Disable error as warning

The previuos change that use gcc-5 set USE_SSE to wrong flag by mistake. Fix it.

.arcconfig

@@ -1,6 +1,6 @@
 {
   "project_id" : "rocksdb",
-  "conduit_uri" : "https://phabricator.fb.com/api/",
+  "conduit_uri" : "https://reviews.facebook.net/",
   "copyright_holder" : "Facebook",
   "load" : [
     "arcanist_util"

.gitignore

@@ -32,19 +32,16 @@ build/
 ldb
 manifest_dump
 sst_dump
-column_aware_encoding_exp
 util/build_version.cc
 build_tools/VALGRIND_LOGS/
 coverage/COVERAGE_REPORT
 .gdbhistory
-.gdb_history
 package/
 .phutil_module_cache
 unity.a
 tags
 rocksdb_dump
 rocksdb_undump
-db_test2
 
 java/out
 java/target
@@ -66,8 +63,3 @@ java/javadoc
 scan_build_report/
 t
 LOG
-
-db_logs/
-tp2/
-fbcode/
-fbcode

.travis.yml

@@ -1,58 +1,41 @@
 sudo: false
-dist: trusty
 language: cpp
-os:
-  - linux
-  - osx
-compiler:
-  - clang
-  - gcc
-jdk:
-  - oraclejdk7
-cache:
-  - ccache
-  - apt
-
-addons:
-   apt:
-      sources: ['ubuntu-toolchain-r-test', 'llvm-toolchain-precise-3.6']
-      packages: ['clang-3.6' , 'g++-6', 'zlib1g-dev', 'libbz2-dev', 'libsnappy-dev', 'curl', 'libgflags-dev']
-env:
-  - TEST_GROUP=platform_dependent1
-  - TEST_GROUP=platform_dependent2
-  - TEST_GROUP=platform_dependent3
-  - TEST_GROUP=1
-  - TEST_GROUP=2
-  # Run java tests
-  - JOB_NAME=java_test
-  # Build ROCKSDB_LITE
-  - JOB_NAME=lite_build
 
 matrix:
-  exclude:
-  - os: osx
-    compiler: gcc
-  - os: osx
-    env: TEST_GROUP=1
-  - os: osx
-    env: TEST_GROUP=2
+  include:
+    - os: linux
+      compiler: clang
+      env: COMPILER=clang++-3.6
+      addons:
+         apt:
+            sources: ['ubuntu-toolchain-r-test', 'llvm-toolchain-precise-3.6']
+            packages: ['clang-3.6', 'clang-format-3.6', 'zlib1g-dev', 'libbz2-dev', 'libsnappy-dev', 'curl']
+    - os: osx
+      compiler: clang
+
+install:
+  # Build gflags
+  # TODO(noetzli): Remove when gflags available through Travis
+  - pushd /tmp/ && curl -L https://github.com/gflags/gflags/archive/v2.1.2.tar.gz -o gflags.tar.gz && tar xfz gflags.tar.gz && cd gflags-2.1.2 && cmake . && make && popd
+  # Download clang-format-diff.py to check source code formatting
+  - pushd /tmp/ && curl -L http://llvm.org/svn/llvm-project/cfe/trunk/tools/clang-format/clang-format-diff.py -o clang-format-diff.py && chmod +x clang-format-diff.py && popd
 
 before_script:
-  - if [[ "${TRAVIS_OS_NAME}" == 'linux' && "${CXX}" == 'clang++' ]]; then CXX=clang++-3.6; fi
-  # test one linux g++ build with g++-6
-  - if [[ "${TRAVIS_OS_NAME}" == 'linux' && "${CXX}" == 'g++' && "${JOB_NAME}" == 'unittests' ]]; then CXX=g++-6; fi
-  # Limit the maximum number of open file descriptors to 8192
-  - ulimit -n 8192 || true
+  # Add gflags to include/library paths
+  # TODO(noetzli): Remove when gflags available through Travis
+  - export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/tmp/gflags-2.1.2/lib"
+  - export LIBRARY_PATH="$LIBRARY_PATH:/tmp/gflags-2.1.2/lib"
+  - export CPLUS_INCLUDE_PATH="$CPLUS_INCLUDE_PATH:/tmp/gflags-2.1.2/include"
+  - if [ -n "${COMPILER}" ]; then CXX=${COMPILER}; fi
+  - if [[ "${TRAVIS_OS_NAME}" == 'osx' ]]; then brew install gflags snappy; fi
+  - ulimit -n 2000 || true
 
+# Lousy hack to disable use and testing of fallocate, which doesn't behave quite
+# as EnvPosixTest::AllocateTest expects within the Travis OpenVZ environment.
 script:
-  - ${CXX} --version
-  - if [[ "${TEST_GROUP}" == 'platform_dependent1' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_END=external_sst_file_basic_test make -j4 check_some; fi
-  - if [[ "${TEST_GROUP}" == 'platform_dependent2' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=external_sst_file_basic_test ROCKSDBTESTS_END=checkpoint_test make -j4 check_some; fi
-  - if [[ "${TEST_GROUP}" == 'platform_dependent3' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=checkpoint_test ROCKSDBTESTS_END=db_block_cache_test make -j4 check_some; fi
-  - if [[ "${TEST_GROUP}" == '1' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=db_block_cache_test ROCKSDBTESTS_END=comparator_db_test make -j4 check_some; fi
-  - if [[ "${TEST_GROUP}" == '2' ]]; then OPT=-DTRAVIS V=1 ROCKSDBTESTS_START=comparator_db_test make -j4 check_some; fi
-  - if [[ "${JOB_NAME}" == 'java_test' ]]; then OPT=-DTRAVIS V=1 make clean jclean rocksdbjava jtest; fi
-  - if [[ "${JOB_NAME}" == 'lite_build' ]]; then OPT="-DTRAVIS -DROCKSDB_LITE" V=1 make -j4 static_lib; fi
+  - if [[ "${TRAVIS_OS_NAME}" == 'linux' ]]; then OPT=-DTRAVIS CLANG_FORMAT_DIFF=/tmp/clang-format-diff.py make format || true; fi
+  - OPT=-DTRAVIS V=1 make -j4 check && OPT=-DTRAVIS V=1 make clean jclean rocksdbjava jtest && make clean && OPT="-DTRAVIS -DROCKSDB_LITE" V=1 make -j4 check
+
 notifications:
     email:
       - leveldb@fb.com

CMakeLists.txt

@@ -1,8 +1,7 @@
-# Prerequisites for Windows:
-#     This cmake build is for Windows 64-bit only.
+# This cmake build is for Windows 64-bit only.
 #
 # Prerequisites:
-#     You must have at least Visual Studio 2015 Update 3. Start the Developer Command Prompt window that is a part of Visual Studio installation.
+#     You must have Visual Studio 2013 Update 4 installed. Start the Developer Command Prompt window that is a part of Visual Studio installation.
 #     Run the build commands from within the Developer Command Prompt window to have paths to the compiler and runtime libraries set.
 #     You must have git.exe in your %PATH% environment variable.
 #
@@ -14,7 +13,8 @@
 #        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 14 Win64" -DGFLAGS=1 -DSNAPPY=1 -DJEMALLOC=1 -DJNI=1 ..
+#        sample command: cmake -G "Visual Studio 12 Win64" -DGFLAGS=1 -DSNAPPY=1 -DJEMALLOC=1 ..
+#        OR for VS Studio 15 cmake -G "Visual Studio 14 Win64" -DGFLAGS=1 -DSNAPPY=1 -DJEMALLOC=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 ot use all avail cores)
 #        msbuild rocksdb.sln
@@ -25,149 +25,42 @@
 # 5. And release mode (/m[:<N>] is also supported)
 #        msbuild rocksdb.sln /p:Configuration=Release
 #
-# Linux:
-#
-# 1. Install a recent toolchain such as devtoolset-3 if you're on a older distro. C++11 required.
-# 2. mkdir build; cd build
-# 3. cmake ..
-# 4. make -j
 
 cmake_minimum_required(VERSION 2.6)
 project(rocksdb)
 
-if(POLICY CMP0042)
-  cmake_policy(SET CMP0042 NEW)
-endif()
+include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
 
-list(APPEND CMAKE_MODULE_PATH "${CMAKE_SOURCE_DIR}/cmake/modules/")
-
-if(WIN32)
-  include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
-else()
-  option(WITH_JEMALLOC "build with JeMalloc" OFF)
-  if(WITH_JEMALLOC)
-    find_package(JeMalloc REQUIRED)
-    add_definitions(-DROCKSDB_JEMALLOC)
-    include_directories(${JEMALLOC_INCLUDE_DIR})
-  endif()
-  if(CMAKE_SYSTEM_NAME STREQUAL "FreeBSD")
-    # FreeBSD has jemaloc as default malloc
-    add_definitions(-DROCKSDB_JEMALLOC)
-    set(WITH_JEMALLOC ON)
-  endif()
-  option(WITH_SNAPPY "build with SNAPPY" OFF)
-  if(WITH_SNAPPY)
-    find_package(snappy REQUIRED)
-    add_definitions(-DSNAPPY)
-    include_directories(${SNAPPY_INCLUDE_DIR})
-    list(APPEND THIRDPARTY_LIBS ${SNAPPY_LIBRARIES})
-  endif()
-endif()
-
-if(WIN32)
-  execute_process(COMMAND powershell -Command "Get-Date -format MM_dd_yyyy" OUTPUT_VARIABLE DATE)
-  execute_process(COMMAND powershell -Command "Get-Date -format HH:mm:ss" OUTPUT_VARIABLE TIME)
-  string(REGEX REPLACE "(..)_(..)_..(..).*" "\\1/\\2/\\3" DATE "${DATE}")
-  string(REGEX REPLACE "(..):(.....).*" " \\1:\\2" TIME "${TIME}")
-  set(GIT_DATE_TIME "${DATE} ${TIME}")
-else()
-  execute_process(COMMAND date "+%Y/%m/%d %H:%M:%S" OUTPUT_VARIABLE DATETIME)
-  string(REGEX REPLACE "\n" "" DATETIME ${DATETIME})
-  set(GIT_DATE_TIME "${DATETIME}")
-endif()
+execute_process(COMMAND $ENV{COMSPEC} " /C date /T" OUTPUT_VARIABLE DATE)
+execute_process(COMMAND $ENV{COMSPEC} " /C time /T" OUTPUT_VARIABLE TIME)
+string(REGEX REPLACE "(..)/(..)/..(..).*" "\\1/\\2/\\3" DATE ${DATE})
+string(REGEX REPLACE "(..):(.....).*" " \\1:\\2" TIME ${TIME})
+string(CONCAT GIT_DATE_TIME ${DATE} ${TIME})
 
 find_package(Git)
 
 if (GIT_FOUND AND EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/.git")
-  if(WIN32)
     execute_process(COMMAND $ENV{COMSPEC} /C ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR} rev-parse HEAD OUTPUT_VARIABLE GIT_SHA)
-  else()
-    execute_process(COMMAND ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR} rev-parse HEAD OUTPUT_VARIABLE GIT_SHA)
-  endif()
 else()
-  set(GIT_SHA 0)
+    set(GIT_SHA 0)
 endif()
 
-string(REGEX REPLACE "[^0-9a-f]+" "" GIT_SHA "${GIT_SHA}")
+string(REGEX REPLACE "[^0-9a-f]+" "" GIT_SHA ${GIT_SHA})
 
-if (NOT WIN32)
-  execute_process(COMMAND
-      "./build_tools/version.sh" "full"
-      WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
-      OUTPUT_VARIABLE ROCKSDB_VERSION
-  )
-  string(STRIP "${ROCKSDB_VERSION}" ROCKSDB_VERSION)
-  execute_process(COMMAND
-      "./build_tools/version.sh" "major"
-      WORKING_DIRECTORY ${PROJECT_SOURCE_DIR}
-      OUTPUT_VARIABLE ROCKSDB_VERSION_MAJOR
-  )
-  string(STRIP "${ROCKSDB_VERSION_MAJOR}" ROCKSDB_VERSION_MAJOR)
-endif()
+set(BUILD_VERSION_CC ${CMAKE_CURRENT_SOURCE_DIR}/util/build_version.cc)
 
-set(BUILD_VERSION_CC ${CMAKE_BINARY_DIR}/build_version.cc)
-configure_file(util/build_version.cc.in ${BUILD_VERSION_CC} @ONLY)
-add_library(build_version OBJECT ${BUILD_VERSION_CC})
-target_include_directories(build_version PRIVATE
-  ${CMAKE_CURRENT_SOURCE_DIR}/util)
-if(WIN32)
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Zi /nologo  /EHsc /GS /Gd /GR /GF /fp:precise /Zc:wchar_t /Zc:forScope /errorReport:queue")
+add_custom_command(OUTPUT ${BUILD_VERSION_CC}
+    COMMAND echo "#include \"build_version.h\"" > ${BUILD_VERSION_CC}
+    COMMAND echo "const char* rocksdb_build_git_sha = \"rocksdb_build_git_sha:${GIT_SHA}\";" >> ${BUILD_VERSION_CC}
+    COMMAND echo "const char* rocksdb_build_git_datetime = \"rocksdb_build_git_datetime:${GIT_DATE_TIME}\";" >> ${BUILD_VERSION_CC}
+    COMMAND echo const char* rocksdb_build_compile_date = __DATE__\; >> ${BUILD_VERSION_CC}
+)
 
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /W3 /wd4127 /wd4800 /wd4996 /wd4351")
-else()
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
-  if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-omit-frame-pointer")
-    include(CheckCXXCompilerFlag)
-    CHECK_CXX_COMPILER_FLAG("-momit-leaf-frame-pointer" HAVE_OMIT_LEAF_FRAME_POINTER)
-    if(HAVE_OMIT_LEAF_FRAME_POINTER)
-      set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -momit-leaf-frame-pointer")
-    endif()
-  endif()
-endif()
+add_custom_target(GenerateBuildVersion DEPENDS ${BUILD_VERSION_CC})
 
-option(FAIL_ON_WARNINGS "Treat compile warnings as errors" ON)
-if(FAIL_ON_WARNINGS)
-  if(MSVC)
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /WX")
-  else() # assume GCC
-    set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Werror")
-  endif()
-endif()
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Zi /nologo  /EHsc /GS /Gd /GR /GF /fp:precise /Zc:wchar_t /Zc:forScope /errorReport:queue")
 
-option(WITH_ASAN "build with ASAN" OFF)
-if(WITH_ASAN)
-  add_definitions(-DROCKSDB_TSAN_RUN)
-  set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=address")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=address")
-  set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fsanitize=address")
-  if(WITH_JEMALLOC)
-    message(FATAL "ASAN does not work well with JeMalloc")
-  endif()
-endif()
-
-option(WITH_TSAN "build with TSAN" OFF)
-if(WITH_TSAN)
-  set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=thread -pie")
-  add_definitions(-DROCKSDB_TSAN_RUN)
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=thread -fPIC")
-  set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fsanitize=thread -fPIC")
-  if(WITH_JEMALLOC)
-    message(FATAL "TSAN does not work well with JeMalloc")
-  endif()
-endif()
-
-option(WITH_UBSAN "build with UBSAN" OFF)
-if(WITH_UBSAN)
-  set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=undefined")
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=undefined")
-  set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fsanitize=undefined")
-  if(WITH_JEMALLOC)
-    message(FATAL "UBSAN does not work well with JeMalloc")
-  endif()
-endif()
+set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /W3 /WX /wd4127 /wd4800 /wd4996 /wd4351")
 
 # Used to run CI build and tests so we can run faster
 set(OPTIMIZE_DEBUG_DEFAULT 0)        # Debug build is unoptimized by default use -DOPTDBG=1 to optimize
@@ -178,94 +71,34 @@ else()
    set(OPTIMIZE_DEBUG ${OPTIMIZE_DEBUG_DEFAULT})
 endif()
 
-if(WIN32)
-  if((${OPTIMIZE_DEBUG} EQUAL 1))
-    message(STATUS "Debug optimization is enabled")
-    set(CMAKE_CXX_FLAGS_DEBUG "/Oxt /MDd")
-  else()
-    set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1 /Gm /MDd")
-  endif()
-  set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /Oxt /Zp8 /Gm- /Gy /MD")
-
-  set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} /DEBUG")
-  set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} /DEBUG")
+if((${OPTIMIZE_DEBUG} EQUAL 1))
+   message(STATUS "Debug optimization is enabled")
+   set(CMAKE_CXX_FLAGS_DEBUG "/Oxt /MDd")
+else()
+   set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1 /Gm /MDd")
 endif()
 
-if(CMAKE_COMPILER_IS_GNUCXX)
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-builtin-memcmp")
-endif()
+set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /Oxt /Zp8 /Gm- /Gy /MD")
 
-option(ROCKSDB_LITE "Build RocksDBLite version" OFF)
-if(ROCKSDB_LITE)
-  add_definitions(-DROCKSDB_LITE)
-  set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-exceptions")
-endif()
+set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} /DEBUG")
+set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} /DEBUG")
 
-if(CMAKE_SYSTEM_NAME MATCHES "Cygwin")
-  add_definitions(-fno-builtin-memcmp -DCYGWIN)
-elseif(CMAKE_SYSTEM_NAME MATCHES "Darwin")
-  add_definitions(-DOS_MACOSX)
-  if(CMAKE_SYSTEM_PROCESSOR MATCHES arm)
-    add_definitions(-DIOS_CROSS_COMPILE -DROCKSDB_LITE)
-    # no debug info for IOS, that will make our library big
-    add_definitions(-DNDEBUG)
-  endif()
-elseif(CMAKE_SYSTEM_NAME MATCHES "Linux")
-  add_definitions(-DOS_LINUX)
-elseif(CMAKE_SYSTEM_NAME MATCHES "SunOS")
-  add_definitions(-DOS_SOLARIS)
-elseif(CMAKE_SYSTEM_NAME MATCHES "FreeBSD")
-  add_definitions(-DOS_FREEBSD)
-elseif(CMAKE_SYSTEM_NAME MATCHES "NetBSD")
-  add_definitions(-DOS_NETBSD)
-elseif(CMAKE_SYSTEM_NAME MATCHES "OpenBSD")
-  add_definitions(-DOS_OPENBSD)
-elseif(CMAKE_SYSTEM_NAME MATCHES "DragonFly")
-  add_definitions(-DOS_DRAGONFLYBSD)
-elseif(CMAKE_SYSTEM_NAME MATCHES "Android")
-  add_definitions(-DOS_ANDROID)
-elseif(CMAKE_SYSTEM_NAME MATCHES "Windows")
-  add_definitions(-DWIN32 -DOS_WIN -D_MBCS -DWIN64 -DNOMINMAX)
-endif()
-
-if(NOT WIN32)
-  add_definitions(-DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX)
-endif()
-
-option(WITH_FALLOCATE "build with fallocate" ON)
-
-if(WITH_FALLOCATE)
-  include(CheckCSourceCompiles)
-  CHECK_C_SOURCE_COMPILES("
-#include <fcntl.h>
-#include <linux/falloc.h>
-int main() {
- int fd = open(\"/dev/null\", 0);
- fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
-}
-" HAVE_FALLOCATE)
-  if(HAVE_FALLOCATE)
-    add_definitions(-DROCKSDB_FALLOCATE_PRESENT)
-  endif()
-endif()
-
-include(CheckFunctionExists)
-CHECK_FUNCTION_EXISTS(malloc_usable_size HAVE_MALLOC_USABLE_SIZE)
-if(HAVE_MALLOC_USABLE_SIZE)
-  add_definitions(-DROCKSDB_MALLOC_USABLE_SIZE)
-endif()
+add_definitions(-DWIN32 -DOS_WIN -D_MBCS -DWIN64)
 
 include_directories(${PROJECT_SOURCE_DIR})
 include_directories(${PROJECT_SOURCE_DIR}/include)
-include_directories(SYSTEM ${PROJECT_SOURCE_DIR}/third-party/gtest-1.7.0/fused-src)
-find_package(Threads REQUIRED)
+include_directories(${PROJECT_SOURCE_DIR}/third-party/gtest-1.7.0/fused-src)
+
+set(ROCKSDB_LIBS rocksdblib${ARTIFACT_SUFFIX})
+set(THIRDPARTY_LIBS ${THIRDPARTY_LIBS} gtest)
+set(SYSTEM_LIBS Shlwapi.lib Rpcrt4.lib)
+
+set(LIBS ${ROCKSDB_LIBS} ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
 
 add_subdirectory(third-party/gtest-1.7.0/fused-src/gtest)
 
 # Main library source code
-
 set(SOURCES
-        db/auto_roll_logger.cc
         db/builder.cc
         db/c.cc
         db/column_family.cc
@@ -281,10 +114,8 @@ set(SOURCES
         db/db_impl_debug.cc
         db/db_impl_experimental.cc
         db/db_impl_readonly.cc
-        db/db_info_dumper.cc
         db/db_iter.cc
         db/event_helpers.cc
-        db/external_sst_file_ingestion_job.cc
         db/experimental.cc
         db/filename.cc
         db/file_indexer.cc
@@ -300,8 +131,8 @@ set(SOURCES
         db/memtable_list.cc
         db/merge_helper.cc
         db/merge_operator.cc
-        db/range_del_aggregator.cc
         db/repair.cc
+        db/slice.cc
         db/snapshot_impl.cc
         db/table_cache.cc
         db/table_properties_collector.cc
@@ -317,9 +148,10 @@ set(SOURCES
         memtable/hash_cuckoo_rep.cc
         memtable/hash_linklist_rep.cc
         memtable/hash_skiplist_rep.cc
-        memtable/skiplistrep.cc
-        memtable/vectorrep.cc
         port/stack_trace.cc
+        port/win/env_win.cc
+        port/win/port_win.cc
+        port/win/win_logger.cc
         table/adaptive_table_factory.cc
         table/block.cc
         table/block_based_filter_block.cc
@@ -327,6 +159,7 @@ set(SOURCES
         table/block_based_table_factory.cc
         table/block_based_table_reader.cc
         table/block_builder.cc
+        table/block_hash_index.cc
         table/block_prefix_index.cc
         table/bloom_block.cc
         table/cuckoo_table_builder.cc
@@ -336,57 +169,53 @@ set(SOURCES
         table/format.cc
         table/full_filter_block.cc
         table/get_context.cc
-        table/index_builder.cc
         table/iterator.cc
-        table/merging_iterator.cc
+        table/merger.cc
         table/sst_file_writer.cc
         table/meta_blocks.cc
-        table/partitioned_filter_block.cc
+        table/mock_table.cc
         table/plain_table_builder.cc
         table/plain_table_factory.cc
         table/plain_table_index.cc
         table/plain_table_key_coding.cc
         table/plain_table_reader.cc
-        table/persistent_cache_helper.cc
         table/table_properties.cc
         table/two_level_iterator.cc
         tools/sst_dump_tool.cc
-        tools/db_bench_tool.cc
         tools/dump/db_dump_tool.cc
         util/arena.cc
+        util/auto_roll_logger.cc
         util/bloom.cc
-        util/cf_options.cc
-        util/clock_cache.cc
+        util/build_version.cc
+        util/cache.cc
         util/coding.cc
         util/compaction_job_stats_impl.cc
         util/comparator.cc
         util/concurrent_arena.cc
         util/crc32c.cc
-        util/db_options.cc
-        util/delete_scheduler.cc
+        util/db_info_dumper.cc
+        util/delete_scheduler_impl.cc
         util/dynamic_bloom.cc
         util/env.cc
-        util/env_chroot.cc
         util/env_hdfs.cc
         util/event_logger.cc
         util/file_util.cc
         util/file_reader_writer.cc
-        util/sst_file_manager_impl.cc
         util/filter_policy.cc
         util/hash.cc
         util/histogram.cc
-        util/histogram_windowing.cc
         util/instrumented_mutex.cc
         util/iostats_context.cc
-        
-        util/lru_cache.cc
         tools/ldb_cmd.cc
         tools/ldb_tool.cc
         util/logging.cc
         util/log_buffer.cc
         util/memenv.cc
+        util/mock_env.cc
         util/murmurhash.cc
+        util/mutable_cf_options.cc
         util/options.cc
+        util/options_builder.cc
         util/options_helper.cc
         util/options_parser.cc
         util/options_sanity_check.cc
@@ -394,49 +223,39 @@ set(SOURCES
         util/perf_level.cc
         util/random.cc
         util/rate_limiter.cc
-        util/sharded_cache.cc
+        util/skiplistrep.cc
         util/slice.cc
         util/statistics.cc
         util/status.cc
         util/status_message.cc
         util/string_util.cc
         util/sync_point.cc
+        util/testharness.cc
         util/testutil.cc
         util/thread_local.cc
-        util/threadpool_imp.cc
         util/thread_status_impl.cc
         util/thread_status_updater.cc
         util/thread_status_util.cc
         util/thread_status_util_debug.cc
-        util/transaction_test_util.cc
+        util/vectorrep.cc
+        util/xfunc.cc
         util/xxhash.cc
         utilities/backupable/backupable_db.cc
-        utilities/blob_db/blob_db.cc
         utilities/checkpoint/checkpoint.cc
-        utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
-        utilities/date_tiered/date_tiered_db_impl.cc
         utilities/document/document_db.cc
         utilities/document/json_document.cc
         utilities/document/json_document_builder.cc
         utilities/env_mirror.cc
+        utilities/flashcache/flashcache.cc
         utilities/geodb/geodb_impl.cc
         utilities/leveldb_options/leveldb_options.cc
-        utilities/lua/rocks_lua_compaction_filter.cc
         utilities/memory/memory_util.cc
         utilities/merge_operators/string_append/stringappend.cc
         utilities/merge_operators/string_append/stringappend2.cc
         utilities/merge_operators/put.cc
-        utilities/merge_operators/max.cc
         utilities/merge_operators/uint64add.cc
-        utilities/option_change_migration/option_change_migration.cc
         utilities/options/options_util.cc
-        utilities/persistent_cache/block_cache_tier.cc
-        utilities/persistent_cache/block_cache_tier_file.cc
-        utilities/persistent_cache/block_cache_tier_metadata.cc
-        utilities/persistent_cache/persistent_cache_tier.cc
-        utilities/persistent_cache/volatile_tier_impl.cc
         utilities/redis/redis_lists.cc
-        utilities/simulator_cache/sim_cache.cc
         utilities/spatialdb/spatial_db.cc
         utilities/table_properties_collectors/compact_on_deletion_collector.cc
         utilities/transactions/optimistic_transaction_impl.cc
@@ -450,85 +269,40 @@ set(SOURCES
         utilities/ttl/db_ttl_impl.cc
         utilities/write_batch_with_index/write_batch_with_index.cc
         utilities/write_batch_with_index/write_batch_with_index_internal.cc
-        utilities/col_buf_encoder.cc
-        utilities/col_buf_decoder.cc
-        utilities/column_aware_encoding_util.cc
-        $<TARGET_OBJECTS:build_version>)
+)
 
-if(WIN32)
-  list(APPEND SOURCES
-    port/win/io_win.cc
-    port/win/env_win.cc
-    port/win/env_default.cc
-    port/win/port_win.cc
-    port/win/win_logger.cc
-    port/win/win_thread.cc
-    port/win/xpress_win.cc)
-else()
-  list(APPEND SOURCES
-    port/port_posix.cc
-    util/env_posix.cc
-    util/io_posix.cc)
-endif()
+# 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
+    util/thread_status_updater_debug.cc
+)
 
-if(WIN32)
-  set(SYSTEM_LIBS ${SYSTEM_LIBS} Shlwapi.lib Rpcrt4.lib)
-  set(ROCKSDB_STATIC_LIB rocksdblib${ARTIFACT_SUFFIX})
-  set(ROCKSDB_IMPORT_LIB rocksdb${ARTIFACT_SUFFIX})
-  set(LIBS ${ROCKSDB_STATIC_LIB} ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
-else()
-  set(SYSTEM_LIBS ${CMAKE_THREAD_LIBS_INIT} rt)
-  set(ROCKSDB_STATIC_LIB rocksdb${ARTIFACT_SUFFIX})
-  set(ROCKSDB_SHARED_LIB rocksdb-shared)
-  set(ROCKSDB_IMPORT_LIB ${ROCKSDB_SHARED_LIB})
-  set(LIBS ${ROCKSDB_SHARED_LIB} ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
+add_library(rocksdblib${ARTIFACT_SUFFIX} ${SOURCES})
+set_target_properties(rocksdblib${ARTIFACT_SUFFIX} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/rocksdblib${ARTIFACT_SUFFIX}.pdb")
+add_dependencies(rocksdblib${ARTIFACT_SUFFIX} GenerateBuildVersion)
 
-  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 ${ROCKSDB_VERSION_MAJOR}
-                        CXX_STANDARD 11
-                        OUTPUT_NAME "rocksdb")
-endif()
+add_library(rocksdb${ARTIFACT_SUFFIX} SHARED ${SOURCES})
+set_target_properties(rocksdb${ARTIFACT_SUFFIX} PROPERTIES COMPILE_FLAGS "-DROCKSDB_DLL -DROCKSDB_LIBRARY_EXPORTS /Fd${CMAKE_CFG_INTDIR}/rocksdb${ARTIFACT_SUFFIX}.pdb")
+add_dependencies(rocksdb${ARTIFACT_SUFFIX} GenerateBuildVersion)
+target_link_libraries(rocksdb${ARTIFACT_SUFFIX} ${LIBS})
 
-option(WITH_LIBRADOS "Build with librados" OFF)
-if(WITH_LIBRADOS)
-  list(APPEND SOURCES
-    utilities/env_librados.cc)
-  list(APPEND THIRDPARTY_LIBS rados)
-endif()
+set(APPS
+        db/db_bench.cc
+        db/memtablerep_bench.cc
+        table/table_reader_bench.cc
+        tools/db_stress.cc
+        tools/write_stress.cc
+        tools/db_repl_stress.cc
+        tools/sst_dump.cc
+        tools/dump/rocksdb_dump.cc
+        tools/dump/rocksdb_undump.cc
+        util/cache_bench.cc
+)
 
-add_library(${ROCKSDB_STATIC_LIB} STATIC ${SOURCES})
-target_link_libraries(${ROCKSDB_STATIC_LIB}
-  ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
-
-if(WIN32)
-  set_target_properties(${ROCKSDB_STATIC_LIB} PROPERTIES
-    COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_STATIC_LIB}.pdb")
-endif()
-
-if(WIN32)
-  add_library(${ROCKSDB_IMPORT_LIB} SHARED ${SOURCES})
-  target_link_libraries(${ROCKSDB_IMPORT_LIB}
-    ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
-  set_target_properties(${ROCKSDB_IMPORT_LIB} PROPERTIES
-    COMPILE_FLAGS "-DROCKSDB_DLL -DROCKSDB_LIBRARY_EXPORTS /Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_IMPORT_LIB}.pdb")
-else()
-endif()
-
-option(WITH_JNI "build with JNI" OFF)
-if(WITH_JNI OR JNI)
-  message(STATUS "JNI library is enabled")
-  add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/java)
-else()
-  message(STATUS "JNI library is disabled")
-endif()
+set(C_TESTS db/c_test.c)
 
 set(TESTS
-        db/auto_roll_logger_test.cc
         db/column_family_test.cc
         db/compact_files_test.cc
         db/compaction_iterator_test.cc
@@ -538,31 +312,17 @@ set(TESTS
         db/comparator_db_test.cc
         db/corruption_test.cc
         db/cuckoo_table_db_test.cc
-        db/db_basic_test.cc
+        db/db_iter_test.cc
+        db/db_test.cc
         db/db_compaction_filter_test.cc
         db/db_compaction_test.cc
         db/db_dynamic_level_test.cc
         db/db_inplace_update_test.cc
-        db/db_iter_test.cc
         db/db_log_iter_test.cc
-        db/db_memtable_test.cc
-        db/db_merge_operator_test.cc
-        db/db_options_test.cc
-        db/db_properties_test.cc
-        db/db_table_properties_test.cc
-        db/db_tailing_iter_test.cc
-        db/db_test.cc
-        db/db_test2.cc
-        db/db_block_cache_test.cc
-        db/db_bloom_filter_test.cc
-        db/db_flush_test.cc
-        db/db_iterator_test.cc
-        db/db_range_del_test.cc
-        db/db_sst_test.cc
-        db/external_sst_file_basic_test.cc
-        db/external_sst_file_test.cc
         db/db_universal_compaction_test.cc
         db/db_wal_test.cc
+        db/db_tailing_iter_test.cc
+        db/db_table_properties_test.cc
         db/dbformat_test.cc
         db/deletefile_test.cc
         db/fault_injection_test.cc
@@ -580,7 +340,6 @@ set(TESTS
         db/perf_context_test.cc
         db/plain_table_db_test.cc
         db/prefix_test.cc
-        db/repair_test.cc
         db/skiplist_test.cc
         db/table_properties_collector_test.cc
         db/version_builder_test.cc
@@ -590,56 +349,48 @@ set(TESTS
         db/write_batch_test.cc
         db/write_callback_test.cc
         db/write_controller_test.cc
-        db/db_io_failure_test.cc
         table/block_based_filter_block_test.cc
+        table/block_hash_index_test.cc
         table/block_test.cc
         table/cuckoo_table_builder_test.cc
         table/cuckoo_table_reader_test.cc
         table/full_filter_block_test.cc
         table/merger_test.cc
         table/table_test.cc
+        tools/db_sanity_test.cc
         tools/ldb_cmd_test.cc
         tools/reduce_levels_test.cc
         tools/sst_dump_test.cc
         util/arena_test.cc
         util/autovector_test.cc
+        util/auto_roll_logger_test.cc
         util/bloom_test.cc
         util/cache_test.cc
         util/coding_test.cc
         util/crc32c_test.cc
         util/delete_scheduler_test.cc
         util/dynamic_bloom_test.cc
-        util/env_basic_test.cc
         util/env_test.cc
         util/event_logger_test.cc
         util/filelock_test.cc
         util/file_reader_writer_test.cc
         util/heap_test.cc
         util/histogram_test.cc
-        util/iostats_context_test.cc
-        util/lru_cache_test.cc
+        util/memenv_test.cc
         util/mock_env_test.cc
-        util/options_settable_test.cc
         util/options_test.cc
         util/rate_limiter_test.cc
         util/slice_transform_test.cc
-        util/statistics_test.cc
         util/thread_list_test.cc
         util/thread_local_test.cc
         utilities/backupable/backupable_db_test.cc
-        utilities/blob_db/blob_db_test.cc
         utilities/checkpoint/checkpoint_test.cc
-        utilities/date_tiered/date_tiered_test.cc
         utilities/document/document_db_test.cc
         utilities/document/json_document_test.cc
-        utilities/object_registry_test.cc
         utilities/geodb/geodb_test.cc
         utilities/memory/memory_test.cc
         utilities/merge_operators/string_append/stringappend_test.cc
-        utilities/option_change_migration/option_change_migration_test.cc
         utilities/options/options_util_test.cc
-        utilities/persistent_cache/hash_table_test.cc
-        utilities/persistent_cache/persistent_cache_test.cc
         utilities/redis/redis_lists_test.cc
         utilities/spatialdb/spatial_db_test.cc
         utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
@@ -647,45 +398,21 @@ set(TESTS
         utilities/transactions/transaction_test.cc
         utilities/ttl/ttl_test.cc
         utilities/write_batch_with_index/write_batch_with_index_test.cc
-        utilities/column_aware_encoding_test.cc
-        utilities/lua/rocks_lua_test.cc
 )
-if(WITH_LIBRADOS)
-  list(APPEND TESTS utilities/env_librados_test.cc)
-endif()
 
-set(BENCHMARKS
-  tools/db_bench.cc
-  table/table_reader_bench.cc
-  util/cache_bench.cc
-  db/memtablerep_bench.cc
-  utilities/column_aware_encoding_exp.cc
-  utilities/persistent_cache/hash_table_bench.cc)
-add_library(testharness OBJECT 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})
+set(EXES ${APPS})
+
+foreach(sourcefile ${EXES})
+    string(REPLACE ".cc" "" exename ${sourcefile})
+    string(REGEX REPLACE "^((.+)/)+" "" exename ${exename})
+    add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile})
+    target_link_libraries(${exename}${ARTIFACT_SUFFIX} ${LIBS})
+endforeach(sourcefile ${EXES})
 
-# 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
-    table/mock_table.cc
-    util/mock_env.cc
-    util/fault_injection_test_env.cc
-    util/thread_status_updater_debug.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 ${TESTUTIL_SOURCE})
-if(WIN32)
-  set_target_properties(${TESTUTILLIB} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/testutillib${ARTIFACT_SUFFIX}.pdb")
-endif()
+set_target_properties(${TESTUTILLIB} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/testutillib${ARTIFACT_SUFFIX}.pdb")
 set_target_properties(${TESTUTILLIB}
       PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
       EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
@@ -696,23 +423,18 @@ set_target_properties(${TESTUTILLIB}
 set(TEST_EXES ${TESTS})
 
 foreach(sourcefile ${TEST_EXES})
-    get_filename_component(exename ${sourcefile} NAME_WE)
-    add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile}
-      $<TARGET_OBJECTS:testharness>)
+    string(REPLACE ".cc" "" 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}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} gtest ${LIBS})
-    if(NOT "${exename}" MATCHES "db_sanity_test")
-      add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
-      add_dependencies(check ${exename}${ARTIFACT_SUFFIX})
-    endif()
+    target_link_libraries(${exename}${ARTIFACT_SUFFIX} ${LIBS} testutillib${ARTIFACT_SUFFIX})
 endforeach(sourcefile ${TEST_EXES})
 
 # C executables must link to a shared object
-set(C_TESTS db/c_test.c)
 set(C_TEST_EXES ${C_TESTS})
 
 foreach(sourcefile ${C_TEST_EXES})
@@ -724,18 +446,5 @@ foreach(sourcefile ${C_TEST_EXES})
       EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
       EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
       )
-    target_link_libraries(${exename}${ARTIFACT_SUFFIX} ${ROCKSDB_IMPORT_LIB} testutillib${ARTIFACT_SUFFIX})
-    add_test(NAME ${exename} COMMAND ${exename}${ARTIFACT_SUFFIX})
-    add_dependencies(check ${exename}${ARTIFACT_SUFFIX})
+    target_link_libraries(${exename}${ARTIFACT_SUFFIX} rocksdb${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX})
 endforeach(sourcefile ${C_TEST_EXES})
-add_subdirectory(tools)
-
-# Installation and packaging for Linux
-if (NOT WIN32)
-install(TARGETS ${ROCKSDB_STATIC_LIB} COMPONENT devel ARCHIVE DESTINATION lib64)
-install(TARGETS ${ROCKSDB_SHARED_LIB} COMPONENT runtime DESTINATION lib64)
-install(DIRECTORY "${PROJECT_SOURCE_DIR}/include/rocksdb/"
-        COMPONENT devel
-        DESTINATION include/rocksdb)
-set(CMAKE_INSTALL_PREFIX /usr)
-endif()

CONTRIBUTING.md

@@ -12,3 +12,8 @@ Complete your CLA here: <https://code.facebook.com/cla>
 
 If you prefer to sign a paper copy, we can send you a PDF.  Send us an 
 e-mail or create a new github issue to request the CLA in PDF format.
+
+## License
+
+By contributing to RocksDB, you agree that your contributions will be
+licensed under the [BSD License](LICENSE).

COPYING

@@ -1,339 +0,0 @@
-                    GNU GENERAL PUBLIC LICENSE
-                       Version 2, June 1991
-
- Copyright (C) 1989, 1991 Free Software Foundation, Inc.,
- 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
- Everyone is permitted to copy and distribute verbatim copies
- of this license document, but changing it is not allowed.
-
-                            Preamble
-
-  The licenses for most software are designed to take away your
-freedom to share and change it.  By contrast, the GNU General Public
-License is intended to guarantee your freedom to share and change free
-software--to make sure the software is free for all its users.  This
-General Public License applies to most of the Free Software
-Foundation's software and to any other program whose authors commit to
-using it.  (Some other Free Software Foundation software is covered by
-the GNU Lesser General Public License instead.)  You can apply it to
-your programs, too.
-
-  When we speak of free software, we are referring to freedom, not
-price.  Our General Public Licenses are designed to make sure that you
-have the freedom to distribute copies of free software (and charge for
-this service if you wish), that you receive source code or can get it
-if you want it, that you can change the software or use pieces of it
-in new free programs; and that you know you can do these things.
-
-  To protect your rights, we need to make restrictions that forbid
-anyone to deny you these rights or to ask you to surrender the rights.
-These restrictions translate to certain responsibilities for you if you
-distribute copies of the software, or if you modify it.
-
-  For example, if you distribute copies of such a program, whether
-gratis or for a fee, you must give the recipients all the rights that
-you have.  You must make sure that they, too, receive or can get the
-source code.  And you must show them these terms so they know their
-rights.
-
-  We protect your rights with two steps: (1) copyright the software, and
-(2) offer you this license which gives you legal permission to copy,
-distribute and/or modify the software.
-
-  Also, for each author's protection and ours, we want to make certain
-that everyone understands that there is no warranty for this free
-software.  If the software is modified by someone else and passed on, we
-want its recipients to know that what they have is not the original, so
-that any problems introduced by others will not reflect on the original
-authors' reputations.
-
-  Finally, any free program is threatened constantly by software
-patents.  We wish to avoid the danger that redistributors of a free
-program will individually obtain patent licenses, in effect making the
-program proprietary.  To prevent this, we have made it clear that any
-patent must be licensed for everyone's free use or not licensed at all.
-
-  The precise terms and conditions for copying, distribution and
-modification follow.
-
-                    GNU GENERAL PUBLIC LICENSE
-   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
-
-  0. This License applies to any program or other work which contains
-a notice placed by the copyright holder saying it may be distributed
-under the terms of this General Public License.  The "Program", below,
-refers to any such program or work, and a "work based on the Program"
-means either the Program or any derivative work under copyright law:
-that is to say, a work containing the Program or a portion of it,
-either verbatim or with modifications and/or translated into another
-language.  (Hereinafter, translation is included without limitation in
-the term "modification".)  Each licensee is addressed as "you".
-
-Activities other than copying, distribution and modification are not
-covered by this License; they are outside its scope.  The act of
-running the Program is not restricted, and the output from the Program
-is covered only if its contents constitute a work based on the
-Program (independent of having been made by running the Program).
-Whether that is true depends on what the Program does.
-
-  1. You may copy and distribute verbatim copies of the Program's
-source code as you receive it, in any medium, provided that you
-conspicuously and appropriately publish on each copy an appropriate
-copyright notice and disclaimer of warranty; keep intact all the
-notices that refer to this License and to the absence of any warranty;
-and give any other recipients of the Program a copy of this License
-along with the Program.
-
-You may charge a fee for the physical act of transferring a copy, and
-you may at your option offer warranty protection in exchange for a fee.
-
-  2. You may modify your copy or copies of the Program or any portion
-of it, thus forming a work based on the Program, and copy and
-distribute such modifications or work under the terms of Section 1
-above, provided that you also meet all of these conditions:
-
-    a) You must cause the modified files to carry prominent notices
-    stating that you changed the files and the date of any change.
-
-    b) You must cause any work that you distribute or publish, that in
-    whole or in part contains or is derived from the Program or any
-    part thereof, to be licensed as a whole at no charge to all third
-    parties under the terms of this License.
-
-    c) If the modified program normally reads commands interactively
-    when run, you must cause it, when started running for such
-    interactive use in the most ordinary way, to print or display an
-    announcement including an appropriate copyright notice and a
-    notice that there is no warranty (or else, saying that you provide
-    a warranty) and that users may redistribute the program under
-    these conditions, and telling the user how to view a copy of this
-    License.  (Exception: if the Program itself is interactive but
-    does not normally print such an announcement, your work based on
-    the Program is not required to print an announcement.)
-
-These requirements apply to the modified work as a whole.  If
-identifiable sections of that work are not derived from the Program,
-and can be reasonably considered independent and separate works in
-themselves, then this License, and its terms, do not apply to those
-sections when you distribute them as separate works.  But when you
-distribute the same sections as part of a whole which is a work based
-on the Program, the distribution of the whole must be on the terms of
-this License, whose permissions for other licensees extend to the
-entire whole, and thus to each and every part regardless of who wrote it.
-
-Thus, it is not the intent of this section to claim rights or contest
-your rights to work written entirely by you; rather, the intent is to
-exercise the right to control the distribution of derivative or
-collective works based on the Program.
-
-In addition, mere aggregation of another work not based on the Program
-with the Program (or with a work based on the Program) on a volume of
-a storage or distribution medium does not bring the other work under
-the scope of this License.
-
-  3. You may copy and distribute the Program (or a work based on it,
-under Section 2) in object code or executable form under the terms of
-Sections 1 and 2 above provided that you also do one of the following:
-
-    a) Accompany it with the complete corresponding machine-readable
-    source code, which must be distributed under the terms of Sections
-    1 and 2 above on a medium customarily used for software interchange; or,
-
-    b) Accompany it with a written offer, valid for at least three
-    years, to give any third party, for a charge no more than your
-    cost of physically performing source distribution, a complete
-    machine-readable copy of the corresponding source code, to be
-    distributed under the terms of Sections 1 and 2 above on a medium
-    customarily used for software interchange; or,
-
-    c) Accompany it with the information you received as to the offer
-    to distribute corresponding source code.  (This alternative is
-    allowed only for noncommercial distribution and only if you
-    received the program in object code or executable form with such
-    an offer, in accord with Subsection b above.)
-
-The source code for a work means the preferred form of the work for
-making modifications to it.  For an executable work, complete source
-code means all the source code for all modules it contains, plus any
-associated interface definition files, plus the scripts used to
-control compilation and installation of the executable.  However, as a
-special exception, the source code distributed need not include
-anything that is normally distributed (in either source or binary
-form) with the major components (compiler, kernel, and so on) of the
-operating system on which the executable runs, unless that component
-itself accompanies the executable.
-
-If distribution of executable or object code is made by offering
-access to copy from a designated place, then offering equivalent
-access to copy the source code from the same place counts as
-distribution of the source code, even though third parties are not
-compelled to copy the source along with the object code.
-
-  4. You may not copy, modify, sublicense, or distribute the Program
-except as expressly provided under this License.  Any attempt
-otherwise to copy, modify, sublicense or distribute the Program is
-void, and will automatically terminate your rights under this License.
-However, parties who have received copies, or rights, from you under
-this License will not have their licenses terminated so long as such
-parties remain in full compliance.
-
-  5. You are not required to accept this License, since you have not
-signed it.  However, nothing else grants you permission to modify or
-distribute the Program or its derivative works.  These actions are
-prohibited by law if you do not accept this License.  Therefore, by
-modifying or distributing the Program (or any work based on the
-Program), you indicate your acceptance of this License to do so, and
-all its terms and conditions for copying, distributing or modifying
-the Program or works based on it.
-
-  6. Each time you redistribute the Program (or any work based on the
-Program), the recipient automatically receives a license from the
-original licensor to copy, distribute or modify the Program subject to
-these terms and conditions.  You may not impose any further
-restrictions on the recipients' exercise of the rights granted herein.
-You are not responsible for enforcing compliance by third parties to
-this License.
-
-  7. If, as a consequence of a court judgment or allegation of patent
-infringement or for any other reason (not limited to patent issues),
-conditions are imposed on you (whether by court order, agreement or
-otherwise) that contradict the conditions of this License, they do not
-excuse you from the conditions of this License.  If you cannot
-distribute so as to satisfy simultaneously your obligations under this
-License and any other pertinent obligations, then as a consequence you
-may not distribute the Program at all.  For example, if a patent
-license would not permit royalty-free redistribution of the Program by
-all those who receive copies directly or indirectly through you, then
-the only way you could satisfy both it and this License would be to
-refrain entirely from distribution of the Program.
-
-If any portion of this section is held invalid or unenforceable under
-any particular circumstance, the balance of the section is intended to
-apply and the section as a whole is intended to apply in other
-circumstances.
-
-It is not the purpose of this section to induce you to infringe any
-patents or other property right claims or to contest validity of any
-such claims; this section has the sole purpose of protecting the
-integrity of the free software distribution system, which is
-implemented by public license practices.  Many people have made
-generous contributions to the wide range of software distributed
-through that system in reliance on consistent application of that
-system; it is up to the author/donor to decide if he or she is willing
-to distribute software through any other system and a licensee cannot
-impose that choice.
-
-This section is intended to make thoroughly clear what is believed to
-be a consequence of the rest of this License.
-
-  8. If the distribution and/or use of the Program is restricted in
-certain countries either by patents or by copyrighted interfaces, the
-original copyright holder who places the Program under this License
-may add an explicit geographical distribution limitation excluding
-those countries, so that distribution is permitted only in or among
-countries not thus excluded.  In such case, this License incorporates
-the limitation as if written in the body of this License.
-
-  9. The Free Software Foundation may publish revised and/or new versions
-of the General Public License from time to time.  Such new versions will
-be similar in spirit to the present version, but may differ in detail to
-address new problems or concerns.
-
-Each version is given a distinguishing version number.  If the Program
-specifies a version number of this License which applies to it and "any
-later version", you have the option of following the terms and conditions
-either of that version or of any later version published by the Free
-Software Foundation.  If the Program does not specify a version number of
-this License, you may choose any version ever published by the Free Software
-Foundation.
-
-  10. If you wish to incorporate parts of the Program into other free
-programs whose distribution conditions are different, write to the author
-to ask for permission.  For software which is copyrighted by the Free
-Software Foundation, write to the Free Software Foundation; we sometimes
-make exceptions for this.  Our decision will be guided by the two goals
-of preserving the free status of all derivatives of our free software and
-of promoting the sharing and reuse of software generally.
-
-                            NO WARRANTY
-
-  11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY
-FOR THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN
-OTHERWISE STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES
-PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED
-OR IMPLIED, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
-MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS
-TO THE QUALITY AND PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE
-PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF ALL NECESSARY SERVICING,
-REPAIR OR CORRECTION.
-
-  12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
-WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR
-REDISTRIBUTE THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES,
-INCLUDING ANY GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING
-OUT OF THE USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED
-TO LOSS OF DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY
-YOU OR THIRD PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER
-PROGRAMS), EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE
-POSSIBILITY OF SUCH DAMAGES.
-
-                     END OF TERMS AND CONDITIONS
-
-            How to Apply These Terms to Your New Programs
-
-  If you develop a new program, and you want it to be of the greatest
-possible use to the public, the best way to achieve this is to make it
-free software which everyone can redistribute and change under these terms.
-
-  To do so, attach the following notices to the program.  It is safest
-to attach them to the start of each source file to most effectively
-convey the exclusion of warranty; and each file should have at least
-the "copyright" line and a pointer to where the full notice is found.
-
-    <one line to give the program's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
-
-    This program is free software; you can redistribute it and/or modify
-    it under the terms of the GNU General Public License as published by
-    the Free Software Foundation; either version 2 of the License, or
-    (at your option) any later version.
-
-    This program is distributed in the hope that it will be useful,
-    but WITHOUT ANY WARRANTY; without even the implied warranty of
-    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-    GNU General Public License for more details.
-
-    You should have received a copy of the GNU General Public License along
-    with this program; if not, write to the Free Software Foundation, Inc.,
-    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
-
-Also add information on how to contact you by electronic and paper mail.
-
-If the program is interactive, make it output a short notice like this
-when it starts in an interactive mode:
-
-    Gnomovision version 69, Copyright (C) year name of author
-    Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
-    This is free software, and you are welcome to redistribute it
-    under certain conditions; type `show c' for details.
-
-The hypothetical commands `show w' and `show c' should show the appropriate
-parts of the General Public License.  Of course, the commands you use may
-be called something other than `show w' and `show c'; they could even be
-mouse-clicks or menu items--whatever suits your program.
-
-You should also get your employer (if you work as a programmer) or your
-school, if any, to sign a "copyright disclaimer" for the program, if
-necessary.  Here is a sample; alter the names:
-
-  Yoyodyne, Inc., hereby disclaims all copyright interest in the program
-  `Gnomovision' (which makes passes at compilers) written by James Hacker.
-
-  <signature of Ty Coon>, 1 April 1989
-  Ty Coon, President of Vice
-
-This General Public License does not permit incorporating your program into
-proprietary programs.  If your program is a subroutine library, you may
-consider it more useful to permit linking proprietary applications with the
-library.  If this is what you want to do, use the GNU Lesser General
-Public License instead of this License.

DEFAULT_OPTIONS_HISTORY.md

@@ -1,21 +0,0 @@
-# RocksDB default options change log
-## Unreleased
-* Change the default of delayed slowdown value to 16MB/s and further increase the L0 stop condition to 36 files.
-
-## 5.0 (11/17/2016)
-* Options::allow_concurrent_memtable_write and Options::enable_write_thread_adaptive_yield are now true by default
-* Options.level0_stop_writes_trigger default value changes from 24 to 32.
-
-## 4.8.0 (5/2/2016)
-* options.max_open_files changes from 5000 to -1. It improves performance, but users need to set file descriptor limit to be large enough and watch memory usage for index and bloom filters.
-* options.base_background_compactions changes from max_background_compactions to 1. When users set higher max_background_compactions but the write throughput is not high, the writes are less spiky to disks.
-* options.wal_recovery_mode changes from kTolerateCorruptedTailRecords to kPointInTimeRecovery. Avoid some false positive when file system or hardware reorder the writes for file data and metadata.
-
-## 4.7.0 (4/8/2016)
-* options.write_buffer_size changes from 4MB to 64MB.
-* options.target_file_size_base changes from 2MB to 64MB.
-* options.max_bytes_for_level_base changes from 10MB to 256MB.
-* options.soft_pending_compaction_bytes_limit changes from 0 (disabled) to 64GB.
-* options.hard_pending_compaction_bytes_limit changes from 0 (disabled) to 256GB.
-* table_cache_numshardbits changes from 4 to 6.
-* max_file_opening_threads changes from 1 to 16.

HISTORY.md

@@ -1,153 +1,6 @@
 # Rocksdb Change Log
-## 5.3.7
-* Change license to Apache + GPLv2
 
-## 5.3.0 (03/08/2017)
-### Public API Change
-* Remove disableDataSync option.
-* Remove timeout_hint_us option from WriteOptions. The option has been deprecated and has no effect since 3.13.0.
-* Remove option min_partial_merge_operands. Partial merge operands will always be merged in flush or compaction if there are more than one.
-* Remove option verify_checksums_in_compaction. Compaction will always verify checksum.
-
-### New Features
-* Memtable flush can be avoided during checkpoint creation if total log file size is smaller than a threshold specified by the user.
-
-### Bug Fixes
-* Fix the bug that iterator may skip keys
-
-## 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 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.
-
-### New Features
-* Added new overloaded function GetApproximateSizes that allows to specify if memtable stats should be computed only without computing SST files' stats approximations.
-* Added new function GetApproximateMemTableStats that approximates both number of records and size of memtables.
-* Add Direct I/O mode for SST file I/O
-
-### Bug Fixes
-* RangeSync() should work if ROCKSDB_FALLOCATE_PRESENT is not set
-* Fix wrong results in a data race case in Get()
-* Some fixes related to 2PC.
-* Fix bugs of data corruption in direct I/O
-
-## 5.1.0 (01/13/2017)
-* Support dynamically change `delete_obsolete_files_period_micros` option via SetDBOptions().
-* Added EventListener::OnExternalFileIngested which will be called when IngestExternalFile() add a file successfully.
-* BackupEngine::Open and BackupEngineReadOnly::Open now always return error statuses matching those of the backup Env.
-
-### Bug Fixes
-* Fix the bug that if 2PC is enabled, checkpoints may loss some recent transactions.
-* When file copying is needed when creating checkpoints or bulk loading files, fsync the file after the file copying.
-
-## 5.0.0 (11/17/2016)
-### Public API Change
-* Options::max_bytes_for_level_multiplier is now a double along with all getters and setters.
-* Support dynamically change `delayed_write_rate` and `max_total_wal_size` options via SetDBOptions().
-* Introduce DB::DeleteRange for optimized deletion of large ranges of contiguous keys.
-* Support dynamically change `delayed_write_rate` option via SetDBOptions().
-* Options::allow_concurrent_memtable_write and Options::enable_write_thread_adaptive_yield are now true by default.
-* Remove Tickers::SEQUENCE_NUMBER to avoid confusion if statistics object is shared among RocksDB instance. Alternatively DB::GetLatestSequenceNumber() can be used to get the same value.
-* Options.level0_stop_writes_trigger default value changes from 24 to 32.
-* New compaction filter API: CompactionFilter::FilterV2(). Allows to drop ranges of keys.
-* Removed flashcache support.
-* DB::AddFile() is deprecated and is replaced with DB::IngestExternalFile(). DB::IngestExternalFile() remove all the restrictions that existed for DB::AddFile.
-
-### New Features
-* Add avoid_flush_during_shutdown option, which speeds up DB shutdown by not flushing unpersisted data (i.e. with disableWAL = true). Unpersisted data will be lost. The options is dynamically changeable via SetDBOptions().
-* Add memtable_insert_with_hint_prefix_extractor option. The option is mean to reduce CPU usage for inserting keys into memtable, if keys can be group by prefix and insert for each prefix are sequential or almost sequential. See include/rocksdb/options.h for more details.
-* Add LuaCompactionFilter in utilities.  This allows developers to write compaction filters in Lua.  To use this feature, LUA_PATH needs to be set to the root directory of Lua.
-* No longer populate "LATEST_BACKUP" file in backup directory, which formerly contained the number of the latest backup. The latest backup can be determined by finding the highest numbered file in the "meta/" subdirectory.
-
-## 4.13.0 (10/18/2016)
-### Public API Change
-* DB::GetOptions() reflect dynamic changed options (i.e. through DB::SetOptions()) and return copy of options instead of reference.
-* Added Statistics::getAndResetTickerCount().
-
-### New Features
-* Add DB::SetDBOptions() to dynamic change base_background_compactions and max_background_compactions.
-* Added Iterator::SeekForPrev(). This new API will seek to the last key that less than or equal to the target key.
-
-## 4.12.0 (9/12/2016)
-### Public API Change
-* CancelAllBackgroundWork() flushes all memtables for databases containing writes that have bypassed the WAL (writes issued with WriteOptions::disableWAL=true) before shutting down background threads.
-* Merge options source_compaction_factor, max_grandparent_overlap_bytes and expanded_compaction_factor into max_compaction_bytes.
-* Remove ImmutableCFOptions.
-* Add a compression type ZSTD, which can work with ZSTD 0.8.0 or up. Still keep ZSTDNotFinal for compatibility reasons.
-
-### New Features
-* Introduce NewClockCache, which is based on CLOCK algorithm with better concurrent performance in some cases. It can be used to replace the default LRU-based block cache and table cache. To use it, RocksDB need to be linked with TBB lib.
-* Change ticker/histogram statistics implementations to accumulate data in thread-local storage, which improves CPU performance by reducing cache coherency costs. Callers of CreateDBStatistics do not need to change anything to use this feature.
-* Block cache mid-point insertion, where index and filter block are inserted into LRU block cache with higher priority. The feature can be enabled by setting BlockBasedTableOptions::cache_index_and_filter_blocks_with_high_priority to true and high_pri_pool_ratio > 0 when creating NewLRUCache.
-
-## 4.11.0 (8/1/2016)
-### Public API Change
-* options.memtable_prefix_bloom_huge_page_tlb_size => memtable_huge_page_size. When it is set, RocksDB will try to allocate memory from huge page for memtable too, rather than just memtable bloom filter.
-
-### 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 destorying iterators.
-
-## 4.10.0 (7/5/2016)
-### Public API Change
-* options.memtable_prefix_bloom_bits changes to options.memtable_prefix_bloom_bits_ratio and deprecate options.memtable_prefix_bloom_probes
-* enum type CompressionType and PerfLevel changes from char to unsigned char. Value of all PerfLevel shift by one.
-* Deprecate options.filter_deletes.
-
-### New Features
-* Add avoid_flush_during_recovery option.
-* Add a read option background_purge_on_iterator_cleanup to avoid deleting files in foreground when destroying iterators. Instead, a job is scheduled in high priority queue and would be executed in a separate background thread.
-* RepairDB support for column families. RepairDB now associates data with non-default column families using information embedded in the SST/WAL files (4.7 or later). For data written by 4.6 or earlier, RepairDB associates it with the default column family.
-* Add options.write_buffer_manager which allows users to control total memtable sizes across multiple DB instances.
-
-## 4.9.0 (6/9/2016)
-### Public API changes
-* Add bottommost_compression option, This option can be used to set a specific compression algorithm for the bottommost level (Last level containing files in the DB).
-* Introduce CompactionJobInfo::compression, This field state the compression algorithm used to generate the output files of the compaction.
-* Deprecate BlockBaseTableOptions.hash_index_allow_collision=false
-* Deprecate options builder (GetOptions()).
-
-### New Features
-* Introduce NewSimCache() in rocksdb/utilities/sim_cache.h. This function creates a block cache that is able to give simulation results (mainly hit rate) of simulating block behavior with a configurable cache size.
-
-## 4.8.0 (5/2/2016)
-### Public API Change
-* Allow preset compression dictionary for improved compression of block-based tables. This is supported for zlib, zstd, and lz4. The compression dictionary's size is configurable via CompressionOptions::max_dict_bytes.
-* Delete deprecated classes for creating backups (BackupableDB) and restoring from backups (RestoreBackupableDB). Now, BackupEngine should be used for creating backups, and BackupEngineReadOnly should be used for restorations. For more details, see https://github.com/facebook/rocksdb/wiki/How-to-backup-RocksDB%3F
-* Expose estimate of per-level compression ratio via DB property: "rocksdb.compression-ratio-at-levelN".
-* Added EventListener::OnTableFileCreationStarted. EventListener::OnTableFileCreated will be called on failure case. User can check creation status via TableFileCreationInfo::status.
-
-### New Features
-* Add ReadOptions::readahead_size. If non-zero, NewIterator will create a new table reader which performs reads of the given size.
-
-## 4.7.0 (4/8/2016)
-### Public API Change
-* rename options compaction_measure_io_stats to report_bg_io_stats and include flush too.
-* Change some default options. Now default options will optimize for server-workloads. Also enable slowdown and full stop triggers for pending compaction bytes. These changes may cause sub-optimal performance or significant increase of resource usage. To avoid these risks, users can open existing RocksDB with options extracted from RocksDB option files. See https://github.com/facebook/rocksdb/wiki/RocksDB-Options-File for how to use RocksDB option files. Or you can call Options.OldDefaults() to recover old defaults. DEFAULT_OPTIONS_HISTORY.md will track change history of default options.
-
-## 4.6.0 (3/10/2016)
-### Public API Changes
-* Change default of BlockBasedTableOptions.format_version to 2. It means default DB created by 4.6 or up cannot be opened by RocksDB version 3.9 or earlier.
-* Added strict_capacity_limit option to NewLRUCache. If the flag is set to true, insert to cache will fail if no enough capacity can be free. Signature of Cache::Insert() is updated accordingly.
-* Tickers [NUMBER_DB_NEXT, NUMBER_DB_PREV, NUMBER_DB_NEXT_FOUND, NUMBER_DB_PREV_FOUND, ITER_BYTES_READ] are not updated immediately. The are updated when the Iterator is deleted.
-* Add monotonically increasing counter (DB property "rocksdb.current-super-version-number") that increments upon any change to the LSM tree.
-
-### New Features
-* Add CompactionPri::kMinOverlappingRatio, a compaction picking mode friendly to write amplification.
-* Deprecate Iterator::IsKeyPinned() and replace it with Iterator::GetProperty() with prop_name="rocksdb.iterator.is.key.pinned"
-
-## 4.5.0 (2/5/2016)
-### Public API Changes
-* Add a new perf context level between kEnableCount and kEnableTime. Level 2 now does not include timers for mutexes.
-* Statistics of mutex operation durations will not be measured by default. If you want to have them enabled, you need to set Statistics::stats_level_ to kAll.
-* DBOptions::delete_scheduler and NewDeleteScheduler() are removed, please use DBOptions::sst_file_manager and NewSstFileManager() instead
-
-### New Features
-* ldb tool now supports operations to non-default column families.
-* Add kPersistedTier to ReadTier.  This option allows Get and MultiGet to read only the persited data and skip mem-tables if writes were done with disableWAL = true.
-* Add DBOptions::sst_file_manager. Use NewSstFileManager() in include/rocksdb/sst_file_manager.h to create a SstFileManager that can be used to track the total size of SST files and control the SST files deletion rate.
+## 4.4.1 (2/18/2016)
 
 ## 4.4.0 (1/14/2016)
 ### Public API Changes
@@ -246,8 +99,8 @@
 * options.hard_rate_limit is deprecated.
 * When options.soft_rate_limit or options.level0_slowdown_writes_trigger is triggered, the way to slow down writes is changed to: write rate to DB is limited to to options.delayed_write_rate.
 * DB::GetApproximateSizes() adds a parameter to allow the estimation to include data in mem table, with default to be not to include. It is now only supported in skip list mem table.
-* DB::CompactRange() now accept CompactRangeOptions instead of multiple parameters. CompactRangeOptions is defined in include/rocksdb/options.h.
-* CompactRange() will now skip bottommost level compaction for level based compaction if there is no compaction filter, bottommost_level_compaction is introduced in CompactRangeOptions to control when it's possible to skip bottommost level compaction. This mean that if you want the compaction to produce a single file you need to set bottommost_level_compaction to BottommostLevelCompaction::kForce.
+* DB::CompactRange() now accept CompactRangeOptions instead of multiple paramters. CompactRangeOptions is defined in include/rocksdb/options.h.
+* CompactRange() will now skip bottommost level compaction for level based compaction if there is no compaction filter, bottommost_level_compaction is introduced in CompactRangeOptions to control when it's possbile to skip bottommost level compaction. This mean that if you want the compaction to produce a single file you need to set bottommost_level_compaction to BottommostLevelCompaction::kForce.
 * Add Cache.GetPinnedUsage() to get the size of memory occupied by entries that are in use by the system.
 * DB:Open() will fail if the compression specified in Options is not linked with the binary. If you see this failure, recompile RocksDB with compression libraries present on your system. Also, previously our default compression was snappy. This behavior is now changed. Now, the default compression is snappy only if it's available on the system. If it isn't we change the default to kNoCompression.
 * We changed how we account for memory used in block cache. Previously, we only counted the sum of block sizes currently present in block cache. Now, we count the actual memory usage of the blocks. For example, a block of size 4.5KB will use 8KB memory with jemalloc. This might decrease your memory usage and possibly decrease performance. Increase block cache size if you see this happening after an upgrade.
@@ -279,7 +132,7 @@
   Lower numbered levels will be placed earlier in the db_paths and higher
   numbered levels will be placed later in the db_paths vector.
 * Potentially big performance improvements if you're using RocksDB with lots of column families (100-1000)
-* Added BlockBasedTableOptions.format_version option, which allows user to specify which version of block based table he wants. As a general guideline, newer versions have more features, but might not be readable by older versions of RocksDB.
+* Added BlockBasedTableOptions.format_version option, which allows user to specify which version of block based table he wants. As a general guidline, newer versions have more features, but might not be readable by older versions of RocksDB.
 * Added new block based table format (version 2), which you can enable by setting BlockBasedTableOptions.format_version = 2. This format changes how we encode size information in compressed blocks and should help with memory allocations if you're using Zlib or BZip2 compressions.
 * MemEnv (env that stores data in memory) is now available in default library build. You can create it by calling NewMemEnv().
 * Add SliceTransform.SameResultWhenAppended() to help users determine it is safe to apply prefix bloom/hash.
@@ -355,7 +208,7 @@
 
 ## 3.5.0 (9/3/2014)
 ### New Features
-* Add include/utilities/write_batch_with_index.h, providing a utility class to query data out of WriteBatch when building it.
+* Add include/utilities/write_batch_with_index.h, providing a utilitiy class to query data out of WriteBatch when building it.
 * Move BlockBasedTable related options to BlockBasedTableOptions from Options. Change corresponding JNI interface. Options affected include:
   no_block_cache, block_cache, block_cache_compressed, block_size, block_size_deviation, block_restart_interval, filter_policy, whole_key_filtering. filter_policy is changed to shared_ptr from a raw pointer.
 * Remove deprecated options: disable_seek_compaction and db_stats_log_interval
@@ -384,7 +237,7 @@
 ### New Features
 * Added JSON API prototype.
 * HashLinklist reduces performance outlier caused by skewed bucket by switching data in the bucket from linked list to skip list. Add parameter threshold_use_skiplist in NewHashLinkListRepFactory().
-* RocksDB is now able to reclaim storage space more effectively during the compaction process.  This is done by compensating the size of each deletion entry by the 2X average value size, which makes compaction to be triggered by deletion entries more easily.
+* RocksDB is now able to reclaim storage space more effectively during the compaction process.  This is done by compensating the size of each deletion entry by the 2X average value size, which makes compaction to be triggerred by deletion entries more easily.
 * Add TimeOut API to write.  Now WriteOptions have a variable called timeout_hint_us.  With timeout_hint_us set to non-zero, any write associated with this timeout_hint_us may be aborted when it runs longer than the specified timeout_hint_us, and it is guaranteed that any write completes earlier than the specified time-out will not be aborted due to the time-out condition.
 * Add a rate_limiter option, which controls total throughput of flush and compaction. The throughput is specified in bytes/sec. Flush always has precedence over compaction when available bandwidth is constrained.
 
@@ -399,11 +252,11 @@
 2) It added some complexity to the important code-paths,
 3) None of our internal customers were really using it.
 Because of that, Options::disable_seek_compaction is now obsolete. It is still a parameter in Options, so it does not break the build, but it does not have any effect. We plan to completely remove it at some point, so we ask users to please remove this option from your code base.
-* Add two parameters to NewHashLinkListRepFactory() for logging on too many entries in a hash bucket when flushing.
+* Add two paramters to NewHashLinkListRepFactory() for logging on too many entries in a hash bucket when flushing.
 * Added new option BlockBasedTableOptions::hash_index_allow_collision. When enabled, prefix hash index for block-based table will not store prefix and allow hash collision, reducing memory consumption.
 
 ### New Features
-* PlainTable now supports a new key encoding: for keys of the same prefix, the prefix is only written once. It can be enabled through encoding_type parameter of NewPlainTableFactory()
+* PlainTable now supports a new key encoding: for keys of the same prefix, the prefix is only written once. It can be enabled through encoding_type paramter of NewPlainTableFactory()
 * Add AdaptiveTableFactory, which is used to convert from a DB of PlainTable to BlockBasedTabe, or vise versa. It can be created using NewAdaptiveTableFactory()
 
 ### Performance Improvements

INSTALL.md

@@ -21,7 +21,7 @@ depend on gflags. You will need to have gflags installed to run `make all`. This
 use binaries compiled by `make all` in production.
 
 * By default the binary we produce is optimized for the platform you're compiling on
-(-march=native or the equivalent). If you want to build a portable binary, add 'PORTABLE=1' before
+(-march=native). If you want to build a portable binary, add 'PORTABLE=1' before
 your make commands, like this: `PORTABLE=1 make static_lib`
 
 ## Dependencies
@@ -29,10 +29,8 @@ your make commands, like this: `PORTABLE=1 make static_lib`
 * You can link RocksDB with following compression libraries:
   - [zlib](http://www.zlib.net/) - a library for data compression.
   - [bzip2](http://www.bzip.org/) - a library for data compression.
-  - [snappy](http://google.github.io/snappy/) - a library for fast
+  - [snappy](https://code.google.com/p/snappy/) - a library for fast
       data compression.
-  - [zstandard](http://www.zstd.net) - Fast real-time compression
-      algorithm.
 
 * All our tools depend on:
   - [gflags](https://gflags.github.io/gflags/) - a library that handles
@@ -42,7 +40,7 @@ your make commands, like this: `PORTABLE=1 make static_lib`
 ## Supported platforms
 
 * **Linux - Ubuntu**
-    * Upgrade your gcc to version at least 4.8 to get C++11 support.
+    * Upgrade your gcc to version at least 4.7 to get C++11 support.
     * Install gflags. First, try: `sudo apt-get install libgflags-dev`
       If this doesn't work and you're using Ubuntu, here's a nice tutorial:
       (http://askubuntu.com/questions/312173/installing-gflags-12-04)
@@ -50,23 +48,21 @@ your make commands, like this: `PORTABLE=1 make static_lib`
       `sudo apt-get install libsnappy-dev`.
     * Install zlib. Try: `sudo apt-get install zlib1g-dev`.
     * Install bzip2: `sudo apt-get install libbz2-dev`.
-    * Install zstandard: `sudo apt-get install libzstd-dev`.
-
-* **Linux - CentOS / RHEL**
-    * Upgrade your gcc to version at least 4.8 to get C++11 support:
-      `yum install gcc48-c++`
+* **Linux - CentOS**
+    * Upgrade your gcc to version at least 4.7 to get C++11 support:
+      `yum install gcc47-c++`
     * Install gflags:
 
-              git clone https://github.com/gflags/gflags.git
-              git checkout v2.0
-              cd gflags
+              wget https://gflags.googlecode.com/files/gflags-2.0-no-svn-files.tar.gz
+              tar -xzvf gflags-2.0-no-svn-files.tar.gz
+              cd gflags-2.0
               ./configure && make && sudo make install
 
     * Install snappy:
 
-              wget https://github.com/google/snappy/releases/download/1.1.4/snappy-1.1.4.tar.gz
-              tar -xzvf snappy-1.1.4.tar.gz
-              cd snappy-1.1.4
+              wget https://snappy.googlecode.com/files/snappy-1.1.1.tar.gz
+              tar -xzvf snappy-1.1.1.tar.gz
+              cd snappy-1.1.1
               ./configure && make && sudo make install
 
     * Install zlib:
@@ -79,20 +75,12 @@ your make commands, like this: `PORTABLE=1 make static_lib`
               sudo yum install bzip2
               sudo yum install bzip2-devel
 
-    * Install zstandard:
-
-             wget https://github.com/facebook/zstd/archive/v1.1.3.tar.gz
-             mv v1.1.3.tar.gz zstandard-1.1.3.tar.gz
-             tar zxvf zstd-1.1.3.tar.gz
-             cd zstd-1.1.3
-             make && sudo make install
-
 * **OS X**:
     * Install latest C++ compiler that supports C++ 11:
         * Update XCode:  run `xcode-select --install` (or install it from XCode App's settting).
         * Install via [homebrew](http://brew.sh/).
             * If you're first time developer in MacOS, you still need to run: `xcode-select --install` in your command line.
-            * run `brew tap homebrew/versions; brew install gcc48 --use-llvm` to install gcc 4.8 (or higher).
+            * run `brew tap homebrew/versions; brew install gcc47 --use-llvm` to install gcc 4.7 (or higher).
     * run `brew install rocksdb`
 
 * **iOS**:

LANGUAGE-BINDINGS.md

@@ -1,13 +0,0 @@
-This is the list of all known third-party language bindings for RocksDB. If something is missing, please open a pull request to add it.
-
-* Java - https://github.com/facebook/rocksdb/tree/master/java
-* Python - http://pyrocksdb.readthedocs.org/en/latest/
-* Perl - https://metacpan.org/pod/RocksDB
-* Node.js - https://npmjs.org/package/rocksdb
-* Go - https://github.com/tecbot/gorocksdb
-* Ruby - http://rubygems.org/gems/rocksdb-ruby
-* Haskell - https://hackage.haskell.org/package/rocksdb-haskell
-* PHP - https://github.com/Photonios/rocksdb-php
-* C# - https://github.com/warrenfalk/rocksdb-sharp
-* Rust - https://github.com/spacejam/rust-rocksdb
-* D programming language - https://github.com/b1naryth1ef/rocksdb

LICENSE

@@ -1,4 +1,10 @@
-This contains code that is from LevelDB, and that code is under the following license:
+BSD License
+
+For rocksdb software
+
+Copyright (c) 2014, Facebook, Inc.
+All rights reserved.
+---------------------------------------------------------------------
 
 Copyright (c) 2011 The LevelDB Authors. All rights reserved.
 

LICENSE.Apache

@@ -1,202 +0,0 @@
-
-                                 Apache License
-                           Version 2.0, January 2004
-                        http://www.apache.org/licenses/
-
-   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
-
-   1. Definitions.
-
-      "License" shall mean the terms and conditions for use, reproduction,
-      and distribution as defined by Sections 1 through 9 of this document.
-
-      "Licensor" shall mean the copyright owner or entity authorized by
-      the copyright owner that is granting the License.
-
-      "Legal Entity" shall mean the union of the acting entity and all
-      other entities that control, are controlled by, or are under common
-      control with that entity. For the purposes of this definition,
-      "control" means (i) the power, direct or indirect, to cause the
-      direction or management of such entity, whether by contract or
-      otherwise, or (ii) ownership of fifty percent (50%) or more of the
-      outstanding shares, or (iii) beneficial ownership of such entity.
-
-      "You" (or "Your") shall mean an individual or Legal Entity
-      exercising permissions granted by this License.
-
-      "Source" form shall mean the preferred form for making modifications,
-      including but not limited to software source code, documentation
-      source, and configuration files.
-
-      "Object" form shall mean any form resulting from mechanical
-      transformation or translation of a Source form, including but
-      not limited to compiled object code, generated documentation,
-      and conversions to other media types.
-
-      "Work" shall mean the work of authorship, whether in Source or
-      Object form, made available under the License, as indicated by a
-      copyright notice that is included in or attached to the work
-      (an example is provided in the Appendix below).
-
-      "Derivative Works" shall mean any work, whether in Source or Object
-      form, that is based on (or derived from) the Work and for which the
-      editorial revisions, annotations, elaborations, or other modifications
-      represent, as a whole, an original work of authorship. For the purposes
-      of this License, Derivative Works shall not include works that remain
-      separable from, or merely link (or bind by name) to the interfaces of,
-      the Work and Derivative Works thereof.
-
-      "Contribution" shall mean any work of authorship, including
-      the original version of the Work and any modifications or additions
-      to that Work or Derivative Works thereof, that is intentionally
-      submitted to Licensor for inclusion in the Work by the copyright owner
-      or by an individual or Legal Entity authorized to submit on behalf of
-      the copyright owner. For the purposes of this definition, "submitted"
-      means any form of electronic, verbal, or written communication sent
-      to the Licensor or its representatives, including but not limited to
-      communication on electronic mailing lists, source code control systems,
-      and issue tracking systems that are managed by, or on behalf of, the
-      Licensor for the purpose of discussing and improving the Work, but
-      excluding communication that is conspicuously marked or otherwise
-      designated in writing by the copyright owner as "Not a Contribution."
-
-      "Contributor" shall mean Licensor and any individual or Legal Entity
-      on behalf of whom a Contribution has been received by Licensor and
-      subsequently incorporated within the Work.
-
-   2. Grant of Copyright License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      copyright license to reproduce, prepare Derivative Works of,
-      publicly display, publicly perform, sublicense, and distribute the
-      Work and such Derivative Works in Source or Object form.
-
-   3. Grant of Patent License. Subject to the terms and conditions of
-      this License, each Contributor hereby grants to You a perpetual,
-      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
-      (except as stated in this section) patent license to make, have made,
-      use, offer to sell, sell, import, and otherwise transfer the Work,
-      where such license applies only to those patent claims licensable
-      by such Contributor that are necessarily infringed by their
-      Contribution(s) alone or by combination of their Contribution(s)
-      with the Work to which such Contribution(s) was submitted. If You
-      institute patent litigation against any entity (including a
-      cross-claim or counterclaim in a lawsuit) alleging that the Work
-      or a Contribution incorporated within the Work constitutes direct
-      or contributory patent infringement, then any patent licenses
-      granted to You under this License for that Work shall terminate
-      as of the date such litigation is filed.
-
-   4. Redistribution. You may reproduce and distribute copies of the
-      Work or Derivative Works thereof in any medium, with or without
-      modifications, and in Source or Object form, provided that You
-      meet the following conditions:
-
-      (a) You must give any other recipients of the Work or
-          Derivative Works a copy of this License; and
-
-      (b) You must cause any modified files to carry prominent notices
-          stating that You changed the files; and
-
-      (c) You must retain, in the Source form of any Derivative Works
-          that You distribute, all copyright, patent, trademark, and
-          attribution notices from the Source form of the Work,
-          excluding those notices that do not pertain to any part of
-          the Derivative Works; and
-
-      (d) If the Work includes a "NOTICE" text file as part of its
-          distribution, then any Derivative Works that You distribute must
-          include a readable copy of the attribution notices contained
-          within such NOTICE file, excluding those notices that do not
-          pertain to any part of the Derivative Works, in at least one
-          of the following places: within a NOTICE text file distributed
-          as part of the Derivative Works; within the Source form or
-          documentation, if provided along with the Derivative Works; or,
-          within a display generated by the Derivative Works, if and
-          wherever such third-party notices normally appear. The contents
-          of the NOTICE file are for informational purposes only and
-          do not modify the License. You may add Your own attribution
-          notices within Derivative Works that You distribute, alongside
-          or as an addendum to the NOTICE text from the Work, provided
-          that such additional attribution notices cannot be construed
-          as modifying the License.
-
-      You may add Your own copyright statement to Your modifications and
-      may provide additional or different license terms and conditions
-      for use, reproduction, or distribution of Your modifications, or
-      for any such Derivative Works as a whole, provided Your use,
-      reproduction, and distribution of the Work otherwise complies with
-      the conditions stated in this License.
-
-   5. Submission of Contributions. Unless You explicitly state otherwise,
-      any Contribution intentionally submitted for inclusion in the Work
-      by You to the Licensor shall be under the terms and conditions of
-      this License, without any additional terms or conditions.
-      Notwithstanding the above, nothing herein shall supersede or modify
-      the terms of any separate license agreement you may have executed
-      with Licensor regarding such Contributions.
-
-   6. Trademarks. This License does not grant permission to use the trade
-      names, trademarks, service marks, or product names of the Licensor,
-      except as required for reasonable and customary use in describing the
-      origin of the Work and reproducing the content of the NOTICE file.
-
-   7. Disclaimer of Warranty. Unless required by applicable law or
-      agreed to in writing, Licensor provides the Work (and each
-      Contributor provides its Contributions) on an "AS IS" BASIS,
-      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
-      implied, including, without limitation, any warranties or conditions
-      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
-      PARTICULAR PURPOSE. You are solely responsible for determining the
-      appropriateness of using or redistributing the Work and assume any
-      risks associated with Your exercise of permissions under this License.
-
-   8. Limitation of Liability. In no event and under no legal theory,
-      whether in tort (including negligence), contract, or otherwise,
-      unless required by applicable law (such as deliberate and grossly
-      negligent acts) or agreed to in writing, shall any Contributor be
-      liable to You for damages, including any direct, indirect, special,
-      incidental, or consequential damages of any character arising as a
-      result of this License or out of the use or inability to use the
-      Work (including but not limited to damages for loss of goodwill,
-      work stoppage, computer failure or malfunction, or any and all
-      other commercial damages or losses), even if such Contributor
-      has been advised of the possibility of such damages.
-
-   9. Accepting Warranty or Additional Liability. While redistributing
-      the Work or Derivative Works thereof, You may choose to offer,
-      and charge a fee for, acceptance of support, warranty, indemnity,
-      or other liability obligations and/or rights consistent with this
-      License. However, in accepting such obligations, You may act only
-      on Your own behalf and on Your sole responsibility, not on behalf
-      of any other Contributor, and only if You agree to indemnify,
-      defend, and hold each Contributor harmless for any liability
-      incurred by, or claims asserted against, such Contributor by reason
-      of your accepting any such warranty or additional liability.
-
-   END OF TERMS AND CONDITIONS
-
-   APPENDIX: How to apply the Apache License to your work.
-
-      To apply the Apache License to your work, attach the following
-      boilerplate notice, with the fields enclosed by brackets "[]"
-      replaced with your own identifying information. (Don't include
-      the brackets!)  The text should be enclosed in the appropriate
-      comment syntax for the file format. We also recommend that a
-      file or class name and description of purpose be included on the
-      same "printed page" as the copyright notice for easier
-      identification within third-party archives.
-
-   Copyright [yyyy] [name of copyright owner]
-
-   Licensed under the Apache License, Version 2.0 (the "License");
-   you may not use this file except in compliance with the License.
-   You may obtain a copy of the License at
-
-       http://www.apache.org/licenses/LICENSE-2.0
-
-   Unless required by applicable law or agreed to in writing, software
-   distributed under the License is distributed on an "AS IS" BASIS,
-   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-   See the License for the specific language governing permissions and
-   limitations under the License.

