.Unlock();
  ReadOptions roptions;
  return NewInternalIterator(roptions, cfd, super_version, arena, range_del_agg,
-                             sequence, allow_unprepared_value);
+                             sequence);
 }

 void DBImpl::SchedulePurge() {
@@ -1448,8 +1437,7 @@ InternalIterator* DBImpl::NewInternalIterator(const ReadOptions& read_options,
                                              SuperVersion* super_version,
                                              Arena* arena,
                                              RangeDelAggregator* range_del_agg,
-                                              SequenceNumber sequence,
-                                              bool allow_unprepared_value) {
+                                              SequenceNumber sequence) {
  InternalIterator* internal_iter;
  assert(arena != nullptr);
  assert(range_del_agg != nullptr);
@@ -1481,8 +1469,7 @@ InternalIterator* DBImpl::NewInternalIterator(const ReadOptions& read_options,
    // Collect iterators for files in L0 - Ln
    if (read_options.read_tier != kMemtableTier) {
      super_version->current->AddIterators(read_options, file_options_,
-                                           &merge_iter_builder, range_del_agg,
-                                           allow_unprepared_value);
+                                           &merge_iter_builder, range_del_agg);
    }
    internal_iter = merge_iter_builder.Finish();
    IterState* cleanup =
@@ -1509,38 +1496,16 @@ ColumnFamilyHandle* DBImpl::PersistentStatsColumnFamily() const {
 Status DBImpl::Get(const ReadOptions& read_options,
                   ColumnFamilyHandle* column_family, const Slice& key,
                   PinnableSlice* value) {
-  return Get(read_options, column_family, key, value, /*timestamp=*/nullptr);
-}
-
-Status DBImpl::Get(const ReadOptions& read_options,
-                   ColumnFamilyHandle* column_family, const Slice& key,
-                   PinnableSlice* value, std::string* timestamp) {
  GetImplOptions get_impl_options;
  get_impl_options.column_family = column_family;
  get_impl_options.value = value;
-  get_impl_options.timestamp = timestamp;
-  Status s = GetImpl(read_options, key, get_impl_options);
-  return s;
+  return GetImpl(read_options, key, get_impl_options);
 }

 Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
-                       GetImplOptions& get_impl_options) {
+                       GetImplOptions get_impl_options) {
  assert(get_impl_options.value != nullptr ||
         get_impl_options.merge_operands != nullptr);
-
-#ifndef NDEBUG
-  assert(get_impl_options.column_family);
-  ColumnFamilyHandle* cf = get_impl_options.column_family;
-  const Comparator* const ucmp = cf->GetComparator();
-  assert(ucmp);
-  if (ucmp->timestamp_size() > 0) {
-    assert(read_options.timestamp);
-    assert(read_options.timestamp->size() == ucmp->timestamp_size());
-  } else {
-    assert(!read_options.timestamp);
-  }
-#endif  // NDEBUG
-
  PERF_CPU_TIMER_GUARD(get_cpu_nanos, env_);
  StopWatch sw(env_, stats_, DB_GET);
  PERF_TIMER_GUARD(get_snapshot_time);
@@ -1618,14 +1583,10 @@ Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
  bool skip_memtable = (read_options.read_tier == kPersistedTier &&
                        has_unpersisted_data_.load(std::memory_order_relaxed));
  bool done = false;
-  const Comparator* comparator =
-      get_impl_options.column_family->GetComparator();
-  size_t ts_sz = comparator->timestamp_size();
-  std::string* timestamp = ts_sz > 0 ? get_impl_options.timestamp : nullptr;
  if (!skip_memtable) {
    // Get value associated with key
    if (get_impl_options.get_value) {
-      if (sv->mem->Get(lkey, get_impl_options.value->GetSelf(), timestamp, &s,
+      if (sv->mem->Get(lkey, get_impl_options.value->GetSelf(), &s,
                       &merge_context, &max_covering_tombstone_seq,
                       read_options, get_impl_options.callback,
                       get_impl_options.is_blob_index)) {
@@ -1633,10 +1594,9 @@ Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
        get_impl_options.value->PinSelf();
        RecordTick(stats_, MEMTABLE_HIT);
      } else if ((s.ok() || s.IsMergeInProgress()) &&
-                 sv->imm->Get(lkey, get_impl_options.value->GetSelf(),
-                              timestamp, &s, &merge_context,
-                              &max_covering_tombstone_seq, read_options,
-                              get_impl_options.callback,
+                 sv->imm->Get(lkey, get_impl_options.value->GetSelf(), &s,
+                              &merge_context, &max_covering_tombstone_seq,
+                              read_options, get_impl_options.callback,
                              get_impl_options.is_blob_index)) {
        done = true;
        get_impl_options.value->PinSelf();
@@ -1645,9 +1605,9 @@ Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
    } else {
      // Get Merge Operands associated with key, Merge Operands should not be
      // merged and raw values should be returned to the user.
-      if (sv->mem->Get(lkey, /*value*/ nullptr, /*timestamp=*/nullptr, &s,
-                       &merge_context, &max_covering_tombstone_seq,
-                       read_options, nullptr, nullptr, false)) {
+      if (sv->mem->Get(lkey, nullptr, &s, &merge_context,
+                       &max_covering_tombstone_seq, read_options, nullptr,
+                       nullptr, false)) {
        done = true;
        RecordTick(stats_, MEMTABLE_HIT);
      } else if ((s.ok() || s.IsMergeInProgress()) &&
@@ -1666,8 +1626,8 @@ Status DBImpl::GetImpl(const ReadOptions& read_options, const Slice& key,
  if (!done) {
    PERF_TIMER_GUARD(get_from_output_files_time);
    sv->current->Get(
-        read_options, lkey, get_impl_options.value, timestamp, &s,
-        &merge_context, &max_covering_tombstone_seq,
+        read_options, lkey, get_impl_options.value, &s, &merge_context,
+        &max_covering_tombstone_seq,
        get_impl_options.get_value ? get_impl_options.value_found : nullptr,
        nullptr, nullptr,
        get_impl_options.get_value ? get_impl_options.callback : nullptr,
@@ -1715,34 +1675,12 @@ std::vector<Status> DBImpl::MultiGet(
    const ReadOptions& read_options,
    const std::vector<ColumnFamilyHandle*>& column_family,
    const std::vector<Slice>& keys, std::vector<std::string>* values) {
-  return MultiGet(read_options, column_family, keys, values,
-                  /*timestamps=*/nullptr);
-}
-
-std::vector<Status> DBImpl::MultiGet(
-    const ReadOptions& read_options,
-    const std::vector<ColumnFamilyHandle*>& column_family,
-    const std::vector<Slice>& keys, std::vector<std::string>* values,
-    std::vector<std::string>* timestamps) {
  PERF_CPU_TIMER_GUARD(get_cpu_nanos, env_);
  StopWatch sw(env_, stats_, DB_MULTIGET);
  PERF_TIMER_GUARD(get_snapshot_time);

-#ifndef NDEBUG
-  for (const auto* cfh : column_family) {
-    assert(cfh);
-    const Comparator* const ucmp = cfh->GetComparator();
-    assert(ucmp);
-    if (ucmp->timestamp_size() > 0) {
-      assert(read_options.timestamp);
-      assert(ucmp->timestamp_size() == read_options.timestamp->size());
-    } else {
-      assert(!read_options.timestamp);
-    }
-  }
-#endif  // NDEBUG
-
  SequenceNumber consistent_seqnum;
+  ;

  std::unordered_map<uint32_t, MultiGetColumnFamilyData> multiget_cf_data(
      column_family.size());
@@ -1773,9 +1711,6 @@ std::vector<Status> DBImpl::MultiGet(
  size_t num_keys = keys.size();
  std::vector<Status> stat_list(num_keys);
  values->resize(num_keys);
-  if (timestamps) {
-    timestamps->resize(num_keys);
-  }

  // Keep track of bytes that we read for statistics-recording later
  uint64_t bytes_read = 0;
@@ -1786,16 +1721,13 @@ std::vector<Status> DBImpl::MultiGet(
  // s is both in/out. When in, s could either be OK or MergeInProgress.
  // merge_operands will contain the sequence of merges in the latter case.
  size_t num_found = 0;
-  size_t keys_read;
-  for (keys_read = 0; keys_read < num_keys; ++keys_read) {
+  for (size_t i = 0; i < num_keys; ++i) {
    merge_context.Clear();
-    Status& s = stat_list[keys_read];
-    std::string* value = &(*values)[keys_read];
-    std::string* timestamp = timestamps ? &(*timestamps)[keys_read] : nullptr;
+    Status& s = stat_list[i];
+    std::string* value = &(*values)[i];

-    LookupKey lkey(keys[keys_read], consistent_seqnum, read_options.timestamp);
-    auto cfh =
-        static_cast_with_check<ColumnFamilyHandleImpl>(column_family[keys_read]);
+    LookupKey lkey(keys[i], consistent_seqnum);
+    auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family[i]);
    SequenceNumber max_covering_tombstone_seq = 0;
    auto mgd_iter = multiget_cf_data.find(cfh->cfd()->GetID());
    assert(mgd_iter != multiget_cf_data.end());
@@ -1806,13 +1738,13 @@ std::vector<Status> DBImpl::MultiGet(
         has_unpersisted_data_.load(std::memory_order_relaxed));
    bool done = false;
    if (!skip_memtable) {
-      if (super_version->mem->Get(lkey, value, timestamp, &s, &merge_context,
+      if (super_version->mem->Get(lkey, value, &s, &merge_context,
                                  &max_covering_tombstone_seq, read_options)) {
        done = true;
        RecordTick(stats_, MEMTABLE_HIT);
-      } else if (super_version->imm->Get(
-                     lkey, value, timestamp, &s, &merge_context,
-                     &max_covering_tombstone_seq, read_options)) {
+      } else if (super_version->imm->Get(lkey, value, &s, &merge_context,
+                                         &max_covering_tombstone_seq,
+                                         read_options)) {
        done = true;
        RecordTick(stats_, MEMTABLE_HIT);
      }
@@ -1820,9 +1752,8 @@ std::vector<Status> DBImpl::MultiGet(
    if (!done) {
      PinnableSlice pinnable_val;
      PERF_TIMER_GUARD(get_from_output_files_time);
-      super_version->current->Get(read_options, lkey, &pinnable_val, timestamp,
-                                  &s, &merge_context,
-                                  &max_covering_tombstone_seq);
+      super_version->current->Get(read_options, lkey, &pinnable_val, &s,
+                                  &merge_context, &max_covering_tombstone_seq);
      value->assign(pinnable_val.data(), pinnable_val.size());
      RecordTick(stats_, MEMTABLE_MISS);
    }
@@ -1831,22 +1762,6 @@ std::vector<Status> DBImpl::MultiGet(
      bytes_read += value->size();
      num_found++;
    }
-
-    if (read_options.deadline.count() &&
-        env_->NowMicros() >
-            static_cast<uint64_t>(read_options.deadline.count())) {
-      break;
-    }
-  }
-
-  if (keys_read < num_keys) {
-    // The only reason to break out of the loop is when the deadline is
-    // exceeded
-    assert(env_->NowMicros() >
-        static_cast<uint64_t>(read_options.deadline.count()));
-    for (++keys_read; keys_read < num_keys; ++keys_read) {
-      stat_list[keys_read] = Status::TimedOut();
-    }
  }

  // Post processing (decrement reference counts and record statistics)
@@ -2000,39 +1915,14 @@ void DBImpl::MultiGet(const ReadOptions& read_options, const size_t num_keys,
                      ColumnFamilyHandle** column_families, const Slice* keys,
                      PinnableSlice* values, Status* statuses,
                      const bool sorted_input) {
-  return MultiGet(read_options, num_keys, column_families, keys, values,
-                  /*timestamps=*/nullptr, statuses, sorted_input);
-}
-
-void DBImpl::MultiGet(const ReadOptions& read_options, const size_t num_keys,
-                      ColumnFamilyHandle** column_families, const Slice* keys,
-                      PinnableSlice* values, std::string* timestamps,
-                      Status* statuses, const bool sorted_input) {
  if (num_keys == 0) {
    return;
  }
-
-#ifndef NDEBUG
-  for (size_t i = 0; i < num_keys; ++i) {
-    ColumnFamilyHandle* cfh = column_families[i];
-    assert(cfh);
-    const Comparator* const ucmp = cfh->GetComparator();
-    assert(ucmp);
-    if (ucmp->timestamp_size() > 0) {
-      assert(read_options.timestamp);
-      assert(read_options.timestamp->size() == ucmp->timestamp_size());
-    } else {
-      assert(!read_options.timestamp);
-    }
-  }
-#endif  // NDEBUG
-
  autovector<KeyContext, MultiGetContext::MAX_BATCH_SIZE> key_context;
  autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE> sorted_keys;
  sorted_keys.resize(num_keys);
  for (size_t i = 0; i < num_keys; ++i) {
    key_context.emplace_back(column_families[i], keys[i], &values[i],
-                             timestamps ? &timestamps[i] : nullptr,
                             &statuses[i]);
  }
  for (size_t i = 0; i < num_keys; ++i) {
@@ -2073,31 +1963,14 @@ void DBImpl::MultiGet(const ReadOptions& read_options, const size_t num_keys,
      read_options, nullptr, iter_deref_lambda, &multiget_cf_data,
      &consistent_seqnum);

-  Status s;
-  auto cf_iter = multiget_cf_data.begin();
-  for (; cf_iter != multiget_cf_data.end(); ++cf_iter) {
-    s = MultiGetImpl(read_options, cf_iter->start, cf_iter->num_keys,
-                     &sorted_keys, cf_iter->super_version, consistent_seqnum,
-                     nullptr, nullptr);
-    if (!s.ok()) {
-      break;
-    }
-  }
-  if (!s.ok()) {
-    assert(s.IsTimedOut());
-    for (++cf_iter; cf_iter != multiget_cf_data.end(); ++cf_iter) {
-      for (size_t i = cf_iter->start; i < cf_iter->start + cf_iter->num_keys;
-           ++i) {
-        *sorted_keys[i]->s = Status::TimedOut();
-      }
-    }
-  }
-
-  for (const auto& iter : multiget_cf_data) {
+  for (auto cf_iter = multiget_cf_data.begin();
+       cf_iter != multiget_cf_data.end(); ++cf_iter) {
+    MultiGetImpl(read_options, cf_iter->start, cf_iter->num_keys, &sorted_keys,
+                 cf_iter->super_version, consistent_seqnum, nullptr, nullptr);
    if (!unref_only) {
-      ReturnAndCleanupSuperVersion(iter.cfd, iter.super_version);
+      ReturnAndCleanupSuperVersion(cf_iter->cfd, cf_iter->super_version);
    } else {
-      iter.cfd->GetSuperVersion()->Unref();
+      cf_iter->cfd->GetSuperVersion()->Unref();
    }
  }
 }
@@ -2120,8 +1993,7 @@ struct CompareKeyContext {
    }

    // Both keys are from the same column family
-    int cmp = comparator->CompareWithoutTimestamp(
-        *(lhs->key), /*a_has_ts=*/false, *(rhs->key), /*b_has_ts=*/false);
+    int cmp = comparator->Compare(*(lhs->key), *(rhs->key));
    if (cmp < 0) {
      return true;
    }
@@ -2153,8 +2025,7 @@ void DBImpl::PrepareMultiGetKeys(
        }

        // Both keys are from the same column family
-        int cmp = comparator->CompareWithoutTimestamp(
-            *(lhs->key), /*a_has_ts=*/false, *(rhs->key), /*b_has_ts=*/false);
+        int cmp = comparator->Compare(*(lhs->key), *(rhs->key));
        assert(cmp <= 0);
      }
      index++;
@@ -2172,22 +2043,11 @@ void DBImpl::MultiGet(const ReadOptions& read_options,
                      ColumnFamilyHandle* column_family, const size_t num_keys,
                      const Slice* keys, PinnableSlice* values,
                      Status* statuses, const bool sorted_input) {
-  return MultiGet(read_options, column_family, num_keys, keys, values,
-                  /*timestamp=*/nullptr, statuses, sorted_input);
-}
-
-void DBImpl::MultiGet(const ReadOptions& read_options,
-                      ColumnFamilyHandle* column_family, const size_t num_keys,
-                      const Slice* keys, PinnableSlice* values,
-                      std::string* timestamps, Status* statuses,
-                      const bool sorted_input) {
  autovector<KeyContext, MultiGetContext::MAX_BATCH_SIZE> key_context;
  autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE> sorted_keys;
  sorted_keys.resize(num_keys);
  for (size_t i = 0; i < num_keys; ++i) {
-    key_context.emplace_back(column_family, keys[i], &values[i],
-                             timestamps ? &timestamps[i] : nullptr,
-                             &statuses[i]);
+    key_context.emplace_back(column_family, keys[i], &values[i], &statuses[i]);
  }
  for (size_t i = 0; i < num_keys; ++i) {
    sorted_keys[i] = &key_context[i];
@@ -2240,24 +2100,14 @@ void DBImpl::MultiGetWithCallback(
    consistent_seqnum = callback->max_visible_seq();
  }

-  Status s = MultiGetImpl(read_options, 0, num_keys, sorted_keys,
-                          multiget_cf_data[0].super_version, consistent_seqnum,
-                          nullptr, nullptr);
-  assert(s.ok() || s.IsTimedOut());
+  MultiGetImpl(read_options, 0, num_keys, sorted_keys,
+               multiget_cf_data[0].super_version, consistent_seqnum, nullptr,
+               nullptr);
  ReturnAndCleanupSuperVersion(multiget_cf_data[0].cfd,
                               multiget_cf_data[0].super_version);
 }

-// The actual implementation of batched MultiGet. Parameters -
-// start_key - Index in the sorted_keys vector to start processing from
-// num_keys - Number of keys to lookup, starting with sorted_keys[start_key]
-// sorted_keys - The entire batch of sorted keys for this CF
-//
-// The per key status is returned in the KeyContext structures pointed to by
-// sorted_keys. An overall Status is also returned, with the only possible
-// values being Status::OK() and Status::TimedOut(). The latter indicates
-// that the call exceeded read_options.deadline
-Status DBImpl::MultiGetImpl(
+void DBImpl::MultiGetImpl(
    const ReadOptions& read_options, size_t start_key, size_t num_keys,
    autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE>* sorted_keys,
    SuperVersion* super_version, SequenceNumber snapshot,
@@ -2270,20 +2120,12 @@ Status DBImpl::MultiGetImpl(
  // s is both in/out. When in, s could either be OK or MergeInProgress.
  // merge_operands will contain the sequence of merges in the latter case.
  size_t keys_left = num_keys;
-  Status s;
  while (keys_left) {
-    if (read_options.deadline.count() &&
-        env_->NowMicros() >
-            static_cast<uint64_t>(read_options.deadline.count())) {
-      s = Status::TimedOut();
-      break;
-    }
-
    size_t batch_size = (keys_left > MultiGetContext::MAX_BATCH_SIZE)
                            ? MultiGetContext::MAX_BATCH_SIZE
                            : keys_left;
    MultiGetContext ctx(sorted_keys, start_key + num_keys - keys_left,
-                        batch_size, snapshot, read_options);
+                        batch_size, snapshot);
    MultiGetRange range = ctx.GetMultiGetRange();
    bool lookup_current = false;

@@ -2321,21 +2163,13 @@ Status DBImpl::MultiGetImpl(
  PERF_TIMER_GUARD(get_post_process_time);
  size_t num_found = 0;
  uint64_t bytes_read = 0;
-  for (size_t i = start_key; i < start_key + num_keys - keys_left; ++i) {
+  for (size_t i = start_key; i < start_key + num_keys; ++i) {
    KeyContext* key = (*sorted_keys)[i];
    if (key->s->ok()) {
      bytes_read += key->value->size();
      num_found++;
    }
  }
-  if (keys_left) {
-    assert(s.IsTimedOut());
-    for (size_t i = start_key + num_keys - keys_left; i < start_key + num_keys;
-         ++i) {
-      KeyContext* key = (*sorted_keys)[i];
-      *key->s = Status::TimedOut();
-    }
-  }

  RecordTick(stats_, NUMBER_MULTIGET_CALLS);
  RecordTick(stats_, NUMBER_MULTIGET_KEYS_READ, num_keys);
@@ -2344,8 +2178,6 @@ Status DBImpl::MultiGetImpl(
  RecordInHistogram(stats_, BYTES_PER_MULTIGET, bytes_read);
  PERF_COUNTER_ADD(multiget_read_bytes, bytes_read);
  PERF_TIMER_STOP(get_post_process_time);
-
-  return s;
 }

 Status DBImpl::CreateColumnFamily(const ColumnFamilyOptions& cf_options,
@@ -2469,7 +2301,7 @@ Status DBImpl::CreateColumnFamilyImpl(const ColumnFamilyOptions& cf_options,
      auto* cfd =
          versions_->GetColumnFamilySet()->GetColumnFamily(column_family_name);
      assert(cfd != nullptr);
-      std::map<std::string, std::shared_ptr<FSDirectory>> dummy_created_dirs;
+      std::map<std::string, std::shared_ptr<Directory>> dummy_created_dirs;
      s = cfd->AddDirectories(&dummy_created_dirs);
    }
    if (s.ok()) {
@@ -2604,8 +2436,7 @@ Status DBImpl::DropColumnFamilyImpl(ColumnFamilyHandle* column_family) {

 bool DBImpl::KeyMayExist(const ReadOptions& read_options,
                         ColumnFamilyHandle* column_family, const Slice& key,
-                         std::string* value, std::string* timestamp,
-                         bool* value_found) {
+                         std::string* value, bool* value_found) {
  assert(value != nullptr);
  if (value_found != nullptr) {
    // falsify later if key-may-exist but can't fetch value
@@ -2618,7 +2449,6 @@ bool DBImpl::KeyMayExist(const ReadOptions& read_options,
  get_impl_options.column_family = column_family;
  get_impl_options.value = &pinnable_val;
  get_impl_options.value_found = value_found;
-  get_impl_options.timestamp = timestamp;
  auto s = GetImpl(roptions, key, get_impl_options);
  value->assign(pinnable_val.data(), pinnable_val.size());

@@ -2634,12 +2464,6 @@ Iterator* DBImpl::NewIterator(const ReadOptions& read_options,
    return NewErrorIterator(
        Status::NotSupported("Managed iterator is not supported anymore."));
  }
-  // We will eventually support deadline for iterators too, but safeguard
-  // for now
-  if (read_options.deadline != std::chrono::microseconds::zero()) {
-    return NewErrorIterator(
-        Status::NotSupported("ReadOptions deadline is not supported"));
-  }
  Iterator* result = nullptr;
  if (read_options.read_tier == kPersistedTier) {
    return NewErrorIterator(Status::NotSupported(
@@ -2664,8 +2488,7 @@ Iterator* DBImpl::NewIterator(const ReadOptions& read_options,

 #else
    SuperVersion* sv = cfd->GetReferencedSuperVersion(this);
-    auto iter = new ForwardIterator(this, read_options, cfd, sv,
-                                    /* allow_unprepared_value */ true);
+    auto iter = new ForwardIterator(this, read_options, cfd, sv);
    result = NewDBIterator(
        env_, read_options, *cfd->ioptions(), sv->mutable_cf_options,
        cfd->user_comparator(), iter, kMaxSequenceNumber,
@@ -2742,8 +2565,7 @@ ArenaWrappedDBIter* DBImpl::NewIteratorImpl(const ReadOptions& read_options,

  InternalIterator* internal_iter =
      NewInternalIterator(read_options, cfd, sv, db_iter->GetArena(),
-                          db_iter->GetRangeDelAggregator(), snapshot,
-                          /* allow_unprepared_value */ true);
+                          db_iter->GetRangeDelAggregator(), snapshot);
  db_iter->SetIterUnderDBIter(internal_iter);

  return db_iter;
@@ -2771,8 +2593,7 @@ Status DBImpl::NewIterators(
    for (auto cfh : column_families) {
      auto cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh)->cfd();
      SuperVersion* sv = cfd->GetReferencedSuperVersion(this);
-      auto iter = new ForwardIterator(this, read_options, cfd, sv,
-                                      /* allow_unprepared_value */ true);
+      auto iter = new ForwardIterator(this, read_options, cfd, sv);
      iterators->push_back(NewDBIterator(
          env_, read_options, *cfd->ioptions(), sv->mutable_cf_options,
          cfd->user_comparator(), iter, kMaxSequenceNumber,
@@ -3641,8 +3462,12 @@ Status DBImpl::Close() {
 Status DB::ListColumnFamilies(const DBOptions& db_options,
                              const std::string& name,
                              std::vector<std::string>* column_families) {
-  const std::shared_ptr<FileSystem>& fs = db_options.env->GetFileSystem();
-  return VersionSet::ListColumnFamilies(column_families, name, fs.get());
+  FileSystem* fs = db_options.file_system.get();
+  LegacyFileSystemWrapper legacy_fs(db_options.env);
+  if (!fs) {
+    fs = &legacy_fs;
+  }
+  return VersionSet::ListColumnFamilies(column_families, name, fs);
 }

 Snapshot::~Snapshot() {}
@@ -3686,15 +3511,24 @@ Status DestroyDB(const std::string& dbname, const Options& options,
      }
    }

-    std::set<std::string> paths;
-    for (const DbPath& db_path : options.db_paths) {
-      paths.insert(db_path.path);
+    std::vector<std::string> paths;
+
+    for (const auto& path : options.db_paths) {
+      paths.emplace_back(path.path);
    }
-    for (const ColumnFamilyDescriptor& cf : column_families) {
-      for (const DbPath& cf_path : cf.options.cf_paths) {
-        paths.insert(cf_path.path);
+    for (const auto& cf : column_families) {
+      for (const auto& path : cf.options.cf_paths) {
+        paths.emplace_back(path.path);
      }
    }
+
+    // Remove duplicate paths.
+    // Note that we compare only the actual paths but not path ids.
+    // This reason is that same path can appear at different path_ids
+    // for different column families.
+    std::sort(paths.begin(), paths.end());
+    paths.erase(std::unique(paths.begin(), paths.end()), paths.end());
+
    for (const auto& path : paths) {
      if (env->GetChildren(path, &filenames).ok()) {
        for (const auto& fname : filenames) {
@@ -3985,9 +3819,8 @@ Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
  *found_record_for_key = false;

  // Check if there is a record for this key in the latest memtable
-  sv->mem->Get(lkey, nullptr, nullptr, &s, &merge_context,
-               &max_covering_tombstone_seq, seq, read_options,
-               nullptr /*read_callback*/, is_blob_index);
+  sv->mem->Get(lkey, nullptr, &s, &merge_context, &max_covering_tombstone_seq,
+               seq, read_options, nullptr /*read_callback*/, is_blob_index);

  if (!(s.ok() || s.IsNotFound() || s.IsMergeInProgress())) {
    // unexpected error reading memtable.
@@ -4012,9 +3845,8 @@ Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
  }

  // Check if there is a record for this key in the immutable memtables
-  sv->imm->Get(lkey, nullptr, nullptr, &s, &merge_context,
-               &max_covering_tombstone_seq, seq, read_options,
-               nullptr /*read_callback*/, is_blob_index);
+  sv->imm->Get(lkey, nullptr, &s, &merge_context, &max_covering_tombstone_seq,
+               seq, read_options, nullptr /*read_callback*/, is_blob_index);

  if (!(s.ok() || s.IsNotFound() || s.IsMergeInProgress())) {
    // unexpected error reading memtable.
@@ -4039,7 +3871,7 @@ Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
  }

  // Check if there is a record for this key in the immutable memtables
-  sv->imm->GetFromHistory(lkey, nullptr, nullptr, &s, &merge_context,
+  sv->imm->GetFromHistory(lkey, nullptr, &s, &merge_context,
                          &max_covering_tombstone_seq, seq, read_options,
                          is_blob_index);

@@ -4067,7 +3899,7 @@ Status DBImpl::GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
  // SST files if cache_only=true?
  if (!cache_only) {
    // Check tables
-    sv->current->Get(read_options, lkey, nullptr, nullptr, &s, &merge_context,
+    sv->current->Get(read_options, lkey, nullptr, &s, &merge_context,
                     &max_covering_tombstone_seq, nullptr /* value_found */,
                     found_record_for_key, seq, nullptr /*read_callback*/,
                     is_blob_index);
@@ -82,13 +82,13 @@ struct MemTableInfo;
 // Class to maintain directories for all database paths other than main one.
 class Directories {
 public:
-  IOStatus SetDirectories(FileSystem* fs, const std::string& dbname,
-                          const std::string& wal_dir,
-                          const std::vector<DbPath>& data_paths);
+  Status SetDirectories(Env* env, const std::string& dbname,
+                        const std::string& wal_dir,
+                        const std::vector<DbPath>& data_paths);

-  FSDirectory* GetDataDir(size_t path_id) const {
+  Directory* GetDataDir(size_t path_id) const {
    assert(path_id < data_dirs_.size());
-    FSDirectory* ret_dir = data_dirs_[path_id].get();
+    Directory* ret_dir = data_dirs_[path_id].get();
    if (ret_dir == nullptr) {
      // Should use db_dir_
      return db_dir_.get();
@@ -96,19 +96,19 @@ class Directories {
    return ret_dir;
  }

-  FSDirectory* GetWalDir() {
+  Directory* GetWalDir() {
    if (wal_dir_) {
      return wal_dir_.get();
    }
    return db_dir_.get();
  }

-  FSDirectory* GetDbDir() { return db_dir_.get(); }
+  Directory* GetDbDir() { return db_dir_.get(); }

 private:
-  std::unique_ptr<FSDirectory> db_dir_;
-  std::vector<std::unique_ptr<FSDirectory>> data_dirs_;
-  std::unique_ptr<FSDirectory> wal_dir_;
+  std::unique_ptr<Directory> db_dir_;
+  std::vector<std::unique_ptr<Directory>> data_dirs_;
+  std::unique_ptr<Directory> wal_dir_;
 };

 // While DB is the public interface of RocksDB, and DBImpl is the actual
@@ -163,9 +163,6 @@ class DBImpl : public DB {
  virtual Status Get(const ReadOptions& options,
                     ColumnFamilyHandle* column_family, const Slice& key,
                     PinnableSlice* value) override;
-  virtual Status Get(const ReadOptions& options,
-                     ColumnFamilyHandle* column_family, const Slice& key,
-                     PinnableSlice* value, std::string* timestamp) override;

  using DB::GetMergeOperands;
  Status GetMergeOperands(const ReadOptions& options,
@@ -188,11 +185,6 @@ class DBImpl : public DB {
      const std::vector<ColumnFamilyHandle*>& column_family,
      const std::vector<Slice>& keys,
      std::vector<std::string>* values) override;
-  virtual std::vector<Status> MultiGet(
-      const ReadOptions& options,
-      const std::vector<ColumnFamilyHandle*>& column_family,
-      const std::vector<Slice>& keys, std::vector<std::string>* values,
-      std::vector<std::string>* timestamps) override;

  // This MultiGet is a batched version, which may be faster than calling Get
  // multiple times, especially if the keys have some spatial locality that
@@ -206,22 +198,11 @@ class DBImpl : public DB {
                        const size_t num_keys, const Slice* keys,
                        PinnableSlice* values, Status* statuses,
                        const bool sorted_input = false) override;
-  virtual void MultiGet(const ReadOptions& options,
-                        ColumnFamilyHandle* column_family,
-                        const size_t num_keys, const Slice* keys,
-                        PinnableSlice* values, std::string* timestamps,
-                        Status* statuses,
-                        const bool sorted_input = false) override;

  virtual void MultiGet(const ReadOptions& options, const size_t num_keys,
                        ColumnFamilyHandle** column_families, const Slice* keys,
                        PinnableSlice* values, Status* statuses,
                        const bool sorted_input = false) override;
-  virtual void MultiGet(const ReadOptions& options, const size_t num_keys,
-                        ColumnFamilyHandle** column_families, const Slice* keys,
-                        PinnableSlice* values, std::string* timestamps,
-                        Status* statuses,
-                        const bool sorted_input = false) override;

  virtual void MultiGetWithCallback(
      const ReadOptions& options, ColumnFamilyHandle* column_family,
@@ -249,7 +230,7 @@ class DBImpl : public DB {
  using DB::KeyMayExist;
  virtual bool KeyMayExist(const ReadOptions& options,
                           ColumnFamilyHandle* column_family, const Slice& key,
-                           std::string* value, std::string* timestamp,
+                           std::string* value,
                           bool* value_found = nullptr) override;

  using DB::NewIterator;
@@ -452,7 +433,6 @@ class DBImpl : public DB {
  struct GetImplOptions {
    ColumnFamilyHandle* column_family = nullptr;
    PinnableSlice* value = nullptr;
-    std::string* timestamp = nullptr;
    bool* value_found = nullptr;
    ReadCallback* callback = nullptr;
    bool* is_blob_index = nullptr;
@@ -475,7 +455,7 @@ class DBImpl : public DB {
  // If get_impl_options.get_value = false get merge operands associated with
  // get_impl_options.key via get_impl_options.merge_operands
  Status GetImpl(const ReadOptions& options, const Slice& key,
-                 GetImplOptions& get_impl_options);
+                 GetImplOptions get_impl_options);

  ArenaWrappedDBIter* NewIteratorImpl(const ReadOptions& options,
                                      ColumnFamilyData* cfd,
@@ -581,14 +561,9 @@ class DBImpl : public DB {
  // Return an internal iterator over the current state of the database.
  // The keys of this iterator are internal keys (see format.h).
  // The returned iterator should be deleted when no longer needed.
-  // If allow_unprepared_value is true, the returned iterator may defer reading
-  // the value and so will require PrepareValue() to be called before value();
-  // allow_unprepared_value = false is convenient when this optimization is not
-  // useful, e.g. when reading the whole column family.
  InternalIterator* NewInternalIterator(
      Arena* arena, RangeDelAggregator* range_del_agg, SequenceNumber sequence,
-      ColumnFamilyHandle* column_family = nullptr,
-      bool allow_unprepared_value = false);
+      ColumnFamilyHandle* column_family = nullptr);

  LogsWithPrepTracker* logs_with_prep_tracker() {
    return &logs_with_prep_tracker_;
@@ -714,8 +689,7 @@ class DBImpl : public DB {

  InternalIterator* NewInternalIterator(
      const ReadOptions&, ColumnFamilyData* cfd, SuperVersion* super_version,
-      Arena* arena, RangeDelAggregator* range_del_agg, SequenceNumber sequence,
-      bool allow_unprepared_value);
+      Arena* arena, RangeDelAggregator* range_del_agg, SequenceNumber sequence);

  // hollow transactions shell used for recovery.
  // these will then be passed to TransactionDB so that
@@ -852,9 +826,8 @@ class DBImpl : public DB {
                     std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
                     const bool seq_per_batch, const bool batch_per_txn);

-  static IOStatus CreateAndNewDirectory(
-      FileSystem* fs, const std::string& dirname,
-      std::unique_ptr<FSDirectory>* directory);
+  static Status CreateAndNewDirectory(Env* env, const std::string& dirname,
+                                      std::unique_ptr<Directory>* directory);

  // find stats map from stats_history_ with smallest timestamp in
  // the range of [start_time, end_time)
@@ -969,12 +942,6 @@ class DBImpl : public DB {
  void TEST_WaitForPersistStatsRun(std::function<void()> callback) const;
  bool TEST_IsPersistentStatsEnabled() const;
  size_t TEST_EstimateInMemoryStatsHistorySize() const;
-
-  VersionSet* TEST_GetVersionSet() const { return versions_.get(); }
-
-  const std::unordered_set<uint64_t>& TEST_GetFilesGrabbedForPurge() const {
-    return files_grabbed_for_purge_;
-  }
 #endif  // NDEBUG

 protected:
@@ -1152,15 +1119,6 @@ class DBImpl : public DB {

  virtual bool OwnTablesAndLogs() const { return true; }

-  // REQUIRES: db mutex held when calling this function, but the db mutex can
-  // be released and re-acquired. Db mutex will be held when the function
-  // returns.
-  // After best-efforts recovery, there may be SST files in db/cf paths that are
-  // not referenced in the MANIFEST. We delete these SST files. In the
-  // meantime, we find out the largest file number present in the paths, and
-  // bump up the version set's next_file_number_ to be 1 + largest_file_number.
-  Status FinishBestEffortsRecovery();
-
 private:
  friend class DB;
  friend class ErrorHandler;
@@ -1374,7 +1332,7 @@ class DBImpl : public DB {
  void ReleaseFileNumberFromPendingOutputs(
      std::unique_ptr<std::list<uint64_t>::iterator>& v);

-  IOStatus SyncClosedLogs(JobContext* job_context);
+  Status SyncClosedLogs(JobContext* job_context);

  // Flush the in-memory write buffer to storage.  Switches to a new
  // log-file/memtable and writes a new descriptor iff successful. Then
@@ -1511,25 +1469,21 @@ class DBImpl : public DB {
                         WriteBatch* tmp_batch, size_t* write_with_wal,
                         WriteBatch** to_be_cached_state);

