You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
rocksdb/CMakeLists.txt

1432 lines
49 KiB

# Prerequisites for Windows:
# 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.
# 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.
#
# To build Rocksdb for Windows is as easy as 1-2-3-4-5:
#
# 1. Update paths to third-party libraries in thirdparty.inc file
# 2. Create a new directory for build artifacts
# mkdir build
# cd build
# 3. Run cmake to generate project files for Windows, add more options to enable required third-party libraries.
# See thirdparty.inc for more information.
# sample command: cmake -G "Visual Studio 15 Win64" -DCMAKE_BUILD_TYPE=Release -DWITH_GFLAGS=1 -DWITH_SNAPPY=1 -DWITH_JEMALLOC=1 -DWITH_JNI=1 ..
# 4. Then build the project in debug mode (you may want to add /m[:<N>] flag to run msbuild in <N> parallel threads
# or simply /m to use all avail cores)
# msbuild rocksdb.sln
#
# rocksdb.sln build features exclusions of test only code in Release. If you build ALL_BUILD then everything
# will be attempted but test only code does not build in Release mode.
#
# 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 3.10)
list(APPEND CMAKE_MODULE_PATH "${CMAKE_CURRENT_LIST_DIR}/cmake/modules/")
include(ReadVersion)
include(GoogleTest)
get_rocksdb_version(rocksdb_VERSION)
project(rocksdb
VERSION ${rocksdb_VERSION}
LANGUAGES CXX C ASM)
if(POLICY CMP0042)
cmake_policy(SET CMP0042 NEW)
endif()
if(NOT CMAKE_BUILD_TYPE)
if(EXISTS "${CMAKE_SOURCE_DIR}/.git")
set(default_build_type "Debug")
else()
set(default_build_type "RelWithDebInfo")
endif()
set(CMAKE_BUILD_TYPE "${default_build_type}" CACHE STRING
"Default BUILD_TYPE is ${default_build_type}" FORCE)
endif()
find_program(CCACHE_FOUND ccache)
if(CCACHE_FOUND)
set_property(GLOBAL PROPERTY RULE_LAUNCH_COMPILE ccache)
set_property(GLOBAL PROPERTY RULE_LAUNCH_LINK ccache)
endif(CCACHE_FOUND)
option(WITH_JEMALLOC "build with JeMalloc" OFF)
option(WITH_LIBURING "build with liburing" ON)
option(WITH_SNAPPY "build with SNAPPY" OFF)
option(WITH_LZ4 "build with lz4" OFF)
option(WITH_ZLIB "build with zlib" OFF)
option(WITH_ZSTD "build with zstd" OFF)
option(WITH_WINDOWS_UTF8_FILENAMES "use UTF8 as characterset for opening files, regardles of the system code page" OFF)
if (WITH_WINDOWS_UTF8_FILENAMES)
add_definitions(-DROCKSDB_WINDOWS_UTF8_FILENAMES)
endif()
if ($ENV{CIRCLECI})
message(STATUS "Build for CircieCI env, a few tests may be disabled")
add_definitions(-DCIRCLECI)
endif()
# third-party/folly is only validated to work on Linux and Windows for now.
# So only turn it on there by default.
if(CMAKE_SYSTEM_NAME MATCHES "Linux|Windows")
if(MSVC AND MSVC_VERSION LESS 1910)
# Folly does not compile with MSVC older than VS2017
option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
else()
option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" ON)
endif()
else()
option(WITH_FOLLY_DISTRIBUTED_MUTEX "build with folly::DistributedMutex" OFF)
endif()
if( NOT DEFINED CMAKE_CXX_STANDARD )
set(CMAKE_CXX_STANDARD 11)
endif()
include(CMakeDependentOption)
if(MSVC)
option(WITH_GFLAGS "build with GFlags" OFF)
option(WITH_XPRESS "build with windows built in compression" OFF)
include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
else()
if(CMAKE_SYSTEM_NAME MATCHES "FreeBSD" AND NOT CMAKE_SYSTEM_NAME MATCHES "kFreeBSD")
# FreeBSD has jemalloc as default malloc
# but it does not have all the jemalloc files in include/...
set(WITH_JEMALLOC ON)
else()
if(WITH_JEMALLOC)
find_package(JeMalloc REQUIRED)
add_definitions(-DROCKSDB_JEMALLOC -DJEMALLOC_NO_DEMANGLE)
list(APPEND THIRDPARTY_LIBS JeMalloc::JeMalloc)
endif()
endif()
Fix race condition causing double deletion of ssts Summary: Possible interleaved execution of background compaction thread calling `FindObsoleteFiles (no full scan) / PurgeObsoleteFiles` and user thread calling `FindObsoleteFiles (full scan) / PurgeObsoleteFiles` can lead to race condition on which RocksDB attempts to delete a file twice. The second attempt will fail and return `IO error`. This may occur to other files, but this PR targets sst. Also add a unit test to verify that this PR fixes the issue. The newly added unit test `obsolete_files_test` has a test case for this scenario, implemented in `ObsoleteFilesTest#RaceForObsoleteFileDeletion`. `TestSyncPoint`s are used to coordinate the interleaving the `user_thread` and background compaction thread. They execute as follows ``` timeline user_thread background_compaction thread t1 | FindObsoleteFiles(full_scan=false) t2 | FindObsoleteFiles(full_scan=true) t3 | PurgeObsoleteFiles t4 | PurgeObsoleteFiles V ``` When `user_thread` invokes `FindObsoleteFiles` with full scan, it collects ALL files in RocksDB directory, including the ones that background compaction thread have collected in its job context. Then `user_thread` will see an IO error when trying to delete these files in `PurgeObsoleteFiles` because background compaction thread has already deleted the file in `PurgeObsoleteFiles`. To fix this, we make RocksDB remember which (SST) files have been found by threads after calling `FindObsoleteFiles` (see `DBImpl#files_grabbed_for_purge_`). Therefore, when another thread calls `FindObsoleteFiles` with full scan, it will not collect such files. ajkr could you take a look and comment? Thanks! Closes https://github.com/facebook/rocksdb/pull/3638 Differential Revision: D7384372 Pulled By: riversand963 fbshipit-source-id: 01489516d60012e722ee65a80e1449e589ce26d3
7 years ago
if(MINGW)
option(WITH_GFLAGS "build with GFlags" OFF)
else()
option(WITH_GFLAGS "build with GFlags" ON)
endif()
set(GFLAGS_LIB)
if(WITH_GFLAGS)
# Config with namespace available since gflags 2.2.2
option(GFLAGS_USE_TARGET_NAMESPACE "Use gflags import target with namespace." ON)
find_package(gflags CONFIG)
if(gflags_FOUND)
if(TARGET ${GFLAGS_TARGET})
# Config with GFLAGS_TARGET available since gflags 2.2.0
set(GFLAGS_LIB ${GFLAGS_TARGET})
else()
# Config with GFLAGS_LIBRARIES available since gflags 2.1.0
set(GFLAGS_LIB ${gflags_LIBRARIES})
endif()
else()
find_package(gflags REQUIRED)
set(GFLAGS_LIB gflags::gflags)
endif()
include_directories(${GFLAGS_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS ${GFLAGS_LIB})
add_definitions(-DGFLAGS=1)
endif()
if(WITH_SNAPPY)
find_package(Snappy CONFIG)
if(NOT Snappy_FOUND)
find_package(Snappy REQUIRED)
endif()
add_definitions(-DSNAPPY)
list(APPEND THIRDPARTY_LIBS Snappy::snappy)
endif()
if(WITH_ZLIB)
find_package(ZLIB REQUIRED)
add_definitions(-DZLIB)
list(APPEND THIRDPARTY_LIBS ZLIB::ZLIB)
endif()
option(WITH_BZ2 "build with bzip2" OFF)
if(WITH_BZ2)
find_package(BZip2 REQUIRED)
add_definitions(-DBZIP2)
if(BZIP2_INCLUDE_DIRS)
include_directories(${BZIP2_INCLUDE_DIRS})
else()
include_directories(${BZIP2_INCLUDE_DIR})
endif()
list(APPEND THIRDPARTY_LIBS ${BZIP2_LIBRARIES})
endif()
if(WITH_LZ4)
find_package(lz4 REQUIRED)
add_definitions(-DLZ4)
list(APPEND THIRDPARTY_LIBS lz4::lz4)
endif()
if(WITH_ZSTD)
find_package(zstd REQUIRED)
add_definitions(-DZSTD)
include_directories(${ZSTD_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS zstd::zstd)
endif()
endif()
string(TIMESTAMP TS "%Y-%m-%d %H:%M:%S" UTC)
set(BUILD_DATE "${TS}" CACHE STRING "the time we first built rocksdb")
find_package(Git)
if(GIT_FOUND AND EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/.git")
execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_SHA COMMAND "${GIT_EXECUTABLE}" rev-parse HEAD )
execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" RESULT_VARIABLE GIT_MOD COMMAND "${GIT_EXECUTABLE}" diff-index HEAD --quiet)
execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_DATE COMMAND "${GIT_EXECUTABLE}" log -1 --date=format:"%Y-%m-%d %T" --format="%ad")
execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_TAG RESULT_VARIABLE rv COMMAND "${GIT_EXECUTABLE}" symbolic-ref -q --short HEAD OUTPUT_STRIP_TRAILING_WHITESPACE)
if (rv AND NOT rv EQUAL 0)
execute_process(WORKING_DIRECTORY "${CMAKE_CURRENT_SOURCE_DIR}" OUTPUT_VARIABLE GIT_TAG COMMAND "${GIT_EXECUTABLE}" describe --tags --exact-match OUTPUT_STRIP_TRAILING_WHITESPACE)
endif()
else()
set(GIT_SHA 0)
set(GIT_MOD 1)
endif()
string(REGEX REPLACE "[^0-9a-fA-F]+" "" GIT_SHA "${GIT_SHA}")
string(REGEX REPLACE "[^0-9: /-]+" "" GIT_DATE "${GIT_DATE}")
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
option(WITH_MD_LIBRARY "build with MD" ON)
if(WIN32 AND MSVC)
if(WITH_MD_LIBRARY)
set(RUNTIME_LIBRARY "MD")
else()
set(RUNTIME_LIBRARY "MT")
endif()
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
endif()
set(BUILD_VERSION_CC ${CMAKE_BINARY_DIR}/build_version.cc)
configure_file(util/build_version.cc.in ${BUILD_VERSION_CC} @ONLY)
if(MSVC)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /Zi /nologo /EHsc /GS /Gd /GR /GF /fp:precise /Zc:wchar_t /Zc:forScope /errorReport:queue")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /FC /d2Zi+ /W4 /wd4127 /wd4800 /wd4996 /wd4351 /wd4100 /wd4204 /wd4324")
else()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -W -Wextra -Wall -pthread")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wsign-compare -Wshadow -Wno-unused-parameter -Wno-unused-variable -Woverloaded-virtual -Wnon-virtual-dtor -Wno-missing-field-initializers -Wno-strict-aliasing")
if(CMAKE_SYSTEM_PROCESSOR MATCHES "x86_64")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -Wstrict-prototypes")
endif()
if(MINGW)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-format -fno-asynchronous-unwind-tables")
add_definitions(-D_POSIX_C_SOURCE=1)
endif()
if(NOT CMAKE_BUILD_TYPE STREQUAL "Debug")
set(CMAKE_CXX_FLAGS "${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 "${CMAKE_CXX_FLAGS} -momit-leaf-frame-pointer")
endif()
endif()
endif()
include(CheckCCompilerFlag)
if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
CHECK_C_COMPILER_FLAG("-mcpu=power9" HAS_POWER9)
if(HAS_POWER9)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcpu=power9 -mtune=power9")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=power9 -mtune=power9")
else()
CHECK_C_COMPILER_FLAG("-mcpu=power8" HAS_POWER8)
if(HAS_POWER8)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mcpu=power8 -mtune=power8")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mcpu=power8 -mtune=power8")
endif(HAS_POWER8)
endif(HAS_POWER9)
CHECK_C_COMPILER_FLAG("-maltivec" HAS_ALTIVEC)
if(HAS_ALTIVEC)
message(STATUS " HAS_ALTIVEC yes")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -maltivec")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -maltivec")
endif(HAS_ALTIVEC)
endif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
if(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64|aarch64|AARCH64")
CHECK_C_COMPILER_FLAG("-march=armv8-a+crc+crypto" HAS_ARMV8_CRC)
if(HAS_ARMV8_CRC)
message(STATUS " HAS_ARMV8_CRC yes")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv8-a+crc+crypto -Wno-unused-function")
endif(HAS_ARMV8_CRC)
endif(CMAKE_SYSTEM_PROCESSOR MATCHES "arm64|aarch64|AARCH64")
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
option(PORTABLE "build a portable binary" OFF)
option(FORCE_SSE42 "force building with SSE4.2, even when PORTABLE=ON" OFF)
option(FORCE_AVX "force building with AVX, even when PORTABLE=ON" OFF)
option(FORCE_AVX2 "force building with AVX2, even when PORTABLE=ON" OFF)
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
if(PORTABLE)
