Bump up version to 6.5.3

Summary: Pull Request resolved: https://github.com/facebook/rocksdb/pull/6194

Differential Revision: D19125292

Pulled By: ltamasi

fbshipit-source-id: d41aca2755ec4bec07feedd6b561e8d18606a931

.circleci/config.yml

@@ -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

.github/workflows/sanity_check.yml

@@ -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

.gitignore

@@ -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
@@ -53,8 +52,6 @@ trace_analyzer
 trace_analyzer_test
 block_cache_trace_analyzer
 .DS_Store
-.vs
-.vscode
 
 java/out
 java/target
@@ -82,6 +79,3 @@ tp2/
 fbcode/
 fbcode
 buckifier/*.pyc
-buckifier/__pycache__
-
-compile_commands.json

.travis.yml

@@ -3,39 +3,28 @@ language: cpp
 os:
   - linux
   - osx
-arch:
-  - amd64
-  - arm64
-  - ppc64le
 compiler:
   - clang
   - gcc
-osx_image: xcode9.4
+osx_image: xcode8.3
+jdk:
+  - openjdk7
 cache:
   - ccache
+  - apt
 
 addons:
   apt:
     sources:
       - ubuntu-toolchain-r-test
     packages:
-      - libgflags-dev
+      - curl
+      - g++-8
       - libbz2-dev
-      - liblz4-dev
+      - libgflags-dev
       - libsnappy-dev
-      - liblzma-dev  # xv
-      - libzstd-dev
+      - mingw-w64
       - zlib1g-dev
-  homebrew:
-    update: true
-    packages:
-      - ccache
-      - gflags
-      - lz4
-      - snappy
-      - xz
-      - zstd
-
 env:
   - TEST_GROUP=platform_dependent # 16-18 minutes
   - TEST_GROUP=1 # 33-35 minutes
@@ -50,193 +39,41 @@ 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
 
+# https://docs.travis-ci.com/user/caching/#ccache-cache
 install:
   - if [ "${TRAVIS_OS_NAME}" == osx ]; then
+      brew install ccache zstd lz4 snappy xz;
       PATH=$PATH:/usr/local/opt/ccache/libexec;
     fi
   - if [ "${JOB_NAME}" == cmake-gcc8 ]; then
-      sudo apt-get install -y g++-8;
       CC=gcc-8 && CXX=g++-8;
     fi
-  - if [ "${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:$PATH;
+      mkdir cmake-dist && curl -sfSL https://github.com/Kitware/CMake/releases/download/v3.14.5/cmake-3.14.5-Linux-x86_64.tar.gz | tar --strip-components=1 -C cmake-dist -xz && export PATH=$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:
@@ -245,20 +82,20 @@ 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)
       OPT=-DTRAVIS V=1 ROCKSDBTESTS_END=db_block_cache_test make -j4 all_but_some_tests check_some
       ;;
     1)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=db_iter_test make -j4 check_some
+      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=full_filter_block_test make -j4 check_some
       ;;
     2)
-      OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" V=1 make -j4 tools && OPT="-DTRAVIS -DROCKSDB_NAMESPACE=alternative_rocksdb_ns" V=1 ROCKSDBTESTS_START=db_iter_test ROCKSDBTESTS_END=options_file_test make -j4 check_some
+      OPT=-DTRAVIS V=1 make -j4 tools && OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=full_filter_block_test ROCKSDBTESTS_END=write_batch_with_index_test make -j4 check_some
       ;;
     3)
-      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=options_file_test ROCKSDBTESTS_END=write_prepared_transaction_test make -j4 check_some
+      OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_batch_with_index_test ROCKSDBTESTS_END=write_prepared_transaction_test make -j4 check_some
       ;;
     4)
       OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=write_prepared_transaction_test make -j4 check_some
@@ -276,18 +113,14 @@ script:
       ;;
     cmake-mingw)
       sudo update-alternatives --set x86_64-w64-mingw32-g++ /usr/bin/x86_64-w64-mingw32-g++-posix;
-      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
+      mkdir build && cd build && cmake -DJNI=1 .. -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:
     email:
       - leveldb@fb.com
+    webhooks:
+      - https://buildtimetrend.herokuapp.com/travis

CMakeLists.txt

@@ -14,7 +14,7 @@
 #        cd build
 # 3. Run cmake to generate project files for Windows, add more options to enable required third-party libraries.
 #    See thirdparty.inc for more information.
-#        sample command: cmake -G "Visual Studio 15 Win64" -DCMAKE_BUILD_TYPE=Release -DWITH_GFLAGS=1 -DWITH_SNAPPY=1 -DWITH_JEMALLOC=1 -DWITH_JNI=1 ..
+#        sample command: cmake -G "Visual Studio 15 Win64" -DWITH_GFLAGS=1 -DWITH_SNAPPY=1 -DWITH_JEMALLOC=1 -DWITH_JNI=1 ..
 # 4. Then build the project in debug mode (you may want to add /m[:<N>] flag to run msbuild in <N> parallel threads
 #                                          or simply /m to use all avail cores)
 #        msbuild rocksdb.sln
@@ -45,16 +45,6 @@ if(POLICY CMP0042)
   cmake_policy(SET CMP0042 NEW)
 endif()
 
-if(NOT CMAKE_BUILD_TYPE)
-  if(EXISTS "${CMAKE_SOURCE_DIR}/.git")
-    set(default_build_type "Debug")
-  else()
-    set(default_build_type "RelWithDebInfo")
-  endif()
-  set(CMAKE_BUILD_TYPE "${default_build_type}" CACHE STRING
-    "Default BUILD_TYPE is ${default_build_type}" FORCE)
-endif()
-
 find_program(CCACHE_FOUND ccache)
 if(CCACHE_FOUND)
   set_property(GLOBAL PROPERTY RULE_LAUNCH_COMPILE ccache)
@@ -72,26 +62,15 @@ if (WITH_WINDOWS_UTF8_FILENAMES)
 endif()
 # third-party/folly is only validated to work on Linux and Windows for now.
 # So only turn it on there by default.
-if(CMAKE_SYSTEM_NAME MATCHES "Linux|Windows")
-  if(MSVC AND MSVC_VERSION LESS 1910)
-    # Folly does not compile with MSVC older than VS2017
-    option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
-  else()
-    option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
-  endif()
+if(CMAKE_SYSTEM_NAME MATCHES "Linux" OR CMAKE_SYSTEM_NAME MATCHES "Windows")
+  option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
 else()
   option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
 endif()
-
-if( NOT DEFINED CMAKE_CXX_STANDARD )
-  set(CMAKE_CXX_STANDARD 11)
-endif()
-
-include(CMakeDependentOption)
-CMAKE_DEPENDENT_OPTION(WITH_GFLAGS "build with GFlags" ON
-  "NOT MSVC;NOT MINGW" OFF)
-
 if(MSVC)
+  # Defaults currently different for GFLAGS.
+  #  We will address find_package work a little later
+  option(WITH_GFLAGS "build with GFlags" OFF)
   option(WITH_XPRESS "build with windows built in compression" OFF)
   include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
 else()
@@ -108,11 +87,14 @@ else()
   endif()
 
   # No config file for this
+  option(WITH_GFLAGS "build with GFlags" ON)
   if(WITH_GFLAGS)
-    find_package(gflags REQUIRED)
-    add_definitions(-DGFLAGS=1)
-    include_directories(${gflags_INCLUDE_DIR})
-    list(APPEND THIRDPARTY_LIBS gflags::gflags)
+    find_package(gflags)
+    if(gflags_FOUND)
+      add_definitions(-DGFLAGS=1)
+      include_directories(${gflags_INCLUDE_DIR})
+      list(APPEND THIRDPARTY_LIBS ${gflags_LIBRARIES})
+    endif()
   endif()
 
   if(WITH_SNAPPY)
@@ -192,9 +174,10 @@ else()
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall")
   set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers -Wno-strict-aliasing")
   if(MINGW)
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format -fno-asynchronous-unwind-tables")
+    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format")
     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 +189,16 @@ 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 +221,7 @@ 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 +231,6 @@ include(CheckCXXSourceCompiles)
 if(NOT MSVC)
   set(CMAKE_REQUIRED_FLAGS "-msse4.2 -mpclmul")
 endif()
-
 CHECK_CXX_SOURCE_COMPILES("
 #include <cstdint>
 #include <nmmintrin.h>
@@ -390,15 +363,7 @@ 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 +467,6 @@ 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 +478,9 @@ 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 +534,6 @@ 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
@@ -590,25 +544,17 @@ set(SOURCES
         env/env_chroot.cc
         env/env_encryption.cc
         env/env_hdfs.cc
-        env/file_system.cc
         env/mock_env.cc
         file/delete_scheduler.cc
-        file/file_prefetch_buffer.cc
         file/file_util.cc
         file/filename.cc
-        file/random_access_file_reader.cc
-        file/read_write_util.cc
-        file/readahead_raf.cc
-        file/sequence_file_reader.cc
         file/sst_file_manager_impl.cc
-        file/writable_file_writer.cc
         logging/auto_roll_logger.cc
         logging/event_logger.cc
         logging/log_buffer.cc
         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
@@ -633,32 +579,23 @@ 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
         table/block_based/filter_block_reader_common.cc
-        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
@@ -685,6 +622,7 @@ set(SOURCES
         test_util/testutil.cc
         test_util/transaction_test_util.cc
         tools/block_cache_analyzer/block_cache_trace_analyzer.cc
+        tools/db_bench_tool.cc
         tools/dump/db_dump_tool.cc
         tools/ldb_cmd.cc
         tools/ldb_tool.cc
@@ -692,6 +630,7 @@ set(SOURCES
         tools/trace_analyzer_tool.cc
         trace_replay/trace_replay.cc
         trace_replay/block_cache_tracer.cc
+        util/bloom.cc
         util/coding.cc
         util/compaction_job_stats_impl.cc
         util/comparator.cc
@@ -699,12 +638,13 @@ set(SOURCES
         util/concurrent_task_limiter_impl.cc
         util/crc32c.cc
         util/dynamic_bloom.cc
+        util/file_reader_writer.cc
+        util/filter_policy.cc
         util/hash.cc
         util/murmurhash.cc
         util/random.cc
         util/rate_limiter.cc
         util/slice.cc
-        util/file_checksum_helper.cc
         util/status.cc
         util/string_util.cc
         util/thread_local.cc
@@ -773,11 +713,11 @@ 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
@@ -807,7 +747,6 @@ else()
   list(APPEND SOURCES
     port/port_posix.cc
     env/env_posix.cc
-    env/fs_posix.cc
     env/io_posix.cc)
 endif()
 
@@ -822,8 +761,7 @@ endif()
 
 set(ROCKSDB_STATIC_LIB rocksdb${ARTIFACT_SUFFIX})
 set(ROCKSDB_SHARED_LIB rocksdb-shared${ARTIFACT_SUFFIX})
-
-option(ROCKSDB_BUILD_SHARED "Build shared versions of the RocksDB libraries" ON)
+set(ROCKSDB_IMPORT_LIB ${ROCKSDB_SHARED_LIB})
 
 option(WITH_LIBRADOS "Build with librados" OFF)
 if(WITH_LIBRADOS)
@@ -833,44 +771,41 @@ if(WITH_LIBRADOS)
 endif()
 
 if(WIN32)
-  set(SYSTEM_LIBS ${SYSTEM_LIBS} shlwapi.lib rpcrt4.lib)
+  set(SYSTEM_LIBS ${SYSTEM_LIBS} Shlwapi.lib Rpcrt4.lib)
+  set(LIBS ${ROCKSDB_STATIC_LIB} ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
 else()
   set(SYSTEM_LIBS ${CMAKE_THREAD_LIBS_INIT})
+  set(LIBS ${ROCKSDB_SHARED_LIB} ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
+
+  add_library(${ROCKSDB_SHARED_LIB} SHARED ${SOURCES})
+  target_link_libraries(${ROCKSDB_SHARED_LIB}
+    ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
+  set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
+                        LINKER_LANGUAGE CXX
+                        VERSION ${rocksdb_VERSION}
+                        SOVERSION ${rocksdb_VERSION_MAJOR}
+                        CXX_STANDARD 11
+                        OUTPUT_NAME "rocksdb")
 endif()
 
 add_library(${ROCKSDB_STATIC_LIB} STATIC ${SOURCES})
 target_link_libraries(${ROCKSDB_STATIC_LIB}
   ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
 
-if(ROCKSDB_BUILD_SHARED)
-  add_library(${ROCKSDB_SHARED_LIB} SHARED ${SOURCES})
-  target_link_libraries(${ROCKSDB_SHARED_LIB}
+if(WIN32)
+  add_library(${ROCKSDB_IMPORT_LIB} SHARED ${SOURCES})
+  target_link_libraries(${ROCKSDB_IMPORT_LIB}
     ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
-
-  if(WIN32)
-    set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
-      COMPILE_DEFINITIONS "ROCKSDB_DLL;ROCKSDB_LIBRARY_EXPORTS")
-    if(MSVC)
-      set_target_properties(${ROCKSDB_STATIC_LIB} PROPERTIES
-        COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_STATIC_LIB}.pdb")
-      set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
-        COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_SHARED_LIB}.pdb")
-    endif()
-  else()
-    set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
-                          LINKER_LANGUAGE CXX
-                          VERSION ${rocksdb_VERSION}
-                          SOVERSION ${rocksdb_VERSION_MAJOR}
-                          OUTPUT_NAME "rocksdb")
+  set_target_properties(${ROCKSDB_IMPORT_LIB} PROPERTIES
+    COMPILE_DEFINITIONS "ROCKSDB_DLL;ROCKSDB_LIBRARY_EXPORTS")
+  if(MSVC)
+    set_target_properties(${ROCKSDB_STATIC_LIB} PROPERTIES
+      COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_STATIC_LIB}.pdb")
+    set_target_properties(${ROCKSDB_IMPORT_LIB} PROPERTIES
+      COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_IMPORT_LIB}.pdb")
   endif()
 endif()
 
-if(ROCKSDB_BUILD_SHARED AND NOT WIN32)
-  set(ROCKSDB_LIB ${ROCKSDB_SHARED_LIB})
-else()
-  set(ROCKSDB_LIB ${ROCKSDB_STATIC_LIB})
-endif()
-
 option(WITH_JNI "build with JNI" OFF)
 if(WITH_JNI OR JNI)
   message(STATUS "JNI library is enabled")
@@ -917,17 +852,15 @@ if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
     INCLUDES DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
   )
 
-  if(ROCKSDB_BUILD_SHARED)
-    install(
-      TARGETS ${ROCKSDB_SHARED_LIB}
-      EXPORT RocksDBTargets
-      COMPONENT runtime
-      ARCHIVE DESTINATION "${CMAKE_INSTALL_LIBDIR}"
-      RUNTIME DESTINATION "${CMAKE_INSTALL_BINDIR}"
-      LIBRARY DESTINATION "${CMAKE_INSTALL_LIBDIR}"
-      INCLUDES DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
-    )
-  endif()
+  install(
+    TARGETS ${ROCKSDB_SHARED_LIB}
+    EXPORT RocksDBTargets
+    COMPONENT runtime
+    ARCHIVE DESTINATION "${CMAKE_INSTALL_LIBDIR}"
+    RUNTIME DESTINATION "${CMAKE_INSTALL_BINDIR}"
+    LIBRARY DESTINATION "${CMAKE_INSTALL_LIBDIR}"
+    INCLUDES DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
+  )
 
   install(
     EXPORT RocksDBTargets
@@ -945,21 +878,12 @@ if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
   )
 endif()
 
-# Tests are excluded from Release builds
-CMAKE_DEPENDENT_OPTION(WITH_TESTS "build with tests" ON
-  "CMAKE_BUILD_TYPE STREQUAL Debug" OFF)
+option(WITH_TESTS "build with tests" ON)
 if(WITH_TESTS)
   add_subdirectory(third-party/gtest-1.8.1/fused-src/gtest)
-  add_library(testharness STATIC
-  test_util/testharness.cc)
-  target_link_libraries(testharness gtest)
-
   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 +894,7 @@ 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 +920,12 @@ 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 +956,12 @@ 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 +982,6 @@ 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
@@ -1073,22 +991,17 @@ if(WITH_TESTS)
         util/bloom_test.cc
         util/coding_test.cc
         util/crc32c_test.cc
-        util/defer_test.cc
         util/dynamic_bloom_test.cc
         util/file_reader_writer_test.cc
         util/filelock_test.cc
         util/hash_test.cc
         util/heap_test.cc
-        util/random_test.cc
         util/rate_limiter_test.cc
         util/repeatable_thread_test.cc
-        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 +1021,6 @@ 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
@@ -1122,19 +1034,35 @@ if(WITH_TESTS)
     list(APPEND TESTS third-party/folly/folly/synchronization/test/DistributedMutexTest.cpp)
   endif()
 
+  set(BENCHMARKS
+    cache/cache_bench.cc
+    memtable/memtablerep_bench.cc
+    db/range_del_aggregator_bench.cc
+    tools/db_bench.cc
+    table/table_reader_bench.cc
+    utilities/persistent_cache/hash_table_bench.cc)
+  add_library(testharness OBJECT test_util/testharness.cc)
+  foreach(sourcefile ${BENCHMARKS})
+    get_filename_component(exename ${sourcefile} NAME_WE)
+    add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile}
+      $<TARGET_OBJECTS:testharness>)
+    target_link_libraries(${exename}${ARTIFACT_SUFFIX} gtest ${LIBS})
+  endforeach(sourcefile ${BENCHMARKS})
+
+  # For test util library that is build only in DEBUG mode
+  # and linked to tests. Add test only code that is not #ifdefed for Release here.
   set(TESTUTIL_SOURCE
       db/db_test_util.cc
       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
   )
+  # test utilities are only build in debug
   enable_testing()
   add_custom_target(check COMMAND ${CMAKE_CTEST_COMMAND})
   set(TESTUTILLIB testutillib${ARTIFACT_SUFFIX})
   add_library(${TESTUTILLIB} STATIC ${TESTUTIL_SOURCE})
-  target_link_libraries(${TESTUTILLIB} ${ROCKSDB_LIB})
   if(MSVC)
     set_target_properties(${TESTUTILLIB} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/testutillib${ARTIFACT_SUFFIX}.pdb")
   endif()
@@ -1142,94 +1070,48 @@ 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})
+  # Tests are excluded from Release builds
+  set(TEST_EXES ${TESTS})
+
+  foreach(sourcefile ${TEST_EXES})
       get_filename_component(exename ${sourcefile} NAME_WE)
-      add_executable(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} ${sourcefile})
+      add_executable(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} ${sourcefile}
+        $<TARGET_OBJECTS:testharness>)
       set_target_properties(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX}
         PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
         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 ${ROCKSDB_LIB})
+        )
+      target_link_libraries(${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} gtest ${LIBS})
       if(NOT "${exename}" MATCHES "db_sanity_test")
         add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
         add_dependencies(check ${CMAKE_PROJECT_NAME}_${exename}${ARTIFACT_SUFFIX})
       endif()
-  endforeach(sourcefile ${TESTS})
+  endforeach(sourcefile ${TEST_EXES})
 
-  if(WIN32)
-    # C executables must link to a shared object
-    if(ROCKSDB_BUILD_SHARED)
-      set(ROCKSDB_LIB_FOR_C ${ROCKSDB_SHARED_LIB})
-    else()
-      set(ROCKSDB_LIB_FOR_C OFF)
-    endif()
-  else()
-    set(ROCKSDB_LIB_FOR_C ${ROCKSDB_LIB})
-  endif()
+  # C executables must link to a shared object
+  set(C_TESTS db/c_test.c)
+  set(C_TEST_EXES ${C_TESTS})
 
-  if(ROCKSDB_LIB_FOR_C)
-    set(C_TESTS db/c_test.c)
-    # C executables must link to a shared object
-    add_executable(c_test db/c_test.c)
-    target_link_libraries(c_test ${ROCKSDB_SHARED_LIB} testharness)
-    add_test(NAME c_test COMMAND c_test${ARTIFACT_SUFFIX})
-    add_dependencies(check c_test)
-  endif()
+  foreach(sourcefile ${C_TEST_EXES})
+      string(REPLACE ".c" "" exename ${sourcefile})
+      string(REGEX REPLACE "^((.+)/)+" "" exename ${exename})
+      add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile})
+      set_target_properties(${exename}${ARTIFACT_SUFFIX}
+        PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
+        EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
+        EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
+        )
+      target_link_libraries(${exename}${ARTIFACT_SUFFIX} ${ROCKSDB_IMPORT_LIB} testutillib${ARTIFACT_SUFFIX})
+      add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
+      add_dependencies(check ${exename}${ARTIFACT_SUFFIX})
+  endforeach(sourcefile ${C_TEST_EXES})
 endif()
 
-option(WITH_BENCHMARK_TOOLS "build with benchmarks" ON)
-if(WITH_BENCHMARK_TOOLS)
-  add_executable(db_bench
-    tools/db_bench.cc
-    tools/db_bench_tool.cc)
-  target_link_libraries(db_bench
-    ${ROCKSDB_LIB})
-
-  add_executable(cache_bench
-    cache/cache_bench.cc)
-  target_link_libraries(cache_bench
-    ${ROCKSDB_LIB})
-
-  add_executable(memtablerep_bench
-    memtable/memtablerep_bench.cc)
-  target_link_libraries(memtablerep_bench
-    ${ROCKSDB_LIB})
-
-  add_executable(range_del_aggregator_bench
-    db/range_del_aggregator_bench.cc)
-  target_link_libraries(range_del_aggregator_bench
-    ${ROCKSDB_LIB})
-
-  add_executable(table_reader_bench
-    table/table_reader_bench.cc)
-  target_link_libraries(table_reader_bench
-    ${ROCKSDB_LIB} testharness)
-
-  add_executable(filter_bench
-    util/filter_bench.cc)
-  target_link_libraries(filter_bench
-    ${ROCKSDB_LIB})
-
-  add_executable(hash_table_bench
-    utilities/persistent_cache/hash_table_bench.cc)
-  target_link_libraries(hash_table_bench
-    ${ROCKSDB_LIB})
-endif()
-
-option(WITH_CORE_TOOLS "build with ldb and sst_dump" ON)
 option(WITH_TOOLS "build with tools" ON)
-if(WITH_CORE_TOOLS OR WITH_TOOLS)
-  add_subdirectory(tools)
-  add_custom_target(core_tools
-    DEPENDS ${core_tool_deps})
-endif()
-
 if(WITH_TOOLS)
-  add_subdirectory(db_stress_tool)
-  add_custom_target(tools
-    DEPENDS ${tool_deps})
+  add_subdirectory(tools)
 endif()

HISTORY.md

@@ -1,194 +1,11 @@
 # Rocksdb Change Log
-## Unreleased
+## 6.5.3 (1/10/2020)
 ### 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)
-### 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.
-
-## 6.8.0 (02/24/2020)
-### Java API Changes
-* Major breaking changes to Java comparators, toward standardizing on ByteBuffer for performant, locale-neutral operations on keys (#6252).
-* Added overloads of common API methods using direct ByteBuffers for keys and values (#2283).
-
-### Bug Fixes
-* Fix incorrect results while block-based table uses kHashSearch, together with Prev()/SeekForPrev().
-* Fix a bug that prevents opening a DB after two consecutive crash with TransactionDB, where the first crash recovers from a corrupted WAL with kPointInTimeRecovery but the second cannot.
-* Fixed issue #6316 that can cause a corruption of the MANIFEST file in the middle when writing to it fails due to no disk space.
-* Add DBOptions::skip_checking_sst_file_sizes_on_db_open. It disables potentially expensive checking of all sst file sizes in DB::Open().
-* BlobDB now ignores trivially moved files when updating the mapping between blob files and SSTs. This should mitigate issue #6338 where out of order flush/compaction notifications could trigger an assertion with the earlier code.
-* Batched MultiGet() ignores IO errors while reading data blocks, causing it to potentially continue looking for a key and returning stale results.
-* `WriteBatchWithIndex::DeleteRange` returns `Status::NotSupported`. Previously it returned success even though reads on the batch did not account for range tombstones. The corresponding language bindings now cannot be used. In C, that includes `rocksdb_writebatch_wi_delete_range`, `rocksdb_writebatch_wi_delete_range_cf`, `rocksdb_writebatch_wi_delete_rangev`, and `rocksdb_writebatch_wi_delete_rangev_cf`. In Java, that includes `WriteBatchWithIndex::deleteRange`.
-* Assign new MANIFEST file number when caller tries to create a new MANIFEST by calling LogAndApply(..., new_descriptor_log=true). This bug can cause MANIFEST being overwritten during recovery if options.write_dbid_to_manifest = true and there are WAL file(s).
-
-### Performance Improvements
-* Perfom readahead when reading from option files. Inside DB, options.log_readahead_size will be used as the readahead size. In other cases, a default 512KB is used.
-
-### Public API Change
-* The BlobDB garbage collector now emits the statistics `BLOB_DB_GC_NUM_FILES` (number of blob files obsoleted during GC), `BLOB_DB_GC_NUM_NEW_FILES` (number of new blob files generated during GC), `BLOB_DB_GC_FAILURES` (number of failed GC passes), `BLOB_DB_GC_NUM_KEYS_RELOCATED` (number of blobs relocated during GC), and `BLOB_DB_GC_BYTES_RELOCATED` (total size of blobs relocated during GC). On the other hand, the following statistics, which are not relevant for the new GC implementation, are now deprecated: `BLOB_DB_GC_NUM_KEYS_OVERWRITTEN`, `BLOB_DB_GC_NUM_KEYS_EXPIRED`, `BLOB_DB_GC_BYTES_OVERWRITTEN`, `BLOB_DB_GC_BYTES_EXPIRED`, and `BLOB_DB_GC_MICROS`.
-* Disable recycle_log_file_num when an inconsistent recovery modes are requested: kPointInTimeRecovery and kAbsoluteConsistency
-
-### New Features
-* Added the checksum for each SST file generated by Flush or Compaction. Added sst_file_checksum_func to Options such that user can plugin their own SST file checksum function via override the FileChecksumFunc class. If user does not set the sst_file_checksum_func, SST file checksum calculation will not be enabled. The checksum information inlcuding uint32_t checksum value and a checksum function name (string). The checksum information is stored in FileMetadata in version store and also logged to MANIFEST. A new tool is added to LDB such that user can dump out a list of file checksum information from MANIFEST (stored in an unordered_map).
-* `db_bench` now supports `value_size_distribution_type`, `value_size_min`, `value_size_max` options for generating random variable sized value. Added `blob_db_compression_type` option for BlobDB to enable blob compression.
-* Replace RocksDB namespace "rocksdb" with flag "ROCKSDB_NAMESPACE" which if is not defined, defined as "rocksdb" in header file rocksdb_namespace.h.
-
-## 6.7.0 (01/21/2020)
-### Public API Change
-* Added a rocksdb::FileSystem class in include/rocksdb/file_system.h to encapsulate file creation/read/write operations, and an option DBOptions::file_system to allow a user to pass in an instance of rocksdb::FileSystem. If its a non-null value, this will take precendence over DBOptions::env for file operations. A new API rocksdb::FileSystem::Default() returns a platform default object. The DBOptions::env option and Env::Default() API will continue to be used for threading and other OS related functions, and where DBOptions::file_system is not specified, for file operations. For storage developers who are accustomed to rocksdb::Env, the interface in rocksdb::FileSystem is new and will probably undergo some changes as more storage systems are ported to it from rocksdb::Env. As of now, no env other than Posix has been ported to the new interface.
-* A new rocksdb::NewSstFileManager() API that allows the caller to pass in separate Env and FileSystem objects.
-* Changed Java API for RocksDB.keyMayExist functions to use Holder<byte[]> instead of StringBuilder, so that retrieved values need not decode to Strings.
-* A new `OptimisticTransactionDBOptions` Option that allows users to configure occ validation policy. The default policy changes from kValidateSerial to kValidateParallel to reduce mutex contention.
-
-### Bug Fixes
-* Fix a bug that can cause unnecessary bg thread to be scheduled(#6104).
-* Fix crash caused by concurrent CF iterations and drops(#6147).
-* Fix a race condition for cfd->log_number_ between manifest switch and memtable switch (PR 6249) when number of column families is greater than 1.
-* Fix a bug on fractional cascading index when multiple files at the same level contain the same smallest user key, and those user keys are for merge operands. In this case, Get() the exact key may miss some merge operands.
-* Delcare kHashSearch index type feature-incompatible with index_block_restart_interval larger than 1.
-* Fixed an issue where the thread pools were not resized upon setting `max_background_jobs` dynamically through the `SetDBOptions` interface.
-* Fix a bug that can cause write threads to hang when a slowdown/stall happens and there is a mix of writers with WriteOptions::no_slowdown set/unset.
-* Fixed an issue where an incorrect "number of input records" value was used to compute the "records dropped" statistics for compactions.
-* Fix a regression bug that causes segfault when hash is used, max_open_files != -1 and total order seek is used and switched back.
-
-### New Features
-* It is now possible to enable periodic compactions for the base DB when using BlobDB.
-* BlobDB now garbage collects non-TTL blobs when `enable_garbage_collection` is set to `true` in `BlobDBOptions`. Garbage collection is performed during compaction: any valid blobs located in the oldest N files (where N is the number of non-TTL blob files multiplied by the value of `BlobDBOptions::garbage_collection_cutoff`) encountered during compaction get relocated to new blob files, and old blob files are dropped once they are no longer needed. Note: we recommend enabling periodic compactions for the base DB when using this feature to deal with the case when some old blob files are kept alive by SSTs that otherwise do not get picked for compaction.
-* `db_bench` now supports the `garbage_collection_cutoff` option for BlobDB.
-* Introduce ReadOptions.auto_prefix_mode. When set to true, iterator will return the same result as total order seek, but may choose to use prefix seek internally based on seek key and iterator upper bound.
-* MultiGet() can use IO Uring to parallelize read from the same SST file. This featuer is by default disabled. It can be enabled with environment variable ROCKSDB_USE_IO_URING.
-
-## 6.6.2 (01/13/2020)
-### Bug Fixes
-* Fixed a bug where non-L0 compaction input files were not considered to compute the `creation_time` of new compaction outputs.
-
-## 6.6.1 (01/02/2020)
-### Bug Fixes
-* Fix a bug in WriteBatchWithIndex::MultiGetFromBatchAndDB, which is called by Transaction::MultiGet, that causes due to stale pointer access when the number of keys is > 32
 * Fixed two performance issues related to memtable history trimming. First, a new SuperVersion is now created only if some memtables were actually trimmed. Second, trimming is only scheduled if there is at least one flushed memtable that is kept in memory for the purposes of transaction conflict checking.
-* BlobDB no longer updates the SST to blob file mapping upon failed compactions.
-* Fix a bug in which a snapshot read through an iterator could be affected by a DeleteRange after the snapshot (#6062).
-* Fixed a bug where BlobDB was comparing the `ColumnFamilyHandle` pointers themselves instead of only the column family IDs when checking whether an API call uses the default column family or not.
-* Delete superversions in BackgroundCallPurge.
-* Fix use-after-free and double-deleting files in BackgroundCallPurge().
-
-## 6.6.0 (11/25/2019)
-### Bug Fixes
-* Fix data corruption caused by output of intra-L0 compaction on ingested file not being placed in correct order in L0.
-* Fix a data race between Version::GetColumnFamilyMetaData() and Compaction::MarkFilesBeingCompacted() for access to being_compacted (#6056). The current fix acquires the db mutex during Version::GetColumnFamilyMetaData(), which may cause regression.
-* Fix a bug in DBIter that is_blob_ state isn't updated when iterating backward using seek.
-* Fix a bug when format_version=3, partitioned filters, and prefix search are used in conjunction. The bug could result into Seek::(prefix) returning NotFound for an existing prefix.
-* Revert the feature "Merging iterator to avoid child iterator reseek for some cases (#5286)" since it might cause strong results when reseek happens with a different iterator upper bound.
-* Fix a bug causing a crash during ingest external file when background compaction cause severe error (file not found).
-* Fix a bug when partitioned filters and prefix search are used in conjunction, ::SeekForPrev could return invalid for an existing prefix. ::SeekForPrev might be called by the user, or internally on ::Prev, or within ::Seek if the return value involves Delete or a Merge operand.
-* Fix OnFlushCompleted fired before flush result persisted in MANIFEST when there's concurrent flush job. The bug exists since OnFlushCompleted was introduced in rocksdb 3.8.
-* Fixed an sst_dump crash on some plain table SST files.
-* Fixed a memory leak in some error cases of opening plain table SST files.
-* Fix a bug when a crash happens while calling WriteLevel0TableForRecovery for multiple column families, leading to a column family's log number greater than the first corrutped log number when the DB is being opened in PointInTime recovery mode during next recovery attempt (#5856).
-
-### New Features
-* Universal compaction to support options.periodic_compaction_seconds. A full compaction will be triggered if any file is over the threshold.
-* `GetLiveFilesMetaData` and `GetColumnFamilyMetaData` now expose the file number of SST files as well as the oldest blob file referenced by each SST.
-* A batched MultiGet API (DB::MultiGet()) that supports retrieving keys from multiple column families.
-* Full and partitioned filters in the block-based table use an improved Bloom filter implementation, enabled with format_version 5 (or above) because previous releases cannot read this filter. This replacement is faster and more accurate, especially for high bits per key or millions of keys in a single (full) filter. For example, the new Bloom filter has the same false positive rate at 9.55 bits per key as the old one at 10 bits per key, and a lower false positive rate at 16 bits per key than the old one at 100 bits per key.
-* Added AVX2 instructions to USE_SSE builds to accelerate the new Bloom filter and XXH3-based hash function on compatible x86_64 platforms (Haswell and later, ~2014).
-* Support options.ttl or options.periodic_compaction_seconds with options.max_open_files = -1. File's oldest ancester time and file creation time will be written to manifest. If it is availalbe, this information will be used instead of creation_time and file_creation_time in table properties.
-* Setting options.ttl for universal compaction now has the same meaning as setting periodic_compaction_seconds.
-* SstFileMetaData also returns file creation time and oldest ancester time.
-* The `sst_dump` command line tool `recompress` command now displays how many blocks were compressed and how many were not, in particular how many were not compressed because the compression ratio was not met (12.5% threshold for GoodCompressionRatio), as seen in the `number.block.not_compressed` counter stat since version 6.0.0.
-* The block cache usage is now takes into account the overhead of metadata per each entry. This results into more accurate management of memory. A side-effect of this feature is that less items are fit into the block cache of the same size, which would result to higher cache miss rates. This can be remedied by increasing the block cache size or passing kDontChargeCacheMetadata to its constuctor to restore the old behavior.
-* When using BlobDB, a mapping is maintained and persisted in the MANIFEST between each SST file and the oldest non-TTL blob file it references.
-* `db_bench` now supports and by default issues non-TTL Puts to BlobDB. TTL Puts can be enabled by specifying a non-zero value for the `blob_db_max_ttl_range` command line parameter explicitly.
-* `sst_dump` now supports printing BlobDB blob indexes in a human-readable format. This can be enabled by specifying the `decode_blob_index` flag on the command line.
-* A number of new information elements are now exposed through the EventListener interface. For flushes, the file numbers of the new SST file and the oldest blob file referenced by the SST are propagated. For compactions, the level, file number, and the oldest blob file referenced are passed to the client for each compaction input and output file.
-
-### Public API Change
-* RocksDB release 4.1 or older will not be able to open DB generated by the new release. 4.2 was released on Feb 23, 2016.
-* TTL Compactions in Level compaction style now initiate successive cascading compactions on a key range so that it reaches the bottom level quickly on TTL expiry. `creation_time` table property for compaction output files is now set to the minimum of the creation times of all compaction inputs.
-* With FIFO compaction style, options.periodic_compaction_seconds will have the same meaning as options.ttl. Whichever stricter will be used. With the default options.periodic_compaction_seconds value with options.ttl's default of 0, RocksDB will give a default of 30 days.
-* Added an API GetCreationTimeOfOldestFile(uint64_t* creation_time) to get the file_creation_time of the oldest SST file in the DB.
-* FilterPolicy now exposes additional API to make it possible to choose filter configurations based on context, such as table level and compaction style. See `LevelAndStyleCustomFilterPolicy` in db_bloom_filter_test.cc. While most existing custom implementations of FilterPolicy should continue to work as before, those wrapping the return of NewBloomFilterPolicy will require overriding new function `GetBuilderWithContext()`, because calling `GetFilterBitsBuilder()` on the FilterPolicy returned by NewBloomFilterPolicy is no longer supported.
-* An unlikely usage of FilterPolicy is no longer supported. Calling GetFilterBitsBuilder() on the FilterPolicy returned by NewBloomFilterPolicy will now cause an assertion violation in debug builds, because RocksDB has internally migrated to a more elaborate interface that is expected to evolve further. Custom implementations of FilterPolicy should work as before, except those wrapping the return of NewBloomFilterPolicy, which will require a new override of a protected function in FilterPolicy.
-* NewBloomFilterPolicy now takes bits_per_key as a double instead of an int. This permits finer control over the memory vs. accuracy trade-off in the new Bloom filter implementation and should not change source code compatibility.
-* The option BackupableDBOptions::max_valid_backups_to_open is now only used when opening BackupEngineReadOnly. When opening a read/write BackupEngine, anything but the default value logs a warning and is treated as the default. This change ensures that backup deletion has proper accounting of shared files to ensure they are deleted when no longer referenced by a backup.
-* Deprecate `snap_refresh_nanos` option.
-* Added DisableManualCompaction/EnableManualCompaction to stop and resume manual compaction.
-* Add TryCatchUpWithPrimary() to StackableDB in non-LITE mode.
-* Add a new Env::LoadEnv() overloaded function to return a shared_ptr to Env.
-* Flush sets file name to "(nil)" for OnTableFileCreationCompleted() if the flush does not produce any L0. This can happen if the file is empty thus delete by RocksDB.
-
-### Default Option Changes
-* Changed the default value of periodic_compaction_seconds to `UINT64_MAX - 1` which allows RocksDB to auto-tune periodic compaction scheduling. When using the default value, periodic compactions are now auto-enabled if a compaction filter is used. A value of `0` will turn off the feature completely.
-* Changed the default value of ttl to `UINT64_MAX - 1` which allows RocksDB to auto-tune ttl value. When using the default value, TTL will be auto-enabled to 30 days, when the feature is supported. To revert the old behavior, you can explicitly set it to 0.
-
-### Performance Improvements
-* For 64-bit hashing, RocksDB is standardizing on a slightly modified preview version of XXH3. This function is now used for many non-persisted hashes, along with fastrange64() in place of the modulus operator, and some benchmarks show a slight improvement.
-* Level iterator to invlidate the iterator more often in prefix seek and the level is filtered out by prefix bloom.
 
 ## 6.5.2 (11/15/2019)
 ### Bug Fixes
-* Fix a assertion failure in MultiGet() when BlockBasedTableOptions::no_block_cache is true and there is no compressed block cache
+* Fix a assertion failure in MultiGe4t() when BlockBasedTableOptions::no_block_cache is true and there is no compressed block cache
 * Fix a buffer overrun problem in BlockBasedTable::MultiGet() when compression is enabled and no compressed block cache is configured.
 * If a call to BackupEngine::PurgeOldBackups or BackupEngine::DeleteBackup suffered a crash, power failure, or I/O error, files could be left over from old backups that could only be purged with a call to GarbageCollect. Any call to PurgeOldBackups, DeleteBackup, or GarbageCollect should now suffice to purge such files.
 
@@ -204,24 +21,21 @@
 * Fix a bug where the compaction snapshot refresh feature is not disabled as advertised when `snap_refresh_nanos` is set to 0..
 * Fix bloom filter lookups by the MultiGet batching API when BlockBasedTableOptions::whole_key_filtering is false, by checking that a key is in the perfix_extractor domain and extracting the prefix before looking up.
 * Fix a bug in file ingestion caused by incorrect file number allocation when the number of column families involved in the ingestion exceeds 2.
-
 ### New Features
 * Introduced DBOptions::max_write_batch_group_size_bytes to configure maximum limit on number of bytes that are written in a single batch of WAL or memtable write. It is followed when the leader write size is larger than 1/8 of this limit.
 * VerifyChecksum() by default will issue readahead. Allow ReadOptions to be passed in to those functions to override the readhead size. For checksum verifying before external SST file ingestion, a new option IngestExternalFileOptions.verify_checksums_readahead_size, is added for this readahead setting.
 * When user uses options.force_consistency_check in RocksDb, instead of crashing the process, we now pass the error back to the users without killing the process.
 * Add an option `memtable_insert_hint_per_batch` to WriteOptions. If it is true, each WriteBatch will maintain its own insert hints for each memtable in concurrent write. See include/rocksdb/options.h for more details.
-
 ### Public API Change
 * Added max_write_buffer_size_to_maintain option to better control memory usage of immutable memtables.
 * Added a lightweight API GetCurrentWalFile() to get last live WAL filename and size. Meant to be used as a helper for backup/restore tooling in a larger ecosystem such as MySQL with a MyRocks storage engine.
 * The MemTable Bloom filter, when enabled, now always uses cache locality. Options::bloom_locality now only affects the PlainTable SST format.
-
 ### Performance Improvements
 * Improve the speed of the MemTable Bloom filter, reducing the write overhead of enabling it by 1/3 to 1/2, with similar benefit to read performance.
 
 ## 6.4.0 (7/30/2019)
 ### Default Option Change
-* LRUCacheOptions.high_pri_pool_ratio is set to 0.5 (previously 0.0) by default, which means that by default midpoint insertion is enabled. The same change is made for the default value of high_pri_pool_ratio argument in NewLRUCache(). When block cache is not explicitly created, the small block cache created by BlockBasedTable will still has this option to be 0.0.
+* LRUCacheOptions.high_pri_pool_ratio is set to 0.5 (previously 0.0) by default, which means that by default midpoint insertion is enabled. The same change is made for the default value of high_pri_pool_ratio argument in NewLRUCache(). When block cache is not explictly created, the small block cache created by BlockBasedTable will still has this option to be 0.0.
 * Change BlockBasedTableOptions.cache_index_and_filter_blocks_with_high_priority's default value from false to true.
 
 ### Public API Change
@@ -245,7 +59,7 @@
 * Support loading custom objects in unit tests. In the affected unit tests, RocksDB will create custom Env objects based on environment variable TEST_ENV_URI. Users need to make sure custom object types are properly registered. For example, a static library should expose a `RegisterCustomObjects` function. By linking the unit test binary with the static library, the unit test can execute this function.
 
 ### Performance Improvements
-* Reduce iterator key comparison for upper/lower bound check.
+* Reduce iterator key comparision for upper/lower bound check.
 * Improve performance of row_cache: make reads with newer snapshots than data in an SST file share the same cache key, except in some transaction cases.
 * The compression dictionary is no longer copied to a new object upon retrieval.
 
@@ -341,7 +155,7 @@
 * Introduce two more stats levels, kExceptHistogramOrTimers and kExceptTimers.
 * Added a feature to perform data-block sampling for compressibility, and report stats to user.
 * Add support for trace filtering.
-* Add DBOptions.avoid_unnecessary_blocking_io. If true, we avoid file deletion when destroying ColumnFamilyHandle and Iterator. Instead, a job is scheduled to delete the files in background.
+* Add DBOptions.avoid_unnecessary_blocking_io. If true, we avoid file deletion when destorying ColumnFamilyHandle and Iterator. Instead, a job is scheduled to delete the files in background.
 
 ### Public API Change
 * Remove bundled fbson library.
@@ -720,7 +534,7 @@ if set to something > 0 user will see 2 changes in iterators behavior 1) only ke
 
 ## 5.2.0 (02/08/2017)
 ### Public API Change
-* NewLRUCache() will determine number of shard bits automatically based on capacity, if the user doesn't pass one. This also impacts the default block cache when the user doesn't explicit provide one.
+* NewLRUCache() will determine number of shard bits automatically based on capacity, if the user doesn't pass one. This also impacts the default block cache when the user doesn't explict provide one.
 * Change the default of delayed slowdown value to 16MB/s and further increase the L0 stop condition to 36 files.
 * Options::use_direct_writes and Options::use_direct_reads are now ready to use.
 * (Experimental) Two-level indexing that partition the index and creates a 2nd level index on the partitions. The feature can be enabled by setting kTwoLevelIndexSearch as IndexType and configuring index_per_partition.
@@ -791,7 +605,7 @@ if set to something > 0 user will see 2 changes in iterators behavior 1) only ke
 
 ### New Features
 * A tool to migrate DB after options change. See include/rocksdb/utilities/option_change_migration.h.
-* Add ReadOptions.background_purge_on_iterator_cleanup. If true, we avoid file deletion when destroying iterators.
+* Add ReadOptions.background_purge_on_iterator_cleanup. If true, we avoid file deletion when destorying iterators.
 
 ## 4.10.0 (7/5/2016)
 ### Public API Change

Makefile

@@ -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 +439,10 @@ 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 +457,14 @@ 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 \
@@ -512,25 +489,22 @@ 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 \
 	corruption_test \
-	slice_test \
 	slice_transform_test \
 	dbformat_test \
 	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 +549,6 @@ TESTS = \
 	deletefile_test \
 	obsolete_files_test \
 	table_test \
-	block_fetcher_test \
 	delete_scheduler_test \
 	options_test \
 	options_settable_test \
@@ -600,7 +573,6 @@ TESTS = \
 	compaction_job_stats_test \
 	option_change_migration_test \
 	transaction_test \
-	transaction_lock_mgr_test \
 	ldb_cmd_test \
 	persistent_cache_test \
 	statistics_test \
@@ -620,11 +592,6 @@ TESTS = \
 	db_secondary_test \
 	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 +616,6 @@ PARALLEL_TEST = \
 	persistent_cache_test \
 	table_test \
 	transaction_test \
-	transaction_lock_mgr_test \
 	write_prepared_transaction_test \
 	write_unprepared_transaction_test \
 
@@ -683,7 +649,7 @@ TEST_LIBS = \
 	librocksdb_env_basic_test.a
 
 # TODO: add back forward_iterator_bench, after making it build in all environemnts.
-BENCHMARKS = db_bench table_reader_bench cache_bench memtablerep_bench filter_bench persistent_cache_bench range_del_aggregator_bench
+BENCHMARKS = db_bench table_reader_bench cache_bench memtablerep_bench persistent_cache_bench range_del_aggregator_bench
 
 # if user didn't config LIBNAME, set the default
 ifeq ($(LIBNAME),)
@@ -696,7 +662,6 @@ endif
 endif
 LIBRARY = ${LIBNAME}.a
 TOOLS_LIBRARY = ${LIBNAME}_tools.a
-STRESS_LIBRARY = ${LIBNAME}_stress.a
 
 ROCKSDB_MAJOR = $(shell egrep "ROCKSDB_MAJOR.[0-9]" include/rocksdb/version.h | cut -d ' ' -f 3)
 ROCKSDB_MINOR = $(shell egrep "ROCKSDB_MINOR.[0-9]" include/rocksdb/version.h | cut -d ' ' -f 3)
@@ -775,8 +740,7 @@ endif  # PLATFORM_SHARED_EXT
 	release tags tags0 valgrind_check whitebox_crash_test format static_lib shared_lib all \
 	dbg rocksdbjavastatic rocksdbjava install install-static install-shared uninstall \
 	analyze tools tools_lib \
-	blackbox_crash_test_with_atomic_flush whitebox_crash_test_with_atomic_flush  \
-	blackbox_crash_test_with_txn whitebox_crash_test_with_txn
+	blackbox_crash_test_with_atomic_flush whitebox_crash_test_with_atomic_flush
 
 
 all: $(LIBRARY) $(BENCHMARKS) tools tools_lib test_libs $(TESTS)
@@ -787,8 +751,6 @@ static_lib: $(LIBRARY)
 
 shared_lib: $(SHARED)
 
-stress_lib: $(STRESS_LIBRARY)
-
 tools: $(TOOLS)
 
 tools_lib: $(TOOLS_LIBRARY)
@@ -966,59 +928,47 @@ 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)
-	$(PYTHON) tools/check_all_python.py
 ifeq ($(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
 
 crash_test_with_atomic_flush: whitebox_crash_test_with_atomic_flush blackbox_crash_test_with_atomic_flush
 
-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)
-
-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 --cf_consistency 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 \
-      $(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 --cf_consistency whitebox  --random_kill_odd \
       $(CRASH_TEST_KILL_ODD) $(CRASH_TEST_EXT_ARGS)
 
 asan_check:
@@ -1036,11 +986,6 @@ asan_crash_test_with_atomic_flush:
 	COMPILE_WITH_ASAN=1 $(MAKE) crash_test_with_atomic_flush
 	$(MAKE) clean
 
-asan_crash_test_with_txn:
-	$(MAKE) clean
-	COMPILE_WITH_ASAN=1 $(MAKE) crash_test_with_txn
-	$(MAKE) clean
-
 ubsan_check:
 	$(MAKE) clean
 	COMPILE_WITH_UBSAN=1 $(MAKE) check -j32
@@ -1056,11 +1001,6 @@ ubsan_crash_test_with_atomic_flush:
 	COMPILE_WITH_UBSAN=1 $(MAKE) crash_test_with_atomic_flush
 	$(MAKE) clean
 
-ubsan_crash_test_with_txn:
-	$(MAKE) clean
-	COMPILE_WITH_UBSAN=1 $(MAKE) crash_test_with_txn
-	$(MAKE) clean
-
 valgrind_test:
 	ROCKSDB_VALGRIND_RUN=1 DISABLE_JEMALLOC=1 $(MAKE) valgrind_check
 
@@ -1087,7 +1027,7 @@ 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'; \
@@ -1130,9 +1070,6 @@ parallel_check: $(TESTS)
 		TMPD=$(TMPD) J=$(J) db_test=0 parloop;
 
 analyze: clean
-	USE_CLANG=1 $(MAKE) analyze_incremental
-
-analyze_incremental:
 	$(CLANG_SCAN_BUILD) --use-analyzer=$(CLANG_ANALYZER) \
 		--use-c++=$(CXX) --use-cc=$(CC) --status-bugs \
 		-o $(CURDIR)/scan_build_report \
@@ -1161,27 +1098,13 @@ unity_test: db/db_test.o db/db_test_util.o $(TESTHARNESS) $(TOOLLIBOBJECTS) unit
 rocksdb.h rocksdb.cc: build_tools/amalgamate.py Makefile $(LIB_SOURCES) unity.cc
 	build_tools/amalgamate.py -I. -i./include unity.cc -x include/rocksdb/c.h -H rocksdb.h -o rocksdb.cc
 
-clean: clean-ext-libraries-all clean-rocks clean-rocksjava
-
-clean-not-downloaded: clean-ext-libraries-bin clean-rocks clean-not-downloaded-rocksjava
-
-clean-rocks:
+clean:
 	rm -f $(BENCHMARKS) $(TOOLS) $(TESTS) $(PARALLEL_TEST) $(LIBRARY) $(SHARED)
 	rm -rf $(CLEAN_FILES) ios-x86 ios-arm scan_build_report
 	$(FIND) . -name "*.[oda]" -exec rm -f {} \;
 	$(FIND) . -type f -regex ".*\.\(\(gcda\)\|\(gcno\)\)" -exec rm {} \;
-
-clean-rocksjava:
-	cd java && $(MAKE) clean
-
-clean-not-downloaded-rocksjava:
-	cd java && $(MAKE) clean-not-downloaded
-
-clean-ext-libraries-all:
 	rm -rf bzip2* snappy* zlib* lz4* zstd*
-
-clean-ext-libraries-bin:
-	find . -maxdepth 1 -type d \( -name bzip2\* -or -name snappy\* -or -name zlib\* -or -name lz4\* -or -name zstd\* \) -prune -exec rm -rf {} \;
+	cd java; $(MAKE) clean
 
 tags:
 	ctags -R .
@@ -1198,12 +1121,6 @@ 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)
 
@@ -1218,10 +1135,6 @@ $(TOOLS_LIBRARY): $(BENCH_LIB_SOURCES:.cc=.o) $(TOOL_LIB_SOURCES:.cc=.o) $(LIB_S
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^
 
-$(STRESS_LIBRARY): $(LIB_SOURCES:.cc=.o) $(TESTUTIL) $(ANALYZER_LIB_SOURCES:.cc=.o) $(STRESS_LIB_SOURCES:.cc=.o)
-	$(AM_V_AR)rm -f $@
-	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^
-
 librocksdb_env_basic_test.a: env/env_basic_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_V_AR)rm -f $@
 	$(AM_V_at)$(AR) $(ARFLAGS) $@ $^
@@ -1249,10 +1162,7 @@ persistent_cache_bench: utilities/persistent_cache/persistent_cache_bench.o $(LI
 memtablerep_bench: memtable/memtablerep_bench.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)
 
-filter_bench: util/filter_bench.o $(LIBOBJECTS) $(TESTUTIL)
-	$(AM_LINK)
-
-db_stress: db_stress_tool/db_stress.o $(STRESSTOOLOBJECTS)
+db_stress: tools/db_stress.o $(LIBOBJECTS) $(TESTUTIL)
 	$(AM_LINK)
 
 write_stress: tools/write_stress.o $(LIBOBJECTS) $(TESTUTIL)
@@ -1266,9 +1176,6 @@ 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)
@@ -1297,9 +1204,6 @@ coding_test: util/coding_test.o $(LIBOBJECTS) $(TESTHARNESS)
 hash_test: util/hash_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-random_test: util/random_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 option_change_migration_test: utilities/option_change_migration/option_change_migration_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
@@ -1327,30 +1231,18 @@ 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)
 
 crc32c_test: util/crc32c_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-slice_test: util/slice_test.o $(LIBOBJECTS) $(TESTHARNESS)
-	$(AM_LINK)
-
 slice_transform_test: util/slice_transform_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 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 +1252,7 @@ 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 +1306,7 @@ 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 +1419,6 @@ 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 +1431,6 @@ 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 +1452,6 @@ 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)
 
@@ -1629,10 +1509,10 @@ util_merge_operators_test: utilities/util_merge_operators_test.o $(LIBOBJECTS) $
 options_file_test: db/options_file_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-deletefile_test: db/deletefile_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+deletefile_test: db/deletefile_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-obsolete_files_test: db/obsolete_files_test.o db/db_test_util.o $(LIBOBJECTS) $(TESTHARNESS)
+obsolete_files_test: db/obsolete_files_test.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
 rocksdb_dump: tools/dump/rocksdb_dump.o $(LIBOBJECTS)
@@ -1710,9 +1590,6 @@ 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)
 
@@ -1779,18 +1656,6 @@ block_cache_tracer_test: trace_replay/block_cache_tracer_test.o trace_replay/blo
 block_cache_trace_analyzer_test: tools/block_cache_analyzer/block_cache_trace_analyzer_test.o tools/block_cache_analyzer/block_cache_trace_analyzer.o $(LIBOBJECTS) $(TESTHARNESS)
 	$(AM_LINK)
 
-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)
-	$(AM_LINK)
-
 #-------------------------------------------------
 # make install related stuff
 INSTALL_PATH ?= /usr/local
@@ -1836,7 +1701,7 @@ JAVA_INCLUDE = -I$(JAVA_HOME)/include/ -I$(JAVA_HOME)/include/linux
 ifeq ($(PLATFORM), OS_SOLARIS)
 	ARCH := $(shell isainfo -b)
 else ifeq ($(PLATFORM), OS_OPENBSD)
-	ifneq (,$(filter amd64 ppc64 ppc64le arm64 aarch64 sparc64, $(MACHINE)))
+	ifneq (,$(filter $(MACHINE), amd64 arm64 aarch64 sparc64))
 		ARCH := 64
 	else
 		ARCH := 32
@@ -1845,23 +1710,12 @@ else
 	ARCH := $(shell getconf LONG_BIT)
 endif
 
-ifeq ($(shell ldd /usr/bin/env 2>/dev/null | grep -q musl; echo $$?),0)
-        JNI_LIBC = musl
-# GNU LibC (or glibc) is so pervasive we can assume it is the default
-# else
-#        JNI_LIBC = glibc
-endif
-
-ifneq ($(origin JNI_LIBC), undefined)
-  JNI_LIBC_POSTFIX = -$(JNI_LIBC)
-endif
-
-ifneq (,$(filter ppc% arm64 aarch64 sparc64, $(MACHINE)))
-	ROCKSDBJNILIB = librocksdbjni-linux-$(MACHINE)$(JNI_LIBC_POSTFIX).so
+ifeq (,$(filter $(MACHINE), ppc arm64 aarch64 sparc64))
+        ROCKSDBJNILIB = librocksdbjni-linux$(ARCH).so
 else
-	ROCKSDBJNILIB = librocksdbjni-linux$(ARCH)$(JNI_LIBC_POSTFIX).so
+        ROCKSDBJNILIB = librocksdbjni-linux-$(MACHINE).so
 endif
-ROCKSDB_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux$(ARCH)$(JNI_LIBC_POSTFIX).jar
+ROCKSDB_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux$(ARCH).jar
 ROCKSDB_JAR_ALL = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH).jar
 ROCKSDB_JAVADOCS_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-javadoc.jar
 ROCKSDB_SOURCES_JAR = rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-sources.jar
@@ -1870,17 +1724,17 @@ SHA256_CMD = sha256sum
 ZLIB_VER ?= 1.2.11
 ZLIB_SHA256 ?= c3e5e9fdd5004dcb542feda5ee4f0ff0744628baf8ed2dd5d66f8ca1197cb1a1
 ZLIB_DOWNLOAD_BASE ?= http://zlib.net
-BZIP2_VER ?= 1.0.8
-BZIP2_SHA256 ?= ab5a03176ee106d3f0fa90e381da478ddae405918153cca248e682cd0c4a2269
-BZIP2_DOWNLOAD_BASE ?= https://sourceware.org/pub/bzip2
-SNAPPY_VER ?= 1.1.8
-SNAPPY_SHA256 ?= 16b677f07832a612b0836178db7f374e414f94657c138e6993cbfc5dcc58651f
+BZIP2_VER ?= 1.0.6
+BZIP2_SHA256 ?= a2848f34fcd5d6cf47def00461fcb528a0484d8edef8208d6d2e2909dc61d9cd
+BZIP2_DOWNLOAD_BASE ?= https://web.archive.org/web/20180624184835/http://www.bzip.org
+SNAPPY_VER ?= 1.1.7
+SNAPPY_SHA256 ?= 3dfa02e873ff51a11ee02b9ca391807f0c8ea0529a4924afa645fbf97163f9d4
 SNAPPY_DOWNLOAD_BASE ?= https://github.com/google/snappy/archive
-LZ4_VER ?= 1.9.2
-LZ4_SHA256 ?= 658ba6191fa44c92280d4aa2c271b0f4fbc0e34d249578dd05e50e76d0e5efcc
+LZ4_VER ?= 1.8.3
+LZ4_SHA256 ?= 33af5936ac06536805f9745e0b6d61da606a1f8b4cc5c04dd3cbaca3b9b4fc43
 LZ4_DOWNLOAD_BASE ?= https://github.com/lz4/lz4/archive
-ZSTD_VER ?= 1.4.4
-ZSTD_SHA256 ?= a364f5162c7d1a455cc915e8e3cf5f4bd8b75d09bc0f53965b0c9ca1383c52c8
+ZSTD_VER ?= 1.4.0
+ZSTD_SHA256 ?= 63be339137d2b683c6d19a9e34f4fb684790e864fee13c7dd40e197a64c705c1
 ZSTD_DOWNLOAD_BASE ?= https://github.com/facebook/zstd/archive
 CURL_SSL_OPTS ?= --tlsv1
 