PATENTS

@@ -0,0 +1,33 @@
+Additional Grant of Patent Rights Version 2
+
+"Software" means the RocksDB software distributed by Facebook, Inc.
+
+Facebook, Inc. ("Facebook") hereby grants to each recipient of the Software
+("you") a perpetual, worldwide, royalty-free, non-exclusive, irrevocable
+(subject to the termination provision below) license under any Necessary
+Claims, to make, have made, use, sell, offer to sell, import, and otherwise
+transfer the Software. For avoidance of doubt, no license is granted under
+Facebook’s rights in any patent claims that are infringed by (i) modifications
+to the Software made by you or any third party or (ii) the Software in
+combination with any software or other technology.
+
+The license granted hereunder will terminate, automatically and without notice,
+if you (or any of your subsidiaries, corporate affiliates or agents) initiate
+directly or indirectly, or take a direct financial interest in, any Patent
+Assertion: (i) against Facebook or any of its subsidiaries or corporate
+affiliates, (ii) against any party if such Patent Assertion arises in whole or
+in part from any software, technology, product or service of Facebook or any of
+its subsidiaries or corporate affiliates, or (iii) against any party relating
+to the Software. Notwithstanding the foregoing, if Facebook or any of its
+subsidiaries or corporate affiliates files a lawsuit alleging patent
+infringement against you in the first instance, and you respond by filing a
+patent infringement counterclaim in that lawsuit against that party that is
+unrelated to the Software, the license granted hereunder will not terminate
+under section (i) of this paragraph due to such counterclaim.
+
+A "Necessary Claim" is a claim of a patent owned by Facebook that is
+necessarily infringed by the Software standing alone.
+
+A "Patent Assertion" is any lawsuit or other action alleging direct, indirect,
+or contributory infringement or inducement to infringe any patent, including a
+cross-claim or counterclaim.

README.md

@@ -1,8 +1,6 @@
 ## RocksDB: A Persistent Key-Value Store for Flash and RAM Storage
 
 [![Build Status](https://travis-ci.org/facebook/rocksdb.svg?branch=master)](https://travis-ci.org/facebook/rocksdb)
-[![Build status](https://ci.appveyor.com/api/projects/status/fbgfu0so3afcno78/branch/master?svg=true)](https://ci.appveyor.com/project/Facebook/rocksdb/branch/master)
-
 
 RocksDB is developed and maintained by Facebook Database Engineering Team.
 It is built on earlier work on LevelDB by Sanjay Ghemawat (sanjay@google.com)

USERS.md

@@ -1,21 +1,15 @@
 This document lists users of RocksDB and their use cases. If you are using RocksDB, please open a pull request and add yourself to the list.
 
 ## Facebook
-At Facebook, we use RocksDB as storage engines in multiple data management services and a backend for many different stateful services, including:
+At Facebook, we use RocksDB as a backend for many different stateful services. We're also experimenting with running RocksDB as a storage engine for two databases:
 
 1. MyRocks -- https://github.com/MySQLOnRocksDB/mysql-5.6
 2. MongoRocks -- https://github.com/mongodb-partners/mongo-rocks
-3. ZippyDB --  Facebook's distributed key-value store with Paxos-style replication, built on top of RocksDB.[*] https://www.youtube.com/watch?v=DfiN7pG0D0khtt
-4. Laser -- Laser is a high query throughput, low (millisecond) latency, key-value storage service built on top of RocksDB.[*]
-4. Dragon -- a distributed graph query engine. https://code.facebook.com/posts/1737605303120405/dragon-a-distributed-graph-query-engine/
-5. Stylus -- a low-level stream processing framework writtenin C++.[*]
-
-[*] https://research.facebook.com/publications/realtime-data-processing-at-facebook/
 
 ## LinkedIn
 Two different use cases at Linkedin are using RocksDB as a storage engine:
 
-1. LinkedIn's follow feed for storing user's activities. Check out the blog post: https://engineering.linkedin.com/blog/2016/03/followfeed--linkedin-s-feed-made-faster-and-smarter
+1. LinkedIn's follow feed for storing user's activities
 2. Apache Samza, open source framework for stream processing
 
 Learn more about those use cases in a Tech Talk by Ankit Gupta and Naveen Somasundaram: http://www.youtube.com/watch?v=plqVp_OnSzg
@@ -51,32 +45,4 @@ Airbnb is using RocksDB as a storage engine for their personalized search servic
 Pinterest's Object Retrieval System uses RocksDB for storage: https://www.youtube.com/watch?v=MtFEVEs_2Vo
 
 ## Smyte
-[Smyte](https://www.smyte.com/) uses RocksDB as the storage layer for their core key-value storage, high-performance counters and time-windowed HyperLogLog services.
-
-## Rakuten Marketing
-[Rakuten Marketing](https://marketing.rakuten.com/) uses RocksDB as the disk cache layer for the real-time bidding service in their Performance DSP.
-
-## VWO, Wingify
-[VWO's](https://vwo.com/) Smart Code checker and URL helper uses RocksDB to store all the URLs where VWO's Smart Code is installed.
-
-## quasardb
-[quasardb](https://www.quasardb.net) is a high-performance, distributed, transactional key-value database that integrates well with in-memory analytics engines such as Apache Spark. 
-quasardb uses a heavily tuned RocksDB as its persistence layer.
-
-## Netflix
-[Netflix](http://techblog.netflix.com/2016/05/application-data-caching-using-ssds.html) Netflix uses RocksDB on AWS EC2 instances with local SSD drives to cache application data.
-
-## TiKV
-[TiKV](https://github.com/pingcap/tikv) is a GEO-replicated, high-performance, distributed, transactional key-value database. TiKV is powered by Rust and Raft. TiKV uses RocksDB as its persistence layer.
-
-## Apache Flink
-[Apache Flink](https://flink.apache.org/news/2016/03/08/release-1.0.0.html) uses RocksDB to store state locally on a machine.
-
-## Dgraph
-[Dgraph](https://github.com/dgraph-io/dgraph) is an open-source, scalable, distributed, low latency, high throughput Graph database .They use RocksDB to store state locally on a machine.
-
-## Uber
-[Uber](http://eng.uber.com/cherami/) uses RocksDB as a durable and and scalable task queue.
-
-## 360 Pika
-[360](http://www.360.cn/) [Pika](https://github.com/Qihoo360/pika) is a nosql compatible with redis. With the huge amount of data stored, redis may suffer for a capacity bottleneck, and pika was born for solving it. It has widely been widely used in many company
+[Smyte](https://www.smyte.com/) uses RocksDB as the storage layer for their core key-value storage, high-performance counters and time-windowed HyperLogLog services.

Vagrantfile

@@ -1,4 +1,3 @@
-# Vagrant file
 Vagrant.configure("2") do |config|
 
   config.vm.provider "virtualbox" do |v|

appveyor.yml

@@ -1,9 +1,8 @@
 version: 1.0.{build}
-image: Visual Studio 2015
 before_build:
 - md %APPVEYOR_BUILD_FOLDER%\build
 - cd %APPVEYOR_BUILD_FOLDER%\build
-- cmake -G "Visual Studio 14 2015 Win64" -DOPTDBG=1 -DXPRESS=1 ..
+- cmake -G "Visual Studio 12 Win64" -DOPTDBG=1 ..
 - cd ..
 build:
   project: build\rocksdb.sln
@@ -11,8 +10,6 @@ build:
   verbosity: minimal
 test:
 test_script:
-- ps: build_tools\run_ci_db_test.ps1 -Run db_basic_test -Concurrency 8
-- ps: build_tools\run_ci_db_test.ps1 -Run db_test2 -Concurrency 8
-- ps: build_tools\run_ci_db_test.ps1 -Run db_test -Concurrency 8
-- ps: build_tools\run_ci_db_test.ps1 -Run env_test,env_basic_test -Concurrency 2
+- ps: build_tools\run_ci_db_test.ps1 -EnableRerun -Run db_test -Exclude DBTest.Randomized,DBTest.FileCreationRandomFailure -Concurrency 18
+- ps: build_tools\run_ci_db_test.ps1 -Run env_test -Concurrency 1
 

arcanist_util/__phutil_library_init__.php

@@ -0,0 +1,3 @@
+<?php
+
+phutil_register_library('arcanist_util', __FILE__);

arcanist_util/__phutil_library_map__.php

@@ -0,0 +1,38 @@
+<?php
+
+/**
+ * This file is automatically generated. Use 'arc liberate' to rebuild it.
+ * @generated
+ * @phutil-library-version 2
+ */
+
+phutil_register_library_map(array(
+  '__library_version__' => 2,
+  'class' =>
+  array(
+    'ArcanistCpplintLinter' => 'cpp_linter/ArcanistCpplintLinter.php',
+    'BaseDirectoryScopedFormatLinter' => 'cpp_linter/BaseDirectoryScopedFormatLinter.php',
+    'FacebookArcanistConfiguration' => 'config/FacebookArcanistConfiguration.php',
+    'FacebookFbcodeLintEngine' => 'lint_engine/FacebookFbcodeLintEngine.php',
+    'FacebookFbcodeUnitTestEngine' => 'unit_engine/FacebookFbcodeUnitTestEngine.php',
+    'FacebookHowtoevenLintEngine' => 'lint_engine/FacebookHowtoevenLintEngine.php',
+    'FacebookHowtoevenLinter' => 'cpp_linter/FacebookHowtoevenLinter.php',
+    'FbcodeClangFormatLinter' => 'cpp_linter/FbcodeClangFormatLinter.php',
+    'FbcodeCppLinter' => 'cpp_linter/FbcodeCppLinter.php',
+  ),
+  'function' =>
+  array(
+  ),
+  'xmap' =>
+  array(
+    'ArcanistCpplintLinter' => 'ArcanistLinter',
+    'BaseDirectoryScopedFormatLinter' => 'ArcanistLinter',
+    'FacebookArcanistConfiguration' => 'ArcanistConfiguration',
+    'FacebookFbcodeLintEngine' => 'ArcanistLintEngine',
+    'FacebookFbcodeUnitTestEngine' => 'ArcanistBaseUnitTestEngine',
+    'FacebookHowtoevenLintEngine' => 'ArcanistLintEngine',
+    'FacebookHowtoevenLinter' => 'ArcanistLinter',
+    'FbcodeClangFormatLinter' => 'BaseDirectoryScopedFormatLinter',
+    'FbcodeCppLinter' => 'ArcanistLinter',
+  ),
+));

arcanist_util/config/FacebookArcanistConfiguration.php

@@ -0,0 +1,35 @@
+<?php
+// Copyright 2004-present Facebook. All Rights Reserved.
+// This source code is licensed under the BSD-style license found in the
+// LICENSE file in the root directory of this source tree. An additional grant
+// of patent rights can be found in the PATENTS file in the same directory.
+
+class FacebookArcanistConfiguration extends ArcanistConfiguration {
+
+  public function didRunWorkflow($command,
+                                 ArcanistBaseWorkflow $workflow,
+                                 $error_code) {
+    if ($command == 'diff' && !$workflow->isRawDiffSource()) {
+      $this->maybePushToJenkins($workflow);
+    }
+  }
+
+  //////////////////////////////////////////////////////////////////////
+  /* Send off builds to jenkins */
+  function maybePushToJenkins($workflow) {
+    $diffID = $workflow->getDiffID();
+    if ($diffID === null) {
+      return;
+    }
+
+    $results = $workflow->getTestResults();
+    if (!$results) {
+      return;
+    }
+
+    $url = "https://ci-builds.fb.com/view/rocksdb/job/rocksdb_diff_check/"
+               ."buildWithParameters?token=AUTH&DIFF_ID=$diffID";
+    system("curl --noproxy '*' \"$url\" > /dev/null 2>&1");
+  }
+
+}

arcanist_util/cpp_linter/ArcanistCpplintLinter.php

@@ -0,0 +1,88 @@
+<?php
+
+/**
+ * Uses google's cpplint.py to check code. RocksDB team forked this file from
+ * phabricator's /src/lint/linter/ArcanistCpplintLinter.php, and customized it
+ * for its own use.
+ *
+ * You can get it here:
+ * http://google-styleguide.googlecode.com/svn/trunk/cpplint/cpplint.py
+ * @group linter
+ */
+final class ArcanistCpplintLinter extends ArcanistLinter {
+
+  public function willLintPaths(array $paths) {
+    return;
+  }
+
+  public function getLinterName() {
+    return 'cpplint.py';
+  }
+
+  public function getLintPath() {
+    $bin = 'cpplint.py';
+    // Search under current dir
+    list($err) = exec_manual('which %s/%s', $this->linterDir(), $bin);
+    if (!$err) {
+      return $this->linterDir().'/'.$bin;
+    }
+
+    // Look for globally installed cpplint.py
+    list($err) = exec_manual('which %s', $bin);
+    if ($err) {
+      throw new ArcanistUsageException(
+        "cpplint.py does not appear to be installed on this system. Install ".
+        "it (e.g., with 'wget \"http://google-styleguide.googlecode.com/".
+        "svn/trunk/cpplint/cpplint.py\"') ".
+        "in your .arcconfig to point to the directory where it resides. ".
+        "Also don't forget to chmod a+x cpplint.py!");
+    }
+
+    return $bin;
+  }
+
+  public function lintPath($path) {
+    $bin = $this->getLintPath();
+    $path = $this->rocksdbDir().'/'.$path;
+
+    $f = new ExecFuture("%C $path", $bin);
+
+    list($err, $stdout, $stderr) = $f->resolve();
+
+    if ($err === 2) {
+      throw new Exception("cpplint failed to run correctly:\n".$stderr);
+    }
+
+    $lines = explode("\n", $stderr);
+    $messages = array();
+    foreach ($lines as $line) {
+      $line = trim($line);
+      $matches = null;
+      $regex = '/^[^:]+:(\d+):\s*(.*)\s*\[(.*)\] \[(\d+)\]$/';
+      if (!preg_match($regex, $line, $matches)) {
+        continue;
+      }
+      foreach ($matches as $key => $match) {
+        $matches[$key] = trim($match);
+      }
+      $message = new ArcanistLintMessage();
+      $message->setPath($path);
+      $message->setLine($matches[1]);
+      $message->setCode($matches[3]);
+      $message->setName($matches[3]);
+      $message->setDescription($matches[2]);
+      $message->setSeverity(ArcanistLintSeverity::SEVERITY_WARNING);
+      $this->addLintMessage($message);
+    }
+  }
+
+  // The path of this linter
+  private function linterDir() {
+    return dirname(__FILE__);
+  }
+
+  // TODO(kaili) a quick and dirty way to figure out rocksdb's root dir.
+  private function rocksdbDir() {
+    return $this->linterDir()."/../..";
+  }
+}

arcanist_util/cpp_linter/BaseDirectoryScopedFormatLinter.php

@@ -0,0 +1,74 @@
+<?php
+// Copyright 2004-present Facebook. All Rights Reserved.
+// This source code is licensed under the BSD-style license found in the
+// LICENSE file in the root directory of this source tree. An additional grant
+// of patent rights can be found in the PATENTS file in the same directory.
+
+abstract class BaseDirectoryScopedFormatLinter extends ArcanistLinter {
+
+  const LINT_FORMATTING = 1;
+
+  private $changedLines = array();
+  private $rawLintOutput = array();
+
+  abstract protected function getPathsToLint();
+
+  protected function shouldLintPath($path) {
+    foreach ($this->getPathsToLint() as $p) {
+      // check if $path starts with $p
+      if (strncmp($path, $p, strlen($p)) === 0) {
+        return true;
+      }
+    }
+    return false;
+  }
+
+  // API to tell this linter which lines were changed
+  final public function setPathChangedLines($path, $changed) {
+    $this->changedLines[$path] = $changed;
+  }
+
+  final public function willLintPaths(array $paths) {
+    $futures = array();
+    foreach ($paths as $path) {
+      if (!$this->shouldLintPath($path)) {
+        continue;
+      }
+
+      $changed = $this->changedLines[$path];
+      if (!isset($changed)) {
+        // do not run linter if there are no changes
+        continue;
+      }
+
+      $futures[$path] = $this->getFormatFuture($path, $changed);
+    }
+
+    foreach (Futures($futures)->limit(8) as $p => $f) {
+      $this->rawLintOutput[$p] = $f->resolvex();
+    }
+  }
+
+  abstract protected function getFormatFuture($path, array $changed);
+  abstract protected function getLintMessage($diff);
+
+  final public function lintPath($path) {
+    if (!isset($this->rawLintOutput[$path])) {
+      return;
+    }
+
+    list($new_content) = $this->rawLintOutput[$path];
+    $old_content = $this->getData($path);
+
+    if ($new_content != $old_content) {
+      $diff = ArcanistDiffUtils::renderDifferences($old_content, $new_content);
+      $this->raiseLintAtOffset(
+        0,
+        self::LINT_FORMATTING,
+        $this->getLintMessage($diff),
+        $old_content,
+        $new_content);
+    }
+  }
+
+}

arcanist_util/cpp_linter/FacebookHowtoevenLinter.php

@@ -0,0 +1,223 @@
+<?php
+// Copyright 2015-present Facebook. All Rights Reserved.
+// This source code is licensed under the BSD-style license found in the
+// LICENSE file in the root directory of this source tree. An additional grant
+// of patent rights can be found in the PATENTS file in the same directory.
+
+final class FacebookHowtoevenLinter extends ArcanistLinter {
+
+  const VERSION = 'fd9192f324c36d28136d14380f0b552a1385b59b';
+
+  private $parsedTargets = array();
+
+  public function getLinterName() {
+    return 'Howtoeven';
+  }
+
+  protected function getSeverity($code) {
+    $severities = array(
+      ArcanistLintSeverity::SEVERITY_DISABLED,
+      ArcanistLintSeverity::SEVERITY_ADVICE,
+      ArcanistLintSeverity::SEVERITY_WARNING,
+      ArcanistLintSeverity::SEVERITY_ERROR,
+    );
+    return idx($severities, $code, ArcanistLintSeverity::SEVERITY_WARNING);
+  }
+
+  public function willLintPaths(array $paths) {
+    // Cleanup previous runs.
+    $this->localExecx("rm -rf _build/_lint");
+
+    // Build compilation database.
+    $lintable_paths = $this->getLintablePaths($paths);
+    $interesting_paths = $this->getInterestingPaths($lintable_paths);
+
+    if (!$lintable_paths) {
+      return;
+    }
+
+    // Run lint.
+    try {
+      $this->localExecx(
+        "%C %C -p _build/dev/ %Ls",
+        $this->getBinaryPath(),
+        $this->getFilteredIssues(),
+        $lintable_paths);
+    } catch (CommandException $exception) {
+      PhutilConsole::getConsole()->writeErr($exception->getMessage());
+    }
+
+    // Load results.
+    $result = id(
+      new SQLite3(
+        $this->getProjectRoot().'/_build/_lint/lint.db',
+        SQLITE3_OPEN_READONLY))
+      ->query("SELECT * FROM raised_issues");
+
+    while ($issue = $result->fetchArray(SQLITE3_ASSOC)) {
+      // Skip issues not part of the linted file.
+      if (in_array($issue['file'], $interesting_paths)) {
+        $this->addLintMessage(id(new ArcanistLintMessage())
+          ->setPath($issue['file'])
+          ->setLine($issue['line'])
+          ->setChar($issue['column'])
+          ->setCode('Howtoeven')
+          ->setSeverity($this->getSeverity($issue['severity']))
+          ->setName('Hte-'.$issue['name'])
+          ->setDescription(
+            sprintf(
+              "%s\n\n%s",
+              ($issue['message']) ? $issue['message'] : $issue['description'],
+              $issue['explanation']))
+          ->setOriginalText(idx($issue, 'original', ''))
+          ->setReplacementText(idx($issue, 'replacement', '')));
+      }
+    }
+  }
+
+  public function lintPath($path) {
+  }
+
+  /**
+   * Get the paths that we know how to lint.
+   *
+   * The strategy is to first look whether there's an existing compilation
+   * database and use that if it's exhaustive. We generate our own only if
+   * necessary.
+   */
+  private function getLintablePaths($paths) {
+    // Replace headers with existing sources.
+    for ($i = 0; $i < count($paths); $i++) {
+      if (preg_match("/\.h$/", $paths[$i])) {
+        $header = preg_replace("/\.h$/", ".cpp", $paths[$i]);
+        if (file_exists($header)) {
+          $paths[$i] = $header;
+        }
+      }
+    }
+
+    // Check if database exists and is exhaustive.
+    $available_paths = $this->getAvailablePaths();
+    $lintable_paths = array_intersect($paths, $available_paths);
+    if ($paths === $lintable_paths) {
+      return $lintable_paths;
+    }
+
+    // Generate our own database.
+    $targets = $this->getTargetsFor($paths);
+    if (!$targets) {
+      PhutilConsole::getConsole()->writeErr(
+        "No build targets found for %s\n",
+        implode(', ', $paths));
+      return array();
+    }
+
+    $this->localExecx("./tools/build/bin/fbconfig.par -r %Ls", $targets);
+    $this->localExecx("./tools/build/bin/fbmake.par gen_cdb");
+
+    $available_paths = $this->getAvailablePaths();
+    $lintable_paths = array_intersect($paths, $available_paths);
+    if ($paths != $lintable_paths) {
+      PhutilConsole::getConsole()->writeErr(
+        "Can't lint %s\n",
+        implode(', ', array_diff($paths, $available_paths)));
+    }
+
+    // Return what we know how to lint.
+    return $lintable_paths;
+  }
+
+  /**
+   * Get the available paths in the current compilation database.
+   */
+  private function getAvailablePaths() {
+    $database_path = $this->getProjectRoot()
+      .'/_build/dev/compile_commands.json';
+    if (!file_exists($database_path)) {
+      return array();
+    }
+
+    $entries = json_decode(file_get_contents($database_path), true);
+    $paths = array();
+    foreach ($entries as $entry) {
+      $paths[] = $entry['file'];
+    }
+    return $paths;
+  }
+
+  /**
+   * Search for the targets directories for the given files.
+   */
+  private static function getTargetsFor($paths) {
+    $targets = array();
+    foreach ($paths as $path) {
+      while (($path = dirname($path)) !== '.') {
+        if (in_array('TARGETS', scandir($path))) {
+          $contents = file_get_contents($path.'/TARGETS');
+          if (strpos($contents, 'cpp_binary') !== false) {
+            $targets[] = $path;
+            break;
+          }
+        }
+      }
+    }
+    return array_unique($targets);
+  }
+
+  /**
+   * The paths that we actually want to report on.
+   */
+  private function getInterestingPaths($paths) {
+    $headers = array();
+    foreach ($paths as $path) {
+      $headers[] = preg_replace("/\.cpp$/", ".h", $path);
+    }
+    return array_merge($paths, $headers);
+  }
+
+  /**
+   * The path where the binary is located. Will return the current dewey binary
+   * unless the `HOWTOEVEN_BUILD` environment variable is set.
+   */
+  private function getBinaryPath() {
+    $path = sprintf(
+      "/mnt/dewey/fbcode/.commits/%s/builds/howtoeven/client",
+      self::VERSION);
+
+    $build = getenv('HOWTOEVEN_BUILD');
+    if ($build) {
+      $path = sprintf(
+        "./_build/%s/tools/howtoeven/client",
+        $build);
+      if (!file_exists($path)) {
+        PhutilConsole::getConsole()->writeErr(">> %s does not exist\n", $path);
+        exit(1);
+      }
+    }
+
+    return $path;
+  }
+
+  /**
+   * Execute the command in the root directory.
+   */
+  private function localExecx($command /* , ... */) {
+    $arguments = func_get_args();
+    return newv('ExecFuture', $arguments)
+      ->setCWD($this->getProjectRoot())
+      ->resolvex();
+  }
+
+  /**
+   * The root of the project.
+   */
+  private function getProjectRoot() {
+    return $this->getEngine()->getWorkingCopy()->getProjectRoot();
+  }
+
+  private function getFilteredIssues() {
+    $issues = getenv('HOWTOEVEN_ISSUES');
+    return ($issues) ? csprintf('-issues %s', $issues) : '';
+  }
+
+}

arcanist_util/cpp_linter/FbcodeClangFormatLinter.php

@@ -0,0 +1,58 @@
+<?php
+// Copyright 2004-present Facebook. All Rights Reserved.
+// This source code is licensed under the BSD-style license found in the
+// LICENSE file in the root directory of this source tree. An additional grant
+// of patent rights can be found in the PATENTS file in the same directory.
+
+final class FbcodeClangFormatLinter extends BaseDirectoryScopedFormatLinter {
+
+  const LINT_FORMATTING = 1;
+  const CLANG_FORMAT_BINARY = '/mnt/vol/engshare/admin/scripts/clang-format';
+
+  protected function getPathsToLint() {
+    return array('');
+  }
+
+  public function getLinterName() {
+    return 'CLANG_FORMAT';
+  }
+
+  public function getLintSeverityMap() {
+    return array(
+      self::LINT_FORMATTING => ArcanistLintSeverity::SEVERITY_ADVICE,
+    );
+  }
+
+  public function getLintNameMap() {
+    return array(
+      self::LINT_FORMATTING => pht('Changes are not clang-formatted'),
+    );
+  }
+
+  protected function getFormatFuture($path, array $changed) {
+    $args = "";
+    foreach ($changed as $key => $value) {
+      $args .= " --lines=$key:$key";
+    }
+
+    $binary = self::CLANG_FORMAT_BINARY;
+    if (!file_exists($binary)) {
+      // trust the $PATH
+      $binary = "clang-format";
+    }
+
+    return new ExecFuture(
+      "%s %s $args",
+      $binary,
+      $this->getEngine()->getFilePathOnDisk($path));
+  }
+
+  protected function getLintMessage($diff) {
+    $link_to_clang_format =
+      "[[ http://fburl.com/clang-format | clang-format ]]";
+    return <<<LINT_MSG
+Changes in this file were not formatted using $link_to_clang_format.
+Please run build_tools/format-diff.sh or `make format`
+LINT_MSG;
+  }
+}

arcanist_util/cpp_linter/FbcodeCppLinter.php

@@ -0,0 +1,126 @@
+<?php
+// Copyright 2004-present Facebook.  All rights reserved.
+
+class FbcodeCppLinter extends ArcanistLinter {
+  const FLINT      = "/home/engshare/tools/flint";
+  const LINT_ERROR   = 1;
+  const LINT_WARNING = 2;
+  const LINT_ADVICE  = 3;
+  const C_FLAG = "--c_mode=true";
+
+  private $rawLintOutput = array();
+
+  public function willLintPaths(array $paths) {
+    if (!file_exists(self::FLINT)) {
+      return;
+    }
+    $futures = array();
+    foreach ($paths as $p) {
+      $lpath = $this->getEngine()->getFilePathOnDisk($p);
+      $lpath_file = file($lpath);
+      if (preg_match('/\.(c)$/', $lpath) ||
+          preg_match('/-\*-.*Mode: C[; ].*-\*-/', $lpath_file[0]) ||
+          preg_match('/vim(:.*)*:\s*(set\s+)?filetype=c\s*:/', $lpath_file[0])
+          ) {
+        $futures[$p] = new ExecFuture("%s %s %s 2>&1",
+                           self::FLINT, self::C_FLAG,
+                           $this->getEngine()->getFilePathOnDisk($p));
+      } else {
+        $futures[$p] = new ExecFuture("%s %s 2>&1",
+          self::FLINT, $this->getEngine()->getFilePathOnDisk($p));
+      }
+    }
+
+    foreach (Futures($futures)->limit(8) as $p => $f) {
+      $this->rawLintOutput[$p] = $f->resolvex();
+    }
+
+    return;
+  }
+
+  public function getLinterName() {
+    return "FBCPP";
+  }
+
+  public function lintPath($path) {
+    $this->runCppLint($path);
+  }
+
+  private function runCppLint($path) {
+    $msgs = $this->getCppLintOutput($path);
+    foreach ($msgs as $m) {
+      $this->raiseLintAtLine($m['line'], 0, $m['severity'], $m['msg']);
+    }
+  }
+
+  private function adviseOnEachPattern(
+    $path,
+    $regex,
+    $message,
+    $lint_type = self::LINT_ADVICE,
+    $match_idx = 0) {
+      $file_data = $this->getData($path);
+      $matches = array();
+      if (!preg_match_all($regex, $file_data, $matches, PREG_OFFSET_CAPTURE)) {
+        return;
+      }
+
+      foreach ($matches[$match_idx] as $match) {
+        list($match_str, $offset) = $match;
+        $this->raiseLintAtOffset($offset, $lint_type, $message, $match_str);
+      }
+  }
+
+  public function getLintSeverityMap() {
+    return array(
+      self::LINT_WARNING => ArcanistLintSeverity::SEVERITY_WARNING,
+      self::LINT_ADVICE  => ArcanistLintSeverity::SEVERITY_ADVICE,
+      self::LINT_ERROR   => ArcanistLintSeverity::SEVERITY_ERROR
+    );
+  }
+
+  public function getLintNameMap() {
+    return array(
+      self::LINT_ADVICE   => "CppLint Advice",
+      self::LINT_WARNING  => "CppLint Warning",
+      self::LINT_ERROR    => "CppLint Error"
+    );
+  }
+
+  private function getCppLintOutput($path) {
+     if (!array_key_exists($path, $this->rawLintOutput)) {
+       return array();
+     }
+    list($output) = $this->rawLintOutput[$path];
+
+    $msgs = array();
+    $current = null;
+    $matches = array();
+    foreach (explode("\n", $output) as $line) {
+      if (preg_match('/.*?:(\d+):(.*)/', $line, $matches)) {
+        if ($current) {
+          $msgs[] = $current;
+        }
+        $line = $matches[1];
+        $text = $matches[2];
+        if (preg_match('/.*Warning.*/', $text)) {
+          $sev = self::LINT_WARNING;
+        } else if (preg_match('/.*Advice.*/', $text)) {
+          $sev = self::LINT_ADVICE;
+        } else {
+          $sev = self::LINT_ERROR;
+        }
+        $current = array('line'     => $line,
+                         'msg'      => $text,
+                         'severity' => $sev);
+      } else if ($current) {
+        $current['msg'] .= ' ' . $line;
+      }
+    }
+    if ($current) {
+      $msgs[] = $current;
+    }
+
+    return $msgs;
+  }
+}

arcanist_util/lint_engine/FacebookFbcodeLintEngine.php

@@ -0,0 +1,140 @@
+<?php
+// Copyright 2004-present Facebook.  All rights reserved.
+// This source code is licensed under the BSD-style license found in the
+// LICENSE file in the root directory of this source tree. An additional grant
+// of patent rights can be found in the PATENTS file in the same directory.
+
+class FacebookFbcodeLintEngine extends ArcanistLintEngine {
+
+  public function buildLinters() {
+    $linters = array();
+    $paths = $this->getPaths();
+
+    // Remove all deleted files, which are not checked by the
+    // following linters.
+    foreach ($paths as $key => $path) {
+      if (!Filesystem::pathExists($this->getFilePathOnDisk($path))) {
+        unset($paths[$key]);
+      }
+    }
+
+    $generated_linter = new ArcanistGeneratedLinter();
+    $linters[] = $generated_linter;
+
+    $nolint_linter = new ArcanistNoLintLinter();
+    $linters[] = $nolint_linter;
+
+    $text_linter = new ArcanistTextLinter();
+    $text_linter->setCustomSeverityMap(array(
+      ArcanistTextLinter::LINT_LINE_WRAP
+        => ArcanistLintSeverity::SEVERITY_ADVICE,
+    ));
+    $linters[] = $text_linter;
+
+    $java_text_linter = new ArcanistTextLinter();
+    $java_text_linter->setMaxLineLength(100);
+    $java_text_linter->setCustomSeverityMap(array(
+      ArcanistTextLinter::LINT_LINE_WRAP
+        => ArcanistLintSeverity::SEVERITY_ADVICE,
+    ));
+    $linters[] = $java_text_linter;
+
+    $python_linter = new ArcanistPEP8Linter();
+    $linters[] = $python_linter;
+
+    if (!$this->getCommitHookMode()) {
+      $cpp_linters = array();
+      $cpp_linters[] = $linters[] = new ArcanistCpplintLinter();
+      $cpp_linters[] = $linters[] = new FbcodeCppLinter();
+
+      $clang_format_linter = new FbcodeClangFormatLinter();
+      $linters[] = $clang_format_linter;
+    }
+
+    $spelling_linter = new ArcanistSpellingLinter();
+    $linters[] = $spelling_linter;
+
+    foreach ($paths as $path) {
+      $is_text = false;
+
+      $text_extensions = (
+        '/\.('.
+        'cpp|cxx|c|cc|h|hpp|hxx|tcc|'.
+        'py|rb|hs|pl|pm|tw|'.
+        'php|phpt|css|js|'.
+        'java|'.
+        'thrift|'.
+        'lua|'.
+        'siv|'.
+        'txt'.
+        ')$/'
+      );
+      if (preg_match($text_extensions, $path)) {
+        $is_text = true;
+      }
+      if ($is_text) {
+        $nolint_linter->addPath($path);
+
+        $generated_linter->addPath($path);
+        $generated_linter->addData($path, $this->loadData($path));
+
+        if (preg_match('/\.java$/', $path)) {
+          $java_text_linter->addPath($path);
+          $java_text_linter->addData($path, $this->loadData($path));
+        } else {
+          $text_linter->addPath($path);
+          $text_linter->addData($path, $this->loadData($path));
+        }
+
+        $spelling_linter->addPath($path);
+        $spelling_linter->addData($path, $this->loadData($path));
+      }
+      if (preg_match('/\.(cpp|c|cc|cxx|h|hh|hpp|hxx|tcc)$/', $path)
+          && !preg_match('/third-party/', $path)) {
+        foreach ($cpp_linters as &$linter) {
+          $linter->addPath($path);
+          $linter->addData($path, $this->loadData($path));
+        }
+
+        $clang_format_linter->addPath($path);
+        $clang_format_linter->addData($path, $this->loadData($path));
+        $clang_format_linter->setPathChangedLines(
+          $path, $this->getPathChangedLines($path));
+      }
+
+      // Match *.py and contbuild config files
+      if (preg_match('/(\.(py|tw|smcprops)|^contbuild\/configs\/[^\/]*)$/',
+                    $path)) {
+        $space_count = 4;
+        $real_path = $this->getFilePathOnDisk($path);
+        $dir = dirname($real_path);
+        do {
+          if (file_exists($dir.'/.python2space')) {
+            $space_count = 2;
+            break;
+          }
+          $dir = dirname($dir);
+        } while ($dir != '/' && $dir != '.');
+
+        $cur_path_linter = $python_linter;
+        $cur_path_linter->addPath($path);
+        $cur_path_linter->addData($path, $this->loadData($path));
+
+        if (preg_match('/\.tw$/', $path)) {
+          $cur_path_linter->setCustomSeverityMap(array(
+            'E251' => ArcanistLintSeverity::SEVERITY_DISABLED,
+          ));
+        }
+      }
+    }
+
+    $name_linter = new ArcanistFilenameLinter();
+    $linters[] = $name_linter;
+    foreach ($paths as $path) {
+      $name_linter->addPath($path);
+    }
+
+    return $linters;
+  }
+
+}

arcanist_util/lint_engine/FacebookHowtoevenLintEngine.php

@@ -0,0 +1,27 @@
+<?php
+// Copyright 2015-present Facebook. All Rights Reserved.
+// This source code is licensed under the BSD-style license found in the
+// LICENSE file in the root directory of this source tree. An additional grant
+// of patent rights can be found in the PATENTS file in the same directory.
+
+final class FacebookHowtoevenLintEngine extends ArcanistLintEngine {
+
+  public function buildLinters() {
+    $paths = array();
+
+    foreach ($this->getPaths() as $path) {
+      // Don't try to lint deleted files or changed directories.
+      if (!Filesystem::pathExists($path) || is_dir($path)) {
+        continue;
+      }
+
+      if (preg_match('/\.(cpp|c|cc|cxx|h|hh|hpp|hxx|tcc)$/', $path)) {
+        $paths[] = $path;
+      }
+    }
+
+    $howtoeven = new FacebookHowtoevenLinter();
+    $howtoeven->setPaths($paths);
+    return array($howtoeven);
+  }
+}

arcanist_util/unit_engine/FacebookFbcodeUnitTestEngine.php

@@ -0,0 +1,21 @@
+<?php
+// Copyright 2004-present Facebook. All Rights Reserved.
+// This source code is licensed under the BSD-style license found in the
+// LICENSE file in the root directory of this source tree. An additional grant
+// of patent rights can be found in the PATENTS file in the same directory.
+
+class FacebookFbcodeUnitTestEngine extends ArcanistBaseUnitTestEngine {
+
+  public function run() {
+    // Here we create a new unit test "jenkins_async_test" and promise we'll
+    // update the results later.
+    // Jenkins updates the results using `arc call-conduit
+    // differential.updateunitresults` call. If you change the name here, also
+    // make sure to change the name in Jenkins script that updates the test
+    // result -- they have to be the same.
+    $result = new ArcanistUnitTestResult();
+    $result->setName("jenkins_async_test");
+    $result->setResult(ArcanistUnitTestResult::RESULT_POSTPONED);
+    return array($result);
+  }
+}

build_tools/build_detect_platform

@@ -19,21 +19,22 @@
 #
 # The PLATFORM_CCFLAGS and PLATFORM_CXXFLAGS might include the following:
 #
-#       -DROCKSDB_PLATFORM_POSIX    if posix-platform based
+#       -DLEVELDB_PLATFORM_POSIX if cstdatomic is present
+#       -DLEVELDB_PLATFORM_NOATOMIC if it is not
 #       -DSNAPPY                    if the Snappy library is present
 #       -DLZ4                       if the LZ4 library is present
 #       -DZSTD                      if the ZSTD library is present
 #       -DNUMA                      if the NUMA library is present
-#       -DTBB                       if the TBB library is present
 #
 # Using gflags in rocksdb:
 # Our project depends on gflags, which requires users to take some extra steps
 # before they can compile the whole repository:
 #   1. Install gflags. You may download it from here:
-#      https://gflags.github.io/gflags/ (Mac users can `brew install gflags`)
-#   2. Once installed, add the include path for gflags to your CPATH env var and
-#      the lib path to LIBRARY_PATH. If installed with default settings, the lib
-#      will be /usr/local/lib and the include path will be /usr/local/include
+#      https://code.google.com/p/gflags/
+#   2. Once install, add the include path/lib path for gflags to CPATH and
+#      LIBRARY_PATH respectively. If installed with default mode, the
+#      lib and include path will be /usr/local/lib and /usr/local/include
+# Mac user can do this by having brew installed and running brew install gflags
 
 OUTPUT=$1
 if test -z "$OUTPUT"; then
@@ -164,7 +165,7 @@ case "$TARGET_OS" in
         ;;
     OS_ANDROID_CROSSCOMPILE)
         PLATFORM=OS_ANDROID
-	COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_ANDROID -DROCKSDB_PLATFORM_POSIX"
+	COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_ANDROID -DLEVELDB_PLATFORM_POSIX"
 	PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS "  # All pthread features are in the Android C library
         # PORT_FILES=port/android/android.cc
         CROSS_COMPILE=true
@@ -183,19 +184,17 @@ if [ "$CROSS_COMPILE" = "true" -o "$FBCODE_BUILD" = "true" ]; then
     # Also don't need any compilation tests if compiling on fbcode
     true
 else
-    if ! test $ROCKSDB_DISABLE_FALLOCATE; then
-        # Test whether fallocate is available
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <fcntl.h>
-          #include <linux/falloc.h>
-          int main() {
-      int fd = open("/dev/null", 0);
-      fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
-          }
+    # Test whether fallocate is available
+    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <fcntl.h>
+      #include <linux/falloc.h>
+      int main() {
+	int fd = open("/dev/null", 0);
+  fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
+      }
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_FALLOCATE_PRESENT"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_FALLOCATE_PRESENT"
     fi
 
     # Test whether Snappy library is installed
@@ -282,7 +281,7 @@ EOF
     # Test whether numa is available
     $CXX $CFLAGS -x c++ - -o /dev/null -lnuma 2>/dev/null  <<EOF
       #include <numa.h>
-      #include <numaif.h>
+      #inlcude <numaif.h>
       int main() {}
 EOF
     if [ "$?" = 0 ]; then
@@ -291,27 +290,15 @@ EOF
         JAVA_LDFLAGS="$JAVA_LDFLAGS -lnuma"
     fi
 
-    # Test whether tbb is available
-    $CXX $CFLAGS $LDFLAGS -x c++ - -o /dev/null -ltbb 2>/dev/null  <<EOF
-      #include <tbb/tbb.h>
-      int main() {}
-EOF
-    if [ "$?" = 0 ]; then
-        COMMON_FLAGS="$COMMON_FLAGS -DTBB"
-        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltbb"
-        JAVA_LDFLAGS="$JAVA_LDFLAGS -ltbb"
-    fi
-
     # Test whether jemalloc is available
     if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null -ljemalloc \
-      2>/dev/null; then
+      2>/dev/null; then 
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ljemalloc"
         JAVA_LDFLAGS="$JAVA_LDFLAGS -ljemalloc"
-        JEMALLOC=1
     else
         # jemalloc is not available. Let's try tcmalloc
         if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null \
-          -ltcmalloc 2>/dev/null; then
+          -ltcmalloc 2>/dev/null; then 
             PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltcmalloc"
             JAVA_LDFLAGS="$JAVA_LDFLAGS -ltcmalloc"
         fi
@@ -328,55 +315,6 @@ EOF
     if [ "$?" = 0 ]; then
         COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_MALLOC_USABLE_SIZE"
     fi
-
-    # Test whether PTHREAD_MUTEX_ADAPTIVE_NP mutex type is available
-    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-      #include <pthread.h>
-      int main() {
-        int x = PTHREAD_MUTEX_ADAPTIVE_NP;
-        return 0;
-      }
-EOF
-    if [ "$?" = 0 ]; then
-        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_PTHREAD_ADAPTIVE_MUTEX"
-    fi
-
-    # Test whether backtrace is available
-    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-      #include <execinfo.h>>
-      int main() {
-        void* frames[1];
-        backtrace_symbols(frames, backtrace(frames, 1));
-        return 0;
-      }
-EOF
-    if [ "$?" = 0 ]; then
-        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
-    else
-        # Test whether execinfo library is installed
-        $CXX $CFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <execinfo.h>
-          int main() {
-            void* frames[1];
-            backtrace_symbols(frames, backtrace(frames, 1));
-          }
-EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lexecinfo"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -lexecinfo"
-        fi
-    fi
-
-    # Test if -pg is supported
-    $CXX $CFLAGS -pg -x c++ - -o /dev/null 2>/dev/null  <<EOF
-      int main() {
-        return 0;
-      }
-EOF
-    if [ "$?" = 0 ]; then
-        PROFILING_FLAGS=-pg
-    fi
 fi
 
 # TODO(tec): Fix -Wshorten-64-to-32 errors on FreeBSD and enable the warning.
@@ -416,15 +354,7 @@ if test "$USE_SSE"; then
   # if Intel SSE instruction set is supported, set USE_SSE=1
   COMMON_FLAGS="$COMMON_FLAGS -msse -msse4.2 "
 elif test -z "$PORTABLE"; then
-  if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
-    # Tune for this POWER processor, treating '+' models as base models
-    POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
-    COMMON_FLAGS="$COMMON_FLAGS -mcpu=$POWER -mtune=$POWER "
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
-    COMMON_FLAGS="$COMMON_FLAGS -march=z10 "
-  else
-    COMMON_FLAGS="$COMMON_FLAGS -march=native "
-  fi
+  COMMON_FLAGS="$COMMON_FLAGS -march=native "
 fi
 
 PLATFORM_CCFLAGS="$PLATFORM_CCFLAGS $COMMON_FLAGS"
@@ -457,8 +387,3 @@ echo "ROCKSDB_MINOR=$ROCKSDB_MINOR" >> "$OUTPUT"
 echo "ROCKSDB_PATCH=$ROCKSDB_PATCH" >> "$OUTPUT"
 echo "CLANG_SCAN_BUILD=$CLANG_SCAN_BUILD" >> "$OUTPUT"
 echo "CLANG_ANALYZER=$CLANG_ANALYZER" >> "$OUTPUT"
-echo "PROFILING_FLAGS=$PROFILING_FLAGS" >> "$OUTPUT"
-if test -n "$JEMALLOC"; then
-  echo "JEMALLOC=1" >> "$OUTPUT"
-fi
-echo "LUA_PATH=$LUA_PATH" >> "$OUTPUT"

build_tools/cont_integration.sh

@@ -1,135 +0,0 @@
-#!/bin/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`
-  echo $DATE $@
-}
-
-function log_err {
-  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 $error
-  fi
-}
-
-#
-# Execution starts here.
-#
-
-# Path to the determinator from the root of the RocksDB repo.
-CONTRUN_DETERMINATOR=./arcanist_util/config/RocksDBCommonHelper.php
-
-# Value of the previous commit.
-PREV_COMMIT=
-
-log "Starting to monitor for new RocksDB changes ..."
-log "Running under `pwd` as `whoami`."
-
-# Paranoia. Make sure that we're using the right branch.
-git checkout master
-
-error=$?
-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_4.8.1.sh

@@ -1,18 +1,16 @@
-GCC_BASE=/mnt/gvfs/third-party2/gcc/cf7d14c625ce30bae1a4661c2319c5a283e4dd22/4.8.1/centos6-native/cc6c9dc
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/8598c375b0e94e1448182eb3df034704144a838d/stable/centos6-native/3f16ddd
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/d6e0a7da6faba45f5e5b1638f9edd7afc2f34e7d/4.8.1/gcc-4.8.1-glibc-2.17/8aac7fc
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/d282e6e8f3d20f4e40a516834847bdc038e07973/2.17/gcc-4.8.1-glibc-2.17/99df8fc
-SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/8c38a4c1e52b4c2cc8a9cdc31b9c947ed7dbfcb4/1.1.3/gcc-4.8.1-glibc-2.17/c3f970a
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/0882df3713c7a84f15abe368dc004581f20b39d7/1.2.8/gcc-4.8.1-glibc-2.17/c3f970a
-BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/740325875f6729f42d28deaa2147b0854f3a347e/1.0.6/gcc-4.8.1-glibc-2.17/c3f970a
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/0e790b441e2d9acd68d51e1d2e028f88c6a79ddf/r131/gcc-4.8.1-glibc-2.17/c3f970a
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/9455f75ff7f4831dc9fda02a6a0f8c68922fad8f/1.0.0/gcc-4.8.1-glibc-2.17/c3f970a
-GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/f001a51b2854957676d07306ef3abf67186b5c8b/2.1.1/gcc-4.8.1-glibc-2.17/c3f970a
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/fc8a13ca1fffa4d0765c716c5a0b49f0c107518f/master/gcc-4.8.1-glibc-2.17/8d31e51
-NUMA_BASE=/mnt/gvfs/third-party2/numa/17c514c4d102a25ca15f4558be564eeed76f4b6a/2.0.8/gcc-4.8.1-glibc-2.17/c3f970a
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/ad576de2a1ea560c4d3434304f0fc4e079bede42/trunk/gcc-4.8.1-glibc-2.17/675d945
-TBB_BASE=/mnt/gvfs/third-party2/tbb/9d9a554877d0c5bef330fe818ab7178806dd316a/4.0_update2/gcc-4.8.1-glibc-2.17/c3f970a
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/7c111ff27e0c466235163f00f280a9d617c3d2ec/4.0.9-36_fbk5_2933_gd092e3f/gcc-4.8.1-glibc-2.17/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/b7fd454c4b10c6a81015d4524ed06cdeab558490/2.26/centos6-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/d7f4d4d86674a57668e3a96f76f0e17dd0eb8765/3.8.1/gcc-4.8.1-glibc-2.17/c3f970a
-LUA_BASE=/mnt/gvfs/third-party2/lua/61e4abf5813bbc39bc4f548757ccfcadde175a48/5.2.3/centos6-native/730f94e
+GCC_BASE=/mnt/gvfs/third-party2/gcc/ebc96bc2fb751b5a0300b8d91a95bdf24ac1d88b/4.8.1/centos6-native/cc6c9dc
+CLANG_BASE=/mnt/vol/engshare/fbcode/third-party2/clang/3.7.1/centos6-native/9d9ecb9/
+LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/ea2fd1278810d3af2ea52218d2767e09d786dbd0/4.8.1/gcc-4.8.1-glibc-2.17/8aac7fc
+GLIBC_BASE=/mnt/gvfs/third-party2/glibc/f5484f168c0e4d19823d41df052c5870c6e575a4/2.17/gcc-4.8.1-glibc-2.17/99df8fc
+SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/cbf6f1f209e5bd160bdc5d971744e039f36b1566/1.1.3/gcc-4.8.1-glibc-2.17/c3f970a
+ZLIB_BASE=/mnt/gvfs/third-party2/zlib/6d39cb54708049f527e713ad19f2aadb9d3667e8/1.2.8/gcc-4.8.1-glibc-2.17/c3f970a
+BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/2ddd45f0853bfc8bb1c27f0f447236a1a26c338a/1.0.6/gcc-4.8.1-glibc-2.17/c3f970a
+LZ4_BASE=/mnt/gvfs/third-party2/lz4/6858fac689e0f92e584224d91bdb0e39f6c8320d/r131/gcc-4.8.1-glibc-2.17/c3f970a
+ZSTD_BASE=/mnt/gvfs/third-party2/zstd/9c833012dea9ae6de1df2cbdcb7aebc57ba2cb39/0.5.0/gcc-4.8.1-glibc-2.17/c3f970a
+GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/c7275a4ceae0aca0929e56964a31dafc53c1ee96/2.1.1/gcc-4.8.1-glibc-2.17/c3f970a
+JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/378c8f95cf28c833e121ca73432101e451c3e62a/4.0.3/gcc-4.8.1-glibc-2.17/8d31e51
+NUMA_BASE=/mnt/gvfs/third-party2/numa/ae54a5ed22cdabb1c6446dce4e8ffae5b4446d73/2.0.8/gcc-4.8.1-glibc-2.17/c3f970a
+LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/303048f72efc92ae079e62dfc84823401aecfd94/trunk/gcc-4.8.1-glibc-2.17/675d945
+KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/1a48835975c66d30e47770ec419758ed3b9ba010/3.10.62-62_fbk17_03959_ge29cc63/gcc-4.8.1-glibc-2.17/da39a3e
+BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/a5b8152b2a15ce8a98808cf954fbccec825a97bc/2.25/centos6-native/da39a3e
+VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/af85c56f424cd5edfc2c97588299b44ecdec96bb/3.8.1/gcc-4.8.1-glibc-2.17/c3f970a

build_tools/error_filter.py

@@ -1,167 +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).
-
-'''Filter for error messages in test output:
-    - Receives merged stdout/stderr from test on stdin
-    - Finds patterns of known error messages for test name (first argument)
-    - Prints those error messages to stdout
-'''
-
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-from __future__ import unicode_literals
-
-import re
-import sys
-
-
-class ErrorParserBase(object):
-    def parse_error(self, line):
-        '''Parses a line of test output. If it contains an error, returns a
-        formatted message describing the error; otherwise, returns None.
-        Subclasses must override this method.
-        '''
-        raise NotImplementedError
-
-
-class GTestErrorParser(ErrorParserBase):
-    '''A parser that remembers the last test that began running so it can print
-    that test's name upon detecting failure.
-    '''
-    _GTEST_NAME_PATTERN = re.compile(r'\[ RUN      \] (\S+)$')
-    # format: '<filename or "unknown file">:<line #>: Failure'
-    _GTEST_FAIL_PATTERN = re.compile(r'(unknown file|\S+:\d+): Failure$')
-
-    def __init__(self):
-        self._last_gtest_name = 'Unknown test'
-
-    def parse_error(self, line):
-        gtest_name_match = self._GTEST_NAME_PATTERN.match(line)
-        if gtest_name_match:
-            self._last_gtest_name = gtest_name_match.group(1)
-            return None
-        gtest_fail_match = self._GTEST_FAIL_PATTERN.match(line)
-        if gtest_fail_match:
-            return '%s failed: %s' % (
-                    self._last_gtest_name, gtest_fail_match.group(1))
-        return None
-
-
-class MatchErrorParser(ErrorParserBase):
-    '''A simple parser that returns the whole line if it matches the pattern.
-    '''
-    def __init__(self, pattern):
-        self._pattern = re.compile(pattern)
-
-    def parse_error(self, line):
-        if self._pattern.match(line):
-            return line
-        return None
-
-
-class CompilerErrorParser(MatchErrorParser):
-    def __init__(self):
-        # format: '<filename>:<line #>:<column #>: error: <error msg>'
-        super(CompilerErrorParser, self).__init__(r'\S+:\d+:\d+: error:')
-
-
-class ScanBuildErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(ScanBuildErrorParser, self).__init__(
-                r'scan-build: \d+ bugs found.$')
-
-
-class DbCrashErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(DbCrashErrorParser, self).__init__(r'\*\*\*.*\^$|TEST FAILED.')
-
-
-class WriteStressErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(WriteStressErrorParser, self).__init__(
-                r'ERROR: write_stress died with exitcode=\d+')
-
-
-class AsanErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(AsanErrorParser, self).__init__(
-                r'==\d+==ERROR: AddressSanitizer:')
-
-
-class UbsanErrorParser(MatchErrorParser):
-    def __init__(self):
-        # format: '<filename>:<line #>:<column #>: runtime error: <error msg>'
-        super(UbsanErrorParser, self).__init__(r'\S+:\d+:\d+: runtime error:')
-
-
-class ValgrindErrorParser(MatchErrorParser):
-    def __init__(self):
-        # just grab the summary, valgrind doesn't clearly distinguish errors
-        # from other log messages.
-        super(ValgrindErrorParser, self).__init__(r'==\d+== ERROR SUMMARY:')
-
-
-class CompatErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(CompatErrorParser, self).__init__(r'==== .*[Ee]rror.* ====$')
-
-
-class TsanErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(TsanErrorParser, self).__init__(r'WARNING: ThreadSanitizer:')
-
-
-_TEST_NAME_TO_PARSERS = {
-    'punit': [CompilerErrorParser, GTestErrorParser],
-    'unit': [CompilerErrorParser, GTestErrorParser],
-    'release': [CompilerErrorParser, GTestErrorParser],
-    'unit_481': [CompilerErrorParser, GTestErrorParser],
-    'release_481': [CompilerErrorParser, GTestErrorParser],
-    'clang_unit': [CompilerErrorParser, GTestErrorParser],
-    'clang_release': [CompilerErrorParser, GTestErrorParser],
-    'clang_analyze': [CompilerErrorParser, ScanBuildErrorParser],
-    'code_cov': [CompilerErrorParser, GTestErrorParser],
-    'unity': [CompilerErrorParser, GTestErrorParser],
-    'lite': [CompilerErrorParser],
-    'lite_test': [CompilerErrorParser, GTestErrorParser],
-    'stress_crash': [CompilerErrorParser, DbCrashErrorParser],
-    'write_stress': [CompilerErrorParser, WriteStressErrorParser],
-    'asan': [CompilerErrorParser, GTestErrorParser, AsanErrorParser],
-    'asan_crash': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
-    'ubsan': [CompilerErrorParser, GTestErrorParser, UbsanErrorParser],
-    'ubsan_crash': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
-    'valgrind': [CompilerErrorParser, GTestErrorParser, ValgrindErrorParser],
-    'tsan': [CompilerErrorParser, GTestErrorParser, TsanErrorParser],
-    'format_compatible': [CompilerErrorParser, CompatErrorParser],
-    'run_format_compatible': [CompilerErrorParser, CompatErrorParser],
-    'no_compression': [CompilerErrorParser, GTestErrorParser],
-    'run_no_compression': [CompilerErrorParser, GTestErrorParser],
-    'regression': [CompilerErrorParser],
-    'run_regression': [CompilerErrorParser],
-}
-
-
-def main():
-    if len(sys.argv) != 2:
-        return 'Usage: %s <test name>' % sys.argv[0]
-    test_name = sys.argv[1]
-    if test_name not in _TEST_NAME_TO_PARSERS:
-        return 'Unknown test name: %s' % test_name
-
-    error_parsers = []
-    for parser_cls in _TEST_NAME_TO_PARSERS[test_name]:
-        error_parsers.append(parser_cls())
-
-    for line in sys.stdin:
-        line = line.strip()
-        for error_parser in error_parsers:
-            error_msg = error_parser.parse_error(line)
-            if error_msg is not None:
-                print(error_msg)
-
-
-if __name__ == '__main__':
-    sys.exit(main())

build_tools/fbcode_config4.8.1.sh

@@ -9,7 +9,7 @@ source "$BASEDIR/dependencies_4.8.1.sh"
 
 # location of libgcc
 LIBGCC_INCLUDE="$LIBGCC_BASE/include"
-LIBGCC_LIBS=" -L $LIBGCC_BASE/lib"
+LIBGCC_LIBS=" -L $LIBGCC_BASE/libs"
 
 # location of glibc
 GLIBC_INCLUDE="$GLIBC_BASE/include"
@@ -48,17 +48,13 @@ NUMA_LIB=" $NUMA_BASE/lib/libnuma.a"
 # location of libunwind
 LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
 
-# location of tbb
-TBB_INCLUDE=" -isystem $TBB_BASE/include/"
-TBB_LIBS="$TBB_BASE/lib/libtbb.a"
-
 # use Intel SSE support for checksum calculations
 export USE_SSE=1
 
 BINUTILS="$BINUTILS_BASE/bin"
 AR="$BINUTILS/ar"
 
-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP2_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE $TBB_INCLUDE"
+DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP2_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE"
 
 STDLIBS="-L $GCC_BASE/lib64"
 
@@ -70,7 +66,6 @@ if [ -z "$USE_CLANG" ]; then
   CFLAGS="-B$BINUTILS/gold -m64 -mtune=generic"
   CFLAGS+=" -isystem $GLIBC_INCLUDE"
   CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  JEMALLOC=1
 else
   # clang
   CLANG_BIN="$CLANG_BASE/bin"
@@ -94,15 +89,13 @@ fi
 
 CFLAGS+=" $DEPS_INCLUDE"
 CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE"
-CFLAGS+=" -DSNAPPY -DGFLAGS=google -DZLIB -DBZIP2 -DLZ4 -DZSTD -DNUMA -DTBB"
+CFLAGS+=" -DSNAPPY -DGFLAGS=google -DZLIB -DBZIP2 -DLZ4 -DZSTD -DNUMA"
 CXXFLAGS+=" $CFLAGS"
 
-EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP2_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB $TBB_LIBS"
+EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP2_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB"
 EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/gcc-4.8.1-glibc-2.17/lib/ld.so"
 EXEC_LDFLAGS+=" $LIBUNWIND"
 EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/gcc-4.8.1-glibc-2.17/lib"
-# required by libtbb
-EXEC_LDFLAGS+=" -ldl"
 
 PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
 
@@ -110,6 +103,4 @@ EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP2_LIBS $LZ4_LIBS $ZSTD_LIBS $G
 
 VALGRIND_VER="$VALGRIND_BASE/bin/"
 
-LUA_PATH="$LUA_BASE"
-
-export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE LUA_PATH
+export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE

build_tools/format-diff.sh

@@ -11,8 +11,7 @@ if ! which $CLANG_FORMAT_DIFF &> /dev/null
 then
   echo "You didn't have clang-format-diff.py available in your computer!"
   echo "You can download it by running: "
-  echo "    curl --location http://goo.gl/iUW1u2 -o ${CLANG_FORMAT_DIFF}"
-  echo "and move ${CLANG_FORMAT_DIFF} to some directory within PATH=${PATH}"
+  echo "    curl http://goo.gl/iUW1u2"
   exit 128
 fi
 
@@ -51,15 +50,14 @@ 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 check the modified lines since last commit
-# from master. Otherwise, we'll check format of the uncommitted code only.
+# format check, in which case we'll check the modified lines from latest commit.
+# Otherwise, we'll check format of the uncommitted code only.
 if [ -z "$uncommitted_code" ]
 then
   # Check the format of last commit
-  diffs=$(git diff -U0 $LAST_MASTER^ | $CLANG_FORMAT_DIFF -p 1)
+  diffs=$(git diff -U0 HEAD^ | $CLANG_FORMAT_DIFF -p 1)
 else
   # Check the format of uncommitted lines,
   diffs=$(git diff -U0 HEAD | $CLANG_FORMAT_DIFF -p 1)
@@ -99,12 +97,7 @@ then
 fi
 
 # Do in-place format adjustment.
-if [ -z "$uncommitted_code" ]
-then
-  git diff -U0 $LAST_MASTER^ | $CLANG_FORMAT_DIFF -i -p 1
-else
-  git diff -U0 HEAD^ | $CLANG_FORMAT_DIFF -i -p 1
-fi
+git diff -U0 HEAD^ | $CLANG_FORMAT_DIFF -i -p 1
 echo "Files reformatted!"
 
 # Amend to last commit if user do the post-commit format check

build_tools/make_new_version.sh

@@ -0,0 +1,46 @@
+#!/bin/bash
+#  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+#  This source code is licensed under the BSD-style license found in the
+#  LICENSE file in the root directory of this source tree. An additional grant
+#  of patent rights can be found in the PATENTS file in the same directory.
+
+set -e
+if [ -z "$GIT" ]
+then
+  GIT="git"
+fi
+
+# Print out the colored progress info so that it can be brainlessly 
+# distinguished by users.
+function title() {
+  echo -e "\033[1;32m$*\033[0m"
+}
+
+usage="Create new RocksDB version and prepare it for the release process\n"
+usage+="USAGE: ./make_new_version.sh <version>"
+
+# -- Pre-check
+if [[ $# < 1 ]]; then
+  echo -e $usage
+  exit 1
+fi
+
+ROCKSDB_VERSION=$1
+
+GIT_BRANCH=`git rev-parse --abbrev-ref HEAD`
+echo $GIT_BRANCH
+
+if [ $GIT_BRANCH != "master" ]; then
+  echo "Error: Current branch is '$GIT_BRANCH', Please switch to master branch."
+  exit 1
+fi
+
+title "Adding new tag for this release ..."
+BRANCH="$ROCKSDB_VERSION.fb"
+$GIT checkout -b $BRANCH
+
+# Setting up the proxy for remote repo access
+title "Pushing new branch to remote repo ..."
+git push origin --set-upstream $BRANCH
+
+title "Branch $BRANCH is pushed to github;"

build_tools/make_package.sh

@@ -65,8 +65,8 @@ function main() {
 
   if [[ -d /vagrant ]]; then
     if [[ $OS = "ubuntu" ]]; then
-      package g++-4.8
-      export CXX=g++-4.8
+      package g++-4.7
+      export CXX=g++-4.7
 
       # the deb would depend on libgflags2, but the static lib is the only thing
       # installed by make install

build_tools/precommit_checker.py

@@ -1,208 +0,0 @@
-#!/usr/local/fbcode/gcc-4.9-glibc-2.20-fb/bin/python2.7
-
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-from __future__ import unicode_literals
-import argparse
-import commands
-import subprocess
-import sys
-import re
-import os
-import time
-
-
-#
-# Simple logger
-#
-
-class Log:
-
-    def __init__(self, filename):
-        self.filename = filename
-        self.f = open(self.filename, 'w+', 0)
-
-    def caption(self, str):
-        line = "\n##### %s #####\n" % str
-        if self.f:
-            self.f.write("%s \n" % line)
-        else:
-            print(line)
-
-    def error(self, str):
-        data = "\n\n##### ERROR ##### %s" % str
-        if self.f:
-            self.f.write("%s \n" % data)
-        else:
-            print(data)
-
-    def log(self, str):
-        if self.f:
-            self.f.write("%s \n" % str)
-        else:
-            print(str)
-
-#
-# Shell Environment
-#
-
-
-class Env(object):
-
-    def __init__(self, logfile, tests):
-        self.tests = tests
-        self.log = Log(logfile)
-
-    def shell(self, cmd, path=os.getcwd()):
-        if path:
-            os.chdir(path)
-
-        self.log.log("==== shell session ===========================")
-        self.log.log("%s> %s" % (path, cmd))
-        status = subprocess.call("cd %s; %s" % (path, cmd), shell=True,
-                                 stdout=self.log.f, stderr=self.log.f)
-        self.log.log("status = %s" % status)
-        self.log.log("============================================== \n\n")
-        return status
-
-    def GetOutput(self, cmd, path=os.getcwd()):
-        if path:
-            os.chdir(path)
-
-        self.log.log("==== shell session ===========================")
-        self.log.log("%s> %s" % (path, cmd))
-        status, out = commands.getstatusoutput(cmd)
-        self.log.log("status = %s" % status)
-        self.log.log("out = %s" % out)
-        self.log.log("============================================== \n\n")
-        return status, out
-
-#
-# Pre-commit checker
-#
-
-
-class PreCommitChecker(Env):
-
-    def __init__(self, args):
-        Env.__init__(self, args.logfile, args.tests)
-        self.ignore_failure = args.ignore_failure
-
-    #
-    #   Get commands for a given job from the determinator file
-    #
-    def get_commands(self, test):
-        status, out = self.GetOutput(
-            "RATIO=1 build_tools/rocksdb-lego-determinator %s" % test, ".")
-        return status, out
-
-    #
-    # Run a specific CI job
-    #
-    def run_test(self, test):
-        self.log.caption("Running test %s locally" % test)
-
-        # get commands for the CI job determinator
-        status, cmds = self.get_commands(test)
-        if status != 0:
-            self.log.error("Error getting commands for test %s" % test)
-            return False
-
-        # Parse the JSON to extract the commands to run
-        cmds = re.findall("'shell':'([^\']*)'", cmds)
-
-        if len(cmds) == 0:
-            self.log.log("No commands found")
-            return False
-
-        # Run commands
-        for cmd in cmds:
-            # Replace J=<..> with the local environment variable
-            if "J" in os.environ:
-                cmd = cmd.replace("J=1", "J=%s" % os.environ["J"])
-                cmd = cmd.replace("make ", "make -j%s " % os.environ["J"])
-            # Run the command
-            status = self.shell(cmd, ".")
-            if status != 0:
-                self.log.error("Error running command %s for test %s"
-                               % (cmd, test))
-                return False
-
-        return True
-
-    #
-    # Run specified CI jobs
-    #
-    def run_tests(self):
-        if not self.tests:
-            self.log.error("Invalid args. Please provide tests")
-            return False
-
-        self.print_separator()
-        self.print_row("TEST", "RESULT")
-        self.print_separator()
-
-        result = True
-        for test in self.tests:
-            start_time = time.time()
-            self.print_test(test)
-            result = self.run_test(test)
-            elapsed_min = (time.time() - start_time) / 60
-            if not result:
-                self.log.error("Error running test %s" % test)
-                self.print_result("FAIL (%dm)" % elapsed_min)
-                if not self.ignore_failure:
-                    return False
-                result = False
-            else:
-                self.print_result("PASS (%dm)" % elapsed_min)
-
-        self.print_separator()
-        return result
-
-    #
-    # Print a line
-    #
-    def print_separator(self):
-        print("".ljust(60, "-"))
-
-    #
-    # Print two colums
-    #
-    def print_row(self, c0, c1):
-        print("%s%s" % (c0.ljust(40), c1.ljust(20)))
-
-    def print_test(self, test):
-        print(test.ljust(40), end="")
-        sys.stdout.flush()
-
-    def print_result(self, result):
-        print(result.ljust(20))
-
-#
-# Main
-#
-parser = argparse.ArgumentParser(description='RocksDB pre-commit checker.')
-
-# --log <logfile>
-parser.add_argument('--logfile', default='/tmp/precommit-check.log',
-                    help='Log file. Default is /tmp/precommit-check.log')
-# --ignore_failure
-parser.add_argument('--ignore_failure', action='store_true', default=False,
-                    help='Stop when an error occurs')
-# <test ....>
-parser.add_argument('tests', nargs='+',
-                    help='CI test(s) to run. e.g: unit punit asan tsan ubsan')
-
-args = parser.parse_args()
-checker = PreCommitChecker(args)
-
-print("Please follow log %s" % checker.log.filename)
-
-if not checker.run_tests():
-    print("Error running tests. Please check log file %s"
-          % checker.log.filename)
-    sys.exit(1)
-
-sys.exit(0)

build_tools/regression_build_test.sh

@@ -55,6 +55,7 @@ make release
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0  > ${STAT_FILE}.fillseq
 
@@ -72,6 +73,7 @@ make release
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=8 > ${STAT_FILE}.overwrite
@@ -90,6 +92,7 @@ make release
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=1 > /dev/null
@@ -108,6 +111,7 @@ make release
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=16 > ${STAT_FILE}.readrandom
@@ -127,6 +131,7 @@ make release
     --use_tailing_iterator=1 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=16 > ${STAT_FILE}.readrandomtailing
@@ -145,6 +150,7 @@ make release
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=16 > ${STAT_FILE}.readrandomsmallblockcache
@@ -165,6 +171,7 @@ make release
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=16 > ${STAT_FILE}.readrandom_mem_sst
@@ -184,6 +191,7 @@ make release
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=1 > /dev/null
@@ -202,6 +210,7 @@ make release
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=16 > /dev/null
@@ -221,6 +230,7 @@ make release
     --disable_auto_compactions=1 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=16 > ${STAT_FILE}.readrandom_filluniquerandom
@@ -241,6 +251,7 @@ make release
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=16 > ${STAT_FILE}.readwhilewriting
@@ -259,6 +270,7 @@ make release
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --value_size=10 \
@@ -283,6 +295,7 @@ common_in_mem_args="--db=/dev/shm/rocksdb \
     --disable_wal=0 \
     --wal_dir=/dev/shm/rocksdb \
     --sync=0 \
+    --disable_data_sync=1 \
     --verify_checksum=1 \
     --delete_obsolete_files_period_micros=314572800 \
     --max_grandparent_overlap_factor=10 \
@@ -343,6 +356,7 @@ common_in_mem_args="--db=/dev/shm/rocksdb \
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0  > ${STAT_FILE}.fillseq_lots_column_families
 
@@ -358,6 +372,7 @@ common_in_mem_args="--db=/dev/shm/rocksdb \
     --open_files=55000 \
     --statistics=1 \
     --histogram=1 \
+    --disable_data_sync=1 \
     --disable_wal=1 \
     --sync=0 \
     --threads=8 > ${STAT_FILE}.overwrite_lots_column_families

build_tools/rocksdb-lego-determinator

@@ -8,7 +8,7 @@
 # Input         Value
 # -------------------------------------------------------------------------
 # EMAIL         Email address to report on trigger conditions
-# ONCALL        Email address to raise a task on failure
+# ONCAL         Email address to raise a task on failure
 # TRIGGER       Trigger conditions for email. Valid values are fail, warn, all
 # SUBSCRIBER    Email addresss to add as subscriber for task
 #
@@ -42,9 +42,6 @@ if [ ! -z $ONCALL ]; then
   },"
 fi
 
-# For now, create the tasks using only the dedicated task creation tool.
-CREATE_TASK=
-
 REPORT=
 if [[ ! -z $REPORT_EMAIL || ! -z $CREATE_TASK ]]; then
   REPORT="'report': [
@@ -59,51 +56,19 @@ fi
 CLEANUP_ENV="
 {
     'name':'Cleanup environment',
-    'shell':'rm -rf /dev/shm/rocksdb && mkdir /dev/shm/rocksdb && (chmod +t /dev/shm || true)  && make clean',
+    'shell':'rm -rf /dev/shm/rocksdb && mkdir /dev/shm/rocksdb && make clean',
     'user':'root'
 }"
 
-# We will eventually set the RATIO to 1, but we want do this
-# in steps. RATIO=$(nproc) will make it work as J=1
-if [ -z $RATIO ]; then
-  RATIO=$(nproc)
-fi
-
-if [ -z $PARALLEL_J ]; then
-  PARALLEL_J="J=$(expr $(nproc) / ${RATIO})"
-fi
-
-if [ -z $PARALLEL_j ]; then
-  PARALLEL_j="-j$(expr $(nproc) / ${RATIO})"
-fi
-
-PARALLELISM="$PARALLEL_J $PARALLEL_j"
-
 DEBUG="OPT=-g"
 SHM="TEST_TMPDIR=/dev/shm/rocksdb"
 GCC_481="ROCKSDB_FBCODE_BUILD_WITH_481=1"
 ASAN="COMPILE_WITH_ASAN=1"
 CLANG="USE_CLANG=1"
-LITE="OPT=\"-DROCKSDB_LITE -g\""
+LITE="OPT=-DROCKSDB_LITE"
 TSAN="COMPILE_WITH_TSAN=1"
-UBSAN="COMPILE_WITH_UBSAN=1"
 DISABLE_JEMALLOC="DISABLE_JEMALLOC=1"
-HTTP_PROXY="https_proxy=http://fwdproxy.29.prn1:8080 http_proxy=http://fwdproxy.29.prn1:8080 ftp_proxy=http://fwdproxy.29.prn1:8080"
-SETUP_JAVA_ENV="export $HTTP_PROXY; export JAVA_HOME=/usr/local/jdk-8u60-64/; export PATH=\$JAVA_HOME/bin:\$PATH"
-PARSER="'parser':'python build_tools/error_filter.py $1'"
-
-CONTRUN_NAME="ROCKSDB_CONTRUN_NAME"
-
-# This code is getting called under various scenarios. What we care about is to
-# understand when it's called from nightly contruns because in that case we'll
-# create tasks for any failures. To follow the existing pattern, we'll check
-# the value of $ONCALL. If it's a diff then just call `false` to make sure
-# that errors will be properly propagated to the caller.
-if [ ! -z $ONCALL ]; then
-  TASK_CREATION_TOOL="/usr/local/bin/mysql_mtr_filter --rocksdb --oncall $ONCALL"
-else
-  TASK_CREATION_TOOL="false"
-fi
+PARSER="'parser':'egrep \'Failure|^#|Abort|Expected|Actual|GoogleTestFailure|^==\''"
 
 ARTIFACTS=" 'artifacts': [
     {
@@ -142,14 +107,14 @@ PARALLEL_UNIT_TEST_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build and test RocksDB debug version',
-                'shell':'$DEBUG make -j$(nproc) all && $SHM make check > /dev/null 2>&1 || $CONTRUN_NAME=punit_check $TASK_CREATION_TOOL || cat t/log-*',
+                'shell':'$DEBUG make -j$(nproc) all && $SHM make check > /dev/null 2>&1 || cat t/log-*',
                 'user':'root',
                 $PARSER
             },
             $CLEANUP_ENV,
             {
                 'name':'Build and test RocksDB debug version under gcc-4.8.1',
-                'shell':'$GCC_481 $DEBUG make -j$(nproc) all && $SHM make check > /dev/null 2>&1 || $CONTRUN_NAME=punit_check_gcc481 $TASK_CREATION_TOOL || cat t/log-*',
+                'shell':'$GCC_481 $DEBUG make -j$(nproc) all && $SHM make check > /dev/null 2>&1 || cat t/log-*',
                 'user':'root',
                 $PARSER
             },
@@ -169,49 +134,7 @@ UNIT_TEST_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build and test RocksDB debug version',
-                'shell':'$SHM $DEBUG make $PARALLELISM check || $CONTRUN_NAME=check $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB unit test not under /dev/shm
-#
-UNIT_TEST_NON_SHM_COMMANDS="[
-    {
-        'name':'Rocksdb Unit Test',
-        'oncall':'$ONCALL',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and test RocksDB debug version',
-                'timeout': 86400,
-                'shell':'$DEBUG make $PARALLELISM check || $CONTRUN_NAME=non_shm_check $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB release build and unit tests
-#
-RELEASE_BUILD_COMMANDS="[
-    {
-        'name':'Rocksdb Release Build',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build RocksDB release',
-                'shell':'make $PARALLEL_j release || $CONTRUN_NAME=release $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 check',
                 'user':'root',
                 $PARSER
             },
@@ -231,27 +154,7 @@ UNIT_TEST_COMMANDS_481="[
             $CLEANUP_ENV,
             {
                 'name':'Build and test RocksDB debug version',
-                'shell':'$SHM $GCC_481 $DEBUG make $PARALLELISM check || $CONTRUN_NAME=unit_gcc_481_check $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB release build and unit tests
-#
-RELEASE_BUILD_COMMANDS_481="[
-    {
-        'name':'Rocksdb Release on GCC 4.8.1',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build RocksDB release on GCC 4.8.1',
-                'shell':'$GCC_481 make $PARALLEL_j release || $CONTRUN_NAME=release_gcc481 $TASK_CREATION_TOOL',
+                'shell':'$SHM $GCC_481 $DEBUG make J=1 check',
                 'user':'root',
                 $PARSER
             },
@@ -271,27 +174,7 @@ CLANG_UNIT_TEST_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build and test RocksDB debug',
-                'shell':'$CLANG $SHM $DEBUG make $PARALLELISM check || $CONTRUN_NAME=clang_check $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB release build with CLANG
-#
-CLANG_RELEASE_BUILD_COMMANDS="[
-    {
-        'name':'Rocksdb CLANG Release Build',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build RocksDB release',
-                'shell':'$CLANG make $PARALLEL_j release|| $CONTRUN_NAME=clang_release $TASK_CREATION_TOOL',
+                'shell':'$CLANG $SHM $DEBUG make J=1 check',
                 'user':'root',
                 $PARSER
             },
@@ -311,7 +194,7 @@ CLANG_ANALYZE_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'RocksDB build and analyze',
-                'shell':'$CLANG $SHM $DEBUG make $PARALLEL_j analyze || $CONTRUN_NAME=clang_analyze $TASK_CREATION_TOOL',
+                'shell':'$CLANG $SHM $DEBUG make J=1 analyze',
                 'user':'root',
                 $PARSER
             },
@@ -331,7 +214,7 @@ CODE_COV_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build, test and collect code coverage info',
-                'shell':'$SHM $DEBUG make $PARALLELISM coverage || $CONTRUN_NAME=coverage $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 coverage',
                 'user':'root',
                 $PARSER
             },
@@ -351,7 +234,7 @@ UNITY_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build, test unity test',
-                'shell':'$SHM $DEBUG V=1 make J=1 unity_test || $CONTRUN_NAME=unity_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG V=1 make J=1 unity_test',
                 'user':'root',
                 $PARSER
             },
@@ -371,7 +254,7 @@ LITE_BUILD_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build RocksDB debug version',
-                'shell':'$LITE make J=1 static_lib || $CONTRUN_NAME=lite_static_lib $TASK_CREATION_TOOL',
+                'shell':'$LITE $DEBUG make J=1 static_lib',
                 'user':'root',
                 $PARSER
             },
@@ -391,7 +274,7 @@ LITE_UNIT_TEST_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build RocksDB debug version',
-                'shell':'$SHM $LITE make J=1 check || $CONTRUN_NAME=lite_check $TASK_CREATION_TOOL',
+                'shell':'$SHM $LITE $DEBUG make J=1 check',
                 'user':'root',
                 $PARSER
             },
@@ -412,14 +295,14 @@ STRESS_CRASH_TEST_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG make J=1 db_stress || $CONTRUN_NAME=db_stress $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 db_stress',
                 'user':'root',
                 $PARSER
             },
             {
                 'name':'Build and run RocksDB debug crash tests',
                 'timeout': 86400,
-                'shell':'$SHM $DEBUG make J=1 crash_test || $CONTRUN_NAME=crash_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 crash_test',
                 'user':'root',
                 $PARSER
             }
@@ -440,7 +323,7 @@ WRITE_STRESS_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Build and run RocksDB write stress tests',
-                'shell':'make write_stress && python tools/write_stress_runner.py --runtime_sec=3600 --db=/tmp/rocksdb_write_stress || $CONTRUN_NAME=write_stress $TASK_CREATION_TOOL',
+                'shell':'make write_stress && python tools/write_stress_runner.py --runtime_sec=3600 --db=/tmp/rocksdb_write_stress',
                 'user':'root',
                 $PARSER
             }
@@ -462,7 +345,7 @@ ASAN_TEST_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Test RocksDB debug under ASAN',
-'shell':'set -o pipefail && ($SHM $ASAN $DEBUG make $PARALLELISM asan_check || $CONTRUN_NAME=asan_check $TASK_CREATION_TOOL) |& /usr/facebook/ops/scripts/asan_symbolize.py -d',
+                'shell':'set -o pipefail && $SHM $ASAN $DEBUG make J=1 asan_check |& /usr/facebook/ops/scripts/asan_symbolize.py -d',
                 'user':'root',
                 $PARSER
             }
@@ -484,49 +367,7 @@ ASAN_CRASH_TEST_COMMANDS="[
             {
                 'name':'Build and run RocksDB debug asan_crash_test',
                 'timeout': 86400,
-                'shell':'$SHM $DEBUG make J=1 asan_crash_test || $CONTRUN_NAME=asan_crash_test $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB test under undefined behavior sanitizer
-#
-UBSAN_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Unit Test under UBSAN',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Test RocksDB debug under UBSAN',
-                'shell':'set -o pipefail && $SHM $UBSAN $DEBUG make $PARALLELISM ubsan_check || $CONTRUN_NAME=ubsan_check $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            }
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash testing under udnefined behavior sanitizer
-#
-UBSAN_CRASH_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb crash test under UBSAN',
-        'oncall':'$ONCALL',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug ubsan_crash_test',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG make J=1 ubsan_crash_test || $CONTRUN_NAME=ubsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'$SHM $DEBUG make J=1 asan_crash_test',
                 'user':'root',
                 $PARSER
             },
@@ -542,13 +383,11 @@ VALGRIND_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under valgrind',
         'oncall':'$ONCALL',
-        'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Run RocksDB debug unit tests',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG make $PARALLELISM valgrind_test || $CONTRUN_NAME=valgrind_check $TASK_CREATION_TOOL',
+                'shell':'$DISABLE_JEMALLOC $SHM $DEBUG make valgrind_check',
                 'user':'root',
                 $PARSER
             },
@@ -564,13 +403,11 @@ TSAN_UNIT_TEST_COMMANDS="[
     {
         'name':'Rocksdb Unit Test under TSAN',
         'oncall':'$ONCALL',
-        'timeout': 86400,
         'steps': [
             $CLEANUP_ENV,
             {
                 'name':'Run RocksDB debug unit test',
-                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN make $PARALLELISM check || $CONTRUN_NAME=tsan_check $TASK_CREATION_TOOL',
+                'shell':'set -o pipefail && $SHM $DEBUG $TSAN make J=1 check',
                 'user':'root',
                 $PARSER
             },
@@ -592,7 +429,7 @@ TSAN_CRASH_TEST_COMMANDS="[
             {
                 'name':'Compile and run',
                 'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN CRASH_TEST_KILL_ODD=1887 make J=1 crash_test || $CONTRUN_NAME=tsan_crash_test $TASK_CREATION_TOOL',
+                'shell':'set -o pipefail && $SHM $DEBUG $TSAN make J=1 crash_test',
                 'user':'root',
                 $PARSER
             },
@@ -601,6 +438,8 @@ TSAN_CRASH_TEST_COMMANDS="[
     }
 ]"
 