# MSVC does not need a separate compiler flag to enable SSE4.2; if nmmintrin.h
# is available, it is available by default.
if(FORCE_SSE42 AND NOT MSVC)
Port 3 way SSE4.2 crc32c implementation from Folly Summary: **# Summary** RocksDB uses SSE crc32 intrinsics to calculate the crc32 values but it does it in single way fashion (not pipelined on single CPU core). Intel's whitepaper () published an algorithm that uses 3-way pipelining for the crc32 intrinsics, then use pclmulqdq intrinsic to combine the values. Because pclmulqdq has overhead on its own, this algorithm will show perf gains on buffers larger than 216 bytes, which makes RocksDB a perfect user, since most of the buffers RocksDB call crc32c on is over 4KB. Initial db_bench show tremendous CPU gain. This change uses the 3-way SSE algorithm by default. The old SSE algorithm is now behind a compiler tag NO_THREEWAY_CRC32C. If user compiles the code with NO_THREEWAY_CRC32C=1 then the old SSE Crc32c algorithm would be used. If the server does not have SSE4.2 at the run time the slow way (Non SSE) will be used. **# Performance Test Results** We ran the FillRandom and ReadRandom benchmarks in db_bench. ReadRandom is the point of interest here since it calculates the CRC32 for the in-mem buffers. We did 3 runs for each algorithm. Before this change the CRC32 value computation takes about 11.5% of total CPU cost, and with the new 3-way algorithm it reduced to around 4.5%. The overall throughput also improved from 25.53MB/s to 27.63MB/s. 1) ReadRandom in db_bench overall metrics PER RUN Algorithm | run | micros/op | ops/sec |Throughput (MB/s) 3-way | 1 | 4.143 | 241387 | 26.7 3-way | 2 | 3.775 | 264872 | 29.3 3-way | 3 | 4.116 | 242929 | 26.9 FastCrc32c|1 | 4.037 | 247727 | 27.4 FastCrc32c|2 | 4.648 | 215166 | 23.8 FastCrc32c|3 | 4.352 | 229799 | 25.4 AVG Algorithm | Average of micros/op | Average of ops/sec | Average of Throughput (MB/s) 3-way | 4.01 | 249,729 | 27.63 FastCrc32c | 4.35 | 230,897 | 25.53 2) Crc32c computation CPU cost (inclusive samples percentage) PER RUN Implementation | run |  TotalSamples | Crc32c percentage 3-way   | 1    |  4,572,250,000 | 4.37% 3-way   | 2    |  3,779,250,000 | 4.62% 3-way   | 3    |  4,129,500,000 | 4.48% FastCrc32c     | 1    |  4,663,500,000 | 11.24% FastCrc32c     | 2    |  4,047,500,000 | 12.34% FastCrc32c     | 3    |  4,366,750,000 | 11.68% **# Test Plan** make -j64 corruption_test && ./corruption_test By default it uses 3-way SSE algorithm NO_THREEWAY_CRC32C=1 make -j64 corruption_test && ./corruption_test make clean && DEBUG_LEVEL=0 make -j64 db_bench make clean && DEBUG_LEVEL=0 NO_THREEWAY_CRC32C=1 make -j64 db_bench Closes https://github.com/facebook/rocksdb/pull/3173 Differential Revision: D6330882 Pulled By: yingsu00 fbshipit-source-id: 8ec3d89719533b63b536a736663ca6f0dd4482e9
7 years ago
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -msse4.2 -mpclmul")
endif()
if(MSVC)
if(FORCE_AVX)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX")
endif()
# MSVC automatically enables BMI / lzcnt with AVX2.
if(FORCE_AVX2)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
endif()
else()
if(FORCE_AVX)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mavx")
endif()
if(FORCE_AVX2)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mavx2 -mbmi -mlzcnt")
endif()
endif()
else()
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
if(MSVC)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} /arch:AVX2")
else()
if(NOT CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64" AND NOT HAS_ARMV8_CRC)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=native")
endif()
endif()
endif()
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
include(CheckCXXSourceCompiles)
set(OLD_CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS})
if(NOT MSVC)
Port 3 way SSE4.2 crc32c implementation from Folly Summary: **# Summary** RocksDB uses SSE crc32 intrinsics to calculate the crc32 values but it does it in single way fashion (not pipelined on single CPU core). Intel's whitepaper () published an algorithm that uses 3-way pipelining for the crc32 intrinsics, then use pclmulqdq intrinsic to combine the values. Because pclmulqdq has overhead on its own, this algorithm will show perf gains on buffers larger than 216 bytes, which makes RocksDB a perfect user, since most of the buffers RocksDB call crc32c on is over 4KB. Initial db_bench show tremendous CPU gain. This change uses the 3-way SSE algorithm by default. The old SSE algorithm is now behind a compiler tag NO_THREEWAY_CRC32C. If user compiles the code with NO_THREEWAY_CRC32C=1 then the old SSE Crc32c algorithm would be used. If the server does not have SSE4.2 at the run time the slow way (Non SSE) will be used. **# Performance Test Results** We ran the FillRandom and ReadRandom benchmarks in db_bench. ReadRandom is the point of interest here since it calculates the CRC32 for the in-mem buffers. We did 3 runs for each algorithm. Before this change the CRC32 value computation takes about 11.5% of total CPU cost, and with the new 3-way algorithm it reduced to around 4.5%. The overall throughput also improved from 25.53MB/s to 27.63MB/s. 1) ReadRandom in db_bench overall metrics PER RUN Algorithm | run | micros/op | ops/sec |Throughput (MB/s) 3-way | 1 | 4.143 | 241387 | 26.7 3-way | 2 | 3.775 | 264872 | 29.3 3-way | 3 | 4.116 | 242929 | 26.9 FastCrc32c|1 | 4.037 | 247727 | 27.4 FastCrc32c|2 | 4.648 | 215166 | 23.8 FastCrc32c|3 | 4.352 | 229799 | 25.4 AVG Algorithm | Average of micros/op | Average of ops/sec | Average of Throughput (MB/s) 3-way | 4.01 | 249,729 | 27.63 FastCrc32c | 4.35 | 230,897 | 25.53 2) Crc32c computation CPU cost (inclusive samples percentage) PER RUN Implementation | run |  TotalSamples | Crc32c percentage 3-way   | 1    |  4,572,250,000 | 4.37% 3-way   | 2    |  3,779,250,000 | 4.62% 3-way   | 3    |  4,129,500,000 | 4.48% FastCrc32c     | 1    |  4,663,500,000 | 11.24% FastCrc32c     | 2    |  4,047,500,000 | 12.34% FastCrc32c     | 3    |  4,366,750,000 | 11.68% **# Test Plan** make -j64 corruption_test && ./corruption_test By default it uses 3-way SSE algorithm NO_THREEWAY_CRC32C=1 make -j64 corruption_test && ./corruption_test make clean && DEBUG_LEVEL=0 make -j64 db_bench make clean && DEBUG_LEVEL=0 NO_THREEWAY_CRC32C=1 make -j64 db_bench Closes https://github.com/facebook/rocksdb/pull/3173 Differential Revision: D6330882 Pulled By: yingsu00 fbshipit-source-id: 8ec3d89719533b63b536a736663ca6f0dd4482e9
7 years ago
set(CMAKE_REQUIRED_FLAGS "-msse4.2 -mpclmul")
endif()
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
CHECK_CXX_SOURCE_COMPILES("
#include <cstdint>
#include <nmmintrin.h>
Port 3 way SSE4.2 crc32c implementation from Folly Summary: **# Summary** RocksDB uses SSE crc32 intrinsics to calculate the crc32 values but it does it in single way fashion (not pipelined on single CPU core). Intel's whitepaper () published an algorithm that uses 3-way pipelining for the crc32 intrinsics, then use pclmulqdq intrinsic to combine the values. Because pclmulqdq has overhead on its own, this algorithm will show perf gains on buffers larger than 216 bytes, which makes RocksDB a perfect user, since most of the buffers RocksDB call crc32c on is over 4KB. Initial db_bench show tremendous CPU gain. This change uses the 3-way SSE algorithm by default. The old SSE algorithm is now behind a compiler tag NO_THREEWAY_CRC32C. If user compiles the code with NO_THREEWAY_CRC32C=1 then the old SSE Crc32c algorithm would be used. If the server does not have SSE4.2 at the run time the slow way (Non SSE) will be used. **# Performance Test Results** We ran the FillRandom and ReadRandom benchmarks in db_bench. ReadRandom is the point of interest here since it calculates the CRC32 for the in-mem buffers. We did 3 runs for each algorithm. Before this change the CRC32 value computation takes about 11.5% of total CPU cost, and with the new 3-way algorithm it reduced to around 4.5%. The overall throughput also improved from 25.53MB/s to 27.63MB/s. 1) ReadRandom in db_bench overall metrics PER RUN Algorithm | run | micros/op | ops/sec |Throughput (MB/s) 3-way | 1 | 4.143 | 241387 | 26.7 3-way | 2 | 3.775 | 264872 | 29.3 3-way | 3 | 4.116 | 242929 | 26.9 FastCrc32c|1 | 4.037 | 247727 | 27.4 FastCrc32c|2 | 4.648 | 215166 | 23.8 FastCrc32c|3 | 4.352 | 229799 | 25.4 AVG Algorithm | Average of micros/op | Average of ops/sec | Average of Throughput (MB/s) 3-way | 4.01 | 249,729 | 27.63 FastCrc32c | 4.35 | 230,897 | 25.53 2) Crc32c computation CPU cost (inclusive samples percentage) PER RUN Implementation | run |  TotalSamples | Crc32c percentage 3-way   | 1    |  4,572,250,000 | 4.37% 3-way   | 2    |  3,779,250,000 | 4.62% 3-way   | 3    |  4,129,500,000 | 4.48% FastCrc32c     | 1    |  4,663,500,000 | 11.24% FastCrc32c     | 2    |  4,047,500,000 | 12.34% FastCrc32c     | 3    |  4,366,750,000 | 11.68% **# Test Plan** make -j64 corruption_test && ./corruption_test By default it uses 3-way SSE algorithm NO_THREEWAY_CRC32C=1 make -j64 corruption_test && ./corruption_test make clean && DEBUG_LEVEL=0 make -j64 db_bench make clean && DEBUG_LEVEL=0 NO_THREEWAY_CRC32C=1 make -j64 db_bench Closes https://github.com/facebook/rocksdb/pull/3173 Differential Revision: D6330882 Pulled By: yingsu00 fbshipit-source-id: 8ec3d89719533b63b536a736663ca6f0dd4482e9
7 years ago
#include <wmmintrin.h>
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
int main() {
volatile uint32_t x = _mm_crc32_u32(0, 0);
Port 3 way SSE4.2 crc32c implementation from Folly Summary: **# Summary** RocksDB uses SSE crc32 intrinsics to calculate the crc32 values but it does it in single way fashion (not pipelined on single CPU core). Intel's whitepaper () published an algorithm that uses 3-way pipelining for the crc32 intrinsics, then use pclmulqdq intrinsic to combine the values. Because pclmulqdq has overhead on its own, this algorithm will show perf gains on buffers larger than 216 bytes, which makes RocksDB a perfect user, since most of the buffers RocksDB call crc32c on is over 4KB. Initial db_bench show tremendous CPU gain. This change uses the 3-way SSE algorithm by default. The old SSE algorithm is now behind a compiler tag NO_THREEWAY_CRC32C. If user compiles the code with NO_THREEWAY_CRC32C=1 then the old SSE Crc32c algorithm would be used. If the server does not have SSE4.2 at the run time the slow way (Non SSE) will be used. **# Performance Test Results** We ran the FillRandom and ReadRandom benchmarks in db_bench. ReadRandom is the point of interest here since it calculates the CRC32 for the in-mem buffers. We did 3 runs for each algorithm. Before this change the CRC32 value computation takes about 11.5% of total CPU cost, and with the new 3-way algorithm it reduced to around 4.5%. The overall throughput also improved from 25.53MB/s to 27.63MB/s. 1) ReadRandom in db_bench overall metrics PER RUN Algorithm | run | micros/op | ops/sec |Throughput (MB/s) 3-way | 1 | 4.143 | 241387 | 26.7 3-way | 2 | 3.775 | 264872 | 29.3 3-way | 3 | 4.116 | 242929 | 26.9 FastCrc32c|1 | 4.037 | 247727 | 27.4 FastCrc32c|2 | 4.648 | 215166 | 23.8 FastCrc32c|3 | 4.352 | 229799 | 25.4 AVG Algorithm | Average of micros/op | Average of ops/sec | Average of Throughput (MB/s) 3-way | 4.01 | 249,729 | 27.63 FastCrc32c | 4.35 | 230,897 | 25.53 2) Crc32c computation CPU cost (inclusive samples percentage) PER RUN Implementation | run |  TotalSamples | Crc32c percentage 3-way   | 1    |  4,572,250,000 | 4.37% 3-way   | 2    |  3,779,250,000 | 4.62% 3-way   | 3    |  4,129,500,000 | 4.48% FastCrc32c     | 1    |  4,663,500,000 | 11.24% FastCrc32c     | 2    |  4,047,500,000 | 12.34% FastCrc32c     | 3    |  4,366,750,000 | 11.68% **# Test Plan** make -j64 corruption_test && ./corruption_test By default it uses 3-way SSE algorithm NO_THREEWAY_CRC32C=1 make -j64 corruption_test && ./corruption_test make clean && DEBUG_LEVEL=0 make -j64 db_bench make clean && DEBUG_LEVEL=0 NO_THREEWAY_CRC32C=1 make -j64 db_bench Closes https://github.com/facebook/rocksdb/pull/3173 Differential Revision: D6330882 Pulled By: yingsu00 fbshipit-source-id: 8ec3d89719533b63b536a736663ca6f0dd4482e9
7 years ago
const auto a = _mm_set_epi64x(0, 0);
const auto b = _mm_set_epi64x(0, 0);
const auto c = _mm_clmulepi64_si128(a, b, 0x00);
auto d = _mm_cvtsi128_si64(c);
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
}
" HAVE_SSE42)
if(HAVE_SSE42)
add_definitions(-DHAVE_SSE42)
add_definitions(-DHAVE_PCLMUL)
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
elseif(FORCE_SSE42)
message(FATAL_ERROR "FORCE_SSE42=ON but unable to compile with SSE4.2 enabled")
endif()
# Check if -latomic is required or not
if (NOT MSVC)
set(CMAKE_REQUIRED_FLAGS "--std=c++11")
CHECK_CXX_SOURCE_COMPILES("
#include <atomic>
std::atomic<uint64_t> x(0);
int main() {
uint64_t i = x.load(std::memory_order_relaxed);
bool b = x.is_lock_free();
return 0;
}
" BUILTIN_ATOMIC)
if (NOT BUILTIN_ATOMIC)
#TODO: Check if -latomic exists
list(APPEND THIRDPARTY_LIBS atomic)
endif()
endif()
if (WITH_LIBURING)
set(CMAKE_REQUIRED_FLAGS "-luring")
CHECK_CXX_SOURCE_COMPILES("
#include <liburing.h>
int main() {
struct io_uring ring;
io_uring_queue_init(1, &ring, 0);
return 0;
}
" HAS_LIBURING)
if (HAS_LIBURING)
add_definitions(-DROCKSDB_IOURING_PRESENT)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -luring")
endif()
endif()
# Reset the required flags
set(CMAKE_REQUIRED_FLAGS ${OLD_CMAKE_REQUIRED_FLAGS})
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
CHECK_CXX_SOURCE_COMPILES("
#if defined(_MSC_VER) && !defined(__thread)
#define __thread __declspec(thread)
#endif
int main() {
static __thread int tls;
(void)tls;
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
}
" HAVE_THREAD_LOCAL)
if(HAVE_THREAD_LOCAL)
add_definitions(-DROCKSDB_SUPPORT_THREAD_LOCAL)
endif()
option(WITH_IOSTATS_CONTEXT "Enable IO stats context" ON)
if (NOT WITH_IOSTATS_CONTEXT)
add_definitions(-DNIOSTATS_CONTEXT)
endif()
option(WITH_PERF_CONTEXT "Enable perf context" ON)
if (NOT WITH_PERF_CONTEXT)
add_definitions(-DNPERF_CONTEXT)
endif()
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 "${CMAKE_CXX_FLAGS} -Werror")
endif()
endif()
option(WITH_ASAN "build with ASAN" OFF)
if(WITH_ASAN)
set(CMAKE_EXE_LINKER_FLAGS "${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 "${CMAKE_EXE_LINKER_FLAGS} -fsanitize=thread -pie")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsanitize=thread -fPIC")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -fsanitize=thread -fPIC")
if(WITH_JEMALLOC)
message(FATAL "TSAN does not work well with JeMalloc")
endif()
endif()
option(WITH_UBSAN "build with UBSAN" OFF)
if(WITH_UBSAN)
add_definitions(-DROCKSDB_UBSAN_RUN)
set(CMAKE_EXE_LINKER_FLAGS "${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()
option(WITH_NUMA "build with NUMA policy support" OFF)
if(WITH_NUMA)
find_package(NUMA REQUIRED)
add_definitions(-DNUMA)
include_directories(${NUMA_INCLUDE_DIR})
list(APPEND THIRDPARTY_LIBS NUMA::NUMA)
endif()
option(WITH_TBB "build with Threading Building Blocks (TBB)" OFF)
if(WITH_TBB)
find_package(TBB REQUIRED)
add_definitions(-DTBB)
list(APPEND THIRDPARTY_LIBS TBB::TBB)
endif()
# Stall notifications eat some performance from inserts
option(DISABLE_STALL_NOTIF "Build with stall notifications" OFF)
if(DISABLE_STALL_NOTIF)
add_definitions(-DROCKSDB_DISABLE_STALL_NOTIFICATION)
endif()
option(WITH_DYNAMIC_EXTENSION "build with dynamic extension support" OFF)
if(NOT WITH_DYNAMIC_EXTENSION)
add_definitions(-DROCKSDB_NO_DYNAMIC_EXTENSION)
endif()
option(ASSERT_STATUS_CHECKED "build with assert status checked" OFF)
if (ASSERT_STATUS_CHECKED)
message(STATUS "Build with assert status checked")
add_definitions(-DROCKSDB_ASSERT_STATUS_CHECKED)
endif()
if(DEFINED USE_RTTI)
if(USE_RTTI)
message(STATUS "Enabling RTTI")
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -DROCKSDB_USE_RTTI")
else()
if(MSVC)
message(STATUS "Disabling RTTI in Release builds. Always on in Debug.")