-  IOStatus WriteToWAL(const WriteBatch& merged_batch, log::Writer* log_writer,
-                      uint64_t* log_used, uint64_t* log_size);
+  Status WriteToWAL(const WriteBatch& merged_batch, log::Writer* log_writer,
+                    uint64_t* log_used, uint64_t* log_size);

-  IOStatus WriteToWAL(const WriteThread::WriteGroup& write_group,
-                      log::Writer* log_writer, uint64_t* log_used,
-                      bool need_log_sync, bool need_log_dir_sync,
-                      SequenceNumber sequence);
+  Status WriteToWAL(const WriteThread::WriteGroup& write_group,
+                    log::Writer* log_writer, uint64_t* log_used,
+                    bool need_log_sync, bool need_log_dir_sync,
+                    SequenceNumber sequence);

-  IOStatus ConcurrentWriteToWAL(const WriteThread::WriteGroup& write_group,
-                                uint64_t* log_used,
-                                SequenceNumber* last_sequence, size_t seq_inc);
+  Status ConcurrentWriteToWAL(const WriteThread::WriteGroup& write_group,
+                              uint64_t* log_used, SequenceNumber* last_sequence,
+                              size_t seq_inc);

  // Used by WriteImpl to update bg_error_ if paranoid check is enabled.
  void WriteStatusCheck(const Status& status);

-  // Used by WriteImpl to update bg_error_ when IO error happens, e.g., write
-  // WAL, sync WAL fails, if paranoid check is enabled.
-  void IOStatusCheck(const IOStatus& status);
-
  // Used by WriteImpl to update bg_error_ in case of memtable insert error.
  void MemTableInsertStatusCheck(const Status& memtable_insert_status);

@@ -1644,7 +1598,7 @@ class DBImpl : public DB {

  uint64_t GetMaxTotalWalSize() const;

-  FSDirectory* GetDataDir(ColumnFamilyData* cfd, size_t path_id) const;
+  Directory* GetDataDir(ColumnFamilyData* cfd, size_t path_id) const;

  Status CloseHelper();

@@ -1773,7 +1727,7 @@ class DBImpl : public DB {
  // to have acquired the SuperVersion and pass in a snapshot sequence number
  // in order to construct the LookupKeys. The start_key and num_keys specify
  // the range of keys in the sorted_keys vector for a single column family.
-  Status MultiGetImpl(
+  void MultiGetImpl(
      const ReadOptions& read_options, size_t start_key, size_t num_keys,
      autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE>* sorted_keys,
      SuperVersion* sv, SequenceNumber snap_seqnum, ReadCallback* callback,
@@ -1941,7 +1895,7 @@ class DBImpl : public DB {
  std::unordered_map<uint64_t, PurgeFileInfo> purge_files_;

  // A vector to store the file numbers that have been assigned to certain
-  // JobContext. Current implementation tracks table and blob files only.
+  // JobContext. Current implementation tracks ssts only.
  std::unordered_set<uint64_t> files_grabbed_for_purge_;

  // A queue to store log writers to close
@@ -2067,7 +2021,7 @@ class DBImpl : public DB {
  // REQUIRES: mutex locked
  std::unique_ptr<ROCKSDB_NAMESPACE::RepeatableThread> thread_persist_stats_;

-  // When set, we use a separate queue for writes that don't write to memtable.
+  // When set, we use a separate queue for writes that dont write to memtable.
  // In 2PC these are the writes at Prepare phase.
  const bool two_write_queues_;
  const bool manual_wal_flush_;
@@ -79,7 +79,7 @@ bool DBImpl::RequestCompactionToken(ColumnFamilyData* cfd, bool force,
  return false;
 }

-IOStatus DBImpl::SyncClosedLogs(JobContext* job_context) {
+Status DBImpl::SyncClosedLogs(JobContext* job_context) {
  TEST_SYNC_POINT("DBImpl::SyncClosedLogs:Start");
  mutex_.AssertHeld();
  autovector<log::Writer*, 1> logs_to_sync;
@@ -96,7 +96,7 @@ IOStatus DBImpl::SyncClosedLogs(JobContext* job_context) {
    logs_to_sync.push_back(log.writer);
  }

-  IOStatus io_s;
+  Status s;
  if (!logs_to_sync.empty()) {
    mutex_.Unlock();

@@ -104,34 +104,34 @@ IOStatus DBImpl::SyncClosedLogs(JobContext* job_context) {
      ROCKS_LOG_INFO(immutable_db_options_.info_log,
                     "[JOB %d] Syncing log #%" PRIu64, job_context->job_id,
                     log->get_log_number());
-      io_s = log->file()->Sync(immutable_db_options_.use_fsync);
-      if (!io_s.ok()) {
+      s = log->file()->Sync(immutable_db_options_.use_fsync);
+      if (!s.ok()) {
        break;
      }

      if (immutable_db_options_.recycle_log_file_num > 0) {
-        io_s = log->Close();
-        if (!io_s.ok()) {
+        s = log->Close();
+        if (!s.ok()) {
          break;
        }
      }
    }
-    if (io_s.ok()) {
-      io_s = directories_.GetWalDir()->Fsync(IOOptions(), nullptr);
+    if (s.ok()) {
+      s = directories_.GetWalDir()->Fsync();
    }

    mutex_.Lock();

    // "number <= current_log_number - 1" is equivalent to
    // "number < current_log_number".
-    MarkLogsSynced(current_log_number - 1, true, io_s);
-    if (!io_s.ok()) {
-      error_handler_.SetBGError(io_s, BackgroundErrorReason::kFlush);
+    MarkLogsSynced(current_log_number - 1, true, s);
+    if (!s.ok()) {
+      error_handler_.SetBGError(s, BackgroundErrorReason::kFlush);
      TEST_SYNC_POINT("DBImpl::SyncClosedLogs:Failed");
-      return io_s;
+      return s;
    }
  }
-  return io_s;
+  return s;
 }

 Status DBImpl::FlushMemTableToOutputFile(
@@ -155,6 +155,7 @@ Status DBImpl::FlushMemTableToOutputFile(
      GetCompressionFlush(*cfd->ioptions(), mutable_cf_options), stats_,
      &event_logger_, mutable_cf_options.report_bg_io_stats,
      true /* sync_output_directory */, true /* write_manifest */, thread_pri);
+
  FileMetaData file_meta;

  TEST_SYNC_POINT("DBImpl::FlushMemTableToOutputFile:BeforePickMemtables");
@@ -167,7 +168,6 @@ Status DBImpl::FlushMemTableToOutputFile(
 #endif  // ROCKSDB_LITE

  Status s;
-  IOStatus io_s;
  if (logfile_number_ > 0 &&
      versions_->GetColumnFamilySet()->NumberOfColumnFamilies() > 1) {
    // If there are more than one column families, we need to make sure that
@@ -176,8 +176,7 @@ Status DBImpl::FlushMemTableToOutputFile(
    // flushed SST may contain data from write batches whose updates to
    // other column families are missing.
    // SyncClosedLogs() may unlock and re-lock the db_mutex.
-    io_s = SyncClosedLogs(job_context);
-    s = io_s;
+    s = SyncClosedLogs(job_context);
  } else {
    TEST_SYNC_POINT("DBImpl::SyncClosedLogs:Skip");
  }
@@ -193,7 +192,6 @@ Status DBImpl::FlushMemTableToOutputFile(
  } else {
    flush_job.Cancel();
  }
-  io_s = flush_job.io_status();

  if (s.ok()) {
    InstallSuperVersionAndScheduleWork(cfd, superversion_context,
@@ -208,13 +206,8 @@ Status DBImpl::FlushMemTableToOutputFile(
  }

  if (!s.ok() && !s.IsShutdownInProgress() && !s.IsColumnFamilyDropped()) {
-    if (!io_s.ok() && !io_s.IsShutdownInProgress() &&
-        !io_s.IsColumnFamilyDropped()) {
-      error_handler_.SetBGError(io_s, BackgroundErrorReason::kFlush);
-    } else {
-      Status new_bg_error = s;
-      error_handler_.SetBGError(new_bg_error, BackgroundErrorReason::kFlush);
-    }
+    Status new_bg_error = s;
+    error_handler_.SetBGError(new_bg_error, BackgroundErrorReason::kFlush);
  }
  if (s.ok()) {
 #ifndef ROCKSDB_LITE
@@ -308,7 +301,7 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
  GetSnapshotContext(job_context, &snapshot_seqs,
                     &earliest_write_conflict_snapshot, &snapshot_checker);

-  autovector<FSDirectory*> distinct_output_dirs;
+  autovector<Directory*> distinct_output_dirs;
  autovector<std::string> distinct_output_dir_paths;
  std::vector<std::unique_ptr<FlushJob>> jobs;
  std::vector<MutableCFOptions> all_mutable_cf_options;
@@ -316,7 +309,7 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
  all_mutable_cf_options.reserve(num_cfs);
  for (int i = 0; i < num_cfs; ++i) {
    auto cfd = cfds[i];
-    FSDirectory* data_dir = GetDataDir(cfd, 0U);
+    Directory* data_dir = GetDataDir(cfd, 0U);
    const std::string& curr_path = cfd->ioptions()->cf_paths[0].path;

    // Add to distinct output directories if eligible. Use linear search. Since
@@ -351,7 +344,6 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(

  std::vector<FileMetaData> file_meta(num_cfs);
  Status s;
-  IOStatus io_s;
  assert(num_cfs == static_cast<int>(jobs.size()));

 #ifndef ROCKSDB_LITE
@@ -366,18 +358,15 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
  if (logfile_number_ > 0) {
    // TODO (yanqin) investigate whether we should sync the closed logs for
    // single column family case.
-    io_s = SyncClosedLogs(job_context);
-    s = io_s;
+    s = SyncClosedLogs(job_context);
  }

  // exec_status stores the execution status of flush_jobs as
  // <bool /* executed */, Status /* status code */>
  autovector<std::pair<bool, Status>> exec_status;
-  autovector<IOStatus> io_status;
  for (int i = 0; i != num_cfs; ++i) {
    // Initially all jobs are not executed, with status OK.
    exec_status.emplace_back(false, Status::OK());
-    io_status.emplace_back(IOStatus::OK());
  }

  if (s.ok()) {
@@ -386,7 +375,6 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
      exec_status[i].second =
          jobs[i]->Run(&logs_with_prep_tracker_, &file_meta[i]);
      exec_status[i].first = true;
-      io_status[i] = jobs[i]->io_status();
    }
    if (num_cfs > 1) {
      TEST_SYNC_POINT(
@@ -399,7 +387,6 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
    exec_status[0].second =
        jobs[0]->Run(&logs_with_prep_tracker_, &file_meta[0]);
    exec_status[0].first = true;
-    io_status[0] = jobs[0]->io_status();

    Status error_status;
    for (const auto& e : exec_status) {
@@ -418,20 +405,6 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
    s = error_status.ok() ? s : error_status;
  }

-  if (io_s.ok()) {
-    IOStatus io_error = IOStatus::OK();
-    for (int i = 0; i != static_cast<int>(io_status.size()); i++) {
-      if (!io_status[i].ok() && !io_status[i].IsShutdownInProgress() &&
-          !io_status[i].IsColumnFamilyDropped()) {
-        io_error = io_status[i];
-      }
-    }
-    io_s = io_error;
-    if (s.ok() && !io_s.ok()) {
-      s = io_s;
-    }
-  }
-
  if (s.IsColumnFamilyDropped()) {
    s = Status::OK();
  }
@@ -440,7 +413,7 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
    // Sync on all distinct output directories.
    for (auto dir : distinct_output_dirs) {
      if (dir != nullptr) {
-        Status error_status = dir->Fsync(IOOptions(), nullptr);
+        Status error_status = dir->Fsync();
        if (!error_status.ok()) {
          s = error_status;
          break;
@@ -570,15 +543,9 @@ Status DBImpl::AtomicFlushMemTablesToOutputFiles(
 #endif  // ROCKSDB_LITE
  }

-  // Need to undo atomic flush if something went wrong, i.e. s is not OK and
-  // it is not because of CF drop.
-  if (!s.ok() && !s.IsColumnFamilyDropped()) {
-    if (!io_s.ok() && io_s.IsColumnFamilyDropped()) {
-      error_handler_.SetBGError(io_s, BackgroundErrorReason::kFlush);
-    } else {
-      Status new_bg_error = s;
-      error_handler_.SetBGError(new_bg_error, BackgroundErrorReason::kFlush);
-    }
+  if (!s.ok() && !s.IsShutdownInProgress()) {
+    Status new_bg_error = s;
+    error_handler_.SetBGError(new_bg_error, BackgroundErrorReason::kFlush);
  }

  return s;
@@ -685,6 +652,8 @@ Status DBImpl::CompactRange(const CompactRangeOptions& options,
    return Status::InvalidArgument("Invalid target path ID");
  }

+  bool exclusive = options.exclusive_manual_compaction;
+
  bool flush_needed = true;
  if (begin != nullptr && end != nullptr) {
    // TODO(ajkr): We could also optimize away the flush in certain cases where
@@ -717,9 +686,25 @@ Status DBImpl::CompactRange(const CompactRangeOptions& options,
    }
  }

-  constexpr int kInvalidLevel = -1;
-  int final_output_level = kInvalidLevel;
-  bool exclusive = options.exclusive_manual_compaction;
+  int max_level_with_files = 0;
+  // max_file_num_to_ignore can be used to filter out newly created SST files,
+  // useful for bottom level compaction in a manual compaction
+  uint64_t max_file_num_to_ignore = port::kMaxUint64;
+  uint64_t next_file_number = port::kMaxUint64;
+  {
+    InstrumentedMutexLock l(&mutex_);
+    Version* base = cfd->current();
+    for (int level = 1; level < base->storage_info()->num_non_empty_levels();
+         level++) {
+      if (base->storage_info()->OverlapInLevel(level, begin, end)) {
+        max_level_with_files = level;
+      }
+    }
+    next_file_number = versions_->current_next_file_number();
+  }
+
+  int final_output_level = 0;
+
  if (cfd->ioptions()->compaction_style == kCompactionStyleUniversal &&
      cfd->NumberLevels() > 1) {
    // Always compact all files together.
@@ -730,98 +715,58 @@ Status DBImpl::CompactRange(const CompactRangeOptions& options,
    }
    s = RunManualCompaction(cfd, ColumnFamilyData::kCompactAllLevels,
                            final_output_level, options, begin, end, exclusive,
-                            false, port::kMaxUint64);
+                            false, max_file_num_to_ignore);
  } else {
-    int first_overlapped_level = kInvalidLevel;
-    int max_overlapped_level = kInvalidLevel;
-    {
-      SuperVersion* super_version = cfd->GetReferencedSuperVersion(this);
-      Version* current_version = super_version->current;
-      ReadOptions ro;
-      ro.total_order_seek = true;
-      bool overlap;
-      for (int level = 0;
-           level < current_version->storage_info()->num_non_empty_levels();
-           level++) {
-        overlap = true;
-        if (begin != nullptr && end != nullptr) {
-          Status status = current_version->OverlapWithLevelIterator(
-              ro, file_options_, *begin, *end, level, &overlap);
-          if (!status.ok()) {
-            overlap = current_version->storage_info()->OverlapInLevel(
-                level, begin, end);
-          }
-        } else {
-          overlap = current_version->storage_info()->OverlapInLevel(level,
-                                                                    begin, end);
-        }
-        if (overlap) {
-          if (first_overlapped_level == kInvalidLevel) {
-            first_overlapped_level = level;
-          }
-          max_overlapped_level = level;
-        }
-      }
-      CleanupSuperVersion(super_version);
-    }
-    if (s.ok() && first_overlapped_level != kInvalidLevel) {
-      // max_file_num_to_ignore can be used to filter out newly created SST
-      // files, useful for bottom level compaction in a manual compaction
-      uint64_t max_file_num_to_ignore = port::kMaxUint64;
-      uint64_t next_file_number = versions_->current_next_file_number();
-      final_output_level = max_overlapped_level;
+    for (int level = 0; level <= max_level_with_files; level++) {
      int output_level;
-      for (int level = first_overlapped_level; level <= max_overlapped_level;
-           level++) {
-        // in case the compaction is universal or if we're compacting the
-        // bottom-most level, the output level will be the same as input one.
-        // level 0 can never be the bottommost level (i.e. if all files are in
-        // level 0, we will compact to level 1)
-        if (cfd->ioptions()->compaction_style == kCompactionStyleUniversal ||
-            cfd->ioptions()->compaction_style == kCompactionStyleFIFO) {
-          output_level = level;
-        } else if (level == max_overlapped_level && level > 0) {
-          if (options.bottommost_level_compaction ==
-              BottommostLevelCompaction::kSkip) {
-            // Skip bottommost level compaction
-            continue;
-          } else if (options.bottommost_level_compaction ==
-                         BottommostLevelCompaction::kIfHaveCompactionFilter &&
-                     cfd->ioptions()->compaction_filter == nullptr &&
-                     cfd->ioptions()->compaction_filter_factory == nullptr) {
-            // Skip bottommost level compaction since we don't have a compaction
-            // filter
-            continue;
-          }
-          output_level = level;
-          // update max_file_num_to_ignore only for bottom level compaction
-          // because data in newly compacted files in middle levels may still
-          // need to be pushed down
-          max_file_num_to_ignore = next_file_number;
-        } else {
-          output_level = level + 1;
-          if (cfd->ioptions()->compaction_style == kCompactionStyleLevel &&
-              cfd->ioptions()->level_compaction_dynamic_level_bytes &&
-              level == 0) {
-            output_level = ColumnFamilyData::kCompactToBaseLevel;
-          }
+      // in case the compaction is universal or if we're compacting the
+      // bottom-most level, the output level will be the same as input one.
+      // level 0 can never be the bottommost level (i.e. if all files are in
+      // level 0, we will compact to level 1)
+      if (cfd->ioptions()->compaction_style == kCompactionStyleUniversal ||
+          cfd->ioptions()->compaction_style == kCompactionStyleFIFO) {
+        output_level = level;
+      } else if (level == max_level_with_files && level > 0) {
+        if (options.bottommost_level_compaction ==
+            BottommostLevelCompaction::kSkip) {
+          // Skip bottommost level compaction
+          continue;
+        } else if (options.bottommost_level_compaction ==
+                       BottommostLevelCompaction::kIfHaveCompactionFilter &&
+                   cfd->ioptions()->compaction_filter == nullptr &&
+                   cfd->ioptions()->compaction_filter_factory == nullptr) {
+          // Skip bottommost level compaction since we don't have a compaction
+          // filter
+          continue;
        }
-        s = RunManualCompaction(cfd, level, output_level, options, begin, end,
-                                exclusive, false, max_file_num_to_ignore);
-        if (!s.ok()) {
-          break;
+        output_level = level;
+        // update max_file_num_to_ignore only for bottom level compaction
+        // because data in newly compacted files in middle levels may still need
+        // to be pushed down
+        max_file_num_to_ignore = next_file_number;
+      } else {
+        output_level = level + 1;
+        if (cfd->ioptions()->compaction_style == kCompactionStyleLevel &&
+            cfd->ioptions()->level_compaction_dynamic_level_bytes &&
+            level == 0) {
+          output_level = ColumnFamilyData::kCompactToBaseLevel;
        }
-        if (output_level == ColumnFamilyData::kCompactToBaseLevel) {
-          final_output_level = cfd->NumberLevels() - 1;
-        } else if (output_level > final_output_level) {
-          final_output_level = output_level;
-        }
-        TEST_SYNC_POINT("DBImpl::RunManualCompaction()::1");
-        TEST_SYNC_POINT("DBImpl::RunManualCompaction()::2");
      }
+      s = RunManualCompaction(cfd, level, output_level, options, begin, end,
+                              exclusive, false, max_file_num_to_ignore);
+      if (!s.ok()) {
+        break;
+      }
+      if (output_level == ColumnFamilyData::kCompactToBaseLevel) {
+        final_output_level = cfd->NumberLevels() - 1;
+      } else if (output_level > final_output_level) {
+        final_output_level = output_level;
+      }
+      TEST_SYNC_POINT("DBImpl::RunManualCompaction()::1");
+      TEST_SYNC_POINT("DBImpl::RunManualCompaction()::2");
    }
  }
-  if (!s.ok() || final_output_level == kInvalidLevel) {
+  if (!s.ok()) {
    LogFlush(immutable_db_options_.info_log);
    return s;
  }
@@ -1092,7 +1037,7 @@ Status DBImpl::CompactFilesImpl(
  }

  if (output_file_names != nullptr) {
-    for (const auto& newf : c->edit()->GetNewFiles()) {
+    for (const auto newf : c->edit()->GetNewFiles()) {
      (*output_file_names)
          .push_back(TableFileName(c->immutable_cf_options()->cf_paths,
                                   newf.second.fd.GetNumber(),
@@ -1192,7 +1137,7 @@ void DBImpl::NotifyOnCompactionBegin(ColumnFamilyData* cfd, Compaction* c,
        }
      }
    }
-    for (const auto& newf : c->edit()->GetNewFiles()) {
+    for (const auto newf : c->edit()->GetNewFiles()) {
      const FileMetaData& meta = newf.second;
      const FileDescriptor& desc = meta.fd;
      const uint64_t file_number = desc.GetNumber();
@@ -1543,12 +1488,7 @@ Status DBImpl::RunManualCompaction(
      }
      manual.incomplete = false;
      bg_compaction_scheduled_++;
-      Env::Priority thread_pool_pri = Env::Priority::LOW;
-      if (compaction->bottommost_level() &&
-          env_->GetBackgroundThreads(Env::Priority::BOTTOM) > 0) {
-        thread_pool_pri = Env::Priority::BOTTOM;
-      }
-      env_->Schedule(&DBImpl::BGWorkCompaction, ca, thread_pool_pri, this,
+      env_->Schedule(&DBImpl::BGWorkCompaction, ca, Env::Priority::LOW, this,
                     &DBImpl::UnscheduleCompactionCallback);
      scheduled = true;
    }
@@ -1906,7 +1846,7 @@ Status DBImpl::WaitForFlushMemTables(
      }
    }
    if (1 == num_dropped && 1 == num) {
-      return Status::ColumnFamilyDropped();
+      return Status::InvalidArgument("Cannot flush a dropped CF");
    }
    // Column families involved in this flush request have either been dropped
    // or finished flush. Then it's time to finish waiting.
@@ -2030,7 +1970,7 @@ void DBImpl::MaybeScheduleFlushOrCompaction() {

 DBImpl::BGJobLimits DBImpl::GetBGJobLimits() const {
  mutex_.AssertHeld();
-  return GetBGJobLimits(mutable_db_options_.max_background_flushes,
+  return GetBGJobLimits(immutable_db_options_.max_background_flushes,
                        mutable_db_options_.max_background_compactions,
                        mutable_db_options_.max_background_jobs,
                        write_controller_.NeedSpeedupCompaction());
@@ -2143,7 +2083,8 @@ void DBImpl::BGWorkFlush(void* arg) {

  IOSTATS_SET_THREAD_POOL_ID(fta.thread_pri_);
  TEST_SYNC_POINT("DBImpl::BGWorkFlush");
-  static_cast_with_check<DBImpl>(fta.db_)->BackgroundCallFlush(fta.thread_pri_);
+  static_cast_with_check<DBImpl, DB>(fta.db_)->BackgroundCallFlush(
+      fta.thread_pri_);
  TEST_SYNC_POINT("DBImpl::BGWorkFlush:done");
 }

@@ -2154,7 +2095,7 @@ void DBImpl::BGWorkCompaction(void* arg) {
  TEST_SYNC_POINT("DBImpl::BGWorkCompaction");
  auto prepicked_compaction =
      static_cast<PrepickedCompaction*>(ca.prepicked_compaction);
-  static_cast_with_check<DBImpl>(ca.db)->BackgroundCallCompaction(
+  static_cast_with_check<DBImpl, DB>(ca.db)->BackgroundCallCompaction(
      prepicked_compaction, Env::Priority::LOW);
  delete prepicked_compaction;
 }
@@ -2548,8 +2489,8 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
                       "[%s] Manual compaction from level-%d from %s .. "
                       "%s; nothing to do\n",
                       m->cfd->GetName().c_str(), m->input_level,
-                       (m->begin ? m->begin->DebugString(true).c_str() : "(begin)"),
-                       (m->end ? m->end->DebugString(true).c_str() : "(end)"));
+                       (m->begin ? m->begin->DebugString().c_str() : "(begin)"),
+                       (m->end ? m->end->DebugString().c_str() : "(end)"));
    } else {
      // First check if we have enough room to do the compaction
      bool enough_room = EnoughRoomForCompaction(
@@ -2568,11 +2509,11 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
            "[%s] Manual compaction from level-%d to level-%d from %s .. "
            "%s; will stop at %s\n",
            m->cfd->GetName().c_str(), m->input_level, c->output_level(),
-            (m->begin ? m->begin->DebugString(true).c_str() : "(begin)"),
-            (m->end ? m->end->DebugString(true).c_str() : "(end)"),
+            (m->begin ? m->begin->DebugString().c_str() : "(begin)"),
+            (m->end ? m->end->DebugString().c_str() : "(end)"),
            ((m->done || m->manual_end == nullptr)
                 ? "(end)"
-                 : m->manual_end->DebugString(true).c_str()));
+                 : m->manual_end->DebugString().c_str()));
      }
    }
  } else if (!is_prepicked && !compaction_queue_.empty()) {
@@ -2665,7 +2606,6 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
    }
  }

-  IOStatus io_s;
  if (!c) {
    // Nothing to do
    ROCKS_LOG_BUFFER(log_buffer, "Compaction nothing to do");
@@ -2687,11 +2627,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
    for (const auto& f : *c->inputs(0)) {
      c->edit()->DeleteFile(c->level(), f->fd.GetNumber());
    }
-    versions_->SetIOStatusOK();
    status = versions_->LogAndApply(c->column_family_data(),
                                    *c->mutable_cf_options(), c->edit(),
                                    &mutex_, directories_.GetDbDir());
-    io_s = versions_->io_status();
    InstallSuperVersionAndScheduleWork(c->column_family_data(),
                                       &job_context->superversion_contexts[0],
                                       *c->mutable_cf_options());
@@ -2745,11 +2683,9 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
      }
    }

-    versions_->SetIOStatusOK();
    status = versions_->LogAndApply(c->column_family_data(),
                                    *c->mutable_cf_options(), c->edit(),
                                    &mutex_, directories_.GetDbDir());
-    io_s = versions_->io_status();
    // Use latest MutableCFOptions
    InstallSuperVersionAndScheduleWork(c->column_family_data(),
                                       &job_context->superversion_contexts[0],
@@ -2836,7 +2772,6 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
    mutex_.Lock();

    status = compaction_job.Install(*c->mutable_cf_options());
-    io_s = compaction_job.io_status();
    if (status.ok()) {
      InstallSuperVersionAndScheduleWork(c->column_family_data(),
                                         &job_context->superversion_contexts[0],
@@ -2846,11 +2781,6 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
    TEST_SYNC_POINT_CALLBACK("DBImpl::BackgroundCompaction:AfterCompaction",
                             c->column_family_data());
  }
-
-  if (status.ok() && !io_s.ok()) {
-    status = io_s;
-  }
-
  if (c != nullptr) {
    c->ReleaseCompactionFiles(status);
    *made_progress = true;
@@ -2876,11 +2806,7 @@ Status DBImpl::BackgroundCompaction(bool* made_progress,
  } else {
    ROCKS_LOG_WARN(immutable_db_options_.info_log, "Compaction error: %s",
                   status.ToString().c_str());
-    if (!io_s.ok()) {
-      error_handler_.SetBGError(io_s, BackgroundErrorReason::kCompaction);
-    } else {
-      error_handler_.SetBGError(status, BackgroundErrorReason::kCompaction);
-    }
+    error_handler_.SetBGError(status, BackgroundErrorReason::kCompaction);
    if (c != nullptr && !is_manual && !error_handler_.IsBGWorkStopped()) {
      // Put this cfd back in the compaction queue so we can retry after some
      // time
@@ -14,7 +14,6 @@
 #include "db/event_helpers.h"
 #include "db/memtable_list.h"
 #include "file/file_util.h"
-#include "file/filename.h"
 #include "file/sst_file_manager_impl.h"
 #include "util/autovector.h"

@@ -36,7 +35,7 @@ uint64_t DBImpl::MinObsoleteSstNumberToKeep() {
  return std::numeric_limits<uint64_t>::max();
 }

-// * Returns the list of live files in 'sst_live' and 'blob_live'.
+// * Returns the list of live files in 'sst_live'
 // If it's doing full scan:
 // * Returns the list of all files in the filesystem in
 // 'full_scan_candidate_files'.
@@ -77,26 +76,26 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
  // Since job_context->min_pending_output is set, until file scan finishes,
  // mutex_ cannot be released. Otherwise, we might see no min_pending_output
  // here but later find newer generated unfinalized files while scanning.
-  job_context->min_pending_output = MinObsoleteSstNumberToKeep();
+  if (!pending_outputs_.empty()) {
+    job_context->min_pending_output = *pending_outputs_.begin();
+  } else {
+    // delete all of them
+    job_context->min_pending_output = std::numeric_limits<uint64_t>::max();
+  }

  // Get obsolete files.  This function will also update the list of
  // pending files in VersionSet().
-  versions_->GetObsoleteFiles(
-      &job_context->sst_delete_files, &job_context->blob_delete_files,
-      &job_context->manifest_delete_files, job_context->min_pending_output);
+  versions_->GetObsoleteFiles(&job_context->sst_delete_files,
+                              &job_context->manifest_delete_files,
+                              job_context->min_pending_output);

-  // Mark the elements in job_context->sst_delete_files and
-  // job_context->blob_delete_files as "grabbed for purge" so that other threads
-  // calling FindObsoleteFiles with full_scan=true will not add these files to
-  // candidate list for purge.
+  // Mark the elements in job_context->sst_delete_files as grabbedForPurge
+  // so that other threads calling FindObsoleteFiles with full_scan=true
+  // will not add these files to candidate list for purge.
  for (const auto& sst_to_del : job_context->sst_delete_files) {
    MarkAsGrabbedForPurge(sst_to_del.metadata->fd.GetNumber());
  }

-  for (const auto& blob_file : job_context->blob_delete_files) {
-    MarkAsGrabbedForPurge(blob_file.GetBlobFileNumber());
-  }
-
  // store the current filenum, lognum, etc
  job_context->manifest_file_number = versions_->manifest_file_number();
  job_context->pending_manifest_file_number =
@@ -104,7 +103,7 @@ void DBImpl::FindObsoleteFiles(JobContext* job_context, bool force,
  job_context->log_number = MinLogNumberToKeep();
  job_context->prev_log_number = versions_->prev_log_number();

-  versions_->AddLiveFiles(&job_context->sst_live, &job_context->blob_live);
+  versions_->AddLiveFiles(&job_context->sst_live);
  if (doing_the_full_scan) {
    InfoLogPrefix info_log_prefix(!immutable_db_options_.db_log_dir.empty(),
                                  dbname_);
@@ -257,11 +256,8 @@ bool CompareCandidateFile(const JobContext::CandidateFileInfo& first,
 void DBImpl::DeleteObsoleteFileImpl(int job_id, const std::string& fname,
                                    const std::string& path_to_sync,
                                    FileType type, uint64_t number) {
-  TEST_SYNC_POINT_CALLBACK("DBImpl::DeleteObsoleteFileImpl::BeforeDeletion",
-                           const_cast<std::string*>(&fname));
-
  Status file_deletion_status;
-  if (type == kTableFile || type == kBlobFile || type == kLogFile) {
+  if (type == kTableFile || type == kLogFile) {
    file_deletion_status =
        DeleteDBFile(&immutable_db_options_, fname, path_to_sync,
                     /*force_bg=*/false, /*force_fg=*/!wal_in_db_path_);
@@ -307,19 +303,19 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
  // FindObsoleteFiles() should've populated this so nonzero
  assert(state.manifest_file_number != 0);

-  // Now, convert lists to unordered sets, WITHOUT mutex held; set is slow.
-  std::unordered_set<uint64_t> sst_live_set(state.sst_live.begin(),
-                                            state.sst_live.end());
-  std::unordered_set<uint64_t> blob_live_set(state.blob_live.begin(),
-                                             state.blob_live.end());
+  // Now, convert live list to an unordered map, WITHOUT mutex held;
+  // set is slow.
+  std::unordered_map<uint64_t, const FileDescriptor*> sst_live_map;
+  for (const FileDescriptor& fd : state.sst_live) {
+    sst_live_map[fd.GetNumber()] = &fd;
+  }
  std::unordered_set<uint64_t> log_recycle_files_set(
      state.log_recycle_files.begin(), state.log_recycle_files.end());

  auto candidate_files = state.full_scan_candidate_files;
  candidate_files.reserve(
      candidate_files.size() + state.sst_delete_files.size() +
-      state.blob_delete_files.size() + state.log_delete_files.size() +
-      state.manifest_delete_files.size());
+      state.log_delete_files.size() + state.manifest_delete_files.size());
  // We may ignore the dbname when generating the file names.
  for (auto& file : state.sst_delete_files) {
    candidate_files.emplace_back(
@@ -330,11 +326,6 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
    file.DeleteMetadata();
  }

-  for (const auto& blob_file : state.blob_delete_files) {
-    candidate_files.emplace_back(BlobFileName(blob_file.GetBlobFileNumber()),
-                                 blob_file.GetPath());
-  }
-
  for (auto file_num : state.log_delete_files) {
    if (file_num > 0) {
      candidate_files.emplace_back(LogFileName(file_num),
@@ -421,19 +412,12 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
      case kTableFile:
        // If the second condition is not there, this makes
        // DontDeletePendingOutputs fail
-        keep = (sst_live_set.find(number) != sst_live_set.end()) ||
+        keep = (sst_live_map.find(number) != sst_live_map.end()) ||
               number >= state.min_pending_output;
        if (!keep) {
          files_to_del.insert(number);
        }
        break;
-      case kBlobFile:
-        keep = number >= state.min_pending_output ||
-               (blob_live_set.find(number) != blob_live_set.end());
-        if (!keep) {
-          files_to_del.insert(number);
-        }
-        break;
      case kTempFile:
        // Any temp files that are currently being written to must
        // be recorded in pending_outputs_, which is inserted into "live".
@@ -443,8 +427,7 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
        //
        // TODO(yhchiang): carefully modify the third condition to safely
        //                 remove the temp options files.
-        keep = (sst_live_set.find(number) != sst_live_set.end()) ||
-               (blob_live_set.find(number) != blob_live_set.end()) ||
+        keep = (sst_live_map.find(number) != sst_live_map.end()) ||
               (number == state.pending_manifest_file_number) ||
               (to_delete.find(kOptionsFileNamePrefix) != std::string::npos);
        break;
@@ -467,6 +450,7 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
      case kDBLockFile:
      case kIdentityFile:
      case kMetaDatabase:
+      case kBlobFile:
        keep = true;
        break;
    }
@@ -482,9 +466,6 @@ void DBImpl::PurgeObsoleteFiles(JobContext& state, bool schedule_only) {
      TableCache::Evict(table_cache_.get(), number);
      fname = MakeTableFileName(candidate_file.file_path, number);
      dir_to_sync = candidate_file.file_path;
-    } else if (type == kBlobFile) {
-      fname = BlobFileName(candidate_file.file_path, number);
-      dir_to_sync = candidate_file.file_path;
    } else {
      dir_to_sync =
          (type == kLogFile) ? immutable_db_options_.wal_dir : dbname_;
@@ -683,69 +664,4 @@ uint64_t PrecomputeMinLogNumberToKeep(
  return min_log_number_to_keep;
 }

-Status DBImpl::FinishBestEffortsRecovery() {
-  mutex_.AssertHeld();
-  std::vector<std::string> paths;
-  paths.push_back(dbname_);
-  for (const auto& db_path : immutable_db_options_.db_paths) {
-    paths.push_back(db_path.path);
-  }
-  for (const auto* cfd : *versions_->GetColumnFamilySet()) {
-    for (const auto& cf_path : cfd->ioptions()->cf_paths) {
-      paths.push_back(cf_path.path);
-    }
-  }
-  // Dedup paths
-  std::sort(paths.begin(), paths.end());
-  paths.erase(std::unique(paths.begin(), paths.end()), paths.end());
-
-  uint64_t next_file_number = versions_->current_next_file_number();
-  uint64_t largest_file_number = next_file_number;
-  std::set<std::string> files_to_delete;
-  for (const auto& path : paths) {
-    std::vector<std::string> files;
-    env_->GetChildren(path, &files);
-    for (const auto& fname : files) {
-      uint64_t number = 0;
-      FileType type;
-      if (!ParseFileName(fname, &number, &type)) {
-        continue;
-      }
-      const std::string normalized_fpath = NormalizePath(path + fname);
-      largest_file_number = std::max(largest_file_number, number);
-      if (type == kTableFile && number >= next_file_number &&
-          files_to_delete.find(normalized_fpath) == files_to_delete.end()) {
-        files_to_delete.insert(normalized_fpath);
-      }
-    }
-  }
-  if (largest_file_number > next_file_number) {
-    versions_->next_file_number_.store(largest_file_number + 1);
-  }
-
-  VersionEdit edit;
-  edit.SetNextFile(versions_->next_file_number_.load());
-  assert(versions_->GetColumnFamilySet());
-  ColumnFamilyData* default_cfd = versions_->GetColumnFamilySet()->GetDefault();
-  assert(default_cfd);
-  // Even if new_descriptor_log is false, we will still switch to a new
-  // MANIFEST and update CURRENT file, since this is in recovery.
-  Status s = versions_->LogAndApply(
-      default_cfd, *default_cfd->GetLatestMutableCFOptions(), &edit, &mutex_,
-      directories_.GetDbDir(), /*new_descriptor_log*/ false);
-  if (!s.ok()) {
-    return s;
-  }
-
-  mutex_.Unlock();
-  for (const auto& fname : files_to_delete) {
-    s = env_->DeleteFile(fname);
-    if (!s.ok()) {
-      break;
-    }
-  }
-  mutex_.Lock();
-  return s;
-}
-
 }  // namespace ROCKSDB_NAMESPACE
@@ -35,8 +35,16 @@ Options SanitizeOptions(const std::string& dbname, const Options& src) {
 DBOptions SanitizeOptions(const std::string& dbname, const DBOptions& src) {
  DBOptions result(src);