@@ -1920,7 +1774,7 @@ endif
 libz.a:
 	-rm -rf zlib-$(ZLIB_VER)
 ifeq (,$(wildcard ./zlib-$(ZLIB_VER).tar.gz))
-	curl --fail --output zlib-$(ZLIB_VER).tar.gz --location ${ZLIB_DOWNLOAD_BASE}/zlib-$(ZLIB_VER).tar.gz
+	curl --output zlib-$(ZLIB_VER).tar.gz -L ${ZLIB_DOWNLOAD_BASE}/zlib-$(ZLIB_VER).tar.gz
 endif
 	ZLIB_SHA256_ACTUAL=`$(SHA256_CMD) zlib-$(ZLIB_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(ZLIB_SHA256)" != "$$ZLIB_SHA256_ACTUAL" ]; then \
@@ -1934,7 +1788,7 @@ endif
 libbz2.a:
 	-rm -rf bzip2-$(BZIP2_VER)
 ifeq (,$(wildcard ./bzip2-$(BZIP2_VER).tar.gz))
-	curl --fail --output bzip2-$(BZIP2_VER).tar.gz --location ${CURL_SSL_OPTS} ${BZIP2_DOWNLOAD_BASE}/bzip2-$(BZIP2_VER).tar.gz
+	curl --output bzip2-$(BZIP2_VER).tar.gz -L ${BZIP2_DOWNLOAD_BASE}/$(BZIP2_VER)/bzip2-$(BZIP2_VER).tar.gz
 endif
 	BZIP2_SHA256_ACTUAL=`$(SHA256_CMD) bzip2-$(BZIP2_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(BZIP2_SHA256)" != "$$BZIP2_SHA256_ACTUAL" ]; then \
@@ -1948,7 +1802,7 @@ endif
 libsnappy.a:
 	-rm -rf snappy-$(SNAPPY_VER)
 ifeq (,$(wildcard ./snappy-$(SNAPPY_VER).tar.gz))
-	curl --fail --output snappy-$(SNAPPY_VER).tar.gz --location ${CURL_SSL_OPTS} ${SNAPPY_DOWNLOAD_BASE}/$(SNAPPY_VER).tar.gz
+	curl --output snappy-$(SNAPPY_VER).tar.gz -L ${CURL_SSL_OPTS} ${SNAPPY_DOWNLOAD_BASE}/$(SNAPPY_VER).tar.gz
 endif
 	SNAPPY_SHA256_ACTUAL=`$(SHA256_CMD) snappy-$(SNAPPY_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(SNAPPY_SHA256)" != "$$SNAPPY_SHA256_ACTUAL" ]; then \
@@ -1963,7 +1817,7 @@ endif
 liblz4.a:
 	-rm -rf lz4-$(LZ4_VER)
 ifeq (,$(wildcard ./lz4-$(LZ4_VER).tar.gz))
-	curl --fail --output lz4-$(LZ4_VER).tar.gz --location ${CURL_SSL_OPTS} ${LZ4_DOWNLOAD_BASE}/v$(LZ4_VER).tar.gz
+	curl --output lz4-$(LZ4_VER).tar.gz -L ${CURL_SSL_OPTS} ${LZ4_DOWNLOAD_BASE}/v$(LZ4_VER).tar.gz
 endif
 	LZ4_SHA256_ACTUAL=`$(SHA256_CMD) lz4-$(LZ4_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(LZ4_SHA256)" != "$$LZ4_SHA256_ACTUAL" ]; then \
@@ -1977,7 +1831,7 @@ endif
 libzstd.a:
 	-rm -rf zstd-$(ZSTD_VER)
 ifeq (,$(wildcard ./zstd-$(ZSTD_VER).tar.gz))
-	curl --fail --output zstd-$(ZSTD_VER).tar.gz --location ${CURL_SSL_OPTS} ${ZSTD_DOWNLOAD_BASE}/v$(ZSTD_VER).tar.gz
+	curl --output zstd-$(ZSTD_VER).tar.gz -L ${CURL_SSL_OPTS} ${ZSTD_DOWNLOAD_BASE}/v$(ZSTD_VER).tar.gz
 endif
 	ZSTD_SHA256_ACTUAL=`$(SHA256_CMD) zstd-$(ZSTD_VER).tar.gz | cut -d ' ' -f 1`; \
 	if [ "$(ZSTD_SHA256)" != "$$ZSTD_SHA256_ACTUAL" ]; then \
@@ -2035,47 +1889,35 @@ rocksdbjavastatic: $(java_static_all_libobjects)
 	cd java/src/main/java;jar -cf ../../../target/$(ROCKSDB_SOURCES_JAR) org
 
 rocksdbjavastaticrelease: rocksdbjavastatic
-	cd java/crossbuild && (vagrant destroy -f || true) && vagrant up linux32 && vagrant halt linux32 && vagrant up linux64 && vagrant halt linux64 && vagrant up linux64-musl && vagrant halt linux64-musl
+	cd java/crossbuild && vagrant destroy -f && vagrant up linux32 && vagrant halt linux32 && vagrant up linux64 && vagrant halt linux64
 	cd java;jar -cf target/$(ROCKSDB_JAR_ALL) HISTORY*.md
 	cd java/target;jar -uf $(ROCKSDB_JAR_ALL) librocksdbjni-*.so librocksdbjni-*.jnilib
 	cd java/target/classes;jar -uf ../$(ROCKSDB_JAR_ALL) org/rocksdb/*.class org/rocksdb/util/*.class
 
-rocksdbjavastaticreleasedocker: rocksdbjavastatic rocksdbjavastaticdockerx86 rocksdbjavastaticdockerx86_64 rocksdbjavastaticdockerx86musl rocksdbjavastaticdockerx86_64musl
+rocksdbjavastaticreleasedocker: rocksdbjavastatic rocksdbjavastaticdockerx86 rocksdbjavastaticdockerx86_64
 	cd java;jar -cf target/$(ROCKSDB_JAR_ALL) HISTORY*.md
 	cd java/target;jar -uf $(ROCKSDB_JAR_ALL) librocksdbjni-*.so librocksdbjni-*.jnilib
 	cd java/target/classes;jar -uf ../$(ROCKSDB_JAR_ALL) org/rocksdb/*.class org/rocksdb/util/*.class
 
 rocksdbjavastaticdockerx86:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x86-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos6_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
+	docker run --rm --name rocksdb_linux_x86-be --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos6_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
 
 rocksdbjavastaticdockerx86_64:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x64-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
+	docker run --rm --name rocksdb_linux_x64-be --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos6_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
 
 rocksdbjavastaticdockerppc64le:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_ppc64le-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos7_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
+	docker run --rm --name rocksdb_linux_ppc64le-be --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos7_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
 
 rocksdbjavastaticdockerarm64v8:
 	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_arm64v8-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:centos7_arm64v8-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
-
-rocksdbjavastaticdockerx86musl:
-	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x86-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:alpine3_x86-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
-
-rocksdbjavastaticdockerx86_64musl:
-	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_x64-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:alpine3_x64-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
-
-rocksdbjavastaticdockerppc64lemusl:
-	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_ppc64le-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:alpine3_ppc64le-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
-
-rocksdbjavastaticdockerarm64v8musl:
-	mkdir -p java/target
-	docker run --rm --name rocksdb_linux_arm64v8-musl-be --attach stdin --attach stdout --attach stderr --volume $(HOME)/.m2:/root/.m2:ro --volume `pwd`:/rocksdb-host:ro --volume /rocksdb-local-build --volume `pwd`/java/target:/rocksdb-java-target --env DEBUG_LEVEL=$(DEBUG_LEVEL) evolvedbinary/rocksjava:alpine3_arm64v8-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh
+	DOCKER_LINUX_ARM64V8_CONTAINER=`docker ps -aqf name=rocksdb_linux_arm64v8-be`; \
+	if [ -z "$$DOCKER_LINUX_ARM64V8_CONTAINER" ]; then \
+		docker container create --attach stdin --attach stdout --attach stderr --volume `pwd`:/rocksdb-host --name rocksdb_linux_arm64v8-be evolvedbinary/rocksjava:centos7_arm64v8-be /rocksdb-host/java/crossbuild/docker-build-linux-centos.sh; \
+	fi
+	docker start -a rocksdb_linux_arm64v8-be
 
 rocksdbjavastaticpublish: rocksdbjavastaticrelease rocksdbjavastaticpublishcentral
 
@@ -2086,8 +1928,6 @@ rocksdbjavastaticpublishcentral:
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-sources.jar -Dclassifier=sources
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux64.jar -Dclassifier=linux64
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux32.jar -Dclassifier=linux32
-	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux64-musl.jar -Dclassifier=linux64-musl
-	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-linux32-musl.jar -Dclassifier=linux32-musl
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-osx.jar -Dclassifier=osx
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH)-win64.jar -Dclassifier=win64
 	mvn gpg:sign-and-deploy-file -Durl=https://oss.sonatype.org/service/local/staging/deploy/maven2/ -DrepositoryId=sonatype-nexus-staging -DpomFile=java/rocksjni.pom -Dfile=java/target/rocksdbjni-$(ROCKSDB_MAJOR).$(ROCKSDB_MINOR).$(ROCKSDB_PATCH).jar
@@ -2141,7 +1981,6 @@ 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
 
 jdb_bench:
 	cd java;$(MAKE) db_bench;
@@ -2189,9 +2028,6 @@ endif
 .cc.o:
 	$(AM_V_CC)$(CXX) $(CXXFLAGS) -c $< -o $@ $(COVERAGEFLAGS)
 
-.cpp.o:
-	$(AM_V_CC)$(CXX) $(CXXFLAGS) -c $< -o $@ $(COVERAGEFLAGS)
-
 .c.o:
 	$(AM_V_CC)$(CC) $(CFLAGS) -c $< -o $@
 endif
@@ -2199,13 +2035,9 @@ endif
 #  	Source files dependencies detection
 # ---------------------------------------------------------------------------
 
-all_sources = $(LIB_SOURCES) $(MAIN_SOURCES) $(MOCK_LIB_SOURCES) $(TOOL_LIB_SOURCES) $(BENCH_LIB_SOURCES) $(TEST_LIB_SOURCES) $(ANALYZER_LIB_SOURCES) $(STRESS_LIB_SOURCES)
+all_sources = $(LIB_SOURCES) $(MAIN_SOURCES) $(MOCK_LIB_SOURCES) $(TOOL_LIB_SOURCES) $(BENCH_LIB_SOURCES) $(TEST_LIB_SOURCES) $(ANALYZER_LIB_SOURCES)
 DEPFILES = $(all_sources:.cc=.cc.d)
 
-ifeq ($(USE_FOLLY_DISTRIBUTED_MUTEX),1)
-  DEPFILES += $(FOLLY_SOURCES:.cpp=.cpp.d)
-endif
-
 # Add proper dependency support so changing a .h file forces a .cc file to
 # rebuild.
 
@@ -2215,10 +2047,6 @@ endif
 	@$(CXX) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) \
 	  -MM -MT'$@' -MT'$(<:.cc=.o)' "$<" -o '$@'
 
-%.cpp.d: %.cpp
-	@$(CXX) $(CXXFLAGS) $(PLATFORM_SHARED_CFLAGS) \
-	  -MM -MT'$@' -MT'$(<:.cpp=.o)' "$<" -o '$@'
-
 ifeq ($(HAVE_POWER8),1)
 DEPFILES_C = $(LIB_SOURCES_C:.c=.c.d)
 DEPFILES_ASM = $(LIB_SOURCES_ASM:.S=.S.d)

README.md

@@ -9,11 +9,11 @@ It is built on earlier work on [LevelDB](https://github.com/google/leveldb) by S
 and Jeff Dean (jeff@google.com)
 
 This code is a library that forms the core building block for a fast
-key-value server, especially suited for storing data on flash drives.
+key value server, especially suited for storing data on flash drives.
 It has a Log-Structured-Merge-Database (LSM) design with flexible tradeoffs
 between Write-Amplification-Factor (WAF), Read-Amplification-Factor (RAF)
 and Space-Amplification-Factor (SAF). It has multi-threaded compactions,
-making it especially suitable for storing multiple terabytes of data in a
+making it specially suitable for storing multiple terabytes of data in a
 single database.
 
 Start with example usage here: https://github.com/facebook/rocksdb/tree/master/examples
@@ -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
 

TARGETS

@@ -1,8 +1,3 @@
-# This file @generated by `python buckifier/buckify_rocksdb.py`
-# --> DO NOT EDIT MANUALLY <--
-# This file is a Facebook-specific integration for buck builds, so can
-# only be validated by Facebook employees.
-#
 load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
 load("@fbcode_macros//build_defs:cpp_library.bzl", "cpp_library")
 load(":defs.bzl", "test_binary")
@@ -32,7 +27,7 @@ ROCKSDB_EXTERNAL_DEPS = [
 ROCKSDB_OS_DEPS = [
     (
         "linux",
-        ["third-party//numa:numa", "third-party//liburing:uring"],
+        ["third-party//numa:numa"],
     ),
 ]
 
@@ -46,9 +41,7 @@ ROCKSDB_OS_PREPROCESSOR_FLAGS = [
             "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
             "-DROCKSDB_RANGESYNC_PRESENT",
             "-DROCKSDB_SCHED_GETCPU_PRESENT",
-            "-DROCKSDB_IOURING_PRESENT",
             "-DHAVE_SSE42",
-            "-DLIBURING",
             "-DNUMA",
         ],
     ),
@@ -112,14 +105,9 @@ 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 +161,6 @@ 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",
@@ -185,27 +172,18 @@ cpp_library(
         "env/env_encryption.cc",
         "env/env_hdfs.cc",
         "env/env_posix.cc",
-        "env/file_system.cc",
-        "env/fs_posix.cc",
         "env/io_posix.cc",
         "env/mock_env.cc",
         "file/delete_scheduler.cc",
-        "file/file_prefetch_buffer.cc",
         "file/file_util.cc",
         "file/filename.cc",
-        "file/random_access_file_reader.cc",
-        "file/read_write_util.cc",
-        "file/readahead_raf.cc",
-        "file/sequence_file_reader.cc",
         "file/sst_file_manager_impl.cc",
-        "file/writable_file_writer.cc",
         "logging/auto_roll_logger.cc",
         "logging/event_logger.cc",
         "logging/log_buffer.cc",
         "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",
@@ -231,33 +209,24 @@ 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",
         "table/block_based/filter_block_reader_common.cc",
-        "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",
@@ -288,6 +257,7 @@ cpp_library(
         "tools/sst_dump_tool.cc",
         "trace_replay/block_cache_tracer.cc",
         "trace_replay/trace_replay.cc",
+        "util/bloom.cc",
         "util/build_version.cc",
         "util/coding.cc",
         "util/compaction_job_stats_impl.cc",
@@ -296,7 +266,8 @@ cpp_library(
         "util/concurrent_task_limiter_impl.cc",
         "util/crc32c.cc",
         "util/dynamic_bloom.cc",
-        "util/file_checksum_helper.cc",
+        "util/file_reader_writer.cc",
+        "util/filter_policy.cc",
         "util/hash.cc",
         "util/murmurhash.cc",
         "util/random.cc",
@@ -380,7 +351,6 @@ 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",
@@ -415,35 +385,6 @@ cpp_library(
     external_deps = ROCKSDB_EXTERNAL_DEPS,
 )
 
-cpp_library(
-    name = "rocksdb_stress_lib",
-    srcs = [
-        "db_stress_tool/batched_ops_stress.cc",
-        "db_stress_tool/cf_consistency_stress.cc",
-        "db_stress_tool/db_stress_common.cc",
-        "db_stress_tool/db_stress_driver.cc",
-        "db_stress_tool/db_stress_gflags.cc",
-        "db_stress_tool/db_stress_shared_state.cc",
-        "db_stress_tool/db_stress_test_base.cc",
-        "db_stress_tool/db_stress_tool.cc",
-        "db_stress_tool/no_batched_ops_stress.cc",
-        "test_util/testutil.cc",
-        "tools/block_cache_analyzer/block_cache_trace_analyzer.cc",
-        "tools/trace_analyzer_tool.cc",
-    ],
-    auto_headers = AutoHeaders.RECURSIVE_GLOB,
-    arch_preprocessor_flags = ROCKSDB_ARCH_PREPROCESSOR_FLAGS,
-    compiler_flags = ROCKSDB_COMPILER_FLAGS,
-    os_deps = ROCKSDB_OS_DEPS,
-    os_preprocessor_flags = ROCKSDB_OS_PREPROCESSOR_FLAGS,
-    preprocessor_flags = ROCKSDB_PREPROCESSOR_FLAGS,
-    deps = [
-        ":rocksdb_lib",
-        ":rocksdb_test_lib",
-    ],
-    external_deps = ROCKSDB_EXTERNAL_DEPS,
-)
-
 cpp_library(
     name = "env_basic_test_lib",
     srcs = ["env/env_basic_test.cc"],
@@ -494,20 +435,6 @@ 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 +456,6 @@ ROCKS_TESTS = [
         [],
         [],
     ],
-    [
-        "block_fetcher_test",
-        "table/block_fetcher_test.cc",
-        "serial",
-        [],
-        [],
-    ],
     [
         "block_test",
         "table/block_based/block_test.cc",
@@ -727,7 +647,7 @@ ROCKS_TESTS = [
     ],
     [
         "db_blob_index_test",
-        "db/blob/db_blob_index_test.cc",
+        "db/db_blob_index_test.cc",
         "serial",
         [],
         [],
@@ -823,13 +743,6 @@ 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",
@@ -838,15 +751,15 @@ ROCKS_TESTS = [
         [],
     ],
     [
-        "db_merge_operand_test",
-        "db/db_merge_operand_test.cc",
-        "serial",
+        "db_merge_operator_test",
+        "db/db_merge_operator_test.cc",
+        "parallel",
         [],
         [],
     ],
     [
-        "db_merge_operator_test",
-        "db/db_merge_operator_test.cc",
+        "db_merge_operand_test",
+        "db/db_merge_operand_test.cc",
         "parallel",
         [],
         [],
@@ -935,20 +848,6 @@ 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",
@@ -963,13 +862,6 @@ ROCKS_TESTS = [
         [],
         [],
     ],
-    [
-        "defer_test",
-        "util/defer_test.cc",
-        "serial",
-        [],
-        [],
-    ],
     [
         "delete_scheduler_test",
         "file/delete_scheduler_test.cc",
@@ -1020,8 +912,8 @@ ROCKS_TESTS = [
         [],
     ],
     [
-        "error_handler_fs_test",
-        "db/error_handler_fs_test.cc",
+        "error_handler_test",
+        "db/error_handler_test.cc",
         "serial",
         [],
         [],
@@ -1138,13 +1030,6 @@ ROCKS_TESTS = [
         [],
         [],
     ],
-    [
-        "io_posix_test",
-        "env/io_posix_test.cc",
-        "serial",
-        [],
-        [],
-    ],
     [
         "iostats_context_test",
         "monitoring/iostats_context_test.cc",
@@ -1187,13 +1072,6 @@ ROCKS_TESTS = [
         [],
         [],
     ],
-    [
-        "memkind_kmem_allocator_test",
-        "memory/memkind_kmem_allocator_test.cc",
-        "serial",
-        [],
-        [],
-    ],
     [
         "memory_test",
         "utilities/memory/memory_test.cc",
@@ -1327,20 +1205,6 @@ ROCKS_TESTS = [
         [],
         [],
     ],
-    [
-        "random_access_file_reader_test",
-        "file/random_access_file_reader_test.cc",
-        "serial",
-        [],
-        [],
-    ],
-    [
-        "random_test",
-        "util/random_test.cc",
-        "serial",
-        [],
-        [],
-    ],
     [
         "range_del_aggregator_test",
         "db/range_del_aggregator_test.cc",
@@ -1397,13 +1261,6 @@ ROCKS_TESTS = [
         [],
         [],
     ],
-    [
-        "slice_test",
-        "util/slice_test.cc",
-        "serial",
-        [],
-        [],
-    ],
     [
         "slice_transform_test",
         "util/slice_transform_test.cc",
@@ -1481,13 +1338,6 @@ ROCKS_TESTS = [
         [],
         [],
     ],
-    [
-        "timer_test",
-        "util/timer_test.cc",
-        "serial",
-        [],
-        [],
-    ],
     [
         "trace_analyzer_test",
         "tools/trace_analyzer_test.cc",
@@ -1495,13 +1345,6 @@ ROCKS_TESTS = [
         [],
         [],
     ],
-    [
-        "transaction_lock_mgr_test",
-        "utilities/transactions/transaction_lock_mgr_test.cc",
-        "parallel",
-        [],
-        [],
-    ],
     [
         "transaction_test",
         "utilities/transactions/transaction_test.cc",
@@ -1551,13 +1394,6 @@ ROCKS_TESTS = [
         [],
         [],
     ],
-    [
-        "work_queue_test",
-        "util/work_queue_test.cc",
-        "serial",
-        [],
-        [],
-    ],
     [
         "write_batch_test",
         "db/write_batch_test.cc",

USERS.md

@@ -97,15 +97,5 @@ LzLabs is using RocksDB as a storage engine in their multi-database distributed
 ## IOTA Foundation
  [IOTA Foundation](https://www.iota.org/) is using RocksDB in the [IOTA Reference Implementation (IRI)](https://github.com/iotaledger/iri) to store the local state of the Tangle. The Tangle is the first open-source distributed ledger powering the future of the Internet of Things.
  
-## Avrio Project
- [Avrio Project](http://avrio-project.github.io/avrio.network/) is using RocksDB in [Avrio ](https://github.com/avrio-project/avrio) to store blocks, account balances and data and other blockchain-releated data. Avrio is a multiblockchain decentralized cryptocurrency empowering monetary transactions.
- 
 ## Crux
 [Crux](https://github.com/juxt/crux) is a document database that uses RocksDB for local [EAV](https://en.wikipedia.org/wiki/Entity%E2%80%93attribute%E2%80%93value_model) index storage to enable point-in-time bitemporal Datalog queries. The "unbundled" architecture uses Kafka to provide horizontal scalability.
-
-## 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/.

appveyor.yml

@@ -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
@@ -17,60 +17,41 @@ environment:
   ZSTD_INCLUDE: $(ZSTD_HOME)\lib;$(ZSTD_HOME)\lib\dictBuilder
   ZSTD_LIB_DEBUG: $(ZSTD_HOME)\build\VS2010\bin\x64_Debug\libzstd_static.lib
   ZSTD_LIB_RELEASE: $(ZSTD_HOME)\build\VS2010\bin\x64_Release\libzstd_static.lib
-  matrix:
-    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2015
-      CMAKE_GENERATOR: Visual Studio 14 Win64
-      DEV_ENV: C:\Program Files (x86)\Microsoft Visual Studio 14.0\Common7\IDE\devenv.com
-    - APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2017
-      CMAKE_GENERATOR: Visual Studio 15 Win64
-      DEV_ENV: C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com
-    - 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%
   - echo "Building Snappy dependency..."
   - cd %THIRDPARTY_HOME%
-  - curl --fail --silent --show-error --output snappy-1.1.7.zip --location https://github.com/google/snappy/archive/1.1.7.zip
+  - curl -fsSL -o snappy-1.1.7.zip https://github.com/google/snappy/archive/1.1.7.zip
   - unzip snappy-1.1.7.zip
   - cd snappy-1.1.7
   - mkdir build
   - cd build
-  - if DEFINED CMAKE_PLATEFORM_NAME (set "PLATEFORM_OPT=-A %CMAKE_PLATEFORM_NAME%")
-  - cmake .. -G "%CMAKE_GENERATOR%" %PLATEFORM_OPT%
+  - cmake -DCMAKE_GENERATOR_PLATFORM=x64 ..
   - msbuild Snappy.sln /p:Configuration=Debug /p:Platform=x64
   - msbuild Snappy.sln /p:Configuration=Release /p:Platform=x64
   - echo "Building LZ4 dependency..."
   - cd %THIRDPARTY_HOME%
-  - curl --fail --silent --show-error --output lz4-1.8.3.zip --location https://github.com/lz4/lz4/archive/v1.8.3.zip
+  - curl -fsSL -o lz4-1.8.3.zip https://github.com/lz4/lz4/archive/v1.8.3.zip
   - unzip lz4-1.8.3.zip
   - cd lz4-1.8.3\visual\VS2010
-  - ps: $CMD="$Env:DEV_ENV"; & $CMD lz4.sln /upgrade
+  - ps: $CMD="C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com"; & $CMD lz4.sln /upgrade
   - msbuild lz4.sln /p:Configuration=Debug /p:Platform=x64
   - msbuild lz4.sln /p:Configuration=Release /p:Platform=x64
   - echo "Building ZStd dependency..."
   - cd %THIRDPARTY_HOME%
-  - curl --fail --silent --show-error --output zstd-1.4.0.zip --location https://github.com/facebook/zstd/archive/v1.4.0.zip
+  - curl -fsSL -o zstd-1.4.0.zip https://github.com/facebook/zstd/archive/v1.4.0.zip
   - unzip zstd-1.4.0.zip
   - cd zstd-1.4.0\build\VS2010
-  - ps: $CMD="$Env:DEV_ENV"; & $CMD zstd.sln /upgrade
+  - ps: $CMD="C:\Program Files (x86)\Microsoft Visual Studio\2017\Community\Common7\IDE\devenv.com"; & $CMD zstd.sln /upgrade
   - msbuild zstd.sln /p:Configuration=Debug /p:Platform=x64
   - msbuild zstd.sln /p:Configuration=Release /p:Platform=x64
 
 before_build:
   - md %APPVEYOR_BUILD_FOLDER%\build
   - cd %APPVEYOR_BUILD_FOLDER%\build
-  - if DEFINED CMAKE_PLATEFORM_NAME (set "PLATEFORM_OPT=-A %CMAKE_PLATEFORM_NAME%")
-  - cmake .. -G "%CMAKE_GENERATOR%" %PLATEFORM_OPT% %CMAKE_OPT% -DCMAKE_BUILD_TYPE=Debug -DOPTDBG=1 -DPORTABLE=1 -DSNAPPY=1 -DLZ4=1 -DZSTD=1 -DXPRESS=1 -DJNI=1
+  - cmake -G "Visual Studio 15 Win64" -DOPTDBG=1 -DPORTABLE=1 -DSNAPPY=1 -DLZ4=1 -DZSTD=1 -DXPRESS=1 -DJNI=1 ..
   - cd ..
-
 build:
   project: build\rocksdb.sln
   parallel: true
@@ -79,7 +60,7 @@ 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

buckifier/buckify_rocksdb.py

@@ -3,10 +3,6 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-try:
-    from builtins import str
-except ImportError:
-    from __builtin__ import str
 from targets_builder import TARGETSBuilder
 import json
 import os
@@ -112,9 +108,9 @@ def get_tests(repo_path):
 # Parse extra dependencies passed by user from command line
 def get_dependencies():
     deps_map = {
-        '': {
-            'extra_deps': [],
-            'extra_compiler_flags': []
+        ''.encode('ascii'): {
+            'extra_deps'.encode('ascii'): [],
+            'extra_compiler_flags'.encode('ascii'): []
         }
     }
     if len(sys.argv) < 2:
@@ -123,7 +119,13 @@ def get_dependencies():
     def encode_dict(data):
         rv = {}
         for k, v in data.items():
-            if isinstance(v, dict):
+            if isinstance(k, unicode):
+                k = k.encode('ascii')
+            if isinstance(v, unicode):
+                v = v.encode('ascii')
+            elif isinstance(v, list):
+                v = [x.encode('ascii') for x in v]
+            elif isinstance(v, dict):
                 v = encode_dict(v)
             rv[k] = v
         return rv
@@ -167,13 +169,6 @@ def generate_targets(repo_path, deps_map):
         src_mk.get("ANALYZER_LIB_SOURCES", []) +
         ["test_util/testutil.cc"],
         [":rocksdb_lib"])
-    # rocksdb_stress_lib
-    TARGETS.add_library(
-        "rocksdb_stress_lib",
-        src_mk.get("ANALYZER_LIB_SOURCES", [])
-        + src_mk.get('STRESS_LIB_SOURCES', [])
-        + ["test_util/testutil.cc"],
-        [":rocksdb_lib", ":rocksdb_test_lib"])
 
     print("Extra dependencies:\n{0}".format(str(deps_map)))
     # test for every test we found in the Makefile

buckifier/check_buck_targets.sh

@@ -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

buckifier/targets_builder.py

@@ -3,12 +3,6 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-try:
-    from builtins import object
-    from builtins import str
-except ImportError:
-    from __builtin__ import object
-    from __builtin__ import str
 import targets_cfg
 
 def pretty_list(lst, indent=8):
@@ -24,7 +18,7 @@ def pretty_list(lst, indent=8):
     return res
 
 
-class TARGETSBuilder(object):
+class TARGETSBuilder:
     def __init__(self, path):
         self.path = path
         self.targets_file = open(path, 'w')

buckifier/targets_cfg.py

@@ -3,13 +3,7 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-
-rocksdb_target_header = """# This file \100generated by `python buckifier/buckify_rocksdb.py`
-# --> DO NOT EDIT MANUALLY <--
-# This file is a Facebook-specific integration for buck builds, so can
-# only be validated by Facebook employees.
-#
-load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
+rocksdb_target_header = """load("@fbcode_macros//build_defs:auto_headers.bzl", "AutoHeaders")
 load("@fbcode_macros//build_defs:cpp_library.bzl", "cpp_library")
 load(":defs.bzl", "test_binary")
 
@@ -38,7 +32,7 @@ ROCKSDB_EXTERNAL_DEPS = [
 ROCKSDB_OS_DEPS = [
     (
         "linux",
-        ["third-party//numa:numa", "third-party//liburing:uring"],
+        ["third-party//numa:numa"],
     ),
 ]
 
@@ -52,9 +46,7 @@ ROCKSDB_OS_PREPROCESSOR_FLAGS = [
             "-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX",
             "-DROCKSDB_RANGESYNC_PRESENT",
             "-DROCKSDB_SCHED_GETCPU_PRESENT",
-            "-DROCKSDB_IOURING_PRESENT",
             "-DHAVE_SSE42",
-            "-DLIBURING",
             "-DNUMA",
         ],
     ),

buckifier/util.py

@@ -6,16 +6,11 @@ from __future__ import absolute_import
 from __future__ import division
 from __future__ import print_function
 from __future__ import unicode_literals
-try:
-    from builtins import object
-except ImportError:
-    from __builtin__ import object
 import subprocess
-import sys
 import os
 import time
 
-class ColorString(object):
+class ColorString:
     """ Generate colorful strings on terminal """
     HEADER = '\033[95m'
     BLUE = '\033[94m'
@@ -26,13 +21,7 @@ class ColorString(object):
 
     @staticmethod
     def _make_color_str(text, color):
-        # In Python2, default encoding for unicode string is ASCII
-        if sys.version_info.major <= 2:
-            return "".join(
-                [color, text.encode('utf-8'), ColorString.ENDC])
-        # From Python3, default encoding for unicode string is UTF-8
-        return "".join(
-            [color, text, ColorString.ENDC])
+        return "".join([color, text.encode('utf-8'), ColorString.ENDC])
 
     @staticmethod
     def ok(text):

build_tools/RocksDBCommonHelper.php

@@ -0,0 +1,377 @@
+<?php
+// Copyright 2004-present Facebook. 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).
+
+// Name of the environment variables which need to be set by the entity which
+// triggers continuous runs so that code at the end of the file gets executed
+// and Sandcastle run starts.
+const ENV_POST_RECEIVE_HOOK = "POST_RECEIVE_HOOK";
+const ENV_HTTPS_APP_VALUE = "HTTPS_APP_VALUE";
+const ENV_HTTPS_TOKEN_VALUE = "HTTPS_TOKEN_VALUE";
+
+const PRIMARY_TOKEN_FILE = '/home/krad/.sandcastle';
+const CONT_RUN_ALIAS = "leveldb";
+
+//////////////////////////////////////////////////////////////////////
+/*  Run tests in sandcastle */
+function postURL($diffID, $url) {
+  assert(strlen($diffID) > 0);
+  assert(is_numeric($diffID));
+  assert(strlen($url) > 0);
+
+  $cmd_args = array(
+    'diff_id' => (int)$diffID,
+    'name' => sprintf(
+      'click here for sandcastle tests for D%d',
+      (int)$diffID
+    ),
+    'link' => $url
+  );
+  $cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
+         . ' | arc call-conduit differential.updateunitresults';
+
+  shell_exec($cmd);
+}
+
+function buildUpdateTestStatusCmd($diffID, $test, $status) {
+  assert(strlen($diffID) > 0);
+  assert(is_numeric($diffID));
+  assert(strlen($test) > 0);
+  assert(strlen($status) > 0);
+
+  $cmd_args = array(
+    'diff_id' => (int)$diffID,
+    'name' => $test,
+    'result' => $status
+  );
+
+  $cmd = 'echo ' . escapeshellarg(json_encode($cmd_args))
+         . ' | arc call-conduit differential.updateunitresults';
+
+  return $cmd;
+}
+
+function updateTestStatus($diffID, $test) {
+  assert(strlen($diffID) > 0);
+  assert(is_numeric($diffID));
+  assert(strlen($test) > 0);
+
+  shell_exec(buildUpdateTestStatusCmd($diffID, $test, "waiting"));
+}
+
+function getSteps($applyDiff, $diffID, $username, $test) {
+  assert(strlen($username) > 0);
+  assert(strlen($test) > 0);
+
+  if ($applyDiff) {
+    assert(strlen($diffID) > 0);
+    assert(is_numeric($diffID));
+
+    $arcrc_content = (PHP_OS == "Darwin" ?
+        exec("cat ~/.arcrc | gzip -f | base64") :
+            exec("cat ~/.arcrc | gzip -f | base64 -w0"));
+    assert(strlen($arcrc_content) > 0);
+
+    // Sandcastle machines don't have arc setup. We copy the user certificate
+    // and authenticate using that in Sandcastle.
+    $setup = array(
+      "name" => "Setup arcrc",
+      "shell" => "echo " . escapeshellarg($arcrc_content) . " | base64 --decode"
+                 . " | gzip -d > ~/.arcrc",
+      "user" => "root"
+    );
+
+    // arc demands certain permission on its config.
+    // also fix the sticky bit issue in sandcastle
+    $fix_permission = array(
+      "name" => "Fix environment",
+      "shell" => "chmod 600 ~/.arcrc && chmod +t /dev/shm",
+      "user" => "root"
+    );
+
+    // Construct the steps in the order of execution.
+    $steps[] = $setup;
+    $steps[] = $fix_permission;
+  }
+
+  // fbcode is a sub-repo. We cannot patch until we add it to ignore otherwise
+  // Git thinks it is an uncommitted change.
+  $fix_git_ignore = array(
+    "name" => "Fix git ignore",
+    "shell" => "echo fbcode >> .git/info/exclude",
+    "user" => "root"
+  );
+
+  // This fixes "FATAL: ThreadSanitizer can not mmap the shadow memory"
+  // Source:
+  // https://github.com/google/sanitizers/wiki/ThreadSanitizerCppManual#FAQ
+  $fix_kernel_issue = array(
+    "name" => "Fix kernel issue with tsan",
+    "shell" => "echo 2 >/proc/sys/kernel/randomize_va_space",
+    "user" => "root"
+  );
+
+  $steps[] = $fix_git_ignore;
+  $steps[] = $fix_kernel_issue;
+
+  // This will be the command used to execute particular type of tests.
+  $cmd = "";
+
+  if ($applyDiff) {
+    // Patch the code (keep your fingures crossed).
+    $patch = array(
+      "name" => "Patch " . $diffID,
+      "shell" => "arc --arcrc-file ~/.arcrc "
+                  . "patch --nocommit --diff " . escapeshellarg($diffID),
+      "user" => "root"
+    );
+
+    $steps[] = $patch;
+
+    updateTestStatus($diffID, $test);
+    $cmd = buildUpdateTestStatusCmd($diffID, $test, "running") . "; ";
+  }
+
+  // Run the actual command.
+  $cmd = $cmd . "J=$(nproc) ./build_tools/precommit_checker.py " .
+           escapeshellarg($test) . "; exit_code=$?; ";
+
+  if ($applyDiff) {
+    $cmd = $cmd . "([[ \$exit_code -eq 0 ]] &&"
+                . buildUpdateTestStatusCmd($diffID, $test, "pass") . ")"
+                . "||" . buildUpdateTestStatusCmd($diffID, $test, "fail")
+                . "; ";
+  }
+
+  // shell command to sort the tests based on exit code and print
+  // the output of the log files.
+  $cat_sorted_logs = "
+    while read code log_file;
+      do echo \"################ cat \$log_file [exit_code : \$code] ################\";
+      cat \$log_file;
+    done < <(tail -n +2 LOG | sort -k7,7n -k4,4gr | awk '{print \$7,\$NF}')";
+
+  // Shell command to cat all log files
+  $cat_all_logs = "for f in `ls t/!(run-*)`; do echo \$f;cat \$f; done";
+
+  // If LOG file exist use it to cat log files sorted by exit code, otherwise
+  // cat everything
+  $logs_cmd = "if [ -f LOG ]; then {$cat_sorted_logs}; else {$cat_all_logs}; fi";
+
+  $cmd = $cmd . " cat /tmp/precommit-check.log"
+              . "; shopt -s extglob; {$logs_cmd}"
+              . "; shopt -u extglob; [[ \$exit_code -eq 0 ]]";
+  assert(strlen($cmd) > 0);
+
+  $run_test = array(
+    "name" => "Run " . $test,
+    "shell" => $cmd,
+    "user" => "root",
+    "parser" => "python build_tools/error_filter.py " . escapeshellarg($test),
+  );
+
+  $steps[] = $run_test;
+
+  if ($applyDiff) {
+    // Clean up the user arc config we are using.
+    $cleanup = array(
+      "name" => "Arc cleanup",
+      "shell" => "rm -f ~/.arcrc",
+      "user" => "root"
+    );
+
+    $steps[] = $cleanup;
+  }
+
+  assert(count($steps) > 0);
+  return $steps;
+}
+
+function getSandcastleConfig() {
+  $sandcastle_config = array();
+
+  $cwd = getcwd();
+  $cwd_token_file = "{$cwd}/.sandcastle";
+  // This is a case when we're executed from a continuous run. Fetch the values
+  // from the environment.
+  if (getenv(ENV_POST_RECEIVE_HOOK)) {
+    $sandcastle_config[0] = getenv(ENV_HTTPS_APP_VALUE);
+    $sandcastle_config[1] = getenv(ENV_HTTPS_TOKEN_VALUE);
+  } else {
+    // This is a typical `[p]arc diff` case. Fetch the values from the specific
+    // configuration files.
+    for ($i = 0; $i < 50; $i++) {
+      if (file_exists(PRIMARY_TOKEN_FILE) ||
+          file_exists($cwd_token_file)) {
+        break;
+      }
+      // If we failed to fetch the tokens, sleep for 0.2 second and try again
+      usleep(200000);
+    }
+    assert(file_exists(PRIMARY_TOKEN_FILE) ||
+           file_exists($cwd_token_file));
+
+    // Try the primary location first, followed by a secondary.
+    if (file_exists(PRIMARY_TOKEN_FILE)) {
+      $cmd = 'cat ' . PRIMARY_TOKEN_FILE;
+    } else {
+      $cmd = 'cat ' . escapeshellarg($cwd_token_file);
+    }
+
+    assert(strlen($cmd) > 0);
+    $sandcastle_config = explode(':', rtrim(shell_exec($cmd)));
+  }
+
+  // In this case be very explicit about the implications.
+  if (count($sandcastle_config) != 2) {
+    echo "Sandcastle configuration files don't contain valid information " .
+         "or the necessary environment variables aren't defined. Unable " .
+         "to validate the code changes.";
+    exit(1);
+  }
+
+  assert(strlen($sandcastle_config[0]) > 0);
+  assert(strlen($sandcastle_config[1]) > 0);
+  assert(count($sandcastle_config) > 0);
+
+  return $sandcastle_config;
+}
+
+// This function can be called either from `[p]arc diff` command or during
+// the Git post-receive hook.
+ function startTestsInSandcastle($applyDiff, $workflow, $diffID) {
+  // Default options don't terminate on failure, but that's what we want. In
+  // the current case we use assertions intentionally as "terminate on failure
+  // invariants".
+  assert_options(ASSERT_BAIL, true);
+
+  // In case of a diff we'll send notificatios to the author. Else it'll go to
+  // the entire team because failures indicate that build quality has regressed.
+  $username = $applyDiff ? exec("whoami") : CONT_RUN_ALIAS;
+  assert(strlen($username) > 0);
+
+  if ($applyDiff) {
+    assert($workflow);
+    assert(strlen($diffID) > 0);
+    assert(is_numeric($diffID));
+  }
+
+  // List of tests we want to run in Sandcastle.
+  $tests = array("unit", "unit_non_shm", "unit_481", "clang_unit", "tsan",
+                 "asan", "lite_test", "valgrind", "release", "release_481",
+                 "clang_release", "clang_analyze", "code_cov",
+                 "java_build", "no_compression", "unity", "ubsan");
+
+  $send_email_template = array(
+    'type' => 'email',
+    'triggers' => array('fail'),
+    'emails' => array($username . '@fb.com'),
+  );
+
+  // Construct a job definition for each test and add it to the master plan.
+  foreach ($tests as $test) {
+    $stepName = "RocksDB diff " . $diffID . " test " . $test;
+
+    if (!$applyDiff) {
+      $stepName = "RocksDB continuous integration test " . $test;
+    }
+
+    $arg[] = array(
+      "name" => $stepName,
+      "report" => array($send_email_template),
+      "steps" => getSteps($applyDiff, $diffID, $username, $test)
+    );
+  }
+
+  // We cannot submit the parallel execution master plan to Sandcastle and
+  // need supply the job plan as a determinator. So we construct a small job
+  // that will spit out the master job plan which Sandcastle will parse and
+  // execute. Why compress the job definitions? Otherwise we run over the max
+  // string size.
+  $cmd = "echo " . base64_encode(json_encode($arg))
+         . (PHP_OS == "Darwin" ?
+             " | gzip -f | base64" :
+                 " | gzip -f | base64 -w0");
+  assert(strlen($cmd) > 0);
+
+  $arg_encoded = shell_exec($cmd);
+  assert(strlen($arg_encoded) > 0);
+
+  $runName = "Run diff " . $diffID . "for user " . $username;
+
+  if (!$applyDiff) {
+    $runName = "RocksDB continuous integration build and test run";
+  }
+
+  $command = array(
+    "name" => $runName,
+    "steps" => array()
+  );
+
+  $command["steps"][] = array(
+    "name" => "Generate determinator",
+    "shell" => "echo " . $arg_encoded . " | base64 --decode | gzip -d"
+               . " | base64 --decode",
+    "determinator" => true,
+    "user" => "root"
+  );
+
+  // Submit to Sandcastle.
+  $url = 'https://interngraph.intern.facebook.com/sandcastle/create';
+
+  $job = array(
+    'command' => 'SandcastleUniversalCommand',
+    'args' => $command,
+    'capabilities' => array(
+      'vcs' => 'rocksdb-int-git',
+      'type' => 'lego',
+    ),
+    'hash' => 'origin/master',
+    'user' => $username,
+    'alias' => 'rocksdb-precommit',
+    'tags' => array('rocksdb'),
+    'description' => 'Rocksdb precommit job',
+  );
+
+  // Fetch the configuration necessary to submit a successful HTTPS request.
+  $sandcastle_config = getSandcastleConfig();
+
+  $app = $sandcastle_config[0];
+  $token = $sandcastle_config[1];
+
+  $cmd = 'curl -s -k '
+          . ' -F app=' . escapeshellarg($app)
+          . ' -F token=' . escapeshellarg($token)
+          . ' -F job=' . escapeshellarg(json_encode($job))
+          .' ' . escapeshellarg($url);
+
+  $output = shell_exec($cmd);
+  assert(strlen($output) > 0);
+
+  // Extract Sandcastle URL from the response.
+  preg_match('/url": "(.+)"/', $output, $sandcastle_url);
+
+  assert(count($sandcastle_url) > 0, "Unable to submit Sandcastle request.");
+  assert(strlen($sandcastle_url[1]) > 0, "Unable to extract Sandcastle URL.");
+
+  if ($applyDiff) {
+    echo "\nSandcastle URL: " . $sandcastle_url[1] . "\n";
+    // Ask Phabricator to display it on the diff UI.
+    postURL($diffID, $sandcastle_url[1]);
+  } else {
+    echo "Continuous integration started Sandcastle tests. You can look at ";
+    echo "the progress at:\n" . $sandcastle_url[1] . "\n";
+  }
+}
+
+// Continuous run cript will set the environment variable and based on that
+// we'll trigger the execution of tests in Sandcastle. In that case we don't
+// need to apply any diffs and there's no associated workflow either.
+if (getenv(ENV_POST_RECEIVE_HOOK)) {
+  startTestsInSandcastle(
+    false /* $applyDiff */,
+    NULL /* $workflow */,
+    NULL /* $diffID */);
+}

build_tools/build_detect_platform

@@ -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
@@ -152,21 +150,6 @@ case "$TARGET_OS" in
             PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -latomic"
         fi
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt"
-        if test $ROCKSDB_USE_IO_URING; then
-            # check for liburing
-            $CXX $CFLAGS -x c++ - -luring -o /dev/null 2>/dev/null  <<EOF
-              #include <liburing.h>
-              int main() {
-                struct io_uring ring;
-                io_uring_queue_init(1, &ring, 0);
-                return 0;
-              }
-EOF
-            if [ "$?" = 0 ]; then
-                PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -luring"
-                COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_IOURING_PRESENT"
-            fi
-        fi
         if test -z "$USE_FOLLY_DISTRIBUTED_MUTEX"; then
           USE_FOLLY_DISTRIBUTED_MUTEX=1
         fi
@@ -241,15 +224,10 @@ esac
 PLATFORM_CXXFLAGS="$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 $ROCKSDB_DISABLE_FALLOCATE; then
@@ -430,23 +408,7 @@ EOF
             COMMON_FLAGS="$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 +493,6 @@ 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 $PLATFORM_CXXFLAGS -faligned-new -x c++ - -o /dev/null 2>/dev/null <<EOF
@@ -624,8 +572,6 @@ if test "$TRY_SSE_ETC"; then
   TRY_SSE42="-msse4.2"
   # PCLMUL available since westmere, ca. 2010-2011
   TRY_PCLMUL="-mpclmul"
-  # AVX2 available since haswell, ca. 2013-2015
-  TRY_AVX2="-mavx2"
 fi
 
 $CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_SSE42 -x c++ - -o /dev/null 2>/dev/null <<EOF
@@ -659,34 +605,6 @@ elif test "$USE_SSE"; then
   echo "warning: USE_SSE specified but compiler could not use PCLMUL intrinsics, disabling" >&2
 fi
 
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS $TRY_AVX2 -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  #include <immintrin.h>
-  int main() {
-    const auto a = _mm256_setr_epi32(0, 1, 2, 3, 4, 7, 6, 5);
-    const auto b = _mm256_permutevar8x32_epi32(a, a);
-    (void)b;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS $TRY_AVX2 -DHAVE_AVX2"
-elif test "$USE_SSE"; then
-  echo "warning: USE_SSE specified but compiler could not use AVX2 intrinsics, disabling" >&2
-fi
-
-$CXX $PLATFORM_CXXFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null <<EOF
-  #include <cstdint>
-  int main() {
-    uint64_t a = 0xffffFFFFffffFFFF;
-    __uint128_t b = __uint128_t(a) * a;
-    a = static_cast<uint64_t>(b >> 64);
-    (void)a;
-  }
-EOF
-if [ "$?" = 0 ]; then
-  COMMON_FLAGS="$COMMON_FLAGS -DHAVE_UINT128_EXTENSION"
-fi
-
 # iOS doesn't support thread-local storage, but this check would erroneously
 # succeed because the cross-compiler flags are added by the Makefile, not this
 # script.
@@ -705,7 +623,6 @@ EOF
   fi
 fi
 
-
 if [ "$FBCODE_BUILD" != "true" -a "$PLATFORM" = OS_LINUX ]; then
   $CXX $COMMON_FLAGS $PLATFORM_SHARED_CFLAGS -x c++ -c - -o test_dl.o 2>/dev/null <<EOF
   void dummy_func() {}
@@ -734,7 +651,6 @@ echo "PLATFORM=$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"

build_tools/cont_integration.sh

@@ -0,0 +1,137 @@
+#!/usr/bin/env bash
+#
+# Copyright (c) 2016, Facebook. All rights reserved.
+#
+# Overall wrapper script for RocksDB continuous builds. The implementation is a
+# trivial pulling scheme. We loop infinitely, check if any new changes have been
+# committed, if yes then trigger a Sandcastle run, and finally go to sleep again
+# for a certain interval.
+#
+
+SRC_GIT_REPO=/data/git/rocksdb-public
+error=0
+
+function log {
+  DATE=`date +%Y-%m-%d:%H:%M:%S`
+  # shellcheck disable=SC2068
+  echo $DATE $@
+}
+
+function log_err {
+  # shellcheck disable=SC2145
+  log "ERROR: $@ Error code: $error."
+}
+
+function update_repo_status {
+  # Update the parent first.
+  pushd $SRC_GIT_REPO
+
+  # This is a fatal error. Something in the environment isn't right and we will
+  # terminate the execution.
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "Where is $SRC_GIT_REPO?"
+    exit $error
+  fi
+
+  HTTPS_PROXY=fwdproxy:8080 git fetch -f
+
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "git fetch -f failed."
+    popd
+    return $error
+  fi
+
+  git update-ref refs/heads/master refs/remotes/origin/master
+
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "git update-ref failed."
+    popd
+    return $error
+  fi
+
+  popd
+
+  # We're back in an instance-specific directory. Get the latest changes.
+  git pull --rebase
+
+  error=$?
+  if [ ! $error -eq 0 ]; then
+    log_err "git pull --rebase failed."
+    return $error
+  fi
+}
+
+#
+# Execution starts here.
+#
+
+# Path to the determinator from the root of the RocksDB repo.
+CONTRUN_DETERMINATOR=./build_tools/RocksDBCommonHelper.php
+
+# Value of the previous commit.
+PREV_COMMIT=
+
+log "Starting to monitor for new RocksDB changes ..."
+log "Running under `pwd` as `whoami`."
+
+# Paranoia. Make sure that we're using the right branch.
+git checkout master
+
+error=$?
+if [ ! $error -eq 0 ]; then
+  log_err "This is not good. Can't checkout master. Bye-bye!"
+  exit 1
+fi
+
+# We'll run forever and let the execution environment terminate us if we'll
+# exceed whatever timeout is set for the job.
+while true;
+do
+  # Get the latest changes committed.
+  update_repo_status
+
+  error=$?
+  if [  $error -eq 0 ]; then
+    LAST_COMMIT=`git log -1 | head -1 | grep commit | awk '{ print $2; }'`
+
+    log "Last commit is '$LAST_COMMIT', previous commit is '$PREV_COMMIT'."
+
+    if [ "$PREV_COMMIT" == "$LAST_COMMIT" ]; then
+      log "There were no changes since the last time I checked. Going to sleep."
+    else
+      if [ ! -z "$LAST_COMMIT" ]; then
+        log "New code has been committed or previous commit not known. " \
+            "Will trigger the tests."
+
+        PREV_COMMIT=$LAST_COMMIT
+        log "Updated previous commit to '$PREV_COMMIT'."
+
+        #
+        # This is where we'll trigger the Sandcastle run. The values for
+        # HTTPS_APP_VALUE and HTTPS_APP_VALUE will be set in the container we're
+        # running in.
+        #
+        POST_RECEIVE_HOOK=1 php $CONTRUN_DETERMINATOR
+
+        error=$?
+        if [ $error -eq 0 ]; then
+          log "Sandcastle run successfully triggered."
+        else
+          log_err "Failed to trigger Sandcastle run."
+        fi
+      else
+        log_err "Previous commit not updated. Don't know what the last one is."
+      fi
+    fi
+  else
+    log_err "Getting latest changes failed. Will skip running tests for now."
+  fi
+
+  # Always sleep, even if errors happens while trying to determine the latest
+  # commit. This will prevent us terminating in case of transient errors.
+  log "Will go to sleep for 5 minutes."
+  sleep 5m
+done

build_tools/dependencies.sh

@@ -1,19 +1,19 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/5.x/centos7-native/c447969
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/1bd23f9917738974ad0ff305aa23eb5f93f18305/9.0.0/centos7-native/c9f9104
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/5.x/gcc-5-glibc-2.23/339d858
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.23/gcc-5-glibc-2.23/ca1d1c0
+GCC_BASE=/mnt/gvfs/third-party2/gcc/112ec378fec7002ad3e09afde022e656049f7191/5.x/centos7-native/c447969
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/04999bdb3ce81a11073535dcb00b5e13dc1cbaf5/stable/centos7-native/c9f9104
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/92b0c8e5c8eecc71eb042594ce1ab3413799b385/5.x/gcc-5-glibc-2.23/339d858
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/3d8698d5973ba94f41620a80a67e4457fdf01e90/2.23/gcc-5-glibc-2.23/ca1d1c0
 SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/gcc-5-glibc-2.23/9bc6787
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/gcc-5-glibc-2.23/9bc6787
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/22c2d65676fb7c23cfa797c4f6937f38b026f3cf/1.2.8/gcc-5-glibc-2.23/9bc6787
 BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/gcc-5-glibc-2.23/9bc6787
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/gcc-5-glibc-2.23/9bc6787
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/gcc-5-glibc-2.23/03859b5
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/907b498203d297947f3bb70b9466f47e100f1873/r131/gcc-5-glibc-2.23/9bc6787
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/af6628a46758f1a15484a1760cd7294164bc5ba1/1.3.5/gcc-5-glibc-2.23/03859b5
 GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/gcc-5-glibc-2.23/9bc6787
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/gcc-5-glibc-2.23/0c8f76d
-NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/gcc-5-glibc-2.23/9bc6787
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/gcc-5-glibc-2.23/b443de1
-TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/gcc-5-glibc-2.23/9bc6787
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/2e3cb7d119b3cea5f1e738cc13a1ac69f49eb875/2.29.1/centos7-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/gcc-5-glibc-2.23/9bc6787
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/b1a0e56c1e3e6929813a4331ade3a58ff083afbb/master/gcc-5-glibc-2.23/aa64d6b
+NUMA_BASE=/mnt/gvfs/third-party2/numa/9cbf2460284c669ed19c3ccb200a71f7dd7e53c7/2.0.11/gcc-5-glibc-2.23/9bc6787
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/bf3d7497fe4e6d007354f0adffa16ce3003f8338/1.3/gcc-5-glibc-2.23/b443de1
+TBB_BASE=/mnt/gvfs/third-party2/tbb/ff4e0b093534704d8abab678a4fd7f5ea7b094c7/2018_U5/gcc-5-glibc-2.23/9bc6787
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/b5c4a61a5c483ba24722005ae07895971a2ac707/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/55031de95a2b46c82948743419a603b3d6aefe28/2.29.1/centos7-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/f3f697a28122e6bcd513273dd9c1ff23852fc59f/3.13.0/gcc-5-glibc-2.23/9bc6787
 LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.2.3/gcc-5-glibc-2.23/65372bd

build_tools/dependencies_platform007.sh

@@ -1,20 +1,19 @@
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
-GCC_BASE=/mnt/gvfs/third-party2/gcc/7331085db891a2ef4a88a48a751d834e8d68f4cb/7.x/centos7-native/b2ef2b6
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/963d9aeda70cc4779885b1277484fe7544a04e3e/9.0.0/platform007/9e92d53/
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/6ace84e956873d53638c738b6f65f3f469cca74c/7.x/platform007/5620abc
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/192b0f42d63dcf6210d6ceae387b49af049e6e0c/2.26/platform007/f259413
+GCC_BASE=/mnt/gvfs/third-party2/gcc/6e8e715624fd15256a7970073387793dfcf79b46/7.x/centos7-native/b2ef2b6
+CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/ef37e1faa1c29782abfac1ae65a291b9b7966f6d/stable/centos7-native/c9f9104
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/c67031f0f739ac61575a061518d6ef5038f99f90/7.x/platform007/5620abc
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/60d6f124a78798b73944f5ba87c2306ae3460153/2.26/platform007/f259413
 SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/7f9bdaada18f59bc27ec2b0871eb8a6144343aef/1.1.3/platform007/ca4da3d
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2d9f0b9a4274cc21f61272a9e89bdb859bce8f1f/1.2.8/platform007/ca4da3d
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/22c2d65676fb7c23cfa797c4f6937f38b026f3cf/1.2.8/platform007/ca4da3d
 BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/dc49a21c5fceec6456a7a28a94dcd16690af1337/1.0.6/platform007/ca4da3d
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/0f607f8fc442ea7d6b876931b1898bb573d5e5da/1.9.1/platform007/ca4da3d
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/ca22bc441a4eb709e9e0b1f9fec9750fed7b31c5/1.4.x/platform007/15a3614
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/907b498203d297947f3bb70b9466f47e100f1873/r131/platform007/ca4da3d
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/3ee276cbacfad3074e3f07bf826ac47f06970f4e/1.3.5/platform007/15a3614
 GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/0b9929d2588991c65a57168bf88aff2db87c5d48/2.2.0/platform007/ca4da3d
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/c26f08f47ac35fc31da2633b7da92d6b863246eb/master/platform007/c26c002
-NUMA_BASE=/mnt/gvfs/third-party2/numa/3f3fb57a5ccc5fd21c66416c0b83e0aa76a05376/2.0.11/platform007/ca4da3d
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/40c73d874898b386a71847f1b99115d93822d11f/1.4/platform007/6f3e0a9
-TBB_BASE=/mnt/gvfs/third-party2/tbb/4ce8e8dba77cdbd81b75d6f0c32fd7a1b76a11ec/2018_U5/platform007/ca4da3d
-LIBURING_BASE=/mnt/gvfs/third-party2/liburing/79427253fd0d42677255aacfe6d13bfe63f752eb/20190828/platform007/ca4da3d
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/fb251ecd2f5ae16f8671f7014c246e52a748fe0b/fb/platform007/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/ab9f09bba370e7066cafd4eb59752db93f2e8312/2.29.1/platform007/15a3614
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d42d152a15636529b0861ec493927200ebebca8e/3.15.0/platform007/ca4da3d
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/9c910d36d6235cc40e8ff559358f1833452300ca/master/platform007/5b0f53e
+NUMA_BASE=/mnt/gvfs/third-party2/numa/9cbf2460284c669ed19c3ccb200a71f7dd7e53c7/2.0.11/platform007/ca4da3d
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/bf3d7497fe4e6d007354f0adffa16ce3003f8338/1.3/platform007/6f3e0a9
+TBB_BASE=/mnt/gvfs/third-party2/tbb/ff4e0b093534704d8abab678a4fd7f5ea7b094c7/2018_U5/platform007/ca4da3d
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/b5c4a61a5c483ba24722005ae07895971a2ac707/fb/platform007/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/92ff90349e2f43ea0a8246d8b1cf17b6869013e3/2.29.1/centos7-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/f3f697a28122e6bcd513273dd9c1ff23852fc59f/3.13.0/platform007/ca4da3d
 LUA_BASE=/mnt/gvfs/third-party2/lua/f0cd714433206d5139df61659eb7b28b1dea6683/5.3.4/platform007/5007832

build_tools/error_filter.py

@@ -133,16 +133,13 @@ _TEST_NAME_TO_PARSERS = {
     'lite_test': [CompilerErrorParser, GTestErrorParser],
     'stress_crash': [CompilerErrorParser, DbCrashErrorParser],
     'stress_crash_with_atomic_flush': [CompilerErrorParser, DbCrashErrorParser],
-    'stress_crash_with_txn': [CompilerErrorParser, DbCrashErrorParser],
     'write_stress': [CompilerErrorParser, WriteStressErrorParser],
     'asan': [CompilerErrorParser, GTestErrorParser, AsanErrorParser],
     'asan_crash': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
     'asan_crash_with_atomic_flush': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
-    'asan_crash_with_txn': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
     'ubsan': [CompilerErrorParser, GTestErrorParser, UbsanErrorParser],
     'ubsan_crash': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
     'ubsan_crash_with_atomic_flush': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
-    'ubsan_crash_with_txn': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
     'valgrind': [CompilerErrorParser, GTestErrorParser, ValgrindErrorParser],
     'tsan': [CompilerErrorParser, GTestErrorParser, TsanErrorParser],
     'format_compatible': [CompilerErrorParser, CompatErrorParser],

build_tools/fbcode_config_platform007.sh

@@ -86,15 +86,6 @@ else
 fi
 CFLAGS+=" -DTBB"
 