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /GR-")
else()
message(STATUS "Disabling RTTI in Release builds")
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -fno-rtti")
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -fno-rtti")
endif()
endif()
else()
message(STATUS "Enabling RTTI in Debug builds only (default)")
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} -DROCKSDB_USE_RTTI")
if(MSVC)
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /GR-")
else()
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -fno-rtti")
endif()
endif()
# Used to run CI build and tests so we can run faster
option(OPTDBG "Build optimized debug build with MSVC" OFF)
option(WITH_RUNTIME_DEBUG "build with debug version of runtime library" ON)
if(MSVC)
if(OPTDBG)
message(STATUS "Debug optimization is enabled")
set(CMAKE_CXX_FLAGS_DEBUG "/Oxt")
else()
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1")
# Minimal Build is deprecated after MSVC 2015
if( MSVC_VERSION GREATER 1900 )
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Gm-")
else()
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Gm")
endif()
endif()
if(WITH_RUNTIME_DEBUG)
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /${RUNTIME_LIBRARY}d")
else()
set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /${RUNTIME_LIBRARY}")
endif()
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /Oxt /Zp8 /Gm- /Gy /${RUNTIME_LIBRARY}")
set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} /DEBUG")
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} /DEBUG")
endif()
if(CMAKE_COMPILER_IS_GNUCXX)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-builtin-memcmp")
endif()
option(ROCKSDB_LITE "Build RocksDBLite version" OFF)
if(ROCKSDB_LITE)
add_definitions(-DROCKSDB_LITE)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fno-exceptions -Os")
endif()
if(CMAKE_SYSTEM_NAME MATCHES "Cygwin")
add_definitions(-fno-builtin-memcmp -DCYGWIN)
elseif(CMAKE_SYSTEM_NAME MATCHES "Darwin")
add_definitions(-DOS_MACOSX)
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 "kFreeBSD")
add_definitions(-DOS_GNU_KFREEBSD)
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)
if(MINGW)
add_definitions(-D_WIN32_WINNT=_WIN32_WINNT_VISTA)
endif()
endif()
if(NOT WIN32)
add_definitions(-DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX)
endif()
option(WITH_FALLOCATE "build with fallocate" ON)
if(WITH_FALLOCATE)
CHECK_CXX_SOURCE_COMPILES("
#include <fcntl.h>
#include <linux/falloc.h>
int main() {
int fd = open(\"/dev/null\", 0);
fallocate(fd, FALLOC_FL_KEEP_SIZE, 0, 1024);
}
" HAVE_FALLOCATE)
if(HAVE_FALLOCATE)
add_definitions(-DROCKSDB_FALLOCATE_PRESENT)
endif()
endif()
CHECK_CXX_SOURCE_COMPILES("
#include <fcntl.h>
int main() {
int fd = open(\"/dev/null\", 0);
sync_file_range(fd, 0, 1024, SYNC_FILE_RANGE_WRITE);
}
" HAVE_SYNC_FILE_RANGE_WRITE)
if(HAVE_SYNC_FILE_RANGE_WRITE)
add_definitions(-DROCKSDB_RANGESYNC_PRESENT)
endif()
CHECK_CXX_SOURCE_COMPILES("
#include <pthread.h>
int main() {
(void) PTHREAD_MUTEX_ADAPTIVE_NP;
}
" HAVE_PTHREAD_MUTEX_ADAPTIVE_NP)
if(HAVE_PTHREAD_MUTEX_ADAPTIVE_NP)
add_definitions(-DROCKSDB_PTHREAD_ADAPTIVE_MUTEX)
endif()
include(CheckCXXSymbolExists)
if(CMAKE_SYSTEM_NAME MATCHES "^FreeBSD")
check_cxx_symbol_exists(malloc_usable_size malloc_np.h HAVE_MALLOC_USABLE_SIZE)
else()
check_cxx_symbol_exists(malloc_usable_size malloc.h HAVE_MALLOC_USABLE_SIZE)
endif()
if(HAVE_MALLOC_USABLE_SIZE)
add_definitions(-DROCKSDB_MALLOC_USABLE_SIZE)
endif()
check_cxx_symbol_exists(sched_getcpu sched.h HAVE_SCHED_GETCPU)
if(HAVE_SCHED_GETCPU)
add_definitions(-DROCKSDB_SCHED_GETCPU_PRESENT)
endif()
check_cxx_symbol_exists(getauxval auvx.h HAVE_AUXV_GETAUXVAL)
if(HAVE_AUXV_GETAUXVAL)
add_definitions(-DROCKSDB_AUXV_GETAUXVAL_PRESENT)
endif()
include_directories(${PROJECT_SOURCE_DIR})
include_directories(${PROJECT_SOURCE_DIR}/include)
if(WITH_FOLLY_DISTRIBUTED_MUTEX)
include_directories(${PROJECT_SOURCE_DIR}/third-party/folly)
endif()
find_package(Threads REQUIRED)
# Main library source code
set(SOURCES
cache/cache.cc
Use deleters to label cache entries and collect stats (#8297) Summary: This change gathers and publishes statistics about the kinds of items in block cache. This is especially important for profiling relative usage of cache by index vs. filter vs. data blocks. It works by iterating over the cache during periodic stats dump (InternalStats, stats_dump_period_sec) or on demand when DB::Get(Map)Property(kBlockCacheEntryStats), except that for efficiency and sharing among column families, saved data from the last scan is used when the data is not considered too old. The new information can be seen in info LOG, for example: Block cache LRUCache@0x7fca62229330 capacity: 95.37 MB collections: 8 last_copies: 0 last_secs: 0.00178 secs_since: 0 Block cache entry stats(count,size,portion): DataBlock(7092,28.24 MB,29.6136%) FilterBlock(215,867.90 KB,0.888728%) FilterMetaBlock(2,5.31 KB,0.00544%) IndexBlock(217,180.11 KB,0.184432%) WriteBuffer(1,256.00 KB,0.262144%) Misc(1,0.00 KB,0%) And also through DB::GetProperty and GetMapProperty (here using ldb just for demonstration): $ ./ldb --db=/dev/shm/dbbench/ get_property rocksdb.block-cache-entry-stats rocksdb.block-cache-entry-stats.bytes.data-block: 0 rocksdb.block-cache-entry-stats.bytes.deprecated-filter-block: 0 rocksdb.block-cache-entry-stats.bytes.filter-block: 0 rocksdb.block-cache-entry-stats.bytes.filter-meta-block: 0 rocksdb.block-cache-entry-stats.bytes.index-block: 178992 rocksdb.block-cache-entry-stats.bytes.misc: 0 rocksdb.block-cache-entry-stats.bytes.other-block: 0 rocksdb.block-cache-entry-stats.bytes.write-buffer: 0 rocksdb.block-cache-entry-stats.capacity: 8388608 rocksdb.block-cache-entry-stats.count.data-block: 0 rocksdb.block-cache-entry-stats.count.deprecated-filter-block: 0 rocksdb.block-cache-entry-stats.count.filter-block: 0 rocksdb.block-cache-entry-stats.count.filter-meta-block: 0 rocksdb.block-cache-entry-stats.count.index-block: 215 rocksdb.block-cache-entry-stats.count.misc: 1 rocksdb.block-cache-entry-stats.count.other-block: 0 rocksdb.block-cache-entry-stats.count.write-buffer: 0 rocksdb.block-cache-entry-stats.id: LRUCache@0x7f3636661290 rocksdb.block-cache-entry-stats.percent.data-block: 0.000000 rocksdb.block-cache-entry-stats.percent.deprecated-filter-block: 0.000000 rocksdb.block-cache-entry-stats.percent.filter-block: 0.000000 rocksdb.block-cache-entry-stats.percent.filter-meta-block: 0.000000 rocksdb.block-cache-entry-stats.percent.index-block: 2.133751 rocksdb.block-cache-entry-stats.percent.misc: 0.000000 rocksdb.block-cache-entry-stats.percent.other-block: 0.000000 rocksdb.block-cache-entry-stats.percent.write-buffer: 0.000000 rocksdb.block-cache-entry-stats.secs_for_last_collection: 0.000052 rocksdb.block-cache-entry-stats.secs_since_last_collection: 0 Solution detail - We need some way to flag what kind of blocks each entry belongs to, preferably without changing the Cache API. One of the complications is that Cache is a general interface that could have other users that don't adhere to whichever convention we decide on for keys and values. Or we would pay for an extra field in the Handle that would only be used for this purpose. This change uses a back-door approach, the deleter, to indicate the "role" of a Cache entry (in addition to the value type, implicitly). This has the added benefit of ensuring proper code origin whenever we recognize a particular role for a cache entry; if the entry came from some other part of the code, it will use an unrecognized deleter, which we simply attribute to the "Misc" role. An internal API makes for simple instantiation and automatic registration of Cache deleters for a given value type and "role". Another internal API, CacheEntryStatsCollector, solves the problem of caching the results of a scan and sharing them, to ensure scans are neither excessive nor redundant so as not to harm Cache performance. Because code is added to BlocklikeTraits, it is pulled out of block_based_table_reader.cc into its own file. This is a reformulation of https://github.com/facebook/rocksdb/issues/8276, without the type checking option (could still be added), and with actual stat gathering. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8297 Test Plan: manual testing with db_bench, and a couple of basic unit tests Reviewed By: ltamasi Differential Revision: D28488721 Pulled By: pdillinger fbshipit-source-id: 472f524a9691b5afb107934be2d41d84f2b129fb
4 years ago
cache/cache_entry_roles.cc
cache/clock_cache.cc
cache/lru_cache.cc
cache/sharded_cache.cc
db/arena_wrapped_db_iter.cc
db/blob/blob_fetcher.cc
db/blob/blob_file_addition.cc
db/blob/blob_file_builder.cc
db/blob/blob_file_cache.cc
db/blob/blob_file_garbage.cc
Add blob files to VersionStorageInfo/VersionBuilder (#6597) Summary: The patch adds a couple of classes to represent metadata about blob files: `SharedBlobFileMetaData` contains the information elements that are immutable (once the blob file is closed), e.g. blob file number, total number and size of blob files, checksum method/value, while `BlobFileMetaData` contains attributes that can vary across versions like the amount of garbage in the file. There is a single `SharedBlobFileMetaData` for each blob file, which is jointly owned by the `BlobFileMetaData` objects that point to it; `BlobFileMetaData` objects, in turn, are owned by `Version`s and can also be shared if the (immutable _and_ mutable) state of the blob file is the same in two versions. In addition, the patch adds the blob file metadata to `VersionStorageInfo`, and extends `VersionBuilder` so that it can apply blob file related `VersionEdit`s (i.e. those containing `BlobFileAddition`s and/or `BlobFileGarbage`), and save blob file metadata to a new `VersionStorageInfo`. Consistency checks are also extended to ensure that table files point to blob files that are part of the `Version`, and that all blob files that are part of any given `Version` have at least some _non_-garbage data in them. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6597 Test Plan: `make check` Reviewed By: riversand963 Differential Revision: D20656803 Pulled By: ltamasi fbshipit-source-id: f1f74d135045b3b42d0146f03ee576ef0a4bfd80
5 years ago
db/blob/blob_file_meta.cc
Introduce a blob file reader class (#7461) Summary: The patch adds a class called `BlobFileReader` that can be used to retrieve blobs using the information available in blob references (e.g. blob file number, offset, and size). This will come in handy when implementing blob support for `Get`, `MultiGet`, and iterators, and also for compaction/garbage collection. When a `BlobFileReader` object is created (using the factory method `Create`), it first checks whether the specified file is potentially valid by comparing the file size against the combined size of the blob file header and footer (files smaller than the threshold are considered malformed). Then, it opens the file, and reads and verifies the header and footer. The verification involves magic number/CRC checks as well as checking for unexpected header/footer fields, e.g. incorrect column family ID or TTL blob files. Blobs can be retrieved using `GetBlob`. `GetBlob` validates the offset and compression type passed by the caller (because of the presence of the header and footer, the specified offset cannot be too close to the start/end of the file; also, the compression type has to match the one in the blob file header), and retrieves and potentially verifies and uncompresses the blob. In particular, when `ReadOptions::verify_checksums` is set, `BlobFileReader` reads the blob record header as well (as opposed to just the blob itself) and verifies the key/value size, the key itself, as well as the CRC of the blob record header and the key/value pair. In addition, the patch exposes the compression type from `BlobIndex` (both using an accessor and via `DebugString`), and adds a blob file read latency histogram to `InternalStats` that can be used with `BlobFileReader`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7461 Test Plan: `make check` Reviewed By: riversand963 Differential Revision: D23999219 Pulled By: ltamasi fbshipit-source-id: deb6b1160d251258b308d5156e2ec063c3e12e5e
4 years ago
db/blob/blob_file_reader.cc
db/blob/blob_garbage_meter.cc
db/blob/blob_log_format.cc
db/blob/blob_log_sequential_reader.cc
db/blob/blob_log_writer.cc
db/builder.cc
db/c.cc
db/column_family.cc
db/compaction/compaction.cc
db/compaction/compaction_iterator.cc
db/compaction/compaction_picker.cc
db/compaction/compaction_job.cc
db/compaction/compaction_picker_fifo.cc
db/compaction/compaction_picker_level.cc
db/compaction/compaction_picker_universal.cc
db/compaction/sst_partitioner.cc
db/convenience.cc
db/db_filesnapshot.cc
db/db_impl/compacted_db_impl.cc
db/db_impl/db_impl.cc
db/db_impl/db_impl_write.cc
db/db_impl/db_impl_compaction_flush.cc
db/db_impl/db_impl_files.cc
db/db_impl/db_impl_open.cc
db/db_impl/db_impl_debug.cc
db/db_impl/db_impl_experimental.cc
db/db_impl/db_impl_readonly.cc
db/db_impl/db_impl_secondary.cc
db/db_info_dumper.cc
db/db_iter.cc
db/dbformat.cc
db/error_handler.cc
db/event_helpers.cc
db/experimental.cc
db/external_sst_file_ingestion_job.cc
db/file_indexer.cc
db/flush_job.cc
db/flush_scheduler.cc
db/forward_iterator.cc
db/import_column_family_job.cc
db/internal_stats.cc