-  if (result.env == nullptr) {
-    result.env = Env::Default();
+  if (result.file_system == nullptr) {
+    if (result.env == Env::Default()) {
+      result.file_system = FileSystem::Default();
+    } else {
+      result.file_system.reset(new LegacyFileSystemWrapper(result.env));
+    }
+  } else {
+    if (result.env == nullptr) {
+      result.env = Env::Default();
+    }
  }

  // result.max_open_files means an "infinite" open files.
@@ -244,12 +252,6 @@ Status DBImpl::ValidateOptions(const DBOptions& db_options) {
        "atomic_flush is incompatible with enable_pipelined_write");
  }

-  // TODO remove this restriction
-  if (db_options.atomic_flush && db_options.best_efforts_recovery) {
-    return Status::InvalidArgument(
-        "atomic_flush is currently incompatible with best-efforts recovery");
-  }
-
  return Status::OK();
 }

@@ -292,16 +294,15 @@ Status DBImpl::NewDB() {
  }
  if (s.ok()) {
    // Make "CURRENT" file that points to the new manifest file.
-    s = SetCurrentFile(fs_.get(), dbname_, 1, directories_.GetDbDir());
+    s = SetCurrentFile(env_, dbname_, 1, directories_.GetDbDir());
  } else {
    fs_->DeleteFile(manifest, IOOptions(), nullptr);
  }
  return s;
 }

-IOStatus DBImpl::CreateAndNewDirectory(
-    FileSystem* fs, const std::string& dirname,
-    std::unique_ptr<FSDirectory>* directory) {
+Status DBImpl::CreateAndNewDirectory(Env* env, const std::string& dirname,
+                                     std::unique_ptr<Directory>* directory) {
  // We call CreateDirIfMissing() as the directory may already exist (if we
  // are reopening a DB), when this happens we don't want creating the
  // directory to cause an error. However, we need to check if creating the
@@ -309,24 +310,24 @@ IOStatus DBImpl::CreateAndNewDirectory(
  // file not existing. One real-world example of this occurring is if
  // env->CreateDirIfMissing() doesn't create intermediate directories, e.g.
  // when dbname_ is "dir/db" but when "dir" doesn't exist.
-  IOStatus io_s = fs->CreateDirIfMissing(dirname, IOOptions(), nullptr);
-  if (!io_s.ok()) {
-    return io_s;
+  Status s = env->CreateDirIfMissing(dirname);
+  if (!s.ok()) {
+    return s;
  }
-  return fs->NewDirectory(dirname, IOOptions(), directory, nullptr);
+  return env->NewDirectory(dirname, directory);
 }

-IOStatus Directories::SetDirectories(FileSystem* fs, const std::string& dbname,
-                                     const std::string& wal_dir,
-                                     const std::vector<DbPath>& data_paths) {
-  IOStatus io_s = DBImpl::CreateAndNewDirectory(fs, dbname, &db_dir_);
-  if (!io_s.ok()) {
-    return io_s;
+Status Directories::SetDirectories(Env* env, const std::string& dbname,
+                                   const std::string& wal_dir,
+                                   const std::vector<DbPath>& data_paths) {
+  Status s = DBImpl::CreateAndNewDirectory(env, dbname, &db_dir_);
+  if (!s.ok()) {
+    return s;
  }
  if (!wal_dir.empty() && dbname != wal_dir) {
-    io_s = DBImpl::CreateAndNewDirectory(fs, wal_dir, &wal_dir_);
-    if (!io_s.ok()) {
-      return io_s;
+    s = DBImpl::CreateAndNewDirectory(env, wal_dir, &wal_dir_);
+    if (!s.ok()) {
+      return s;
    }
  }

@@ -336,16 +337,16 @@ IOStatus Directories::SetDirectories(FileSystem* fs, const std::string& dbname,
    if (db_path == dbname) {
      data_dirs_.emplace_back(nullptr);
    } else {
-      std::unique_ptr<FSDirectory> path_directory;
-      io_s = DBImpl::CreateAndNewDirectory(fs, db_path, &path_directory);
-      if (!io_s.ok()) {
-        return io_s;
+      std::unique_ptr<Directory> path_directory;
+      s = DBImpl::CreateAndNewDirectory(env, db_path, &path_directory);
+      if (!s.ok()) {
+        return s;
      }
      data_dirs_.emplace_back(path_directory.release());
    }
  }
  assert(data_dirs_.size() == data_paths.size());
-  return IOStatus::OK();
+  return Status::OK();
 }

 Status DBImpl::Recover(
@@ -357,7 +358,7 @@ Status DBImpl::Recover(
  bool is_new_db = false;
  assert(db_lock_ == nullptr);
  if (!read_only) {
-    Status s = directories_.SetDirectories(fs_.get(), dbname_,
+    Status s = directories_.SetDirectories(env_, dbname_,
                                           immutable_db_options_.wal_dir,
                                           immutable_db_options_.db_paths);
    if (!s.ok()) {
@@ -417,17 +418,7 @@ Status DBImpl::Recover(
    }
  }
  assert(db_id_.empty());
-  Status s;
-  bool missing_table_file = false;
-  if (!immutable_db_options_.best_efforts_recovery) {
-    s = versions_->Recover(column_families, read_only, &db_id_);
-  } else {
-    s = versions_->TryRecover(column_families, read_only, &db_id_,
-                              &missing_table_file);
-    if (s.ok()) {
-      s = FinishBestEffortsRecovery();
-    }
-  }
+  Status s = versions_->Recover(column_families, read_only, &db_id_);
  if (!s.ok()) {
    return s;
  }
@@ -467,7 +458,7 @@ Status DBImpl::Recover(
    s = CheckConsistency();
  }
  if (s.ok() && !read_only) {
-    std::map<std::string, std::shared_ptr<FSDirectory>> created_dirs;
+    std::map<std::string, std::shared_ptr<Directory>> created_dirs;
    for (auto cfd : *versions_->GetColumnFamilySet()) {
      s = cfd->AddDirectories(&created_dirs);
      if (!s.ok()) {
@@ -507,9 +498,7 @@ Status DBImpl::Recover(
    // attention to it in case we are recovering a database
    // produced by an older version of rocksdb.
    std::vector<std::string> filenames;
-    if (!immutable_db_options_.best_efforts_recovery) {
-      s = env_->GetChildren(immutable_db_options_.wal_dir, &filenames);
-    }
+    s = env_->GetChildren(immutable_db_options_.wal_dir, &filenames);
    if (s.IsNotFound()) {
      return Status::InvalidArgument("wal_dir not found",
                                     immutable_db_options_.wal_dir);
@@ -1239,7 +1228,6 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
      if (range_del_iter != nullptr) {
        range_del_iters.emplace_back(range_del_iter);
      }
-      IOStatus io_s;
      s = BuildTable(
          dbname_, env_, fs_.get(), *cfd->ioptions(), mutable_cf_options,
          file_options_for_compaction_, cfd->table_cache(), iter.get(),
@@ -1248,8 +1236,8 @@ Status DBImpl::WriteLevel0TableForRecovery(int job_id, ColumnFamilyData* cfd,
          snapshot_seqs, earliest_write_conflict_snapshot, snapshot_checker,
          GetCompressionFlush(*cfd->ioptions(), mutable_cf_options),
          mutable_cf_options.sample_for_compression,
-          mutable_cf_options.compression_opts, paranoid_file_checks,
-          cfd->internal_stats(), TableFileCreationReason::kRecovery, &io_s,
+          cfd->ioptions()->compression_opts, paranoid_file_checks,
+          cfd->internal_stats(), TableFileCreationReason::kRecovery,
          &event_logger_, job_id, Env::IO_HIGH, nullptr /* table_properties */,
          -1 /* level */, current_time, write_hint);
      LogFlush(immutable_db_options_.info_log);
@@ -1412,9 +1400,13 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
      impl->error_handler_.EnableAutoRecovery();
    }
  }
-  if (s.ok()) {
-    s = impl->CreateArchivalDirectory();
+
+  if (!s.ok()) {
+    delete impl;
+    return s;
  }
+
+  s = impl->CreateArchivalDirectory();
  if (!s.ok()) {
    delete impl;
    return s;
@@ -1485,7 +1477,7 @@ Status DBImpl::Open(const DBOptions& db_options, const std::string& dbname,
      }

      impl->DeleteObsoleteFiles();
-      s = impl->directories_.GetDbDir()->Fsync(IOOptions(), nullptr);
+      s = impl->directories_.GetDbDir()->Fsync();
    }
    if (s.ok()) {
      // In WritePrepared there could be gap in sequence numbers. This breaks
@@ -48,16 +48,14 @@ Status DBImplReadOnly::Get(const ReadOptions& read_options,
  SequenceNumber max_covering_tombstone_seq = 0;
  LookupKey lkey(key, snapshot);
  PERF_TIMER_STOP(get_snapshot_time);
-  if (super_version->mem->Get(lkey, pinnable_val->GetSelf(),
-                              /*timestamp=*/nullptr, &s, &merge_context,
+  if (super_version->mem->Get(lkey, pinnable_val->GetSelf(), &s, &merge_context,
                              &max_covering_tombstone_seq, read_options)) {
    pinnable_val->PinSelf();
    RecordTick(stats_, MEMTABLE_HIT);
  } else {
    PERF_TIMER_GUARD(get_from_output_files_time);
-    super_version->current->Get(read_options, lkey, pinnable_val,
-                                /*timestamp=*/nullptr, &s, &merge_context,
-                                &max_covering_tombstone_seq);
+    super_version->current->Get(read_options, lkey, pinnable_val, &s,
+                                &merge_context, &max_covering_tombstone_seq);
    RecordTick(stats_, MEMTABLE_MISS);
  }
  RecordTick(stats_, NUMBER_KEYS_READ);
@@ -87,8 +85,7 @@ Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
      super_version->version_number, read_callback);
  auto internal_iter =
      NewInternalIterator(read_options, cfd, super_version, db_iter->GetArena(),
-                          db_iter->GetRangeDelAggregator(), read_seq,
-                          /* allow_unprepared_value */ true);
+                          db_iter->GetRangeDelAggregator(), read_seq);
  db_iter->SetIterUnderDBIter(internal_iter);
  return db_iter;
 }
@@ -119,8 +116,7 @@ Status DBImplReadOnly::NewIterators(
        sv->version_number, read_callback);
    auto* internal_iter =
        NewInternalIterator(read_options, cfd, sv, db_iter->GetArena(),
-                            db_iter->GetRangeDelAggregator(), read_seq,
-                            /* allow_unprepared_value */ true);
+                            db_iter->GetRangeDelAggregator(), read_seq);
    db_iter->SetIterUnderDBIter(internal_iter);
    iterators->push_back(db_iter);
  }
@@ -340,16 +340,15 @@ Status DBImplSecondary::GetImpl(const ReadOptions& read_options,
  PERF_TIMER_STOP(get_snapshot_time);

  bool done = false;
-  if (super_version->mem->Get(lkey, pinnable_val->GetSelf(),
-                              /*timestamp=*/nullptr, &s, &merge_context,
+  if (super_version->mem->Get(lkey, pinnable_val->GetSelf(), &s, &merge_context,
                              &max_covering_tombstone_seq, read_options)) {
    done = true;
    pinnable_val->PinSelf();
    RecordTick(stats_, MEMTABLE_HIT);
  } else if ((s.ok() || s.IsMergeInProgress()) &&
             super_version->imm->Get(
-                 lkey, pinnable_val->GetSelf(), /*timestamp=*/nullptr, &s,
-                 &merge_context, &max_covering_tombstone_seq, read_options)) {
+                 lkey, pinnable_val->GetSelf(), &s, &merge_context,
+                 &max_covering_tombstone_seq, read_options)) {
    done = true;
    pinnable_val->PinSelf();
    RecordTick(stats_, MEMTABLE_HIT);
@@ -360,9 +359,8 @@ Status DBImplSecondary::GetImpl(const ReadOptions& read_options,
  }
  if (!done) {
    PERF_TIMER_GUARD(get_from_output_files_time);
-    super_version->current->Get(read_options, lkey, pinnable_val,
-                                /*timestamp=*/nullptr, &s, &merge_context,
-                                &max_covering_tombstone_seq);
+    super_version->current->Get(read_options, lkey, pinnable_val, &s,
+                                &merge_context, &max_covering_tombstone_seq);
    RecordTick(stats_, MEMTABLE_MISS);
  }
  {
@@ -417,8 +415,7 @@ ArenaWrappedDBIter* DBImplSecondary::NewIteratorImpl(
      super_version->version_number, read_callback);
  auto internal_iter =
      NewInternalIterator(read_options, cfd, super_version, db_iter->GetArena(),
-                          db_iter->GetRangeDelAggregator(), snapshot,
-                          /* allow_unprepared_value */ true);
+                          db_iter->GetRangeDelAggregator(), snapshot);
  db_iter->SetIterUnderDBIter(internal_iter);
  return db_iter;
 }
@@ -101,7 +101,6 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
         disable_memtable);

  Status status;
-  IOStatus io_s;
  if (write_options.low_pri) {
    status = ThrottleLowPriWritesIfNeeded(write_options, my_batch);
    if (!status.ok()) {
@@ -323,22 +322,21 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
    if (!two_write_queues_) {
      if (status.ok() && !write_options.disableWAL) {
        PERF_TIMER_GUARD(write_wal_time);
-        io_s = WriteToWAL(write_group, log_writer, log_used, need_log_sync,
-                          need_log_dir_sync, last_sequence + 1);
+        status = WriteToWAL(write_group, log_writer, log_used, need_log_sync,
+                            need_log_dir_sync, last_sequence + 1);
      }
    } else {
      if (status.ok() && !write_options.disableWAL) {
        PERF_TIMER_GUARD(write_wal_time);
        // LastAllocatedSequence is increased inside WriteToWAL under
        // wal_write_mutex_ to ensure ordered events in WAL
-        io_s = ConcurrentWriteToWAL(write_group, log_used, &last_sequence,
-                                    seq_inc);
+        status = ConcurrentWriteToWAL(write_group, log_used, &last_sequence,
+                                      seq_inc);
      } else {
        // Otherwise we inc seq number for memtable writes
        last_sequence = versions_->FetchAddLastAllocatedSequence(seq_inc);
      }
    }
-    status = io_s;
    assert(last_sequence != kMaxSequenceNumber);
    const SequenceNumber current_sequence = last_sequence + 1;
    last_sequence += seq_inc;
@@ -413,11 +411,7 @@ Status DBImpl::WriteImpl(const WriteOptions& write_options,
  PERF_TIMER_START(write_pre_and_post_process_time);

  if (!w.CallbackFailed()) {
-    if (!io_s.ok()) {
-      IOStatusCheck(io_s);
-    } else {
-      WriteStatusCheck(status);
-    }
+    WriteStatusCheck(status);
  }

  if (need_log_sync) {
@@ -521,7 +515,6 @@ Status DBImpl::PipelinedWriteImpl(const WriteOptions& write_options,

    PERF_TIMER_STOP(write_pre_and_post_process_time);

-    IOStatus io_s;
    if (w.status.ok() && !write_options.disableWAL) {
      PERF_TIMER_GUARD(write_wal_time);
      stats->AddDBStats(InternalStats::kIntStatsWriteDoneBySelf, 1);
@@ -531,17 +524,12 @@ Status DBImpl::PipelinedWriteImpl(const WriteOptions& write_options,
                          wal_write_group.size - 1);
        RecordTick(stats_, WRITE_DONE_BY_OTHER, wal_write_group.size - 1);
      }
-      io_s = WriteToWAL(wal_write_group, log_writer, log_used, need_log_sync,
-                        need_log_dir_sync, current_sequence);
-      w.status = io_s;
+      w.status = WriteToWAL(wal_write_group, log_writer, log_used,
+                            need_log_sync, need_log_dir_sync, current_sequence);
    }

    if (!w.CallbackFailed()) {
-      if (!io_s.ok()) {
-        IOStatusCheck(io_s);
-      } else {
-        WriteStatusCheck(w.status);
-      }
+      WriteStatusCheck(w.status);
    }

    if (need_log_sync) {
@@ -752,10 +740,9 @@ Status DBImpl::WriteImplWALOnly(
    }
    seq_inc = total_batch_cnt;
  }
-  IOStatus io_s;
  if (!write_options.disableWAL) {
-    io_s = ConcurrentWriteToWAL(write_group, log_used, &last_sequence, seq_inc);
-    status = io_s;
+    status =
+        ConcurrentWriteToWAL(write_group, log_used, &last_sequence, seq_inc);
  } else {
    // Otherwise we inc seq number to do solely the seq allocation
    last_sequence = versions_->FetchAddLastAllocatedSequence(seq_inc);
@@ -790,11 +777,7 @@ Status DBImpl::WriteImplWALOnly(
  PERF_TIMER_START(write_pre_and_post_process_time);

  if (!w.CallbackFailed()) {
-    if (!io_s.ok()) {
-      IOStatusCheck(io_s);
-    } else {
-      WriteStatusCheck(status);
-    }
+    WriteStatusCheck(status);
  }
  if (status.ok()) {
    size_t index = 0;
@@ -840,17 +823,6 @@ void DBImpl::WriteStatusCheck(const Status& status) {
  }
 }

-void DBImpl::IOStatusCheck(const IOStatus& io_status) {
-  // Is setting bg_error_ enough here?  This will at least stop
-  // compaction and fail any further writes.
-  if (immutable_db_options_.paranoid_checks && !io_status.ok() &&
-      !io_status.IsBusy() && !io_status.IsIncomplete()) {
-    mutex_.Lock();
-    error_handler_.SetBGError(io_status, BackgroundErrorReason::kWriteCallback);
-    mutex_.Unlock();
-  }
-}
-
 void DBImpl::MemTableInsertStatusCheck(const Status& status) {
  // A non-OK status here indicates that the state implied by the
  // WAL has diverged from the in-memory state.  This could be
@@ -989,9 +961,9 @@ WriteBatch* DBImpl::MergeBatch(const WriteThread::WriteGroup& write_group,

 // When two_write_queues_ is disabled, this function is called from the only
 // write thread. Otherwise this must be called holding log_write_mutex_.
-IOStatus DBImpl::WriteToWAL(const WriteBatch& merged_batch,
-                            log::Writer* log_writer, uint64_t* log_used,
-                            uint64_t* log_size) {
+Status DBImpl::WriteToWAL(const WriteBatch& merged_batch,
+                          log::Writer* log_writer, uint64_t* log_used,
+                          uint64_t* log_size) {
  assert(log_size != nullptr);
  Slice log_entry = WriteBatchInternal::Contents(&merged_batch);
  *log_size = log_entry.size();
@@ -1006,8 +978,7 @@ IOStatus DBImpl::WriteToWAL(const WriteBatch& merged_batch,
  if (UNLIKELY(needs_locking)) {
    log_write_mutex_.Lock();
  }
-  IOStatus io_s = log_writer->AddRecord(log_entry);
-
+  Status status = log_writer->AddRecord(log_entry);
  if (UNLIKELY(needs_locking)) {
    log_write_mutex_.Unlock();
  }
@@ -1019,14 +990,15 @@ IOStatus DBImpl::WriteToWAL(const WriteBatch& merged_batch,
  // since alive_log_files_ might be modified concurrently
  alive_log_files_.back().AddSize(log_entry.size());
  log_empty_ = false;
-  return io_s;
+  return status;
 }

-IOStatus DBImpl::WriteToWAL(const WriteThread::WriteGroup& write_group,
-                            log::Writer* log_writer, uint64_t* log_used,
-                            bool need_log_sync, bool need_log_dir_sync,
-                            SequenceNumber sequence) {
-  IOStatus io_s;
+Status DBImpl::WriteToWAL(const WriteThread::WriteGroup& write_group,
+                          log::Writer* log_writer, uint64_t* log_used,
+                          bool need_log_sync, bool need_log_dir_sync,
+                          SequenceNumber sequence) {
+  Status status;
+
  assert(!write_group.leader->disable_wal);
  // Same holds for all in the batch group
  size_t write_with_wal = 0;
@@ -1044,13 +1016,13 @@ IOStatus DBImpl::WriteToWAL(const WriteThread::WriteGroup& write_group,
  WriteBatchInternal::SetSequence(merged_batch, sequence);

  uint64_t log_size;
-  io_s = WriteToWAL(*merged_batch, log_writer, log_used, &log_size);
+  status = WriteToWAL(*merged_batch, log_writer, log_used, &log_size);
  if (to_be_cached_state) {
    cached_recoverable_state_ = *to_be_cached_state;
    cached_recoverable_state_empty_ = false;
  }

-  if (io_s.ok() && need_log_sync) {
+  if (status.ok() && need_log_sync) {
    StopWatch sw(env_, stats_, WAL_FILE_SYNC_MICROS);
    // It's safe to access logs_ with unlocked mutex_ here because:
    //  - we've set getting_synced=true for all logs,
@@ -1060,24 +1032,23 @@ IOStatus DBImpl::WriteToWAL(const WriteThread::WriteGroup& write_group,
    //  - as long as other threads don't modify it, it's safe to read
    //    from std::deque from multiple threads concurrently.
    for (auto& log : logs_) {
-      io_s = log.writer->file()->Sync(immutable_db_options_.use_fsync);
-      if (!io_s.ok()) {
+      status = log.writer->file()->Sync(immutable_db_options_.use_fsync);
+      if (!status.ok()) {
        break;
      }
    }
-
-    if (io_s.ok() && need_log_dir_sync) {
+    if (status.ok() && need_log_dir_sync) {
      // We only sync WAL directory the first time WAL syncing is
      // requested, so that in case users never turn on WAL sync,
      // we can avoid the disk I/O in the write code path.
-      io_s = directories_.GetWalDir()->Fsync(IOOptions(), nullptr);
+      status = directories_.GetWalDir()->Fsync();
    }
  }

  if (merged_batch == &tmp_batch_) {
    tmp_batch_.Clear();
  }
-  if (io_s.ok()) {
+  if (status.ok()) {
    auto stats = default_cf_internal_stats_;
    if (need_log_sync) {
      stats->AddDBStats(InternalStats::kIntStatsWalFileSynced, 1);
@@ -1088,13 +1059,14 @@ IOStatus DBImpl::WriteToWAL(const WriteThread::WriteGroup& write_group,
    stats->AddDBStats(InternalStats::kIntStatsWriteWithWal, write_with_wal);
    RecordTick(stats_, WRITE_WITH_WAL, write_with_wal);
  }
-  return io_s;
+  return status;
 }

-IOStatus DBImpl::ConcurrentWriteToWAL(
-    const WriteThread::WriteGroup& write_group, uint64_t* log_used,
-    SequenceNumber* last_sequence, size_t seq_inc) {
-  IOStatus io_s;
+Status DBImpl::ConcurrentWriteToWAL(const WriteThread::WriteGroup& write_group,
+                                    uint64_t* log_used,
+                                    SequenceNumber* last_sequence,
+                                    size_t seq_inc) {
+  Status status;

  assert(!write_group.leader->disable_wal);
  // Same holds for all in the batch group
@@ -1120,14 +1092,14 @@ IOStatus DBImpl::ConcurrentWriteToWAL(

  log::Writer* log_writer = logs_.back().writer;
  uint64_t log_size;
-  io_s = WriteToWAL(*merged_batch, log_writer, log_used, &log_size);
+  status = WriteToWAL(*merged_batch, log_writer, log_used, &log_size);
  if (to_be_cached_state) {
    cached_recoverable_state_ = *to_be_cached_state;
    cached_recoverable_state_empty_ = false;
  }
  log_write_mutex_.Unlock();

-  if (io_s.ok()) {
+  if (status.ok()) {
    const bool concurrent = true;
    auto stats = default_cf_internal_stats_;
    stats->AddDBStats(InternalStats::kIntStatsWalFileBytes, log_size,
@@ -1137,7 +1109,7 @@ IOStatus DBImpl::ConcurrentWriteToWAL(
                      concurrent);
    RecordTick(stats_, WRITE_WITH_WAL, write_with_wal);
  }
-  return io_s;
+  return status;
 }

 Status DBImpl::WriteRecoverableState() {
@@ -1820,8 +1792,6 @@ Status DB::Put(const WriteOptions& opt, ColumnFamilyHandle* column_family,
  const Slice* ts = opt.timestamp;
  assert(nullptr != ts);
  size_t ts_sz = ts->size();
-  assert(column_family->GetComparator());
-  assert(ts_sz == column_family->GetComparator()->timestamp_size());
  WriteBatch batch(key.size() + ts_sz + value.size() + 24, /*max_bytes=*/0,
                   ts_sz);
  Status s = batch.Put(column_family, key, value);
@@ -45,8 +45,6 @@ class DBSecondaryTest : public DBTestBase {

  void OpenSecondary(const Options& options);

-  Status TryOpenSecondary(const Options& options);
-
  void OpenSecondaryWithColumnFamilies(
      const std::vector<std::string>& column_families, const Options& options);

@@ -72,13 +70,9 @@ class DBSecondaryTest : public DBTestBase {
 };

 void DBSecondaryTest::OpenSecondary(const Options& options) {
-  ASSERT_OK(TryOpenSecondary(options));
-}
-
-Status DBSecondaryTest::TryOpenSecondary(const Options& options) {
  Status s =
      DB::OpenAsSecondary(options, dbname_, secondary_path_, &db_secondary_);
-  return s;
+  ASSERT_OK(s);
 }

 void DBSecondaryTest::OpenSecondaryWithColumnFamilies(
@@ -864,56 +858,6 @@ TEST_F(DBSecondaryTest, CheckConsistencyWhenOpen) {
  thread.join();
  ASSERT_TRUE(called);
 }
-
-TEST_F(DBSecondaryTest, StartFromInconsistent) {
-  Options options = CurrentOptions();
-  DestroyAndReopen(options);
-  ASSERT_OK(Put("foo", "value"));
-  ASSERT_OK(Flush());
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->SetCallBack(
-      "VersionBuilder::CheckConsistencyBeforeReturn", [&](void* arg) {
-        ASSERT_NE(nullptr, arg);
-        *(reinterpret_cast<Status*>(arg)) =
-            Status::Corruption("Inject corruption");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-  Options options1;
-  Status s = TryOpenSecondary(options1);
-  ASSERT_TRUE(s.IsCorruption());
-}
-
-TEST_F(DBSecondaryTest, InconsistencyDuringCatchUp) {
-  Options options = CurrentOptions();
-  DestroyAndReopen(options);
-  ASSERT_OK(Put("foo", "value"));
-  ASSERT_OK(Flush());
-
-  Options options1;
-  OpenSecondary(options1);
-
-  {
-    std::string value;
-    ASSERT_OK(db_secondary_->Get(ReadOptions(), "foo", &value));
-    ASSERT_EQ("value", value);
-  }
-
-  ASSERT_OK(Put("bar", "value1"));
-  ASSERT_OK(Flush());
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->SetCallBack(
-      "VersionBuilder::CheckConsistencyBeforeReturn", [&](void* arg) {
-        ASSERT_NE(nullptr, arg);
-        *(reinterpret_cast<Status*>(arg)) =
-            Status::Corruption("Inject corruption");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-  Status s = db_secondary_->TryCatchUpWithPrimary();
-  ASSERT_TRUE(s.IsCorruption());
-}
 #endif  //! ROCKSDB_LITE

 }  // namespace ROCKSDB_NAMESPACE
@@ -49,8 +49,6 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
      read_callback_(read_callback),
      sequence_(s),
      statistics_(cf_options.statistics),
-      max_skip_(max_sequential_skip_in_iterations),
-      max_skippable_internal_keys_(read_options.max_skippable_internal_keys),
      num_internal_keys_skipped_(0),
      iterate_lower_bound_(read_options.iterate_lower_bound),
      iterate_upper_bound_(read_options.iterate_upper_bound),
@@ -71,18 +69,16 @@ DBIter::DBIter(Env* _env, const ReadOptions& read_options,
      range_del_agg_(&cf_options.internal_comparator, s),
      db_impl_(db_impl),
      cfd_(cfd),
-      start_seqnum_(read_options.iter_start_seqnum),
-      timestamp_ub_(read_options.timestamp),
-      timestamp_lb_(read_options.iter_start_ts),
-      timestamp_size_(timestamp_ub_ ? timestamp_ub_->size() : 0) {
+      start_seqnum_(read_options.iter_start_seqnum) {
  RecordTick(statistics_, NO_ITERATOR_CREATED);
+  max_skip_ = max_sequential_skip_in_iterations;
+  max_skippable_internal_keys_ = read_options.max_skippable_internal_keys;
  if (pin_thru_lifetime_) {
    pinned_iters_mgr_.StartPinning();
  }
  if (iter_.iter()) {
    iter_.iter()->SetPinnedItersMgr(&pinned_iters_mgr_);
  }
-  assert(timestamp_size_ == user_comparator_.timestamp_size());
 }

 Status DBIter::GetProperty(std::string prop_name, std::string* prop) {
@@ -224,13 +220,9 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
    is_key_seqnum_zero_ = (ikey_.sequence == 0);

    assert(iterate_upper_bound_ == nullptr || iter_.MayBeOutOfUpperBound() ||
-           user_comparator_.CompareWithoutTimestamp(
-               ikey_.user_key, /*a_has_ts=*/true, *iterate_upper_bound_,
-               /*b_has_ts=*/false) < 0);
+           user_comparator_.Compare(ikey_.user_key, *iterate_upper_bound_) < 0);
    if (iterate_upper_bound_ != nullptr && iter_.MayBeOutOfUpperBound() &&
-        user_comparator_.CompareWithoutTimestamp(
-            ikey_.user_key, /*a_has_ts=*/true, *iterate_upper_bound_,
-            /*b_has_ts=*/false) >= 0) {
+        user_comparator_.Compare(ikey_.user_key, *iterate_upper_bound_) >= 0) {
      break;
    }

@@ -245,33 +237,20 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
      return false;
    }

-    assert(ikey_.user_key.size() >= timestamp_size_);
-    Slice ts;
-    bool more_recent = false;
-    if (timestamp_size_ > 0) {
-      ts = ExtractTimestampFromUserKey(ikey_.user_key, timestamp_size_);
-    }
-    if (IsVisible(ikey_.sequence, ts, &more_recent)) {
+    if (IsVisible(ikey_.sequence)) {
      // If the previous entry is of seqnum 0, the current entry will not
      // possibly be skipped. This condition can potentially be relaxed to
      // prev_key.seq <= ikey_.sequence. We are cautious because it will be more
      // prone to bugs causing the same user key with the same sequence number.
-      // Note that with current timestamp implementation, the same user key can
-      // have different timestamps and zero sequence number on the bottommost
-      // level. This will change in the future.
-      if ((!is_prev_key_seqnum_zero || timestamp_size_ > 0) &&
-          skipping_saved_key &&
-          CompareKeyForSkip(ikey_.user_key, saved_key_.GetUserKey()) <= 0) {
+      if (!is_prev_key_seqnum_zero && skipping_saved_key &&
+          user_comparator_.Compare(ikey_.user_key, saved_key_.GetUserKey()) <=
+              0) {
        num_skipped++;  // skip this entry
        PERF_COUNTER_ADD(internal_key_skipped_count, 1);
      } else {
        assert(!skipping_saved_key ||
-               CompareKeyForSkip(ikey_.user_key, saved_key_.GetUserKey()) > 0);
-        if (!iter_.PrepareValue()) {
-          assert(!iter_.status().ok());
-          valid_ = false;
-          return false;
-        }
+               user_comparator_.Compare(ikey_.user_key,
+                                        saved_key_.GetUserKey()) > 0);
        num_skipped = 0;
        reseek_done = false;
        switch (ikey_.type) {
@@ -372,15 +351,13 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
        }
      }
    } else {
-      if (more_recent) {
-        PERF_COUNTER_ADD(internal_recent_skipped_count, 1);
-      }
+      PERF_COUNTER_ADD(internal_recent_skipped_count, 1);

-      // This key was inserted after our snapshot was taken or skipped by
-      // timestamp range. If this happens too many times in a row for the same
-      // user key, we want to seek to the target sequence number.
-      int cmp = user_comparator_.CompareWithoutTimestamp(
-          ikey_.user_key, saved_key_.GetUserKey());
+      // This key was inserted after our snapshot was taken.
+      // If this happens too many times in a row for the same user key, we want
+      // to seek to the target sequence number.
+      int cmp =
+          user_comparator_.Compare(ikey_.user_key, saved_key_.GetUserKey());
      if (cmp == 0 || (skipping_saved_key && cmp < 0)) {
        num_skipped++;
      } else {
@@ -411,17 +388,8 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
        // We're looking for the next user-key but all we see are the same
        // user-key with decreasing sequence numbers. Fast forward to
        // sequence number 0 and type deletion (the smallest type).
-        if (timestamp_size_ == 0) {
-          AppendInternalKey(
-              &last_key,
-              ParsedInternalKey(saved_key_.GetUserKey(), 0, kTypeDeletion));
-        } else {
-          std::string min_ts(timestamp_size_, static_cast<char>(0));
-          AppendInternalKeyWithDifferentTimestamp(
-              &last_key,
-              ParsedInternalKey(saved_key_.GetUserKey(), 0, kTypeDeletion),
-              min_ts);
-        }
+        AppendInternalKey(&last_key, ParsedInternalKey(saved_key_.GetUserKey(),
+                                                       0, kTypeDeletion));
        // Don't set skipping_saved_key = false because we may still see more
        // user-keys equal to saved_key_.
      } else {
@@ -430,17 +398,9 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
        // Note that this only covers a case when a higher key was overwritten
        // many times since our snapshot was taken, not the case when a lot of
        // different keys were inserted after our snapshot was taken.
-        if (timestamp_size_ == 0) {
-          AppendInternalKey(
-              &last_key, ParsedInternalKey(saved_key_.GetUserKey(), sequence_,
-                                           kValueTypeForSeek));
-        } else {
-          AppendInternalKeyWithDifferentTimestamp(
-              &last_key,
-              ParsedInternalKey(saved_key_.GetUserKey(), sequence_,
-                                kValueTypeForSeek),
-              *timestamp_ub_);
-        }
+        AppendInternalKey(&last_key,
+                          ParsedInternalKey(saved_key_.GetUserKey(), sequence_,
+                                            kValueTypeForSeek));
      }
      iter_.Seek(last_key);
      RecordTick(statistics_, NUMBER_OF_RESEEKS_IN_ITERATION);
@@ -457,7 +417,6 @@ bool DBIter::FindNextUserEntryInternal(bool skipping_saved_key,
 // Scan from the newer entries to older entries.
 // PRE: iter_.key() points to the first merge type entry
 //      saved_key_ stores the user key
-//      iter_.PrepareValue() has been called
 // POST: saved_value_ has the merged value for the user key
 //       iter_ points to the next entry (or invalid)
 bool DBIter::MergeValuesNewToOld() {
@@ -487,21 +446,14 @@ bool DBIter::MergeValuesNewToOld() {
    if (!user_comparator_.Equal(ikey.user_key, saved_key_.GetUserKey())) {
      // hit the next user key, stop right here
      break;
-    }
-    if (kTypeDeletion == ikey.type || kTypeSingleDeletion == ikey.type ||
+    } else if (kTypeDeletion == ikey.type || kTypeSingleDeletion == ikey.type ||
               range_del_agg_.ShouldDelete(
                   ikey, RangeDelPositioningMode::kForwardTraversal)) {
      // hit a delete with the same user key, stop right here
      // iter_ is positioned after delete
      iter_.Next();
      break;
-    }
-    if (!iter_.PrepareValue()) {
-      valid_ = false;
-      return false;
-    }
-
-    if (kTypeValue == ikey.type) {
+    } else if (kTypeValue == ikey.type) {
      // hit a put, merge the put value with operands and store the
      // final result in saved_value_. We are done!
      const Slice val = iter_.value();
@@ -567,13 +519,6 @@ bool DBIter::MergeValuesNewToOld() {
 }

 void DBIter::Prev() {
-  if (timestamp_size_ > 0) {
-    valid_ = false;
-    status_ = Status::NotSupported(
-        "SeekToLast/SeekForPrev/Prev currently not supported with timestamp.");
-    return;
-  }
-
  assert(valid_);
  assert(status_.ok());