-# location of LIBURING
-LIBURING_INCLUDE=" -isystem $LIBURING_BASE/include/"
-if test -z $PIC_BUILD; then
-  LIBURING_LIBS="$LIBURING_BASE/lib/liburing.a"
-else
-  LIBURING_LIBS="$LIBURING_BASE/lib/liburing_pic.a"
-fi
-CFLAGS+=" -DLIBURING"
-
 test "$USE_SSE" || USE_SSE=1
 export USE_SSE
 test "$PORTABLE" || PORTABLE=1
@@ -103,7 +94,7 @@ export PORTABLE
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
 
-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE $LIBURING_INCLUDE"
+DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE"
 
 STDLIBS="-L $GCC_BASE/lib64"
 
@@ -144,10 +135,10 @@ else
 fi
 
 CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42 -DROCKSDB_IOURING_PRESENT"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE -DROCKSDB_RANGESYNC_PRESENT -DROCKSDB_SCHED_GETCPU_PRESENT -DROCKSDB_SUPPORT_THREAD_LOCAL -DHAVE_SSE42"
 CXXFLAGS+=" $CFLAGS"
 
-EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS $LIBURING_LIBS"
+EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"
 EXEC_LDFLAGS+=" -B$BINUTILS/gold"
 EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/platform007/lib/ld.so"
 EXEC_LDFLAGS+=" $LIBUNWIND"
@@ -157,7 +148,7 @@ EXEC_LDFLAGS+=" -ldl"
 
 PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
 
-EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $TBB_LIBS $LIBURING_LIBS"
+EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $TBB_LIBS"
 
 VALGRIND_VER="$VALGRIND_BASE/bin/"
 

build_tools/format-diff.sh

@@ -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 +10,13 @@ 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 "Then, move both files (i.e. ${CLANG_FORMAT_DIFF} and clang-format) to some directory within PATH=${PATH}"
+  exit 128
 fi
 
 # Check argparse, a library that clang-format-diff.py requires.
@@ -93,25 +54,15 @@ fi
 set -e
 
 uncommitted_code=`git diff HEAD`
+LAST_MASTER=`git merge-base master HEAD`
 
 # If there's no uncommitted changes, we assume user are doing post-commit
-# format check, in which case we'll try to check the modified lines vs. the
-# facebook/rocksdb.git master branch. Otherwise, we'll check format of the
-# uncommitted code only.
+# format check, in which case we'll check the modified lines since last commit
+# from master. Otherwise, we'll check format of the uncommitted code only.
 if [ -z "$uncommitted_code" ]
 then
-  # Attempt to get name of facebook/rocksdb.git remote.
-  [ "$FORMAT_REMOTE" ] || FORMAT_REMOTE="$(git remote -v | grep 'facebook/rocksdb.git' | head -n 1 | cut -f 1)"
-  # Fall back on 'origin' if that fails
-  [ "$FORMAT_REMOTE" ] || FORMAT_REMOTE=origin
-  # Use master branch from that remote
-  [ "$FORMAT_UPSTREAM" ] || FORMAT_UPSTREAM="$FORMAT_REMOTE/master"
-  # Get the common ancestor with that remote branch. Everything after that
-  # common ancestor would be considered the contents of a pull request, so
-  # should be relevant for formatting fixes.
-  FORMAT_UPSTREAM_MERGE_BASE="$(git merge-base "$FORMAT_UPSTREAM" HEAD)"
-  # Get the differences
-  diffs=$(git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -p 1)
+  # Check the format of last commit
+  diffs=$(git diff -U0 $LAST_MASTER^ | $CLANG_FORMAT_DIFF -p 1)
 else
   # Check the format of uncommitted lines,
   diffs=$(git diff -U0 HEAD | $CLANG_FORMAT_DIFF -p 1)
@@ -121,20 +72,16 @@ if [ -z "$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
 COLOR_END="\033[0m"
-COLOR_RED="\033[0;31m"
-COLOR_GREEN="\033[0;32m"
+COLOR_RED="\033[0;31m" 
+COLOR_GREEN="\033[0;32m" 
 
 echo -e "Detect lines that doesn't follow the format rules:\r"
 # Add the color to the diff. lines added will be green; lines removed will be red.
-echo "$diffs" |
+echo "$diffs" | 
   sed -e "s/\(^-.*$\)/`echo -e \"$COLOR_RED\1$COLOR_END\"`/" |
   sed -e "s/\(^+.*$\)/`echo -e \"$COLOR_GREEN\1$COLOR_END\"`/"
 
@@ -157,9 +104,9 @@ fi
 # Do in-place format adjustment.
 if [ -z "$uncommitted_code" ]
 then
-  git diff -U0 "$FORMAT_UPSTREAM_MERGE_BASE" | $CLANG_FORMAT_DIFF -i -p 1
+  git diff -U0 $LAST_MASTER^ | $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!"
 

build_tools/gnu_parallel

@@ -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

build_tools/precommit_checker.py

@@ -1,4 +1,4 @@
-#!/usr/bin/env python2.7
+#!/usr/local/fbcode/gcc-4.9-glibc-2.20-fb/bin/python2.7
 # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
 
 from __future__ import absolute_import

build_tools/regression_build_test.sh

@@ -378,7 +378,7 @@ function send_to_ods {
     echo >&2 "ERROR: Key $key doesn't have a value."
     return
   fi
-  curl --silent "https://www.intern.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build$git_br&key=$key&value=$value" \
+  curl -s "https://www.intern.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build$git_br&key=$key&value=$value" \
     --connect-timeout 60
 }
 

build_tools/rocksdb-lego-determinator

@@ -414,8 +414,7 @@ STRESS_CRASH_TEST_COMMANDS="[
                 'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test || $CONTRUN_NAME=crash_test $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
-            },
-            $UPLOAD_DB_DIR,
+            }
         ],
         $REPORT
     }
@@ -451,36 +450,6 @@ STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
     }
 ]"
 
-#
-# RocksDB stress/crash test with txn
-#
-STRESS_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb Stress and Crash Test with txn',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            {
-                'name':'Build and run RocksDB debug crash tests with txn',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 crash_test_with_txn || $CONTRUN_NAME=crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
 # RocksDB write stress test.
 # We run on disk device on purpose (i.e. no $SHM)
 # because we want to add some randomness to fsync commands
@@ -543,7 +512,6 @@ ASAN_CRASH_TEST_COMMANDS="[
                 'user':'root',
                 $PARSER
             },
-            $UPLOAD_DB_DIR,
         ],
         $REPORT
     }
@@ -573,30 +541,6 @@ ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
     }
 ]"
 
-#
-# RocksDB crash testing with txn under address sanitizer
-#
-ASAN_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with txn under ASAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug asan_crash_test_with_txn',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 asan_crash_test_with_txn || $CONTRUN_NAME=asan_crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB test under undefined behavior sanitizer
 #
@@ -609,7 +553,7 @@ UBSAN_TEST_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Test RocksDB debug under UBSAN',
-                'shell':'set -o pipefail && $SHM $UBSAN $CLANG $DEBUG make $PARALLELISM ubsan_check || $CONTRUN_NAME=ubsan_check $TASK_CREATION_TOOL',
+                'shell':'set -o pipefail && $SHM $UBSAN $DEBUG make $PARALLELISM ubsan_check || $CONTRUN_NAME=ubsan_check $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             }
@@ -632,11 +576,10 @@ UBSAN_CRASH_TEST_COMMANDS="[
             {
                 'name':'Build and run RocksDB debug ubsan_crash_test',
                 'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
-            $UPLOAD_DB_DIR,
         ],
         $REPORT
     }
@@ -656,31 +599,7 @@ UBSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
             {
                 'name':'Build and run RocksDB debug ubsan_crash_test_with_atomic_flush',
                 'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test_with_atomic_flush || $CONTRUN_NAME=ubsan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash testing with txn under undefined behavior sanitizer
-#
-UBSAN_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb crash test with txn under UBSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug ubsan_crash_test_with_txn',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG $NON_TSAN_CRASH $CLANG make J=1 ubsan_crash_test_with_txn || $CONTRUN_NAME=ubsan_crash_test_with_txn $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG $NON_TSAN_CRASH make J=1 ubsan_crash_test_with_atomic_flush || $CONTRUN_NAME=ubsan_crash_test_with_atomic_flush $TASK_CREATION_TOOL',
                 'user':'root',
                 $PARSER
             },
@@ -754,7 +673,6 @@ TSAN_CRASH_TEST_COMMANDS="[
                 'user':'root',
                 $PARSER
             },
-            $UPLOAD_DB_DIR,
         ],
         $REPORT
     }
@@ -784,30 +702,6 @@ TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS="[
     }
 ]"
 
-#
-# RocksDB crash test with txn under TSAN
-#
-TSAN_CRASH_TEST_WITH_TXN_COMMANDS="[
-    {
-        'name':'Rocksdb Crash Test with txn under TSAN',
-        'oncall':'$ONCALL',
-        'executeLocal': 'true',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Compile and run',
-                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN $TSAN_CRASH CRASH_TEST_KILL_ODD=1887 make J=1 crash_test_with_txn || $CONTRUN_NAME=tsan_crash_test_with_txn $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-            $UPLOAD_DB_DIR,
-        ],
-        $REPORT
-    }
-]"
-
 #
 # RocksDB format compatible
 #
@@ -818,8 +712,6 @@ run_format_compatible()
   rm -rf /dev/shm/rocksdb
   mkdir /dev/shm/rocksdb
 
-  export https_proxy="fwdproxy:8080"
-  
   tools/check_format_compatible.sh
 }
 
@@ -886,7 +778,7 @@ run_regression()
 
   # parameters: $1 -- key, $2 -- value
   function send_size_to_ods {
-    curl --silent "https://www.intern.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build&key=rocksdb.build_size.$1&value=$2" \
+    curl -s "https://www.intern.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build&key=rocksdb.build_size.$1&value=$2" \
       --connect-timeout 60
   }
 
@@ -997,9 +889,6 @@ case $1 in
   stress_crash_with_atomic_flush)
     echo $STRESS_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
     ;;
-  stress_crash_with_txn)
-    echo $STRESS_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   write_stress)
     echo $WRITE_STRESS_COMMANDS
     ;;
@@ -1012,9 +901,6 @@ case $1 in
   asan_crash_with_atomic_flush)
     echo $ASAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
     ;;
-  asan_crash_with_txn)
-    echo $ASAN_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   ubsan)
     echo $UBSAN_TEST_COMMANDS
     ;;
@@ -1024,9 +910,6 @@ case $1 in
   ubsan_crash_with_atomic_flush)
     echo $UBSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
     ;;
-  ubsan_crash_with_txn)
-    echo $UBSAN_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   valgrind)
     echo $VALGRIND_TEST_COMMANDS
     ;;
@@ -1039,9 +922,6 @@ case $1 in
   tsan_crash_with_atomic_flush)
     echo $TSAN_CRASH_TEST_WITH_ATOMIC_FLUSH_COMMANDS
     ;;
-  tsan_crash_with_txn)
-    echo $TSAN_CRASH_TEST_WITH_TXN_COMMANDS
-    ;;
   format_compatible)
     echo $FORMAT_COMPATIBLE_COMMANDS
     ;;
@@ -1065,6 +945,5 @@ case $1 in
     ;;
   *)
     echo "Invalid determinator command"
-    exit 1
     ;;
 esac

build_tools/setup_centos7.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

build_tools/update_dependencies.sh

@@ -6,12 +6,6 @@
 BASEDIR=$(dirname $0)
 OUTPUT=""
 
-function log_header()
-{
-  echo "# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved." >> "$OUTPUT"
-}
-
-
 function log_variable()
 {
   echo "$1=${!1}" >> "$OUTPUT"
@@ -75,7 +69,6 @@ echo "Writing dependencies to $OUTPUT"
 GCC_BASE=`readlink -f $TP2_LATEST/gcc/7.x/centos7-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`
 
-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE
 
@@ -92,7 +85,6 @@ get_lib_base jemalloc   LATEST  platform007
 get_lib_base numa       LATEST  platform007
 get_lib_base libunwind  LATEST  platform007
 get_lib_base tbb        LATEST  platform007
-get_lib_base liburing   LATEST  platform007
 
 get_lib_base kernel-headers fb platform007
 get_lib_base binutils   LATEST centos7-native
@@ -116,7 +108,6 @@ echo "Writing dependencies to $OUTPUT"
 GCC_BASE=`readlink -f $TP2_LATEST/gcc/5.x/centos7-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos7-native/*/`
 
-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE
 
@@ -156,7 +147,6 @@ echo "Writing 4.8.1 dependencies to $OUTPUT"
 GCC_BASE=`readlink -f $TP2_LATEST/gcc/4.8.1/centos6-native/*/`
 CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`
 
-log_header
 log_variable GCC_BASE
 log_variable CLANG_BASE
 

cache/cache.cc

@@ -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

cache/cache_bench.cc

@@ -11,66 +11,59 @@ int main() {
 }
 #else
 
-#include <stdio.h>
-#include <sys/types.h>
 #include <cinttypes>
-#include <limits>
+#include <sys/types.h>
+#include <stdio.h>
 
 #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, "");
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 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_) {
@@ -192,31 +138,30 @@ 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);
     }
   }
 
   bool Run() {
-    ROCKSDB_NAMESPACE::Env* env = ROCKSDB_NAMESPACE::Env::Default();
+    rocksdb::Env* env = rocksdb::Env::Default();
 
     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;
 
     {
@@ -280,82 +220,44 @@ 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");
   }
 };
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ParseCommandLineFlags(&argc, &argv, true);
@@ -365,11 +267,9 @@ int main(int argc, char** argv) {
     exit(1);
   }
 
-  ROCKSDB_NAMESPACE::CacheBench bench;
+  rocksdb::CacheBench bench;
   if (FLAGS_populate_cache) {
     bench.PopulateCache();
-    printf("Population complete\n");
-    printf("----------------------------\n");
   }
   if (bench.Run()) {
     return 0;

cache/cache_test.cc

@@ -20,7 +20,7 @@
 #include "util/coding.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 // Conversions between numeric keys/values and the types expected by Cache.
 static std::string EncodeKey(int k) {
@@ -86,22 +86,14 @@ class CacheTest : public testing::TestWithParam<std::string> {
     return nullptr;
   }
 
-  std::shared_ptr<Cache> NewCache(
-      size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-      CacheMetadataChargePolicy charge_policy = kDontChargeCacheMetadata) {
+  std::shared_ptr<Cache> NewCache(size_t capacity, int num_shard_bits,
+                                  bool strict_capacity_limit) {
     auto type = GetParam();
     if (type == kLRU) {
-      LRUCacheOptions co;
-      co.capacity = capacity;
-      co.num_shard_bits = num_shard_bits;
-      co.strict_capacity_limit = strict_capacity_limit;
-      co.high_pri_pool_ratio = 0;
-      co.metadata_charge_policy = charge_policy;
-      return NewLRUCache(co);
+      return NewLRUCache(capacity, num_shard_bits, strict_capacity_limit, 0.0);
     }
     if (type == kClock) {
-      return NewClockCache(capacity, num_shard_bits, strict_capacity_limit,
-                           charge_policy);
+      return NewClockCache(capacity, num_shard_bits, strict_capacity_limit);
     }
     return nullptr;
   }
@@ -151,15 +143,10 @@ class CacheTest : public testing::TestWithParam<std::string> {
 };
 CacheTest* CacheTest::current_;
 
-class LRUCacheTest : public CacheTest {};
-
 TEST_P(CacheTest, UsageTest) {
   // cache is std::shared_ptr and will be automatically cleaned up.
   const uint64_t kCapacity = 100000;
-  auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
-  auto precise_cache = NewCache(kCapacity, 0, false, kFullChargeCacheMetadata);
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
+  auto cache = NewCache(kCapacity, 8, false);
 
   size_t usage = 0;
   char value[10] = "abcdef";
@@ -168,45 +155,31 @@ TEST_P(CacheTest, UsageTest) {
     std::string key(i, 'a');
     auto kv_size = key.size() + 5;
     cache->Insert(key, reinterpret_cast<void*>(value), kv_size, dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), kv_size,
-                          dumbDeleter);
     usage += kv_size;
     ASSERT_EQ(usage, cache->GetUsage());
-    ASSERT_LT(usage, precise_cache->GetUsage());
   }
 
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
-
   // make sure the cache will be overloaded
   for (uint64_t i = 1; i < kCapacity; ++i) {
     auto key = ToString(i);
     cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
                   dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
-                          dumbDeleter);
   }
 
   // the usage should be close to the capacity
   ASSERT_GT(kCapacity, cache->GetUsage());
-  ASSERT_GT(kCapacity, precise_cache->GetUsage());
   ASSERT_LT(kCapacity * 0.95, cache->GetUsage());
-  ASSERT_LT(kCapacity * 0.95, precise_cache->GetUsage());
 }
 
 TEST_P(CacheTest, PinnedUsageTest) {
   // cache is std::shared_ptr and will be automatically cleaned up.
-  const uint64_t kCapacity = 200000;
-  auto cache = NewCache(kCapacity, 8, false, kDontChargeCacheMetadata);
-  auto precise_cache = NewCache(kCapacity, 8, false, kFullChargeCacheMetadata);
+  const uint64_t kCapacity = 100000;
+  auto cache = NewCache(kCapacity, 8, false);
 
   size_t pinned_usage = 0;
   char value[10] = "abcdef";
 
   std::forward_list<Cache::Handle*> unreleased_handles;
-  std::forward_list<Cache::Handle*> unreleased_handles_in_precise_cache;
 
   // Add entries. Unpin some of them after insertion. Then, pin some of them
   // again. Check GetPinnedUsage().
@@ -214,72 +187,40 @@ TEST_P(CacheTest, PinnedUsageTest) {
     std::string key(i, 'a');
     auto kv_size = key.size() + 5;
     Cache::Handle* handle;
-    Cache::Handle* handle_in_precise_cache;
     cache->Insert(key, reinterpret_cast<void*>(value), kv_size, dumbDeleter,
                   &handle);
-    assert(handle);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), kv_size,
-                          dumbDeleter, &handle_in_precise_cache);
-    assert(handle_in_precise_cache);
     pinned_usage += kv_size;
     ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-    ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
     if (i % 2 == 0) {
       cache->Release(handle);
-      precise_cache->Release(handle_in_precise_cache);
       pinned_usage -= kv_size;
       ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-      ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
     } else {
       unreleased_handles.push_front(handle);
-      unreleased_handles_in_precise_cache.push_front(handle_in_precise_cache);
     }
     if (i % 3 == 0) {
       unreleased_handles.push_front(cache->Lookup(key));
-      auto x = precise_cache->Lookup(key);
-      assert(x);
-      unreleased_handles_in_precise_cache.push_front(x);
       // If i % 2 == 0, then the entry was unpinned before Lookup, so pinned
       // usage increased
       if (i % 2 == 0) {
         pinned_usage += kv_size;
       }
       ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-      ASSERT_LT(pinned_usage, precise_cache->GetPinnedUsage());
     }
   }
-  auto precise_cache_pinned_usage = precise_cache->GetPinnedUsage();
-  ASSERT_LT(pinned_usage, precise_cache_pinned_usage);
 
   // check that overloading the cache does not change the pinned usage
   for (uint64_t i = 1; i < 2 * kCapacity; ++i) {
     auto key = ToString(i);
     cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
                   dumbDeleter);
-    precise_cache->Insert(key, reinterpret_cast<void*>(value), key.size() + 5,
-                          dumbDeleter);
   }
   ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-  ASSERT_EQ(precise_cache_pinned_usage, precise_cache->GetPinnedUsage());
-
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(pinned_usage, cache->GetPinnedUsage());
-  ASSERT_EQ(precise_cache_pinned_usage, precise_cache->GetPinnedUsage());
 
   // release handles for pinned entries to prevent memory leaks
   for (auto handle : unreleased_handles) {
     cache->Release(handle);
   }
-  for (auto handle : unreleased_handles_in_precise_cache) {
-    precise_cache->Release(handle);
-  }
-  ASSERT_EQ(0, cache->GetPinnedUsage());
-  ASSERT_EQ(0, precise_cache->GetPinnedUsage());
-  cache->EraseUnRefEntries();
-  precise_cache->EraseUnRefEntries();
-  ASSERT_EQ(0, cache->GetUsage());
-  ASSERT_EQ(0, precise_cache->GetUsage());
 }
 
 TEST_P(CacheTest, HitAndMiss) {
@@ -365,7 +306,7 @@ TEST_P(CacheTest, EvictionPolicy) {
   Insert(200, 201);
 
   // Frequently used entry must be kept around
-  for (int i = 0; i < kCacheSize * 2; i++) {
+  for (int i = 0; i < kCacheSize + 200; i++) {
     Insert(1000+i, 2000+i);
     ASSERT_EQ(101, Lookup(100));
   }
@@ -418,7 +359,7 @@ TEST_P(CacheTest, EvictionPolicyRef) {
   Insert(303, 104);
 
   // Insert entries much more than Cache capacity
-  for (int i = 0; i < kCacheSize * 2; i++) {
+  for (int i = 0; i < kCacheSize + 200; i++) {
     Insert(1000 + i, 2000 + i);
   }
 
@@ -609,10 +550,10 @@ TEST_P(CacheTest, SetCapacity) {
   }
 }
 
-TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
+TEST_P(CacheTest, SetStrictCapacityLimit) {
   // test1: set the flag to false. Insert more keys than capacity. See if they
   // all go through.
-  std::shared_ptr<Cache> cache = NewCache(5, 0, false);
+  std::shared_ptr<Cache> cache = NewLRUCache(5, 0, false);
   std::vector<Cache::Handle*> handles(10);
   Status s;
   for (size_t i = 0; i < 10; i++) {
@@ -638,7 +579,7 @@ TEST_P(LRUCacheTest, SetStrictCapacityLimit) {
   }
 
   // test3: init with flag being true.
-  std::shared_ptr<Cache> cache2 = NewCache(5, 0, true);
+  std::shared_ptr<Cache> cache2 = NewLRUCache(5, 0, true);
   for (size_t i = 0; i < 5; i++) {
     std::string key = ToString(i + 1);
     s = cache2->Insert(key, new Value(i + 1), 1, &deleter, &handles[i]);
@@ -756,16 +697,15 @@ TEST_P(CacheTest, GetCharge) {
 }
 
 #ifdef SUPPORT_CLOCK_CACHE
-std::shared_ptr<Cache> (*new_clock_cache_func)(
-    size_t, int, bool, CacheMetadataChargePolicy) = NewClockCache;
+std::shared_ptr<Cache> (*new_clock_cache_func)(size_t, int,
+                                               bool) = NewClockCache;
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest,
                         testing::Values(kLRU, kClock));
 #else
 INSTANTIATE_TEST_CASE_P(CacheTestInstance, CacheTest, testing::Values(kLRU));
 #endif  // SUPPORT_CLOCK_CACHE
-INSTANTIATE_TEST_CASE_P(CacheTestInstance, LRUCacheTest, testing::Values(kLRU));
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

cache/clock_cache.cc

@@ -11,16 +11,15 @@
 
 #ifndef SUPPORT_CLOCK_CACHE
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
-std::shared_ptr<Cache> NewClockCache(
-    size_t /*capacity*/, int /*num_shard_bits*/, bool /*strict_capacity_limit*/,
-    CacheMetadataChargePolicy /*metadata_charge_policy*/) {
+std::shared_ptr<Cache> NewClockCache(size_t /*capacity*/, int /*num_shard_bits*/,
+                                     bool /*strict_capacity_limit*/) {
   // Clock cache not supported.
   return nullptr;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 #else
 
@@ -36,12 +35,11 @@ std::shared_ptr<Cache> NewClockCache(
 #include "tbb/concurrent_hash_map.h"
 
 #include "cache/sharded_cache.h"
-#include "port/malloc.h"
 #include "port/port.h"
 #include "util/autovector.h"
 #include "util/mutexlock.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 namespace {
 
@@ -204,27 +202,6 @@ struct CacheHandle {
     deleter = a.deleter;
     return *this;
   }
-
-  inline static size_t CalcTotalCharge(
-      Slice key, size_t charge,
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    size_t meta_charge = 0;
-    if (metadata_charge_policy == kFullChargeCacheMetadata) {
-      meta_charge += sizeof(CacheHandle);
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-      meta_charge +=
-          malloc_usable_size(static_cast<void*>(const_cast<char*>(key.data())));
-#else
-      meta_charge += key.size();
-#endif
-    }
-    return charge + meta_charge;
-  }
-
-  inline size_t CalcTotalCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    return CalcTotalCharge(key, charge, metadata_charge_policy);
-  }
 };
 
 // Key of hash map. We store hash value with the key for convenience.
@@ -341,8 +318,7 @@ 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.
@@ -428,12 +404,11 @@ void ClockCacheShard::RecycleHandle(CacheHandle* handle,
   assert(!InCache(handle->flags) && CountRefs(handle->flags) == 0);
   context->to_delete_key.push_back(handle->key.data());
   context->to_delete_value.emplace_back(*handle);
-  size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
   handle->key.clear();
   handle->value = nullptr;
   handle->deleter = nullptr;
   recycle_.push_back(handle);
-  usage_.fetch_sub(total_charge, std::memory_order_relaxed);
+  usage_.fetch_sub(handle->charge, std::memory_order_relaxed);
 }
 
 void ClockCacheShard::Cleanup(const CleanupContext& context) {
@@ -459,8 +434,7 @@ bool ClockCacheShard::Ref(Cache::Handle* h) {
                                             std::memory_order_relaxed)) {
       if (CountRefs(flags) == 0) {
         // No reference count before the operation.
-        size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
-        pinned_usage_.fetch_add(total_charge, std::memory_order_relaxed);
+        pinned_usage_.fetch_add(handle->charge, std::memory_order_relaxed);
       }
       return true;
     }
@@ -480,8 +454,7 @@ bool ClockCacheShard::Unref(CacheHandle* handle, bool set_usage,
   assert(CountRefs(flags) > 0);
   if (CountRefs(flags) == 1) {
     // this is the last reference.
-    size_t total_charge = handle->CalcTotalCharge(metadata_charge_policy_);
-    pinned_usage_.fetch_sub(total_charge, std::memory_order_relaxed);
+    pinned_usage_.fetch_sub(handle->charge, std::memory_order_relaxed);
     // Cleanup if it is the last reference.
     if (!InCache(flags)) {
       MutexLock l(&mutex_);
@@ -565,12 +538,9 @@ 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);
-  size_t total_charge =
-      CacheHandle::CalcTotalCharge(key, charge, metadata_charge_policy_);
+    CleanupContext* context) {
   MutexLock l(&mutex_);
-  bool success = EvictFromCache(total_charge, context);
+  bool success = EvictFromCache(charge, context);
   bool strict = strict_capacity_limit_.load(std::memory_order_relaxed);
   if (!success && (strict || !hold_reference)) {
     context->to_delete_key.push_back(key.data());
@@ -599,16 +569,15 @@ 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);
   }
   table_.insert(HashTable::value_type(CacheKey(key, hash), handle));
   if (hold_reference) {
-    pinned_usage_.fetch_add(total_charge, std::memory_order_relaxed);
+    pinned_usage_.fetch_add(charge, std::memory_order_relaxed);
   }
-  usage_.fetch_add(total_charge, std::memory_order_relaxed);
+  usage_.fetch_add(charge, std::memory_order_relaxed);
   return handle;
 }
 
@@ -622,9 +591,8 @@ 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 +601,6 @@ 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;
 }
@@ -710,14 +674,10 @@ void ClockCacheShard::EraseUnRefEntries() {
 
 class ClockCache final : public ShardedCache {
  public:
-  ClockCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-             CacheMetadataChargePolicy metadata_charge_policy)
+  ClockCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit)
       : ShardedCache(capacity, num_shard_bits, strict_capacity_limit) {
     int num_shards = 1 << num_shard_bits;
     shards_ = new ClockCacheShard[num_shards];
-    for (int i = 0; i < num_shards; i++) {
-      shards_[i].set_metadata_charge_policy(metadata_charge_policy);
-    }
     SetCapacity(capacity);
     SetStrictCapacityLimit(strict_capacity_limit);
   }
@@ -754,16 +714,15 @@ class ClockCache final : public ShardedCache {
 
 }  // end anonymous namespace
 
-std::shared_ptr<Cache> NewClockCache(
-    size_t capacity, int num_shard_bits, bool strict_capacity_limit,
-    CacheMetadataChargePolicy metadata_charge_policy) {
+std::shared_ptr<Cache> NewClockCache(size_t capacity, int num_shard_bits,
+                                     bool strict_capacity_limit) {
   if (num_shard_bits < 0) {
     num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
-  return std::make_shared<ClockCache>(
-      capacity, num_shard_bits, strict_capacity_limit, metadata_charge_policy);
+  return std::make_shared<ClockCache>(capacity, num_shard_bits,
+                                      strict_capacity_limit);
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 #endif  // SUPPORT_CLOCK_CACHE

cache/lru_cache.cc

@@ -16,7 +16,7 @@
 
 #include "util/mutexlock.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 LRUHandleTable::LRUHandleTable() : list_(nullptr), length_(0), elems_(0) {
   Resize();
@@ -97,8 +97,7 @@ void LRUHandleTable::Resize() {
 
 LRUCacheShard::LRUCacheShard(size_t capacity, bool strict_capacity_limit,
                              double high_pri_pool_ratio,
-                             bool use_adaptive_mutex,
-                             CacheMetadataChargePolicy metadata_charge_policy)
+                             bool use_adaptive_mutex)
     : capacity_(0),
       high_pri_pool_usage_(0),
       strict_capacity_limit_(strict_capacity_limit),
@@ -107,7 +106,6 @@ LRUCacheShard::LRUCacheShard(size_t capacity, bool strict_capacity_limit,
       usage_(0),
       lru_usage_(0),
       mutex_(use_adaptive_mutex) {
-  set_metadata_charge_policy(metadata_charge_policy);
   // Make empty circular linked list
   lru_.next = &lru_;
   lru_.prev = &lru_;
@@ -126,9 +124,7 @@ void LRUCacheShard::EraseUnRefEntries() {
       LRU_Remove(old);
       table_.Remove(old->key(), old->hash);
       old->SetInCache(false);
-      size_t total_charge = old->CalcTotalCharge(metadata_charge_policy_);
-      assert(usage_ >= total_charge);
-      usage_ -= total_charge;
+      usage_ -= old->charge;
       last_reference_list.push_back(old);
     }
   }
@@ -184,19 +180,16 @@ void LRUCacheShard::LRU_Remove(LRUHandle* e) {
   e->next->prev = e->prev;
   e->prev->next = e->next;
   e->prev = e->next = nullptr;
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-  assert(lru_usage_ >= total_charge);
-  lru_usage_ -= total_charge;
+  lru_usage_ -= e->charge;
   if (e->InHighPriPool()) {
-    assert(high_pri_pool_usage_ >= total_charge);
-    high_pri_pool_usage_ -= total_charge;
+    assert(high_pri_pool_usage_ >= e->charge);
+    high_pri_pool_usage_ -= e->charge;
   }
 }
 
 void LRUCacheShard::LRU_Insert(LRUHandle* e) {
   assert(e->next == nullptr);
   assert(e->prev == nullptr);
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
   if (high_pri_pool_ratio_ > 0 && (e->IsHighPri() || e->HasHit())) {
     // Inset "e" to head of LRU list.
     e->next = &lru_;
@@ -204,7 +197,7 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
     e->prev->next = e;
     e->next->prev = e;
     e->SetInHighPriPool(true);
-    high_pri_pool_usage_ += total_charge;
+    high_pri_pool_usage_ += e->charge;
     MaintainPoolSize();
   } else {
     // Insert "e" to the head of low-pri pool. Note that when
@@ -216,7 +209,7 @@ void LRUCacheShard::LRU_Insert(LRUHandle* e) {
     e->SetInHighPriPool(false);
     lru_low_pri_ = e;
   }
-  lru_usage_ += total_charge;
+  lru_usage_ += e->charge;
 }
 
 void LRUCacheShard::MaintainPoolSize() {
@@ -225,10 +218,7 @@ void LRUCacheShard::MaintainPoolSize() {
     lru_low_pri_ = lru_low_pri_->next;
     assert(lru_low_pri_ != &lru_);
     lru_low_pri_->SetInHighPriPool(false);
-    size_t total_charge =
-        lru_low_pri_->CalcTotalCharge(metadata_charge_policy_);
-    assert(high_pri_pool_usage_ >= total_charge);
-    high_pri_pool_usage_ -= total_charge;
+    high_pri_pool_usage_ -= lru_low_pri_->charge;
   }
 }
 
@@ -241,9 +231,7 @@ void LRUCacheShard::EvictFromLRU(size_t charge,
     LRU_Remove(old);
     table_.Remove(old->key(), old->hash);
     old->SetInCache(false);
-    size_t old_total_charge = old->CalcTotalCharge(metadata_charge_policy_);
-    assert(usage_ >= old_total_charge);
-    usage_ -= old_total_charge;
+    usage_ -= old->charge;
     deleted->push_back(old);
   }
 }
@@ -323,9 +311,7 @@ bool LRUCacheShard::Release(Cache::Handle* handle, bool force_erase) {
       }
     }
     if (last_reference) {
-      size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-      assert(usage_ >= total_charge);
-      usage_ -= total_charge;
+      usage_ -= e->charge;
     }
   }
 
@@ -359,16 +345,15 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
   e->SetInCache(true);
   e->SetPriority(priority);
   memcpy(e->key_data, key.data(), key.size());
-  size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
 
   {
     MutexLock l(&mutex_);
 
     // Free the space following strict LRU policy until enough space
     // is freed or the lru list is empty
-    EvictFromLRU(total_charge, &last_reference_list);
+    EvictFromLRU(charge, &last_reference_list);
 
-    if ((usage_ + total_charge) > capacity_ &&
+    if ((usage_ + charge) > capacity_ &&
         (strict_capacity_limit_ || handle == nullptr)) {
       if (handle == nullptr) {
         // Don't insert the entry but still return ok, as if the entry inserted
@@ -384,18 +369,14 @@ Status LRUCacheShard::Insert(const Slice& key, uint32_t hash, void* value,
       // Insert into the cache. Note that the cache might get larger than its
       // capacity if not enough space was freed up.
       LRUHandle* old = table_.Insert(e);
-      usage_ += total_charge;
+      usage_ += e->charge;
       if (old != nullptr) {
-        s = Status::OkOverwritten();
         assert(old->InCache());
         old->SetInCache(false);
         if (!old->HasRefs()) {
           // old is on LRU because it's in cache and its reference count is 0
           LRU_Remove(old);
-          size_t old_total_charge =
-              old->CalcTotalCharge(metadata_charge_policy_);
-          assert(usage_ >= old_total_charge);
-          usage_ -= old_total_charge;
+          usage_ -= old->charge;
           last_reference_list.push_back(old);
         }
       }
@@ -428,9 +409,7 @@ void LRUCacheShard::Erase(const Slice& key, uint32_t hash) {
       if (!e->HasRefs()) {
         // The entry is in LRU since it's in hash and has no external references
         LRU_Remove(e);
-        size_t total_charge = e->CalcTotalCharge(metadata_charge_policy_);
-        assert(usage_ >= total_charge);
-        usage_ -= total_charge;
+        usage_ -= e->charge;
         last_reference = true;
       }
     }
@@ -468,8 +447,7 @@ std::string LRUCacheShard::GetPrintableOptions() const {
 LRUCache::LRUCache(size_t capacity, int num_shard_bits,
                    bool strict_capacity_limit, double high_pri_pool_ratio,
                    std::shared_ptr<MemoryAllocator> allocator,
-                   bool use_adaptive_mutex,
-                   CacheMetadataChargePolicy metadata_charge_policy)
+                   bool use_adaptive_mutex)
     : ShardedCache(capacity, num_shard_bits, strict_capacity_limit,
                    std::move(allocator)) {
   num_shards_ = 1 << num_shard_bits;
@@ -479,7 +457,7 @@ LRUCache::LRUCache(size_t capacity, int num_shard_bits,
   for (int i = 0; i < num_shards_; i++) {
     new (&shards_[i])
         LRUCacheShard(per_shard, strict_capacity_limit, high_pri_pool_ratio,
-                      use_adaptive_mutex, metadata_charge_policy);
+            use_adaptive_mutex);
   }
 }
 
@@ -548,15 +526,15 @@ std::shared_ptr<Cache> NewLRUCache(const LRUCacheOptions& cache_opts) {
   return NewLRUCache(cache_opts.capacity, cache_opts.num_shard_bits,
                      cache_opts.strict_capacity_limit,
                      cache_opts.high_pri_pool_ratio,
-                     cache_opts.memory_allocator, cache_opts.use_adaptive_mutex,
-                     cache_opts.metadata_charge_policy);
+                     cache_opts.memory_allocator,
+                     cache_opts.use_adaptive_mutex);
 }
 
 std::shared_ptr<Cache> NewLRUCache(
     size_t capacity, int num_shard_bits, bool strict_capacity_limit,
     double high_pri_pool_ratio,
-    std::shared_ptr<MemoryAllocator> memory_allocator, bool use_adaptive_mutex,
-    CacheMetadataChargePolicy metadata_charge_policy) {
+    std::shared_ptr<MemoryAllocator> memory_allocator,
+    bool use_adaptive_mutex) {
   if (num_shard_bits >= 20) {
     return nullptr;  // the cache cannot be sharded into too many fine pieces
   }
@@ -567,9 +545,10 @@ std::shared_ptr<Cache> NewLRUCache(
   if (num_shard_bits < 0) {
     num_shard_bits = GetDefaultCacheShardBits(capacity);
   }
-  return std::make_shared<LRUCache>(
-      capacity, num_shard_bits, strict_capacity_limit, high_pri_pool_ratio,
-      std::move(memory_allocator), use_adaptive_mutex, metadata_charge_policy);
+  return std::make_shared<LRUCache>(capacity, num_shard_bits,
+                                    strict_capacity_limit, high_pri_pool_ratio,
+                                    std::move(memory_allocator),
+                                    use_adaptive_mutex);
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

cache/lru_cache.h

@@ -12,11 +12,10 @@
 
 #include "cache/sharded_cache.h"
 
-#include "port/malloc.h"
 #include "port/port.h"
 #include "util/autovector.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 // LRU cache implementation. This class is not thread-safe.
 
@@ -129,21 +128,6 @@ struct LRUHandle {
     }
     delete[] reinterpret_cast<char*>(this);
   }
-
-  // Caclculate the memory usage by metadata
-  inline size_t CalcTotalCharge(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    size_t meta_charge = 0;
-    if (metadata_charge_policy == kFullChargeCacheMetadata) {
-#ifdef ROCKSDB_MALLOC_USABLE_SIZE
-      meta_charge += malloc_usable_size(static_cast<void*>(this));
-#else
-      // This is the size that is used when a new handle is created
-      meta_charge += sizeof(LRUHandle) - 1 + key_length;
-#endif
-    }
-    return charge + meta_charge;
-  }
 };
 
 // We provide our own simple hash table since it removes a whole bunch
@@ -192,8 +176,7 @@ class LRUHandleTable {
 class ALIGN_AS(CACHE_LINE_SIZE) LRUCacheShard final : public CacheShard {
  public:
   LRUCacheShard(size_t capacity, bool strict_capacity_limit,
-                double high_pri_pool_ratio, bool use_adaptive_mutex,
-                CacheMetadataChargePolicy metadata_charge_policy);
+                double high_pri_pool_ratio, bool use_adaptive_mutex);
   virtual ~LRUCacheShard() override = default;
 
   // Separate from constructor so caller can easily make an array of LRUCache
@@ -314,9 +297,7 @@ class LRUCache
   LRUCache(size_t capacity, int num_shard_bits, bool strict_capacity_limit,
            double high_pri_pool_ratio,
            std::shared_ptr<MemoryAllocator> memory_allocator = nullptr,
-           bool use_adaptive_mutex = kDefaultToAdaptiveMutex,
-           CacheMetadataChargePolicy metadata_charge_policy =
-               kDontChargeCacheMetadata);
+           bool use_adaptive_mutex = kDefaultToAdaptiveMutex);
   virtual ~LRUCache();
   virtual const char* Name() const override { return "LRUCache"; }
   virtual CacheShard* GetShard(int shard) override;
@@ -336,4 +317,4 @@ class LRUCache
   int num_shards_ = 0;
 };
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

cache/lru_cache_test.cc

@@ -10,7 +10,7 @@
 #include "port/port.h"
 #include "test_util/testharness.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class LRUCacheTest : public testing::Test {
  public:
@@ -31,8 +31,7 @@ class LRUCacheTest : public testing::Test {
     cache_ = reinterpret_cast<LRUCacheShard*>(
         port::cacheline_aligned_alloc(sizeof(LRUCacheShard)));
     new (cache_) LRUCacheShard(capacity, false /*strict_capcity_limit*/,
-                               high_pri_pool_ratio, use_adaptive_mutex,
-                               kDontChargeCacheMetadata);
+                               high_pri_pool_ratio, use_adaptive_mutex);
   }
 
   void Insert(const std::string& key,
@@ -190,7 +189,7 @@ TEST_F(LRUCacheTest, EntriesWithPriority) {
   ValidateLRUList({"e", "f", "g", "Z", "d"}, 2);
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

cache/sharded_cache.cc

@@ -13,7 +13,7 @@
 
 #include "util/mutexlock.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 ShardedCache::ShardedCache(size_t capacity, int num_shard_bits,
                            bool strict_capacity_limit,
@@ -159,4 +159,4 @@ int GetDefaultCacheShardBits(size_t capacity) {
   return num_shard_bits;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

cache/sharded_cache.h

@@ -16,7 +16,7 @@
 #include "rocksdb/cache.h"
 #include "util/hash.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 // Single cache shard interface.
 class CacheShard {
@@ -40,13 +40,6 @@ class CacheShard {
                                       bool thread_safe) = 0;
   virtual void EraseUnRefEntries() = 0;
   virtual std::string GetPrintableOptions() const { return ""; }
-  void set_metadata_charge_policy(
-      CacheMetadataChargePolicy metadata_charge_policy) {
-    metadata_charge_policy_ = metadata_charge_policy;
-  }
-
- protected:
-  CacheMetadataChargePolicy metadata_charge_policy_ = kDontChargeCacheMetadata;
 };
 
 // Generic cache interface which shards cache by hash of keys. 2^num_shard_bits
@@ -108,4 +101,4 @@ class ShardedCache : public Cache {
 
 extern int GetDefaultCacheShardBits(size_t capacity);
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

cmake/modules/CxxFlags.cmake

@@ -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()

cmake/modules/Findgflags.cmake

@@ -1,29 +0,0 @@
-# - Find gflags library
-# Find the gflags includes and library
-#
-# gflags_INCLUDE_DIR - where to find gflags.h.
-# gflags_LIBRARIES - List of libraries when using gflags.
-# gflags_FOUND - True if gflags found.
-
-find_path(GFLAGS_INCLUDE_DIR
-  NAMES gflags/gflags.h)
-
-find_library(GFLAGS_LIBRARIES
-  NAMES gflags)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(gflags
-  DEFAULT_MSG GFLAGS_LIBRARIES GFLAGS_INCLUDE_DIR)
-
-mark_as_advanced(
-  GFLAGS_LIBRARIES
-  GFLAGS_INCLUDE_DIR)
-
-if(gflags_FOUND AND NOT (TARGET gflags::gflags))
-  add_library(gflags::gflags UNKNOWN IMPORTED)
-  set_target_properties(gflags::gflags
-    PROPERTIES
-      IMPORTED_LOCATION ${GFLAGS_LIBRARIES}
-      INTERFACE_INCLUDE_DIRECTORIES ${GFLAGS_INCLUDE_DIR}
-      IMPORTED_LINK_INTERFACE_LANGUAGES "CXX")
-endif()

cmake/modules/ReadVersion.cmake

@@ -1,7 +1,7 @@
 # Read rocksdb version from version.h header file.
 
 function(get_rocksdb_version version_var)
-  file(READ "${CMAKE_CURRENT_SOURCE_DIR}/include/rocksdb/version.h" version_header_file)
+  file(READ "${CMAKE_SOURCE_DIR}/include/rocksdb/version.h" version_header_file)
   foreach(component MAJOR MINOR PATCH)
     string(REGEX MATCH "#define ROCKSDB_${component} ([0-9]+)" _ ${version_header_file})
     set(ROCKSDB_VERSION_${component} ${CMAKE_MATCH_1})

coverage/coverage_test.sh

@@ -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"
 

coverage/parse_gcov_output.py

@@ -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)
 

db/arena_wrapped_db_iter.cc

@@ -1,106 +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/arena_wrapped_db_iter.h"
-#include "memory/arena.h"
-#include "rocksdb/env.h"
-#include "rocksdb/iterator.h"
-#include "rocksdb/options.h"
-#include "table/internal_iterator.h"
-#include "table/iterator_wrapper.h"
-#include "util/user_comparator_wrapper.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-Status ArenaWrappedDBIter::GetProperty(std::string prop_name,
-                                       std::string* prop) {
-  if (prop_name == "rocksdb.iterator.super-version-number") {
-    // First try to pass the value returned from inner iterator.
-    if (!db_iter_->GetProperty(prop_name, prop).ok()) {
-      *prop = ToString(sv_number_);
-    }
-    return Status::OK();
-  }
-  return db_iter_->GetProperty(prop_name, prop);
-}
-
-void ArenaWrappedDBIter::Init(Env* env, const ReadOptions& read_options,
-                              const ImmutableCFOptions& cf_options,
-                              const MutableCFOptions& mutable_cf_options,
-                              const SequenceNumber& sequence,
-                              uint64_t max_sequential_skip_in_iteration,
-                              uint64_t version_number,
-                              ReadCallback* read_callback, DBImpl* db_impl,
-                              ColumnFamilyData* cfd, bool allow_blob,
-                              bool allow_refresh) {
-  auto mem = arena_.AllocateAligned(sizeof(DBIter));
-  db_iter_ = new (mem) DBIter(env, read_options, cf_options, mutable_cf_options,
-                              cf_options.user_comparator, nullptr, sequence,
-                              true, max_sequential_skip_in_iteration,
-                              read_callback, db_impl, cfd, allow_blob);
-  sv_number_ = version_number;
-  allow_refresh_ = allow_refresh;
-}
-
-Status ArenaWrappedDBIter::Refresh() {
-  if (cfd_ == nullptr || db_impl_ == nullptr || !allow_refresh_) {
-    return Status::NotSupported("Creating renew iterator is not allowed.");
-  }
-  assert(db_iter_ != nullptr);
-  // TODO(yiwu): For last_seq_same_as_publish_seq_==false, this is not the
-  // correct behavior. Will be corrected automatically when we take a snapshot
-  // here for the case of WritePreparedTxnDB.
-  SequenceNumber latest_seq = db_impl_->GetLatestSequenceNumber();
-  uint64_t cur_sv_number = cfd_->GetSuperVersionNumber();
-  if (sv_number_ != cur_sv_number) {
-    Env* env = db_iter_->env();
-    db_iter_->~DBIter();
-    arena_.~Arena();
-    new (&arena_) Arena();
-
-    SuperVersion* sv = cfd_->GetReferencedSuperVersion(db_impl_);
-    if (read_callback_) {
-      read_callback_->Refresh(latest_seq);
-    }
-    Init(env, read_options_, *(cfd_->ioptions()), sv->mutable_cf_options,
-         latest_seq, sv->mutable_cf_options.max_sequential_skip_in_iterations,
-         cur_sv_number, read_callback_, db_impl_, cfd_, allow_blob_,
-         allow_refresh_);
-
-    InternalIterator* internal_iter = db_impl_->NewInternalIterator(
-        read_options_, cfd_, sv, &arena_, db_iter_->GetRangeDelAggregator(),
-        latest_seq, /* allow_unprepared_value */ true);
-    SetIterUnderDBIter(internal_iter);
-  } else {
-    db_iter_->set_sequence(latest_seq);
-    db_iter_->set_valid(false);
-  }
-  return Status::OK();
-}
-
-ArenaWrappedDBIter* NewArenaWrappedDbIterator(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableCFOptions& cf_options,
-    const MutableCFOptions& mutable_cf_options, const SequenceNumber& sequence,
-    uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-    ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
-    bool allow_blob, bool allow_refresh) {
-  ArenaWrappedDBIter* iter = new ArenaWrappedDBIter();
-  iter->Init(env, read_options, cf_options, mutable_cf_options, sequence,
-             max_sequential_skip_in_iterations, version_number, read_callback,
-             db_impl, cfd, allow_blob, allow_refresh);
-  if (db_impl != nullptr && cfd != nullptr && allow_refresh) {
-    iter->StoreRefreshInfo(read_options, db_impl, cfd, read_callback,
-                           allow_blob);
-  }
-
-  return iter;
-}
-
-}  // namespace ROCKSDB_NAMESPACE

db/arena_wrapped_db_iter.h

@@ -1,115 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#pragma once
-#include <stdint.h>
-#include <string>
-#include "db/db_impl/db_impl.h"
-#include "db/db_iter.h"
-#include "db/dbformat.h"
-#include "db/range_del_aggregator.h"
-#include "memory/arena.h"
-#include "options/cf_options.h"
-#include "rocksdb/db.h"
-#include "rocksdb/iterator.h"
-#include "util/autovector.h"
-
-namespace ROCKSDB_NAMESPACE {
-
-class Arena;
-
-// A wrapper iterator which wraps DB Iterator and the arena, with which the DB
-// iterator is supposed to be allocated. This class is used as an entry point of
-// a iterator hierarchy whose memory can be allocated inline. In that way,
-// accessing the iterator tree can be more cache friendly. It is also faster
-// to allocate.
-// When using the class's Iterator interface, the behavior is exactly
-// the same as the inner DBIter.
-class ArenaWrappedDBIter : public Iterator {
- public:
-  virtual ~ArenaWrappedDBIter() { db_iter_->~DBIter(); }
-
-  // Get the arena to be used to allocate memory for DBIter to be wrapped,
-  // as well as child iterators in it.
-  virtual Arena* GetArena() { return &arena_; }
-  virtual ReadRangeDelAggregator* GetRangeDelAggregator() {
-    return db_iter_->GetRangeDelAggregator();
-  }
-
-  // Set the internal iterator wrapped inside the DB Iterator. Usually it is
-  // a merging iterator.
-  virtual void SetIterUnderDBIter(InternalIterator* iter) {
-    db_iter_->SetIter(iter);
-  }
-
-  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);
-  }
-  void Next() override { db_iter_->Next(); }
-  void Prev() override { db_iter_->Prev(); }
-  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;
-
-  Status Refresh() override;
-
-  void Init(Env* env, const ReadOptions& read_options,
-            const ImmutableCFOptions& cf_options,
-            const MutableCFOptions& mutable_cf_options,
-            const SequenceNumber& sequence,
-            uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-            ReadCallback* read_callback, DBImpl* db_impl, ColumnFamilyData* cfd,
-            bool allow_blob, bool allow_refresh);
-
-  // Store some parameters so we can refresh the iterator at a later point
-  // with these same params
-  void StoreRefreshInfo(const ReadOptions& read_options, DBImpl* db_impl,
-                        ColumnFamilyData* cfd, ReadCallback* read_callback,
-                        bool allow_blob) {
-    read_options_ = read_options;
-    db_impl_ = db_impl;
-    cfd_ = cfd;
-    read_callback_ = read_callback;
-    allow_blob_ = allow_blob;
-  }
-
- private:
-  DBIter* db_iter_;
-  Arena arena_;
-  uint64_t sv_number_;
-  ColumnFamilyData* cfd_ = nullptr;
-  DBImpl* db_impl_ = nullptr;
-  ReadOptions read_options_;
-  ReadCallback* read_callback_;
-  bool allow_blob_ = false;
-  bool allow_refresh_ = true;
-};
-
-// Generate the arena wrapped iterator class.
-// `db_impl` and `cfd` are used for reneweal. If left null, renewal will not
-// be supported.
-extern ArenaWrappedDBIter* NewArenaWrappedDbIterator(
-    Env* env, const ReadOptions& read_options,
-    const ImmutableCFOptions& cf_options,
-    const MutableCFOptions& mutable_cf_options, const SequenceNumber& sequence,
-    uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
-    ReadCallback* read_callback, DBImpl* db_impl = nullptr,
-    ColumnFamilyData* cfd = nullptr, bool allow_blob = false,
-    bool allow_refresh = true);
-}  // namespace ROCKSDB_NAMESPACE

db/blob/blob_constants.h

@@ -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

db/blob/blob_file_addition.cc

@@ -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

db/blob/blob_file_addition.h

@@ -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

db/blob/blob_file_addition_test.cc

@@ -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();
-}

db/blob/blob_file_garbage.cc

@@ -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

db/blob/blob_file_garbage.h

@@ -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

db/blob/blob_file_garbage_test.cc

@@ -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();
-}

db/blob/blob_file_meta.cc

@@ -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

db/blob/blob_file_meta.h

@@ -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

db/builder.cc

@@ -22,8 +22,6 @@
 #include "db/table_cache.h"
 #include "db/version_edit.h"
 #include "file/filename.h"
-#include "file/read_write_util.h"
-#include "file/writable_file_writer.h"
 #include "monitoring/iostats_context_imp.h"
 #include "monitoring/thread_status_util.h"
 #include "rocksdb/db.h"
@@ -35,9 +33,10 @@
 #include "table/format.h"
 #include "table/internal_iterator.h"
 #include "test_util/sync_point.h"
+#include "util/file_reader_writer.h"
 #include "util/stop_watch.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class TableFactory;
 
@@ -66,9 +65,8 @@ TableBuilder* NewTableBuilder(
 }
 
 Status BuildTable(
-    const std::string& dbname, Env* env, FileSystem* fs,
-    const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options, const FileOptions& file_options,
+    const std::string& dbname, Env* env, const ImmutableCFOptions& ioptions,
+    const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
     TableCache* table_cache, InternalIterator* iter,
     std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
         range_del_iters,
@@ -81,11 +79,10 @@ 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());
@@ -117,25 +114,24 @@ Status BuildTable(
     compression_opts_for_flush.max_dict_bytes = 0;
     compression_opts_for_flush.zstd_max_train_bytes = 0;
     {
-      std::unique_ptr<FSWritableFile> file;
+      std::unique_ptr<WritableFile> file;
 #ifndef NDEBUG
-      bool use_direct_writes = file_options.use_direct_writes;
+      bool use_direct_writes = env_options.use_direct_writes;
       TEST_SYNC_POINT_CALLBACK("BuildTable:create_file", &use_direct_writes);
 #endif  // !NDEBUG
-      s = NewWritableFile(fs, fname, &file, file_options);
+      s = NewWritableFile(env, fname, &file, env_options);
       if (!s.ok()) {
         EventHelpers::LogAndNotifyTableFileCreationFinished(
             event_logger, ioptions.listeners, dbname, column_family_name, fname,
-            job_id, meta->fd, kInvalidBlobFileNumber, tp, reason, s);
+            job_id, meta->fd, tp, reason, s);
         return s;
       }
       file->SetIOPriority(io_priority);
       file->SetWriteLifeTimeHint(write_hint);
 
-      file_writer.reset(new WritableFileWriter(
-          std::move(file), fname, file_options, env, ioptions.statistics,
-          ioptions.listeners, ioptions.file_checksum_gen_factory));
-
+      file_writer.reset(
+          new WritableFileWriter(std::move(file), fname, env_options, env,
+                                 ioptions.statistics, ioptions.listeners));
       builder = NewTableBuilder(
           ioptions, mutable_cf_options, internal_comparator,
           int_tbl_prop_collector_factories, column_family_id,
@@ -160,9 +156,8 @@ Status BuildTable(
     for (; c_iter.Valid(); c_iter.Next()) {
       const Slice& key = c_iter.key();
       const Slice& value = c_iter.value();
-      const ParsedInternalKey& ikey = c_iter.ikey();
       builder->Add(key, value);
-      meta->UpdateBoundaries(key, value, ikey.sequence, ikey.type);
+      meta->UpdateBoundaries(key, c_iter.ikey().sequence);
 