Skip deleted WALs during recovery Summary: This patch record min log number to keep to the manifest while flushing SST files to ignore them and any WAL older than them during recovery. This is to avoid scenarios when we have a gap between the WAL files are fed to the recovery procedure. The gap could happen by for example out-of-order WAL deletion. Such gap could cause problems in 2PC recovery where the prepared and commit entry are placed into two separate WAL and gap in the WALs could result into not processing the WAL with the commit entry and hence breaking the 2PC recovery logic. Before the commit, for 2PC case, we determined which log number to keep in FindObsoleteFiles(). We looked at the earliest logs with outstanding prepare entries, or prepare entries whose respective commit or abort are in memtable. With the commit, the same calculation is done while we apply the SST flush. Just before installing the flush file, we precompute the earliest log file to keep after the flush finishes using the same logic (but skipping the memtables just flushed), record this information to the manifest entry for this new flushed SST file. This pre-computed value is also remembered in memory, and will later be used to determine whether a log file can be deleted. This value is unlikely to change until next flush because the commit entry will stay in memtable. (In WritePrepared, we could have removed the older log files as soon as all prepared entries are committed. It's not yet done anyway. Even if we do it, the only thing we loss with this new approach is earlier log deletion between two flushes, which does not guarantee to happen anyway because the obsolete file clean-up function is only executed after flush or compaction) This min log number to keep is stored in the manifest using the safely-ignore customized field of AddFile entry, in order to guarantee that the DB generated using newer release can be opened by previous releases no older than 4.2. Closes https://github.com/facebook/rocksdb/pull/3765 Differential Revision: D7747618 Pulled By: siying fbshipit-source-id: d00c92105b4f83852e9754a1b70d6b64cb590729
7 years ago
db/logs_with_prep_tracker.cc
db/log_reader.cc
db/log_writer.cc
db: avoid `#include`ing malloc and jemalloc simultaneously Summary: This fixes a compilation failure on Linux when the system libc is not glibc. jemalloc's configure script incorrectly assumes that glibc is always used on Linux systems, producing glibc-style signatures; when the system libc is e.g. musl, the following error is observed: ``` [ 0%] Building CXX object CMakeFiles/rocksdb.dir/db/db_impl.cc.o In file included from /go/src/github.com/cockroachdb/cockroach/c-deps/rocksdb.src/table/block.h:19:0, from /go/src/github.com/cockroachdb/cockroach/c-deps/rocksdb.src/db/db_impl.cc:77: /x-tools/x86_64-unknown-linux-musl/x86_64-unknown-linux-musl/sysroot/usr/include/malloc.h:19:8: error: declaration of 'size_t malloc_usable_size(void*)' has a different exception specifier size_t malloc_usable_size(void *); ^~~~~~~~~~~~~~~~~~ In file included from /go/src/github.com/cockroachdb/cockroach/c-deps/rocksdb.src/db/db_impl.cc:20:0: /go/native/x86_64-unknown-linux-musl/jemalloc/include/jemalloc/jemalloc.h:78:33: note: from previous declaration 'size_t malloc_usable_size(void*) throw ()' # define je_malloc_usable_size malloc_usable_size ^ /go/native/x86_64-unknown-linux-musl/jemalloc/include/jemalloc/jemalloc.h:239:41: note: in expansion of macro 'je_malloc_usable_size' JEMALLOC_EXPORT size_t JEMALLOC_NOTHROW je_malloc_usable_size( ^~~~~~~~~~~~~~~~~~~~~ CMakeFiles/rocksdb.dir/build.make:350: recipe for target 'CMakeFiles/rocksdb.dir/db/db_impl.cc.o' failed ``` This works around the issue by rearranging the sources such that jemalloc's headers are never in the same scope as the system's malloc header. The jemalloc issue has been reported as well, see: https://github.com/jemalloc/jemalloc/issues/778. cc tschottdorf Closes https://github.com/facebook/rocksdb/pull/2188 Differential Revision: D5163048 Pulled By: siying fbshipit-source-id: c553125458892def175c1be5682b0330d80b2a0d
8 years ago
db/malloc_stats.cc
db/memtable.cc
db/memtable_list.cc
db/merge_helper.cc
db/merge_operator.cc
db/output_validator.cc
db/periodic_work_scheduler.cc
Compaction Support for Range Deletion Summary: This diff introduces RangeDelAggregator, which takes ownership of iterators provided to it via AddTombstones(). The tombstones are organized in a two-level map (snapshot stripe -> begin key -> tombstone). Tombstone creation avoids data copy by holding Slices returned by the iterator, which remain valid thanks to pinning. For compaction, we create a hierarchical range tombstone iterator with structure matching the iterator over compaction input data. An aggregator based on that iterator is used by CompactionIterator to determine which keys are covered by range tombstones. In case of merge operand, the same aggregator is used by MergeHelper. Upon finishing each file in the compaction, relevant range tombstones are added to the output file's range tombstone metablock and file boundaries are updated accordingly. To check whether a key is covered by range tombstone, RangeDelAggregator::ShouldDelete() considers tombstones in the key's snapshot stripe. When this function is used outside of compaction, it also checks newer stripes, which can contain covering tombstones. Currently the intra-stripe check involves a linear scan; however, in the future we plan to collapse ranges within a stripe such that binary search can be used. RangeDelAggregator::AddToBuilder() adds all range tombstones in the table's key-range to a new table's range tombstone meta-block. Since range tombstones may fall in the gap between files, we may need to extend some files' key-ranges. The strategy is (1) first file extends as far left as possible and other files do not extend left, (2) all files extend right until either the start of the next file or the end of the last range tombstone in the gap, whichever comes first. One other notable change is adding release/move semantics to ScopedArenaIterator such that it can be used to transfer ownership of an arena-allocated iterator, similar to how unique_ptr is used for malloc'd data. Depends on D61473 Test Plan: compaction_iterator_test, mock_table, end-to-end tests in D63927 Reviewers: sdong, IslamAbdelRahman, wanning, yhchiang, lightmark Reviewed By: lightmark Subscribers: andrewkr, dhruba, leveldb Differential Revision: https://reviews.facebook.net/D62205
8 years ago
db/range_del_aggregator.cc
Use only "local" range tombstones during Get (#4449) Summary: Previously, range tombstones were accumulated from every level, which was necessary if a range tombstone in a higher level covered a key in a lower level. However, RangeDelAggregator::AddTombstones's complexity is based on the number of tombstones that are currently stored in it, which is wasteful in the Get case, where we only need to know the highest sequence number of range tombstones that cover the key from higher levels, and compute the highest covering sequence number at the current level. This change introduces this optimization, and removes the use of RangeDelAggregator from the Get path. In the benchmark results, the following command was used to initialize the database: ``` ./db_bench -db=/dev/shm/5k-rts -use_existing_db=false -benchmarks=filluniquerandom -write_buffer_size=1048576 -compression_type=lz4 -target_file_size_base=1048576 -max_bytes_for_level_base=4194304 -value_size=112 -key_size=16 -block_size=4096 -level_compaction_dynamic_level_bytes=true -num=5000000 -max_background_jobs=12 -benchmark_write_rate_limit=20971520 -range_tombstone_width=100 -writes_per_range_tombstone=100 -max_num_range_tombstones=50000 -bloom_bits=8 ``` ...and the following command was used to measure read throughput: ``` ./db_bench -db=/dev/shm/5k-rts/ -use_existing_db=true -benchmarks=readrandom -disable_auto_compactions=true -num=5000000 -reads=100000 -threads=32 ``` The filluniquerandom command was only run once, and the resulting database was used to measure read performance before and after the PR. Both binaries were compiled with `DEBUG_LEVEL=0`. Readrandom results before PR: ``` readrandom : 4.544 micros/op 220090 ops/sec; 16.9 MB/s (63103 of 100000 found) ``` Readrandom results after PR: ``` readrandom : 11.147 micros/op 89707 ops/sec; 6.9 MB/s (63103 of 100000 found) ``` So it's actually slower right now, but this PR paves the way for future optimizations (see #4493). ---- Pull Request resolved: https://github.com/facebook/rocksdb/pull/4449 Differential Revision: D10370575 Pulled By: abhimadan fbshipit-source-id: 9a2e152be1ef36969055c0e9eb4beb0d96c11f4d
6 years ago
db/range_tombstone_fragmenter.cc
db/repair.cc
db/snapshot_impl.cc
db/table_cache.cc
db/table_properties_collector.cc
db/transaction_log_impl.cc
Refactor trimming logic for immutable memtables (#5022) Summary: MyRocks currently sets `max_write_buffer_number_to_maintain` in order to maintain enough history for transaction conflict checking. The effectiveness of this approach depends on the size of memtables. When memtables are small, it may not keep enough history; when memtables are large, this may consume too much memory. We are proposing a new way to configure memtable list history: by limiting the memory usage of immutable memtables. The new option is `max_write_buffer_size_to_maintain` and it will take precedence over the old `max_write_buffer_number_to_maintain` if they are both set to non-zero values. The new option accounts for the total memory usage of flushed immutable memtables and mutable memtable. When the total usage exceeds the limit, RocksDB may start dropping immutable memtables (which is also called trimming history), starting from the oldest one. The semantics of the old option actually works both as an upper bound and lower bound. History trimming will start if number of immutable memtables exceeds the limit, but it will never go below (limit-1) due to history trimming. In order the mimic the behavior with the new option, history trimming will stop if dropping the next immutable memtable causes the total memory usage go below the size limit. For example, assuming the size limit is set to 64MB, and there are 3 immutable memtables with sizes of 20, 30, 30. Although the total memory usage is 80MB > 64MB, dropping the oldest memtable will reduce the memory usage to 60MB < 64MB, so in this case no memtable will be dropped. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5022 Differential Revision: D14394062 Pulled By: miasantreble fbshipit-source-id: 60457a509c6af89d0993f988c9b5c2aa9e45f5c5
5 years ago
db/trim_history_scheduler.cc
db/version_builder.cc
db/version_edit.cc
db/version_edit_handler.cc
db/version_set.cc
Define WAL related classes to be used in VersionEdit and VersionSet (#7164) Summary: `WalAddition`, `WalDeletion` are defined in `wal_version.h` and used in `VersionEdit`. `WalAddition` is used to represent events of creating a new WAL (no size, just log number), or closing a WAL (with size). `WalDeletion` is used to represent events of deleting or archiving a WAL, it means the WAL is no longer alive (won't be replayed during recovery). `WalSet` is the set of alive WALs kept in `VersionSet`. 1. Why use `WalDeletion` instead of relying on `MinLogNumber` to identify outdated WALs On recovery, we can compute `MinLogNumber()` based on the log numbers kept in MANIFEST, any log with number < MinLogNumber can be ignored. So it seems that we don't need to persist `WalDeletion` to MANIFEST, since we can ignore the WALs based on MinLogNumber. But the `MinLogNumber()` is actually a lower bound, it does not exactly mean that logs starting from MinLogNumber must exist. This is because in a corner case, when a column family is empty and never flushed, its log number is set to the largest log number, but not persisted in MANIFEST. So let's say there are 2 column families, when creating the DB, the first WAL has log number 1, so it's persisted to MANIFEST for both column families. Then CF 0 is empty and never flushed, CF 1 is updated and flushed, so a new WAL with log number 2 is created and persisted to MANIFEST for CF 1. But CF 0's log number in MANIFEST is still 1. So on recovery, MinLogNumber is 1, but since log 1 only contains data for CF 1, and CF 1 is flushed, log 1 might have already been deleted from disk. We can make `MinLogNumber()` be the exactly minimum log number that must exist, by persisting the most recent log number for empty column families that are not flushed. But if there are N such column families, then every time a new WAL is created, we need to add N records to MANIFEST. In current design, a record is persisted to MANIFEST only when WAL is created, closed, or deleted/archived, so the number of WAL related records are bounded to 3x number of WALs. 2. Why keep `WalSet` in `VersionSet` instead of applying the `VersionEdit`s to `VersionStorageInfo` `VersionEdit`s are originally designed to track the addition and deletion of SST files. The SST files are related to column families, each column family has a list of `Version`s, and each `Version` keeps the set of active SST files in `VersionStorageInfo`. But WALs are a concept of DB, they are not bounded to specific column families. So logically it does not make sense to store WALs in a column family's `Version`s. Also, `Version`'s purpose is to keep reference to SST / blob files, so that they are not deleted until there is no version referencing them. But a WAL is deleted regardless of version references. So we keep the WALs in `VersionSet` for the purpose of writing out the DB state's snapshot when creating new MANIFESTs. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7164 Test Plan: make version_edit_test && ./version_edit_test make wal_edit_test && ./wal_edit_test Reviewed By: ltamasi Differential Revision: D22677936 Pulled By: cheng-chang fbshipit-source-id: 5a3b6890140e572ffd79eb37e6e4c3c32361a859
4 years ago
db/wal_edit.cc
db/wal_manager.cc
db/write_batch.cc
db/write_batch_base.cc
db/write_controller.cc
db/write_thread.cc
env/composite_env.cc
env/env.cc
env/env_chroot.cc