@@ -752,13 +697,7 @@ bool DBIter::FindValueForCurrentKey() {
      return false;
    }

-    assert(ikey.user_key.size() >= timestamp_size_);
-    Slice ts;
-    if (timestamp_size_ > 0) {
-      ts = Slice(ikey.user_key.data() + ikey.user_key.size() - timestamp_size_,
-                 timestamp_size_);
-    }
-    if (!IsVisible(ikey.sequence, ts) ||
+    if (!IsVisible(ikey.sequence) ||
        !user_comparator_.Equal(ikey.user_key, saved_key_.GetUserKey())) {
      break;
    }
@@ -773,11 +712,6 @@ bool DBIter::FindValueForCurrentKey() {
      return FindValueForCurrentKeyUsingSeek();
    }

-    if (!iter_.PrepareValue()) {
-      valid_ = false;
-      return false;
-    }
-
    last_key_entry_type = ikey.type;
    switch (last_key_entry_type) {
      case kTypeValue:
@@ -919,13 +853,6 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
    if (!ParseKey(&ikey)) {
      return false;
    }
-    assert(ikey.user_key.size() >= timestamp_size_);
-    Slice ts;
-    if (timestamp_size_ > 0) {
-      ts = Slice(ikey.user_key.data() + ikey.user_key.size() - timestamp_size_,
-                 timestamp_size_);
-    }
-
    if (!user_comparator_.Equal(ikey.user_key, saved_key_.GetUserKey())) {
      // No visible values for this key, even though FindValueForCurrentKey()
      // has seen some. This is possible if we're using a tailing iterator, and
@@ -934,7 +861,7 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
      return true;
    }

-    if (IsVisible(ikey.sequence, ts)) {
+    if (IsVisible(ikey.sequence)) {
      break;
    }

@@ -955,10 +882,6 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
    valid_ = false;
    return false;
  }
-  if (!iter_.PrepareValue()) {
-    valid_ = false;
-    return false;
-  }
  if (ikey.type == kTypeValue || ikey.type == kTypeBlobIndex) {
    assert(iter_.iter()->IsValuePinned());
    pinned_value_ = iter_.value();
@@ -990,17 +913,12 @@ bool DBIter::FindValueForCurrentKeyUsingSeek() {
    if (!user_comparator_.Equal(ikey.user_key, saved_key_.GetUserKey())) {
      break;
    }
+
    if (ikey.type == kTypeDeletion || ikey.type == kTypeSingleDeletion ||
        range_del_agg_.ShouldDelete(
            ikey, RangeDelPositioningMode::kForwardTraversal)) {
      break;
-    }
-    if (!iter_.PrepareValue()) {
-      valid_ = false;
-      return false;
-    }
-
-    if (ikey.type == kTypeValue) {
+    } else if (ikey.type == kTypeValue) {
      const Slice val = iter_.value();
      Status s = MergeHelper::TimedFullMerge(
          merge_operator_, saved_key_.GetUserKey(), &val,
@@ -1083,13 +1001,7 @@ bool DBIter::FindUserKeyBeforeSavedKey() {
    }

    assert(ikey.sequence != kMaxSequenceNumber);
-    assert(ikey.user_key.size() >= timestamp_size_);
-    Slice ts;
-    if (timestamp_size_ > 0) {
-      ts = Slice(ikey.user_key.data() + ikey.user_key.size() - timestamp_size_,
-                 timestamp_size_);
-    }
-    if (!IsVisible(ikey.sequence, ts)) {
+    if (!IsVisible(ikey.sequence)) {
      PERF_COUNTER_ADD(internal_recent_skipped_count, 1);
    } else {
      PERF_COUNTER_ADD(internal_key_skipped_count, 1);
@@ -1134,40 +1046,26 @@ bool DBIter::TooManyInternalKeysSkipped(bool increment) {
  return false;
 }

-bool DBIter::IsVisible(SequenceNumber sequence, const Slice& ts,
-                       bool* more_recent) {
-  // Remember that comparator orders preceding timestamp as larger.
-  // TODO(yanqin): support timestamp in read_callback_.
-  bool visible_by_seq = (read_callback_ == nullptr)
-                            ? sequence <= sequence_
-                            : read_callback_->IsVisible(sequence);
-
-  bool visible_by_ts =
-      (timestamp_ub_ == nullptr ||
-       user_comparator_.CompareTimestamp(ts, *timestamp_ub_) <= 0) &&
-      (timestamp_lb_ == nullptr ||
-       user_comparator_.CompareTimestamp(ts, *timestamp_lb_) >= 0);
-
-  if (more_recent) {
-    *more_recent = !visible_by_seq;
+bool DBIter::IsVisible(SequenceNumber sequence) {
+  if (read_callback_ == nullptr) {
+    return sequence <= sequence_;
+  } else {
+    return read_callback_->IsVisible(sequence);
  }
-  return visible_by_seq && visible_by_ts;
 }

 void DBIter::SetSavedKeyToSeekTarget(const Slice& target) {
  is_key_seqnum_zero_ = false;
  SequenceNumber seq = sequence_;
  saved_key_.Clear();
-  saved_key_.SetInternalKey(target, seq, kValueTypeForSeek, timestamp_ub_);
+  saved_key_.SetInternalKey(target, seq);

  if (iterate_lower_bound_ != nullptr &&
-      user_comparator_.CompareWithoutTimestamp(
-          saved_key_.GetUserKey(), /*a_has_ts=*/true, *iterate_lower_bound_,
-          /*b_has_ts=*/false) < 0) {
+      user_comparator_.Compare(saved_key_.GetUserKey(), *iterate_lower_bound_) <
+          0) {
    // Seek key is smaller than the lower bound.
    saved_key_.Clear();
-    saved_key_.SetInternalKey(*iterate_lower_bound_, seq, kValueTypeForSeek,
-                              timestamp_ub_);
+    saved_key_.SetInternalKey(*iterate_lower_bound_, seq);
  }
 }

@@ -1257,13 +1155,6 @@ void DBIter::SeekForPrev(const Slice& target) {
  }
 #endif  // ROCKSDB_LITE

-  if (timestamp_size_ > 0) {
-    valid_ = false;
-    status_ = Status::NotSupported(
-        "SeekToLast/SeekForPrev/Prev currently not supported with timestamp.");
-    return;
-  }
-
  status_ = Status::OK();
  ReleaseTempPinnedData();
  ResetInternalKeysSkippedCounter();
@@ -1357,13 +1248,6 @@ void DBIter::SeekToFirst() {
 }

 void DBIter::SeekToLast() {
-  if (timestamp_size_ > 0) {
-    valid_ = false;
-    status_ = Status::NotSupported(
-        "SeekToLast/SeekForPrev/Prev currently not supported with timestamp.");
-    return;
-  }
-
  if (iterate_upper_bound_ != nullptr) {
    // Seek to last key strictly less than ReadOptions.iterate_upper_bound.
    SeekForPrev(*iterate_upper_bound_);
@@ -146,8 +146,7 @@ class DBIter final : public Iterator {
    if (start_seqnum_ > 0) {
      return saved_key_.GetInternalKey();
    } else {
-      const Slice ukey_and_ts = saved_key_.GetUserKey();
-      return Slice(ukey_and_ts.data(), ukey_and_ts.size() - timestamp_size_);
+      return saved_key_.GetUserKey();
    }
  }
  Slice value() const override {
@@ -170,13 +169,6 @@ class DBIter final : public Iterator {
      return status_;
    }
  }
-  Slice timestamp() const override {
-    assert(valid_);
-    assert(timestamp_size_ > 0);
-    const Slice ukey_and_ts = saved_key_.GetUserKey();
-    assert(timestamp_size_ < ukey_and_ts.size());
-    return ExtractTimestampFromUserKey(ukey_and_ts, timestamp_size_);
-  }
  bool IsBlob() const {
    assert(valid_ && (allow_blob_ || !is_blob_));
    return is_blob_;
@@ -186,8 +178,6 @@ class DBIter final : public Iterator {

  void Next() final override;
  void Prev() final override;
-  // 'target' does not contain timestamp, even if user timestamp feature is
-  // enabled.
  void Seek(const Slice& target) final override;
  void SeekForPrev(const Slice& target) final override;
  void SeekToFirst() final override;
@@ -231,8 +221,7 @@ class DBIter final : public Iterator {
  // entry can be found within the prefix.
  void PrevInternal(const Slice* prefix);
  bool TooManyInternalKeysSkipped(bool increment = true);
-  bool IsVisible(SequenceNumber sequence, const Slice& ts,
-                 bool* more_recent = nullptr);
+  bool IsVisible(SequenceNumber sequence);

  // Temporarily pin the blocks that we encounter until ReleaseTempPinnedData()
  // is called
@@ -271,15 +260,6 @@ class DBIter final : public Iterator {
    return expect_total_order_inner_iter_;
  }

-  // If lower bound of timestamp is given by ReadOptions.iter_start_ts, we need
-  // to return versions of the same key. We cannot just skip if the key value
-  // is the same but timestamps are different but fall in timestamp range.
-  inline int CompareKeyForSkip(const Slice& a, const Slice& b) {
-    return timestamp_lb_ != nullptr
-               ? user_comparator_.Compare(a, b)
-               : user_comparator_.CompareWithoutTimestamp(a, b);
-  }
-
  const SliceTransform* prefix_extractor_;
  Env* const env_;
  Logger* logger_;
@@ -347,9 +327,6 @@ class DBIter final : public Iterator {
  // for diff snapshots we want the lower bound on the seqnum;
  // if this value > 0 iterator will return internal keys
  SequenceNumber start_seqnum_;
-  const Slice* const timestamp_ub_;
-  const Slice* const timestamp_lb_;
-  const size_t timestamp_size_;
 };

 // Return a new iterator that converts internal keys (yielded by
@@ -1167,62 +1167,32 @@ TEST_P(DBIteratorTest, IndexWithFirstKey) {
    ropt.tailing = tailing;
    std::unique_ptr<Iterator> iter(NewIterator(ropt));

-    ropt.read_tier = ReadTier::kBlockCacheTier;
-    std::unique_ptr<Iterator> nonblocking_iter(NewIterator(ropt));
-
    iter->Seek("b10");
    ASSERT_TRUE(iter->Valid());
    EXPECT_EQ("b2", iter->key().ToString());
    EXPECT_EQ("y2", iter->value().ToString());
    EXPECT_EQ(1, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));

-    // The cache-only iterator should succeed too, using the blocks pulled into
-    // the cache by the previous iterator.
-    nonblocking_iter->Seek("b10");
-    ASSERT_TRUE(nonblocking_iter->Valid());
-    EXPECT_EQ("b2", nonblocking_iter->key().ToString());
-    EXPECT_EQ("y2", nonblocking_iter->value().ToString());
-    EXPECT_EQ(1, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
-
-    // ... but it shouldn't be able to step forward since the next block is
-    // not in cache yet.
-    nonblocking_iter->Next();
-    ASSERT_FALSE(nonblocking_iter->Valid());
-    ASSERT_TRUE(nonblocking_iter->status().IsIncomplete());
-
-    // ... nor should a seek to the next key succeed.
-    nonblocking_iter->Seek("b20");
-    ASSERT_FALSE(nonblocking_iter->Valid());
-    ASSERT_TRUE(nonblocking_iter->status().IsIncomplete());
-
    iter->Next();
    ASSERT_TRUE(iter->Valid());
    EXPECT_EQ("b3", iter->key().ToString());
    EXPECT_EQ("y3", iter->value().ToString());
-    EXPECT_EQ(4, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));
-    EXPECT_EQ(1, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
-
-    // After the blocking iterator loaded the next block, the nonblocking
-    // iterator's seek should succeed.
-    nonblocking_iter->Seek("b20");
-    ASSERT_TRUE(nonblocking_iter->Valid());
-    EXPECT_EQ("b3", nonblocking_iter->key().ToString());
-    EXPECT_EQ("y3", nonblocking_iter->value().ToString());
-    EXPECT_EQ(2, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
+    EXPECT_EQ(2, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));
+    EXPECT_EQ(0, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));

    iter->Seek("c0");
    ASSERT_TRUE(iter->Valid());
    EXPECT_EQ("c0", iter->key().ToString());
    EXPECT_EQ("z1,z2", iter->value().ToString());
-    EXPECT_EQ(2, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
-    EXPECT_EQ(6, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));
+    EXPECT_EQ(0, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
+    EXPECT_EQ(4, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));

    iter->Next();
    ASSERT_TRUE(iter->Valid());
    EXPECT_EQ("c3", iter->key().ToString());
    EXPECT_EQ("z3", iter->value().ToString());
-    EXPECT_EQ(2, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
-    EXPECT_EQ(7, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));
+    EXPECT_EQ(0, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
+    EXPECT_EQ(5, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));

    iter.reset();

@@ -1237,13 +1207,13 @@ TEST_P(DBIteratorTest, IndexWithFirstKey) {
    ASSERT_TRUE(iter->Valid());
    EXPECT_EQ("b2", iter->key().ToString());
    EXPECT_EQ("y2", iter->value().ToString());
-    EXPECT_EQ(3, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
-    EXPECT_EQ(7, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));
+    EXPECT_EQ(1, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
+    EXPECT_EQ(5, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));

    iter->Next();
    ASSERT_FALSE(iter->Valid());
-    EXPECT_EQ(3, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
-    EXPECT_EQ(7, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));
+    EXPECT_EQ(1, stats->getTickerCount(BLOCK_CACHE_DATA_HIT));
+    EXPECT_EQ(5, stats->getTickerCount(BLOCK_CACHE_DATA_MISS));
  }
 }

@@ -1903,7 +1873,7 @@ TEST_P(DBIteratorTest, IterPrevKeyCrossingBlocksRandomized) {
  DestroyAndReopen(options);

  const int kNumKeys = 500;
-  // Small number of merge operands to make sure that DBIter::Prev() don't
+  // Small number of merge operands to make sure that DBIter::Prev() dont
  // fall back to Seek()
  const int kNumMergeOperands = 3;
  // Use value size that will make sure that every block contain 1 key
@@ -1938,7 +1908,7 @@ TEST_P(DBIteratorTest, IterPrevKeyCrossingBlocksRandomized) {
  ASSERT_OK(Flush());

  // Separate values and merge operands in different file so that we
-  // make sure that we don't merge them while flushing but actually
+  // make sure that we dont merge them while flushing but actually
  // merge them in the read path
  for (int i = 0; i < kNumKeys; i++) {
    if (rnd.PercentTrue(kNoMergeOpPercentage)) {
@@ -1,513 +0,0 @@
-// Copyright (c) 2020-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 "test_util/testharness.h"
-
-#ifdef OS_LINUX
-#include "env/io_posix.h"
-#include "rocksdb/db.h"
-#include "rocksdb/env.h"
-
-namespace ROCKSDB_NAMESPACE {
-class EnvWithCustomLogicalBlockSizeCache : public EnvWrapper {
- public:
-  EnvWithCustomLogicalBlockSizeCache(Env* env, LogicalBlockSizeCache* cache)
-      : EnvWrapper(env), cache_(cache) {}
-
-  Status RegisterDbPaths(const std::vector<std::string>& paths) override {
-    return cache_->RefAndCacheLogicalBlockSize(paths);
-  }
-
-  Status UnregisterDbPaths(const std::vector<std::string>& paths) override {
-    cache_->UnrefAndTryRemoveCachedLogicalBlockSize(paths);
-    return Status::OK();
-  }
-
- private:
-  LogicalBlockSizeCache* cache_;
-};
-
-class DBLogicalBlockSizeCacheTest : public testing::Test {
- public:
-  DBLogicalBlockSizeCacheTest()
-      : dbname_(test::PerThreadDBPath("logical_block_size_cache_test")),
-        data_path_0_(dbname_ + "/data_path_0"),
-        data_path_1_(dbname_ + "/data_path_1"),
-        cf_path_0_(dbname_ + "/cf_path_0"),
-        cf_path_1_(dbname_ + "/cf_path_1") {
-    auto get_fd_block_size = [&](int fd) { return fd; };
-    auto get_dir_block_size = [&](const std::string& /*dir*/, size_t* size) {
-      *size = 1024;
-      return Status::OK();
-    };
-    cache_.reset(
-        new LogicalBlockSizeCache(get_fd_block_size, get_dir_block_size));
-    env_.reset(
-        new EnvWithCustomLogicalBlockSizeCache(Env::Default(), cache_.get()));
-  }
-
- protected:
-  std::string dbname_;
-  std::string data_path_0_;
-  std::string data_path_1_;
-  std::string cf_path_0_;
-  std::string cf_path_1_;
-  std::unique_ptr<LogicalBlockSizeCache> cache_;
-  std::unique_ptr<Env> env_;
-};
-
-TEST_F(DBLogicalBlockSizeCacheTest, OpenClose) {
-  // Tests that Open will cache the logical block size for data paths,
-  // and Close will remove the cached sizes.
-  Options options;
-  options.create_if_missing = true;
-  options.env = env_.get();
-  options.db_paths = {{data_path_0_, 2048}, {data_path_1_, 2048}};
-
-  for (int i = 0; i < 2; i++) {
-    DB* db;
-    if (!i) {
-      printf("Open\n");
-      ASSERT_OK(DB::Open(options, dbname_, &db));
-    } else {
-#ifdef ROCKSDB_LITE
-      break;
-#else
-      printf("OpenForReadOnly\n");
-      ASSERT_OK(DB::OpenForReadOnly(options, dbname_, &db));
-#endif
-    }
-    ASSERT_EQ(2, cache_->Size());
-    ASSERT_TRUE(cache_->Contains(data_path_0_));
-    ASSERT_EQ(1, cache_->GetRefCount(data_path_0_));
-    ASSERT_TRUE(cache_->Contains(data_path_1_));
-    ASSERT_EQ(1, cache_->GetRefCount(data_path_1_));
-    ASSERT_OK(db->Close());
-    ASSERT_EQ(0, cache_->Size());
-    delete db;
-  }
-  ASSERT_OK(DestroyDB(dbname_, options, {}));
-}
-
-TEST_F(DBLogicalBlockSizeCacheTest, OpenDelete) {
-  // Tests that Open will cache the logical block size for data paths,
-  // and delete the db pointer will remove the cached sizes.
-  Options options;
-  options.create_if_missing = true;
-  options.env = env_.get();
-
-  for (int i = 0; i < 2; i++) {
-    DB* db;
-    if (!i) {
-      printf("Open\n");
-      ASSERT_OK(DB::Open(options, dbname_, &db));
-    } else {
-#ifdef ROCKSDB_LITE
-      break;
-#else
-      printf("OpenForReadOnly\n");
-      ASSERT_OK(DB::OpenForReadOnly(options, dbname_, &db));
-#endif
-    }
-    ASSERT_EQ(1, cache_->Size());
-    ASSERT_TRUE(cache_->Contains(dbname_));
-    ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-    delete db;
-    ASSERT_EQ(0, cache_->Size());
-  }
-  ASSERT_OK(DestroyDB(dbname_, options, {}));
-}
-
-TEST_F(DBLogicalBlockSizeCacheTest, CreateColumnFamily) {
-  // Tests that CreateColumnFamily will cache the cf_paths,
-  // drop the column family handle won't drop the cache,
-  // drop and then delete the column family handle will drop the cache.
-  Options options;
-  options.create_if_missing = true;
-  options.env = env_.get();
-  ColumnFamilyOptions cf_options;
-  cf_options.cf_paths = {{cf_path_0_, 1024}, {cf_path_1_, 2048}};
-
-  DB* db;
-  ASSERT_OK(DB::Open(options, dbname_, &db));
-  ASSERT_EQ(1, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-
-  ColumnFamilyHandle* cf = nullptr;
-  ASSERT_OK(db->CreateColumnFamily(cf_options, "cf", &cf));
-  ASSERT_EQ(3, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-  ASSERT_TRUE(cache_->Contains(cf_path_1_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_1_));
-
-  // Drop column family does not drop cache.
-  ASSERT_OK(db->DropColumnFamily(cf));
-  ASSERT_EQ(3, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-  ASSERT_TRUE(cache_->Contains(cf_path_1_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_1_));
-
-  // Delete handle will drop cache.
-  ASSERT_OK(db->DestroyColumnFamilyHandle(cf));
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-
-  delete db;
-  ASSERT_EQ(0, cache_->Size());
-  ASSERT_OK(DestroyDB(dbname_, options, {{"cf", cf_options}}));
-}
-
-TEST_F(DBLogicalBlockSizeCacheTest, CreateColumnFamilies) {
-  // Tests that CreateColumnFamilies will cache the cf_paths,
-  // drop the column family handle won't drop the cache,
-  // drop and then delete the column family handle will drop the cache.
-  Options options;
-  options.create_if_missing = true;
-  options.env = env_.get();
-  ColumnFamilyOptions cf_options;
-  cf_options.cf_paths = {{cf_path_0_, 1024}};
-
-  DB* db;
-  ASSERT_OK(DB::Open(options, dbname_, &db));
-  ASSERT_EQ(1, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-
-  std::vector<ColumnFamilyHandle*> cfs;
-  ASSERT_OK(db->CreateColumnFamilies(cf_options, {"cf1", "cf2"}, &cfs));
-  ASSERT_EQ(2, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(2, cache_->GetRefCount(cf_path_0_));
-
-  // Drop column family does not drop cache.
-  for (ColumnFamilyHandle* cf : cfs) {
-    ASSERT_OK(db->DropColumnFamily(cf));
-    ASSERT_EQ(2, cache_->Size());
-    ASSERT_TRUE(cache_->Contains(dbname_));
-    ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-    ASSERT_TRUE(cache_->Contains(cf_path_0_));
-    ASSERT_EQ(2, cache_->GetRefCount(cf_path_0_));
-  }
-
-  // Delete one handle will not drop cache because another handle is still
-  // referencing cf_path_0_.
-  ASSERT_OK(db->DestroyColumnFamilyHandle(cfs[0]));
-  ASSERT_EQ(2, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-
-  // Delete the last handle will drop cache.
-  ASSERT_OK(db->DestroyColumnFamilyHandle(cfs[1]));
-  ASSERT_EQ(1, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-
-  delete db;
-  ASSERT_EQ(0, cache_->Size());
-  ASSERT_OK(DestroyDB(dbname_, options,
-      {{"cf1", cf_options}, {"cf2", cf_options}}));
-}
-
-TEST_F(DBLogicalBlockSizeCacheTest, OpenWithColumnFamilies) {
-  // Tests that Open two column families with the same cf_path will cache the
-  // cf_path and have 2 references to the cached size,
-  // drop the column family handle won't drop the cache,
-  // drop and then delete the column family handle will drop the cache.
-  Options options;
-  options.create_if_missing = true;
-  options.env = env_.get();
-
-  ColumnFamilyOptions cf_options;
-  cf_options.cf_paths = {{cf_path_0_, 1024}};
-
-  for (int i = 0; i < 2; i++) {
-    DB* db;
-    ColumnFamilyHandle* cf1 = nullptr;
-    ColumnFamilyHandle* cf2 = nullptr;
-    ASSERT_OK(DB::Open(options, dbname_, &db));
-    ASSERT_OK(db->CreateColumnFamily(cf_options, "cf1", &cf1));
-    ASSERT_OK(db->CreateColumnFamily(cf_options, "cf2", &cf2));
-    ASSERT_OK(db->DestroyColumnFamilyHandle(cf1));
-    ASSERT_OK(db->DestroyColumnFamilyHandle(cf2));
-    delete db;
-    ASSERT_EQ(0, cache_->Size());
-
-    std::vector<ColumnFamilyHandle*> cfs;
-    if (!i) {
-      printf("Open\n");
-      ASSERT_OK(DB::Open(options, dbname_,
-                         {{"cf1", cf_options},
-                          {"cf2", cf_options},
-                          {"default", ColumnFamilyOptions()}},
-                         &cfs, &db));
-    } else {
-#ifdef ROCKSDB_LITE
-      break;
-#else
-      printf("OpenForReadOnly\n");
-      ASSERT_OK(DB::OpenForReadOnly(options, dbname_,
-                                    {{"cf1", cf_options},
-                                     {"cf2", cf_options},
-                                     {"default", ColumnFamilyOptions()}},
-                                    &cfs, &db));
-#endif
-    }
-
-    // Logical block sizes of dbname_ and cf_path_0_ are cached during Open.
-    ASSERT_EQ(2, cache_->Size());
-    ASSERT_TRUE(cache_->Contains(dbname_));
-    ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-    ASSERT_TRUE(cache_->Contains(cf_path_0_));
-    ASSERT_EQ(2, cache_->GetRefCount(cf_path_0_));
-
-    // Drop handles won't drop the cache.
-    ASSERT_OK(db->DropColumnFamily(cfs[0]));
-    ASSERT_OK(db->DropColumnFamily(cfs[1]));
-    ASSERT_EQ(2, cache_->Size());
-    ASSERT_TRUE(cache_->Contains(dbname_));
-    ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-    ASSERT_TRUE(cache_->Contains(cf_path_0_));
-    ASSERT_EQ(2, cache_->GetRefCount(cf_path_0_));
-
-    // Delete 1st handle won't drop the cache for cf_path_0_.
-    ASSERT_OK(db->DestroyColumnFamilyHandle(cfs[0]));
-    ASSERT_EQ(2, cache_->Size());
-    ASSERT_TRUE(cache_->Contains(dbname_));
-    ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-    ASSERT_TRUE(cache_->Contains(cf_path_0_));
-    ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-
-    // Delete 2nd handle will drop the cache for cf_path_0_.
-    ASSERT_OK(db->DestroyColumnFamilyHandle(cfs[1]));
-    ASSERT_EQ(1, cache_->Size());
-    ASSERT_TRUE(cache_->Contains(dbname_));
-    ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-
-    // Delete the default handle won't affect the cache because db still refers
-    // to the default CF.
-    ASSERT_OK(db->DestroyColumnFamilyHandle(cfs[2]));
-    ASSERT_EQ(1, cache_->Size());
-    ASSERT_TRUE(cache_->Contains(dbname_));
-    ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-
-    delete db;
-    ASSERT_EQ(0, cache_->Size());
-  }
-  ASSERT_OK(DestroyDB(dbname_, options,
-      {{"cf1", cf_options}, {"cf2", cf_options}}));
-}
-
-TEST_F(DBLogicalBlockSizeCacheTest, DestroyColumnFamilyHandle) {
-  // Tests that destroy column family without dropping won't drop the cache,
-  // because compaction and flush might still need to get logical block size
-  // when opening new files.
-  Options options;
-  options.create_if_missing = true;
-  options.env = env_.get();
-  ColumnFamilyOptions cf_options;
-  cf_options.cf_paths = {{cf_path_0_, 1024}};
-
-  DB* db;
-  ASSERT_OK(DB::Open(options, dbname_, &db));
-  ASSERT_EQ(1, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-  ColumnFamilyHandle* cf = nullptr;
-  ASSERT_OK(db->CreateColumnFamily(cf_options, "cf", &cf));
-  ASSERT_EQ(2, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-
-  // Delete handle won't drop cache.
-  ASSERT_OK(db->DestroyColumnFamilyHandle(cf));
-  ASSERT_EQ(2, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(dbname_));
-  ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-
-  delete db;
-  ASSERT_EQ(0, cache_->Size());
-
-  // Open with column families.
-  std::vector<ColumnFamilyHandle*> cfs;
-  for (int i = 0; i < 2; i++) {
-    if (!i) {
-      printf("Open\n");
-      ASSERT_OK(DB::Open(
-          options, dbname_,
-          {{"cf", cf_options}, {"default", ColumnFamilyOptions()}}, &cfs, &db));
-    } else {
-#ifdef ROCKSDB_LITE
-      break;
-#else
-      printf("OpenForReadOnly\n");
-      ASSERT_OK(DB::OpenForReadOnly(
-          options, dbname_,
-          {{"cf", cf_options}, {"default", ColumnFamilyOptions()}}, &cfs, &db));
-#endif
-    }
-    // cf_path_0_ and dbname_ are cached.
-    ASSERT_EQ(2, cache_->Size());
-    ASSERT_TRUE(cache_->Contains(dbname_));
-    ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-    ASSERT_TRUE(cache_->Contains(cf_path_0_));
-    ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-
-    // Deleting handle won't drop cache.
-    ASSERT_OK(db->DestroyColumnFamilyHandle(cfs[0]));
-    ASSERT_OK(db->DestroyColumnFamilyHandle(cfs[1]));
-    ASSERT_EQ(2, cache_->Size());
-    ASSERT_TRUE(cache_->Contains(dbname_));
-    ASSERT_EQ(1, cache_->GetRefCount(dbname_));
-    ASSERT_TRUE(cache_->Contains(cf_path_0_));
-    ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-
-    delete db;
-    ASSERT_EQ(0, cache_->Size());
-  }
-  ASSERT_OK(DestroyDB(dbname_, options, {{"cf", cf_options}}));
-}
-
-TEST_F(DBLogicalBlockSizeCacheTest, MultiDBWithDifferentPaths) {
-  // Tests the cache behavior when there are multiple DBs sharing the same env
-  // with different db_paths and cf_paths.
-  Options options;
-  options.create_if_missing = true;
-  options.env = env_.get();
-
-  ASSERT_OK(env_->CreateDirIfMissing(dbname_));
-
-  DB* db0;
-  ASSERT_OK(DB::Open(options, data_path_0_, &db0));
-  ASSERT_EQ(1, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(data_path_0_));
-
-  ColumnFamilyOptions cf_options0;
-  cf_options0.cf_paths = {{cf_path_0_, 1024}};
-  ColumnFamilyHandle* cf0;
-  db0->CreateColumnFamily(cf_options0, "cf", &cf0);
-  ASSERT_EQ(2, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(data_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(data_path_0_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-
-  DB* db1;
-  ASSERT_OK(DB::Open(options, data_path_1_, &db1));
-  ASSERT_EQ(3, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(data_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(data_path_0_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-  ASSERT_TRUE(cache_->Contains(data_path_1_));
-  ASSERT_EQ(1, cache_->GetRefCount(data_path_1_));
-
-  ColumnFamilyOptions cf_options1;
-  cf_options1.cf_paths = {{cf_path_1_, 1024}};
-  ColumnFamilyHandle* cf1;
-  db1->CreateColumnFamily(cf_options1, "cf", &cf1);
-  ASSERT_EQ(4, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(data_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(data_path_0_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-  ASSERT_TRUE(cache_->Contains(data_path_1_));
-  ASSERT_EQ(1, cache_->GetRefCount(data_path_1_));
-  ASSERT_TRUE(cache_->Contains(cf_path_1_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_1_));
-
-  db0->DestroyColumnFamilyHandle(cf0);
-  delete db0;
-  ASSERT_EQ(2, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(data_path_1_));
-  ASSERT_EQ(1, cache_->GetRefCount(data_path_1_));
-  ASSERT_TRUE(cache_->Contains(cf_path_1_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_1_));
-  ASSERT_OK(DestroyDB(data_path_0_, options, {{"cf", cf_options0}}));
-
-  db1->DestroyColumnFamilyHandle(cf1);
-  delete db1;
-  ASSERT_EQ(0, cache_->Size());
-  ASSERT_OK(DestroyDB(data_path_1_, options, {{"cf", cf_options1}}));
-}
-
-TEST_F(DBLogicalBlockSizeCacheTest, MultiDBWithSamePaths) {
-  // Tests the cache behavior when there are multiple DBs sharing the same env
-  // with the same db_paths and cf_paths.
-  Options options;
-  options.create_if_missing = true;
-  options.env = env_.get();
-  options.db_paths = {{data_path_0_, 1024}};
-  ColumnFamilyOptions cf_options;
-  cf_options.cf_paths = {{cf_path_0_, 1024}};
-
-  ASSERT_OK(env_->CreateDirIfMissing(dbname_));
-
-  DB* db0;
-  ASSERT_OK(DB::Open(options, dbname_ + "/db0", &db0));
-  ASSERT_EQ(1, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(data_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(data_path_0_));
-
-  ColumnFamilyHandle* cf0;
-  db0->CreateColumnFamily(cf_options, "cf", &cf0);
-  ASSERT_EQ(2, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(data_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(data_path_0_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-
-  DB* db1;
-  ASSERT_OK(DB::Open(options, dbname_ + "/db1", &db1));
-  ASSERT_EQ(2, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(data_path_0_));
-  ASSERT_EQ(2, cache_->GetRefCount(data_path_0_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-
-  ColumnFamilyHandle* cf1;
-  db1->CreateColumnFamily(cf_options, "cf", &cf1);
-  ASSERT_EQ(2, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(data_path_0_));
-  ASSERT_EQ(2, cache_->GetRefCount(data_path_0_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(2, cache_->GetRefCount(cf_path_0_));
-
-  db0->DestroyColumnFamilyHandle(cf0);
-  delete db0;
-  ASSERT_EQ(2, cache_->Size());
-  ASSERT_TRUE(cache_->Contains(data_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(data_path_0_));
-  ASSERT_TRUE(cache_->Contains(cf_path_0_));
-  ASSERT_EQ(1, cache_->GetRefCount(cf_path_0_));
-  ASSERT_OK(DestroyDB(dbname_ + "/db0", options, {{"cf", cf_options}}));
-
-  db1->DestroyColumnFamilyHandle(cf1);
-  delete db1;
-  ASSERT_EQ(0, cache_->Size());
-  ASSERT_OK(DestroyDB(dbname_ + "/db1", options, {{"cf", cf_options}}));
-}
-
-}  // namespace ROCKSDB_NAMESPACE
-#endif  // OS_LINUX
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
@@ -261,7 +261,7 @@ TEST_F(DBMemTableTest, ConcurrentMergeWrite) {
  ReadOptions roptions;
  SequenceNumber max_covering_tombstone_seq = 0;
  LookupKey lkey("key", kMaxSequenceNumber);
-  res = mem->Get(lkey, &value, /*timestamp=*/nullptr, &status, &merge_context,
+  res = mem->Get(lkey, &value, &status, &merge_context,
                 &max_covering_tombstone_seq, roptions);
  ASSERT_TRUE(res);
  uint64_t ivalue = DecodeFixed64(Slice(value).data());
@@ -33,14 +33,13 @@ class DBOptionsTest : public DBTestBase {
  std::unordered_map<std::string, std::string> GetMutableDBOptionsMap(
      const DBOptions& options) {
    std::string options_str;
-    ConfigOptions config_options;
-    config_options.delimiter = "; ";
-    GetStringFromDBOptions(config_options, options, &options_str);
+    GetStringFromDBOptions(&options_str, options);
    std::unordered_map<std::string, std::string> options_map;
    StringToMap(options_str, &options_map);
    std::unordered_map<std::string, std::string> mutable_map;
    for (const auto opt : db_options_type_info) {
-      if (opt.second.IsMutable() && opt.second.ShouldSerialize()) {
+      if (opt.second.is_mutable &&
+          opt.second.verification != OptionVerificationType::kDeprecated) {
        mutable_map[opt.first] = options_map[opt.first];
      }
    }
@@ -50,15 +49,13 @@ class DBOptionsTest : public DBTestBase {
  std::unordered_map<std::string, std::string> GetMutableCFOptionsMap(
      const ColumnFamilyOptions& options) {
    std::string options_str;
-    ConfigOptions config_options;
-    config_options.delimiter = "; ";
-
-    GetStringFromColumnFamilyOptions(config_options, options, &options_str);
+    GetStringFromColumnFamilyOptions(&options_str, options);
    std::unordered_map<std::string, std::string> options_map;
    StringToMap(options_str, &options_map);
    std::unordered_map<std::string, std::string> mutable_map;
    for (const auto opt : cf_options_type_info) {
-      if (opt.second.IsMutable() && opt.second.ShouldSerialize()) {
+      if (opt.second.is_mutable &&
+          opt.second.verification != OptionVerificationType::kDeprecated) {
        mutable_map[opt.first] = options_map[opt.first];
      }
    }
@@ -407,20 +404,6 @@ TEST_F(DBOptionsTest, SetBackgroundCompactionThreads) {
  ASSERT_EQ(3, dbfull()->TEST_BGCompactionsAllowed());
 }

-TEST_F(DBOptionsTest, SetBackgroundFlushThreads) {
-  Options options;
-  options.create_if_missing = true;
-  options.max_background_flushes = 1;
-  options.env = env_;
-  Reopen(options);
-  ASSERT_EQ(1, dbfull()->TEST_BGFlushesAllowed());
-  ASSERT_EQ(1, env_->GetBackgroundThreads(Env::Priority::HIGH));
-  ASSERT_OK(dbfull()->SetDBOptions({{"max_background_flushes", "3"}}));
-  ASSERT_EQ(3, env_->GetBackgroundThreads(Env::Priority::HIGH));
-  ASSERT_EQ(3, dbfull()->TEST_BGFlushesAllowed());
-}
-
-
 TEST_F(DBOptionsTest, SetBackgroundJobs) {
  Options options;
  options.create_if_missing = true;
@@ -876,66 +859,6 @@ TEST_F(DBOptionsTest, FIFOTtlBackwardCompatible) {
  ASSERT_EQ(dbfull()->GetOptions().ttl, 191);
 }