+TSAN_CRASH_TEST_COMMANDS=$DISABLE_COMMANDS
+
 #
 # RocksDB format compatible
 #
@@ -623,9 +462,9 @@ run_format_compatible()
   if [ -e "build_detect_platform" ]
   then
     sed "s/tcmalloc/nothingnothingnothing/g" build_detect_platform > $TEST_TMPDIR/temp_build_file
-    rm -rf build_detect_platform
+    rm -rf build_detect_platform 
     cp $TEST_TMPDIR/temp_build_file build_detect_platform
-    chmod +x build_detect_platform
+    chmod +x build_detect_platform 
   fi
 
   make ldb -j32
@@ -654,7 +493,7 @@ FORMAT_COMPATIBLE_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Run RocksDB debug unit test',
-                'shell':'build_tools/rocksdb-lego-determinator run_format_compatible || $CONTRUN_NAME=run_format_compatible $TASK_CREATION_TOOL',
+                'shell':'build_tools/rocksdb-lego-determinator run_format_compatible',
                 'user':'root',
                 $PARSER
             },
@@ -687,7 +526,7 @@ NO_COMPRESSION_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Run RocksDB debug unit test',
-                'shell':'build_tools/rocksdb-lego-determinator run_no_compression || $CONTRUN_NAME=run_no_compression $TASK_CREATION_TOOL',
+                'shell':'build_tools/rocksdb-lego-determinator run_no_compression',
                 'user':'root',
                 $PARSER
             },
@@ -744,7 +583,7 @@ REGRESSION_COMMANDS="[
             $CLEANUP_ENV,
             {
                 'name':'Make and run script',
-                'shell':'build_tools/rocksdb-lego-determinator run_regression || $CONTRUN_NAME=run_regression $TASK_CREATION_TOOL',
+                'shell':'build_tools/rocksdb-lego-determinator run_regression',
                 'user':'root',
                 $PARSER
             },
@@ -753,27 +592,6 @@ REGRESSION_COMMANDS="[
     }
 ]"
 
-#
-# RocksDB Java build
-#
-JAVA_BUILD_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Java Build',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build RocksDB for Java',
-                'shell':'$SETUP_JAVA_ENV; $SHM make rocksdbjava || $CONTRUN_NAME=rocksdbjava $TASK_CREATION_TOOL',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-
 case $1 in
   punit)
     echo $PARALLEL_UNIT_TEST_COMMANDS
@@ -781,24 +599,12 @@ case $1 in
   unit)
     echo $UNIT_TEST_COMMANDS
     ;;
-  unit_non_shm)
-    echo $UNIT_TEST_NON_SHM_COMMANDS
-    ;;
-  release)
-    echo $RELEASE_BUILD_COMMANDS
-    ;;
   unit_481)
     echo $UNIT_TEST_COMMANDS_481
     ;;
-  release_481)
-    echo $RELEASE_BUILD_COMMANDS_481
-    ;;
   clang_unit)
     echo $CLANG_UNIT_TEST_COMMANDS
     ;;
-  clang_release)
-    echo $CLANG_RELEASE_BUILD_COMMANDS
-    ;;
   clang_analyze)
     echo $CLANG_ANALYZE_COMMANDS
     ;;
@@ -826,12 +632,6 @@ case $1 in
   asan_crash)
     echo $ASAN_CRASH_TEST_COMMANDS
     ;;
-  ubsan)
-    echo $UBSAN_TEST_COMMANDS
-    ;;
-  ubsan_crash)
-    echo $UBSAN_CRASH_TEST_COMMANDS
-    ;;
   valgrind)
     echo $VALGRIND_TEST_COMMANDS
     ;;
@@ -859,9 +659,6 @@ case $1 in
   run_regression)
     run_regression
     ;;
-  java_build)
-    echo $JAVA_BUILD_TEST_COMMANDS
-    ;;
   *)
     echo "Invalid determinator command"
     ;;

build_tools/run_ci_db_test.ps1

@@ -9,7 +9,7 @@ Param(
   [string]$WorkFolder = "",  # Direct tests to use that folder
   [int]$Limit = -1, # -1 means run all otherwise limit for testing purposes
   [string]$Exclude = "", # Expect a comma separated list, no spaces
-  [string]$Run = "db_test",  # Run db_test|db_test2|tests|testname1,testname2...
+  [string]$Run = "db_test",  # Run db_test|tests|testname1,testname2...
    # Number of async tasks that would run concurrently. Recommend a number below 64.
    # However, CPU utlization really depends on the storage media. Recommend ram based disk.
    # a value of 1 will run everything serially
@@ -46,26 +46,15 @@ if($WorkFolder -eq "") {
   $Env:TEST_TMPDIR = $WorkFolder
 }
 
-Write-Output "Root: $RootFolder, WorkFolder: $WorkFolder"
-
 # Use JEMALLOC executables
-if($Run -ceq "db_test" -or
-   $Run -ceq "db_test2" -or
-   $Run -ceq "db_basic_test") {
-
-   $file_name = $Run
-
-   if($EnableJE) {
-     $file_name += "_je"
-   }
-
-   $file_name += ".exe"
-
-   $db_test = -Join ($BinariesFolder, $file_name)
-
-   Write-Output "Binaries: $BinariesFolder db_test: $db_test"
+if($EnableJE) {
+    $db_test = -Join ($BinariesFolder, "db_test_je.exe")
+} else {
+    $db_test = -Join ($BinariesFolder, "db_test.exe")
 }
 
+Write-Output "Root: $RootFolder, WorkFolder: $WorkFolder"
+Write-Output "Binaries: $BinariesFolder db_test: $db_test"
 
 #Exclusions that we do not want to run
 $ExcludeTests = New-Object System.Collections.Generic.HashSet[string]
@@ -151,7 +140,7 @@ function MakeAndAdd([string]$token, $HashTable) {
 # Test executable name -> Log file
 function Discover-TestBinaries([string]$Pattern, $HashTable) {
 
-    $Exclusions = @("db_test*", "db_sanity_test*", "db_basic_test*")
+    $Exclusions = @("db_test*", "db_sanity_test*")
 
     $p = -join ($BinariesFolder, $pattern)
 
@@ -164,9 +153,7 @@ function Discover-TestBinaries([string]$Pattern, $HashTable) {
 
 $TestsToRun = [ordered]@{}
 
-if($Run -ceq "db_test" -or
-   $Run -ceq "db_test2" -or
-   $Run -ceq "db_basic_test") {
+if($Run -ceq "db_test") {
     Normalize-DbTests -HashTable $TestsToRun
 } elseif($Run -ceq "tests") {
     if($EnableJE) {
@@ -238,9 +225,7 @@ function RunJobs($TestToLog, [int]$ConcurrencyVal, [bool]$AddForRerun)
             Write-Host "Starting $k"
             $log_path = ($TestToLog.$k)
 
-            if($Run -ceq "db_test" -or
-               $Run -ceq "db_test2" -or
-               $Run -ceq "db_basic_test") {
+            if($Run -ceq "db_test") {
               $job = Start-Job -Name $k -ScriptBlock $InvokeTestCase -ArgumentList @($db_test,$k,$log_path)
             } else {
               [string]$Exe =  -Join ($BinariesFolder, $k)

build_tools/update_dependencies.sh

@@ -72,8 +72,8 @@ log_variable CLANG_BASE
 
 # Libraries locations
 get_lib_base libgcc     4.9.x
-get_lib_base glibc      2.20
-get_lib_base snappy     LATEST gcc-4.9-glibc-2.20
+get_lib_base glibc      2.20 
+get_lib_base snappy     LATEST
 get_lib_base zlib       LATEST
 get_lib_base bzip2      LATEST
 get_lib_base lz4        LATEST
@@ -82,12 +82,10 @@ get_lib_base gflags     LATEST
 get_lib_base jemalloc   LATEST
 get_lib_base numa       LATEST
 get_lib_base libunwind  LATEST
-get_lib_base tbb        4.0_update2 gcc-4.9-glibc-2.20
 
 get_lib_base kernel-headers LATEST 
 get_lib_base binutils   LATEST centos6-native 
-get_lib_base valgrind   3.10.0 gcc-4.9-glibc-2.20
-get_lib_base lua        5.2.3 gcc-4.9-glibc-2.20
+get_lib_base valgrind   LATEST
 
 git diff $OUTPUT
 
@@ -121,11 +119,9 @@ get_lib_base gflags     LATEST gcc-4.8.1-glibc-2.17
 get_lib_base jemalloc   LATEST gcc-4.8.1-glibc-2.17
 get_lib_base numa       LATEST gcc-4.8.1-glibc-2.17
 get_lib_base libunwind  LATEST gcc-4.8.1-glibc-2.17
-get_lib_base tbb        4.0_update2 gcc-4.8.1-glibc-2.17
 
 get_lib_base kernel-headers LATEST gcc-4.8.1-glibc-2.17 
 get_lib_base binutils   LATEST centos6-native 
 get_lib_base valgrind   3.8.1  gcc-4.8.1-glibc-2.17
-get_lib_base lua        5.2.3 centos6-native
 
 git diff $OUTPUT

build_tools/version.sh

@@ -1,9 +1,8 @@
 #!/bin/sh
 if [ "$#" = "0" ]; then
-  echo "Usage: $0 major|minor|patch|full"
+  echo "Usage: $0 major|minor|patch"
   exit 1
 fi
-
 if [ "$1" = "major" ]; then
   cat include/rocksdb/version.h  | grep MAJOR | head -n1 | awk '{print $3}'
 fi
@@ -13,10 +12,3 @@ fi
 if [ "$1" = "patch" ]; then
   cat include/rocksdb/version.h  | grep PATCH | head -n1 | awk '{print $3}'
 fi
-if [ "$1" = "full" ]; then
-  awk '/#define ROCKSDB/ { env[$2] = $3 }
-       END { printf "%s.%s.%s\n", env["ROCKSDB_MAJOR"],
-                                  env["ROCKSDB_MINOR"],
-                                  env["ROCKSDB_PATCH"] }'  \
-      include/rocksdb/version.h
-fi

cmake/modules/FindJeMalloc.cmake

@@ -1,22 +0,0 @@
-# - Find JeMalloc library
-# Find the native JeMalloc includes and library
-# This module defines
-#  JEMALLOC_INCLUDE_DIRS, where to find jemalloc.h, Set when
-#                        JEMALLOC_INCLUDE_DIR is found.
-#  JEMALLOC_LIBRARIES, libraries to link against to use JeMalloc.
-#  JEMALLOC_FOUND, If false, do not try to use JeMalloc.
-#
-find_path(JEMALLOC_INCLUDE_DIR
-  jemalloc/jemalloc.h)
-
-find_library(JEMALLOC_LIBRARIES
-  jemalloc)
-
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(JeMalloc DEFAULT_MSG
-    JEMALLOC_LIBRARIES JEMALLOC_INCLUDE_DIR)
-
-MARK_AS_ADVANCED(
-  JEMALLOC_INCLUDE_DIR
-  JEMALLOC_LIBRARIES
-)

cmake/modules/Findsnappy.cmake

@@ -1,23 +0,0 @@
-# - Find Snappy
-# Find the snappy compression library and includes
-#
-# SNAPPY_INCLUDE_DIR - where to find snappy.h, etc.
-# SNAPPY_LIBRARIES - List of libraries when using snappy.
-# SNAPPY_FOUND - True if snappy found.
-
-find_path(SNAPPY_INCLUDE_DIR
-  NAMES snappy.h
-  HINTS ${SNAPPY_ROOT_DIR}/include)
-
-find_library(SNAPPY_LIBRARIES
-  NAMES snappy
-  HINTS ${SNAPPY_ROOT_DIR}/lib)
-
-# handle the QUIETLY and REQUIRED arguments and set UUID_FOUND to TRUE if
-# all listed variables are TRUE
-include(FindPackageHandleStandardArgs)
-find_package_handle_standard_args(snappy DEFAULT_MSG SNAPPY_LIBRARIES SNAPPY_INCLUDE_DIR)
-
-mark_as_advanced(
-  SNAPPY_LIBRARIES
-  SNAPPY_INCLUDE_DIR)

db/builder.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -15,7 +15,6 @@
 
 #include "db/compaction_iterator.h"
 #include "db/dbformat.h"
-#include "db/event_helpers.h"
 #include "db/filename.h"
 #include "db/internal_stats.h"
 #include "db/merge_helper.h"
@@ -42,94 +41,65 @@ TableBuilder* NewTableBuilder(
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
-    uint32_t column_family_id, const std::string& column_family_name,
-    WritableFileWriter* file, const CompressionType compression_type,
-    const CompressionOptions& compression_opts,
-    int level,
-    const std::string* compression_dict, const bool skip_filters) {
-  assert((column_family_id ==
-          TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
-         column_family_name.empty());
+    uint32_t column_family_id, WritableFileWriter* file,
+    const CompressionType compression_type,
+    const CompressionOptions& compression_opts, const bool skip_filters) {
   return ioptions.table_factory->NewTableBuilder(
       TableBuilderOptions(ioptions, internal_comparator,
                           int_tbl_prop_collector_factories, compression_type,
-                          compression_opts, compression_dict, skip_filters,
-                          column_family_name, level),
+                          compression_opts, skip_filters),
       column_family_id, file);
 }
 
 Status BuildTable(
     const std::string& dbname, Env* env, const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
-    TableCache* table_cache, InternalIterator* iter,
-    std::unique_ptr<InternalIterator> range_del_iter, FileMetaData* meta,
+    const EnvOptions& env_options, TableCache* table_cache,
+    InternalIterator* iter, FileMetaData* meta,
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
-    uint32_t column_family_id, const std::string& column_family_name,
-    std::vector<SequenceNumber> snapshots,
+    uint32_t column_family_id, std::vector<SequenceNumber> snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     const CompressionType compression,
     const CompressionOptions& compression_opts, bool paranoid_file_checks,
-    InternalStats* internal_stats, TableFileCreationReason reason,
-    EventLogger* event_logger, int job_id, const Env::IOPriority io_priority,
-    TableProperties* table_properties, int level) {
-  assert((column_family_id ==
-          TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
-         column_family_name.empty());
+    InternalStats* internal_stats, const Env::IOPriority io_priority,
+    TableProperties* table_properties) {
   // Reports the IOStats for flush for every following bytes.
   const size_t kReportFlushIOStatsEvery = 1048576;
   Status s;
   meta->fd.file_size = 0;
   iter->SeekToFirst();
-  std::unique_ptr<RangeDelAggregator> range_del_agg(
-      new RangeDelAggregator(internal_comparator, snapshots));
-  s = range_del_agg->AddTombstones(std::move(range_del_iter));
-  if (!s.ok()) {
-    // may be non-ok if a range tombstone key is unparsable
-    return s;
-  }
 
   std::string fname = TableFileName(ioptions.db_paths, meta->fd.GetNumber(),
                                     meta->fd.GetPathId());
-#ifndef ROCKSDB_LITE
-  EventHelpers::NotifyTableFileCreationStarted(
-      ioptions.listeners, dbname, column_family_name, fname, job_id, reason);
-#endif  // !ROCKSDB_LITE
-  TableProperties tp;
-
-  if (iter->Valid() || range_del_agg->ShouldAddTombstones()) {
+  if (iter->Valid()) {
     TableBuilder* builder;
     unique_ptr<WritableFileWriter> file_writer;
     {
       unique_ptr<WritableFile> file;
       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, tp, reason, s);
         return s;
       }
       file->SetIOPriority(io_priority);
 
-      file_writer.reset(new WritableFileWriter(std::move(file), env_options,
-                                               ioptions.statistics));
+      file_writer.reset(new WritableFileWriter(std::move(file), env_options));
 
       builder = NewTableBuilder(
           ioptions, internal_comparator, int_tbl_prop_collector_factories,
-          column_family_id, column_family_name, file_writer.get(), compression,
-          compression_opts, level);
+          column_family_id, file_writer.get(), compression, compression_opts);
     }
 
     MergeHelper merge(env, internal_comparator.user_comparator(),
                       ioptions.merge_operator, nullptr, ioptions.info_log,
+                      ioptions.min_partial_merge_operands,
                       true /* internal key corruption is not ok */,
                       snapshots.empty() ? 0 : snapshots.back());
 
-    CompactionIterator c_iter(
-        iter, internal_comparator.user_comparator(), &merge, kMaxSequenceNumber,
-        &snapshots, earliest_write_conflict_snapshot, env,
-        true /* internal key corruption is not ok */, range_del_agg.get());
+    CompactionIterator c_iter(iter, internal_comparator.user_comparator(),
+                              &merge, kMaxSequenceNumber, &snapshots,
+                              earliest_write_conflict_snapshot, env,
+                              true /* internal key corruption is not ok */);
     c_iter.SeekToFirst();
     for (; c_iter.Valid(); c_iter.Next()) {
       const Slice& key = c_iter.key();
@@ -144,9 +114,6 @@ Status BuildTable(
             ThreadStatus::FLUSH_BYTES_WRITTEN, IOSTATS(bytes_written));
       }
     }
-    // nullptr for table_{min,max} so all range tombstones will be flushed
-    range_del_agg->AddToBuilder(builder, nullptr /* lower_bound */,
-                                nullptr /* upper_bound */, meta);
 
     // Finish and check for builder errors
     bool empty = builder->NumEntries() == 0;
@@ -158,19 +125,17 @@ Status BuildTable(
     }
 
     if (s.ok() && !empty) {
-      uint64_t file_size = builder->FileSize();
-      meta->fd.file_size = file_size;
+      meta->fd.file_size = builder->FileSize();
       meta->marked_for_compaction = builder->NeedCompact();
       assert(meta->fd.GetFileSize() > 0);
-      tp = builder->GetTableProperties();
       if (table_properties) {
-        *table_properties = tp;
+        *table_properties = builder->GetTableProperties();
       }
     }
     delete builder;
 
     // Finish and check for file errors
-    if (s.ok() && !empty) {
+    if (s.ok() && !empty && !ioptions.disable_data_sync) {
       StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
       file_writer->Sync(ioptions.use_fsync);
     }
@@ -181,12 +146,10 @@ Status BuildTable(
     if (s.ok() && !empty) {
       // Verify that the table is usable
       std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
-          ReadOptions(), env_options, internal_comparator, meta->fd,
-          nullptr /* range_del_agg */, nullptr,
+          ReadOptions(), env_options, internal_comparator, meta->fd, nullptr,
           (internal_stats == nullptr) ? nullptr
                                       : internal_stats->GetFileReadHist(0),
-          false /* for_compaction */, nullptr /* arena */,
-          false /* skip_filter */, level));
+          false));
       s = it->status();
       if (s.ok() && paranoid_file_checks) {
         for (it->SeekToFirst(); it->Valid(); it->Next()) {
@@ -204,12 +167,6 @@ Status BuildTable(
   if (!s.ok() || meta->fd.GetFileSize() == 0) {
     env->DeleteFile(fname);
   }
-
-  // Output to event logger and fire events.
-  EventHelpers::LogAndNotifyTableFileCreationFinished(
-      event_logger, ioptions.listeners, dbname, column_family_name, fname,
-      job_id, meta->fd, tp, reason, s);
-
   return s;
 }
 

db/builder.h

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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.
@@ -12,14 +12,11 @@
 #include "db/table_properties_collector.h"
 #include "rocksdb/comparator.h"
 #include "rocksdb/env.h"
-#include "rocksdb/listener.h"
-#include "rocksdb/options.h"
 #include "rocksdb/status.h"
-#include "rocksdb/table_properties.h"
 #include "rocksdb/types.h"
-#include "table/scoped_arena_iterator.h"
-#include "util/cf_options.h"
-#include "util/event_logger.h"
+#include "rocksdb/options.h"
+#include "rocksdb/immutable_options.h"
+#include "rocksdb/table_properties.h"
 
 namespace rocksdb {
 
@@ -36,21 +33,14 @@ class WritableFileWriter;
 class InternalStats;
 class InternalIterator;
 
-// @param column_family_name Name of the column family that is also identified
-//    by column_family_id, or empty string if unknown. It must outlive the
-//    TableBuilder returned by this function.
-// @param compression_dict Data for presetting the compression library's
-//    dictionary, or nullptr.
 TableBuilder* NewTableBuilder(
     const ImmutableCFOptions& options,
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
-    uint32_t column_family_id, const std::string& column_family_name,
-    WritableFileWriter* file, const CompressionType compression_type,
+    uint32_t column_family_id, WritableFileWriter* file,
+    const CompressionType compression_type,
     const CompressionOptions& compression_opts,
-    int level,
-    const std::string* compression_dict = nullptr,
     const bool skip_filters = false);
 
 // Build a Table file from the contents of *iter.  The generated file
@@ -58,25 +48,19 @@ TableBuilder* NewTableBuilder(
 // *meta will be filled with metadata about the generated table.
 // If no data is present in *iter, meta->file_size will be set to
 // zero, and no Table file will be produced.
-//
-// @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, const ImmutableCFOptions& options,
-    const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
-    TableCache* table_cache, InternalIterator* iter,
-    std::unique_ptr<InternalIterator> range_del_iter, FileMetaData* meta,
+    const EnvOptions& env_options, TableCache* table_cache,
+    InternalIterator* iter, FileMetaData* meta,
     const InternalKeyComparator& internal_comparator,
     const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories,
-    uint32_t column_family_id, const std::string& column_family_name,
-    std::vector<SequenceNumber> snapshots,
+    uint32_t column_family_id, std::vector<SequenceNumber> snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     const CompressionType compression,
     const CompressionOptions& compression_opts, bool paranoid_file_checks,
-    InternalStats* internal_stats, TableFileCreationReason reason,
-    EventLogger* event_logger = nullptr, int job_id = 0,
+    InternalStats* internal_stats,
     const Env::IOPriority io_priority = Env::IO_HIGH,
-    TableProperties* table_properties = nullptr, int level = -1);
+    TableProperties* table_properties = nullptr);
 
 }  // namespace rocksdb

db/c.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -30,7 +30,6 @@
 #include "rocksdb/statistics.h"
 #include "rocksdb/slice_transform.h"
 #include "rocksdb/table.h"
-#include "rocksdb/rate_limiter.h"
 #include "rocksdb/utilities/backupable_db.h"
 #include "utilities/merge_operators.h"
 
@@ -44,16 +43,13 @@ using rocksdb::CompactionFilterContext;
 using rocksdb::CompactionOptionsFIFO;
 using rocksdb::Comparator;
 using rocksdb::CompressionType;
-using rocksdb::WALRecoveryMode;
 using rocksdb::DB;
 using rocksdb::DBOptions;
 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;
@@ -71,7 +67,6 @@ using rocksdb::Slice;
 using rocksdb::SliceParts;
 using rocksdb::SliceTransform;
 using rocksdb::Snapshot;
-using rocksdb::SstFileWriter;
 using rocksdb::Status;
 using rocksdb::WritableFile;
 using rocksdb::WriteBatch;
@@ -82,8 +77,6 @@ using rocksdb::BackupableDBOptions;
 using rocksdb::BackupInfo;
 using rocksdb::RestoreOptions;
 using rocksdb::CompactRangeOptions;
-using rocksdb::RateLimiter;
-using rocksdb::NewGenericRateLimiter;
 
 using std::shared_ptr;
 
@@ -104,9 +97,6 @@ struct rocksdb_readoptions_t {
 };
 struct rocksdb_writeoptions_t    { WriteOptions      rep; };
 struct rocksdb_options_t         { Options           rep; };
-struct rocksdb_compactoptions_t {
-  CompactRangeOptions rep;
-};
 struct rocksdb_block_based_table_options_t  { BlockBasedTableOptions rep; };
 struct rocksdb_cuckoo_table_options_t  { CuckooTableOptions rep; };
 struct rocksdb_seqfile_t         { SequentialFile*   rep; };
@@ -117,10 +107,6 @@ struct rocksdb_logger_t          { shared_ptr<Logger>  rep; };
 struct rocksdb_cache_t           { shared_ptr<Cache>   rep; };
 struct rocksdb_livefiles_t       { std::vector<LiveFileMetaData> rep; };
 struct rocksdb_column_family_handle_t  { ColumnFamilyHandle* rep; };
-struct rocksdb_envoptions_t      { EnvOptions        rep; };
-struct rocksdb_ingestexternalfileoptions_t  { IngestExternalFileOptions rep; };
-struct rocksdb_sstfilewriter_t   { SstFileWriter*    rep; };
-struct rocksdb_ratelimiter_t     { RateLimiter*      rep; };
 
 struct rocksdb_compactionfiltercontext_t {
   CompactionFilter::Context rep;
@@ -137,7 +123,6 @@ struct rocksdb_compactionfilter_t : public CompactionFilter {
       char** new_value, size_t *new_value_length,
       unsigned char* value_changed);
   const char* (*name_)(void*);
-  unsigned char ignore_snapshots_;
 
   virtual ~rocksdb_compactionfilter_t() {
     (*destructor_)(state_);
@@ -163,8 +148,6 @@ struct rocksdb_compactionfilter_t : public CompactionFilter {
   }
 
   virtual const char* Name() const override { return (*name_)(state_); }
-
-  virtual bool IgnoreSnapshots() const override { return ignore_snapshots_; }
 };
 
 struct rocksdb_compactionfilterfactory_t : public CompactionFilterFactory {
@@ -286,31 +269,33 @@ struct rocksdb_mergeoperator_t : public MergeOperator {
 
   virtual const char* Name() const override { return (*name_)(state_); }
 
-  virtual bool FullMergeV2(const MergeOperationInput& merge_in,
-                           MergeOperationOutput* merge_out) const override {
-    size_t n = merge_in.operand_list.size();
+  virtual bool FullMerge(const Slice& key, const Slice* existing_value,
+                         const std::deque<std::string>& operand_list,
+                         std::string* new_value,
+                         Logger* logger) const override {
+    size_t n = operand_list.size();
     std::vector<const char*> operand_pointers(n);
     std::vector<size_t> operand_sizes(n);
     for (size_t i = 0; i < n; i++) {
-      Slice operand(merge_in.operand_list[i]);
+      Slice operand(operand_list[i]);
       operand_pointers[i] = operand.data();
       operand_sizes[i] = operand.size();
     }
 
     const char* existing_value_data = nullptr;
     size_t existing_value_len = 0;
-    if (merge_in.existing_value != nullptr) {
-      existing_value_data = merge_in.existing_value->data();
-      existing_value_len = merge_in.existing_value->size();
+    if (existing_value != nullptr) {
+      existing_value_data = existing_value->data();
+      existing_value_len = existing_value->size();
     }
 
     unsigned char success;
     size_t new_value_len;
     char* tmp_new_value = (*full_merge_)(
-        state_, merge_in.key.data(), merge_in.key.size(), existing_value_data,
-        existing_value_len, &operand_pointers[0], &operand_sizes[0],
-        static_cast<int>(n), &success, &new_value_len);
-    merge_out->new_value.assign(tmp_new_value, new_value_len);
+        state_, key.data(), key.size(), existing_value_data, existing_value_len,
+        &operand_pointers[0], &operand_sizes[0], static_cast<int>(n), &success,
+        &new_value_len);
+    new_value->assign(tmp_new_value, new_value_len);
 
     if (delete_value_ != nullptr) {
       (*delete_value_)(state_, tmp_new_value, new_value_len);
@@ -448,11 +433,7 @@ rocksdb_backup_engine_t* rocksdb_backup_engine_open(
     const rocksdb_options_t* options, const char* path, char** errptr) {
   BackupEngine* be;
   if (SaveError(errptr, BackupEngine::Open(options->rep.env,
-                                           BackupableDBOptions(path,
-                                                               nullptr,
-                                                               true,
-                                                               options->rep.info_log.get()),
-                                           &be))) {
+                                           BackupableDBOptions(path), &be))) {
     return nullptr;
   }
   rocksdb_backup_engine_t* result = new rocksdb_backup_engine_t;
@@ -465,12 +446,6 @@ void rocksdb_backup_engine_create_new_backup(rocksdb_backup_engine_t* be,
   SaveError(errptr, be->rep->CreateNewBackup(db->rep));
 }
 
-void rocksdb_backup_engine_purge_old_backups(rocksdb_backup_engine_t* be,
-                                             uint32_t num_backups_to_keep,
-                                             char** errptr) {
-  SaveError(errptr, be->rep->PurgeOldBackups(num_backups_to_keep));
-}
-
 rocksdb_restore_options_t* rocksdb_restore_options_create() {
   return new rocksdb_restore_options_t;
 }
@@ -850,31 +825,6 @@ rocksdb_iterator_t* rocksdb_create_iterator_cf(
   return result;
 }
 
-void rocksdb_create_iterators(
-    rocksdb_t *db,
-    rocksdb_readoptions_t* opts,
-    rocksdb_column_family_handle_t** column_families,
-    rocksdb_iterator_t** iterators,
-    size_t size,
-    char** errptr) {
-  std::vector<ColumnFamilyHandle*> column_families_vec;
-  for (size_t i = 0; i < size; i++) {
-    column_families_vec.push_back(column_families[i]->rep);
-  }
-
-  std::vector<Iterator*> res;
-  Status status = db->rep->NewIterators(opts->rep, column_families_vec, &res);
-  assert(res.size() == size);
-  if (SaveError(errptr, status)) {
-    return;
-  }
-
-  for (size_t i = 0; i < size; i++) {
-    iterators[i] = new rocksdb_iterator_t;
-    iterators[i]->rep = res[i];
-  }
-}
-
 const rocksdb_snapshot_t* rocksdb_create_snapshot(
     rocksdb_t* db) {
   rocksdb_snapshot_t* result = new rocksdb_snapshot_t;
@@ -901,17 +851,6 @@ char* rocksdb_property_value(
   }
 }
 
-int rocksdb_property_int(
-    rocksdb_t* db,
-    const char* propname,
-    uint64_t *out_val) {
-  if (db->rep->GetIntProperty(Slice(propname), out_val)) {
-    return 0;
-  } else {
-    return -1;
-  }
-}
-
 char* rocksdb_property_value_cf(
     rocksdb_t* db,
     rocksdb_column_family_handle_t* column_family,
@@ -994,30 +933,6 @@ void rocksdb_compact_range_cf(
       (limit_key ? (b = Slice(limit_key, limit_key_len), &b) : nullptr));
 }
 
-void rocksdb_compact_range_opt(rocksdb_t* db, rocksdb_compactoptions_t* opt,
-                               const char* start_key, size_t start_key_len,
-                               const char* limit_key, size_t limit_key_len) {
-  Slice a, b;
-  db->rep->CompactRange(
-      opt->rep,
-      // Pass nullptr Slice if corresponding "const char*" is nullptr
-      (start_key ? (a = Slice(start_key, start_key_len), &a) : nullptr),
-      (limit_key ? (b = Slice(limit_key, limit_key_len), &b) : nullptr));
-}
-
-void rocksdb_compact_range_cf_opt(rocksdb_t* db,
-                                  rocksdb_column_family_handle_t* column_family,
-                                  rocksdb_compactoptions_t* opt,
-                                  const char* start_key, size_t start_key_len,
-                                  const char* limit_key, size_t limit_key_len) {
-  Slice a, b;
-  db->rep->CompactRange(
-      opt->rep, column_family->rep,
-      // Pass nullptr Slice if corresponding "const char*" is nullptr
-      (start_key ? (a = Slice(start_key, start_key_len), &a) : nullptr),
-      (limit_key ? (b = Slice(limit_key, limit_key_len), &b) : nullptr));
-}
-
 void rocksdb_flush(
     rocksdb_t* db,
     const rocksdb_flushoptions_t* options,
@@ -1073,11 +988,6 @@ void rocksdb_iter_seek(rocksdb_iterator_t* iter, const char* k, size_t klen) {
   iter->rep->Seek(Slice(k, klen));
 }
 
-void rocksdb_iter_seek_for_prev(rocksdb_iterator_t* iter, const char* k,
-                                size_t klen) {
-  iter->rep->SeekForPrev(Slice(k, klen));
-}
-
 void rocksdb_iter_next(rocksdb_iterator_t* iter) {
   iter->rep->Next();
 }
@@ -1265,53 +1175,6 @@ void rocksdb_writebatch_deletev_cf(
   b->rep.Delete(column_family->rep, SliceParts(key_slices.data(), num_keys));
 }
 
-void rocksdb_writebatch_delete_range(rocksdb_writebatch_t* b,
-                                     const char* start_key,
-                                     size_t start_key_len, const char* end_key,
-                                     size_t end_key_len) {
-  b->rep.DeleteRange(Slice(start_key, start_key_len),
-                     Slice(end_key, end_key_len));
-}
-
-void rocksdb_writebatch_delete_range_cf(
-    rocksdb_writebatch_t* b, 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) {
-  b->rep.DeleteRange(column_family->rep, Slice(start_key, start_key_len),
-                     Slice(end_key, end_key_len));
-}
-
-void rocksdb_writebatch_delete_rangev(rocksdb_writebatch_t* b, int num_keys,
-                                      const char* const* start_keys_list,
-                                      const size_t* start_keys_list_sizes,
-                                      const char* const* end_keys_list,
-                                      const size_t* end_keys_list_sizes) {
-  std::vector<Slice> start_key_slices(num_keys);
-  std::vector<Slice> end_key_slices(num_keys);
-  for (int i = 0; i < num_keys; i++) {
-    start_key_slices[i] = Slice(start_keys_list[i], start_keys_list_sizes[i]);
-    end_key_slices[i] = Slice(end_keys_list[i], end_keys_list_sizes[i]);
-  }
-  b->rep.DeleteRange(SliceParts(start_key_slices.data(), num_keys),
-                     SliceParts(end_key_slices.data(), num_keys));
-}
-
-void rocksdb_writebatch_delete_rangev_cf(
-    rocksdb_writebatch_t* b, rocksdb_column_family_handle_t* column_family,
-    int num_keys, const char* const* start_keys_list,
-    const size_t* start_keys_list_sizes, const char* const* end_keys_list,
-    const size_t* end_keys_list_sizes) {
-  std::vector<Slice> start_key_slices(num_keys);
-  std::vector<Slice> end_key_slices(num_keys);
-  for (int i = 0; i < num_keys; i++) {
-    start_key_slices[i] = Slice(start_keys_list[i], start_keys_list_sizes[i]);
-    end_key_slices[i] = Slice(end_keys_list[i], end_keys_list_sizes[i]);
-  }
-  b->rep.DeleteRange(column_family->rep,
-                     SliceParts(start_key_slices.data(), num_keys),
-                     SliceParts(end_key_slices.data(), num_keys));
-}
-
 void rocksdb_writebatch_put_log_data(
     rocksdb_writebatch_t* b,
     const char* blob, size_t len) {
@@ -1347,15 +1210,6 @@ const char* rocksdb_writebatch_data(rocksdb_writebatch_t* b, size_t* size) {
   return b->rep.Data().c_str();
 }
 
-void rocksdb_writebatch_set_save_point(rocksdb_writebatch_t* b) {
-  b->rep.SetSavePoint();
-}
-
-void rocksdb_writebatch_rollback_to_save_point(rocksdb_writebatch_t* b,
-                                               char** errptr) {
-  SaveError(errptr, b->rep.RollbackToSavePoint());
-}
-
 rocksdb_block_based_table_options_t*
 rocksdb_block_based_options_create() {
   return new rocksdb_block_based_table_options_t;
@@ -1434,9 +1288,9 @@ void rocksdb_block_based_options_set_cache_index_and_filter_blocks(
   options->rep.cache_index_and_filter_blocks = v;
 }
 
-void rocksdb_block_based_options_set_pin_l0_filter_and_index_blocks_in_cache(
+void rocksdb_block_based_options_set_skip_table_builder_flush(
     rocksdb_block_based_table_options_t* options, unsigned char v) {
-  options->rep.pin_l0_filter_and_index_blocks_in_cache = v;
+  options->rep.skip_table_builder_flush = v;
 }
 
 void rocksdb_options_set_block_based_table_factory(
@@ -1493,14 +1347,6 @@ void rocksdb_options_set_cuckoo_table_factory(
   }
 }
 
-void rocksdb_set_options(
-    rocksdb_t* db, int count, const char* const keys[], const char* const values[], char** errptr) {
-        std::unordered_map<std::string, std::string> options_map;
-        for (int i=0; i<count; i++)
-            options_map[keys[i]] = values[i];
-        SaveError(errptr,
-            db->rep->SetOptions(options_map));
-    }
 
 rocksdb_options_t* rocksdb_options_create() {
   return new rocksdb_options_t;
@@ -1542,11 +1388,6 @@ void rocksdb_options_set_compaction_filter_factory(
       std::shared_ptr<CompactionFilterFactory>(factory);
 }
 
-void rocksdb_options_compaction_readahead_size(
-    rocksdb_options_t* opt, size_t s) {
-  opt->rep.compaction_readahead_size = s;
-}
-
 void rocksdb_options_set_comparator(
     rocksdb_options_t* opt,
     rocksdb_comparator_t* cmp) {
@@ -1627,19 +1468,19 @@ void rocksdb_options_set_max_bytes_for_level_base(
   opt->rep.max_bytes_for_level_base = 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;
-}
-
-void rocksdb_options_set_max_bytes_for_level_multiplier(rocksdb_options_t* opt,
-                                                        double n) {
+void rocksdb_options_set_max_bytes_for_level_multiplier(
+    rocksdb_options_t* opt, int n) {
   opt->rep.max_bytes_for_level_multiplier = n;
 }
 
-void rocksdb_options_set_max_compaction_bytes(rocksdb_options_t* opt,
-                                              uint64_t n) {
-  opt->rep.max_compaction_bytes = n;
+void rocksdb_options_set_expanded_compaction_factor(
+    rocksdb_options_t* opt, int n) {
+  opt->rep.expanded_compaction_factor = n;
+}
+
+void rocksdb_options_set_max_grandparent_overlap_factor(
+    rocksdb_options_t* opt, int n) {
+  opt->rep.max_grandparent_overlap_factor = n;
 }
 
 void rocksdb_options_set_max_bytes_for_level_multiplier_additional(
@@ -1676,10 +1517,6 @@ void rocksdb_options_set_level0_stop_writes_trigger(
 void rocksdb_options_set_max_mem_compaction_level(rocksdb_options_t* opt,
                                                   int n) {}
 
-void rocksdb_options_set_wal_recovery_mode(rocksdb_options_t* opt,int mode) {
-  opt->rep.wal_recovery_mode = static_cast<WALRecoveryMode>(mode);
-}
-
 void rocksdb_options_set_compression(rocksdb_options_t* opt, int t) {
   opt->rep.compression = static_cast<CompressionType>(t);
 }
@@ -1694,13 +1531,11 @@ void rocksdb_options_set_compression_per_level(rocksdb_options_t* opt,
   }
 }
 
-void rocksdb_options_set_compression_options(rocksdb_options_t* opt, int w_bits,
-                                             int level, int strategy,
-                                             int max_dict_bytes) {
+void rocksdb_options_set_compression_options(
+    rocksdb_options_t* opt, int w_bits, int level, int strategy) {
   opt->rep.compression_opts.window_bits = w_bits;
   opt->rep.compression_opts.level = level;
   opt->rep.compression_opts.strategy = strategy;
-  opt->rep.compression_opts.max_dict_bytes = max_dict_bytes;
 }
 
 void rocksdb_options_set_prefix_extractor(
@@ -1708,6 +1543,11 @@ void rocksdb_options_set_prefix_extractor(
   opt->rep.prefix_extractor.reset(prefix_extractor);
 }
 
+void rocksdb_options_set_disable_data_sync(
+    rocksdb_options_t* opt, int disable_data_sync) {
+  opt->rep.disableDataSync = disable_data_sync;
+}
+
 void rocksdb_options_set_use_fsync(
     rocksdb_options_t* opt, int use_fsync) {
   opt->rep.use_fsync = use_fsync;
@@ -1741,14 +1581,9 @@ void rocksdb_options_set_manifest_preallocation_size(
 void rocksdb_options_set_purge_redundant_kvs_while_flush(rocksdb_options_t* opt,
                                                          unsigned char v) {}
 
-void rocksdb_options_set_use_direct_reads(rocksdb_options_t* opt,
-                                          unsigned char v) {
-  opt->rep.use_direct_reads = v;
-}
-
-void rocksdb_options_set_use_direct_writes(rocksdb_options_t* opt,
-                                           unsigned char v) {
-  opt->rep.use_direct_writes = v;
+void rocksdb_options_set_allow_os_buffer(rocksdb_options_t* opt,
+                                         unsigned char v) {
+  opt->rep.allow_os_buffer = v;
 }
 
 void rocksdb_options_set_allow_mmap_reads(
@@ -1809,14 +1644,14 @@ void rocksdb_options_set_bytes_per_sync(
   opt->rep.bytes_per_sync = v;
 }
 
-void rocksdb_options_set_allow_concurrent_memtable_write(rocksdb_options_t* opt,
-                                                         unsigned char v) {
-  opt->rep.allow_concurrent_memtable_write = v;
+void rocksdb_options_set_verify_checksums_in_compaction(
+    rocksdb_options_t* opt, unsigned char v) {
+  opt->rep.verify_checksums_in_compaction = v;
 }
 
-void rocksdb_options_set_enable_write_thread_adaptive_yield(
+void rocksdb_options_set_filter_deletes(
     rocksdb_options_t* opt, unsigned char v) {
-  opt->rep.enable_write_thread_adaptive_yield = v;
+  opt->rep.filter_deletes = v;
 }
 
 void rocksdb_options_set_max_sequential_skip_in_iterations(
@@ -1841,11 +1676,6 @@ void rocksdb_options_set_max_background_compactions(rocksdb_options_t* opt, int
   opt->rep.max_background_compactions = n;
 }
 
-void rocksdb_options_set_base_background_compactions(rocksdb_options_t* opt,
-                                                     int n) {
-  opt->rep.base_background_compactions = n;
-}
-
 void rocksdb_options_set_max_background_flushes(rocksdb_options_t* opt, int n) {
   opt->rep.max_background_flushes = n;
 }
@@ -1875,14 +1705,6 @@ void rocksdb_options_set_hard_rate_limit(rocksdb_options_t* opt, double v) {
   opt->rep.hard_rate_limit = v;
 }
 
-void rocksdb_options_set_soft_pending_compaction_bytes_limit(rocksdb_options_t* opt, size_t v) {
-  opt->rep.soft_pending_compaction_bytes_limit = v;
-}
-
-void rocksdb_options_set_hard_pending_compaction_bytes_limit(rocksdb_options_t* opt, size_t v) {
-  opt->rep.hard_pending_compaction_bytes_limit = v;
-}
-
 void rocksdb_options_set_rate_limit_delay_max_milliseconds(
     rocksdb_options_t* opt, unsigned int v) {
   opt->rep.rate_limit_delay_max_milliseconds = v;
@@ -1912,56 +1734,76 @@ void rocksdb_options_set_disable_auto_compactions(rocksdb_options_t* opt, int di
   opt->rep.disable_auto_compactions = disable;
 }
 
-void rocksdb_options_set_optimize_filters_for_hits(rocksdb_options_t* opt, int v) {
-  opt->rep.optimize_filters_for_hits = v;
-}
-
 void rocksdb_options_set_delete_obsolete_files_period_micros(
     rocksdb_options_t* opt, uint64_t v) {
   opt->rep.delete_obsolete_files_period_micros = v;
 }
 
+void rocksdb_options_set_source_compaction_factor(
+    rocksdb_options_t* opt, int n) {
+  opt->rep.expanded_compaction_factor = n;
+}
+
 void rocksdb_options_prepare_for_bulk_load(rocksdb_options_t* opt) {
   opt->rep.PrepareForBulkLoad();
 }
 
 void rocksdb_options_set_memtable_vector_rep(rocksdb_options_t *opt) {
-  opt->rep.memtable_factory.reset(new rocksdb::VectorRepFactory);
+  static rocksdb::VectorRepFactory* factory = 0;
+  if (!factory) {
+    factory = new rocksdb::VectorRepFactory;
+  }
+  opt->rep.memtable_factory.reset(factory);
 }
 
-void rocksdb_options_set_memtable_prefix_bloom_size_ratio(
-    rocksdb_options_t* opt, double v) {
-  opt->rep.memtable_prefix_bloom_size_ratio = v;
+void rocksdb_options_set_memtable_prefix_bloom_bits(
+    rocksdb_options_t* opt, uint32_t v) {
+  opt->rep.memtable_prefix_bloom_bits = v;
 }
 
-void rocksdb_options_set_memtable_huge_page_size(rocksdb_options_t* opt,
-                                                 size_t v) {
-  opt->rep.memtable_huge_page_size = v;
+void rocksdb_options_set_memtable_prefix_bloom_probes(
+    rocksdb_options_t* opt, uint32_t v) {
+  opt->rep.memtable_prefix_bloom_probes = v;
+}
+
+void rocksdb_options_set_memtable_prefix_bloom_huge_page_tlb_size(
+    rocksdb_options_t* opt, size_t v) {
+  opt->rep.memtable_prefix_bloom_huge_page_tlb_size = v;
 }
 
 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::MemTableRepFactory* factory = rocksdb::NewHashSkipListRepFactory(
-      bucket_count, skiplist_height, skiplist_branching_factor);
+  static rocksdb::MemTableRepFactory* factory = 0;
+  if (!factory) {
+    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::NewHashLinkListRepFactory(bucket_count));
+  static rocksdb::MemTableRepFactory* factory = 0;
+  if (!factory) {
+    factory = rocksdb::NewHashLinkListRepFactory(bucket_count);
+  }
+  opt->rep.memtable_factory.reset(factory);
 }
 
 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::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;
+  static rocksdb::TableFactory* factory = 0;
+  if (!factory) {
+    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::TableFactory* factory = rocksdb::NewPlainTableFactory(options);
+    factory = rocksdb::NewPlainTableFactory(options);
+  }
   opt->rep.table_factory.reset(factory);
 }
 
@@ -1970,6 +1812,11 @@ void rocksdb_options_set_max_successive_merges(
   opt->rep.max_successive_merges = v;
 }
 
+void rocksdb_options_set_min_partial_merge_operands(
+    rocksdb_options_t* opt, uint32_t v) {
+  opt->rep.min_partial_merge_operands = v;
+}
+
 void rocksdb_options_set_bloom_locality(
     rocksdb_options_t* opt, uint32_t v) {
   opt->rep.bloom_locality = v;
@@ -1985,11 +1832,6 @@ void rocksdb_options_set_inplace_update_num_locks(
   opt->rep.inplace_update_num_locks = v;
 }
 
-void rocksdb_options_set_report_bg_io_stats(
-    rocksdb_options_t* opt, int v) {
-  opt->rep.report_bg_io_stats = v;
-}
-
 void rocksdb_options_set_compaction_style(rocksdb_options_t *opt, int style) {
   opt->rep.compaction_style = static_cast<rocksdb::CompactionStyle>(style);
 }
@@ -2012,28 +1854,6 @@ char *rocksdb_options_statistics_get_string(rocksdb_options_t *opt) {
   return nullptr;
 }
 
-void rocksdb_options_set_ratelimiter(rocksdb_options_t *opt, rocksdb_ratelimiter_t *limiter) {
-  opt->rep.rate_limiter.reset(limiter->rep);
-  limiter->rep = nullptr;
-}
-
-rocksdb_ratelimiter_t* rocksdb_ratelimiter_create(
-    int64_t rate_bytes_per_sec,
-    int64_t refill_period_us,
-    int32_t fairness) {
-  rocksdb_ratelimiter_t* rate_limiter = new rocksdb_ratelimiter_t;
-  rate_limiter->rep = NewGenericRateLimiter(rate_bytes_per_sec,
-                                            refill_period_us, fairness);
-  return rate_limiter;
-}
-
-void rocksdb_ratelimiter_destroy(rocksdb_ratelimiter_t *limiter) {
-  if (limiter->rep) {
-    delete limiter->rep;
-  }
-  delete limiter;
-}
-
 /*
 TODO:
 DB::OpenForReadOnly
@@ -2063,17 +1883,10 @@ rocksdb_compactionfilter_t* rocksdb_compactionfilter_create(
   result->state_ = state;
   result->destructor_ = destructor;
   result->filter_ = filter;
-  result->ignore_snapshots_ = false;
   result->name_ = name;
   return result;
 }
 
-void rocksdb_compactionfilter_set_ignore_snapshots(
-  rocksdb_compactionfilter_t* filter,
-  unsigned char whether_ignore) {
-  filter->ignore_snapshots_ = whether_ignore;
-}
-
 void rocksdb_compactionfilter_destroy(rocksdb_compactionfilter_t* filter) {
   delete filter;
 }
@@ -2266,21 +2079,6 @@ void rocksdb_readoptions_set_tailing(
   opt->rep.tailing = v;
 }
 
-void rocksdb_readoptions_set_readahead_size(
-    rocksdb_readoptions_t* opt, size_t v) {
-  opt->rep.readahead_size = v;
-}
-
-void rocksdb_readoptions_set_pin_data(rocksdb_readoptions_t* opt,
-                                      unsigned char v) {
-  opt->rep.pin_data = v;
-}
-
-void rocksdb_readoptions_set_total_order_seek(rocksdb_readoptions_t* opt,
-                                              unsigned char v) {
-  opt->rep.total_order_seek = v;
-}
-
 rocksdb_writeoptions_t* rocksdb_writeoptions_create() {
   return new rocksdb_writeoptions_t;
 }
@@ -2298,28 +2096,6 @@ void rocksdb_writeoptions_disable_WAL(rocksdb_writeoptions_t* opt, int disable)
   opt->rep.disableWAL = disable;
 }
 
-rocksdb_compactoptions_t* rocksdb_compactoptions_create() {
-  return new rocksdb_compactoptions_t;
-}
-
-void rocksdb_compactoptions_destroy(rocksdb_compactoptions_t* opt) {
-  delete opt;
-}
-
-void rocksdb_compactoptions_set_exclusive_manual_compaction(
-    rocksdb_compactoptions_t* opt, unsigned char v) {
-  opt->rep.exclusive_manual_compaction = v;
-}
-
-void rocksdb_compactoptions_set_change_level(rocksdb_compactoptions_t* opt,
-                                             unsigned char v) {
-  opt->rep.change_level = v;
-}
-
-void rocksdb_compactoptions_set_target_level(rocksdb_compactoptions_t* opt,
-                                             int n) {
-  opt->rep.target_level = n;
-}
 
 rocksdb_flushoptions_t* rocksdb_flushoptions_create() {
   return new rocksdb_flushoptions_t;
@@ -2344,18 +2120,6 @@ void rocksdb_cache_destroy(rocksdb_cache_t* cache) {
   delete cache;
 }
 
-void rocksdb_cache_set_capacity(rocksdb_cache_t* cache, size_t capacity) {
-  cache->rep->SetCapacity(capacity);
-}
-
-size_t rocksdb_cache_get_usage(rocksdb_cache_t* cache) {
-  return cache->rep->GetUsage();
-}
-
-size_t rocksdb_cache_get_pinned_usage(rocksdb_cache_t* cache) {
-  return cache->rep->GetPinnedUsage();
-}
-
 rocksdb_env_t* rocksdb_create_default_env() {
   rocksdb_env_t* result = new rocksdb_env_t;
   result->rep = Env::Default();
@@ -2363,13 +2127,6 @@ rocksdb_env_t* rocksdb_create_default_env() {
   return result;
 }
 
-rocksdb_env_t* rocksdb_create_mem_env() {
-  rocksdb_env_t* result = new rocksdb_env_t;
-  result->rep = rocksdb::NewMemEnv(Env::Default());
-  result->is_default = false;
-  return result;
-}
-
 void rocksdb_env_set_background_threads(rocksdb_env_t* env, int n) {
   env->rep->SetBackgroundThreads(n);
 }
@@ -2387,107 +2144,6 @@ void rocksdb_env_destroy(rocksdb_env_t* env) {
   delete env;
 }
 
-rocksdb_envoptions_t* rocksdb_envoptions_create() {
-  rocksdb_envoptions_t* opt = new rocksdb_envoptions_t;
-  return opt;
-}
-
-void rocksdb_envoptions_destroy(rocksdb_envoptions_t* opt) { delete opt; }
-
-rocksdb_sstfilewriter_t* rocksdb_sstfilewriter_create(
-    const rocksdb_envoptions_t* env, const rocksdb_options_t* io_options) {
-  rocksdb_sstfilewriter_t* writer = new rocksdb_sstfilewriter_t;
-  writer->rep =
-      new SstFileWriter(env->rep, io_options->rep, io_options->rep.comparator);
-  return writer;
-}
-
-rocksdb_sstfilewriter_t* rocksdb_sstfilewriter_create_with_comparator(
-    const rocksdb_envoptions_t* env, const rocksdb_options_t* io_options,
-    const rocksdb_comparator_t* comparator) {
-  rocksdb_sstfilewriter_t* writer = new rocksdb_sstfilewriter_t;
-  writer->rep =
-      new SstFileWriter(env->rep, io_options->rep, io_options->rep.comparator);
-  return writer;
-}
-
-void rocksdb_sstfilewriter_open(rocksdb_sstfilewriter_t* writer,
-                                const char* name, char** errptr) {
-  SaveError(errptr, writer->rep->Open(std::string(name)));
-}
-
-void rocksdb_sstfilewriter_add(rocksdb_sstfilewriter_t* writer, const char* key,
-                               size_t keylen, const char* val, size_t vallen,
-                               char** errptr) {
-  SaveError(errptr, writer->rep->Add(Slice(key, keylen), Slice(val, vallen)));
-}
-
-void rocksdb_sstfilewriter_finish(rocksdb_sstfilewriter_t* writer,
-                                  char** errptr) {
-  SaveError(errptr, writer->rep->Finish(NULL));
-}
-
-void rocksdb_sstfilewriter_destroy(rocksdb_sstfilewriter_t* writer) {
-  delete writer->rep;
-  delete writer;
-}
-
-rocksdb_ingestexternalfileoptions_t*
-rocksdb_ingestexternalfileoptions_create() {
-  rocksdb_ingestexternalfileoptions_t* opt =
-      new rocksdb_ingestexternalfileoptions_t;
-  return opt;
-}
-
-void rocksdb_ingestexternalfileoptions_set_move_files(
-    rocksdb_ingestexternalfileoptions_t* opt, unsigned char move_files) {
-  opt->rep.move_files = move_files;
-}
-
-void rocksdb_ingestexternalfileoptions_set_snapshot_consistency(
-    rocksdb_ingestexternalfileoptions_t* opt,
-    unsigned char snapshot_consistency) {
-  opt->rep.snapshot_consistency = snapshot_consistency;
-}
-
-void rocksdb_ingestexternalfileoptions_set_allow_global_seqno(
-    rocksdb_ingestexternalfileoptions_t* opt,
-    unsigned char allow_global_seqno) {
-  opt->rep.allow_global_seqno = allow_global_seqno;
-}
-
-void rocksdb_ingestexternalfileoptions_set_allow_blocking_flush(
-    rocksdb_ingestexternalfileoptions_t* opt,
-    unsigned char allow_blocking_flush) {
-  opt->rep.allow_blocking_flush = allow_blocking_flush;
-}
-
-void rocksdb_ingestexternalfileoptions_destroy(
-    rocksdb_ingestexternalfileoptions_t* opt) {
-  delete opt;
-}
-
-void rocksdb_ingest_external_file(
-    rocksdb_t* db, const char* const* file_list, const size_t list_len,
-    const rocksdb_ingestexternalfileoptions_t* opt, char** errptr) {
-  std::vector<std::string> files(list_len);
-  for (size_t i = 0; i < list_len; ++i) {
-    files[i] = std::string(file_list[i]);
-  }
-  SaveError(errptr, db->rep->IngestExternalFile(files, opt->rep));
-}
-
-void rocksdb_ingest_external_file_cf(
-    rocksdb_t* db, rocksdb_column_family_handle_t* handle,
-    const char* const* file_list, const size_t list_len,
-    const rocksdb_ingestexternalfileoptions_t* opt, char** errptr) {
-  std::vector<std::string> files(list_len);
-  for (size_t i = 0; i < list_len; ++i) {
-    files[i] = std::string(file_list[i]);
-  }
-  SaveError(errptr, db->rep->IngestExternalFile(handle->rep, files, opt->rep));
-}
-
 rocksdb_slicetransform_t* rocksdb_slicetransform_create(
     void* state,
     void (*destructor)(void*),
@@ -2682,31 +2338,6 @@ void rocksdb_get_options_from_string(const rocksdb_options_t* base_options,
                                  &new_options->rep));
 }
 
-void rocksdb_delete_file_in_range(rocksdb_t* db, const char* start_key,
-                                  size_t start_key_len, const char* limit_key,
-                                  size_t limit_key_len, char** errptr) {
-  Slice a, b;
-  SaveError(
-      errptr,
-      DeleteFilesInRange(
-          db->rep, db->rep->DefaultColumnFamily(),
-          (start_key ? (a = Slice(start_key, start_key_len), &a) : nullptr),
-          (limit_key ? (b = Slice(limit_key, limit_key_len), &b) : nullptr)));
-}
-
-void rocksdb_delete_file_in_range_cf(
-    rocksdb_t* db, rocksdb_column_family_handle_t* column_family,
-    const char* start_key, size_t start_key_len, const char* limit_key,
-    size_t limit_key_len, char** errptr) {
-  Slice a, b;
-  SaveError(
-      errptr,
-      DeleteFilesInRange(
-          db->rep, column_family->rep,
-          (start_key ? (a = Slice(start_key, start_key_len), &a) : nullptr),
-          (limit_key ? (b = Slice(limit_key, limit_key_len), &b) : nullptr)));
-}
-
 void rocksdb_free(void* ptr) { free(ptr); }
 
 }  // end extern "C"

db/c_test.c

@@ -2,18 +2,17 @@
    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 <stdio.h>
-
 #ifndef ROCKSDB_LITE  // Lite does not support C API
 
 #include "rocksdb/c.h"
 
 #include <stddef.h>
+#include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
 #ifndef OS_WIN
-#include <unistd.h>
+#  include <unistd.h>
 #endif
 #include <inttypes.h>
 
@@ -22,10 +21,11 @@
 
 #include <Windows.h>
 
-#define snprintf _snprintf
+# define snprintf _snprintf
 
 // Ok for uniqueness
 int geteuid() {
+
   int result = 0;
 
   result = ((int)GetCurrentProcessId() << 16);
@@ -38,13 +38,13 @@ int geteuid() {
 
 const char* phase = "";
 static char dbname[200];
-static char sstfilename[200];
 static char dbbackupname[200];
 
 static void StartPhase(const char* name) {
   fprintf(stderr, "=== Test %s\n", name);
   phase = name;
 }
+
 static const char* GetTempDir(void) {
     const char* ret = getenv("TEST_TMPDIR");
     if (ret == NULL || ret[0] == '\0')
@@ -288,11 +288,9 @@ int main(int argc, char** argv) {
   rocksdb_cache_t* cache;
   rocksdb_env_t* env;
   rocksdb_options_t* options;
-  rocksdb_compactoptions_t* coptions;
   rocksdb_block_based_table_options_t* table_options;
   rocksdb_readoptions_t* roptions;
   rocksdb_writeoptions_t* woptions;
-  rocksdb_ratelimiter_t* rate_limiter;
   char* err = NULL;
   int run = -1;
 
@@ -306,11 +304,6 @@ int main(int argc, char** argv) {
            GetTempDir(),
            ((int) geteuid()));
 
-  snprintf(sstfilename, sizeof(sstfilename),
-           "%s/rocksdb_c_test-%d-sst",
-           GetTempDir(),
-           ((int)geteuid()));
-
   StartPhase("create_objects");
   cmp = rocksdb_comparator_create(NULL, CmpDestroy, CmpCompare, CmpName);
   env = rocksdb_create_default_env();
@@ -324,30 +317,23 @@ int main(int argc, char** argv) {
   rocksdb_options_set_write_buffer_size(options, 100000);
   rocksdb_options_set_paranoid_checks(options, 1);
   rocksdb_options_set_max_open_files(options, 10);
-  rocksdb_options_set_base_background_compactions(options, 1);
   table_options = rocksdb_block_based_options_create();
   rocksdb_block_based_options_set_block_cache(table_options, cache);
   rocksdb_options_set_block_based_table_factory(options, table_options);
 
   rocksdb_options_set_compression(options, rocksdb_no_compression);
-  rocksdb_options_set_compression_options(options, -14, -1, 0, 0);
+  rocksdb_options_set_compression_options(options, -14, -1, 0);
   int compression_levels[] = {rocksdb_no_compression, rocksdb_no_compression,
                               rocksdb_no_compression, rocksdb_no_compression};
   rocksdb_options_set_compression_per_level(options, compression_levels, 4);
-  rate_limiter = rocksdb_ratelimiter_create(1000 * 1024 * 1024, 100 * 1000, 10);
-  rocksdb_options_set_ratelimiter(options, rate_limiter);
-  rocksdb_ratelimiter_destroy(rate_limiter);
 
   roptions = rocksdb_readoptions_create();
   rocksdb_readoptions_set_verify_checksums(roptions, 1);
-  rocksdb_readoptions_set_fill_cache(roptions, 1);
+  rocksdb_readoptions_set_fill_cache(roptions, 0);
 
   woptions = rocksdb_writeoptions_create();
   rocksdb_writeoptions_set_sync(woptions, 1);
 
-  coptions = rocksdb_compactoptions_create();
-  rocksdb_compactoptions_set_exclusive_manual_compaction(coptions, 1);
-
   StartPhase("destroy");
   rocksdb_destroy_db(options, dbname, &err);
   Free(&err);
@@ -379,24 +365,6 @@ int main(int argc, char** argv) {
     rocksdb_backup_engine_create_new_backup(be, db, &err);
     CheckNoError(err);
 
-    // need a change to trigger a new backup
-    rocksdb_delete(db, woptions, "does-not-exist", 14, &err);
-    CheckNoError(err);
-
-    rocksdb_backup_engine_create_new_backup(be, db, &err);
-    CheckNoError(err);
-
-    const rocksdb_backup_engine_info_t* bei = rocksdb_backup_engine_get_backup_info(be);
-    CheckCondition(rocksdb_backup_engine_info_count(bei) > 1);
-    rocksdb_backup_engine_info_destroy(bei);
-
-    rocksdb_backup_engine_purge_old_backups(be, 1, &err);
-    CheckNoError(err);
-
-    bei = rocksdb_backup_engine_get_backup_info(be);
-    CheckCondition(rocksdb_backup_engine_info_count(bei) == 1);
-    rocksdb_backup_engine_info_destroy(bei);
-
     rocksdb_delete(db, woptions, "foo", 3, &err);
     CheckNoError(err);
 
@@ -429,95 +397,6 @@ int main(int argc, char** argv) {
   rocksdb_compact_range(db, "a", 1, "z", 1);
   CheckGet(db, roptions, "foo", "hello");
 
-  StartPhase("compactallopt");
-  rocksdb_compact_range_opt(db, coptions, NULL, 0, NULL, 0);
-  CheckGet(db, roptions, "foo", "hello");
-
-  StartPhase("compactrangeopt");
-  rocksdb_compact_range_opt(db, coptions, "a", 1, "z", 1);
-  CheckGet(db, roptions, "foo", "hello");
-
-  // Simple check cache usage
-  StartPhase("cache_usage");
-  {
-    rocksdb_readoptions_set_pin_data(roptions, 1);
-    rocksdb_iterator_t* iter = rocksdb_create_iterator(db, roptions);
-    rocksdb_iter_seek(iter, "foo", 3);
-
-    size_t usage = rocksdb_cache_get_usage(cache);
-    CheckCondition(usage > 0);
-
-    size_t pin_usage = rocksdb_cache_get_pinned_usage(cache);
-    CheckCondition(pin_usage > 0);
-
-    rocksdb_iter_next(iter);
-    rocksdb_iter_destroy(iter);
-    rocksdb_readoptions_set_pin_data(roptions, 0);
-  }
-
-  StartPhase("addfile");
-  {
-    rocksdb_envoptions_t* env_opt = rocksdb_envoptions_create();
-    rocksdb_options_t* io_options = rocksdb_options_create();
-    rocksdb_sstfilewriter_t* writer =
-        rocksdb_sstfilewriter_create(env_opt, io_options);
-
-    unlink(sstfilename);
-    rocksdb_sstfilewriter_open(writer, sstfilename, &err);
-    CheckNoError(err);
-    rocksdb_sstfilewriter_add(writer, "sstk1", 5, "v1", 2, &err);
-    CheckNoError(err);
-    rocksdb_sstfilewriter_add(writer, "sstk2", 5, "v2", 2, &err);
-    CheckNoError(err);
-    rocksdb_sstfilewriter_add(writer, "sstk3", 5, "v3", 2, &err);
-    CheckNoError(err);
-    rocksdb_sstfilewriter_finish(writer, &err);
-    CheckNoError(err);
-
-    rocksdb_ingestexternalfileoptions_t* ing_opt =
-        rocksdb_ingestexternalfileoptions_create();
-    const char* file_list[1] = {sstfilename};
-    rocksdb_ingest_external_file(db, file_list, 1, ing_opt, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "sstk1", "v1");
-    CheckGet(db, roptions, "sstk2", "v2");
-    CheckGet(db, roptions, "sstk3", "v3");
-
-    unlink(sstfilename);
-    rocksdb_sstfilewriter_open(writer, sstfilename, &err);
-    CheckNoError(err);
-    rocksdb_sstfilewriter_add(writer, "sstk2", 5, "v4", 2, &err);
-    CheckNoError(err);
-    rocksdb_sstfilewriter_add(writer, "sstk22", 6, "v5", 2, &err);
-    CheckNoError(err);
-    rocksdb_sstfilewriter_add(writer, "sstk3", 5, "v6", 2, &err);
-    CheckNoError(err);
-    rocksdb_sstfilewriter_finish(writer, &err);
-    CheckNoError(err);
-
-    rocksdb_ingest_external_file(db, file_list, 1, ing_opt, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "sstk1", "v1");
-    CheckGet(db, roptions, "sstk2", "v4");
-    CheckGet(db, roptions, "sstk22", "v5");
-    CheckGet(db, roptions, "sstk3", "v6");
-
-    rocksdb_ingestexternalfileoptions_destroy(ing_opt);
-    rocksdb_sstfilewriter_destroy(writer);
-    rocksdb_options_destroy(io_options);
-    rocksdb_envoptions_destroy(env_opt);
-
-    // Delete all keys we just ingested
-    rocksdb_delete(db, woptions, "sstk1", 5, &err);
-    CheckNoError(err);
-    rocksdb_delete(db, woptions, "sstk2", 5, &err);
-    CheckNoError(err);
-    rocksdb_delete(db, woptions, "sstk22", 6, &err);
-    CheckNoError(err);
-    rocksdb_delete(db, woptions, "sstk3", 5, &err);
-    CheckNoError(err);
-  }
-
   StartPhase("writebatch");
   {
     rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
@@ -534,24 +413,6 @@ int main(int argc, char** argv) {
     int pos = 0;
     rocksdb_writebatch_iterate(wb, &pos, CheckPut, CheckDel);
     CheckCondition(pos == 3);
-    rocksdb_writebatch_clear(wb);
-    rocksdb_writebatch_put(wb, "bar", 3, "b", 1);
-    rocksdb_writebatch_put(wb, "bay", 3, "d", 1);
-    rocksdb_writebatch_delete_range(wb, "bar", 3, "bay", 3);
-    rocksdb_write(db, woptions, wb, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "bar", NULL);
-    CheckGet(db, roptions, "bay", "d");
-    rocksdb_writebatch_clear(wb);
-    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_delete_rangev(wb, 1, start_list, start_sizes, end_list,
-                                     end_sizes);
-    rocksdb_write(db, woptions, wb, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "bay", NULL);
     rocksdb_writebatch_destroy(wb);
   }
 
@@ -573,23 +434,6 @@ int main(int argc, char** argv) {
     rocksdb_writebatch_destroy(wb);
   }
 
-  StartPhase("writebatch_savepoint");
-  {
-    rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
-    rocksdb_writebatch_set_save_point(wb);
-    const char* k_list[2] = {"z", "ap"};
-    const size_t k_sizes[2] = {1, 2};
-    const char* v_list[3] = {"x", "y", "z"};
-    const size_t v_sizes[3] = {1, 1, 1};
-    rocksdb_writebatch_putv(wb, 2, k_list, k_sizes, 3, v_list, v_sizes);
-    rocksdb_writebatch_rollback_to_save_point(wb, &err);
-    CheckNoError(err);
-    rocksdb_write(db, woptions, wb, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "zap", NULL);
-    rocksdb_writebatch_destroy(wb);
-  }
-
   StartPhase("writebatch_rep");
   {
     rocksdb_writebatch_t* wb1 = rocksdb_writebatch_create();
@@ -625,10 +469,6 @@ int main(int argc, char** argv) {
     CheckIter(iter, "foo", "hello");
     rocksdb_iter_seek(iter, "b", 1);
     CheckIter(iter, "box", "c");
-    rocksdb_iter_seek_for_prev(iter, "g", 1);
-    CheckIter(iter, "foo", "hello");
-    rocksdb_iter_seek_for_prev(iter, "box", 3);
-    CheckIter(iter, "box", "c");
     rocksdb_iter_get_error(iter, &err);
     CheckNoError(err);
     rocksdb_iter_destroy(iter);
@@ -717,7 +557,6 @@ int main(int argc, char** argv) {
     rocksdb_close(db);
     rocksdb_options_set_create_if_missing(options, 0);
     rocksdb_options_set_error_if_exists(options, 0);
-    rocksdb_options_set_wal_recovery_mode(options, 2);
     rocksdb_repair_db(options, dbname, &err);
     CheckNoError(err);
     db = rocksdb_open(options, dbname, &err);
@@ -840,7 +679,7 @@ int main(int argc, char** argv) {
   {
     rocksdb_close(db);
     rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
+    CheckNoError(err)
 
     rocksdb_options_t* db_options = rocksdb_options_create();
     rocksdb_options_set_create_if_missing(db_options, 1);
@@ -929,30 +768,6 @@ int main(int argc, char** argv) {
     CheckNoError(err);
     rocksdb_iter_destroy(iter);
 
-    rocksdb_column_family_handle_t* iters_cf_handles[2] = { handles[0], handles[1] };
-    rocksdb_iterator_t* iters_handles[2];
-    rocksdb_create_iterators(db, roptions, iters_cf_handles, iters_handles, 2, &err);
-    CheckNoError(err);
-
-    iter = iters_handles[0];
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_first(iter);
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_destroy(iter);
-
-    iter = iters_handles[1];
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_first(iter);
-    CheckCondition(rocksdb_iter_valid(iter));
-
-    for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
-      i++;
-    }
-    CheckCondition(i == 1);
-    rocksdb_iter_get_error(iter, &err);
-    CheckNoError(err);
-    rocksdb_iter_destroy(iter);
-
     rocksdb_drop_column_family(db, handles[1], &err);
     CheckNoError(err);
     for (i = 0; i < 2; i++) {
@@ -971,7 +786,6 @@ int main(int argc, char** argv) {
     rocksdb_options_set_prefix_extractor(options, rocksdb_slicetransform_create_fixed_prefix(3));
     rocksdb_options_set_hash_skip_list_rep(options, 5000, 4, 4);
     rocksdb_options_set_plain_table_factory(options, 4, 10, 0.75, 16);
-    rocksdb_options_set_allow_concurrent_memtable_write(options, 0);
 
     db = rocksdb_open(options, dbname, &err);
     CheckNoError(err);
@@ -1006,19 +820,6 @@ int main(int argc, char** argv) {
     CheckNoError(err);
     rocksdb_iter_destroy(iter);
 
-    rocksdb_readoptions_set_total_order_seek(roptions, 1);
-    iter = rocksdb_create_iterator(db, roptions);
-    CheckCondition(!rocksdb_iter_valid(iter));
-
-    rocksdb_iter_seek(iter, "ba", 2);
-    rocksdb_iter_get_error(iter, &err);
-    CheckNoError(err);
-    CheckCondition(rocksdb_iter_valid(iter));
-    CheckIter(iter, "bar1", "bar");
-
-    rocksdb_iter_destroy(iter);
-    rocksdb_readoptions_set_total_order_seek(roptions, 0);
-
     rocksdb_close(db);
     rocksdb_destroy_db(options, dbname, &err);
   }
@@ -1100,35 +901,12 @@ int main(int argc, char** argv) {
     }
   }
 
-  // Simple sanity check that setting memtable rep works.
-  StartPhase("memtable_reps");
-  {
-    // Create database with vector memtable.
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_options_set_memtable_vector_rep(options);
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-
-    // Create database with hash skiplist memtable.
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_options_set_hash_skip_list_rep(options, 5000, 4, 4);
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-  }
-
   StartPhase("cleanup");
   rocksdb_close(db);
   rocksdb_options_destroy(options);
   rocksdb_block_based_options_destroy(table_options);
   rocksdb_readoptions_destroy(roptions);
   rocksdb_writeoptions_destroy(woptions);
-  rocksdb_compactoptions_destroy(coptions);
   rocksdb_cache_destroy(cache);
   rocksdb_comparator_destroy(cmp);
   rocksdb_env_destroy(env);
@@ -1138,6 +916,7 @@ int main(int argc, char** argv) {
 }
 
 #else
+#include <stdio.h>
 
 int main() {
   fprintf(stderr, "SKIPPED\n");

db/column_family.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -26,12 +26,13 @@
 #include "db/table_properties_collector.h"
 #include "db/version_set.h"
 #include "db/write_controller.h"
+#include "db/writebuffer.h"
 #include "memtable/hash_skiplist_rep.h"
-#include "table/block_based_table_factory.h"
 #include "util/autovector.h"
 #include "util/compression.h"
 #include "util/options_helper.h"
 #include "util/thread_status_util.h"
+#include "util/xfunc.h"
 
 namespace rocksdb {
 
@@ -45,11 +46,6 @@ ColumnFamilyHandleImpl::ColumnFamilyHandleImpl(
 
 ColumnFamilyHandleImpl::~ColumnFamilyHandleImpl() {
   if (cfd_ != nullptr) {
-#ifndef ROCKSDB_LITE
-    for (auto& listener : cfd_->ioptions()->listeners) {
-      listener->OnColumnFamilyHandleDeletionStarted(this);
-    }
-#endif  // ROCKSDB_LITE
     // Job id == 0 means that this is not our background process, but rather
     // user thread
     JobContext job_context(0);
@@ -76,23 +72,26 @@ Status ColumnFamilyHandleImpl::GetDescriptor(ColumnFamilyDescriptor* desc) {
 #ifndef ROCKSDB_LITE
   // accessing mutable cf-options requires db mutex.
   InstrumentedMutexLock l(mutex_);
-  *desc = ColumnFamilyDescriptor(cfd()->GetName(), cfd()->GetLatestCFOptions());
+  *desc = ColumnFamilyDescriptor(
+      cfd()->GetName(),
+      BuildColumnFamilyOptions(*cfd()->options(),
+                               *cfd()->GetLatestMutableCFOptions()));
   return Status::OK();
 #else
   return Status::NotSupported();
 #endif  // !ROCKSDB_LITE
 }
 
-const Comparator* ColumnFamilyHandleImpl::GetComparator() const {
+const Comparator* ColumnFamilyHandleImpl::user_comparator() const {
   return cfd()->user_comparator();
 }
 
 void GetIntTblPropCollectorFactory(
-    const ImmutableCFOptions& ioptions,
+    const ColumnFamilyOptions& cf_options,
     std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories) {
-  auto& collector_factories = ioptions.table_properties_collector_factories;
-  for (size_t i = 0; i < ioptions.table_properties_collector_factories.size();
+  auto& collector_factories = cf_options.table_properties_collector_factories;
+  for (size_t i = 0; i < cf_options.table_properties_collector_factories.size();
        ++i) {
     assert(collector_factories[i]);
     int_tbl_prop_collector_factories->emplace_back(
@@ -131,6 +130,11 @@ Status CheckConcurrentWritesSupported(const ColumnFamilyOptions& cf_options) {
         "In-place memtable updates (inplace_update_support) is not compatible "
         "with concurrent writes (allow_concurrent_memtable_write)");
   }
+  if (cf_options.filter_deletes) {
+    return Status::InvalidArgument(
+        "Delete filtering (filter_deletes) is not compatible with concurrent "
+        "memtable writes (allow_concurrent_memtable_writes)");
+  }
   if (!cf_options.memtable_factory->IsInsertConcurrentlySupported()) {
     return Status::InvalidArgument(
         "Memtable doesn't concurrent writes (allow_concurrent_memtable_write)");
@@ -138,13 +142,18 @@ Status CheckConcurrentWritesSupported(const ColumnFamilyOptions& cf_options) {
   return Status::OK();
 }
 
-ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
+ColumnFamilyOptions SanitizeOptions(const DBOptions& db_options,
+                                    const InternalKeyComparator* icmp,
                                     const ColumnFamilyOptions& src) {
   ColumnFamilyOptions result = src;
-  size_t clamp_max = std::conditional<
-      sizeof(size_t) == 4, std::integral_constant<size_t, 0xffffffff>,
-      std::integral_constant<uint64_t, 64ull << 30>>::type::value;
-  ClipToRange(&result.write_buffer_size, ((size_t)64) << 10, clamp_max);
+  result.comparator = icmp;
+#ifdef OS_MACOSX
+  // TODO(icanadi) make write_buffer_size uint64_t instead of size_t
+  ClipToRange(&result.write_buffer_size, ((size_t)64) << 10, ((size_t)1) << 30);
+#else
+  ClipToRange(&result.write_buffer_size,
+              ((size_t)64) << 10, ((size_t)64) << 30);
+#endif
   // if user sets arena_block_size, we trust user to use this value. Otherwise,
   // calculate a proper value from writer_buffer_size;
   if (result.arena_block_size <= 0) {
@@ -158,10 +167,6 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
   result.min_write_buffer_number_to_merge =
       std::min(result.min_write_buffer_number_to_merge,
                result.max_write_buffer_number - 1);
-  if (result.min_write_buffer_number_to_merge < 1) {
-    result.min_write_buffer_number_to_merge = 1;
-  }
-
   if (result.num_levels < 1) {
     result.num_levels = 1;
   }
@@ -175,12 +180,14 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
   if (result.max_write_buffer_number_to_maintain < 0) {
     result.max_write_buffer_number_to_maintain = result.max_write_buffer_number;
   }
-  // bloom filter size shouldn't exceed 1/4 of memtable size.
-  if (result.memtable_prefix_bloom_size_ratio > 0.25) {
-    result.memtable_prefix_bloom_size_ratio = 0.25;
-  } else if (result.memtable_prefix_bloom_size_ratio < 0) {
-    result.memtable_prefix_bloom_size_ratio = 0;
-  }
+  XFUNC_TEST("memtablelist_history", "transaction_xftest_SanitizeOptions",
+             xf_transaction_set_memtable_history1,
+             xf_transaction_set_memtable_history,
+             &result.max_write_buffer_number_to_maintain);
+  XFUNC_TEST("memtablelist_history_clear", "transaction_xftest_SanitizeOptions",
+             xf_transaction_clear_memtable_history1,
+             xf_transaction_clear_memtable_history,
+             &result.max_write_buffer_number_to_maintain);
 
   if (!result.prefix_extractor) {
     assert(result.memtable_factory);
@@ -200,10 +207,6 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
     result.level0_stop_writes_trigger = std::numeric_limits<int>::max();
   }
 
-  if (result.max_bytes_for_level_multiplier <= 0) {
-    result.max_bytes_for_level_multiplier = 1;
-  }
-
   if (result.level0_file_num_compaction_trigger == 0) {
     Warn(db_options.info_log.get(),
          "level0_file_num_compaction_trigger cannot be 0");
@@ -240,17 +243,6 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
          result.level0_slowdown_writes_trigger,
          result.level0_file_num_compaction_trigger);
   }
-
-  if (result.soft_pending_compaction_bytes_limit == 0) {
-    result.soft_pending_compaction_bytes_limit =
-        result.hard_pending_compaction_bytes_limit;
-  } else if (result.hard_pending_compaction_bytes_limit > 0 &&
-             result.soft_pending_compaction_bytes_limit >
-                 result.hard_pending_compaction_bytes_limit) {
-    result.soft_pending_compaction_bytes_limit =
-        result.hard_pending_compaction_bytes_limit;
-  }
-
   if (result.level_compaction_dynamic_level_bytes) {
     if (result.compaction_style != kCompactionStyleLevel ||
         db_options.db_paths.size() > 1U) {
@@ -262,10 +254,6 @@ ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
     }
   }
 
-  if (result.max_compaction_bytes == 0) {
-    result.max_compaction_bytes = result.target_file_size_base * 25;
-  }
-
   return result;
 }
 
@@ -333,8 +321,8 @@ void SuperVersionUnrefHandle(void* ptr) {
 
 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,
+    Cache* _table_cache, WriteBuffer* write_buffer,
+    const ColumnFamilyOptions& cf_options, const DBOptions* db_options,
     const EnvOptions& env_options, ColumnFamilySet* column_family_set)
     : id_(id),
       name_(name),
@@ -343,15 +331,14 @@ ColumnFamilyData::ColumnFamilyData(
       refs_(0),
       dropped_(false),
       internal_comparator_(cf_options.comparator),
-      initial_cf_options_(SanitizeOptions(db_options, cf_options)),
-      ioptions_(db_options, initial_cf_options_),
-      mutable_cf_options_(initial_cf_options_),
-      is_delete_range_supported_(strcmp(cf_options.table_factory->Name(),
-                                        BlockBasedTableFactory().Name()) == 0),
-      write_buffer_manager_(write_buffer_manager),
+      options_(*db_options,
+               SanitizeOptions(*db_options, &internal_comparator_, cf_options)),
+      ioptions_(options_),
+      mutable_cf_options_(options_, ioptions_),
+      write_buffer_(write_buffer),
       mem_(nullptr),
-      imm_(ioptions_.min_write_buffer_number_to_merge,
-           ioptions_.max_write_buffer_number_to_maintain),
+      imm_(options_.min_write_buffer_number_to_merge,
+           options_.max_write_buffer_number_to_maintain),
       super_version_(nullptr),
       super_version_number_(0),
       local_sv_(new ThreadLocalPtr(&SuperVersionUnrefHandle)),
@@ -361,17 +348,16 @@ ColumnFamilyData::ColumnFamilyData(
       column_family_set_(column_family_set),
       pending_flush_(false),
       pending_compaction_(false),
-      prev_compaction_needed_bytes_(0),
-      allow_2pc_(db_options.allow_2pc) {
+      prev_compaction_needed_bytes_(0) {
   Ref();
 
   // Convert user defined table properties collector factories to internal ones.
-  GetIntTblPropCollectorFactory(ioptions_, &int_tbl_prop_collector_factories_);
+  GetIntTblPropCollectorFactory(options_, &int_tbl_prop_collector_factories_);
 
   // if _dummy_versions is nullptr, then this is a dummy column family.
   if (_dummy_versions != nullptr) {
     internal_stats_.reset(
-        new InternalStats(ioptions_.num_levels, db_options.env, this));
+        new InternalStats(ioptions_.num_levels, db_options->env, this));
     table_cache_.reset(new TableCache(ioptions_, env_options, _table_cache));
     if (ioptions_.compaction_style == kCompactionStyleLevel) {
       compaction_picker_.reset(
@@ -403,7 +389,7 @@ ColumnFamilyData::ColumnFamilyData(
     if (column_family_set_->NumberOfColumnFamilies() < 10) {
       Log(InfoLogLevel::INFO_LEVEL, ioptions_.info_log,
           "--------------- Options for column family [%s]:\n", name.c_str());
-      initial_cf_options_.Dump(ioptions_.info_log);
+      options_.DumpCFOptions(ioptions_.info_log);
     } else {
       Log(InfoLogLevel::INFO_LEVEL, ioptions_.info_log,
           "\t(skipping printing options)\n");
@@ -480,43 +466,15 @@ void ColumnFamilyData::SetDropped() {
   column_family_set_->RemoveColumnFamily(this);
 }
 
-ColumnFamilyOptions ColumnFamilyData::GetLatestCFOptions() const {
-  return BuildColumnFamilyOptions(initial_cf_options_, mutable_cf_options_);
-}
-
-uint64_t ColumnFamilyData::OldestLogToKeep() {
-  auto current_log = GetLogNumber();
-
-  if (allow_2pc_) {
-    auto imm_prep_log = imm()->GetMinLogContainingPrepSection();
-    auto mem_prep_log = mem()->GetMinLogContainingPrepSection();
-
-    if (imm_prep_log > 0 && imm_prep_log < current_log) {
-      current_log = imm_prep_log;
-    }
-
-    if (mem_prep_log > 0 && mem_prep_log < current_log) {
-      current_log = mem_prep_log;
-    }
-  }
-
-  return current_log;
-}
-
-const double kIncSlowdownRatio = 0.8;
-const double kDecSlowdownRatio = 1 / kIncSlowdownRatio;
-const double kNearStopSlowdownRatio = 0.6;
-const double kDelayRecoverSlowdownRatio = 1.4;
+const double kSlowdownRatio = 1.2;
 
 namespace {
-// If penalize_stop is true, we further reduce slowdown rate.
 std::unique_ptr<WriteControllerToken> SetupDelay(
-    WriteController* write_controller, uint64_t compaction_needed_bytes,
-    uint64_t prev_compaction_need_bytes, bool penalize_stop,
+    uint64_t max_write_rate, WriteController* write_controller,
+    uint64_t compaction_needed_bytes, uint64_t prev_compaction_neeed_bytes,
     bool auto_comapctions_disabled) {
-  const uint64_t kMinWriteRate = 16 * 1024u;  // Minimum write rate 16KB/s.
+  const uint64_t kMinWriteRate = 1024u;  // Minimum write rate 1KB/s.
 