       // TODO(noetzli): Update stats after flush, too.
       if (io_priority == Env::IO_HIGH &&
@@ -183,15 +178,14 @@ 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();
@@ -208,22 +202,11 @@ Status BuildTable(
     // 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
@@ -233,15 +216,14 @@ Status BuildTable(
       // we will regrad this verification as user reads since the goal is
       // to cache it here for further user reads
       std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
-          ReadOptions(), file_options, internal_comparator, *meta,
+          ReadOptions(), env_options, internal_comparator, *meta,
           nullptr /* range_del_agg */,
           mutable_cf_options.prefix_extractor.get(), nullptr,
           (internal_stats == nullptr) ? nullptr
                                       : 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()) {
@@ -257,18 +239,15 @@ Status BuildTable(
   }
 
   if (!s.ok() || meta->fd.GetFileSize() == 0) {
-    fs->DeleteFile(fname, IOOptions(), nullptr);
+    env->DeleteFile(fname);
   }
 
-  if (meta->fd.GetFileSize() == 0) {
-    fname = "(nil)";
-  }
   // Output to event logger and fire events.
   EventHelpers::LogAndNotifyTableFileCreationFinished(
       event_logger, ioptions.listeners, dbname, column_family_name, fname,
-      job_id, meta->fd, meta->oldest_blob_file_number, tp, reason, s);
+      job_id, meta->fd, tp, reason, s);
 
   return s;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/builder.h

@@ -22,7 +22,7 @@
 #include "rocksdb/types.h"
 #include "table/scoped_arena_iterator.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 struct Options;
 struct FileMetaData;
@@ -62,9 +62,8 @@ TableBuilder* NewTableBuilder(
 // @param column_family_name Name of the column family that is also identified
 //    by column_family_id, or empty string if unknown.
 extern Status BuildTable(
-    const std::string& dbname, Env* env, FileSystem* fs,
-    const ImmutableCFOptions& options,
-    const MutableCFOptions& mutable_cf_options, const FileOptions& file_options,
+    const std::string& dbname, Env* env, const ImmutableCFOptions& options,
+    const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
     TableCache* table_cache, InternalIterator* iter,
     std::vector<std::unique_ptr<FragmentedRangeTombstoneIterator>>
         range_del_iters,
@@ -78,11 +77,11 @@ 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,
     Env::WriteLifeTimeHint write_hint = Env::WLTH_NOT_SET,
     const uint64_t file_creation_time = 0);
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/c.cc

@@ -46,74 +46,74 @@
 #include <unordered_set>
 #include <map>
 
-using ROCKSDB_NAMESPACE::BackupableDBOptions;
-using ROCKSDB_NAMESPACE::BackupEngine;
-using ROCKSDB_NAMESPACE::BackupID;
-using ROCKSDB_NAMESPACE::BackupInfo;
-using ROCKSDB_NAMESPACE::BatchResult;
-using ROCKSDB_NAMESPACE::BlockBasedTableOptions;
-using ROCKSDB_NAMESPACE::BottommostLevelCompaction;
-using ROCKSDB_NAMESPACE::BytewiseComparator;
-using ROCKSDB_NAMESPACE::Cache;
-using ROCKSDB_NAMESPACE::Checkpoint;
-using ROCKSDB_NAMESPACE::ColumnFamilyDescriptor;
-using ROCKSDB_NAMESPACE::ColumnFamilyHandle;
-using ROCKSDB_NAMESPACE::ColumnFamilyOptions;
-using ROCKSDB_NAMESPACE::CompactionFilter;
-using ROCKSDB_NAMESPACE::CompactionFilterContext;
-using ROCKSDB_NAMESPACE::CompactionFilterFactory;
-using ROCKSDB_NAMESPACE::CompactionOptionsFIFO;
-using ROCKSDB_NAMESPACE::CompactRangeOptions;
-using ROCKSDB_NAMESPACE::Comparator;
-using ROCKSDB_NAMESPACE::CompressionType;
-using ROCKSDB_NAMESPACE::CuckooTableOptions;
-using ROCKSDB_NAMESPACE::DB;
-using ROCKSDB_NAMESPACE::DBOptions;
-using ROCKSDB_NAMESPACE::DbPath;
-using ROCKSDB_NAMESPACE::Env;
-using ROCKSDB_NAMESPACE::EnvOptions;
-using ROCKSDB_NAMESPACE::FileLock;
-using ROCKSDB_NAMESPACE::FilterPolicy;
-using ROCKSDB_NAMESPACE::FlushOptions;
-using ROCKSDB_NAMESPACE::InfoLogLevel;
-using ROCKSDB_NAMESPACE::IngestExternalFileOptions;
-using ROCKSDB_NAMESPACE::Iterator;
-using ROCKSDB_NAMESPACE::LiveFileMetaData;
-using ROCKSDB_NAMESPACE::Logger;
-using ROCKSDB_NAMESPACE::MemoryUtil;
-using ROCKSDB_NAMESPACE::MergeOperator;
-using ROCKSDB_NAMESPACE::MergeOperators;
-using ROCKSDB_NAMESPACE::NewBloomFilterPolicy;
-using ROCKSDB_NAMESPACE::NewGenericRateLimiter;
-using ROCKSDB_NAMESPACE::NewLRUCache;
-using ROCKSDB_NAMESPACE::OptimisticTransactionDB;
-using ROCKSDB_NAMESPACE::OptimisticTransactionOptions;
-using ROCKSDB_NAMESPACE::Options;
-using ROCKSDB_NAMESPACE::PerfContext;
-using ROCKSDB_NAMESPACE::PerfLevel;
-using ROCKSDB_NAMESPACE::PinnableSlice;
-using ROCKSDB_NAMESPACE::RandomAccessFile;
-using ROCKSDB_NAMESPACE::Range;
-using ROCKSDB_NAMESPACE::RateLimiter;
-using ROCKSDB_NAMESPACE::ReadOptions;
-using ROCKSDB_NAMESPACE::RestoreOptions;
-using ROCKSDB_NAMESPACE::SequentialFile;
-using ROCKSDB_NAMESPACE::Slice;
-using ROCKSDB_NAMESPACE::SliceParts;
-using ROCKSDB_NAMESPACE::SliceTransform;
-using ROCKSDB_NAMESPACE::Snapshot;
-using ROCKSDB_NAMESPACE::SstFileWriter;
-using ROCKSDB_NAMESPACE::Status;
-using ROCKSDB_NAMESPACE::Transaction;
-using ROCKSDB_NAMESPACE::TransactionDB;
-using ROCKSDB_NAMESPACE::TransactionDBOptions;
-using ROCKSDB_NAMESPACE::TransactionLogIterator;
-using ROCKSDB_NAMESPACE::TransactionOptions;
-using ROCKSDB_NAMESPACE::WALRecoveryMode;
-using ROCKSDB_NAMESPACE::WritableFile;
-using ROCKSDB_NAMESPACE::WriteBatch;
-using ROCKSDB_NAMESPACE::WriteBatchWithIndex;
-using ROCKSDB_NAMESPACE::WriteOptions;
+using rocksdb::BytewiseComparator;
+using rocksdb::Cache;
+using rocksdb::ColumnFamilyDescriptor;
+using rocksdb::ColumnFamilyHandle;
+using rocksdb::ColumnFamilyOptions;
+using rocksdb::CompactionFilter;
+using rocksdb::CompactionFilterFactory;
+using rocksdb::CompactionFilterContext;
+using rocksdb::CompactionOptionsFIFO;
+using rocksdb::Comparator;
+using rocksdb::CompressionType;
+using rocksdb::WALRecoveryMode;
+using rocksdb::DB;
+using rocksdb::DBOptions;
+using rocksdb::DbPath;
+using rocksdb::Env;
+using rocksdb::EnvOptions;
+using rocksdb::InfoLogLevel;
+using rocksdb::FileLock;
+using rocksdb::FilterPolicy;
+using rocksdb::FlushOptions;
+using rocksdb::IngestExternalFileOptions;
+using rocksdb::Iterator;
+using rocksdb::Logger;
+using rocksdb::MergeOperator;
+using rocksdb::MergeOperators;
+using rocksdb::NewBloomFilterPolicy;
+using rocksdb::NewLRUCache;
+using rocksdb::Options;
+using rocksdb::BlockBasedTableOptions;
+using rocksdb::CuckooTableOptions;
+using rocksdb::RandomAccessFile;
+using rocksdb::Range;
+using rocksdb::ReadOptions;
+using rocksdb::SequentialFile;
+using rocksdb::Slice;
+using rocksdb::SliceParts;
+using rocksdb::SliceTransform;
+using rocksdb::Snapshot;
+using rocksdb::SstFileWriter;
+using rocksdb::Status;
+using rocksdb::WritableFile;
+using rocksdb::WriteBatch;
+using rocksdb::WriteBatchWithIndex;
+using rocksdb::WriteOptions;
+using rocksdb::LiveFileMetaData;
+using rocksdb::BackupEngine;
+using rocksdb::BackupableDBOptions;
+using rocksdb::BackupInfo;
+using rocksdb::BackupID;
+using rocksdb::RestoreOptions;
+using rocksdb::CompactRangeOptions;
+using rocksdb::BottommostLevelCompaction;
+using rocksdb::RateLimiter;
+using rocksdb::NewGenericRateLimiter;
+using rocksdb::PinnableSlice;
+using rocksdb::TransactionDBOptions;
+using rocksdb::TransactionDB;
+using rocksdb::TransactionOptions;
+using rocksdb::OptimisticTransactionDB;
+using rocksdb::OptimisticTransactionOptions;
+using rocksdb::Transaction;
+using rocksdb::Checkpoint;
+using rocksdb::TransactionLogIterator;
+using rocksdb::BatchResult;
+using rocksdb::PerfLevel;
+using rocksdb::PerfContext;
+using rocksdb::MemoryUtil;
 
 using std::shared_ptr;
 using std::vector;
@@ -452,7 +452,7 @@ struct rocksdb_slicetransform_t : public SliceTransform {
 };
 
 struct rocksdb_universal_compaction_options_t {
-  ROCKSDB_NAMESPACE::CompactionOptionsUniversal* rep;
+  rocksdb::CompactionOptionsUniversal *rep;
 };
 
 static bool SaveError(char** errptr, const Status& s) {
@@ -494,9 +494,8 @@ rocksdb_t* rocksdb_open_with_ttl(
     const char* name,
     int ttl,
     char** errptr) {
-  ROCKSDB_NAMESPACE::DBWithTTL* db;
-  if (SaveError(errptr, ROCKSDB_NAMESPACE::DBWithTTL::Open(
-                            options->rep, std::string(name), &db, ttl))) {
+  rocksdb::DBWithTTL* db;
+  if (SaveError(errptr, rocksdb::DBWithTTL::Open(options->rep, std::string(name), &db, ttl))) {
     return nullptr;
   }
   rocksdb_t* result = new rocksdb_t;
@@ -665,15 +664,17 @@ void rocksdb_close(rocksdb_t* db) {
 }
 
 void rocksdb_options_set_uint64add_merge_operator(rocksdb_options_t* opt) {
-  opt->rep.merge_operator =
-      ROCKSDB_NAMESPACE::MergeOperators::CreateUInt64AddOperator();
+  opt->rep.merge_operator = rocksdb::MergeOperators::CreateUInt64AddOperator();
 }
 
 rocksdb_t* rocksdb_open_column_families(
-    const rocksdb_options_t* db_options, const char* name,
-    int num_column_families, const char* const* column_family_names,
-    const rocksdb_options_t* const* column_family_options,
-    rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
+    const rocksdb_options_t* db_options,
+    const char* name,
+    int num_column_families,
+    const char** column_family_names,
+    const rocksdb_options_t** column_family_options,
+    rocksdb_column_family_handle_t** column_family_handles,
+    char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
     column_families.push_back(ColumnFamilyDescriptor(
@@ -699,11 +700,14 @@ rocksdb_t* rocksdb_open_column_families(
 }
 
 rocksdb_t* rocksdb_open_for_read_only_column_families(
-    const rocksdb_options_t* db_options, const char* name,
-    int num_column_families, const char* const* column_family_names,
-    const rocksdb_options_t* const* column_family_options,
+    const rocksdb_options_t* db_options,
+    const char* name,
+    int num_column_families,
+    const char** column_family_names,
+    const rocksdb_options_t** column_family_options,
     rocksdb_column_family_handle_t** column_family_handles,
-    unsigned char error_if_log_file_exist, char** errptr) {
+    unsigned char error_if_log_file_exist,
+    char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
     column_families.push_back(ColumnFamilyDescriptor(
@@ -731,8 +735,8 @@ rocksdb_t* rocksdb_open_for_read_only_column_families(
 rocksdb_t* rocksdb_open_as_secondary_column_families(
     const rocksdb_options_t* db_options, const char* name,
     const char* secondary_path, int num_column_families,
-    const char* const* column_family_names,
-    const rocksdb_options_t* const* column_family_options,
+    const char** column_family_names,
+    const rocksdb_options_t** column_family_options,
     rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i != num_column_families; ++i) {
@@ -848,17 +852,6 @@ void rocksdb_delete_cf(
         Slice(key, keylen)));
 }
 
-void rocksdb_delete_range_cf(rocksdb_t* db,
-                             const rocksdb_writeoptions_t* options,
-                             rocksdb_column_family_handle_t* column_family,
-                             const char* start_key, size_t start_key_len,
-                             const char* end_key, size_t end_key_len,
-                             char** errptr) {
-  SaveError(errptr, db->rep->DeleteRange(options->rep, column_family->rep,
-                                         Slice(start_key, start_key_len),
-                                         Slice(end_key, end_key_len)));
-}
-
 void rocksdb_merge(
     rocksdb_t* db,
     const rocksdb_writeoptions_t* options,
@@ -2039,17 +2032,6 @@ void rocksdb_block_based_options_set_index_type(
   options->rep.index_type = static_cast<BlockBasedTableOptions::IndexType>(v);
 }
 
-void rocksdb_block_based_options_set_data_block_index_type(
-    rocksdb_block_based_table_options_t* options, int v) {
-  options->rep.data_block_index_type =
-          static_cast<BlockBasedTableOptions::DataBlockIndexType>(v);
-}
-
-void rocksdb_block_based_options_set_data_block_hash_ratio(
-    rocksdb_block_based_table_options_t* options, double v) {
-  options->rep.data_block_hash_table_util_ratio = v;
-}
-
 void rocksdb_block_based_options_set_hash_index_allow_collision(
     rocksdb_block_based_table_options_t* options, unsigned char v) {
   options->rep.hash_index_allow_collision = v;
@@ -2080,7 +2062,7 @@ void rocksdb_options_set_block_based_table_factory(
     rocksdb_block_based_table_options_t* table_options) {
   if (table_options) {
     opt->rep.table_factory.reset(
-        ROCKSDB_NAMESPACE::NewBlockBasedTableFactory(table_options->rep));
+        rocksdb::NewBlockBasedTableFactory(table_options->rep));
   }
 }
 
@@ -2124,7 +2106,7 @@ void rocksdb_options_set_cuckoo_table_factory(
     rocksdb_cuckoo_table_options_t* table_options) {
   if (table_options) {
     opt->rep.table_factory.reset(
-        ROCKSDB_NAMESPACE::NewCuckooTableFactory(table_options->rep));
+        rocksdb::NewCuckooTableFactory(table_options->rep));
   }
 }
 
@@ -2290,6 +2272,11 @@ void rocksdb_options_set_max_bytes_for_level_base(
   opt->rep.max_bytes_for_level_base = n;
 }
 
+void rocksdb_options_set_snap_refresh_nanos(rocksdb_options_t* opt,
+                                            uint64_t n) {
+  opt->rep.snap_refresh_nanos = n;
+}
+
 void rocksdb_options_set_level_compaction_dynamic_level_bytes(
     rocksdb_options_t* opt, unsigned char v) {
   opt->rep.level_compaction_dynamic_level_bytes = v;
@@ -2314,7 +2301,7 @@ void rocksdb_options_set_max_bytes_for_level_multiplier_additional(
 }
 
 void rocksdb_options_enable_statistics(rocksdb_options_t* opt) {
-  opt->rep.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  opt->rep.statistics = rocksdb::CreateDBStatistics();
 }
 
 void rocksdb_options_set_skip_stats_update_on_db_open(rocksdb_options_t* opt,
@@ -2322,11 +2309,6 @@ void rocksdb_options_set_skip_stats_update_on_db_open(rocksdb_options_t* opt,
   opt->rep.skip_stats_update_on_db_open = val;
 }
 
-void rocksdb_options_set_skip_checking_sst_file_sizes_on_db_open(
-    rocksdb_options_t* opt, unsigned char val) {
-  opt->rep.skip_checking_sst_file_sizes_on_db_open = val;
-}
-
 void rocksdb_options_set_num_levels(rocksdb_options_t* opt, int n) {
   opt->rep.num_levels = n;
 }
@@ -2470,20 +2452,16 @@ void rocksdb_options_set_access_hint_on_compaction_start(
     rocksdb_options_t* opt, int v) {
   switch(v) {
     case 0:
-      opt->rep.access_hint_on_compaction_start =
-          ROCKSDB_NAMESPACE::Options::NONE;
+      opt->rep.access_hint_on_compaction_start = rocksdb::Options::NONE;
       break;
     case 1:
-      opt->rep.access_hint_on_compaction_start =
-          ROCKSDB_NAMESPACE::Options::NORMAL;
+      opt->rep.access_hint_on_compaction_start = rocksdb::Options::NORMAL;
       break;
     case 2:
-      opt->rep.access_hint_on_compaction_start =
-          ROCKSDB_NAMESPACE::Options::SEQUENTIAL;
+      opt->rep.access_hint_on_compaction_start = rocksdb::Options::SEQUENTIAL;
       break;
     case 3:
-      opt->rep.access_hint_on_compaction_start =
-          ROCKSDB_NAMESPACE::Options::WILLNEED;
+      opt->rep.access_hint_on_compaction_start = rocksdb::Options::WILLNEED;
       break;
   }
 }
@@ -2649,7 +2627,7 @@ void rocksdb_options_prepare_for_bulk_load(rocksdb_options_t* opt) {
 }
 
 void rocksdb_options_set_memtable_vector_rep(rocksdb_options_t *opt) {
-  opt->rep.memtable_factory.reset(new ROCKSDB_NAMESPACE::VectorRepFactory);
+  opt->rep.memtable_factory.reset(new rocksdb::VectorRepFactory);
 }
 
 void rocksdb_options_set_memtable_prefix_bloom_size_ratio(
@@ -2665,29 +2643,26 @@ void rocksdb_options_set_memtable_huge_page_size(rocksdb_options_t* opt,
 void rocksdb_options_set_hash_skip_list_rep(
     rocksdb_options_t *opt, size_t bucket_count,
     int32_t skiplist_height, int32_t skiplist_branching_factor) {
-  ROCKSDB_NAMESPACE::MemTableRepFactory* factory =
-      ROCKSDB_NAMESPACE::NewHashSkipListRepFactory(
-          bucket_count, skiplist_height, skiplist_branching_factor);
+  rocksdb::MemTableRepFactory* factory = rocksdb::NewHashSkipListRepFactory(
+      bucket_count, skiplist_height, skiplist_branching_factor);
   opt->rep.memtable_factory.reset(factory);
 }
 
 void rocksdb_options_set_hash_link_list_rep(
     rocksdb_options_t *opt, size_t bucket_count) {
-  opt->rep.memtable_factory.reset(
-      ROCKSDB_NAMESPACE::NewHashLinkListRepFactory(bucket_count));
+  opt->rep.memtable_factory.reset(rocksdb::NewHashLinkListRepFactory(bucket_count));
 }
 
 void rocksdb_options_set_plain_table_factory(
     rocksdb_options_t *opt, uint32_t user_key_len, int bloom_bits_per_key,
     double hash_table_ratio, size_t index_sparseness) {
-  ROCKSDB_NAMESPACE::PlainTableOptions options;
+  rocksdb::PlainTableOptions options;
   options.user_key_len = user_key_len;
   options.bloom_bits_per_key = bloom_bits_per_key;
   options.hash_table_ratio = hash_table_ratio;
   options.index_sparseness = index_sparseness;
 
-  ROCKSDB_NAMESPACE::TableFactory* factory =
-      ROCKSDB_NAMESPACE::NewPlainTableFactory(options);
+  rocksdb::TableFactory* factory = rocksdb::NewPlainTableFactory(options);
   opt->rep.table_factory.reset(factory);
 }
 
@@ -2717,8 +2692,7 @@ void rocksdb_options_set_report_bg_io_stats(
 }
 
 void rocksdb_options_set_compaction_style(rocksdb_options_t *opt, int style) {
-  opt->rep.compaction_style =
-      static_cast<ROCKSDB_NAMESPACE::CompactionStyle>(style);
+  opt->rep.compaction_style = static_cast<rocksdb::CompactionStyle>(style);
 }
 
 void rocksdb_options_set_universal_compaction_options(rocksdb_options_t *opt, rocksdb_universal_compaction_options_t *uco) {
@@ -2732,7 +2706,7 @@ void rocksdb_options_set_fifo_compaction_options(
 }
 
 char *rocksdb_options_statistics_get_string(rocksdb_options_t *opt) {
-  ROCKSDB_NAMESPACE::Statistics* statistics = opt->rep.statistics.get();
+  rocksdb::Statistics *statistics = opt->rep.statistics.get();
   if (statistics) {
     return strdup(statistics->ToString().c_str());
   }
@@ -2745,11 +2719,6 @@ void rocksdb_options_set_ratelimiter(rocksdb_options_t *opt, rocksdb_ratelimiter
   }
 }
 
-void rocksdb_options_set_atomic_flush(rocksdb_options_t* opt,
-                                      unsigned char atomic_flush) {
-  opt->rep.atomic_flush = atomic_flush;
-}
-
 rocksdb_ratelimiter_t* rocksdb_ratelimiter_create(
     int64_t rate_bytes_per_sec,
     int64_t refill_period_us,
@@ -2765,12 +2734,6 @@ void rocksdb_ratelimiter_destroy(rocksdb_ratelimiter_t *limiter) {
   delete limiter;
 }
 
-void rocksdb_options_set_row_cache(rocksdb_options_t* opt, rocksdb_cache_t* cache) {
-  if(cache) {
-    opt->rep.row_cache = cache->rep;
-  }
-}
-
 void rocksdb_set_perf_level(int v) {
   PerfLevel level = static_cast<PerfLevel>(v);
   SetPerfLevel(level);
@@ -2778,7 +2741,7 @@ void rocksdb_set_perf_level(int v) {
 
 rocksdb_perfcontext_t* rocksdb_perfcontext_create() {
   rocksdb_perfcontext_t* context = new rocksdb_perfcontext_t;
-  context->rep = ROCKSDB_NAMESPACE::get_perf_context();
+  context->rep = rocksdb::get_perf_context();
   return context;
 }
 
@@ -3079,17 +3042,7 @@ rocksdb_filterpolicy_t* rocksdb_filterpolicy_create_bloom_format(int bits_per_ke
     bool KeyMayMatch(const Slice& key, const Slice& filter) const override {
       return rep_->KeyMayMatch(key, filter);
     }
-    // No need to override GetFilterBitsBuilder if this one is overridden
-    ROCKSDB_NAMESPACE::FilterBitsBuilder* GetBuilderWithContext(
-        const ROCKSDB_NAMESPACE::FilterBuildingContext& context)
-        const override {
-      return rep_->GetBuilderWithContext(context);
-    }
-    ROCKSDB_NAMESPACE::FilterBitsReader* GetFilterBitsReader(
-        const Slice& contents) const override {
-      return rep_->GetFilterBitsReader(contents);
-    }
-    static void DoNothing(void*) {}
+    static void DoNothing(void*) { }
   };
   Wrapper* wrapper = new Wrapper;
   wrapper->rep_ = NewBloomFilterPolicy(bits_per_key, original_format);
@@ -3187,7 +3140,7 @@ void rocksdb_readoptions_set_iterate_lower_bound(
 
 void rocksdb_readoptions_set_read_tier(
     rocksdb_readoptions_t* opt, int v) {
-  opt->rep.read_tier = static_cast<ROCKSDB_NAMESPACE::ReadTier>(v);
+  opt->rep.read_tier = static_cast<rocksdb::ReadTier>(v);
 }
 
 void rocksdb_readoptions_set_tailing(
@@ -3359,7 +3312,7 @@ rocksdb_env_t* rocksdb_create_default_env() {
 
 rocksdb_env_t* rocksdb_create_mem_env() {
   rocksdb_env_t* result = new rocksdb_env_t;
-  result->rep = ROCKSDB_NAMESPACE::NewMemEnv(Env::Default());
+  result->rep = rocksdb::NewMemEnv(Env::Default());
   result->is_default = false;
   return result;
 }
@@ -3574,7 +3527,7 @@ struct Wrapper : public rocksdb_slicetransform_t {
 
 rocksdb_slicetransform_t* rocksdb_slicetransform_create_fixed_prefix(size_t prefixLen) {
   Wrapper* wrapper = new Wrapper;
-  wrapper->rep_ = ROCKSDB_NAMESPACE::NewFixedPrefixTransform(prefixLen);
+  wrapper->rep_ = rocksdb::NewFixedPrefixTransform(prefixLen);
   wrapper->state_ = nullptr;
   wrapper->destructor_ = &Wrapper::DoNothing;
   return wrapper;
@@ -3582,7 +3535,7 @@ rocksdb_slicetransform_t* rocksdb_slicetransform_create_fixed_prefix(size_t pref
 
 rocksdb_slicetransform_t* rocksdb_slicetransform_create_noop() {
   Wrapper* wrapper = new Wrapper;
-  wrapper->rep_ = ROCKSDB_NAMESPACE::NewNoopTransform();
+  wrapper->rep_ = rocksdb::NewNoopTransform();
   wrapper->state_ = nullptr;
   wrapper->destructor_ = &Wrapper::DoNothing;
   return wrapper;
@@ -3590,7 +3543,7 @@ rocksdb_slicetransform_t* rocksdb_slicetransform_create_noop() {
 
 rocksdb_universal_compaction_options_t* rocksdb_universal_compaction_options_create() {
   rocksdb_universal_compaction_options_t* result = new rocksdb_universal_compaction_options_t;
-  result->rep = new ROCKSDB_NAMESPACE::CompactionOptionsUniversal;
+  result->rep = new rocksdb::CompactionOptionsUniversal;
   return result;
 }
 
@@ -3621,8 +3574,7 @@ void rocksdb_universal_compaction_options_set_compression_size_percent(
 
 void rocksdb_universal_compaction_options_set_stop_style(
   rocksdb_universal_compaction_options_t* uco, int style) {
-  uco->rep->stop_style =
-      static_cast<ROCKSDB_NAMESPACE::CompactionStopStyle>(style);
+  uco->rep->stop_style = static_cast<rocksdb::CompactionStopStyle>(style);
 }
 
 void rocksdb_universal_compaction_options_destroy(
@@ -3652,7 +3604,7 @@ void rocksdb_options_set_min_level_to_compress(rocksdb_options_t* opt, int level
     assert(level <= opt->rep.num_levels);
     opt->rep.compression_per_level.resize(opt->rep.num_levels);
     for (int i = 0; i < level; i++) {
-      opt->rep.compression_per_level[i] = ROCKSDB_NAMESPACE::kNoCompression;
+      opt->rep.compression_per_level[i] = rocksdb::kNoCompression;
     }
     for (int i = level; i < opt->rep.num_levels; i++) {
       opt->rep.compression_per_level[i] = opt->rep.compression;
@@ -3859,8 +3811,8 @@ rocksdb_transactiondb_t* rocksdb_transactiondb_open(
 rocksdb_transactiondb_t* rocksdb_transactiondb_open_column_families(
     const rocksdb_options_t* options,
     const rocksdb_transactiondb_options_t* txn_db_options, const char* name,
-    int num_column_families, const char* const* column_family_names,
-    const rocksdb_options_t* const* column_family_options,
+    int num_column_families, const char** column_family_names,
+    const rocksdb_options_t** column_family_options,
     rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
@@ -4237,8 +4189,8 @@ rocksdb_optimistictransactiondb_t* rocksdb_optimistictransactiondb_open(
 rocksdb_optimistictransactiondb_t*
 rocksdb_optimistictransactiondb_open_column_families(
     const rocksdb_options_t* db_options, const char* name,
-    int num_column_families, const char* const* column_family_names,
-    const rocksdb_options_t* const* column_family_options,
+    int num_column_families, const char** column_family_names,
+    const rocksdb_options_t** column_family_options,
     rocksdb_column_family_handle_t** column_family_handles, char** errptr) {
   std::vector<ColumnFamilyDescriptor> column_families;
   for (int i = 0; i < num_column_families; i++) {
@@ -4354,8 +4306,7 @@ const char* rocksdb_pinnableslice_value(const rocksdb_pinnableslice_t* v,
   return v->rep.data();
 }
 
-// container to keep databases and caches in order to use
-// ROCKSDB_NAMESPACE::MemoryUtil
+// container to keep databases and caches in order to use rocksdb::MemoryUtil
 struct rocksdb_memory_consumers_t {
   std::vector<rocksdb_t*> dbs;
   std::unordered_set<rocksdb_cache_t*> caches;
@@ -4383,7 +4334,7 @@ void rocksdb_memory_consumers_destroy(rocksdb_memory_consumers_t* consumers) {
   delete consumers;
 }
 
-// contains memory usage statistics provided by ROCKSDB_NAMESPACE::MemoryUtil
+// contains memory usage statistics provided by rocksdb::MemoryUtil
 struct rocksdb_memory_usage_t {
   uint64_t mem_table_total;
   uint64_t mem_table_unflushed;
@@ -4405,7 +4356,7 @@ rocksdb_memory_usage_t* rocksdb_approximate_memory_usage_create(
     cache_set.insert(const_cast<const Cache*>(cache->rep.get()));
   }
 
-  std::map<ROCKSDB_NAMESPACE::MemoryUtil::UsageType, uint64_t> usage_by_type;
+  std::map<rocksdb::MemoryUtil::UsageType, uint64_t> usage_by_type;
 
   auto status = MemoryUtil::GetApproximateMemoryUsageByType(dbs, cache_set,
                                                             &usage_by_type);
@@ -4441,16 +4392,6 @@ 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;

db/c_test.c

@@ -487,11 +487,8 @@ int main(int argc, char** argv) {
   rocksdb_options_set_paranoid_checks(options, 1);
   rocksdb_options_set_max_open_files(options, 10);
   rocksdb_options_set_base_background_compactions(options, 1);
-
   table_options = rocksdb_block_based_options_create();
   rocksdb_block_based_options_set_block_cache(table_options, cache);
-  rocksdb_block_based_options_set_data_block_index_type(table_options, 1);
-  rocksdb_block_based_options_set_data_block_hash_ratio(table_options, 0.75);
   rocksdb_options_set_block_based_table_factory(options, table_options);
 
   rocksdb_options_set_compression(options, rocksdb_no_compression);
@@ -835,6 +832,23 @@ int main(int argc, char** argv) {
     rocksdb_writebatch_wi_iterate(wbi, &pos, CheckPut, CheckDel);
     CheckCondition(pos == 3);
     rocksdb_writebatch_wi_clear(wbi);
+    rocksdb_writebatch_wi_put(wbi, "bar", 3, "b", 1);
+    rocksdb_writebatch_wi_put(wbi, "bay", 3, "d", 1);
+    rocksdb_writebatch_wi_delete_range(wbi, "bar", 3, "bay", 3);
+    rocksdb_write_writebatch_wi(db, woptions, wbi, &err);
+    CheckNoError(err);
+    CheckGet(db, roptions, "bar", NULL);
+    CheckGet(db, roptions, "bay", "d");
+    rocksdb_writebatch_wi_clear(wbi);
+    const char* start_list[1] = {"bay"};
+    const size_t start_sizes[1] = {3};
+    const char* end_list[1] = {"baz"};
+    const size_t end_sizes[1] = {3};
+    rocksdb_writebatch_wi_delete_rangev(wbi, 1, start_list, start_sizes, end_list,
+                                     end_sizes);
+    rocksdb_write_writebatch_wi(db, woptions, wbi, &err);
+    CheckNoError(err);
+    CheckGet(db, roptions, "bay", NULL);
     rocksdb_writebatch_wi_destroy(wbi);
   }
 
@@ -1034,20 +1048,17 @@ int main(int argc, char** argv) {
   }
 
   StartPhase("filter");
-  for (run = 0; run <= 2; run++) {
-    // First run uses custom filter
-    // Second run uses old block-based bloom filter
-    // Third run uses full bloom filter
+  for (run = 0; run < 2; run++) {
+    // First run uses custom filter, second run uses bloom filter
     CheckNoError(err);
     rocksdb_filterpolicy_t* policy;
     if (run == 0) {
-      policy = rocksdb_filterpolicy_create(NULL, FilterDestroy, FilterCreate,
-                                           FilterKeyMatch, NULL, FilterName);
-    } else if (run == 1) {
-      policy = rocksdb_filterpolicy_create_bloom(8);
+      policy = rocksdb_filterpolicy_create(
+          NULL, FilterDestroy, FilterCreate, FilterKeyMatch, NULL, FilterName);
     } else {
-      policy = rocksdb_filterpolicy_create_bloom_full(8);
+      policy = rocksdb_filterpolicy_create_bloom(10);
     }
+
     rocksdb_block_based_options_set_filter_policy(table_options, policy);
 
     // Create new database
@@ -1060,24 +1071,12 @@ int main(int argc, char** argv) {
     CheckNoError(err);
     rocksdb_put(db, woptions, "bar", 3, "barvalue", 8, &err);
     CheckNoError(err);
-
-    {
-      // Add enough keys to get just one reasonably populated Bloom filter
-      const int keys_to_add = 1500;
-      int i;
-      char keybuf[100];
-      for (i = 0; i < keys_to_add; i++) {
-        snprintf(keybuf, sizeof(keybuf), "yes%020d", i);
-        rocksdb_put(db, woptions, keybuf, strlen(keybuf), "val", 3, &err);
-        CheckNoError(err);
-      }
-    }
     rocksdb_compact_range(db, NULL, 0, NULL, 0);
 
     fake_filter_result = 1;
     CheckGet(db, roptions, "foo", "foovalue");
     CheckGet(db, roptions, "bar", "barvalue");
-    if (run == 0) {
+    if (phase == 0) {
       // Must not find value when custom filter returns false
       fake_filter_result = 0;
       CheckGet(db, roptions, "foo", NULL);
@@ -1087,43 +1086,6 @@ int main(int argc, char** argv) {
       CheckGet(db, roptions, "foo", "foovalue");
       CheckGet(db, roptions, "bar", "barvalue");
     }
-
-    {
-      // Query some keys not added to identify Bloom filter implementation
-      // from false positive queries, using perfcontext to detect Bloom
-      // filter behavior
-      rocksdb_perfcontext_t* perf = rocksdb_perfcontext_create();
-      rocksdb_perfcontext_reset(perf);
-
-      const int keys_to_query = 10000;
-      int i;
-      char keybuf[100];
-      for (i = 0; i < keys_to_query; i++) {
-        fake_filter_result = i % 2;
-        snprintf(keybuf, sizeof(keybuf), "no%020d", i);
-        CheckGet(db, roptions, keybuf, NULL);
-      }
-
-      const int hits =
-          (int)rocksdb_perfcontext_metric(perf, rocksdb_bloom_sst_hit_count);
-      if (run == 0) {
-        // Due to half true, half false with fake filter result
-        CheckCondition(hits == keys_to_query / 2);
-      } else if (run == 1) {
-        // Essentially a fingerprint of the block-based Bloom schema
-        CheckCondition(hits == 241);
-      } else {
-        // Essentially a fingerprint of the full Bloom schema(s),
-        // format_version < 5, which vary for three different CACHE_LINE_SIZEs
-        CheckCondition(hits == 224 || hits == 180 || hits == 125);
-      }
-      CheckCondition(
-          (keys_to_query - hits) ==
-          (int)rocksdb_perfcontext_metric(perf, rocksdb_bloom_sst_miss_count));
-
-      rocksdb_perfcontext_destroy(perf);
-    }
-
     // Reset the policy
     rocksdb_block_based_options_set_filter_policy(table_options, NULL);
     rocksdb_options_set_block_based_table_factory(options, table_options);
@@ -1227,15 +1189,6 @@ int main(int argc, char** argv) {
     rocksdb_put_cf(db, woptions, handles[1], "foo", 3, "hello", 5, &err);
     CheckNoError(err);
 
-    rocksdb_put_cf(db, woptions, handles[1], "foobar1", 7, "hello1", 6, &err);
-    CheckNoError(err);
-    rocksdb_put_cf(db, woptions, handles[1], "foobar2", 7, "hello2", 6, &err);
-    CheckNoError(err);
-    rocksdb_put_cf(db, woptions, handles[1], "foobar3", 7, "hello3", 6, &err);
-    CheckNoError(err);
-    rocksdb_put_cf(db, woptions, handles[1], "foobar4", 7, "hello4", 6, &err);
-    CheckNoError(err);
-
     rocksdb_flushoptions_t *flush_options = rocksdb_flushoptions_create();
     rocksdb_flushoptions_set_wait(flush_options, 1);
     rocksdb_flush_cf(db, flush_options, handles[1], &err);
@@ -1248,10 +1201,6 @@ int main(int argc, char** argv) {
     rocksdb_delete_cf(db, woptions, handles[1], "foo", 3, &err);
     CheckNoError(err);
 
-    rocksdb_delete_range_cf(db, woptions, handles[1], "foobar2", 7, "foobar4",
-                            7, &err);
-    CheckNoError(err);
-
     CheckGetCF(db, roptions, handles[1], "foo", NULL);
     CheckPinGetCF(db, roptions, handles[1], "foo", NULL);
 
@@ -1304,7 +1253,7 @@ int main(int argc, char** argv) {
     for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
       i++;
     }
-    CheckCondition(i == 3);
+    CheckCondition(i == 1);
     rocksdb_iter_get_error(iter, &err);
     CheckNoError(err);
     rocksdb_iter_destroy(iter);
@@ -1328,7 +1277,7 @@ int main(int argc, char** argv) {
     for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
       i++;
     }
-    CheckCondition(i == 3);
+    CheckCondition(i == 1);
     rocksdb_iter_get_error(iter, &err);
     CheckNoError(err);
     rocksdb_iter_destroy(iter);
@@ -1518,7 +1467,6 @@ int main(int argc, char** argv) {
        CheckCondition(!rocksdb_iter_valid(iter));
 
        rocksdb_iter_destroy(iter);
-       rocksdb_readoptions_set_iterate_upper_bound(roptions, NULL, 0);
     }
   }
 

db/column_family.cc

@@ -9,11 +9,11 @@
 
 #include "db/column_family.h"
 
-#include <algorithm>
 #include <cinttypes>
-#include <limits>
-#include <string>
 #include <vector>
+#include <string>
+#include <algorithm>
+#include <limits>
 
 #include "db/compaction/compaction_picker.h"
 #include "db/compaction/compaction_picker_fifo.h"
@@ -30,13 +30,12 @@
 #include "memtable/hash_skiplist_rep.h"
 #include "monitoring/thread_status_util.h"
 #include "options/options_helper.h"
-#include "port/port.h"
 #include "table/block_based/block_based_table_factory.h"
 #include "table/merging_iterator.h"
 #include "util/autovector.h"
 #include "util/compression.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 ColumnFamilyHandleImpl::ColumnFamilyHandleImpl(
     ColumnFamilyData* column_family_data, DBImpl* db, InstrumentedMutex* mutex)
@@ -60,8 +59,11 @@ ColumnFamilyHandleImpl::~ColumnFamilyHandleImpl() {
     ColumnFamilyOptions initial_cf_options_copy = cfd_->initial_cf_options();
     JobContext job_context(0);
     mutex_->Lock();
-    bool dropped = cfd_->IsDropped();
-    if (cfd_->UnrefAndTryDelete()) {
+    if (cfd_->Unref()) {
+      bool dropped = cfd_->IsDropped();
+
+      delete cfd_;
+
       if (dropped) {
         db_->FindObsoleteFiles(&job_context, false, true);
       }
@@ -185,11 +187,6 @@ Status CheckCFPathsSupported(const DBOptions& db_options,
   return Status::OK();
 }
 
-namespace {
-const uint64_t kDefaultTtl = 0xfffffffffffffffe;
-const uint64_t kDefaultPeriodicCompSecs = 0xfffffffffffffffe;
-};  // namespace
-
 ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
                                     const ColumnFamilyOptions& src) {
   ColumnFamilyOptions result = src;
@@ -345,61 +342,6 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
     result.max_compaction_bytes = result.target_file_size_base * 25;
   }
 
-  bool is_block_based_table =
-      (result.table_factory->Name() == BlockBasedTableFactory().Name());
-
-  const uint64_t kAdjustedTtl = 30 * 24 * 60 * 60;
-  if (result.ttl == kDefaultTtl) {
-    if (is_block_based_table &&
-        result.compaction_style != kCompactionStyleFIFO) {
-      result.ttl = kAdjustedTtl;
-    } else {
-      result.ttl = 0;
-    }
-  }
-
-  const uint64_t kAdjustedPeriodicCompSecs = 30 * 24 * 60 * 60;
-
-  // Turn on periodic compactions and set them to occur once every 30 days if
-  // compaction filters are used and periodic_compaction_seconds is set to the
-  // default value.
-  if (result.compaction_style != kCompactionStyleFIFO) {
-    if ((result.compaction_filter != nullptr ||
-         result.compaction_filter_factory != nullptr) &&
-        result.periodic_compaction_seconds == kDefaultPeriodicCompSecs &&
-        is_block_based_table) {
-      result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
-    }
-  } else {
-    // result.compaction_style == kCompactionStyleFIFO
-    if (result.ttl == 0) {
-      if (is_block_based_table) {
-        if (result.periodic_compaction_seconds == kDefaultPeriodicCompSecs) {
-          result.periodic_compaction_seconds = kAdjustedPeriodicCompSecs;
-        }
-        result.ttl = result.periodic_compaction_seconds;
-      }
-    } else if (result.periodic_compaction_seconds != 0) {
-      result.ttl = std::min(result.ttl, result.periodic_compaction_seconds);
-    }
-  }
-
-  // TTL compactions would work similar to Periodic Compactions in Universal in
-  // most of the cases. So, if ttl is set, execute the periodic compaction
-  // codepath.
-  if (result.compaction_style == kCompactionStyleUniversal && result.ttl != 0) {
-    if (result.periodic_compaction_seconds != 0) {
-      result.periodic_compaction_seconds =
-          std::min(result.ttl, result.periodic_compaction_seconds);
-    } else {
-      result.periodic_compaction_seconds = result.ttl;
-    }
-  }
-
-  if (result.periodic_compaction_seconds == kDefaultPeriodicCompSecs) {
-    result.periodic_compaction_seconds = 0;
-  }
-
   return result;
 }
 
@@ -436,18 +378,13 @@ void SuperVersion::Cleanup() {
     to_delete.push_back(m);
   }
   current->Unref();
-  if (cfd->Unref()) {
-    delete cfd;
-  }
 }
 
-void SuperVersion::Init(ColumnFamilyData* new_cfd, MemTable* new_mem,
-                        MemTableListVersion* new_imm, Version* new_current) {
-  cfd = new_cfd;
+void SuperVersion::Init(MemTable* new_mem, MemTableListVersion* new_imm,
+                        Version* new_current) {
   mem = new_mem;
   imm = new_imm;
   current = new_current;
-  cfd->Ref();
   mem->Ref();
   imm->Ref();
   current->Ref();
@@ -471,22 +408,11 @@ 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,
     const ColumnFamilyOptions& cf_options, const ImmutableDBOptions& db_options,
-    const FileOptions& file_options, ColumnFamilySet* column_family_set,
+    const EnvOptions& env_options, ColumnFamilySet* column_family_set,
     BlockCacheTracer* const block_cache_tracer)
     : id_(id),
       name_(name),
@@ -518,23 +444,7 @@ 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.
@@ -544,7 +454,7 @@ ColumnFamilyData::ColumnFamilyData(
   if (_dummy_versions != nullptr) {
     internal_stats_.reset(
         new InternalStats(ioptions_.num_levels, db_options.env, this));
-    table_cache_.reset(new TableCache(ioptions_, file_options, _table_cache,
+    table_cache_.reset(new TableCache(ioptions_, env_options, _table_cache,
                                       block_cache_tracer));
     if (ioptions_.compaction_style == kCompactionStyleLevel) {
       compaction_picker_.reset(
@@ -610,7 +520,21 @@ ColumnFamilyData::~ColumnFamilyData() {
   // compaction_queue_ and we destroyed it
   assert(!queued_for_flush_);
   assert(!queued_for_compaction_);
-  assert(super_version_ == nullptr);
+
+  if (super_version_ != nullptr) {
+    // Release SuperVersion reference kept in ThreadLocalPtr.
+    // This must be done outside of mutex_ since unref handler can lock mutex.
+    super_version_->db_mutex->Unlock();
+    local_sv_.reset();
+    super_version_->db_mutex->Lock();
+
+    bool is_last_reference __attribute__((__unused__));
+    is_last_reference = super_version_->Unref();
+    assert(is_last_reference);
+    super_version_->Cleanup();
+    delete super_version_;
+    super_version_ = nullptr;
+  }
 
   if (dummy_versions_ != nullptr) {
     // List must be empty
@@ -628,48 +552,6 @@ 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() {
-  int old_refs = refs_.fetch_sub(1);
-  assert(old_refs > 0);
-
-  if (old_refs == 1) {
-    assert(super_version_ == nullptr);
-    delete this;
-    return true;
-  }
-
-  if (old_refs == 2 && super_version_ != nullptr) {
-    // Only the super_version_ holds me
-    SuperVersion* sv = super_version_;
-    super_version_ = nullptr;
-    // Release SuperVersion reference kept in ThreadLocalPtr.
-    // This must be done outside of mutex_ since unref handler can lock mutex.
-    sv->db_mutex->Unlock();
-    local_sv_.reset();
-    sv->db_mutex->Lock();
-
-    if (sv->Unref()) {
-      // May delete this ColumnFamilyData after calling Cleanup()
-      sv->Cleanup();
-      delete sv;
-      return true;
-    }
-  }
-  return false;
 }
 
 void ColumnFamilyData::SetDropped() {
@@ -1006,8 +888,8 @@ WriteStallCondition ColumnFamilyData::RecalculateWriteStallConditions(
   return write_stall_condition;
 }
 
-const FileOptions* ColumnFamilyData::soptions() const {
-  return &(column_family_set_->file_options_);
+const EnvOptions* ColumnFamilyData::soptions() const {
+  return &(column_family_set_->env_options_);
 }
 
 void ColumnFamilyData::SetCurrent(Version* current_version) {
@@ -1047,12 +929,8 @@ bool ColumnFamilyData::NeedsCompaction() const {
 
 Compaction* ColumnFamilyData::PickCompaction(
     const MutableCFOptions& mutable_options, LogBuffer* log_buffer) {
-  SequenceNumber earliest_mem_seqno =
-      std::min(mem_->GetEarliestSequenceNumber(),
-               imm_.current()->GetEarliestSequenceNumber(false));
   auto* result = compaction_picker_->PickCompaction(
-      GetName(), mutable_options, current_->storage_info(), log_buffer,
-      earliest_mem_seqno);
+      GetName(), mutable_options, current_->storage_info(), log_buffer);
   if (result != nullptr) {
     result->SetInputVersion(current_);
   }
@@ -1137,8 +1015,9 @@ Compaction* ColumnFamilyData::CompactRange(
   return result;
 }
 
-SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(DBImpl* db) {
-  SuperVersion* sv = GetThreadLocalSuperVersion(db);
+SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(
+    InstrumentedMutex* db_mutex) {
+  SuperVersion* sv = GetThreadLocalSuperVersion(db_mutex);
   sv->Ref();
   if (!ReturnThreadLocalSuperVersion(sv)) {
     // This Unref() corresponds to the Ref() in GetThreadLocalSuperVersion()
@@ -1150,7 +1029,8 @@ SuperVersion* ColumnFamilyData::GetReferencedSuperVersion(DBImpl* db) {
   return sv;
 }
 
-SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(DBImpl* db) {
+SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(
+    InstrumentedMutex* db_mutex) {
   // The SuperVersion is cached in thread local storage to avoid acquiring
   // mutex when SuperVersion does not change since the last use. When a new
   // SuperVersion is installed, the compaction or flush thread cleans up
@@ -1177,21 +1057,16 @@ SuperVersion* ColumnFamilyData::GetThreadLocalSuperVersion(DBImpl* db) {
 
     if (sv && sv->Unref()) {
       RecordTick(ioptions_.statistics, NUMBER_SUPERVERSION_CLEANUPS);
-      db->mutex()->Lock();
+      db_mutex->Lock();
       // NOTE: underlying resources held by superversion (sst files) might
       // not be released until the next background job.
       sv->Cleanup();
-      if (db->immutable_db_options().avoid_unnecessary_blocking_io) {
-        db->AddSuperVersionsToFreeQueue(sv);
-        db->SchedulePurge();
-      } else {
-        sv_to_delete = sv;
-      }
+      sv_to_delete = sv;
     } else {
-      db->mutex()->Lock();
+      db_mutex->Lock();
     }
     sv = super_version_->Ref();
-    db->mutex()->Unlock();
+    db_mutex->Unlock();
 
     delete sv_to_delete;
   }
@@ -1229,7 +1104,7 @@ void ColumnFamilyData::InstallSuperVersion(
   SuperVersion* new_superversion = sv_context->new_superversion.release();
   new_superversion->db_mutex = db_mutex;
   new_superversion->mutable_cf_options = mutable_cf_options;
-  new_superversion->Init(this, mem_, imm_.current(), current_);
+  new_superversion->Init(mem_, imm_.current(), current_);
   SuperVersion* old_superversion = super_version_;
   super_version_ = new_superversion;
   ++super_version_number_;
@@ -1286,11 +1161,6 @@ Status ColumnFamilyData::ValidateOptions(
   if (s.ok() && db_options.allow_concurrent_memtable_write) {
     s = CheckConcurrentWritesSupported(cf_options);
   }
-  if (s.ok() && db_options.unordered_write &&
-      cf_options.max_successive_merges != 0) {
-    s = Status::InvalidArgument(
-        "max_successive_merges > 0 is incompatible with unordered_write");
-  }
   if (s.ok()) {
     s = CheckCFPathsSupported(db_options, cf_options);
   }
@@ -1298,15 +1168,24 @@ Status ColumnFamilyData::ValidateOptions(
     return s;
   }
 
-  if (cf_options.ttl > 0 && cf_options.ttl != kDefaultTtl) {
+  if (cf_options.ttl > 0) {
+    if (db_options.max_open_files != -1) {
+      return Status::NotSupported(
+          "TTL is only supported when files are always "
+          "kept open (set max_open_files = -1). ");
+    }
     if (cf_options.table_factory->Name() != BlockBasedTableFactory().Name()) {
       return Status::NotSupported(
           "TTL is only supported in Block-Based Table format. ");
     }
   }
 
-  if (cf_options.periodic_compaction_seconds > 0 &&
-      cf_options.periodic_compaction_seconds != kDefaultPeriodicCompSecs) {
+  if (cf_options.periodic_compaction_seconds > 0) {
+    if (db_options.max_open_files != -1) {
+      return Status::NotSupported(
+          "Periodic Compaction is only supported when files are always "
+          "kept open (set max_open_files = -1). ");
+    }
     if (cf_options.table_factory->Name() != BlockBasedTableFactory().Name()) {
       return Status::NotSupported(
           "Periodic Compaction is only supported in "
@@ -1350,41 +1229,28 @@ Env::WriteLifeTimeHint ColumnFamilyData::CalculateSSTWriteHint(int level) {
   // L1: medium, L2: long, ...
   if (level - base_level >= 2) {
     return Env::WLTH_EXTREME;
-  } else if (level < base_level) {
-    // There is no restriction which prevents level passed in to be smaller
-    // than base_level.
-    return Env::WLTH_MEDIUM;
   }
   return static_cast<Env::WriteLifeTimeHint>(level - base_level +
                             static_cast<int>(Env::WLTH_MEDIUM));
 }
 
-Status ColumnFamilyData::AddDirectories(
-    std::map<std::string, std::shared_ptr<FSDirectory>>* created_dirs) {
+Status ColumnFamilyData::AddDirectories() {
   Status s;
-  assert(created_dirs != nullptr);
   assert(data_dirs_.empty());
   for (auto& p : ioptions_.cf_paths) {
-    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);
-      if (!s.ok()) {
-        return s;
-      }
-      assert(path_directory != nullptr);
-      data_dirs_.emplace_back(path_directory.release());
-      (*created_dirs)[p.path] = data_dirs_.back();
-    } else {
-      data_dirs_.emplace_back(existing_dir->second);
+    std::unique_ptr<Directory> path_directory;
+    s = DBImpl::CreateAndNewDirectory(ioptions_.env, p.path, &path_directory);
+    if (!s.ok()) {
+      return s;
     }
+    assert(path_directory != nullptr);
+    data_dirs_.emplace_back(path_directory.release());
   }
   assert(data_dirs_.size() == ioptions_.cf_paths.size());
   return s;
 }
 
-FSDirectory* ColumnFamilyData::GetDataDir(size_t path_id) const {
+Directory* ColumnFamilyData::GetDataDir(size_t path_id) const {
   if (data_dirs_.empty()) {
     return nullptr;
   }
@@ -1395,23 +1261,22 @@ FSDirectory* ColumnFamilyData::GetDataDir(size_t path_id) const {
 
 ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
                                  const ImmutableDBOptions* db_options,
-                                 const FileOptions& file_options,
+                                 const EnvOptions& env_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,
+          env_options, nullptr, block_cache_tracer)),
       default_cfd_cache_(nullptr),
       db_name_(dbname),
       db_options_(db_options),
-      file_options_(file_options),
+      env_options_(env_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_;
@@ -1423,12 +1288,14 @@ ColumnFamilySet::~ColumnFamilySet() {
     // cfd destructor will delete itself from column_family_data_
     auto cfd = column_family_data_.begin()->second;
     bool last_ref __attribute__((__unused__));
-    last_ref = cfd->UnrefAndTryDelete();
+    last_ref = cfd->Unref();
     assert(last_ref);
+    delete cfd;
   }
   bool dummy_last_ref __attribute__((__unused__));
-  dummy_last_ref = dummy_cfd_->UnrefAndTryDelete();
+  dummy_last_ref = dummy_cfd_->Unref();
   assert(dummy_last_ref);
+  delete dummy_cfd_;
 }
 
 ColumnFamilyData* ColumnFamilySet::GetDefault() const {
@@ -1478,7 +1345,7 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
   assert(column_families_.find(name) == column_families_.end());
   ColumnFamilyData* new_cfd = new ColumnFamilyData(
       id, name, dummy_versions, table_cache_, write_buffer_manager_, options,
-      *db_options_, file_options_, this, block_cache_tracer_);
+      *db_options_, env_options_, this, block_cache_tracer_);
   column_families_.insert({name, id});
   column_family_data_.insert({id, new_cfd});
   max_column_family_ = std::max(max_column_family_, id);
@@ -1560,4 +1427,4 @@ const Comparator* GetColumnFamilyUserComparator(
   return nullptr;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/column_family.h

@@ -27,7 +27,7 @@
 #include "trace_replay/block_cache_tracer.h"
 #include "util/thread_local.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class Version;
 class VersionSet;
@@ -198,7 +198,6 @@ class ColumnFamilyHandleInternal : public ColumnFamilyHandleImpl {
 struct SuperVersion {
   // Accessing members of this class is not thread-safe and requires external
   // synchronization (ie db mutex held or on write thread).
-  ColumnFamilyData* cfd;
   MemTable* mem;
   MemTableListVersion* imm;
   Version* current;
@@ -222,8 +221,8 @@ struct SuperVersion {
   // that needs to be deleted in to_delete vector. Unrefing those
   // objects needs to be done in the mutex
   void Cleanup();
-  void Init(ColumnFamilyData* new_cfd, MemTable* new_mem,
-            MemTableListVersion* new_imm, Version* new_current);
+  void Init(MemTable* new_mem, MemTableListVersion* new_imm,
+            Version* new_current);
 
   // The value of dummy is not actually used. kSVInUse takes its address as a
   // mark in the thread local storage to indicate the SuperVersion is in use
@@ -289,11 +288,6 @@ class ColumnFamilyData {
     return old_refs == 1;
   }
 
-  // UnrefAndTryDelete() decreases the reference count and do free if needed,
-  // return true if this is freed else false, UnrefAndTryDelete() can only
-  // be called while holding a DB mutex, or during single-threaded recovery.
-  bool UnrefAndTryDelete();
-
   // SetDropped() can only be called under following conditions:
   // 1) Holding a DB mutex,
   // 2) from single-threaded write thread, AND
@@ -324,7 +318,7 @@ class ColumnFamilyData {
   }
   FlushReason GetFlushReason() const { return flush_reason_; }
   // thread-safe
-  const FileOptions* soptions() const;
+  const EnvOptions* soptions() const;
   const ImmutableCFOptions* ioptions() const { return &ioptions_; }
   // REQUIRES: DB mutex held
   // This returns the MutableCFOptions used by current SuperVersion
@@ -436,11 +430,11 @@ class ColumnFamilyData {
   SuperVersion* GetSuperVersion() { return super_version_; }
   // thread-safe
   // Return a already referenced SuperVersion to be used safely.
-  SuperVersion* GetReferencedSuperVersion(DBImpl* db);
+  SuperVersion* GetReferencedSuperVersion(InstrumentedMutex* db_mutex);
   // thread-safe
   // Get SuperVersion stored in thread local storage. If it does not exist,
   // get a reference from a current SuperVersion.
-  SuperVersion* GetThreadLocalSuperVersion(DBImpl* db);
+  SuperVersion* GetThreadLocalSuperVersion(InstrumentedMutex* db_mutex);
   // Try to return SuperVersion back to thread local storage. Retrun true on
   // success and false on failure. It fails when the thread local storage
   // contains anything other than SuperVersion::kSVInUse flag.
@@ -497,29 +491,23 @@ class ColumnFamilyData {
 
   Env::WriteLifeTimeHint CalculateSSTWriteHint(int level);
 
-  // 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);
+  Status AddDirectories();
 
-  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,
                    const ColumnFamilyOptions& options,
                    const ImmutableDBOptions& db_options,
-                   const FileOptions& file_options,
+                   const EnvOptions& env_options,
                    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 +583,7 @@ 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::unique_ptr<Directory>> data_dirs_;
 };
 
 // ColumnFamilySet has interesting thread-safety requirements
@@ -646,9 +632,9 @@ 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,
+                  const EnvOptions& env_options, Cache* table_cache,
+                  WriteBufferManager* write_buffer_manager,
+                  WriteController* write_controller,
                   BlockCacheTracer* const block_cache_tracer);
   ~ColumnFamilySet();
 
@@ -678,10 +664,6 @@ 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
@@ -708,7 +690,7 @@ class ColumnFamilySet {
 
   const std::string db_name_;
   const ImmutableDBOptions* const db_options_;
-  const FileOptions file_options_;
+  const EnvOptions env_options_;
   Cache* table_cache_;
   WriteBufferManager* write_buffer_manager_;
   WriteController* write_controller_;
@@ -763,4 +745,4 @@ extern uint32_t GetColumnFamilyID(ColumnFamilyHandle* column_family);
 extern const Comparator* GetColumnFamilyUserComparator(
     ColumnFamilyHandle* column_family);
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/column_family_test.cc