-TEST_F(DBOptionsTest, ChangeCompression) {
-  if (!Snappy_Supported() || !LZ4_Supported()) {
-    return;
-  }
-  Options options;
-  options.write_buffer_size = 10 << 10;  // 10KB
-  options.level0_file_num_compaction_trigger = 2;
-  options.create_if_missing = true;
-  options.compression = CompressionType::kLZ4Compression;
-  options.bottommost_compression = CompressionType::kNoCompression;
-  options.bottommost_compression_opts.level = 2;
-  options.bottommost_compression_opts.parallel_threads = 1;
-
-  ASSERT_OK(TryReopen(options));
-
-  CompressionType compression_used = CompressionType::kLZ4Compression;
-  CompressionOptions compression_opt_used;
-  bool compacted = false;
-  SyncPoint::GetInstance()->SetCallBack(
-      "LevelCompactionPicker::PickCompaction:Return", [&](void* arg) {
-        Compaction* c = reinterpret_cast<Compaction*>(arg);
-        compression_used = c->output_compression();
-        compression_opt_used = c->output_compression_opts();
-        compacted = true;
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put("foo", "foofoofoo"));
-  ASSERT_OK(Put("bar", "foofoofoo"));
-  ASSERT_OK(Flush());
-  ASSERT_OK(Put("foo", "foofoofoo"));
-  ASSERT_OK(Put("bar", "foofoofoo"));
-  ASSERT_OK(Flush());
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_TRUE(compacted);
-  ASSERT_EQ(CompressionType::kNoCompression, compression_used);
-  ASSERT_EQ(options.compression_opts.level, compression_opt_used.level);
-  ASSERT_EQ(options.compression_opts.parallel_threads,
-            compression_opt_used.parallel_threads);
-
-  compression_used = CompressionType::kLZ4Compression;
-  compacted = false;
-  ASSERT_OK(dbfull()->SetOptions(
-      {{"bottommost_compression", "kSnappyCompression"},
-       {"bottommost_compression_opts", "0:6:0:0:4:true"}}));
-  ASSERT_OK(Put("foo", "foofoofoo"));
-  ASSERT_OK(Put("bar", "foofoofoo"));
-  ASSERT_OK(Flush());
-  ASSERT_OK(Put("foo", "foofoofoo"));
-  ASSERT_OK(Put("bar", "foofoofoo"));
-  ASSERT_OK(Flush());
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_TRUE(compacted);
-  ASSERT_EQ(CompressionType::kSnappyCompression, compression_used);
-  ASSERT_EQ(6, compression_opt_used.level);
-  // Right now parallel_level is not yet allowed to be changed.
-
-  SyncPoint::GetInstance()->DisableProcessing();
-}
-
 #endif  // ROCKSDB_LITE

 }  // namespace ROCKSDB_NAMESPACE
@@ -47,21 +47,6 @@ TEST_F(DBRangeDelTest, WriteBatchWithIndexNotSupported) {
  ASSERT_TRUE(indexedBatch.DeleteRange("dr1", "dr1").IsNotSupported());
 }

-TEST_F(DBRangeDelTest, EndSameAsStartCoversNothing) {
-  ASSERT_OK(db_->Put(WriteOptions(), "b", "val"));
-  ASSERT_OK(
-      db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(), "b", "b"));
-  ASSERT_EQ("val", Get("b"));
-}
-
-TEST_F(DBRangeDelTest, EndComesBeforeStartInvalidArgument) {
-  db_->Put(WriteOptions(), "b", "val");
-  ASSERT_TRUE(
-      db_->DeleteRange(WriteOptions(), db_->DefaultColumnFamily(), "b", "a")
-          .IsInvalidArgument());
-  ASSERT_EQ("val", Get("b"));
-}
-
 TEST_F(DBRangeDelTest, FlushOutputHasOnlyRangeTombstones) {
  do {
    DestroyAndReopen(CurrentOptions());
@@ -356,25 +356,37 @@ TEST_F(DBSSTTest, RateLimitedDelete) {
      "InstrumentedCondVar::TimedWaitInternal", [&](void* arg) {
        // Turn timed wait into a simulated sleep
        uint64_t* abs_time_us = static_cast<uint64_t*>(arg);
-        uint64_t cur_time = env_->NowMicros();
-        if (*abs_time_us > cur_time) {
-          env_->addon_time_.fetch_add(*abs_time_us - cur_time);
+        int64_t cur_time = 0;
+        env_->GetCurrentTime(&cur_time);
+        if (*abs_time_us > static_cast<uint64_t>(cur_time)) {
+          env_->addon_time_.fetch_add(*abs_time_us -
+                                      static_cast<uint64_t>(cur_time));
        }

        // Randomly sleep shortly
        env_->addon_time_.fetch_add(
            static_cast<uint64_t>(Random::GetTLSInstance()->Uniform(10)));

-        // Set wait until time to before (actual) current time to force not
-        // to sleep
-        *abs_time_us = Env::Default()->NowMicros();
+        // Set wait until time to before current to force not to sleep.
+        int64_t real_cur_time = 0;
+        Env::Default()->GetCurrentTime(&real_cur_time);
+        *abs_time_us = static_cast<uint64_t>(real_cur_time);
      });

  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();

+  env_->no_slowdown_ = true;
+  env_->time_elapse_only_sleep_ = true;
  Options options = CurrentOptions();
-  env_->SetTimeElapseOnlySleep(&options);
  options.disable_auto_compactions = true;
+  // Need to disable stats dumping and persisting which also use
+  // RepeatableThread, one of whose member variables is of type
+  // InstrumentedCondVar. The callback for
+  // InstrumentedCondVar::TimedWaitInternal can be triggered by stats dumping
+  // and persisting threads and cause time_spent_deleting measurement to become
+  // incorrect.
+  options.stats_dump_period_sec = 0;
+  options.stats_persist_period_sec = 0;
  options.env = env_;

  int64_t rate_bytes_per_sec = 1024 * 10;  // 10 Kbs / Sec
@@ -45,8 +45,7 @@ void VerifyTableProperties(DB* db, uint64_t expected_entries_size) {
 }
 }  // namespace

-class DBTablePropertiesTest : public DBTestBase,
-                              public testing::WithParamInterface<std::string> {
+class DBTablePropertiesTest : public DBTestBase {
 public:
  DBTablePropertiesTest() : DBTestBase("/db_table_properties_test") {}
  TablePropertiesCollection TestGetPropertiesOfTablesInRange(
@@ -252,20 +251,7 @@ TEST_F(DBTablePropertiesTest, GetColumnFamilyNameProperty) {
  }
 }

-class DeletionTriggeredCompactionTestListener : public EventListener {
- public:
-  void OnCompactionBegin(DB* , const CompactionJobInfo& ci) override {
-    ASSERT_EQ(ci.compaction_reason,
-              CompactionReason::kFilesMarkedForCompaction);
-  }
-
-  void OnCompactionCompleted(DB* , const CompactionJobInfo& ci) override {
-    ASSERT_EQ(ci.compaction_reason,
-              CompactionReason::kFilesMarkedForCompaction);
-  }
-};
-
-TEST_P(DBTablePropertiesTest, DeletionTriggeredCompactionMarking) {
+TEST_F(DBTablePropertiesTest, DeletionTriggeredCompactionMarking) {
  int kNumKeys = 1000;
  int kWindowSize = 100;
  int kNumDelsTrigger = 90;
@@ -274,10 +260,6 @@ TEST_P(DBTablePropertiesTest, DeletionTriggeredCompactionMarking) {

  Options opts = CurrentOptions();
  opts.table_properties_collector_factories.emplace_back(compact_on_del);
-
-  if(GetParam() == "kCompactionStyleUniversal") {
-    opts.compaction_style = kCompactionStyleUniversal;
-  }
  Reopen(opts);

  // add an L1 file to prevent tombstones from dropping due to obsolescence
@@ -286,11 +268,6 @@ TEST_P(DBTablePropertiesTest, DeletionTriggeredCompactionMarking) {
  Flush();
  MoveFilesToLevel(1);

-  DeletionTriggeredCompactionTestListener *listener =
-    new DeletionTriggeredCompactionTestListener();
-  opts.listeners.emplace_back(listener);
-  Reopen(opts);
-
  for (int i = 0; i < kNumKeys; ++i) {
    if (i >= kNumKeys - kWindowSize &&
        i < kNumKeys - kWindowSize + kNumDelsTrigger) {
@@ -303,6 +280,7 @@ TEST_P(DBTablePropertiesTest, DeletionTriggeredCompactionMarking) {

  dbfull()->TEST_WaitForCompact();
  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+  ASSERT_GT(NumTableFilesAtLevel(1), 0);

  // Change the window size and deletion trigger and ensure new values take
  // effect
@@ -324,6 +302,7 @@ TEST_P(DBTablePropertiesTest, DeletionTriggeredCompactionMarking) {

  dbfull()->TEST_WaitForCompact();
  ASSERT_EQ(0, NumTableFilesAtLevel(0));
+  ASSERT_GT(NumTableFilesAtLevel(1), 0);

  // Change the window size to disable delete triggered compaction
  kWindowSize = 0;
@@ -343,15 +322,8 @@ TEST_P(DBTablePropertiesTest, DeletionTriggeredCompactionMarking) {

  dbfull()->TEST_WaitForCompact();
  ASSERT_EQ(1, NumTableFilesAtLevel(0));
-}

-INSTANTIATE_TEST_CASE_P(
-    DBTablePropertiesTest,
-    DBTablePropertiesTest,
-    ::testing::Values(
-      "kCompactionStyleLevel",
-      "kCompactionStyleUniversal"
-      ));
+}

 }  // namespace ROCKSDB_NAMESPACE

@@ -24,7 +24,7 @@
 #endif

 #include "cache/lru_cache.h"
-#include "db/blob/blob_index.h"
+#include "db/blob_index.h"
 #include "db/db_impl/db_impl.h"
 #include "db/db_test_util.h"
 #include "db/dbformat.h"
@@ -1421,7 +1421,7 @@ TEST_F(DBTest, ApproximateSizesMemTable) {
    keys[i * 3 + 1] = i * 5 + 1;
    keys[i * 3 + 2] = i * 5 + 2;
  }
-  RandomShuffle(std::begin(keys), std::end(keys));
+  std::random_shuffle(std::begin(keys), std::end(keys));

  for (int i = 0; i < N * 3; i++) {
    ASSERT_OK(Put(Key(keys[i] + 1000), RandomString(&rnd, 1024)));
@@ -2309,42 +2309,6 @@ TEST_F(DBTest, ReadonlyDBGetLiveManifestSize) {
    Close();
  } while (ChangeCompactOptions());
 }
-
-TEST_F(DBTest, GetLiveBlobFiles) {
-  VersionSet* const versions = dbfull()->TEST_GetVersionSet();
-  assert(versions);
-  assert(versions->GetColumnFamilySet());
-
-  ColumnFamilyData* const cfd = versions->GetColumnFamilySet()->GetDefault();
-  assert(cfd);
-
-  // Add a live blob file.
-  VersionEdit edit;
-
-  constexpr uint64_t blob_file_number = 234;
-  constexpr uint64_t total_blob_count = 555;
-  constexpr uint64_t total_blob_bytes = 66666;
-  constexpr char checksum_method[] = "CRC32";
-  constexpr char checksum_value[] = "3d87ff57";
-
-  edit.AddBlobFile(blob_file_number, total_blob_count, total_blob_bytes,
-                   checksum_method, checksum_value);
-
-  dbfull()->TEST_LockMutex();
-  Status s = versions->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
-                                   &edit, dbfull()->mutex());
-  dbfull()->TEST_UnlockMutex();
-
-  ASSERT_OK(s);
-
-  // Make sure it appears in the results returned by GetLiveFiles.
-  uint64_t manifest_size = 0;
-  std::vector<std::string> files;
-  ASSERT_OK(dbfull()->GetLiveFiles(files, &manifest_size));
-
-  ASSERT_FALSE(files.empty());
-  ASSERT_EQ(files[0], BlobFileName("", blob_file_number));
-}
 #endif

 TEST_F(DBTest, PurgeInfoLogs) {
@@ -4333,7 +4297,7 @@ TEST_P(DBTestWithParam, PreShutdownManualCompaction) {
    ASSERT_EQ("1,1,1", FilesPerLevel(1));

    // Compaction range overlaps files
-    Compact(1, "p", "q");
+    Compact(1, "p1", "p9");
    ASSERT_EQ("0,0,1", FilesPerLevel(1));

    // Populate a different range
@@ -4566,7 +4530,7 @@ TEST_F(DBTest, DynamicLevelCompressionPerLevel) {
  for (int i = 0; i < kNKeys; i++) {
    keys[i] = i;
  }
-  RandomShuffle(std::begin(keys), std::end(keys));
+  std::random_shuffle(std::begin(keys), std::end(keys));

  Random rnd(301);
  Options options;
@@ -4649,7 +4613,7 @@ TEST_F(DBTest, DynamicLevelCompressionPerLevel2) {
  for (int i = 0; i < kNKeys; i++) {
    keys[i] = i;
  }
-  RandomShuffle(std::begin(keys), std::end(keys));
+  std::random_shuffle(std::begin(keys), std::end(keys));

  Random rnd(301);
  Options options;
@@ -5406,8 +5370,6 @@ class DelayedMergeOperator : public MergeOperator {
  const char* Name() const override { return "DelayedMergeOperator"; }
 };

-// TODO: hangs in CircleCI's Windows env
-#ifndef OS_WIN
 TEST_F(DBTest, MergeTestTime) {
  std::string one, two, three;
  PutFixed64(&one, 1);
@@ -5455,7 +5417,6 @@ TEST_F(DBTest, MergeTestTime) {
 #endif  // ROCKSDB_USING_THREAD_STATUS
  this->env_->time_elapse_only_sleep_ = false;
 }
-#endif // OS_WIN

 #ifndef ROCKSDB_LITE
 TEST_P(DBTestWithParam, MergeCompactionTimeTest) {
@@ -5539,7 +5500,7 @@ TEST_F(DBTest, EmptyCompactedDB) {
 #endif  // ROCKSDB_LITE

 #ifndef ROCKSDB_LITE
-TEST_F(DBTest, DISABLED_SuggestCompactRangeTest) {
+TEST_F(DBTest, SuggestCompactRangeTest) {
  class CompactionFilterFactoryGetContext : public CompactionFilterFactory {
   public:
    std::unique_ptr<CompactionFilter> CreateCompactionFilter(
@@ -5647,7 +5608,6 @@ TEST_F(DBTest, DISABLED_SuggestCompactRangeTest) {
  ASSERT_EQ(1, NumTableFilesAtLevel(1));
 }

-
 TEST_F(DBTest, PromoteL0) {
  Options options = CurrentOptions();
  options.disable_auto_compactions = true;
@@ -1288,10 +1288,6 @@ TEST_F(DBTest2, CompressionOptions) {
  const int kValSize = 20;
  Random rnd(301);

-  std::vector<uint32_t> compression_parallel_threads = {1, 4};
-
-  std::map<std::string, std::string> key_value_written;
-
  for (int iter = 0; iter <= 2; iter++) {
    listener->max_level_checked = 0;

@@ -1316,37 +1312,19 @@ TEST_F(DBTest2, CompressionOptions) {
      options.bottommost_compression = kDisableCompressionOption;
    }

-    for (auto num_threads : compression_parallel_threads) {
-      options.compression_opts.parallel_threads = num_threads;
-      options.bottommost_compression_opts.parallel_threads = num_threads;
-
-      DestroyAndReopen(options);
-      // Write 10 random files
-      for (int i = 0; i < 10; i++) {
-        for (int j = 0; j < 5; j++) {
-          std::string key = RandomString(&rnd, kKeySize);
-          std::string value = RandomString(&rnd, kValSize);
-          key_value_written[key] = value;
-          ASSERT_OK(Put(key, value));
-        }
-        ASSERT_OK(Flush());
-        dbfull()->TEST_WaitForCompact();
+    DestroyAndReopen(options);
+    // Write 10 random files
+    for (int i = 0; i < 10; i++) {
+      for (int j = 0; j < 5; j++) {
+        ASSERT_OK(
+            Put(RandomString(&rnd, kKeySize), RandomString(&rnd, kValSize)));
      }
-
-      // Make sure that we wrote enough to check all 7 levels
-      ASSERT_EQ(listener->max_level_checked, 6);
-
-      // Make sure database content is the same as key_value_written
-      std::unique_ptr<Iterator> db_iter(db_->NewIterator(ReadOptions()));
-      for (db_iter->SeekToFirst(); db_iter->Valid(); db_iter->Next()) {
-        std::string key = db_iter->key().ToString();
-        std::string value = db_iter->value().ToString();
-        ASSERT_NE(key_value_written.find(key), key_value_written.end());
-        ASSERT_EQ(key_value_written[key], value);
-        key_value_written.erase(key);
-      }
-      ASSERT_EQ(0, key_value_written.size());
+      ASSERT_OK(Flush());
+      dbfull()->TEST_WaitForCompact();
    }
+
+    // Make sure that we wrote enough to check all 7 levels
+    ASSERT_EQ(listener->max_level_checked, 6);
  }
 }

@@ -1700,12 +1678,12 @@ TEST_P(PinL0IndexAndFilterBlocksTest, DisablePrefetchingNonL0IndexAndFilter) {
    ASSERT_EQ(fm + 3, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
    ASSERT_EQ(fh, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
    ASSERT_EQ(im + 3, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
-    ASSERT_EQ(ih + 3, TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT));
+    ASSERT_EQ(ih + 2, TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT));
  } else {
    ASSERT_EQ(fm + 3, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
    ASSERT_EQ(fh + 1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
    ASSERT_EQ(im + 3, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
-    ASSERT_EQ(ih + 4, TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT));
+    ASSERT_EQ(ih + 3, TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT));
  }

  // Bloom and index hit will happen when a Get() happens.
@@ -1714,12 +1692,12 @@ TEST_P(PinL0IndexAndFilterBlocksTest, DisablePrefetchingNonL0IndexAndFilter) {
    ASSERT_EQ(fm + 3, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
    ASSERT_EQ(fh + 1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
    ASSERT_EQ(im + 3, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
-    ASSERT_EQ(ih + 4, TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT));
+    ASSERT_EQ(ih + 3, TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT));
  } else {
    ASSERT_EQ(fm + 3, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
    ASSERT_EQ(fh + 2, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
    ASSERT_EQ(im + 3, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
-    ASSERT_EQ(ih + 5, TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT));
+    ASSERT_EQ(ih + 4, TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT));
  }
 }

@@ -4328,24 +4306,6 @@ TEST_F(DBTest2, SameSmallestInSameLevel) {
  ASSERT_EQ("2,3,4,5,6,7,8", Get("key"));
 }

-TEST_F(DBTest2, FileConsistencyCheckInOpen) {
-  Put("foo", "bar");
-  Flush();
-
-  SyncPoint::GetInstance()->SetCallBack(
-      "VersionBuilder::CheckConsistencyBeforeReturn", [&](void* arg) {
-        Status* ret_s = static_cast<Status*>(arg);
-        *ret_s = Status::Corruption("fcc");
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  Options options = CurrentOptions();
-  options.force_consistency_checks = true;
-  ASSERT_NOK(TryReopen(options));
-
-  SyncPoint::GetInstance()->DisableProcessing();
-}
-
 TEST_F(DBTest2, BlockBasedTablePrefixIndexSeekForPrev) {
  // create a DB with block prefix index
  BlockBasedTableOptions table_options;
@@ -14,19 +14,10 @@

 namespace ROCKSDB_NAMESPACE {

-namespace {
-int64_t MaybeCurrentTime(Env* env) {
-  int64_t time = 1337346000;  // arbitrary fallback default
-  (void)env->GetCurrentTime(&time);
-  return time;
-}
-}  // namespace
-
 // Special Env used to delay background operations

 SpecialEnv::SpecialEnv(Env* base)
    : EnvWrapper(base),
-      maybe_starting_time_(MaybeCurrentTime(base)),
      rnd_(301),
      sleep_counter_(this),
      addon_time_(0),
@@ -408,7 +399,20 @@ Options DBTestBase::GetOptions(
        options.use_direct_reads = true;
        options.use_direct_io_for_flush_and_compaction = true;
        options.compaction_readahead_size = 2 * 1024 * 1024;
-        test::SetupSyncPointsToMockDirectIO();
+  #if !defined(OS_MACOSX) && !defined(OS_WIN) && !defined(OS_SOLARIS) && \
+      !defined(OS_AIX) && !defined(OS_OPENBSD)
+        ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+            "NewWritableFile:O_DIRECT", [&](void* arg) {
+              int* val = static_cast<int*>(arg);
+              *val &= ~O_DIRECT;
+            });
+        ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+            "NewRandomAccessFile:O_DIRECT", [&](void* arg) {
+              int* val = static_cast<int*>(arg);
+              *val &= ~O_DIRECT;
+            });
+        ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+#endif
        break;
      }
 #endif  // ROCKSDB_LITE
@@ -502,14 +502,10 @@ class SpecialEnv : public EnvWrapper {

  virtual Status GetCurrentTime(int64_t* unix_time) override {
    Status s;
-    if (time_elapse_only_sleep_) {
-      *unix_time = maybe_starting_time_;
-    } else {
+    if (!time_elapse_only_sleep_) {
      s = target()->GetCurrentTime(unix_time);
    }
    if (s.ok()) {
-      // FIXME: addon_time_ sometimes used to mean seconds (here) and
-      // sometimes microseconds
      *unix_time += addon_time_.load();
    }
    return s;
@@ -535,20 +531,6 @@ class SpecialEnv : public EnvWrapper {
    return target()->DeleteFile(fname);
  }

-  void SetTimeElapseOnlySleep(Options* options) {
-    time_elapse_only_sleep_ = true;
-    no_slowdown_ = true;
-    // Need to disable stats dumping and persisting which also use
-    // RepeatableThread, which uses InstrumentedCondVar::TimedWaitInternal.
-    // With time_elapse_only_sleep_, this can hang on some platforms.
-    // TODO: why? investigate/fix
-    options->stats_dump_period_sec = 0;
-    options->stats_persist_period_sec = 0;
-  }
-
-  // Something to return when mocking current time
-  const int64_t maybe_starting_time_;
-
  Random rnd_;
  port::Mutex rnd_mutex_;  // Lock to pretect rnd_

@@ -665,72 +647,6 @@ class TestPutOperator : public MergeOperator {
  virtual const char* Name() const override { return "TestPutOperator"; }
 };