-  uint64_t max_write_rate = write_controller->max_delayed_write_rate();
   uint64_t write_rate = write_controller->delayed_write_rate();
 
   if (auto_comapctions_disabled) {
@@ -539,32 +497,19 @@ std::unique_ptr<WriteControllerToken> SetupDelay(
     // insert to mem tables, so we need to actively slow down before we get
     // feedback signal from compaction and flushes to avoid the full stop
     // because of hitting the max write buffer number.
-    //
-    // If DB just falled into the stop condition, we need to further reduce
-    // the write rate to avoid the stop condition.
-    if (penalize_stop) {
-      // Penalize the near stop or stop condition by more agressive slowdown.
-      // This is to provide the long term slowdown increase signal.
-      // The penalty is more than the reward of recovering to the normal
-      // condition.
-      write_rate = static_cast<uint64_t>(static_cast<double>(write_rate) *
-                                         kNearStopSlowdownRatio);
+    if (prev_compaction_neeed_bytes > 0 &&
+        prev_compaction_neeed_bytes <= compaction_needed_bytes) {
+      write_rate = static_cast<uint64_t>(static_cast<double>(write_rate) /
+                                         kSlowdownRatio);
       if (write_rate < kMinWriteRate) {
         write_rate = kMinWriteRate;
       }
-    } else if (prev_compaction_need_bytes > 0 &&
-               prev_compaction_need_bytes <= compaction_needed_bytes) {
-      write_rate = static_cast<uint64_t>(static_cast<double>(write_rate) *
-                                         kIncSlowdownRatio);
-      if (write_rate < kMinWriteRate) {
-        write_rate = kMinWriteRate;
-      }
-    } else if (prev_compaction_need_bytes > compaction_needed_bytes) {
+    } else if (prev_compaction_neeed_bytes > compaction_needed_bytes) {
       // We are speeding up by ratio of kSlowdownRatio when we have paid
       // compaction debt. But we'll never speed up to faster than the write rate
       // given by users.
       write_rate = static_cast<uint64_t>(static_cast<double>(write_rate) *
-                                         kDecSlowdownRatio);
+                                         kSlowdownRatio);
       if (write_rate > max_write_rate) {
         write_rate = max_write_rate;
       }
@@ -572,38 +517,6 @@ std::unique_ptr<WriteControllerToken> SetupDelay(
   }
   return write_controller->GetDelayToken(write_rate);
 }
-
-int GetL0ThresholdSpeedupCompaction(int level0_file_num_compaction_trigger,
-                                    int level0_slowdown_writes_trigger) {
-  // SanitizeOptions() ensures it.
-  assert(level0_file_num_compaction_trigger <= level0_slowdown_writes_trigger);
-
-  if (level0_file_num_compaction_trigger < 0) {
-    return std::numeric_limits<int>::max();
-  }
-
-  const int64_t twice_level0_trigger =
-      static_cast<int64_t>(level0_file_num_compaction_trigger) * 2;
-
-  const int64_t one_fourth_trigger_slowdown =
-      static_cast<int64_t>(level0_file_num_compaction_trigger) +
-      ((level0_slowdown_writes_trigger - level0_file_num_compaction_trigger) /
-       4);
-
-  assert(twice_level0_trigger >= 0);
-  assert(one_fourth_trigger_slowdown >= 0);
-
-  // 1/4 of the way between L0 compaction trigger threshold and slowdown
-  // condition.
-  // Or twice as compaction trigger, if it is smaller.
-  int64_t res = std::min(twice_level0_trigger, one_fourth_trigger_slowdown);
-  if (res >= port::kMaxInt32) {
-    return port::kMaxInt32;
-  } else {
-    // res fits in int
-    return static_cast<int>(res);
-  }
-}
 }  // namespace
 
 void ColumnFamilyData::RecalculateWriteStallConditions(
@@ -614,9 +527,6 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
     uint64_t compaction_needed_bytes =
         vstorage->estimated_compaction_needed_bytes();
 
-    bool was_stopped = write_controller->IsStopped();
-    bool needed_delay = write_controller->NeedsDelay();
-
     if (imm()->NumNotFlushed() >= mutable_cf_options.max_write_buffer_number) {
       write_controller_token_ = write_controller->GetStopToken();
       internal_stats_->AddCFStats(InternalStats::MEMTABLE_COMPACTION, 1);
@@ -625,35 +535,12 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
           "(waiting for flush), max_write_buffer_number is set to %d",
           name_.c_str(), imm()->NumNotFlushed(),
           mutable_cf_options.max_write_buffer_number);
-    } else if (!mutable_cf_options.disable_auto_compactions &&
-               vstorage->l0_delay_trigger_count() >=
-                   mutable_cf_options.level0_stop_writes_trigger) {
-      write_controller_token_ = write_controller->GetStopToken();
-      internal_stats_->AddCFStats(InternalStats::LEVEL0_NUM_FILES_TOTAL, 1);
-      if (compaction_picker_->IsLevel0CompactionInProgress()) {
-        internal_stats_->AddCFStats(
-            InternalStats::LEVEL0_NUM_FILES_WITH_COMPACTION, 1);
-      }
-      Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
-          "[%s] Stopping writes because we have %d level-0 files",
-          name_.c_str(), vstorage->l0_delay_trigger_count());
-    } else if (!mutable_cf_options.disable_auto_compactions &&
-               mutable_cf_options.hard_pending_compaction_bytes_limit > 0 &&
-               compaction_needed_bytes >=
-                   mutable_cf_options.hard_pending_compaction_bytes_limit) {
-      write_controller_token_ = write_controller->GetStopToken();
-      internal_stats_->AddCFStats(
-          InternalStats::HARD_PENDING_COMPACTION_BYTES_LIMIT, 1);
-      Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
-          "[%s] Stopping writes because of estimated pending compaction "
-          "bytes %" PRIu64,
-          name_.c_str(), compaction_needed_bytes);
     } else if (mutable_cf_options.max_write_buffer_number > 3 &&
                imm()->NumNotFlushed() >=
                    mutable_cf_options.max_write_buffer_number - 1) {
       write_controller_token_ =
-          SetupDelay(write_controller, compaction_needed_bytes,
-                     prev_compaction_needed_bytes_, was_stopped,
+          SetupDelay(ioptions_.delayed_write_rate, write_controller,
+                     compaction_needed_bytes, prev_compaction_needed_bytes_,
                      mutable_cf_options.disable_auto_compactions);
       internal_stats_->AddCFStats(InternalStats::MEMTABLE_SLOWDOWN, 1);
       Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
@@ -663,16 +550,33 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
           name_.c_str(), imm()->NumNotFlushed(),
           mutable_cf_options.max_write_buffer_number,
           write_controller->delayed_write_rate());
-    } else if (!mutable_cf_options.disable_auto_compactions &&
-               mutable_cf_options.level0_slowdown_writes_trigger >= 0 &&
+    } else if (vstorage->l0_delay_trigger_count() >=
+               mutable_cf_options.level0_stop_writes_trigger) {
+      write_controller_token_ = write_controller->GetStopToken();
+      internal_stats_->AddCFStats(InternalStats::LEVEL0_NUM_FILES_TOTAL, 1);
+      if (compaction_picker_->IsLevel0CompactionInProgress()) {
+        internal_stats_->AddCFStats(
+            InternalStats::LEVEL0_NUM_FILES_WITH_COMPACTION, 1);
+      }
+      Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
+          "[%s] Stopping writes because we have %d level-0 files",
+          name_.c_str(), vstorage->l0_delay_trigger_count());
+    } else if (mutable_cf_options.hard_pending_compaction_bytes_limit > 0 &&
+               compaction_needed_bytes >=
+                   mutable_cf_options.hard_pending_compaction_bytes_limit) {
+      write_controller_token_ = write_controller->GetStopToken();
+      internal_stats_->AddCFStats(
+          InternalStats::HARD_PENDING_COMPACTION_BYTES_LIMIT, 1);
+      Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
+          "[%s] Stopping writes because of estimated pending compaction "
+          "bytes %" PRIu64,
+          name_.c_str(), compaction_needed_bytes);
+    } else if (mutable_cf_options.level0_slowdown_writes_trigger >= 0 &&
                vstorage->l0_delay_trigger_count() >=
                    mutable_cf_options.level0_slowdown_writes_trigger) {
-      // L0 is the last two files from stopping.
-      bool near_stop = vstorage->l0_delay_trigger_count() >=
-                       mutable_cf_options.level0_stop_writes_trigger - 2;
       write_controller_token_ =
-          SetupDelay(write_controller, compaction_needed_bytes,
-                     prev_compaction_needed_bytes_, was_stopped || near_stop,
+          SetupDelay(ioptions_.delayed_write_rate, write_controller,
+                     compaction_needed_bytes, prev_compaction_needed_bytes_,
                      mutable_cf_options.disable_auto_compactions);
       internal_stats_->AddCFStats(InternalStats::LEVEL0_SLOWDOWN_TOTAL, 1);
       if (compaction_picker_->IsLevel0CompactionInProgress()) {
@@ -684,24 +588,12 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
           "rate %" PRIu64,
           name_.c_str(), vstorage->l0_delay_trigger_count(),
           write_controller->delayed_write_rate());
-    } else if (!mutable_cf_options.disable_auto_compactions &&
-               mutable_cf_options.soft_pending_compaction_bytes_limit > 0 &&
+    } else if (mutable_cf_options.soft_pending_compaction_bytes_limit > 0 &&
                vstorage->estimated_compaction_needed_bytes() >=
                    mutable_cf_options.soft_pending_compaction_bytes_limit) {
-      // If the distance to hard limit is less than 1/4 of the gap between soft
-      // and
-      // hard bytes limit, we think it is near stop and speed up the slowdown.
-      bool near_stop =
-          mutable_cf_options.hard_pending_compaction_bytes_limit > 0 &&
-          (compaction_needed_bytes -
-           mutable_cf_options.soft_pending_compaction_bytes_limit) >
-              3 * (mutable_cf_options.hard_pending_compaction_bytes_limit -
-                   mutable_cf_options.soft_pending_compaction_bytes_limit) /
-                  4;
-
       write_controller_token_ =
-          SetupDelay(write_controller, compaction_needed_bytes,
-                     prev_compaction_needed_bytes_, was_stopped || near_stop,
+          SetupDelay(ioptions_.delayed_write_rate, write_controller,
+                     compaction_needed_bytes, prev_compaction_needed_bytes_,
                      mutable_cf_options.disable_auto_compactions);
       internal_stats_->AddCFStats(
           InternalStats::SOFT_PENDING_COMPACTION_BYTES_LIMIT, 1);
@@ -711,42 +603,7 @@ void ColumnFamilyData::RecalculateWriteStallConditions(
           name_.c_str(), vstorage->estimated_compaction_needed_bytes(),
           write_controller->delayed_write_rate());
     } else {
-      if (vstorage->l0_delay_trigger_count() >=
-          GetL0ThresholdSpeedupCompaction(
-              mutable_cf_options.level0_file_num_compaction_trigger,
-              mutable_cf_options.level0_slowdown_writes_trigger)) {
-        write_controller_token_ =
-            write_controller->GetCompactionPressureToken();
-        Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
-            "[%s] Increasing compaction threads because we have %d level-0 "
-            "files ",
-            name_.c_str(), vstorage->l0_delay_trigger_count());
-      } else if (vstorage->estimated_compaction_needed_bytes() >=
-                 mutable_cf_options.soft_pending_compaction_bytes_limit / 4) {
-        // Increase compaction threads if bytes needed for compaction exceeds
-        // 1/4 of threshold for slowing down.
-        // If soft pending compaction byte limit is not set, always speed up
-        // compaction.
-        write_controller_token_ =
-            write_controller->GetCompactionPressureToken();
-        if (mutable_cf_options.soft_pending_compaction_bytes_limit > 0) {
-          Log(InfoLogLevel::WARN_LEVEL, ioptions_.info_log,
-              "[%s] Increasing compaction threads because of estimated pending "
-              "compaction "
-              "bytes %" PRIu64,
-              name_.c_str(), vstorage->estimated_compaction_needed_bytes());
-        }
-      } else {
-        write_controller_token_.reset();
-      }
-      // If the DB recovers from delay conditions, we reward with reducing
-      // double the slowdown ratio. This is to balance the long term slowdown
-      // increase signal.
-      if (needed_delay) {
-        uint64_t write_rate = write_controller->delayed_write_rate();
-        write_controller->set_delayed_write_rate(static_cast<uint64_t>(
-            static_cast<double>(write_rate) * kDelayRecoverSlowdownRatio));
-      }
+      write_controller_token_.reset();
     }
     prev_compaction_needed_bytes_ = compaction_needed_bytes;
   }
@@ -772,7 +629,7 @@ MemTable* ColumnFamilyData::ConstructNewMemtable(
     const MutableCFOptions& mutable_cf_options, SequenceNumber earliest_seq) {
   assert(current_ != nullptr);
   return new MemTable(internal_comparator_, ioptions_, mutable_cf_options,
-                      write_buffer_manager_, earliest_seq);
+                      write_buffer_, earliest_seq);
 }
 
 void ColumnFamilyData::CreateNewMemtable(
@@ -798,13 +655,6 @@ Compaction* ColumnFamilyData::PickCompaction(
   return result;
 }
 
-bool ColumnFamilyData::RangeOverlapWithCompaction(
-    const Slice& smallest_user_key, const Slice& largest_user_key,
-    int level) const {
-  return compaction_picker_->RangeOverlapWithCompaction(
-      smallest_user_key, largest_user_key, level);
-}
-
 const int ColumnFamilyData::kCompactAllLevels = -1;
 const int ColumnFamilyData::kCompactToBaseLevel = -2;
 
@@ -955,21 +805,21 @@ Status ColumnFamilyData::SetOptions(
 #endif  // ROCKSDB_LITE
 
 ColumnFamilySet::ColumnFamilySet(const std::string& dbname,
-                                 const ImmutableDBOptions* db_options,
+                                 const DBOptions* db_options,
                                  const EnvOptions& env_options,
                                  Cache* table_cache,
-                                 WriteBufferManager* write_buffer_manager,
+                                 WriteBuffer* write_buffer,
                                  WriteController* write_controller)
     : max_column_family_(0),
       dummy_cfd_(new ColumnFamilyData(0, "", nullptr, nullptr, nullptr,
-                                      ColumnFamilyOptions(), *db_options,
+                                      ColumnFamilyOptions(), db_options,
                                       env_options, nullptr)),
       default_cfd_cache_(nullptr),
       db_name_(dbname),
       db_options_(db_options),
       env_options_(env_options),
       table_cache_(table_cache),
-      write_buffer_manager_(write_buffer_manager),
+      write_buffer_(write_buffer),
       write_controller_(write_controller) {
   // initialize linked list
   dummy_cfd_->prev_ = dummy_cfd_;
@@ -1032,9 +882,10 @@ ColumnFamilyData* ColumnFamilySet::CreateColumnFamily(
     const std::string& name, uint32_t id, Version* dummy_versions,
     const ColumnFamilyOptions& options) {
   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_, env_options_, this);
+  ColumnFamilyData* new_cfd =
+      new ColumnFamilyData(id, name, dummy_versions, table_cache_,
+                           write_buffer_, options, db_options_,
+                           env_options_, this);
   column_families_.insert({name, id});
   column_family_data_.insert({id, new_cfd});
   max_column_family_ = std::max(max_column_family_, id);
@@ -1111,7 +962,8 @@ uint32_t GetColumnFamilyID(ColumnFamilyHandle* column_family) {
 const Comparator* GetColumnFamilyUserComparator(
     ColumnFamilyHandle* column_family) {
   if (column_family != nullptr) {
-    return column_family->GetComparator();
+    auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
+    return cfh->user_comparator();
   }
   return nullptr;
 }

db/column_family.h

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -15,15 +15,15 @@
 #include <atomic>
 
 #include "db/memtable_list.h"
-#include "db/table_cache.h"
-#include "db/table_properties_collector.h"
 #include "db/write_batch_internal.h"
 #include "db/write_controller.h"
+#include "db/table_cache.h"
+#include "db/table_properties_collector.h"
 #include "rocksdb/compaction_job_stats.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
-#include "util/cf_options.h"
+#include "util/mutable_cf_options.h"
 #include "util/thread_local.h"
 
 namespace rocksdb {
@@ -42,7 +42,7 @@ class LogBuffer;
 class InstrumentedMutex;
 class InstrumentedMutexLock;
 
-extern const double kIncSlowdownRatio;
+extern const double kSlowdownRatio;
 
 // ColumnFamilyHandleImpl is the class that clients use to access different
 // column families. It has non-trivial destructor, which gets called when client
@@ -55,11 +55,11 @@ class ColumnFamilyHandleImpl : public ColumnFamilyHandle {
   // destroy without mutex
   virtual ~ColumnFamilyHandleImpl();
   virtual ColumnFamilyData* cfd() const { return cfd_; }
+  virtual const Comparator* user_comparator() const;
 
   virtual uint32_t GetID() const override;
   virtual const std::string& GetName() const override;
   virtual Status GetDescriptor(ColumnFamilyDescriptor* desc) override;
-  virtual const Comparator* GetComparator() const override;
 
  private:
   ColumnFamilyData* cfd_;
@@ -136,13 +136,14 @@ extern Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options);
 extern Status CheckConcurrentWritesSupported(
     const ColumnFamilyOptions& cf_options);
 
-extern ColumnFamilyOptions SanitizeOptions(const ImmutableDBOptions& db_options,
+extern ColumnFamilyOptions SanitizeOptions(const DBOptions& db_options,
+                                           const InternalKeyComparator* icmp,
                                            const ColumnFamilyOptions& src);
 // Wrap user defined table proproties collector factories `from cf_options`
 // into internal ones in int_tbl_prop_collector_factories. Add a system internal
 // one too.
 extern void GetIntTblPropCollectorFactory(
-    const ImmutableCFOptions& ioptions,
+    const ColumnFamilyOptions& cf_options,
     std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
         int_tbl_prop_collector_factories);
 
@@ -200,12 +201,15 @@ class ColumnFamilyData {
   void SetLogNumber(uint64_t log_number) { log_number_ = log_number; }
   uint64_t GetLogNumber() const { return log_number_; }
 
+  // !!! To be deprecated! Please don't not use this function anymore!
+  const Options* options() const { return &options_; }
+
   // thread-safe
   const EnvOptions* soptions() const;
   const ImmutableCFOptions* ioptions() const { return &ioptions_; }
   // REQUIRES: DB mutex held
   // This returns the MutableCFOptions used by current SuperVersion
-  // You should use this API to reference MutableCFOptions most of the time.
+  // You shoul use this API to reference MutableCFOptions most of the time.
   const MutableCFOptions* GetCurrentMutableCFOptions() const {
     return &(super_version_->mutable_cf_options);
   }
@@ -214,14 +218,6 @@ class ColumnFamilyData {
   const MutableCFOptions* GetLatestMutableCFOptions() const {
     return &mutable_cf_options_;
   }
-
-  // REQUIRES: DB mutex held
-  // Build ColumnFamiliesOptions with immutable options and latest mutable
-  // options.
-  ColumnFamilyOptions GetLatestCFOptions() const;
-
-  bool is_delete_range_supported() { return is_delete_range_supported_; }
-
 #ifndef ROCKSDB_LITE
   // REQUIRES: DB mutex held
   Status SetOptions(
@@ -239,9 +235,6 @@ class ColumnFamilyData {
   uint64_t GetTotalSstFilesSize() const;  // REQUIRE: DB mutex held
   void SetMemtable(MemTable* new_mem) { mem_ = new_mem; }
 
-  // calculate the oldest log needed for the durability of this column family
-  uint64_t OldestLogToKeep();
-
   // See Memtable constructor for explanation of earliest_seq param.
   MemTable* ConstructNewMemtable(const MutableCFOptions& mutable_cf_options,
                                  SequenceNumber earliest_seq);
@@ -256,13 +249,6 @@ class ColumnFamilyData {
   // REQUIRES: DB mutex held
   Compaction* PickCompaction(const MutableCFOptions& mutable_options,
                              LogBuffer* log_buffer);
-
-  // Check if the passed range overlap with any running compactions.
-  // REQUIRES: DB mutex held
-  bool RangeOverlapWithCompaction(const Slice& smallest_user_key,
-                                  const Slice& largest_user_key,
-                                  int level) const;
-
   // A flag to tell a manual compaction is to compact all levels together
   // instad of for specific level.
   static const int kCompactAllLevels;
@@ -337,10 +323,9 @@ class ColumnFamilyData {
   friend class ColumnFamilySet;
   ColumnFamilyData(uint32_t id, const std::string& name,
                    Version* dummy_versions, Cache* table_cache,
-                   WriteBufferManager* write_buffer_manager,
+                   WriteBuffer* write_buffer,
                    const ColumnFamilyOptions& options,
-                   const ImmutableDBOptions& db_options,
-                   const EnvOptions& env_options,
+                   const DBOptions* db_options, const EnvOptions& env_options,
                    ColumnFamilySet* column_family_set);
 
   uint32_t id_;
@@ -355,17 +340,15 @@ class ColumnFamilyData {
   std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
       int_tbl_prop_collector_factories_;
 
-  const ColumnFamilyOptions initial_cf_options_;
+  const Options options_;
   const ImmutableCFOptions ioptions_;
   MutableCFOptions mutable_cf_options_;
 
-  const bool is_delete_range_supported_;
-
   std::unique_ptr<TableCache> table_cache_;
 
   std::unique_ptr<InternalStats> internal_stats_;
 
-  WriteBufferManager* write_buffer_manager_;
+  WriteBuffer* write_buffer_;
 
   MemTable* mem_;
   MemTableList imm_;
@@ -407,9 +390,6 @@ class ColumnFamilyData {
   bool pending_compaction_;
 
   uint64_t prev_compaction_needed_bytes_;
-
-  // if the database was opened with 2pc enabled
-  bool allow_2pc_;
 };
 
 // ColumnFamilySet has interesting thread-safety requirements
@@ -456,11 +436,9 @@ class ColumnFamilySet {
     ColumnFamilyData* current_;
   };
 
-  ColumnFamilySet(const std::string& dbname,
-                  const ImmutableDBOptions* db_options,
+  ColumnFamilySet(const std::string& dbname, const DBOptions* db_options,
                   const EnvOptions& env_options, Cache* table_cache,
-                  WriteBufferManager* write_buffer_manager,
-                  WriteController* write_controller);
+                  WriteBuffer* write_buffer, WriteController* write_controller);
   ~ColumnFamilySet();
 
   ColumnFamilyData* GetDefault() const;
@@ -487,8 +465,6 @@ class ColumnFamilySet {
   // Don't call while iterating over ColumnFamilySet
   void FreeDeadColumnFamilies();
 
-  Cache* get_table_cache() { return table_cache_; }
-
  private:
   friend class ColumnFamilyData;
   // helper function that gets called from cfd destructor
@@ -514,10 +490,10 @@ class ColumnFamilySet {
   ColumnFamilyData* default_cfd_cache_;
 
   const std::string db_name_;
-  const ImmutableDBOptions* const db_options_;
+  const DBOptions* const db_options_;
   const EnvOptions env_options_;
   Cache* table_cache_;
-  WriteBufferManager* write_buffer_manager_;
+  WriteBuffer* write_buffer_;
   WriteController* write_controller_;
 };
 

db/compact_files_test.cc

@@ -1,17 +1,14 @@
-//  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) 2014, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 #ifndef ROCKSDB_LITE
 
 #include <mutex>
 #include <string>
-#include <thread>
 #include <vector>
 
-#include "db/db_impl.h"
-#include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "util/string_util.h"
@@ -51,10 +48,6 @@ class FlushedFileCollector : public EventListener {
     }
     return result;
   }
-  void ClearFlushedFiles() {
-    std::lock_guard<std::mutex> lock(mutex_);
-    flushed_files_.clear();
-  }
 
  private:
   std::vector<std::string> flushed_files_;
@@ -121,12 +114,13 @@ TEST_F(CompactFilesTest, L0ConflictsFiles) {
 TEST_F(CompactFilesTest, ObsoleteFiles) {
   Options options;
   // to trigger compaction more easily
-  const int kWriteBufferSize = 65536;
+  const int kWriteBufferSize = 10000;
   options.create_if_missing = true;
   // Disable RocksDB background compaction.
   options.compaction_style = kCompactionStyleNone;
-  options.level0_slowdown_writes_trigger = (1 << 30);
-  options.level0_stop_writes_trigger = (1 << 30);
+  // Small slowdown and stop trigger for experimental purpose.
+  options.level0_slowdown_writes_trigger = 20;
+  options.level0_stop_writes_trigger = 20;
   options.write_buffer_size = kWriteBufferSize;
   options.max_write_buffer_number = 2;
   options.compression = kNoCompression;
@@ -148,8 +142,10 @@ TEST_F(CompactFilesTest, ObsoleteFiles) {
   }
 
   auto l0_files = collector->GetFlushedFiles();
+  CompactionOptions compact_opt;
+  compact_opt.compression = kNoCompression;
+  compact_opt.output_file_size_limit = kWriteBufferSize * 5;
   ASSERT_OK(db->CompactFiles(CompactionOptions(), l0_files, 1));
-  reinterpret_cast<DBImpl*>(db)->TEST_WaitForCompact();
 
   // verify all compaction input files are deleted
   for (auto fname : l0_files) {
@@ -158,157 +154,6 @@ TEST_F(CompactFilesTest, ObsoleteFiles) {
   delete db;
 }
 
-TEST_F(CompactFilesTest, NotCutOutputOnLevel0) {
-  Options options;
-  options.create_if_missing = true;
-  // Disable RocksDB background compaction.
-  options.compaction_style = kCompactionStyleNone;
-  options.level0_slowdown_writes_trigger = 1000;
-  options.level0_stop_writes_trigger = 1000;
-  options.write_buffer_size = 65536;
-  options.max_write_buffer_number = 2;
-  options.compression = kNoCompression;
-  options.max_compaction_bytes = 5000;
-
-  // Add listener
-  FlushedFileCollector* collector = new FlushedFileCollector();
-  options.listeners.emplace_back(collector);
-
-  DB* db = nullptr;
-  DestroyDB(db_name_, options);
-  Status s = DB::Open(options, db_name_, &db);
-  assert(s.ok());
-  assert(db);
-
-  // create couple files
-  for (int i = 0; i < 500; ++i) {
-    db->Put(WriteOptions(), ToString(i), std::string(1000, 'a' + (i % 26)));
-  }
-  reinterpret_cast<DBImpl*>(db)->TEST_WaitForFlushMemTable();
-  auto l0_files_1 = collector->GetFlushedFiles();
-  collector->ClearFlushedFiles();
-  for (int i = 0; i < 500; ++i) {
-    db->Put(WriteOptions(), ToString(i), std::string(1000, 'a' + (i % 26)));
-  }
-  reinterpret_cast<DBImpl*>(db)->TEST_WaitForFlushMemTable();
-  auto l0_files_2 = collector->GetFlushedFiles();
-  ASSERT_OK(db->CompactFiles(CompactionOptions(), l0_files_1, 0));
-  ASSERT_OK(db->CompactFiles(CompactionOptions(), l0_files_2, 0));
-  // no assertion failure
-  delete db;
-}
-
-TEST_F(CompactFilesTest, CapturingPendingFiles) {
-  Options options;
-  options.create_if_missing = true;
-  // Disable RocksDB background compaction.
-  options.compaction_style = kCompactionStyleNone;
-  // Always do full scans for obsolete files (needed to reproduce the issue).
-  options.delete_obsolete_files_period_micros = 0;
-
-  // Add listener.
-  FlushedFileCollector* collector = new FlushedFileCollector();
-  options.listeners.emplace_back(collector);
-
-  DB* db = nullptr;
-  DestroyDB(db_name_, options);
-  Status s = DB::Open(options, db_name_, &db);
-  assert(s.ok());
-  assert(db);
-
-  // Create 5 files.
-  for (int i = 0; i < 5; ++i) {
-    db->Put(WriteOptions(), "key" + ToString(i), "value");
-    db->Flush(FlushOptions());
-  }
-
-  auto l0_files = collector->GetFlushedFiles();
-  EXPECT_EQ(5, l0_files.size());
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency({
-      {"CompactFilesImpl:2", "CompactFilesTest.CapturingPendingFiles:0"},
-      {"CompactFilesTest.CapturingPendingFiles:1", "CompactFilesImpl:3"},
-  });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  // Start compacting files.
-  rocksdb::port::Thread compaction_thread(
-      [&] { EXPECT_OK(db->CompactFiles(CompactionOptions(), l0_files, 1)); });
-
-  // In the meantime flush another file.
-  TEST_SYNC_POINT("CompactFilesTest.CapturingPendingFiles:0");
-  db->Put(WriteOptions(), "key5", "value");
-  db->Flush(FlushOptions());
-  TEST_SYNC_POINT("CompactFilesTest.CapturingPendingFiles:1");
-
-  compaction_thread.join();
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-
-  delete db;
-
-  // Make sure we can reopen the DB.
-  s = DB::Open(options, db_name_, &db);
-  ASSERT_TRUE(s.ok());
-  assert(db);
-  delete db;
-}
-
-TEST_F(CompactFilesTest, CompactionFilterWithGetSv) {
-  class FilterWithGet : public CompactionFilter {
-   public:
-    virtual bool Filter(int level, const Slice& key, const Slice& value,
-                        std::string* new_value,
-                        bool* value_changed) const override {
-      if (db_ == nullptr) {
-        return true;
-      }
-      std::string res;
-      db_->Get(ReadOptions(), "", &res);
-      return true;
-    }
-
-    void SetDB(DB* db) {
-      db_ = db;
-    }
-
-    virtual const char* Name() const override { return "FilterWithGet"; }
-
-   private:
-    DB* db_;
-  };
-
-
-  std::shared_ptr<FilterWithGet> cf(new FilterWithGet());
-
-  Options options;
-  options.create_if_missing = true;
-  options.compaction_filter = cf.get();
-
-  DB* db = nullptr;
-  DestroyDB(db_name_, options);
-  Status s = DB::Open(options, db_name_, &db);
-  ASSERT_OK(s);
-
-  cf->SetDB(db);
-
-  // Write one L0 file
-  db->Put(WriteOptions(), "K1", "V1");
-  db->Flush(FlushOptions());
-
-  // Compact all L0 files using CompactFiles
-  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::CompactionOptions(), {fname}, 0));
-  }
-
-
-  delete db;
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/compacted_db_impl.cc

@@ -1,7 +1,7 @@
-//  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) 2014, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 #ifndef ROCKSDB_LITE
 #include "db/compacted_db_impl.h"
@@ -46,7 +46,7 @@ Status CompactedDBImpl::Get(const ReadOptions& options,
      ColumnFamilyHandle*, const Slice& key, std::string* value) {
   GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                          GetContext::kNotFound, key, value, nullptr, nullptr,
-                         nullptr, nullptr);
+                         nullptr);
   LookupKey lkey(key, kMaxSequenceNumber);
   files_.files[FindFile(key)].fd.table_reader->Get(
       options, lkey.internal_key(), &get_context);
@@ -77,7 +77,7 @@ std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
     if (r != nullptr) {
       GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
                              GetContext::kNotFound, keys[idx], &(*values)[idx],
-                             nullptr, nullptr, nullptr, nullptr);
+                             nullptr, nullptr, nullptr);
       LookupKey lkey(keys[idx], kMaxSequenceNumber);
       r->Get(options, lkey.internal_key(), &get_context);
       if (get_context.State() == GetContext::kFound) {
@@ -93,7 +93,7 @@ Status CompactedDBImpl::Init(const Options& options) {
   mutex_.Lock();
   ColumnFamilyDescriptor cf(kDefaultColumnFamilyName,
                             ColumnFamilyOptions(options));
-  Status s = Recover({cf}, true /* read only */, false, true);
+  Status s = Recover({ cf }, true /* read only */, false);
   if (s.ok()) {
     cfd_ = reinterpret_cast<ColumnFamilyHandleImpl*>(
               DefaultColumnFamily())->cfd();
@@ -151,9 +151,9 @@ Status CompactedDBImpl::Open(const Options& options,
   std::unique_ptr<CompactedDBImpl> db(new CompactedDBImpl(db_options, dbname));
   Status s = db->Init(options);
   if (s.ok()) {
-    Log(INFO_LEVEL, db->immutable_db_options_.info_log,
+    Log(INFO_LEVEL, db->db_options_.info_log,
         "Opened the db as fully compacted mode");
-    LogFlush(db->immutable_db_options_.info_log);
+    LogFlush(db->db_options_.info_log);
     *dbptr = db.release();
   }
   return s;

db/compacted_db_impl.h

@@ -1,7 +1,7 @@
-//  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) 2014, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 #pragma once
 #ifndef ROCKSDB_LITE
@@ -76,13 +76,6 @@ class CompactedDBImpl : public DBImpl {
                        ColumnFamilyHandle* column_family) override {
     return Status::NotSupported("Not supported in compacted db mode.");
   }
-  using DB::IngestExternalFile;
-  virtual Status IngestExternalFile(
-      ColumnFamilyHandle* column_family,
-      const std::vector<std::string>& external_files,
-      const IngestExternalFileOptions& ingestion_options) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
 
  private:
   friend class DB;

db/compaction.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -16,8 +16,8 @@
 #include <inttypes.h>
 #include <vector>
 
-#include "db/column_family.h"
 #include "rocksdb/compaction_filter.h"
+#include "db/column_family.h"
 #include "util/logging.h"
 #include "util/sync_point.h"
 
@@ -140,22 +140,19 @@ bool Compaction::IsFullCompaction(
 }
 
 Compaction::Compaction(VersionStorageInfo* vstorage,
-                       const ImmutableCFOptions& _immutable_cf_options,
                        const MutableCFOptions& _mutable_cf_options,
                        std::vector<CompactionInputFiles> _inputs,
                        int _output_level, uint64_t _target_file_size,
-                       uint64_t _max_compaction_bytes, uint32_t _output_path_id,
-                       CompressionType _compression,
+                       uint64_t _max_grandparent_overlap_bytes,
+                       uint32_t _output_path_id, CompressionType _compression,
                        std::vector<FileMetaData*> _grandparents,
                        bool _manual_compaction, double _score,
                        bool _deletion_compaction,
                        CompactionReason _compaction_reason)
-    : input_vstorage_(vstorage),
-      start_level_(_inputs[0].level),
+    : start_level_(_inputs[0].level),
       output_level_(_output_level),
       max_output_file_size_(_target_file_size),
-      max_compaction_bytes_(_max_compaction_bytes),
-      immutable_cf_options_(_immutable_cf_options),
+      max_grandparent_overlap_bytes_(_max_grandparent_overlap_bytes),
       mutable_cf_options_(_mutable_cf_options),
       input_version_(nullptr),
       number_levels_(vstorage->num_levels()),
@@ -165,6 +162,9 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
       deletion_compaction_(_deletion_compaction),
       inputs_(std::move(_inputs)),
       grandparents_(std::move(_grandparents)),
+      grandparent_index_(0),
+      seen_key_(false),
+      overlapped_bytes_(0),
       score_(_score),
       bottommost_level_(IsBottommostLevel(output_level_, vstorage, inputs_)),
       is_full_compaction_(IsFullCompaction(vstorage, inputs_)),
@@ -190,7 +190,8 @@ Compaction::Compaction(VersionStorageInfo* vstorage,
     }
   }
 
-  GetBoundaryKeys(vstorage, inputs_, &smallest_user_key_, &largest_user_key_);
+  Slice smallest_user_key;
+  GetBoundaryKeys(vstorage, inputs_, &smallest_user_key, &largest_user_key_);
 }
 
 Compaction::~Compaction() {
@@ -205,9 +206,8 @@ Compaction::~Compaction() {
 }
 
 bool Compaction::InputCompressionMatchesOutput() const {
-  int base_level = input_vstorage_->base_level();
-  bool matches = (GetCompressionType(immutable_cf_options_, input_vstorage_,
-                                     mutable_cf_options_, start_level_,
+  int base_level = input_version_->storage_info()->base_level();
+  bool matches = (GetCompressionType(*cfd_->ioptions(), start_level_,
                                      base_level) == output_compression_);
   if (matches) {
     TEST_SYNC_POINT("Compaction::InputCompressionMatchesOutput:Matches");
@@ -225,14 +225,15 @@ bool Compaction::IsTrivialMove() const {
   // filter to be applied to that level, and thus cannot be a trivial move.
 
   // Check if start level have files with overlapping ranges
-  if (start_level_ == 0 && input_vstorage_->level0_non_overlapping() == false) {
+  if (start_level_ == 0 &&
+      input_version_->storage_info()->level0_non_overlapping() == false) {
     // We cannot move files from L0 to L1 if the files are overlapping
     return false;
   }
 
   if (is_manual_compaction_ &&
-      (immutable_cf_options_.compaction_filter != nullptr ||
-       immutable_cf_options_.compaction_filter_factory != nullptr)) {
+      (cfd_->ioptions()->compaction_filter != nullptr ||
+       cfd_->ioptions()->compaction_filter_factory != nullptr)) {
     // This is a manual compaction and we have a compaction filter that should
     // be executed, we cannot do a trivial move
     return false;
@@ -240,34 +241,15 @@ bool Compaction::IsTrivialMove() const {
 
   // Used in universal compaction, where trivial move can be done if the
   // input files are non overlapping
-  if ((immutable_cf_options_.compaction_options_universal.allow_trivial_move) &&
+  if ((cfd_->ioptions()->compaction_options_universal.allow_trivial_move) &&
       (output_level_ != 0)) {
     return is_trivial_move_;
   }
 
-  if (!(start_level_ != output_level_ && num_input_levels() == 1 &&
+  return (start_level_ != output_level_ && num_input_levels() == 1 &&
           input(0, 0)->fd.GetPathId() == output_path_id() &&
-          InputCompressionMatchesOutput())) {
-    return false;
-  }
-
-  // assert inputs_.size() == 1
-
-  for (const auto& file : inputs_.front().files) {
-    std::vector<FileMetaData*> file_grand_parents;
-    if (output_level_ + 1 >= number_levels_) {
-      continue;
-    }
-    input_vstorage_->GetOverlappingInputs(output_level_ + 1, &file->smallest,
-                                          &file->largest, &file_grand_parents);
-    const auto compaction_size =
-        file->fd.GetFileSize() + TotalFileSize(file_grand_parents);
-    if (compaction_size > max_compaction_bytes_) {
-      return false;
-    }
-  }
-
-  return true;
+          InputCompressionMatchesOutput() &&
+          TotalFileSize(grandparents_) <= max_grandparent_overlap_bytes_);
 }
 
 void Compaction::AddInputDeletions(VersionEdit* out_edit) {
@@ -290,7 +272,8 @@ bool Compaction::KeyNotExistsBeyondOutputLevel(
   // Maybe use binary search to find right entry instead of linear search?
   const Comparator* user_cmp = cfd_->user_comparator();
   for (int lvl = output_level_ + 1; lvl < number_levels_; lvl++) {
-    const std::vector<FileMetaData*>& files = input_vstorage_->LevelFiles(lvl);
+    const std::vector<FileMetaData*>& files =
+        input_version_->storage_info()->LevelFiles(lvl);
     for (; level_ptrs->at(lvl) < files.size(); level_ptrs->at(lvl)++) {
       auto* f = files[level_ptrs->at(lvl)];
       if (user_cmp->Compare(user_key, f->largest.user_key()) <= 0) {
@@ -307,12 +290,38 @@ bool Compaction::KeyNotExistsBeyondOutputLevel(
   return true;
 }
 
+bool Compaction::ShouldStopBefore(const Slice& internal_key) {
+  // Scan to find earliest grandparent file that contains key.
+  const InternalKeyComparator* icmp = &cfd_->internal_comparator();
+  while (grandparent_index_ < grandparents_.size() &&
+      icmp->Compare(internal_key,
+                    grandparents_[grandparent_index_]->largest.Encode()) > 0) {
+    if (seen_key_) {
+      overlapped_bytes_ += grandparents_[grandparent_index_]->fd.GetFileSize();
+    }
+    assert(grandparent_index_ + 1 >= grandparents_.size() ||
+           icmp->Compare(grandparents_[grandparent_index_]->largest.Encode(),
+                         grandparents_[grandparent_index_+1]->smallest.Encode())
+                         < 0);
+    grandparent_index_++;
+  }
+  seen_key_ = true;
+
+  if (overlapped_bytes_ > max_grandparent_overlap_bytes_) {
+    // Too much overlap for current output; start new output
+    overlapped_bytes_ = 0;
+    return true;
+  } else {
+    return false;
+  }
+}
+
 // Mark (or clear) each file that is being compacted
 void Compaction::MarkFilesBeingCompacted(bool mark_as_compacted) {
   for (size_t i = 0; i < num_input_levels(); i++) {
     for (size_t j = 0; j < inputs_[i].size(); j++) {
-      assert(mark_as_compacted ? !inputs_[i][j]->being_compacted
-                               : inputs_[i][j]->being_compacted);
+      assert(mark_as_compacted ? !inputs_[i][j]->being_compacted :
+                                  inputs_[i][j]->being_compacted);
       inputs_[i][j]->being_compacted = mark_as_compacted;
     }
   }
@@ -362,7 +371,7 @@ void Compaction::ReleaseCompactionFiles(Status status) {
 
 void Compaction::ResetNextCompactionIndex() {
   assert(input_version_ != nullptr);
-  input_vstorage_->ResetNextCompactionIndex(start_level_);
+  input_version_->storage_info()->ResetNextCompactionIndex(start_level_);
 }
 
 namespace {
@@ -387,8 +396,10 @@ int InputSummary(const std::vector<FileMetaData*>& files, char* output,
 
 void Compaction::Summary(char* output, int len) {
   int write =
-      snprintf(output, len, "Base version %" PRIu64 " Base level %d, inputs: [",
-               input_version_->GetVersionNumber(), start_level_);
+      snprintf(output, len, "Base version %" PRIu64
+                            " Base level %d, inputs: [",
+               input_version_->GetVersionNumber(),
+               start_level_);
   if (write < 0 || write >= len) {
     return;
   }
@@ -410,7 +421,7 @@ void Compaction::Summary(char* output, int len) {
   snprintf(output + write, len - write, "]");
 }
 
-uint64_t Compaction::OutputFilePreallocationSize() const {
+uint64_t Compaction::OutputFilePreallocationSize() {
   uint64_t preallocation_size = 0;
 
   if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel ||
@@ -446,7 +457,7 @@ bool Compaction::IsOutputLevelEmpty() const {
 }
 
 bool Compaction::ShouldFormSubcompactions() const {
-  if (immutable_cf_options_.max_subcompactions <= 1 || cfd_ == nullptr) {
+  if (mutable_cf_options_.max_subcompactions <= 1 || cfd_ == nullptr) {
     return false;
   }
   if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {

db/compaction.h

@@ -1,17 +1,17 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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 "db/version_set.h"
 #include "util/arena.h"
 #include "util/autovector.h"
-#include "util/cf_options.h"
+#include "util/mutable_cf_options.h"
+#include "db/version_set.h"
 
 namespace rocksdb {
 
@@ -35,10 +35,9 @@ class CompactionFilter;
 class Compaction {
  public:
   Compaction(VersionStorageInfo* input_version,
-             const ImmutableCFOptions& immutable_cf_options,
              const MutableCFOptions& mutable_cf_options,
              std::vector<CompactionInputFiles> inputs, int output_level,
-             uint64_t target_file_size, uint64_t max_compaction_bytes,
+             uint64_t target_file_size, uint64_t max_grandparent_overlap_bytes,
              uint32_t output_path_id, CompressionType compression,
              std::vector<FileMetaData*> grandparents,
              bool manual_compaction = false, double score = -1,
@@ -104,10 +103,8 @@ class Compaction {
     return &inputs_[compaction_input_level].files;
   }
 
-  const std::vector<CompactionInputFiles>* inputs() { return &inputs_; }
-
   // Returns the LevelFilesBrief of the specified compaction input level.
-  const LevelFilesBrief* input_levels(size_t compaction_input_level) const {
+  LevelFilesBrief* input_levels(size_t compaction_input_level) {
     return &input_levels_[compaction_input_level];
   }
 
@@ -135,10 +132,12 @@ class Compaction {
   bool KeyNotExistsBeyondOutputLevel(const Slice& user_key,
                                      std::vector<size_t>* level_ptrs) const;
 
+  // Returns true iff we should stop building the current output
+  // before processing "internal_key".
+  bool ShouldStopBefore(const Slice& internal_key);
+
   // Clear all files to indicate that they are not being compacted
   // Delete this compaction from the list of running compactions.
-  //
-  // Requirement: DB mutex held
   void ReleaseCompactionFiles(Status status);
 
   // Returns the summary of the compaction in "output" with maximum "len"
@@ -150,13 +149,13 @@ class Compaction {
   double score() const { return score_; }
 
   // Is this compaction creating a file in the bottom most level?
-  bool bottommost_level() const { return bottommost_level_; }
+  bool bottommost_level() { return bottommost_level_; }
 
   // Does this compaction include all sst files?
-  bool is_full_compaction() const { return is_full_compaction_; }
+  bool is_full_compaction() { return is_full_compaction_; }
 
   // Was this compaction triggered manually by the client?
-  bool is_manual_compaction() const { return is_manual_compaction_; }
+  bool is_manual_compaction() { return is_manual_compaction_; }
 
   // Used when allow_trivial_move option is set in
   // Universal compaction. If all the input files are
@@ -169,27 +168,19 @@ class Compaction {
   // Used when allow_trivial_move option is set in
   // Universal compaction. Returns true, if the input files
   // are non-overlapping and can be trivially moved.
-  bool is_trivial_move() const { return is_trivial_move_; }
+  bool is_trivial_move() { return is_trivial_move_; }
 
   // How many total levels are there?
   int number_levels() const { return number_levels_; }
 
-  // Return the ImmutableCFOptions that should be used throughout the compaction
-  // procedure
-  const ImmutableCFOptions* immutable_cf_options() const {
-    return &immutable_cf_options_;
-  }
-
   // Return the MutableCFOptions that should be used throughout the compaction
   // procedure
-  const MutableCFOptions* mutable_cf_options() const {
-    return &mutable_cf_options_;
-  }
+  const MutableCFOptions* mutable_cf_options() { return &mutable_cf_options_; }
 
   // Returns the size in bytes that the output file should be preallocated to.
   // In level compaction, that is max_file_size_. In universal compaction, that
   // is the sum of all input file sizes.
-  uint64_t OutputFilePreallocationSize() const;
+  uint64_t OutputFilePreallocationSize();
 
   void SetInputVersion(Version* input_version);
 
@@ -228,18 +219,10 @@ class Compaction {
     output_table_properties_ = std::move(tp);
   }
 
-  Slice GetSmallestUserKey() const { return smallest_user_key_; }
-
   Slice GetLargestUserKey() const { return largest_user_key_; }
 
   CompactionReason compaction_reason() { return compaction_reason_; }
 
-  const std::vector<FileMetaData*>& grandparents() const {
-    return grandparents_;
-  }
-
-  uint64_t max_compaction_bytes() const { return max_compaction_bytes_; }
-
  private:
   // mark (or clear) all files that are being compacted
   void MarkFilesBeingCompacted(bool mark_as_compacted);
@@ -258,14 +241,11 @@ class Compaction {
   static bool IsFullCompaction(VersionStorageInfo* vstorage,
                                const std::vector<CompactionInputFiles>& inputs);
 
-  VersionStorageInfo* input_vstorage_;
-
   const int start_level_;    // the lowest level to be compacted
   const int output_level_;  // levels to which output files are stored
   uint64_t max_output_file_size_;
-  uint64_t max_compaction_bytes_;
-  const ImmutableCFOptions immutable_cf_options_;
-  const MutableCFOptions mutable_cf_options_;
+  uint64_t max_grandparent_overlap_bytes_;
+  MutableCFOptions mutable_cf_options_;
   Version* input_version_;
   VersionEdit edit_;
   const int number_levels_;
@@ -283,9 +263,13 @@ class Compaction {
   // A copy of inputs_, organized more closely in memory
   autovector<LevelFilesBrief, 2> input_levels_;
 
-  // State used to check for number of overlapping grandparent files
+  // State used to check for number of of overlapping grandparent files
   // (grandparent == "output_level_ + 1")
   std::vector<FileMetaData*> grandparents_;
+  size_t grandparent_index_;   // Index in grandparent_starts_
+  bool seen_key_;              // Some output key has been seen
+  uint64_t overlapped_bytes_;  // Bytes of overlap between current output
+                               // and grandparent files
   const double score_;         // score that was used to pick this compaction.
 
   // Is this compaction creating a file in the bottom most level?
@@ -306,9 +290,6 @@ class Compaction {
   // table properties of output files
   TablePropertiesCollection output_table_properties_;
 
-  // smallest user keys in compaction
-  Slice smallest_user_key_;
-
   // largest user keys in compaction
   Slice largest_user_key_;
 

db/compaction_iteration_stats.h

@@ -1,33 +0,0 @@
-//  Copyright (c) 2016-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
-
-struct CompactionIterationStats {
-  // Compaction statistics
-
-  // Doesn't include records skipped because of
-  // CompactionFilter::Decision::kRemoveAndSkipUntil.
-  int64_t num_record_drop_user = 0;
-
-  int64_t num_record_drop_hidden = 0;
-  int64_t num_record_drop_obsolete = 0;
-  int64_t num_record_drop_range_del = 0;
-  int64_t num_range_del_drop_obsolete = 0;
-  uint64_t total_filter_time = 0;
-
-  // Input statistics
-  // TODO(noetzli): The stats are incomplete. They are lacking everything
-  // consumed by MergeHelper.
-  uint64_t num_input_records = 0;
-  uint64_t num_input_deletion_records = 0;
-  uint64_t num_input_corrupt_records = 0;
-  uint64_t total_input_raw_key_bytes = 0;
-  uint64_t total_input_raw_value_bytes = 0;
-
-  // Single-Delete diagnostics for exceptional situations
-  uint64_t num_single_del_fallthru = 0;
-  uint64_t num_single_del_mismatch = 0;
-};

db/compaction_iterator.cc

@@ -1,7 +1,9 @@
-//  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).
+// 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.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 #include "db/compaction_iterator.h"
 #include "table/internal_iterator.h"
@@ -12,25 +14,8 @@ CompactionIterator::CompactionIterator(
     InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
     SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
     SequenceNumber earliest_write_conflict_snapshot, Env* env,
-    bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
-    const Compaction* compaction, const CompactionFilter* compaction_filter,
-    const std::atomic<bool>* shutting_down)
-    : CompactionIterator(
-          input, cmp, merge_helper, last_sequence, snapshots,
-          earliest_write_conflict_snapshot, env, expect_valid_internal_key,
-          range_del_agg,
-          std::unique_ptr<CompactionProxy>(
-              compaction ? new CompactionProxy(compaction) : nullptr),
-          compaction_filter, shutting_down) {}
-
-CompactionIterator::CompactionIterator(
-    InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
-    SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-    SequenceNumber earliest_write_conflict_snapshot, Env* env,
-    bool expect_valid_internal_key, RangeDelAggregator* range_del_agg,
-    std::unique_ptr<CompactionProxy> compaction,
-    const CompactionFilter* compaction_filter,
-    const std::atomic<bool>* shutting_down)
+    bool expect_valid_internal_key, Compaction* compaction,
+    const CompactionFilter* compaction_filter, LogBuffer* log_buffer)
     : input_(input),
       cmp_(cmp),
       merge_helper_(merge_helper),
@@ -38,10 +23,9 @@ CompactionIterator::CompactionIterator(
       earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
       env_(env),
       expect_valid_internal_key_(expect_valid_internal_key),
-      range_del_agg_(range_del_agg),
-      compaction_(std::move(compaction)),
+      compaction_(compaction),
       compaction_filter_(compaction_filter),
-      shutting_down_(shutting_down),
+      log_buffer_(log_buffer),
       merge_out_iter_(merge_helper_) {
   assert(compaction_filter_ == nullptr || compaction_ != nullptr);
   bottommost_level_ =
@@ -52,11 +36,11 @@ CompactionIterator::CompactionIterator(
 
   if (snapshots_->size() == 0) {
     // optimize for fast path if there are no snapshots
-    visible_at_tip_ = true;
-    earliest_snapshot_ = last_sequence;
+    visible_at_tip_ = last_sequence;
+    earliest_snapshot_ = visible_at_tip_;
     latest_snapshot_ = 0;
   } else {
-    visible_at_tip_ = false;
+    visible_at_tip_ = 0;
     earliest_snapshot_ = snapshots_->at(0);
     latest_snapshot_ = snapshots_->back();
   }
@@ -65,20 +49,12 @@ CompactionIterator::CompactionIterator(
   } else {
     ignore_snapshots_ = false;
   }
-  input_->SetPinnedItersMgr(&pinned_iters_mgr_);
-}
-
-CompactionIterator::~CompactionIterator() {
-  // input_ Iteartor lifetime is longer than pinned_iters_mgr_ lifetime
-  input_->SetPinnedItersMgr(nullptr);
 }
 
 void CompactionIterator::ResetRecordCounts() {
   iter_stats_.num_record_drop_user = 0;
   iter_stats_.num_record_drop_hidden = 0;
   iter_stats_.num_record_drop_obsolete = 0;
-  iter_stats_.num_record_drop_range_del = 0;
-  iter_stats_.num_range_del_drop_obsolete = 0;
 }
 
 void CompactionIterator::SeekToFirst() {
@@ -107,8 +83,6 @@ void CompactionIterator::Next() {
       ikey_.user_key = current_key_.GetUserKey();
       valid_ = true;
     } else {
-      // We consumed all pinned merge operands, release pinned iterators
-      pinned_iters_mgr_.ReleasePinnedData();
       // MergeHelper moves the iterator to the first record after the merged
       // records, so even though we reached the end of the merge output, we do
       // not want to advance the iterator.
@@ -124,7 +98,7 @@ void CompactionIterator::Next() {
   }
 
   if (valid_) {
-    // Record that we've outputted a record for the current key.
+    // Record that we've ouputted a record for the current key.
     has_outputted_key_ = true;
   }
 
@@ -135,7 +109,7 @@ void CompactionIterator::NextFromInput() {
   at_next_ = false;
   valid_ = false;
 
-  while (!valid_ && input_->Valid() && !IsShuttingDown()) {
+  while (!valid_ && input_->Valid()) {
     key_ = input_->key();
     value_ = input_->value();
     iter_stats_.num_input_records++;
@@ -165,20 +139,12 @@ void CompactionIterator::NextFromInput() {
     iter_stats_.total_input_raw_key_bytes += key_.size();
     iter_stats_.total_input_raw_value_bytes += value_.size();
 
-    // If need_skip is true, we should seek the input iterator
-    // to internal key skip_until and continue from there.
-    bool need_skip = false;
-    // Points either into compaction_filter_skip_until_ or into
-    // merge_helper_->compaction_filter_skip_until_.
-    Slice skip_until;
-
     // Check whether the user key changed. After this if statement current_key_
     // is a copy of the current input key (maybe converted to a delete by the
     // compaction filter). ikey_.user_key is pointing to the copy.
     if (!has_current_user_key_ ||
         !cmp_->Equal(ikey_.user_key, current_user_key_)) {
       // First occurrence of this user key
-      // Copy key for output
       key_ = current_key_.SetKey(key_, &ikey_);
       current_user_key_ = ikey_.user_key;
       has_current_user_key_ = true;
@@ -194,42 +160,26 @@ void CompactionIterator::NextFromInput() {
         // number is greater than any external snapshot, then invoke the
         // filter. If the return value of the compaction filter is true,
         // replace the entry with a deletion marker.
-        CompactionFilter::Decision filter;
+        bool value_changed = false;
+        bool to_delete = false;
         compaction_filter_value_.clear();
-        compaction_filter_skip_until_.Clear();
         {
           StopWatchNano timer(env_, true);
-          filter = compaction_filter_->FilterV2(
-              compaction_->level(), ikey_.user_key,
-              CompactionFilter::ValueType::kValue, value_,
-              &compaction_filter_value_, compaction_filter_skip_until_.rep());
+          to_delete = compaction_filter_->Filter(
+              compaction_->level(), ikey_.user_key, value_,
+              &compaction_filter_value_, &value_changed);
           iter_stats_.total_filter_time +=
               env_ != nullptr ? timer.ElapsedNanos() : 0;
         }
-
-        if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil &&
-            cmp_->Compare(*compaction_filter_skip_until_.rep(),
-                          ikey_.user_key) <= 0) {
-          // Can't skip to a key smaller than the current one.
-          // Keep the key as per FilterV2 documentation.
-          filter = CompactionFilter::Decision::kKeep;
-        }
-
-        if (filter == CompactionFilter::Decision::kRemove) {
-          // convert the current key to a delete; key_ is pointing into
-          // current_key_ at this point, so updating current_key_ updates key()
+        if (to_delete) {
+          // convert the current key to a delete
           ikey_.type = kTypeDeletion;
           current_key_.UpdateInternalKey(ikey_.sequence, kTypeDeletion);
           // no value associated with delete
           value_.clear();
           iter_stats_.num_record_drop_user++;
-        } else if (filter == CompactionFilter::Decision::kChangeValue) {
+        } else if (value_changed) {
           value_ = compaction_filter_value_;
-        } else if (filter == CompactionFilter::Decision::kRemoveAndSkipUntil) {
-          need_skip = true;
-          compaction_filter_skip_until_.ConvertFromUserKey(kMaxSequenceNumber,
-                                                           kValueTypeForSeek);
-          skip_until = compaction_filter_skip_until_.Encode();
         }
       }
     } else {
@@ -252,13 +202,10 @@ void CompactionIterator::NextFromInput() {
     SequenceNumber last_snapshot = current_user_key_snapshot_;
     SequenceNumber prev_snapshot = 0;  // 0 means no previous snapshot
     current_user_key_snapshot_ =
-        visible_at_tip_
-            ? earliest_snapshot_
-            : findEarliestVisibleSnapshot(ikey_.sequence, &prev_snapshot);
+        visible_at_tip_ ? visible_at_tip_ : findEarliestVisibleSnapshot(
+                                                ikey_.sequence, &prev_snapshot);
 
-    if (need_skip) {
-      // This case is handled below.
-    } else if (clear_and_output_next_key_) {
+    if (clear_and_output_next_key_) {
       // In the previous iteration we encountered a single delete that we could
       // not compact out.  We will keep this Put, but can drop it's data.
       // (See Optimization 3, below.)
@@ -299,7 +246,6 @@ void CompactionIterator::NextFromInput() {
       // those operations for a given key is documented as being undefined.  So
       // we can choose how to handle such a combinations of operations.  We will
       // try to compact out as much as we can in these cases.
-      // We will report counts on these anomalous cases.
 
       // The easiest way to process a SingleDelete during iteration is to peek
       // ahead at the next key.
@@ -322,7 +268,6 @@ void CompactionIterator::NextFromInput() {
             // First SingleDelete has been skipped since we already called
             // input_->Next().
             ++iter_stats_.num_record_drop_obsolete;
-            ++iter_stats_.num_single_del_mismatch;
           } else if ((ikey_.sequence <= earliest_write_conflict_snapshot_) ||
                      has_outputted_key_) {
             // Found a matching value, we can drop the single delete and the
@@ -332,12 +277,7 @@ void CompactionIterator::NextFromInput() {
 
             // Note: it doesn't matter whether the second key is a Put or if it
             // is an unexpected Merge or Delete.  We will compact it out
-            // either way. We will maintain counts of how many mismatches
-            // happened
-            if (next_ikey.type != kTypeValue) {
-              ++iter_stats_.num_single_del_mismatch;
-            }
-
+            // either way.
             ++iter_stats_.num_record_drop_hidden;
             ++iter_stats_.num_record_drop_obsolete;
             // Already called input_->Next() once.  Call it a second time to
@@ -349,6 +289,7 @@ void CompactionIterator::NextFromInput() {
             // to know that a write happened in this snapshot (Rule 2 above).
             // Clear the value and output the SingleDelete. (The value will be
             // outputted on the next iteration.)
+            ++iter_stats_.num_record_drop_hidden;
 
             // Setting valid_ to true will output the current SingleDelete
             valid_ = true;
@@ -364,7 +305,7 @@ void CompactionIterator::NextFromInput() {
         }
       } else {
         // We are at the end of the input, could not parse the next key, or hit
-        // a different key. The iterator returns the single delete if the key
+        // the next key. The iterator returns the single delete if the key
         // possibly exists beyond the current output level.  We set
         // has_current_user_key to false so that if the iterator is at the next
         // key, we do not compare it again against the previous key at the next
@@ -377,7 +318,6 @@ void CompactionIterator::NextFromInput() {
           // Key doesn't exist outside of this range.
           // Can compact out this SingleDelete.
           ++iter_stats_.num_record_drop_obsolete;
-          ++iter_stats_.num_single_del_fallthru;
         } else {
           // Output SingleDelete
           valid_ = true;
@@ -422,24 +362,20 @@ void CompactionIterator::NextFromInput() {
       input_->Next();
     } else if (ikey_.type == kTypeMerge) {
       if (!merge_helper_->HasOperator()) {
+        LogToBuffer(log_buffer_, "Options::merge_operator is null.");
         status_ = Status::InvalidArgument(
             "merge_operator is not properly initialized.");
         return;
       }
 
-      pinned_iters_mgr_.StartPinning();
       // We know the merge type entry is not hidden, otherwise we would
       // have hit (A)
       // We encapsulate the merge related state machine in a different
       // object to minimize change to the existing flow.
-      Status s = merge_helper_->MergeUntil(input_, range_del_agg_,
-                                           prev_snapshot, bottommost_level_);
+      merge_helper_->MergeUntil(input_, prev_snapshot, bottommost_level_);
       merge_out_iter_.SeekToFirst();
 
-      if (!s.ok() && !s.IsMergeInProgress()) {
-        status_ = s;
-        return;
-      } else if (merge_out_iter_.Valid()) {
+      if (merge_out_iter_.Valid()) {
         // NOTE: key, value, and ikey_ refer to old entries.
         //       These will be correctly set below.
         key_ = merge_out_iter_.key();
@@ -459,33 +395,10 @@ void CompactionIterator::NextFromInput() {
         // batch consumed by the merge operator should not shadow any keys
         // coming after the merges
         has_current_user_key_ = false;
-        pinned_iters_mgr_.ReleasePinnedData();
-
-        if (merge_helper_->FilteredUntil(&skip_until)) {
-          need_skip = true;
-        }
       }
     } else {
-      // 1. new user key -OR-
-      // 2. different snapshot stripe
-      bool should_delete = range_del_agg_->ShouldDelete(
-          key_, RangeDelAggregator::RangePositioningMode::kForwardTraversal);
-      if (should_delete) {
-        ++iter_stats_.num_record_drop_hidden;
-        ++iter_stats_.num_record_drop_range_del;
-        input_->Next();
-      } else {
-        valid_ = true;
-      }
+      valid_ = true;
     }
-
-    if (need_skip) {
-      input_->Seek(skip_until);
-    }
-  }
-
-  if (!valid_ && IsShuttingDown()) {
-    status_ = Status::ShutdownInProgress();
   }
 }
 
@@ -510,15 +423,15 @@ void CompactionIterator::PrepareOutput() {
 inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
     SequenceNumber in, SequenceNumber* prev_snapshot) {
   assert(snapshots_->size());
-  SequenceNumber prev __attribute__((__unused__)) = kMaxSequenceNumber;
+  SequenceNumber prev __attribute__((unused)) = 0;
   for (const auto cur : *snapshots_) {
-    assert(prev == kMaxSequenceNumber || prev <= cur);
+    assert(prev <= cur);
     if (cur >= in) {
-      *prev_snapshot = prev == kMaxSequenceNumber ? 0 : prev;
+      *prev_snapshot = prev;
       return cur;
     }
     prev = cur;
-    assert(prev < kMaxSequenceNumber);
+    assert(prev);
   }
   *prev_snapshot = prev;
   return kMaxSequenceNumber;

db/compaction_iterator.h

@@ -1,7 +1,9 @@
-//  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).
+// 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.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 #pragma once
 
 #include <algorithm>
@@ -10,68 +12,39 @@
 #include <vector>
 
 #include "db/compaction.h"
-#include "db/compaction_iteration_stats.h"
 #include "db/merge_helper.h"
-#include "db/pinned_iterators_manager.h"
-#include "db/range_del_aggregator.h"
 #include "rocksdb/compaction_filter.h"
+#include "util/log_buffer.h"
 
 namespace rocksdb {
 
+struct CompactionIteratorStats {
+  // Compaction statistics
+  int64_t num_record_drop_user = 0;
+  int64_t num_record_drop_hidden = 0;
+  int64_t num_record_drop_obsolete = 0;
+  uint64_t total_filter_time = 0;
+
+  // Input statistics
+  // TODO(noetzli): The stats are incomplete. They are lacking everything
+  // consumed by MergeHelper.
+  uint64_t num_input_records = 0;
+  uint64_t num_input_deletion_records = 0;
+  uint64_t num_input_corrupt_records = 0;
+  uint64_t total_input_raw_key_bytes = 0;
+  uint64_t total_input_raw_value_bytes = 0;
+};
+
 class CompactionIterator {
  public:
-  // A wrapper around Compaction. Has a much smaller interface, only what
-  // CompactionIterator uses. Tests can override it.
-  class CompactionProxy {
-   public:
-    explicit CompactionProxy(const Compaction* compaction)
-        : compaction_(compaction) {}
-
-    virtual ~CompactionProxy() = default;
-    virtual int level(size_t compaction_input_level = 0) const {
-      return compaction_->level();
-    }
-    virtual bool KeyNotExistsBeyondOutputLevel(
-        const Slice& user_key, std::vector<size_t>* level_ptrs) const {
-      return compaction_->KeyNotExistsBeyondOutputLevel(user_key, level_ptrs);
-    }
-    virtual bool bottommost_level() const {
-      return compaction_->bottommost_level();
-    }
-    virtual int number_levels() const { return compaction_->number_levels(); }
-    virtual Slice GetLargestUserKey() const {
-      return compaction_->GetLargestUserKey();
-    }
-
-   protected:
-    CompactionProxy() = default;
-
-   private:
-    const Compaction* compaction_;
-  };
-
   CompactionIterator(InternalIterator* input, const Comparator* cmp,
                      MergeHelper* merge_helper, SequenceNumber last_sequence,
                      std::vector<SequenceNumber>* snapshots,
                      SequenceNumber earliest_write_conflict_snapshot, Env* env,
                      bool expect_valid_internal_key,
-                     RangeDelAggregator* range_del_agg,
-                     const Compaction* compaction = nullptr,
+                     Compaction* compaction = nullptr,
                      const CompactionFilter* compaction_filter = nullptr,
-                     const std::atomic<bool>* shutting_down = 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, Env* env,
-                     bool expect_valid_internal_key,
-                     RangeDelAggregator* range_del_agg,
-                     std::unique_ptr<CompactionProxy> compaction,
-                     const CompactionFilter* compaction_filter = nullptr,
-                     const std::atomic<bool>* shutting_down = nullptr);
-
-  ~CompactionIterator();
+                     LogBuffer* log_buffer = nullptr);
 
   void ResetRecordCounts();
 
@@ -92,7 +65,7 @@ class CompactionIterator {
   const ParsedInternalKey& ikey() const { return ikey_; }
   bool Valid() const { return valid_; }
   const Slice& user_key() const { return current_user_key_; }
-  const CompactionIterationStats& iter_stats() const { return iter_stats_; }
+  const CompactionIteratorStats& iter_stats() const { return iter_stats_; }
 
  private:
   // Processes the input stream to find the next output
@@ -119,13 +92,12 @@ class CompactionIterator {
   const SequenceNumber earliest_write_conflict_snapshot_;
   Env* env_;
   bool expect_valid_internal_key_;
-  RangeDelAggregator* range_del_agg_;
-  std::unique_ptr<CompactionProxy> compaction_;
+  Compaction* compaction_;
   const CompactionFilter* compaction_filter_;
-  const std::atomic<bool>* shutting_down_;
+  LogBuffer* log_buffer_;
   bool bottommost_level_;
   bool valid_ = false;
-  bool visible_at_tip_;
+  SequenceNumber visible_at_tip_;
   SequenceNumber earliest_snapshot_;
   SequenceNumber latest_snapshot_;
   bool ignore_snapshots_;
@@ -164,11 +136,7 @@ class CompactionIterator {
   bool clear_and_output_next_key_ = false;
 
   MergeOutputIterator merge_out_iter_;
-  // PinnedIteratorsManager used to pin input_ Iterator blocks while reading
-  // merge operands and then releasing them after consuming them.
-  PinnedIteratorsManager pinned_iters_mgr_;
   std::string compaction_filter_value_;
-  InternalKey compaction_filter_skip_until_;
   // "level_ptrs" holds indices that remember which file of an associated
   // level we were last checking during the last call to compaction->
   // KeyNotExistsBeyondOutputLevel(). This allows future calls to the function
@@ -176,11 +144,6 @@ class CompactionIterator {
   // increasing so a later call to the function must be looking for a key that
   // is in or beyond the last file checked during the previous call
   std::vector<size_t> level_ptrs_;
-  CompactionIterationStats iter_stats_;
-
-  bool IsShuttingDown() {
-    // This is a best-effort facility, so memory_order_relaxed is sufficient.
-    return shutting_down_ && shutting_down_->load(std::memory_order_relaxed);
-  }
+  CompactionIteratorStats iter_stats_;
 };
 }  // namespace rocksdb

db/compaction_iterator_test.cc

@@ -1,216 +1,43 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 #include "db/compaction_iterator.h"
-
-#include <string>
-#include <vector>
-
-#include "port/port.h"
 #include "util/testharness.h"
 #include "util/testutil.h"
 
 namespace rocksdb {
 
-// Expects no merging attempts.
-class NoMergingMergeOp : public MergeOperator {
- public:
-  bool FullMergeV2(const MergeOperationInput& merge_in,
-                   MergeOperationOutput* merge_out) const override {
-    ADD_FAILURE();
-    return false;
-  }
-  bool PartialMergeMulti(const Slice& key,
-                         const std::deque<Slice>& operand_list,
-                         std::string* new_value,
-                         Logger* logger) const override {
-    ADD_FAILURE();
-    return false;
-  }
-  const char* Name() const override {
-    return "CompactionIteratorTest NoMergingMergeOp";
-  }
-};
-
-// Compaction filter that gets stuck when it sees a particular key,
-// then gets unstuck when told to.
-// Always returns Decition::kRemove.
-class StallingFilter : public CompactionFilter {
- public:
-  virtual Decision FilterV2(int level, const Slice& key, ValueType t,
-                            const Slice& existing_value, std::string* new_value,
-                            std::string* skip_until) const override {
-    int k = std::atoi(key.ToString().c_str());
-    last_seen.store(k);
-    while (k >= stall_at.load()) {
-      std::this_thread::yield();
-    }
-    return Decision::kRemove;
-  }
-
-  const char* Name() const override {
-    return "CompactionIteratorTest StallingFilter";
-  }
-
-  // Wait until the filter sees a key >= k and stalls at that key.
-  // If `exact`, asserts that the seen key is equal to k.
-  void WaitForStall(int k, bool exact = true) {
-    stall_at.store(k);
-    while (last_seen.load() < k) {
-      std::this_thread::yield();
-    }
-    if (exact) {
-      EXPECT_EQ(k, last_seen.load());
-    }
-  }
-
-  // Filter will stall on key >= stall_at. Advance stall_at to unstall.
-  mutable std::atomic<int> stall_at{0};
-  // Last key the filter was called with.
-  mutable std::atomic<int> last_seen{0};
-};
-
-class LoggingForwardVectorIterator : public InternalIterator {
- public:
-  struct Action {
-    enum class Type {
-      SEEK_TO_FIRST,
-      SEEK,
-      NEXT,
-    };
-
-    Type type;
-    std::string arg;
-
-    explicit Action(Type _type, std::string _arg = "")
-        : type(_type), arg(_arg) {}
-
-    bool operator==(const Action& rhs) const {
-      return std::tie(type, arg) == std::tie(rhs.type, rhs.arg);
-    }
-  };
-
-  LoggingForwardVectorIterator(const std::vector<std::string>& keys,
-                               const std::vector<std::string>& values)
-      : keys_(keys), values_(values), current_(keys.size()) {
-    assert(keys_.size() == values_.size());
-  }
-
-  virtual bool Valid() const override { return current_ < keys_.size(); }
-
-  virtual void SeekToFirst() override {
-    log.emplace_back(Action::Type::SEEK_TO_FIRST);
-    current_ = 0;
-  }
-  virtual void SeekToLast() override { assert(false); }
-
-  virtual void Seek(const Slice& target) override {
-    log.emplace_back(Action::Type::SEEK, target.ToString());
-    current_ = std::lower_bound(keys_.begin(), keys_.end(), target.ToString()) -
-               keys_.begin();
-  }
-
-  virtual void SeekForPrev(const Slice& target) override { assert(false); }
-
-  virtual void Next() override {
-    assert(Valid());
-    log.emplace_back(Action::Type::NEXT);
-    current_++;
-  }
-  virtual void Prev() override { assert(false); }
-
-  virtual Slice key() const override {
-    assert(Valid());
-    return Slice(keys_[current_]);
-  }
-  virtual Slice value() const override {
-    assert(Valid());
-    return Slice(values_[current_]);
-  }
-
-  virtual Status status() const override { return Status::OK(); }
-
-  std::vector<Action> log;
-
- private:
-  std::vector<std::string> keys_;
-  std::vector<std::string> values_;
-  size_t current_;
-};
-
-class FakeCompaction : public CompactionIterator::CompactionProxy {
- public:
-  FakeCompaction() = default;
-
-  virtual int level(size_t compaction_input_level) const { return 0; }
-  virtual bool KeyNotExistsBeyondOutputLevel(
-      const Slice& user_key, std::vector<size_t>* level_ptrs) const {
-    return key_not_exists_beyond_output_level;
-  }
-  virtual bool bottommost_level() const { return false; }
-  virtual int number_levels() const { return 1; }
-  virtual Slice GetLargestUserKey() const {
-    return "\xff\xff\xff\xff\xff\xff\xff\xff\xff";
-  }
-
-  bool key_not_exists_beyond_output_level = false;
-};
-
 class CompactionIteratorTest : public testing::Test {
  public:
-  CompactionIteratorTest()
-      : cmp_(BytewiseComparator()), icmp_(cmp_), snapshots_({}) {}
+  CompactionIteratorTest() : cmp_(BytewiseComparator()), snapshots_({}) {}
 
-  void InitIterators(const std::vector<std::string>& ks,
-                     const std::vector<std::string>& vs,
-                     const std::vector<std::string>& range_del_ks,
-                     const std::vector<std::string>& range_del_vs,
-                     SequenceNumber last_sequence,
-                     MergeOperator* merge_op = nullptr,
-                     CompactionFilter* filter = nullptr) {
-    std::unique_ptr<InternalIterator> range_del_iter(
-        new test::VectorIterator(range_del_ks, range_del_vs));
-    range_del_agg_.reset(new RangeDelAggregator(icmp_, snapshots_));
-    ASSERT_OK(range_del_agg_->AddTombstones(std::move(range_del_iter)));
-
-    std::unique_ptr<CompactionIterator::CompactionProxy> compaction;
-    if (filter) {
-      compaction_proxy_ = new FakeCompaction();
-      compaction.reset(compaction_proxy_);
-    }
-
-    merge_helper_.reset(new MergeHelper(Env::Default(), cmp_, merge_op, filter,
-                                        nullptr, false, 0, 0, nullptr,
-                                        &shutting_down_));
-    iter_.reset(new LoggingForwardVectorIterator(ks, vs));
+  void InitIterator(const std::vector<std::string>& ks,
+                    const std::vector<std::string>& vs,
+                    SequenceNumber last_sequence) {
+    merge_helper_.reset(new MergeHelper(Env::Default(), cmp_, nullptr, nullptr,
+                                        nullptr, 0U, false, 0));
+    iter_.reset(new test::VectorIterator(ks, vs));
     iter_->SeekToFirst();
     c_iter_.reset(new CompactionIterator(
         iter_.get(), cmp_, merge_helper_.get(), last_sequence, &snapshots_,
-        kMaxSequenceNumber, Env::Default(), false, range_del_agg_.get(),
-        std::move(compaction), filter, &shutting_down_));
+        kMaxSequenceNumber, Env::Default(), false));
   }
 
-  void AddSnapshot(SequenceNumber snapshot) { snapshots_.push_back(snapshot); }
-
   const Comparator* cmp_;
-  const InternalKeyComparator icmp_;
   std::vector<SequenceNumber> snapshots_;
   std::unique_ptr<MergeHelper> merge_helper_;
-  std::unique_ptr<LoggingForwardVectorIterator> iter_;
+  std::unique_ptr<test::VectorIterator> iter_;
   std::unique_ptr<CompactionIterator> c_iter_;
-  std::unique_ptr<RangeDelAggregator> range_del_agg_;
-  std::atomic<bool> shutting_down_{false};
-  FakeCompaction* compaction_proxy_;
 };
 