Encryption at rest support Summary: This PR adds support for encrypting data stored by RocksDB when written to disk. It adds an `EncryptedEnv` override of the `Env` class with matching overrides for sequential&random access files. The encryption itself is done through a configurable `EncryptionProvider`. This class creates is asked to create `BlockAccessCipherStream` for a file. This is where the actual encryption/decryption is being done. Currently there is a Counter mode implementation of `BlockAccessCipherStream` with a `ROT13` block cipher (NOTE the `ROT13` is for demo purposes only!!). The Counter operation mode uses an initial counter & random initialization vector (IV). Both are created randomly for each file and stored in a 4K (default size) block that is prefixed to that file. The `EncryptedEnv` implementation is such that clients of the `Env` class do not see this prefix (nor data, nor in filesize). The largest part of the prefix block is also encrypted, and there is room left for implementation specific settings/values/keys in there. To test the encryption, the `DBTestBase` class has been extended to consider a new environment variable called `ENCRYPTED_ENV`. If set, the test will setup a encrypted instance of the `Env` class to use for all tests. Typically you would run it like this: ``` ENCRYPTED_ENV=1 make check_some ``` There is also an added test that checks that some data inserted into the database is or is not "visible" on disk. With `ENCRYPTED_ENV` active it must not find plain text strings, with `ENCRYPTED_ENV` unset, it must find the plain text strings. Closes https://github.com/facebook/rocksdb/pull/2424 Differential Revision: D5322178 Pulled By: sdwilsh fbshipit-source-id: 253b0a9c2c498cc98f580df7f2623cbf7678a27f
8 years ago
env/env_encryption.cc
env/env_hdfs.cc
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
5 years ago
env/file_system.cc
env/file_system_tracer.cc
Make backups openable as read-only DBs (#8142) Summary: A current limitation of backups is that you don't know the exact database state of when the backup was taken. With this new feature, you can at least inspect the backup's DB state without restoring it by opening it as a read-only DB. Rather than add something like OpenAsReadOnlyDB to the BackupEngine API, which would inhibit opening stackable DB implementations read-only (if/when their APIs support it), we instead provide a DB name and Env that can be used to open as a read-only DB. Possible follow-up work: * Add a version of GetBackupInfo for a single backup. * Let CreateNewBackup return the BackupID of the newly-created backup. Implementation details: Refactored ChrootFileSystem to split off new base class RemapFileSystem, which allows more general remapping of files. We use this base class to implement BackupEngineImpl::RemapSharedFileSystem. To minimize API impact, I decided to just add these fields `name_for_open` and `env_for_open` to those set by GetBackupInfo when include_file_details=true. Creating the RemapSharedFileSystem adds a bit to the memory consumption, perhaps unnecessarily in some cases, but this has been mitigated by (a) only initialize the RemapSharedFileSystem lazily when GetBackupInfo with include_file_details=true is called, and (b) using the existing `shared_ptr<FileInfo>` objects to hold most of the mapping data. To enhance API safety, RemapSharedFileSystem is wrapped by new ReadOnlyFileSystem which rejects any attempts to write. This uncovered a couple of places in which DB::OpenForReadOnly would write to the filesystem, so I fixed these. Added a release note because this affects logging. Additional minor refactoring in backupable_db.cc to support the new functionality. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8142 Test Plan: new test (run with ASAN and UBSAN), added to stress test and ran it for a while with amplified backup_one_in Reviewed By: ajkr Differential Revision: D27535408 Pulled By: pdillinger fbshipit-source-id: 04666d310aa0261ef6b2385c43ca793ce1dfd148
4 years ago
env/fs_remap.cc
env/mock_env.cc
file/delete_scheduler.cc
file/file_prefetch_buffer.cc
file/file_util.cc
file/filename.cc
file/line_file_reader.cc
file/random_access_file_reader.cc
file/read_write_util.cc
file/readahead_raf.cc
file/sequence_file_reader.cc
file/sst_file_manager_impl.cc
file/writable_file_writer.cc
logging/auto_roll_logger.cc
logging/event_logger.cc
logging/log_buffer.cc
memory/arena.cc
memory/concurrent_arena.cc
memory/jemalloc_nodump_allocator.cc
Provide an allocator for new memory type to be used with RocksDB block cache (#6214) Summary: New memory technologies are being developed by various hardware vendors (Intel DCPMM is one such technology currently available). These new memory types require different libraries for allocation and management (such as PMDK and memkind). The high capacities available make it possible to provision large caches (up to several TBs in size), beyond what is achievable with DRAM. The new allocator provided in this PR uses the memkind library to allocate memory on different media. **Performance** We tested the new allocator using db_bench. - For each test, we vary the size of the block cache (relative to the size of the uncompressed data in the database). - The database is filled sequentially. Throughput is then measured with a readrandom benchmark. - We use a uniform distribution as a worst-case scenario. The plot shows throughput (ops/s) relative to a configuration with no block cache and default allocator. For all tests, p99 latency is below 500 us. ![image](https://user-images.githubusercontent.com/26400080/71108594-42479100-2178-11ea-8231-8a775bbc92db.png) **Changes** - Add MemkindKmemAllocator - Add --use_cache_memkind_kmem_allocator db_bench option (to create an LRU block cache with the new allocator) - Add detection of memkind library with KMEM DAX support - Add test for MemkindKmemAllocator **Minimum Requirements** - kernel 5.3.12 - ndctl v67 - https://github.com/pmem/ndctl - memkind v1.10.0 - https://github.com/memkind/memkind **Memory Configuration** The allocator uses the MEMKIND_DAX_KMEM memory kind. Follow the instructions on[ memkind’s GitHub page](https://github.com/memkind/memkind) to set up NVDIMM memory accordingly. Note on memory allocation with NVDIMM memory exposed as system memory. - The MemkindKmemAllocator will only allocate from NVDIMM memory (using memkind_malloc with MEMKIND_DAX_KMEM kind). - The default allocator is not restricted to RAM by default. Based on NUMA node latency, the kernel should allocate from local RAM preferentially, but it’s a kernel decision. numactl --preferred/--membind can be used to allocate preferentially/exclusively from the local RAM node. **Usage** When creating an LRU cache, pass a MemkindKmemAllocator object as argument. For example (replace capacity with the desired value in bytes): ``` #include "rocksdb/cache.h" #include "memory/memkind_kmem_allocator.h" NewLRUCache( capacity /*size_t*/, 6 /*cache_numshardbits*/, false /*strict_capacity_limit*/, false /*cache_high_pri_pool_ratio*/, std::make_shared<MemkindKmemAllocator>()); ``` Refer to [RocksDB’s block cache documentation](https://github.com/facebook/rocksdb/wiki/Block-Cache) to assign the LRU cache as block cache for a database. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6214 Reviewed By: cheng-chang Differential Revision: D19292435 fbshipit-source-id: 7202f47b769e7722b539c86c2ffd669f64d7b4e1
5 years ago
memory/memkind_kmem_allocator.cc
memtable/alloc_tracker.cc
memtable/hash_linklist_rep.cc
memtable/hash_skiplist_rep.cc
memtable/skiplistrep.cc
memtable/vectorrep.cc
memtable/write_buffer_manager.cc
monitoring/histogram.cc
monitoring/histogram_windowing.cc
monitoring/in_memory_stats_history.cc
monitoring/instrumented_mutex.cc
monitoring/iostats_context.cc
monitoring/perf_context.cc
monitoring/perf_level.cc
monitoring/persistent_stats_history.cc
monitoring/statistics.cc
monitoring/thread_status_impl.cc
monitoring/thread_status_updater.cc
monitoring/thread_status_util.cc
monitoring/thread_status_util_debug.cc
options/cf_options.cc
options/configurable.cc
options/customizable.cc
options/db_options.cc
options/options.cc
options/options_helper.cc
options/options_parser.cc
port/stack_trace.cc
table/adaptive/adaptive_table_factory.cc
table/block_based/binary_search_index_reader.cc
table/block_based/block.cc
table/block_based/block_based_filter_block.cc
table/block_based/block_based_table_builder.cc
table/block_based/block_based_table_factory.cc
De-template block based table iterator (#6531) Summary: Right now block based table iterator is used as both of iterating data for block based table, and for the index iterator for partitioend index. This was initially convenient for introducing a new iterator and block type for new index format, while reducing code change. However, these two usage doesn't go with each other very well. For example, Prev() is never called for partitioned index iterator, and some other complexity is maintained in block based iterators, which is not needed for index iterator but maintainers will always need to reason about it. Furthermore, the template usage is not following Google C++ Style which we are following, and makes a large chunk of code tangled together. This commit separate the two iterators. Right now, here is what it is done: 1. Copy the block based iterator code into partitioned index iterator, and de-template them. 2. Remove some code not needed for partitioned index. The upper bound check and tricks are removed. We never tested performance for those tricks when partitioned index is enabled in the first place. It's unlikelyl to generate performance regression, as creating new partitioned index block is much rarer than data blocks. 3. Separate out the prefetch logic to a helper class and both classes call them. This commit will enable future follow-ups. One direction is that we might separate index iterator interface for data blocks and index blocks, as they are quite different. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6531 Test Plan: build using make and cmake. And build release Differential Revision: D20473108 fbshipit-source-id: e48011783b339a4257c204cc07507b171b834b0f
5 years ago
table/block_based/block_based_table_iterator.cc
table/block_based/block_based_table_reader.cc
table/block_based/block_builder.cc
De-template block based table iterator (#6531) Summary: Right now block based table iterator is used as both of iterating data for block based table, and for the index iterator for partitioend index. This was initially convenient for introducing a new iterator and block type for new index format, while reducing code change. However, these two usage doesn't go with each other very well. For example, Prev() is never called for partitioned index iterator, and some other complexity is maintained in block based iterators, which is not needed for index iterator but maintainers will always need to reason about it. Furthermore, the template usage is not following Google C++ Style which we are following, and makes a large chunk of code tangled together. This commit separate the two iterators. Right now, here is what it is done: 1. Copy the block based iterator code into partitioned index iterator, and de-template them. 2. Remove some code not needed for partitioned index. The upper bound check and tricks are removed. We never tested performance for those tricks when partitioned index is enabled in the first place. It's unlikelyl to generate performance regression, as creating new partitioned index block is much rarer than data blocks. 3. Separate out the prefetch logic to a helper class and both classes call them. This commit will enable future follow-ups. One direction is that we might separate index iterator interface for data blocks and index blocks, as they are quite different. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6531 Test Plan: build using make and cmake. And build release Differential Revision: D20473108 fbshipit-source-id: e48011783b339a4257c204cc07507b171b834b0f
5 years ago
table/block_based/block_prefetcher.cc
table/block_based/block_prefix_index.cc
table/block_based/data_block_hash_index.cc
table/block_based/data_block_footer.cc
table/block_based/filter_block_reader_common.cc
table/block_based/filter_policy.cc
table/block_based/flush_block_policy.cc
table/block_based/full_filter_block.cc
table/block_based/hash_index_reader.cc
table/block_based/index_builder.cc
table/block_based/index_reader_common.cc
Store the filter bits reader alongside the filter block contents (#5936) Summary: Amongst other things, PR https://github.com/facebook/rocksdb/issues/5504 refactored the filter block readers so that only the filter block contents are stored in the block cache (as opposed to the earlier design where the cache stored the filter block reader itself, leading to potentially dangling pointers and concurrency bugs). However, this change introduced a performance hit since with the new code, the metadata fields are re-parsed upon every access. This patch reunites the block contents with the filter bits reader to eliminate this overhead; since this is still a self-contained pure data object, it is safe to store it in the cache. (Note: this is similar to how the zstd digest is handled.) Pull Request resolved: https://github.com/facebook/rocksdb/pull/5936 Test Plan: make asan_check filter_bench results for the old code: ``` $ ./filter_bench -quick WARNING: Assertions are enabled; benchmarks unnecessarily slow Building... Build avg ns/key: 26.7153 Number of filters: 16669 Total memory (MB): 200.009 Bits/key actual: 10.0647 ---------------------------- Inside queries... Dry run (46b) ns/op: 33.4258 Single filter ns/op: 42.5974 Random filter ns/op: 217.861 ---------------------------- Outside queries... Dry run (25d) ns/op: 32.4217 Single filter ns/op: 50.9855 Random filter ns/op: 219.167 Average FP rate %: 1.13993 ---------------------------- Done. (For more info, run with -legend or -help.) $ ./filter_bench -quick -use_full_block_reader WARNING: Assertions are enabled; benchmarks unnecessarily slow Building... Build avg ns/key: 26.5172 Number of filters: 16669 Total memory (MB): 200.009 Bits/key actual: 10.0647 ---------------------------- Inside queries... Dry run (46b) ns/op: 32.3556 Single filter ns/op: 83.2239 Random filter ns/op: 370.676 ---------------------------- Outside queries... Dry run (25d) ns/op: 32.2265 Single filter ns/op: 93.5651 Random filter ns/op: 408.393 Average FP rate %: 1.13993 ---------------------------- Done. (For more info, run with -legend or -help.) ``` With the new code: ``` $ ./filter_bench -quick WARNING: Assertions are enabled; benchmarks unnecessarily slow Building... Build avg ns/key: 25.4285 Number of filters: 16669 Total memory (MB): 200.009 Bits/key actual: 10.0647 ---------------------------- Inside queries... Dry run (46b) ns/op: 31.0594 Single filter ns/op: 43.8974 Random filter ns/op: 226.075 ---------------------------- Outside queries... Dry run (25d) ns/op: 31.0295 Single filter ns/op: 50.3824 Random filter ns/op: 226.805 Average FP rate %: 1.13993 ---------------------------- Done. (For more info, run with -legend or -help.) $ ./filter_bench -quick -use_full_block_reader WARNING: Assertions are enabled; benchmarks unnecessarily slow Building... Build avg ns/key: 26.5308 Number of filters: 16669 Total memory (MB): 200.009 Bits/key actual: 10.0647 ---------------------------- Inside queries... Dry run (46b) ns/op: 33.2968 Single filter ns/op: 58.6163 Random filter ns/op: 291.434 ---------------------------- Outside queries... Dry run (25d) ns/op: 32.1839 Single filter ns/op: 66.9039 Random filter ns/op: 292.828 Average FP rate %: 1.13993 ---------------------------- Done. (For more info, run with -legend or -help.) ``` Differential Revision: D17991712 Pulled By: ltamasi fbshipit-source-id: 7ea205550217bfaaa1d5158ebd658e5832e60f29