-// A wrapper around Cache that can easily be extended with instrumentation,
-// etc.
-class CacheWrapper : public Cache {
- public:
-  explicit CacheWrapper(std::shared_ptr<Cache> target)
-      : target_(std::move(target)) {}
-
-  const char* Name() const override { return target_->Name(); }
-
-  Status Insert(const Slice& key, void* value, size_t charge,
-                void (*deleter)(const Slice& key, void* value),
-                Handle** handle = nullptr,
-                Priority priority = Priority::LOW) override {
-    return target_->Insert(key, value, charge, deleter, handle, priority);
-  }
-
-  Handle* Lookup(const Slice& key, Statistics* stats = nullptr) override {
-    return target_->Lookup(key, stats);
-  }
-
-  bool Ref(Handle* handle) override { return target_->Ref(handle); }
-
-  bool Release(Handle* handle, bool force_erase = false) override {
-    return target_->Release(handle, force_erase);
-  }
-
-  void* Value(Handle* handle) override { return target_->Value(handle); }
-
-  void Erase(const Slice& key) override { target_->Erase(key); }
-  uint64_t NewId() override { return target_->NewId(); }
-
-  void SetCapacity(size_t capacity) override { target_->SetCapacity(capacity); }
-
-  void SetStrictCapacityLimit(bool strict_capacity_limit) override {
-    target_->SetStrictCapacityLimit(strict_capacity_limit);
-  }
-
-  bool HasStrictCapacityLimit() const override {
-    return target_->HasStrictCapacityLimit();
-  }
-
-  size_t GetCapacity() const override { return target_->GetCapacity(); }
-
-  size_t GetUsage() const override { return target_->GetUsage(); }
-
-  size_t GetUsage(Handle* handle) const override {
-    return target_->GetUsage(handle);
-  }
-
-  size_t GetPinnedUsage() const override { return target_->GetPinnedUsage(); }
-
-  size_t GetCharge(Handle* handle) const override {
-    return target_->GetCharge(handle);
-  }
-
-  void ApplyToAllCacheEntries(void (*callback)(void*, size_t),
-                              bool thread_safe) override {
-    target_->ApplyToAllCacheEntries(callback, thread_safe);
-  }
-
-  void EraseUnRefEntries() override { target_->EraseUnRefEntries(); }
-
- protected:
-  std::shared_ptr<Cache> target_;
-};
-
 class DBTestBase : public testing::Test {
 public:
  // Sequence of option configurations to try
@@ -1422,11 +1422,8 @@ TEST_F(DBWALTest, RecoverFromCorruptedWALWithoutFlush) {
    delete iter;
    return data;
  };
-  for (auto& mode : {WALRecoveryMode::kTolerateCorruptedTailRecords,
-                     WALRecoveryMode::kAbsoluteConsistency,
-                     WALRecoveryMode::kPointInTimeRecovery,
-                     WALRecoveryMode::kSkipAnyCorruptedRecords}) {
-    options.wal_recovery_mode = mode;
+  for (auto& mode : wal_recovery_mode_string_map) {
+    options.wal_recovery_mode = mode.second;
    for (auto trunc : {true, false}) {
      for (int i = 0; i < 4; i++) {
        for (int j = jstart; j < jend; j++) {
@@ -1531,24 +1528,6 @@ TEST_F(DBWALTest, TruncateLastLogAfterRecoverWithoutFlush) {
  constexpr size_t kKB = 1024;
  Options options = CurrentOptions();
  options.avoid_flush_during_recovery = true;
-  // Test fallocate support of running file system.
-  // Skip this test if fallocate is not supported.
-  std::string fname_test_fallocate = dbname_ + "/preallocate_testfile";
-  int fd = -1;
-  do {
-    fd = open(fname_test_fallocate.c_str(), O_CREAT | O_RDWR | O_TRUNC, 0644);
-  } while (fd < 0 && errno == EINTR);
-  ASSERT_GT(fd, 0);
-  int alloc_status = fallocate(fd, 0, 0, 1);
-  int err_number = errno;
-  close(fd);
-  ASSERT_OK(options.env->DeleteFile(fname_test_fallocate));
-  if (err_number == ENOSYS || err_number == EOPNOTSUPP) {
-    fprintf(stderr, "Skipped preallocated space check: %s\n", strerror(err_number));
-    return;
-  }
-  ASSERT_EQ(0, alloc_status);
-
  DestroyAndReopen(options);
  size_t preallocated_size =
      dbfull()->TEST_GetWalPreallocateBlockSize(options.write_buffer_size);
@@ -1,980 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-#include "rocksdb/perf_context.h"
-#include "rocksdb/utilities/debug.h"
-#include "table/block_based/block_based_table_reader.h"
-#include "table/block_based/block_builder.h"
-#include "test_util/fault_injection_test_env.h"
-#if !defined(ROCKSDB_LITE)
-#include "test_util/sync_point.h"
-#endif
-
-namespace ROCKSDB_NAMESPACE {
-class DBBasicTestWithTimestampBase : public DBTestBase {
- public:
-  explicit DBBasicTestWithTimestampBase(const std::string& dbname)
-      : DBTestBase(dbname) {}
-
- protected:
-  static std::string Key1(uint64_t k) {
-    std::string ret;
-    PutFixed64(&ret, k);
-    std::reverse(ret.begin(), ret.end());
-    return ret;
-  }
-
-  class TestComparator : public Comparator {
-   private:
-    const Comparator* cmp_without_ts_;
-
-   public:
-    explicit TestComparator(size_t ts_sz)
-        : Comparator(ts_sz), cmp_without_ts_(nullptr) {
-      cmp_without_ts_ = BytewiseComparator();
-    }
-
-    const char* Name() const override { return "TestComparator"; }
-
-    void FindShortSuccessor(std::string*) const override {}
-
-    void FindShortestSeparator(std::string*, const Slice&) const override {}
-
-    int Compare(const Slice& a, const Slice& b) const override {
-      int r = CompareWithoutTimestamp(a, b);
-      if (r != 0 || 0 == timestamp_size()) {
-        return r;
-      }
-      return -CompareTimestamp(
-          Slice(a.data() + a.size() - timestamp_size(), timestamp_size()),
-          Slice(b.data() + b.size() - timestamp_size(), timestamp_size()));
-    }
-
-    using Comparator::CompareWithoutTimestamp;
-    int CompareWithoutTimestamp(const Slice& a, bool a_has_ts, const Slice& b,
-                                bool b_has_ts) const override {
-      if (a_has_ts) {
-        assert(a.size() >= timestamp_size());
-      }
-      if (b_has_ts) {
-        assert(b.size() >= timestamp_size());
-      }
-      Slice lhs = a_has_ts ? StripTimestampFromUserKey(a, timestamp_size()) : a;
-      Slice rhs = b_has_ts ? StripTimestampFromUserKey(b, timestamp_size()) : b;
-      return cmp_without_ts_->Compare(lhs, rhs);
-    }
-
-    int CompareTimestamp(const Slice& ts1, const Slice& ts2) const override {
-      if (!ts1.data() && !ts2.data()) {
-        return 0;
-      } else if (ts1.data() && !ts2.data()) {
-        return 1;
-      } else if (!ts1.data() && ts2.data()) {
-        return -1;
-      }
-      assert(ts1.size() == ts2.size());
-      uint64_t low1 = 0;
-      uint64_t low2 = 0;
-      uint64_t high1 = 0;
-      uint64_t high2 = 0;
-      const size_t kSize = ts1.size();
-      std::unique_ptr<char[]> ts1_buf(new char[kSize]);
-      memcpy(ts1_buf.get(), ts1.data(), ts1.size());
-      std::unique_ptr<char[]> ts2_buf(new char[kSize]);
-      memcpy(ts2_buf.get(), ts2.data(), ts2.size());
-      Slice ts1_copy = Slice(ts1_buf.get(), kSize);
-      Slice ts2_copy = Slice(ts2_buf.get(), kSize);
-      auto* ptr1 = const_cast<Slice*>(&ts1_copy);
-      auto* ptr2 = const_cast<Slice*>(&ts2_copy);
-      if (!GetFixed64(ptr1, &low1) || !GetFixed64(ptr1, &high1) ||
-          !GetFixed64(ptr2, &low2) || !GetFixed64(ptr2, &high2)) {
-        assert(false);
-      }
-      if (high1 < high2) {
-        return -1;
-      } else if (high1 > high2) {
-        return 1;
-      }
-      if (low1 < low2) {
-        return -1;
-      } else if (low1 > low2) {
-        return 1;
-      }
-      return 0;
-    }
-  };
-
-  std::string Timestamp(uint64_t low, uint64_t high) {
-    std::string ts;
-    PutFixed64(&ts, low);
-    PutFixed64(&ts, high);
-    return ts;
-  }
-
-  void CheckIterUserEntry(const Iterator* it, const Slice& expected_key,
-                          const Slice& expected_value,
-                          const Slice& expected_ts) const {
-    ASSERT_TRUE(it->Valid());
-    ASSERT_OK(it->status());
-    ASSERT_EQ(expected_key, it->key());
-    ASSERT_EQ(expected_value, it->value());
-    ASSERT_EQ(expected_ts, it->timestamp());
-  }
-
-  void CheckIterEntry(const Iterator* it, const Slice& expected_ukey,
-                      SequenceNumber expected_seq, ValueType expected_val_type,
-                      const Slice& expected_value, const Slice& expected_ts) {
-    ASSERT_TRUE(it->Valid());
-    ASSERT_OK(it->status());
-    std::string ukey_and_ts;
-    ukey_and_ts.assign(expected_ukey.data(), expected_ukey.size());
-    ukey_and_ts.append(expected_ts.data(), expected_ts.size());
-    ParsedInternalKey parsed_ikey(ukey_and_ts, expected_seq, expected_val_type);
-    std::string ikey;
-    AppendInternalKey(&ikey, parsed_ikey);
-    ASSERT_EQ(Slice(ikey), it->key());
-    if (expected_val_type == kTypeValue) {
-      ASSERT_EQ(expected_value, it->value());
-    }
-    ASSERT_EQ(expected_ts, it->timestamp());
-  }
-};
-
-class DBBasicTestWithTimestamp : public DBBasicTestWithTimestampBase {
- public:
-  DBBasicTestWithTimestamp()
-      : DBBasicTestWithTimestampBase("db_basic_test_with_timestamp") {}
-};
-
-TEST_F(DBBasicTestWithTimestamp, SimpleForwardIterate) {
-  const int kNumKeysPerFile = 128;
-  const uint64_t kMaxKey = 1024;
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  const size_t kTimestampSize = Timestamp(0, 0).size();
-  TestComparator test_cmp(kTimestampSize);
-  options.comparator = &test_cmp;
-  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
-  DestroyAndReopen(options);
-  const std::vector<uint64_t> start_keys = {1, 0};
-  const std::vector<std::string> write_timestamps = {Timestamp(1, 0),
-                                                     Timestamp(3, 0)};
-  const std::vector<std::string> read_timestamps = {Timestamp(2, 0),
-                                                    Timestamp(4, 0)};
-  for (size_t i = 0; i < write_timestamps.size(); ++i) {
-    WriteOptions write_opts;
-    Slice write_ts = write_timestamps[i];
-    write_opts.timestamp = &write_ts;
-    for (uint64_t key = start_keys[i]; key <= kMaxKey; ++key) {
-      Status s = db_->Put(write_opts, Key1(key), "value" + std::to_string(i));
-      ASSERT_OK(s);
-    }
-  }
-  for (size_t i = 0; i < read_timestamps.size(); ++i) {
-    ReadOptions read_opts;
-    Slice read_ts = read_timestamps[i];
-    read_opts.timestamp = &read_ts;
-    std::unique_ptr<Iterator> it(db_->NewIterator(read_opts));
-    int count = 0;
-    uint64_t key = 0;
-    for (it->Seek(Key1(0)), key = start_keys[i]; it->Valid();
-         it->Next(), ++count, ++key) {
-      CheckIterUserEntry(it.get(), Key1(key), "value" + std::to_string(i),
-                         write_timestamps[i]);
-    }
-    size_t expected_count = kMaxKey - start_keys[i] + 1;
-    ASSERT_EQ(expected_count, count);
-
-    // SeekToFirst() with lower bound.
-    // Then iter with lower and upper bounds.
-    uint64_t l = 0;
-    uint64_t r = kMaxKey + 1;
-    while (l < r) {
-      std::string lb_str = Key1(l);
-      Slice lb = lb_str;
-      std::string ub_str = Key1(r);
-      Slice ub = ub_str;
-      read_opts.iterate_lower_bound = &lb;
-      read_opts.iterate_upper_bound = &ub;
-      it.reset(db_->NewIterator(read_opts));
-      for (it->SeekToFirst(), key = std::max(l, start_keys[i]), count = 0;
-           it->Valid(); it->Next(), ++key, ++count) {
-        CheckIterUserEntry(it.get(), Key1(key), "value" + std::to_string(i),
-                           write_timestamps[i]);
-      }
-      ASSERT_EQ(r - std::max(l, start_keys[i]), count);
-      l += (kMaxKey / 100);
-      r -= (kMaxKey / 100);
-    }
-  }
-  Close();
-}
-
-TEST_F(DBBasicTestWithTimestamp, SimpleForwardIterateLowerTsBound) {
-  const int kNumKeysPerFile = 128;
-  const uint64_t kMaxKey = 1024;
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  const size_t kTimestampSize = Timestamp(0, 0).size();
-  TestComparator test_cmp(kTimestampSize);
-  options.comparator = &test_cmp;
-  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
-  DestroyAndReopen(options);
-  const std::vector<std::string> write_timestamps = {Timestamp(1, 0),
-                                                     Timestamp(3, 0)};
-  const std::vector<std::string> read_timestamps = {Timestamp(2, 0),
-                                                    Timestamp(4, 0)};
-  const std::vector<std::string> read_timestamps_lb = {Timestamp(1, 0),
-                                                       Timestamp(1, 0)};
-  for (size_t i = 0; i < write_timestamps.size(); ++i) {
-    WriteOptions write_opts;
-    Slice write_ts = write_timestamps[i];
-    write_opts.timestamp = &write_ts;
-    for (uint64_t key = 0; key <= kMaxKey; ++key) {
-      Status s = db_->Put(write_opts, Key1(key), "value" + std::to_string(i));
-      ASSERT_OK(s);
-    }
-  }
-  for (size_t i = 0; i < read_timestamps.size(); ++i) {
-    ReadOptions read_opts;
-    Slice read_ts = read_timestamps[i];
-    Slice read_ts_lb = read_timestamps_lb[i];
-    read_opts.timestamp = &read_ts;
-    read_opts.iter_start_ts = &read_ts_lb;
-    std::unique_ptr<Iterator> it(db_->NewIterator(read_opts));
-    int count = 0;
-    uint64_t key = 0;
-    for (it->Seek(Key1(0)), key = 0; it->Valid(); it->Next(), ++count, ++key) {
-      CheckIterUserEntry(it.get(), Key1(key), "value" + std::to_string(i),
-                         write_timestamps[i]);
-      if (i > 0) {
-        it->Next();
-        CheckIterUserEntry(it.get(), Key1(key), "value" + std::to_string(i - 1),
-                           write_timestamps[i - 1]);
-      }
-    }
-    size_t expected_count = kMaxKey + 1;
-    ASSERT_EQ(expected_count, count);
-  }
-  Close();
-}
-
-TEST_F(DBBasicTestWithTimestamp, ForwardIterateStartSeqnum) {
-  const int kNumKeysPerFile = 128;
-  const uint64_t kMaxKey = 0xffffffffffffffff;
-  const uint64_t kMinKey = kMaxKey - 1023;
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  // Need to disable compaction to bottommost level when sequence number will be
-  // zeroed out, causing the verification of sequence number to fail in this
-  // test.
-  options.disable_auto_compactions = true;
-  const size_t kTimestampSize = Timestamp(0, 0).size();
-  TestComparator test_cmp(kTimestampSize);
-  options.comparator = &test_cmp;
-  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
-  DestroyAndReopen(options);
-  std::vector<SequenceNumber> start_seqs;
-
-  const int kNumTimestamps = 4;
-  std::vector<std::string> write_ts_list;
-  for (int t = 0; t != kNumTimestamps; ++t) {
-    write_ts_list.push_back(Timestamp(2 * t, /*do not care*/ 17));
-  }
-  WriteOptions write_opts;
-  for (size_t i = 0; i != write_ts_list.size(); ++i) {
-    Slice write_ts = write_ts_list[i];
-    write_opts.timestamp = &write_ts;
-    uint64_t k = kMinKey;
-    do {
-      Status s = db_->Put(write_opts, Key1(k), "value" + std::to_string(i));
-      ASSERT_OK(s);
-      if (k == kMaxKey) {
-        break;
-      }
-      ++k;
-    } while (k != 0);
-    start_seqs.push_back(db_->GetLatestSequenceNumber());
-  }
-  std::vector<std::string> read_ts_list;
-  for (int t = 0; t != kNumTimestamps - 1; ++t) {
-    read_ts_list.push_back(Timestamp(2 * t + 3, /*do not care*/ 17));
-  }
-  ReadOptions read_opts;
-  for (size_t i = 0; i != read_ts_list.size(); ++i) {
-    Slice read_ts = read_ts_list[i];
-    read_opts.timestamp = &read_ts;
-    read_opts.iter_start_seqnum = start_seqs[i];
-    std::unique_ptr<Iterator> iter(db_->NewIterator(read_opts));
-    SequenceNumber expected_seq = start_seqs[i] + 1;
-    uint64_t key = kMinKey;
-    for (iter->Seek(Key1(kMinKey)); iter->Valid(); iter->Next()) {
-      CheckIterEntry(iter.get(), Key1(key), expected_seq, kTypeValue,
-                     "value" + std::to_string(i + 1), write_ts_list[i + 1]);
-      ++key;
-      ++expected_seq;
-    }
-  }
-  Close();
-}
-
-TEST_F(DBBasicTestWithTimestamp, ReseekToTargetTimestamp) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  constexpr size_t kNumKeys = 16;
-  options.max_sequential_skip_in_iterations = kNumKeys / 2;
-  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-  const size_t kTimestampSize = Timestamp(0, 0).size();
-  TestComparator test_cmp(kTimestampSize);
-  options.comparator = &test_cmp;
-  DestroyAndReopen(options);
-  // Insert kNumKeys
-  WriteOptions write_opts;
-  Status s;
-  for (size_t i = 0; i != kNumKeys; ++i) {
-    std::string ts_str = Timestamp(static_cast<uint64_t>(i + 1), 0);
-    Slice ts = ts_str;
-    write_opts.timestamp = &ts;
-    s = db_->Put(write_opts, "foo", "value" + std::to_string(i));
-    ASSERT_OK(s);
-  }
-  {
-    ReadOptions read_opts;
-    std::string ts_str = Timestamp(1, 0);
-    Slice ts = ts_str;
-    read_opts.timestamp = &ts;
-    std::unique_ptr<Iterator> iter(db_->NewIterator(read_opts));
-    iter->SeekToFirst();
-    CheckIterUserEntry(iter.get(), "foo", "value0", ts_str);
-    ASSERT_EQ(
-        1, options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION));
-  }
-  Close();
-}
-
-TEST_F(DBBasicTestWithTimestamp, ReseekToNextUserKey) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  constexpr size_t kNumKeys = 16;
-  options.max_sequential_skip_in_iterations = kNumKeys / 2;
-  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-  const size_t kTimestampSize = Timestamp(0, 0).size();
-  TestComparator test_cmp(kTimestampSize);
-  options.comparator = &test_cmp;
-  DestroyAndReopen(options);
-  // Write kNumKeys + 1 keys
-  WriteOptions write_opts;
-  Status s;
-  for (size_t i = 0; i != kNumKeys; ++i) {
-    std::string ts_str = Timestamp(static_cast<uint64_t>(i + 1), 0);
-    Slice ts = ts_str;
-    write_opts.timestamp = &ts;
-    s = db_->Put(write_opts, "a", "value" + std::to_string(i));
-    ASSERT_OK(s);
-  }
-  {
-    std::string ts_str = Timestamp(static_cast<uint64_t>(kNumKeys + 1), 0);
-    WriteBatch batch(0, 0, kTimestampSize);
-    batch.Put("a", "new_value");
-    batch.Put("b", "new_value");
-    s = batch.AssignTimestamp(ts_str);
-    ASSERT_OK(s);
-    s = db_->Write(write_opts, &batch);
-    ASSERT_OK(s);
-  }
-  {
-    ReadOptions read_opts;
-    std::string ts_str = Timestamp(static_cast<uint64_t>(kNumKeys + 1), 0);
-    Slice ts = ts_str;
-    read_opts.timestamp = &ts;
-    std::unique_ptr<Iterator> iter(db_->NewIterator(read_opts));
-    iter->Seek("a");
-    iter->Next();
-    CheckIterUserEntry(iter.get(), "b", "new_value", ts_str);
-    ASSERT_EQ(
-        1, options.statistics->getTickerCount(NUMBER_OF_RESEEKS_IN_ITERATION));
-  }
-  Close();
-}
-
-TEST_F(DBBasicTestWithTimestamp, MaxKeysSkipped) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  const size_t kTimestampSize = Timestamp(0, 0).size();
-  TestComparator test_cmp(kTimestampSize);
-  options.comparator = &test_cmp;
-  DestroyAndReopen(options);
-  constexpr size_t max_skippable_internal_keys = 2;
-  const size_t kNumKeys = max_skippable_internal_keys + 2;
-  WriteOptions write_opts;
-  Status s;
-  {
-    std::string ts_str = Timestamp(1, 0);
-    Slice ts = ts_str;
-    write_opts.timestamp = &ts;
-    ASSERT_OK(db_->Put(write_opts, "a", "value"));
-  }
-  for (size_t i = 0; i < kNumKeys; ++i) {
-    std::string ts_str = Timestamp(static_cast<uint64_t>(i + 1), 0);
-    Slice ts = ts_str;
-    write_opts.timestamp = &ts;
-    s = db_->Put(write_opts, "b", "value" + std::to_string(i));
-    ASSERT_OK(s);
-  }
-  {
-    ReadOptions read_opts;
-    read_opts.max_skippable_internal_keys = max_skippable_internal_keys;
-    std::string ts_str = Timestamp(1, 0);
-    Slice ts = ts_str;
-    read_opts.timestamp = &ts;
-    std::unique_ptr<Iterator> iter(db_->NewIterator(read_opts));
-    iter->SeekToFirst();
-    iter->Next();
-    ASSERT_TRUE(iter->status().IsIncomplete());
-  }
-  Close();
-}
-
-class DBBasicTestWithTimestampCompressionSettings
-    : public DBBasicTestWithTimestampBase,
-      public testing::WithParamInterface<
-          std::tuple<std::shared_ptr<const FilterPolicy>, CompressionType,
-                     uint32_t, uint32_t>> {
- public:
-  DBBasicTestWithTimestampCompressionSettings()
-      : DBBasicTestWithTimestampBase(
-            "db_basic_test_with_timestamp_compression") {}
-};
-
-TEST_P(DBBasicTestWithTimestampCompressionSettings, PutAndGet) {
-  const int kNumKeysPerFile = 1024;
-  const size_t kNumTimestamps = 4;
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.env = env_;
-  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
-  size_t ts_sz = Timestamp(0, 0).size();
-  TestComparator test_cmp(ts_sz);
-  options.comparator = &test_cmp;
-  BlockBasedTableOptions bbto;
-  bbto.filter_policy = std::get<0>(GetParam());
-  bbto.whole_key_filtering = true;
-  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-
-  const CompressionType comp_type = std::get<1>(GetParam());
-#if LZ4_VERSION_NUMBER < 10400  // r124+
-  if (comp_type == kLZ4Compression || comp_type == kLZ4HCCompression) {
-    return;
-  }
-#endif  // LZ4_VERSION_NUMBER >= 10400
-  if (!ZSTD_Supported() && comp_type == kZSTD) {
-    return;
-  }
-  if (!Zlib_Supported() && comp_type == kZlibCompression) {
-    return;
-  }
-
-  options.compression = comp_type;
-  options.compression_opts.max_dict_bytes = std::get<2>(GetParam());
-  if (comp_type == kZSTD) {
-    options.compression_opts.zstd_max_train_bytes = std::get<2>(GetParam());
-  }
-  options.compression_opts.parallel_threads = std::get<3>(GetParam());
-  options.target_file_size_base = 1 << 26;  // 64MB
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  size_t num_cfs = handles_.size();
-  ASSERT_EQ(2, num_cfs);
-  std::vector<std::string> write_ts_list;
-  std::vector<std::string> read_ts_list;
-
-  for (size_t i = 0; i != kNumTimestamps; ++i) {
-    write_ts_list.push_back(Timestamp(i * 2, 0));
-    read_ts_list.push_back(Timestamp(1 + i * 2, 0));
-    const Slice write_ts = write_ts_list.back();
-    WriteOptions wopts;
-    wopts.timestamp = &write_ts;
-    for (int cf = 0; cf != static_cast<int>(num_cfs); ++cf) {
-      for (size_t j = 0; j != (kNumKeysPerFile - 1) / kNumTimestamps; ++j) {
-        ASSERT_OK(Put(cf, Key1(j),
-                      "value_" + std::to_string(j) + "_" + std::to_string(i),
-                      wopts));
-      }
-    }
-  }
-  const auto& verify_db_func = [&]() {
-    for (size_t i = 0; i != kNumTimestamps; ++i) {
-      ReadOptions ropts;
-      const Slice read_ts = read_ts_list[i];
-      ropts.timestamp = &read_ts;
-      for (int cf = 0; cf != static_cast<int>(num_cfs); ++cf) {
-        ColumnFamilyHandle* cfh = handles_[cf];
-        for (size_t j = 0; j != (kNumKeysPerFile - 1) / kNumTimestamps; ++j) {
-          std::string value;
-          ASSERT_OK(db_->Get(ropts, cfh, Key1(j), &value));
-          ASSERT_EQ("value_" + std::to_string(j) + "_" + std::to_string(i),
-                    value);
-        }
-      }
-    }
-  };
-  verify_db_func();
-  Close();
-}
-
-#ifndef ROCKSDB_LITE
-// A class which remembers the name of each flushed file.
-class FlushedFileCollector : public EventListener {
- public:
-  FlushedFileCollector() {}
-  ~FlushedFileCollector() override {}
-
-  void OnFlushCompleted(DB* /*db*/, const FlushJobInfo& info) override {
-    InstrumentedMutexLock lock(&mutex_);
-    flushed_files_.push_back(info.file_path);
-  }
-
-  std::vector<std::string> GetFlushedFiles() {
-    std::vector<std::string> result;
-    {
-      InstrumentedMutexLock lock(&mutex_);
-      result = flushed_files_;
-    }
-    return result;
-  }
-
-  void ClearFlushedFiles() {
-    InstrumentedMutexLock lock(&mutex_);
-    flushed_files_.clear();
-  }
-
- private:
-  std::vector<std::string> flushed_files_;
-  InstrumentedMutex mutex_;
-};
-
-TEST_P(DBBasicTestWithTimestampCompressionSettings, PutAndGetWithCompaction) {
-  const int kNumKeysPerFile = 1024;
-  const size_t kNumTimestamps = 2;
-  const size_t kNumKeysPerTimestamp = (kNumKeysPerFile - 1) / kNumTimestamps;
-  const size_t kSplitPosBase = kNumKeysPerTimestamp / 2;
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.env = env_;
-  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
-
-  FlushedFileCollector* collector = new FlushedFileCollector();
-  options.listeners.emplace_back(collector);
-
-  size_t ts_sz = Timestamp(0, 0).size();
-  TestComparator test_cmp(ts_sz);
-  options.comparator = &test_cmp;
-  BlockBasedTableOptions bbto;
-  bbto.filter_policy = std::get<0>(GetParam());
-  bbto.whole_key_filtering = true;
-  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-
-  const CompressionType comp_type = std::get<1>(GetParam());
-#if LZ4_VERSION_NUMBER < 10400  // r124+
-  if (comp_type == kLZ4Compression || comp_type == kLZ4HCCompression) {
-    return;
-  }
-#endif  // LZ4_VERSION_NUMBER >= 10400
-  if (!ZSTD_Supported() && comp_type == kZSTD) {
-    return;
-  }
-  if (!Zlib_Supported() && comp_type == kZlibCompression) {
-    return;
-  }
-
-  options.compression = comp_type;
-  options.compression_opts.max_dict_bytes = std::get<2>(GetParam());
-  if (comp_type == kZSTD) {
-    options.compression_opts.zstd_max_train_bytes = std::get<2>(GetParam());
-  }
-  options.compression_opts.parallel_threads = std::get<3>(GetParam());
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  size_t num_cfs = handles_.size();
-  ASSERT_EQ(2, num_cfs);
-  std::vector<std::string> write_ts_list;
-  std::vector<std::string> read_ts_list;
-
-  const auto& verify_records_func = [&](size_t i, size_t begin, size_t end,
-                                        ColumnFamilyHandle* cfh) {
-    std::string value;
-    std::string timestamp;
-
-    ReadOptions ropts;
-    const Slice read_ts = read_ts_list[i];
-    ropts.timestamp = &read_ts;
-    std::string expected_timestamp =
-        std::string(write_ts_list[i].data(), write_ts_list[i].size());
-
-    for (size_t j = begin; j <= end; ++j) {
-      ASSERT_OK(db_->Get(ropts, cfh, Key1(j), &value, &timestamp));
-      ASSERT_EQ("value_" + std::to_string(j) + "_" + std::to_string(i), value);
-      ASSERT_EQ(expected_timestamp, timestamp);
-    }
-  };
-
-  for (size_t i = 0; i != kNumTimestamps; ++i) {
-    write_ts_list.push_back(Timestamp(i * 2, 0));
-    read_ts_list.push_back(Timestamp(1 + i * 2, 0));
-    const Slice write_ts = write_ts_list.back();
-    WriteOptions wopts;
-    wopts.timestamp = &write_ts;
-    for (int cf = 0; cf != static_cast<int>(num_cfs); ++cf) {
-      size_t memtable_get_start = 0;
-      for (size_t j = 0; j != kNumKeysPerTimestamp; ++j) {
-        ASSERT_OK(Put(cf, Key1(j),
-                      "value_" + std::to_string(j) + "_" + std::to_string(i),
-                      wopts));
-        if (j == kSplitPosBase + i || j == kNumKeysPerTimestamp - 1) {
-          verify_records_func(i, memtable_get_start, j, handles_[cf]);
-          memtable_get_start = j + 1;
-
-          // flush all keys with the same timestamp to two sst files, split at
-          // incremental positions such that lowerlevel[1].smallest.userkey ==
-          // higherlevel[0].largest.userkey
-          ASSERT_OK(Flush(cf));
-
-          // compact files (2 at each level) to a lower level such that all
-          // keys with the same timestamp is at one level, with newer versions
-          // at higher levels.
-          CompactionOptions compact_opt;
-          compact_opt.compression = kNoCompression;
-          db_->CompactFiles(compact_opt, handles_[cf],
-                            collector->GetFlushedFiles(),
-                            static_cast<int>(kNumTimestamps - i));
-          collector->ClearFlushedFiles();
-        }
-      }
-    }
-  }
-  const auto& verify_db_func = [&]() {
-    for (size_t i = 0; i != kNumTimestamps; ++i) {
-      ReadOptions ropts;
-      const Slice read_ts = read_ts_list[i];
-      ropts.timestamp = &read_ts;
-      std::string expected_timestamp(write_ts_list[i].data(),
-                                     write_ts_list[i].size());
-      for (int cf = 0; cf != static_cast<int>(num_cfs); ++cf) {
-        ColumnFamilyHandle* cfh = handles_[cf];
-        verify_records_func(i, 0, kNumKeysPerTimestamp - 1, cfh);
-      }
-    }
-  };
-  verify_db_func();
-  Close();
-}
-
-TEST_F(DBBasicTestWithTimestamp, BatchWriteAndMultiGet) {
-  const int kNumKeysPerFile = 8192;
-  const size_t kNumTimestamps = 2;
-  const size_t kNumKeysPerTimestamp = (kNumKeysPerFile - 1) / kNumTimestamps;
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.env = env_;
-  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
-
-  size_t ts_sz = Timestamp(0, 0).size();
-  TestComparator test_cmp(ts_sz);
-  options.comparator = &test_cmp;
-  BlockBasedTableOptions bbto;
-  bbto.filter_policy.reset(NewBloomFilterPolicy(
-      10 /*bits_per_key*/, false /*use_block_based_builder*/));
-  bbto.whole_key_filtering = true;
-  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  size_t num_cfs = handles_.size();
-  ASSERT_EQ(2, num_cfs);
-  std::vector<std::string> write_ts_list;
-  std::vector<std::string> read_ts_list;
-
-  const auto& verify_records_func = [&](size_t i, ColumnFamilyHandle* cfh) {
-    std::vector<Slice> keys;
-    std::vector<std::string> key_vals;
-    std::vector<std::string> values;
-    std::vector<std::string> timestamps;
-
-    for (size_t j = 0; j != kNumKeysPerTimestamp; ++j) {
-      key_vals.push_back(Key1(j));
-    }
-    for (size_t j = 0; j != kNumKeysPerTimestamp; ++j) {
-      keys.push_back(key_vals[j]);
-    }
-
-    ReadOptions ropts;
-    const Slice read_ts = read_ts_list[i];
-    ropts.timestamp = &read_ts;
-    std::string expected_timestamp(write_ts_list[i].data(),
-                                   write_ts_list[i].size());
-
-    std::vector<ColumnFamilyHandle*> cfhs(keys.size(), cfh);
-    std::vector<Status> statuses =
-        db_->MultiGet(ropts, cfhs, keys, &values, &timestamps);
-    for (size_t j = 0; j != kNumKeysPerTimestamp; ++j) {
-      ASSERT_OK(statuses[j]);
-      ASSERT_EQ("value_" + std::to_string(j) + "_" + std::to_string(i),
-                values[j]);
-      ASSERT_EQ(expected_timestamp, timestamps[j]);
-    }
-  };
-
-  for (size_t i = 0; i != kNumTimestamps; ++i) {
-    write_ts_list.push_back(Timestamp(i * 2, 0));
-    read_ts_list.push_back(Timestamp(1 + i * 2, 0));
-    const Slice& write_ts = write_ts_list.back();
-    for (int cf = 0; cf != static_cast<int>(num_cfs); ++cf) {
-      WriteOptions wopts;
-      WriteBatch batch(0, 0, ts_sz);
-      for (size_t j = 0; j != kNumKeysPerTimestamp; ++j) {
-        ASSERT_OK(
-            batch.Put(handles_[cf], Key1(j),
-                      "value_" + std::to_string(j) + "_" + std::to_string(i)));
-      }
-      batch.AssignTimestamp(write_ts);
-      ASSERT_OK(db_->Write(wopts, &batch));
-
-      verify_records_func(i, handles_[cf]);
-
-      ASSERT_OK(Flush(cf));
-    }
-  }
-
-  const auto& verify_db_func = [&]() {
-    for (size_t i = 0; i != kNumTimestamps; ++i) {
-      ReadOptions ropts;
-      const Slice read_ts = read_ts_list[i];
-      ropts.timestamp = &read_ts;
-      for (int cf = 0; cf != static_cast<int>(num_cfs); ++cf) {
-        ColumnFamilyHandle* cfh = handles_[cf];
-        verify_records_func(i, cfh);
-      }
-    }
-  };
-  verify_db_func();
-  Close();
-}
-
-TEST_F(DBBasicTestWithTimestamp, MultiGetNoReturnTs) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  const size_t kTimestampSize = Timestamp(0, 0).size();
-  TestComparator test_cmp(kTimestampSize);
-  options.comparator = &test_cmp;
-  DestroyAndReopen(options);
-  WriteOptions write_opts;
-  std::string ts_str = Timestamp(1, 0);
-  Slice ts = ts_str;
-  write_opts.timestamp = &ts;
-  ASSERT_OK(db_->Put(write_opts, "foo", "value"));
-  ASSERT_OK(db_->Put(write_opts, "bar", "value"));
-  ASSERT_OK(db_->Put(write_opts, "fooxxxxxxxxxxxxxxxx", "value"));
-  ASSERT_OK(db_->Put(write_opts, "barxxxxxxxxxxxxxxxx", "value"));
-  ColumnFamilyHandle* cfh = dbfull()->DefaultColumnFamily();
-  ts_str = Timestamp(2, 0);
-  ts = ts_str;
-  ReadOptions read_opts;
-  read_opts.timestamp = &ts;
-  {
-    ColumnFamilyHandle* column_families[] = {cfh, cfh};
-    Slice keys[] = {"foo", "bar"};
-    PinnableSlice values[] = {PinnableSlice(), PinnableSlice()};
-    Status statuses[] = {Status::OK(), Status::OK()};
-    dbfull()->MultiGet(read_opts, /*num_keys=*/2, &column_families[0], &keys[0],
-                       &values[0], &statuses[0], /*sorted_input=*/false);
-    for (const auto& s : statuses) {
-      ASSERT_OK(s);
-    }
-  }
-  {
-    ColumnFamilyHandle* column_families[] = {cfh, cfh, cfh, cfh};
-    // Make user keys longer than configured timestamp size (16 bytes) to
-    // verify RocksDB does not use the trailing bytes 'x' as timestamp.
-    Slice keys[] = {"fooxxxxxxxxxxxxxxxx", "barxxxxxxxxxxxxxxxx", "foo", "bar"};
-    PinnableSlice values[] = {PinnableSlice(), PinnableSlice(), PinnableSlice(),
-                              PinnableSlice()};
-    Status statuses[] = {Status::OK(), Status::OK(), Status::OK(),
-                         Status::OK()};
-    dbfull()->MultiGet(read_opts, /*num_keys=*/4, &column_families[0], &keys[0],
-                       &values[0], &statuses[0], /*sorted_input=*/false);
-    for (const auto& s : statuses) {
-      ASSERT_OK(s);
-    }
-  }
-  Close();
-}
-
-#endif  // !ROCKSDB_LITE
-
-INSTANTIATE_TEST_CASE_P(
-    Timestamp, DBBasicTestWithTimestampCompressionSettings,
-    ::testing::Combine(
-        ::testing::Values(std::shared_ptr<const FilterPolicy>(nullptr),
-                          std::shared_ptr<const FilterPolicy>(
-                              NewBloomFilterPolicy(10, false))),
-        ::testing::Values(kNoCompression, kZlibCompression, kLZ4Compression,
-                          kLZ4HCCompression, kZSTD),
-        ::testing::Values(0, 1 << 14), ::testing::Values(1, 4)));
-
-class DBBasicTestWithTimestampPrefixSeek
-    : public DBBasicTestWithTimestampBase,
-      public testing::WithParamInterface<
-          std::tuple<std::shared_ptr<const SliceTransform>,
-                     std::shared_ptr<const FilterPolicy>, bool>> {
- public:
-  DBBasicTestWithTimestampPrefixSeek()
-      : DBBasicTestWithTimestampBase(
-            "/db_basic_test_with_timestamp_prefix_seek") {}
-};
-
-TEST_P(DBBasicTestWithTimestampPrefixSeek, ForwardIterateWithPrefix) {
-  const size_t kNumKeysPerFile = 128;
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  const size_t kTimestampSize = Timestamp(0, 0).size();
-  TestComparator test_cmp(kTimestampSize);
-  options.comparator = &test_cmp;
-  options.prefix_extractor = std::get<0>(GetParam());
-  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
-  BlockBasedTableOptions bbto;
-  bbto.filter_policy = std::get<1>(GetParam());
-  options.table_factory.reset(NewBlockBasedTableFactory(bbto));
-  DestroyAndReopen(options);
-
-  const uint64_t kMaxKey = 0xffffffffffffffff;
-  const uint64_t kMinKey = 0xfffffffffffff000;
-  const std::vector<std::string> write_ts_list = {Timestamp(3, 0xffffffff),
-                                                  Timestamp(6, 0xffffffff)};
-  WriteOptions write_opts;
-  {
-    for (size_t i = 0; i != write_ts_list.size(); ++i) {
-      Slice write_ts = write_ts_list[i];
-      write_opts.timestamp = &write_ts;
-      uint64_t key = kMinKey;
-      do {
-        Status s = db_->Put(write_opts, Key1(key), "value" + std::to_string(i));
-        ASSERT_OK(s);
-        if (key == kMaxKey) {
-          break;
-        }
-        ++key;
-      } while (true);
-    }
-  }
-  const std::vector<std::string> read_ts_list = {Timestamp(5, 0xffffffff),
-                                                 Timestamp(9, 0xffffffff)};
-  {
-    ReadOptions read_opts;
-    read_opts.total_order_seek = false;
-    read_opts.prefix_same_as_start = std::get<2>(GetParam());
-    fprintf(stdout, "%s %s %d\n", options.prefix_extractor->Name(),
-            bbto.filter_policy ? bbto.filter_policy->Name() : "null",
-            static_cast<int>(read_opts.prefix_same_as_start));
-    for (size_t i = 0; i != read_ts_list.size(); ++i) {
-      Slice read_ts = read_ts_list[i];
-      read_opts.timestamp = &read_ts;
-      std::unique_ptr<Iterator> iter(db_->NewIterator(read_opts));
-
-      // Seek to kMaxKey
-      iter->Seek(Key1(kMaxKey));
-      CheckIterUserEntry(iter.get(), Key1(kMaxKey), "value" + std::to_string(i),
-                         write_ts_list[i]);
-      iter->Next();
-      ASSERT_FALSE(iter->Valid());
-    }
-    const std::vector<uint64_t> targets = {kMinKey, kMinKey + 0x10,
-                                           kMinKey + 0x100, kMaxKey};
-    const SliceTransform* const pe = options.prefix_extractor.get();
-    ASSERT_NE(nullptr, pe);
-    const size_t kPrefixShift =
-        8 * (Key1(0).size() - pe->Transform(Key1(0)).size());
-    const uint64_t kPrefixMask =
-        ~((static_cast<uint64_t>(1) << kPrefixShift) - 1);
-    const uint64_t kNumKeysWithinPrefix =
-        (static_cast<uint64_t>(1) << kPrefixShift);
-    for (size_t i = 0; i != read_ts_list.size(); ++i) {
-      Slice read_ts = read_ts_list[i];
-      read_opts.timestamp = &read_ts;
-      std::unique_ptr<Iterator> it(db_->NewIterator(read_opts));
-      for (size_t j = 0; j != targets.size(); ++j) {
-        std::string start_key = Key1(targets[j]);
-        uint64_t expected_ub =
-            (targets[j] & kPrefixMask) - 1 + kNumKeysWithinPrefix;
-        uint64_t expected_key = targets[j];
-        size_t count = 0;
-        it->Seek(Key1(targets[j]));
-        while (it->Valid()) {
-          std::string saved_prev_key;
-          saved_prev_key.assign(it->key().data(), it->key().size());
-
-          // Out of prefix
-          if (!read_opts.prefix_same_as_start &&
-              pe->Transform(saved_prev_key) != pe->Transform(start_key)) {
-            break;
-          }
-          CheckIterUserEntry(it.get(), Key1(expected_key),
-                             "value" + std::to_string(i), write_ts_list[i]);
-          ++count;
-          ++expected_key;
-          it->Next();
-        }
-        ASSERT_EQ(expected_ub - targets[j] + 1, count);
-      }
-    }
-  }
-  Close();
-}
-
-// TODO(yanqin): consider handling non-fixed-length prefix extractors, e.g.
-// NoopTransform.
-INSTANTIATE_TEST_CASE_P(
-    Timestamp, DBBasicTestWithTimestampPrefixSeek,
-    ::testing::Combine(
-        ::testing::Values(
-            std::shared_ptr<const SliceTransform>(NewFixedPrefixTransform(4)),
-            std::shared_ptr<const SliceTransform>(NewFixedPrefixTransform(7)),
-            std::shared_ptr<const SliceTransform>(NewFixedPrefixTransform(8))),
-        ::testing::Values(std::shared_ptr<const FilterPolicy>(nullptr),
-                          std::shared_ptr<const FilterPolicy>(
-                              NewBloomFilterPolicy(10 /*bits_per_key*/, false)),
-                          std::shared_ptr<const FilterPolicy>(
-                              NewBloomFilterPolicy(20 /*bits_per_key*/,
-                                                   false))),
-        ::testing::Bool()));
-
-}  // namespace ROCKSDB_NAMESPACE
-
-#ifdef ROCKSDB_UNITTESTS_WITH_CUSTOM_OBJECTS_FROM_STATIC_LIBS
-extern "C" {
-void RegisterCustomObjects(int argc, char** argv);
-}
-#else
-void RegisterCustomObjects(int /*argc*/, char** /*argv*/) {}
-#endif  // !ROCKSDB_UNITTESTS_WITH_CUSTOM_OBJECTS_FROM_STATIC_LIBS
-
-int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  RegisterCustomObjects(argc, argv);
-  return RUN_ALL_TESTS();
-}
@@ -1,119 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include "db/compaction/compaction.h"
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-namespace {
-std::string Key1(uint64_t key) {
-  std::string ret;
-  PutFixed64(&ret, key);
-  std::reverse(ret.begin(), ret.end());
-  return ret;
-}
-
-std::string Timestamp(uint64_t ts) {
-  std::string ret;
-  PutFixed64(&ret, ts);
-  return ret;
-}
-}  // anonymous namespace
-
-class TimestampCompatibleCompactionTest : public DBTestBase {
- public:
-  TimestampCompatibleCompactionTest()
-      : DBTestBase("/ts_compatible_compaction_test") {}
-
-  std::string Get(const std::string& key, uint64_t ts) {
-    ReadOptions read_opts;
-    std::string ts_str = Timestamp(ts);
-    Slice ts_slice = ts_str;
-    read_opts.timestamp = &ts_slice;
-    std::string value;
-    Status s = db_->Get(read_opts, key, &value);
-    if (s.IsNotFound()) {
-      value.assign("NOT_FOUND");
-    } else if (!s.ok()) {
-      value.assign(s.ToString());
-    }
-    return value;
-  }
-};
-
-TEST_F(TimestampCompatibleCompactionTest, UserKeyCrossFileBoundary) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.compaction_style = kCompactionStyleLevel;
-  options.comparator = test::ComparatorWithU64Ts();
-  options.level0_file_num_compaction_trigger = 3;
-  constexpr size_t kNumKeysPerFile = 101;
-  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
-  DestroyAndReopen(options);
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->SetCallBack(
-      "LevelCompactionPicker::PickCompaction:Return", [&](void* arg) {
-        const auto* compaction = reinterpret_cast<Compaction*>(arg);
-        ASSERT_NE(nullptr, compaction);
-        ASSERT_EQ(0, compaction->start_level());
-        ASSERT_EQ(1, compaction->num_input_levels());
-        // Check that all 3 L0 ssts are picked for level compaction.
-        ASSERT_EQ(3, compaction->num_input_files(0));
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-  // Write a L0 with keys 0, 1, ..., 99 with ts from 100 to 199.
-  uint64_t ts = 100;
-  uint64_t key = 0;
-  WriteOptions write_opts;
-  for (; key < kNumKeysPerFile - 1; ++key, ++ts) {
-    std::string ts_str = Timestamp(ts);
-    Slice ts_slice = ts_str;
-    write_opts.timestamp = &ts_slice;
-    ASSERT_OK(db_->Put(write_opts, Key1(key), "foo_" + std::to_string(key)));
-  }
-  // Write another L0 with keys 99 with newer ts.
-  ASSERT_OK(Flush());
-  uint64_t saved_read_ts1 = ts++;
-  key = 99;
-  for (int i = 0; i < 4; ++i, ++ts) {
-    std::string ts_str = Timestamp(ts);
-    Slice ts_slice = ts_str;
-    write_opts.timestamp = &ts_slice;
-    ASSERT_OK(db_->Put(write_opts, Key1(key), "bar_" + std::to_string(key)));
-  }
-  ASSERT_OK(Flush());
-  uint64_t saved_read_ts2 = ts++;
-  // Write another L0 with keys 99, 100, 101, ..., 150
-  for (; key <= 150; ++key, ++ts) {
-    std::string ts_str = Timestamp(ts);
-    Slice ts_slice = ts_str;
-    write_opts.timestamp = &ts_slice;
-    ASSERT_OK(db_->Put(write_opts, Key1(key), "foo1_" + std::to_string(key)));
-  }
-  ASSERT_OK(Flush());
-  // Wait for compaction to finish
-  ASSERT_OK(dbfull()->TEST_WaitForCompact());
-  uint64_t read_ts = ts;
-  ASSERT_EQ("foo_99", Get(Key1(99), saved_read_ts1));
-  ASSERT_EQ("bar_99", Get(Key1(99), saved_read_ts2));
-  ASSERT_EQ("foo1_99", Get(Key1(99), read_ts));
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->DisableProcessing();
-}
-
-}  // namespace ROCKSDB_NAMESPACE
-
-int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
@@ -75,15 +75,6 @@ void AppendInternalKey(std::string* result, const ParsedInternalKey& key) {
  PutFixed64(result, PackSequenceAndType(key.sequence, key.type));
 }

-void AppendInternalKeyWithDifferentTimestamp(std::string* result,
-                                             const ParsedInternalKey& key,
-                                             const Slice& ts) {
-  assert(key.user_key.size() >= ts.size());
-  result->append(key.user_key.data(), key.user_key.size() - ts.size());
-  result->append(ts.data(), ts.size());
-  PutFixed64(result, PackSequenceAndType(key.sequence, key.type));
-}
-
 void AppendInternalKeyFooter(std::string* result, SequenceNumber s,
                             ValueType t) {
  PutFixed64(result, PackSequenceAndType(s, t));
@@ -104,7 +104,6 @@ struct ParsedInternalKey {
  ParsedInternalKey()
      : sequence(kMaxSequenceNumber)  // Make code analyzer happy
  {}  // Intentionally left uninitialized (for speed)
-  // u contains timestamp if user timestamp feature is enabled.
  ParsedInternalKey(const Slice& u, const SequenceNumber& seq, ValueType t)
      : user_key(u), sequence(seq), type(t) {}
  std::string DebugString(bool hex = false) const;
@@ -133,12 +132,6 @@ EntryType GetEntryType(ValueType value_type);
 // Append the serialization of "key" to *result.
 extern void AppendInternalKey(std::string* result,
                              const ParsedInternalKey& key);
-
-// Append the serialization of "key" to *result, replacing the original
-// timestamp with argument ts.
-extern void AppendInternalKeyWithDifferentTimestamp(
-    std::string* result, const ParsedInternalKey& key, const Slice& ts);
-
 // Serialized internal key consists of user key followed by footer.
 // This function appends the footer to *result, assuming that *result already
 // contains the user key at the end.
@@ -169,11 +162,6 @@ inline Slice StripTimestampFromUserKey(const Slice& user_key, size_t ts_sz) {
  return Slice(user_key.data(), user_key.size() - ts_sz);
 }