 // It is possible that the output of the compaction iterator is empty even if
 // the input is not.
 TEST_F(CompactionIteratorTest, EmptyResult) {
-  InitIterators({test::KeyStr("a", 5, kTypeSingleDeletion),
-                 test::KeyStr("a", 3, kTypeValue)},
-                {"", "val"}, {}, {}, 5);
+  InitIterator({test::KeyStr("a", 5, kTypeSingleDeletion),
+                test::KeyStr("a", 3, kTypeValue)},
+               {"", "val"}, 5);
   c_iter_->SeekToFirst();
   ASSERT_FALSE(c_iter_->Valid());
 }
@@ -218,10 +45,10 @@ TEST_F(CompactionIteratorTest, EmptyResult) {
 // If there is a corruption after a single deletion, the corrupted key should
 // be preserved.
 TEST_F(CompactionIteratorTest, CorruptionAfterSingleDeletion) {
-  InitIterators({test::KeyStr("a", 5, kTypeSingleDeletion),
-                 test::KeyStr("a", 3, kTypeValue, true),
-                 test::KeyStr("b", 10, kTypeValue)},
-                {"", "val", "val2"}, {}, {}, 10);
+  InitIterator({test::KeyStr("a", 5, kTypeSingleDeletion),
+                test::KeyStr("a", 3, kTypeValue, true),
+                test::KeyStr("b", 10, kTypeValue)},
+               {"", "val", "val2"}, 10);
   c_iter_->SeekToFirst();
   ASSERT_TRUE(c_iter_->Valid());
   ASSERT_EQ(test::KeyStr("a", 5, kTypeSingleDeletion),
@@ -236,224 +63,6 @@ TEST_F(CompactionIteratorTest, CorruptionAfterSingleDeletion) {
   ASSERT_FALSE(c_iter_->Valid());
 }
 
-TEST_F(CompactionIteratorTest, SimpleRangeDeletion) {
-  InitIterators({test::KeyStr("morning", 5, kTypeValue),
-                 test::KeyStr("morning", 2, kTypeValue),
-                 test::KeyStr("night", 3, kTypeValue)},
-                {"zao", "zao", "wan"},
-                {test::KeyStr("ma", 4, kTypeRangeDeletion)}, {"mz"}, 5);
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("morning", 5, kTypeValue), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("night", 3, kTypeValue), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_FALSE(c_iter_->Valid());
-}
-
-TEST_F(CompactionIteratorTest, RangeDeletionWithSnapshots) {
-  AddSnapshot(10);
-  std::vector<std::string> ks1;
-  ks1.push_back(test::KeyStr("ma", 28, kTypeRangeDeletion));
-  std::vector<std::string> vs1{"mz"};
-  std::vector<std::string> ks2{test::KeyStr("morning", 15, kTypeValue),
-                               test::KeyStr("morning", 5, kTypeValue),
-                               test::KeyStr("night", 40, kTypeValue),
-                               test::KeyStr("night", 20, kTypeValue)};
-  std::vector<std::string> vs2{"zao 15", "zao 5", "wan 40", "wan 20"};
-  InitIterators(ks2, vs2, ks1, vs1, 40);
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("morning", 5, kTypeValue), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("night", 40, kTypeValue), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_FALSE(c_iter_->Valid());
-}
-
-TEST_F(CompactionIteratorTest, CompactionFilterSkipUntil) {
-  class Filter : public CompactionFilter {
-    virtual Decision FilterV2(int level, const Slice& key, ValueType t,
-                              const Slice& existing_value,
-                              std::string* new_value,
-                              std::string* skip_until) const override {
-      std::string k = key.ToString();
-      std::string v = existing_value.ToString();
-      // See InitIterators() call below for the sequence of keys and their
-      // filtering decisions. Here we closely assert that compaction filter is
-      // called with the expected keys and only them, and with the right values.
-      if (k == "a") {
-        EXPECT_EQ(ValueType::kValue, t);
-        EXPECT_EQ("av50", v);
-        return Decision::kKeep;
-      }
-      if (k == "b") {
-        EXPECT_EQ(ValueType::kValue, t);
-        EXPECT_EQ("bv60", v);
-        *skip_until = "d+";
-        return Decision::kRemoveAndSkipUntil;
-      }
-      if (k == "e") {
-        EXPECT_EQ(ValueType::kMergeOperand, t);
-        EXPECT_EQ("em71", v);
-        return Decision::kKeep;
-      }
-      if (k == "f") {
-        if (v == "fm65") {
-          EXPECT_EQ(ValueType::kMergeOperand, t);
-          *skip_until = "f";
-        } else {
-          EXPECT_EQ("fm30", v);
-          EXPECT_EQ(ValueType::kMergeOperand, t);
-          *skip_until = "g+";
-        }
-        return Decision::kRemoveAndSkipUntil;
-      }
-      if (k == "h") {
-        EXPECT_EQ(ValueType::kValue, t);
-        EXPECT_EQ("hv91", v);
-        return Decision::kKeep;
-      }
-      if (k == "i") {
-        EXPECT_EQ(ValueType::kMergeOperand, t);
-        EXPECT_EQ("im95", v);
-        *skip_until = "z";
-        return Decision::kRemoveAndSkipUntil;
-      }
-      ADD_FAILURE();
-      return Decision::kKeep;
-    }
-
-    const char* Name() const override {
-      return "CompactionIteratorTest.CompactionFilterSkipUntil::Filter";
-    }
-  };
-
-  NoMergingMergeOp merge_op;
-  Filter filter;
-  InitIterators(
-      {test::KeyStr("a", 50, kTypeValue),  // keep
-       test::KeyStr("a", 45, kTypeMerge),
-       test::KeyStr("b", 60, kTypeValue),  // skip to "d+"
-       test::KeyStr("b", 40, kTypeValue), test::KeyStr("c", 35, kTypeValue),
-       test::KeyStr("d", 70, kTypeMerge),
-       test::KeyStr("e", 71, kTypeMerge),  // keep
-       test::KeyStr("f", 65, kTypeMerge),  // skip to "f", aka keep
-       test::KeyStr("f", 30, kTypeMerge),  // skip to "g+"
-       test::KeyStr("f", 25, kTypeValue), test::KeyStr("g", 90, kTypeValue),
-       test::KeyStr("h", 91, kTypeValue),  // keep
-       test::KeyStr("i", 95, kTypeMerge),  // skip to "z"
-       test::KeyStr("j", 99, kTypeValue)},
-      {"av50", "am45", "bv60", "bv40", "cv35", "dm70", "em71", "fm65", "fm30",
-       "fv25", "gv90", "hv91", "im95", "jv99"},
-      {}, {}, kMaxSequenceNumber, &merge_op, &filter);
-
-  // Compaction should output just "a", "e" and "h" keys.
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("a", 50, kTypeValue), c_iter_->key().ToString());
-  ASSERT_EQ("av50", c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("e", 71, kTypeMerge), c_iter_->key().ToString());
-  ASSERT_EQ("em71", c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("h", 91, kTypeValue), c_iter_->key().ToString());
-  ASSERT_EQ("hv91", c_iter_->value().ToString());
-  c_iter_->Next();
-  ASSERT_FALSE(c_iter_->Valid());
-
-  // Check that the compaction iterator did the correct sequence of calls on
-  // the underlying iterator.
-  using A = LoggingForwardVectorIterator::Action;
-  using T = A::Type;
-  std::vector<A> expected_actions = {
-      A(T::SEEK_TO_FIRST),
-      A(T::NEXT),
-      A(T::NEXT),
-      A(T::SEEK, test::KeyStr("d+", kMaxSequenceNumber, kValueTypeForSeek)),
-      A(T::NEXT),
-      A(T::NEXT),
-      A(T::SEEK, test::KeyStr("g+", kMaxSequenceNumber, kValueTypeForSeek)),
-      A(T::NEXT),
-      A(T::SEEK, test::KeyStr("z", kMaxSequenceNumber, kValueTypeForSeek))};
-  ASSERT_EQ(expected_actions, iter_->log);
-}
-
-TEST_F(CompactionIteratorTest, ShuttingDownInFilter) {
-  NoMergingMergeOp merge_op;
-  StallingFilter filter;
-  InitIterators(
-      {test::KeyStr("1", 1, kTypeValue), test::KeyStr("2", 2, kTypeValue),
-       test::KeyStr("3", 3, kTypeValue), test::KeyStr("4", 4, kTypeValue)},
-      {"v1", "v2", "v3", "v4"}, {}, {}, kMaxSequenceNumber, &merge_op, &filter);
-  // Don't leave tombstones (kTypeDeletion) for filtered keys.
-  compaction_proxy_->key_not_exists_beyond_output_level = true;
-
-  std::atomic<bool> seek_done{false};
-  rocksdb::port::Thread compaction_thread([&] {
-    c_iter_->SeekToFirst();
-    EXPECT_FALSE(c_iter_->Valid());
-    EXPECT_TRUE(c_iter_->status().IsShutdownInProgress());
-    seek_done.store(true);
-  });
-
-  // Let key 1 through.
-  filter.WaitForStall(1);
-
-  // Shutdown during compaction filter call for key 2.
-  filter.WaitForStall(2);
-  shutting_down_.store(true);
-  EXPECT_FALSE(seek_done.load());
-
-  // Unstall filter and wait for SeekToFirst() to return.
-  filter.stall_at.store(3);
-  compaction_thread.join();
-  assert(seek_done.load());
-
-  // Check that filter was never called again.
-  EXPECT_EQ(2, filter.last_seen.load());
-}
-
-// Same as ShuttingDownInFilter, but shutdown happens during filter call for
-// a merge operand, not for a value.
-TEST_F(CompactionIteratorTest, ShuttingDownInMerge) {
-  NoMergingMergeOp merge_op;
-  StallingFilter filter;
-  InitIterators(
-      {test::KeyStr("1", 1, kTypeValue), test::KeyStr("2", 2, kTypeMerge),
-       test::KeyStr("3", 3, kTypeMerge), test::KeyStr("4", 4, kTypeValue)},
-      {"v1", "v2", "v3", "v4"}, {}, {}, kMaxSequenceNumber, &merge_op, &filter);
-  compaction_proxy_->key_not_exists_beyond_output_level = true;
-
-  std::atomic<bool> seek_done{false};
-  rocksdb::port::Thread compaction_thread([&] {
-    c_iter_->SeekToFirst();
-    ASSERT_FALSE(c_iter_->Valid());
-    ASSERT_TRUE(c_iter_->status().IsShutdownInProgress());
-    seek_done.store(true);
-  });
-
-  // Let key 1 through.
-  filter.WaitForStall(1);
-
-  // Shutdown during compaction filter call for key 2.
-  filter.WaitForStall(2);
-  shutting_down_.store(true);
-  EXPECT_FALSE(seek_done.load());
-
-  // Unstall filter and wait for SeekToFirst() to return.
-  filter.stall_at.store(3);
-  compaction_thread.join();
-  assert(seek_done.load());
-
-  // Check that filter was never called again.
-  EXPECT_EQ(2, filter.last_seen.load());
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/compaction_job.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -16,13 +16,12 @@
 #include <inttypes.h>
 #include <algorithm>
 #include <functional>
-#include <list>
+#include <vector>
 #include <memory>
-#include <random>
+#include <list>
 #include <set>
 #include <thread>
 #include <utility>
-#include <vector>
 
 #include "db/builder.h"
 #include "db/db_iter.h"
@@ -45,14 +44,13 @@
 #include "rocksdb/table.h"
 #include "table/block.h"
 #include "table/block_based_table_factory.h"
-#include "table/merging_iterator.h"
+#include "table/merger.h"
 #include "table/table_builder.h"
 #include "util/coding.h"
 #include "util/file_reader_writer.h"
 #include "util/iostats_context_imp.h"
 #include "util/log_buffer.h"
 #include "util/logging.h"
-#include "util/sst_file_manager_impl.h"
 #include "util/mutexlock.h"
 #include "util/perf_context_imp.h"
 #include "util/stop_watch.h"
@@ -64,7 +62,7 @@ namespace rocksdb {
 
 // Maintains state for each sub-compaction
 struct CompactionJob::SubcompactionState {
-  const Compaction* compaction;
+  Compaction* compaction;
   std::unique_ptr<CompactionIterator> c_iter;
 
   // The boundaries of the key-range this compaction is interested in. No two
@@ -99,22 +97,12 @@ struct CompactionJob::SubcompactionState {
     }
   }
 
-  uint64_t current_output_file_size;
-
   // 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;
-  // An index that used to speed up ShouldStopBefore().
-  size_t grandparent_index = 0;
-  // The number of bytes overlapping between the current output and
-  // grandparent files used in ShouldStopBefore().
-  uint64_t overlapped_bytes = 0;
-  // A flag determine whether the key has been seen in ShouldStopBefore()
-  bool seen_key = false;
-  std::string compression_dict;
 
   SubcompactionState(Compaction* c, Slice* _start, Slice* _end,
                      uint64_t size = 0)
@@ -123,15 +111,10 @@ struct CompactionJob::SubcompactionState {
         end(_end),
         outfile(nullptr),
         builder(nullptr),
-        current_output_file_size(0),
         total_bytes(0),
         num_input_records(0),
         num_output_records(0),
-        approx_size(size),
-        grandparent_index(0),
-        overlapped_bytes(0),
-        seen_key(false),
-        compression_dict() {
+        approx_size(size) {
     assert(compaction != nullptr);
   }
 
@@ -145,16 +128,11 @@ struct CompactionJob::SubcompactionState {
     outputs = std::move(o.outputs);
     outfile = std::move(o.outfile);
     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);
-    grandparent_index = std::move(o.grandparent_index);
-    overlapped_bytes = std::move(o.overlapped_bytes);
-    seen_key = std::move(o.seen_key);
-    compression_dict = std::move(o.compression_dict);
     return *this;
   }
 
@@ -162,39 +140,6 @@ struct CompactionJob::SubcompactionState {
   SubcompactionState(const SubcompactionState&) = delete;
 
   SubcompactionState& operator=(const SubcompactionState&) = delete;
-
-  // Returns true iff we should stop building the current output
-  // before processing "internal_key".
-  bool ShouldStopBefore(const Slice& internal_key, uint64_t curr_file_size) {
-    const InternalKeyComparator* icmp =
-        &compaction->column_family_data()->internal_comparator();
-    const std::vector<FileMetaData*>& grandparents = compaction->grandparents();
-
-    // Scan to find earliest grandparent file that contains key.
-    while (grandparent_index < grandparents.size() &&
-           icmp->Compare(internal_key,
-                         grandparents[grandparent_index]->largest.Encode()) >
-               0) {
-      if (seen_key) {
-        overlapped_bytes += grandparents[grandparent_index]->fd.GetFileSize();
-      }
-      assert(grandparent_index + 1 >= grandparents.size() ||
-             icmp->Compare(
-                 grandparents[grandparent_index]->largest.Encode(),
-                 grandparents[grandparent_index + 1]->smallest.Encode()) <= 0);
-      grandparent_index++;
-    }
-    seen_key = true;
-
-    if (overlapped_bytes + curr_file_size >
-        compaction->max_compaction_bytes()) {
-      // Too much overlap for current output; start new output
-      overlapped_bytes = 0;
-      return true;
-    }
-
-    return false;
-  }
 };
 
 // Maintains state for the entire compaction
@@ -262,11 +207,10 @@ void CompactionJob::AggregateStatistics() {
 }
 
 CompactionJob::CompactionJob(
-    int job_id, Compaction* compaction, const ImmutableDBOptions& db_options,
+    int job_id, Compaction* compaction, const DBOptions& db_options,
     const EnvOptions& env_options, VersionSet* versions,
-    const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
+    std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
     Directory* db_directory, Directory* output_directory, Statistics* stats,
-    InstrumentedMutex* db_mutex, Status* db_bg_error,
     std::vector<SequenceNumber> existing_snapshots,
     SequenceNumber earliest_write_conflict_snapshot,
     std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
@@ -286,8 +230,6 @@ CompactionJob::CompactionJob(
       db_directory_(db_directory),
       output_directory_(output_directory),
       stats_(stats),
-      db_mutex_(db_mutex),
-      db_bg_error_(db_bg_error),
       existing_snapshots_(std::move(existing_snapshots)),
       earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
       table_cache_(std::move(table_cache)),
@@ -295,9 +237,7 @@ CompactionJob::CompactionJob(
       paranoid_file_checks_(paranoid_file_checks),
       measure_io_stats_(measure_io_stats) {
   assert(log_buffer_ != nullptr);
-  const auto* cfd = compact_->compaction->column_family_data();
-  ThreadStatusUtil::SetColumnFamily(cfd, cfd->ioptions()->env,
-                                    db_options_.enable_thread_tracking);
+  ThreadStatusUtil::SetColumnFamily(compact_->compaction->column_family_data());
   ThreadStatusUtil::SetThreadOperation(ThreadStatus::OP_COMPACTION);
   ReportStartedCompaction(compaction);
 }
@@ -309,9 +249,8 @@ CompactionJob::~CompactionJob() {
 
 void CompactionJob::ReportStartedCompaction(
     Compaction* compaction) {
-  const auto* cfd = compact_->compaction->column_family_data();
-  ThreadStatusUtil::SetColumnFamily(cfd, cfd->ioptions()->env,
-                                    db_options_.enable_thread_tracking);
+  ThreadStatusUtil::SetColumnFamily(
+      compact_->compaction->column_family_data());
 
   ThreadStatusUtil::SetThreadOperationProperty(
       ThreadStatus::COMPACTION_JOB_ID,
@@ -417,7 +356,7 @@ void CompactionJob::GenSubcompactionBoundaries() {
       size_t num_files = flevel->num_files;
 
       if (num_files == 0) {
-        continue;
+        break;
       }
 
       if (lvl == 0) {
@@ -476,16 +415,20 @@ void CompactionJob::GenSubcompactionBoundaries() {
 
   // Group the ranges into subcompactions
   const double min_file_fill_percent = 4.0 / 5;
-  uint64_t max_output_files = static_cast<uint64_t>(
-      std::ceil(sum / min_file_fill_percent /
-                c->mutable_cf_options()->MaxFileSizeForLevel(out_lvl)));
+  uint64_t max_output_files = 
+    static_cast<uint64_t>(
+        std::ceil(
+          sum / min_file_fill_percent /
+          cfd->GetCurrentMutableCFOptions()->MaxFileSizeForLevel(out_lvl))
+          );
   uint64_t subcompactions =
       std::min({static_cast<uint64_t>(ranges.size()),
                 static_cast<uint64_t>(db_options_.max_subcompactions),
                 max_output_files});
 
+  double mean = sum * 1.0 / subcompactions;
+
   if (subcompactions > 1) {
-    double mean = sum * 1.0 / subcompactions;
     // Greedily add ranges to the subcompaction until the sum of the ranges'
     // sizes becomes >= the expected mean size of a subcompaction
     sum = 0;
@@ -522,7 +465,7 @@ Status CompactionJob::Run() {
   const uint64_t start_micros = env_->NowMicros();
 
   // Launch a thread for each of subcompactions 1...num_threads-1
-  std::vector<port::Thread> thread_pool;
+  std::vector<std::thread> thread_pool;
   thread_pool.reserve(num_threads - 1);
   for (size_t i = 1; i < compact_->sub_compact_states.size(); i++) {
     thread_pool.emplace_back(&CompactionJob::ProcessKeyValueCompaction, this,
@@ -538,7 +481,7 @@ Status CompactionJob::Run() {
     thread.join();
   }
 
-  if (output_directory_) {
+  if (output_directory_ && !db_options_.disableDataSync) {
     output_directory_->Fsync();
   }
 
@@ -575,31 +518,22 @@ Status CompactionJob::Run() {
   return status;
 }
 
-Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
+Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options,
+                              InstrumentedMutex* db_mutex) {
   AutoThreadOperationStageUpdater stage_updater(
       ThreadStatus::STAGE_COMPACTION_INSTALL);
-  db_mutex_->AssertHeld();
+  db_mutex->AssertHeld();
   Status status = compact_->status;
   ColumnFamilyData* cfd = compact_->compaction->column_family_data();
   cfd->internal_stats()->AddCompactionStats(
       compact_->compaction->output_level(), compaction_stats_);
 
   if (status.ok()) {
-    status = InstallCompactionResults(mutable_cf_options);
+    status = InstallCompactionResults(mutable_cf_options, db_mutex);
   }
   VersionStorageInfo::LevelSummaryStorage tmp;
   auto vstorage = cfd->current()->storage_info();
   const auto& stats = compaction_stats_;
-
-  double read_write_amp = 0.0;
-  double write_amp = 0.0;
-  if (stats.bytes_read_non_output_levels > 0) {
-    read_write_amp = (stats.bytes_written + stats.bytes_read_output_level +
-                      stats.bytes_read_non_output_levels) /
-                     static_cast<double>(stats.bytes_read_non_output_levels);
-    write_amp = stats.bytes_written /
-                static_cast<double>(stats.bytes_read_non_output_levels);
-  }
   LogToBuffer(
       log_buffer_,
       "[%s] compacted to: %s, MB/sec: %.1f rd, %.1f wr, level %d, "
@@ -612,10 +546,16 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
       stats.bytes_written / static_cast<double>(stats.micros),
       compact_->compaction->output_level(),
       stats.num_input_files_in_non_output_levels,
-      stats.num_input_files_in_output_level, stats.num_output_files,
+      stats.num_input_files_in_output_level,
+      stats.num_output_files,
       stats.bytes_read_non_output_levels / 1048576.0,
       stats.bytes_read_output_level / 1048576.0,
-      stats.bytes_written / 1048576.0, read_write_amp, write_amp,
+      stats.bytes_written / 1048576.0,
+      (stats.bytes_written + stats.bytes_read_output_level +
+       stats.bytes_read_non_output_levels) /
+          static_cast<double>(stats.bytes_read_non_output_levels),
+      stats.bytes_written /
+          static_cast<double>(stats.bytes_read_non_output_levels),
       status.ToString().c_str(), stats.num_input_records,
       stats.num_dropped_records);
 
@@ -632,13 +572,6 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
          << "num_output_records" << compact_->num_output_records
          << "num_subcompactions" << compact_->sub_compact_states.size();
 
-  if (compaction_job_stats_ != nullptr) {
-    stream << "num_single_delete_mismatches"
-           << compaction_job_stats_->num_single_del_mismatch;
-    stream << "num_single_delete_fallthrough"
-           << compaction_job_stats_->num_single_del_fallthru;
-  }
-
   if (measure_io_stats_ && compaction_job_stats_ != nullptr) {
     stream << "file_write_nanos" << compaction_job_stats_->file_write_nanos;
     stream << "file_range_sync_nanos"
@@ -661,11 +594,8 @@ Status CompactionJob::Install(const MutableCFOptions& mutable_cf_options) {
 
 void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   assert(sub_compact != nullptr);
-  ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
-  std::unique_ptr<RangeDelAggregator> range_del_agg(
-      new RangeDelAggregator(cfd->internal_comparator(), existing_snapshots_));
-  std::unique_ptr<InternalIterator> input(versions_->MakeInputIterator(
-      sub_compact->compaction, range_del_agg.get()));
+  std::unique_ptr<InternalIterator> input(
+      versions_->MakeInputIterator(sub_compact->compaction));
 
   AutoThreadOperationStageUpdater stage_updater(
       ThreadStatus::STAGE_COMPACTION_PROCESS_KV);
@@ -686,31 +616,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     prev_prepare_write_nanos = IOSTATS(prepare_write_nanos);
   }
 
-  const MutableCFOptions* mutable_cf_options =
-      sub_compact->compaction->mutable_cf_options();
-
-  // To build compression dictionary, we sample the first output file, assuming
-  // it'll reach the maximum length, and then use the dictionary for compressing
-  // subsequent output files. The dictionary may be less than max_dict_bytes if
-  // the first output file's length is less than the maximum.
-  const int kSampleLenShift = 6;  // 2^6 = 64-byte samples
-  std::set<size_t> sample_begin_offsets;
-  if (bottommost_level_ &&
-      cfd->ioptions()->compression_opts.max_dict_bytes > 0) {
-    const size_t kMaxSamples =
-        cfd->ioptions()->compression_opts.max_dict_bytes >> kSampleLenShift;
-    const size_t kOutFileLen = mutable_cf_options->MaxFileSizeForLevel(
-        compact_->compaction->output_level());
-    if (kOutFileLen != port::kMaxSizet) {
-      const size_t kOutFileNumSamples = kOutFileLen >> kSampleLenShift;
-      Random64 generator{versions_->NewFileNumber()};
-      for (size_t i = 0; i < kMaxSamples; ++i) {
-        sample_begin_offsets.insert(generator.Uniform(kOutFileNumSamples)
-                                    << kSampleLenShift);
-      }
-    }
-  }
-
+  ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
   auto compaction_filter = cfd->ioptions()->compaction_filter;
   std::unique_ptr<CompactionFilter> compaction_filter_from_factory = nullptr;
   if (compaction_filter == nullptr) {
@@ -721,10 +627,10 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   MergeHelper merge(
       env_, cfd->user_comparator(), cfd->ioptions()->merge_operator,
       compaction_filter, db_options_.info_log.get(),
+      cfd->ioptions()->min_partial_merge_operands,
       false /* internal key corruption is expected */,
       existing_snapshots_.empty() ? 0 : existing_snapshots_.back(),
-      compact_->compaction->level(), db_options_.statistics.get(),
-      shutting_down_);
+      compact_->compaction->level(), db_options_.statistics.get());
 
   TEST_SYNC_POINT("CompactionJob::Run():Inprogress");
 
@@ -742,27 +648,14 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   sub_compact->c_iter.reset(new CompactionIterator(
       input.get(), cfd->user_comparator(), &merge, versions_->LastSequence(),
       &existing_snapshots_, earliest_write_conflict_snapshot_, env_, false,
-      range_del_agg.get(), sub_compact->compaction, compaction_filter,
-      shutting_down_));
+      sub_compact->compaction, compaction_filter));
   auto c_iter = sub_compact->c_iter.get();
   c_iter->SeekToFirst();
-  if (c_iter->Valid() &&
-      sub_compact->compaction->output_level() != 0) {
-    // ShouldStopBefore() maintains state based on keys processed so far. The
-    // compaction loop always calls it on the "next" key, thus won't tell it the
-    // first key. So we do that here.
-    sub_compact->ShouldStopBefore(
-      c_iter->key(), sub_compact->current_output_file_size);
-  }
   const auto& c_iter_stats = c_iter->iter_stats();
-  auto sample_begin_offset_iter = sample_begin_offsets.cbegin();
-  // data_begin_offset and compression_dict are only valid while generating
-  // dictionary from the first output file.
-  size_t data_begin_offset = 0;
-  std::string compression_dict;
-  compression_dict.reserve(cfd->ioptions()->compression_opts.max_dict_bytes);
-
-  while (status.ok() && !cfd->IsDropped() && c_iter->Valid()) {
+  // TODO(noetzli): check whether we could check !shutting_down_->... only
+  // only occasionally (see diff D42687)
+  while (status.ok() && !shutting_down_->load(std::memory_order_acquire) &&
+         !cfd->IsDropped() && c_iter->Valid()) {
     // Invariant: c_iter.status() is guaranteed to be OK if c_iter->Valid()
     // returns true.
     const Slice& key = c_iter->key();
@@ -773,7 +666,14 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
     if (end != nullptr &&
         cfd->user_comparator()->Compare(c_iter->user_key(), *end) >= 0) {
       break;
+    } else if (sub_compact->compaction->ShouldStopBefore(key) &&
+               sub_compact->builder != nullptr) {
+      status = FinishCompactionOutputFile(input->status(), sub_compact);
+      if (!status.ok()) {
+        break;
+      }
     }
+
     if (c_iter_stats.num_input_records % kRecordStatsEvery ==
         kRecordStatsEvery - 1) {
       RecordDroppedKeys(c_iter_stats, &sub_compact->compaction_job_stats);
@@ -791,107 +691,21 @@ 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->FileSize();
     sub_compact->current_output()->meta.UpdateBoundaries(
         key, c_iter->ikey().sequence);
     sub_compact->num_output_records++;
 
-    if (sub_compact->outputs.size() == 1) {  // first output file
-      // Check if this key/value overlaps any sample intervals; if so, appends
-      // overlapping portions to the dictionary.
-      for (const auto& data_elmt : {key, value}) {
-        size_t data_end_offset = data_begin_offset + data_elmt.size();
-        while (sample_begin_offset_iter != sample_begin_offsets.cend() &&
-               *sample_begin_offset_iter < data_end_offset) {
-          size_t sample_end_offset =
-              *sample_begin_offset_iter + (1 << kSampleLenShift);
-          // Invariant: Because we advance sample iterator while processing the
-          // data_elmt containing the sample's last byte, the current sample
-          // cannot end before the current data_elmt.
-          assert(data_begin_offset < sample_end_offset);
-
-          size_t data_elmt_copy_offset, data_elmt_copy_len;
-          if (*sample_begin_offset_iter <= data_begin_offset) {
-            // The sample starts before data_elmt starts, so take bytes starting
-            // at the beginning of data_elmt.
-            data_elmt_copy_offset = 0;
-          } else {
-            // data_elmt starts before the sample starts, so take bytes starting
-            // at the below offset into data_elmt.
-            data_elmt_copy_offset =
-                *sample_begin_offset_iter - data_begin_offset;
-          }
-          if (sample_end_offset <= data_end_offset) {
-            // The sample ends before data_elmt ends, so take as many bytes as
-            // needed.
-            data_elmt_copy_len =
-                sample_end_offset - (data_begin_offset + data_elmt_copy_offset);
-          } else {
-            // data_elmt ends before the sample ends, so take all remaining
-            // bytes in data_elmt.
-            data_elmt_copy_len =
-                data_end_offset - (data_begin_offset + data_elmt_copy_offset);
-          }
-          compression_dict.append(&data_elmt.data()[data_elmt_copy_offset],
-                                  data_elmt_copy_len);
-          if (sample_end_offset > data_end_offset) {
-            // Didn't finish sample. Try to finish it with the next data_elmt.
-            break;
-          }
-          // Next sample may require bytes from same data_elmt.
-          sample_begin_offset_iter++;
-        }
-        data_begin_offset = data_end_offset;
-      }
-    }
-
-    // Close output file if it is big enough. Two possibilities determine it's
-    // time to close it: (1) the current key should be this file's last key, (2)
-    // the next key should not be in this file.
-    //
+    // Close output file if it is big enough
     // TODO(aekmekji): determine if file should be closed earlier than this
     // during subcompactions (i.e. if output size, estimated by input size, is
     // going to be 1.2MB and max_output_file_size = 1MB, prefer to have 0.6MB
     // and 0.6MB instead of 1MB and 0.2MB)
-    bool output_file_ended = false;
-    Status input_status;
-    if (sub_compact->compaction->output_level() != 0 &&
-        sub_compact->current_output_file_size >=
-            sub_compact->compaction->max_output_file_size()) {
-      // (1) this key terminates the file. For historical reasons, the iterator
-      // status before advancing will be given to FinishCompactionOutputFile().
-      input_status = input->status();
-      output_file_ended = true;
+    if (sub_compact->builder->FileSize() >=
+        sub_compact->compaction->max_output_file_size()) {
+      status = FinishCompactionOutputFile(input->status(), sub_compact);
     }
+
     c_iter->Next();
-    if (!output_file_ended && c_iter->Valid() &&
-        sub_compact->compaction->output_level() != 0 &&
-        sub_compact->ShouldStopBefore(
-          c_iter->key(), sub_compact->current_output_file_size) &&
-        sub_compact->builder != nullptr) {
-      // (2) this key belongs to the next file. For historical reasons, the
-      // iterator status after advancing will be given to
-      // FinishCompactionOutputFile().
-      input_status = input->status();
-      output_file_ended = true;
-    }
-    if (output_file_ended) {
-      const Slice* next_key = nullptr;
-      if (c_iter->Valid()) {
-        next_key = &c_iter->key();
-      }
-      CompactionIterationStats range_del_out_stats;
-      status = FinishCompactionOutputFile(input_status, sub_compact,
-                                          range_del_agg.get(),
-                                          &range_del_out_stats, next_key);
-      RecordDroppedKeys(range_del_out_stats,
-                        &sub_compact->compaction_job_stats);
-      if (sub_compact->outputs.size() == 1) {
-        // Use dictionary from first output file for compression of subsequent
-        // files.
-        sub_compact->compression_dict = std::move(compression_dict);
-      }
-    }
   }
 
   sub_compact->num_input_records = c_iter_stats.num_input_records;
@@ -899,10 +713,6 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
       c_iter_stats.num_input_deletion_records;
   sub_compact->compaction_job_stats.num_corrupt_keys =
       c_iter_stats.num_input_corrupt_records;
-  sub_compact->compaction_job_stats.num_single_del_fallthru =
-      c_iter_stats.num_single_del_fallthru;
-  sub_compact->compaction_job_stats.num_single_del_mismatch =
-      c_iter_stats.num_single_del_mismatch;
   sub_compact->compaction_job_stats.total_input_raw_key_bytes +=
       c_iter_stats.total_input_raw_key_bytes;
   sub_compact->compaction_job_stats.total_input_raw_value_bytes +=
@@ -913,36 +723,17 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
   RecordDroppedKeys(c_iter_stats, &sub_compact->compaction_job_stats);
   RecordCompactionIOStats();
 
-  if (status.ok() && (shutting_down_->load(std::memory_order_relaxed) ||
-                      cfd->IsDropped())) {
+  if (status.ok() &&
+      (shutting_down_->load(std::memory_order_acquire) || cfd->IsDropped())) {
     status = Status::ShutdownInProgress(
         "Database shutdown or Column family drop during compaction");
   }
+  if (status.ok() && sub_compact->builder != nullptr) {
+    status = FinishCompactionOutputFile(input->status(), sub_compact);
+  }
   if (status.ok()) {
     status = input->status();
   }
-  if (status.ok()) {
-    status = c_iter->status();
-  }
-
-  if (status.ok() && sub_compact->builder == nullptr &&
-      sub_compact->outputs.size() == 0 &&
-      range_del_agg->ShouldAddTombstones(bottommost_level_)) {
-    // handle subcompaction containing only range deletions
-    status = OpenCompactionOutputFile(sub_compact);
-  }
-
-  // Call FinishCompactionOutputFile() even if status is not ok: it needs to
-  // close the output file.
-  if (sub_compact->builder != nullptr) {
-    CompactionIterationStats range_del_out_stats;
-    Status s = FinishCompactionOutputFile(
-        status, sub_compact, range_del_agg.get(), &range_del_out_stats);
-    if (status.ok()) {
-      status = s;
-    }
-    RecordDroppedKeys(range_del_out_stats, &sub_compact->compaction_job_stats);
-  }
 
   if (measure_io_stats_) {
     sub_compact->compaction_job_stats.file_write_nanos +=
@@ -964,7 +755,7 @@ void CompactionJob::ProcessKeyValueCompaction(SubcompactionState* sub_compact) {
 }
 
 void CompactionJob::RecordDroppedKeys(
-    const CompactionIterationStats& c_iter_stats,
+    const CompactionIteratorStats& c_iter_stats,
     CompactionJobStats* compaction_job_stats) {
   if (c_iter_stats.num_record_drop_user > 0) {
     RecordTick(stats_, COMPACTION_KEY_DROP_USER,
@@ -986,21 +777,10 @@ void CompactionJob::RecordDroppedKeys(
           c_iter_stats.num_record_drop_obsolete;
     }
   }
-  if (c_iter_stats.num_record_drop_range_del > 0) {
-    RecordTick(stats_, COMPACTION_KEY_DROP_RANGE_DEL,
-               c_iter_stats.num_record_drop_range_del);
-  }
-  if (c_iter_stats.num_range_del_drop_obsolete > 0) {
-    RecordTick(stats_, COMPACTION_RANGE_DEL_DROP_OBSOLETE,
-               c_iter_stats.num_range_del_drop_obsolete);
-  }
 }
 
 Status CompactionJob::FinishCompactionOutputFile(
-    const Status& input_status, SubcompactionState* sub_compact,
-    RangeDelAggregator* range_del_agg,
-    CompactionIterationStats* range_del_out_stats,
-    const Slice* next_table_min_key /* = nullptr */) {
+    const Status& input_status, SubcompactionState* sub_compact) {
   AutoThreadOperationStageUpdater stage_updater(
       ThreadStatus::STAGE_COMPACTION_SYNC_FILE);
   assert(sub_compact != nullptr);
@@ -1015,36 +795,6 @@ Status CompactionJob::FinishCompactionOutputFile(
   // Check for iterator errors
   Status s = input_status;
   auto meta = &sub_compact->current_output()->meta;
-  if (s.ok()) {
-    Slice lower_bound_guard, upper_bound_guard;
-    const Slice *lower_bound, *upper_bound;
-    if (sub_compact->outputs.size() == 1) {
-      // For the first output table, include range tombstones before the min key
-      // but after the subcompaction boundary.
-      lower_bound = sub_compact->start;
-    } else if (meta->smallest.size() > 0) {
-      // For subsequent output tables, only include range tombstones from min
-      // key onwards since the previous file was extended to contain range
-      // tombstones falling before min key.
-      lower_bound_guard = meta->smallest.user_key();
-      lower_bound = &lower_bound_guard;
-    } else {
-      lower_bound = nullptr;
-    }
-    if (next_table_min_key != nullptr) {
-      // This isn't the last file in the subcompaction, so extend until the next
-      // file starts.
-      upper_bound_guard = ExtractUserKey(*next_table_min_key);
-      upper_bound = &upper_bound_guard;
-    } else {
-      // This is the last file in the subcompaction, so extend until the
-      // subcompaction ends.
-      upper_bound = sub_compact->end;
-    }
-    range_del_agg->AddToBuilder(sub_compact->builder.get(), lower_bound,
-                                upper_bound, meta, range_del_out_stats,
-                                bottommost_level_);
-  }
   const uint64_t current_entries = sub_compact->builder->NumEntries();
   meta->marked_for_compaction = sub_compact->builder->NeedCompact();
   if (s.ok()) {
@@ -1058,7 +808,7 @@ Status CompactionJob::FinishCompactionOutputFile(
   sub_compact->total_bytes += current_bytes;
 
   // Finish and check for file errors
-  if (s.ok()) {
+  if (s.ok() && !db_options_.disableDataSync) {
     StopWatch sw(env_, stats_, COMPACTION_OUTFILE_SYNC_MICROS);
     s = sub_compact->outfile->Sync(db_options_.use_fsync);
   }
@@ -1067,15 +817,13 @@ Status CompactionJob::FinishCompactionOutputFile(
   }
   sub_compact->outfile.reset();
 
-  ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
-  TableProperties tp;
   if (s.ok() && current_entries > 0) {
     // Verify that the table is usable
+    ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
     InternalIterator* iter = cfd->table_cache()->NewIterator(
         ReadOptions(), env_options_, cfd->internal_comparator(), meta->fd,
-        nullptr /* range_del_agg */, nullptr,
-        cfd->internal_stats()->GetFileReadHist(
-            compact_->compaction->output_level()),
+        nullptr, cfd->internal_stats()->GetFileReadHist(
+                     compact_->compaction->output_level()),
         false);
     s = iter->status();
 
@@ -1085,54 +833,35 @@ Status CompactionJob::FinishCompactionOutputFile(
     }
 
     delete iter;
-
-    // Output to event logger and fire events.
     if (s.ok()) {
-      tp = sub_compact->builder->GetTableProperties();
+      auto tp = sub_compact->builder->GetTableProperties();
       sub_compact->current_output()->table_properties =
           std::make_shared<TableProperties>(tp);
+      TableFileCreationInfo info(std::move(tp));
+      info.db_name = dbname_;
+      info.cf_name = cfd->GetName();
+      info.file_path =
+          TableFileName(cfd->ioptions()->db_paths, meta->fd.GetNumber(),
+                        meta->fd.GetPathId());
+      info.file_size = meta->fd.GetFileSize();
+      info.job_id = job_id_;
       Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
           "[%s] [JOB %d] Generated table #%" PRIu64 ": %" PRIu64
           " keys, %" PRIu64 " bytes%s",
           cfd->GetName().c_str(), job_id_, output_number, current_entries,
           current_bytes,
           meta->marked_for_compaction ? " (need compaction)" : "");
+      EventHelpers::LogAndNotifyTableFileCreation(
+          event_logger_, cfd->ioptions()->listeners, meta->fd, info);
     }
   }
-  std::string fname = TableFileName(db_options_.db_paths, meta->fd.GetNumber(),
-                                    meta->fd.GetPathId());
-  EventHelpers::LogAndNotifyTableFileCreationFinished(
-      event_logger_, cfd->ioptions()->listeners, dbname_, cfd->GetName(), fname,
-      job_id_, meta->fd, tp, TableFileCreationReason::kCompaction, s);
-
-#ifndef ROCKSDB_LITE
-  // Report new file to SstFileManagerImpl
-  auto sfm =
-      static_cast<SstFileManagerImpl*>(db_options_.sst_file_manager.get());
-  if (sfm && meta->fd.GetPathId() == 0) {
-    auto fn = TableFileName(cfd->ioptions()->db_paths, meta->fd.GetNumber(),
-                            meta->fd.GetPathId());
-    sfm->OnAddFile(fn);
-    if (sfm->IsMaxAllowedSpaceReached()) {
-      InstrumentedMutexLock l(db_mutex_);
-      if (db_bg_error_->ok()) {
-        s = Status::IOError("Max allowed space was reached");
-        *db_bg_error_ = s;
-        TEST_SYNC_POINT(
-            "CompactionJob::FinishCompactionOutputFile:MaxAllowedSpaceReached");
-      }
-    }
-  }
-#endif
-
   sub_compact->builder.reset();
-  sub_compact->current_output_file_size = 0;
   return s;
 }
 
 Status CompactionJob::InstallCompactionResults(
-    const MutableCFOptions& mutable_cf_options) {
-  db_mutex_->AssertHeld();
+    const MutableCFOptions& mutable_cf_options, InstrumentedMutex* db_mutex) {
+  db_mutex->AssertHeld();
 
   auto* compaction = compact_->compaction;
   // paranoia: verify that the files that we started with
@@ -1167,7 +896,7 @@ Status CompactionJob::InstallCompactionResults(
   }
   return versions_->LogAndApply(compaction->column_family_data(),
                                 mutable_cf_options, compaction->edit(),
-                                db_mutex_, db_directory_);
+                                db_mutex, db_directory_);
 }
 
 void CompactionJob::RecordCompactionIOStats() {
@@ -1187,17 +916,10 @@ Status CompactionJob::OpenCompactionOutputFile(
   assert(sub_compact->builder == nullptr);
   // no need to lock because VersionSet::next_file_number_ is atomic
   uint64_t file_number = versions_->NewFileNumber();
-  std::string fname = TableFileName(db_options_.db_paths, file_number,
-                                    sub_compact->compaction->output_path_id());
-  // Fire events.
-  ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
-#ifndef ROCKSDB_LITE
-  EventHelpers::NotifyTableFileCreationStarted(
-      cfd->ioptions()->listeners, dbname_, cfd->GetName(), fname, job_id_,
-      TableFileCreationReason::kCompaction);
-#endif  // !ROCKSDB_LITE
   // Make the output file
   unique_ptr<WritableFile> writable_file;
+  std::string fname = TableFileName(db_options_.db_paths, file_number,
+                                    sub_compact->compaction->output_path_id());
   Status s = NewWritableFile(env_, fname, &writable_file, env_options_);
   if (!s.ok()) {
     Log(InfoLogLevel::ERROR_LEVEL, db_options_.info_log,
@@ -1206,13 +928,8 @@ Status CompactionJob::OpenCompactionOutputFile(
         sub_compact->compaction->column_family_data()->GetName().c_str(),
         job_id_, file_number, s.ToString().c_str());
     LogFlush(db_options_.info_log);
-    EventHelpers::LogAndNotifyTableFileCreationFinished(
-        event_logger_, cfd->ioptions()->listeners, dbname_, cfd->GetName(),
-        fname, job_id_, FileDescriptor(), TableProperties(),
-        TableFileCreationReason::kCompaction, s);
     return s;
   }
-
   SubcompactionState::Output out;
   out.meta.fd =
       FileDescriptor(file_number, sub_compact->compaction->output_path_id(), 0);
@@ -1222,9 +939,10 @@ Status CompactionJob::OpenCompactionOutputFile(
   writable_file->SetIOPriority(Env::IO_LOW);
   writable_file->SetPreallocationBlockSize(static_cast<size_t>(
       sub_compact->compaction->OutputFilePreallocationSize()));
-  sub_compact->outfile.reset(new WritableFileWriter(
-      std::move(writable_file), env_options_, db_options_.statistics.get()));
+  sub_compact->outfile.reset(
+      new WritableFileWriter(std::move(writable_file), env_options_));
 
+  ColumnFamilyData* cfd = sub_compact->compaction->column_family_data();
   // 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
@@ -1232,12 +950,9 @@ Status CompactionJob::OpenCompactionOutputFile(
       cfd->ioptions()->optimize_filters_for_hits && bottommost_level_;
   sub_compact->builder.reset(NewTableBuilder(
       *cfd->ioptions(), cfd->internal_comparator(),
-      cfd->int_tbl_prop_collector_factories(), cfd->GetID(), cfd->GetName(),
+      cfd->int_tbl_prop_collector_factories(), cfd->GetID(),
       sub_compact->outfile.get(), sub_compact->compaction->output_compression(),
-      cfd->ioptions()->compression_opts,
-      sub_compact->compaction->output_level(),
-      &sub_compact->compression_dict,
-      skip_filters));
+      cfd->ioptions()->compression_opts, skip_filters));
   LogFlush(db_options_.info_log);
   return s;
 }
@@ -1284,7 +999,8 @@ void CompactionJob::UpdateCompactionStats() {
   for (int input_level = 0;
        input_level < static_cast<int>(compaction->num_input_levels());
        ++input_level) {
-    if (compaction->level(input_level) != compaction->output_level()) {
+    if (compaction->start_level() + input_level
+        != compaction->output_level()) {
       UpdateCompactionInputStatsHelper(
           &compaction_stats_.num_input_files_in_non_output_levels,
           &compaction_stats_.bytes_read_non_output_levels,

db/compaction_job.h

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -25,7 +25,6 @@
 #include "db/job_context.h"
 #include "db/log_writer.h"
 #include "db/memtable_list.h"
-#include "db/range_del_aggregator.h"
 #include "db/version_edit.h"
 #include "db/write_controller.h"
 #include "db/write_thread.h"
@@ -38,7 +37,6 @@
 #include "rocksdb/transaction_log.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
-#include "util/db_options.h"
 #include "util/event_logger.h"
 #include "util/stop_watch.h"
 #include "util/thread_local.h"
@@ -54,13 +52,11 @@ class Arena;
 
 class CompactionJob {
  public:
-  CompactionJob(int job_id, Compaction* compaction,
-                const ImmutableDBOptions& db_options,
+  CompactionJob(int job_id, Compaction* compaction, const DBOptions& db_options,
                 const EnvOptions& env_options, VersionSet* versions,
-                const std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
+                std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
                 Directory* db_directory, Directory* output_directory,
-                Statistics* stats, InstrumentedMutex* db_mutex,
-                Status* db_bg_error,
+                Statistics* stats,
                 std::vector<SequenceNumber> existing_snapshots,
                 SequenceNumber earliest_write_conflict_snapshot,
                 std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
@@ -81,7 +77,8 @@ class CompactionJob {
   Status Run();
 
   // REQUIRED: mutex held
-  Status Install(const MutableCFOptions& mutable_cf_options);
+  Status Install(const MutableCFOptions& mutable_cf_options,
+                 InstrumentedMutex* db_mutex);
 
  private:
   struct SubcompactionState;
@@ -96,18 +93,16 @@ class CompactionJob {
   // kv-pairs
   void ProcessKeyValueCompaction(SubcompactionState* sub_compact);
 
-  Status FinishCompactionOutputFile(
-      const Status& input_status, SubcompactionState* sub_compact,
-      RangeDelAggregator* range_del_agg,
-      CompactionIterationStats* range_del_out_stats,
-      const Slice* next_table_min_key = nullptr);
-  Status InstallCompactionResults(const MutableCFOptions& mutable_cf_options);
+  Status FinishCompactionOutputFile(const Status& input_status,
+                                    SubcompactionState* sub_compact);
+  Status InstallCompactionResults(const MutableCFOptions& mutable_cf_options,
+                                  InstrumentedMutex* db_mutex);
   void RecordCompactionIOStats();
   Status OpenCompactionOutputFile(SubcompactionState* sub_compact);
   void CleanupCompaction();
   void UpdateCompactionJobStats(
     const InternalStats::CompactionStats& stats) const;
-  void RecordDroppedKeys(const CompactionIterationStats& c_iter_stats,
+  void RecordDroppedKeys(const CompactionIteratorStats& c_iter_stats,
                          CompactionJobStats* compaction_job_stats = nullptr);
 
   void UpdateCompactionStats();
@@ -126,18 +121,15 @@ class CompactionJob {
 
   // DBImpl state
   const std::string& dbname_;
-  const ImmutableDBOptions& db_options_;
+  const DBOptions& db_options_;
   const EnvOptions& env_options_;
-
   Env* env_;
   VersionSet* versions_;
-  const std::atomic<bool>* shutting_down_;
+  std::atomic<bool>* shutting_down_;
   LogBuffer* log_buffer_;
   Directory* db_directory_;
   Directory* output_directory_;
   Statistics* stats_;
-  InstrumentedMutex* db_mutex_;
-  Status* db_bg_error_;
   // If there were two snapshots with seq numbers s1 and
   // s2 and s1 < s2, and if we find two instances of a key k1 then lies
   // entirely within s1 and s2, then the earlier version of k1 can be safely

db/compaction_job_stats_test.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -61,6 +61,7 @@
 #include "util/testharness.h"
 #include "util/testutil.h"
 #include "util/thread_status_util.h"
+#include "util/xfunc.h"
 #include "utilities/merge_operators.h"
 
 #if !defined(IOS_CROSS_COMPILE)
@@ -623,10 +624,7 @@ CompressionType GetAnyCompression() {
     return kBZip2Compression;
   } else if (LZ4_Supported()) {
     return kLZ4Compression;
-  } else if (XPRESS_Supported()) {
-    return kXpressCompression;
   }
-
   return kNoCompression;
 }
 
@@ -662,7 +660,7 @@ TEST_P(CompactionJobStatsTest, CompactionJobStatsTest) {
   options.max_subcompactions = max_subcompactions_;
   options.bytes_per_sync = 512 * 1024;
 
-  options.report_bg_io_stats = true;
+  options.compaction_measure_io_stats = true;
   for (int test = 0; test < 2; ++test) {
     DestroyAndReopen(options);
     CreateAndReopenWithCF({"pikachu"}, options);
@@ -956,7 +954,7 @@ TEST_P(CompactionJobStatsTest, UniversalCompactionTest) {
   uint64_t key_base = 100000000l;
   // Note: key_base must be multiple of num_keys_per_L0_file
   int num_keys_per_table = 100;
-  const uint32_t kTestScale = 6;
+  const uint32_t kTestScale = 8;
   const int kKeySize = 10;
   const int kValueSize = 900;
   double compression_ratio = 1.0;
@@ -1007,9 +1005,8 @@ TEST_P(CompactionJobStatsTest, UniversalCompactionTest) {
             num_input_units,
             num_keys_per_table * num_input_units,
             1.0, 0, false));
-    dbfull()->TEST_WaitForCompact();
   }
-  ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 3U);
+  ASSERT_EQ(stats_checker->NumberOfUnverifiedStats(), 4U);
 
   for (uint64_t start_key = key_base;
                 start_key <= key_base * kTestScale;

db/compaction_job_test.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 #ifndef ROCKSDB_LITE
 
@@ -10,13 +10,13 @@
 #include <string>
 #include <tuple>
 
-#include "db/column_family.h"
 #include "db/compaction_job.h"
+#include "db/column_family.h"
 #include "db/version_set.h"
+#include "db/writebuffer.h"
 #include "rocksdb/cache.h"
 #include "rocksdb/db.h"
 #include "rocksdb/options.h"
-#include "rocksdb/write_buffer_manager.h"
 #include "table/mock_table.h"
 #include "util/file_reader_writer.h"
 #include "util/string_util.h"
@@ -68,12 +68,11 @@ class CompactionJobTest : public testing::Test {
   CompactionJobTest()
       : env_(Env::Default()),
         dbname_(test::TmpDir() + "/compaction_job_test"),
-        db_options_(),
-        mutable_cf_options_(cf_options_),
+        mutable_cf_options_(Options(), ImmutableCFOptions(Options())),
         table_cache_(NewLRUCache(50000, 16)),
-        write_buffer_manager_(db_options_.db_write_buffer_size),
+        write_buffer_(db_options_.db_write_buffer_size),
         versions_(new VersionSet(dbname_, &db_options_, env_options_,
-                                 table_cache_.get(), &write_buffer_manager_,
+                                 table_cache_.get(), &write_buffer_,
                                  &write_controller_)),
         shutting_down_(false),
         mock_table_factory_(new mock::MockTableFactory()) {
@@ -240,10 +239,10 @@ class CompactionJobTest : public testing::Test {
       num_input_files += level_files.size();
     }
 
-    Compaction compaction(cfd->current()->storage_info(), *cfd->ioptions(),
+    Compaction compaction(cfd->current()->storage_info(),
                           *cfd->GetLatestMutableCFOptions(),
-                          compaction_input_files, 1, 1024 * 1024,
-                          10 * 1024 * 1024, 0, kNoCompression, {}, true);
+                          compaction_input_files, 1, 1024 * 1024, 10, 0,
+                          kNoCompression, {}, true);
     compaction.SetInputVersion(cfd->current());
 
     LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, db_options_.info_log.get());
@@ -251,9 +250,9 @@ class CompactionJobTest : public testing::Test {
     EventLogger event_logger(db_options_.info_log.get());
     CompactionJob compaction_job(
         0, &compaction, db_options_, env_options_, versions_.get(),
-        &shutting_down_, &log_buffer, nullptr, nullptr, nullptr, &mutex_,
-        &bg_error_, snapshots, earliest_write_conflict_snapshot, table_cache_,
-        &event_logger, false, false, dbname_, &compaction_job_stats_);
+        &shutting_down_, &log_buffer, nullptr, nullptr, nullptr, snapshots,
+        earliest_write_conflict_snapshot, table_cache_, &event_logger, false,
+        false, dbname_, &compaction_job_stats_);
 
     VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
 
@@ -263,7 +262,8 @@ class CompactionJobTest : public testing::Test {
     s = compaction_job.Run();
     ASSERT_OK(s);
     mutex_.Lock();
-    ASSERT_OK(compaction_job.Install(*cfd->GetLatestMutableCFOptions()));
+    ASSERT_OK(compaction_job.Install(*cfd->GetLatestMutableCFOptions(),
+                                     &mutex_));
     mutex_.Unlock();
 
     if (expected_results.size() == 0) {
@@ -281,12 +281,12 @@ class CompactionJobTest : public testing::Test {
   Env* env_;
   std::string dbname_;
   EnvOptions env_options_;
-  ImmutableDBOptions db_options_;
-  ColumnFamilyOptions cf_options_;
   MutableCFOptions mutable_cf_options_;
   std::shared_ptr<Cache> table_cache_;
   WriteController write_controller_;
-  WriteBufferManager write_buffer_manager_;
+  DBOptions db_options_;
+  ColumnFamilyOptions cf_options_;
+  WriteBuffer write_buffer_;
   std::unique_ptr<VersionSet> versions_;
   InstrumentedMutex mutex_;
   std::atomic<bool> shutting_down_;
@@ -295,7 +295,6 @@ class CompactionJobTest : public testing::Test {
   ColumnFamilyData* cfd_;
   std::unique_ptr<CompactionFilter> compaction_filter_;
   std::shared_ptr<MergeOperator> merge_op_;
-  Status bg_error_;
 };
 
 TEST_F(CompactionJobTest, Simple) {

db/compaction_picker.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -18,6 +18,7 @@
 #include <queue>
 #include <string>
 #include <utility>
+
 #include "db/column_family.h"
 #include "db/filename.h"
 #include "util/log_buffer.h"
@@ -69,8 +70,7 @@ struct UserKeyComparator {
 };
 
 typedef std::priority_queue<InputFileInfo, std::vector<InputFileInfo>,
-                            UserKeyComparator>
-    SmallestKeyHeap;
+                            UserKeyComparator> SmallestKeyHeap;
 
 // This function creates the heap that is used to find if the files are
 // overlapping during universal compaction when the allow_trivial_move
@@ -109,22 +109,13 @@ SmallestKeyHeap create_level_heap(Compaction* c, const Comparator* ucmp) {
 // matter what the values of the other two parameters are.
 // Otherwise, the compression type is determined based on options and level.
 CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
-                                   const VersionStorageInfo* vstorage,
-                                   const MutableCFOptions& mutable_cf_options,
                                    int level, int base_level,
                                    const bool enable_compression) {
   if (!enable_compression) {
     // disable compression
     return kNoCompression;
   }
-
-  // If bottommost_compression is set and we are compacting to the
-  // bottommost level then we should use it.
-  if (ioptions.bottommost_compression != kDisableCompressionOption &&
-      level > base_level && level >= (vstorage->num_non_empty_levels() - 1)) {
-    return ioptions.bottommost_compression;
-  }
-  // If the user has specified a different compression level for each level,
+  // If the use has specified a different compression level for each level,
   // then pick the compression for that level.
   if (!ioptions.compression_per_level.empty()) {
     assert(level == 0 || level >= base_level);
@@ -138,7 +129,7 @@ CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
     // specified compression levels, use the last value.
     return ioptions.compression_per_level[std::max(0, std::min(idx, n))];
   } else {
-    return mutable_cf_options.compression;
+    return ioptions.compression;
   }
 }
 
@@ -150,15 +141,16 @@ CompactionPicker::~CompactionPicker() {}
 
 // Delete this compaction from the list of running compactions.
 void CompactionPicker::ReleaseCompactionFiles(Compaction* c, Status status) {
-  UnregisterCompaction(c);
+  if (c->start_level() == 0) {
+    level0_compactions_in_progress_.erase(c);
+  }
   if (!status.ok()) {
     c->ResetNextCompactionIndex();
   }
 }
 
 void CompactionPicker::GetRange(const CompactionInputFiles& inputs,
-                                InternalKey* smallest,
-                                InternalKey* largest) const {
+                                InternalKey* smallest, InternalKey* largest) {
   const int level = inputs.level;
   assert(!inputs.empty());
   smallest->Clear();
@@ -187,8 +179,7 @@ void CompactionPicker::GetRange(const CompactionInputFiles& inputs,
 
 void CompactionPicker::GetRange(const CompactionInputFiles& inputs1,
                                 const CompactionInputFiles& inputs2,
-                                InternalKey* smallest,
-                                InternalKey* largest) const {
+                                InternalKey* smallest, InternalKey* largest) {
   assert(!inputs1.empty() || !inputs2.empty());
   if (inputs1.empty()) {
     GetRange(inputs2, smallest, largest);
@@ -198,39 +189,13 @@ void CompactionPicker::GetRange(const CompactionInputFiles& inputs1,
     InternalKey smallest1, smallest2, largest1, largest2;
     GetRange(inputs1, &smallest1, &largest1);
     GetRange(inputs2, &smallest2, &largest2);
-    *smallest =
-        icmp_->Compare(smallest1, smallest2) < 0 ? smallest1 : smallest2;
-    *largest = icmp_->Compare(largest1, largest2) < 0 ? largest2 : largest1;
+    *smallest = icmp_->Compare(smallest1, smallest2) < 0 ?
+                smallest1 : smallest2;
+    *largest = icmp_->Compare(largest1, largest2) < 0 ?
+               largest2 : largest1;
   }
 }
 
-void CompactionPicker::GetRange(const std::vector<CompactionInputFiles>& inputs,
-                                InternalKey* smallest,
-                                InternalKey* largest) const {
-  InternalKey current_smallest;
-  InternalKey current_largest;
-  bool initialized = false;
-  for (const auto& in : inputs) {
-    if (in.empty()) {
-      continue;
-    }
-    GetRange(in, &current_smallest, &current_largest);
-    if (!initialized) {
-      *smallest = current_smallest;
-      *largest = current_largest;
-      initialized = true;
-    } else {
-      if (icmp_->Compare(current_smallest, *smallest) < 0) {
-        *smallest = current_smallest;
-      }
-      if (icmp_->Compare(current_largest, *largest) > 0) {
-        *largest = current_largest;
-      }
-    }
-  }
-  assert(initialized);
-}
-
 bool CompactionPicker::ExpandWhileOverlapping(const std::string& cf_name,
                                               VersionStorageInfo* vstorage,
                                               CompactionInputFiles* inputs) {
@@ -275,42 +240,6 @@ bool CompactionPicker::ExpandWhileOverlapping(const std::string& cf_name,
   return true;
 }
 
-bool CompactionPicker::RangeOverlapWithCompaction(
-    const Slice& smallest_user_key, const Slice& largest_user_key,
-    int level) const {
-  const Comparator* ucmp = icmp_->user_comparator();
-  for (Compaction* c : compactions_in_progress_) {
-    if (c->output_level() == level &&
-        ucmp->Compare(smallest_user_key, c->GetLargestUserKey()) <= 0 &&
-        ucmp->Compare(largest_user_key, c->GetSmallestUserKey()) >= 0) {
-      // Overlap
-      return true;
-    }
-  }
-  // Did not overlap with any running compaction in level `level`
-  return false;
-}
-
-bool CompactionPicker::FilesRangeOverlapWithCompaction(
-    const std::vector<CompactionInputFiles>& inputs, int level) const {
-  bool is_empty = true;
-  for (auto& in : inputs) {
-    if (!in.empty()) {
-      is_empty = false;
-      break;
-    }
-  }
-  if (is_empty) {
-    // No files in inputs
-    return false;
-  }
-
-  InternalKey smallest, largest;
-  GetRange(inputs, &smallest, &largest);
-  return RangeOverlapWithCompaction(smallest.user_key(), largest.user_key(),
-                                    level);
-}
-
 // Returns true if any one of specified files are being compacted
 bool CompactionPicker::FilesInCompaction(
     const std::vector<FileMetaData*>& files) {
@@ -327,6 +256,10 @@ Compaction* CompactionPicker::FormCompaction(
     const std::vector<CompactionInputFiles>& input_files, int output_level,
     VersionStorageInfo* vstorage, const MutableCFOptions& mutable_cf_options,
     uint32_t output_path_id) {
+  uint64_t max_grandparent_overlap_bytes =
+      output_level + 1 < vstorage->num_levels() ?
+          mutable_cf_options.MaxGrandParentOverlapBytes(output_level + 1) :
+          std::numeric_limits<uint64_t>::max();
   assert(input_files.size());
 
   // TODO(rven ): we might be able to run concurrent level 0 compaction
@@ -335,25 +268,23 @@ Compaction* CompactionPicker::FormCompaction(
   if ((input_files[0].level == 0) && !level0_compactions_in_progress_.empty()) {
     return nullptr;
   }
-  // This compaction output could overlap with a running compaction
-  if (FilesRangeOverlapWithCompaction(input_files, output_level)) {
-    return nullptr;
-  }
-  auto c =
-      new Compaction(vstorage, ioptions_, mutable_cf_options, input_files,
-                     output_level, compact_options.output_file_size_limit,
-                     mutable_cf_options.max_compaction_bytes, output_path_id,
-                     compact_options.compression, /* grandparents */ {}, true);
+  auto c = new Compaction(
+      vstorage, mutable_cf_options, input_files, output_level,
+      compact_options.output_file_size_limit, max_grandparent_overlap_bytes,
+      output_path_id, compact_options.compression, /* grandparents */ {}, true);
 
   // If it's level 0 compaction, make sure we don't execute any other level 0
   // compactions in parallel
-  RegisterCompaction(c);
+  if ((c != nullptr) && (input_files[0].level == 0)) {
+    level0_compactions_in_progress_.insert(c);
+  }
   return c;
 }
 
 Status CompactionPicker::GetCompactionInputsFromFileNumbers(
     std::vector<CompactionInputFiles>* input_files,
-    std::unordered_set<uint64_t>* input_set, const VersionStorageInfo* vstorage,
+    std::unordered_set<uint64_t>* input_set,
+    const VersionStorageInfo* vstorage,
     const CompactionOptions& compact_options) const {
   if (input_set->size() == 0U) {
     return Status::InvalidArgument(
@@ -391,8 +322,8 @@ Status CompactionPicker::GetCompactionInputsFromFileNumbers(
     return Status::InvalidArgument(message);
   }
 
-  for (int level = first_non_empty_level; level <= last_non_empty_level;
-       ++level) {
+  for (int level = first_non_empty_level;
+       level <= last_non_empty_level; ++level) {
     matched_input_files[level].level = level;
     input_files->emplace_back(std::move(matched_input_files[level]));
   }
@@ -400,6 +331,8 @@ Status CompactionPicker::GetCompactionInputsFromFileNumbers(
   return Status::OK();
 }
 
+
+
 // Returns true if any one of the parent files are being compacted
 bool CompactionPicker::RangeInCompaction(VersionStorageInfo* vstorage,
                                          const InternalKey* smallest,
@@ -450,14 +383,10 @@ bool CompactionPicker::SetupOtherInputs(
   vstorage->GetOverlappingInputs(output_level, &smallest, &largest,
                                  &output_level_inputs->files, *parent_index,
                                  parent_index);
+
   if (FilesInCompaction(output_level_inputs->files)) {
     return false;
   }
-  if (!output_level_inputs->empty()) {
-    if (!ExpandWhileOverlapping(cf_name, vstorage, output_level_inputs)) {
-      return false;
-    }
-  }
 
   // See if we can further grow the number of inputs in "level" without
   // changing the number of "level+1" files we pick up. We also choose NOT
@@ -465,66 +394,46 @@ bool CompactionPicker::SetupOtherInputs(
   // user key, while excluding other entries for the same user key. This
   // can happen when one user key spans multiple files.
   if (!output_level_inputs->empty()) {
-    const uint64_t limit = mutable_cf_options.max_compaction_bytes;
-    const uint64_t output_level_inputs_size =
-        TotalCompensatedFileSize(output_level_inputs->files);
-    const uint64_t inputs_size = TotalCompensatedFileSize(inputs->files);
-    bool expand_inputs = false;
-
-    CompactionInputFiles expanded_inputs;
-    expanded_inputs.level = input_level;
-    // Get closed interval of output level
+    CompactionInputFiles expanded0;
+    expanded0.level = input_level;
+    // Get entire range covered by compaction
     InternalKey all_start, all_limit;
     GetRange(*inputs, *output_level_inputs, &all_start, &all_limit);
-    bool try_overlapping_inputs = true;
+
     vstorage->GetOverlappingInputs(input_level, &all_start, &all_limit,
-                                   &expanded_inputs.files, base_index, nullptr);
-    uint64_t expanded_inputs_size =
-        TotalCompensatedFileSize(expanded_inputs.files);
-    if (!ExpandWhileOverlapping(cf_name, vstorage, &expanded_inputs)) {
-      try_overlapping_inputs = false;
-    }
-    if (try_overlapping_inputs && expanded_inputs.size() > inputs->size() &&
-        output_level_inputs_size + expanded_inputs_size < limit &&
-        !FilesInCompaction(expanded_inputs.files)) {
+                                   &expanded0.files, base_index, nullptr);
+    const uint64_t inputs0_size = TotalCompensatedFileSize(inputs->files);
+    const uint64_t inputs1_size =
+        TotalCompensatedFileSize(output_level_inputs->files);
+    const uint64_t expanded0_size = TotalCompensatedFileSize(expanded0.files);
+    uint64_t limit =
+        mutable_cf_options.ExpandedCompactionByteSizeLimit(input_level);
+    if (expanded0.size() > inputs->size() &&
+        inputs1_size + expanded0_size < limit &&
+        !FilesInCompaction(expanded0.files) &&
+        !vstorage->HasOverlappingUserKey(&expanded0.files, input_level)) {
       InternalKey new_start, new_limit;
-      GetRange(expanded_inputs, &new_start, &new_limit);
-      CompactionInputFiles expanded_output_level_inputs;
-      expanded_output_level_inputs.level = output_level;
+      GetRange(expanded0, &new_start, &new_limit);
+      std::vector<FileMetaData*> expanded1;
       vstorage->GetOverlappingInputs(output_level, &new_start, &new_limit,
-                                     &expanded_output_level_inputs.files,
-                                     *parent_index, parent_index);
-      assert(!expanded_output_level_inputs.empty());
-      if (!FilesInCompaction(expanded_output_level_inputs.files) &&
-          ExpandWhileOverlapping(cf_name, vstorage,
-                                 &expanded_output_level_inputs) &&
-          expanded_output_level_inputs.size() == output_level_inputs->size()) {
-        expand_inputs = true;
+                                     &expanded1, *parent_index, parent_index);
+      if (expanded1.size() == output_level_inputs->size() &&
+          !FilesInCompaction(expanded1)) {
+        Log(InfoLogLevel::INFO_LEVEL, ioptions_.info_log,
+            "[%s] Expanding@%d %" ROCKSDB_PRIszt "+%" ROCKSDB_PRIszt "(%" PRIu64
+            "+%" PRIu64 " bytes) to %" ROCKSDB_PRIszt "+%" ROCKSDB_PRIszt
+            " (%" PRIu64 "+%" PRIu64 "bytes)\n",
+            cf_name.c_str(), input_level, inputs->size(),
+            output_level_inputs->size(), inputs0_size, inputs1_size,
+            expanded0.size(), expanded1.size(), expanded0_size, inputs1_size);
+        smallest = new_start;
+        largest = new_limit;
+        inputs->files = expanded0.files;
+        output_level_inputs->files = expanded1;
       }
     }
-    if (!expand_inputs) {
-      vstorage->GetCleanInputsWithinInterval(input_level, &all_start,
-                                             &all_limit, &expanded_inputs.files,
-                                             base_index, nullptr);
-      expanded_inputs_size = TotalCompensatedFileSize(expanded_inputs.files);
-      if (expanded_inputs.size() > inputs->size() &&
-          output_level_inputs_size + expanded_inputs_size < limit &&
-          !FilesInCompaction(expanded_inputs.files)) {
-        expand_inputs = true;
-      }
-    }
-    if (expand_inputs) {
-      Log(InfoLogLevel::INFO_LEVEL, ioptions_.info_log,
-          "[%s] Expanding@%d %" ROCKSDB_PRIszt "+%" ROCKSDB_PRIszt "(%" PRIu64
-          "+%" PRIu64 " bytes) to %" ROCKSDB_PRIszt "+%" ROCKSDB_PRIszt
-          " (%" PRIu64 "+%" PRIu64 "bytes)\n",
-          cf_name.c_str(), input_level, inputs->size(),
-          output_level_inputs->size(), inputs_size, output_level_inputs_size,
-          expanded_inputs.size(), output_level_inputs->size(),
-          expanded_inputs_size, output_level_inputs_size);
-      inputs->files = expanded_inputs.files;
-    }
   }
+
   return true;
 }
 
@@ -591,24 +500,15 @@ Compaction* CompactionPicker::CompactRange(
         return nullptr;
       }
     }
-
-    // 2 non-exclusive manual compactions could run at the same time producing
-    // overlaping outputs in the same level.
-    if (FilesRangeOverlapWithCompaction(inputs, output_level)) {
-      // This compaction output could potentially conflict with the output
-      // of a currently running compaction, we cannot run it.
-      *manual_conflict = true;
-      return nullptr;
-    }
-
     Compaction* c = new Compaction(
-        vstorage, ioptions_, mutable_cf_options, std::move(inputs),
-        output_level, mutable_cf_options.MaxFileSizeForLevel(output_level),
-        /* max_compaction_bytes */ LLONG_MAX, output_path_id,
-        GetCompressionType(ioptions_, vstorage, mutable_cf_options,
-                           output_level, 1),
+        vstorage, mutable_cf_options, std::move(inputs), output_level,
+        mutable_cf_options.MaxFileSizeForLevel(output_level),
+        /* max_grandparent_overlap_bytes */ LLONG_MAX, output_path_id,
+        GetCompressionType(ioptions_, output_level, 1),
         /* grandparents */ {}, /* is manual */ true);
-    RegisterCompaction(c);
+    if (start_level == 0) {
+      level0_compactions_in_progress_.insert(c);
+    }
     return c;
   }
 
@@ -640,7 +540,8 @@ Compaction* CompactionPicker::CompactRange(
   // and we must not pick one file and drop another older file if the
   // two files overlap.
   if (input_level > 0) {
-    const uint64_t limit = mutable_cf_options.max_compaction_bytes;
+    const uint64_t limit = mutable_cf_options.MaxFileSizeForLevel(input_level) *
+      mutable_cf_options.source_compaction_factor;
     uint64_t total = 0;
     for (size_t i = 0; i + 1 < inputs.size(); ++i) {
       uint64_t s = inputs[i]->compensated_file_size;
@@ -697,42 +598,29 @@ Compaction* CompactionPicker::CompactRange(
     }
   }
 
-  // 2 non-exclusive manual compactions could run at the same time producing
-  // overlaping outputs in the same level.
-  if (FilesRangeOverlapWithCompaction(compaction_inputs, output_level)) {
-    // This compaction output could potentially conflict with the output
-    // of a currently running compaction, we cannot run it.
-    *manual_conflict = true;
-    return nullptr;
-  }
-
   std::vector<FileMetaData*> grandparents;
   GetGrandparents(vstorage, inputs, output_level_inputs, &grandparents);
   Compaction* compaction = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(compaction_inputs),
-      output_level, mutable_cf_options.MaxFileSizeForLevel(output_level),
-      mutable_cf_options.max_compaction_bytes, output_path_id,
-      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
-                         vstorage->base_level()),
+      vstorage, mutable_cf_options, std::move(compaction_inputs), output_level,
+      mutable_cf_options.MaxFileSizeForLevel(output_level),
+      mutable_cf_options.MaxGrandParentOverlapBytes(input_level),
+      output_path_id,
+      GetCompressionType(ioptions_, output_level, vstorage->base_level()),
       std::move(grandparents), /* is manual compaction */ true);
 
   TEST_SYNC_POINT_CALLBACK("CompactionPicker::CompactRange:Return", compaction);
-  RegisterCompaction(compaction);
-
-  // Creating a compaction influences the compaction score because the score
-  // takes running compactions into account (by skipping files that are already
-  // being compacted). Since we just changed compaction score, we recalculate it
-  // here
-  vstorage->ComputeCompactionScore(ioptions_, mutable_cf_options);
-
+  if (input_level == 0) {
+    level0_compactions_in_progress_.insert(compaction);
+  }
   return compaction;
 }
 
 #ifndef ROCKSDB_LITE
 namespace {
 // Test whether two files have overlapping key-ranges.
-bool HaveOverlappingKeyRanges(const Comparator* c, const SstFileMetaData& a,
-                              const SstFileMetaData& b) {
+bool HaveOverlappingKeyRanges(
+    const Comparator* c,
+    const SstFileMetaData& a, const SstFileMetaData& b) {
   if (c->Compare(a.smallestkey, b.smallestkey) >= 0) {
     if (c->Compare(a.smallestkey, b.largestkey) <= 0) {
       // b.smallestkey <= a.smallestkey <= b.largestkey
@@ -756,8 +644,9 @@ bool HaveOverlappingKeyRanges(const Comparator* c, const SstFileMetaData& a,
 }  // namespace
 
 Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
-    std::unordered_set<uint64_t>* input_files,
-    const ColumnFamilyMetaData& cf_meta, const int output_level) const {
+      std::unordered_set<uint64_t>* input_files,
+      const ColumnFamilyMetaData& cf_meta,
+      const int output_level) const {
   auto& levels = cf_meta.levels;
   auto comparator = icmp_->user_comparator();
 
@@ -810,17 +699,18 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
       // has overlapping key-range with other non-compaction input
       // files in the same level.
       while (first_included > 0) {
-        if (comparator->Compare(current_files[first_included - 1].largestkey,
-                                current_files[first_included].smallestkey) <
-            0) {
+        if (comparator->Compare(
+                current_files[first_included - 1].largestkey,
+                current_files[first_included].smallestkey) < 0) {
           break;
         }
         first_included--;
       }
 
       while (last_included < static_cast<int>(current_files.size()) - 1) {
-        if (comparator->Compare(current_files[last_included + 1].smallestkey,
-                                current_files[last_included].largestkey) > 0) {
+        if (comparator->Compare(
+                current_files[last_included + 1].smallestkey,
+                current_files[last_included].largestkey) > 0) {
           break;
         }
         last_included++;
@@ -830,31 +720,33 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
     // include all files between the first and the last compaction input files.
     for (int f = first_included; f <= last_included; ++f) {
       if (current_files[f].being_compacted) {
-        return Status::Aborted("Necessary compaction input file " +
-                               current_files[f].name +
-                               " is currently being compacted.");
+        return Status::Aborted(
+            "Necessary compaction input file " + current_files[f].name +
+            " is currently being compacted.");
       }
-      input_files->insert(TableFileNameToNumber(current_files[f].name));
+      input_files->insert(
+          TableFileNameToNumber(current_files[f].name));
     }
 
     // update smallest and largest key
     if (l == 0) {
       for (int f = first_included; f <= last_included; ++f) {
-        if (comparator->Compare(smallestkey, current_files[f].smallestkey) >
-            0) {
+        if (comparator->Compare(
+            smallestkey, current_files[f].smallestkey) > 0) {
           smallestkey = current_files[f].smallestkey;
         }
-        if (comparator->Compare(largestkey, current_files[f].largestkey) < 0) {
+        if (comparator->Compare(
+            largestkey, current_files[f].largestkey) < 0) {
           largestkey = current_files[f].largestkey;
         }
       }
     } else {
-      if (comparator->Compare(smallestkey,
-                              current_files[first_included].smallestkey) > 0) {
+      if (comparator->Compare(
+          smallestkey, current_files[first_included].smallestkey) > 0) {
         smallestkey = current_files[first_included].smallestkey;
       }
-      if (comparator->Compare(largestkey,
-                              current_files[last_included].largestkey) < 0) {
+      if (comparator->Compare(
+          largestkey, current_files[last_included].largestkey) < 0) {
         largestkey = current_files[last_included].largestkey;
       }
     }
@@ -871,15 +763,16 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
     // time and not by key
     for (int m = std::max(l, 1); m <= output_level; ++m) {
       for (auto& next_lv_file : levels[m].files) {
-        if (HaveOverlappingKeyRanges(comparator, aggregated_file_meta,
-                                     next_lv_file)) {
+        if (HaveOverlappingKeyRanges(
+            comparator, aggregated_file_meta, next_lv_file)) {
           if (next_lv_file.being_compacted) {
             return Status::Aborted(
                 "File " + next_lv_file.name +
                 " that has overlapping key range with one of the compaction "
                 " input file is currently being compacted.");
           }
-          input_files->insert(TableFileNameToNumber(next_lv_file.name));
+          input_files->insert(
+              TableFileNameToNumber(next_lv_file.name));
         }
       }
     }
@@ -889,25 +782,28 @@ Status CompactionPicker::SanitizeCompactionInputFilesForAllLevels(
 
 Status CompactionPicker::SanitizeCompactionInputFiles(
     std::unordered_set<uint64_t>* input_files,
-    const ColumnFamilyMetaData& cf_meta, const int output_level) const {
+    const ColumnFamilyMetaData& cf_meta,
+    const int output_level) const {
   assert(static_cast<int>(cf_meta.levels.size()) - 1 ==
          cf_meta.levels[cf_meta.levels.size() - 1].level);
   if (output_level >= static_cast<int>(cf_meta.levels.size())) {
     return Status::InvalidArgument(
         "Output level for column family " + cf_meta.name +
         " must between [0, " +
-        ToString(cf_meta.levels[cf_meta.levels.size() - 1].level) + "].");
+        ToString(cf_meta.levels[cf_meta.levels.size() - 1].level) +
+        "].");
   }
 
   if (output_level > MaxOutputLevel()) {
     return Status::InvalidArgument(
         "Exceed the maximum output level defined by "
         "the current compaction algorithm --- " +
-        ToString(MaxOutputLevel()));
+            ToString(MaxOutputLevel()));
   }
 
   if (output_level < 0) {
-    return Status::InvalidArgument("Output level cannot be negative.");
+    return Status::InvalidArgument(
+        "Output level cannot be negative.");
   }
 
   if (input_files->size() == 0) {
@@ -915,8 +811,8 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
         "A compaction must contain at least one file.");
   }
 
-  Status s = SanitizeCompactionInputFilesForAllLevels(input_files, cf_meta,
-                                                      output_level);
+  Status s = SanitizeCompactionInputFilesForAllLevels(
+      input_files, cf_meta, output_level);
 
   if (!s.ok()) {
     return s;
@@ -930,9 +826,10 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
       for (auto file_meta : level_meta.files) {
         if (file_num == TableFileNameToNumber(file_meta.name)) {
           if (file_meta.being_compacted) {
-            return Status::Aborted("Specified compaction input file " +
-                                   MakeTableFileName("", file_num) +
-                                   " is already being compacted.");
+            return Status::Aborted(
+                "Specified compaction input file " +
+                MakeTableFileName("", file_num) +
+                " is already being compacted.");
           }
           found = true;
           break;
@@ -944,7 +841,8 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
     }
     if (!found) {
       return Status::InvalidArgument(
-          "Specified compaction input file " + MakeTableFileName("", file_num) +
+          "Specified compaction input file " +
+          MakeTableFileName("", file_num) +
           " does not exist in column family " + cf_meta.name + ".");
     }
   }
@@ -953,32 +851,8 @@ Status CompactionPicker::SanitizeCompactionInputFiles(
 }
 #endif  // !ROCKSDB_LITE
 
-void CompactionPicker::RegisterCompaction(Compaction* c) {
-  if (c == nullptr) {
-    return;
-  }
-  assert(ioptions_.compaction_style != kCompactionStyleLevel ||
-         !FilesRangeOverlapWithCompaction(*c->inputs(), c->output_level()));
-  if (c->start_level() == 0 ||
-      ioptions_.compaction_style == kCompactionStyleUniversal) {
-    level0_compactions_in_progress_.insert(c);
-  }
-  compactions_in_progress_.insert(c);
-}
-
-void CompactionPicker::UnregisterCompaction(Compaction* c) {
-  if (c == nullptr) {
-    return;
-  }
-  if (c->start_level() == 0 ||
-      ioptions_.compaction_style == kCompactionStyleUniversal) {
-    level0_compactions_in_progress_.erase(c);
-  }
-  compactions_in_progress_.erase(c);
-}
-
-bool LevelCompactionPicker::NeedsCompaction(
-    const VersionStorageInfo* vstorage) const {
+bool LevelCompactionPicker::NeedsCompaction(const VersionStorageInfo* vstorage)
+    const {
   if (!vstorage->FilesMarkedForCompaction().empty()) {
     return true;
   }
@@ -1060,8 +934,7 @@ Compaction* LevelCompactionPicker::PickCompaction(
       output_level = (level == 0) ? vstorage->base_level() : level + 1;
       if (PickCompactionBySize(vstorage, level, output_level, &inputs,
                                &parent_index, &base_index) &&
-          ExpandWhileOverlapping(cf_name, vstorage, &inputs) &&
-          !FilesRangeOverlapWithCompaction({inputs}, output_level)) {
+          ExpandWhileOverlapping(cf_name, vstorage, &inputs)) {
         // found the compaction!
         if (level == 0) {
           // L0 score = `num L0 files` / `level0_file_num_compaction_trigger`
@@ -1125,7 +998,7 @@ Compaction* LevelCompactionPicker::PickCompaction(
   CompactionInputFiles output_level_inputs;
   output_level_inputs.level = output_level;
   if (!SetupOtherInputs(cf_name, mutable_cf_options, vstorage, &inputs,
-                        &output_level_inputs, &parent_index, base_index)) {
+                   &output_level_inputs, &parent_index, base_index)) {
     return nullptr;
   }
 