5 years ago
table/block_based/parsed_full_filter_block.cc
table/block_based/partitioned_filter_block.cc
De-template block based table iterator (#6531) Summary: Right now block based table iterator is used as both of iterating data for block based table, and for the index iterator for partitioend index. This was initially convenient for introducing a new iterator and block type for new index format, while reducing code change. However, these two usage doesn't go with each other very well. For example, Prev() is never called for partitioned index iterator, and some other complexity is maintained in block based iterators, which is not needed for index iterator but maintainers will always need to reason about it. Furthermore, the template usage is not following Google C++ Style which we are following, and makes a large chunk of code tangled together. This commit separate the two iterators. Right now, here is what it is done: 1. Copy the block based iterator code into partitioned index iterator, and de-template them. 2. Remove some code not needed for partitioned index. The upper bound check and tricks are removed. We never tested performance for those tricks when partitioned index is enabled in the first place. It's unlikelyl to generate performance regression, as creating new partitioned index block is much rarer than data blocks. 3. Separate out the prefetch logic to a helper class and both classes call them. This commit will enable future follow-ups. One direction is that we might separate index iterator interface for data blocks and index blocks, as they are quite different. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6531 Test Plan: build using make and cmake. And build release Differential Revision: D20473108 fbshipit-source-id: e48011783b339a4257c204cc07507b171b834b0f
5 years ago
table/block_based/partitioned_index_iterator.cc
table/block_based/partitioned_index_reader.cc
table/block_based/reader_common.cc
table/block_based/uncompression_dict_reader.cc
table/block_fetcher.cc
table/cuckoo/cuckoo_table_builder.cc
table/cuckoo/cuckoo_table_factory.cc
table/cuckoo/cuckoo_table_reader.cc
table/format.cc
table/get_context.cc
table/iterator.cc
table/merging_iterator.cc
table/meta_blocks.cc
table/persistent_cache_helper.cc
table/plain/plain_table_bloom.cc
table/plain/plain_table_builder.cc
table/plain/plain_table_factory.cc
table/plain/plain_table_index.cc
table/plain/plain_table_key_coding.cc
table/plain/plain_table_reader.cc
table/sst_file_dumper.cc
table/sst_file_reader.cc
table/sst_file_writer.cc
table/table_factory.cc
table/table_properties.cc
table/two_level_iterator.cc
test_util/sync_point.cc
test_util/sync_point_impl.cc
test_util/testutil.cc
test_util/transaction_test_util.cc
tools/block_cache_analyzer/block_cache_trace_analyzer.cc
tools/dump/db_dump_tool.cc
tools/io_tracer_parser_tool.cc
tools/ldb_cmd.cc
tools/ldb_tool.cc
tools/sst_dump_tool.cc
RocksDB Trace Analyzer (#4091) Summary: A framework of trace analyzing for RocksDB After collecting the trace by using the tool of [PR #3837](https://github.com/facebook/rocksdb/pull/3837). User can use the Trace Analyzer to interpret, analyze, and characterize the collected workload. **Input:** 1. trace file 2. Whole keys space file **Statistics:** 1. Access count of each operation (Get, Put, Delete, SingleDelete, DeleteRange, Merge) in each column family. 2. Key hotness (access count) of each one 3. Key space separation based on given prefix 4. Key size distribution 5. Value size distribution if appliable 6. Top K accessed keys 7. QPS statistics including the average QPS and peak QPS 8. Top K accessed prefix 9. The query correlation analyzing, output the number of X after Y and the corresponding average time intervals **Output:** 1. key access heat map (either in the accessed key space or whole key space) 2. trace sequence file (interpret the raw trace file to line base text file for future use) 3. Time serial (The key space ID and its access time) 4. Key access count distritbution 5. Key size distribution 6. Value size distribution (in each intervals) 7. whole key space separation by the prefix 8. Accessed key space separation by the prefix 9. QPS of each operation and each column family 10. Top K QPS and their accessed prefix range **Test:** 1. Added the unit test of analyzing Get, Put, Delete, SingleDelete, DeleteRange, Merge 2. Generated the trace and analyze the trace **Implemented but not tested (due to the limitation of trace_replay):** 1. Analyzing Iterator, supporting Seek() and SeekForPrev() analyzing 2. Analyzing the number of Key found by Get **Future Work:** 1. Support execution time analyzing of each requests 2. Support cache hit situation and block read situation of Get Pull Request resolved: https://github.com/facebook/rocksdb/pull/4091 Differential Revision: D9256157 Pulled By: zhichao-cao fbshipit-source-id: f0ceacb7eedbc43a3eee6e85b76087d7832a8fe6
6 years ago
tools/trace_analyzer_tool.cc
trace_replay/trace_replay.cc
trace_replay/block_cache_tracer.cc
trace_replay/io_tracer.cc
util/coding.cc
util/compaction_job_stats_impl.cc
util/comparator.cc
util/compression_context_cache.cc
Concurrent task limiter for compaction thread control (#4332) Summary: The PR is targeting to resolve the issue of: https://github.com/facebook/rocksdb/issues/3972#issue-330771918 We have a rocksdb created with leveled-compaction with multiple column families (CFs), some of CFs are using HDD to store big and less frequently accessed data and others are using SSD. When there are continuously write traffics going on to all CFs, the compaction thread pool is mostly occupied by those slow HDD compactions, which blocks fully utilize SSD bandwidth. Since atomic write and transaction is needed across CFs, so splitting it to multiple rocksdb instance is not an option for us. With the compaction thread control, we got 30%+ HDD write throughput gain, and also a lot smooth SSD write since less write stall happening. ConcurrentTaskLimiter can be shared with multi-CFs across rocksdb instances, so the feature does not only work for multi-CFs scenarios, but also for multi-rocksdbs scenarios, who need disk IO resource control per tenant. The usage is straight forward: e.g.: // // Enable compaction thread limiter thru ColumnFamilyOptions // std::shared_ptr<ConcurrentTaskLimiter> ctl(NewConcurrentTaskLimiter("foo_limiter", 4)); Options options; ColumnFamilyOptions cf_opt(options); cf_opt.compaction_thread_limiter = ctl; ... // // Compaction thread limiter can be tuned or disabled on-the-fly // ctl->SetMaxOutstandingTask(12); // enlarge to 12 tasks ... ctl->ResetMaxOutstandingTask(); // disable (bypass) thread limiter ctl->SetMaxOutstandingTask(-1); // Same as above ... ctl->SetMaxOutstandingTask(0); // full throttle (0 task) // // Sharing compaction thread limiter among CFs (to resolve multiple storage perf issue) // std::shared_ptr<ConcurrentTaskLimiter> ctl_ssd(NewConcurrentTaskLimiter("ssd_limiter", 8)); std::shared_ptr<ConcurrentTaskLimiter> ctl_hdd(NewConcurrentTaskLimiter("hdd_limiter", 4)); Options options; ColumnFamilyOptions cf_opt_ssd1(options); ColumnFamilyOptions cf_opt_ssd2(options); ColumnFamilyOptions cf_opt_hdd1(options); ColumnFamilyOptions cf_opt_hdd2(options); ColumnFamilyOptions cf_opt_hdd3(options); // SSD CFs cf_opt_ssd1.compaction_thread_limiter = ctl_ssd; cf_opt_ssd2.compaction_thread_limiter = ctl_ssd; // HDD CFs cf_opt_hdd1.compaction_thread_limiter = ctl_hdd; cf_opt_hdd2.compaction_thread_limiter = ctl_hdd; cf_opt_hdd3.compaction_thread_limiter = ctl_hdd; ... // // The limiter is disabled by default (or set to nullptr explicitly) // Options options; ColumnFamilyOptions cf_opt(options); cf_opt.compaction_thread_limiter = nullptr; Pull Request resolved: https://github.com/facebook/rocksdb/pull/4332 Differential Revision: D13226590 Pulled By: siying fbshipit-source-id: 14307aec55b8bd59c8223d04aa6db3c03d1b0c1d
6 years ago
util/concurrent_task_limiter_impl.cc
util/crc32c.cc
util/dynamic_bloom.cc
util/hash.cc
util/murmurhash.cc
util/random.cc
util/rate_limiter.cc
Refine Ribbon configuration, improve testing, add Homogeneous (#7879) Summary: This change only affects non-schema-critical aspects of the production candidate Ribbon filter. Specifically, it refines choice of internal configuration parameters based on inputs. The changes are minor enough that the schema tests in bloom_test, some of which depend on this, are unaffected. There are also some minor optimizations and refactorings. This would be a schema change for "smash" Ribbon, to fix some known issues with small filters, but "smash" Ribbon is not accessible in public APIs. Unit test CompactnessAndBacktrackAndFpRate updated to test small and medium-large filters. Run with --thoroughness=100 or so for much better detection power (not appropriate for continuous regression testing). Homogenous Ribbon: This change adds internally a Ribbon filter variant we call Homogeneous Ribbon, in collaboration with Stefan Walzer. The expected "result" value for every key is zero, instead of computed from a hash. Entropy for queries not to be false positives comes from free variables ("overhead") in the solution structure, which are populated pseudorandomly. Construction is slightly faster for not tracking result values, and never fails. Instead, FP rate can jump up whenever and whereever entries are packed too tightly. For small structures, we can choose overhead to make this FP rate jump unlikely, as seen in updated unit test CompactnessAndBacktrackAndFpRate. Unlike standard Ribbon, Homogeneous Ribbon seems to scale to arbitrary number of keys when accepting an FP rate penalty for small pockets of high FP rate in the structure. For example, 64-bit ribbon with 8 solution columns and 10% allocated space overhead for slots seems to achieve about 10.5% space overhead vs. information-theoretic minimum based on its observed FP rate with expected pockets of degradation. (FP rate is close to 1/256.) If targeting a higher FP rate with fewer solution columns, Homogeneous Ribbon can be even more space efficient, because the penalty from degradation is relatively smaller. If targeting a lower FP rate, Homogeneous Ribbon is less space efficient, as more allocated overhead is needed to keep the FP rate impact of degradation relatively under control. The new OptimizeHomogAtScale tool in ribbon_test helps to find these optimal allocation overheads for different numbers of solution columns. And Ribbon widths, with 128-bit Ribbon apparently cutting space overheads in half vs. 64-bit. Other misc item specifics: * Ribbon APIs in util/ribbon_config.h now provide configuration data for not just 5% construction failure rate (95% success), but also 50% and 0.1%. * Note that the Ribbon structure does not exhibit "threshold" behavior as standard Xor filter does, so there is a roughly fixed space penalty to cut construction failure rate in half. Thus, there isn't really an "almost sure" setting. * Although we can extrapolate settings for large filters, we don't have a good formula for configuring smaller filters (< 2^17 slots or so), and efforts to summarize with a formula have failed. Thus, small data is hard-coded from updated FindOccupancy tool. * Enhances ApproximateNumEntries for public API Ribbon using more precise data (new API GetNumToAdd), thus a more accurate but not perfect reversal of CalculateSpace. (bloom_test updated to expect the greater precision) * Move EndianSwapValue from coding.h to coding_lean.h to keep Ribbon code easily transferable from RocksDB * Add some missing 'const' to member functions * Small optimization to 128-bit BitParity * Small refactoring of BandingStorage in ribbon_alg.h to support Homogeneous Ribbon * CompactnessAndBacktrackAndFpRate now has an "expand" test: on construction failure, a possible alternative to re-seeding hash functions is simply to increase the number of slots (allocated space overhead) and try again with essentially the same hash values. (Start locations will be different roundings of the same scaled hash values--because fastrange not mod.) This seems to be as effective or more effective than re-seeding, as long as we increase the number of slots (m) by roughly m += m/w where w is the Ribbon width. This way, there is effectively an expansion by one slot for each ribbon-width window in the banding. (This approach assumes that getting "bad data" from your hash function is as unlikely as it naturally should be, e.g. no adversary.) * 32-bit and 16-bit Ribbon configurations are added to ribbon_test for understanding their behavior, e.g. with FindOccupancy. They are not considered useful at this time and not tested with CompactnessAndBacktrackAndFpRate. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7879 Test Plan: unit test updates included Reviewed By: jay-zhuang Differential Revision: D26371245 Pulled By: pdillinger fbshipit-source-id: da6600d90a3785b99ad17a88b2a3027710b4ea3a
4 years ago
util/ribbon_config.cc
util/slice.cc
util/file_checksum_helper.cc
util/status.cc
util/string_util.cc
util/thread_local.cc