-inline Slice ExtractTimestampFromUserKey(const Slice& user_key, size_t ts_sz) {
-  assert(user_key.size() >= ts_sz);
-  return Slice(user_key.data() + user_key.size() - ts_sz, ts_sz);
-}
-
 inline uint64_t ExtractInternalKeyFooter(const Slice& internal_key) {
  assert(internal_key.size() >= 8);
  const size_t n = internal_key.size();
@@ -199,8 +187,7 @@ class InternalKeyComparator

 public:
  explicit InternalKeyComparator(const Comparator* c)
-      : Comparator(c->timestamp_size()),
-        user_comparator_(c),
+      : user_comparator_(c),
        name_("rocksdb.InternalKeyComparator:" +
              std::string(user_comparator_.Name())) {}
  virtual ~InternalKeyComparator() {}
@@ -447,31 +434,24 @@ class IterKey {

  void SetInternalKey(const Slice& key_prefix, const Slice& user_key,
                      SequenceNumber s,
-                      ValueType value_type = kValueTypeForSeek,
-                      const Slice* ts = nullptr) {
+                      ValueType value_type = kValueTypeForSeek) {
    size_t psize = key_prefix.size();
    size_t usize = user_key.size();
-    size_t ts_sz = (ts != nullptr ? ts->size() : 0);
-    EnlargeBufferIfNeeded(psize + usize + sizeof(uint64_t) + ts_sz);
+    EnlargeBufferIfNeeded(psize + usize + sizeof(uint64_t));
    if (psize > 0) {
      memcpy(buf_, key_prefix.data(), psize);
    }
    memcpy(buf_ + psize, user_key.data(), usize);
-    if (ts) {
-      memcpy(buf_ + psize + usize, ts->data(), ts_sz);
-    }
-    EncodeFixed64(buf_ + usize + psize + ts_sz,
-                  PackSequenceAndType(s, value_type));
+    EncodeFixed64(buf_ + usize + psize, PackSequenceAndType(s, value_type));

    key_ = buf_;
-    key_size_ = psize + usize + sizeof(uint64_t) + ts_sz;
+    key_size_ = psize + usize + sizeof(uint64_t);
    is_user_key_ = false;
  }

  void SetInternalKey(const Slice& user_key, SequenceNumber s,
-                      ValueType value_type = kValueTypeForSeek,
-                      const Slice* ts = nullptr) {
-    SetInternalKey(Slice(), user_key, s, value_type, ts);
+                      ValueType value_type = kValueTypeForSeek) {
+    SetInternalKey(Slice(), user_key, s, value_type);
  }

  void Reserve(size_t size) {
@@ -238,46 +238,6 @@ Status ErrorHandler::SetBGError(const Status& bg_err, BackgroundErrorReason reas
  return bg_error_;
 }

-Status ErrorHandler::SetBGError(const IOStatus& bg_io_err,
-                                BackgroundErrorReason reason) {
-  db_mutex_->AssertHeld();
-  if (bg_io_err.ok()) {
-    return Status::OK();
-  }
-  if (recovery_in_prog_ && recovery_error_.ok()) {
-    recovery_error_ = bg_io_err;
-  }
-  Status new_bg_io_err = bg_io_err;
-  Status s;
-  if (bg_io_err.GetDataLoss()) {
-    // FIrst, data loss is treated as unrecoverable error. So it can directly
-    // overwrite any existing bg_error_.
-    bool auto_recovery = false;
-    Status bg_err(new_bg_io_err, Status::Severity::kUnrecoverableError);
-    bg_error_ = bg_err;
-    EventHelpers::NotifyOnBackgroundError(db_options_.listeners, reason, &s,
-                                          db_mutex_, &auto_recovery);
-    return bg_error_;
-  } else if (bg_io_err.GetRetryable()) {
-    // Second, check if the error is a retryable IO error or not. if it is
-    // retryable error and its severity is higher than bg_error_, overwrite
-    // the bg_error_ with new error.
-    // In current stage, treat retryable error as HardError. No automatic
-    // recovery.
-    bool auto_recovery = false;
-    Status bg_err(new_bg_io_err, Status::Severity::kHardError);
-    EventHelpers::NotifyOnBackgroundError(db_options_.listeners, reason, &s,
-                                          db_mutex_, &auto_recovery);
-    if (bg_err.severity() > bg_error_.severity()) {
-      bg_error_ = bg_err;
-    }
-    return bg_error_;
-  } else {
-    s = SetBGError(new_bg_io_err, reason);
-  }
-  return s;
-}
-
 Status ErrorHandler::OverrideNoSpaceError(Status bg_error,
                                          bool* auto_recovery) {
 #ifndef ROCKSDB_LITE
@@ -6,7 +6,6 @@

 #include "monitoring/instrumented_mutex.h"
 #include "options/db_options.h"
-#include "rocksdb/io_status.h"
 #include "rocksdb/listener.h"
 #include "rocksdb/status.h"

@@ -35,8 +34,6 @@ class ErrorHandler {

   Status SetBGError(const Status& bg_err, BackgroundErrorReason reason);

-   Status SetBGError(const IOStatus& bg_io_err, BackgroundErrorReason reason);
-
   Status GetBGError() { return bg_error_; }

   Status GetRecoveryError() { return recovery_error_; }
@@ -10,20 +10,18 @@

 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
-#include "rocksdb/io_status.h"
 #include "rocksdb/perf_context.h"
 #include "rocksdb/sst_file_manager.h"
 #include "test_util/fault_injection_test_env.h"
-#include "test_util/fault_injection_test_fs.h"
 #if !defined(ROCKSDB_LITE)
 #include "test_util/sync_point.h"
 #endif

 namespace ROCKSDB_NAMESPACE {

-class DBErrorHandlingFSTest : public DBTestBase {
+class DBErrorHandlingTest : public DBTestBase {
 public:
-  DBErrorHandlingFSTest() : DBTestBase("/db_error_handling_fs_test") {}
+  DBErrorHandlingTest() : DBTestBase("/db_error_handling_test") {}

  std::string GetManifestNameFromLiveFiles() {
    std::vector<std::string> live_files;
@@ -41,24 +39,21 @@ class DBErrorHandlingFSTest : public DBTestBase {
  }
 };

-class DBErrorHandlingFS : public FileSystemWrapper {
- public:
-  DBErrorHandlingFS()
-      : FileSystemWrapper(FileSystem::Default()),
-        trig_no_space(false),
-        trig_io_error(false) {}
+class DBErrorHandlingEnv : public EnvWrapper {
+  public:
+    DBErrorHandlingEnv() : EnvWrapper(Env::Default()),
+      trig_no_space(false), trig_io_error(false) {}

-  void SetTrigNoSpace() { trig_no_space = true; }
-  void SetTrigIoError() { trig_io_error = true; }
-
- private:
-  bool trig_no_space;
-  bool trig_io_error;
+    void SetTrigNoSpace() {trig_no_space = true;}
+    void SetTrigIoError() {trig_io_error = true;}
+  private:
+    bool trig_no_space;
+    bool trig_io_error;
 };

-class ErrorHandlerFSListener : public EventListener {
+class ErrorHandlerListener : public EventListener {
 public:
-  ErrorHandlerFSListener()
+  ErrorHandlerListener()
      : mutex_(),
        cv_(&mutex_),
        no_auto_recovery_(false),
@@ -66,7 +61,7 @@ class ErrorHandlerFSListener : public EventListener {
        file_creation_started_(false),
        override_bg_error_(false),
        file_count_(0),
-        fault_fs_(nullptr) {}
+        fault_env_(nullptr) {}

  void OnTableFileCreationStarted(
      const TableFileCreationBriefInfo& /*ti*/) override {
@@ -74,15 +69,16 @@ class ErrorHandlerFSListener : public EventListener {
    file_creation_started_ = true;
    if (file_count_ > 0) {
      if (--file_count_ == 0) {
-        fault_fs_->SetFilesystemActive(false, file_creation_error_);
-        file_creation_error_ = IOStatus::OK();
+        fault_env_->SetFilesystemActive(false, file_creation_error_);
+        file_creation_error_ = Status::OK();
      }
    }
    cv_.SignalAll();
  }

  void OnErrorRecoveryBegin(BackgroundErrorReason /*reason*/,
-                            Status /*bg_error*/, bool* auto_recovery) override {
+                            Status /*bg_error*/,
+                            bool* auto_recovery) override {
    if (*auto_recovery && no_auto_recovery_) {
      *auto_recovery = false;
    }
@@ -129,11 +125,11 @@ class ErrorHandlerFSListener : public EventListener {
    override_bg_error_ = true;
  }

-  void InjectFileCreationError(FaultInjectionTestFS* fs, int file_count,
-                               IOStatus io_s) {
-    fault_fs_ = fs;
+  void InjectFileCreationError(FaultInjectionTestEnv* env, int file_count,
+                               Status s) {
+    fault_env_ = env;
    file_count_ = file_count;
-    file_creation_error_ = io_s;
+    file_creation_error_ = s;
  }

 private:
@@ -144,20 +140,18 @@ class ErrorHandlerFSListener : public EventListener {
  bool file_creation_started_;
  bool override_bg_error_;
  int file_count_;
-  IOStatus file_creation_error_;
+  Status file_creation_error_;
  Status bg_error_;
-  FaultInjectionTestFS* fault_fs_;
+  FaultInjectionTestEnv* fault_env_;
 };

-TEST_F(DBErrorHandlingFSTest, FLushWriteError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
+TEST_F(DBErrorHandlingTest, FLushWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
  options.create_if_missing = true;
+  options.env = fault_env.get();
  options.listeners.emplace_back(listener);
  Status s;

@@ -165,14 +159,15 @@ TEST_F(DBErrorHandlingFSTest, FLushWriteError) {
  DestroyAndReopen(options);

  Put(Key(0), "val");
-  SyncPoint::GetInstance()->SetCallBack("FlushJob::Start", [&](void*) {
-    fault_fs->SetFilesystemActive(false, IOStatus::NoSpace("Out of space"));
+  SyncPoint::GetInstance()->SetCallBack(
+      "FlushJob::Start", [&](void *) {
+    fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
  });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs->SetFilesystemActive(true);
+  fault_env->SetFilesystemActive(true);
  s = dbfull()->Resume();
  ASSERT_EQ(s, Status::OK());

@@ -181,78 +176,13 @@ TEST_F(DBErrorHandlingFSTest, FLushWriteError) {
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, FLushWritRetryableeError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
+TEST_F(DBErrorHandlingTest, ManifestWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
-  options.create_if_missing = true;
-  options.listeners.emplace_back(listener);
-  Status s;
-
-  listener->EnableAutoRecovery(false);
-  DestroyAndReopen(options);
-
-  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
-  error_msg.SetRetryable(true);
-
-  Put(Key(1), "val1");
-  SyncPoint::GetInstance()->SetCallBack(
-      "BuildTable:BeforeFinishBuildTable",
-      [&](void*) { fault_fs->SetFilesystemActive(false, error_msg); });
-  SyncPoint::GetInstance()->EnableProcessing();
-  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs->SetFilesystemActive(true);
-  s = dbfull()->Resume();
-  ASSERT_EQ(s, Status::OK());
-  Reopen(options);
-  ASSERT_EQ("val1", Get(Key(1)));
-
-  Put(Key(2), "val2");
-  SyncPoint::GetInstance()->SetCallBack(
-      "BuildTable:BeforeSyncTable",
-      [&](void*) { fault_fs->SetFilesystemActive(false, error_msg); });
-  SyncPoint::GetInstance()->EnableProcessing();
-  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs->SetFilesystemActive(true);
-  s = dbfull()->Resume();
-  ASSERT_EQ(s, Status::OK());
-  Reopen(options);
-  ASSERT_EQ("val2", Get(Key(2)));
-
-  Put(Key(3), "val3");
-  SyncPoint::GetInstance()->SetCallBack(
-      "BuildTable:BeforeCloseTableFile",
-      [&](void*) { fault_fs->SetFilesystemActive(false, error_msg); });
-  SyncPoint::GetInstance()->EnableProcessing();
-  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs->SetFilesystemActive(true);
-  s = dbfull()->Resume();
-  ASSERT_EQ(s, Status::OK());
-  Reopen(options);
-  ASSERT_EQ("val3", Get(Key(3)));
-
-  Destroy(options);
-}
-
-TEST_F(DBErrorHandlingFSTest, ManifestWriteError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
-  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
  options.create_if_missing = true;
+  options.env = fault_env.get();
  options.listeners.emplace_back(listener);
  Status s;
  std::string old_manifest;
@@ -266,15 +196,15 @@ TEST_F(DBErrorHandlingFSTest, ManifestWriteError) {
  Flush();
  Put(Key(1), "val");
  SyncPoint::GetInstance()->SetCallBack(
-      "VersionSet::LogAndApply:WriteManifest", [&](void*) {
-        fault_fs->SetFilesystemActive(false, IOStatus::NoSpace("Out of space"));
-      });
+      "VersionSet::LogAndApply:WriteManifest", [&](void *) {
+    fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
+  });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
  SyncPoint::GetInstance()->ClearAllCallBacks();
  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs->SetFilesystemActive(true);
+  fault_env->SetFilesystemActive(true);
  s = dbfull()->Resume();
  ASSERT_EQ(s, Status::OK());

@@ -287,60 +217,13 @@ TEST_F(DBErrorHandlingFSTest, ManifestWriteError) {
  Close();
 }

-TEST_F(DBErrorHandlingFSTest, ManifestWriteRetryableError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
+TEST_F(DBErrorHandlingTest, DoubleManifestWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
-  options.create_if_missing = true;
-  options.listeners.emplace_back(listener);
-  Status s;
-  std::string old_manifest;
-  std::string new_manifest;
-
-  listener->EnableAutoRecovery(false);
-  DestroyAndReopen(options);
-  old_manifest = GetManifestNameFromLiveFiles();
-
-  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
-  error_msg.SetRetryable(true);
-
-  Put(Key(0), "val");
-  Flush();
-  Put(Key(1), "val");
-  SyncPoint::GetInstance()->SetCallBack(
-      "VersionSet::LogAndApply:WriteManifest",
-      [&](void*) { fault_fs->SetFilesystemActive(false, error_msg); });
-  SyncPoint::GetInstance()->EnableProcessing();
-  s = Flush();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs->SetFilesystemActive(true);
-  s = dbfull()->Resume();
-  ASSERT_EQ(s, Status::OK());
-
-  new_manifest = GetManifestNameFromLiveFiles();
-  ASSERT_NE(new_manifest, old_manifest);
-
-  Reopen(options);
-  ASSERT_EQ("val", Get(Key(0)));
-  ASSERT_EQ("val", Get(Key(1)));
-  Close();
-}
-
-TEST_F(DBErrorHandlingFSTest, DoubleManifestWriteError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
-  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
  options.create_if_missing = true;
+  options.env = fault_env.get();
  options.listeners.emplace_back(listener);
  Status s;
  std::string old_manifest;
@@ -354,18 +237,18 @@ TEST_F(DBErrorHandlingFSTest, DoubleManifestWriteError) {
  Flush();
  Put(Key(1), "val");
  SyncPoint::GetInstance()->SetCallBack(
-      "VersionSet::LogAndApply:WriteManifest", [&](void*) {
-        fault_fs->SetFilesystemActive(false, IOStatus::NoSpace("Out of space"));
-      });
+      "VersionSet::LogAndApply:WriteManifest", [&](void *) {
+    fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
+  });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  fault_fs->SetFilesystemActive(true);
+  fault_env->SetFilesystemActive(true);

  // This Resume() will attempt to create a new manifest file and fail again
  s = dbfull()->Resume();
  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-  fault_fs->SetFilesystemActive(true);
+  fault_env->SetFilesystemActive(true);
  SyncPoint::GetInstance()->ClearAllCallBacks();
  SyncPoint::GetInstance()->DisableProcessing();

@@ -382,17 +265,15 @@ TEST_F(DBErrorHandlingFSTest, DoubleManifestWriteError) {
  Close();
 }

-TEST_F(DBErrorHandlingFSTest, CompactionManifestWriteError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
+TEST_F(DBErrorHandlingTest, CompactionManifestWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
  options.create_if_missing = true;
  options.level0_file_num_compaction_trigger = 2;
  options.listeners.emplace_back(listener);
+  options.env = fault_env.get();
  Status s;
  std::string old_manifest;
  std::string new_manifest;
@@ -423,8 +304,8 @@ TEST_F(DBErrorHandlingFSTest, CompactionManifestWriteError) {
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "VersionSet::LogAndApply:WriteManifest", [&](void*) {
        if (fail_manifest.load()) {
-          fault_fs->SetFilesystemActive(false,
-                                        IOStatus::NoSpace("Out of space"));
+          fault_env->SetFilesystemActive(false,
+                                         Status::NoSpace("Out of space"));
        }
      });
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
@@ -437,7 +318,7 @@ TEST_F(DBErrorHandlingFSTest, CompactionManifestWriteError) {

  TEST_SYNC_POINT("CompactionManifestWriteError:0");
  // Clear all errors so when the compaction is retried, it will succeed
-  fault_fs->SetFilesystemActive(true);
+  fault_env->SetFilesystemActive(true);
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
  TEST_SYNC_POINT("CompactionManifestWriteError:1");
  TEST_SYNC_POINT("CompactionManifestWriteError:2");
@@ -455,91 +336,15 @@ TEST_F(DBErrorHandlingFSTest, CompactionManifestWriteError) {
  Close();
 }

-TEST_F(DBErrorHandlingFSTest, CompactionManifestWriteRetryableError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
+TEST_F(DBErrorHandlingTest, CompactionWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
-  options.create_if_missing = true;
-  options.level0_file_num_compaction_trigger = 2;
-  options.listeners.emplace_back(listener);
-  Status s;
-  std::string old_manifest;
-  std::string new_manifest;
-  std::atomic<bool> fail_manifest(false);
-  DestroyAndReopen(options);
-  old_manifest = GetManifestNameFromLiveFiles();
-
-  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
-  error_msg.SetRetryable(true);
-
-  Put(Key(0), "val");
-  Put(Key(2), "val");
-  s = Flush();
-  ASSERT_EQ(s, Status::OK());
-
-  listener->OverrideBGError(Status(error_msg, Status::Severity::kHardError));
-  listener->EnableAutoRecovery(false);
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-      // Wait for flush of 2nd L0 file before starting compaction
-      {{"DBImpl::FlushMemTable:FlushMemTableFinished",
-        "BackgroundCallCompaction:0"},
-       // Wait for compaction to detect manifest write error
-       {"BackgroundCallCompaction:1", "CompactionManifestWriteError:0"},
-       // Make compaction thread wait for error to be cleared
-       {"CompactionManifestWriteError:1",
-        "DBImpl::BackgroundCallCompaction:FoundObsoleteFiles"}});
-  // trigger manifest write failure in compaction thread
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "BackgroundCallCompaction:0", [&](void*) { fail_manifest.store(true); });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "VersionSet::LogAndApply:WriteManifest", [&](void*) {
-        if (fail_manifest.load()) {
-          fault_fs->SetFilesystemActive(false, error_msg);
-        }
-      });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-
-  Put(Key(1), "val");
-  s = Flush();
-  ASSERT_EQ(s, Status::OK());
-
-  TEST_SYNC_POINT("CompactionManifestWriteError:0");
-  TEST_SYNC_POINT("CompactionManifestWriteError:1");
-
-  s = dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-
-  fault_fs->SetFilesystemActive(true);
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->DisableProcessing();
-  s = dbfull()->Resume();
-  ASSERT_EQ(s, Status::OK());
-
-  new_manifest = GetManifestNameFromLiveFiles();
-  ASSERT_NE(new_manifest, old_manifest);
-
-  Reopen(options);
-  ASSERT_EQ("val", Get(Key(0)));
-  ASSERT_EQ("val", Get(Key(1)));
-  ASSERT_EQ("val", Get(Key(2)));
-  Close();
-}
-
-TEST_F(DBErrorHandlingFSTest, CompactionWriteError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
-  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
  options.create_if_missing = true;
  options.level0_file_num_compaction_trigger = 2;
  options.listeners.emplace_back(listener);
+  options.env = fault_env.get();
  Status s;
  DestroyAndReopen(options);

@@ -549,14 +354,15 @@ TEST_F(DBErrorHandlingFSTest, CompactionWriteError) {
  ASSERT_EQ(s, Status::OK());

  listener->OverrideBGError(
-      Status(Status::NoSpace(), Status::Severity::kHardError));
+      Status(Status::NoSpace(), Status::Severity::kHardError)
+      );
  listener->EnableAutoRecovery(false);
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
      {{"DBImpl::FlushMemTable:FlushMemTableFinished",
        "BackgroundCallCompaction:0"}});
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "BackgroundCallCompaction:0", [&](void*) {
-        fault_fs->SetFilesystemActive(false, IOStatus::NoSpace("Out of space"));
+        fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
      });
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();

@@ -567,67 +373,19 @@ TEST_F(DBErrorHandlingFSTest, CompactionWriteError) {
  s = dbfull()->TEST_WaitForCompact();
  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);

-  fault_fs->SetFilesystemActive(true);
+  fault_env->SetFilesystemActive(true);
  s = dbfull()->Resume();
  ASSERT_EQ(s, Status::OK());
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, CompactionWriteRetryableError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
+TEST_F(DBErrorHandlingTest, CorruptionError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
-  options.create_if_missing = true;
-  options.level0_file_num_compaction_trigger = 2;
-  options.listeners.emplace_back(listener);
-  Status s;
-  DestroyAndReopen(options);
-
-  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
-  error_msg.SetRetryable(true);
-
-  Put(Key(0), "va;");
-  Put(Key(2), "va;");
-  s = Flush();
-  ASSERT_EQ(s, Status::OK());
-
-  listener->OverrideBGError(Status(error_msg, Status::Severity::kHardError));
-  listener->EnableAutoRecovery(false);
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::FlushMemTable:FlushMemTableFinished",
-        "BackgroundCallCompaction:0"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "BackgroundCallCompaction:0",
-      [&](void*) { fault_fs->SetFilesystemActive(false, error_msg); });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-
-  Put(Key(1), "val");
-  s = Flush();
-  ASSERT_EQ(s, Status::OK());
-
-  s = dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
-
-  fault_fs->SetFilesystemActive(true);
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->DisableProcessing();
-  s = dbfull()->Resume();
-  ASSERT_EQ(s, Status::OK());
-  Destroy(options);
-}
-
-TEST_F(DBErrorHandlingFSTest, CorruptionError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
  options.create_if_missing = true;
  options.level0_file_num_compaction_trigger = 2;
+  options.env = fault_env.get();
  Status s;
  DestroyAndReopen(options);

@@ -641,8 +399,7 @@ TEST_F(DBErrorHandlingFSTest, CorruptionError) {
        "BackgroundCallCompaction:0"}});
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
      "BackgroundCallCompaction:0", [&](void*) {
-        fault_fs->SetFilesystemActive(false,
-                                      IOStatus::Corruption("Corruption"));
+        fault_env->SetFilesystemActive(false, Status::Corruption("Corruption"));
      });
  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();

@@ -654,21 +411,19 @@ TEST_F(DBErrorHandlingFSTest, CorruptionError) {
  ASSERT_EQ(s.severity(),
            ROCKSDB_NAMESPACE::Status::Severity::kUnrecoverableError);

-  fault_fs->SetFilesystemActive(true);
+  fault_env->SetFilesystemActive(true);
  s = dbfull()->Resume();
  ASSERT_NE(s, Status::OK());
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, AutoRecoverFlushError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
+TEST_F(DBErrorHandlingTest, AutoRecoverFlushError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
  options.create_if_missing = true;
+  options.env = fault_env.get();
  options.listeners.emplace_back(listener);
  Status s;

@@ -677,13 +432,13 @@ TEST_F(DBErrorHandlingFSTest, AutoRecoverFlushError) {

  Put(Key(0), "val");
  SyncPoint::GetInstance()->SetCallBack("FlushJob::Start", [&](void*) {
-    fault_fs->SetFilesystemActive(false, IOStatus::NoSpace("Out of space"));
+    fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
  });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
  ASSERT_EQ(s.severity(), ROCKSDB_NAMESPACE::Status::Severity::kHardError);
  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs->SetFilesystemActive(true);
+  fault_env->SetFilesystemActive(true);
  ASSERT_EQ(listener->WaitForRecovery(5000000), true);

  s = Put(Key(1), "val");
@@ -695,15 +450,13 @@ TEST_F(DBErrorHandlingFSTest, AutoRecoverFlushError) {
  Destroy(options);
 }

-TEST_F(DBErrorHandlingFSTest, FailRecoverFlushError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
+TEST_F(DBErrorHandlingTest, FailRecoverFlushError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
  options.create_if_missing = true;
+  options.env = fault_env.get();
  options.listeners.emplace_back(listener);
  Status s;

@@ -712,7 +465,7 @@ TEST_F(DBErrorHandlingFSTest, FailRecoverFlushError) {

  Put(Key(0), "val");
  SyncPoint::GetInstance()->SetCallBack("FlushJob::Start", [&](void*) {
-    fault_fs->SetFilesystemActive(false, IOStatus::NoSpace("Out of space"));
+    fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
  });
  SyncPoint::GetInstance()->EnableProcessing();
  s = Flush();
@@ -723,16 +476,14 @@ TEST_F(DBErrorHandlingFSTest, FailRecoverFlushError) {
  DestroyDB(dbname_, options);
 }

-TEST_F(DBErrorHandlingFSTest, WALWriteError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
+TEST_F(DBErrorHandlingTest, WALWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
  options.create_if_missing = true;
  options.writable_file_max_buffer_size = 32768;
+  options.env = fault_env.get();
  options.listeners.emplace_back(listener);
  Status s;
  Random rnd(301);
@@ -743,7 +494,7 @@ TEST_F(DBErrorHandlingFSTest, WALWriteError) {
  {
    WriteBatch batch;

-    for (auto i = 0; i < 100; ++i) {
+    for (auto i = 0; i<100; ++i) {
      batch.Put(Key(i), RandomString(&rnd, 1024));
    }

@@ -756,18 +507,16 @@ TEST_F(DBErrorHandlingFSTest, WALWriteError) {
    WriteBatch batch;
    int write_error = 0;

-    for (auto i = 100; i < 199; ++i) {
+    for (auto i = 100; i<199; ++i) {
      batch.Put(Key(i), RandomString(&rnd, 1024));
    }

-    SyncPoint::GetInstance()->SetCallBack(
-        "WritableFileWriter::Append:BeforePrepareWrite", [&](void*) {
-          write_error++;
-          if (write_error > 2) {
-            fault_fs->SetFilesystemActive(false,
-                                          IOStatus::NoSpace("Out of space"));
-          }
-        });
+    SyncPoint::GetInstance()->SetCallBack("WritableFileWriter::Append:BeforePrepareWrite", [&](void*) {
+      write_error++;
+      if (write_error > 2) {
+        fault_env->SetFilesystemActive(false, Status::NoSpace("Out of space"));
+      }
+    });
    SyncPoint::GetInstance()->EnableProcessing();
    WriteOptions wopts;
    wopts.sync = true;
@@ -775,9 +524,9 @@ TEST_F(DBErrorHandlingFSTest, WALWriteError) {
    ASSERT_EQ(s, s.NoSpace());
  }
  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs->SetFilesystemActive(true);
+  fault_env->SetFilesystemActive(true);
  ASSERT_EQ(listener->WaitForRecovery(5000000), true);
-  for (auto i = 0; i < 199; ++i) {
+  for (auto i=0; i<199; ++i) {
    if (i < 100) {
      ASSERT_NE(Get(Key(i)), "NOT_FOUND");
    } else {
@@ -785,7 +534,7 @@ TEST_F(DBErrorHandlingFSTest, WALWriteError) {
    }
  }
  Reopen(options);
-  for (auto i = 0; i < 199; ++i) {
+  for (auto i=0; i<199; ++i) {
    if (i < 100) {
      ASSERT_NE(Get(Key(i)), "NOT_FOUND");
    } else {
@@ -795,111 +544,14 @@ TEST_F(DBErrorHandlingFSTest, WALWriteError) {
  Close();
 }

-TEST_F(DBErrorHandlingFSTest, WALWriteRetryableError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
+TEST_F(DBErrorHandlingTest, MultiCFWALWriteError) {
+  std::unique_ptr<FaultInjectionTestEnv> fault_env(
+      new FaultInjectionTestEnv(Env::Default()));
+  std::shared_ptr<ErrorHandlerListener> listener(new ErrorHandlerListener());
  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
-  options.create_if_missing = true;
-  options.writable_file_max_buffer_size = 32768;
-  options.listeners.emplace_back(listener);
-  options.paranoid_checks = true;
-  Status s;
-  Random rnd(301);
-
-  DestroyAndReopen(options);
-
-  IOStatus error_msg = IOStatus::IOError("Retryable IO Error");
-  error_msg.SetRetryable(true);
-
-  // For the first batch, write is successful, require sync
-  {
-    WriteBatch batch;
-
-    for (auto i = 0; i < 100; ++i) {
-      batch.Put(Key(i), RandomString(&rnd, 1024));
-    }
-
-    WriteOptions wopts;
-    wopts.sync = true;
-    ASSERT_EQ(dbfull()->Write(wopts, &batch), Status::OK());
-  };
-
-  // For the second batch, the first 2 file Append are successful, then the
-  // following Append fails due to file system retryable IOError.
-  {
-    WriteBatch batch;
-    int write_error = 0;
-
-    for (auto i = 100; i < 200; ++i) {
-      batch.Put(Key(i), RandomString(&rnd, 1024));
-    }
-
-    SyncPoint::GetInstance()->SetCallBack(
-        "WritableFileWriter::Append:BeforePrepareWrite", [&](void*) {
-          write_error++;
-          if (write_error > 2) {
-            fault_fs->SetFilesystemActive(false, error_msg);
-          }
-        });
-    SyncPoint::GetInstance()->EnableProcessing();
-    WriteOptions wopts;
-    wopts.sync = true;
-    s = dbfull()->Write(wopts, &batch);
-    ASSERT_EQ(true, s.IsIOError());
-  }
-  fault_fs->SetFilesystemActive(true);
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->DisableProcessing();
-
-  // Data in corrupted WAL are not stored
-  for (auto i = 0; i < 199; ++i) {
-    if (i < 100) {
-      ASSERT_NE(Get(Key(i)), "NOT_FOUND");
-    } else {
-      ASSERT_EQ(Get(Key(i)), "NOT_FOUND");
-    }
-  }
-
-  // Resume and write a new batch, should be in the WAL
-  s = dbfull()->Resume();
-  ASSERT_EQ(s, Status::OK());
-  {
-    WriteBatch batch;
-
-    for (auto i = 200; i < 300; ++i) {
-      batch.Put(Key(i), RandomString(&rnd, 1024));
-    }
-
-    WriteOptions wopts;
-    wopts.sync = true;
-    ASSERT_EQ(dbfull()->Write(wopts, &batch), Status::OK());
-  };
-
-  Reopen(options);
-  for (auto i = 0; i < 300; ++i) {
-    if (i < 100 || i >= 200) {
-      ASSERT_NE(Get(Key(i)), "NOT_FOUND");
-    } else {
-      ASSERT_EQ(Get(Key(i)), "NOT_FOUND");
-    }
-  }
-  Close();
-}
-
-TEST_F(DBErrorHandlingFSTest, MultiCFWALWriteError) {
-  std::shared_ptr<FaultInjectionTestFS> fault_fs(
-      new FaultInjectionTestFS(FileSystem::Default()));
-  std::unique_ptr<Env> fault_fs_env(NewCompositeEnv(fault_fs));
-  std::shared_ptr<ErrorHandlerFSListener> listener(
-      new ErrorHandlerFSListener());
-  Options options = GetDefaultOptions();
-  options.env = fault_fs_env.get();
  options.create_if_missing = true;
  options.writable_file_max_buffer_size = 32768;
+  options.env = fault_env.get();
  options.listeners.emplace_back(listener);
  Status s;
  Random rnd(301);
@@ -934,8 +586,8 @@ TEST_F(DBErrorHandlingFSTest, MultiCFWALWriteError) {
        "WritableFileWriter::Append:BeforePrepareWrite", [&](void*) {
          write_error++;
          if (write_error > 2) {
-            fault_fs->SetFilesystemActive(false,
-                                          IOStatus::NoSpace("Out of space"));
+            fault_env->SetFilesystemActive(false,
+                                           Status::NoSpace("Out of space"));
          }
        });
    SyncPoint::GetInstance()->EnableProcessing();
@@ -945,7 +597,7 @@ TEST_F(DBErrorHandlingFSTest, MultiCFWALWriteError) {
    ASSERT_EQ(s, s.NoSpace());
  }
  SyncPoint::GetInstance()->DisableProcessing();
-  fault_fs->SetFilesystemActive(true);
+  fault_env->SetFilesystemActive(true);
  ASSERT_EQ(listener->WaitForRecovery(5000000), true);

  for (auto i = 1; i < 4; ++i) {
@@ -975,27 +627,24 @@ TEST_F(DBErrorHandlingFSTest, MultiCFWALWriteError) {
  Close();
 }

-TEST_F(DBErrorHandlingFSTest, MultiDBCompactionError) {
+TEST_F(DBErrorHandlingTest, MultiDBCompactionError) {
  FaultInjectionTestEnv* def_env = new FaultInjectionTestEnv(Env::Default());
-  std::vector<std::unique_ptr<Env>> fault_envs;
-  std::vector<FaultInjectionTestFS*> fault_fs;
+  std::vector<std::unique_ptr<FaultInjectionTestEnv>> fault_env;
  std::vector<Options> options;
-  std::vector<std::shared_ptr<ErrorHandlerFSListener>> listener;
+  std::vector<std::shared_ptr<ErrorHandlerListener>> listener;
  std::vector<DB*> db;
  std::shared_ptr<SstFileManager> sfm(NewSstFileManager(def_env));
  int kNumDbInstances = 3;
  Random rnd(301);

  for (auto i = 0; i < kNumDbInstances; ++i) {
-    listener.emplace_back(new ErrorHandlerFSListener());
+    listener.emplace_back(new ErrorHandlerListener());
    options.emplace_back(GetDefaultOptions());
-    fault_fs.emplace_back(new FaultInjectionTestFS(FileSystem::Default()));
-    std::shared_ptr<FileSystem> fs(fault_fs.back());
-    fault_envs.emplace_back(new CompositeEnvWrapper(def_env, fs));
-    options[i].env = fault_envs.back().get();
+    fault_env.emplace_back(new FaultInjectionTestEnv(Env::Default()));
    options[i].create_if_missing = true;
    options[i].level0_file_num_compaction_trigger = 2;
    options[i].writable_file_max_buffer_size = 32768;
+    options[i].env = fault_env[i].get();
    options[i].listeners.emplace_back(listener[i]);
    options[i].sst_file_manager = sfm;
    DB* dbptr;
@@ -1003,8 +652,8 @@ TEST_F(DBErrorHandlingFSTest, MultiDBCompactionError) {

    listener[i]->EnableAutoRecovery();
    // Setup for returning error for the 3rd SST, which would be level 1
-    listener[i]->InjectFileCreationError(fault_fs[i], 3,
-                                         IOStatus::NoSpace("Out of space"));
+    listener[i]->InjectFileCreationError(fault_env[i].get(), 3,
+                                         Status::NoSpace("Out of space"));
    snprintf(buf, sizeof(buf), "_%d", i);
    DestroyDB(dbname_ + std::string(buf), options[i]);
    ASSERT_EQ(DB::Open(options[i], dbname_ + std::string(buf), &dbptr),
@@ -1043,7 +692,7 @@ TEST_F(DBErrorHandlingFSTest, MultiDBCompactionError) {
  for (auto i = 0; i < kNumDbInstances; ++i) {
    Status s = static_cast<DBImpl*>(db[i])->TEST_WaitForCompact(true);
    ASSERT_EQ(s.severity(), Status::Severity::kSoftError);
-    fault_fs[i]->SetFilesystemActive(true);
+    fault_env[i]->SetFilesystemActive(true);
  }

  def_env->SetFilesystemActive(true);
@@ -1064,7 +713,7 @@ TEST_F(DBErrorHandlingFSTest, MultiDBCompactionError) {
    char buf[16];
    snprintf(buf, sizeof(buf), "_%d", i);
    delete db[i];
-    fault_fs[i]->SetFilesystemActive(true);
+    fault_env[i]->SetFilesystemActive(true);
    if (getenv("KEEP_DB")) {
      printf("DB is still at %s%s\n", dbname_.c_str(), buf);
    } else {
@@ -1076,27 +725,24 @@ TEST_F(DBErrorHandlingFSTest, MultiDBCompactionError) {
  delete def_env;
 }