@@ -1134,39 +1007,32 @@ Compaction* LevelCompactionPicker::PickCompaction(
     compaction_inputs.push_back(output_level_inputs);
   }
 
-  // In some edge cases we could pick a compaction that will be compacting
-  // a key range that overlap with another running compaction, and both
-  // of them have the same output leve. This could happen if
-  // (1) we are running a non-exclusive manual compaction
-  // (2) AddFile ingest a new file into the LSM tree
-  // We need to disallow this from happening.
-  if (FilesRangeOverlapWithCompaction(compaction_inputs, output_level)) {
-    // This compaction output could potentially conflict with the output
-    // of a currently running compaction, we cannot run it.
-    return nullptr;
-  }
-
   std::vector<FileMetaData*> grandparents;
   GetGrandparents(vstorage, inputs, output_level_inputs, &grandparents);
   auto c = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(compaction_inputs),
-      output_level, mutable_cf_options.MaxFileSizeForLevel(output_level),
-      mutable_cf_options.max_compaction_bytes,
+      vstorage, mutable_cf_options, std::move(compaction_inputs), output_level,
+      mutable_cf_options.MaxFileSizeForLevel(output_level),
+      mutable_cf_options.MaxGrandParentOverlapBytes(level),
       GetPathId(ioptions_, mutable_cf_options, output_level),
-      GetCompressionType(ioptions_, vstorage, mutable_cf_options, output_level,
-                         vstorage->base_level()),
+      GetCompressionType(ioptions_, output_level, vstorage->base_level()),
       std::move(grandparents), is_manual, score,
       false /* deletion_compaction */, compaction_reason);
 
   // If it's level 0 compaction, make sure we don't execute any other level 0
   // compactions in parallel
-  RegisterCompaction(c);
+  if (level == 0) {
+    level0_compactions_in_progress_.insert(c);
+  }
 
   // Creating a compaction influences the compaction score because the score
   // takes running compactions into account (by skipping files that are already
   // being compacted). Since we just changed compaction score, we recalculate it
   // here
-  vstorage->ComputeCompactionScore(ioptions_, mutable_cf_options);
+  {  // this piece of code recomputes compaction score
+    CompactionOptionsFIFO dummy_compaction_options_fifo;
+    vstorage->ComputeCompactionScore(mutable_cf_options,
+                                     dummy_compaction_options_fifo);
+  }
 
   TEST_SYNC_POINT_CALLBACK("LevelCompactionPicker::PickCompaction:Return", c);
 
@@ -1200,8 +1066,7 @@ uint32_t LevelCompactionPicker::GetPathId(
         return p;
       } else {
         current_path_size -= level_size;
-        level_size = static_cast<uint64_t>(
-            level_size * mutable_cf_options.max_bytes_for_level_multiplier);
+        level_size *= mutable_cf_options.max_bytes_for_level_multiplier;
         cur_level++;
         continue;
       }
@@ -1443,8 +1308,6 @@ Compaction* UniversalCompactionPicker::PickCompaction(
       sorted_runs.size() <
           (unsigned int)mutable_cf_options.level0_file_num_compaction_trigger) {
     LogToBuffer(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;
@@ -1479,34 +1342,19 @@ Compaction* UniversalCompactionPicker::PickCompaction(
       assert(sorted_runs.size() >=
              static_cast<size_t>(
                  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) {
-          num_sr_not_compacted++;
-        }
-      }
-
-      // 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) {
-        unsigned int num_files =
-            num_sr_not_compacted -
-            mutable_cf_options.level0_file_num_compaction_trigger + 1;
-        if ((c = PickCompactionUniversalReadAmp(
-                 cf_name, mutable_cf_options, vstorage, score, UINT_MAX,
-                 num_files, sorted_runs, log_buffer)) != nullptr) {
-          LogToBuffer(log_buffer,
-                      "[%s] Universal: compacting for file num -- %u\n",
-                      cf_name.c_str(), num_files);
-        }
+      unsigned int num_files =
+          static_cast<unsigned int>(sorted_runs.size()) -
+          mutable_cf_options.level0_file_num_compaction_trigger;
+      if ((c = PickCompactionUniversalReadAmp(
+               cf_name, mutable_cf_options, vstorage, score, UINT_MAX,
+               num_files, sorted_runs, log_buffer)) != nullptr) {
+        LogToBuffer(log_buffer,
+                    "[%s] Universal: compacting for file num -- %u\n",
+                    cf_name.c_str(), num_files);
       }
     }
   }
   if (c == nullptr) {
-    TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
-                             nullptr);
     return nullptr;
   }
 
@@ -1557,10 +1405,8 @@ Compaction* UniversalCompactionPicker::PickCompaction(
   MeasureTime(ioptions_.statistics, NUM_FILES_IN_SINGLE_COMPACTION,
               c->inputs(0)->size());
 
-  RegisterCompaction(c);
+  level0_compactions_in_progress_.insert(c);
 
-  TEST_SYNC_POINT_CALLBACK("UniversalCompactionPicker::PickCompaction:Return",
-                           c);
   return c;
 }
 
@@ -1581,9 +1427,8 @@ uint32_t UniversalCompactionPicker::GetPathId(
   // considered in this algorithm. So the target size can be violated in
   // that case. We need to improve it.
   uint64_t accumulated_size = 0;
-  uint64_t future_size =
-      file_size * (100 - ioptions.compaction_options_universal.size_ratio) /
-      100;
+  uint64_t future_size = file_size *
+    (100 - ioptions.compaction_options_universal.size_ratio) / 100;
   uint32_t p = 0;
   assert(!ioptions.db_paths.empty());
   for (; p < ioptions.db_paths.size() - 1; p++) {
@@ -1607,17 +1452,17 @@ Compaction* UniversalCompactionPicker::PickCompactionUniversalReadAmp(
     unsigned int max_number_of_files_to_compact,
     const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
   unsigned int min_merge_width =
-      ioptions_.compaction_options_universal.min_merge_width;
+    ioptions_.compaction_options_universal.min_merge_width;
   unsigned int max_merge_width =
-      ioptions_.compaction_options_universal.max_merge_width;
+    ioptions_.compaction_options_universal.max_merge_width;
 
   const SortedRun* sr = nullptr;
   bool done = false;
   size_t start_index = 0;
   unsigned int candidate_count = 0;
 
-  unsigned int max_files_to_compact =
-      std::min(max_merge_width, max_number_of_files_to_compact);
+  unsigned int max_files_to_compact = std::min(max_merge_width,
+                                       max_number_of_files_to_compact);
   min_merge_width = std::max(min_merge_width, 2U);
 
   // Caller checks the size before executing this function. This invariant is
@@ -1729,7 +1574,7 @@ Compaction* UniversalCompactionPicker::PickCompactionUniversalReadAmp(
     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;
-      if (older_file_size * 100L >= total_size * (long)ratio_to_compress) {
+      if (older_file_size * 100L >= total_size * (long) ratio_to_compress) {
         enable_compression = false;
         break;
       }
@@ -1779,10 +1624,9 @@ Compaction* UniversalCompactionPicker::PickCompactionUniversalReadAmp(
     compaction_reason = CompactionReason::kUniversalSizeRatio;
   }
   return new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), output_level,
+      vstorage, mutable_cf_options, std::move(inputs), output_level,
       mutable_cf_options.MaxFileSizeForLevel(output_level), LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage, mutable_cf_options, start_level,
-                         1, enable_compression),
+      GetCompressionType(ioptions_, start_level, 1, enable_compression),
       /* grandparents */ {}, /* is manual */ false, score,
       false /* deletion_compaction */, compaction_reason);
 }
@@ -1798,8 +1642,8 @@ Compaction* UniversalCompactionPicker::PickCompactionUniversalSizeAmp(
     VersionStorageInfo* vstorage, double score,
     const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer) {
   // percentage flexibilty while reducing size amplification
-  uint64_t ratio =
-      ioptions_.compaction_options_universal.max_size_amplification_percent;
+  uint64_t ratio = ioptions_.compaction_options_universal.
+                     max_size_amplification_percent;
 
   unsigned int candidate_count = 0;
   uint64_t candidate_size = 0;
@@ -1810,7 +1654,7 @@ Compaction* UniversalCompactionPicker::PickCompactionUniversalSizeAmp(
   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.
+      start_index = loop;         // Consider this as the first candidate.
       break;
     }
     char file_num_buf[kFormatFileNumberBufSize];
@@ -1822,7 +1666,7 @@ Compaction* UniversalCompactionPicker::PickCompactionUniversalSizeAmp(
   }
 
   if (sr == nullptr) {
-    return nullptr;  // no candidate files
+    return nullptr;             // no candidate files
   }
   {
     char file_num_buf[kFormatFileNumberBufSize];
@@ -1860,14 +1704,14 @@ Compaction* UniversalCompactionPicker::PickCompactionUniversalSizeAmp(
     LogToBuffer(
         log_buffer,
         "[%s] Universal: size amp not needed. newer-files-total-size %" PRIu64
-        " earliest-file-size %" PRIu64,
+        "earliest-file-size %" PRIu64,
         cf_name.c_str(), candidate_size, earliest_file_size);
     return nullptr;
   } else {
     LogToBuffer(
         log_buffer,
         "[%s] Universal: size amp needed. newer-files-total-size %" PRIu64
-        " earliest-file-size %" PRIu64,
+        "earliest-file-size %" PRIu64,
         cf_name.c_str(), candidate_size, earliest_file_size);
   }
   assert(start_index < sorted_runs.size() - 1);
@@ -1903,19 +1747,18 @@ Compaction* UniversalCompactionPicker::PickCompactionUniversalSizeAmp(
   }
 
   return new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs),
+      vstorage, mutable_cf_options, std::move(inputs),
       vstorage->num_levels() - 1,
       mutable_cf_options.MaxFileSizeForLevel(vstorage->num_levels() - 1),
       /* max_grandparent_overlap_bytes */ LLONG_MAX, path_id,
-      GetCompressionType(ioptions_, vstorage, mutable_cf_options,
-                         vstorage->num_levels() - 1, 1),
+      GetCompressionType(ioptions_, vstorage->num_levels() - 1, 1),
       /* grandparents */ {}, /* is manual */ false, score,
       false /* deletion_compaction */,
       CompactionReason::kUniversalSizeAmplification);
 }
 
-bool FIFOCompactionPicker::NeedsCompaction(
-    const VersionStorageInfo* vstorage) const {
+bool FIFOCompactionPicker::NeedsCompaction(const VersionStorageInfo* vstorage)
+    const {
   const int kLevel0 = 0;
   return vstorage->CompactionScore(kLevel0) >= 1;
 }
@@ -1968,10 +1811,10 @@ Compaction* FIFOCompactionPicker::PickCompaction(
     }
   }
   Compaction* c = new Compaction(
-      vstorage, ioptions_, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
+      vstorage, mutable_cf_options, std::move(inputs), 0, 0, 0, 0,
       kNoCompression, {}, /* is manual */ false, vstorage->CompactionScore(0),
       /* is deletion compaction */ true, CompactionReason::kFIFOMaxSize);
-  RegisterCompaction(c);
+  level0_compactions_in_progress_.insert(c);
   return c;
 }
 

db/compaction_picker.h

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -20,7 +20,8 @@
 #include "rocksdb/env.h"
 #include "rocksdb/options.h"
 #include "rocksdb/status.h"
-#include "util/cf_options.h"
+#include "util/mutable_cf_options.h"
+
 
 namespace rocksdb {
 
@@ -62,25 +63,26 @@ class CompactionPicker {
       InternalKey** compaction_end, bool* manual_conflict);
 
   // The maximum allowed output level.  Default value is NumberLevels() - 1.
-  virtual int MaxOutputLevel() const { return NumberLevels() - 1; }
+  virtual int MaxOutputLevel() const {
+    return NumberLevels() - 1;
+  }
 
   virtual bool NeedsCompaction(const VersionStorageInfo* vstorage) const = 0;
 
-// Sanitize the input set of compaction input files.
-// When the input parameters do not describe a valid compaction, the
-// function will try to fix the input_files by adding necessary
-// files.  If it's not possible to conver an invalid input_files
-// into a valid one by adding more files, the function will return a
-// non-ok status with specific reason.
+  // Sanitize the input set of compaction input files.
+  // When the input parameters do not describe a valid compaction, the
+  // function will try to fix the input_files by adding necessary
+  // files.  If it's not possible to conver an invalid input_files
+  // into a valid one by adding more files, the function will return a
+  // non-ok status with specific reason.
 #ifndef ROCKSDB_LITE
-  Status SanitizeCompactionInputFiles(std::unordered_set<uint64_t>* input_files,
-                                      const ColumnFamilyMetaData& cf_meta,
-                                      const int output_level) const;
+  Status SanitizeCompactionInputFiles(
+      std::unordered_set<uint64_t>* input_files,
+      const ColumnFamilyMetaData& cf_meta,
+      const int output_level) const;
 #endif  // ROCKSDB_LITE
 
   // Free up the files that participated in a compaction
-  //
-  // Requirement: DB mutex held
   void ReleaseCompactionFiles(Compaction* c, Status status);
 
   // Returns true if any one of the specified files are being compacted
@@ -113,33 +115,21 @@ class CompactionPicker {
     return !level0_compactions_in_progress_.empty();
   }
 
-  // Return true if the passed key range overlap with a compaction output
-  // that is currently running.
-  bool RangeOverlapWithCompaction(const Slice& smallest_user_key,
-                                  const Slice& largest_user_key,
-                                  int level) const;
+ protected:
+  int NumberLevels() const { return ioptions_.num_levels; }
 
   // Stores the minimal range that covers all entries in inputs in
   // *smallest, *largest.
   // REQUIRES: inputs is not empty
-  void GetRange(const CompactionInputFiles& inputs, InternalKey* smallest,
-                InternalKey* largest) const;
+  void GetRange(const CompactionInputFiles& inputs,
+                InternalKey* smallest, InternalKey* largest);
 
   // Stores the minimal range that covers all entries in inputs1 and inputs2
   // in *smallest, *largest.
   // REQUIRES: inputs is not empty
   void GetRange(const CompactionInputFiles& inputs1,
-                const CompactionInputFiles& inputs2, InternalKey* smallest,
-                InternalKey* largest) const;
-
-  // Stores the minimal range that covers all entries in inputs
-  // in *smallest, *largest.
-  // REQUIRES: inputs is not empty (at least on entry have one file)
-  void GetRange(const std::vector<CompactionInputFiles>& inputs,
-                InternalKey* smallest, InternalKey* largest) const;
-
- protected:
-  int NumberLevels() const { return ioptions_.num_levels; }
+                const CompactionInputFiles& inputs2,
+                InternalKey* smallest, InternalKey* largest);
 
   // Add more files to the inputs on "level" to make sure that
   // no newer version of a key is compacted to "level+1" while leaving an older
@@ -160,11 +150,6 @@ class CompactionPicker {
                          const InternalKey* smallest,
                          const InternalKey* largest, int level, int* index);
 
-  // Returns true if the key range that `inputs` files cover overlap with the
-  // key range of a currently running compaction.
-  bool FilesRangeOverlapWithCompaction(
-      const std::vector<CompactionInputFiles>& inputs, int level) const;
-
   bool SetupOtherInputs(const std::string& cf_name,
                         const MutableCFOptions& mutable_cf_options,
                         VersionStorageInfo* vstorage,
@@ -179,28 +164,19 @@ class CompactionPicker {
 
   const ImmutableCFOptions& ioptions_;
 
-// A helper function to SanitizeCompactionInputFiles() that
-// sanitizes "input_files" by adding necessary files.
+  // A helper function to SanitizeCompactionInputFiles() that
+  // sanitizes "input_files" by adding necessary files.
 #ifndef ROCKSDB_LITE
   virtual Status SanitizeCompactionInputFilesForAllLevels(
       std::unordered_set<uint64_t>* input_files,
-      const ColumnFamilyMetaData& cf_meta, const int output_level) const;
+      const ColumnFamilyMetaData& cf_meta,
+      const int output_level) const;
 #endif  // ROCKSDB_LITE
 
-  // Register this compaction in the set of running compactions
-  void RegisterCompaction(Compaction* c);
-
-  // Remove this compaction from the set of running compactions
-  void UnregisterCompaction(Compaction* c);
-
   // Keeps track of all compactions that are running on Level0.
-  // Protected by DB mutex
+  // It is protected by DB mutex
   std::set<Compaction*> level0_compactions_in_progress_;
 
-  // Keeps track of all compactions that are running.
-  // Protected by DB mutex
-  std::unordered_set<Compaction*> compactions_in_progress_;
-
   const InternalKeyComparator* const icmp_;
 };
 
@@ -214,8 +190,8 @@ class LevelCompactionPicker : public CompactionPicker {
                                      VersionStorageInfo* vstorage,
                                      LogBuffer* log_buffer) override;
 
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
+  virtual bool NeedsCompaction(const VersionStorageInfo* vstorage) const
+      override;
 
   // Pick a path ID to place a newly generated file, with its level
   static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
@@ -254,8 +230,8 @@ class UniversalCompactionPicker : public CompactionPicker {
 
   virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
 
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
+  virtual bool NeedsCompaction(const VersionStorageInfo* vstorage) const
+      override;
 
  private:
   struct SortedRun {
@@ -329,17 +305,19 @@ class FIFOCompactionPicker : public CompactionPicker {
       InternalKey** compaction_end, bool* manual_conflict) override;
 
   // The maximum allowed output level.  Always returns 0.
-  virtual int MaxOutputLevel() const override { return 0; }
+  virtual int MaxOutputLevel() const override {
+    return 0;
+  }
 
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
+  virtual bool NeedsCompaction(const VersionStorageInfo* vstorage) const
+      override;
 };
 
 class NullCompactionPicker : public CompactionPicker {
  public:
   NullCompactionPicker(const ImmutableCFOptions& ioptions,
-                       const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
+                       const InternalKeyComparator* icmp) :
+      CompactionPicker(ioptions, icmp) {}
   virtual ~NullCompactionPicker() {}
 
   // Always return "nullptr"
@@ -362,16 +340,14 @@ class NullCompactionPicker : public CompactionPicker {
   }
 
   // Always returns false.
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override {
+  virtual bool NeedsCompaction(const VersionStorageInfo* vstorage) const
+      override {
     return false;
   }
 };
 #endif  // !ROCKSDB_LITE
 
 CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
-                                   const VersionStorageInfo* vstorage,
-                                   const MutableCFOptions& mutable_cf_options,
                                    int level, int base_level,
                                    const bool enable_compression = true);
 

db/compaction_picker_test.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 #include "db/compaction.h"
 #include "db/compaction_picker.h"
@@ -48,7 +48,7 @@ class CompactionPickerTest : public testing::Test {
       : ucmp_(BytewiseComparator()),
         icmp_(ucmp_),
         ioptions_(options_),
-        mutable_cf_options_(options_),
+        mutable_cf_options_(options_, ioptions_),
         level_compaction_picker(ioptions_, &icmp_),
         cf_name_("dummy"),
         log_buffer_(InfoLogLevel::INFO_LEVEL, &logger_),
@@ -66,8 +66,8 @@ class CompactionPickerTest : public testing::Test {
   void NewVersionStorage(int num_levels, CompactionStyle style) {
     DeleteVersionStorage();
     options_.num_levels = num_levels;
-    vstorage_.reset(new VersionStorageInfo(&icmp_, ucmp_, options_.num_levels,
-                                           style, nullptr, false));
+    vstorage_.reset(new VersionStorageInfo(
+        &icmp_, ucmp_, options_.num_levels, style, nullptr));
     vstorage_->CalculateBaseBytes(ioptions_, mutable_cf_options_);
   }
 
@@ -79,7 +79,7 @@ class CompactionPickerTest : public testing::Test {
   }
 
   void Add(int level, uint32_t file_number, const char* smallest,
-           const char* largest, uint64_t file_size = 1, uint32_t path_id = 0,
+           const char* largest, uint64_t file_size = 0, uint32_t path_id = 0,
            SequenceNumber smallest_seq = 100,
            SequenceNumber largest_seq = 100) {
     assert(level < vstorage_->num_levels());
@@ -115,13 +115,12 @@ class CompactionPickerTest : public testing::Test {
 
   void UpdateVersionStorageInfo() {
     vstorage_->CalculateBaseBytes(ioptions_, mutable_cf_options_);
-    vstorage_->UpdateFilesByCompactionPri(ioptions_.compaction_pri);
+    vstorage_->UpdateFilesByCompactionPri(mutable_cf_options_);
     vstorage_->UpdateNumNonEmptyLevels();
     vstorage_->GenerateFileIndexer();
     vstorage_->GenerateLevelFilesBrief();
-    vstorage_->ComputeCompactionScore(ioptions_, mutable_cf_options_);
+    vstorage_->ComputeCompactionScore(mutable_cf_options_, fifo_options_);
     vstorage_->GenerateLevel0NonOverlapping();
-    vstorage_->ComputeFilesMarkedForCompaction();
     vstorage_->SetFinalized();
   }
 };
@@ -196,7 +195,6 @@ TEST_F(CompactionPickerTest, LevelMaxScore) {
   NewVersionStorage(6, kCompactionStyleLevel);
   mutable_cf_options_.target_file_size_base = 10000000;
   mutable_cf_options_.target_file_size_multiplier = 10;
-  mutable_cf_options_.max_bytes_for_level_base = 10 * 1024 * 1024;
   Add(0, 1U, "150", "200", 1000000000U);
   // Level 1 score 1.2
   Add(1, 66U, "150", "200", 6000000U);
@@ -321,7 +319,6 @@ TEST_F(CompactionPickerTest, Level0TriggerDynamic4) {
   mutable_cf_options_.level0_file_num_compaction_trigger = 2;
   mutable_cf_options_.max_bytes_for_level_base = 200;
   mutable_cf_options_.max_bytes_for_level_multiplier = 10;
-
   NewVersionStorage(num_levels, kCompactionStyleLevel);
   Add(0, 1U, "150", "200");
   Add(0, 2U, "200", "250");
@@ -351,7 +348,6 @@ TEST_F(CompactionPickerTest, Level0TriggerDynamic4) {
 TEST_F(CompactionPickerTest, LevelTriggerDynamic4) {
   int num_levels = ioptions_.num_levels;
   ioptions_.level_compaction_dynamic_level_bytes = true;
-  ioptions_.compaction_pri = kMinOverlappingRatio;
   mutable_cf_options_.level0_file_num_compaction_trigger = 2;
   mutable_cf_options_.max_bytes_for_level_base = 200;
   mutable_cf_options_.max_bytes_for_level_multiplier = 10;
@@ -370,9 +366,11 @@ TEST_F(CompactionPickerTest, LevelTriggerDynamic4) {
       cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
   ASSERT_TRUE(compaction.get() != nullptr);
   ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(5U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(0, compaction->num_input_files(1));
-  ASSERT_EQ(1U, compaction->num_input_levels());
+  ASSERT_EQ(6U, compaction->input(0, 0)->fd.GetNumber());
+  ASSERT_EQ(2U, compaction->num_input_files(1));
+  ASSERT_EQ(3U, compaction->input(1, 0)->fd.GetNumber());
+  ASSERT_EQ(4U, compaction->input(1, 1)->fd.GetNumber());
+  ASSERT_EQ(2U, compaction->num_input_levels());
   ASSERT_EQ(num_levels - 1, compaction->output_level());
 }
 
@@ -468,6 +466,7 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
   fifo_options_.max_table_files_size = kMaxSize;
   ioptions_.compaction_options_fifo = fifo_options_;
   FIFOCompactionPicker fifo_compaction_picker(ioptions_, &icmp_);
+
   UpdateVersionStorageInfo();
   // must return false when there's no files.
   ASSERT_EQ(fifo_compaction_picker.NeedsCompaction(vstorage_.get()), false);
@@ -488,90 +487,6 @@ TEST_F(CompactionPickerTest, NeedsCompactionFIFO) {
 }
 #endif  // ROCKSDB_LITE
 
-TEST_F(CompactionPickerTest, CompactionPriMinOverlapping1) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  ioptions_.compaction_pri = kMinOverlappingRatio;
-  mutable_cf_options_.target_file_size_base = 10000000;
-  mutable_cf_options_.target_file_size_multiplier = 10;
-  mutable_cf_options_.max_bytes_for_level_base = 10 * 1024 * 1024;
-
-  Add(2, 6U, "150", "179", 50000000U);
-  Add(2, 7U, "180", "220", 50000000U);
-  Add(2, 8U, "321", "400", 50000000U);  // File not overlapping
-  Add(2, 9U, "721", "800", 50000000U);
-
-  Add(3, 26U, "150", "170", 260000000U);
-  Add(3, 27U, "171", "179", 260000000U);
-  Add(3, 28U, "191", "220", 260000000U);
-  Add(3, 29U, "221", "300", 260000000U);
-  Add(3, 30U, "750", "900", 260000000U);
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  // Pick file 8 because it overlaps with 0 files on level 3.
-  ASSERT_EQ(8U, compaction->input(0, 0)->fd.GetNumber());
-}
-
-TEST_F(CompactionPickerTest, CompactionPriMinOverlapping2) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  ioptions_.compaction_pri = kMinOverlappingRatio;
-  mutable_cf_options_.target_file_size_base = 10000000;
-  mutable_cf_options_.target_file_size_multiplier = 10;
-  mutable_cf_options_.max_bytes_for_level_base = 10 * 1024 * 1024;
-
-  Add(2, 6U, "150", "175",
-      60000000U);  // Overlaps with file 26, 27, total size 521M
-  Add(2, 7U, "176", "200", 60000000U);  // Overlaps with file 27, 28, total size
-                                        // 520M, the smalelst overlapping
-  Add(2, 8U, "201", "300",
-      60000000U);  // Overlaps with file 28, 29, total size 521M
-
-  Add(3, 26U, "100", "110", 261000000U);
-  Add(3, 26U, "150", "170", 261000000U);
-  Add(3, 27U, "171", "179", 260000000U);
-  Add(3, 28U, "191", "220", 260000000U);
-  Add(3, 29U, "221", "300", 261000000U);
-  Add(3, 30U, "321", "400", 261000000U);
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  // Picking file 7 because overlapping ratio is the biggest.
-  ASSERT_EQ(7U, compaction->input(0, 0)->fd.GetNumber());
-}
-
-TEST_F(CompactionPickerTest, CompactionPriMinOverlapping3) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  ioptions_.compaction_pri = kMinOverlappingRatio;
-  mutable_cf_options_.max_bytes_for_level_base = 10000000;
-  mutable_cf_options_.max_bytes_for_level_multiplier = 10;
-
-  // file 7 and 8 over lap with the same file, but file 8 is smaller so
-  // it will be picked.
-  Add(2, 6U, "150", "167", 60000000U);  // Overlaps with file 26, 27
-  Add(2, 7U, "168", "169", 60000000U);  // Overlaps with file 27
-  Add(2, 8U, "201", "300", 61000000U);  // Overlaps with file 28, but the file
-                                        // itself is larger. Should be picked.
-
-  Add(3, 26U, "160", "165", 260000000U);
-  Add(3, 27U, "166", "170", 260000000U);
-  Add(3, 28U, "180", "400", 260000000U);
-  Add(3, 29U, "401", "500", 260000000U);
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  // Picking file 8 because overlapping ratio is the biggest.
-  ASSERT_EQ(8U, compaction->input(0, 0)->fd.GetNumber());
-}
-
 // This test exhibits the bug where we don't properly reset parent_index in
 // PickCompaction()
 TEST_F(CompactionPickerTest, ParentIndexResetBug) {
@@ -599,8 +514,6 @@ TEST_F(CompactionPickerTest, ParentIndexResetBug) {
 // ranges (with different sequence numbers) in the input files.
 TEST_F(CompactionPickerTest, OverlappingUserKeys) {
   NewVersionStorage(6, kCompactionStyleLevel);
-  ioptions_.compaction_pri = kByCompensatedSize;
-
   Add(1, 1U, "100", "150", 1U);
   // Overlapping user keys
   Add(1, 2U, "200", "400", 1U);
@@ -622,9 +535,9 @@ TEST_F(CompactionPickerTest, OverlappingUserKeys2) {
   // Overlapping user keys on same level and output level
   Add(1, 1U, "200", "400", 1000000000U);
   Add(1, 2U, "400", "500", 1U, 0, 0);
-  Add(2, 3U, "000", "100", 1U);
-  Add(2, 4U, "100", "600", 1U, 0, 0);
-  Add(2, 5U, "600", "700", 1U, 0, 0);
+  Add(2, 3U, "400", "600", 1U);
+  // The following file is not in the compaction despite overlapping user keys
+  Add(2, 4U, "600", "700", 1U, 0, 0);
   UpdateVersionStorageInfo();
 
   std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
@@ -632,12 +545,10 @@ TEST_F(CompactionPickerTest, OverlappingUserKeys2) {
   ASSERT_TRUE(compaction.get() != nullptr);
   ASSERT_EQ(2U, compaction->num_input_levels());
   ASSERT_EQ(2U, compaction->num_input_files(0));
-  ASSERT_EQ(3U, compaction->num_input_files(1));
+  ASSERT_EQ(1U, compaction->num_input_files(1));
   ASSERT_EQ(1U, compaction->input(0, 0)->fd.GetNumber());
   ASSERT_EQ(2U, compaction->input(0, 1)->fd.GetNumber());
   ASSERT_EQ(3U, compaction->input(1, 0)->fd.GetNumber());
-  ASSERT_EQ(4U, compaction->input(1, 1)->fd.GetNumber());
-  ASSERT_EQ(5U, compaction->input(1, 2)->fd.GetNumber());
 }
 
 TEST_F(CompactionPickerTest, OverlappingUserKeys3) {
@@ -669,159 +580,6 @@ TEST_F(CompactionPickerTest, OverlappingUserKeys3) {
   ASSERT_EQ(7U, compaction->input(1, 1)->fd.GetNumber());
 }
 
-TEST_F(CompactionPickerTest, OverlappingUserKeys4) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  mutable_cf_options_.max_bytes_for_level_base = 1000000;
-
-  Add(1, 1U, "100", "150", 1U);
-  Add(1, 2U, "150", "199", 1U, 0, 0);
-  Add(1, 3U, "200", "250", 1100000U, 0, 0);
-  Add(1, 4U, "251", "300", 1U, 0, 0);
-  Add(1, 5U, "300", "350", 1U, 0, 0);
-
-  Add(2, 6U, "100", "115", 1U);
-  Add(2, 7U, "125", "325", 1U);
-  Add(2, 8U, "350", "400", 1U);
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(2U, compaction->num_input_levels());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(1U, compaction->num_input_files(1));
-  ASSERT_EQ(3U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(7U, compaction->input(1, 0)->fd.GetNumber());
-}
-
-TEST_F(CompactionPickerTest, OverlappingUserKeys5) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  // Overlapping user keys on same level and output level
-  Add(1, 1U, "200", "400", 1000000000U);
-  Add(1, 2U, "400", "500", 1U, 0, 0);
-  Add(2, 3U, "000", "100", 1U);
-  Add(2, 4U, "100", "600", 1U, 0, 0);
-  Add(2, 5U, "600", "700", 1U, 0, 0);
-
-  vstorage_->LevelFiles(2)[2]->being_compacted = true;
-
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() == nullptr);
-}
-
-TEST_F(CompactionPickerTest, OverlappingUserKeys6) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  // Overlapping user keys on same level and output level
-  Add(1, 1U, "200", "400", 1U, 0, 0);
-  Add(1, 2U, "401", "500", 1U, 0, 0);
-  Add(2, 3U, "000", "100", 1U);
-  Add(2, 4U, "100", "300", 1U, 0, 0);
-  Add(2, 5U, "305", "450", 1U, 0, 0);
-  Add(2, 6U, "460", "600", 1U, 0, 0);
-  Add(2, 7U, "600", "700", 1U, 0, 0);
-
-  vstorage_->LevelFiles(1)[0]->marked_for_compaction = true;
-  vstorage_->LevelFiles(1)[1]->marked_for_compaction = true;
-
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(2U, compaction->num_input_levels());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(3U, compaction->num_input_files(1));
-}
-
-TEST_F(CompactionPickerTest, OverlappingUserKeys7) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  mutable_cf_options_.max_compaction_bytes = 100000000000u;
-  // Overlapping user keys on same level and output level
-  Add(1, 1U, "200", "400", 1U, 0, 0);
-  Add(1, 2U, "401", "500", 1000000000U, 0, 0);
-  Add(2, 3U, "100", "250", 1U);
-  Add(2, 4U, "300", "600", 1U, 0, 0);
-  Add(2, 5U, "600", "800", 1U, 0, 0);
-
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(2U, compaction->num_input_levels());
-  ASSERT_GE(1U, compaction->num_input_files(0));
-  ASSERT_GE(2U, compaction->num_input_files(1));
-  // File 5 has to be included in the compaction
-  ASSERT_EQ(5U, compaction->inputs(1)->back()->fd.GetNumber());
-}
-
-TEST_F(CompactionPickerTest, OverlappingUserKeys8) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  mutable_cf_options_.max_compaction_bytes = 100000000000u;
-  // grow the number of inputs in "level" without
-  // changing the number of "level+1" files we pick up
-  // Expand input level as much as possible
-  // no overlapping case
-  Add(1, 1U, "101", "150", 1U);
-  Add(1, 2U, "151", "200", 1U);
-  Add(1, 3U, "201", "300", 1000000000U);
-  Add(1, 4U, "301", "400", 1U);
-  Add(1, 5U, "401", "500", 1U);
-  Add(2, 6U, "150", "200", 1U);
-  Add(2, 7U, "200", "450", 1U, 0, 0);
-  Add(2, 8U, "500", "600", 1U);
-
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(2U, compaction->num_input_levels());
-  ASSERT_EQ(3U, compaction->num_input_files(0));
-  ASSERT_EQ(2U, compaction->num_input_files(1));
-  ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(3U, compaction->input(0, 1)->fd.GetNumber());
-  ASSERT_EQ(4U, compaction->input(0, 2)->fd.GetNumber());
-  ASSERT_EQ(6U, compaction->input(1, 0)->fd.GetNumber());
-  ASSERT_EQ(7U, compaction->input(1, 1)->fd.GetNumber());
-}
-
-TEST_F(CompactionPickerTest, OverlappingUserKeys9) {
-  NewVersionStorage(6, kCompactionStyleLevel);
-  mutable_cf_options_.max_compaction_bytes = 100000000000u;
-  // grow the number of inputs in "level" without
-  // changing the number of "level+1" files we pick up
-  // Expand input level as much as possible
-  // overlapping case
-  Add(1, 1U, "121", "150", 1U);
-  Add(1, 2U, "151", "200", 1U);
-  Add(1, 3U, "201", "300", 1000000000U);
-  Add(1, 4U, "301", "400", 1U);
-  Add(1, 5U, "401", "500", 1U);
-  Add(2, 6U, "100", "120", 1U);
-  Add(2, 7U, "150", "200", 1U);
-  Add(2, 8U, "200", "450", 1U, 0, 0);
-  Add(2, 9U, "501", "600", 1U);
-
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(2U, compaction->num_input_levels());
-  ASSERT_EQ(5U, compaction->num_input_files(0));
-  ASSERT_EQ(2U, compaction->num_input_files(1));
-  ASSERT_EQ(1U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(2U, compaction->input(0, 1)->fd.GetNumber());
-  ASSERT_EQ(3U, compaction->input(0, 2)->fd.GetNumber());
-  ASSERT_EQ(4U, compaction->input(0, 3)->fd.GetNumber());
-  ASSERT_EQ(7U, compaction->input(1, 0)->fd.GetNumber());
-  ASSERT_EQ(8U, compaction->input(1, 1)->fd.GetNumber());
-}
-
 TEST_F(CompactionPickerTest, NotScheduleL1IfL0WithHigherPri1) {
   NewVersionStorage(6, kCompactionStyleLevel);
   mutable_cf_options_.level0_file_num_compaction_trigger = 2;
@@ -931,22 +689,19 @@ TEST_F(CompactionPickerTest, EstimateCompactionBytesNeeded1) {
   Add(1, 4U, "400", "500", 600);
   Add(1, 5U, "600", "700", 600);
   // Level 2 is less than target 10000 even added size of level 1
-  // Size ratio of L2/L1 is 9600 / 1200 = 8
   Add(2, 6U, "150", "200", 2500);
   Add(2, 7U, "201", "210", 2000);
-  Add(2, 8U, "300", "310", 2600);
+  Add(2, 8U, "300", "310", 2500);
   Add(2, 9U, "400", "500", 2500);
   // Level 3 exceeds target 100,000 of 1000
   Add(3, 10U, "400", "500", 101000);
-  // Level 4 exceeds target 1,000,000 by 900 after adding size from level 3
-  // Size ratio L4/L3 is 9.9
-  // After merge from L3, L4 size is 1000900
-  Add(4, 11U, "400", "500", 999900);
-  Add(5, 11U, "400", "500", 8007200);
+  // Level 4 exceeds target 1,000,000 of 500 after adding size from level 3
+  Add(4, 11U, "400", "500", 999500);
+  Add(5, 11U, "400", "500", 8000000);
 
   UpdateVersionStorageInfo();
 
-  ASSERT_EQ(200u * 9u + 10900u + 900u * 9,
+  ASSERT_EQ(2200u + 11000u + 5500u,
             vstorage_->estimated_compaction_needed_bytes());
 }
 
@@ -962,42 +717,17 @@ TEST_F(CompactionPickerTest, EstimateCompactionBytesNeeded2) {
   Add(0, 4U, "150", "200", 200);
   Add(0, 5U, "150", "200", 200);
   Add(0, 6U, "150", "200", 200);
-  // Level 1 size will be 1400 after merging with L0
+  // Level 1 is over target by
   Add(1, 7U, "400", "500", 200);
   Add(1, 8U, "600", "700", 200);
   // Level 2 is less than target 10000 even added size of level 1
-  Add(2, 9U, "150", "200", 9100);
-  // Level 3 over the target, but since level 4 is empty, we assume it will be
-  // a trivial move.
+  Add(2, 9U, "150", "200", 9500);
   Add(3, 10U, "400", "500", 101000);
 
   UpdateVersionStorageInfo();
 
-  // estimated L1->L2 merge: 400 * (9100.0 / 1400.0 + 1.0)
-  ASSERT_EQ(1400u + 3000u, vstorage_->estimated_compaction_needed_bytes());
-}
-
-TEST_F(CompactionPickerTest, EstimateCompactionBytesNeeded3) {
-  int num_levels = ioptions_.num_levels;
-  ioptions_.level_compaction_dynamic_level_bytes = false;
-  mutable_cf_options_.level0_file_num_compaction_trigger = 3;
-  mutable_cf_options_.max_bytes_for_level_base = 1000;
-  mutable_cf_options_.max_bytes_for_level_multiplier = 10;
-  NewVersionStorage(num_levels, kCompactionStyleLevel);
-  Add(0, 1U, "150", "200", 2000);
-  Add(0, 2U, "150", "200", 2000);
-  Add(0, 4U, "150", "200", 2000);
-  Add(0, 5U, "150", "200", 2000);
-  Add(0, 6U, "150", "200", 1000);
-  // Level 1 size will be 10000 after merging with L0
-  Add(1, 7U, "400", "500", 500);
-  Add(1, 8U, "600", "700", 500);
-
-  Add(2, 9U, "150", "200", 10000);
-
-  UpdateVersionStorageInfo();
-
-  ASSERT_EQ(10000u + 18000u, vstorage_->estimated_compaction_needed_bytes());
+  ASSERT_EQ(1400u + 4400u + 11000u,
+            vstorage_->estimated_compaction_needed_bytes());
 }
 
 TEST_F(CompactionPickerTest, EstimateCompactionBytesNeededDynamicLevel) {
@@ -1021,14 +751,12 @@ TEST_F(CompactionPickerTest, EstimateCompactionBytesNeededDynamicLevel) {
   // num_levels - 3 is over target by 100 + 1000
   Add(num_levels - 3, 7U, "400", "500", 300);
   Add(num_levels - 3, 8U, "600", "700", 300);
-  // num_levels - 2 is over target by 1100 + 200
-  Add(num_levels - 2, 9U, "150", "200", 5200);
+  // Level 2 is over target by 1100 + 100
+  Add(num_levels - 2, 9U, "150", "200", 5100);
 
   UpdateVersionStorageInfo();
 
-  // Merging to the second last level: (5200 / 1600 + 1) * 1100
-  // Merging to the last level: (50000 / 6300 + 1) * 1300
-  ASSERT_EQ(1600u + 4675u + 11617u,
+  ASSERT_EQ(1600u + 12100u + 13200u,
             vstorage_->estimated_compaction_needed_bytes());
 }
 
@@ -1190,101 +918,6 @@ TEST_F(CompactionPickerTest, IsBottommostLevelTest) {
   DeleteVersionStorage();
 }
 
-TEST_F(CompactionPickerTest, MaxCompactionBytesHit) {
-  mutable_cf_options_.max_bytes_for_level_base = 1000000u;
-  mutable_cf_options_.max_compaction_bytes = 800000u;
-  ioptions_.level_compaction_dynamic_level_bytes = false;
-  NewVersionStorage(6, kCompactionStyleLevel);
-  // A compaction should be triggered and pick file 2 and 5.
-  // It can expand because adding file 1 and 3, the compaction size will
-  // exceed mutable_cf_options_.max_bytes_for_level_base.
-  Add(1, 1U, "100", "150", 300000U);
-  Add(1, 2U, "151", "200", 300001U, 0, 0);
-  Add(1, 3U, "201", "250", 300000U, 0, 0);
-  Add(1, 4U, "251", "300", 300000U, 0, 0);
-  Add(2, 5U, "100", "256", 1U);
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(2U, compaction->num_input_levels());
-  ASSERT_EQ(1U, compaction->num_input_files(0));
-  ASSERT_EQ(1U, compaction->num_input_files(1));
-  ASSERT_EQ(2U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(5U, compaction->input(1, 0)->fd.GetNumber());
-}
-
-TEST_F(CompactionPickerTest, MaxCompactionBytesNotHit) {
-  mutable_cf_options_.max_bytes_for_level_base = 800000u;
-  mutable_cf_options_.max_compaction_bytes = 1000000u;
-  ioptions_.level_compaction_dynamic_level_bytes = false;
-  NewVersionStorage(6, kCompactionStyleLevel);
-  // A compaction should be triggered and pick file 2 and 5.
-  // and it expands to file 1 and 3 too.
-  Add(1, 1U, "100", "150", 300000U);
-  Add(1, 2U, "151", "200", 300001U, 0, 0);
-  Add(1, 3U, "201", "250", 300000U, 0, 0);
-  Add(1, 4U, "251", "300", 300000U, 0, 0);
-  Add(2, 5U, "000", "251", 1U);
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-      cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_EQ(2U, compaction->num_input_levels());
-  ASSERT_EQ(3U, compaction->num_input_files(0));
-  ASSERT_EQ(1U, compaction->num_input_files(1));
-  ASSERT_EQ(1U, compaction->input(0, 0)->fd.GetNumber());
-  ASSERT_EQ(2U, compaction->input(0, 1)->fd.GetNumber());
-  ASSERT_EQ(3U, compaction->input(0, 2)->fd.GetNumber());
-  ASSERT_EQ(5U, compaction->input(1, 0)->fd.GetNumber());
-}
-
-TEST_F(CompactionPickerTest, IsTrivialMoveOn) {
-  mutable_cf_options_.max_bytes_for_level_base = 10000u;
-  mutable_cf_options_.max_compaction_bytes = 10001u;
-  ioptions_.level_compaction_dynamic_level_bytes = false;
-  NewVersionStorage(6, kCompactionStyleLevel);
-  // A compaction should be triggered and pick file 2
-  Add(1, 1U, "100", "150", 3000U);
-  Add(1, 2U, "151", "200", 3001U);
-  Add(1, 3U, "201", "250", 3000U);
-  Add(1, 4U, "251", "300", 3000U);
-
-  Add(3, 5U, "120", "130", 7000U);
-  Add(3, 6U, "170", "180", 7000U);
-  Add(3, 5U, "220", "230", 7000U);
-  Add(3, 5U, "270", "280", 7000U);
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-    cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_TRUE(compaction->IsTrivialMove());
-}
-
-TEST_F(CompactionPickerTest, IsTrivialMoveOff) {
-  mutable_cf_options_.max_bytes_for_level_base = 1000000u;
-  mutable_cf_options_.max_compaction_bytes = 10000u;
-  ioptions_.level_compaction_dynamic_level_bytes = false;
-  NewVersionStorage(6, kCompactionStyleLevel);
-  // A compaction should be triggered and pick all files from level 1
-  Add(1, 1U, "100", "150", 300000U, 0, 0);
-  Add(1, 2U, "150", "200", 300000U, 0, 0);
-  Add(1, 3U, "200", "250", 300000U, 0, 0);
-  Add(1, 4U, "250", "300", 300000U, 0, 0);
-
-  Add(3, 5U, "120", "130", 6000U);
-  Add(3, 6U, "140", "150", 6000U);
-  UpdateVersionStorageInfo();
-
-  std::unique_ptr<Compaction> compaction(level_compaction_picker.PickCompaction(
-    cf_name_, mutable_cf_options_, vstorage_.get(), &log_buffer_));
-  ASSERT_TRUE(compaction.get() != nullptr);
-  ASSERT_FALSE(compaction->IsTrivialMove());
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/comparator_db_test.cc

@@ -1,7 +1,9 @@
-//  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).
+// 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.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 #include <map>
 #include <string>
 
@@ -38,10 +40,6 @@ class KVIter : public Iterator {
   virtual void Seek(const Slice& k) override {
     iter_ = map_->lower_bound(k.ToString());
   }
-  virtual void SeekForPrev(const Slice& k) override {
-    iter_ = map_->upper_bound(k.ToString());
-    Prev();
-  }
   virtual void Next() override { ++iter_; }
   virtual void Prev() override {
     if (iter_ == map_->begin()) {

db/convenience.cc

@@ -1,8 +1,11 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 //
+// Copyright (c) 2012 Facebook.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
 
 #ifndef ROCKSDB_LITE
 

db/corruption_test.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -41,11 +41,7 @@ class CorruptionTest : public testing::Test {
   DB* db_;
 
   CorruptionTest() {
-    // If LRU cache shard bit is smaller than 2 (or -1 which will automatically
-    // set it to 0), test SequenceNumberRecovery will fail, likely because of a
-    // bug in recovery code. Keep it 4 for now to make the test passes.
-    tiny_cache_ = NewLRUCache(100, 4);
-    options_.wal_recovery_mode = WALRecoveryMode::kTolerateCorruptedTailRecords;
+    tiny_cache_ = NewLRUCache(100);
     options_.env = &env_;
     dbname_ = test::TmpDir() + "/corruption_test";
     DestroyDB(dbname_, options_);

db/cuckoo_table_db_test.cc

@@ -1,7 +1,7 @@
-//  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) 2014, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 #ifndef ROCKSDB_LITE
 
@@ -41,7 +41,6 @@ class CuckooTableDBTest : public testing::Test {
     options.memtable_factory.reset(NewHashLinkListRepFactory(4, 0, 3, true));
     options.allow_mmap_reads = true;
     options.create_if_missing = true;
-    options.allow_concurrent_memtable_write = false;
     return options;
   }
 

db/db_basic_test.cc

@@ -1,852 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-#include "rocksdb/perf_context.h"
-#if !defined(ROCKSDB_LITE)
-#include "util/sync_point.h"
-#endif
-
-namespace rocksdb {
-
-class DBBasicTest : public DBTestBase {
- public:
-  DBBasicTest() : DBTestBase("/db_basic_test") {}
-};
-
-TEST_F(DBBasicTest, OpenWhenOpen) {
-  Options options = CurrentOptions();
-  options.env = env_;
-  rocksdb::DB* db2 = nullptr;
-  rocksdb::Status s = DB::Open(options, dbname_, &db2);
-
-  ASSERT_EQ(Status::Code::kIOError, s.code());
-  ASSERT_EQ(Status::SubCode::kNone, s.subcode());
-  ASSERT_TRUE(strstr(s.getState(), "lock ") != nullptr);
-
-  delete db2;
-}
-
-#ifndef ROCKSDB_LITE
-TEST_F(DBBasicTest, ReadOnlyDB) {
-  ASSERT_OK(Put("foo", "v1"));
-  ASSERT_OK(Put("bar", "v2"));
-  ASSERT_OK(Put("foo", "v3"));
-  Close();
-
-  auto options = CurrentOptions();
-  assert(options.env = env_);
-  ASSERT_OK(ReadOnlyReopen(options));
-  ASSERT_EQ("v3", Get("foo"));
-  ASSERT_EQ("v2", Get("bar"));
-  Iterator* iter = db_->NewIterator(ReadOptions());
-  int count = 0;
-  for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
-    ASSERT_OK(iter->status());
-    ++count;
-  }
-  ASSERT_EQ(count, 2);
-  delete iter;
-  Close();
-
-  // Reopen and flush memtable.
-  Reopen(options);
-  Flush();
-  Close();
-  // Now check keys in read only mode.
-  ASSERT_OK(ReadOnlyReopen(options));
-  ASSERT_EQ("v3", Get("foo"));
-  ASSERT_EQ("v2", Get("bar"));
-  ASSERT_TRUE(db_->SyncWAL().IsNotSupported());
-}
-
-TEST_F(DBBasicTest, CompactedDB) {
-  const uint64_t kFileSize = 1 << 20;
-  Options options = CurrentOptions();
-  options.disable_auto_compactions = true;
-  options.write_buffer_size = kFileSize;
-  options.target_file_size_base = kFileSize;
-  options.max_bytes_for_level_base = 1 << 30;
-  options.compression = kNoCompression;
-  Reopen(options);
-  // 1 L0 file, use CompactedDB if max_open_files = -1
-  ASSERT_OK(Put("aaa", DummyString(kFileSize / 2, '1')));
-  Flush();
-  Close();
-  ASSERT_OK(ReadOnlyReopen(options));
-  Status s = Put("new", "value");
-  ASSERT_EQ(s.ToString(),
-            "Not implemented: Not supported operation in read only mode.");
-  ASSERT_EQ(DummyString(kFileSize / 2, '1'), Get("aaa"));
-  Close();
-  options.max_open_files = -1;
-  ASSERT_OK(ReadOnlyReopen(options));
-  s = Put("new", "value");
-  ASSERT_EQ(s.ToString(),
-            "Not implemented: Not supported in compacted db mode.");
-  ASSERT_EQ(DummyString(kFileSize / 2, '1'), Get("aaa"));
-  Close();
-  Reopen(options);
-  // Add more L0 files
-  ASSERT_OK(Put("bbb", DummyString(kFileSize / 2, '2')));
-  Flush();
-  ASSERT_OK(Put("aaa", DummyString(kFileSize / 2, 'a')));
-  Flush();
-  ASSERT_OK(Put("bbb", DummyString(kFileSize / 2, 'b')));
-  ASSERT_OK(Put("eee", DummyString(kFileSize / 2, 'e')));
-  Flush();
-  Close();
-
-  ASSERT_OK(ReadOnlyReopen(options));
-  // Fallback to read-only DB
-  s = Put("new", "value");
-  ASSERT_EQ(s.ToString(),
-            "Not implemented: Not supported operation in read only mode.");
-  Close();
-
-  // Full compaction
-  Reopen(options);
-  // Add more keys
-  ASSERT_OK(Put("fff", DummyString(kFileSize / 2, 'f')));
-  ASSERT_OK(Put("hhh", DummyString(kFileSize / 2, 'h')));
-  ASSERT_OK(Put("iii", DummyString(kFileSize / 2, 'i')));
-  ASSERT_OK(Put("jjj", DummyString(kFileSize / 2, 'j')));
-  db_->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  ASSERT_EQ(3, NumTableFilesAtLevel(1));
-  Close();
-
-  // CompactedDB
-  ASSERT_OK(ReadOnlyReopen(options));
-  s = Put("new", "value");
-  ASSERT_EQ(s.ToString(),
-            "Not implemented: Not supported in compacted db mode.");
-  ASSERT_EQ("NOT_FOUND", Get("abc"));
-  ASSERT_EQ(DummyString(kFileSize / 2, 'a'), Get("aaa"));
-  ASSERT_EQ(DummyString(kFileSize / 2, 'b'), Get("bbb"));
-  ASSERT_EQ("NOT_FOUND", Get("ccc"));
-  ASSERT_EQ(DummyString(kFileSize / 2, 'e'), Get("eee"));
-  ASSERT_EQ(DummyString(kFileSize / 2, 'f'), Get("fff"));
-  ASSERT_EQ("NOT_FOUND", Get("ggg"));
-  ASSERT_EQ(DummyString(kFileSize / 2, 'h'), Get("hhh"));
-  ASSERT_EQ(DummyString(kFileSize / 2, 'i'), Get("iii"));
-  ASSERT_EQ(DummyString(kFileSize / 2, 'j'), Get("jjj"));
-  ASSERT_EQ("NOT_FOUND", Get("kkk"));
-
-  // MultiGet
-  std::vector<std::string> values;
-  std::vector<Status> status_list = dbfull()->MultiGet(
-      ReadOptions(),
-      std::vector<Slice>({Slice("aaa"), Slice("ccc"), Slice("eee"),
-                          Slice("ggg"), Slice("iii"), Slice("kkk")}),
-      &values);
-  ASSERT_EQ(status_list.size(), static_cast<uint64_t>(6));
-  ASSERT_EQ(values.size(), static_cast<uint64_t>(6));
-  ASSERT_OK(status_list[0]);
-  ASSERT_EQ(DummyString(kFileSize / 2, 'a'), values[0]);
-  ASSERT_TRUE(status_list[1].IsNotFound());
-  ASSERT_OK(status_list[2]);
-  ASSERT_EQ(DummyString(kFileSize / 2, 'e'), values[2]);
-  ASSERT_TRUE(status_list[3].IsNotFound());
-  ASSERT_OK(status_list[4]);
-  ASSERT_EQ(DummyString(kFileSize / 2, 'i'), values[4]);
-  ASSERT_TRUE(status_list[5].IsNotFound());
-
-  Reopen(options);
-  // Add a key
-  ASSERT_OK(Put("fff", DummyString(kFileSize / 2, 'f')));
-  Close();
-  ASSERT_OK(ReadOnlyReopen(options));
-  s = Put("new", "value");
-  ASSERT_EQ(s.ToString(),
-            "Not implemented: Not supported operation in read only mode.");
-}
-
-TEST_F(DBBasicTest, LevelLimitReopen) {
-  Options options = CurrentOptions();
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  const std::string value(1024 * 1024, ' ');
-  int i = 0;
-  while (NumTableFilesAtLevel(2, 1) == 0) {
-    ASSERT_OK(Put(1, Key(i++), value));
-  }
-
-  options.num_levels = 1;
-  options.max_bytes_for_level_multiplier_additional.resize(1, 1);
-  Status s = TryReopenWithColumnFamilies({"default", "pikachu"}, options);
-  ASSERT_EQ(s.IsInvalidArgument(), true);
-  ASSERT_EQ(s.ToString(),
-            "Invalid argument: db has more levels than options.num_levels");
-
-  options.num_levels = 10;
-  options.max_bytes_for_level_multiplier_additional.resize(10, 1);
-  ASSERT_OK(TryReopenWithColumnFamilies({"default", "pikachu"}, options));
-}
-#endif  // ROCKSDB_LITE
-
-TEST_F(DBBasicTest, PutDeleteGet) {
-  do {
-    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
-    ASSERT_OK(Put(1, "foo", "v1"));
-    ASSERT_EQ("v1", Get(1, "foo"));
-    ASSERT_OK(Put(1, "foo", "v2"));
-    ASSERT_EQ("v2", Get(1, "foo"));
-    ASSERT_OK(Delete(1, "foo"));
-    ASSERT_EQ("NOT_FOUND", Get(1, "foo"));
-  } while (ChangeOptions());
-}
-
-TEST_F(DBBasicTest, PutSingleDeleteGet) {
-  do {
-    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
-    ASSERT_OK(Put(1, "foo", "v1"));
-    ASSERT_EQ("v1", Get(1, "foo"));
-    ASSERT_OK(Put(1, "foo2", "v2"));
-    ASSERT_EQ("v2", Get(1, "foo2"));
-    ASSERT_OK(SingleDelete(1, "foo"));
-    ASSERT_EQ("NOT_FOUND", Get(1, "foo"));
-    // Skip HashCuckooRep as it does not support single delete. FIFO and
-    // universal compaction do not apply to the test case. Skip MergePut
-    // because single delete does not get removed when it encounters a merge.
-  } while (ChangeOptions(kSkipHashCuckoo | kSkipFIFOCompaction |
-                         kSkipUniversalCompaction | kSkipMergePut));
-}
-
-TEST_F(DBBasicTest, EmptyFlush) {
-  // It is possible to produce empty flushes when using single deletes. Tests
-  // whether empty flushes cause issues.
-  do {
-    Random rnd(301);
-
-    Options options = CurrentOptions();
-    options.disable_auto_compactions = true;
-    CreateAndReopenWithCF({"pikachu"}, options);
-
-    Put(1, "a", Slice());
-    SingleDelete(1, "a");
-    ASSERT_OK(Flush(1));
-
-    ASSERT_EQ("[ ]", AllEntriesFor("a", 1));
-    // Skip HashCuckooRep as it does not support single delete. FIFO and
-    // universal compaction do not apply to the test case. Skip MergePut
-    // because merges cannot be combined with single deletions.
-  } while (ChangeOptions(kSkipHashCuckoo | kSkipFIFOCompaction |
-                         kSkipUniversalCompaction | kSkipMergePut));
-}
-
-TEST_F(DBBasicTest, GetFromVersions) {
-  do {
-    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
-    ASSERT_OK(Put(1, "foo", "v1"));
-    ASSERT_OK(Flush(1));
-    ASSERT_EQ("v1", Get(1, "foo"));
-    ASSERT_EQ("NOT_FOUND", Get(0, "foo"));
-  } while (ChangeOptions());
-}
-
-#ifndef ROCKSDB_LITE
-TEST_F(DBBasicTest, GetSnapshot) {
-  anon::OptionsOverride options_override;
-  options_override.skip_policy = kSkipNoSnapshot;
-  do {
-    CreateAndReopenWithCF({"pikachu"}, CurrentOptions(options_override));
-    // Try with both a short key and a long key
-    for (int i = 0; i < 2; i++) {
-      std::string key = (i == 0) ? std::string("foo") : std::string(200, 'x');
-      ASSERT_OK(Put(1, key, "v1"));
-      const Snapshot* s1 = db_->GetSnapshot();
-      if (option_config_ == kHashCuckoo) {
-        // Unsupported case.
-        ASSERT_TRUE(s1 == nullptr);
-        break;
-      }
-      ASSERT_OK(Put(1, key, "v2"));
-      ASSERT_EQ("v2", Get(1, key));
-      ASSERT_EQ("v1", Get(1, key, s1));
-      ASSERT_OK(Flush(1));
-      ASSERT_EQ("v2", Get(1, key));
-      ASSERT_EQ("v1", Get(1, key, s1));
-      db_->ReleaseSnapshot(s1);
-    }
-  } while (ChangeOptions());
-}
-#endif  // ROCKSDB_LITE
-
-TEST_F(DBBasicTest, CheckLock) {
-  do {
-    DB* localdb;
-    Options options = CurrentOptions();
-    ASSERT_OK(TryReopen(options));
-
-    // second open should fail
-    ASSERT_TRUE(!(DB::Open(options, dbname_, &localdb)).ok());
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBBasicTest, FlushMultipleMemtable) {
-  do {
-    Options options = CurrentOptions();
-    WriteOptions writeOpt = WriteOptions();
-    writeOpt.disableWAL = true;
-    options.max_write_buffer_number = 4;
-    options.min_write_buffer_number_to_merge = 3;
-    options.max_write_buffer_number_to_maintain = -1;
-    CreateAndReopenWithCF({"pikachu"}, options);
-    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v1"));
-    ASSERT_OK(Flush(1));
-    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v1"));
-
-    ASSERT_EQ("v1", Get(1, "foo"));
-    ASSERT_EQ("v1", Get(1, "bar"));
-    ASSERT_OK(Flush(1));
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBBasicTest, FlushEmptyColumnFamily) {
-  // Block flush thread and disable compaction thread
-  env_->SetBackgroundThreads(1, Env::HIGH);
-  env_->SetBackgroundThreads(1, Env::LOW);
-  test::SleepingBackgroundTask sleeping_task_low;
-  env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask, &sleeping_task_low,
-                 Env::Priority::LOW);
-  test::SleepingBackgroundTask sleeping_task_high;
-  env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask,
-                 &sleeping_task_high, Env::Priority::HIGH);
-
-  Options options = CurrentOptions();
-  // disable compaction
-  options.disable_auto_compactions = true;
-  WriteOptions writeOpt = WriteOptions();
-  writeOpt.disableWAL = true;
-  options.max_write_buffer_number = 2;
-  options.min_write_buffer_number_to_merge = 1;
-  options.max_write_buffer_number_to_maintain = 1;
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  // Compaction can still go through even if no thread can flush the
-  // mem table.
-  ASSERT_OK(Flush(0));
-  ASSERT_OK(Flush(1));
-
-  // Insert can go through
-  ASSERT_OK(dbfull()->Put(writeOpt, handles_[0], "foo", "v1"));
-  ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v1"));
-
-  ASSERT_EQ("v1", Get(0, "foo"));
-  ASSERT_EQ("v1", Get(1, "bar"));
-
-  sleeping_task_high.WakeUp();
-  sleeping_task_high.WaitUntilDone();
-
-  // Flush can still go through.
-  ASSERT_OK(Flush(0));
-  ASSERT_OK(Flush(1));
-
-  sleeping_task_low.WakeUp();
-  sleeping_task_low.WaitUntilDone();
-}
-
-TEST_F(DBBasicTest, FLUSH) {
-  do {
-    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
-    WriteOptions writeOpt = WriteOptions();
-    writeOpt.disableWAL = true;
-    SetPerfLevel(kEnableTime);
-    ;
-    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v1"));
-    // this will now also flush the last 2 writes
-    ASSERT_OK(Flush(1));
-    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v1"));
-
-    perf_context.Reset();
-    Get(1, "foo");
-    ASSERT_TRUE((int)perf_context.get_from_output_files_time > 0);
-
-    ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
-    ASSERT_EQ("v1", Get(1, "foo"));
-    ASSERT_EQ("v1", Get(1, "bar"));
-
-    writeOpt.disableWAL = true;
-    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v2"));
-    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v2"));
-    ASSERT_OK(Flush(1));
-
-    ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
-    ASSERT_EQ("v2", Get(1, "bar"));
-    perf_context.Reset();
-    ASSERT_EQ("v2", Get(1, "foo"));
-    ASSERT_TRUE((int)perf_context.get_from_output_files_time > 0);
-
-    writeOpt.disableWAL = false;
-    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "bar", "v3"));
-    ASSERT_OK(dbfull()->Put(writeOpt, handles_[1], "foo", "v3"));
-    ASSERT_OK(Flush(1));
-
-    ReopenWithColumnFamilies({"default", "pikachu"}, CurrentOptions());
-    // 'foo' should be there because its put
-    // has WAL enabled.
-    ASSERT_EQ("v3", Get(1, "foo"));
-    ASSERT_EQ("v3", Get(1, "bar"));
-
-    SetPerfLevel(kDisable);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBBasicTest, ManifestRollOver) {
-  do {
-    Options options;
-    options.max_manifest_file_size = 10;  // 10 bytes
-    options = CurrentOptions(options);
-    CreateAndReopenWithCF({"pikachu"}, options);
-    {
-      ASSERT_OK(Put(1, "manifest_key1", std::string(1000, '1')));
-      ASSERT_OK(Put(1, "manifest_key2", std::string(1000, '2')));
-      ASSERT_OK(Put(1, "manifest_key3", std::string(1000, '3')));
-      uint64_t manifest_before_flush = dbfull()->TEST_Current_Manifest_FileNo();
-      ASSERT_OK(Flush(1));  // This should trigger LogAndApply.
-      uint64_t manifest_after_flush = dbfull()->TEST_Current_Manifest_FileNo();
-      ASSERT_GT(manifest_after_flush, manifest_before_flush);
-      ReopenWithColumnFamilies({"default", "pikachu"}, options);
-      ASSERT_GT(dbfull()->TEST_Current_Manifest_FileNo(), manifest_after_flush);
-      // check if a new manifest file got inserted or not.
-      ASSERT_EQ(std::string(1000, '1'), Get(1, "manifest_key1"));
-      ASSERT_EQ(std::string(1000, '2'), Get(1, "manifest_key2"));
-      ASSERT_EQ(std::string(1000, '3'), Get(1, "manifest_key3"));
-    }
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBBasicTest, IdentityAcrossRestarts) {
-  do {
-    std::string id1;
-    ASSERT_OK(db_->GetDbIdentity(id1));
-
-    Options options = CurrentOptions();
-    Reopen(options);
-    std::string id2;
-    ASSERT_OK(db_->GetDbIdentity(id2));
-    // id1 should match id2 because identity was not regenerated
-    ASSERT_EQ(id1.compare(id2), 0);
-
-    std::string idfilename = IdentityFileName(dbname_);
-    ASSERT_OK(env_->DeleteFile(idfilename));
-    Reopen(options);
-    std::string id3;
-    ASSERT_OK(db_->GetDbIdentity(id3));
-    // id1 should NOT match id3 because identity was regenerated
-    ASSERT_NE(id1.compare(id3), 0);
-  } while (ChangeCompactOptions());
-}
-
-#ifndef ROCKSDB_LITE
-TEST_F(DBBasicTest, Snapshot) {
-  anon::OptionsOverride options_override;
-  options_override.skip_policy = kSkipNoSnapshot;
-  do {
-    CreateAndReopenWithCF({"pikachu"}, CurrentOptions(options_override));
-    Put(0, "foo", "0v1");
-    Put(1, "foo", "1v1");
-
-    const Snapshot* s1 = db_->GetSnapshot();
-    ASSERT_EQ(1U, GetNumSnapshots());
-    uint64_t time_snap1 = GetTimeOldestSnapshots();
-    ASSERT_GT(time_snap1, 0U);
-    Put(0, "foo", "0v2");
-    Put(1, "foo", "1v2");
-
-    env_->addon_time_.fetch_add(1);
-
-    const Snapshot* s2 = db_->GetSnapshot();
-    ASSERT_EQ(2U, GetNumSnapshots());
-    ASSERT_EQ(time_snap1, GetTimeOldestSnapshots());
-    Put(0, "foo", "0v3");
-    Put(1, "foo", "1v3");
-
-    {
-      ManagedSnapshot s3(db_);
-      ASSERT_EQ(3U, GetNumSnapshots());
-      ASSERT_EQ(time_snap1, GetTimeOldestSnapshots());
-
-      Put(0, "foo", "0v4");
-      Put(1, "foo", "1v4");
-      ASSERT_EQ("0v1", Get(0, "foo", s1));
-      ASSERT_EQ("1v1", Get(1, "foo", s1));
-      ASSERT_EQ("0v2", Get(0, "foo", s2));
-      ASSERT_EQ("1v2", Get(1, "foo", s2));
-      ASSERT_EQ("0v3", Get(0, "foo", s3.snapshot()));
-      ASSERT_EQ("1v3", Get(1, "foo", s3.snapshot()));
-      ASSERT_EQ("0v4", Get(0, "foo"));
-      ASSERT_EQ("1v4", Get(1, "foo"));
-    }
-
-    ASSERT_EQ(2U, GetNumSnapshots());
-    ASSERT_EQ(time_snap1, GetTimeOldestSnapshots());
-    ASSERT_EQ("0v1", Get(0, "foo", s1));
-    ASSERT_EQ("1v1", Get(1, "foo", s1));
-    ASSERT_EQ("0v2", Get(0, "foo", s2));
-    ASSERT_EQ("1v2", Get(1, "foo", s2));
-    ASSERT_EQ("0v4", Get(0, "foo"));
-    ASSERT_EQ("1v4", Get(1, "foo"));
-
-    db_->ReleaseSnapshot(s1);
-    ASSERT_EQ("0v2", Get(0, "foo", s2));
-    ASSERT_EQ("1v2", Get(1, "foo", s2));
-    ASSERT_EQ("0v4", Get(0, "foo"));
-    ASSERT_EQ("1v4", Get(1, "foo"));
-    ASSERT_EQ(1U, GetNumSnapshots());
-    ASSERT_LT(time_snap1, GetTimeOldestSnapshots());
-
-    db_->ReleaseSnapshot(s2);
-    ASSERT_EQ(0U, GetNumSnapshots());
-    ASSERT_EQ("0v4", Get(0, "foo"));
-    ASSERT_EQ("1v4", Get(1, "foo"));
-  } while (ChangeOptions(kSkipHashCuckoo));
-}
-
-#endif  // ROCKSDB_LITE
-
-TEST_F(DBBasicTest, CompactBetweenSnapshots) {
-  anon::OptionsOverride options_override;
-  options_override.skip_policy = kSkipNoSnapshot;
-  do {
-    Options options = CurrentOptions(options_override);
-    options.disable_auto_compactions = true;
-    CreateAndReopenWithCF({"pikachu"}, options);
-    Random rnd(301);
-    FillLevels("a", "z", 1);
-
-    Put(1, "foo", "first");
-    const Snapshot* snapshot1 = db_->GetSnapshot();
-    Put(1, "foo", "second");
-    Put(1, "foo", "third");
-    Put(1, "foo", "fourth");
-    const Snapshot* snapshot2 = db_->GetSnapshot();
-    Put(1, "foo", "fifth");
-    Put(1, "foo", "sixth");
-
-    // All entries (including duplicates) exist
-    // before any compaction or flush is triggered.
-    ASSERT_EQ(AllEntriesFor("foo", 1),
-              "[ sixth, fifth, fourth, third, second, first ]");
-    ASSERT_EQ("sixth", Get(1, "foo"));
-    ASSERT_EQ("fourth", Get(1, "foo", snapshot2));
-    ASSERT_EQ("first", Get(1, "foo", snapshot1));
-
-    // After a flush, "second", "third" and "fifth" should
-    // be removed
-    ASSERT_OK(Flush(1));
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ sixth, fourth, first ]");
-
-    // after we release the snapshot1, only two values left
-    db_->ReleaseSnapshot(snapshot1);
-    FillLevels("a", "z", 1);
-    dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                           nullptr);
-
-    // We have only one valid snapshot snapshot2. Since snapshot1 is
-    // not valid anymore, "first" should be removed by a compaction.
-    ASSERT_EQ("sixth", Get(1, "foo"));
-    ASSERT_EQ("fourth", Get(1, "foo", snapshot2));
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ sixth, fourth ]");
-
-    // after we release the snapshot2, only one value should be left
-    db_->ReleaseSnapshot(snapshot2);
-    FillLevels("a", "z", 1);
-    dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                           nullptr);
-    ASSERT_EQ("sixth", Get(1, "foo"));
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ sixth ]");
-    // skip HashCuckooRep as it does not support snapshot
-  } while (ChangeOptions(kSkipHashCuckoo | kSkipFIFOCompaction));
-}
-
-TEST_F(DBBasicTest, DBOpen_Options) {
-  Options options = CurrentOptions();
-  std::string dbname = test::TmpDir(env_) + "/db_options_test";
-  ASSERT_OK(DestroyDB(dbname, options));
-
-  // Does not exist, and create_if_missing == false: error
-  DB* db = nullptr;
-  options.create_if_missing = false;
-  Status s = DB::Open(options, dbname, &db);
-  ASSERT_TRUE(strstr(s.ToString().c_str(), "does not exist") != nullptr);
-  ASSERT_TRUE(db == nullptr);
-
-  // Does not exist, and create_if_missing == true: OK
-  options.create_if_missing = true;
-  s = DB::Open(options, dbname, &db);
-  ASSERT_OK(s);
-  ASSERT_TRUE(db != nullptr);
-
-  delete db;
-  db = nullptr;
-
-  // Does exist, and error_if_exists == true: error
-  options.create_if_missing = false;
-  options.error_if_exists = true;
-  s = DB::Open(options, dbname, &db);
-  ASSERT_TRUE(strstr(s.ToString().c_str(), "exists") != nullptr);
-  ASSERT_TRUE(db == nullptr);
-
-  // Does exist, and error_if_exists == false: OK
-  options.create_if_missing = true;
-  options.error_if_exists = false;
-  s = DB::Open(options, dbname, &db);
-  ASSERT_OK(s);
-  ASSERT_TRUE(db != nullptr);
-
-  delete db;
-  db = nullptr;
-}
-
-TEST_F(DBBasicTest, CompactOnFlush) {
-  anon::OptionsOverride options_override;
-  options_override.skip_policy = kSkipNoSnapshot;
-  do {
-    Options options = CurrentOptions(options_override);
-    options.disable_auto_compactions = true;
-    CreateAndReopenWithCF({"pikachu"}, options);
-
-    Put(1, "foo", "v1");
-    ASSERT_OK(Flush(1));
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ v1 ]");
-
-    // Write two new keys
-    Put(1, "a", "begin");
-    Put(1, "z", "end");
-    Flush(1);
-
-    // Case1: Delete followed by a put
-    Delete(1, "foo");
-    Put(1, "foo", "v2");
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ v2, DEL, v1 ]");
-
-    // After the current memtable is flushed, the DEL should
-    // have been removed
-    ASSERT_OK(Flush(1));
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ v2, v1 ]");
-
-    dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                           nullptr);
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ v2 ]");
-
-    // Case 2: Delete followed by another delete
-    Delete(1, "foo");
-    Delete(1, "foo");
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ DEL, DEL, v2 ]");
-    ASSERT_OK(Flush(1));
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ DEL, v2 ]");
-    dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                           nullptr);
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ ]");
-
-    // Case 3: Put followed by a delete
-    Put(1, "foo", "v3");
-    Delete(1, "foo");
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ DEL, v3 ]");
-    ASSERT_OK(Flush(1));
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ DEL ]");
-    dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                           nullptr);
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ ]");
-
-    // Case 4: Put followed by another Put
-    Put(1, "foo", "v4");
-    Put(1, "foo", "v5");
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ v5, v4 ]");
-    ASSERT_OK(Flush(1));
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ v5 ]");
-    dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                           nullptr);
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ v5 ]");
-
-    // clear database
-    Delete(1, "foo");
-    dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                           nullptr);
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ ]");
-
-    // Case 5: Put followed by snapshot followed by another Put
-    // Both puts should remain.
-    Put(1, "foo", "v6");
-    const Snapshot* snapshot = db_->GetSnapshot();
-    Put(1, "foo", "v7");
-    ASSERT_OK(Flush(1));
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ v7, v6 ]");
-    db_->ReleaseSnapshot(snapshot);
-
-    // clear database
-    Delete(1, "foo");
-    dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                           nullptr);
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ ]");
-
-    // Case 5: snapshot followed by a put followed by another Put
-    // Only the last put should remain.
-    const Snapshot* snapshot1 = db_->GetSnapshot();
-    Put(1, "foo", "v8");
-    Put(1, "foo", "v9");
-    ASSERT_OK(Flush(1));
-    ASSERT_EQ(AllEntriesFor("foo", 1), "[ v9 ]");
-    db_->ReleaseSnapshot(snapshot1);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBBasicTest, FlushOneColumnFamily) {
-  Options options = CurrentOptions();
-  CreateAndReopenWithCF({"pikachu", "ilya", "muromec", "dobrynia", "nikitich",
-                         "alyosha", "popovich"},
-                        options);
-
-  ASSERT_OK(Put(0, "Default", "Default"));
-  ASSERT_OK(Put(1, "pikachu", "pikachu"));
-  ASSERT_OK(Put(2, "ilya", "ilya"));
-  ASSERT_OK(Put(3, "muromec", "muromec"));
-  ASSERT_OK(Put(4, "dobrynia", "dobrynia"));
-  ASSERT_OK(Put(5, "nikitich", "nikitich"));
-  ASSERT_OK(Put(6, "alyosha", "alyosha"));
-  ASSERT_OK(Put(7, "popovich", "popovich"));
-
-  for (int i = 0; i < 8; ++i) {
-    Flush(i);
-    auto tables = ListTableFiles(env_, dbname_);
-    ASSERT_EQ(tables.size(), i + 1U);
-  }
-}
-
-TEST_F(DBBasicTest, MultiGetSimple) {
-  do {
-    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
-    ASSERT_OK(Put(1, "k1", "v1"));
-    ASSERT_OK(Put(1, "k2", "v2"));
-    ASSERT_OK(Put(1, "k3", "v3"));
-    ASSERT_OK(Put(1, "k4", "v4"));
-    ASSERT_OK(Delete(1, "k4"));
-    ASSERT_OK(Put(1, "k5", "v5"));
-    ASSERT_OK(Delete(1, "no_key"));
-
-    std::vector<Slice> keys({"k1", "k2", "k3", "k4", "k5", "no_key"});
-
-    std::vector<std::string> values(20, "Temporary data to be overwritten");
-    std::vector<ColumnFamilyHandle*> cfs(keys.size(), handles_[1]);
-
-    std::vector<Status> s = db_->MultiGet(ReadOptions(), cfs, keys, &values);
-    ASSERT_EQ(values.size(), keys.size());
-    ASSERT_EQ(values[0], "v1");
-    ASSERT_EQ(values[1], "v2");
-    ASSERT_EQ(values[2], "v3");
-    ASSERT_EQ(values[4], "v5");
-
-    ASSERT_OK(s[0]);
-    ASSERT_OK(s[1]);
-    ASSERT_OK(s[2]);
-    ASSERT_TRUE(s[3].IsNotFound());
-    ASSERT_OK(s[4]);
-    ASSERT_TRUE(s[5].IsNotFound());
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBBasicTest, MultiGetEmpty) {
-  do {
-    CreateAndReopenWithCF({"pikachu"}, CurrentOptions());
-    // Empty Key Set
-    std::vector<Slice> keys;
-    std::vector<std::string> values;
-    std::vector<ColumnFamilyHandle*> cfs;
-    std::vector<Status> s = db_->MultiGet(ReadOptions(), cfs, keys, &values);
-    ASSERT_EQ(s.size(), 0U);
-
-    // Empty Database, Empty Key Set
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    DestroyAndReopen(options);
-    CreateAndReopenWithCF({"pikachu"}, options);
-    s = db_->MultiGet(ReadOptions(), cfs, keys, &values);
-    ASSERT_EQ(s.size(), 0U);
-
-    // Empty Database, Search for Keys
-    keys.resize(2);
-    keys[0] = "a";
-    keys[1] = "b";
-    cfs.push_back(handles_[0]);
-    cfs.push_back(handles_[1]);
-    s = db_->MultiGet(ReadOptions(), cfs, keys, &values);
-    ASSERT_EQ(static_cast<int>(s.size()), 2);
-    ASSERT_TRUE(s[0].IsNotFound() && s[1].IsNotFound());
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBBasicTest, ChecksumTest) {
-  BlockBasedTableOptions table_options;
-  Options options = CurrentOptions();
-
-  table_options.checksum = kCRC32c;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  Reopen(options);
-  ASSERT_OK(Put("a", "b"));
-  ASSERT_OK(Put("c", "d"));
-  ASSERT_OK(Flush());  // table with crc checksum
-
-  table_options.checksum = kxxHash;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  Reopen(options);
-  ASSERT_OK(Put("e", "f"));
-  ASSERT_OK(Put("g", "h"));
-  ASSERT_OK(Flush());  // table with xxhash checksum
-
-  table_options.checksum = kCRC32c;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  Reopen(options);
-  ASSERT_EQ("b", Get("a"));
-  ASSERT_EQ("d", Get("c"));
-  ASSERT_EQ("f", Get("e"));
-  ASSERT_EQ("h", Get("g"));
-
-  table_options.checksum = kCRC32c;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-  Reopen(options);
-  ASSERT_EQ("b", Get("a"));
-  ASSERT_EQ("d", Get("c"));
-  ASSERT_EQ("f", Get("e"));
-  ASSERT_EQ("h", Get("g"));
-}
-
-// On Windows you can have either memory mapped file or a file
-// with unbuffered access. So this asserts and does not make
-// sense to run
-#ifndef OS_WIN
-TEST_F(DBBasicTest, MmapAndBufferOptions) {
-  Options options = CurrentOptions();
-
-  options.use_direct_reads = true;
-  options.allow_mmap_reads = true;
-  ASSERT_NOK(TryReopen(options));
-
-  // All other combinations are acceptable
-  options.use_direct_reads = false;
-  ASSERT_OK(TryReopen(options));
-
-  if (IsDirectIOSupported()) {
-    options.use_direct_reads = true;
-    options.allow_mmap_reads = false;
-    ASSERT_OK(TryReopen(options));
-  }
-
-  options.use_direct_reads = false;
-  ASSERT_OK(TryReopen(options));
-}
-#endif
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_block_cache_test.cc