util/threadpool_imp.cc
util/xxhash.cc
utilities/backupable/backupable_db.cc
utilities/blob_db/blob_compaction_filter.cc
utilities/blob_db/blob_db.cc
utilities/blob_db/blob_db_impl.cc
utilities/blob_db/blob_db_impl_filesnapshot.cc
utilities/blob_db/blob_dump_tool.cc
utilities/blob_db/blob_file.cc
utilities/cassandra/cassandra_compaction_filter.cc
utilities/cassandra/format.cc
utilities/cassandra/merge_operator.cc
utilities/checkpoint/checkpoint_impl.cc
utilities/compaction_filters.cc
utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
utilities/debug.cc
utilities/env_mirror.cc
utilities/env_timed.cc
utilities/fault_injection_env.cc
utilities/fault_injection_fs.cc
utilities/leveldb_options/leveldb_options.cc
utilities/memory/memory_util.cc
utilities/merge_operators.cc
utilities/merge_operators/bytesxor.cc
utilities/merge_operators/max.cc
utilities/merge_operators/put.cc
New API to get all merge operands for a Key (#5604) Summary: This is a new API added to db.h to allow for fetching all merge operands associated with a Key. The main motivation for this API is to support use cases where doing a full online merge is not necessary as it is performance sensitive. Example use-cases: 1. Update subset of columns and read subset of columns - Imagine a SQL Table, a row is encoded as a K/V pair (as it is done in MyRocks). If there are many columns and users only updated one of them, we can use merge operator to reduce write amplification. While users only read one or two columns in the read query, this feature can avoid a full merging of the whole row, and save some CPU. 2. Updating very few attributes in a value which is a JSON-like document - Updating one attribute can be done efficiently using merge operator, while reading back one attribute can be done more efficiently if we don't need to do a full merge. ---------------------------------------------------------------------------------------------------- API : Status GetMergeOperands( const ReadOptions& options, ColumnFamilyHandle* column_family, const Slice& key, PinnableSlice* merge_operands, GetMergeOperandsOptions* get_merge_operands_options, int* number_of_operands) Example usage : int size = 100; int number_of_operands = 0; std::vector<PinnableSlice> values(size); GetMergeOperandsOptions merge_operands_info; db_->GetMergeOperands(ReadOptions(), db_->DefaultColumnFamily(), "k1", values.data(), merge_operands_info, &number_of_operands); Description : Returns all the merge operands corresponding to the key. If the number of merge operands in DB is greater than merge_operands_options.expected_max_number_of_operands no merge operands are returned and status is Incomplete. Merge operands returned are in the order of insertion. merge_operands-> Points to an array of at-least merge_operands_options.expected_max_number_of_operands and the caller is responsible for allocating it. If the status returned is Incomplete then number_of_operands will contain the total number of merge operands found in DB for key. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5604 Test Plan: Added unit test and perf test in db_bench that can be run using the command: ./db_bench -benchmarks=getmergeoperands --merge_operator=sortlist Differential Revision: D16657366 Pulled By: vjnadimpalli fbshipit-source-id: 0faadd752351745224ee12d4ae9ef3cb529951bf
5 years ago
utilities/merge_operators/sortlist.cc
utilities/merge_operators/string_append/stringappend.cc
utilities/merge_operators/string_append/stringappend2.cc
utilities/merge_operators/uint64add.cc
utilities/object_registry.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/simulator_cache/cache_simulator.cc
utilities/simulator_cache/sim_cache.cc
utilities/table_properties_collectors/compact_on_deletion_collector.cc
utilities/trace/file_trace_reader_writer.cc
utilities/transactions/lock/lock_manager.cc
utilities/transactions/lock/point/point_lock_tracker.cc
utilities/transactions/lock/point/point_lock_manager.cc
utilities/transactions/lock/range/range_tree/range_tree_lock_manager.cc
utilities/transactions/lock/range/range_tree/range_tree_lock_tracker.cc
utilities/transactions/optimistic_transaction_db_impl.cc
utilities/transactions/optimistic_transaction.cc
utilities/transactions/pessimistic_transaction.cc
utilities/transactions/pessimistic_transaction_db.cc
utilities/transactions/snapshot_checker.cc
utilities/transactions/transaction_base.cc
utilities/transactions/transaction_db_mutex_impl.cc
utilities/transactions/transaction_util.cc
utilities/transactions/write_prepared_txn.cc
utilities/transactions/write_prepared_txn_db.cc
utilities/transactions/write_unprepared_txn.cc
utilities/transactions/write_unprepared_txn_db.cc
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)
list(APPEND SOURCES
utilities/transactions/lock/range/range_tree/lib/locktree/concurrent_tree.cc
utilities/transactions/lock/range/range_tree/lib/locktree/keyrange.cc
utilities/transactions/lock/range/range_tree/lib/locktree/lock_request.cc
utilities/transactions/lock/range/range_tree/lib/locktree/locktree.cc
utilities/transactions/lock/range/range_tree/lib/locktree/manager.cc
utilities/transactions/lock/range/range_tree/lib/locktree/range_buffer.cc
utilities/transactions/lock/range/range_tree/lib/locktree/treenode.cc
utilities/transactions/lock/range/range_tree/lib/locktree/txnid_set.cc
utilities/transactions/lock/range/range_tree/lib/locktree/wfg.cc
utilities/transactions/lock/range/range_tree/lib/standalone_port.cc
utilities/transactions/lock/range/range_tree/lib/util/dbt.cc
utilities/transactions/lock/range/range_tree/lib/util/memarena.cc)
if(HAVE_SSE42 AND NOT MSVC)
set_source_files_properties(
util/crc32c.cc
PROPERTIES COMPILE_FLAGS "-msse4.2 -mpclmul")
endif()
if(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
list(APPEND SOURCES
util/crc32c_ppc.c
util/crc32c_ppc_asm.S)
endif(CMAKE_SYSTEM_PROCESSOR MATCHES "^(powerpc|ppc)64")
if(HAS_ARMV8_CRC)
list(APPEND SOURCES
util/crc32c_arm64.cc)
endif(HAS_ARMV8_CRC)
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)
if(WITH_XPRESS)
list(APPEND SOURCES
port/win/xpress_win.cc)
endif()
if(WITH_JEMALLOC)
list(APPEND SOURCES
port/win/win_jemalloc.cc)
endif()
else()
list(APPEND SOURCES
port/port_posix.cc
env/env_posix.cc
Introduce a new storage specific Env API (#5761) Summary: The current Env API encompasses both storage/file operations, as well as OS related operations. Most of the APIs return a Status, which does not have enough metadata about an error, such as whether its retry-able or not, scope (i.e fault domain) of the error etc., that may be required in order to properly handle a storage error. The file APIs also do not provide enough control over the IO SLA, such as timeout, prioritization, hinting about placement and redundancy etc. This PR separates out the file/storage APIs from Env into a new FileSystem class. The APIs are updated to return an IOStatus with metadata about the error, as well as to take an IOOptions structure as input in order to allow more control over the IO. The user can set both ```options.env``` and ```options.file_system``` to specify that RocksDB should use the former for OS related operations and the latter for storage operations. Internally, a ```CompositeEnvWrapper``` has been introduced that inherits from ```Env``` and redirects individual methods to either an ```Env``` implementation or the ```FileSystem``` as appropriate. When options are sanitized during ```DB::Open```, ```options.env``` is replaced with a newly allocated ```CompositeEnvWrapper``` instance if both env and file_system have been specified. This way, the rest of the RocksDB code can continue to function as before. This PR also ports PosixEnv to the new API by splitting it into two - PosixEnv and PosixFileSystem. PosixEnv is defined as a sub-class of CompositeEnvWrapper, and threading/time functions are overridden with Posix specific implementations in order to avoid an extra level of indirection. The ```CompositeEnvWrapper``` translates ```IOStatus``` return code to ```Status```, and sets the severity to ```kSoftError``` if the io_status is retryable. The error handling code in RocksDB can then recover the DB automatically. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5761 Differential Revision: D18868376 Pulled By: anand1976 fbshipit-source-id: 39efe18a162ea746fabac6360ff529baba48486f
5 years ago
env/fs_posix.cc
env/io_posix.cc)
endif()
if(WITH_FOLLY_DISTRIBUTED_MUTEX)
list(APPEND SOURCES
third-party/folly/folly/detail/Futex.cpp
third-party/folly/folly/synchronization/AtomicNotification.cpp
third-party/folly/folly/synchronization/DistributedMutex.cpp
third-party/folly/folly/synchronization/ParkingLot.cpp
third-party/folly/folly/synchronization/WaitOptions.cpp)
endif()
set(ROCKSDB_STATIC_LIB rocksdb${ARTIFACT_SUFFIX})
set(ROCKSDB_SHARED_LIB rocksdb-shared${ARTIFACT_SUFFIX})
option(ROCKSDB_BUILD_SHARED "Build shared versions of the RocksDB libraries" ON)
option(WITH_LIBRADOS "Build with librados" OFF)
if(WITH_LIBRADOS)
list(APPEND SOURCES
utilities/env_librados.cc)
list(APPEND THIRDPARTY_LIBS rados)
endif()
if(WIN32)
set(SYSTEM_LIBS ${SYSTEM_LIBS} shlwapi.lib rpcrt4.lib)
else()
cross-platform compatibility improvements Summary: We've had a couple CockroachDB users fail to build RocksDB on exotic platforms, so I figured I'd try my hand at solving these issues upstream. The problems stem from a) `USE_SSE=1` being too aggressive about turning on SSE4.2, even on toolchains that don't support SSE4.2 and b) RocksDB attempting to detect support for thread-local storage based on OS, even though it can vary by compiler on the same OS. See the individual commit messages for details. Regarding SSE support, this PR should change virtually nothing for non-CMake based builds. `make`, `PORTABLE=1 make`, `USE_SSE=1 make`, and `PORTABLE=1 USE_SSE=1 make` function exactly as before, except that SSE support will be automatically disabled when a simple SSE4.2-using test program fails to compile, as it does on OpenBSD. (OpenBSD's ports GCC supports SSE4.2, but its binutils do not, so `__SSE_4_2__` is defined but an SSE4.2-using program will fail to assemble.) A warning is emitted in this case. The CMake build is modified to support the same set of options, except that `USE_SSE` is spelled `FORCE_SSE42` because `USE_SSE` is rather useless now that we can automatically detect SSE support, and I figure changing options in the CMake build is less disruptive than changing the non-CMake build. I've tested these changes on all the platforms I can get my hands on (macOS, Windows MSVC, Windows MinGW, and OpenBSD) and it all works splendidly. Let me know if there's anything you object to—I obviously don't mean to break any of your build pipelines in the process of fixing ours downstream. Closes https://github.com/facebook/rocksdb/pull/2199 Differential Revision: D5054042 Pulled By: yiwu-arbug fbshipit-source-id: 938e1fc665c049c02ae15698e1409155b8e72171
8 years ago
set(SYSTEM_LIBS ${CMAKE_THREAD_LIBS_INIT})
endif()
add_library(${ROCKSDB_STATIC_LIB} STATIC ${SOURCES} ${BUILD_VERSION_CC})
target_link_libraries(${ROCKSDB_STATIC_LIB} PRIVATE
${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
if(ROCKSDB_BUILD_SHARED)
add_library(${ROCKSDB_SHARED_LIB} SHARED ${SOURCES} ${BUILD_VERSION_CC})
target_link_libraries(${ROCKSDB_SHARED_LIB} PRIVATE
${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
if(WIN32)
set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
COMPILE_DEFINITIONS "ROCKSDB_DLL;ROCKSDB_LIBRARY_EXPORTS")
if(MSVC)
set_target_properties(${ROCKSDB_STATIC_LIB} PROPERTIES
COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_STATIC_LIB}.pdb")
set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/${ROCKSDB_SHARED_LIB}.pdb")
endif()
else()
set_target_properties(${ROCKSDB_SHARED_LIB} PROPERTIES
LINKER_LANGUAGE CXX
VERSION ${rocksdb_VERSION}
SOVERSION ${rocksdb_VERSION_MAJOR}
OUTPUT_NAME "rocksdb${ARTIFACT_SUFFIX}")
endif()
endif()
if(ROCKSDB_BUILD_SHARED AND NOT WIN32)
set(ROCKSDB_LIB ${ROCKSDB_SHARED_LIB})
else()
set(ROCKSDB_LIB ${ROCKSDB_STATIC_LIB})
endif()
option(WITH_JNI "build with JNI" OFF)
# Tests are excluded from Release builds
CMAKE_DEPENDENT_OPTION(WITH_TESTS "build with tests" ON
"CMAKE_BUILD_TYPE STREQUAL Debug" OFF)
option(WITH_BENCHMARK_TOOLS "build with benchmarks" ON)
option(WITH_CORE_TOOLS "build with ldb and sst_dump" ON)
option(WITH_TOOLS "build with tools" ON)
if(WITH_TESTS OR WITH_BENCHMARK_TOOLS OR WITH_TOOLS OR WITH_JNI OR JNI)
include_directories(SYSTEM ${PROJECT_SOURCE_DIR}/third-party/gtest-1.8.1/fused-src)
endif()
if(WITH_JNI OR JNI)
message(STATUS "JNI library is enabled")
add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/java)
else()
message(STATUS "JNI library is disabled")
endif()
# Installation and packaging
if(WIN32)
option(ROCKSDB_INSTALL_ON_WINDOWS "Enable install target on Windows" OFF)
endif()
if(NOT WIN32 OR ROCKSDB_INSTALL_ON_WINDOWS)
if(CMAKE_INSTALL_PREFIX_INITIALIZED_TO_DEFAULT)
if(${CMAKE_SYSTEM_NAME} STREQUAL "Linux")
# Change default installation prefix on Linux to /usr
set(CMAKE_INSTALL_PREFIX /usr CACHE PATH "Install path prefix, prepended onto install directories." FORCE)
endif()
endif()
include(GNUInstallDirs)
include(CMakePackageConfigHelpers)
set(package_config_destination ${CMAKE_INSTALL_LIBDIR}/cmake/rocksdb)
configure_package_config_file(
${CMAKE_CURRENT_LIST_DIR}/cmake/RocksDBConfig.cmake.in RocksDBConfig.cmake
INSTALL_DESTINATION ${package_config_destination}
)
write_basic_package_version_file(
RocksDBConfigVersion.cmake
VERSION ${rocksdb_VERSION}
COMPATIBILITY SameMajorVersion
)
install(DIRECTORY include/rocksdb COMPONENT devel DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}")
install(DIRECTORY "${PROJECT_SOURCE_DIR}/cmake/modules" COMPONENT devel DESTINATION ${package_config_destination})
install(
TARGETS ${ROCKSDB_STATIC_LIB}
EXPORT RocksDBTargets
COMPONENT devel
ARCHIVE DESTINATION "${CMAKE_INSTALL_LIBDIR}"
INCLUDES DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
)
if(ROCKSDB_BUILD_SHARED)
install(
TARGETS ${ROCKSDB_SHARED_LIB}
EXPORT RocksDBTargets
COMPONENT runtime
ARCHIVE DESTINATION "${CMAKE_INSTALL_LIBDIR}"