-TEST_F(DBErrorHandlingFSTest, MultiDBVariousErrors) {
+TEST_F(DBErrorHandlingTest, MultiDBVariousErrors) {
  FaultInjectionTestEnv* def_env = new FaultInjectionTestEnv(Env::Default());
-  std::vector<std::unique_ptr<Env>> fault_envs;
-  std::vector<FaultInjectionTestFS*> fault_fs;
+  std::vector<std::unique_ptr<FaultInjectionTestEnv>> fault_env;
  std::vector<Options> options;
-  std::vector<std::shared_ptr<ErrorHandlerFSListener>> listener;
+  std::vector<std::shared_ptr<ErrorHandlerListener>> listener;
  std::vector<DB*> db;
  std::shared_ptr<SstFileManager> sfm(NewSstFileManager(def_env));
  int kNumDbInstances = 3;
  Random rnd(301);

  for (auto i = 0; i < kNumDbInstances; ++i) {
-    listener.emplace_back(new ErrorHandlerFSListener());
+    listener.emplace_back(new ErrorHandlerListener());
    options.emplace_back(GetDefaultOptions());
-    fault_fs.emplace_back(new FaultInjectionTestFS(FileSystem::Default()));
-    std::shared_ptr<FileSystem> fs(fault_fs.back());
-    fault_envs.emplace_back(new CompositeEnvWrapper(def_env, fs));
-    options[i].env = fault_envs.back().get();
+    fault_env.emplace_back(new FaultInjectionTestEnv(Env::Default()));
    options[i].create_if_missing = true;
    options[i].level0_file_num_compaction_trigger = 2;
    options[i].writable_file_max_buffer_size = 32768;
+    options[i].env = fault_env[i].get();
    options[i].listeners.emplace_back(listener[i]);
    options[i].sst_file_manager = sfm;
    DB* dbptr;
@@ -1106,14 +752,14 @@ TEST_F(DBErrorHandlingFSTest, MultiDBVariousErrors) {
    switch (i) {
      case 0:
        // Setup for returning error for the 3rd SST, which would be level 1
-        listener[i]->InjectFileCreationError(fault_fs[i], 3,
-                                             IOStatus::NoSpace("Out of space"));
+        listener[i]->InjectFileCreationError(fault_env[i].get(), 3,
+                                             Status::NoSpace("Out of space"));
        break;
      case 1:
        // Setup for returning error after the 1st SST, which would result
        // in a hard error
-        listener[i]->InjectFileCreationError(fault_fs[i], 2,
-                                             IOStatus::NoSpace("Out of space"));
+        listener[i]->InjectFileCreationError(fault_env[i].get(), 2,
+                                             Status::NoSpace("Out of space"));
        break;
      default:
        break;
@@ -1170,7 +816,7 @@ TEST_F(DBErrorHandlingFSTest, MultiDBVariousErrors) {
        ASSERT_EQ(s, Status::OK());
        break;
    }
-    fault_fs[i]->SetFilesystemActive(true);
+    fault_env[i]->SetFilesystemActive(true);
  }

  def_env->SetFilesystemActive(true);
@@ -1194,7 +840,7 @@ TEST_F(DBErrorHandlingFSTest, MultiDBVariousErrors) {
  for (auto i = 0; i < kNumDbInstances; ++i) {
    char buf[16];
    snprintf(buf, sizeof(buf), "_%d", i);
-    fault_fs[i]->SetFilesystemActive(true);
+    fault_env[i]->SetFilesystemActive(true);
    delete db[i];
    if (getenv("KEEP_DB")) {
      printf("DB is still at %s%s\n", dbname_.c_str(), buf);
@@ -1205,6 +851,7 @@ TEST_F(DBErrorHandlingFSTest, MultiDBVariousErrors) {
  options.clear();
  delete def_env;
 }
+
 }  // namespace ROCKSDB_NAMESPACE

 int main(int argc, char** argv) {
@@ -796,45 +796,6 @@ TEST_F(ExternalSSTFileBasicTest, VerifyChecksumReadahead) {
  Destroy(options);
 }

-TEST_F(ExternalSSTFileBasicTest, IngestRangeDeletionTombstoneWithGlobalSeqno) {
-  for (int i = 5; i < 25; i++) {
-    ASSERT_OK(db_->Put(WriteOptions(), db_->DefaultColumnFamily(), Key(i),
-                       Key(i) + "_val"));
-  }
-
-  Options options = CurrentOptions();
-  options.disable_auto_compactions = true;
-  Reopen(options);
-  SstFileWriter sst_file_writer(EnvOptions(), options);
-
-  // file.sst (delete 0 => 30)
-  std::string file = sst_files_dir_ + "file.sst";
-  ASSERT_OK(sst_file_writer.Open(file));
-  ASSERT_OK(sst_file_writer.DeleteRange(Key(0), Key(30)));
-  ExternalSstFileInfo file_info;
-  ASSERT_OK(sst_file_writer.Finish(&file_info));
-  ASSERT_EQ(file_info.file_path, file);
-  ASSERT_EQ(file_info.num_entries, 0);
-  ASSERT_EQ(file_info.smallest_key, "");
-  ASSERT_EQ(file_info.largest_key, "");
-  ASSERT_EQ(file_info.num_range_del_entries, 1);
-  ASSERT_EQ(file_info.smallest_range_del_key, Key(0));
-  ASSERT_EQ(file_info.largest_range_del_key, Key(30));
-
-  IngestExternalFileOptions ifo;
-  ifo.move_files = true;
-  ifo.snapshot_consistency = true;
-  ifo.allow_global_seqno = true;
-  ifo.write_global_seqno = true;
-  ifo.verify_checksums_before_ingest = false;
-  ASSERT_OK(db_->IngestExternalFile({file}, ifo));
-
-  for (int i = 5; i < 25; i++) {
-    std::string res;
-    ASSERT_TRUE(db_->Get(ReadOptions(), Key(i), &res).IsNotFound());
-  }
-}
-
 TEST_P(ExternalSSTFileBasicTest, IngestionWithRangeDeletions) {
  int kNumLevels = 7;
  Options options = CurrentOptions();
@@ -46,7 +46,7 @@ Status ExternalSstFileIngestionJob::Prepare(
            TablePropertiesCollectorFactory::Context::kUnknownColumnFamily &&
        f.cf_id != cfd_->GetID()) {
      return Status::InvalidArgument(
-          "External file column family id don't match");
+          "External file column family id dont match");
    }
  }

@@ -55,7 +55,7 @@ Status ExternalSstFileIngestionJob::Prepare(
  if (num_files == 0) {
    return Status::InvalidArgument("The list of files is empty");
  } else if (num_files > 1) {
-    // Verify that passed files don't have overlapping ranges
+    // Verify that passed files dont have overlapping ranges
    autovector<const IngestedFileInfo*> sorted_files;
    for (size_t i = 0; i < num_files; i++) {
      sorted_files.push_back(&files_to_ingest_[i]);
@@ -148,7 +148,7 @@ Status ExternalSstFileIngestionJob::Prepare(
  TEST_SYNC_POINT("ExternalSstFileIngestionJob::BeforeSyncDir");
  if (status.ok()) {
    for (auto path_id : ingestion_path_ids) {
-      status = directories_->GetDataDir(path_id)->Fsync(IOOptions(), nullptr);
+      status = directories_->GetDataDir(path_id)->Fsync();
      if (!status.ok()) {
        ROCKS_LOG_WARN(db_options_.info_log,
                       "Failed to sync directory %" ROCKSDB_PRIszt
@@ -212,7 +212,7 @@ Status ExternalSstFileIngestionJob::Run() {

  if (ingestion_options_.snapshot_consistency && !db_snapshots_->empty()) {
    // We need to assign a global sequence number to all the files even
-    // if the don't overlap with any ranges since we have snapshots
+    // if the dont overlap with any ranges since we have snapshots
    force_global_seqno = true;
  }
  // It is safe to use this instead of LastAllocatedSequence since we are
@@ -588,7 +588,7 @@ Status ExternalSstFileIngestionJob::AssignLevelAndSeqnoForIngestedFile(
      continue;
    }

-    // We don't overlap with any keys in this level, but we still need to check
+    // We dont overlap with any keys in this level, but we still need to check
    // if our file can fit in it
    if (IngestedFileFitInLevel(file_to_ingest, lvl)) {
      target_level = lvl;
@@ -646,7 +646,7 @@ Status ExternalSstFileIngestionJob::AssignGlobalSeqnoForIngestedFile(
    return Status::InvalidArgument("Global seqno is required, but disabled");
  } else if (file_to_ingest->global_seqno_offset == 0) {
    return Status::InvalidArgument(
-        "Trying to set global seqno for a file that don't have a global seqno "
+        "Trying to set global seqno for a file that dont have a global seqno "
        "field");
  }

@@ -6,9 +6,7 @@
 #ifndef ROCKSDB_LITE

 #include <functional>
-
 #include "db/db_test_util.h"
-#include "db/dbformat.h"
 #include "file/filename.h"
 #include "port/port.h"
 #include "port/stack_trace.h"
@@ -478,17 +476,17 @@ TEST_F(ExternalSSTFileTest, Basic) {
    }
    ASSERT_NE(db_->GetLatestSequenceNumber(), 0U);

-    // Key range of file5 (400 => 499) don't overlap with any keys in DB
+    // Key range of file5 (400 => 499) dont overlap with any keys in DB
    ASSERT_OK(DeprecatedAddFile({file5}));

    // This file has overlapping values with the existing data
    s = DeprecatedAddFile({file6});
    ASSERT_FALSE(s.ok()) << s.ToString();

-    // Key range of file7 (500 => 598) don't overlap with any keys in DB
+    // Key range of file7 (500 => 598) dont overlap with any keys in DB
    ASSERT_OK(DeprecatedAddFile({file7}));

-    // Key range of file7 (600 => 700) don't overlap with any keys in DB
+    // Key range of file7 (600 => 700) dont overlap with any keys in DB
    ASSERT_OK(DeprecatedAddFile({file8}));

    // Make sure values are correct before and after flush/compaction
@@ -1611,15 +1609,15 @@ TEST_F(ExternalSSTFileTest, AddExternalSstFileWithCustomCompartor) {
              generated_files[7]};
  ASSERT_NOK(DeprecatedAddFile(in_files));

-  // These 2 files don't overlap with each other
+  // These 2 files dont overlap with each other
  in_files = {generated_files[0], generated_files[2]};
  ASSERT_OK(DeprecatedAddFile(in_files));

-  // These 2 files don't overlap with each other but overlap with keys in DB
+  // These 2 files dont overlap with each other but overlap with keys in DB
  in_files = {generated_files[3], generated_files[7]};
  ASSERT_NOK(DeprecatedAddFile(in_files));

-  // Files don't overlap and don't overlap with DB key range
+  // Files dont overlap and dont overlap with DB key range
  in_files = {generated_files[4], generated_files[6], generated_files[8]};
  ASSERT_OK(DeprecatedAddFile(in_files));

@@ -1799,7 +1797,7 @@ TEST_P(ExternalSSTFileTest, IngestFileWithGlobalSeqnoAssignedLevel) {
      options, file_data, -1, true, write_global_seqno,
      verify_checksums_before_ingest, false, false, &true_data));

-  // This file don't overlap with anything in the DB, will go to L4
+  // This file dont overlap with anything in the DB, will go to L4
  ASSERT_EQ("0,0,0,0,1", FilesPerLevel());

  // Insert 80 -> 130 using AddFile
@@ -1824,7 +1822,7 @@ TEST_P(ExternalSSTFileTest, IngestFileWithGlobalSeqnoAssignedLevel) {
      options, file_data, -1, true, write_global_seqno,
      verify_checksums_before_ingest, false, false, &true_data));

-  // This file don't overlap with anything in the DB and fit in L4 as well
+  // This file dont overlap with anything in the DB and fit in L4 as well
  ASSERT_EQ("2,0,0,0,2", FilesPerLevel());

  // Insert 10 -> 40 using AddFile
@@ -2061,16 +2059,16 @@ TEST_F(ExternalSSTFileTest, FileWithCFInfo) {

  IngestExternalFileOptions ifo;

-  // SST CF don't match
+  // SST CF dont match
  ASSERT_NOK(db_->IngestExternalFile(handles_[0], {cf1_sst}, ifo));
-  // SST CF don't match
+  // SST CF dont match
  ASSERT_NOK(db_->IngestExternalFile(handles_[2], {cf1_sst}, ifo));
  // SST CF match
  ASSERT_OK(db_->IngestExternalFile(handles_[1], {cf1_sst}, ifo));

-  // SST CF don't match
+  // SST CF dont match
  ASSERT_NOK(db_->IngestExternalFile(handles_[1], {cf_default_sst}, ifo));
-  // SST CF don't match
+  // SST CF dont match
  ASSERT_NOK(db_->IngestExternalFile(handles_[2], {cf_default_sst}, ifo));
  // SST CF match
  ASSERT_OK(db_->IngestExternalFile(handles_[0], {cf_default_sst}, ifo));
@@ -2801,47 +2799,6 @@ TEST_P(ExternalSSTFileTest, IngestFilesTriggerFlushingWithTwoWriteQueue) {
  GenerateAndAddExternalFile(options, data);
 }

-TEST_P(ExternalSSTFileTest, DeltaEncodingWhileGlobalSeqnoPresents) {
-  Options options = CurrentOptions();
-  DestroyAndReopen(options);
-  constexpr size_t kValueSize = 8;
-  Random rnd(301);
-  std::string value(RandomString(&rnd, kValueSize));
-
-  // Write some key to make global seqno larger than zero
-  for (int i = 0; i < 10; i++) {
-    ASSERT_OK(Put("ab" + Key(i), value));
-  }
-  // Get a Snapshot to make RocksDB assign global seqno to ingested sst files.
-  auto snap = dbfull()->GetSnapshot();
-
-  std::string fname = sst_files_dir_ + "test_file";
-  rocksdb::SstFileWriter writer(EnvOptions(), options);
-  ASSERT_OK(writer.Open(fname));
-  std::string key1 = "ab";
-  std::string key2 = "ab";
-
-  // Make the prefix of key2 is same with key1 add zero seqno. The tail of every
-  // key is composed as (seqno << 8 | value_type), and here `1` represents
-  // ValueType::kTypeValue
-
-  PutFixed64(&key2, PackSequenceAndType(0, kTypeValue));
-  key2 += "cdefghijkl";
-
-  ASSERT_OK(writer.Put(key1, value));
-  ASSERT_OK(writer.Put(key2, value));
-
-  ExternalSstFileInfo info;
-  ASSERT_OK(writer.Finish(&info));
-
-  ASSERT_OK(dbfull()->IngestExternalFile({info.file_path},
-                                         IngestExternalFileOptions()));
-  dbfull()->ReleaseSnapshot(snap);
-  ASSERT_EQ(value, Get(key1));
-  // You will get error here
-  ASSERT_EQ(value, Get(key2));
-}
-
 INSTANTIATE_TEST_CASE_P(ExternalSSTFileTest, ExternalSSTFileTest,
                        testing::Values(std::make_tuple(false, false),
                                        std::make_tuple(false, true),
@@ -92,8 +92,8 @@ FlushJob::FlushJob(const std::string& dbname, ColumnFamilyData* cfd,
                   std::vector<SequenceNumber> existing_snapshots,
                   SequenceNumber earliest_write_conflict_snapshot,
                   SnapshotChecker* snapshot_checker, JobContext* job_context,
-                   LogBuffer* log_buffer, FSDirectory* db_directory,
-                   FSDirectory* output_file_directory,
+                   LogBuffer* log_buffer, Directory* db_directory,
+                   Directory* output_file_directory,
                   CompressionType output_compression, Statistics* stats,
                   EventLogger* event_logger, bool measure_io_stats,
                   const bool sync_output_directory, const bool write_manifest,
@@ -238,14 +238,10 @@ Status FlushJob::Run(LogsWithPrepTracker* prep_tracker,
  } else if (write_manifest_) {
    TEST_SYNC_POINT("FlushJob::InstallResults");
    // Replace immutable memtable with the generated Table
-    IOStatus tmp_io_s;
    s = cfd_->imm()->TryInstallMemtableFlushResults(
        cfd_, mutable_cf_options_, mems_, prep_tracker, versions_, db_mutex_,
        meta_.fd.GetNumber(), &job_context_->memtables_to_free, db_directory_,
-        log_buffer_, &committed_flush_jobs_info_, &tmp_io_s);
-    if (!tmp_io_s.ok()) {
-      io_status_ = tmp_io_s;
-    }
+        log_buffer_, &committed_flush_jobs_info_);
  }

  if (s.ok() && file_meta != nullptr) {
@@ -380,7 +376,6 @@ Status FlushJob::WriteLevel0Table() {
                                   ? current_time
                                   : meta_.oldest_ancester_time;

-      IOStatus io_s;
      s = BuildTable(
          dbname_, db_options_.env, db_options_.fs.get(), *cfd_->ioptions(),
          mutable_cf_options_, file_options_, cfd_->table_cache(), iter.get(),
@@ -389,14 +384,11 @@ Status FlushJob::WriteLevel0Table() {
          cfd_->GetName(), existing_snapshots_,
          earliest_write_conflict_snapshot_, snapshot_checker_,
          output_compression_, mutable_cf_options_.sample_for_compression,
-          mutable_cf_options_.compression_opts,
+          cfd_->ioptions()->compression_opts,
          mutable_cf_options_.paranoid_file_checks, cfd_->internal_stats(),
-          TableFileCreationReason::kFlush, &io_s, event_logger_,
-          job_context_->job_id, Env::IO_HIGH, &table_properties_, 0 /* level */,
+          TableFileCreationReason::kFlush, event_logger_, job_context_->job_id,
+          Env::IO_HIGH, &table_properties_, 0 /* level */,
          creation_time, oldest_key_time, write_hint, current_time);
-      if (!io_s.ok()) {
-        io_status_ = io_s;
-      }
      LogFlush(db_options_.info_log);
    }
    ROCKS_LOG_INFO(db_options_.info_log,
@@ -409,7 +401,7 @@ Status FlushJob::WriteLevel0Table() {
                   meta_.marked_for_compaction ? " (needs compaction)" : "");

    if (s.ok() && output_file_directory_ != nullptr && sync_output_directory_) {
-      s = output_file_directory_->Fsync(IOOptions(), nullptr);
+      s = output_file_directory_->Fsync();
    }
    TEST_SYNC_POINT_CALLBACK("FlushJob::WriteLevel0Table", &mems_);
    db_mutex_->Lock();
@@ -67,10 +67,9 @@ class FlushJob {
           std::vector<SequenceNumber> existing_snapshots,
           SequenceNumber earliest_write_conflict_snapshot,
           SnapshotChecker* snapshot_checker, JobContext* job_context,
-           LogBuffer* log_buffer, FSDirectory* db_directory,
-           FSDirectory* output_file_directory,
-           CompressionType output_compression, Statistics* stats,
-           EventLogger* event_logger, bool measure_io_stats,
+           LogBuffer* log_buffer, Directory* db_directory,
+           Directory* output_file_directory, CompressionType output_compression,
+           Statistics* stats, EventLogger* event_logger, bool measure_io_stats,
           const bool sync_output_directory, const bool write_manifest,
           Env::Priority thread_pri);

@@ -90,9 +89,6 @@ class FlushJob {
  }
 #endif  // !ROCKSDB_LITE

-  // Return the IO status
-  IOStatus io_status() const { return io_status_; }
-
 private:
  void ReportStartedFlush();
  void ReportFlushInputSize(const autovector<MemTable*>& mems);
@@ -121,8 +117,8 @@ class FlushJob {
  SnapshotChecker* snapshot_checker_;
  JobContext* job_context_;
  LogBuffer* log_buffer_;
-  FSDirectory* db_directory_;
-  FSDirectory* output_file_directory_;
+  Directory* db_directory_;
+  Directory* output_file_directory_;
  CompressionType output_compression_;
  Statistics* stats_;
  EventLogger* event_logger_;
@@ -157,7 +153,6 @@ class FlushJob {
  Version* base_;
  bool pick_memtable_called;
  Env::Priority thread_pri_;
-  IOStatus io_status_;
 };

 }  // namespace ROCKSDB_NAMESPACE
@@ -8,7 +8,7 @@
 #include <map>
 #include <string>

-#include "db/blob/blob_index.h"
+#include "db/blob_index.h"
 #include "db/column_family.h"
 #include "db/db_impl/db_impl.h"
 #include "db/flush_job.h"
@@ -108,7 +108,7 @@ class FlushJobTest : public testing::Test {
    }
    ASSERT_OK(s);
    // Make "CURRENT" file that points to the new manifest file.
-    s = SetCurrentFile(fs_.get(), dbname_, 1, nullptr);
+    s = SetCurrentFile(env_, dbname_, 1, nullptr);
  }

  Env* env_;
@@ -181,8 +181,8 @@ TEST_F(FlushJobTest, NonEmpty) {
  // Note: the first two blob references will not be considered when resolving
  // the oldest blob file referenced (the first one is inlined TTL, while the
  // second one is TTL and thus points to a TTL blob file).
-  constexpr std::array<uint64_t, 6> blob_file_numbers{{
-      kInvalidBlobFileNumber, 5, 103, 17, 102, 101}};
+  constexpr std::array<uint64_t, 6> blob_file_numbers{
+      kInvalidBlobFileNumber, 5, 103, 17, 102, 101};
  for (size_t i = 0; i < blob_file_numbers.size(); ++i) {
    std::string key(ToString(i + 10001));
    std::string blob_index;
@@ -36,8 +36,7 @@ class ForwardLevelIterator : public InternalIterator {
  ForwardLevelIterator(const ColumnFamilyData* const cfd,
                       const ReadOptions& read_options,
                       const std::vector<FileMetaData*>& files,
-                       const SliceTransform* prefix_extractor,
-                       bool allow_unprepared_value)
+                       const SliceTransform* prefix_extractor)
      : cfd_(cfd),
        read_options_(read_options),
        files_(files),
@@ -45,8 +44,7 @@ class ForwardLevelIterator : public InternalIterator {
        file_index_(std::numeric_limits<uint32_t>::max()),
        file_iter_(nullptr),
        pinned_iters_mgr_(nullptr),
-        prefix_extractor_(prefix_extractor),
-        allow_unprepared_value_(allow_unprepared_value) {}
+        prefix_extractor_(prefix_extractor) {}

  ~ForwardLevelIterator() override {
    // Reset current pointer
@@ -85,8 +83,7 @@ class ForwardLevelIterator : public InternalIterator {
        /*file_read_hist=*/nullptr, TableReaderCaller::kUserIterator,
        /*arena=*/nullptr, /*skip_filters=*/false, /*level=*/-1,
        /*smallest_compaction_key=*/nullptr,
-        /*largest_compaction_key=*/nullptr,
-        allow_unprepared_value_);
+        /*largest_compaction_key=*/nullptr);
    file_iter_->SetPinnedItersMgr(pinned_iters_mgr_);
    valid_ = false;
    if (!range_del_agg.IsEmpty()) {
@@ -174,16 +171,6 @@ class ForwardLevelIterator : public InternalIterator {
    }
    return Status::OK();
  }
-  bool PrepareValue() override {
-    assert(valid_);
-    if (file_iter_->PrepareValue()) {
-      return true;
-    }
-
-    assert(!file_iter_->Valid());
-    valid_ = false;
-    return false;
-  }
  bool IsKeyPinned() const override {
    return pinned_iters_mgr_ && pinned_iters_mgr_->PinningEnabled() &&
           file_iter_->IsKeyPinned();
@@ -210,19 +197,16 @@ class ForwardLevelIterator : public InternalIterator {
  InternalIterator* file_iter_;
  PinnedIteratorsManager* pinned_iters_mgr_;
  const SliceTransform* prefix_extractor_;
-  const bool allow_unprepared_value_;
 };

 ForwardIterator::ForwardIterator(DBImpl* db, const ReadOptions& read_options,
                                 ColumnFamilyData* cfd,
-                                 SuperVersion* current_sv,
-                                 bool allow_unprepared_value)
+                                 SuperVersion* current_sv)
    : db_(db),
      read_options_(read_options),
      cfd_(cfd),
      prefix_extractor_(current_sv->mutable_cf_options.prefix_extractor.get()),
      user_comparator_(cfd->user_comparator()),
-      allow_unprepared_value_(allow_unprepared_value),
      immutable_min_heap_(MinIterComparator(&cfd_->internal_comparator())),
      sv_(current_sv),
      mutable_iter_(nullptr),
@@ -576,22 +560,6 @@ Status ForwardIterator::status() const {
  return immutable_status_;
 }

-bool ForwardIterator::PrepareValue() {
-  assert(valid_);
-  if (current_->PrepareValue()) {
-    return true;
-  }
-
-  assert(!current_->Valid());
-  assert(!current_->status().ok());
-  assert(current_ != mutable_iter_); // memtable iterator can't fail
-  assert(immutable_status_.ok());
-
-  valid_ = false;
-  immutable_status_ = current_->status();
-  return false;
-}
-
 Status ForwardIterator::GetProperty(std::string prop_name, std::string* prop) {
  assert(prop != nullptr);
  if (prop_name == "rocksdb.iterator.super-version-number") {
@@ -687,8 +655,7 @@ void ForwardIterator::RebuildIterators(bool refresh_sv) {
        TableReaderCaller::kUserIterator, /*arena=*/nullptr,
        /*skip_filters=*/false, /*level=*/-1,
        /*smallest_compaction_key=*/nullptr,
-        /*largest_compaction_key=*/nullptr,
-        allow_unprepared_value_));
+        /*largest_compaction_key=*/nullptr));
  }
  BuildLevelIterators(vstorage);
  current_ = nullptr;
@@ -765,8 +732,7 @@ void ForwardIterator::RenewIterators() {
        TableReaderCaller::kUserIterator, /*arena=*/nullptr,
        /*skip_filters=*/false, /*level=*/-1,
        /*smallest_compaction_key=*/nullptr,
-        /*largest_compaction_key=*/nullptr,
-        allow_unprepared_value_));
+        /*largest_compaction_key=*/nullptr));
  }

  for (auto* f : l0_iters_) {
@@ -809,8 +775,7 @@ void ForwardIterator::BuildLevelIterators(const VersionStorageInfo* vstorage) {
    } else {
      level_iters_.push_back(new ForwardLevelIterator(
          cfd_, read_options_, level_files,
-          sv_->mutable_cf_options.prefix_extractor.get(),
-          allow_unprepared_value_));
+          sv_->mutable_cf_options.prefix_extractor.get()));
    }
  }
 }
@@ -831,8 +796,7 @@ void ForwardIterator::ResetIncompleteIterators() {
        TableReaderCaller::kUserIterator, /*arena=*/nullptr,
        /*skip_filters=*/false, /*level=*/-1,
        /*smallest_compaction_key=*/nullptr,
-        /*largest_compaction_key=*/nullptr,
-        allow_unprepared_value_);
+        /*largest_compaction_key=*/nullptr);
    l0_iters_[i]->SetPinnedItersMgr(pinned_iters_mgr_);
  }

@@ -52,8 +52,7 @@ typedef std::priority_queue<InternalIterator*, std::vector<InternalIterator*>,
 class ForwardIterator : public InternalIterator {
 public:
  ForwardIterator(DBImpl* db, const ReadOptions& read_options,
-                  ColumnFamilyData* cfd, SuperVersion* current_sv = nullptr,
-                  bool allow_unprepared_value = false);
+                  ColumnFamilyData* cfd, SuperVersion* current_sv = nullptr);
  virtual ~ForwardIterator();

  void SeekForPrev(const Slice& /*target*/) override {
@@ -76,7 +75,6 @@ class ForwardIterator : public InternalIterator {
  virtual Slice key() const override;
  virtual Slice value() const override;
  virtual Status status() const override;
-  virtual bool PrepareValue() override;
  virtual Status GetProperty(std::string prop_name, std::string* prop) override;
  virtual void SetPinnedItersMgr(
      PinnedIteratorsManager* pinned_iters_mgr) override;
@@ -122,7 +120,6 @@ class ForwardIterator : public InternalIterator {
  ColumnFamilyData* const cfd_;
  const SliceTransform* const prefix_extractor_;
  const Comparator* user_comparator_;
-  const bool allow_unprepared_value_;
  MinIterHeap immutable_min_heap_;

  SuperVersion* sv_;
Author	SHA1	Message	Date
Peter Dillinger	dc58bf9f04	HISTORY.md update for bzip upgrade (#6767 ) Summary: See https://github.com/facebook/rocksdb/issues/6714 and https://github.com/facebook/rocksdb/issues/6703 Pull Request resolved: https://github.com/facebook/rocksdb/pull/6767 Reviewed By: riversand963 Differential Revision: D21283307 Pulled By: pdillinger fbshipit-source-id: 8463bec725669d13846c728ad4b5bde43f9a84f8	2020-04-28 13:50:06 -07:00
Adam Retter	27e593fbe1	Update RocksJava static version of bzip2 (#6714 ) Summary: Updates the version of bzip2 used for RocksJava static builds. Please, can we also get this cherry-picked to: 1. 6.7.fb 2. 6.8.fb 3. 6.9.fb Pull Request resolved: https://github.com/facebook/rocksdb/pull/6714 Reviewed By: cheng-chang Differential Revision: D21067233 Pulled By: pdillinger fbshipit-source-id: 8164b7eb99c5ca7b2021ab8c371ba9ded4cb4f7e	2020-04-16 16:01:15 -07:00
Peter Dillinger	d7b6149563	Use an Amazon S3 bucket for downloading deps (#6526 ) Summary: After we had a lot of failures with maven.org downloads, we wanted an alternative location for downloading binary dependencies. Hosting them through github would have been good in terms of organizational and network dependencies, but that approach seems to be awkward (fake releases, so would need a 'rocksdb-deps' repo) and strangely complicated for Facebook policy on open source repositories. This commit moves the downloads (that are not officially hosted by others on github) from my personal rocksdb fork to an S3 bucket owned by the Facebook RocksDB AWS account. Facebook employees can access this through an internal tool, and we should be able to grant permission to outside collaborators. Assuming this works out, I will back-port to older branches to stabilize their CI testing as well. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6526 Test Plan: CI Differential Revision: D20430130 Pulled By: pdillinger fbshipit-source-id: df52394a65e0a57942db3039bdaade8a4d520cb2	2020-04-16 16:01:08 -07:00
Adam Retter	6731fef82b	Update to latest Snappy to fix compilation issue on latest MacOS XCode (#6496 ) Summary: * macOS version: 10.15.2 (Catalina) * XCode/Clang version: Apple clang version 11.0.0 (clang-1100.0.33.16) Before this bugfix the error generated is: ``` In file included from ./util/compression.h:23: ./snappy-1.1.7/snappy.h:76:59: error: unknown type name 'string'; did you mean 'std::string'? size_t Compress(const char* input, size_t input_length, string* output); ^~~~~~ std::string /Library/Developer/CommandLineTools/usr/bin/../include/c++/v1/iosfwd:211:65: note: 'std::string' declared here typedef basic_string<char, char_traits<char>, allocator<char> > string; ^ In file included from db/builder.cc:10: In file included from ./db/builder.h:12: In file included from ./db/range_tombstone_fragmenter.h:15: In file included from ./db/pinned_iterators_manager.h:12: In file included from ./table/internal_iterator.h:13: In file included from ./table/format.h:25: In file included from ./options/cf_options.h:14: In file included from ./util/compression.h:23: ./snappy-1.1.7/snappy.h:85:19: error: unknown type name 'string'; did you mean 'std::string'? string* uncompressed); ^~~~~~ std::string /Library/Developer/CommandLineTools/usr/bin/../include/c++/v1/iosfwd:211:65: note: 'std::string' declared here typedef basic_string<char, char_traits<char>, allocator<char> > string; ^ 2 errors generated. make: *** [jls/db/builder.o] Error 1 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/6496 Differential Revision: D20389254 Pulled By: pdillinger fbshipit-source-id: 2864245c8d0dba7b2ab81294241a62f2adf02e20	2020-04-15 10:05:11 -07:00
sdong	3482d4dc2a	cmake: add option WITH_CORE_TOOLS to exclude tools except ldb and sst_dump (#6506 ) Summary: ldb and sst_dump are most important tools and they don't dependend on gflags. In cmake, we don't have an way to only build these two tools and exclude other tools. This is inconvenient if the environment has a problem with gflags. Add such an option WITH_CORE_TOOLS. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6506 Test Plan: cmake and build with WITH_TOOLS and without. Differential Revision: D20473029 fbshipit-source-id: 3d730fd14bbae6eeeae7f9cc9aec50a4e488ad72	2020-04-15 10:04:56 -07:00
Yanqin Jin	d75da26396	Update HISTORY and version	2020-03-30 21:44:30 -07:00
Yanqin Jin	00894a289f	Use flush time for the props.creation_time for FIFO compaction (#6612 ) Summary: For FIFO compaction, we use flush time instead of oldest key time as the creation time. This is to prevent FIFO compaction dropping files whose oldest key time is older than TTL but which has newer keys than TTL. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6612 Test Plan: make check Reviewed By: siying Differential Revision: D20748217 Pulled By: riversand963 fbshipit-source-id: 3f7b00a847020760537cdddd12f6fe039e5bc663	2020-03-30 21:10:29 -07:00
sdong	bba5e7bc21	Fix data race of GetCreationTimeOfOldestFile() (#6473 ) Summary: When DBImpl::GetCreationTimeOfOldestFile() calls Version::GetCreationTimeOfOldestFile(), the version is not directly or indirectly referenced, so an event like compaction can race with the operation and cause DBImpl::GetCreationTimeOfOldestFile() to access delocated data. This was caught by an ASAN run: ==268==ERROR: AddressSanitizer: heap-use-after-free on address 0x612000b7d198 at pc 0x000018332913 bp 0x7f391510d310 sp 0x7f391510d308 READ of size 8 at 0x612000b7d198 thread T845 (store_load-33) SCARINESS: 51 (8-byte-read-heap-use-after-free) #0 0x18332912 in rocksdb::Version::GetCreationTimeOfOldestFile(unsigned long) rocksdb/src/db/version_set.cc:1488 https://github.com/facebook/rocksdb/issues/1 0x1803ddaa in rocksdb::DBImpl::GetCreationTimeOfOldestFile(unsigned long) rocksdb/src/db/db_impl/db_impl.cc:4499 https://github.com/facebook/rocksdb/issues/2 0xe24ca09 in rocksdb::StackableDB::GetCreationTimeOfOldestFile(unsigned long) rocksdb/utilities/stackable_db.h:392 ...... 0x612000b7d198 is located 216 bytes inside of 296-byte region [0x612000b7d0c0,0x612000b7d1e8) freed by thread T28 here: ...... https://github.com/facebook/rocksdb/issues/5 0x1832c73f in std::vector<rocksdb::FileMetaData, std::allocator<rocksdb::FileMetaData> >::~vector() third-party-buck/platform007/build/libgcc/include/c++/trunk/bits/stl_vector.h:435 https://github.com/facebook/rocksdb/issues/6 0x1832c73f in rocksdb::VersionStorageInfo::~VersionStorageInfo() rocksdb/src/db/version_set.cc:734 https://github.com/facebook/rocksdb/issues/7 0x1832cf42 in rocksdb::Version::~Version() rocksdb/src/db/version_set.cc:758 https://github.com/facebook/rocksdb/issues/8 0x9d1bb5 in rocksdb::Version::Unref() rocksdb/src/db/version_set.cc:2869 https://github.com/facebook/rocksdb/issues/9 0x183e7631 in rocksdb::Compaction::~Compaction() rocksdb/src/db/compaction/compaction.cc:275 https://github.com/facebook/rocksdb/issues/10 0x9e6de6 in std::default_delete<rocksdb::Compaction>::operator()(rocksdb::Compaction) const third-party-buck/platform007/build/libgcc/include/c++/trunk/bits/unique_ptr.h:78 https://github.com/facebook/rocksdb/issues/11 0x9e6de6 in std::unique_ptr<rocksdb::Compaction, std::default_delete<rocksdb::Compaction> >::reset(rocksdb::Compaction) third-party-buck/platform007/build/libgcc/include/c++/trunk/bits/unique_ptr.h:376 https://github.com/facebook/rocksdb/issues/12 0x9e6de6 in rocksdb::DBImpl::BackgroundCompaction(bool, rocksdb::JobContext, rocksdb::LogBuffer, rocksdb::DBImpl::PrepickedCompaction, rocksdb::Env::Priority) rocksdb/src/db/db_impl/db_impl_compaction_flush.cc:2826 https://github.com/facebook/rocksdb/issues/13 0x9ac3b8 in rocksdb::DBImpl::BackgroundCallCompaction(rocksdb::DBImpl::PrepickedCompaction, rocksdb::Env::Priority) rocksdb/src/db/db_impl/db_impl_compaction_flush.cc:2320 https://github.com/facebook/rocksdb/issues/14 0x9abff7 in rocksdb::DBImpl::BGWorkCompaction(void*) rocksdb/src/db/db_impl/db_impl_compaction_flush.cc:2096 ...... Fix the issue by reference the super version and use the referenced version from it. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6473 Test Plan: Run ASAN for all existing tests. Differential Revision: D20196416 fbshipit-source-id: 5f4a7918110fc7b8dd7841932d376bc9d1e59d6f	2020-03-03 11:12:05 -08:00
sdong	cfaaaaddef	Buck config: Re-enable liburing under Linux (#6451 ) Summary: The known bug of liburing has been fixed. Now we can re-enable liburing under Linux Pull Request resolved: https://github.com/facebook/rocksdb/pull/6451 Test Plan: Watch internal CI Differential Revision: D20079009 fbshipit-source-id: 04a6f53a900ff721f9a62a188cf906771b5d68d2	2020-02-24 18:24:51 -08:00
Cheng Chang	5a868c18cb	Update release version to 6.8 (#6450 ) Summary: Update release version to 6.8 Pull Request resolved: https://github.com/facebook/rocksdb/pull/6450 Test Plan: no code change Differential Revision: D20071889 Pulled By: cheng-chang fbshipit-source-id: 91450aae09b201926469ff32f59ed436366f3b74	2020-02-24 12:17:36 -08:00