@@ -1,579 +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 <cstdlib>
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-#include "util/lru_cache.h"
-
-namespace rocksdb {
-
-class DBBlockCacheTest : public DBTestBase {
- private:
-  size_t miss_count_ = 0;
-  size_t hit_count_ = 0;
-  size_t insert_count_ = 0;
-  size_t failure_count_ = 0;
-  size_t compressed_miss_count_ = 0;
-  size_t compressed_hit_count_ = 0;
-  size_t compressed_insert_count_ = 0;
-  size_t compressed_failure_count_ = 0;
-
- public:
-  const size_t kNumBlocks = 10;
-  const size_t kValueSize = 100;
-
-  DBBlockCacheTest() : DBTestBase("/db_block_cache_test") {}
-
-  BlockBasedTableOptions GetTableOptions() {
-    BlockBasedTableOptions table_options;
-    // Set a small enough block size so that each key-value get its own block.
-    table_options.block_size = 1;
-    return table_options;
-  }
-
-  Options GetOptions(const BlockBasedTableOptions& table_options) {
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    options.avoid_flush_during_recovery = false;
-    // options.compression = kNoCompression;
-    options.statistics = rocksdb::CreateDBStatistics();
-    options.table_factory.reset(new BlockBasedTableFactory(table_options));
-    return options;
-  }
-
-  void InitTable(const Options& options) {
-    std::string value(kValueSize, 'a');
-    for (size_t i = 0; i < kNumBlocks; i++) {
-      ASSERT_OK(Put(ToString(i), value.c_str()));
-    }
-  }
-
-  void RecordCacheCounters(const Options& options) {
-    miss_count_ = TestGetTickerCount(options, BLOCK_CACHE_MISS);
-    hit_count_ = TestGetTickerCount(options, BLOCK_CACHE_HIT);
-    insert_count_ = TestGetTickerCount(options, BLOCK_CACHE_ADD);
-    failure_count_ = TestGetTickerCount(options, BLOCK_CACHE_ADD_FAILURES);
-    compressed_miss_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS);
-    compressed_hit_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_HIT);
-    compressed_insert_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD);
-    compressed_failure_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD_FAILURES);
-  }
-
-  void CheckCacheCounters(const Options& options, size_t expected_misses,
-                          size_t expected_hits, size_t expected_inserts,
-                          size_t expected_failures) {
-    size_t new_miss_count = TestGetTickerCount(options, BLOCK_CACHE_MISS);
-    size_t new_hit_count = TestGetTickerCount(options, BLOCK_CACHE_HIT);
-    size_t new_insert_count = TestGetTickerCount(options, BLOCK_CACHE_ADD);
-    size_t new_failure_count =
-        TestGetTickerCount(options, BLOCK_CACHE_ADD_FAILURES);
-    ASSERT_EQ(miss_count_ + expected_misses, new_miss_count);
-    ASSERT_EQ(hit_count_ + expected_hits, new_hit_count);
-    ASSERT_EQ(insert_count_ + expected_inserts, new_insert_count);
-    ASSERT_EQ(failure_count_ + expected_failures, new_failure_count);
-    miss_count_ = new_miss_count;
-    hit_count_ = new_hit_count;
-    insert_count_ = new_insert_count;
-    failure_count_ = new_failure_count;
-  }
-
-  void CheckCompressedCacheCounters(const Options& options,
-                                    size_t expected_misses,
-                                    size_t expected_hits,
-                                    size_t expected_inserts,
-                                    size_t expected_failures) {
-    size_t new_miss_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS);
-    size_t new_hit_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_HIT);
-    size_t new_insert_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD);
-    size_t new_failure_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD_FAILURES);
-    ASSERT_EQ(compressed_miss_count_ + expected_misses, new_miss_count);
-    ASSERT_EQ(compressed_hit_count_ + expected_hits, new_hit_count);
-    ASSERT_EQ(compressed_insert_count_ + expected_inserts, new_insert_count);
-    ASSERT_EQ(compressed_failure_count_ + expected_failures, new_failure_count);
-    compressed_miss_count_ = new_miss_count;
-    compressed_hit_count_ = new_hit_count;
-    compressed_insert_count_ = new_insert_count;
-    compressed_failure_count_ = new_failure_count;
-  }
-};
-
-TEST_F(DBBlockCacheTest, TestWithoutCompressedBlockCache) {
-  ReadOptions read_options;
-  auto table_options = GetTableOptions();
-  auto options = GetOptions(table_options);
-  InitTable(options);
-
-  std::shared_ptr<Cache> cache = NewLRUCache(0, 0, false);
-  table_options.block_cache = cache;
-  options.table_factory.reset(new BlockBasedTableFactory(table_options));
-  Reopen(options);
-  RecordCacheCounters(options);
-
-  std::vector<std::unique_ptr<Iterator>> iterators(kNumBlocks - 1);
-  Iterator* iter = nullptr;
-
-  // Load blocks into cache.
-  for (size_t i = 0; i < kNumBlocks - 1; i++) {
-    iter = db_->NewIterator(read_options);
-    iter->Seek(ToString(i));
-    ASSERT_OK(iter->status());
-    CheckCacheCounters(options, 1, 0, 1, 0);
-    iterators[i].reset(iter);
-  }
-  size_t usage = cache->GetUsage();
-  ASSERT_LT(0, usage);
-  cache->SetCapacity(usage);
-  ASSERT_EQ(usage, cache->GetPinnedUsage());
-
-  // Test with strict capacity limit.
-  cache->SetStrictCapacityLimit(true);
-  iter = db_->NewIterator(read_options);
-  iter->Seek(ToString(kNumBlocks - 1));
-  ASSERT_TRUE(iter->status().IsIncomplete());
-  CheckCacheCounters(options, 1, 0, 0, 1);
-  delete iter;
-  iter = nullptr;
-
-  // Release interators and access cache again.
-  for (size_t i = 0; i < kNumBlocks - 1; i++) {
-    iterators[i].reset();
-    CheckCacheCounters(options, 0, 0, 0, 0);
-  }
-  ASSERT_EQ(0, cache->GetPinnedUsage());
-  for (size_t i = 0; i < kNumBlocks - 1; i++) {
-    iter = db_->NewIterator(read_options);
-    iter->Seek(ToString(i));
-    ASSERT_OK(iter->status());
-    CheckCacheCounters(options, 0, 1, 0, 0);
-    iterators[i].reset(iter);
-  }
-}
-
-#ifdef SNAPPY
-TEST_F(DBBlockCacheTest, TestWithCompressedBlockCache) {
-  ReadOptions read_options;
-  auto table_options = GetTableOptions();
-  auto options = GetOptions(table_options);
-  options.compression = CompressionType::kSnappyCompression;
-  InitTable(options);
-
-  std::shared_ptr<Cache> cache = NewLRUCache(0, 0, false);
-  std::shared_ptr<Cache> compressed_cache = NewLRUCache(1 << 25, 0, false);
-  table_options.block_cache = cache;
-  table_options.block_cache_compressed = compressed_cache;
-  options.table_factory.reset(new BlockBasedTableFactory(table_options));
-  Reopen(options);
-  RecordCacheCounters(options);
-
-  std::vector<std::unique_ptr<Iterator>> iterators(kNumBlocks - 1);
-  Iterator* iter = nullptr;
-
-  // Load blocks into cache.
-  for (size_t i = 0; i < kNumBlocks - 1; i++) {
-    iter = db_->NewIterator(read_options);
-    iter->Seek(ToString(i));
-    ASSERT_OK(iter->status());
-    CheckCacheCounters(options, 1, 0, 1, 0);
-    CheckCompressedCacheCounters(options, 1, 0, 1, 0);
-    iterators[i].reset(iter);
-  }
-  size_t usage = cache->GetUsage();
-  ASSERT_LT(0, usage);
-  ASSERT_EQ(usage, cache->GetPinnedUsage());
-  size_t compressed_usage = compressed_cache->GetUsage();
-  ASSERT_LT(0, compressed_usage);
-  // Compressed block cache cannot be pinned.
-  ASSERT_EQ(0, compressed_cache->GetPinnedUsage());
-
-  // Set strict capacity limit flag. Now block will only load into compressed
-  // block cache.
-  cache->SetCapacity(usage);
-  cache->SetStrictCapacityLimit(true);
-  ASSERT_EQ(usage, cache->GetPinnedUsage());
-  iter = db_->NewIterator(read_options);
-  iter->Seek(ToString(kNumBlocks - 1));
-  ASSERT_TRUE(iter->status().IsIncomplete());
-  CheckCacheCounters(options, 1, 0, 0, 1);
-  CheckCompressedCacheCounters(options, 1, 0, 1, 0);
-  delete iter;
-  iter = nullptr;
-
-  // Clear strict capacity limit flag. This time we shall hit compressed block
-  // cache.
-  cache->SetStrictCapacityLimit(false);
-  iter = db_->NewIterator(read_options);
-  iter->Seek(ToString(kNumBlocks - 1));
-  ASSERT_OK(iter->status());
-  CheckCacheCounters(options, 1, 0, 1, 0);
-  CheckCompressedCacheCounters(options, 0, 1, 0, 0);
-  delete iter;
-  iter = nullptr;
-}
-#endif  // SNAPPY
-
-#ifndef ROCKSDB_LITE
-
-// Make sure that when options.block_cache is set, after a new table is
-// created its index/filter blocks are added to block cache.
-TEST_F(DBBlockCacheTest, IndexAndFilterBlocksOfNewTableAddedToCache) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.statistics = rocksdb::CreateDBStatistics();
-  BlockBasedTableOptions table_options;
-  table_options.cache_index_and_filter_blocks = true;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(20));
-  options.table_factory.reset(new BlockBasedTableFactory(table_options));
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  ASSERT_OK(Put(1, "key", "val"));
-  // Create a new table.
-  ASSERT_OK(Flush(1));
-
-  // index/filter blocks added to block cache right after table creation.
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
-  ASSERT_EQ(2, /* only index/filter were added */
-            TestGetTickerCount(options, BLOCK_CACHE_ADD));
-  ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_DATA_MISS));
-  uint64_t int_num;
-  ASSERT_TRUE(
-      dbfull()->GetIntProperty("rocksdb.estimate-table-readers-mem", &int_num));
-  ASSERT_EQ(int_num, 0U);
-
-  // Make sure filter block is in cache.
-  std::string value;
-  ReadOptions ropt;
-  db_->KeyMayExist(ReadOptions(), handles_[1], "key", &value);
-
-  // Miss count should remain the same.
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
-
-  db_->KeyMayExist(ReadOptions(), handles_[1], "key", &value);
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
-  ASSERT_EQ(2, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
-
-  // Make sure index block is in cache.
-  auto index_block_hit = TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT);
-  value = Get(1, "key");
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
-  ASSERT_EQ(index_block_hit + 1,
-            TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT));
-
-  value = Get(1, "key");
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
-  ASSERT_EQ(index_block_hit + 2,
-            TestGetTickerCount(options, BLOCK_CACHE_INDEX_HIT));
-}
-
-TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.statistics = rocksdb::CreateDBStatistics();
-  BlockBasedTableOptions table_options;
-  table_options.cache_index_and_filter_blocks = true;
-  // 200 bytes are enough to hold the first two blocks
-  std::shared_ptr<Cache> cache = NewLRUCache(200, 0, false);
-  table_options.block_cache = cache;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(20));
-  options.table_factory.reset(new BlockBasedTableFactory(table_options));
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  ASSERT_OK(Put(1, "key", "val"));
-  // Create a new table
-  ASSERT_OK(Flush(1));
-  size_t index_bytes_insert =
-      TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_INSERT);
-  size_t filter_bytes_insert =
-      TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_INSERT);
-  ASSERT_GT(index_bytes_insert, 0);
-  ASSERT_GT(filter_bytes_insert, 0);
-  ASSERT_EQ(cache->GetUsage(), index_bytes_insert + filter_bytes_insert);
-  // set the cache capacity to the current usage
-  cache->SetCapacity(index_bytes_insert + filter_bytes_insert);
-  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT), 0);
-  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT), 0);
-  ASSERT_OK(Put(1, "key2", "val"));
-  // Create a new table
-  ASSERT_OK(Flush(1));
-  // cache evicted old index and block entries
-  ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_INSERT),
-            index_bytes_insert);
-  ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_INSERT),
-            filter_bytes_insert);
-  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT),
-            index_bytes_insert);
-  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT),
-            filter_bytes_insert);
-}
-
-namespace {
-
-// A mock cache wraps LRUCache, and record how many entries have been
-// inserted for each priority.
-class MockCache : public LRUCache {
- public:
-  static uint32_t high_pri_insert_count;
-  static uint32_t low_pri_insert_count;
-
-  MockCache() : LRUCache(1 << 25, 0, false, 0.0) {}
-
-  virtual Status Insert(const Slice& key, void* value, size_t charge,
-                        void (*deleter)(const Slice& key, void* value),
-                        Handle** handle, Priority priority) override {
-    if (priority == Priority::LOW) {
-      low_pri_insert_count++;
-    } else {
-      high_pri_insert_count++;
-    }
-    return LRUCache::Insert(key, value, charge, deleter, handle, priority);
-  }
-};
-
-uint32_t MockCache::high_pri_insert_count = 0;
-uint32_t MockCache::low_pri_insert_count = 0;
-
-}  // anonymous namespace
-
-TEST_F(DBBlockCacheTest, IndexAndFilterBlocksCachePriority) {
-  for (auto priority : {Cache::Priority::LOW, Cache::Priority::HIGH}) {
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    options.statistics = rocksdb::CreateDBStatistics();
-    BlockBasedTableOptions table_options;
-    table_options.cache_index_and_filter_blocks = true;
-    table_options.block_cache.reset(new MockCache());
-    table_options.filter_policy.reset(NewBloomFilterPolicy(20));
-    table_options.cache_index_and_filter_blocks_with_high_priority =
-        priority == Cache::Priority::HIGH ? true : false;
-    options.table_factory.reset(new BlockBasedTableFactory(table_options));
-    DestroyAndReopen(options);
-
-    MockCache::high_pri_insert_count = 0;
-    MockCache::low_pri_insert_count = 0;
-
-    // Create a new table.
-    ASSERT_OK(Put("foo", "value"));
-    ASSERT_OK(Put("bar", "value"));
-    ASSERT_OK(Flush());
-    ASSERT_EQ(1, NumTableFilesAtLevel(0));
-
-    // index/filter blocks added to block cache right after table creation.
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
-    ASSERT_EQ(2, /* only index/filter were added */
-              TestGetTickerCount(options, BLOCK_CACHE_ADD));
-    ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_DATA_MISS));
-    if (priority == Cache::Priority::LOW) {
-      ASSERT_EQ(0, MockCache::high_pri_insert_count);
-      ASSERT_EQ(2, MockCache::low_pri_insert_count);
-    } else {
-      ASSERT_EQ(2, MockCache::high_pri_insert_count);
-      ASSERT_EQ(0, MockCache::low_pri_insert_count);
-    }
-
-    // Access data block.
-    ASSERT_EQ("value", Get("foo"));
-
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
-    ASSERT_EQ(3, /*adding data block*/
-              TestGetTickerCount(options, BLOCK_CACHE_ADD));
-    ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_DATA_MISS));
-
-    // Data block should be inserted with low priority.
-    if (priority == Cache::Priority::LOW) {
-      ASSERT_EQ(0, MockCache::high_pri_insert_count);
-      ASSERT_EQ(3, MockCache::low_pri_insert_count);
-    } else {
-      ASSERT_EQ(2, MockCache::high_pri_insert_count);
-      ASSERT_EQ(1, MockCache::low_pri_insert_count);
-    }
-  }
-}
-
-TEST_F(DBBlockCacheTest, ParanoidFileChecks) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.statistics = rocksdb::CreateDBStatistics();
-  options.level0_file_num_compaction_trigger = 2;
-  options.paranoid_file_checks = true;
-  BlockBasedTableOptions table_options;
-  table_options.cache_index_and_filter_blocks = false;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(20));
-  options.table_factory.reset(new BlockBasedTableFactory(table_options));
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  ASSERT_OK(Put(1, "1_key", "val"));
-  ASSERT_OK(Put(1, "9_key", "val"));
-  // Create a new table.
-  ASSERT_OK(Flush(1));
-  ASSERT_EQ(1, /* read and cache data block */
-            TestGetTickerCount(options, BLOCK_CACHE_ADD));
-
-  ASSERT_OK(Put(1, "1_key2", "val2"));
-  ASSERT_OK(Put(1, "9_key2", "val2"));
-  // Create a new SST file. This will further trigger a compaction
-  // and generate another file.
-  ASSERT_OK(Flush(1));
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(3, /* Totally 3 files created up to now */
-            TestGetTickerCount(options, BLOCK_CACHE_ADD));
-
-  // After disabling options.paranoid_file_checks. NO further block
-  // is added after generating a new file.
-  ASSERT_OK(
-      dbfull()->SetOptions(handles_[1], {{"paranoid_file_checks", "false"}}));
-
-  ASSERT_OK(Put(1, "1_key3", "val3"));
-  ASSERT_OK(Put(1, "9_key3", "val3"));
-  ASSERT_OK(Flush(1));
-  ASSERT_OK(Put(1, "1_key4", "val4"));
-  ASSERT_OK(Put(1, "9_key4", "val4"));
-  ASSERT_OK(Flush(1));
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(3, /* Totally 3 files created up to now */
-            TestGetTickerCount(options, BLOCK_CACHE_ADD));
-}
-
-TEST_F(DBBlockCacheTest, CompressedCache) {
-  if (!Snappy_Supported()) {
-    return;
-  }
-  int num_iter = 80;
-
-  // Run this test three iterations.
-  // Iteration 1: only a uncompressed block cache
-  // Iteration 2: only a compressed block cache
-  // Iteration 3: both block cache and compressed cache
-  // Iteration 4: both block cache and compressed cache, but DB is not
-  // compressed
-  for (int iter = 0; iter < 4; iter++) {
-    Options options = CurrentOptions();
-    options.write_buffer_size = 64 * 1024;  // small write buffer
-    options.statistics = rocksdb::CreateDBStatistics();
-
-    BlockBasedTableOptions table_options;
-    switch (iter) {
-      case 0:
-        // only uncompressed block cache
-        table_options.block_cache = NewLRUCache(8 * 1024);
-        table_options.block_cache_compressed = nullptr;
-        options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-        break;
-      case 1:
-        // no block cache, only compressed cache
-        table_options.no_block_cache = true;
-        table_options.block_cache = nullptr;
-        table_options.block_cache_compressed = NewLRUCache(8 * 1024);
-        options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-        break;
-      case 2:
-        // both compressed and uncompressed block cache
-        table_options.block_cache = NewLRUCache(1024);
-        table_options.block_cache_compressed = NewLRUCache(8 * 1024);
-        options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-        break;
-      case 3:
-        // both block cache and compressed cache, but DB is not compressed
-        // also, make block cache sizes bigger, to trigger block cache hits
-        table_options.block_cache = NewLRUCache(1024 * 1024);
-        table_options.block_cache_compressed = NewLRUCache(8 * 1024 * 1024);
-        options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-        options.compression = kNoCompression;
-        break;
-      default:
-        ASSERT_TRUE(false);
-    }
-    CreateAndReopenWithCF({"pikachu"}, options);
-    // default column family doesn't have block cache
-    Options no_block_cache_opts;
-    no_block_cache_opts.statistics = options.statistics;
-    no_block_cache_opts = CurrentOptions(no_block_cache_opts);
-    BlockBasedTableOptions table_options_no_bc;
-    table_options_no_bc.no_block_cache = true;
-    no_block_cache_opts.table_factory.reset(
-        NewBlockBasedTableFactory(table_options_no_bc));
-    ReopenWithColumnFamilies(
-        {"default", "pikachu"},
-        std::vector<Options>({no_block_cache_opts, options}));
-
-    Random rnd(301);
-
-    // Write 8MB (80 values, each 100K)
-    ASSERT_EQ(NumTableFilesAtLevel(0, 1), 0);
-    std::vector<std::string> values;
-    std::string str;
-    for (int i = 0; i < num_iter; i++) {
-      if (i % 4 == 0) {  // high compression ratio
-        str = RandomString(&rnd, 1000);
-      }
-      values.push_back(str);
-      ASSERT_OK(Put(1, Key(i), values[i]));
-    }
-
-    // flush all data from memtable so that reads are from block cache
-    ASSERT_OK(Flush(1));
-
-    for (int i = 0; i < num_iter; i++) {
-      ASSERT_EQ(Get(1, Key(i)), values[i]);
-    }
-
-    // check that we triggered the appropriate code paths in the cache
-    switch (iter) {
-      case 0:
-        // only uncompressed block cache
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_MISS), 0);
-        ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS), 0);
-        break;
-      case 1:
-        // no block cache, only compressed cache
-        ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_MISS), 0);
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS), 0);
-        break;
-      case 2:
-        // both compressed and uncompressed block cache
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_MISS), 0);
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS), 0);
-        break;
-      case 3:
-        // both compressed and uncompressed block cache
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_MISS), 0);
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_HIT), 0);
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS), 0);
-        // compressed doesn't have any hits since blocks are not compressed on
-        // storage
-        ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_HIT), 0);
-        break;
-      default:
-        ASSERT_TRUE(false);
-    }
-
-    options.create_if_missing = true;
-    DestroyAndReopen(options);
-  }
-}
-
-#endif  // ROCKSDB_LITE
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_compaction_filter_test.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -13,7 +13,6 @@
 namespace rocksdb {
 
 static int cfilter_count = 0;
-static int cfilter_skips = 0;
 
 // This is a static filter used for filtering
 // kvs during the compaction process.
@@ -66,30 +65,6 @@ class DeleteISFilter : public CompactionFilter {
   virtual const char* Name() const override { return "DeleteFilter"; }
 };
 
-// Skip x if floor(x/10) is even, use range skips. Requires that keys are
-// zero-padded to length 10.
-class SkipEvenFilter : public CompactionFilter {
- public:
-  virtual Decision FilterV2(int level, const Slice& key, ValueType value_type,
-                            const Slice& existing_value, std::string* new_value,
-                            std::string* skip_until) const override {
-    cfilter_count++;
-    int i = std::stoi(key.ToString());
-    if (i / 10 % 2 == 0) {
-      char key_str[100];
-      snprintf(key_str, sizeof(key), "%010d", i / 10 * 10 + 10);
-      *skip_until = key_str;
-      ++cfilter_skips;
-      return Decision::kRemoveAndSkipUntil;
-    }
-    return Decision::kKeep;
-  }
-
-  virtual bool IgnoreSnapshots() const override { return true; }
-
-  virtual const char* Name() const override { return "DeleteFilter"; }
-};
-
 class DelayFilter : public CompactionFilter {
  public:
   explicit DelayFilter(DBTestBase* d) : db_test(d) {}
@@ -199,20 +174,6 @@ class DeleteISFilterFactory : public CompactionFilterFactory {
   virtual const char* Name() const override { return "DeleteFilterFactory"; }
 };
 
-class SkipEvenFilterFactory : public CompactionFilterFactory {
- public:
-  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
-      const CompactionFilter::Context& context) override {
-    if (context.is_manual_compaction) {
-      return std::unique_ptr<CompactionFilter>(new SkipEvenFilter());
-    } else {
-      return std::unique_ptr<CompactionFilter>(nullptr);
-    }
-  }
-
-  virtual const char* Name() const override { return "SkipEvenFilterFactory"; }
-};
-
 class DelayFilterFactory : public CompactionFilterFactory {
  public:
   explicit DelayFilterFactory(DBTestBase* d) : db_test(d) {}
@@ -300,10 +261,8 @@ TEST_F(DBTestCompactionFilter, CompactionFilter) {
   int total = 0;
   Arena arena;
   {
-    InternalKeyComparator icmp(options.comparator);
-    RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
     ScopedArenaIterator iter(
-        dbfull()->NewInternalIterator(&arena, &range_del_agg, handles_[1]));
+        dbfull()->NewInternalIterator(&arena, handles_[1]));
     iter->SeekToFirst();
     ASSERT_OK(iter->status());
     while (iter->Valid()) {
@@ -390,10 +349,8 @@ TEST_F(DBTestCompactionFilter, CompactionFilter) {
   // level Lmax because this record is at the tip
   count = 0;
   {
-    InternalKeyComparator icmp(options.comparator);
-    RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
     ScopedArenaIterator iter(
-        dbfull()->NewInternalIterator(&arena, &range_del_agg, handles_[1]));
+        dbfull()->NewInternalIterator(&arena, handles_[1]));
     iter->SeekToFirst();
     ASSERT_OK(iter->status());
     while (iter->Valid()) {
@@ -411,10 +368,11 @@ TEST_F(DBTestCompactionFilter, CompactionFilter) {
 // entries are deleted. The compaction should create bunch of 'DeleteFile'
 // entries in VersionEdit, but none of the 'AddFile's.
 TEST_F(DBTestCompactionFilter, CompactionFilterDeletesAll) {
-  Options options = CurrentOptions();
+  Options options;
   options.compaction_filter_factory = std::make_shared<DeleteFilterFactory>();
   options.disable_auto_compactions = true;
   options.create_if_missing = true;
+  options = CurrentOptions(options);
   DestroyAndReopen(options);
 
   // put some data
@@ -442,10 +400,11 @@ TEST_F(DBTestCompactionFilter, CompactionFilterDeletesAll) {
 
 TEST_F(DBTestCompactionFilter, CompactionFilterWithValueChange) {
   do {
-    Options options = CurrentOptions();
+    Options options;
     options.num_levels = 3;
     options.compaction_filter_factory =
       std::make_shared<ChangeFilterFactory>();
+    options = CurrentOptions(options);
     CreateAndReopenWithCF({"pikachu"}, options);
 
     // Write 100K+1 keys, these are written to a few files
@@ -508,7 +467,8 @@ TEST_F(DBTestCompactionFilter, CompactionFilterWithMergeOperator) {
   PutFixed64(&three, 3);
   PutFixed64(&four, 4);
 
-  Options options = CurrentOptions();
+  Options options;
+  options = CurrentOptions(options);
   options.create_if_missing = true;
   options.merge_operator = MergeOperators::CreateUInt64AddOperator();
   options.num_levels = 3;
@@ -609,10 +569,7 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextManual) {
     int count = 0;
     int total = 0;
     Arena arena;
-    InternalKeyComparator icmp(options.comparator);
-    RangeDelAggregator range_del_agg(icmp, {} /* snapshots */);
-    ScopedArenaIterator iter(
-        dbfull()->NewInternalIterator(&arena, &range_del_agg));
+    ScopedArenaIterator iter(dbfull()->NewInternalIterator(&arena));
     iter->SeekToFirst();
     ASSERT_OK(iter->status());
     while (iter->Valid()) {
@@ -664,10 +621,11 @@ TEST_F(DBTestCompactionFilter, CompactionFilterContextCfId) {
 // Compaction filters should only be applied to records that are newer than the
 // latest snapshot. This test inserts records and applies a delete filter.
 TEST_F(DBTestCompactionFilter, CompactionFilterSnapshot) {
-  Options options = CurrentOptions();
+  Options options;
   options.compaction_filter_factory = std::make_shared<DeleteFilterFactory>();
   options.disable_auto_compactions = true;
   options.create_if_missing = true;
+  options = CurrentOptions(options);
   DestroyAndReopen(options);
 
   // Put some data.
@@ -701,10 +659,11 @@ TEST_F(DBTestCompactionFilter, CompactionFilterSnapshot) {
 // records newer than the snapshot will also be processed
 TEST_F(DBTestCompactionFilter, CompactionFilterIgnoreSnapshot) {
   std::string five = ToString(5);
-  Options options = CurrentOptions();
+  Options options;
   options.compaction_filter_factory = std::make_shared<DeleteISFilterFactory>();
   options.disable_auto_compactions = true;
   options.create_if_missing = true;
+  options = CurrentOptions(options);
   DestroyAndReopen(options);
 
   // Put some data.
@@ -758,47 +717,6 @@ TEST_F(DBTestCompactionFilter, CompactionFilterIgnoreSnapshot) {
 }
 #endif  // ROCKSDB_LITE
 
-TEST_F(DBTestCompactionFilter, SkipUntil) {
-  Options options = CurrentOptions();
-  options.compaction_filter_factory = std::make_shared<SkipEvenFilterFactory>();
-  options.disable_auto_compactions = true;
-  options.create_if_missing = true;
-  DestroyAndReopen(options);
-
-  // Write 100K keys, these are written to a few files in L0.
-  for (int table = 0; table < 4; ++table) {
-    // Key ranges in tables are [0, 38], [106, 149], [212, 260], [318, 371].
-    for (int i = table * 6; i < 39 + table * 11; ++i) {
-      char key[100];
-      snprintf(key, sizeof(key), "%010d", table * 100 + i);
-      Put(key, std::to_string(table * 1000 + i));
-    }
-    Flush();
-  }
-
-  cfilter_skips = 0;
-  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  // Numberof skips in tables: 2, 3, 3, 3.
-  ASSERT_EQ(11, cfilter_skips);
-
-  for (int table = 0; table < 4; ++table) {
-    for (int i = table * 6; i < 39 + table * 11; ++i) {
-      int k = table * 100 + i;
-      char key[100];
-      snprintf(key, sizeof(key), "%010d", table * 100 + i);
-      auto expected = std::to_string(table * 1000 + i);
-      std::string val;
-      Status s = db_->Get(ReadOptions(), key, &val);
-      if (k / 10 % 2 == 0) {
-        ASSERT_TRUE(s.IsNotFound());
-      } else {
-        ASSERT_OK(s);
-        ASSERT_EQ(expected, val);
-      }
-    }
-  }
-}
-
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {

db/db_compaction_test.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -9,7 +9,6 @@
 
 #include "db/db_test_util.h"
 #include "port/stack_trace.h"
-#include "port/port.h"
 #include "rocksdb/experimental.h"
 #include "rocksdb/utilities/convenience.h"
 #include "util/sync_point.h"
@@ -41,6 +40,34 @@ class DBCompactionTestWithParam
 };
 
 namespace {
+class OnFileDeletionListener : public EventListener {
+ public:
+  OnFileDeletionListener() :
+      matched_count_(0),
+      expected_file_name_("") {}
+
+  void SetExpectedFileName(
+      const std::string file_name) {
+    expected_file_name_ = file_name;
+  }
+
+  void VerifyMatchedCount(size_t expected_value) {
+    ASSERT_EQ(matched_count_, expected_value);
+  }
+
+  void OnTableFileDeleted(
+      const TableFileDeletionInfo& info) override {
+    if (expected_file_name_ != "") {
+      ASSERT_EQ(expected_file_name_, info.file_path);
+      expected_file_name_ = "";
+      matched_count_++;
+    }
+  }
+
+ private:
+  size_t matched_count_;
+  std::string expected_file_name_;
+};
 
 class FlushedFileCollector : public EventListener {
  public:
@@ -71,7 +98,8 @@ class FlushedFileCollector : public EventListener {
 static const int kCDTValueSize = 1000;
 static const int kCDTKeysPerBuffer = 4;
 static const int kCDTNumLevels = 8;
-Options DeletionTriggerOptions(Options options) {
+Options DeletionTriggerOptions() {
+  Options options;
   options.compression = kNoCompression;
   options.write_buffer_size = kCDTKeysPerBuffer * (kCDTValueSize + 24);
   options.min_write_buffer_number_to_merge = 1;
@@ -174,7 +202,7 @@ const SstFileMetaData* PickFileRandomly(
 TEST_P(DBCompactionTestWithParam, CompactionDeletionTrigger) {
   for (int tid = 0; tid < 3; ++tid) {
     uint64_t db_size[2];
-    Options options = DeletionTriggerOptions(CurrentOptions());
+    Options options = CurrentOptions(DeletionTriggerOptions());
     options.max_subcompactions = max_subcompactions_;
 
     if (tid == 1) {
@@ -213,11 +241,12 @@ TEST_P(DBCompactionTestWithParam, CompactionDeletionTrigger) {
 }
 
 TEST_F(DBCompactionTest, SkipStatsUpdateTest) {
-  // This test verify UpdateAccumulatedStats is not on
-  // if options.skip_stats_update_on_db_open = true
+  // This test verify UpdateAccumulatedStats is not on by observing
+  // the compaction behavior when there are many of deletion entries.
   // The test will need to be updated if the internal behavior changes.
 
-  Options options = DeletionTriggerOptions(CurrentOptions());
+  Options options = DeletionTriggerOptions();
+  options = CurrentOptions(options);
   options.env = env_;
   DestroyAndReopen(options);
   Random rnd(301);
@@ -231,6 +260,10 @@ TEST_F(DBCompactionTest, SkipStatsUpdateTest) {
   dbfull()->TEST_WaitForFlushMemTable();
   dbfull()->TEST_WaitForCompact();
 
+  for (int k = 0; k < kTestSize; ++k) {
+    ASSERT_OK(Delete(Key(k)));
+  }
+
   // Reopen the DB with stats-update disabled
   options.skip_stats_update_on_db_open = true;
   env_->random_file_open_counter_.store(0);
@@ -255,7 +288,8 @@ TEST_F(DBCompactionTest, SkipStatsUpdateTest) {
 }
 
 TEST_F(DBCompactionTest, TestTableReaderForCompaction) {
-  Options options = CurrentOptions();
+  Options options;
+  options = CurrentOptions(options);
   options.env = env_;
   options.new_table_reader_for_compaction_inputs = true;
   options.max_open_files = 100;
@@ -306,8 +340,7 @@ TEST_F(DBCompactionTest, TestTableReaderForCompaction) {
   dbfull()->TEST_WaitForCompact();
   // Preloading iterator issues one table cache lookup and creates
   // a new table reader. One file is created for flush and one for compaction.
-  // Compaction inputs make no table cache look-up for data/range deletion
-  // iterators
+  // Compaction inputs make no table cache look-up.
   ASSERT_EQ(num_table_cache_lookup, 2);
   // Create new iterator for:
   // (1) 1 for verifying flush results
@@ -328,8 +361,7 @@ TEST_F(DBCompactionTest, TestTableReaderForCompaction) {
   cro.target_level = 2;
   cro.bottommost_level_compaction = BottommostLevelCompaction::kForce;
   db_->CompactRange(cro, nullptr, nullptr);
-  // Only verifying compaction outputs issues one table cache lookup
-  // for both data block and range deletion block).
+  // Only verifying compaction outputs issues one table cache lookup.
   ASSERT_EQ(num_table_cache_lookup, 1);
   // One for compaction input, one for verifying compaction results.
   ASSERT_EQ(num_new_table_reader, 2);
@@ -346,7 +378,7 @@ TEST_F(DBCompactionTest, TestTableReaderForCompaction) {
 TEST_P(DBCompactionTestWithParam, CompactionDeletionTriggerReopen) {
   for (int tid = 0; tid < 2; ++tid) {
     uint64_t db_size[3];
-    Options options = DeletionTriggerOptions(CurrentOptions());
+    Options options = CurrentOptions(DeletionTriggerOptions());
     options.max_subcompactions = max_subcompactions_;
 
     if (tid == 1) {
@@ -403,7 +435,7 @@ TEST_P(DBCompactionTestWithParam, CompactionDeletionTriggerReopen) {
 TEST_F(DBCompactionTest, DisableStatsUpdateReopen) {
   uint64_t db_size[3];
   for (int test = 0; test < 2; ++test) {
-    Options options = DeletionTriggerOptions(CurrentOptions());
+    Options options = CurrentOptions(DeletionTriggerOptions());
     options.skip_stats_update_on_db_open = (test == 0);
 
     env_->random_read_counter_.Reset();
@@ -461,13 +493,14 @@ TEST_F(DBCompactionTest, DisableStatsUpdateReopen) {
 TEST_P(DBCompactionTestWithParam, CompactionTrigger) {
   const int kNumKeysPerFile = 100;
 
-  Options options = CurrentOptions();
+  Options options;
   options.write_buffer_size = 110 << 10;  // 110KB
   options.arena_block_size = 4 << 10;
   options.num_levels = 3;
   options.level0_file_num_compaction_trigger = 3;
   options.max_subcompactions = max_subcompactions_;
   options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
+  options = CurrentOptions(options);
   CreateAndReopenWithCF({"pikachu"}, options);
 
   Random rnd(301);
@@ -500,107 +533,11 @@ TEST_P(DBCompactionTestWithParam, CompactionTrigger) {
   ASSERT_EQ(NumTableFilesAtLevel(1, 1), 1);
 }
 
-TEST_F(DBCompactionTest, BGCompactionsAllowed) {
-  // Create several column families. Make compaction triggers in all of them
-  // and see number of compactions scheduled to be less than allowed.
-  const int kNumKeysPerFile = 100;
-
-  Options options = CurrentOptions();
-  options.write_buffer_size = 110 << 10;  // 110KB
-  options.arena_block_size = 4 << 10;
-  options.num_levels = 3;
-  // Should speed up compaction when there are 4 files.
-  options.level0_file_num_compaction_trigger = 2;
-  options.level0_slowdown_writes_trigger = 20;
-  options.soft_pending_compaction_bytes_limit = 1 << 30;  // Infinitely large
-  options.base_background_compactions = 1;
-  options.max_background_compactions = 3;
-  options.memtable_factory.reset(new SpecialSkipListFactory(kNumKeysPerFile));
-
-  // Block all threads in thread pool.
-  const size_t kTotalTasks = 4;
-  env_->SetBackgroundThreads(4, Env::LOW);
-  test::SleepingBackgroundTask sleeping_tasks[kTotalTasks];
-  for (size_t i = 0; i < kTotalTasks; i++) {
-    env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask,
-                   &sleeping_tasks[i], Env::Priority::LOW);
-    sleeping_tasks[i].WaitUntilSleeping();
-  }
-
-  CreateAndReopenWithCF({"one", "two", "three"}, options);
-
-  Random rnd(301);
-  for (int cf = 0; cf < 4; cf++) {
-    for (int num = 0; num < options.level0_file_num_compaction_trigger; num++) {
-      for (int i = 0; i < kNumKeysPerFile; i++) {
-        ASSERT_OK(Put(cf, Key(i), ""));
-      }
-      // put extra key to trigger flush
-      ASSERT_OK(Put(cf, "", ""));
-      dbfull()->TEST_WaitForFlushMemTable(handles_[cf]);
-      ASSERT_EQ(NumTableFilesAtLevel(0, cf), num + 1);
-    }
-  }
-
-  // Now all column families qualify compaction but only one should be
-  // scheduled, because no column family hits speed up condition.
-  ASSERT_EQ(1, env_->GetThreadPoolQueueLen(Env::Priority::LOW));
-
-  // Create two more files for one column family, which triggers speed up
-  // condition, three compactions will be scheduled.
-  for (int num = 0; num < options.level0_file_num_compaction_trigger; num++) {
-    for (int i = 0; i < kNumKeysPerFile; i++) {
-      ASSERT_OK(Put(2, Key(i), ""));
-    }
-    // put extra key to trigger flush
-    ASSERT_OK(Put(2, "", ""));
-    dbfull()->TEST_WaitForFlushMemTable(handles_[2]);
-    ASSERT_EQ(options.level0_file_num_compaction_trigger + num + 1,
-              NumTableFilesAtLevel(0, 2));
-  }
-  ASSERT_EQ(3, env_->GetThreadPoolQueueLen(Env::Priority::LOW));
-
-  // Unblock all threads to unblock all compactions.
-  for (size_t i = 0; i < kTotalTasks; i++) {
-    sleeping_tasks[i].WakeUp();
-    sleeping_tasks[i].WaitUntilDone();
-  }
-  dbfull()->TEST_WaitForCompact();
-
-  // Verify number of compactions allowed will come back to 1.
-
-  for (size_t i = 0; i < kTotalTasks; i++) {
-    sleeping_tasks[i].Reset();
-    env_->Schedule(&test::SleepingBackgroundTask::DoSleepTask,
-                   &sleeping_tasks[i], Env::Priority::LOW);
-    sleeping_tasks[i].WaitUntilSleeping();
-  }
-  for (int cf = 0; cf < 4; cf++) {
-    for (int num = 0; num < options.level0_file_num_compaction_trigger; num++) {
-      for (int i = 0; i < kNumKeysPerFile; i++) {
-        ASSERT_OK(Put(cf, Key(i), ""));
-      }
-      // put extra key to trigger flush
-      ASSERT_OK(Put(cf, "", ""));
-      dbfull()->TEST_WaitForFlushMemTable(handles_[cf]);
-      ASSERT_EQ(NumTableFilesAtLevel(0, cf), num + 1);
-    }
-  }
-
-  // Now all column families qualify compaction but only one should be
-  // scheduled, because no column family hits speed up condition.
-  ASSERT_EQ(1, env_->GetThreadPoolQueueLen(Env::Priority::LOW));
-
-  for (size_t i = 0; i < kTotalTasks; i++) {
-    sleeping_tasks[i].WakeUp();
-    sleeping_tasks[i].WaitUntilDone();
-  }
-}
-
 TEST_P(DBCompactionTestWithParam, CompactionsGenerateMultipleFiles) {
-  Options options = CurrentOptions();
+  Options options;
   options.write_buffer_size = 100000000;        // Large write buffer
   options.max_subcompactions = max_subcompactions_;
+  options = CurrentOptions(options);
   CreateAndReopenWithCF({"pikachu"}, options);
 
   Random rnd(301);
@@ -627,8 +564,9 @@ TEST_P(DBCompactionTestWithParam, CompactionsGenerateMultipleFiles) {
 
 TEST_F(DBCompactionTest, MinorCompactionsHappen) {
   do {
-    Options options = CurrentOptions();
+    Options options;
     options.write_buffer_size = 10000;
+    options = CurrentOptions(options);
     CreateAndReopenWithCF({"pikachu"}, options);
 
     const int N = 500;
@@ -652,74 +590,8 @@ TEST_F(DBCompactionTest, MinorCompactionsHappen) {
   } while (ChangeCompactOptions());
 }
 
-TEST_F(DBCompactionTest, UserKeyCrossFile1) {
-  Options options = CurrentOptions();
-  options.compaction_style = kCompactionStyleLevel;
-  options.level0_file_num_compaction_trigger = 3;
-
-  DestroyAndReopen(options);
-
-  // create first file and flush to l0
-  Put("4", "A");
-  Put("3", "A");
-  Flush();
-  dbfull()->TEST_WaitForFlushMemTable();
-
-  Put("2", "A");
-  Delete("3");
-  Flush();
-  dbfull()->TEST_WaitForFlushMemTable();
-  ASSERT_EQ("NOT_FOUND", Get("3"));
-
-  // move both files down to l1
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  ASSERT_EQ("NOT_FOUND", Get("3"));
-
-  for (int i = 0; i < 3; i++) {
-    Put("2", "B");
-    Flush();
-    dbfull()->TEST_WaitForFlushMemTable();
-  }
-  dbfull()->TEST_WaitForCompact();
-
-  ASSERT_EQ("NOT_FOUND", Get("3"));
-}
-
-TEST_F(DBCompactionTest, UserKeyCrossFile2) {
-  Options options = CurrentOptions();
-  options.compaction_style = kCompactionStyleLevel;
-  options.level0_file_num_compaction_trigger = 3;
-
-  DestroyAndReopen(options);
-
-  // create first file and flush to l0
-  Put("4", "A");
-  Put("3", "A");
-  Flush();
-  dbfull()->TEST_WaitForFlushMemTable();
-
-  Put("2", "A");
-  SingleDelete("3");
-  Flush();
-  dbfull()->TEST_WaitForFlushMemTable();
-  ASSERT_EQ("NOT_FOUND", Get("3"));
-
-  // move both files down to l1
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  ASSERT_EQ("NOT_FOUND", Get("3"));
-
-  for (int i = 0; i < 3; i++) {
-    Put("2", "B");
-    Flush();
-    dbfull()->TEST_WaitForFlushMemTable();
-  }
-  dbfull()->TEST_WaitForCompact();
-
-  ASSERT_EQ("NOT_FOUND", Get("3"));
-}
-
 TEST_F(DBCompactionTest, ZeroSeqIdCompaction) {
-  Options options = CurrentOptions();
+  Options options;
   options.compaction_style = kCompactionStyleLevel;
   options.level0_file_num_compaction_trigger = 3;
 
@@ -733,6 +605,7 @@ TEST_F(DBCompactionTest, ZeroSeqIdCompaction) {
   const size_t key_len =
     static_cast<size_t>(compact_opt.output_file_size_limit) / 5;
 
+  options = CurrentOptions(options);
   DestroyAndReopen(options);
 
   std::vector<const Snapshot*> snaps;
@@ -776,8 +649,10 @@ TEST_F(DBCompactionTest, ZeroSeqIdCompaction) {
 // if the database is shutdown during the memtable compaction.
 TEST_F(DBCompactionTest, RecoverDuringMemtableCompaction) {
   do {
-    Options options = CurrentOptions();
+    Options options;
     options.env = env_;
+    options.write_buffer_size = 1000000;
+    options = CurrentOptions(options);
     CreateAndReopenWithCF({"pikachu"}, options);
 
     // Trigger a long memtable compaction and reopen the database during it
@@ -801,9 +676,10 @@ TEST_P(DBCompactionTestWithParam, TrivialMoveOneFile) {
       [&](void* arg) { trivial_move++; });
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
-  Options options = CurrentOptions();
+  Options options;
   options.write_buffer_size = 100000000;
   options.max_subcompactions = max_subcompactions_;
+  options = CurrentOptions(options);
   DestroyAndReopen(options);
 
   int32_t num_keys = 80;
@@ -1018,21 +894,17 @@ TEST_P(DBCompactionTestWithParam, ManualCompactionPartial) {
       "DBImpl::BackgroundCompaction:NonTrivial",
       [&](void* arg) { non_trivial_move++; });
   bool first = true;
-  // Purpose of dependencies:
-  // 4 -> 1: ensure the order of two non-trivial compactions
-  // 5 -> 2 and 5 -> 3: ensure we do a check before two non-trivial compactions
-  // are installed
+  bool second = true;
   rocksdb::SyncPoint::GetInstance()->LoadDependency(
       {{"DBCompaction::ManualPartial:4", "DBCompaction::ManualPartial:1"},
-       {"DBCompaction::ManualPartial:5", "DBCompaction::ManualPartial:2"},
-       {"DBCompaction::ManualPartial:5", "DBCompaction::ManualPartial:3"}});
+       {"DBCompaction::ManualPartial:2", "DBCompaction::ManualPartial:3"}});
   rocksdb::SyncPoint::GetInstance()->SetCallBack(
       "DBImpl::BackgroundCompaction:NonTrivial:AfterRun", [&](void* arg) {
         if (first) {
-          first = false;
           TEST_SYNC_POINT("DBCompaction::ManualPartial:4");
+          first = false;
           TEST_SYNC_POINT("DBCompaction::ManualPartial:3");
-        } else {  // second non-trivial compaction
+        } else if (second) {
           TEST_SYNC_POINT("DBCompaction::ManualPartial:2");
         }
       });
@@ -1102,14 +974,13 @@ TEST_P(DBCompactionTestWithParam, ManualCompactionPartial) {
   ASSERT_EQ(trivial_move, 6);
   ASSERT_EQ(non_trivial_move, 0);
 
-  rocksdb::port::Thread threads([&] {
+  std::thread threads([&] {
     compact_options.change_level = false;
     compact_options.exclusive_manual_compaction = false;
     std::string begin_string = Key(0);
     std::string end_string = Key(199);
     Slice begin(begin_string);
     Slice end(end_string);
-    // First non-trivial compaction is triggered
     ASSERT_OK(db_->CompactRange(compact_options, &begin, &end));
   });
 
@@ -1133,17 +1004,13 @@ TEST_P(DBCompactionTestWithParam, ManualCompactionPartial) {
     values[i] = RandomString(&rnd, value_size);
     ASSERT_OK(Put(Key(i), values[i]));
   }
-  // Second non-trivial compaction is triggered
   ASSERT_OK(Flush());
 
-  // Before two non-trivial compactions are installed, there are 3 files in L0
+  // 3 files in L0
   ASSERT_EQ("3,0,0,0,0,1,2", FilesPerLevel(0));
-  TEST_SYNC_POINT("DBCompaction::ManualPartial:5");
-
+  // 1 file in L6, 1 file in L1
   dbfull()->TEST_WaitForFlushMemTable();
   dbfull()->TEST_WaitForCompact();
-  // After two non-trivial compactions are installed, there is 1 file in L6, and
-  // 1 file in L1
   ASSERT_EQ("0,1,0,0,0,0,1", FilesPerLevel(0));
   threads.join();
 
@@ -1234,7 +1101,7 @@ TEST_F(DBCompactionTest, ManualPartialFill) {
   ASSERT_EQ(trivial_move, 2);
   ASSERT_EQ(non_trivial_move, 0);
 
-  rocksdb::port::Thread threads([&] {
+  std::thread threads([&] {
     compact_options.change_level = false;
     compact_options.exclusive_manual_compaction = false;
     std::string begin_string = Key(0);
@@ -1261,8 +1128,7 @@ TEST_F(DBCompactionTest, ManualPartialFill) {
   uint64_t target_size = 4 * options.max_bytes_for_level_base;
   for (int32_t i = 1; i < options.num_levels; i++) {
     ASSERT_LE(SizeAtLevel(i), target_size);
-    target_size = static_cast<uint64_t>(target_size *
-                                        options.max_bytes_for_level_multiplier);
+    target_size *= options.max_bytes_for_level_multiplier;
   }
 
   TEST_SYNC_POINT("DBCompaction::PartialFill:2");
@@ -1339,8 +1205,7 @@ TEST_F(DBCompactionTest, DeleteFileRange) {
   uint64_t target_size = 4 * options.max_bytes_for_level_base;
   for (int32_t i = 1; i < options.num_levels; i++) {
     ASSERT_LE(SizeAtLevel(i), target_size);
-    target_size = static_cast<uint64_t>(target_size *
-                                        options.max_bytes_for_level_multiplier);
+    target_size *= options.max_bytes_for_level_multiplier;
   }
 
   size_t old_num_files = CountFiles();
@@ -1406,9 +1271,10 @@ TEST_P(DBCompactionTestWithParam, TrivialMoveToLastLevelWithFiles) {
       [&](void* arg) { non_trivial_move++; });
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
-  Options options = CurrentOptions();
+  Options options;
   options.write_buffer_size = 100000000;
   options.max_subcompactions = max_subcompactions_;
+  options = CurrentOptions(options);
   DestroyAndReopen(options);
 
   int32_t value_size = 10 * 1024;  // 10 KB
@@ -1697,7 +1563,7 @@ TEST_P(DBCompactionTestWithParam, ConvertCompactionStyle) {
   int max_key_universal_insert = 600;
 
   // Stage 1: generate a db with level compaction
-  Options options = CurrentOptions();
+  Options options;
   options.write_buffer_size = 110 << 10;  // 110KB
   options.arena_block_size = 4 << 10;
   options.num_levels = 4;
@@ -1707,6 +1573,7 @@ TEST_P(DBCompactionTestWithParam, ConvertCompactionStyle) {
   options.target_file_size_base = 200 << 10;  // 200KB
   options.target_file_size_multiplier = 1;
   options.max_subcompactions = max_subcompactions_;
+  options = CurrentOptions(options);
   CreateAndReopenWithCF({"pikachu"}, options);
 
   for (int i = 0; i <= max_key_level_insert; i++) {
@@ -2031,7 +1898,7 @@ TEST_P(DBCompactionTestWithParam, DISABLED_CompactFilesOnLevelCompaction) {
     std::set<std::string> overlapping_file_names;
     std::vector<std::string> compaction_input_file_names;
     for (int f = 0; f < file_picked; ++f) {
-      int level = 0;
+      int level;
       auto file_meta = PickFileRandomly(cf_meta, &rnd, &level);
       compaction_input_file_names.push_back(file_meta->name);
       GetOverlappingFileNumbersForLevelCompaction(
@@ -2331,25 +2198,6 @@ TEST_P(DBCompactionTestWithParam, CompressLevelCompaction) {
   Destroy(options);
 }
 
-TEST_F(DBCompactionTest, SanitizeCompactionOptionsTest) {
-  Options options = CurrentOptions();
-  options.max_background_compactions = 5;
-  options.soft_pending_compaction_bytes_limit = 0;
-  options.hard_pending_compaction_bytes_limit = 100;
-  options.create_if_missing = true;
-  DestroyAndReopen(options);
-  ASSERT_EQ(5, db_->GetOptions().base_background_compactions);
-  ASSERT_EQ(100, db_->GetOptions().soft_pending_compaction_bytes_limit);
-
-  options.base_background_compactions = 4;
-  options.max_background_compactions = 3;
-  options.soft_pending_compaction_bytes_limit = 200;
-  options.hard_pending_compaction_bytes_limit = 150;
-  DestroyAndReopen(options);
-  ASSERT_EQ(3, db_->GetOptions().base_background_compactions);
-  ASSERT_EQ(150, db_->GetOptions().soft_pending_compaction_bytes_limit);
-}
-
 // This tests for a bug that could cause two level0 compactions running
 // concurrently
 // TODO(aekmekji): Make sure that the reason this fails when run with
@@ -2421,9 +2269,10 @@ TEST_P(DBCompactionTestWithParam, ForceBottommostLevelCompaction) {
       [&](void* arg) { non_trivial_move++; });
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
 
-  Options options = CurrentOptions();
+  Options options;
   options.write_buffer_size = 100000000;
   options.max_subcompactions = max_subcompactions_;
+  options = CurrentOptions(options);
   DestroyAndReopen(options);
 
   int32_t value_size = 10 * 1024;  // 10 KB
@@ -2513,14 +2362,14 @@ class CompactionPriTest : public DBTestBase,
 };
 
 TEST_P(CompactionPriTest, Test) {
-  Options options = CurrentOptions();
+  Options options;
   options.write_buffer_size = 16 * 1024;
   options.compaction_pri = static_cast<CompactionPri>(compaction_pri_);
   options.hard_pending_compaction_bytes_limit = 256 * 1024;
   options.max_bytes_for_level_base = 64 * 1024;
   options.max_bytes_for_level_multiplier = 4;
   options.compression = kNoCompression;
-
+  options = CurrentOptions(options);
   DestroyAndReopen(options);
 
   Random rnd(301);
@@ -2541,12 +2390,8 @@ TEST_P(CompactionPriTest, Test) {
   }
 }
 
-INSTANTIATE_TEST_CASE_P(
-    CompactionPriTest, CompactionPriTest,
-    ::testing::Values(CompactionPri::kByCompensatedSize,
-                      CompactionPri::kOldestLargestSeqFirst,
-                      CompactionPri::kOldestSmallestSeqFirst,
-                      CompactionPri::kMinOverlappingRatio));
+INSTANTIATE_TEST_CASE_P(CompactionPriTest, CompactionPriTest,
+                        ::testing::Values(0, 1, 2));
 
 #endif // !defined(ROCKSDB_LITE)
 }  // namespace rocksdb

db/db_dynamic_level_test.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -13,7 +13,6 @@
 #if !defined(ROCKSDB_LITE)
 
 #include "db/db_test_util.h"
-#include "port/port.h"
 #include "port/stack_trace.h"
 
 namespace rocksdb {
@@ -126,19 +125,19 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
 
   Options options = CurrentOptions();
   options.create_if_missing = true;
-  options.db_write_buffer_size = 204800;
-  options.write_buffer_size = 20480;
+  options.db_write_buffer_size = 2048;
+  options.write_buffer_size = 2048;
   options.max_write_buffer_number = 2;
   options.level0_file_num_compaction_trigger = 2;
   options.level0_slowdown_writes_trigger = 9999;
   options.level0_stop_writes_trigger = 9999;
-  options.target_file_size_base = 9102;
+  options.target_file_size_base = 2048;
   options.level_compaction_dynamic_level_bytes = true;
-  options.max_bytes_for_level_base = 40960;
+  options.max_bytes_for_level_base = 10240;
   options.max_bytes_for_level_multiplier = 4;
   options.max_background_compactions = 2;
   options.num_levels = 5;
-  options.max_compaction_bytes = 0;  // Force not expanding in compactions
+  options.expanded_compaction_factor = 0;  // Force not expanding in compactions
   BlockBasedTableOptions table_options;
   table_options.block_size = 1024;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
@@ -155,10 +154,10 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
   ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
   ASSERT_EQ(4U, int_prop);
 
-  // Put about 28K to L0
+  // Put about 7K to L0
   for (int i = 0; i < 70; i++) {
     ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 380)));
+                  RandomString(&rnd, 80)));
   }
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "false"},
@@ -168,14 +167,14 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
   ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
   ASSERT_EQ(4U, int_prop);
 
-  // Insert extra about 28K to L0. After they are compacted to L4, base level
+  // Insert extra about 3.5K to L0. After they are compacted to L4, base level
   // should be changed to L3.
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "true"},
   }));
   for (int i = 0; i < 70; i++) {
     ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 380)));
+                  RandomString(&rnd, 80)));
   }
 
   ASSERT_OK(dbfull()->SetOptions({
@@ -200,10 +199,10 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "true"},
   }));
-  // Write about 40K more
+  // Write about 10K more
   for (int i = 0; i < 100; i++) {
     ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 380)));
+                  RandomString(&rnd, 80)));
   }
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "false"},
@@ -219,16 +218,15 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
 
   // Trigger a condition that the compaction changes base level and L0->Lbase
   // happens at the same time.
-  // We try to make last levels' targets to be 40K, 160K, 640K, add triggers
+  // We try to make last levels' targets to be 10K, 40K, 160K, add triggers
   // another compaction from 40K->160K.
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "true"},
   }));
-  // Write about 650K more.
-  // Each file is about 11KB, with 9KB of data.
-  for (int i = 0; i < 1300; i++) {
+  // Write about 150K more
+  for (int i = 0; i < 1350; i++) {
     ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 380)));
+                  RandomString(&rnd, 80)));
   }
   ASSERT_OK(dbfull()->SetOptions({
       {"disable_auto_compactions", "false"},
@@ -238,40 +236,30 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
   ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
   ASSERT_EQ(2U, int_prop);
 
-  // A manual compaction will trigger the base level to become L2
   // Keep Writing data until base level changed 2->1. There will be L0->L2
   // compaction going on at the same time.
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency({
-      {"CompactionJob::Run():Start", "DynamicLevelMaxBytesBase2:0"},
-      {"DynamicLevelMaxBytesBase2:1", "CompactionJob::Run():End"},
-      {"DynamicLevelMaxBytesBase2:compact_range_finish",
-       "FlushJob::WriteLevel0Table"},
-  });
   rocksdb::SyncPoint::GetInstance()->EnableProcessing();
+  for (int attempt = 0; attempt <= 20; attempt++) {
+    // Write about 5K more data with two flushes. It should be flush to level 2
+    // but when it is applied, base level is already 1.
+    for (int i = 0; i < 50; i++) {
+      ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
+                    RandomString(&rnd, 80)));
+    }
+    Flush();
 
-  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");
-  });
-
-  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:0");
-  for (int i = 0; i < 2; i++) {
-    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 380)));
+    ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
+    if (int_prop == 2U) {
+      env_->SleepForMicroseconds(50000);
+    } else {
+      break;
+    }
   }
-  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:1");
-
-  Flush();
-
-  thread.join();
-
   rocksdb::SyncPoint::GetInstance()->DisableProcessing();
   rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
 
+  env_->SleepForMicroseconds(200000);
+
   ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
   ASSERT_EQ(1U, int_prop);
 }
@@ -296,7 +284,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesCompactRange) {
   options.max_background_compactions = 1;
   const int kNumLevels = 5;
   options.num_levels = kNumLevels;
-  options.max_compaction_bytes = 1;  // Force not expanding in compactions
+  options.expanded_compaction_factor = 0;  // Force not expanding in compactions
   BlockBasedTableOptions table_options;
   table_options.block_size = 1024;
   options.table_factory.reset(NewBlockBasedTableFactory(table_options));
@@ -407,7 +395,7 @@ TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBaseInc) {
   env_->SetBackgroundThreads(1, Env::HIGH);
 }
 
-TEST_F(DBTestDynamicLevel, DISABLED_MigrateToDynamicLevelMaxBytesBase) {
+TEST_F(DBTestDynamicLevel, MigrateToDynamicLevelMaxBytesBase) {
   Random rnd(301);
   const int kMaxKey = 2000;
 
@@ -463,7 +451,7 @@ TEST_F(DBTestDynamicLevel, DISABLED_MigrateToDynamicLevelMaxBytesBase) {
   compaction_finished = false;
   // Issue manual compaction in one thread and still verify DB state
   // in main thread.
-  rocksdb::port::Thread t([&]() {
+  std::thread t([&]() {
     CompactRangeOptions compact_options;
     compact_options.change_level = true;
     compact_options.target_level = options.num_levels - 1;

db/db_filesnapshot.cc

@@ -1,8 +1,11 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 //
+// Copyright (c) 2012 Facebook.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
 
 #ifndef ROCKSDB_LITE
 
@@ -11,19 +14,19 @@
 #endif
 
 #include <inttypes.h>
-#include <stdint.h>
 #include <algorithm>
 #include <string>
+#include <stdint.h>
 #include "db/db_impl.h"
 #include "db/filename.h"
 #include "db/job_context.h"
 #include "db/version_set.h"
-#include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
-#include "util/file_util.h"
+#include "port/port.h"
 #include "util/mutexlock.h"
 #include "util/sync_point.h"
+#include "util/file_util.h"
 
 namespace rocksdb {
 
@@ -31,10 +34,10 @@ Status DBImpl::DisableFileDeletions() {
   InstrumentedMutexLock l(&mutex_);
   ++disable_delete_obsolete_files_;
   if (disable_delete_obsolete_files_ == 1) {
-    Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+    Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
         "File Deletions Disabled");
   } else {
-    Log(InfoLogLevel::WARN_LEVEL, immutable_db_options_.info_log,
+    Log(InfoLogLevel::WARN_LEVEL, db_options_.info_log,
         "File Deletions Disabled, but already disabled. Counter: %d",
         disable_delete_obsolete_files_);
   }
@@ -55,12 +58,12 @@ Status DBImpl::EnableFileDeletions(bool force) {
       --disable_delete_obsolete_files_;
     }
     if (disable_delete_obsolete_files_ == 0)  {
-      Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+      Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
           "File Deletions Enabled");
       should_purge_files = true;
       FindObsoleteFiles(&job_context, true);
     } else {
-      Log(InfoLogLevel::WARN_LEVEL, immutable_db_options_.info_log,
+      Log(InfoLogLevel::WARN_LEVEL, db_options_.info_log,
           "File Deletions Enable, but not really enabled. Counter: %d",
           disable_delete_obsolete_files_);
     }
@@ -69,7 +72,7 @@ Status DBImpl::EnableFileDeletions(bool force) {
     PurgeObsoleteFiles(job_context);
   }
   job_context.Clean();
-  LogFlush(immutable_db_options_.info_log);
+  LogFlush(db_options_.info_log);
   return Status::OK();
 }
 
@@ -80,6 +83,7 @@ int DBImpl::IsFileDeletionsEnabled() const {
 Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
                             uint64_t* manifest_file_size,
                             bool flush_memtable) {
+
   *manifest_file_size = 0;
 
   mutex_.Lock();
@@ -106,7 +110,7 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
 
     if (!status.ok()) {
       mutex_.Unlock();
-      Log(InfoLogLevel::ERROR_LEVEL, immutable_db_options_.info_log,
+      Log(InfoLogLevel::ERROR_LEVEL, db_options_.info_log,
           "Cannot Flush data %s\n", status.ToString().c_str());
       return status;
     }
@@ -122,7 +126,7 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
   }
 
   ret.clear();
-  ret.reserve(live.size() + 3);  // *.sst + CURRENT + MANIFEST + OPTIONS
+  ret.reserve(live.size() + 2); //*.sst + CURRENT + MANIFEST
 
   // create names of the live files. The names are not absolute
   // paths, instead they are relative to dbname_;
@@ -132,7 +136,6 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
 
   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();

db/db_flush_test.cc

@@ -1,91 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-#include "util/fault_injection_test_env.h"
-#include "util/sync_point.h"
-
-namespace rocksdb {
-
-class DBFlushTest : public DBTestBase {
- public:
-  DBFlushTest() : DBTestBase("/db_flush_test") {}
-};
-
-// We had issue when two background threads trying to flush at the same time,
-// only one of them get committed. The test verifies the issue is fixed.
-TEST_F(DBFlushTest, FlushWhileWritingManifest) {
-  Options options;
-  options.disable_auto_compactions = true;
-  options.max_background_flushes = 2;
-  Reopen(options);
-  FlushOptions no_wait;
-  no_wait.wait = false;
-
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"VersionSet::LogAndApply:WriteManifest",
-        "DBFlushTest::FlushWhileWritingManifest:1"},
-       {"MemTableList::InstallMemtableFlushResults:InProgress",
-        "VersionSet::LogAndApply:WriteManifestDone"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  ASSERT_OK(Put("foo", "v"));
-  ASSERT_OK(dbfull()->Flush(no_wait));
-  TEST_SYNC_POINT("DBFlushTest::FlushWhileWritingManifest:1");
-  ASSERT_OK(Put("bar", "v"));
-  ASSERT_OK(dbfull()->Flush(no_wait));
-  // If the issue is hit we will wait here forever.
-  dbfull()->TEST_WaitForFlushMemTable();
-#ifndef ROCKSDB_LITE
-  ASSERT_EQ(2, TotalTableFiles());
-#endif  // ROCKSDB_LITE
-}
-
-TEST_F(DBFlushTest, SyncFail) {
-  std::unique_ptr<FaultInjectionTestEnv> fault_injection_env(
-      new FaultInjectionTestEnv(Env::Default()));
-  Options options;
-  options.disable_auto_compactions = true;
-  options.env = fault_injection_env.get();
-
-  SyncPoint::GetInstance()->LoadDependency(
-      {{"DBFlushTest::SyncFail:1", "DBImpl::SyncClosedLogs:Start"},
-       {"DBImpl::SyncClosedLogs:Failed", "DBFlushTest::SyncFail:2"}});
-  SyncPoint::GetInstance()->EnableProcessing();
-
-  Reopen(options);
-  Put("key", "value");
-  auto* cfd =
-      reinterpret_cast<ColumnFamilyHandleImpl*>(db_->DefaultColumnFamily())
-          ->cfd();
-  int refs_before = cfd->current()->TEST_refs();
-  FlushOptions flush_options;
-  flush_options.wait = false;
-  ASSERT_OK(dbfull()->Flush(flush_options));
-  fault_injection_env->SetFilesystemActive(false);
-  TEST_SYNC_POINT("DBFlushTest::SyncFail:1");
-  TEST_SYNC_POINT("DBFlushTest::SyncFail:2");
-  fault_injection_env->SetFilesystemActive(true);
-  dbfull()->TEST_WaitForFlushMemTable();
-#ifndef ROCKSDB_LITE
-  ASSERT_EQ("", FilesPerLevel());  // flush failed.
-#endif                             // ROCKSDB_LITE
-  // Flush job should release ref count to current version.
-  ASSERT_EQ(refs_before, cfd->current()->TEST_refs());
-  Destroy(options);
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_impl.h

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -10,11 +10,8 @@
 
 #include <atomic>
 #include <deque>
-#include <functional>
 #include <limits>
 #include <list>
-#include <map>
-#include <queue>
 #include <set>
 #include <string>
 #include <utility>
@@ -23,7 +20,6 @@
 #include "db/column_family.h"
 #include "db/compaction_job.h"
 #include "db/dbformat.h"
-#include "db/external_sst_file_ingestion_job.h"
 #include "db/flush_job.h"
 #include "db/flush_scheduler.h"
 #include "db/internal_stats.h"
@@ -33,16 +29,15 @@
 #include "db/wal_manager.h"
 #include "db/write_controller.h"
 #include "db/write_thread.h"
+#include "db/writebuffer.h"
 #include "memtable_list.h"
 #include "port/port.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "rocksdb/memtablerep.h"
 #include "rocksdb/transaction_log.h"
-#include "rocksdb/write_buffer_manager.h"
 #include "table/scoped_arena_iterator.h"
 #include "util/autovector.h"
-#include "util/db_options.h"
 #include "util/event_logger.h"
 #include "util/hash.h"
 #include "util/instrumented_mutex.h"
@@ -60,7 +55,6 @@ class Arena;
 class WriteCallback;
 struct JobContext;
 struct ExternalSstFileInfo;
-struct MemTableInfo;
 
 class DBImpl : public DB {
  public:
@@ -125,10 +119,6 @@ class DBImpl : public DB {
   using DB::GetProperty;
   virtual bool GetProperty(ColumnFamilyHandle* column_family,
                            const Slice& property, std::string* value) override;
-  using DB::GetMapProperty;
-  virtual bool GetMapProperty(ColumnFamilyHandle* column_family,
-                              const Slice& property,
-                              std::map<std::string, double>* value) override;
   using DB::GetIntProperty;
   virtual bool GetIntProperty(ColumnFamilyHandle* column_family,
                               const Slice& property, uint64_t* value) override;
@@ -138,13 +128,7 @@ class DBImpl : public DB {
   using DB::GetApproximateSizes;
   virtual void GetApproximateSizes(ColumnFamilyHandle* column_family,
                                    const Range* range, int n, uint64_t* sizes,
-                                   uint8_t include_flags
-                                   = INCLUDE_FILES) override;
-  using DB::GetApproximateMemTableStats;
-  virtual void GetApproximateMemTableStats(ColumnFamilyHandle* column_family,
-                                           const Range& range,
-                                           uint64_t* const count,
-                                           uint64_t* const size) override;
+                                   bool include_memtable = false) override;
   using DB::CompactRange;
   virtual Status CompactRange(const CompactRangeOptions& options,
                               ColumnFamilyHandle* column_family,
@@ -168,9 +152,6 @@ class DBImpl : public DB {
       ColumnFamilyHandle* column_family,
       const std::unordered_map<std::string, std::string>& options_map) override;
 
-  virtual Status SetDBOptions(
-      const std::unordered_map<std::string, std::string>& options_map) override;
-
   using DB::NumberLevels;
   virtual int NumberLevels(ColumnFamilyHandle* column_family) override;
   using DB::MaxMemCompactionLevel;
@@ -181,9 +162,10 @@ class DBImpl : public DB {
   virtual const std::string& GetName() const override;
   virtual Env* GetEnv() const override;
   using DB::GetOptions;
-  virtual Options GetOptions(ColumnFamilyHandle* column_family) const override;
+  virtual const Options& GetOptions(
+      ColumnFamilyHandle* column_family) const override;
   using DB::GetDBOptions;
-  virtual DBOptions GetDBOptions() const override;
+  virtual const DBOptions& GetDBOptions() const override;
   using DB::Flush;
   virtual Status Flush(const FlushOptions& options,
                        ColumnFamilyHandle* column_family) override;
@@ -250,7 +232,7 @@ class DBImpl : public DB {
   // SST files will also be checked.
   //
   // If a key is found, *found_record_for_key will be set to true and
-  // *seq will be set to the stored sequence number for the latest
+  // *seq will will be set to the stored sequence number for the latest
   // operation on this key or kMaxSequenceNumber if unknown.
   // If no key is found, *found_record_for_key will be set to false.
   //
@@ -267,16 +249,16 @@ class DBImpl : public DB {
   //
   // Returns OK or NotFound on success,
   // other status on unexpected error.
-  // TODO(andrewkr): this API need to be aware of range deletion operations
   Status GetLatestSequenceForKey(SuperVersion* sv, const Slice& key,
                                  bool cache_only, SequenceNumber* seq,
                                  bool* found_record_for_key);
 
-  using DB::IngestExternalFile;
-  virtual Status IngestExternalFile(
-      ColumnFamilyHandle* column_family,
-      const std::vector<std::string>& external_files,
-      const IngestExternalFileOptions& ingestion_options) override;
+  using DB::AddFile;
+  virtual Status AddFile(ColumnFamilyHandle* column_family,
+                         const ExternalSstFileInfo* file_info,
+                         bool move_file) override;
+  virtual Status AddFile(ColumnFamilyHandle* column_family,
+                         const std::string& file_path, bool move_file) override;
 
 #endif  // ROCKSDB_LITE
 
@@ -302,8 +284,7 @@ class DBImpl : public DB {
   // The keys of this iterator are internal keys (see format.h).
   // The returned iterator should be deleted when no longer needed.
   InternalIterator* NewInternalIterator(
-      Arena* arena, RangeDelAggregator* range_del_agg,
-      ColumnFamilyHandle* column_family = nullptr);
+      Arena* arena, ColumnFamilyHandle* column_family = nullptr);
 
 #ifndef NDEBUG
   // Extra methods (for testing) that are not in the public DB interface
@@ -314,19 +295,8 @@ class DBImpl : public DB {
                            ColumnFamilyHandle* column_family = nullptr,
                            bool disallow_trivial_move = false);
 
-  void TEST_MaybeFlushColumnFamilies();
-
-  bool TEST_UnableToFlushOldestLog() {
-    return unable_to_flush_oldest_log_;
-  }
-
-  bool TEST_IsLogGettingFlushed() {
-    return alive_log_files_.begin()->getting_flushed;
-  }
-
   // Force current memtable contents to be flushed.
-  Status TEST_FlushMemTable(bool wait = true,
-                            ColumnFamilyHandle* cfh = nullptr);
+  Status TEST_FlushMemTable(bool wait = true);
 
   // Wait for memtable compaction
   Status TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family = nullptr);
@@ -367,37 +337,16 @@ class DBImpl : public DB {
 
   uint64_t TEST_LogfileNumber();
 
-  uint64_t TEST_total_log_size() const { return total_log_size_; }
-
   // Returns column family name to ImmutableCFOptions map.
   Status TEST_GetAllImmutableCFOptions(
       std::unordered_map<std::string, const ImmutableCFOptions*>* iopts_map);
 
-  // Return the lastest MutableCFOptions of of a column family
-  Status TEST_GetLatestMutableCFOptions(ColumnFamilyHandle* column_family,
-                                        MutableCFOptions* mutable_cf_opitons);
-
   Cache* TEST_table_cache() { return table_cache_.get(); }
 
   WriteController& TEST_write_controler() { return write_controller_; }
 
-  uint64_t TEST_FindMinLogContainingOutstandingPrep();
-  uint64_t TEST_FindMinPrepLogReferencedByMemTable();
-
-  int TEST_BGCompactionsAllowed() const;
-
 #endif  // NDEBUG
 
-  // Return maximum background compaction allowed to be scheduled based on
-  // compaction status.
-  int BGCompactionsAllowed() const;
-
-  // move logs pending closing from job_context to the DB queue and
-  // schedule a purge
-  void ScheduleBgLogWriterClose(JobContext* job_context);
-
-  uint64_t MinLogNumberToKeep();
-
   // Returns the list of live files in 'live' and the list
   // of all files in the filesystem in 'candidate_files'.
   // If force == false and the last call was less than
@@ -410,19 +359,12 @@ class DBImpl : public DB {
   // belong to live files are posibly removed. Also, removes all the
   // files in sst_delete_files and log_delete_files.
   // It is not necessary to hold the mutex when invoking this method.
-  void PurgeObsoleteFiles(const JobContext& background_contet,
-                          bool schedule_only = false);
-
-  void SchedulePurge();
+  void PurgeObsoleteFiles(const JobContext& background_contet);
 
   ColumnFamilyHandle* DefaultColumnFamily() const override;
 
   const SnapshotList& snapshots() const { return snapshots_; }
 
-  const ImmutableDBOptions& immutable_db_options() const {
-    return immutable_db_options_;
-  }
-
   void CancelAllBackgroundWork(bool wait);
 
   // Find Super version and reference it. Based on options, it might return
@@ -436,6 +378,9 @@ class DBImpl : public DB {
   // mutex is held.
   SuperVersion* GetAndRefSuperVersion(uint32_t column_family_id);
 
+  // Same as above, should called without mutex held and not on write thread.
+  SuperVersion* GetAndRefSuperVersionUnlocked(uint32_t column_family_id);
+
   // Un-reference the super version and return it to thread local cache if
   // needed. If it is the last reference of the super version. Clean it up
   // after un-referencing it.
@@ -446,11 +391,18 @@ class DBImpl : public DB {
   // REQUIRED: this function should only be called on the write thread.
   void ReturnAndCleanupSuperVersion(uint32_t colun_family_id, SuperVersion* sv);
 
+  // Same as above, should called without mutex held and not on write thread.
+  void ReturnAndCleanupSuperVersionUnlocked(uint32_t colun_family_id,
+                                            SuperVersion* sv);
+
   // REQUIRED: this function should only be called on the write thread or if the
   // mutex is held.  Return value only valid until next call to this function or
   // mutex is released.
   ColumnFamilyHandle* GetColumnFamilyHandle(uint32_t column_family_id);
 
+  // Same as above, should called without mutex held and not on write thread.
+  ColumnFamilyHandle* GetColumnFamilyHandleUnlocked(uint32_t column_family_id);
+
   // Returns the number of currently running flushes.
   // REQUIREMENT: mutex_ must be held when calling this function.
   int num_running_flushes() {
@@ -465,85 +417,17 @@ class DBImpl : public DB {
     return num_running_compactions_;
   }
 
-  const WriteController& write_controller() { return write_controller_; }
-
-  // hollow transactions shell used for recovery.
-  // these will then be passed to TransactionDB so that
-  // locks can be reacquired before writing can resume.
-  struct RecoveredTransaction {
-    uint64_t log_number_;
-    std::string name_;
-    WriteBatch* batch_;
-    explicit RecoveredTransaction(const uint64_t log, const std::string& name,
-                                  WriteBatch* batch)
-        : log_number_(log), name_(name), batch_(batch) {}
-
-    ~RecoveredTransaction() { delete batch_; }
-  };
-
-  bool allow_2pc() const { return immutable_db_options_.allow_2pc; }
-
-  std::unordered_map<std::string, RecoveredTransaction*>
-  recovered_transactions() {
-    return recovered_transactions_;
-  }
-
-  RecoveredTransaction* GetRecoveredTransaction(const std::string& name) {
-    auto it = recovered_transactions_.find(name);
-    if (it == recovered_transactions_.end()) {
-      return nullptr;
-    } else {
-      return it->second;
-    }
-  }
-
-  void InsertRecoveredTransaction(const uint64_t log, const std::string& name,
-                                  WriteBatch* batch) {
-    recovered_transactions_[name] = new RecoveredTransaction(log, name, batch);
-    MarkLogAsContainingPrepSection(log);
-  }
-
-  void DeleteRecoveredTransaction(const std::string& name) {
-    auto it = recovered_transactions_.find(name);
-    assert(it != recovered_transactions_.end());
-    auto* trx = it->second;
-    recovered_transactions_.erase(it);
-    MarkLogAsHavingPrepSectionFlushed(trx->log_number_);
-    delete trx;
-  }
-
-  void DeleteAllRecoveredTransactions() {
-    for (auto it = recovered_transactions_.begin();
-         it != recovered_transactions_.end(); it++) {
-      delete it->second;
-    }
-    recovered_transactions_.clear();
-  }
-
-  void MarkLogAsHavingPrepSectionFlushed(uint64_t log);
-  void MarkLogAsContainingPrepSection(uint64_t log);
-  void AddToLogsToFreeQueue(log::Writer* log_writer) {
-    logs_to_free_queue_.push_back(log_writer);
-  }
-
-  Status NewDB();
-
  protected:
   Env* const env_;
   const std::string dbname_;
   unique_ptr<VersionSet> versions_;
-  const DBOptions initial_db_options_;
-  const ImmutableDBOptions immutable_db_options_;
-  MutableDBOptions mutable_db_options_;
+  const DBOptions db_options_;
   Statistics* stats_;
-  std::unordered_map<std::string, RecoveredTransaction*>
-      recovered_transactions_;
 
   InternalIterator* NewInternalIterator(const ReadOptions&,
                                         ColumnFamilyData* cfd,
                                         SuperVersion* super_version,
-                                        Arena* arena,
-                                        RangeDelAggregator* range_del_agg);
+                                        Arena* arena);
 
   // Except in DB::Open(), WriteOptionsFile can only be called when:
   // 1. WriteThread::Writer::EnterUnbatched() is used.
@@ -564,13 +448,6 @@ class DBImpl : public DB {
                                    Compaction *c, const Status &st,
                                    const CompactionJobStats& job_stats,
                                    int job_id);
-  void NotifyOnMemTableSealed(ColumnFamilyData* cfd,
-                              const MemTableInfo& mem_table_info);
-
-#ifndef ROCKSDB_LITE
-  void NotifyOnExternalFileIngested(
-      ColumnFamilyData* cfd, const ExternalSstFileIngestionJob& ingestion_job);
-#endif  // !ROCKSDB_LITE
 
   void NewThreadStatusCfInfo(ColumnFamilyData* cfd) const;
 
@@ -579,17 +456,11 @@ class DBImpl : public DB {
   void EraseThreadStatusDbInfo() const;
 
   Status WriteImpl(const WriteOptions& options, WriteBatch* updates,
-                   WriteCallback* callback = nullptr,
-                   uint64_t* log_used = nullptr, uint64_t log_ref = 0,
-                   bool disable_memtable = false);
-
-  uint64_t FindMinLogContainingOutstandingPrep();
-  uint64_t FindMinPrepLogReferencedByMemTable();
+                   WriteCallback* callback);
 
  private:
   friend class DB;
   friend class InternalStats;
-  friend class TransactionImpl;
 #ifndef ROCKSDB_LITE
   friend class ForwardIterator;
 #endif
@@ -602,14 +473,13 @@ class DBImpl : public DB {
 
   struct WriteContext;
 
-  struct PurgeFileInfo;
+  Status NewDB();
 
   // 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.
   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);
+                 bool read_only = false, bool error_if_log_file_exist = false);
 
   void MaybeIgnoreError(Status* s) const;
 
@@ -617,18 +487,13 @@ class DBImpl : public DB {
 
   // Delete any unneeded files and stale in-memory entries.
   void DeleteObsoleteFiles();
-  // Delete obsolete files and log status and information of file deletion
-  void DeleteObsoleteFileImpl(Status file_deletion_status, int job_id,
-                              const std::string& fname, FileType type,
-                              uint64_t number, uint32_t path_id);
 
   // Background process needs to call
   //     auto x = CaptureCurrentFileNumberInPendingOutputs()
-  //     auto file_num = versions_->NewFileNumber();
   //     <do something>
   //     ReleaseFileNumberFromPendingOutputs(x)
-  // This will protect any file with number `file_num` or greater from being
-  // deleted while <do something> is running.
+  // This will protect any temporary files created while <do something> is
+  // executing from being deleted.
   // -----------
   // This function will capture current file number and append it to
   // pending_outputs_. This will prevent any background process to delete any
@@ -641,8 +506,6 @@ class DBImpl : public DB {
   // and blocked by any other pending_outputs_ calls)
   void ReleaseFileNumberFromPendingOutputs(std::list<uint64_t>::iterator v);
 
-  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.
   Status FlushMemTableToOutputFile(ColumnFamilyData* cfd,
@@ -652,10 +515,10 @@ class DBImpl : public DB {
 
   // REQUIRES: log_numbers are sorted in ascending order
   Status RecoverLogFiles(const std::vector<uint64_t>& log_numbers,
-                         SequenceNumber* next_sequence, bool read_only);
+                         SequenceNumber* max_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
+  // storage. The first one is used atdatabase RecoveryTime (when the
   // database is opened) and is heavyweight because it holds the mutex
   // for the entire period. The second method WriteLevel0Table supports
   // concurrent flush memtables to storage.
@@ -664,35 +527,27 @@ class DBImpl : public DB {
 
   // num_bytes: for slowdown case, delay time is calculated based on
   //            `num_bytes` going through.
-  Status DelayWrite(uint64_t num_bytes, const WriteOptions& write_options);
+  Status DelayWrite(uint64_t num_bytes);
 
   Status ScheduleFlushes(WriteContext* context);
 
   Status SwitchMemtable(ColumnFamilyData* cfd, WriteContext* context);
 
   // Force current memtable contents to be flushed.
-  Status FlushMemTable(ColumnFamilyData* cfd, const FlushOptions& options,
-                       bool writes_stopped = false);
+  Status FlushMemTable(ColumnFamilyData* cfd, const FlushOptions& options);
 
   // Wait for memtable flushed
   Status WaitForFlushMemTable(ColumnFamilyData* cfd);
 