@@ -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"
@@ -30,7 +30,7 @@
 #include "util/string_util.h"
 #include "utilities/merge_operators.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 static const int kValueSize = 1000;
 
@@ -67,9 +67,9 @@ class ColumnFamilyTestBase : public testing::Test {
 #ifndef ROCKSDB_LITE
     const char* test_env_uri = getenv("TEST_ENV_URI");
     if (test_env_uri) {
-      Env* test_env = nullptr;
-      Status s = Env::LoadEnv(test_env_uri, &test_env, &env_guard_);
-      base_env = test_env;
+      Status s = ObjectRegistry::NewInstance()->NewSharedObject(test_env_uri,
+                                                                &env_guard_);
+      base_env = env_guard_.get();
       EXPECT_OK(s);
       EXPECT_NE(Env::Default(), base_env);
     }
@@ -91,7 +91,7 @@ class ColumnFamilyTestBase : public testing::Test {
       column_families.push_back(cfdescriptor);
     }
     Close();
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
     Destroy(column_families);
     delete env_;
   }
@@ -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++;
     }
@@ -597,15 +595,14 @@ TEST_P(ColumnFamilyTest, DontReuseColumnFamilyID) {
 TEST_P(ColumnFamilyTest, CreateCFRaceWithGetAggProperty) {
   Open();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"DBImpl::WriteOptionsFile:1",
         "ColumnFamilyTest.CreateCFRaceWithGetAggProperty:1"},
        {"ColumnFamilyTest.CreateCFRaceWithGetAggProperty:2",
         "DBImpl::WriteOptionsFile:2"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
-  ROCKSDB_NAMESPACE::port::Thread thread(
-      [&] { CreateColumnFamilies({"one"}); });
+  rocksdb::port::Thread thread([&] { CreateColumnFamilies({"one"}); });
 
   TEST_SYNC_POINT("ColumnFamilyTest.CreateCFRaceWithGetAggProperty:1");
   uint64_t pv;
@@ -614,7 +611,7 @@ TEST_P(ColumnFamilyTest, CreateCFRaceWithGetAggProperty) {
 
   thread.join();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 }
 #endif  // !ROCKSDB_LITE
 
@@ -823,7 +820,7 @@ 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"});
@@ -1256,14 +1253,13 @@ TEST_P(ColumnFamilyTest, DifferentWriteBufferSizes) {
 // #endif  // !ROCKSDB_LITE
 
 class TestComparator : public Comparator {
-  int Compare(const ROCKSDB_NAMESPACE::Slice& /*a*/,
-              const ROCKSDB_NAMESPACE::Slice& /*b*/) const override {
+  int Compare(const rocksdb::Slice& /*a*/,
+              const rocksdb::Slice& /*b*/) const override {
     return 0;
   }
   const char* Name() const override { return "Test"; }
-  void FindShortestSeparator(
-      std::string* /*start*/,
-      const ROCKSDB_NAMESPACE::Slice& /*limit*/) const override {}
+  void FindShortestSeparator(std::string* /*start*/,
+                             const rocksdb::Slice& /*limit*/) const override {}
   void FindShortSuccessor(std::string* /*key*/) const override {}
 };
 
@@ -1431,11 +1427,11 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
     AssertFilesPerLevel(ToString(i + 1), 1);
   }
   bool cf_1_1 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::MultiManual:4", "ColumnFamilyTest::MultiManual:1"},
        {"ColumnFamilyTest::MultiManual:2", "ColumnFamilyTest::MultiManual:5"},
        {"ColumnFamilyTest::MultiManual:2", "ColumnFamilyTest::MultiManual:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::MultiManual:4");
@@ -1444,7 +1440,7 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
   std::vector<port::Thread> threads;
   threads.emplace_back([&] {
     CompactRangeOptions compact_options;
@@ -1487,8 +1483,8 @@ TEST_P(ColumnFamilyTest, MultipleManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
   Close();
 }
 
@@ -1527,11 +1523,11 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
       dbfull()->TEST_write_controler().GetCompactionPressureToken();
 
   bool cf_1_1 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::AutoManual:4", "ColumnFamilyTest::AutoManual:1"},
        {"ColumnFamilyTest::AutoManual:2", "ColumnFamilyTest::AutoManual:5"},
        {"ColumnFamilyTest::AutoManual:2", "ColumnFamilyTest::AutoManual:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           cf_1_1 = false;
@@ -1539,7 +1535,7 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
           TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:3");
         }
       });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
   // SETUP column family "one" -- universal style
   for (int i = 0; i < one.level0_file_num_compaction_trigger; ++i) {
     PutRandomData(1, 10, 12000, true);
@@ -1557,7 +1553,7 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
     WaitForFlush(2);
     AssertFilesPerLevel(ToString(i + 1), 2);
   }
-  ROCKSDB_NAMESPACE::port::Thread threads([&] {
+  rocksdb::port::Thread threads([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = false;
     ASSERT_OK(
@@ -1584,8 +1580,8 @@ TEST_P(ColumnFamilyTest, AutomaticAndManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
 TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
@@ -1631,11 +1627,11 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
   }
   bool cf_1_1 = true;
   bool cf_1_2 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:1"},
        {"ColumnFamilyTest::ManualAuto:5", "ColumnFamilyTest::ManualAuto:2"},
        {"ColumnFamilyTest::ManualAuto:2", "ColumnFamilyTest::ManualAuto:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:4");
@@ -1647,8 +1643,8 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-  ROCKSDB_NAMESPACE::port::Thread threads([&] {
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::port::Thread threads([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = false;
     ASSERT_OK(
@@ -1683,8 +1679,8 @@ TEST_P(ColumnFamilyTest, ManualAndAutomaticCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
 TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
@@ -1725,13 +1721,13 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
   }
   bool cf_1_1 = true;
   bool cf_1_2 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::ManualManual:4", "ColumnFamilyTest::ManualManual:2"},
        {"ColumnFamilyTest::ManualManual:4", "ColumnFamilyTest::ManualManual:5"},
        {"ColumnFamilyTest::ManualManual:1", "ColumnFamilyTest::ManualManual:2"},
        {"ColumnFamilyTest::ManualManual:1",
         "ColumnFamilyTest::ManualManual:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::ManualManual:4");
@@ -1743,8 +1739,8 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-  ROCKSDB_NAMESPACE::port::Thread threads([&] {
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::port::Thread threads([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = true;
     ASSERT_OK(
@@ -1764,7 +1760,7 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
                         1);
   }
 
-  ROCKSDB_NAMESPACE::port::Thread threads1([&] {
+  rocksdb::port::Thread threads1([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = false;
     ASSERT_OK(
@@ -1785,8 +1781,8 @@ TEST_P(ColumnFamilyTest, SameCFManualManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
 TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
@@ -1827,12 +1823,12 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
   }
   bool cf_1_1 = true;
   bool cf_1_2 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:2"},
        {"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:5"},
        {"ColumnFamilyTest::ManualAuto:1", "ColumnFamilyTest::ManualAuto:2"},
        {"ColumnFamilyTest::ManualAuto:1", "ColumnFamilyTest::ManualAuto:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:4");
@@ -1844,8 +1840,8 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-  ROCKSDB_NAMESPACE::port::Thread threads([&] {
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::port::Thread threads([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = false;
     ASSERT_OK(
@@ -1878,8 +1874,8 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
 TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
@@ -1920,14 +1916,14 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
   }
   bool cf_1_1 = true;
   bool cf_1_2 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:2"},
        {"ColumnFamilyTest::ManualAuto:4", "ColumnFamilyTest::ManualAuto:5"},
        {"ColumnFamilyTest::ManualAuto:3", "ColumnFamilyTest::ManualAuto:2"},
        {"LevelCompactionPicker::PickCompactionBySize:0",
         "ColumnFamilyTest::ManualAuto:3"},
        {"ColumnFamilyTest::ManualAuto:1", "ColumnFamilyTest::ManualAuto:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::ManualAuto:4");
@@ -1939,8 +1935,8 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
-  ROCKSDB_NAMESPACE::port::Thread threads([&] {
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::port::Thread threads([&] {
     CompactRangeOptions compact_options;
     compact_options.exclusive_manual_compaction = false;
     ASSERT_OK(
@@ -1971,8 +1967,8 @@ TEST_P(ColumnFamilyTest, SameCFManualAutomaticCompactionsLevel) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 
 // In this test, we generate enough files to trigger automatic compactions.
@@ -2012,12 +2008,12 @@ TEST_P(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
 
   bool cf_1_1 = true;
   bool cf_1_2 = true;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"ColumnFamilyTest::AutoManual:4", "ColumnFamilyTest::AutoManual:2"},
        {"ColumnFamilyTest::AutoManual:4", "ColumnFamilyTest::AutoManual:5"},
        {"CompactionPicker::CompactRange:Conflict",
         "ColumnFamilyTest::AutoManual:3"}});
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* /*arg*/) {
         if (cf_1_1) {
           TEST_SYNC_POINT("ColumnFamilyTest::AutoManual:4");
@@ -2029,7 +2025,7 @@ TEST_P(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
         }
       });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   // SETUP column family "one" -- universal style
   for (int i = 0; i < one.level0_file_num_compaction_trigger; ++i) {
@@ -2063,8 +2059,8 @@ TEST_P(ColumnFamilyTest, SameCFAutomaticManualCompactions) {
     ASSERT_NE("NOT_FOUND", Get(1, *key_iter));
     key_iter++;
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 #endif  // !ROCKSDB_LITE
 
@@ -2369,45 +2365,6 @@ TEST_P(ColumnFamilyTest, ReadDroppedColumnFamily) {
   }
 }
 
-TEST_P(ColumnFamilyTest, LiveIteratorWithDroppedColumnFamily) {
-  db_options_.create_missing_column_families = true;
-  db_options_.max_open_files = 20;
-  // delete obsolete files always
-  db_options_.delete_obsolete_files_period_micros = 0;
-  Open({"default", "one", "two"});
-  ColumnFamilyOptions options;
-  options.level0_file_num_compaction_trigger = 100;
-  options.level0_slowdown_writes_trigger = 200;
-  options.level0_stop_writes_trigger = 200;
-  options.write_buffer_size = 100000;  // small write buffer size
-  Reopen({options, options, options});
-
-  // 1MB should create ~10 files for each CF
-  int kKeysNum = 10000;
-  PutRandomData(1, kKeysNum, 100);
-
-  {
-    std::unique_ptr<Iterator> iterator(
-        db_->NewIterator(ReadOptions(), handles_[1]));
-    iterator->SeekToFirst();
-
-    DropColumnFamilies({1});
-
-    // Make sure iterator created can still be used.
-    int count = 0;
-    for (; iterator->Valid(); iterator->Next()) {
-      ASSERT_OK(iterator->status());
-      ++count;
-    }
-    ASSERT_OK(iterator->status());
-    ASSERT_EQ(count, kKeysNum);
-  }
-
-  Reopen();
-  Close();
-  Destroy();
-}
-
 TEST_P(ColumnFamilyTest, FlushAndDropRaceCondition) {
   db_options_.create_missing_column_families = true;
   Open({"default", "one"});
@@ -2419,7 +2376,7 @@ TEST_P(ColumnFamilyTest, FlushAndDropRaceCondition) {
   options.write_buffer_size = 100000;  // small write buffer size
   Reopen({options, options});
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"VersionSet::LogAndApply::ColumnFamilyDrop:0",
         "FlushJob::WriteLevel0Table"},
        {"VersionSet::LogAndApply::ColumnFamilyDrop:1",
@@ -2427,7 +2384,7 @@ TEST_P(ColumnFamilyTest, FlushAndDropRaceCondition) {
        {"FlushJob::InstallResults",
         "VersionSet::LogAndApply::ColumnFamilyDrop:2"}});
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
   test::SleepingBackgroundTask sleeping_task;
 
   env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask, &sleeping_task,
@@ -2506,21 +2463,21 @@ TEST_P(ColumnFamilyTest, CreateAndDropRace) {
 
   auto main_thread_id = std::this_thread::get_id();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
-      "PersistRocksDBOptions:start", [&](void* /*arg*/) {
-        auto current_thread_id = std::this_thread::get_id();
-        // If it's the main thread hitting this sync-point, then it
-        // will be blocked until some other thread update the test_stage.
-        if (main_thread_id == current_thread_id) {
-          test_stage = kMainThreadStartPersistingOptionsFile;
-          while (test_stage < kChildThreadFinishDroppingColumnFamily &&
-                 !ordered_by_writethread) {
-            Env::Default()->SleepForMicroseconds(100);
-          }
-        }
-      });
+  rocksdb::SyncPoint::GetInstance()->SetCallBack("PersistRocksDBOptions:start",
+                                                 [&](void* /*arg*/) {
+    auto current_thread_id = std::this_thread::get_id();
+    // If it's the main thread hitting this sync-point, then it
+    // will be blocked until some other thread update the test_stage.
+    if (main_thread_id == current_thread_id) {
+      test_stage = kMainThreadStartPersistingOptionsFile;
+      while (test_stage < kChildThreadFinishDroppingColumnFamily &&
+             !ordered_by_writethread) {
+        Env::Default()->SleepForMicroseconds(100);
+      }
+    }
+  });
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "WriteThread::EnterUnbatched:Wait", [&](void* /*arg*/) {
         // This means a thread doing DropColumnFamily() is waiting for
         // other thread to finish persisting options.
@@ -2532,12 +2489,12 @@ TEST_P(ColumnFamilyTest, CreateAndDropRace) {
   Open({"default", "one", "two", "three"},
        {cf_opts[0], cf_opts[1], cf_opts[2], cf_opts[3]});
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   // Start a thread that will drop the first column family
   // and its comparator
-  ROCKSDB_NAMESPACE::port::Thread drop_cf_thread(DropSingleColumnFamily, this,
-                                                 1, &comparators);
+  rocksdb::port::Thread drop_cf_thread(DropSingleColumnFamily, this, 1,
+                                       &comparators);
 
   DropColumnFamilies({2});
 
@@ -2550,8 +2507,8 @@ TEST_P(ColumnFamilyTest, CreateAndDropRace) {
     }
   }
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 }
 #endif  // !ROCKSDB_LITE
 
@@ -2986,10 +2943,10 @@ TEST_P(ColumnFamilyTest, FlushCloseWALFiles) {
   ASSERT_OK(Put(0, "fodor", "mirko"));
   ASSERT_OK(Put(1, "fodor", "mirko"));
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"DBImpl::BGWorkFlush:done", "FlushCloseWALFiles:0"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   // Block flush jobs from running
   test::SleepingBackgroundTask sleeping_task;
@@ -3005,7 +2962,7 @@ TEST_P(ColumnFamilyTest, FlushCloseWALFiles) {
   sleeping_task.WakeUp();
   sleeping_task.WaitUntilDone();
   TEST_SYNC_POINT("FlushCloseWALFiles:0");
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
   ASSERT_EQ(1, env.num_open_wal_file_.load());
 
   Reopen();
@@ -3083,14 +3040,14 @@ TEST_P(ColumnFamilyTest, IteratorCloseWALFile2) {
   ASSERT_OK(Put(0, "fodor", "mirko"));
   ASSERT_OK(Put(1, "fodor", "mirko"));
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"ColumnFamilyTest::IteratorCloseWALFile2:0",
        "DBImpl::BGWorkPurge:start"},
       {"ColumnFamilyTest::IteratorCloseWALFile2:2",
        "DBImpl::BackgroundCallFlush:start"},
       {"DBImpl::BGWorkPurge:end", "ColumnFamilyTest::IteratorCloseWALFile2:1"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   WriteOptions wo;
   wo.sync = true;
@@ -3108,7 +3065,7 @@ TEST_P(ColumnFamilyTest, IteratorCloseWALFile2) {
   TEST_SYNC_POINT("ColumnFamilyTest::IteratorCloseWALFile2:2");
   WaitForFlush(1);
   ASSERT_EQ(1, env.num_open_wal_file_.load());
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 
   Reopen();
   ASSERT_EQ("mirko", Get(0, "fodor"));
@@ -3152,14 +3109,14 @@ TEST_P(ColumnFamilyTest, ForwardIteratorCloseWALFile) {
   ASSERT_OK(Put(0, "fodor", "mirko"));
   ASSERT_OK(Put(1, "fodor", "mirko"));
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"ColumnFamilyTest::IteratorCloseWALFile2:0",
        "DBImpl::BGWorkPurge:start"},
       {"ColumnFamilyTest::IteratorCloseWALFile2:2",
        "DBImpl::BackgroundCallFlush:start"},
       {"DBImpl::BGWorkPurge:end", "ColumnFamilyTest::IteratorCloseWALFile2:1"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   WriteOptions wo;
   wo.sync = true;
@@ -3183,7 +3140,7 @@ TEST_P(ColumnFamilyTest, ForwardIteratorCloseWALFile) {
   ASSERT_EQ(1, env.delete_count_.load());
 
   delete it;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 
   Reopen();
   ASSERT_EQ("mirko", Get(0, "fodor"));
@@ -3203,15 +3160,15 @@ TEST_P(ColumnFamilyTest, LogSyncConflictFlush) {
   Put(0, "", "");
   Put(1, "foo", "bar");
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency(
+  rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"DBImpl::SyncWAL:BeforeMarkLogsSynced:1",
         "ColumnFamilyTest::LogSyncConflictFlush:1"},
        {"ColumnFamilyTest::LogSyncConflictFlush:2",
         "DBImpl::SyncWAL:BeforeMarkLogsSynced:2"}});
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
-  ROCKSDB_NAMESPACE::port::Thread thread([&] { db_->SyncWAL(); });
+  rocksdb::port::Thread thread([&] { db_->SyncWAL(); });
 
   TEST_SYNC_POINT("ColumnFamilyTest::LogSyncConflictFlush:1");
   Flush(1);
@@ -3222,7 +3179,7 @@ TEST_P(ColumnFamilyTest, LogSyncConflictFlush) {
 
   thread.join();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
   Close();
 }
 #endif
@@ -3371,7 +3328,7 @@ TEST_P(ColumnFamilyTest, MultipleCFPathsTest) {
   }
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 #ifdef ROCKSDB_UNITTESTS_WITH_CUSTOM_OBJECTS_FROM_STATIC_LIBS
 extern "C" {
@@ -3382,7 +3339,7 @@ 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();
+  rocksdb::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
   RegisterCustomObjects(argc, argv);
   return RUN_ALL_TESTS();

db/compact_files_test.cc

@@ -18,7 +18,7 @@
 #include "test_util/testharness.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class CompactFilesTest : public testing::Test {
  public:
@@ -81,11 +81,11 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
   assert(s.ok());
   assert(db);
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"CompactFilesImpl:0", "BackgroundCallCompaction:0"},
       {"BackgroundCallCompaction:1", "CompactFilesImpl:1"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   // create couple files
   // Background compaction starts and waits in BackgroundCallCompaction:0
@@ -95,7 +95,7 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
     db->Flush(FlushOptions());
   }
 
-  ROCKSDB_NAMESPACE::ColumnFamilyMetaData meta;
+  rocksdb::ColumnFamilyMetaData meta;
   db->GetColumnFamilyMetaData(&meta);
   std::string file1;
   for (auto& file : meta.levels[0].files) {
@@ -108,12 +108,12 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
       // The background compaction then notices that there is an L0 compaction
       // already in progress and doesn't do an L0 compaction
       // Once the background compaction finishes, the compact files finishes
-      ASSERT_OK(db->CompactFiles(ROCKSDB_NAMESPACE::CompactionOptions(),
-                                 {file1, file2}, 0));
+      ASSERT_OK(
+          db->CompactFiles(rocksdb::CompactionOptions(), {file1, file2}, 0));
       break;
     }
   }
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
   delete db;
 }
 
@@ -224,14 +224,14 @@ TEST_F(CompactFilesTest, CapturingPendingFiles) {
   auto l0_files = collector->GetFlushedFiles();
   EXPECT_EQ(5, l0_files.size());
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"CompactFilesImpl:2", "CompactFilesTest.CapturingPendingFiles:0"},
       {"CompactFilesTest.CapturingPendingFiles:1", "CompactFilesImpl:3"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   // Start compacting files.
-  ROCKSDB_NAMESPACE::port::Thread compaction_thread(
+  rocksdb::port::Thread compaction_thread(
       [&] { EXPECT_OK(db->CompactFiles(CompactionOptions(), l0_files, 1)); });
 
   // In the meantime flush another file.
@@ -242,7 +242,7 @@ TEST_F(CompactFilesTest, CapturingPendingFiles) {
 
   compaction_thread.join();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 
   delete db;
 
@@ -296,12 +296,12 @@ TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
   db->Flush(FlushOptions());
 
   // Compact all L0 files using CompactFiles
-  ROCKSDB_NAMESPACE::ColumnFamilyMetaData meta;
+  rocksdb::ColumnFamilyMetaData meta;
   db->GetColumnFamilyMetaData(&meta);
   for (auto& file : meta.levels[0].files) {
     std::string fname = file.db_path + "/" + file.name;
     ASSERT_OK(
-        db->CompactFiles(ROCKSDB_NAMESPACE::CompactionOptions(), {fname}, 0));
+        db->CompactFiles(rocksdb::CompactionOptions(), {fname}, 0));
   }
 
 
@@ -347,7 +347,7 @@ TEST_F(CompactFilesTest, SentinelCompressionType) {
     compaction_opts.compression = CompressionType::kDisableCompressionOption;
     ASSERT_OK(db->CompactFiles(compaction_opts, l0_files, 1));
 
-    ROCKSDB_NAMESPACE::TablePropertiesCollection all_tables_props;
+    rocksdb::TablePropertiesCollection all_tables_props;
     ASSERT_OK(db->GetPropertiesOfAllTables(&all_tables_props));
     for (const auto& name_and_table_props : all_tables_props) {
       ASSERT_EQ(CompressionTypeToString(CompressionType::kZlibCompression),
@@ -387,7 +387,7 @@ TEST_F(CompactFilesTest, GetCompactionJobInfo) {
   auto l0_files_1 = collector->GetFlushedFiles();
   CompactionOptions co;
   co.compression = CompressionType::kLZ4Compression;
-  CompactionJobInfo compaction_job_info{};
+  CompactionJobInfo compaction_job_info;
   ASSERT_OK(
       db->CompactFiles(co, l0_files_1, 0, -1, nullptr, &compaction_job_info));
   ASSERT_EQ(compaction_job_info.base_input_level, 0);
@@ -402,7 +402,7 @@ TEST_F(CompactFilesTest, GetCompactionJobInfo) {
   delete db;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

db/compacted_db_impl.cc

@@ -9,7 +9,7 @@
 #include "db/version_set.h"
 #include "table/get_context.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 extern void MarkKeyMayExist(void* arg);
 extern bool SaveValue(void* arg, const ParsedInternalKey& parsed_key,
@@ -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());
@@ -156,5 +156,5 @@ Status CompactedDBImpl::Open(const Options& options,
   return s;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}   // namespace rocksdb
 #endif  // ROCKSDB_LITE

db/compacted_db_impl.h

@@ -9,7 +9,7 @@
 #include <vector>
 #include "db/db_impl/db_impl.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class CompactedDBImpl : public DBImpl {
  public:
@@ -109,5 +109,5 @@ class CompactedDBImpl : public DBImpl {
   const Comparator* user_comparator_;
   LevelFilesBrief files_;
 };
-}  // namespace ROCKSDB_NAMESPACE
+}
 #endif  // ROCKSDB_LITE

db/compaction/compaction.cc

@@ -16,14 +16,14 @@
 #include "test_util/sync_point.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 const uint64_t kRangeTombstoneSentinel =
     PackSequenceAndType(kMaxSequenceNumber, kTypeRangeDeletion);
 
 int sstableKeyCompare(const Comparator* user_cmp, const InternalKey& a,
                       const InternalKey& b) {
-  auto c = user_cmp->CompareWithoutTimestamp(a.user_key(), b.user_key());
+  auto c = user_cmp->Compare(a.user_key(), b.user_key());
   if (c != 0) {
     return c;
   }
@@ -275,7 +275,9 @@ Compaction::~Compaction() {
     input_version_->Unref();
   }
   if (cfd_ != nullptr) {
-    cfd_->UnrefAndTryDelete();
+    if (cfd_->Unref()) {
+      delete cfd_;
+    }
   }
 }
 
@@ -543,22 +545,21 @@ bool Compaction::ShouldFormSubcompactions() const {
   }
 }
 
-uint64_t Compaction::MinInputFileOldestAncesterTime() const {
-  uint64_t min_oldest_ancester_time = port::kMaxUint64;
-  for (const auto& level_files : inputs_) {
-    for (const auto& file : level_files.files) {
-      uint64_t oldest_ancester_time = file->TryGetOldestAncesterTime();
-      if (oldest_ancester_time != 0) {
-        min_oldest_ancester_time =
-            std::min(min_oldest_ancester_time, oldest_ancester_time);
-      }
+uint64_t Compaction::MaxInputFileCreationTime() const {
+  uint64_t max_creation_time = 0;
+  for (const auto& file : inputs_[0].files) {
+    if (file->fd.table_reader != nullptr &&
+        file->fd.table_reader->GetTableProperties() != nullptr) {
+      uint64_t creation_time =
+          file->fd.table_reader->GetTableProperties()->creation_time;
+      max_creation_time = std::max(max_creation_time, creation_time);
     }
   }
-  return min_oldest_ancester_time;
+  return max_creation_time;
 }
 
 int Compaction::GetInputBaseLevel() const {
   return input_vstorage_->base_level();
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction/compaction.h

@@ -13,7 +13,7 @@
 #include "options/cf_options.h"
 #include "util/autovector.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 // The file contains class Compaction, as well as some helper functions
 // and data structures used by the class.
 
@@ -291,7 +291,7 @@ class Compaction {
 
   uint32_t max_subcompactions() const { return max_subcompactions_; }
 
-  uint64_t MinInputFileOldestAncesterTime() const;
+  uint64_t MaxInputFileCreationTime() const;
 
  private:
   // mark (or clear) all files that are being compacted
@@ -381,4 +381,4 @@ class Compaction {
 // Return sum of sizes of all files in `files`.
 extern uint64_t TotalFileSize(const std::vector<FileMetaData*>& files);
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction/compaction_iteration_stats.h

@@ -5,8 +5,6 @@
 
 #pragma once
 
-#include "rocksdb/rocksdb_namespace.h"
-
 struct CompactionIterationStats {
   // Compaction statistics
 

db/compaction/compaction_iterator.cc

@@ -3,8 +3,6 @@
 //  COPYING file in the root directory) and Apache 2.0 License
 //  (found in the LICENSE.Apache file in the root directory).
 
-#include <cinttypes>
-
 #include "db/compaction/compaction_iterator.h"
 #include "db/snapshot_checker.h"
 #include "port/likely.h"
@@ -28,7 +26,7 @@
   ((seq) <= earliest_snapshot_ && \
    (snapshot_checker_ == nullptr || LIKELY(IsInEarliestSnapshot(seq))))
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
@@ -40,8 +38,7 @@ CompactionIterator::CompactionIterator(
     const CompactionFilter* compaction_filter,
     const std::atomic<bool>* shutting_down,
     const SequenceNumber preserve_deletes_seqnum,
-    const std::atomic<bool>* manual_compaction_paused,
-    const std::shared_ptr<Logger> info_log)
+    SnapshotListFetchCallback* snap_list_callback)
     : CompactionIterator(
           input, cmp, merge_helper, last_sequence, snapshots,
           earliest_write_conflict_snapshot, snapshot_checker, env,
@@ -49,7 +46,7 @@ CompactionIterator::CompactionIterator(
           std::unique_ptr<CompactionProxy>(
               compaction ? new CompactionProxy(compaction) : nullptr),
           compaction_filter, shutting_down, preserve_deletes_seqnum,
-          manual_compaction_paused, info_log) {}
+          snap_list_callback) {}
 
 CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
@@ -62,8 +59,7 @@ CompactionIterator::CompactionIterator(
     const CompactionFilter* compaction_filter,
     const std::atomic<bool>* shutting_down,
     const SequenceNumber preserve_deletes_seqnum,
-    const std::atomic<bool>* manual_compaction_paused,
-    const std::shared_ptr<Logger> info_log)
+    SnapshotListFetchCallback* snap_list_callback)
     : input_(input),
       cmp_(cmp),
       merge_helper_(merge_helper),
@@ -77,13 +73,12 @@ CompactionIterator::CompactionIterator(
       compaction_(std::move(compaction)),
       compaction_filter_(compaction_filter),
       shutting_down_(shutting_down),
-      manual_compaction_paused_(manual_compaction_paused),
       preserve_deletes_seqnum_(preserve_deletes_seqnum),
       current_user_key_sequence_(0),
       current_user_key_snapshot_(0),
       merge_out_iter_(merge_helper_),
       current_key_committed_(false),
-      info_log_(info_log) {
+      snap_list_callback_(snap_list_callback) {
   assert(compaction_filter_ == nullptr || compaction_ != nullptr);
   assert(snapshots_ != nullptr);
   bottommost_level_ =
@@ -91,24 +86,7 @@ CompactionIterator::CompactionIterator(
   if (compaction_ != nullptr) {
     level_ptrs_ = std::vector<size_t>(compaction_->number_levels(), 0);
   }
-  if (snapshots_->size() == 0) {
-    // optimize for fast path if there are no snapshots
-    visible_at_tip_ = true;
-    earliest_snapshot_iter_ = snapshots_->end();
-    earliest_snapshot_ = kMaxSequenceNumber;
-    latest_snapshot_ = 0;
-  } else {
-    visible_at_tip_ = false;
-    earliest_snapshot_iter_ = snapshots_->begin();
-    earliest_snapshot_ = snapshots_->at(0);
-    latest_snapshot_ = snapshots_->back();
-  }
-#ifndef NDEBUG
-  // findEarliestVisibleSnapshot assumes this ordering.
-  for (size_t i = 1; i < snapshots_->size(); ++i) {
-    assert(snapshots_->at(i - 1) < snapshots_->at(i));
-  }
-#endif
+  ProcessSnapshotList();
   input_->SetPinnedItersMgr(&pinned_iters_mgr_);
   TEST_SYNC_POINT_CALLBACK("CompactionIterator:AfterInit", compaction_.get());
 }
@@ -147,11 +125,6 @@ void CompactionIterator::Next() {
       // MergeUntil stops when it encounters a corrupt key and does not
       // include them in the result, so we expect the keys here to be valid.
       assert(valid_key);
-      if (!valid_key) {
-        ROCKS_LOG_FATAL(info_log_, "Invalid key (%s) in compaction",
-                        key_.ToString(true).c_str());
-      }
-
       // Keep current_key_ in sync.
       current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
       key_ = current_key_.GetInternalKey();
@@ -235,12 +208,33 @@ void CompactionIterator::InvokeFilterIfNeeded(bool* need_skip,
   }
 }
 
+void CompactionIterator::ProcessSnapshotList() {
+#ifndef NDEBUG
+  // findEarliestVisibleSnapshot assumes this ordering.
+  for (size_t i = 1; i < snapshots_->size(); ++i) {
+    assert(snapshots_->at(i - 1) < snapshots_->at(i));
+  }
+#endif
+  if (snapshots_->size() == 0) {
+    // optimize for fast path if there are no snapshots
+    visible_at_tip_ = true;
+    earliest_snapshot_iter_ = snapshots_->end();
+    earliest_snapshot_ = kMaxSequenceNumber;
+    latest_snapshot_ = 0;
+  } else {
+    visible_at_tip_ = false;
+    earliest_snapshot_iter_ = snapshots_->begin();
+    earliest_snapshot_ = snapshots_->at(0);
+    latest_snapshot_ = snapshots_->back();
+  }
+  released_snapshots_.clear();
+}
+
 void CompactionIterator::NextFromInput() {
   at_next_ = false;
   valid_ = false;
 
-  while (!valid_ && input_->Valid() && !IsPausingManualCompaction() &&
-         !IsShuttingDown()) {
+  while (!valid_ && input_->Valid() && !IsShuttingDown()) {
     key_ = input_->key();
     value_ = input_->value();
     iter_stats_.num_input_records++;
@@ -283,6 +277,13 @@ void CompactionIterator::NextFromInput() {
     // compaction filter). ikey_.user_key is pointing to the copy.
     if (!has_current_user_key_ ||
         !cmp_->Equal(ikey_.user_key, current_user_key_)) {
+      num_keys_++;
+      // Use num_keys_ to reduce the overhead of reading current time
+      if (snap_list_callback_ && snapshots_->size() &&
+          snap_list_callback_->TimeToRefresh(num_keys_)) {
+        snap_list_callback_->Refresh(snapshots_, latest_snapshot_);
+        ProcessSnapshotList();
+      }
       // First occurrence of this user key
       // Copy key for output
       key_ = current_key_.SetInternalKey(key_, &ikey_);
@@ -348,18 +349,7 @@ void CompactionIterator::NextFromInput() {
       // not compact out.  We will keep this Put, but can drop it's data.
       // (See Optimization 3, below.)
       assert(ikey_.type == kTypeValue);
-      if (ikey_.type != kTypeValue) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "Unexpected key type %d for compaction output",
-                        ikey_.type);
-      }
       assert(current_user_key_snapshot_ == last_snapshot);
-      if (current_user_key_snapshot_ != last_snapshot) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "current_user_key_snapshot_ (%" PRIu64
-                        ") != last_snapshot (%" PRIu64 ")",
-                        current_user_key_snapshot_, last_snapshot);
-      }
 
       value_.clear();
       valid_ = true;
@@ -501,12 +491,6 @@ void CompactionIterator::NextFromInput() {
       // checking since there has already been a record returned for this key
       // in this snapshot.
       assert(last_sequence >= current_user_key_sequence_);
-      if (last_sequence < current_user_key_sequence_) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "last_sequence (%" PRIu64
-                        ") < current_user_key_sequence_ (%" PRIu64 ")",
-                        last_sequence, current_user_key_sequence_);
-      }
 
       ++iter_stats_.num_record_drop_hidden;  // (A)
       input_->Next();
@@ -590,10 +574,6 @@ void CompactionIterator::NextFromInput() {
         // MergeUntil stops when it encounters a corrupt key and does not
         // include them in the result, so we expect the keys here to valid.
         assert(valid_key);
-        if (!valid_key) {
-          ROCKS_LOG_FATAL(info_log_, "Invalid key (%s) in compaction",
-                          key_.ToString(true).c_str());
-        }
         // Keep current_key_ in sync.
         current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
         key_ = current_key_.GetInternalKey();
@@ -632,65 +612,32 @@ void CompactionIterator::NextFromInput() {
   if (!valid_ && IsShuttingDown()) {
     status_ = Status::ShutdownInProgress();
   }
-
-  if (IsPausingManualCompaction()) {
-    status_ = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
-  }
 }
 
 void CompactionIterator::PrepareOutput() {
-  if (valid_) {
-    if (compaction_filter_ && ikey_.type == kTypeBlobIndex) {
-      const auto blob_decision = compaction_filter_->PrepareBlobOutput(
-          user_key(), value_, &compaction_filter_value_);
-
-      if (blob_decision == CompactionFilter::BlobDecision::kCorruption) {
-        status_ = Status::Corruption(
-            "Corrupted blob reference encountered during GC");
-        valid_ = false;
-      } else if (blob_decision == CompactionFilter::BlobDecision::kIOError) {
-        status_ = Status::IOError("Could not relocate blob during GC");
-        valid_ = false;
-      } else if (blob_decision ==
-                 CompactionFilter::BlobDecision::kChangeValue) {
-        value_ = compaction_filter_value_;
-      }
-    }
-
-    // Zeroing out the sequence number leads to better compression.
-    // If this is the bottommost level (no files in lower levels)
-    // and the earliest snapshot is larger than this seqno
-    // and the userkey differs from the last userkey in compaction
-    // then we can squash the seqno to zero.
-    //
-    // This is safe for TransactionDB write-conflict checking since transactions
-    // only care about sequence number larger than any active snapshots.
-    //
-    // Can we do the same for levels above bottom level as long as
-    // KeyNotExistsBeyondOutputLevel() return true?
-    if (valid_ && compaction_ != nullptr &&
-        !compaction_->allow_ingest_behind() &&
-        ikeyNotNeededForIncrementalSnapshot() && bottommost_level_ &&
-        IN_EARLIEST_SNAPSHOT(ikey_.sequence) && ikey_.type != kTypeMerge) {
-      assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
-      if (ikey_.type == kTypeDeletion || ikey_.type == kTypeSingleDeletion) {
-        ROCKS_LOG_FATAL(info_log_,
-                        "Unexpected key type %d for seq-zero optimization",
-                        ikey_.type);
-      }
-      ikey_.sequence = 0;
-      current_key_.UpdateInternalKey(0, ikey_.type);
-    }
+  // Zeroing out the sequence number leads to better compression.
+  // If this is the bottommost level (no files in lower levels)
+  // and the earliest snapshot is larger than this seqno
+  // and the userkey differs from the last userkey in compaction
+  // then we can squash the seqno to zero.
+  //
+  // This is safe for TransactionDB write-conflict checking since transactions
+  // only care about sequence number larger than any active snapshots.
+  //
+  // Can we do the same for levels above bottom level as long as
+  // KeyNotExistsBeyondOutputLevel() return true?
+  if ((compaction_ != nullptr && !compaction_->allow_ingest_behind()) &&
+      ikeyNotNeededForIncrementalSnapshot() && bottommost_level_ && valid_ &&
+      IN_EARLIEST_SNAPSHOT(ikey_.sequence) && ikey_.type != kTypeMerge) {
+    assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
+    ikey_.sequence = 0;
+    current_key_.UpdateInternalKey(0, ikey_.type);
   }
 }
 
 inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
     SequenceNumber in, SequenceNumber* prev_snapshot) {
   assert(snapshots_->size());
-  if (snapshots_->size() == 0) {
-    ROCKS_LOG_FATAL(info_log_,
-                    "No snapshot left in findEarliestVisibleSnapshot");
-  }
   auto snapshots_iter = std::lower_bound(
       snapshots_->begin(), snapshots_->end(), in);
   if (snapshots_iter == snapshots_->begin()) {
@@ -698,10 +645,6 @@ inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
   } else {
     *prev_snapshot = *std::prev(snapshots_iter);
     assert(*prev_snapshot < in);
-    if (*prev_snapshot >= in) {
-      ROCKS_LOG_FATAL(info_log_,
-                      "*prev_snapshot >= in in findEarliestVisibleSnapshot");
-    }
   }
   if (snapshot_checker_ == nullptr) {
     return snapshots_iter != snapshots_->end()
@@ -711,9 +654,6 @@ inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
   for (; snapshots_iter != snapshots_->end(); ++snapshots_iter) {
     auto cur = *snapshots_iter;
     assert(in <= cur);
-    if (in > cur) {
-      ROCKS_LOG_FATAL(info_log_, "in > cur in findEarliestVisibleSnapshot");
-    }
     // Skip if cur is in released_snapshots.
     if (has_released_snapshot && released_snapshots_.count(cur) > 0) {
       continue;
@@ -738,14 +678,9 @@ inline bool CompactionIterator::ikeyNotNeededForIncrementalSnapshot() {
 
 bool CompactionIterator::IsInEarliestSnapshot(SequenceNumber sequence) {
   assert(snapshot_checker_ != nullptr);
-  bool pre_condition = (earliest_snapshot_ == kMaxSequenceNumber ||
-                        (earliest_snapshot_iter_ != snapshots_->end() &&
-                         *earliest_snapshot_iter_ == earliest_snapshot_));
-  assert(pre_condition);
-  if (!pre_condition) {
-    ROCKS_LOG_FATAL(info_log_,
-                    "Pre-Condition is not hold in IsInEarliestSnapshot");
-  }
+  assert(earliest_snapshot_ == kMaxSequenceNumber ||
+         (earliest_snapshot_iter_ != snapshots_->end() &&
+          *earliest_snapshot_iter_ == earliest_snapshot_));
   auto in_snapshot =
       snapshot_checker_->CheckInSnapshot(sequence, earliest_snapshot_);
   while (UNLIKELY(in_snapshot == SnapshotCheckerResult::kSnapshotReleased)) {
@@ -764,11 +699,7 @@ bool CompactionIterator::IsInEarliestSnapshot(SequenceNumber sequence) {
         snapshot_checker_->CheckInSnapshot(sequence, earliest_snapshot_);
   }
   assert(in_snapshot != SnapshotCheckerResult::kSnapshotReleased);
-  if (in_snapshot == SnapshotCheckerResult::kSnapshotReleased) {
-    ROCKS_LOG_FATAL(info_log_,
-                    "Unexpected released snapshot in IsInEarliestSnapshot");
-  }
   return in_snapshot == SnapshotCheckerResult::kInSnapshot;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction/compaction_iterator.h

@@ -19,7 +19,55 @@
 #include "options/cf_options.h"
 #include "rocksdb/compaction_filter.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
+
+// This callback can be used to refresh the snapshot list from the db. It
+// includes logics to exponentially decrease the refresh rate to limit the
+// overhead of refresh.
+class SnapshotListFetchCallback {
+ public:
+  SnapshotListFetchCallback(Env* env, uint64_t snap_refresh_nanos,
+                            size_t every_nth_key = 1024)
+      : timer_(env, /*auto restart*/ true),
+        snap_refresh_nanos_(snap_refresh_nanos),
+        every_nth_key_minus_one_(every_nth_key - 1) {
+    assert(every_nth_key > 0);
+    assert((ceil(log2(every_nth_key)) == floor(log2(every_nth_key))));
+  }
+  // Refresh the snapshot list. snapshots will bre replacted with the new list.
+  // max is the upper bound. Note: this function will acquire the db_mutex_.
+  virtual void Refresh(std::vector<SequenceNumber>* snapshots,
+                       SequenceNumber max) = 0;
+  inline bool TimeToRefresh(const size_t key_index) {
+    assert(snap_refresh_nanos_ != 0);
+    // skip the key if key_index % every_nth_key (which is of power 2) is not 0.
+    if ((key_index & every_nth_key_minus_one_) != 0) {
+      return false;
+    }
+    const uint64_t elapsed = timer_.ElapsedNanos();
+    auto ret = elapsed > snap_refresh_nanos_;
+    // pre-compute the next time threshold
+    if (ret) {
+      // inc next refresh period exponentially (by x4)
+      auto next_refresh_threshold = snap_refresh_nanos_ << 2;
+      // make sure the shift has not overflown the highest 1 bit
+      snap_refresh_nanos_ =
+          std::max(snap_refresh_nanos_, next_refresh_threshold);
+    }
+    return ret;
+  }
+  static constexpr SnapshotListFetchCallback* kDisabled = nullptr;
+
+  virtual ~SnapshotListFetchCallback() {}
+
+ private:
+  // Time since the callback was created
+  StopWatchNano timer_;
+  // The delay before calling ::Refresh. To be increased exponentially.
+  uint64_t snap_refresh_nanos_;
+  // Skip evey nth key. Number n if of power 2. The math will require n-1.
+  const uint64_t every_nth_key_minus_one_;
+};
 
 class CompactionIterator {
  public:
@@ -59,34 +107,32 @@ class CompactionIterator {
     const Compaction* compaction_;
   };
 
-  CompactionIterator(
-      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
-      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-      SequenceNumber earliest_write_conflict_snapshot,
-      const SnapshotChecker* snapshot_checker, Env* env,
-      bool report_detailed_time, bool expect_valid_internal_key,
-      CompactionRangeDelAggregator* range_del_agg,
-      const Compaction* compaction = nullptr,
-      const CompactionFilter* compaction_filter = nullptr,
-      const std::atomic<bool>* shutting_down = nullptr,
-      const SequenceNumber preserve_deletes_seqnum = 0,
-      const std::atomic<bool>* manual_compaction_paused = nullptr,
-      const std::shared_ptr<Logger> info_log = nullptr);
+  CompactionIterator(InternalIterator* input, const Comparator* cmp,
+                     MergeHelper* merge_helper, SequenceNumber last_sequence,
+                     std::vector<SequenceNumber>* snapshots,
+                     SequenceNumber earliest_write_conflict_snapshot,
+                     const SnapshotChecker* snapshot_checker, Env* env,
+                     bool report_detailed_time, bool expect_valid_internal_key,
+                     CompactionRangeDelAggregator* range_del_agg,
+                     const Compaction* compaction = nullptr,
+                     const CompactionFilter* compaction_filter = nullptr,
+                     const std::atomic<bool>* shutting_down = nullptr,
+                     const SequenceNumber preserve_deletes_seqnum = 0,
+                     SnapshotListFetchCallback* snap_list_callback = nullptr);
 
   // Constructor with custom CompactionProxy, used for tests.
-  CompactionIterator(
-      InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
-      SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-      SequenceNumber earliest_write_conflict_snapshot,
-      const SnapshotChecker* snapshot_checker, Env* env,
-      bool report_detailed_time, bool expect_valid_internal_key,
-      CompactionRangeDelAggregator* range_del_agg,
-      std::unique_ptr<CompactionProxy> compaction,
-      const CompactionFilter* compaction_filter = nullptr,
-      const std::atomic<bool>* shutting_down = nullptr,
-      const SequenceNumber preserve_deletes_seqnum = 0,
-      const std::atomic<bool>* manual_compaction_paused = nullptr,
-      const std::shared_ptr<Logger> info_log = nullptr);
+  CompactionIterator(InternalIterator* input, const Comparator* cmp,
+                     MergeHelper* merge_helper, SequenceNumber last_sequence,
+                     std::vector<SequenceNumber>* snapshots,
+                     SequenceNumber earliest_write_conflict_snapshot,
+                     const SnapshotChecker* snapshot_checker, Env* env,
+                     bool report_detailed_time, bool expect_valid_internal_key,
+                     CompactionRangeDelAggregator* range_del_agg,
+                     std::unique_ptr<CompactionProxy> compaction,
+                     const CompactionFilter* compaction_filter = nullptr,
+                     const std::atomic<bool>* shutting_down = nullptr,
+                     const SequenceNumber preserve_deletes_seqnum = 0,
+                     SnapshotListFetchCallback* snap_list_callback = nullptr);
 
   ~CompactionIterator();
 
@@ -114,6 +160,8 @@ class CompactionIterator {
  private:
   // Processes the input stream to find the next output
   void NextFromInput();
+  // Process snapshots_ and assign related variables
+  void ProcessSnapshotList();
 
   // Do last preparations before presenting the output to the callee. At this
   // point this only zeroes out the sequence number if possible for better
@@ -148,7 +196,7 @@ class CompactionIterator {
   InternalIterator* input_;
   const Comparator* cmp_;
   MergeHelper* merge_helper_;
-  const std::vector<SequenceNumber>* snapshots_;
+  std::vector<SequenceNumber>* snapshots_;
   // List of snapshots released during compaction.
   // findEarliestVisibleSnapshot() find them out from return of
   // snapshot_checker, and make sure they will not be returned as
@@ -165,7 +213,6 @@ class CompactionIterator {
   std::unique_ptr<CompactionProxy> compaction_;
   const CompactionFilter* compaction_filter_;
   const std::atomic<bool>* shutting_down_;
-  const std::atomic<bool>* manual_compaction_paused_;
   const SequenceNumber preserve_deletes_seqnum_;
   bool bottommost_level_;
   bool valid_ = false;
@@ -224,17 +271,13 @@ class CompactionIterator {
   // Used to avoid purging uncommitted values. The application can specify
   // uncommitted values by providing a SnapshotChecker object.
   bool current_key_committed_;
-  std::shared_ptr<Logger> info_log_;
+  SnapshotListFetchCallback* snap_list_callback_;
+  // number of distinct keys processed
+  size_t num_keys_ = 0;
 
   bool IsShuttingDown() {
     // This is a best-effort facility, so memory_order_relaxed is sufficient.
     return shutting_down_ && shutting_down_->load(std::memory_order_relaxed);
   }
-
-  bool IsPausingManualCompaction() {
-    // This is a best-effort facility, so memory_order_relaxed is sufficient.
-    return manual_compaction_paused_ &&
-           manual_compaction_paused_->load(std::memory_order_relaxed);
-  }
 };
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction/compaction_iterator_test.cc

@@ -14,7 +14,7 @@
 #include "util/string_util.h"
 #include "utilities/merge_operators.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 // Expects no merging attempts.
 class NoMergingMergeOp : public MergeOperator {
@@ -184,7 +184,7 @@ class TestSnapshotChecker : public SnapshotChecker {
  public:
   explicit TestSnapshotChecker(
       SequenceNumber last_committed_sequence,
-      const std::unordered_map<SequenceNumber, SequenceNumber>& snapshots = {{}})
+      const std::unordered_map<SequenceNumber, SequenceNumber>& snapshots = {})
       : last_committed_sequence_(last_committed_sequence),
         snapshots_(snapshots) {}
 
@@ -494,7 +494,7 @@ TEST_P(CompactionIteratorTest, ShuttingDownInFilter) {
   compaction_proxy_->key_not_exists_beyond_output_level = true;
 
   std::atomic<bool> seek_done{false};
-  ROCKSDB_NAMESPACE::port::Thread compaction_thread([&] {
+  rocksdb::port::Thread compaction_thread([&] {
     c_iter_->SeekToFirst();
     EXPECT_FALSE(c_iter_->Valid());
     EXPECT_TRUE(c_iter_->status().IsShutdownInProgress());
@@ -531,7 +531,7 @@ TEST_P(CompactionIteratorTest, ShuttingDownInMerge) {
   compaction_proxy_->key_not_exists_beyond_output_level = true;
 
   std::atomic<bool> seek_done{false};
-  ROCKSDB_NAMESPACE::port::Thread compaction_thread([&] {
+  rocksdb::port::Thread compaction_thread([&] {
     c_iter_->SeekToFirst();
     ASSERT_FALSE(c_iter_->Valid());
     ASSERT_TRUE(c_iter_->status().IsShutdownInProgress());
@@ -968,7 +968,7 @@ TEST_F(CompactionIteratorWithSnapshotCheckerTest, CompactionFilter_FullMerge) {
       compaction_filter.get());
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

db/compaction/compaction_job.cc

@@ -7,8 +7,8 @@
 // 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 <algorithm>
 #include <cinttypes>
+#include <algorithm>
 #include <functional>
 #include <list>
 #include <memory>
@@ -34,9 +34,7 @@
 #include "db/range_del_aggregator.h"
 #include "db/version_set.h"
 #include "file/filename.h"
-#include "file/read_write_util.h"
 #include "file/sst_file_manager_impl.h"
-#include "file/writable_file_writer.h"
 #include "logging/log_buffer.h"
 #include "logging/logging.h"
 #include "monitoring/iostats_context_imp.h"
@@ -54,12 +52,13 @@
 #include "table/table_builder.h"
 #include "test_util/sync_point.h"
 #include "util/coding.h"
+#include "util/file_reader_writer.h"
 #include "util/mutexlock.h"
 #include "util/random.h"
 #include "util/stop_watch.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 const char* GetCompactionReasonString(CompactionReason compaction_reason) {
   switch (compaction_reason) {
@@ -144,6 +143,7 @@ struct CompactionJob::SubcompactionState {
 
   // State during the subcompaction
   uint64_t total_bytes;
+  uint64_t num_input_records;
   uint64_t num_output_records;
   CompactionJobStats compaction_job_stats;
   uint64_t approx_size;
@@ -164,6 +164,7 @@ struct CompactionJob::SubcompactionState {
         builder(nullptr),
         current_output_file_size(0),
         total_bytes(0),
+        num_input_records(0),
         num_output_records(0),
         approx_size(size),
         grandparent_index(0),
@@ -184,6 +185,7 @@ struct CompactionJob::SubcompactionState {
     builder = std::move(o.builder);
     current_output_file_size = std::move(o.current_output_file_size);
     total_bytes = std::move(o.total_bytes);
+    num_input_records = std::move(o.num_input_records);
     num_output_records = std::move(o.num_output_records);
     compaction_job_stats = std::move(o.compaction_job_stats);
     approx_size = std::move(o.approx_size);
@@ -242,11 +244,13 @@ struct CompactionJob::CompactionState {
   Status status;
 
   uint64_t total_bytes;
+  uint64_t num_input_records;
   uint64_t num_output_records;
 
   explicit CompactionState(Compaction* c)
       : compaction(c),
         total_bytes(0),
+        num_input_records(0),
         num_output_records(0) {}
 
   size_t NumOutputFiles() {
@@ -284,6 +288,7 @@ struct CompactionJob::CompactionState {
 void CompactionJob::AggregateStatistics() {
   for (SubcompactionState& sc : compact_->sub_compact_states) {
     compact_->total_bytes += sc.total_bytes;
+    compact_->num_input_records += sc.num_input_records;
     compact_->num_output_records += sc.num_output_records;
   }
   if (compaction_job_stats_) {
@@ -295,31 +300,29 @@ void CompactionJob::AggregateStatistics() {
 
 CompactionJob::CompactionJob(
     int job_id, Compaction* compaction, const ImmutableDBOptions& db_options,
-    const FileOptions& file_options, VersionSet* versions,
+    const EnvOptions env_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,
     const SnapshotChecker* snapshot_checker, std::shared_ptr<Cache> table_cache,
     EventLogger* event_logger, bool paranoid_file_checks, bool measure_io_stats,
     const std::string& dbname, CompactionJobStats* compaction_job_stats,
-    Env::Priority thread_pri, const std::atomic<bool>* manual_compaction_paused)
+    Env::Priority thread_pri, SnapshotListFetchCallback* snap_list_callback)
     : job_id_(job_id),
       compact_(new CompactionState(compaction)),
       compaction_job_stats_(compaction_job_stats),
       compaction_stats_(compaction->compaction_reason(), 1),
       dbname_(dbname),
       db_options_(db_options),
-      file_options_(file_options),
+      env_options_(env_options),
       env_(db_options.env),
-      fs_(db_options.fs.get()),
-      file_options_for_read_(
-          fs_->OptimizeForCompactionTableRead(file_options, db_options_)),
+      env_options_for_read_(
+          env_->OptimizeForCompactionTableRead(env_options, db_options_)),
       versions_(versions),
       shutting_down_(shutting_down),
-      manual_compaction_paused_(manual_compaction_paused),
       preserve_deletes_seqnum_(preserve_deletes_seqnum),
       log_buffer_(log_buffer),
       db_directory_(db_directory),
@@ -328,6 +331,7 @@ CompactionJob::CompactionJob(
       db_mutex_(db_mutex),
       db_error_handler_(db_error_handler),
       existing_snapshots_(std::move(existing_snapshots)),
+      snap_list_callback_(snap_list_callback),
       earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
       snapshot_checker_(snapshot_checker),
       table_cache_(std::move(table_cache)),
@@ -613,13 +617,8 @@ 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()) {
@@ -647,7 +646,7 @@ Status CompactionJob::Run() {
         // we will regard this verification as user reads since the goal is
         // to cache it here for further user reads
         InternalIterator* iter = cfd->table_cache()->NewIterator(
-            ReadOptions(), file_options_, cfd->internal_comparator(),
+            ReadOptions(), env_options_, cfd->internal_comparator(),
             *files_meta[file_idx], /*range_del_agg=*/nullptr, prefix_extractor,
             /*table_reader_ptr=*/nullptr,
             cfd->internal_stats()->GetFileReadHist(
@@ -655,8 +654,7 @@ 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 +717,9 @@ 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_;
@@ -774,12 +768,12 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
   auto stream = event_logger_->LogToBuffer(log_buffer_);
   stream << "job" << job_id_ << "event"
          << "compaction_finished"
-         << "compaction_time_micros" << stats.micros
-         << "compaction_time_cpu_micros" << stats.cpu_micros << "output_level"
-         << compact_->compaction->output_level() << "num_output_files"
-         << compact_->NumOutputFiles() << "total_output_size"
-         << compact_->total_bytes << "num_input_records"
-         << stats.num_input_records << "num_output_records"
+         << "compaction_time_micros" << compaction_stats_.micros
+         << "compaction_time_cpu_micros" << compaction_stats_.cpu_micros
+         << "output_level" << compact_->compaction->output_level()
+         << "num_output_files" << compact_->NumOutputFiles()
+         << "total_output_size" << compact_->total_bytes << "num_input_records"
+         << compact_->num_input_records << "num_output_records"
          << compact_->num_output_records << "num_subcompactions"
          << compact_->sub_compact_states.size() << "output_compression"
          << CompressionTypeToString(compact_->compaction->output_compression());
@@ -841,7 +835,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   // Although the v2 aggregator is what the level iterator(s) know about,
   // the AddTombstones calls will be propagated down to the v1 aggregator.
   std::unique_ptr<InternalIterator> input(versions_->MakeInputIterator(
-      sub_compact->compaction, &range_del_agg, file_options_for_read_));
+      sub_compact->compaction, &range_del_agg, env_options_for_read_));
 
   AutoThreadOperationStageUpdater stage_updater(
       ThreadStatus::STAGE_COMPACTION_PROCESS_KV);
@@ -872,13 +866,9 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       false /* internal key corruption is expected */,
       existing_snapshots_.empty() ? 0 : existing_snapshots_.back(),
       snapshot_checker_, compact_->compaction->level(),
-      db_options_.statistics.get());
+      db_options_.statistics.get(), shutting_down_);
 
   TEST_SYNC_POINT("CompactionJob::Run():Inprogress");
-  TEST_SYNC_POINT_CALLBACK(
-      "CompactionJob::Run():PausingManualCompaction:1",
-      reinterpret_cast<void*>(
-          const_cast<std::atomic<bool>*>(manual_compaction_paused_)));
 
   Slice* start = sub_compact->start;
   Slice* end = sub_compact->end;
@@ -896,8 +886,9 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       &existing_snapshots_, earliest_write_conflict_snapshot_,
       snapshot_checker_, env_, ShouldReportDetailedTime(env_, stats_), false,
       &range_del_agg, sub_compact->compaction, compaction_filter,
-      shutting_down_, preserve_deletes_seqnum_, manual_compaction_paused_,
-      db_options_.info_log));
+      shutting_down_, preserve_deletes_seqnum_,
+      // Currently range_del_agg is incompatible with snapshot refresh feature.
+      range_del_agg.IsEmpty() ? snap_list_callback_ : nullptr));
   auto c_iter = sub_compact->c_iter.get();
   c_iter->SeekToFirst();
   if (c_iter->Valid() && sub_compact->compaction->output_level() != 0) {
@@ -938,11 +929,9 @@ 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();
-    const ParsedInternalKey& ikey = c_iter->ikey();
+    sub_compact->current_output_file_size = sub_compact->builder->FileSize();
     sub_compact->current_output()->meta.UpdateBoundaries(
-        key, value, ikey.sequence, ikey.type);
+        key, c_iter->ikey().sequence);
     sub_compact->num_output_records++;
 
     // Close output file if it is big enough. Two possibilities determine it's
@@ -963,14 +952,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       input_status = input->status();
       output_file_ended = true;
     }
-    TEST_SYNC_POINT_CALLBACK(
-        "CompactionJob::Run():PausingManualCompaction:2",
-        reinterpret_cast<void*>(
-            const_cast<std::atomic<bool>*>(manual_compaction_paused_)));
     c_iter->Next();
-    if (c_iter->status().IsManualCompactionPaused()) {
-      break;
-    }
     if (!output_file_ended && c_iter->Valid() &&
         sub_compact->compaction->output_level() != 0 &&
         sub_compact->ShouldStopBefore(c_iter->key(),
@@ -996,6 +978,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     }
   }
 
+  sub_compact->num_input_records = c_iter_stats.num_input_records;
   sub_compact->compaction_job_stats.num_input_deletion_records =
       c_iter_stats.num_input_deletion_records;
   sub_compact->compaction_job_stats.num_corrupt_keys =
@@ -1022,11 +1005,6 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       shutting_down_->load(std::memory_order_relaxed)) {
     status = Status::ShutdownInProgress("Database shutdown");
   }
-  if ((status.ok() || status.IsColumnFamilyDropped()) &&
-      (manual_compaction_paused_ &&
-       manual_compaction_paused_->load(std::memory_order_relaxed))) {
-    status = Status::Incomplete(Status::SubCode::kManualCompactionPaused);
-  }
   if (status.ok()) {
     status = input->status();
   }
@@ -1305,10 +1283,6 @@ 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()) {
     meta->fd.file_size = current_bytes;
@@ -1317,23 +1291,12 @@ Status CompactionJob::FinishCompactionOutputFile(
   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();
 
@@ -1371,20 +1334,17 @@ Status CompactionJob::FinishCompactionOutputFile(
   }
   std::string fname;
   FileDescriptor output_fd;
-  uint64_t oldest_blob_file_number = kInvalidBlobFileNumber;
   if (meta != nullptr) {
     fname =
         TableFileName(sub_compact->compaction->immutable_cf_options()->cf_paths,
                       meta->fd.GetNumber(), meta->fd.GetPathId());
     output_fd = meta->fd;
-    oldest_blob_file_number = meta->oldest_blob_file_number;
   } else {
     fname = "(nil)";
   }
   EventHelpers::LogAndNotifyTableFileCreationFinished(
       event_logger_, cfd->ioptions()->listeners, dbname_, cfd->GetName(), fname,
-      job_id_, output_fd, oldest_blob_file_number, tp,
-      TableFileCreationReason::kCompaction, s);
+      job_id_, output_fd, tp, TableFileCreationReason::kCompaction, s);
 
 #ifndef ROCKSDB_LITE
   // Report new file to SstFileManagerImpl
@@ -1477,13 +1437,13 @@ Status CompactionJob::OpenCompactionOutputFile(
       TableFileCreationReason::kCompaction);
 #endif  // !ROCKSDB_LITE
   // Make the output file
-  std::unique_ptr<FSWritableFile> writable_file;
+  std::unique_ptr<WritableFile> writable_file;
 #ifndef NDEBUG
-  bool syncpoint_arg = file_options_.use_direct_writes;
+  bool syncpoint_arg = env_options_.use_direct_writes;
   TEST_SYNC_POINT_CALLBACK("CompactionJob::OpenCompactionOutputFile",
                            &syncpoint_arg);
 #endif
-  Status s = NewWritableFile(fs_, fname, &writable_file, file_options_);
+  Status s = NewWritableFile(env_, fname, &writable_file, env_options_);
   if (!s.ok()) {
     ROCKS_LOG_ERROR(
         db_options_.info_log,
@@ -1494,12 +1454,33 @@ Status CompactionJob::OpenCompactionOutputFile(
     LogFlush(db_options_.info_log);
     EventHelpers::LogAndNotifyTableFileCreationFinished(
         event_logger_, cfd->ioptions()->listeners, dbname_, cfd->GetName(),
-        fname, job_id_, FileDescriptor(), kInvalidBlobFileNumber,
-        TableProperties(), TableFileCreationReason::kCompaction, s);
+        fname, job_id_, FileDescriptor(), TableProperties(),
+        TableFileCreationReason::kCompaction, s);
     return s;
   }
 
-  // Try to figure out the output file's oldest ancester time.
+  SubcompactionState::Output out;
+  out.meta.fd =
+      FileDescriptor(file_number, sub_compact->compaction->output_path_id(), 0);
+  out.finished = false;
+
+  sub_compact->outputs.push_back(out);
+  writable_file->SetIOPriority(Env::IO_LOW);
+  writable_file->SetWriteLifeTimeHint(write_hint_);
+  writable_file->SetPreallocationBlockSize(static_cast<size_t>(
+      sub_compact->compaction->OutputFilePreallocationSize()));
+  const auto& listeners =
+      sub_compact->compaction->immutable_cf_options()->listeners;
+  sub_compact->outfile.reset(
+      new WritableFileWriter(std::move(writable_file), fname, env_options_,
+                             env_, db_options_.statistics.get(), listeners));
+
+  // If the Column family flag is to only optimize filters for hits,
+  // we can skip creating filters if this is the bottommost_level where
+  // data is going to be found
+  bool skip_filters =
+      cfd->ioptions()->optimize_filters_for_hits && bottommost_level_;
+
   int64_t temp_current_time = 0;
   auto get_time_status = env_->GetCurrentTime(&temp_current_time);
   // Safe to proceed even if GetCurrentTime fails. So, log and proceed.
@@ -1509,40 +1490,13 @@ Status CompactionJob::OpenCompactionOutputFile(
                    get_time_status.ToString().c_str());
   }
   uint64_t current_time = static_cast<uint64_t>(temp_current_time);
-  uint64_t oldest_ancester_time =
-      sub_compact->compaction->MinInputFileOldestAncesterTime();
-  if (oldest_ancester_time == port::kMaxUint64) {
-    oldest_ancester_time = current_time;
+
+  uint64_t latest_key_time =
+      sub_compact->compaction->MaxInputFileCreationTime();
+  if (latest_key_time == 0) {
+    latest_key_time = current_time;
   }
 
-  // Initialize a SubcompactionState::Output and add it to sub_compact->outputs
-  {
-    SubcompactionState::Output out;
-    out.meta.fd = FileDescriptor(file_number,
-                                 sub_compact->compaction->output_path_id(), 0);
-    out.meta.oldest_ancester_time = oldest_ancester_time;
-    out.meta.file_creation_time = current_time;
-    out.finished = false;
-    sub_compact->outputs.push_back(out);
-  }
-
-  writable_file->SetIOPriority(Env::IOPriority::IO_LOW);
-  writable_file->SetWriteLifeTimeHint(write_hint_);
-  writable_file->SetPreallocationBlockSize(static_cast<size_t>(
-      sub_compact->compaction->OutputFilePreallocationSize()));
-  const auto& listeners =
-      sub_compact->compaction->immutable_cf_options()->listeners;
-  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()));
-
-  // If the Column family flag is to only optimize filters for hits,
-  // we can skip creating filters if this is the bottommost_level where
-  // data is going to be found
-  bool skip_filters =
-      cfd->ioptions()->optimize_filters_for_hits && bottommost_level_;
-
   sub_compact->builder.reset(NewTableBuilder(
       *cfd->ioptions(), *(sub_compact->compaction->mutable_cf_options()),
       cfd->internal_comparator(), cfd->int_tbl_prop_collector_factories(),
@@ -1550,9 +1504,9 @@ Status CompactionJob::OpenCompactionOutputFile(
       sub_compact->compaction->output_compression(),
       0 /*sample_for_compression */,
       sub_compact->compaction->output_compression_opts(),
-      sub_compact->compaction->output_level(), skip_filters,
-      oldest_ancester_time, 0 /* oldest_key_time */,
-      sub_compact->compaction->max_output_file_size(), current_time));
+      sub_compact->compaction->output_level(), skip_filters, latest_key_time,
+      0 /* oldest_key_time */, sub_compact->compaction->max_output_file_size(),
+      current_time));
   LogFlush(db_options_.info_log);
   return s;
 }
@@ -1609,8 +1563,6 @@ void CompactionJob::UpdateCompactionStats() {
     }
   }
 
-  uint64_t num_output_records = 0;
-
   for (const auto& sub_compact : compact_->sub_compact_states) {
     size_t num_output_files = sub_compact.outputs.size();
     if (sub_compact.builder != nullptr) {
@@ -1620,16 +1572,13 @@ void CompactionJob::UpdateCompactionStats() {
     }
     compaction_stats_.num_output_files += static_cast<int>(num_output_files);
 
-    num_output_records += sub_compact.num_output_records;
-
     for (const auto& out : sub_compact.outputs) {
       compaction_stats_.bytes_written += out.meta.fd.file_size;
     }
-  }
-
-  if (compaction_stats_.num_input_records > num_output_records) {
-    compaction_stats_.num_dropped_records =
-        compaction_stats_.num_input_records - num_output_records;
+    if (sub_compact.num_input_records > sub_compact.num_output_records) {
+      compaction_stats_.num_dropped_records +=
+          sub_compact.num_input_records - sub_compact.num_output_records;
+    }
   }
 }
 
@@ -1657,7 +1606,7 @@ void CompactionJob::UpdateCompactionJobStats(
     // input information
     compaction_job_stats_->total_input_bytes =
         stats.bytes_read_non_output_levels + stats.bytes_read_output_level;
-    compaction_job_stats_->num_input_records = stats.num_input_records;
+    compaction_job_stats_->num_input_records = compact_->num_input_records;
     compaction_job_stats_->num_input_files =
         stats.num_input_files_in_non_output_levels +
         stats.num_input_files_in_output_level;
@@ -1718,4 +1667,4 @@ void CompactionJob::LogCompaction() {
   }
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction/compaction_job.h

@@ -44,7 +44,7 @@
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class Arena;
 class ErrorHandler;
@@ -62,23 +62,20 @@ class VersionSet;
 // if needed.
 class CompactionJob {
  public:
-  CompactionJob(int job_id, Compaction* compaction,
-                const ImmutableDBOptions& db_options,
-                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,
-                InstrumentedMutex* db_mutex, ErrorHandler* db_error_handler,
-                std::vector<SequenceNumber> existing_snapshots,
-                SequenceNumber earliest_write_conflict_snapshot,
-                const SnapshotChecker* snapshot_checker,
-                std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
-                bool paranoid_file_checks, bool measure_io_stats,
-                const std::string& dbname,
-                CompactionJobStats* compaction_job_stats,
-                Env::Priority thread_pri,
-                const std::atomic<bool>* manual_compaction_paused = nullptr);
+  CompactionJob(
+      int job_id, Compaction* compaction, const ImmutableDBOptions& db_options,
+      const EnvOptions env_options, VersionSet* versions,
+      const std::atomic<bool>* shutting_down,
+      const SequenceNumber preserve_deletes_seqnum, 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,
+      const SnapshotChecker* snapshot_checker,
+      std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
+      bool paranoid_file_checks, bool measure_io_stats,
+      const std::string& dbname, CompactionJobStats* compaction_job_stats,
+      Env::Priority thread_pri, SnapshotListFetchCallback* snap_list_callback);
 
   ~CompactionJob();
 
@@ -100,9 +97,6 @@ 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;
 
@@ -153,19 +147,17 @@ class CompactionJob {
   // DBImpl state
   const std::string& dbname_;
   const ImmutableDBOptions& db_options_;
-  const FileOptions file_options_;
+  const EnvOptions env_options_;
 
   Env* env_;
-  FileSystem* fs_;
   // env_option optimized for compaction table reads
-  FileOptions file_options_for_read_;
+  EnvOptions env_options_for_read_;
   VersionSet* versions_;
   const std::atomic<bool>* shutting_down_;
-  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_;
@@ -174,6 +166,7 @@ class CompactionJob {
   // entirely within s1 and s2, then the earlier version of k1 can be safely
   // deleted because that version is not visible in any snapshot.
   std::vector<SequenceNumber> existing_snapshots_;
+  SnapshotListFetchCallback* snap_list_callback_;
 
   // This is the earliest snapshot that could be used for write-conflict
   // checking by a transaction.  For any user-key newer than this snapshot, we
@@ -196,7 +189,6 @@ class CompactionJob {
   std::vector<uint64_t> sizes_;
   Env::WriteLifeTimeHint write_hint_;
   Env::Priority thread_pri_;
-  IOStatus io_status_;
 };
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction/compaction_job_stats_test.cc

@@ -7,8 +7,8 @@
 // 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 <algorithm>
 #include <cinttypes>
+#include <algorithm>
 #include <iostream>
 #include <mutex>
 #include <queue>
@@ -61,7 +61,7 @@
 
 #if !defined(IOS_CROSS_COMPILE)
 #ifndef ROCKSDB_LITE
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 static std::string RandomString(Random* rnd, int len, double ratio) {
   std::string r;
@@ -110,9 +110,9 @@ class CompactionJobStatsTest : public testing::Test,
   }
 
   ~CompactionJobStatsTest() override {
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({});
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+    rocksdb::SyncPoint::GetInstance()->LoadDependency({});
+    rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
     Close();
     Options options;
     options.db_paths.emplace_back(dbname_, 0);
@@ -801,7 +801,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
 
     stats_checker->set_verify_next_comp_io_stats(true);
     std::atomic<bool> first_prepare_write(true);
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+    rocksdb::SyncPoint::GetInstance()->SetCallBack(
         "WritableFileWriter::Append:BeforePrepareWrite", [&](void* /*arg*/) {
           if (first_prepare_write.load()) {
             options.env->SleepForMicroseconds(3);
@@ -810,7 +810,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
         });
 
     std::atomic<bool> first_flush(true);
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+    rocksdb::SyncPoint::GetInstance()->SetCallBack(
         "WritableFileWriter::Flush:BeforeAppend", [&](void* /*arg*/) {
           if (first_flush.load()) {
             options.env->SleepForMicroseconds(3);
@@ -819,7 +819,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
         });
 
     std::atomic<bool> first_sync(true);
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+    rocksdb::SyncPoint::GetInstance()->SetCallBack(
         "WritableFileWriter::SyncInternal:0", [&](void* /*arg*/) {
           if (first_sync.load()) {
             options.env->SleepForMicroseconds(3);
@@ -828,14 +828,14 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
         });
 
     std::atomic<bool> first_range_sync(true);
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+    rocksdb::SyncPoint::GetInstance()->SetCallBack(
         "WritableFileWriter::RangeSync:0", [&](void* /*arg*/) {
           if (first_range_sync.load()) {
             options.env->SleepForMicroseconds(3);
             first_range_sync.store(false);
           }
         });
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+    rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
     Compact(1, smallest_key, largest_key);
 
@@ -844,7 +844,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
     ASSERT_TRUE(!first_flush.load());
     ASSERT_TRUE(!first_sync.load());
     ASSERT_TRUE(!first_range_sync.load());
-    ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+    rocksdb::SyncPoint::GetInstance()->DisableProcessing();
   }
   ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 0U);
 }
@@ -1019,10 +1019,10 @@ TEST_P(CompactionJobStatsTest, UniversalCompactionTest) {
 
 INSTANTIATE_TEST_CASE_P(CompactionJobStatsTest, CompactionJobStatsTest,
                         ::testing::Values(1, 4));
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  rocksdb::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }

db/compaction/compaction_job_test.cc

@@ -5,20 +5,18 @@
 
 #ifndef ROCKSDB_LITE
 
+#include <cinttypes>
 #include <algorithm>
 #include <array>
-#include <cinttypes>
 #include <map>
 #include <string>
 #include <tuple>
 
-#include "db/blob/blob_index.h"
 #include "db/column_family.h"
 #include "db/compaction/compaction_job.h"
 #include "db/db_impl/db_impl.h"
 #include "db/error_handler.h"
 #include "db/version_set.h"
-#include "file/writable_file_writer.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/db.h"
 #include "rocksdb/options.h"
@@ -26,10 +24,11 @@
 #include "table/mock_table.h"
 #include "test_util/testharness.h"
 #include "test_util/testutil.h"
+#include "util/file_reader_writer.h"
 #include "util/string_util.h"
 #include "utilities/merge_operators.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 namespace {
 
@@ -72,7 +71,6 @@ class CompactionJobTest : public testing::Test {
  public:
   CompactionJobTest()
       : env_(Env::Default()),
-        fs_(std::make_shared<LegacyFileSystemWrapper>(env_)),
         dbname_(test::PerThreadDBPath("compaction_job_test")),
         db_options_(),
         mutable_cf_options_(cf_options_),
@@ -87,8 +85,6 @@ class CompactionJobTest : public testing::Test {
         mock_table_factory_(new mock::MockTableFactory()),
         error_handler_(nullptr, db_options_, &mutex_) {
     EXPECT_OK(env_->CreateDirIfMissing(dbname_));
-    db_options_.env = env_;
-    db_options_.fs = fs_;
     db_options_.db_paths.emplace_back(dbname_,
                                       std::numeric_limits<uint64_t>::max());
   }
@@ -101,34 +97,11 @@ class CompactionJobTest : public testing::Test {
     return TableFileName(db_paths, meta.fd.GetNumber(), meta.fd.GetPathId());
   }
 
-  static std::string KeyStr(const std::string& user_key,
-                            const SequenceNumber seq_num, const ValueType t) {
+  std::string KeyStr(const std::string& user_key, const SequenceNumber seq_num,
+      const ValueType t) {
     return InternalKey(user_key, seq_num, t).Encode().ToString();
   }
 
-  static std::string BlobStr(uint64_t blob_file_number, uint64_t offset,
-                             uint64_t size) {
-    std::string blob_index;
-    BlobIndex::EncodeBlob(&blob_index, blob_file_number, offset, size,
-                          kNoCompression);
-    return blob_index;
-  }
-
-  static std::string BlobStrTTL(uint64_t blob_file_number, uint64_t offset,
-                                uint64_t size, uint64_t expiration) {
-    std::string blob_index;
-    BlobIndex::EncodeBlobTTL(&blob_index, expiration, blob_file_number, offset,
-                             size, kNoCompression);
-    return blob_index;
-  }
-
-  static std::string BlobStrInlinedTTL(const Slice& value,
-                                       uint64_t expiration) {
-    std::string blob_index;
-    BlobIndex::EncodeInlinedTTL(&blob_index, expiration, value);
-    return blob_index;
-  }
-
   void AddMockFile(const stl_wrappers::KVMap& contents, int level = 0) {
     assert(contents.size() > 0);
 
@@ -137,13 +110,12 @@ class CompactionJobTest : public testing::Test {
     InternalKey smallest_key, largest_key;
     SequenceNumber smallest_seqno = kMaxSequenceNumber;
     SequenceNumber largest_seqno = 0;
-    uint64_t oldest_blob_file_number = kInvalidBlobFileNumber;
     for (auto kv : contents) {
       ParsedInternalKey key;
       std::string skey;
       std::string value;
       std::tie(skey, value) = kv;
-      bool parsed = ParseInternalKey(skey, &key);
+      ParseInternalKey(skey, &key);
 
       smallest_seqno = std::min(smallest_seqno, key.sequence);
       largest_seqno = std::max(largest_seqno, key.sequence);
@@ -160,24 +132,6 @@ class CompactionJobTest : public testing::Test {
       }
 
       first_key = false;
-
-      if (parsed && key.type == kTypeBlobIndex) {
-        BlobIndex blob_index;
-        const Status s = blob_index.DecodeFrom(value);
-        if (!s.ok()) {
-          continue;
-        }
-
-        if (blob_index.IsInlined() || blob_index.HasTTL() ||
-            blob_index.file_number() == kInvalidBlobFileNumber) {
-          continue;
-        }
-
-        if (oldest_blob_file_number == kInvalidBlobFileNumber ||
-            oldest_blob_file_number > blob_index.file_number()) {
-          oldest_blob_file_number = blob_index.file_number();
-        }
-      }
     }
 
     uint64_t file_number = versions_->NewFileNumber();
@@ -186,9 +140,7 @@ class CompactionJobTest : public testing::Test {
 
     VersionEdit edit;
     edit.AddFile(level, file_number, 0, 10, smallest_key, largest_key,
-                 smallest_seqno, largest_seqno, false, oldest_blob_file_number,
-                 kUnknownOldestAncesterTime, kUnknownFileCreationTime,
-                 kUnknownFileChecksum, kUnknownFileChecksumFuncName);
+        smallest_seqno, largest_seqno, false);
 
     mutex_.Lock();
     versions_->LogAndApply(versions_->GetColumnFamilySet()->GetDefault(),
@@ -271,8 +223,8 @@ class CompactionJobTest : public testing::Test {
     Status s = env_->NewWritableFile(
         manifest, &file, env_->OptimizeForManifestWrite(env_options_));
     ASSERT_OK(s);
-    std::unique_ptr<WritableFileWriter> file_writer(new WritableFileWriter(
-        NewLegacyWritableFileWrapper(std::move(file)), manifest, env_options_));
+    std::unique_ptr<WritableFileWriter> file_writer(
+        new WritableFileWriter(std::move(file), manifest, env_options_));
     {
       log::Writer log(std::move(file_writer), 0, false);
       std::string record;
@@ -281,7 +233,7 @@ 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_;
@@ -299,7 +251,8 @@ class CompactionJobTest : public testing::Test {
       const std::vector<SequenceNumber>& snapshots = {},
       SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber,
       int output_level = 1, bool verify = true,
-      uint64_t expected_oldest_blob_file_number = kInvalidBlobFileNumber) {
+      SnapshotListFetchCallback* snapshot_fetcher =
+          SnapshotListFetchCallback::kDisabled) {
     auto cfd = versions_->GetColumnFamilySet()->GetDefault();
 
     size_t num_input_files = 0;
@@ -314,11 +267,11 @@ 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());
@@ -332,7 +285,7 @@ class CompactionJobTest : public testing::Test {
         nullptr, nullptr, &mutex_, &error_handler_, snapshots,
         earliest_write_conflict_snapshot, snapshot_checker, table_cache_,
         &event_logger, false, false, dbname_, &compaction_job_stats_,
-        Env::Priority::USER);
+        Env::Priority::USER, snapshot_fetcher);
     VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
 
     compaction_job.Prepare();
@@ -345,26 +298,20 @@ class CompactionJobTest : public testing::Test {
     mutex_.Unlock();
 
     if (verify) {
-      ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
-      ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
-
-      if (expected_results.empty()) {
+      if (expected_results.size() == 0) {
+        ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
+        ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
         ASSERT_EQ(compaction_job_stats_.num_output_files, 0U);
       } else {
+        ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
+        ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
         ASSERT_EQ(compaction_job_stats_.num_output_files, 1U);
         mock_table_factory_->AssertLatestFile(expected_results);
-
-        auto output_files =
-            cfd->current()->storage_info()->LevelFiles(output_level);
-        ASSERT_EQ(output_files.size(), 1);
-        ASSERT_EQ(output_files[0]->oldest_blob_file_number,
-                  expected_oldest_blob_file_number);
       }
     }
   }
 
   Env* env_;
-  std::shared_ptr<FileSystem> fs_;
   std::string dbname_;
   EnvOptions env_options_;
   ImmutableDBOptions db_options_;
@@ -1015,55 +962,106 @@ TEST_F(CompactionJobTest, CorruptionAfterDeletion) {
   RunCompaction({files}, expected_results);
 }
 
-TEST_F(CompactionJobTest, OldestBlobFileNumber) {
+// Test the snapshot fetcher in compaction
+TEST_F(CompactionJobTest, SnapshotRefresh) {
+  uint64_t time_seed = env_->NowMicros();
+  printf("time_seed is %" PRIu64 "\n", time_seed);  // would help to reproduce
+  Random64 rand(time_seed);
+  std::vector<SequenceNumber> db_snapshots;
+  class SnapshotListFetchCallbackTest : public SnapshotListFetchCallback {
+   public:
+    SnapshotListFetchCallbackTest(Env* env, Random64& rand,
+                                  std::vector<SequenceNumber>* snapshots)
+        : SnapshotListFetchCallback(env, 1 /*short time delay*/,
+                                    1 /*fetch after each key*/),
+          rand_(rand),
+          snapshots_(snapshots) {}
+    virtual void Refresh(std::vector<SequenceNumber>* snapshots,
+                         SequenceNumber) override {
+      assert(snapshots->size());
+      assert(snapshots_->size());
+      assert(snapshots_->size() == snapshots->size());
+      if (rand_.OneIn(2)) {
+        uint64_t release_index = rand_.Uniform(snapshots_->size());
+        snapshots_->erase(snapshots_->begin() + release_index);
+        *snapshots = *snapshots_;
+      }
+    }
+
+   private:
+    Random64 rand_;
+    std::vector<SequenceNumber>* snapshots_;
+  } snapshot_fetcher(env_, rand, &db_snapshots);
+
+  std::vector<std::pair<const std::string, std::string>> file1_kvs, file2_kvs;
+  std::array<ValueType, 4> types = {kTypeValue, kTypeDeletion,
+                                    kTypeSingleDeletion};
+  SequenceNumber last_seq = 0;
+  for (int i = 1; i < 100; i++) {
+    SequenceNumber seq = last_seq + 1;
+    last_seq = seq;
+    if (rand.OneIn(2)) {
+      auto type = types[rand.Uniform(types.size())];
+      file1_kvs.push_back(
+          {test::KeyStr("k" + ToString(i), seq, type), "v" + ToString(i)});
+    }
+  }
+  auto file1 = mock::MakeMockFile(file1_kvs);
+  for (int i = 1; i < 100; i++) {
+    SequenceNumber seq = last_seq + 1;
+    last_seq++;
+    if (rand.OneIn(2)) {
+      auto type = types[rand.Uniform(types.size())];
+      file2_kvs.push_back(
+          {test::KeyStr("k" + ToString(i), seq, type), "v" + ToString(i)});
+    }
+  }
+  auto file2 = mock::MakeMockFile(file2_kvs);
+  for (SequenceNumber i = 1; i < last_seq + 1; i++) {
+    if (rand.OneIn(5)) {
+      db_snapshots.push_back(i);
+    }
+  }
+
+  const bool kVerify = true;
+  const int output_level_0 = 0;
   NewDB();
-
-  // Note: blob1 is inlined TTL, so it will not be considered for the purposes
-  // of identifying the oldest referenced blob file. Similarly, blob6 will be
-  // ignored because it has TTL and hence refers to a TTL blob file.
-  const stl_wrappers::KVMap::value_type blob1(
-      KeyStr("a", 1U, kTypeBlobIndex), BlobStrInlinedTTL("foo", 1234567890ULL));
-  const stl_wrappers::KVMap::value_type blob2(KeyStr("b", 2U, kTypeBlobIndex),
-                                              BlobStr(59, 123456, 999));
-  const stl_wrappers::KVMap::value_type blob3(KeyStr("c", 3U, kTypeBlobIndex),
-                                              BlobStr(138, 1000, 1 << 8));
-  auto file1 = mock::MakeMockFile({blob1, blob2, blob3});
   AddMockFile(file1);
-
-  const stl_wrappers::KVMap::value_type blob4(KeyStr("d", 4U, kTypeBlobIndex),
-                                              BlobStr(199, 3 << 10, 1 << 20));
-  const stl_wrappers::KVMap::value_type blob5(KeyStr("e", 5U, kTypeBlobIndex),
-                                              BlobStr(19, 6789, 333));
-  const stl_wrappers::KVMap::value_type blob6(
-      KeyStr("f", 6U, kTypeBlobIndex),
-      BlobStrTTL(5, 2048, 1 << 7, 1234567890ULL));
-  auto file2 = mock::MakeMockFile({blob4, blob5, blob6});
   AddMockFile(file2);
-
-  const stl_wrappers::KVMap::value_type expected_blob1(
-      KeyStr("a", 0U, kTypeBlobIndex), blob1.second);
-  const stl_wrappers::KVMap::value_type expected_blob2(
-      KeyStr("b", 0U, kTypeBlobIndex), blob2.second);
-  const stl_wrappers::KVMap::value_type expected_blob3(
-      KeyStr("c", 0U, kTypeBlobIndex), blob3.second);
-  const stl_wrappers::KVMap::value_type expected_blob4(
-      KeyStr("d", 0U, kTypeBlobIndex), blob4.second);
-  const stl_wrappers::KVMap::value_type expected_blob5(
-      KeyStr("e", 0U, kTypeBlobIndex), blob5.second);
-  const stl_wrappers::KVMap::value_type expected_blob6(
-      KeyStr("f", 0U, kTypeBlobIndex), blob6.second);
-  auto expected_results =
-      mock::MakeMockFile({expected_blob1, expected_blob2, expected_blob3,
-                          expected_blob4, expected_blob5, expected_blob6});
-
-  SetLastSequence(6U);
+  SetLastSequence(last_seq);
   auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results, std::vector<SequenceNumber>(),
-                kMaxSequenceNumber, /* output_level */ 1, /* verify */ true,
-                /* expected_oldest_blob_file_number */ 19);
+  // put the output on L0 since it is easier to feed them again to the 2nd
+  // compaction
+  RunCompaction({files}, file1, db_snapshots, kMaxSequenceNumber,
+                output_level_0, !kVerify, &snapshot_fetcher);
+
+  // Now db_snapshots are changed. Run the compaction again without snapshot
+  // fetcher but with the updated snapshot list.
+  compaction_job_stats_.Reset();
+  files = cfd_->current()->storage_info()->LevelFiles(0);
+  RunCompaction({files}, file1, db_snapshots, kMaxSequenceNumber,
+                output_level_0 + 1, !kVerify);
+  // The result should be what we get if we run compaction without snapshot
+  // fetcher on the updated list of snapshots
+  auto expected = mock_table_factory_->output();
+
+  NewDB();
+  AddMockFile(file1);
+  AddMockFile(file2);
+  SetLastSequence(last_seq);
+  files = cfd_->current()->storage_info()->LevelFiles(0);
+  RunCompaction({files}, expected, db_snapshots, kMaxSequenceNumber,
+                output_level_0, !kVerify);
+  // The 2nd compaction above would get rid of useless delete markers. To get
+  // the output here exactly as what we got above after two compactions, we also
+  // run the compaction for 2nd time.
+  compaction_job_stats_.Reset();
+  files = cfd_->current()->storage_info()->LevelFiles(0);
+  RunCompaction({files}, expected, db_snapshots, kMaxSequenceNumber,
+                output_level_0 + 1, !kVerify);
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

db/compaction/compaction_picker.cc

@@ -23,7 +23,7 @@
 #include "util/random.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 namespace {
 uint64_t TotalCompensatedFileSize(const std::vector<FileMetaData*>& files) {
@@ -39,41 +39,20 @@ bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
                            size_t min_files_to_compact,
                            uint64_t max_compact_bytes_per_del_file,
                            uint64_t max_compaction_bytes,
-                           CompactionInputFiles* comp_inputs,
-                           SequenceNumber earliest_mem_seqno) {
-  // Do not pick ingested file when there is at least one memtable not flushed
-  // which of seqno is overlap with the sst.
-  TEST_SYNC_POINT("FindIntraL0Compaction");
-  size_t start = 0;
-  for (; start < level_files.size(); start++) {
-    if (level_files[start]->being_compacted) {
-      return false;
-    }
-    // If there is no data in memtable, the earliest sequence number would the
-    // largest sequence number in last memtable.
-    // Because all files are sorted in descending order by largest_seqno, so we
-    // only need to check the first one.
-    if (level_files[start]->fd.largest_seqno <= earliest_mem_seqno) {
-      break;
-    }
-  }
-  if (start >= level_files.size()) {
-    return false;
-  }
-  size_t compact_bytes = static_cast<size_t>(level_files[start]->fd.file_size);
-  uint64_t compensated_compact_bytes =
-      level_files[start]->compensated_file_size;
+                           CompactionInputFiles* comp_inputs) {
+  size_t compact_bytes = static_cast<size_t>(level_files[0]->fd.file_size);
+  uint64_t compensated_compact_bytes = level_files[0]->compensated_file_size;
   size_t compact_bytes_per_del_file = port::kMaxSizet;
-  // Compaction range will be [start, limit).
-  size_t limit;
+  // Compaction range will be [0, span_len).
+  size_t span_len;
   // Pull in files until the amount of compaction work per deleted file begins
   // increasing or maximum total compaction size is reached.
   size_t new_compact_bytes_per_del_file = 0;
-  for (limit = start + 1; limit < level_files.size(); ++limit) {
-    compact_bytes += static_cast<size_t>(level_files[limit]->fd.file_size);
-    compensated_compact_bytes += level_files[limit]->compensated_file_size;
-    new_compact_bytes_per_del_file = compact_bytes / (limit - start);
-    if (level_files[limit]->being_compacted ||
+  for (span_len = 1; span_len < level_files.size(); ++span_len) {
+    compact_bytes += static_cast<size_t>(level_files[span_len]->fd.file_size);
+    compensated_compact_bytes += level_files[span_len]->compensated_file_size;
+    new_compact_bytes_per_del_file = compact_bytes / span_len;
+    if (level_files[span_len]->being_compacted ||
         new_compact_bytes_per_del_file > compact_bytes_per_del_file ||
         compensated_compact_bytes > max_compaction_bytes) {
       break;
@@ -81,11 +60,11 @@ bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
     compact_bytes_per_del_file = new_compact_bytes_per_del_file;
   }
 
-  if ((limit - start) >= min_files_to_compact &&
+  if (span_len >= min_files_to_compact &&
       compact_bytes_per_del_file < max_compact_bytes_per_del_file) {
     assert(comp_inputs != nullptr);
     comp_inputs->level = 0;
-    for (size_t i = start; i < limit; ++i) {
+    for (size_t i = 0; i < span_len; ++i) {
       comp_inputs->files.push_back(level_files[i]);
     }
     return true;
@@ -110,9 +89,9 @@ 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 +111,22 @@ 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 +338,7 @@ 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 +613,7 @@ 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 +766,7 @@ 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);
 
@@ -1128,4 +1107,4 @@ bool CompactionPicker::GetOverlappingL0Files(
   return true;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction/compaction_picker.h

@@ -22,7 +22,7 @@
 #include "rocksdb/options.h"
 #include "rocksdb/status.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 // The file contains an abstract class CompactionPicker, and its two
 // sub-classes LevelCompactionPicker and NullCompactionPicker, as
@@ -54,10 +54,10 @@ class CompactionPicker {
   // Returns nullptr if there is no compaction to be done.
   // Otherwise returns a pointer to a heap-allocated object that
   // describes the compaction.  Caller should delete the result.
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) = 0;
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) = 0;
 
   // Return a compaction object for compacting the range [begin,end] in
   // the specified level.  Returns nullptr if there is nothing in that
@@ -247,11 +247,10 @@ class NullCompactionPicker : public CompactionPicker {
   virtual ~NullCompactionPicker() {}
 
   // Always return "nullptr"
-  Compaction* PickCompaction(
-      const std::string& /*cf_name*/,
-      const MutableCFOptions& /*mutable_cf_options*/,
-      VersionStorageInfo* /*vstorage*/, LogBuffer* /* log_buffer */,
-      SequenceNumber /* earliest_memtable_seqno */) override {
+  Compaction* PickCompaction(const std::string& /*cf_name*/,
+                             const MutableCFOptions& /*mutable_cf_options*/,
+                             VersionStorageInfo* /*vstorage*/,
+                             LogBuffer* /*log_buffer*/) override {
     return nullptr;
   }
 
@@ -293,11 +292,11 @@ class NullCompactionPicker : public CompactionPicker {
 //                                        files. Cannot be nullptr.
 //
 // @return                                true iff compaction was found.
-bool FindIntraL0Compaction(
-    const std::vector<FileMetaData*>& level_files, size_t min_files_to_compact,
-    uint64_t max_compact_bytes_per_del_file, uint64_t max_compaction_bytes,
-    CompactionInputFiles* comp_inputs,
-    SequenceNumber earliest_mem_seqno = kMaxSequenceNumber);
+bool FindIntraL0Compaction(const std::vector<FileMetaData*>& level_files,
+                           size_t min_files_to_compact,
+                           uint64_t max_compact_bytes_per_del_file,
+                           uint64_t max_compaction_bytes,
+                           CompactionInputFiles* comp_inputs);
 
 CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
                                    const VersionStorageInfo* vstorage,
@@ -305,9 +304,9 @@ 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
+}  // namespace rocksdb

db/compaction/compaction_picker_fifo.cc

@@ -17,7 +17,7 @@
 #include "logging/log_buffer.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 namespace {
 uint64_t GetTotalFilesSize(const std::vector<FileMetaData*>& files) {
   uint64_t total_size = 0;
@@ -70,18 +70,18 @@ Compaction* FIFOCompactionPicker::PickTTLCompaction(
   // avoid underflow
   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 =
+      auto f = *ritr;
+      if (f->fd.table_reader != nullptr &&
+          f->fd.table_reader->GetTableProperties() != nullptr) {
+        auto creation_time =
             f->fd.table_reader->GetTableProperties()->creation_time;
         if (creation_time == 0 ||
             creation_time >= (current_time - mutable_cf_options.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);
     }
   }
 
@@ -96,22 +96,17 @@ 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()) {
-      creation_time = f->fd.table_reader->GetTableProperties()->creation_time;
-    }
     ROCKS_LOG_BUFFER(log_buffer,
                      "[%s] FIFO compaction: picking file %" PRIu64
                      " with creation time %" PRIu64 " for deletion",
-                     cf_name.c_str(), f->fd.GetNumber(), creation_time);
+                     cf_name.c_str(), f->fd.GetNumber(),
+                     f->fd.table_reader->GetTableProperties()->creation_time);
   }
 
   Compaction* c = new Compaction(
       vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
-      kNoCompression, 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 +146,7 @@ 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);
@@ -199,17 +194,15 @@ 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;
 }
 
 Compaction* FIFOCompactionPicker::PickCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-    SequenceNumber /*earliest_memtable_seqno*/) {
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
   assert(vstorage->num_levels() == 1);
 
   Compaction* c = nullptr;
@@ -244,5 +237,5 @@ Compaction* FIFOCompactionPicker::CompactRange(
   return c;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 #endif  // !ROCKSDB_LITE

db/compaction/compaction_picker_fifo.h

@@ -12,17 +12,17 @@
 
 #include "db/compaction/compaction_picker.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 class FIFOCompactionPicker : public CompactionPicker {
  public:
   FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
                        const InternalKeyComparator* icmp)
       : CompactionPicker(ioptions, icmp) {}
 
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* version, LogBuffer* log_buffer,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) override;
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* version,
+                                     LogBuffer* log_buffer) override;
 
   virtual Compaction* CompactRange(
       const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
@@ -49,5 +49,5 @@ class FIFOCompactionPicker : public CompactionPicker {
                                  VersionStorageInfo* version,
                                  LogBuffer* log_buffer);
 };
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 #endif  // !ROCKSDB_LITE

db/compaction/compaction_picker_level.cc

@@ -15,7 +15,7 @@
 #include "logging/log_buffer.h"
 #include "test_util/sync_point.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 bool LevelCompactionPicker::NeedsCompaction(
     const VersionStorageInfo* vstorage) const {
@@ -45,14 +45,12 @@ class LevelCompactionBuilder {
  public:
   LevelCompactionBuilder(const std::string& cf_name,
                          VersionStorageInfo* vstorage,
-                         SequenceNumber earliest_mem_seqno,
                          CompactionPicker* compaction_picker,
                          LogBuffer* log_buffer,
                          const MutableCFOptions& mutable_cf_options,
                          const ImmutableCFOptions& ioptions)
       : cf_name_(cf_name),
         vstorage_(vstorage),
-        earliest_mem_seqno_(earliest_mem_seqno),
         compaction_picker_(compaction_picker),
         log_buffer_(log_buffer),
         mutable_cf_options_(mutable_cf_options),
@@ -93,17 +91,12 @@ 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_;
-  SequenceNumber earliest_mem_seqno_;
   CompactionPicker* compaction_picker_;
   LogBuffer* log_buffer_;
   int start_level_ = -1;
@@ -128,34 +121,72 @@ 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 +235,64 @@ 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 +381,7 @@ 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_);
 
@@ -488,19 +537,17 @@ bool LevelCompactionBuilder::PickIntraL0Compaction() {
     // resort to L0->L0 compaction yet.
     return false;
   }
-  return FindIntraL0Compaction(level_files, kMinFilesForIntraL0Compaction,
-                               port::kMaxUint64,
-                               mutable_cf_options_.max_compaction_bytes,
-                               &start_level_inputs_, earliest_mem_seqno_);
+  return FindIntraL0Compaction(
+      level_files, kMinFilesForIntraL0Compaction, port::kMaxUint64,
+      mutable_cf_options_.max_compaction_bytes, &start_level_inputs_);
 }
 }  // namespace
 
 Compaction* LevelCompactionPicker::PickCompaction(
     const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-    SequenceNumber earliest_mem_seqno) {
-  LevelCompactionBuilder builder(cf_name, vstorage, earliest_mem_seqno, this,
-                                 log_buffer, mutable_cf_options, ioptions_);
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
+  LevelCompactionBuilder builder(cf_name, vstorage, this, log_buffer,
+                                 mutable_cf_options, ioptions_);
   return builder.PickCompaction();
 }
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction/compaction_picker_level.h

@@ -11,7 +11,7 @@
 
 #include "db/compaction/compaction_picker.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 // Picking compactions for leveled compaction. See wiki page
 // https://github.com/facebook/rocksdb/wiki/Leveled-Compaction
 // for description of Leveled compaction.
@@ -20,13 +20,13 @@ class LevelCompactionPicker : public CompactionPicker {
   LevelCompactionPicker(const ImmutableCFOptions& ioptions,
                         const InternalKeyComparator* icmp)
       : CompactionPicker(ioptions, icmp) {}
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) override;
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) override;
 
   virtual bool NeedsCompaction(
       const VersionStorageInfo* vstorage) const override;
 };
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb

db/compaction/compaction_picker_test.cc

@@ -17,7 +17,7 @@
 #include "test_util/testutil.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class CountingLogger : public Logger {
  public:
@@ -57,8 +57,6 @@ class CompactionPickerTest : public testing::Test {
         log_buffer_(InfoLogLevel::INFO_LEVEL, &logger_),
         file_num_(1),
         vstorage_(nullptr) {
-    mutable_cf_options_.ttl = 0;
-    mutable_cf_options_.periodic_compaction_seconds = 0;
     // ioptions_.compaction_pri = kMinOverlappingRatio has its own set of
     // tests to cover.
     ioptions_.compaction_pri = kByCompensatedSize;
@@ -90,15 +88,15 @@ class CompactionPickerTest : public testing::Test {
            SequenceNumber smallest_seq = 100, SequenceNumber largest_seq = 100,
            size_t compensated_file_size = 0) {
     assert(level < vstorage_->num_levels());
-    FileMetaData* f = new FileMetaData(
-        file_number, path_id, file_size,
-        InternalKey(smallest, smallest_seq, kTypeValue),
-        InternalKey(largest, largest_seq, kTypeValue), smallest_seq,
-        largest_seq, /* marked_for_compact */ false, kInvalidBlobFileNumber,
-        kUnknownOldestAncesterTime, kUnknownFileCreationTime,
-        kUnknownFileChecksum, kUnknownFileChecksumFuncName);
+    FileMetaData* f = new FileMetaData;
+    f->fd = FileDescriptor(file_number, path_id, file_size);
+    f->smallest = InternalKey(smallest, smallest_seq, kTypeValue);
+    f->largest = InternalKey(largest, largest_seq, kTypeValue);
+    f->fd.smallest_seqno = smallest_seq;
+    f->fd.largest_seqno = largest_seq;
     f->compensated_file_size =
         (compensated_file_size != 0) ? compensated_file_size : file_size;
+    f->refs = 0;
     vstorage_->AddFile(level, f);
     files_.emplace_back(f);
     file_map_.insert({file_number, {f, level}});
@@ -503,168 +501,6 @@ TEST_F(CompactionPickerTest, AllowsTrivialMoveUniversal) {
   ASSERT_TRUE(compaction->is_trivial_move());
 }
 
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction1) {
-  // The case where universal periodic compaction can be picked
-  // with some newer files being compacted.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(0, 2U, "201", "250", kFileSize, 0, 401, 450);
-  Add(0, 4U, "260", "300", kFileSize, 0, 260, 300);
-  Add(3, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(4, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(4, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[2].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(4, file_map_[3].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  ASSERT_TRUE(compaction);
-  ASSERT_EQ(4, compaction->output_level());
-  ASSERT_EQ(0, compaction->start_level());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction2) {
-  // The case where universal periodic compaction does not
-  // pick up only level to compact if it doesn't cover
-  // any file marked as periodic compaction.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(3, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(4, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(4, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[5].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[1].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  ASSERT_FALSE(compaction);
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction3) {
-  // The case where universal periodic compaction does not
-  // pick up only the last sorted run which is an L0 file if it isn't
-  // marked as periodic compaction.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(0, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(0, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[5].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[1].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-
-  ASSERT_FALSE(compaction);
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction4) {
-  // The case where universal periodic compaction couldn't form
-  // a compaction that inlcudes any file marked for periodic compaction.
-  // Right now we form the compaction anyway if it is more than one
-  // sorted run. Just put the case here to validate that it doesn't
-  // crash.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 1U, "150", "200", kFileSize, 0, 500, 550);
-  Add(2, 2U, "010", "080", kFileSize, 0, 200, 251);
-  Add(3, 5U, "010", "080", kFileSize, 0, 200, 251);
-  Add(4, 3U, "301", "350", kFileSize, 0, 101, 150);
-  Add(4, 6U, "501", "750", kFileSize, 0, 101, 150);
-
-  file_map_[2].first->being_compacted = true;
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[2].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(!compaction ||
-              compaction->start_level() != compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction5) {
-  // Test single L0 file periodic compaction triggering.
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(0, 6U, "150", "200", kFileSize, 0, 500, 550);
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(0, file_map_[6].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction);
-  ASSERT_EQ(0, compaction->start_level());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(6U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(4, compaction->output_level());
-}
-
-TEST_F(CompactionPickerTest, UniversalPeriodicCompaction6) {
-  // Test single sorted run non-L0 periodic compaction
-  const uint64_t kFileSize = 100000;
-
-  mutable_cf_options_.periodic_compaction_seconds = 1000;
-  UniversalCompactionPicker universal_compaction_picker(ioptions_, &icmp_);
-
-  NewVersionStorage(5, kCompactionStyleUniversal);
-
-  Add(4, 5U, "150", "200", kFileSize, 0, 500, 550);
-  Add(4, 6U, "350", "400", kFileSize, 0, 500, 550);
-  UpdateVersionStorageInfo();
-  vstorage_->TEST_AddFileMarkedForPeriodicCompaction(4, file_map_[6].first);
-
-  std::unique_ptr<Compaction> compaction(
-      universal_compaction_picker.PickCompaction(
-          cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction);
-  ASSERT_EQ(4, compaction->start_level());
-  ASSERT_EQ(2U, compaction->num_input_files(0));
-  ASSERT_EQ(5U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(6U, compaction->input(0, 1)->fd.GetNumber());
-  ASSERT_EQ(4, compaction->output_level());
-}
-
 TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
   NewVersionStorage(1, kCompactionStyleFIFO);
   const int kFileCount =
@@ -1652,12 +1488,12 @@ TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesNotHit) {
   // All 5 L0 files will be picked for intra L0 compaction. The one L1 file
   // spans entire L0 key range and is marked as being compacted to avoid
   // L0->L1 compaction.
-  Add(0, 1U, "100", "150", 200000U, 0, 100, 101);
-  Add(0, 2U, "151", "200", 200000U, 0, 102, 103);
-  Add(0, 3U, "201", "250", 200000U, 0, 104, 105);
-  Add(0, 4U, "251", "300", 200000U, 0, 106, 107);
-  Add(0, 5U, "301", "350", 200000U, 0, 108, 109);
-  Add(1, 6U, "100", "350", 200000U, 0, 110, 111);
+  Add(0, 1U, "100", "150", 200000U);
+  Add(0, 2U, "151", "200", 200000U);
+  Add(0, 3U, "201", "250", 200000U);
+  Add(0, 4U, "251", "300", 200000U);
+  Add(0, 5U, "301", "350", 200000U);
+  Add(1, 6U, "100", "350", 200000U);
   vstorage_->LevelFiles(1)[0]->being_compacted = true;
   UpdateVersionStorageInfo();
 
@@ -1682,12 +1518,12 @@ TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesHit) {
   // max_compaction_bytes limit (the minimum number of files for triggering
   // intra L0 compaction is 4). The one L1 file spans entire L0 key range and
   // is marked as being compacted to avoid L0->L1 compaction.
-  Add(0, 1U, "100", "150", 200000U, 0, 100, 101);
-  Add(0, 2U, "151", "200", 200000U, 0, 102, 103);
-  Add(0, 3U, "201", "250", 200000U, 0, 104, 105);
-  Add(0, 4U, "251", "300", 200000U, 0, 106, 107);
-  Add(0, 5U, "301", "350", 200000U, 0, 108, 109);
-  Add(1, 6U, "100", "350", 200000U, 0, 109, 110);
+  Add(0, 1U, "100", "150", 200000U);
+  Add(0, 2U, "151", "200", 200000U);
+  Add(0, 3U, "201", "250", 200000U);
+  Add(0, 4U, "251", "300", 200000U);
+  Add(0, 5U, "301", "350", 200000U);
+  Add(1, 6U, "100", "350", 200000U);
   vstorage_->LevelFiles(1)[0]->being_compacted = true;
   UpdateVersionStorageInfo();
 
@@ -1701,39 +1537,7 @@ TEST_F(CompactionPickerTest, IntraL0MaxCompactionBytesHit) {
   ASSERT_EQ(0, compaction->output_level());
 }
 
-TEST_F(CompactionPickerTest, IntraL0ForEarliestSeqno) {
-  // Intra L0 compaction triggers only if there are at least
-  // level0_file_num_compaction_trigger + 2 L0 files.
-  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
-  mutable_cf_options_.max_compaction_bytes = 999999u;
-  NewVersionStorage(6, kCompactionStyleLevel);
-
-  // 4 out of 6 L0 files will be picked for intra L0 compaction due to
-  // being_compact limit. And the latest one L0 will be skipped due to earliest
-  // seqno. The one L1 file spans entire L0 key range and is marked as being
-  // compacted to avoid L0->L1 compaction.
-  Add(1, 1U, "100", "350", 200000U, 0, 110, 111);
-  Add(0, 2U, "301", "350", 1U, 0, 108, 109);
-  Add(0, 3U, "251", "300", 1U, 0, 106, 107);
-  Add(0, 4U, "201", "250", 1U, 0, 104, 105);
-  Add(0, 5U, "151", "200", 1U, 0, 102, 103);
-  Add(0, 6U, "100", "150", 1U, 0, 100, 101);
-  Add(0, 7U, "100", "100", 1U, 0, 99, 100);
-  vstorage_->LevelFiles(0)[5]->being_compacted = true;
-  vstorage_->LevelFiles(1)[0]->being_compacted = true;
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_, 107));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_levels());
-  ASSERT_EQ(4U, compaction->num_input_files(0));
-  ASSERT_EQ(CompactionReason::kLevelL0FilesNum,
-            compaction->compaction_reason());
-  ASSERT_EQ(0, compaction->output_level());
-}
-
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

db/compaction/compaction_picker_universal.cc

@@ -23,113 +23,8 @@
 #include "util/random.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 namespace {
-// A helper class that form universal compactions. The class is used by
-// UniversalCompactionPicker::PickCompaction().
-// The usage is to create the class, and get the compaction object by calling
-// PickCompaction().
-class UniversalCompactionBuilder {
- public:
-  UniversalCompactionBuilder(const ImmutableCFOptions& ioptions,
-                             const InternalKeyComparator* icmp,
-                             const std::string& cf_name,
-                             const MutableCFOptions& mutable_cf_options,
-                             VersionStorageInfo* vstorage,
-                             UniversalCompactionPicker* picker,
-                             LogBuffer* log_buffer)
-      : ioptions_(ioptions),
-        icmp_(icmp),
-        cf_name_(cf_name),
-        mutable_cf_options_(mutable_cf_options),
-        vstorage_(vstorage),
-        picker_(picker),
-        log_buffer_(log_buffer) {}
-
-  // Form and return the compaction object. The caller owns return object.
-  Compaction* PickCompaction();
-
- private:
-  struct SortedRun {
-    SortedRun(int _level, FileMetaData* _file, uint64_t _size,
-              uint64_t _compensated_file_size, bool _being_compacted)
-        : level(_level),
-          file(_file),
-          size(_size),
-          compensated_file_size(_compensated_file_size),
-          being_compacted(_being_compacted) {
-      assert(compensated_file_size > 0);
-      assert(level != 0 || file != nullptr);
-    }
-
-    void Dump(char* out_buf, size_t out_buf_size,
-              bool print_path = false) const;
-
-    // sorted_run_count is added into the string to print
-    void DumpSizeInfo(char* out_buf, size_t out_buf_size,
-                      size_t sorted_run_count) const;
-
-    int level;
-    // `file` Will be null for level > 0. For level = 0, the sorted run is
-    // for this file.
-    FileMetaData* file;
-    // For level > 0, `size` and `compensated_file_size` are sum of sizes all
-    // files in the level. `being_compacted` should be the same for all files
-    // in a non-zero level. Use the value here.
-    uint64_t size;
-    uint64_t compensated_file_size;
-    bool being_compacted;
-  };
-
-  // Pick Universal compaction to limit read amplification
-  Compaction* PickCompactionToReduceSortedRuns(
-      unsigned int ratio, unsigned int max_number_of_files_to_compact);
-
-  // Pick Universal compaction to limit space amplification.
-  Compaction* PickCompactionToReduceSizeAmp();
-
-  Compaction* PickDeleteTriggeredCompaction();
-
-  // Form a compaction from the sorted run indicated by start_index to the
-  // oldest sorted run.
-  // The caller is responsible for making sure that those files are not in
-  // compaction.
-  Compaction* PickCompactionToOldest(size_t start_index,
-                                     CompactionReason compaction_reason);
-
-  // Try to pick periodic compaction. The caller should only call it
-  // if there is at least one file marked for periodic compaction.
-  // null will be returned if no such a compaction can be formed
-  // because some files are being compacted.
-  Compaction* PickPeriodicCompaction();
-
-  // Used in universal compaction when the enabled_trivial_move
-  // option is set. Checks whether there are any overlapping files
-  // in the input. Returns true if the input files are non
-  // overlapping.
-  bool IsInputFilesNonOverlapping(Compaction* c);
-
-  const ImmutableCFOptions& ioptions_;
-  const InternalKeyComparator* icmp_;
-  double score_;
-  std::vector<SortedRun> sorted_runs_;
-  const std::string& cf_name_;
-  const MutableCFOptions& mutable_cf_options_;
-  VersionStorageInfo* vstorage_;
-  UniversalCompactionPicker* picker_;
-  LogBuffer* log_buffer_;
-
-  static std::vector<SortedRun> CalculateSortedRuns(
-      const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions,
-      const MutableCFOptions& mutable_cf_options);
-
-  // Pick a path ID to place a newly generated file, with its estimated file
-  // size.
-  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
-                            const MutableCFOptions& mutable_cf_options,
-                            uint64_t file_size);
-};
-
 // Used in universal compaction when trivial move is enabled.
 // This structure is used for the construction of min heap
 // that contains the file meta data, the level of the file
@@ -218,7 +113,7 @@ void GetSmallestLargestSeqno(const std::vector<FileMetaData*>& files,
 
 // Algorithm that checks to see if there are any overlapping
 // files in the input
-bool UniversalCompactionBuilder::IsInputFilesNonOverlapping(Compaction* c) {
+bool UniversalCompactionPicker::IsInputFilesNonOverlapping(Compaction* c) {
   auto comparator = icmp_->user_comparator();
   int first_iter = 1;
 
@@ -247,8 +142,7 @@ bool UniversalCompactionBuilder::IsInputFilesNonOverlapping(Compaction* c) {
 
     next.f = nullptr;
 
-    if (c->level(curr.level) != 0 &&
-        curr.index < c->num_input_files(curr.level) - 1) {
+    if (curr.level != 0 && curr.index < c->num_input_files(curr.level) - 1) {
       next.f = c->input(curr.level, curr.index + 1);
       next.level = curr.level;
       next.index = curr.index + 1;
@@ -267,28 +161,15 @@ bool UniversalCompactionPicker::NeedsCompaction(
   if (vstorage->CompactionScore(kLevel0) >= 1) {
     return true;
   }
-  if (!vstorage->FilesMarkedForPeriodicCompaction().empty()) {
-    return true;
-  }
   if (!vstorage->FilesMarkedForCompaction().empty()) {
     return true;
   }
   return false;
 }
 
-Compaction* UniversalCompactionPicker::PickCompaction(
-    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-    VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-    SequenceNumber /* earliest_memtable_seqno */) {
-  UniversalCompactionBuilder builder(ioptions_, icmp_, cf_name,
-                                     mutable_cf_options, vstorage, this,
-                                     log_buffer);
-  return builder.PickCompaction();
-}
-
-void UniversalCompactionBuilder::SortedRun::Dump(char* out_buf,
-                                                 size_t out_buf_size,
-                                                 bool print_path) const {
+void UniversalCompactionPicker::SortedRun::Dump(char* out_buf,
+                                                size_t out_buf_size,
+                                                bool print_path) const {
   if (level == 0) {
     assert(file != nullptr);
     if (file->fd.GetPathId() == 0 || !print_path) {
@@ -304,7 +185,7 @@ void UniversalCompactionBuilder::SortedRun::Dump(char* out_buf,
   }
 }
 
-void UniversalCompactionBuilder::SortedRun::DumpSizeInfo(
+void UniversalCompactionPicker::SortedRun::DumpSizeInfo(
     char* out_buf, size_t out_buf_size, size_t sorted_run_count) const {
   if (level == 0) {
     assert(file != nullptr);
@@ -323,11 +204,11 @@ void UniversalCompactionBuilder::SortedRun::DumpSizeInfo(
   }
 }
 
-std::vector<UniversalCompactionBuilder::SortedRun>
-UniversalCompactionBuilder::CalculateSortedRuns(
+std::vector<UniversalCompactionPicker::SortedRun>
+UniversalCompactionPicker::CalculateSortedRuns(
     const VersionStorageInfo& vstorage, const ImmutableCFOptions& /*ioptions*/,
     const MutableCFOptions& mutable_cf_options) {
-  std::vector<UniversalCompactionBuilder::SortedRun> ret;
+  std::vector<UniversalCompactionPicker::SortedRun> ret;
   for (FileMetaData* f : vstorage.LevelFiles(0)) {
     ret.emplace_back(0, f, f->fd.GetFileSize(), f->compensated_file_size,
                      f->being_compacted);
@@ -350,8 +231,8 @@ UniversalCompactionBuilder::CalculateSortedRuns(
         // non-zero level, all the files should share the same being_compacted
         // value.
         // This assumption is only valid when
-        // mutable_cf_options.compaction_options_universal.allow_trivial_move
-        // is false
+        // mutable_cf_options.compaction_options_universal.allow_trivial_move is
+        // false
         assert(is_first || f->being_compacted == being_compacted);
       }
       if (is_first) {
@@ -369,68 +250,65 @@ UniversalCompactionBuilder::CalculateSortedRuns(
 