+  void RecordFlushIOStats();
+  void RecordCompactionIOStats();
+
 #ifndef ROCKSDB_LITE
-
-  Status CompactFilesImpl(const CompactionOptions& compact_options,
-                          ColumnFamilyData* cfd, Version* version,
-                          const std::vector<std::string>& input_file_names,
-                          const int output_level, int output_path_id,
-                          JobContext* job_context, LogBuffer* log_buffer);
-
-  // Wait for current IngestExternalFile() calls to finish.
-  // REQUIRES: mutex_ held
-  void WaitForIngestFile();
-
-#else
-  // IngestExternalFile is not supported in ROCKSDB_LITE so this function
-  // will be no-op
-  void WaitForIngestFile() {}
+  Status CompactFilesImpl(
+      const CompactionOptions& compact_options, ColumnFamilyData* cfd,
+      Version* version, const std::vector<std::string>& input_file_names,
+      const int output_level, int output_path_id, JobContext* job_context,
+      LogBuffer* log_buffer);
 #endif  // ROCKSDB_LITE
 
   ColumnFamilyData* GetColumnFamilyDataByName(const std::string& cf_name);
@@ -700,15 +555,11 @@ class DBImpl : public DB {
   void MaybeScheduleFlushOrCompaction();
   void SchedulePendingFlush(ColumnFamilyData* cfd);
   void SchedulePendingCompaction(ColumnFamilyData* cfd);
-  void SchedulePendingPurge(std::string fname, FileType type, uint64_t number,
-                            uint32_t path_id, int job_id);
   static void BGWorkCompaction(void* arg);
   static void BGWorkFlush(void* db);
-  static void BGWorkPurge(void* arg);
   static void UnscheduleCallback(void* arg);
   void BackgroundCallCompaction(void* arg);
   void BackgroundCallFlush();
-  void BackgroundCallPurge();
   Status BackgroundCompaction(bool* madeProgress, JobContext* job_context,
                               LogBuffer* log_buffer, void* m = 0);
   Status BackgroundFlush(bool* madeProgress, JobContext* job_context,
@@ -740,14 +591,6 @@ class DBImpl : public DB {
 
   const Snapshot* GetSnapshotImpl(bool is_write_conflict_boundary);
 
-  // Persist RocksDB options under the single write thread
-  // REQUIRES: mutex locked
-  Status PersistOptions();
-
-  void MaybeFlushColumnFamilies();
-
-  uint64_t GetMaxTotalWalSize() const;
-
   // table_cache_ provides its own synchronization
   std::shared_ptr<Cache> table_cache_;
 
@@ -759,7 +602,7 @@ class DBImpl : public DB {
   //       same time.
   InstrumentedMutex options_files_mutex_;
   // State below is protected by mutex_
-  mutable InstrumentedMutex mutex_;
+  InstrumentedMutex mutex_;
 
   std::atomic<bool> shutting_down_;
   // This condition variable is signaled on these conditions:
@@ -767,10 +610,9 @@ class DBImpl : public DB {
   // * if AnyManualCompaction, whenever a compaction finishes, even if it hasn't
   // made any progress
   // * whenever a compaction made any progress
-  // * whenever bg_flush_scheduled_ or bg_purge_scheduled_ value decreases
-  // (i.e. whenever a flush is done, even if it didn't make any progress)
-  // * whenever there is an error in background purge, flush or compaction
-  // * whenever num_running_ingest_file_ goes to 0.
+  // * whenever bg_flush_scheduled_ value decreases (i.e. whenever a flush is
+  // done, even if it didn't make any progress)
+  // * whenever there is an error in background flush or compaction
   InstrumentedCondVar bg_cv_;
   uint64_t logfile_number_;
   std::deque<uint64_t>
@@ -863,7 +705,7 @@ class DBImpl : public DB {
 
   Directories directories_;
 
-  WriteBufferManager* write_buffer_manager_;
+  WriteBuffer write_buffer_;
 
   WriteThread write_thread_;
 
@@ -890,19 +732,6 @@ class DBImpl : public DB {
   // State is protected with db mutex.
   std::list<uint64_t> pending_outputs_;
 
-  // PurgeFileInfo is a structure to hold information of files to be deleted in
-  // purge_queue_
-  struct PurgeFileInfo {
-    std::string fname;
-    FileType type;
-    uint64_t number;
-    uint32_t path_id;
-    int job_id;
-    PurgeFileInfo(std::string fn, FileType t, uint64_t num, uint32_t pid,
-                  int jid)
-        : fname(fn), type(t), number(num), path_id(pid), job_id(jid) {}
-  };
-
   // flush_queue_ and compaction_queue_ hold column families that we need to
   // flush and compact, respectively.
   // A column family is inserted into flush_queue_ when it satisfies condition
@@ -927,12 +756,6 @@ class DBImpl : public DB {
   // invariant(column family present in compaction_queue_ <==>
   // ColumnFamilyData::pending_compaction_ == true)
   std::deque<ColumnFamilyData*> compaction_queue_;
-
-  // A queue to store filenames of the files to be purged
-  std::deque<PurgeFileInfo> purge_queue_;
-
-  // A queue to store log writers to close
-  std::deque<log::Writer*> logs_to_free_queue_;
   int unscheduled_flushes_;
   int unscheduled_compactions_;
 
@@ -948,9 +771,6 @@ class DBImpl : public DB {
   // stores the number of flushes are currently running
   int num_running_flushes_;
 
-  // number of background obsolete file purge jobs, submitted to the HIGH pool
-  int bg_purge_scheduled_;
-
   // Information for a manual compaction
   struct ManualCompaction {
     ColumnFamilyData* cfd;
@@ -988,9 +808,8 @@ class DBImpl : public DB {
   // without any synchronization
   int disable_delete_obsolete_files_;
 
-  // last time when DeleteObsoleteFiles with full scan was executed. Originaly
-  // initialized with startup time.
-  uint64_t delete_obsolete_files_last_run_;
+  // next time when we should run DeleteObsoleteFiles with full scan
+  uint64_t delete_obsolete_files_next_run_;
 
   // last time stats were dumped to LOG
   std::atomic<uint64_t> last_stats_dump_time_microsec_;
@@ -999,18 +818,7 @@ class DBImpl : public DB {
   // they're unique
   std::atomic<int> next_job_id_;
 
-  // A flag indicating whether the current rocksdb database has any
-  // data that is not yet persisted into either WAL or SST file.
-  // Used when disableWAL is true.
-  std::atomic<bool> has_unpersisted_data_;
-
-  // if an attempt was made to flush all column families that
-  // the oldest log depends on but uncommited data in the oldest
-  // log prevents the log from being released.
-  // We must attempt to free the dependent memtables again
-  // at a later time after the transaction in the oldest
-  // log is fully commited.
-  bool unable_to_flush_oldest_log_;
+  bool flush_on_destroy_; // Used when disableWAL is true.
 
   static const int KEEP_LOG_FILE_NUM = 1000;
   // MSVC version 1800 still does not have constexpr for ::max()
@@ -1021,10 +829,6 @@ class DBImpl : public DB {
   // The options to access storage files
   const EnvOptions env_options_;
 
-  // Number of running IngestExternalFile() calls.
-  // REQUIRES: mutex held
-  int num_running_ingest_file_;
-
 #ifndef ROCKSDB_LITE
   WalManager wal_manager_;
 #endif  // ROCKSDB_LITE
@@ -1032,40 +836,15 @@ class DBImpl : public DB {
   // Unified interface for logging events
   EventLogger event_logger_;
 
-  // A value of > 0 temporarily disables scheduling of background work
+  // A value of >0 temporarily disables scheduling of background work
   int bg_work_paused_;
 
-  // A value of > 0 temporarily disables scheduling of background compaction
-  int bg_compaction_paused_;
-
   // Guard against multiple concurrent refitting
   bool refitting_level_;
 
   // Indicate DB was opened successfully
   bool opened_successfully_;
 
-  // minmum log number still containing prepared data.
-  // this is used by FindObsoleteFiles to determine which
-  // flushed logs we must keep around because they still
-  // contain prepared data which has not been flushed or rolled back
-  std::priority_queue<uint64_t, std::vector<uint64_t>, std::greater<uint64_t>>
-      min_log_with_prep_;
-
-  // to be used in conjunction with min_log_with_prep_.
-  // once a transaction with data in log L is committed or rolled back
-  // rather than removing the value from the heap we add that value
-  // to prepared_section_completed_ which maps LOG -> instance_count
-  // since a log could contain multiple prepared sections
-  //
-  // when trying to determine the minmum log still active we first
-  // consult min_log_with_prep_. while that root value maps to
-  // a value > 0 in prepared_section_completed_ we decrement the
-  // instance_count for that log and pop the root value in
-  // min_log_with_prep_. This will work the same as a min_heap
-  // where we are deleteing arbitrary elements and the up heaping.
-  std::unordered_map<uint64_t, uint64_t> prepared_section_completed_;
-  std::mutex prep_heap_mutex_;
-
   // No copying allowed
   DBImpl(const DBImpl&);
   void operator=(const DBImpl&);
@@ -1110,8 +889,9 @@ class DBImpl : public DB {
                  bool* value_found = nullptr);
 
   bool GetIntPropertyInternal(ColumnFamilyData* cfd,
-                              const DBPropertyInfo& property_info,
-                              bool is_locked, uint64_t* value);
+                              DBPropertyType property_type,
+                              bool need_out_of_mutex, bool is_locked,
+                              uint64_t* value);
 
   bool HasPendingManualCompaction();
   bool HasExclusiveManualCompaction();
@@ -1120,13 +900,13 @@ class DBImpl : public DB {
   bool ShouldntRunManualCompaction(ManualCompaction* m);
   bool HaveManualCompaction(ColumnFamilyData* cfd);
   bool MCOverlap(ManualCompaction* m, ManualCompaction* m1);
-
-  size_t GetWalPreallocateBlockSize(uint64_t write_buffer_size) const;
 };
 
+// Sanitize db options.  The caller should delete result.info_log if
+// it is not equal to src.info_log.
 extern Options SanitizeOptions(const std::string& db,
+                               const InternalKeyComparator* icmp,
                                const Options& src);
-
 extern DBOptions SanitizeOptions(const std::string& db, const DBOptions& src);
 
 // Fix user-supplied options to be reasonable

db/db_impl_debug.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -19,11 +19,6 @@ uint64_t DBImpl::TEST_GetLevel0TotalSize() {
   return default_cf_handle_->cfd()->current()->storage_info()->NumLevelBytes(0);
 }
 
-void DBImpl::TEST_MaybeFlushColumnFamilies() {
-  InstrumentedMutexLock l(&mutex_);
-  MaybeFlushColumnFamilies();
-}
-
 int64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
     ColumnFamilyHandle* column_family) {
   ColumnFamilyData* cfd;
@@ -79,17 +74,10 @@ Status DBImpl::TEST_CompactRange(int level, const Slice* begin,
                              disallow_trivial_move);
 }
 
-Status DBImpl::TEST_FlushMemTable(bool wait, ColumnFamilyHandle* cfh) {
+Status DBImpl::TEST_FlushMemTable(bool wait) {
   FlushOptions fo;
   fo.wait = wait;
-  ColumnFamilyData* cfd;
-  if (cfh == nullptr) {
-    cfd = default_cf_handle_->cfd();
-  } else {
-    auto cfhi = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh);
-    cfd = cfhi->cfd();
-  }
-  return FlushMemTable(cfd, fo);
+  return FlushMemTable(default_cf_handle_->cfd(), fo);
 }
 
 Status DBImpl::TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family) {
@@ -166,27 +154,5 @@ Status DBImpl::TEST_GetAllImmutableCFOptions(
   return Status::OK();
 }
 
-uint64_t DBImpl::TEST_FindMinLogContainingOutstandingPrep() {
-  return FindMinLogContainingOutstandingPrep();
-}
-
-uint64_t DBImpl::TEST_FindMinPrepLogReferencedByMemTable() {
-  return FindMinPrepLogReferencedByMemTable();
-}
-
-Status DBImpl::TEST_GetLatestMutableCFOptions(
-    ColumnFamilyHandle* column_family, MutableCFOptions* mutable_cf_options) {
-  InstrumentedMutexLock l(&mutex_);
-
-  auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
-  *mutable_cf_options = *cfh->cfd()->GetLatestMutableCFOptions();
-  return Status::OK();
-}
-
-int DBImpl::TEST_BGCompactionsAllowed() const {
-  InstrumentedMutexLock l(&mutex_);
-  return BGCompactionsAllowed();
-}
-
 }  // namespace rocksdb
 #endif  // NDEBUG

db/db_impl_experimental.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -49,8 +49,8 @@ Status DBImpl::SuggestCompactRange(ColumnFamilyHandle* column_family,
     }
     // Since we have some more files to compact, we should also recompute
     // compaction score
-    vstorage->ComputeCompactionScore(*cfd->ioptions(),
-                                     *cfd->GetLatestMutableCFOptions());
+    vstorage->ComputeCompactionScore(*cfd->GetLatestMutableCFOptions(),
+                                     CompactionOptionsFIFO());
     SchedulePendingCompaction(cfd);
     MaybeScheduleFlushOrCompaction();
   }
@@ -61,7 +61,7 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
   assert(column_family);
 
   if (target_level < 1) {
-    Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+    Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
         "PromoteL0 FAILED. Invalid target level %d\n", target_level);
     return Status::InvalidArgument("Invalid target level");
   }
@@ -75,7 +75,7 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
     const auto* vstorage = cfd->current()->storage_info();
 
     if (target_level >= vstorage->num_levels()) {
-      Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+      Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
           "PromoteL0 FAILED. Target level %d does not exist\n", target_level);
       job_context.Clean();
       return Status::InvalidArgument("Target level does not exist");
@@ -94,7 +94,7 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
     for (size_t i = 0; i < l0_files.size(); ++i) {
       auto f = l0_files[i];
       if (f->being_compacted) {
-        Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+        Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
             "PromoteL0 FAILED. File %" PRIu64 " being compacted\n",
             f->fd.GetNumber());
         job_context.Clean();
@@ -104,7 +104,7 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
       if (i == 0) continue;
       auto prev_f = l0_files[i - 1];
       if (icmp->Compare(prev_f->largest, f->smallest) >= 0) {
-        Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+        Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
             "PromoteL0 FAILED. Files %" PRIu64 " and %" PRIu64
             " have overlapping ranges\n",
             prev_f->fd.GetNumber(), f->fd.GetNumber());
@@ -116,7 +116,7 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
     // Check that all levels up to target_level are empty.
     for (int level = 1; level <= target_level; ++level) {
       if (vstorage->NumLevelFiles(level) > 0) {
-        Log(InfoLogLevel::INFO_LEVEL, immutable_db_options_.info_log,
+        Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
             "PromoteL0 FAILED. Level %d not empty\n", level);
         job_context.Clean();
         return Status::InvalidArgument(
@@ -141,7 +141,7 @@ Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
           cfd, &job_context, *cfd->GetLatestMutableCFOptions());
     }
   }  // lock released here
-  LogFlush(immutable_db_options_.info_log);
+  LogFlush(db_options_.info_log);
   job_context.Clean();
 
   return status;

db/db_impl_readonly.cc

@@ -1,16 +1,15 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 
 #include "db/db_impl_readonly.h"
 
 #include "db/compacted_db_impl.h"
 #include "db/db_impl.h"
-#include "db/db_iter.h"
 #include "db/merge_context.h"
-#include "db/range_del_aggregator.h"
+#include "db/db_iter.h"
 #include "util/perf_context_imp.h"
 
 namespace rocksdb {
@@ -20,9 +19,8 @@ namespace rocksdb {
 DBImplReadOnly::DBImplReadOnly(const DBOptions& db_options,
                                const std::string& dbname)
     : DBImpl(db_options, dbname) {
-  Log(INFO_LEVEL, immutable_db_options_.info_log,
-      "Opening the db in read only mode");
-  LogFlush(immutable_db_options_.info_log);
+  Log(INFO_LEVEL, db_options_.info_log, "Opening the db in read only mode");
+  LogFlush(db_options_.info_log);
 }
 
 DBImplReadOnly::~DBImplReadOnly() {
@@ -38,14 +36,11 @@ Status DBImplReadOnly::Get(const ReadOptions& read_options,
   auto cfd = cfh->cfd();
   SuperVersion* super_version = cfd->GetSuperVersion();
   MergeContext merge_context;
-  RangeDelAggregator range_del_agg(cfd->internal_comparator(), snapshot);
   LookupKey lkey(key, snapshot);
-  if (super_version->mem->Get(lkey, value, &s, &merge_context, &range_del_agg,
-                              read_options)) {
+  if (super_version->mem->Get(lkey, value, &s, &merge_context)) {
   } else {
     PERF_TIMER_GUARD(get_from_output_files_time);
-    super_version->current->Get(read_options, lkey, value, &s, &merge_context,
-                                &range_del_agg);
+    super_version->current->Get(read_options, lkey, value, &s, &merge_context);
   }
   return s;
 }
@@ -59,14 +54,12 @@ Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
   auto db_iter = NewArenaWrappedDbIterator(
       env_, *cfd->ioptions(), cfd->user_comparator(),
       (read_options.snapshot != nullptr
-           ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
-                 ->number_
+           ? reinterpret_cast<const SnapshotImpl*>(
+                read_options.snapshot)->number_
            : latest_snapshot),
-      super_version->mutable_cf_options.max_sequential_skip_in_iterations,
-      super_version->version_number);
-  auto internal_iter =
-      NewInternalIterator(read_options, cfd, super_version, db_iter->GetArena(),
-                          db_iter->GetRangeDelAggregator());
+      super_version->mutable_cf_options.max_sequential_skip_in_iterations);
+  auto internal_iter = NewInternalIterator(
+      read_options, cfd, super_version, db_iter->GetArena());
   db_iter->SetIterUnderDBIter(internal_iter);
   return db_iter;
 }
@@ -88,14 +81,12 @@ Status DBImplReadOnly::NewIterators(
     auto* db_iter = NewArenaWrappedDbIterator(
         env_, *cfd->ioptions(), cfd->user_comparator(),
         (read_options.snapshot != nullptr
-             ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
-                   ->number_
-             : latest_snapshot),
-        sv->mutable_cf_options.max_sequential_skip_in_iterations,
-        sv->version_number);
-    auto* internal_iter =
-        NewInternalIterator(read_options, cfd, sv, db_iter->GetArena(),
-                            db_iter->GetRangeDelAggregator());
+            ? reinterpret_cast<const SnapshotImpl*>(
+                  read_options.snapshot)->number_
+            : latest_snapshot),
+        sv->mutable_cf_options.max_sequential_skip_in_iterations);
+    auto* internal_iter = NewInternalIterator(
+        read_options, cfd, sv, db_iter->GetArena());
     db_iter->SetIterUnderDBIter(internal_iter);
     iterators->push_back(db_iter);
   }

db/db_impl_readonly.h

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 #pragma once
 
@@ -79,6 +79,7 @@ class DBImplReadOnly : public DBImpl {
     return Status::NotSupported("Not supported operation in read only mode.");
   }
 
+#ifndef ROCKSDB_LITE
   virtual Status DisableFileDeletions() override {
     return Status::NotSupported("Not supported operation in read only mode.");
   }
@@ -91,6 +92,7 @@ class DBImplReadOnly : public DBImpl {
                               bool flush_memtable = true) override {
     return Status::NotSupported("Not supported operation in read only mode.");
   }
+#endif  // ROCKSDB_LITE
 
   using DBImpl::Flush;
   virtual Status Flush(const FlushOptions& options,
@@ -103,14 +105,6 @@ class DBImplReadOnly : public DBImpl {
     return Status::NotSupported("Not supported operation in read only mode.");
   }
 
-  using DB::IngestExternalFile;
-  virtual Status IngestExternalFile(
-      ColumnFamilyHandle* column_family,
-      const std::vector<std::string>& external_files,
-      const IngestExternalFileOptions& ingestion_options) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-
  private:
   friend class DB;
 

db/db_info_dumper.h

@@ -1,14 +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 <string>
-
-#include "util/db_options.h"
-
-namespace rocksdb {
-void DumpDBFileSummary(const ImmutableDBOptions& options,
-                       const std::string& dbname);
-}  // namespace rocksdb

db/db_inplace_update_test.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -18,13 +18,12 @@ class DBTestInPlaceUpdate : public DBTestBase {
 
 TEST_F(DBTestInPlaceUpdate, InPlaceUpdate) {
   do {
-    Options options = CurrentOptions();
+    Options options;
     options.create_if_missing = true;
     options.inplace_update_support = true;
     options.env = env_;
     options.write_buffer_size = 100000;
-    options.allow_concurrent_memtable_write = false;
-    Reopen(options);
+    options = CurrentOptions(options);
     CreateAndReopenWithCF({"pikachu"}, options);
 
     // Update key with values of smaller size
@@ -42,13 +41,12 @@ TEST_F(DBTestInPlaceUpdate, InPlaceUpdate) {
 
 TEST_F(DBTestInPlaceUpdate, InPlaceUpdateLargeNewValue) {
   do {
-    Options options = CurrentOptions();
+    Options options;
     options.create_if_missing = true;
     options.inplace_update_support = true;
     options.env = env_;
     options.write_buffer_size = 100000;
-    options.allow_concurrent_memtable_write = false;
-    Reopen(options);
+    options = CurrentOptions(options);
     CreateAndReopenWithCF({"pikachu"}, options);
 
     // Update key with values of larger size
@@ -66,7 +64,7 @@ TEST_F(DBTestInPlaceUpdate, InPlaceUpdateLargeNewValue) {
 
 TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackSmallerSize) {
   do {
-    Options options = CurrentOptions();
+    Options options;
     options.create_if_missing = true;
     options.inplace_update_support = true;
 
@@ -74,8 +72,7 @@ TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackSmallerSize) {
     options.write_buffer_size = 100000;
     options.inplace_callback =
       rocksdb::DBTestInPlaceUpdate::updateInPlaceSmallerSize;
-    options.allow_concurrent_memtable_write = false;
-    Reopen(options);
+    options = CurrentOptions(options);
     CreateAndReopenWithCF({"pikachu"}, options);
 
     // Update key with values of smaller size
@@ -95,7 +92,7 @@ TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackSmallerSize) {
 
 TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackSmallerVarintSize) {
   do {
-    Options options = CurrentOptions();
+    Options options;
     options.create_if_missing = true;
     options.inplace_update_support = true;
 
@@ -103,8 +100,7 @@ TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackSmallerVarintSize) {
     options.write_buffer_size = 100000;
     options.inplace_callback =
       rocksdb::DBTestInPlaceUpdate::updateInPlaceSmallerVarintSize;
-    options.allow_concurrent_memtable_write = false;
-    Reopen(options);
+    options = CurrentOptions(options);
     CreateAndReopenWithCF({"pikachu"}, options);
 
     // Update key with values of smaller varint size
@@ -124,7 +120,7 @@ TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackSmallerVarintSize) {
 
 TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackLargeNewValue) {
   do {
-    Options options = CurrentOptions();
+    Options options;
     options.create_if_missing = true;
     options.inplace_update_support = true;
 
@@ -132,8 +128,7 @@ TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackLargeNewValue) {
     options.write_buffer_size = 100000;
     options.inplace_callback =
       rocksdb::DBTestInPlaceUpdate::updateInPlaceLargerSize;
-    options.allow_concurrent_memtable_write = false;
-    Reopen(options);
+    options = CurrentOptions(options);
     CreateAndReopenWithCF({"pikachu"}, options);
 
     // Update key with values of larger size
@@ -151,16 +146,15 @@ TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackLargeNewValue) {
 
 TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackNoAction) {
   do {
-    Options options = CurrentOptions();
+    Options options;
     options.create_if_missing = true;
     options.inplace_update_support = true;
 
     options.env = env_;
     options.write_buffer_size = 100000;
     options.inplace_callback =
-        rocksdb::DBTestInPlaceUpdate::updateInPlaceNoAction;
-    options.allow_concurrent_memtable_write = false;
-    Reopen(options);
+      rocksdb::DBTestInPlaceUpdate::updateInPlaceNoAction;
+    options = CurrentOptions(options);
     CreateAndReopenWithCF({"pikachu"}, options);
 
     // Callback function requests no actions from db

db/db_io_failure_test.cc

@@ -1,260 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under both the GPLv2 (found in the
-//  COPYING file in the root directory) and Apache 2.0 License
-//  (found in the LICENSE.Apache file in the root directory).
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-
-namespace rocksdb {
-
-class DBIOFailureTest : public DBTestBase {
- public:
-  DBIOFailureTest() : DBTestBase("/db_io_failure_test") {}
-};
-
-#ifndef ROCKSDB_LITE
-// Check that number of files does not grow when writes are dropped
-TEST_F(DBIOFailureTest, DropWrites) {
-  do {
-    Options options = CurrentOptions();
-    options.env = env_;
-    options.paranoid_checks = false;
-    Reopen(options);
-
-    ASSERT_OK(Put("foo", "v1"));
-    ASSERT_EQ("v1", Get("foo"));
-    Compact("a", "z");
-    const size_t num_files = CountFiles();
-    // Force out-of-space errors
-    env_->drop_writes_.store(true, std::memory_order_release);
-    env_->sleep_counter_.Reset();
-    env_->no_slowdown_ = true;
-    for (int i = 0; i < 5; i++) {
-      if (option_config_ != kUniversalCompactionMultiLevel &&
-          option_config_ != kUniversalSubcompactions) {
-        for (int level = 0; level < dbfull()->NumberLevels(); level++) {
-          if (level > 0 && level == dbfull()->NumberLevels() - 1) {
-            break;
-          }
-          dbfull()->TEST_CompactRange(level, nullptr, nullptr, nullptr,
-                                      true /* disallow trivial move */);
-        }
-      } else {
-        dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-      }
-    }
-
-    std::string property_value;
-    ASSERT_TRUE(db_->GetProperty("rocksdb.background-errors", &property_value));
-    ASSERT_EQ("5", property_value);
-
-    env_->drop_writes_.store(false, std::memory_order_release);
-    ASSERT_LT(CountFiles(), num_files + 3);
-
-    // Check that compaction attempts slept after errors
-    // TODO @krad: Figure out why ASSERT_EQ 5 keeps failing in certain compiler
-    // versions
-    ASSERT_GE(env_->sleep_counter_.Read(), 4);
-  } while (ChangeCompactOptions());
-}
-
-// Check background error counter bumped on flush failures.
-TEST_F(DBIOFailureTest, DropWritesFlush) {
-  do {
-    Options options = CurrentOptions();
-    options.env = env_;
-    options.max_background_flushes = 1;
-    Reopen(options);
-
-    ASSERT_OK(Put("foo", "v1"));
-    // Force out-of-space errors
-    env_->drop_writes_.store(true, std::memory_order_release);
-
-    std::string property_value;
-    // Background error count is 0 now.
-    ASSERT_TRUE(db_->GetProperty("rocksdb.background-errors", &property_value));
-    ASSERT_EQ("0", property_value);
-
-    dbfull()->TEST_FlushMemTable(true);
-
-    ASSERT_TRUE(db_->GetProperty("rocksdb.background-errors", &property_value));
-    ASSERT_EQ("1", property_value);
-
-    env_->drop_writes_.store(false, std::memory_order_release);
-  } while (ChangeCompactOptions());
-}
-#endif  // ROCKSDB_LITE
-
-// Check that CompactRange() returns failure if there is not enough space left
-// on device
-TEST_F(DBIOFailureTest, NoSpaceCompactRange) {
-  do {
-    Options options = CurrentOptions();
-    options.env = env_;
-    options.disable_auto_compactions = true;
-    Reopen(options);
-
-    // generate 5 tables
-    for (int i = 0; i < 5; ++i) {
-      ASSERT_OK(Put(Key(i), Key(i) + "v"));
-      ASSERT_OK(Flush());
-    }
-
-    // Force out-of-space errors
-    env_->no_space_.store(true, std::memory_order_release);
-
-    Status s = dbfull()->TEST_CompactRange(0, nullptr, nullptr, nullptr,
-                                           true /* disallow trivial move */);
-    ASSERT_TRUE(s.IsIOError());
-    ASSERT_TRUE(s.IsNoSpace());
-
-    env_->no_space_.store(false, std::memory_order_release);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBIOFailureTest, NonWritableFileSystem) {
-  do {
-    Options options = CurrentOptions();
-    options.write_buffer_size = 4096;
-    options.arena_block_size = 4096;
-    options.env = env_;
-    Reopen(options);
-    ASSERT_OK(Put("foo", "v1"));
-    env_->non_writeable_rate_.store(100);
-    std::string big(100000, 'x');
-    int errors = 0;
-    for (int i = 0; i < 20; i++) {
-      if (!Put("foo", big).ok()) {
-        errors++;
-        env_->SleepForMicroseconds(100000);
-      }
-    }
-    ASSERT_GT(errors, 0);
-    env_->non_writeable_rate_.store(0);
-  } while (ChangeCompactOptions());
-}
-
-#ifndef ROCKSDB_LITE
-TEST_F(DBIOFailureTest, ManifestWriteError) {
-  // Test for the following problem:
-  // (a) Compaction produces file F
-  // (b) Log record containing F is written to MANIFEST file, but Sync() fails
-  // (c) GC deletes F
-  // (d) After reopening DB, reads fail since deleted F is named in log record
-
-  // We iterate twice.  In the second iteration, everything is the
-  // same except the log record never makes it to the MANIFEST file.
-  for (int iter = 0; iter < 2; iter++) {
-    std::atomic<bool>* error_type = (iter == 0) ? &env_->manifest_sync_error_
-                                                : &env_->manifest_write_error_;
-
-    // Insert foo=>bar mapping
-    Options options = CurrentOptions();
-    options.env = env_;
-    options.create_if_missing = true;
-    options.error_if_exists = false;
-    options.paranoid_checks = true;
-    DestroyAndReopen(options);
-    ASSERT_OK(Put("foo", "bar"));
-    ASSERT_EQ("bar", Get("foo"));
-
-    // Memtable compaction (will succeed)
-    Flush();
-    ASSERT_EQ("bar", Get("foo"));
-    const int last = 2;
-    MoveFilesToLevel(2);
-    ASSERT_EQ(NumTableFilesAtLevel(last), 1);  // foo=>bar is now in last level
-
-    // Merging compaction (will fail)
-    error_type->store(true, std::memory_order_release);
-    dbfull()->TEST_CompactRange(last, nullptr, nullptr);  // Should fail
-    ASSERT_EQ("bar", Get("foo"));
-
-    error_type->store(false, std::memory_order_release);
-
-    // Since paranoid_checks=true, writes should fail
-    ASSERT_NOK(Put("foo2", "bar2"));
-
-    // Recovery: should not lose data
-    ASSERT_EQ("bar", Get("foo"));
-
-    // Try again with paranoid_checks=false
-    Close();
-    options.paranoid_checks = false;
-    Reopen(options);
-
-    // Merging compaction (will fail)
-    error_type->store(true, std::memory_order_release);
-    dbfull()->TEST_CompactRange(last, nullptr, nullptr);  // Should fail
-    ASSERT_EQ("bar", Get("foo"));
-
-    // Recovery: should not lose data
-    error_type->store(false, std::memory_order_release);
-    Reopen(options);
-    ASSERT_EQ("bar", Get("foo"));
-
-    // Since paranoid_checks=false, writes should succeed
-    ASSERT_OK(Put("foo2", "bar2"));
-    ASSERT_EQ("bar", Get("foo"));
-    ASSERT_EQ("bar2", Get("foo2"));
-  }
-}
-#endif  // ROCKSDB_LITE
-
-TEST_F(DBIOFailureTest, PutFailsParanoid) {
-  // Test the following:
-  // (a) A random put fails in paranoid mode (simulate by sync fail)
-  // (b) All other puts have to fail, even if writes would succeed
-  // (c) All of that should happen ONLY if paranoid_checks = true
-
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  options.error_if_exists = false;
-  options.paranoid_checks = true;
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  Status s;
-
-  ASSERT_OK(Put(1, "foo", "bar"));
-  ASSERT_OK(Put(1, "foo1", "bar1"));
-  // simulate error
-  env_->log_write_error_.store(true, std::memory_order_release);
-  s = Put(1, "foo2", "bar2");
-  ASSERT_TRUE(!s.ok());
-  env_->log_write_error_.store(false, std::memory_order_release);
-  s = Put(1, "foo3", "bar3");
-  // the next put should fail, too
-  ASSERT_TRUE(!s.ok());
-  // but we're still able to read
-  ASSERT_EQ("bar", Get(1, "foo"));
-
-  // do the same thing with paranoid checks off
-  options.paranoid_checks = false;
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  ASSERT_OK(Put(1, "foo", "bar"));
-  ASSERT_OK(Put(1, "foo1", "bar1"));
-  // simulate error
-  env_->log_write_error_.store(true, std::memory_order_release);
-  s = Put(1, "foo2", "bar2");
-  ASSERT_TRUE(!s.ok());
-  env_->log_write_error_.store(false, std::memory_order_release);
-  s = Put(1, "foo3", "bar3");
-  // the next put should NOT fail
-  ASSERT_TRUE(s.ok());
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_iter.h

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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
@@ -9,14 +9,11 @@
 
 #pragma once
 #include <stdint.h>
-#include <string>
-#include "db/dbformat.h"
-#include "db/range_del_aggregator.h"
 #include "rocksdb/db.h"
 #include "rocksdb/iterator.h"
+#include "db/dbformat.h"
 #include "util/arena.h"
 #include "util/autovector.h"
-#include "util/cf_options.h"
 
 namespace rocksdb {
 
@@ -27,13 +24,14 @@ class InternalIterator;
 // Return a new iterator that converts internal keys (yielded by
 // "*internal_iter") that were live at the specified "sequence" number
 // into appropriate user keys.
-extern Iterator* NewDBIterator(
-    Env* env, const ImmutableCFOptions& options,
-    const Comparator* user_key_comparator, InternalIterator* internal_iter,
-    const SequenceNumber& sequence, uint64_t max_sequential_skip_in_iterations,
-    uint64_t version_number, const Slice* iterate_upper_bound = nullptr,
-    bool prefix_same_as_start = false, bool pin_data = false,
-    bool total_order_seek = false);
+extern Iterator* NewDBIterator(Env* env, const ImmutableCFOptions& options,
+                               const Comparator* user_key_comparator,
+                               InternalIterator* internal_iter,
+                               const SequenceNumber& sequence,
+                               uint64_t max_sequential_skip_in_iterations,
+                               const Slice* iterate_upper_bound = nullptr,
+                               bool prefix_same_as_start = false,
+                               bool pin_data = false);
 
 // A wrapper iterator which wraps DB Iterator and the arena, with which the DB
 // iterator is supposed be allocated. This class is used as an entry point of
@@ -47,7 +45,6 @@ class ArenaWrappedDBIter : public Iterator {
   // Get the arena to be used to allocate memory for DBIter to be wrapped,
   // as well as child iterators in it.
   virtual Arena* GetArena() { return &arena_; }
-  virtual RangeDelAggregator* GetRangeDelAggregator();
 
   // Set the DB Iterator to be wrapped
 
@@ -60,7 +57,6 @@ class ArenaWrappedDBIter : public Iterator {
   virtual void SeekToFirst() override;
   virtual void SeekToLast() override;
   virtual void Seek(const Slice& target) override;
-  virtual void SeekForPrev(const Slice& target) override;
   virtual void Next() override;
   virtual void Prev() override;
   virtual Slice key() const override;
@@ -68,7 +64,9 @@ class ArenaWrappedDBIter : public Iterator {
   virtual Status status() const override;
 
   void RegisterCleanup(CleanupFunction function, void* arg1, void* arg2);
-  virtual Status GetProperty(std::string prop_name, std::string* prop) override;
+  virtual Status PinData();
+  virtual Status ReleasePinnedData();
+  virtual bool IsKeyPinned() const override;
 
  private:
   DBIter* db_iter_;
@@ -79,9 +77,8 @@ class ArenaWrappedDBIter : public Iterator {
 extern ArenaWrappedDBIter* NewArenaWrappedDbIterator(
     Env* env, const ImmutableCFOptions& options,
     const Comparator* user_key_comparator, const SequenceNumber& sequence,
-    uint64_t max_sequential_skip_in_iterations, uint64_t version_number,
+    uint64_t max_sequential_skip_in_iterations,
     const Slice* iterate_upper_bound = nullptr,
-    bool prefix_same_as_start = false, bool pin_data = false,
-    bool total_order_seek = false);
+    bool prefix_same_as_start = false, bool pin_data = false);
 
 }  // namespace rocksdb

db/db_iter_test.cc

@@ -1,7 +1,7 @@
-//  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) 2014, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same directory.
 
 #include <string>
 #include <vector>
@@ -16,7 +16,7 @@
 #include "rocksdb/slice.h"
 #include "rocksdb/statistics.h"
 #include "table/iterator_wrapper.h"
-#include "table/merging_iterator.h"
+#include "table/merger.h"
 #include "util/string_util.h"
 #include "util/sync_point.h"
 #include "util/testharness.h"
@@ -117,11 +117,6 @@ class TestIterator : public InternalIterator {
     }
   }
 
-  virtual void SeekForPrev(const Slice& target) override {
-    assert(initialized_);
-    SeekForPrevImpl(target, &cmp);
-  }
-
   virtual void Next() override {
     assert(initialized_);
     if (data_.empty() || (iter_ == data_.size() - 1)) {
@@ -155,9 +150,6 @@ class TestIterator : public InternalIterator {
     return Status::OK();
   }
 
-  virtual bool IsKeyPinned() const override { return true; }
-  virtual bool IsValuePinned() const override { return true; }
-
  private:
   bool initialized_;
   bool valid_;
@@ -189,9 +181,10 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     internal_iter->AddPut("b", "val_b");
     internal_iter->Finish();
 
-    std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0));
+    std::unique_ptr<Iterator> db_iter(
+        NewDBIterator(env_, ImmutableCFOptions(options),
+                      BytewiseComparator(), internal_iter, 10,
+                      options.max_sequential_skip_in_iterations));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -222,7 +215,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0));
+        10, options.max_sequential_skip_in_iterations));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -248,8 +241,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0,
-        ro.iterate_upper_bound));
+        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -281,8 +273,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0,
-        ro.iterate_upper_bound));
+        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -317,8 +308,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0,
-        ro.iterate_upper_bound));
+        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
@@ -347,8 +337,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        7, options.max_sequential_skip_in_iterations, 0,
-        ro.iterate_upper_bound));
+        7, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
 
     SetPerfLevel(kEnableCount);
     ASSERT_TRUE(GetPerfLevel() == kEnableCount);
@@ -357,7 +346,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     db_iter->SeekToLast();
 
     ASSERT_TRUE(db_iter->Valid());
-    ASSERT_EQ(static_cast<int>(perf_context.internal_key_skipped_count), 7);
+    ASSERT_EQ(static_cast<int>(perf_context.internal_key_skipped_count), 1);
     ASSERT_EQ(db_iter->key().ToString(), "b");
 
     SetPerfLevel(kDisable);
@@ -385,8 +374,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        4, options.max_sequential_skip_in_iterations, 0,
-        ro.iterate_upper_bound));
+        4, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -411,8 +399,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0,
-        ro.iterate_upper_bound));
+        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
@@ -434,8 +421,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0,
-        ro.iterate_upper_bound));
+        10, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -470,8 +456,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        7, options.max_sequential_skip_in_iterations, 0,
-        ro.iterate_upper_bound));
+        7, options.max_sequential_skip_in_iterations, ro.iterate_upper_bound));
 
     SetPerfLevel(kEnableCount);
     ASSERT_TRUE(GetPerfLevel() == kEnableCount);
@@ -480,7 +465,7 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     db_iter->SeekToLast();
 
     ASSERT_TRUE(db_iter->Valid());
-    ASSERT_EQ(static_cast<int>(perf_context.internal_delete_skipped_count), 1);
+    ASSERT_EQ(static_cast<int>(perf_context.internal_delete_skipped_count), 0);
     ASSERT_EQ(db_iter->key().ToString(), "b");
 
     SetPerfLevel(kDisable);
@@ -497,9 +482,10 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     internal_iter->AddPut("b", "val_b");
     internal_iter->Finish();
 
-    std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0));
+    std::unique_ptr<Iterator> db_iter(
+        NewDBIterator(env_, ImmutableCFOptions(options),
+                      BytewiseComparator(), internal_iter, 10,
+                      options.max_sequential_skip_in_iterations));
 
     db_iter->SeekToFirst();
     ASSERT_TRUE(db_iter->Valid());
@@ -538,9 +524,10 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     internal_iter->AddPut("b", "val_b");
     internal_iter->Finish();
 
-    std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        2, options.max_sequential_skip_in_iterations, 0));
+    std::unique_ptr<Iterator> db_iter(
+        NewDBIterator(env_, ImmutableCFOptions(options),
+                      BytewiseComparator(), internal_iter, 2,
+                      options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -568,9 +555,10 @@ TEST_F(DBIteratorTest, DBIteratorPrevNext) {
     internal_iter->AddPut("c", "val_c");
     internal_iter->Finish();
 
-    std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0));
+    std::unique_ptr<Iterator> db_iter(
+        NewDBIterator(env_, ImmutableCFOptions(options),
+                      BytewiseComparator(), internal_iter, 10,
+                      options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -595,9 +583,10 @@ TEST_F(DBIteratorTest, DBIteratorEmpty) {
     TestIterator* internal_iter = new TestIterator(BytewiseComparator());
     internal_iter->Finish();
 
-    std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        0, options.max_sequential_skip_in_iterations, 0));
+    std::unique_ptr<Iterator> db_iter(
+        NewDBIterator(env_, ImmutableCFOptions(options),
+                      BytewiseComparator(), internal_iter, 0,
+                      options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
   }
@@ -606,9 +595,10 @@ TEST_F(DBIteratorTest, DBIteratorEmpty) {
     TestIterator* internal_iter = new TestIterator(BytewiseComparator());
     internal_iter->Finish();
 
-    std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        0, options.max_sequential_skip_in_iterations, 0));
+    std::unique_ptr<Iterator> db_iter(
+        NewDBIterator(env_, ImmutableCFOptions(options),
+                      BytewiseComparator(), internal_iter, 0,
+                      options.max_sequential_skip_in_iterations));
     db_iter->SeekToFirst();
     ASSERT_TRUE(!db_iter->Valid());
   }
@@ -627,9 +617,10 @@ TEST_F(DBIteratorTest, DBIteratorUseSkipCountSkips) {
   }
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(NewDBIterator(
-      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 2,
-      options.max_sequential_skip_in_iterations, 0));
+  std::unique_ptr<Iterator> db_iter(
+      NewDBIterator(env_, ImmutableCFOptions(options),
+                    BytewiseComparator(), internal_iter, 2,
+                    options.max_sequential_skip_in_iterations));
   db_iter->SeekToLast();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -668,8 +659,9 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
 
       options.statistics = rocksdb::CreateDBStatistics();
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options), BytewiseComparator(),
-          internal_iter, i + 2, options.max_sequential_skip_in_iterations, 0));
+          env_, ImmutableCFOptions(options),
+          BytewiseComparator(), internal_iter, i + 2,
+          options.max_sequential_skip_in_iterations));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
 
@@ -703,8 +695,9 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options), BytewiseComparator(),
-          internal_iter, i + 2, options.max_sequential_skip_in_iterations, 0));
+          env_, ImmutableCFOptions(options),
+          BytewiseComparator(), internal_iter, i + 2,
+          options.max_sequential_skip_in_iterations));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
 
@@ -731,8 +724,9 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options), BytewiseComparator(),
-          internal_iter, 202, options.max_sequential_skip_in_iterations, 0));
+          env_, ImmutableCFOptions(options),
+          BytewiseComparator(), internal_iter, 202,
+          options.max_sequential_skip_in_iterations));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
 
@@ -762,9 +756,10 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       }
       internal_iter->AddPut("c", "200");
       internal_iter->Finish();
-      std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options), BytewiseComparator(),
-          internal_iter, i, options.max_sequential_skip_in_iterations, 0));
+      std::unique_ptr<Iterator> db_iter(
+          NewDBIterator(env_, ImmutableCFOptions(options),
+                        BytewiseComparator(), internal_iter, i,
+                        options.max_sequential_skip_in_iterations));
       db_iter->SeekToLast();
       ASSERT_TRUE(!db_iter->Valid());
 
@@ -778,9 +773,10 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
     }
     internal_iter->AddPut("c", "200");
     internal_iter->Finish();
-    std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        200, options.max_sequential_skip_in_iterations, 0));
+    std::unique_ptr<Iterator> db_iter(
+        NewDBIterator(env_, ImmutableCFOptions(options),
+                      BytewiseComparator(), internal_iter, 200,
+                      options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -813,8 +809,9 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options), BytewiseComparator(),
-          internal_iter, i + 2, options.max_sequential_skip_in_iterations, 0));
+          env_, ImmutableCFOptions(options),
+          BytewiseComparator(), internal_iter, i + 2,
+          options.max_sequential_skip_in_iterations));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
 
@@ -847,8 +844,9 @@ TEST_F(DBIteratorTest, DBIteratorUseSkip) {
       internal_iter->Finish();
 
       std::unique_ptr<Iterator> db_iter(NewDBIterator(
-          env_, ImmutableCFOptions(options), BytewiseComparator(),
-          internal_iter, i + 2, options.max_sequential_skip_in_iterations, 0));
+          env_, ImmutableCFOptions(options),
+          BytewiseComparator(), internal_iter, i + 2,
+          options.max_sequential_skip_in_iterations));
       db_iter->SeekToLast();
       ASSERT_TRUE(db_iter->Valid());
 
@@ -889,7 +887,7 @@ TEST_F(DBIteratorTest, DBIterator1) {
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
       env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 1,
-      options.max_sequential_skip_in_iterations, 0));
+      options.max_sequential_skip_in_iterations));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -915,7 +913,7 @@ TEST_F(DBIteratorTest, DBIterator2) {
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
       env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 0,
-      options.max_sequential_skip_in_iterations, 0));
+      options.max_sequential_skip_in_iterations));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -938,7 +936,7 @@ TEST_F(DBIteratorTest, DBIterator3) {
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
       env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 2,
-      options.max_sequential_skip_in_iterations, 0));
+      options.max_sequential_skip_in_iterations));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -960,7 +958,7 @@ TEST_F(DBIteratorTest, DBIterator4) {
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
       env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 4,
-      options.max_sequential_skip_in_iterations, 0));
+      options.max_sequential_skip_in_iterations));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -989,7 +987,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        0, options.max_sequential_skip_in_iterations, 0));
+        0, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1011,7 +1009,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        1, options.max_sequential_skip_in_iterations, 0));
+        1, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1033,7 +1031,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        2, options.max_sequential_skip_in_iterations, 0));
+        2, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1055,7 +1053,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        3, options.max_sequential_skip_in_iterations, 0));
+        3, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1077,7 +1075,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        4, options.max_sequential_skip_in_iterations, 0));
+        4, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1099,7 +1097,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        5, options.max_sequential_skip_in_iterations, 0));
+        5, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1121,7 +1119,7 @@ TEST_F(DBIteratorTest, DBIterator5) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        6, options.max_sequential_skip_in_iterations, 0));
+        6, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1129,26 +1127,6 @@ TEST_F(DBIteratorTest, DBIterator5) {
     db_iter->Prev();
     ASSERT_TRUE(!db_iter->Valid());
   }
-
-  {
-    // put, singledelete, merge
-    TestIterator* internal_iter = new TestIterator(BytewiseComparator());
-    internal_iter->AddPut("a", "val_a");
-    internal_iter->AddSingleDeletion("a");
-    internal_iter->AddMerge("a", "merge_1");
-    internal_iter->AddMerge("a", "merge_2");
-    internal_iter->AddPut("b", "val_b");
-    internal_iter->Finish();
-    std::unique_ptr<Iterator> db_iter(NewDBIterator(
-        env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0));
-    db_iter->Seek("b");
-    ASSERT_TRUE(db_iter->Valid());
-    ASSERT_EQ(db_iter->key().ToString(), "b");
-    db_iter->Prev();
-    ASSERT_TRUE(db_iter->Valid());
-    ASSERT_EQ(db_iter->key().ToString(), "a");
-  }
 }
 
 TEST_F(DBIteratorTest, DBIterator6) {
@@ -1167,7 +1145,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        0, options.max_sequential_skip_in_iterations, 0));
+        0, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1189,7 +1167,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        1, options.max_sequential_skip_in_iterations, 0));
+        1, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1211,7 +1189,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        2, options.max_sequential_skip_in_iterations, 0));
+        2, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1233,7 +1211,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        3, options.max_sequential_skip_in_iterations, 0));
+        3, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(!db_iter->Valid());
   }
@@ -1251,7 +1229,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        4, options.max_sequential_skip_in_iterations, 0));
+        4, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1273,7 +1251,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        5, options.max_sequential_skip_in_iterations, 0));
+        5, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1295,7 +1273,7 @@ TEST_F(DBIteratorTest, DBIterator6) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        6, options.max_sequential_skip_in_iterations, 0));
+        6, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1333,7 +1311,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        0, options.max_sequential_skip_in_iterations, 0));
+        0, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1367,7 +1345,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        2, options.max_sequential_skip_in_iterations, 0));
+        2, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1407,7 +1385,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        4, options.max_sequential_skip_in_iterations, 0));
+        4, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1447,7 +1425,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        5, options.max_sequential_skip_in_iterations, 0));
+        5, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1492,7 +1470,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        6, options.max_sequential_skip_in_iterations, 0));
+        6, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1538,7 +1516,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        7, options.max_sequential_skip_in_iterations, 0));
+        7, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1578,7 +1556,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        9, options.max_sequential_skip_in_iterations, 0));
+        9, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1624,7 +1602,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        13, options.max_sequential_skip_in_iterations, 0));
+        13, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1671,7 +1649,7 @@ TEST_F(DBIteratorTest, DBIterator7) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        14, options.max_sequential_skip_in_iterations, 0));
+        14, options.max_sequential_skip_in_iterations));
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
 
@@ -1700,7 +1678,7 @@ TEST_F(DBIteratorTest, DBIterator8) {
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
       env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-      10, options.max_sequential_skip_in_iterations, 0));
+      10, options.max_sequential_skip_in_iterations));
   db_iter->SeekToLast();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "b");
@@ -1729,7 +1707,7 @@ TEST_F(DBIteratorTest, DBIterator9) {
 
     std::unique_ptr<Iterator> db_iter(NewDBIterator(
         env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-        10, options.max_sequential_skip_in_iterations, 0));
+        10, options.max_sequential_skip_in_iterations));
 
     db_iter->SeekToLast();
     ASSERT_TRUE(db_iter->Valid());
@@ -1751,15 +1729,6 @@ TEST_F(DBIteratorTest, DBIterator9) {
     ASSERT_EQ(db_iter->key().ToString(), "a");
     ASSERT_EQ(db_iter->value().ToString(), "merge_1,merge_2");
 
-    db_iter->SeekForPrev("b");
-    ASSERT_TRUE(db_iter->Valid());
-    ASSERT_EQ(db_iter->key().ToString(), "b");
-    ASSERT_EQ(db_iter->value().ToString(), "merge_3,merge_4");
-    db_iter->Next();
-    ASSERT_TRUE(db_iter->Valid());
-    ASSERT_EQ(db_iter->key().ToString(), "d");
-    ASSERT_EQ(db_iter->value().ToString(), "merge_5,merge_6");
-
     db_iter->Seek("c");
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "d");
@@ -1768,15 +1737,6 @@ TEST_F(DBIteratorTest, DBIterator9) {
     ASSERT_TRUE(db_iter->Valid());
     ASSERT_EQ(db_iter->key().ToString(), "b");
     ASSERT_EQ(db_iter->value().ToString(), "merge_3,merge_4");
-
-    db_iter->SeekForPrev("c");
-    ASSERT_TRUE(db_iter->Valid());
-    ASSERT_EQ(db_iter->key().ToString(), "b");
-    ASSERT_EQ(db_iter->value().ToString(), "merge_3,merge_4");
-    db_iter->Next();
-    ASSERT_TRUE(db_iter->Valid());
-    ASSERT_EQ(db_iter->key().ToString(), "d");
-    ASSERT_EQ(db_iter->value().ToString(), "merge_5,merge_6");
   }
 }
 
@@ -1794,7 +1754,7 @@ TEST_F(DBIteratorTest, DBIterator10) {
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
       env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
-      10, options.max_sequential_skip_in_iterations, 0));
+      10, options.max_sequential_skip_in_iterations));
 
   db_iter->Seek("c");
   ASSERT_TRUE(db_iter->Valid());
@@ -1807,18 +1767,6 @@ TEST_F(DBIteratorTest, DBIterator10) {
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "c");
   ASSERT_EQ(db_iter->value().ToString(), "3");
-
-  db_iter->SeekForPrev("c");
-  ASSERT_TRUE(db_iter->Valid());
-  db_iter->Next();
-  ASSERT_TRUE(db_iter->Valid());
-  ASSERT_EQ(db_iter->key().ToString(), "d");
-  ASSERT_EQ(db_iter->value().ToString(), "4");
-
-  db_iter->Prev();
-  ASSERT_TRUE(db_iter->Valid());
-  ASSERT_EQ(db_iter->key().ToString(), "c");
-  ASSERT_EQ(db_iter->value().ToString(), "3");
 }
 
 TEST_F(DBIteratorTest, SeekToLastOccurrenceSeq0) {
@@ -1830,9 +1778,9 @@ TEST_F(DBIteratorTest, SeekToLastOccurrenceSeq0) {
   internal_iter->AddPut("b", "2");
   internal_iter->Finish();
 
-  std::unique_ptr<Iterator> db_iter(
-      NewDBIterator(env_, ImmutableCFOptions(options), BytewiseComparator(),
-                    internal_iter, 10, 0 /* force seek */, 0));
+  std::unique_ptr<Iterator> db_iter(NewDBIterator(
+      env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter,
+      10, 0 /* force seek */));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1859,7 +1807,7 @@ TEST_F(DBIteratorTest, DBIterator11) {
 
   std::unique_ptr<Iterator> db_iter(NewDBIterator(
       env_, ImmutableCFOptions(options), BytewiseComparator(), internal_iter, 1,
-      options.max_sequential_skip_in_iterations, 0));
+      options.max_sequential_skip_in_iterations));
   db_iter->SeekToFirst();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "a");
@@ -1884,7 +1832,7 @@ TEST_F(DBIteratorTest, DBIterator12) {
 
   std::unique_ptr<Iterator> db_iter(
       NewDBIterator(env_, ImmutableCFOptions(options), BytewiseComparator(),
-                    internal_iter, 10, 0, 0));
+                    internal_iter, 10, 0));
   db_iter->SeekToLast();
   ASSERT_TRUE(db_iter->Valid());
   ASSERT_EQ(db_iter->key().ToString(), "c");
@@ -1897,66 +1845,6 @@ TEST_F(DBIteratorTest, DBIterator12) {
   ASSERT_FALSE(db_iter->Valid());
 }
 
-TEST_F(DBIteratorTest, DBIterator13) {
-  Options options;
-  options.merge_operator = nullptr;
-
-  std::string key;
-  key.resize(9);
-  key.assign(9, static_cast<char>(0));
-  key[0] = 'b';
-
-  TestIterator* internal_iter = new TestIterator(BytewiseComparator());
-  internal_iter->AddPut(key, "0");
-  internal_iter->AddPut(key, "1");
-  internal_iter->AddPut(key, "2");
-  internal_iter->AddPut(key, "3");
-  internal_iter->AddPut(key, "4");
-  internal_iter->AddPut(key, "5");
-  internal_iter->AddPut(key, "6");
-  internal_iter->AddPut(key, "7");
-  internal_iter->AddPut(key, "8");
-  internal_iter->Finish();
-
-  std::unique_ptr<Iterator> db_iter(
-      NewDBIterator(env_, ImmutableCFOptions(options), BytewiseComparator(),
-                    internal_iter, 2, 3, 0));
-  db_iter->Seek("b");
-  ASSERT_TRUE(db_iter->Valid());
-  ASSERT_EQ(db_iter->key().ToString(), key);
-  ASSERT_EQ(db_iter->value().ToString(), "2");
-}
-
-TEST_F(DBIteratorTest, DBIterator14) {
-  Options options;
-  options.merge_operator = nullptr;
-
-  std::string key("b");
-  TestIterator* internal_iter = new TestIterator(BytewiseComparator());
-  internal_iter->AddPut("b", "0");
-  internal_iter->AddPut("b", "1");
-  internal_iter->AddPut("b", "2");
-  internal_iter->AddPut("b", "3");
-  internal_iter->AddPut("a", "4");
-  internal_iter->AddPut("a", "5");
-  internal_iter->AddPut("a", "6");
-  internal_iter->AddPut("c", "7");
-  internal_iter->AddPut("c", "8");
-  internal_iter->AddPut("c", "9");
-  internal_iter->Finish();
-
-  std::unique_ptr<Iterator> db_iter(
-      NewDBIterator(env_, ImmutableCFOptions(options), BytewiseComparator(),
-                    internal_iter, 4, 1, 0));
-  db_iter->Seek("b");
-  ASSERT_TRUE(db_iter->Valid());
-  ASSERT_EQ(db_iter->key().ToString(), "b");
-  ASSERT_EQ(db_iter->value().ToString(), "3");
-  db_iter->SeekToFirst();
-  ASSERT_EQ(db_iter->key().ToString(), "a");
-  ASSERT_EQ(db_iter->value().ToString(), "4");
-}
-
 class DBIterWithMergeIterTest : public testing::Test {
  public:
   DBIterWithMergeIterTest()
@@ -1986,7 +1874,7 @@ class DBIterWithMergeIterTest : public testing::Test {
     db_iter_.reset(NewDBIterator(env_, ImmutableCFOptions(options_),
                                  BytewiseComparator(), merge_iter,
                                  8 /* read data earlier than seqId 8 */,
-                                 3 /* max iterators before reseek */, 0));
+                                 3 /* max iterators before reseek */));
   }
 
   Env* env_;
@@ -2029,7 +1917,7 @@ TEST_F(DBIterWithMergeIterTest, InnerMergeIterator1) {
 
 TEST_F(DBIterWithMergeIterTest, InnerMergeIterator2) {
   // Test Prev() when one child iterator is at its end.
-  db_iter_->SeekForPrev("g");
+  db_iter_->Seek("g");
   ASSERT_TRUE(db_iter_->Valid());
   ASSERT_EQ(db_iter_->key().ToString(), "g");
   ASSERT_EQ(db_iter_->value().ToString(), "3");

db/db_log_iter_test.cc

@@ -1,7 +1,7 @@
-//  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) 2013, Facebook, Inc.  All rights reserved.
+//  This source code is licensed under the BSD-style license found in the
+//  LICENSE file in the root directory of this source tree. An additional grant
+//  of patent rights can be found in the PATENTS file in the same 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

db/db_memtable_test.cc

@@ -1,163 +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 <memory>
-#include <string>
-
-#include "db/db_test_util.h"
-#include "db/memtable.h"
-#include "port/stack_trace.h"
-#include "rocksdb/memtablerep.h"
-#include "rocksdb/slice_transform.h"
-
-namespace rocksdb {
-
-class DBMemTableTest : public DBTestBase {
- public:
-  DBMemTableTest() : DBTestBase("/db_memtable_test") {}
-};
-
-class MockMemTableRep : public MemTableRep {
- public:
-  explicit MockMemTableRep(MemTableAllocator* allocator, MemTableRep* rep)
-      : MemTableRep(allocator), rep_(rep), num_insert_with_hint_(0) {}
-
-  virtual KeyHandle Allocate(const size_t len, char** buf) override {
-    return rep_->Allocate(len, buf);
-  }
-
-  virtual void Insert(KeyHandle handle) override {
-    return rep_->Insert(handle);
-  }
-
-  virtual void InsertWithHint(KeyHandle handle, void** hint) override {
-    num_insert_with_hint_++;
-    ASSERT_NE(nullptr, hint);
-    last_hint_in_ = *hint;
-    rep_->InsertWithHint(handle, hint);
-    last_hint_out_ = *hint;
-  }
-
-  virtual bool Contains(const char* key) const override {
-    return rep_->Contains(key);
-  }
-
-  virtual void Get(const LookupKey& k, void* callback_args,
-                   bool (*callback_func)(void* arg,
-                                         const char* entry)) override {
-    rep_->Get(k, callback_args, callback_func);
-  }
-
-  virtual size_t ApproximateMemoryUsage() override {
-    return rep_->ApproximateMemoryUsage();
-  }
-
-  virtual Iterator* GetIterator(Arena* arena) override {
-    return rep_->GetIterator(arena);
-  }
-
-  void* last_hint_in() { return last_hint_in_; }
-  void* last_hint_out() { return last_hint_out_; }
-  int num_insert_with_hint() { return num_insert_with_hint_; }
-
- private:
-  std::unique_ptr<MemTableRep> rep_;
-  void* last_hint_in_;
-  void* last_hint_out_;
-  int num_insert_with_hint_;
-};
-
-class MockMemTableRepFactory : public MemTableRepFactory {
- public:
-  virtual MemTableRep* CreateMemTableRep(const MemTableRep::KeyComparator& cmp,
-                                         MemTableAllocator* allocator,
-                                         const SliceTransform* transform,
-                                         Logger* logger) override {
-    SkipListFactory factory;
-    MemTableRep* skiplist_rep =
-        factory.CreateMemTableRep(cmp, allocator, transform, logger);
-    mock_rep_ = new MockMemTableRep(allocator, skiplist_rep);
-    return mock_rep_;
-  }
-
-  virtual const char* Name() const override { return "MockMemTableRepFactory"; }
-
-  MockMemTableRep* rep() { return mock_rep_; }
-
-  bool IsInsertConcurrentlySupported() const override { return false; }
-
- private:
-  MockMemTableRep* mock_rep_;
-};
-
-class TestPrefixExtractor : public SliceTransform {
- public:
-  virtual const char* Name() const override { return "TestPrefixExtractor"; }
-
-  virtual Slice Transform(const Slice& key) const override {
-    const char* p = separator(key);
-    if (p == nullptr) {
-      return Slice();
-    }
-    return Slice(key.data(), p - key.data() + 1);
-  }
-
-  virtual bool InDomain(const Slice& key) const override {
-    return separator(key) != nullptr;
-  }
-
-  virtual bool InRange(const Slice& key) const override { return false; }
-
- private:
-  const char* separator(const Slice& key) const {
-    return reinterpret_cast<const char*>(memchr(key.data(), '_', key.size()));
-  }
-};
-
-TEST_F(DBMemTableTest, InsertWithHint) {
-  Options options;
-  options.allow_concurrent_memtable_write = false;
-  options.create_if_missing = true;
-  options.memtable_factory.reset(new MockMemTableRepFactory());
-  options.memtable_insert_with_hint_prefix_extractor.reset(
-      new TestPrefixExtractor());
-  Reopen(options);
-  MockMemTableRep* rep =
-      reinterpret_cast<MockMemTableRepFactory*>(options.memtable_factory.get())
-          ->rep();
-  ASSERT_OK(Put("foo_k1", "foo_v1"));
-  ASSERT_EQ(nullptr, rep->last_hint_in());
-  void* hint_foo = rep->last_hint_out();
-  ASSERT_OK(Put("foo_k2", "foo_v2"));
-  ASSERT_EQ(hint_foo, rep->last_hint_in());
-  ASSERT_EQ(hint_foo, rep->last_hint_out());
-  ASSERT_OK(Put("foo_k3", "foo_v3"));
-  ASSERT_EQ(hint_foo, rep->last_hint_in());
-  ASSERT_EQ(hint_foo, rep->last_hint_out());
-  ASSERT_OK(Put("bar_k1", "bar_v1"));
-  ASSERT_EQ(nullptr, rep->last_hint_in());
-  void* hint_bar = rep->last_hint_out();
-  ASSERT_NE(hint_foo, hint_bar);
-  ASSERT_OK(Put("bar_k2", "bar_v2"));
-  ASSERT_EQ(hint_bar, rep->last_hint_in());
-  ASSERT_EQ(hint_bar, rep->last_hint_out());
-  ASSERT_EQ(5, rep->num_insert_with_hint());
-  ASSERT_OK(Put("whitelisted", "vvv"));
-  ASSERT_EQ(5, rep->num_insert_with_hint());
-  ASSERT_EQ("foo_v1", Get("foo_k1"));
-  ASSERT_EQ("foo_v2", Get("foo_k2"));
-  ASSERT_EQ("foo_v3", Get("foo_k3"));
-  ASSERT_EQ("bar_v1", Get("bar_k1"));
-  ASSERT_EQ("bar_v2", Get("bar_k2"));
-  ASSERT_EQ("vvv", Get("whitelisted"));
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_merge_operator_test.cc

@@ -1,98 +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 <string>
-#include <vector>
-
-#include "db/db_test_util.h"
-#include "db/forward_iterator.h"
-#include "port/stack_trace.h"
-#include "utilities/merge_operators.h"
-
-namespace rocksdb {
-
-// Test merge operator functionality.
-class DBMergeOperatorTest : public DBTestBase {
- public:
-  DBMergeOperatorTest() : DBTestBase("/db_merge_operator_test") {}
-};
-
-// A test merge operator mimics put but also fails if one of merge operands is
-// "corrupted".
-class TestPutOperator : public MergeOperator {
- public:
-  virtual bool FullMergeV2(const MergeOperationInput& merge_in,
-                           MergeOperationOutput* merge_out) const override {
-    if (merge_in.existing_value != nullptr &&
-        *(merge_in.existing_value) == "corrupted") {
-      return false;
-    }
-    for (auto value : merge_in.operand_list) {
-      if (value == "corrupted") {
-        return false;
-      }
-    }
-    merge_out->existing_operand = merge_in.operand_list.back();
-    return true;
-  }
-
-  virtual const char* Name() const override { return "TestPutOperator"; }
-};
-
-TEST_F(DBMergeOperatorTest, MergeErrorOnRead) {
-  Options options;
-  options.create_if_missing = true;
-  options.merge_operator.reset(new TestPutOperator());
-  Reopen(options);
-  ASSERT_OK(Merge("k1", "v1"));
-  ASSERT_OK(Merge("k1", "corrupted"));
-  std::string value;
-  ASSERT_TRUE(db_->Get(ReadOptions(), "k1", &value).IsCorruption());
-  VerifyDBInternal({{"k1", "corrupted"}, {"k1", "v1"}});
-}
-
-TEST_F(DBMergeOperatorTest, MergeErrorOnWrite) {
-  Options options;
-  options.create_if_missing = true;
-  options.merge_operator.reset(new TestPutOperator());
-  options.max_successive_merges = 3;
-  Reopen(options);
-  ASSERT_OK(Merge("k1", "v1"));
-  ASSERT_OK(Merge("k1", "v2"));
-  // Will trigger a merge when hitting max_successive_merges and the merge
-  // will fail. The delta will be inserted nevertheless.
-  ASSERT_OK(Merge("k1", "corrupted"));
-  // Data should stay unmerged after the error.
-  VerifyDBInternal({{"k1", "corrupted"}, {"k1", "v2"}, {"k1", "v1"}});
-}
-
-TEST_F(DBMergeOperatorTest, MergeErrorOnIteration) {
-  Options options;
-  options.create_if_missing = true;
-  options.merge_operator.reset(new TestPutOperator());
-
-  DestroyAndReopen(options);
-  ASSERT_OK(Merge("k1", "v1"));
-  ASSERT_OK(Merge("k1", "corrupted"));
-  ASSERT_OK(Put("k2", "v2"));
-  VerifyDBFromMap({{"k1", ""}, {"k2", "v2"}}, nullptr, false,
-                  {{"k1", Status::Corruption()}});
-  VerifyDBInternal({{"k1", "corrupted"}, {"k1", "v1"}, {"k2", "v2"}});
-
-  DestroyAndReopen(options);
-  ASSERT_OK(Merge("k1", "v1"));
-  ASSERT_OK(Put("k2", "v2"));
-  ASSERT_OK(Merge("k2", "corrupted"));
-  VerifyDBFromMap({{"k1", "v1"}, {"k2", ""}}, nullptr, false,
-                  {{"k2", Status::Corruption()}});
-  VerifyDBInternal({{"k1", "v1"}, {"k2", "corrupted"}, {"k2", "v2"}});
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_options_test.cc

@@ -1,368 +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 <limits>
-#include <string>
-#include <unordered_map>
-
-#include "db/column_family.h"
-#include "db/db_impl.h"
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-#include "rocksdb/convenience.h"
-#include "util/options_helper.h"
-#include "util/random.h"
-#include "util/sync_point.h"
-#include "util/testutil.h"
-
-namespace rocksdb {
-
-class DBOptionsTest : public DBTestBase {
- public:
-  DBOptionsTest() : DBTestBase("/db_options_test") {}
-
-#ifndef ROCKSDB_LITE
-  std::unordered_map<std::string, std::string> GetMutableDBOptionsMap(
-      const DBOptions& options) {
-    std::string options_str;
-    GetStringFromDBOptions(&options_str, options);
-    std::unordered_map<std::string, std::string> options_map;
-    StringToMap(options_str, &options_map);
-    std::unordered_map<std::string, std::string> mutable_map;
-    for (const auto opt : db_options_type_info) {
-      if (opt.second.is_mutable &&
-          opt.second.verification != OptionVerificationType::kDeprecated) {
-        mutable_map[opt.first] = options_map[opt.first];
-      }
-    }
-    return mutable_map;
-  }
-
-  std::unordered_map<std::string, std::string> GetMutableCFOptionsMap(
-      const ColumnFamilyOptions& options) {
-    std::string options_str;
-    GetStringFromColumnFamilyOptions(&options_str, options);
-    std::unordered_map<std::string, std::string> options_map;
-    StringToMap(options_str, &options_map);
-    std::unordered_map<std::string, std::string> mutable_map;
-    for (const auto opt : cf_options_type_info) {
-      if (opt.second.is_mutable &&
-          opt.second.verification != OptionVerificationType::kDeprecated) {
-        mutable_map[opt.first] = options_map[opt.first];
-      }
-    }
-    return mutable_map;
-  }
-
-  std::unordered_map<std::string, std::string> GetRandomizedMutableCFOptionsMap(
-      Random* rnd) {
-    Options options;
-    ImmutableDBOptions db_options(options);
-    test::RandomInitCFOptions(&options, rnd);
-    auto sanitized_options = SanitizeOptions(db_options, options);
-    auto opt_map = GetMutableCFOptionsMap(sanitized_options);
-    delete options.compaction_filter;
-    return opt_map;
-  }
-
-  std::unordered_map<std::string, std::string> GetRandomizedMutableDBOptionsMap(
-      Random* rnd) {
-    DBOptions db_options;
-    test::RandomInitDBOptions(&db_options, rnd);
-    auto sanitized_options = SanitizeOptions(dbname_, db_options);
-    return GetMutableDBOptionsMap(sanitized_options);
-  }
-#endif  // ROCKSDB_LITE
-};
-
-// RocksDB lite don't support dynamic options.
-#ifndef ROCKSDB_LITE
-
-TEST_F(DBOptionsTest, GetLatestDBOptions) {
-  // GetOptions should be able to get latest option changed by SetOptions.
-  Options options;
-  options.create_if_missing = true;
-  Random rnd(228);
-  Reopen(options);
-  auto new_options = GetRandomizedMutableDBOptionsMap(&rnd);
-  ASSERT_OK(dbfull()->SetDBOptions(new_options));
-  ASSERT_EQ(new_options, GetMutableDBOptionsMap(dbfull()->GetDBOptions()));
-}
-
-TEST_F(DBOptionsTest, GetLatestCFOptions) {
-  // GetOptions should be able to get latest option changed by SetOptions.
-  Options options;
-  options.create_if_missing = true;
-  Random rnd(228);
-  Reopen(options);
-  CreateColumnFamilies({"foo"}, options);
-  ReopenWithColumnFamilies({"default", "foo"}, options);
-  auto options_default = GetRandomizedMutableCFOptionsMap(&rnd);
-  auto options_foo = GetRandomizedMutableCFOptionsMap(&rnd);
-  ASSERT_OK(dbfull()->SetOptions(handles_[0], options_default));
-  ASSERT_OK(dbfull()->SetOptions(handles_[1], options_foo));
-  ASSERT_EQ(options_default,
-            GetMutableCFOptionsMap(dbfull()->GetOptions(handles_[0])));
-  ASSERT_EQ(options_foo,
-            GetMutableCFOptionsMap(dbfull()->GetOptions(handles_[1])));
-}
-
-TEST_F(DBOptionsTest, SetOptionsAndReopen) {
-  Random rnd(1044);
-  auto rand_opts = GetRandomizedMutableCFOptionsMap(&rnd);
-  ASSERT_OK(dbfull()->SetOptions(rand_opts));
-  // Verify if DB can be reopen after setting options.
-  Options options;
-  ASSERT_OK(TryReopen(options));
-}
-
-TEST_F(DBOptionsTest, EnableAutoCompactionAndTriggerStall) {
-  const std::string kValue(1024, 'v');
-  for (int method_type = 0; method_type < 2; method_type++) {
-    for (int option_type = 0; option_type < 4; option_type++) {
-      Options options;
-      options.create_if_missing = true;
-      options.disable_auto_compactions = true;
-      options.write_buffer_size = 1024 * 1024 * 10;
-      options.compression = CompressionType::kNoCompression;
-      options.level0_file_num_compaction_trigger = 1;
-      options.level0_stop_writes_trigger = std::numeric_limits<int>::max();
-      options.level0_slowdown_writes_trigger = std::numeric_limits<int>::max();
-      options.hard_pending_compaction_bytes_limit =
-          std::numeric_limits<uint64_t>::max();
-      options.soft_pending_compaction_bytes_limit =
-          std::numeric_limits<uint64_t>::max();
-
-      DestroyAndReopen(options);
-      int i = 0;
-      for (; i < 1024; i++) {
-        Put(Key(i), kValue);
-      }
-      Flush();
-      for (; i < 1024 * 2; i++) {
-        Put(Key(i), kValue);
-      }
-      Flush();
-      dbfull()->TEST_WaitForFlushMemTable();
-      ASSERT_EQ(2, NumTableFilesAtLevel(0));
-      uint64_t l0_size = SizeAtLevel(0);
-
-      switch (option_type) {
-        case 0:
-          // test with level0_stop_writes_trigger
-          options.level0_stop_writes_trigger = 2;
-          options.level0_slowdown_writes_trigger = 2;
-          break;
-        case 1:
-          options.level0_slowdown_writes_trigger = 2;
-          break;
-        case 2:
-          options.hard_pending_compaction_bytes_limit = l0_size;
-          options.soft_pending_compaction_bytes_limit = l0_size;
-          break;
-        case 3:
-          options.soft_pending_compaction_bytes_limit = l0_size;
-          break;
-      }
-      Reopen(options);
-      dbfull()->TEST_WaitForCompact();
-      ASSERT_FALSE(dbfull()->TEST_write_controler().IsStopped());
-      ASSERT_FALSE(dbfull()->TEST_write_controler().NeedsDelay());
-
-      SyncPoint::GetInstance()->LoadDependency(
-          {{"DBOptionsTest::EnableAutoCompactionAndTriggerStall:1",
-            "BackgroundCallCompaction:0"},
-           {"DBImpl::BackgroundCompaction():BeforePickCompaction",
-            "DBOptionsTest::EnableAutoCompactionAndTriggerStall:2"},
-           {"DBOptionsTest::EnableAutoCompactionAndTriggerStall:3",
-            "DBImpl::BackgroundCompaction():AfterPickCompaction"}});
-      // Block background compaction.
-      SyncPoint::GetInstance()->EnableProcessing();
-
-      switch (method_type) {
-        case 0:
-          ASSERT_OK(
-              dbfull()->SetOptions({{"disable_auto_compactions", "false"}}));
-          break;
-        case 1:
-          ASSERT_OK(dbfull()->EnableAutoCompaction(
-              {dbfull()->DefaultColumnFamily()}));
-          break;
-      }
-      TEST_SYNC_POINT("DBOptionsTest::EnableAutoCompactionAndTriggerStall:1");
-      // Wait for stall condition recalculate.
-      TEST_SYNC_POINT("DBOptionsTest::EnableAutoCompactionAndTriggerStall:2");
-
-      switch (option_type) {
-        case 0:
-          ASSERT_TRUE(dbfull()->TEST_write_controler().IsStopped());
-          break;
-        case 1:
-          ASSERT_FALSE(dbfull()->TEST_write_controler().IsStopped());
-          ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
-          break;
-        case 2:
-          ASSERT_TRUE(dbfull()->TEST_write_controler().IsStopped());
-          break;
-        case 3:
-          ASSERT_FALSE(dbfull()->TEST_write_controler().IsStopped());
-          ASSERT_TRUE(dbfull()->TEST_write_controler().NeedsDelay());
-          break;
-      }
-      TEST_SYNC_POINT("DBOptionsTest::EnableAutoCompactionAndTriggerStall:3");
-
-      // Background compaction executed.
-      dbfull()->TEST_WaitForCompact();
-      ASSERT_FALSE(dbfull()->TEST_write_controler().IsStopped());
-      ASSERT_FALSE(dbfull()->TEST_write_controler().NeedsDelay());
-    }
-  }
-}
-
-TEST_F(DBOptionsTest, SetOptionsMayTriggerCompaction) {
-  Options options;
-  options.create_if_missing = true;
-  options.level0_file_num_compaction_trigger = 1000;
-  Reopen(options);
-  for (int i = 0; i < 3; i++) {
-    // Need to insert two keys to avoid trivial move.
-    ASSERT_OK(Put("foo", ToString(i)));
-    ASSERT_OK(Put("bar", ToString(i)));
-    Flush();
-  }
-  ASSERT_EQ("3", FilesPerLevel());
-  ASSERT_OK(
-      dbfull()->SetOptions({{"level0_file_num_compaction_trigger", "3"}}));
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ("0,1", FilesPerLevel());
-}
-
-TEST_F(DBOptionsTest, SetBackgroundCompactionThreads) {
-  Options options;
-  options.create_if_missing = true;
-  options.base_background_compactions = 1;  // default value
-  options.max_background_compactions = 1;   // default value
-  Reopen(options);
-  ASSERT_EQ(1, dbfull()->TEST_BGCompactionsAllowed());
-  ASSERT_OK(dbfull()->SetDBOptions({{"base_background_compactions", "2"},
-                                    {"max_background_compactions", "3"}}));
-  ASSERT_EQ(2, dbfull()->TEST_BGCompactionsAllowed());
-  auto stop_token = dbfull()->TEST_write_controler().GetStopToken();
-  ASSERT_EQ(3, dbfull()->TEST_BGCompactionsAllowed());
-}
-
-TEST_F(DBOptionsTest, AvoidFlushDuringShutdown) {
-  Options options;
-  options.create_if_missing = true;
-  options.disable_auto_compactions = true;
-  WriteOptions write_without_wal;
-  write_without_wal.disableWAL = true;
-
-  ASSERT_FALSE(options.avoid_flush_during_shutdown);
-  DestroyAndReopen(options);
-  ASSERT_OK(Put("foo", "v1", write_without_wal));
-  Reopen(options);
-  ASSERT_EQ("v1", Get("foo"));
-  ASSERT_EQ("1", FilesPerLevel());
-
-  DestroyAndReopen(options);
-  ASSERT_OK(Put("foo", "v2", write_without_wal));
-  ASSERT_OK(dbfull()->SetDBOptions({{"avoid_flush_during_shutdown", "true"}}));
-  Reopen(options);
-  ASSERT_EQ("NOT_FOUND", Get("foo"));
-  ASSERT_EQ("", FilesPerLevel());
-}
-
-TEST_F(DBOptionsTest, SetDelayedWriteRateOption) {
-  Options options;
-  options.create_if_missing = true;
-  options.delayed_write_rate = 2 * 1024U * 1024U;
-  Reopen(options);
-  ASSERT_EQ(2 * 1024U * 1024U, dbfull()->TEST_write_controler().max_delayed_write_rate());
-
-  ASSERT_OK(dbfull()->SetDBOptions({{"delayed_write_rate", "20000"}}));
-  ASSERT_EQ(20000, dbfull()->TEST_write_controler().max_delayed_write_rate());
-}
-
-TEST_F(DBOptionsTest, MaxTotalWalSizeChange) {
-  Random rnd(1044);
-  const auto value_size = size_t(1024);
-  std::string value;
-  test::RandomString(&rnd, value_size, &value);
-
-  Options options;
-  options.create_if_missing = true;
-  CreateColumnFamilies({"1", "2", "3"}, options);
-  ReopenWithColumnFamilies({"default", "1", "2", "3"}, options);
-
-  WriteOptions write_options;
-
-  const int key_count = 100;
-  for (int i = 0; i < key_count; ++i) {
-    for (size_t cf = 0; cf < handles_.size(); ++cf) {
-      ASSERT_OK(Put(static_cast<int>(cf), Key(i), value));
-    }
-  }
-  ASSERT_OK(dbfull()->SetDBOptions({{"max_total_wal_size", "10"}}));
-
-  for (size_t cf = 0; cf < handles_.size(); ++cf) {
-    dbfull()->TEST_WaitForFlushMemTable(handles_[cf]);
-    ASSERT_EQ("1", FilesPerLevel(static_cast<int>(cf)));
-  }
-}
-
-static void assert_candidate_files_empty(DBImpl* dbfull, const bool empty) {
-  dbfull->TEST_LockMutex();
-  JobContext job_context(0);
-  dbfull->FindObsoleteFiles(&job_context, false);
-  ASSERT_EQ(empty, job_context.full_scan_candidate_files.empty());
-  job_context.Clean();
-  dbfull->TEST_UnlockMutex();
-}
-
-TEST_F(DBOptionsTest, DeleteObsoleteFilesPeriodChange) {
-  SpecialEnv env(Env::Default());
-  env.time_elapse_only_sleep_ = true;
-  Options options;
-  options.env = &env;
-  options.create_if_missing = true;
-  ASSERT_OK(TryReopen(options));
-
-  // Verify that candidate files set is empty when no full scan requested.
-  assert_candidate_files_empty(dbfull(), true);
-
-  ASSERT_OK(
-      dbfull()->SetDBOptions({{"delete_obsolete_files_period_micros", "0"}}));
-
-  // After delete_obsolete_files_period_micros updated to 0, the next call
-  // to FindObsoleteFiles should make a full scan
-  assert_candidate_files_empty(dbfull(), false);
-
-  ASSERT_OK(
-      dbfull()->SetDBOptions({{"delete_obsolete_files_period_micros", "20"}}));
-
-  assert_candidate_files_empty(dbfull(), true);
-
-  env.addon_time_.store(20);
-  assert_candidate_files_empty(dbfull(), true);
-
-  env.addon_time_.store(21);
-  assert_candidate_files_empty(dbfull(), false);
-
-  Close();
-}
-
-#endif  // ROCKSDB_LITE
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}