 // Universal style of compaction. Pick files that are contiguous in
 // time-range to compact.
-Compaction* UniversalCompactionBuilder::PickCompaction() {
+Compaction* UniversalCompactionPicker::PickCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, LogBuffer* log_buffer) {
   const int kLevel0 = 0;
-  score_ = vstorage_->CompactionScore(kLevel0);
-  sorted_runs_ =
-      CalculateSortedRuns(*vstorage_, ioptions_, mutable_cf_options_);
+  double score = vstorage->CompactionScore(kLevel0);
+  std::vector<SortedRun> sorted_runs =
+      CalculateSortedRuns(*vstorage, ioptions_, mutable_cf_options);
 
-  if (sorted_runs_.size() == 0 ||
-      (vstorage_->FilesMarkedForPeriodicCompaction().empty() &&
-       vstorage_->FilesMarkedForCompaction().empty() &&
-       sorted_runs_.size() < (unsigned int)mutable_cf_options_
-                                 .level0_file_num_compaction_trigger)) {
-    ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: nothing to do\n",
-                     cf_name_.c_str());
-    TEST_SYNC_POINT_CALLBACK(
-        "UniversalCompactionBuilder::PickCompaction:Return", nullptr);
+  if (sorted_runs.size() == 0 ||
+      (vstorage->FilesMarkedForCompaction().empty() &&
+       sorted_runs.size() < (unsigned int)mutable_cf_options
+                                .level0_file_num_compaction_trigger)) {
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: nothing to do\n",
+                     cf_name.c_str());
+    TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
+                             nullptr);
     return nullptr;
   }
   VersionStorageInfo::LevelSummaryStorage tmp;
   ROCKS_LOG_BUFFER_MAX_SZ(
-      log_buffer_, 3072,
-      "[%s] Universal: sorted runs: %" ROCKSDB_PRIszt " files: %s\n",
-      cf_name_.c_str(), sorted_runs_.size(), vstorage_->LevelSummary(&tmp));
+      log_buffer, 3072,
+      "[%s] Universal: sorted runs files(%" ROCKSDB_PRIszt "): %s\n",
+      cf_name.c_str(), sorted_runs.size(), vstorage->LevelSummary(&tmp));
 
+  // Check for size amplification first.
   Compaction* c = nullptr;
-  // Periodic compaction has higher priority than other type of compaction
-  // because it's a hard requirement.
-  if (!vstorage_->FilesMarkedForPeriodicCompaction().empty()) {
-    // Always need to do a full compaction for periodic compaction.
-    c = PickPeriodicCompaction();
-  }
-
-  // Check for size amplification.
-  if (c == nullptr &&
-      sorted_runs_.size() >=
-          static_cast<size_t>(
-              mutable_cf_options_.level0_file_num_compaction_trigger)) {
-    if ((c = PickCompactionToReduceSizeAmp()) != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: compacting for size amp\n",
-                       cf_name_.c_str());
+  if (sorted_runs.size() >=
+      static_cast<size_t>(
+          mutable_cf_options.level0_file_num_compaction_trigger)) {
+    if ((c = PickCompactionToReduceSizeAmp(cf_name, mutable_cf_options,
+                                           vstorage, score, sorted_runs,
+                                           log_buffer)) != nullptr) {
+      ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: compacting for size amp\n",
+                       cf_name.c_str());
     } else {
       // Size amplification is within limits. Try reducing read
       // amplification while maintaining file size ratios.
       unsigned int ratio =
-          mutable_cf_options_.compaction_options_universal.size_ratio;
+          mutable_cf_options.compaction_options_universal.size_ratio;
 
-      if ((c = PickCompactionToReduceSortedRuns(ratio, UINT_MAX)) != nullptr) {
-        ROCKS_LOG_BUFFER(log_buffer_,
+      if ((c = PickCompactionToReduceSortedRuns(
+               cf_name, mutable_cf_options, vstorage, score, ratio, UINT_MAX,
+               sorted_runs, log_buffer)) != nullptr) {
+        ROCKS_LOG_BUFFER(log_buffer,
                          "[%s] Universal: compacting for size ratio\n",
-                         cf_name_.c_str());
+                         cf_name.c_str());
       } else {
         // Size amplification and file size ratios are within configured limits.
         // If max read amplification is exceeding configured limits, then force
         // compaction without looking at filesize ratios and try to reduce
         // the number of files to fewer than level0_file_num_compaction_trigger.
         // This is guaranteed by NeedsCompaction()
-        assert(sorted_runs_.size() >=
+        assert(sorted_runs.size() >=
                static_cast<size_t>(
-                   mutable_cf_options_.level0_file_num_compaction_trigger));
+                   mutable_cf_options.level0_file_num_compaction_trigger));
         // Get the total number of sorted runs that are not being compacted
         int num_sr_not_compacted = 0;
-        for (size_t i = 0; i < sorted_runs_.size(); i++) {
-          if (sorted_runs_[i].being_compacted == false) {
+        for (size_t i = 0; i < sorted_runs.size(); i++) {
+          if (sorted_runs[i].being_compacted == false) {
             num_sr_not_compacted++;
           }
         }
@@ -438,15 +316,16 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
         // The number of sorted runs that are not being compacted is greater
         // than the maximum allowed number of sorted runs
         if (num_sr_not_compacted >
-            mutable_cf_options_.level0_file_num_compaction_trigger) {
+            mutable_cf_options.level0_file_num_compaction_trigger) {
           unsigned int num_files =
               num_sr_not_compacted -
-              mutable_cf_options_.level0_file_num_compaction_trigger + 1;
-          if ((c = PickCompactionToReduceSortedRuns(UINT_MAX, num_files)) !=
-              nullptr) {
-            ROCKS_LOG_BUFFER(log_buffer_,
+              mutable_cf_options.level0_file_num_compaction_trigger + 1;
+          if ((c = PickCompactionToReduceSortedRuns(
+                   cf_name, mutable_cf_options, vstorage, score, UINT_MAX,
+                   num_files, sorted_runs, log_buffer)) != nullptr) {
+            ROCKS_LOG_BUFFER(log_buffer,
                              "[%s] Universal: compacting for file num -- %u\n",
-                             cf_name_.c_str(), num_files);
+                             cf_name.c_str(), num_files);
           }
         }
       }
@@ -454,22 +333,23 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
   }
 
   if (c == nullptr) {
-    if ((c = PickDeleteTriggeredCompaction()) != nullptr) {
-      ROCKS_LOG_BUFFER(log_buffer_,
+    if ((c = PickDeleteTriggeredCompaction(cf_name, mutable_cf_options,
+                                           vstorage, score, sorted_runs,
+                                           log_buffer)) != nullptr) {
+      ROCKS_LOG_BUFFER(log_buffer,
                        "[%s] Universal: delete triggered compaction\n",
-                       cf_name_.c_str());
+                       cf_name.c_str());
     }
   }
 
   if (c == nullptr) {
-    TEST_SYNC_POINT_CALLBACK(
-        "UniversalCompactionBuilder::PickCompaction:Return", nullptr);
+    TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
+                             nullptr);
     return nullptr;
   }
 
-  if (mutable_cf_options_.compaction_options_universal.allow_trivial_move ==
-          true &&
-      c->compaction_reason() != CompactionReason::kPeriodicCompaction) {
+  if (mutable_cf_options.compaction_options_universal.allow_trivial_move ==
+      true) {
     c->set_is_trivial_move(IsInputFilesNonOverlapping(c));
   }
 
@@ -514,15 +394,15 @@ Compaction* UniversalCompactionBuilder::PickCompaction() {
   RecordInHistogram(ioptions_.statistics, NUM_FILES_IN_SINGLE_COMPACTION,
                     c->inputs(0)->size());
 
-  picker_->RegisterCompaction(c);
-  vstorage_->ComputeCompactionScore(ioptions_, mutable_cf_options_);
+  RegisterCompaction(c);
+  vstorage->ComputeCompactionScore(ioptions_, mutable_cf_options);
 
-  TEST_SYNC_POINT_CALLBACK("UniversalCompactionBuilder::PickCompaction:Return",
+  TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
                            c);
   return c;
 }
 
-uint32_t UniversalCompactionBuilder::GetPathId(
+uint32_t UniversalCompactionPicker::GetPathId(
     const ImmutableCFOptions& ioptions,
     const MutableCFOptions& mutable_cf_options, uint64_t file_size) {
   // Two conditions need to be satisfied:
@@ -560,12 +440,15 @@ uint32_t UniversalCompactionBuilder::GetPathId(
 // Consider compaction files based on their size differences with
 // the next file in time order.
 //
-Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
-    unsigned int ratio, unsigned int max_number_of_files_to_compact) {
+Compaction* UniversalCompactionPicker::PickCompactionToReduceSortedRuns(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, double score, unsigned int ratio,
+    unsigned int max_number_of_files_to_compact,
+    const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
   unsigned int min_merge_width =
-      mutable_cf_options_.compaction_options_universal.min_merge_width;
+      mutable_cf_options.compaction_options_universal.min_merge_width;
   unsigned int max_merge_width =
-      mutable_cf_options_.compaction_options_universal.max_merge_width;
+      mutable_cf_options.compaction_options_universal.max_merge_width;
 
   const SortedRun* sr = nullptr;
   bool done = false;
@@ -579,16 +462,16 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
   // Caller checks the size before executing this function. This invariant is
   // important because otherwise we may have a possible integer underflow when
   // dealing with unsigned types.
-  assert(sorted_runs_.size() > 0);
+  assert(sorted_runs.size() > 0);
 
   // Considers a candidate file only if it is smaller than the
   // total size accumulated so far.
-  for (size_t loop = 0; loop < sorted_runs_.size(); loop++) {
+  for (size_t loop = 0; loop < sorted_runs.size(); loop++) {
     candidate_count = 0;
 
     // Skip files that are already being compacted
-    for (sr = nullptr; loop < sorted_runs_.size(); loop++) {
-      sr = &sorted_runs_[loop];
+    for (sr = nullptr; loop < sorted_runs.size(); loop++) {
+      sr = &sorted_runs[loop];
 
       if (!sr->being_compacted) {
         candidate_count = 1;
@@ -596,10 +479,10 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
       }
       char file_num_buf[kFormatFileNumberBufSize];
       sr->Dump(file_num_buf, sizeof(file_num_buf));
-      ROCKS_LOG_BUFFER(log_buffer_,
+      ROCKS_LOG_BUFFER(log_buffer,
                        "[%s] Universal: %s"
                        "[%d] being compacted, skipping",
-                       cf_name_.c_str(), file_num_buf, loop);
+                       cf_name.c_str(), file_num_buf, loop);
 
       sr = nullptr;
     }
@@ -610,16 +493,15 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
     if (sr != nullptr) {
       char file_num_buf[kFormatFileNumberBufSize];
       sr->Dump(file_num_buf, sizeof(file_num_buf), true);
-      ROCKS_LOG_BUFFER(log_buffer_,
-                       "[%s] Universal: Possible candidate %s[%d].",
-                       cf_name_.c_str(), file_num_buf, loop);
+      ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: Possible candidate %s[%d].",
+                       cf_name.c_str(), file_num_buf, loop);
     }
 
     // Check if the succeeding files need compaction.
     for (size_t i = loop + 1;
-         candidate_count < max_files_to_compact && i < sorted_runs_.size();
+         candidate_count < max_files_to_compact && i < sorted_runs.size();
          i++) {
-      const SortedRun* succeeding_sr = &sorted_runs_[i];
+      const SortedRun* succeeding_sr = &sorted_runs[i];
       if (succeeding_sr->being_compacted) {
         break;
       }
@@ -633,7 +515,7 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
       if (sz < static_cast<double>(succeeding_sr->size)) {
         break;
       }
-      if (mutable_cf_options_.compaction_options_universal.stop_style ==
+      if (mutable_cf_options.compaction_options_universal.stop_style ==
           kCompactionStopStyleSimilarSize) {
         // Similar-size stopping rule: also check the last picked file isn't
         // far larger than the next candidate file.
@@ -659,12 +541,12 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
       break;
     } else {
       for (size_t i = loop;
-           i < loop + candidate_count && i < sorted_runs_.size(); i++) {
-        const SortedRun* skipping_sr = &sorted_runs_[i];
+           i < loop + candidate_count && i < sorted_runs.size(); i++) {
+        const SortedRun* skipping_sr = &sorted_runs[i];
         char file_num_buf[256];
         skipping_sr->DumpSizeInfo(file_num_buf, sizeof(file_num_buf), loop);
-        ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: Skipping %s",
-                         cf_name_.c_str(), file_num_buf);
+        ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: Skipping %s",
+                         cf_name.c_str(), file_num_buf);
       }
     }
   }
@@ -676,16 +558,16 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
   // size ratio of compression.
   bool enable_compression = true;
   int ratio_to_compress =
-      mutable_cf_options_.compaction_options_universal.compression_size_percent;
+      mutable_cf_options.compaction_options_universal.compression_size_percent;
   if (ratio_to_compress >= 0) {
     uint64_t total_size = 0;
-    for (auto& sorted_run : sorted_runs_) {
+    for (auto& sorted_run : sorted_runs) {
       total_size += sorted_run.compensated_file_size;
     }
 
     uint64_t older_file_size = 0;
-    for (size_t i = sorted_runs_.size() - 1; i >= first_index_after; i--) {
-      older_file_size += sorted_runs_[i].size;
+    for (size_t i = sorted_runs.size() - 1; i >= first_index_after; i--) {
+      older_file_size += sorted_runs[i].size;
       if (older_file_size * 100L >= total_size * (long)ratio_to_compress) {
         enable_compression = false;
         break;
@@ -695,46 +577,46 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
 
   uint64_t estimated_total_size = 0;
   for (unsigned int i = 0; i < first_index_after; i++) {
-    estimated_total_size += sorted_runs_[i].size;
+    estimated_total_size += sorted_runs[i].size;
   }
   uint32_t path_id =
-      GetPathId(ioptions_, mutable_cf_options_, estimated_total_size);
-  int start_level = sorted_runs_[start_index].level;
+      GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
+  int start_level = sorted_runs[start_index].level;
   int output_level;
-  if (first_index_after == sorted_runs_.size()) {
-    output_level = vstorage_->num_levels() - 1;
-  } else if (sorted_runs_[first_index_after].level == 0) {
+  if (first_index_after == sorted_runs.size()) {
+    output_level = vstorage->num_levels() - 1;
+  } else if (sorted_runs[first_index_after].level == 0) {
     output_level = 0;
   } else {
-    output_level = sorted_runs_[first_index_after].level - 1;
+    output_level = sorted_runs[first_index_after].level - 1;
   }
 
   // last level is reserved for the files ingested behind
   if (ioptions_.allow_ingest_behind &&
-      (output_level == vstorage_->num_levels() - 1)) {
+      (output_level == vstorage->num_levels() - 1)) {
     assert(output_level > 1);
     output_level--;
   }
 
-  std::vector<CompactionInputFiles> inputs(vstorage_->num_levels());
+  std::vector<CompactionInputFiles> inputs(vstorage->num_levels());
   for (size_t i = 0; i < inputs.size(); ++i) {
     inputs[i].level = start_level + static_cast<int>(i);
   }
   for (size_t i = start_index; i < first_index_after; i++) {
-    auto& picking_sr = sorted_runs_[i];
+    auto& picking_sr = sorted_runs[i];
     if (picking_sr.level == 0) {
       FileMetaData* picking_file = picking_sr.file;
       inputs[0].files.push_back(picking_file);
     } else {
       auto& files = inputs[picking_sr.level - start_level].files;
-      for (auto* f : vstorage_->LevelFiles(picking_sr.level)) {
+      for (auto* f : vstorage->LevelFiles(picking_sr.level)) {
         files.push_back(f);
       }
     }
     char file_num_buf[256];
     picking_sr.DumpSizeInfo(file_num_buf, sizeof(file_num_buf), i);
-    ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: Picking %s",
-                     cf_name_.c_str(), file_num_buf);
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: Picking %s", cf_name.c_str(),
+                     file_num_buf);
   }
 
   CompactionReason compaction_reason;
@@ -744,17 +626,16 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
     compaction_reason = CompactionReason::kUniversalSortedRunNum;
   }
   return new Compaction(
-      vstorage_, ioptions_, mutable_cf_options_, std::move(inputs),
-      output_level,
-      MaxFileSizeForLevel(mutable_cf_options_, output_level,
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
+      MaxFileSizeForLevel(mutable_cf_options, output_level,
                           kCompactionStyleUniversal),
       LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_, start_level,
+      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);
+      score, false /* deletion_compaction */, compaction_reason);
 }
 
 // Look at overall size amplification. If size amplification
@@ -763,9 +644,12 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSortedRuns(
 // base file (overrides configured values of file-size ratios,
 // min_merge_width and max_merge_width).
 //
-Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
+Compaction* UniversalCompactionPicker::PickCompactionToReduceSizeAmp(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, double score,
+    const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
   // percentage flexibility while reducing size amplification
-  uint64_t ratio = mutable_cf_options_.compaction_options_universal
+  uint64_t ratio = mutable_cf_options.compaction_options_universal
                        .max_size_amplification_percent;
 
   unsigned int candidate_count = 0;
@@ -773,23 +657,21 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
   size_t start_index = 0;
   const SortedRun* sr = nullptr;
 
-  assert(!sorted_runs_.empty());
-  if (sorted_runs_.back().being_compacted) {
+  if (sorted_runs.back().being_compacted) {
     return nullptr;
   }
 
   // Skip files that are already being compacted
-  for (size_t loop = 0; loop < sorted_runs_.size() - 1; loop++) {
-    sr = &sorted_runs_[loop];
+  for (size_t loop = 0; loop < sorted_runs.size() - 1; loop++) {
+    sr = &sorted_runs[loop];
     if (!sr->being_compacted) {
       start_index = loop;  // Consider this as the first candidate.
       break;
     }
     char file_num_buf[kFormatFileNumberBufSize];
     sr->Dump(file_num_buf, sizeof(file_num_buf), true);
-    ROCKS_LOG_BUFFER(log_buffer_,
-                     "[%s] Universal: skipping %s[%d] compacted %s",
-                     cf_name_.c_str(), file_num_buf, loop,
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: skipping %s[%d] compacted %s",
+                     cf_name.c_str(), file_num_buf, loop,
                      " cannot be a candidate to reduce size amp.\n");
     sr = nullptr;
   }
@@ -801,20 +683,20 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
     char file_num_buf[kFormatFileNumberBufSize];
     sr->Dump(file_num_buf, sizeof(file_num_buf), true);
     ROCKS_LOG_BUFFER(
-        log_buffer_,
+        log_buffer,
         "[%s] Universal: First candidate %s[%" ROCKSDB_PRIszt "] %s",
-        cf_name_.c_str(), file_num_buf, start_index, " to reduce size amp.\n");
+        cf_name.c_str(), file_num_buf, start_index, " to reduce size amp.\n");
   }
 
   // keep adding up all the remaining files
-  for (size_t loop = start_index; loop < sorted_runs_.size() - 1; loop++) {
-    sr = &sorted_runs_[loop];
+  for (size_t loop = start_index; loop < sorted_runs.size() - 1; loop++) {
+    sr = &sorted_runs[loop];
     if (sr->being_compacted) {
       char file_num_buf[kFormatFileNumberBufSize];
       sr->Dump(file_num_buf, sizeof(file_num_buf), true);
       ROCKS_LOG_BUFFER(
-          log_buffer_, "[%s] Universal: Possible candidate %s[%d] %s",
-          cf_name_.c_str(), file_num_buf, start_index,
+          log_buffer, "[%s] Universal: Possible candidate %s[%d] %s",
+          cf_name.c_str(), file_num_buf, start_index,
           " is already being compacted. No size amp reduction possible.\n");
       return nullptr;
     }
@@ -826,35 +708,88 @@ Compaction* UniversalCompactionBuilder::PickCompactionToReduceSizeAmp() {
   }
 
   // size of earliest file
-  uint64_t earliest_file_size = sorted_runs_.back().size;
+  uint64_t earliest_file_size = sorted_runs.back().size;
 
   // size amplification = percentage of additional size
   if (candidate_size * 100 < ratio * earliest_file_size) {
     ROCKS_LOG_BUFFER(
-        log_buffer_,
+        log_buffer,
         "[%s] Universal: size amp not needed. newer-files-total-size %" PRIu64
         " earliest-file-size %" PRIu64,
-        cf_name_.c_str(), candidate_size, earliest_file_size);
+        cf_name.c_str(), candidate_size, earliest_file_size);
     return nullptr;
   } else {
     ROCKS_LOG_BUFFER(
-        log_buffer_,
+        log_buffer,
         "[%s] Universal: size amp needed. newer-files-total-size %" PRIu64
         " earliest-file-size %" PRIu64,
-        cf_name_.c_str(), candidate_size, earliest_file_size);
+        cf_name.c_str(), candidate_size, earliest_file_size);
   }
-  return PickCompactionToOldest(start_index,
-                                CompactionReason::kUniversalSizeAmplification);
+  assert(start_index < sorted_runs.size() - 1);
+
+  // Estimate total file size
+  uint64_t estimated_total_size = 0;
+  for (size_t loop = start_index; loop < sorted_runs.size(); loop++) {
+    estimated_total_size += sorted_runs[loop].size;
+  }
+  uint32_t path_id =
+      GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
+  int start_level = sorted_runs[start_index].level;
+
+  std::vector<CompactionInputFiles> inputs(vstorage->num_levels());
+  for (size_t i = 0; i < inputs.size(); ++i) {
+    inputs[i].level = start_level + static_cast<int>(i);
+  }
+  // We always compact all the files, so always compress.
+  for (size_t loop = start_index; loop < sorted_runs.size(); loop++) {
+    auto& picking_sr = sorted_runs[loop];
+    if (picking_sr.level == 0) {
+      FileMetaData* f = picking_sr.file;
+      inputs[0].files.push_back(f);
+    } else {
+      auto& files = inputs[picking_sr.level - start_level].files;
+      for (auto* f : vstorage->LevelFiles(picking_sr.level)) {
+        files.push_back(f);
+      }
+    }
+    char file_num_buf[256];
+    picking_sr.DumpSizeInfo(file_num_buf, sizeof(file_num_buf), loop);
+    ROCKS_LOG_BUFFER(log_buffer, "[%s] Universal: size amp picking %s",
+                     cf_name.c_str(), file_num_buf);
+  }
+
+  // output files at the bottom most level, unless it's reserved
+  int output_level = vstorage->num_levels() - 1;
+  // last level is reserved for the files ingested behind
+  if (ioptions_.allow_ingest_behind) {
+    assert(output_level > 1);
+    output_level--;
+  }
+
+  return new Compaction(
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
+      MaxFileSizeForLevel(mutable_cf_options, output_level,
+                          kCompactionStyleUniversal),
+      /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
+      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
+                         1),
+      GetCompressionOptions(ioptions_, vstorage, output_level),
+      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
+      score, false /* deletion_compaction */,
+      CompactionReason::kUniversalSizeAmplification);
 }
 
 // Pick files marked for compaction. Typically, files are marked by
 // CompactOnDeleteCollector due to the presence of tombstones.
-Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
+Compaction* UniversalCompactionPicker::PickDeleteTriggeredCompaction(
+    const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+    VersionStorageInfo* vstorage, double score,
+    const std::vector<SortedRun>& /*sorted_runs*/, LogBuffer* /*log_buffer*/) {
   CompactionInputFiles start_level_inputs;
   int output_level;
   std::vector<CompactionInputFiles> inputs;
 
-  if (vstorage_->num_levels() == 1) {
+  if (vstorage->num_levels() == 1) {
     // This is single level universal. Since we're basically trying to reclaim
     // space by processing files marked for compaction due to high tombstone
     // density, let's do the same thing as compaction to reduce size amp which
@@ -864,7 +799,7 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
     start_level_inputs.level = 0;
     start_level_inputs.files.clear();
     output_level = 0;
-    for (FileMetaData* f : vstorage_->LevelFiles(0)) {
+    for (FileMetaData* f : vstorage->LevelFiles(0)) {
       if (f->marked_for_compaction) {
         compact = true;
       }
@@ -883,24 +818,24 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
     // For multi-level universal, the strategy is to make this look more like
     // leveled. We pick one of the files marked for compaction and compact with
     // overlapping files in the adjacent level.
-    picker_->PickFilesMarkedForCompaction(cf_name_, vstorage_, &start_level,
-                                          &output_level, &start_level_inputs);
+    PickFilesMarkedForCompaction(cf_name, vstorage, &start_level, &output_level,
+                                 &start_level_inputs);
     if (start_level_inputs.empty()) {
       return nullptr;
     }
 
     // Pick the first non-empty level after the start_level
-    for (output_level = start_level + 1; output_level < vstorage_->num_levels();
+    for (output_level = start_level + 1; output_level < vstorage->num_levels();
          output_level++) {
-      if (vstorage_->NumLevelFiles(output_level) != 0) {
+      if (vstorage->NumLevelFiles(output_level) != 0) {
         break;
       }
     }
 
     // If all higher levels are empty, pick the highest level as output level
-    if (output_level == vstorage_->num_levels()) {
+    if (output_level == vstorage->num_levels()) {
       if (start_level == 0) {
-        output_level = vstorage_->num_levels() - 1;
+        output_level = vstorage->num_levels() - 1;
       } else {
         // If start level is non-zero and all higher levels are empty, this
         // compaction will translate into a trivial move. Since the idea is
@@ -910,15 +845,15 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
       }
     }
     if (ioptions_.allow_ingest_behind &&
-        output_level == vstorage_->num_levels() - 1) {
+        output_level == vstorage->num_levels() - 1) {
       assert(output_level > 1);
       output_level--;
     }
 
     if (output_level != 0) {
       if (start_level == 0) {
-        if (!picker_->GetOverlappingL0Files(vstorage_, &start_level_inputs,
-                                            output_level, nullptr)) {
+        if (!GetOverlappingL0Files(vstorage, &start_level_inputs, output_level,
+                                   nullptr)) {
           return nullptr;
         }
       }
@@ -927,16 +862,16 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
       int parent_index = -1;
 
       output_level_inputs.level = output_level;
-      if (!picker_->SetupOtherInputs(cf_name_, mutable_cf_options_, vstorage_,
-                                     &start_level_inputs, &output_level_inputs,
-                                     &parent_index, -1)) {
+      if (!SetupOtherInputs(cf_name, mutable_cf_options, vstorage,
+                            &start_level_inputs, &output_level_inputs,
+                            &parent_index, -1)) {
         return nullptr;
       }
       inputs.push_back(start_level_inputs);
       if (!output_level_inputs.empty()) {
         inputs.push_back(output_level_inputs);
       }
-      if (picker_->FilesRangeOverlapWithCompaction(inputs, output_level)) {
+      if (FilesRangeOverlapWithCompaction(inputs, output_level)) {
         return nullptr;
       }
     } else {
@@ -946,160 +881,23 @@ Compaction* UniversalCompactionBuilder::PickDeleteTriggeredCompaction() {
 
   uint64_t estimated_total_size = 0;
   // Use size of the output level as estimated file size
-  for (FileMetaData* f : vstorage_->LevelFiles(output_level)) {
+  for (FileMetaData* f : vstorage->LevelFiles(output_level)) {
     estimated_total_size += f->fd.GetFileSize();
   }
   uint32_t path_id =
-      GetPathId(ioptions_, mutable_cf_options_, estimated_total_size);
+      GetPathId(ioptions_, mutable_cf_options, estimated_total_size);
   return new Compaction(
-      vstorage_, ioptions_, mutable_cf_options_, std::move(inputs),
-      output_level,
-      MaxFileSizeForLevel(mutable_cf_options_, output_level,
+      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
+      MaxFileSizeForLevel(mutable_cf_options, output_level,
                           kCompactionStyleUniversal),
       /* 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,
-      score_, false /* deletion_compaction */,
+      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
+                         1),
+      GetCompressionOptions(ioptions_, vstorage, output_level),
+      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ true,
+      score, false /* deletion_compaction */,
       CompactionReason::kFilesMarkedForCompaction);
 }
-
-Compaction* UniversalCompactionBuilder::PickCompactionToOldest(
-    size_t start_index, CompactionReason compaction_reason) {
-  assert(start_index < sorted_runs_.size());
-
-  // Estimate total file size
-  uint64_t estimated_total_size = 0;
-  for (size_t loop = start_index; loop < sorted_runs_.size(); loop++) {
-    estimated_total_size += sorted_runs_[loop].size;
-  }
-  uint32_t path_id =
-      GetPathId(ioptions_, mutable_cf_options_, estimated_total_size);
-  int start_level = sorted_runs_[start_index].level;
-
-  std::vector<CompactionInputFiles> inputs(vstorage_->num_levels());
-  for (size_t i = 0; i < inputs.size(); ++i) {
-    inputs[i].level = start_level + static_cast<int>(i);
-  }
-  for (size_t loop = start_index; loop < sorted_runs_.size(); loop++) {
-    auto& picking_sr = sorted_runs_[loop];
-    if (picking_sr.level == 0) {
-      FileMetaData* f = picking_sr.file;
-      inputs[0].files.push_back(f);
-    } else {
-      auto& files = inputs[picking_sr.level - start_level].files;
-      for (auto* f : vstorage_->LevelFiles(picking_sr.level)) {
-        files.push_back(f);
-      }
-    }
-    std::string comp_reason_print_string;
-    if (compaction_reason == CompactionReason::kPeriodicCompaction) {
-      comp_reason_print_string = "periodic compaction";
-    } else if (compaction_reason ==
-               CompactionReason::kUniversalSizeAmplification) {
-      comp_reason_print_string = "size amp";
-    } else {
-      assert(false);
-    }
-
-    char file_num_buf[256];
-    picking_sr.DumpSizeInfo(file_num_buf, sizeof(file_num_buf), loop);
-    ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: %s picking %s",
-                     cf_name_.c_str(), comp_reason_print_string.c_str(),
-                     file_num_buf);
-  }
-
-  // output files at the bottom most level, unless it's reserved
-  int output_level = vstorage_->num_levels() - 1;
-  // last level is reserved for the files ingested behind
-  if (ioptions_.allow_ingest_behind) {
-    assert(output_level > 1);
-    output_level--;
-  }
-
-  // We never check size for
-  // compaction_options_universal.compression_size_percent,
-  // because we always compact all the files, so always compress.
-  return new Compaction(
-      vstorage_, ioptions_, mutable_cf_options_, std::move(inputs),
-      output_level,
-      MaxFileSizeForLevel(mutable_cf_options_, output_level,
-                          kCompactionStyleUniversal),
-      LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage_, mutable_cf_options_, start_level,
-                         1, true /* enable_compression */),
-      GetCompressionOptions(mutable_cf_options_, vstorage_, start_level,
-                            true /* enable_compression */),
-      /* max_subcompactions */ 0, /* grandparents */ {}, /* is manual */ false,
-      score_, false /* deletion_compaction */, compaction_reason);
-}
-
-Compaction* UniversalCompactionBuilder::PickPeriodicCompaction() {
-  ROCKS_LOG_BUFFER(log_buffer_, "[%s] Universal: Periodic Compaction",
-                   cf_name_.c_str());
-
-  // In universal compaction, sorted runs contain older data are almost always
-  // generated earlier too. To simplify the problem, we just try to trigger
-  // a full compaction. We start from the oldest sorted run and include
-  // all sorted runs, until we hit a sorted already being compacted.
-  // Since usually the largest (which is usually the oldest) sorted run is
-  // included anyway, doing a full compaction won't increase write
-  // amplification much.
-
-  // Get some information from marked files to check whether a file is
-  // included in the compaction.
-
-  size_t start_index = sorted_runs_.size();
-  while (start_index > 0 && !sorted_runs_[start_index - 1].being_compacted) {
-    start_index--;
-  }
-  if (start_index == sorted_runs_.size()) {
-    return nullptr;
-  }
-
-  // There is a rare corner case where we can't pick up all the files
-  // because some files are being compacted and we end up with picking files
-  // but none of them need periodic compaction. Unless we simply recompact
-  // the last sorted run (either the last level or last L0 file), we would just
-  // execute the compaction, in order to simplify  the logic.
-  if (start_index == sorted_runs_.size() - 1) {
-    bool included_file_marked = false;
-    int start_level = sorted_runs_[start_index].level;
-    FileMetaData* start_file = sorted_runs_[start_index].file;
-    for (const std::pair<int, FileMetaData*>& level_file_pair :
-         vstorage_->FilesMarkedForPeriodicCompaction()) {
-      if (start_level != 0) {
-        // Last sorted run is a level
-        if (start_level == level_file_pair.first) {
-          included_file_marked = true;
-          break;
-        }
-      } else {
-        // Last sorted run is a L0 file.
-        if (start_file == level_file_pair.second) {
-          included_file_marked = true;
-          break;
-        }
-      }
-    }
-    if (!included_file_marked) {
-      ROCKS_LOG_BUFFER(log_buffer_,
-                       "[%s] Universal: Cannot form a compaction covering file "
-                       "marked for periodic compaction",
-                       cf_name_.c_str());
-      return nullptr;
-    }
-  }
-
-  Compaction* c = PickCompactionToOldest(start_index,
-                                         CompactionReason::kPeriodicCompaction);
-
-  TEST_SYNC_POINT_CALLBACK(
-      "UniversalCompactionPicker::PickPeriodicCompaction:Return", c);
-
-  return c;
-}
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 #endif  // !ROCKSDB_LITE

db/compaction/compaction_picker_universal.h

@@ -12,20 +12,87 @@
 
 #include "db/compaction/compaction_picker.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 class UniversalCompactionPicker : public CompactionPicker {
  public:
   UniversalCompactionPicker(const ImmutableCFOptions& ioptions,
                             const InternalKeyComparator* icmp)
       : CompactionPicker(ioptions, icmp) {}
-  virtual Compaction* PickCompaction(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, LogBuffer* log_buffer,
-      SequenceNumber earliest_memtable_seqno = kMaxSequenceNumber) override;
+  virtual Compaction* PickCompaction(const std::string& cf_name,
+                                     const MutableCFOptions& mutable_cf_options,
+                                     VersionStorageInfo* vstorage,
+                                     LogBuffer* log_buffer) override;
+
   virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
 
   virtual bool NeedsCompaction(
       const VersionStorageInfo* vstorage) const override;
+
+ private:
+  struct SortedRun {
+    SortedRun(int _level, FileMetaData* _file, uint64_t _size,
+              uint64_t _compensated_file_size, bool _being_compacted)
+        : level(_level),
+          file(_file),
+          size(_size),
+          compensated_file_size(_compensated_file_size),
+          being_compacted(_being_compacted) {
+      assert(compensated_file_size > 0);
+      assert(level != 0 || file != nullptr);
+    }
+
+    void Dump(char* out_buf, size_t out_buf_size,
+              bool print_path = false) const;
+
+    // sorted_run_count is added into the string to print
+    void DumpSizeInfo(char* out_buf, size_t out_buf_size,
+                      size_t sorted_run_count) const;
+
+    int level;
+    // `file` Will be null for level > 0. For level = 0, the sorted run is
+    // for this file.
+    FileMetaData* file;
+    // For level > 0, `size` and `compensated_file_size` are sum of sizes all
+    // files in the level. `being_compacted` should be the same for all files
+    // in a non-zero level. Use the value here.
+    uint64_t size;
+    uint64_t compensated_file_size;
+    bool being_compacted;
+  };
+
+  // Pick Universal compaction to limit read amplification
+  Compaction* PickCompactionToReduceSortedRuns(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score, unsigned int ratio,
+      unsigned int num_files, const std::vector<SortedRun>& sorted_runs,
+      LogBuffer* log_buffer);
+
+  // Pick Universal compaction to limit space amplification.
+  Compaction* PickCompactionToReduceSizeAmp(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score,
+      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
+
+  Compaction* PickDeleteTriggeredCompaction(
+      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
+      VersionStorageInfo* vstorage, double score,
+      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
+
+  // Used in universal compaction when the enabled_trivial_move
+  // option is set. Checks whether there are any overlapping files
+  // in the input. Returns true if the input files are non
+  // overlapping.
+  bool IsInputFilesNonOverlapping(Compaction* c);
+
+  static std::vector<SortedRun> CalculateSortedRuns(
+      const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions,
+      const MutableCFOptions& mutable_cf_options);
+
+  // Pick a path ID to place a newly generated file, with its estimated file
+  // size.
+  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
+                            const MutableCFOptions& mutable_cf_options,
+                            uint64_t file_size);
 };
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 #endif  // !ROCKSDB_LITE

db/comparator_db_test.cc

@@ -18,10 +18,10 @@
 
 using std::unique_ptr;
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 namespace {
 
-static const Comparator* kTestComparator = nullptr;
+static const Comparator* comparator;
 
 class KVIter : public Iterator {
  public:
@@ -74,7 +74,7 @@ void AssertItersEqual(Iterator* iter1, Iterator* iter2) {
 void DoRandomIteraratorTest(DB* db, std::vector<std::string> source_strings,
                             Random* rnd, int num_writes, int num_iter_ops,
                             int num_trigger_flush) {
-  stl_wrappers::KVMap map((stl_wrappers::LessOfComparator(kTestComparator)));
+  stl_wrappers::KVMap map((stl_wrappers::LessOfComparator(comparator)));
 
   for (int i = 0; i < num_writes; i++) {
     if (num_trigger_flush > 0 && i != 0 && i % num_trigger_flush == 0) {
@@ -263,19 +263,19 @@ class ComparatorDBTest
 
  public:
   ComparatorDBTest() : env_(Env::Default()), db_(nullptr) {
-    kTestComparator = BytewiseComparator();
+    comparator = BytewiseComparator();
     dbname_ = test::PerThreadDBPath("comparator_db_test");
     BlockBasedTableOptions toptions;
     toptions.format_version = GetParam();
     last_options_.table_factory.reset(
-        ROCKSDB_NAMESPACE::NewBlockBasedTableFactory(toptions));
+        rocksdb::NewBlockBasedTableFactory(toptions));
     EXPECT_OK(DestroyDB(dbname_, last_options_));
   }
 
   ~ComparatorDBTest() override {
     delete db_;
     EXPECT_OK(DestroyDB(dbname_, last_options_));
-    kTestComparator = BytewiseComparator();
+    comparator = BytewiseComparator();
   }
 
   DB* GetDB() { return db_; }
@@ -286,7 +286,7 @@ class ComparatorDBTest
     } else {
       comparator_guard.reset();
     }
-    kTestComparator = cmp;
+    comparator = cmp;
     last_options_.comparator = cmp;
   }
 
@@ -334,7 +334,7 @@ TEST_P(ComparatorDBTest, SimpleSuffixReverseComparator) {
 
   for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
     Options* opt = GetOptions();
-    opt->comparator = kTestComparator;
+    opt->comparator = comparator;
     DestroyAndReopen();
     Random rnd(rnd_seed);
 
@@ -360,7 +360,7 @@ TEST_P(ComparatorDBTest, Uint64Comparator) {
 
   for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
     Options* opt = GetOptions();
-    opt->comparator = kTestComparator;
+    opt->comparator = comparator;
     DestroyAndReopen();
     Random rnd(rnd_seed);
     Random64 rnd64(rnd_seed);
@@ -384,7 +384,7 @@ TEST_P(ComparatorDBTest, DoubleComparator) {
 
   for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
     Options* opt = GetOptions();
-    opt->comparator = kTestComparator;
+    opt->comparator = comparator;
     DestroyAndReopen();
     Random rnd(rnd_seed);
 
@@ -409,7 +409,7 @@ TEST_P(ComparatorDBTest, HashComparator) {
 
   for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
     Options* opt = GetOptions();
-    opt->comparator = kTestComparator;
+    opt->comparator = comparator;
     DestroyAndReopen();
     Random rnd(rnd_seed);
 
@@ -428,7 +428,7 @@ TEST_P(ComparatorDBTest, TwoStrComparator) {
 
   for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
     Options* opt = GetOptions();
-    opt->comparator = kTestComparator;
+    opt->comparator = comparator;
     DestroyAndReopen();
     Random rnd(rnd_seed);
 
@@ -652,7 +652,7 @@ TEST_P(ComparatorDBTest, SeparatorSuccessorRandomizeTest) {
   }
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

db/convenience.cc

@@ -11,10 +11,10 @@
 #include "db/db_impl/db_impl.h"
 #include "util/cast_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 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);
 }
 
@@ -41,16 +41,14 @@ Status VerifySstFileChecksum(const Options& options,
                              const EnvOptions& env_options,
                              const ReadOptions& read_options,
                              const std::string& file_path) {
-  std::unique_ptr<FSRandomAccessFile> file;
+  std::unique_ptr<RandomAccessFile> file;
   uint64_t file_size;
   InternalKeyComparator internal_comparator(options.comparator);
   ImmutableCFOptions ioptions(options);
 
-  Status s = ioptions.fs->NewRandomAccessFile(file_path,
-                                              FileOptions(env_options),
-                                              &file, nullptr);
+  Status s = ioptions.env->NewRandomAccessFile(file_path, &file, env_options);
   if (s.ok()) {
-    s = ioptions.fs->GetFileSize(file_path, IOOptions(), &file_size, nullptr);
+    s = ioptions.env->GetFileSize(file_path, &file_size);
   } else {
     return s;
   }
@@ -72,6 +70,6 @@ Status VerifySstFileChecksum(const Options& options,
   return s;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 #endif  // ROCKSDB_LITE

db/corruption_test.cc

@@ -20,7 +20,6 @@
 #include "db/db_test_util.h"
 #include "db/log_format.h"
 #include "db/version_set.h"
-#include "env/composite_env_wrapper.h"
 #include "file/filename.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/convenience.h"
@@ -33,7 +32,7 @@
 #include "test_util/testutil.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 static const int kValueSize = 1000;
 
@@ -98,7 +97,7 @@ class CorruptionTest : public testing::Test {
   void RepairDB() {
     delete db_;
     db_ = nullptr;
-    ASSERT_OK(::ROCKSDB_NAMESPACE::RepairDB(dbname_, options_));
+    ASSERT_OK(::rocksdb::RepairDB(dbname_, options_));
   }
 
   void Build(int n, int flush_every = 0) {
@@ -392,16 +391,12 @@ TEST_F(CorruptionTest, TableFileIndexData) {
 
   // corrupt an index block of an entire file
   Corrupt(kTableFile, -2000, 500);
-  options.paranoid_checks = false;
-  Reopen(&options);
+  Reopen();
   dbi = reinterpret_cast<DBImpl*>(db_);
   // one full file may be readable, since only one was corrupted
   // the other file should be fully non-readable, since index was corrupted
   Check(0, 5000);
   ASSERT_NOK(dbi->VerifyChecksum());
-
-  // In paranoid mode, the db cannot be opened due to the corrupted file.
-  ASSERT_TRUE(TryReopen().IsCorruption());
 }
 
 TEST_F(CorruptionTest, MissingDescriptor) {
@@ -544,8 +539,7 @@ TEST_F(CorruptionTest, RangeDeletionCorrupted) {
   std::unique_ptr<RandomAccessFile> file;
   ASSERT_OK(options_.env->NewRandomAccessFile(filename, &file, EnvOptions()));
   std::unique_ptr<RandomAccessFileReader> file_reader(
-      new RandomAccessFileReader(NewLegacyRandomAccessFileWrapper(file),
-                                 filename));
+      new RandomAccessFileReader(std::move(file), filename));
 
   uint64_t file_size;
   ASSERT_OK(options_.env->GetFileSize(filename, &file_size));
@@ -557,7 +551,13 @@ TEST_F(CorruptionTest, RangeDeletionCorrupted) {
 
   ASSERT_OK(TryReopen());
   CorruptFile(filename, static_cast<int>(range_del_handle.offset()), 1);
-  ASSERT_TRUE(TryReopen().IsCorruption());
+  // The test case does not fail on TryReopen because failure to preload table
+  // handlers is not considered critical.
+  ASSERT_OK(TryReopen());
+  std::string val;
+  // However, it does fail on any read involving that file since that file
+  // cannot be opened with a corrupt range deletion meta-block.
+  ASSERT_TRUE(db_->Get(ReadOptions(), "a", &val).IsCorruption());
 }
 
 TEST_F(CorruptionTest, FileSystemStateCorrupted) {
@@ -582,19 +582,18 @@ TEST_F(CorruptionTest, FileSystemStateCorrupted) {
       env_.NewWritableFile(filename, &file, EnvOptions());
       file->Append(Slice("corrupted sst"));
       file.reset();
-      Status x = TryReopen(&options);
-      ASSERT_TRUE(x.IsCorruption());
     } else {  // delete the file
       env_.DeleteFile(filename);
-      Status x = TryReopen(&options);
-      ASSERT_TRUE(x.IsPathNotFound());
     }
 
+    Status x = TryReopen(&options);
+    ASSERT_TRUE(x.IsCorruption());
     DestroyDB(dbname_, options_);
+    Reopen(&options);
   }
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
   ::testing::InitGoogleTest(&argc, argv);

db/cuckoo_table_db_test.cc

@@ -15,7 +15,7 @@
 #include "test_util/testutil.h"
 #include "util/string_util.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class CuckooTableDBTest : public testing::Test {
  private:
@@ -285,9 +285,6 @@ TEST_F(CuckooTableDBTest, SameKeyInsertedInTwoDifferentFilesAndCompacted) {
 TEST_F(CuckooTableDBTest, AdaptiveTable) {
   Options options = CurrentOptions();
 
-  // Ensure options compatible with PlainTable
-  options.prefix_extractor.reset(NewCappedPrefixTransform(8));
-
   // Write some keys using cuckoo table.
   options.table_factory.reset(NewCuckooTableFactory());
   Reopen(&options);
@@ -298,25 +295,17 @@ TEST_F(CuckooTableDBTest, AdaptiveTable) {
   dbfull()->TEST_FlushMemTable();
 
   // Write some keys using plain table.
-  std::shared_ptr<TableFactory> block_based_factory(
-      NewBlockBasedTableFactory());
-  std::shared_ptr<TableFactory> plain_table_factory(
-      NewPlainTableFactory());
-  std::shared_ptr<TableFactory> cuckoo_table_factory(
-      NewCuckooTableFactory());
   options.create_if_missing = false;
-  options.table_factory.reset(NewAdaptiveTableFactory(
-    plain_table_factory, block_based_factory, plain_table_factory,
-    cuckoo_table_factory));
+  options.table_factory.reset(NewPlainTableFactory());
   Reopen(&options);
   ASSERT_OK(Put("key4", "v4"));
   ASSERT_OK(Put("key1", "v5"));
   dbfull()->TEST_FlushMemTable();
 
   // Write some keys using block based table.
-  options.table_factory.reset(NewAdaptiveTableFactory(
-    block_based_factory, block_based_factory, plain_table_factory,
-    cuckoo_table_factory));
+  std::shared_ptr<TableFactory> block_based_factory(
+      NewBlockBasedTableFactory());
+  options.table_factory.reset(NewAdaptiveTableFactory(block_based_factory));
   Reopen(&options);
   ASSERT_OK(Put("key5", "v6"));
   ASSERT_OK(Put("key2", "v7"));
@@ -328,13 +317,14 @@ TEST_F(CuckooTableDBTest, AdaptiveTable) {
   ASSERT_EQ("v4", Get("key4"));
   ASSERT_EQ("v6", Get("key5"));
 }
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  if (ROCKSDB_NAMESPACE::port::kLittleEndian) {
+  if (rocksdb::port::kLittleEndian) {
     ::testing::InitGoogleTest(&argc, argv);
     return RUN_ALL_TESTS();
-  } else {
+  }
+  else {
     fprintf(stderr, "SKIPPED as Cuckoo table doesn't support Big Endian\n");
     return 0;
   }

db/db_blob_index_test.cc

@@ -12,7 +12,6 @@
 #include <utility>
 #include <vector>
 
-#include "db/arena_wrapped_db_iter.h"
 #include "db/column_family.h"
 #include "db/db_iter.h"
 #include "db/db_test_util.h"
@@ -23,7 +22,7 @@
 #include "util/string_util.h"
 #include "utilities/merge_operators.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 // kTypeBlobIndex is a value type used by BlobDB only. The base rocksdb
 // should accept the value type on write, and report not supported value
@@ -398,39 +397,16 @@ TEST_F(DBBlobIndexTest, Iterate) {
     verify(15, Status::kOk, get_value(16, 0), get_value(14, 0),
            create_blob_iterator, check_is_blob(false));
 
-#ifndef ROCKSDB_LITE
-    // Iterator with blob support and using seek.
-    ASSERT_OK(dbfull()->SetOptions(
-        cfh(), {{"max_sequential_skip_in_iterations", "0"}}));
-    verify(1, Status::kOk, get_value(1, 0), get_value(1, 0),
-           create_blob_iterator, check_is_blob(true));
-    verify(3, Status::kOk, get_value(3, 0), get_value(3, 0),
-           create_blob_iterator, check_is_blob(true));
-    verify(5, Status::kOk, get_value(5, 0), get_value(5, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(7, Status::kOk, get_value(8, 0), get_value(6, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(9, Status::kOk, get_value(10, 0), get_value(8, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(11, Status::kNotSupported, "", "", create_blob_iterator);
-    verify(13, Status::kOk,
-           get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
-           get_value(13, 2) + "," + get_value(13, 1) + "," + get_value(13, 0),
-           create_blob_iterator, check_is_blob(false));
-    verify(15, Status::kOk, get_value(16, 0), get_value(14, 0),
-           create_blob_iterator, check_is_blob(false));
-#endif  // !ROCKSDB_LITE
-
     for (auto* snapshot : snapshots) {
       dbfull()->ReleaseSnapshot(snapshot);
     }
   }
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  rocksdb::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }

db/db_block_cache_test.cc

@@ -10,9 +10,8 @@
 #include "cache/lru_cache.h"
 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
-#include "util/compression.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class DBBlockCacheTest : public DBTestBase {
  private:
@@ -46,7 +45,7 @@ class DBBlockCacheTest : public DBTestBase {
     options.create_if_missing = true;
     options.avoid_flush_during_recovery = false;
     // options.compression = kNoCompression;
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.statistics = rocksdb::CreateDBStatistics();
     options.table_factory.reset(new BlockBasedTableFactory(table_options));
     return options;
   }
@@ -292,7 +291,7 @@ TEST_F(DBBlockCacheTest, TestWithCompressedBlockCache) {
 TEST_F(DBBlockCacheTest, IndexAndFilterBlocksOfNewTableAddedToCache) {
   Options options = CurrentOptions();
   options.create_if_missing = true;
-  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  options.statistics = rocksdb::CreateDBStatistics();
   BlockBasedTableOptions table_options;
   table_options.cache_index_and_filter_blocks = true;
   table_options.filter_policy.reset(NewBloomFilterPolicy(20));
@@ -378,16 +377,11 @@ TEST_F(DBBlockCacheTest, FillCacheAndIterateDB) {
 TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
   Options options = CurrentOptions();
   options.create_if_missing = true;
-  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  options.statistics = rocksdb::CreateDBStatistics();
   BlockBasedTableOptions table_options;
   table_options.cache_index_and_filter_blocks = true;
-  LRUCacheOptions co;
   // 500 bytes are enough to hold the first two blocks
-  co.capacity = 500;
-  co.num_shard_bits = 0;
-  co.strict_capacity_limit = false;
-  co.metadata_charge_policy = kDontChargeCacheMetadata;
-  std::shared_ptr<Cache> cache = NewLRUCache(co);
+  std::shared_ptr<Cache> cache = NewLRUCache(500, 0, false);
   table_options.block_cache = cache;
   table_options.filter_policy.reset(NewBloomFilterPolicy(20, true));
   options.table_factory.reset(new BlockBasedTableFactory(table_options));
@@ -464,7 +458,7 @@ TEST_F(DBBlockCacheTest, IndexAndFilterBlocksCachePriority) {
   for (auto priority : {Cache::Priority::LOW, Cache::Priority::HIGH}) {
     Options options = CurrentOptions();
     options.create_if_missing = true;
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.statistics = rocksdb::CreateDBStatistics();
     BlockBasedTableOptions table_options;
     table_options.cache_index_and_filter_blocks = true;
     table_options.block_cache.reset(new MockCache());
@@ -517,143 +511,10 @@ 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;
-  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  options.statistics = rocksdb::CreateDBStatistics();
   options.level0_file_num_compaction_trigger = 2;
   options.paranoid_file_checks = true;
   BlockBasedTableOptions table_options;
@@ -709,7 +570,7 @@ TEST_F(DBBlockCacheTest, CompressedCache) {
   for (int iter = 0; iter < 4; iter++) {
     Options options = CurrentOptions();
     options.write_buffer_size = 64 * 1024;  // small write buffer
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.statistics = rocksdb::CreateDBStatistics();
 
     BlockBasedTableOptions table_options;
     switch (iter) {
@@ -819,18 +680,16 @@ TEST_F(DBBlockCacheTest, CacheCompressionDict) {
 
   // Try all the available libraries that support dictionary compression
   std::vector<CompressionType> compression_types;
-  if (Zlib_Supported()) {
-    compression_types.push_back(kZlibCompression);
-  }
-  if (LZ4_Supported()) {
-    compression_types.push_back(kLZ4Compression);
-    compression_types.push_back(kLZ4HCCompression);
-  }
-  if (ZSTD_Supported()) {
-    compression_types.push_back(kZSTD);
-  } else if (ZSTDNotFinal_Supported()) {
-    compression_types.push_back(kZSTDNotFinalCompression);
-  }
+#ifdef ZLIB
+  compression_types.push_back(kZlibCompression);
+#endif  // ZLIB
+#if LZ4_VERSION_NUMBER >= 10400
+  compression_types.push_back(kLZ4Compression);
+  compression_types.push_back(kLZ4HCCompression);
+#endif  // LZ4_VERSION_NUMBER >= 10400
+#if ZSTD_VERSION_NUMBER >= 500
+  compression_types.push_back(kZSTD);
+#endif  // ZSTD_VERSION_NUMBER >= 500
   Random rnd(301);
   for (auto compression_type : compression_types) {
     Options options = CurrentOptions();
@@ -838,7 +697,7 @@ TEST_F(DBBlockCacheTest, CacheCompressionDict) {
     options.compression_opts.max_dict_bytes = 4096;
     options.create_if_missing = true;
     options.num_levels = 2;
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.statistics = rocksdb::CreateDBStatistics();
     options.target_file_size_base = kNumEntriesPerFile * kNumBytesPerEntry;
     BlockBasedTableOptions table_options;
     table_options.cache_index_and_filter_blocks = true;
@@ -885,10 +744,10 @@ TEST_F(DBBlockCacheTest, CacheCompressionDict) {
 
 #endif  // ROCKSDB_LITE
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  rocksdb::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }

db/db_bloom_filter_test.cc

@@ -8,16 +8,10 @@
 // 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"
 
-namespace ROCKSDB_NAMESPACE {
-
-namespace {
-using BFP = BloomFilterPolicy;
-}  // namespace
+namespace rocksdb {
 
 // DB tests related to bloom filter.
 
@@ -26,12 +20,12 @@ class DBBloomFilterTest : public DBTestBase {
   DBBloomFilterTest() : DBTestBase("/db_bloom_filter_test") {}
 };
 
-class DBBloomFilterTestWithParam : public DBTestBase,
-                                   public testing::WithParamInterface<
-                                       std::tuple<BFP::Mode, bool, uint32_t>> {
+class DBBloomFilterTestWithParam
+    : public DBTestBase,
+      public testing::WithParamInterface<std::tuple<bool, bool, uint32_t>> {
   //                             public testing::WithParamInterface<bool> {
  protected:
-  BFP::Mode bfp_impl_;
+  bool use_block_based_filter_;
   bool partition_filters_;
   uint32_t format_version_;
 
@@ -41,7 +35,7 @@ class DBBloomFilterTestWithParam : public DBTestBase,
   ~DBBloomFilterTestWithParam() override {}
 
   void SetUp() override {
-    bfp_impl_ = std::get<0>(GetParam());
+    use_block_based_filter_ = std::get<0>(GetParam());
     partition_filters_ = std::get<1>(GetParam());
     format_version_ = std::get<2>(GetParam());
   }
@@ -77,7 +71,8 @@ TEST_P(DBBloomFilterTestDefFormatVersion, KeyMayExist) {
     ReadOptions ropts;
     std::string value;
     anon::OptionsOverride options_override;
-    options_override.filter_policy.reset(new BFP(20, bfp_impl_));
+    options_override.filter_policy.reset(
+        NewBloomFilterPolicy(20, use_block_based_filter_));
     options_override.partition_filters = partition_filters_;
     options_override.metadata_block_size = 32;
     Options options = CurrentOptions(options_override);
@@ -89,7 +84,7 @@ TEST_P(DBBloomFilterTestDefFormatVersion, KeyMayExist) {
       // indexes
       continue;
     }
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.statistics = rocksdb::CreateDBStatistics();
     CreateAndReopenWithCF({"pikachu"}, options);
 
     ASSERT_TRUE(!db_->KeyMayExist(ropts, handles_[1], "a", &value));
@@ -151,7 +146,7 @@ TEST_F(DBBloomFilterTest, GetFilterByPrefixBloomCustomPrefixExtractor) {
     Options options = last_options_;
     options.prefix_extractor =
         std::make_shared<SliceTransformLimitedDomainGeneric>();
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.statistics = rocksdb::CreateDBStatistics();
     get_perf_context()->EnablePerLevelPerfContext();
     BlockBasedTableOptions bbto;
     bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
@@ -217,7 +212,7 @@ TEST_F(DBBloomFilterTest, GetFilterByPrefixBloom) {
   for (bool partition_filters : {true, false}) {
     Options options = last_options_;
     options.prefix_extractor.reset(NewFixedPrefixTransform(8));
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.statistics = rocksdb::CreateDBStatistics();
     get_perf_context()->EnablePerLevelPerfContext();
     BlockBasedTableOptions bbto;
     bbto.filter_policy.reset(NewBloomFilterPolicy(10, false));
@@ -268,7 +263,7 @@ TEST_F(DBBloomFilterTest, WholeKeyFilterProp) {
   for (bool partition_filters : {true, false}) {
     Options options = last_options_;
     options.prefix_extractor.reset(NewFixedPrefixTransform(3));
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.statistics = rocksdb::CreateDBStatistics();
     get_perf_context()->EnablePerLevelPerfContext();
 
     BlockBasedTableOptions bbto;
@@ -437,7 +432,8 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
     // trigger reset of table_factory
     BlockBasedTableOptions table_options;
     table_options.no_block_cache = true;
-    table_options.filter_policy.reset(new BFP(10, bfp_impl_));
+    table_options.filter_policy.reset(
+        NewBloomFilterPolicy(10, use_block_based_filter_));
     table_options.partition_filters = partition_filters_;
     if (partition_filters_) {
       table_options.index_type =
@@ -506,33 +502,30 @@ TEST_P(DBBloomFilterTestWithParam, BloomFilter) {
 #ifndef ROCKSDB_VALGRIND_RUN
 INSTANTIATE_TEST_CASE_P(
     FormatDef, DBBloomFilterTestDefFormatVersion,
-    ::testing::Values(
-        std::make_tuple(BFP::kDeprecatedBlock, false,
-                        test::kDefaultFormatVersion),
-        std::make_tuple(BFP::kAuto, true, test::kDefaultFormatVersion),
-        std::make_tuple(BFP::kAuto, false, test::kDefaultFormatVersion)));
+    ::testing::Values(std::make_tuple(true, false, test::kDefaultFormatVersion),
+                      std::make_tuple(false, true, test::kDefaultFormatVersion),
+                      std::make_tuple(false, false,
+                                      test::kDefaultFormatVersion)));
 
 INSTANTIATE_TEST_CASE_P(
     FormatDef, DBBloomFilterTestWithParam,
-    ::testing::Values(
-        std::make_tuple(BFP::kDeprecatedBlock, false,
-                        test::kDefaultFormatVersion),
-        std::make_tuple(BFP::kAuto, true, test::kDefaultFormatVersion),
-        std::make_tuple(BFP::kAuto, false, test::kDefaultFormatVersion)));
+    ::testing::Values(std::make_tuple(true, false, test::kDefaultFormatVersion),
+                      std::make_tuple(false, true, test::kDefaultFormatVersion),
+                      std::make_tuple(false, false,
+                                      test::kDefaultFormatVersion)));
 
 INSTANTIATE_TEST_CASE_P(
     FormatLatest, DBBloomFilterTestWithParam,
-    ::testing::Values(
-        std::make_tuple(BFP::kDeprecatedBlock, false,
-                        test::kLatestFormatVersion),
-        std::make_tuple(BFP::kAuto, true, test::kLatestFormatVersion),
-        std::make_tuple(BFP::kAuto, false, test::kLatestFormatVersion)));
+    ::testing::Values(std::make_tuple(true, false, test::kLatestFormatVersion),
+                      std::make_tuple(false, true, test::kLatestFormatVersion),
+                      std::make_tuple(false, false,
+                                      test::kLatestFormatVersion)));
 #endif  // ROCKSDB_VALGRIND_RUN
 
 TEST_F(DBBloomFilterTest, BloomFilterRate) {
   while (ChangeFilterOptions()) {
     Options options = CurrentOptions();
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.statistics = rocksdb::CreateDBStatistics();
     get_perf_context()->EnablePerLevelPerfContext();
     CreateAndReopenWithCF({"pikachu"}, options);
 
@@ -564,7 +557,7 @@ TEST_F(DBBloomFilterTest, BloomFilterRate) {
 
 TEST_F(DBBloomFilterTest, BloomFilterCompatibility) {
   Options options = CurrentOptions();
-  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  options.statistics = rocksdb::CreateDBStatistics();
   BlockBasedTableOptions table_options;
   table_options.filter_policy.reset(NewBloomFilterPolicy(10, true));
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
@@ -608,7 +601,7 @@ TEST_F(DBBloomFilterTest, BloomFilterCompatibility) {
 TEST_F(DBBloomFilterTest, BloomFilterReverseCompatibility) {
   for (bool partition_filters : {true, false}) {
     Options options = CurrentOptions();
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+    options.statistics = rocksdb::CreateDBStatistics();
     BlockBasedTableOptions table_options;
     if (partition_filters) {
       table_options.partition_filters = true;
@@ -643,30 +636,27 @@ TEST_F(DBBloomFilterTest, BloomFilterReverseCompatibility) {
 }
 
 namespace {
-// A wrapped bloom over block-based FilterPolicy
-class TestingWrappedBlockBasedFilterPolicy : public FilterPolicy {
+// A wrapped bloom over default FilterPolicy
+class WrappedBloom : public FilterPolicy {
  public:
-  explicit TestingWrappedBlockBasedFilterPolicy(int bits_per_key)
-      : filter_(NewBloomFilterPolicy(bits_per_key, true)), counter_(0) {}
+  explicit WrappedBloom(int bits_per_key)
+      : filter_(NewBloomFilterPolicy(bits_per_key)), counter_(0) {}
 
-  ~TestingWrappedBlockBasedFilterPolicy() override { delete filter_; }
+  ~WrappedBloom() override { delete filter_; }
 
-  const char* Name() const override {
-    return "TestingWrappedBlockBasedFilterPolicy";
-  }
+  const char* Name() const override { return "WrappedRocksDbFilterPolicy"; }
 
-  void CreateFilter(const ROCKSDB_NAMESPACE::Slice* keys, int n,
+  void CreateFilter(const rocksdb::Slice* keys, int n,
                     std::string* dst) const override {
-    std::unique_ptr<ROCKSDB_NAMESPACE::Slice[]> user_keys(
-        new ROCKSDB_NAMESPACE::Slice[n]);
+    std::unique_ptr<rocksdb::Slice[]> user_keys(new rocksdb::Slice[n]);
     for (int i = 0; i < n; ++i) {
       user_keys[i] = convertKey(keys[i]);
     }
     return filter_->CreateFilter(user_keys.get(), n, dst);
   }
 
-  bool KeyMayMatch(const ROCKSDB_NAMESPACE::Slice& key,
-                   const ROCKSDB_NAMESPACE::Slice& filter) const override {
+  bool KeyMayMatch(const rocksdb::Slice& key,
+                   const rocksdb::Slice& filter) const override {
     counter_++;
     return filter_->KeyMayMatch(convertKey(key), filter);
   }
@@ -677,20 +667,16 @@ class TestingWrappedBlockBasedFilterPolicy : public FilterPolicy {
   const FilterPolicy* filter_;
   mutable uint32_t counter_;
 
-  ROCKSDB_NAMESPACE::Slice convertKey(
-      const ROCKSDB_NAMESPACE::Slice& key) const {
-    return key;
-  }
+  rocksdb::Slice convertKey(const rocksdb::Slice& key) const { return key; }
 };
 }  // namespace
 
-TEST_F(DBBloomFilterTest, WrappedBlockBasedFilterPolicy) {
+TEST_F(DBBloomFilterTest, BloomFilterWrapper) {
   Options options = CurrentOptions();
-  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
+  options.statistics = rocksdb::CreateDBStatistics();
 
   BlockBasedTableOptions table_options;
-  TestingWrappedBlockBasedFilterPolicy* policy =
-      new TestingWrappedBlockBasedFilterPolicy(10);
+  WrappedBloom* policy = new WrappedBloom(10);
   table_options.filter_policy.reset(policy);
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
 
@@ -720,166 +706,6 @@ TEST_F(DBBloomFilterTest, WrappedBlockBasedFilterPolicy) {
   ASSERT_EQ(2U * maxKey, policy->GetCounter());
 }
 
-namespace {
-// NOTE: This class is referenced by HISTORY.md as a model for a wrapper
-// FilterPolicy selecting among configurations based on context.
-class LevelAndStyleCustomFilterPolicy : public FilterPolicy {
- public:
-  explicit LevelAndStyleCustomFilterPolicy(int bpk_fifo, int bpk_l0_other,
-                                           int bpk_otherwise)
-      : policy_fifo_(NewBloomFilterPolicy(bpk_fifo)),
-        policy_l0_other_(NewBloomFilterPolicy(bpk_l0_other)),
-        policy_otherwise_(NewBloomFilterPolicy(bpk_otherwise)) {}
-
-  // OK to use built-in policy name because we are deferring to a
-  // built-in builder. We aren't changing the serialized format.
-  const char* Name() const override { return policy_fifo_->Name(); }
-
-  FilterBitsBuilder* GetBuilderWithContext(
-      const FilterBuildingContext& context) const override {
-    if (context.compaction_style == kCompactionStyleFIFO) {
-      return policy_fifo_->GetBuilderWithContext(context);
-    } else if (context.level_at_creation == 0) {
-      return policy_l0_other_->GetBuilderWithContext(context);
-    } else {
-      return policy_otherwise_->GetBuilderWithContext(context);
-    }
-  }
-
-  FilterBitsReader* GetFilterBitsReader(const Slice& contents) const override {
-    // OK to defer to any of them; they all can parse built-in filters
-    // from any settings.
-    return policy_fifo_->GetFilterBitsReader(contents);
-  }
-
-  // Defer just in case configuration uses block-based filter
-  void CreateFilter(const Slice* keys, int n, std::string* dst) const override {
-    policy_otherwise_->CreateFilter(keys, n, dst);
-  }
-  bool KeyMayMatch(const Slice& key, const Slice& filter) const override {
-    return policy_otherwise_->KeyMayMatch(key, filter);
-  }
-
- private:
-  const std::unique_ptr<const FilterPolicy> policy_fifo_;
-  const std::unique_ptr<const FilterPolicy> policy_l0_other_;
-  const std::unique_ptr<const FilterPolicy> policy_otherwise_;
-};
-
-class TestingContextCustomFilterPolicy
-    : public LevelAndStyleCustomFilterPolicy {
- public:
-  explicit TestingContextCustomFilterPolicy(int bpk_fifo, int bpk_l0_other,
-                                            int bpk_otherwise)
-      : LevelAndStyleCustomFilterPolicy(bpk_fifo, bpk_l0_other, bpk_otherwise) {
-  }
-
-  FilterBitsBuilder* GetBuilderWithContext(
-      const FilterBuildingContext& context) const override {
-    test_report_ += "cf=";
-    test_report_ += context.column_family_name;
-    test_report_ += ",cs=";
-    test_report_ +=
-        OptionsHelper::compaction_style_to_string[context.compaction_style];
-    test_report_ += ",lv=";
-    test_report_ += std::to_string(context.level_at_creation);
-    test_report_ += "\n";
-
-    return LevelAndStyleCustomFilterPolicy::GetBuilderWithContext(context);
-  }
-
-  std::string DumpTestReport() {
-    std::string rv;
-    std::swap(rv, test_report_);
-    return rv;
-  }
-
- private:
-  mutable std::string test_report_;
-};
-}  // namespace
-
-TEST_F(DBBloomFilterTest, ContextCustomFilterPolicy) {
-  for (bool fifo : {true, false}) {
-    Options options = CurrentOptions();
-    options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-    options.compaction_style =
-        fifo ? kCompactionStyleFIFO : kCompactionStyleLevel;
-
-    BlockBasedTableOptions table_options;
-    auto policy = std::make_shared<TestingContextCustomFilterPolicy>(15, 8, 5);
-    table_options.filter_policy = policy;
-    table_options.format_version = 5;
-    options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-
-    CreateAndReopenWithCF({fifo ? "abe" : "bob"}, options);
-
-    const int maxKey = 10000;
-    for (int i = 0; i < maxKey / 2; i++) {
-      ASSERT_OK(Put(1, Key(i), Key(i)));
-    }
-    // Add a large key to make the file contain wide range
-    ASSERT_OK(Put(1, Key(maxKey + 55555), Key(maxKey + 55555)));
-    Flush(1);
-    EXPECT_EQ(policy->DumpTestReport(),
-              fifo ? "cf=abe,cs=kCompactionStyleFIFO,lv=0\n"
-                   : "cf=bob,cs=kCompactionStyleLevel,lv=0\n");
-
-    for (int i = maxKey / 2; i < maxKey; i++) {
-      ASSERT_OK(Put(1, Key(i), Key(i)));
-    }
-    Flush(1);
-    EXPECT_EQ(policy->DumpTestReport(),
-              fifo ? "cf=abe,cs=kCompactionStyleFIFO,lv=0\n"
-                   : "cf=bob,cs=kCompactionStyleLevel,lv=0\n");
-
-    // Check that they can be found
-    for (int i = 0; i < maxKey; i++) {
-      ASSERT_EQ(Key(i), Get(1, Key(i)));
-    }
-    // Since we have two tables / two filters, we might have Bloom checks on
-    // our queries, but no more than one "useful" per query on a found key.
-    EXPECT_LE(TestGetAndResetTickerCount(options, BLOOM_FILTER_USEFUL), maxKey);
-
-    // Check that we have two filters, each about
-    // fifo: 0.12% FP rate (15 bits per key)
-    // level: 2.3% FP rate (8 bits per key)
-    for (int i = 0; i < maxKey; i++) {
-      ASSERT_EQ("NOT_FOUND", Get(1, Key(i + 33333)));
-    }
-    {
-      auto useful_count =
-          TestGetAndResetTickerCount(options, BLOOM_FILTER_USEFUL);
-      EXPECT_GE(useful_count, maxKey * 2 * (fifo ? 0.9980 : 0.975));
-      EXPECT_LE(useful_count, maxKey * 2 * (fifo ? 0.9995 : 0.98));
-    }
-
-    if (!fifo) {  // FIFO only has L0
-      // Full compaction
-      ASSERT_OK(db_->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                                  nullptr));
-      EXPECT_EQ(policy->DumpTestReport(),
-                "cf=bob,cs=kCompactionStyleLevel,lv=1\n");
-
-      // Check that we now have one filter, about 9.2% FP rate (5 bits per key)
-      for (int i = 0; i < maxKey; i++) {
-        ASSERT_EQ("NOT_FOUND", Get(1, Key(i + 33333)));
-      }
-      {
-        auto useful_count =
-            TestGetAndResetTickerCount(options, BLOOM_FILTER_USEFUL);
-        EXPECT_GE(useful_count, maxKey * 0.90);
-        EXPECT_LE(useful_count, maxKey * 0.91);
-      }
-    }
-
-    // Destroy
-    ASSERT_OK(dbfull()->DropColumnFamily(handles_[1]));
-    dbfull()->DestroyColumnFamilyHandle(handles_[1]);
-    handles_[1] = nullptr;
-  }
-}
-
 class SliceTransformLimitedDomain : public SliceTransform {
   const char* Name() const override { return "SliceTransformLimitedDomain"; }
 
@@ -901,7 +727,7 @@ class SliceTransformLimitedDomain : public SliceTransform {
 TEST_F(DBBloomFilterTest, PrefixExtractorFullFilter) {
   BlockBasedTableOptions bbto;
   // Full Filter Block
-  bbto.filter_policy.reset(ROCKSDB_NAMESPACE::NewBloomFilterPolicy(10, false));
+  bbto.filter_policy.reset(rocksdb::NewBloomFilterPolicy(10, false));
   bbto.whole_key_filtering = false;
 
   Options options = CurrentOptions();
@@ -930,7 +756,7 @@ TEST_F(DBBloomFilterTest, PrefixExtractorFullFilter) {
 TEST_F(DBBloomFilterTest, PrefixExtractorBlockFilter) {
   BlockBasedTableOptions bbto;
   // Block Filter Block
-  bbto.filter_policy.reset(ROCKSDB_NAMESPACE::NewBloomFilterPolicy(10, true));
+  bbto.filter_policy.reset(rocksdb::NewBloomFilterPolicy(10, true));
 
   Options options = CurrentOptions();
   options.prefix_extractor = std::make_shared<SliceTransformLimitedDomain>();
@@ -969,8 +795,7 @@ TEST_F(DBBloomFilterTest, MemtableWholeKeyBloomFilter) {
   Options options = CurrentOptions();
   options.memtable_prefix_bloom_size_ratio =
       static_cast<double>(kMemtablePrefixFilterSize) / kMemtableSize;
-  options.prefix_extractor.reset(
-      ROCKSDB_NAMESPACE::NewFixedPrefixTransform(kPrefixLen));
+  options.prefix_extractor.reset(rocksdb::NewFixedPrefixTransform(kPrefixLen));
   options.write_buffer_size = kMemtableSize;
   options.memtable_whole_key_filtering = false;
   Reopen(options);
@@ -1030,244 +855,36 @@ 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 {
-// Extends BFP::Mode with option to use Plain table
-using PseudoMode = int;
-static constexpr PseudoMode kPlainTable = -1;
-}  // namespace BFP2
-}  // namespace
-
 class BloomStatsTestWithParam
     : public DBBloomFilterTest,
-      public testing::WithParamInterface<std::tuple<BFP2::PseudoMode, bool>> {
+      public testing::WithParamInterface<std::tuple<bool, bool, bool>> {
  public:
   BloomStatsTestWithParam() {
-    bfp_impl_ = std::get<0>(GetParam());
-    partition_filters_ = std::get<1>(GetParam());
+    use_block_table_ = std::get<0>(GetParam());
+    use_block_based_builder_ = std::get<1>(GetParam());
+    partition_filters_ = std::get<2>(GetParam());
 
     options_.create_if_missing = true;
-    options_.prefix_extractor.reset(
-        ROCKSDB_NAMESPACE::NewFixedPrefixTransform(4));
+    options_.prefix_extractor.reset(rocksdb::NewFixedPrefixTransform(4));
     options_.memtable_prefix_bloom_size_ratio =
         8.0 * 1024.0 / static_cast<double>(options_.write_buffer_size);
-    if (bfp_impl_ == BFP2::kPlainTable) {
-      assert(!partition_filters_);  // not supported in plain table
-      PlainTableOptions table_options;
-      options_.table_factory.reset(NewPlainTableFactory(table_options));
-    } else {
+    if (use_block_table_) {
       BlockBasedTableOptions table_options;
       table_options.hash_index_allow_collision = false;
       if (partition_filters_) {
-        assert(bfp_impl_ != BFP::kDeprecatedBlock);
+        assert(!use_block_based_builder_);
         table_options.partition_filters = partition_filters_;
         table_options.index_type =
             BlockBasedTableOptions::IndexType::kTwoLevelIndexSearch;
       }
       table_options.filter_policy.reset(
-          new BFP(10, static_cast<BFP::Mode>(bfp_impl_)));
+          NewBloomFilterPolicy(10, use_block_based_builder_));
       options_.table_factory.reset(NewBlockBasedTableFactory(table_options));
+    } else {
+      assert(!partition_filters_);  // not supported in plain table
+      PlainTableOptions table_options;
+      options_.table_factory.reset(NewPlainTableFactory(table_options));
     }
     options_.env = env_;
 
@@ -1284,7 +901,8 @@ class BloomStatsTestWithParam
   static void SetUpTestCase() {}
   static void TearDownTestCase() {}
 
-  BFP2::PseudoMode bfp_impl_;
+  bool use_block_table_;
+  bool use_block_based_builder_;
   bool partition_filters_;
   Options options_;
 };
@@ -1388,7 +1006,7 @@ TEST_P(BloomStatsTestWithParam, BloomStatsTestWithIter) {
   ASSERT_EQ(value3, iter->value().ToString());
   // The seek doesn't check block-based bloom filter because last index key
   // starts with the same prefix we're seeking to.
-  uint64_t expected_hits = bfp_impl_ == BFP::kDeprecatedBlock ? 1 : 2;
+  uint64_t expected_hits = use_block_based_builder_ ? 1 : 2;
   ASSERT_EQ(expected_hits, get_perf_context()->bloom_sst_hit_count);
 
   iter->Seek(key2);
@@ -1398,14 +1016,12 @@ TEST_P(BloomStatsTestWithParam, BloomStatsTestWithIter) {
   ASSERT_EQ(expected_hits, get_perf_context()->bloom_sst_hit_count);
 }
 
-INSTANTIATE_TEST_CASE_P(
-    BloomStatsTestWithParam, BloomStatsTestWithParam,
-    ::testing::Values(std::make_tuple(BFP::kDeprecatedBlock, false),
-                      std::make_tuple(BFP::kLegacyBloom, false),
-                      std::make_tuple(BFP::kLegacyBloom, true),
-                      std::make_tuple(BFP::kFastLocalBloom, false),
-                      std::make_tuple(BFP::kFastLocalBloom, true),
-                      std::make_tuple(BFP2::kPlainTable, false)));
+INSTANTIATE_TEST_CASE_P(BloomStatsTestWithParam, BloomStatsTestWithParam,
+                        ::testing::Values(std::make_tuple(true, true, false),
+                                          std::make_tuple(true, false, false),
+                                          std::make_tuple(true, false, true),
+                                          std::make_tuple(false, false,
+                                                          false)));
 
 namespace {
 void PrefixScanInit(DBBloomFilterTest* dbtest) {
@@ -1530,8 +1146,7 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
   bbto.whole_key_filtering = true;
   options.table_factory.reset(NewBlockBasedTableFactory(bbto));
   options.optimize_filters_for_hits = true;
-  options.statistics = ROCKSDB_NAMESPACE::CreateDBStatistics();
-  get_perf_context()->Reset();
+  options.statistics = rocksdb::CreateDBStatistics();
   get_perf_context()->EnablePerLevelPerfContext();
   CreateAndReopenWithCF({"mypikachu"}, options);
 
@@ -1544,7 +1159,8 @@ 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"));
@@ -1655,13 +1271,13 @@ TEST_F(DBBloomFilterTest, OptimizeFiltersForHits) {
 
   int32_t trivial_move = 0;
   int32_t non_trivial_move = 0;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:TrivialMove",
       [&](void* /*arg*/) { trivial_move++; });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial",
       [&](void* /*arg*/) { non_trivial_move++; });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   CompactRangeOptions compact_options;
   compact_options.bottommost_level_compaction =
@@ -1712,8 +1328,8 @@ int CountIter(std::unique_ptr<Iterator>& iter, const Slice& key) {
 // into the same string, or 2) the transformed seek key is of the same length
 // as the upper bound and two keys are adjacent according to the comparator.
 TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
-  for (auto bfp_impl : BFP::kAllFixedImpls) {
-    int using_full_builder = bfp_impl != BFP::kDeprecatedBlock;
+  int iteration = 0;
+  for (bool use_block_based_builder : {true, false}) {
     Options options;
     options.create_if_missing = true;
     options.prefix_extractor.reset(NewCappedPrefixTransform(4));
@@ -1722,7 +1338,8 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
     // Enable prefix bloom for SST files
     BlockBasedTableOptions table_options;
     table_options.cache_index_and_filter_blocks = true;
-    table_options.filter_policy.reset(new BFP(10, bfp_impl));
+    table_options.filter_policy.reset(
+        NewBloomFilterPolicy(10, use_block_based_builder));
     table_options.index_shortening = BlockBasedTableOptions::
         IndexShorteningMode::kShortenSeparatorsAndSuccessor;
     options.table_factory.reset(NewBlockBasedTableFactory(table_options));
@@ -1765,7 +1382,7 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       ASSERT_EQ(CountIter(iter, "abcdxx00"), 4);
       // should check bloom filter since upper bound meets requirement
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + using_full_builder);
+                2 + iteration);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
     }
     {
@@ -1779,7 +1396,7 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       ASSERT_EQ(CountIter(iter, "abcdxx01"), 4);
       // should skip bloom filter since upper bound is too long
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + using_full_builder);
+                2 + iteration);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
     }
     {
@@ -1793,7 +1410,7 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       // should check bloom filter since upper bound matches transformed seek
       // key
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + using_full_builder * 2);
+                2 + iteration * 2);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
     }
     {
@@ -1807,7 +1424,7 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       ASSERT_EQ(CountIter(iter, "aaaaaaaa"), 0);
       // should skip bloom filter since mismatch is found
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + using_full_builder * 2);
+                2 + iteration * 2);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
     }
     ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "fixed:3"}}));
@@ -1821,7 +1438,7 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "abc"), 4);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + using_full_builder * 2);
+                2 + iteration * 2);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
     }
     ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:4"}}));
@@ -1834,17 +1451,18 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterUpperBound) {
       std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter, "abc"), 0);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                3 + using_full_builder * 2);
+                3 + iteration * 2);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
     }
+    iteration++;
   }
 }
 
 // Create multiple SST files each with a different prefix_extractor config,
 // verify iterators can read all SST files using the latest config.
 TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
-  for (auto bfp_impl : BFP::kAllFixedImpls) {
-    int using_full_builder = bfp_impl != BFP::kDeprecatedBlock;
+  int iteration = 0;
+  for (bool use_block_based_builder : {true, false}) {
     Options options;
     options.create_if_missing = true;
     options.prefix_extractor.reset(NewFixedPrefixTransform(1));
@@ -1852,7 +1470,8 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
     options.statistics = CreateDBStatistics();
     // Enable prefix bloom for SST files
     BlockBasedTableOptions table_options;
-    table_options.filter_policy.reset(new BFP(10, bfp_impl));
+    table_options.filter_policy.reset(
+        NewBloomFilterPolicy(10, use_block_based_builder));
     table_options.cache_index_and_filter_blocks = true;
     options.table_factory.reset(NewBlockBasedTableFactory(table_options));
     DestroyAndReopen(options);
@@ -1878,10 +1497,10 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
     std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
     ASSERT_EQ(CountIter(iter, "foo"), 2);
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-              1 + using_full_builder);
+              1 + iteration);
     ASSERT_EQ(CountIter(iter, "gpk"), 0);
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-              1 + using_full_builder);
+              1 + iteration);
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
 
     // second SST with capped:3 BF
@@ -1895,13 +1514,13 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
       std::unique_ptr<Iterator> iter_tmp(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter_tmp, "foo"), 4);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                2 + using_full_builder * 2);
+                2 + iteration * 2);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 0);
       ASSERT_EQ(CountIter(iter_tmp, "gpk"), 0);
       // both counters are incremented because BF is "not changed" for 1 of the
       // 2 SST files, so filter is checked once and found no match.
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                3 + using_full_builder * 2);
+                3 + iteration * 2);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
     }
 
@@ -1920,24 +1539,24 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
       ASSERT_EQ(CountIter(iter_tmp, "foo"), 9);
       // the first and last BF are checked
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                4 + using_full_builder * 3);
+                4 + iteration * 3);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 1);
       ASSERT_EQ(CountIter(iter_tmp, "gpk"), 0);
       // only last BF is checked and not found
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                5 + using_full_builder * 3);
+                5 + iteration * 3);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 2);
     }
 
     // iter_old can only see the first SST, so checked plus 1
     ASSERT_EQ(CountIter(iter_old, "foo"), 4);
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-              6 + using_full_builder * 3);
+              6 + iteration * 3);
     // iter was created after the first setoptions call so only full filter
     // will check the filter
     ASSERT_EQ(CountIter(iter, "foo"), 2);
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-              6 + using_full_builder * 4);
+              6 + iteration * 4);
 
     {
       // keys in all three SSTs are visible to iterator
@@ -1946,11 +1565,11 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
       std::unique_ptr<Iterator> iter_all(db_->NewIterator(read_options));
       ASSERT_EQ(CountIter(iter_all, "foo"), 9);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                7 + using_full_builder * 5);
+                7 + iteration * 5);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 2);
       ASSERT_EQ(CountIter(iter_all, "gpk"), 0);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                8 + using_full_builder * 5);
+                8 + iteration * 5);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 3);
     }
     ASSERT_OK(dbfull()->SetOptions({{"prefix_extractor", "capped:3"}}));
@@ -1962,14 +1581,15 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
       // all three SST are checked because the current options has the same as
       // the remaining SST (capped:3)
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                9 + using_full_builder * 7);
+                9 + iteration * 7);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 3);
       ASSERT_EQ(CountIter(iter_all, "gpk"), 0);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED),
-                10 + using_full_builder * 7);
+                10 + iteration * 7);
       ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 4);
     }
     // TODO(Zhongyi): Maybe also need to add Get calls to test point look up?
+    iteration++;
   }
 }
 
@@ -1978,7 +1598,7 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterMultipleSST) {
 // as expected
 TEST_F(DBBloomFilterTest, DynamicBloomFilterNewColumnFamily) {
   int iteration = 0;
-  for (auto bfp_impl : BFP::kAllFixedImpls) {
+  for (bool use_block_based_builder : {true, false}) {
     Options options = CurrentOptions();
     options.create_if_missing = true;
     options.prefix_extractor.reset(NewFixedPrefixTransform(1));
@@ -1987,7 +1607,8 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterNewColumnFamily) {
     // Enable prefix bloom for SST files
     BlockBasedTableOptions table_options;
     table_options.cache_index_and_filter_blocks = true;
-    table_options.filter_policy.reset(new BFP(10, bfp_impl));
+    table_options.filter_policy.reset(
+        NewBloomFilterPolicy(10, use_block_based_builder));
     options.table_factory.reset(NewBlockBasedTableFactory(table_options));
     CreateAndReopenWithCF({"pikachu" + std::to_string(iteration)}, options);
     ReadOptions read_options;
@@ -2036,7 +1657,8 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterNewColumnFamily) {
 // Verify it's possible to change prefix_extractor at runtime and iterators
 // behaves as expected
 TEST_F(DBBloomFilterTest, DynamicBloomFilterOptions) {
-  for (auto bfp_impl : BFP::kAllFixedImpls) {
+  int iteration = 0;
+  for (bool use_block_based_builder : {true, false}) {
     Options options;
     options.create_if_missing = true;
     options.prefix_extractor.reset(NewFixedPrefixTransform(1));
@@ -2045,7 +1667,8 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterOptions) {
     // Enable prefix bloom for SST files
     BlockBasedTableOptions table_options;
     table_options.cache_index_and_filter_blocks = true;
-    table_options.filter_policy.reset(new BFP(10, bfp_impl));
+    table_options.filter_policy.reset(
+        NewBloomFilterPolicy(10, use_block_based_builder));
     options.table_factory.reset(NewBlockBasedTableFactory(table_options));
     DestroyAndReopen(options);
 
@@ -2096,15 +1719,16 @@ TEST_F(DBBloomFilterTest, DynamicBloomFilterOptions) {
     ASSERT_EQ(CountIter(iter_old, "abc"), 0);
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_CHECKED), 12);
     ASSERT_EQ(TestGetTickerCount(options, BLOOM_FILTER_PREFIX_USEFUL), 3);
+    iteration++;
   }
 }
 
 #endif  // ROCKSDB_LITE
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  rocksdb::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }

db/db_compaction_filter_test.cc

@@ -10,7 +10,7 @@
 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 static int cfilter_count = 0;
 static int cfilter_skips = 0;
@@ -47,7 +47,8 @@ class DBTestCompactionFilterWithCompactParam
 
 #ifndef ROCKSDB_VALGRIND_RUN
 INSTANTIATE_TEST_CASE_P(
-    CompactionFilterWithOption, DBTestCompactionFilterWithCompactParam,
+    DBTestCompactionFilterWithCompactOption,
+    DBTestCompactionFilterWithCompactParam,
     ::testing::Values(DBTestBase::OptionConfig::kDefault,
                       DBTestBase::OptionConfig::kUniversalCompaction,
                       DBTestBase::OptionConfig::kUniversalCompactionMultiLevel,
@@ -55,7 +56,7 @@ INSTANTIATE_TEST_CASE_P(
                       DBTestBase::OptionConfig::kUniversalSubcompactions));
 #else
 // Run fewer cases in valgrind
-INSTANTIATE_TEST_CASE_P(CompactionFilterWithOption,
+INSTANTIATE_TEST_CASE_P(DBTestCompactionFilterWithCompactOption,
                         DBTestCompactionFilterWithCompactParam,
                         ::testing::Values(DBTestBase::OptionConfig::kDefault));
 #endif  // ROCKSDB_VALGRIND_RUN
@@ -863,10 +864,10 @@ TEST_F(DBTestCompactionFilter, IgnoreSnapshotsFalse) {
   delete options.compaction_filter;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  rocksdb::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }

db/db_dynamic_level_test.cc

@@ -16,7 +16,7 @@
 #include "port/port.h"
 #include "port/stack_trace.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 class DBTestDynamicLevel : public DBTestBase {
  public:
   DBTestDynamicLevel() : DBTestBase("/db_dynamic_level_test") {}
@@ -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) {
@@ -221,10 +221,10 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
 
   // Make sure that the compaction starts before the last bit of data is
   // flushed, so that the base level isn't raised to L1.
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"CompactionJob::Run():Start", "DynamicLevelMaxBytesBase2:0"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "false"},
@@ -235,20 +235,20 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
   dbfull()->TEST_WaitForCompact();
   ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
   ASSERT_EQ(2U, int_prop);
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 
   // Write more data until the base level changes to L1. There will be
   // a manual compaction going on at the same time.
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->LoadDependency({
+  rocksdb::SyncPoint::GetInstance()->LoadDependency({
       {"CompactionJob::Run():Start", "DynamicLevelMaxBytesBase2:1"},
       {"DynamicLevelMaxBytesBase2:2", "CompactionJob::Run():End"},
       {"DynamicLevelMaxBytesBase2:compact_range_finish",
        "FlushJob::WriteLevel0Table"},
   });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
-  ROCKSDB_NAMESPACE::port::Thread thread([this] {
+  rocksdb::port::Thread thread([this] {
     TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:compact_range_start");
     ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
     TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:compact_range_finish");
@@ -265,8 +265,8 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
 
   thread.join();
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 
   ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
   ASSERT_EQ(1U, int_prop);
@@ -329,16 +329,16 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesCompactRange) {
   ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level2", &str_prop));
   ASSERT_EQ("0", str_prop);
 
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->ClearAllCallBacks();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 
   std::set<int> output_levels;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "CompactionPicker::CompactRange:Return", [&](void* arg) {
         Compaction* compaction = reinterpret_cast<Compaction*>(arg);
         output_levels.insert(compaction->output_level());
       });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
   ASSERT_EQ(output_levels.size(), 2);
@@ -373,10 +373,10 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBaseInc) {
   DestroyAndReopen(options);
 
   int non_trivial = 0;
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->SetCallBack(
+  rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial",
       [&](void* /*arg*/) { non_trivial++; });
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->EnableProcessing();
+  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
   Random rnd(301);
   const int total_keys = 3000;
@@ -388,7 +388,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBaseInc) {
   }
   Flush();
   dbfull()->TEST_WaitForCompact();
-  ROCKSDB_NAMESPACE::SyncPoint::GetInstance()->DisableProcessing();
+  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
 
   ASSERT_EQ(non_trivial, 0);
 
@@ -457,7 +457,7 @@ TEST_F(DBTestDynamicLevel, DISABLED_MigrateToDynamicLevelMaxBytesBase) {
   compaction_finished = false;
   // Issue manual compaction in one thread and still verify DB state
   // in main thread.
-  ROCKSDB_NAMESPACE::port::Thread t([&]() {
+  rocksdb::port::Thread t([&]() {
     CompactRangeOptions compact_options;
     compact_options.change_level = true;
     compact_options.target_level = options.num_levels - 1;
@@ -488,13 +488,13 @@ TEST_F(DBTestDynamicLevel, DISABLED_MigrateToDynamicLevelMaxBytesBase) {
   ASSERT_EQ(NumTableFilesAtLevel(1), 0);
   ASSERT_EQ(NumTableFilesAtLevel(2), 0);
 }
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 #endif  // !defined(ROCKSDB_LITE)
 
 int main(int argc, char** argv) {
 #if !defined(ROCKSDB_LITE)
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  rocksdb::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 #else

db/db_encryption_test.cc

@@ -12,7 +12,7 @@
 #include <iostream>
 #include <string>
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class DBEncryptionTest : public DBTestBase {
  public:
@@ -113,10 +113,10 @@ TEST_F(DBEncryptionTest, ReadEmptyFile) {
 
 #endif // ROCKSDB_LITE
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  rocksdb::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }

db/db_filesnapshot.cc

@@ -6,9 +6,9 @@
 
 #ifndef ROCKSDB_LITE
 
+#include <cinttypes>
 #include <stdint.h>
 #include <algorithm>
-#include <cinttypes>
 #include <string>
 #include "db/db_impl/db_impl.h"
 #include "db/job_context.h"
@@ -21,7 +21,7 @@
 #include "test_util/sync_point.h"
 #include "util/mutexlock.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 Status DBImpl::DisableFileDeletions() {
   InstrumentedMutexLock l(&mutex_);
@@ -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()) {
@@ -105,11 +102,9 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
         TEST_SYNC_POINT("DBImpl::GetLiveFiles:1");
         TEST_SYNC_POINT("DBImpl::GetLiveFiles:2");
         mutex_.Lock();
-        cfd->UnrefAndTryDelete();
-        if (!status.ok() && !status.IsColumnFamilyDropped()) {
+        cfd->Unref();
+        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();
@@ -183,6 +172,7 @@ Status DBImpl::GetCurrentWalFile(std::unique_ptr<LogFile>* current_log_file) {
 
   return wal_manager_.GetLiveWalFile(current_logfile_number, current_log_file);
 }
-}  // namespace ROCKSDB_NAMESPACE
+
+}
 
 #endif  // ROCKSDB_LITE

db/db_flush_test.cc

@@ -7,18 +7,12 @@
 // 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 <atomic>
-
-#include "db/db_impl/db_impl.h"
 #include "db/db_test_util.h"
-#include "port/port.h"
 #include "port/stack_trace.h"
 #include "test_util/fault_injection_test_env.h"
 #include "test_util/sync_point.h"
-#include "util/cast_util.h"
-#include "util/mutexlock.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class DBFlushTest : public DBTestBase {
  public:
@@ -212,30 +206,6 @@ TEST_F(DBFlushTest, ManualFlushWithMinWriteBufferNumberToMerge) {
   t.join();
 }
 
-TEST_F(DBFlushTest, ScheduleOnlyOneBgThread) {
-  Options options = CurrentOptions();
-  Reopen(options);
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  int called = 0;
-  SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::MaybeScheduleFlushOrCompaction:AfterSchedule:0", [&](void* arg) {
-        ASSERT_NE(nullptr, arg);
-        auto unscheduled_flushes = *reinterpret_cast<int*>(arg);
-        ASSERT_EQ(0, unscheduled_flushes);
-        ++called;
-      });
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put("a", "foo"));
-  FlushOptions flush_opts;
-  ASSERT_OK(dbfull()->Flush(flush_opts));
-  ASSERT_EQ(1, called);
-
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
 TEST_P(DBFlushDirectIOTest, DirectIO) {
   Options options;
   options.create_if_missing = true;
@@ -353,96 +323,6 @@ TEST_F(DBFlushTest, CFDropRaceWithWaitForFlushMemTables) {
   SyncPoint::GetInstance()->DisableProcessing();
 }
 
-#ifndef ROCKSDB_LITE
-TEST_F(DBFlushTest, FireOnFlushCompletedAfterCommittedResult) {
-  class TestListener : public EventListener {
-   public:
-    void OnFlushCompleted(DB* db, const FlushJobInfo& info) override {
-      // There's only one key in each flush.
-      ASSERT_EQ(info.smallest_seqno, info.largest_seqno);
-      ASSERT_NE(0, info.smallest_seqno);
-      if (info.smallest_seqno == seq1) {
-        // First flush completed
-        ASSERT_FALSE(completed1);
-        completed1 = true;
-        CheckFlushResultCommitted(db, seq1);
-      } else {
-        // Second flush completed
-        ASSERT_FALSE(completed2);
-        completed2 = true;
-        ASSERT_EQ(info.smallest_seqno, seq2);
-        CheckFlushResultCommitted(db, seq2);
-      }
-    }
-
-    void CheckFlushResultCommitted(DB* db, SequenceNumber seq) {
-      DBImpl* db_impl = static_cast_with_check<DBImpl>(db);
-      InstrumentedMutex* mutex = db_impl->mutex();
-      mutex->Lock();
-      auto* cfd =
-          reinterpret_cast<ColumnFamilyHandleImpl*>(db->DefaultColumnFamily())
-              ->cfd();
-      ASSERT_LT(seq, cfd->imm()->current()->GetEarliestSequenceNumber());
-      mutex->Unlock();
-    }
-
-    std::atomic<SequenceNumber> seq1{0};
-    std::atomic<SequenceNumber> seq2{0};
-    std::atomic<bool> completed1{false};
-    std::atomic<bool> completed2{false};
-  };
-  std::shared_ptr<TestListener> listener = std::make_shared<TestListener>();
-
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBImpl::BackgroundCallFlush:start",
-        "DBFlushTest::FireOnFlushCompletedAfterCommittedResult:WaitFirst"},
-       {"DBImpl::FlushMemTableToOutputFile:Finish",
-        "DBFlushTest::FireOnFlushCompletedAfterCommittedResult:WaitSecond"}});
-  SyncPoint::GetInstance()->SetCallBack(
-      "FlushJob::WriteLevel0Table", [&listener](void* arg) {
-        // Wait for the second flush finished, out of mutex.
-        auto* mems = reinterpret_cast<autovector<MemTable*>*>(arg);
-        if (mems->front()->GetEarliestSequenceNumber() == listener->seq1 - 1) {
-          TEST_SYNC_POINT(
-              "DBFlushTest::FireOnFlushCompletedAfterCommittedResult:"
-              "WaitSecond");
-        }
-      });
-
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.listeners.push_back(listener);
-  // Setting max_flush_jobs = max_background_jobs / 4 = 2.
-  options.max_background_jobs = 8;
-  // Allow 2 immutable memtables.
-  options.max_write_buffer_number = 3;
-  Reopen(options);
-  SyncPoint::GetInstance()->EnableProcessing();
-  ASSERT_OK(Put("foo", "v"));
-  listener->seq1 = db_->GetLatestSequenceNumber();
-  // t1 will wait for the second flush complete before committing flush result.
-  auto t1 = port::Thread([&]() {
-    // flush_opts.wait = true
-    ASSERT_OK(db_->Flush(FlushOptions()));
-  });
-  // Wait for first flush started.
-  TEST_SYNC_POINT(
-      "DBFlushTest::FireOnFlushCompletedAfterCommittedResult:WaitFirst");
-  // The second flush will exit early without commit its result. The work
-  // is delegated to the first flush.
-  ASSERT_OK(Put("bar", "v"));
-  listener->seq2 = db_->GetLatestSequenceNumber();
-  FlushOptions flush_opts;
-  flush_opts.wait = false;
-  ASSERT_OK(db_->Flush(flush_opts));
-  t1.join();
-  ASSERT_TRUE(listener->completed1);
-  ASSERT_TRUE(listener->completed2);
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-#endif  // !ROCKSDB_LITE
-
 TEST_P(DBAtomicFlushTest, ManualAtomicFlush) {
   Options options = CurrentOptions();
   options.create_if_missing = true;
@@ -741,44 +621,15 @@ TEST_P(DBAtomicFlushTest, CFDropRaceWithWaitForFlushMemTables) {
   SyncPoint::GetInstance()->DisableProcessing();
 }
 
-TEST_P(DBAtomicFlushTest, RollbackAfterFailToInstallResults) {
-  bool atomic_flush = GetParam();
-  if (!atomic_flush) {
-    return;
-  }
-  auto fault_injection_env = std::make_shared<FaultInjectionTestEnv>(env_);
-  Options options = CurrentOptions();
-  options.env = fault_injection_env.get();
-  options.create_if_missing = true;
-  options.atomic_flush = atomic_flush;
-  CreateAndReopenWithCF({"pikachu"}, options);
-  ASSERT_EQ(2, handles_.size());
-  for (size_t cf = 0; cf < handles_.size(); ++cf) {
-    ASSERT_OK(Put(static_cast<int>(cf), "a", "value"));
-  }
-  SyncPoint::GetInstance()->DisableProcessing();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-  SyncPoint::GetInstance()->SetCallBack(
-      "VersionSet::ProcessManifestWrites:BeforeWriteLastVersionEdit:0",
-      [&](void* /*arg*/) { fault_injection_env->SetFilesystemActive(false); });
-  SyncPoint::GetInstance()->EnableProcessing();
-  FlushOptions flush_opts;
-  Status s = db_->Flush(flush_opts, handles_);
-  ASSERT_NOK(s);
-  fault_injection_env->SetFilesystemActive(true);
-  Close();
-  SyncPoint::GetInstance()->ClearAllCallBacks();
-}
-
 INSTANTIATE_TEST_CASE_P(DBFlushDirectIOTest, DBFlushDirectIOTest,
                         testing::Bool());
 
 INSTANTIATE_TEST_CASE_P(DBAtomicFlushTest, DBAtomicFlushTest, testing::Bool());
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  ROCKSDB_NAMESPACE::port::InstallStackTraceHandler();
+  rocksdb::port::InstallStackTraceHandler();
   ::testing::InitGoogleTest(&argc, argv);
   return RUN_ALL_TESTS();
 }

db/db_impl/db_impl.h

@@ -62,7 +62,7 @@
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
 
-namespace ROCKSDB_NAMESPACE {
+namespace rocksdb {
 
 class Arena;
 class ArenaWrappedDBIter;
@@ -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
@@ -206,27 +198,12 @@ 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(
+  void MultiGetImpl(
       const ReadOptions& options, ColumnFamilyHandle* column_family,
-      ReadCallback* callback,
-      autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE>* sorted_keys);
+      autovector<KeyContext, MultiGetContext::MAX_BATCH_SIZE>& key_context,
+      bool sorted_input, ReadCallback* callback = nullptr,
+      bool* is_blob_index = nullptr);
 
   virtual Status CreateColumnFamily(const ColumnFamilyOptions& cf_options,
                                     const std::string& column_family,
@@ -249,7 +226,7 @@ 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;
@@ -305,9 +282,6 @@ class DBImpl : public DB {
   virtual Status EnableAutoCompaction(
       const std::vector<ColumnFamilyHandle*>& column_family_handles) override;
 
-  virtual void EnableManualCompaction() override;
-  virtual void DisableManualCompaction() override;
-
   using DB::SetOptions;
   Status SetOptions(
       ColumnFamilyHandle* column_family,
@@ -325,7 +299,6 @@ class DBImpl : public DB {
       ColumnFamilyHandle* column_family) override;
   virtual const std::string& GetName() const override;
   virtual Env* GetEnv() const override;
-  virtual FileSystem* GetFileSystem() const override;
   using DB::GetOptions;
   virtual Options GetOptions(ColumnFamilyHandle* column_family) const override;
   using DB::GetDBOptions;
@@ -371,10 +344,7 @@ class DBImpl : public DB {
                               uint64_t* manifest_file_size,
                               bool flush_memtable = true) override;
   virtual Status GetSortedWalFiles(VectorLogPtr& files) override;
-  virtual Status GetCurrentWalFile(
-      std::unique_ptr<LogFile>* current_log_file) override;
-  virtual Status GetCreationTimeOfOldestFile(
-      uint64_t* creation_time) override;
+  virtual Status GetCurrentWalFile(std::unique_ptr<LogFile>* current_log_file) override;
 
   virtual Status GetUpdatesSince(
       SequenceNumber seq_number, std::unique_ptr<TransactionLogIterator>* iter,
@@ -452,7 +422,6 @@ 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 +444,7 @@ 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 +550,9 @@ 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 +678,7 @@ 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
@@ -825,10 +788,6 @@ class DBImpl : public DB {
     logs_to_free_queue_.push_back(log_writer);
   }
 
-  void AddSuperVersionsToFreeQueue(SuperVersion* sv) {
-    superversions_to_free_queue_.push_back(sv);
-  }
-
   void SetSnapshotChecker(SnapshotChecker* snapshot_checker);
 
   // Fill JobContext with snapshot information needed by flush and compaction.
@@ -852,9 +811,9 @@ 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)
@@ -969,23 +928,16 @@ 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:
+  Env* const env_;
   const std::string dbname_;
   std::string db_id_;
   std::unique_ptr<VersionSet> versions_;
   // Flag to check whether we allocated and own the info log file
   bool own_info_log_;
   const DBOptions initial_db_options_;
-  Env* const env_;
-  std::shared_ptr<FileSystem> fs_;
   const ImmutableDBOptions immutable_db_options_;
   MutableDBOptions mutable_db_options_;
   Statistics* stats_;
@@ -1013,10 +965,10 @@ class DBImpl : public DB {
   bool single_column_family_mode_;
 
   // The options to access storage files
-  const FileOptions file_options_;
+  const EnvOptions env_options_;
 
   // Additonal options for compaction and flush
-  FileOptions file_options_for_compaction_;
+  EnvOptions env_options_for_compaction_;
 
   std::unique_ptr<ColumnFamilyMemTablesImpl> column_family_memtables_;
 
@@ -1049,11 +1001,11 @@ class DBImpl : public DB {
 
   void NotifyOnFlushBegin(ColumnFamilyData* cfd, FileMetaData* file_meta,
                           const MutableCFOptions& mutable_cf_options,
-                          int job_id);
+                          int job_id, TableProperties prop);
 
-  void NotifyOnFlushCompleted(
-      ColumnFamilyData* cfd, const MutableCFOptions& mutable_cf_options,
-      std::list<std::unique_ptr<FlushJobInfo>>* flush_jobs_info);
+  void NotifyOnFlushCompleted(ColumnFamilyData* cfd, FileMetaData* file_meta,
+                              const MutableCFOptions& mutable_cf_options,
+                              int job_id, TableProperties prop);
 
   void NotifyOnCompactionBegin(ColumnFamilyData* cfd, Compaction* c,
                                const Status& st,
@@ -1142,24 +1094,10 @@ class DBImpl : public DB {
   // Recover the descriptor from persistent storage.  May do a significant
   // amount of work to recover recently logged updates.  Any changes to
   // be made to the descriptor are added to *edit.
-  // recovered_seq is set to less than kMaxSequenceNumber if the log's tail is
-  // skipped.
   virtual Status Recover(
       const std::vector<ColumnFamilyDescriptor>& column_families,
       bool read_only = false, bool error_if_log_file_exist = false,
-      bool error_if_data_exists_in_logs = false,
-      uint64_t* recovered_seq = nullptr);
-
-  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();
+      bool error_if_data_exists_in_logs = false);
 
  private:
   friend class DB;
@@ -1245,7 +1183,7 @@ class DBImpl : public DB {
   };
 
   // PurgeFileInfo is a structure to hold information of files to be deleted in
-  // purge_files_
+  // purge_queue_
   struct PurgeFileInfo {
     std::string fname;
     std::string dir_to_sync;
@@ -1371,10 +1309,9 @@ class DBImpl : public DB {
   // created between the calls CaptureCurrentFileNumberInPendingOutputs() and
   // ReleaseFileNumberFromPendingOutputs() can now be deleted (if it's not live
   // and blocked by any other pending_outputs_ calls)
-  void ReleaseFileNumberFromPendingOutputs(
-      std::unique_ptr<std::list<uint64_t>::iterator>& v);
+  void ReleaseFileNumberFromPendingOutputs(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
@@ -1399,10 +1336,8 @@ class DBImpl : public DB {
       JobContext* job_context, LogBuffer* log_buffer, Env::Priority thread_pri);
 
   // REQUIRES: log_numbers are sorted in ascending order
-  // corrupted_log_found is set to true if we recover from a corrupted log file.
   Status RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
-                         SequenceNumber* next_sequence, bool read_only,
-                         bool* corrupted_log_found);
+                         SequenceNumber* next_sequence, bool read_only);
 
   // The following two methods are used to flush a memtable to
   // storage. The first one is used at database RecoveryTime (when the
@@ -1425,7 +1360,6 @@ class DBImpl : public DB {
   Status ThrottleLowPriWritesIfNeeded(const WriteOptions& write_options,
                                       WriteBatch* my_batch);
 
-  // REQUIRES: mutex locked and in write thread.
   Status ScheduleFlushes(WriteContext* context);
 
   void MaybeFlushStatsCF(autovector<ColumnFamilyData*>* cfds);
@@ -1468,23 +1402,10 @@ class DBImpl : public DB {
       bool resuming_from_bg_err);
 
   inline void WaitForPendingWrites() {
-    mutex_.AssertHeld();
-    TEST_SYNC_POINT("DBImpl::WaitForPendingWrites:BeforeBlock");
-    // In case of pipelined write is enabled, wait for all pending memtable
-    // writers.
-    if (immutable_db_options_.enable_pipelined_write) {
-      // Memtable writers may call DB::Get in case max_successive_merges > 0,
-      // which may lock mutex. Unlocking mutex here to avoid deadlock.
-      mutex_.Unlock();
-      write_thread_.WaitForMemTableWriters();
-      mutex_.Lock();
-    }
-
     if (!immutable_db_options_.unordered_write) {
       // Then the writes are finished before the next write group starts
       return;
     }
-
     // Wait for the ones who already wrote to the WAL to finish their
     // memtable write.
     if (pending_memtable_writes_.load() != 0) {
@@ -1497,10 +1418,10 @@ class DBImpl : public DB {
   // REQUIRES: mutex locked and in write thread.
   void AssignAtomicFlushSeq(const autovector<ColumnFamilyData*>& cfds);
 
-  // REQUIRES: mutex locked and in write thread.
+  // REQUIRES: mutex locked
   Status SwitchWAL(WriteContext* write_context);
 
-  // REQUIRES: mutex locked and in write thread.
+  // REQUIRES: mutex locked
   Status HandleWriteBufferFull(WriteContext* write_context);
 
   // REQUIRES: mutex locked
@@ -1511,25 +1432,21 @@ 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 +1561,7 @@ 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();
 
@@ -1684,7 +1601,7 @@ class DBImpl : public DB {
   // Write a version edit to the MANIFEST.
   Status ReserveFileNumbersBeforeIngestion(
       ColumnFamilyData* cfd, uint64_t num,
-      std::unique_ptr<std::list<uint64_t>::iterator>& pending_output_elem,
+      std::list<uint64_t>::iterator* pending_output_elem,
       uint64_t* next_file_number);
 #endif  //! ROCKSDB_LITE
 
@@ -1704,81 +1621,6 @@ class DBImpl : public DB {
       const DBOptions& db_options,
       const std::vector<ColumnFamilyDescriptor>& column_families);
 
-  // Utility function to do some debug validation and sort the given vector
-  // of MultiGet keys
-  void PrepareMultiGetKeys(
-      const size_t num_keys, bool sorted,
-      autovector<KeyContext*, MultiGetContext::MAX_BATCH_SIZE>* key_ptrs);
-
-  // A structure to hold the information required to process MultiGet of keys
-  // belonging to one column family. For a multi column family MultiGet, there
-  // will be a container of these objects.
-  struct MultiGetColumnFamilyData {
-    ColumnFamilyHandle* cf;
-    ColumnFamilyData* cfd;
-
-    // For the batched MultiGet which relies on sorted keys, start specifies
-    // the index of first key belonging to this column family in the sorted
-    // list.
-    size_t start;
-
-    // For the batched MultiGet case, num_keys specifies the number of keys
-    // belonging to this column family in the sorted list
-    size_t num_keys;
-
-    // SuperVersion for the column family obtained in a manner that ensures a
-    // consistent view across all column families in the DB
-    SuperVersion* super_version;
-    MultiGetColumnFamilyData(ColumnFamilyHandle* column_family,
-                             SuperVersion* sv)
-        : cf(column_family),
-          cfd(static_cast<ColumnFamilyHandleImpl*>(cf)->cfd()),
-          start(0),
-          num_keys(0),
-          super_version(sv) {}
-
-    MultiGetColumnFamilyData(ColumnFamilyHandle* column_family, size_t first,
-                             size_t count, SuperVersion* sv)
-        : cf(column_family),
-          cfd(static_cast<ColumnFamilyHandleImpl*>(cf)->cfd()),
-          start(first),
-          num_keys(count),
-          super_version(sv) {}
-
-    MultiGetColumnFamilyData() = default;
-  };
-
-  // A common function to obtain a consistent snapshot, which can be implicit
-  // if the user doesn't specify a snapshot in read_options, across
-  // multiple column families for MultiGet. It will attempt to get an implicit
-  // snapshot without acquiring the db_mutes, but will give up after a few
-  // tries and acquire the mutex if a memtable flush happens. The template
-  // allows both the batched and non-batched MultiGet to call this with
-  // either an std::unordered_map or autovector of column families.
-  //
-  // If callback is non-null, the callback is refreshed with the snapshot
-  // sequence number
-  //
-  // A return value of true indicates that the SuperVersions were obtained
-  // from the ColumnFamilyData, whereas false indicates they are thread
-  // local
-  template <class T>
-  bool MultiCFSnapshot(
-      const ReadOptions& read_options, ReadCallback* callback,
-      std::function<MultiGetColumnFamilyData*(typename T::iterator&)>&
-          iter_deref_func,
-      T* cf_list, SequenceNumber* snapshot);
-
-  // The actual implementation of the batching MultiGet. The caller is expected
-  // 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(
-      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,
-      bool* is_blob_index);
-
   // table_cache_ provides its own synchronization
   std::shared_ptr<Cache> table_cache_;
 
@@ -1796,7 +1638,6 @@ class DBImpl : public DB {
   InstrumentedMutex log_write_mutex_;
 
   std::atomic<bool> shutting_down_;
-  std::atomic<bool> manual_compaction_paused_;
   // This condition variable is signaled on these conditions:
   // * whenever bg_compaction_scheduled_ goes down to 0
   // * if AnyManualCompaction, whenever a compaction finishes, even if it hasn't
@@ -1889,6 +1730,8 @@ class DBImpl : public DB {
 
   WriteController write_controller_;
 
+  std::unique_ptr<RateLimiter> low_pri_write_rate_limiter_;
+
   // Size of the last batch group. In slowdown mode, next write needs to
   // sleep if it uses up the quota.
   // Note: This is to protect memtable and compaction. If the batch only writes
@@ -1937,16 +1780,15 @@ class DBImpl : public DB {
   // ColumnFamilyData::pending_compaction_ == true)
   std::deque<ColumnFamilyData*> compaction_queue_;
 
-  // A map to store file numbers and filenames of the files to be purged
-  std::unordered_map<uint64_t, PurgeFileInfo> purge_files_;
+  // A queue to store filenames of the files to be purged
+  std::deque<PurgeFileInfo> purge_queue_;
 
   // A vector to store the file numbers that have been assigned to certain
-  // JobContext. Current implementation tracks table and blob files only.
-  std::unordered_set<uint64_t> files_grabbed_for_purge_;
+  // JobContext. Current implementation tracks ssts only.
+  std::vector<uint64_t> files_grabbed_for_purge_;
 
   // A queue to store log writers to close
   std::deque<log::Writer*> logs_to_free_queue_;
-  std::deque<SuperVersion*> superversions_to_free_queue_;
   int unscheduled_flushes_;
   int unscheduled_compactions_;
 
@@ -2061,13 +1903,13 @@ class DBImpl : public DB {
 
   // handle for scheduling stats dumping at fixed intervals
   // REQUIRES: mutex locked
-  std::unique_ptr<ROCKSDB_NAMESPACE::RepeatableThread> thread_dump_stats_;
+  std::unique_ptr<rocksdb::RepeatableThread> thread_dump_stats_;
 
   // handle for scheduling stats snapshoting at fixed intervals
   // REQUIRES: mutex locked
-  std::unique_ptr<ROCKSDB_NAMESPACE::RepeatableThread> thread_persist_stats_;
+  std::unique_ptr<rocksdb::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_;
@@ -2150,4 +1992,4 @@ static void ClipToRange(T* ptr, V minvalue, V maxvalue) {
   if (static_cast<V>(*ptr) < minvalue) *ptr = minvalue;
 }
 
-}  // namespace ROCKSDB_NAMESPACE
+}  // namespace rocksdb