RUNTIME DESTINATION "${CMAKE_INSTALL_BINDIR}"
LIBRARY DESTINATION "${CMAKE_INSTALL_LIBDIR}"
INCLUDES DESTINATION "${CMAKE_INSTALL_INCLUDEDIR}"
)
endif()
install(
EXPORT RocksDBTargets
COMPONENT devel
DESTINATION ${package_config_destination}
NAMESPACE RocksDB::
)
install(
FILES
${CMAKE_CURRENT_BINARY_DIR}/RocksDBConfig.cmake
${CMAKE_CURRENT_BINARY_DIR}/RocksDBConfigVersion.cmake
COMPONENT devel
DESTINATION ${package_config_destination}
)
endif()
option(WITH_ALL_TESTS "Build all test, rather than a small subset" ON)
if(WITH_TESTS OR WITH_BENCHMARK_TOOLS)
add_subdirectory(third-party/gtest-1.8.1/fused-src/gtest)
add_library(testharness STATIC
test_util/mock_time_env.cc
test_util/testharness.cc)
target_link_libraries(testharness gtest)
endif()
if(WITH_TESTS)
set(TESTS
db/db_basic_test.cc
env/env_basic_test.cc
)
if(WITH_ALL_TESTS)
list(APPEND TESTS
cache/cache_test.cc
cache/lru_cache_test.cc
db/blob/blob_counting_iterator_test.cc
db/blob/blob_file_addition_test.cc
db/blob/blob_file_builder_test.cc
db/blob/blob_file_cache_test.cc
db/blob/blob_file_garbage_test.cc
Introduce a blob file reader class (#7461) Summary: The patch adds a class called `BlobFileReader` that can be used to retrieve blobs using the information available in blob references (e.g. blob file number, offset, and size). This will come in handy when implementing blob support for `Get`, `MultiGet`, and iterators, and also for compaction/garbage collection. When a `BlobFileReader` object is created (using the factory method `Create`), it first checks whether the specified file is potentially valid by comparing the file size against the combined size of the blob file header and footer (files smaller than the threshold are considered malformed). Then, it opens the file, and reads and verifies the header and footer. The verification involves magic number/CRC checks as well as checking for unexpected header/footer fields, e.g. incorrect column family ID or TTL blob files. Blobs can be retrieved using `GetBlob`. `GetBlob` validates the offset and compression type passed by the caller (because of the presence of the header and footer, the specified offset cannot be too close to the start/end of the file; also, the compression type has to match the one in the blob file header), and retrieves and potentially verifies and uncompresses the blob. In particular, when `ReadOptions::verify_checksums` is set, `BlobFileReader` reads the blob record header as well (as opposed to just the blob itself) and verifies the key/value size, the key itself, as well as the CRC of the blob record header and the key/value pair. In addition, the patch exposes the compression type from `BlobIndex` (both using an accessor and via `DebugString`), and adds a blob file read latency histogram to `InternalStats` that can be used with `BlobFileReader`. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7461 Test Plan: `make check` Reviewed By: riversand963 Differential Revision: D23999219 Pulled By: ltamasi fbshipit-source-id: deb6b1160d251258b308d5156e2ec063c3e12e5e
4 years ago
db/blob/blob_file_reader_test.cc
db/blob/blob_garbage_meter_test.cc
db/blob/db_blob_basic_test.cc
db/blob/db_blob_compaction_test.cc
db/blob/db_blob_corruption_test.cc
db/blob/db_blob_index_test.cc
db/column_family_test.cc
db/compact_files_test.cc
db/compaction/clipping_iterator_test.cc
db/compaction/compaction_job_stats_test.cc
db/compaction/compaction_job_test.cc
db/compaction/compaction_iterator_test.cc
db/compaction/compaction_picker_test.cc
db/compaction/compaction_service_test.cc
db/comparator_db_test.cc
db/corruption_test.cc
db/cuckoo_table_db_test.cc
db/db_with_timestamp_basic_test.cc
db/db_block_cache_test.cc
db/db_bloom_filter_test.cc
db/db_compaction_filter_test.cc
db/db_compaction_test.cc
db/db_dynamic_level_test.cc
db/db_flush_test.cc
db/db_inplace_update_test.cc
db/db_io_failure_test.cc
db/db_iter_test.cc
Change and clarify the relationship between Valid(), status() and Seek*() for all iterators. Also fix some bugs Summary: Before this PR, Iterator/InternalIterator may simultaneously have non-ok status() and Valid() = true. That state means that the last operation failed, but the iterator is nevertheless positioned on some unspecified record. Likely intended uses of that are: * If some sst files are corrupted, a normal iterator can be used to read the data from files that are not corrupted. * When using read_tier = kBlockCacheTier, read the data that's in block cache, skipping over the data that is not. However, this behavior wasn't documented well (and until recently the wiki on github had misleading incorrect information). In the code there's a lot of confusion about the relationship between status() and Valid(), and about whether Seek()/SeekToLast()/etc reset the status or not. There were a number of bugs caused by this confusion, both inside rocksdb and in the code that uses rocksdb (including ours). This PR changes the convention to: * If status() is not ok, Valid() always returns false. * Any seek operation resets status. (Before the PR, it depended on iterator type and on particular error.) This does sacrifice the two use cases listed above, but siying said it's ok. Overview of the changes: * A commit that adds missing status checks in MergingIterator. This fixes a bug that actually affects us, and we need it fixed. `DBIteratorTest.NonBlockingIterationBugRepro` explains the scenario. * Changes to lots of iterator types to make all of them conform to the new convention. Some bug fixes along the way. By far the biggest changes are in DBIter, which is a big messy piece of code; I tried to make it less big and messy but mostly failed. * A stress-test for DBIter, to gain some confidence that I didn't break it. It does a few million random operations on the iterator, while occasionally modifying the underlying data (like ForwardIterator does) and occasionally returning non-ok status from internal iterator. To find the iterator types that needed changes I searched for "public .*Iterator" in the code. Here's an overview of all 27 iterator types: Iterators that didn't need changes: * status() is always ok(), or Valid() is always false: MemTableIterator, ModelIter, TestIterator, KVIter (2 classes with this name anonymous namespaces), LoggingForwardVectorIterator, VectorIterator, MockTableIterator, EmptyIterator, EmptyInternalIterator. * Thin wrappers that always pass through Valid() and status(): ArenaWrappedDBIter, TtlIterator, InternalIteratorFromIterator. Iterators with changes (see inline comments for details): * DBIter - an overhaul: - It used to silently skip corrupted keys (`FindParseableKey()`), which seems dangerous. This PR makes it just stop immediately after encountering a corrupted key, just like it would for other kinds of corruption. Let me know if there was actually some deeper meaning in this behavior and I should put it back. - It had a few code paths silently discarding subiterator's status. The stress test caught a few. - The backwards iteration code path was expecting the internal iterator's set of keys to be immutable. It's probably always true in practice at the moment, since ForwardIterator doesn't support backwards iteration, but this PR fixes it anyway. See added DBIteratorTest.ReverseToForwardBug for an example. - Some parts of backwards iteration code path even did things like `assert(iter_->Valid())` after a seek, which is never a safe assumption. - It used to not reset status on seek for some types of errors. - Some simplifications and better comments. - Some things got more complicated from the added error handling. I'm open to ideas for how to make it nicer. * MergingIterator - check status after every operation on every subiterator, and in some places assert that valid subiterators have ok status. * ForwardIterator - changed to the new convention, also slightly simplified. * ForwardLevelIterator - fixed some bugs and simplified. * LevelIterator - simplified. * TwoLevelIterator - changed to the new convention. Also fixed a bug that would make SeekForPrev() sometimes silently ignore errors from first_level_iter_. * BlockBasedTableIterator - minor changes. * BlockIter - replaced `SetStatus()` with `Invalidate()` to make sure non-ok BlockIter is always invalid. * PlainTableIterator - some seeks used to not reset status. * CuckooTableIterator - tiny code cleanup. * ManagedIterator - fixed some bugs. * BaseDeltaIterator - changed to the new convention and fixed a bug. * BlobDBIterator - seeks used to not reset status. * KeyConvertingIterator - some small change. Closes https://github.com/facebook/rocksdb/pull/3810 Differential Revision: D7888019 Pulled By: al13n321 fbshipit-source-id: 4aaf6d3421c545d16722a815b2fa2e7912bc851d
7 years ago
db/db_iter_stress_test.cc
db/db_iterator_test.cc
Integrity protection for live updates to WriteBatch (#7748) Summary: This PR adds the foundation classes for key-value integrity protection and the first use case: protecting live updates from the source buffers added to `WriteBatch` through the destination buffer in `MemTable`. The width of the protection info is not yet configurable -- only eight bytes per key is supported. This PR allows users to enable protection by constructing `WriteBatch` with `protection_bytes_per_key == 8`. It does not yet expose a way for users to get integrity protection via other write APIs (e.g., `Put()`, `Merge()`, `Delete()`, etc.). The foundation classes (`ProtectionInfo.*`) embed the coverage info in their type, and provide `Protect.*()` and `Strip.*()` functions to navigate between types with different coverage. For making bytes per key configurable (for powers of two up to eight) in the future, these classes are templated on the unsigned integer type used to store the protection info. That integer contains the XOR'd result of hashes with independent seeds for all covered fields. For integer fields, the hash is computed on the raw unadjusted bytes, so the result is endian-dependent. The most significant bytes are truncated when the hash value (8 bytes) is wider than the protection integer. When `WriteBatch` is constructed with `protection_bytes_per_key == 8`, we hold a `ProtectionInfoKVOTC` (i.e., one that covers key, value, optype aka `ValueType`, timestamp, and CF ID) for each entry added to the batch. The protection info is generated from the original buffers passed by the user, as well as the original metadata generated internally. When writing to memtable, each entry is transformed to a `ProtectionInfoKVOTS` (i.e., dropping coverage of CF ID and adding coverage of sequence number), since at that point we know the sequence number, and have already selected a memtable corresponding to a particular CF. This protection info is verified once the entry is encoded in the `MemTable` buffer. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7748 Test Plan: - an integration test to verify a wide variety of single-byte changes to the encoded `MemTable` buffer are caught - add to stress/crash test to verify it works in variety of configs/operations without intentional corruption - [deferred] unit tests for `ProtectionInfo.*` classes for edge cases like KV swap, `SliceParts` and `Slice` APIs are interchangeable, etc. Reviewed By: pdillinger Differential Revision: D25754492 Pulled By: ajkr fbshipit-source-id: e481bac6c03c2ab268be41359730f1ceb9964866
4 years ago
db/db_kv_checksum_test.cc
db/db_log_iter_test.cc
db/db_memtable_test.cc
db/db_merge_operator_test.cc
New API to get all merge operands for a Key (#5604) Summary: This is a new API added to db.h to allow for fetching all merge operands associated with a Key. The main motivation for this API is to support use cases where doing a full online merge is not necessary as it is performance sensitive. Example use-cases: 1. Update subset of columns and read subset of columns - Imagine a SQL Table, a row is encoded as a K/V pair (as it is done in MyRocks). If there are many columns and users only updated one of them, we can use merge operator to reduce write amplification. While users only read one or two columns in the read query, this feature can avoid a full merging of the whole row, and save some CPU. 2. Updating very few attributes in a value which is a JSON-like document - Updating one attribute can be done efficiently using merge operator, while reading back one attribute can be done more efficiently if we don't need to do a full merge. ---------------------------------------------------------------------------------------------------- API : Status GetMergeOperands( const ReadOptions& options, ColumnFamilyHandle* column_family, const Slice& key, PinnableSlice* merge_operands, GetMergeOperandsOptions* get_merge_operands_options, int* number_of_operands) Example usage : int size = 100; int number_of_operands = 0; std::vector<PinnableSlice> values(size); GetMergeOperandsOptions merge_operands_info; db_->GetMergeOperands(ReadOptions(), db_->DefaultColumnFamily(), "k1", values.data(), merge_operands_info, &number_of_operands); Description : Returns all the merge operands corresponding to the key. If the number of merge operands in DB is greater than merge_operands_options.expected_max_number_of_operands no merge operands are returned and status is Incomplete. Merge operands returned are in the order of insertion. merge_operands-> Points to an array of at-least merge_operands_options.expected_max_number_of_operands and the caller is responsible for allocating it. If the status returned is Incomplete then number_of_operands will contain the total number of merge operands found in DB for key. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5604 Test Plan: Added unit test and perf test in db_bench that can be run using the command: ./db_bench -benchmarks=getmergeoperands --merge_operator=sortlist Differential Revision: D16657366 Pulled By: vjnadimpalli fbshipit-source-id: 0faadd752351745224ee12d4ae9ef3cb529951bf
5 years ago
db/db_merge_operand_test.cc
db/db_options_test.cc
db/db_properties_test.cc
db/db_range_del_test.cc
db/db_secondary_test.cc
db/db_sst_test.cc
db/db_statistics_test.cc
db/db_table_properties_test.cc
db/db_tailing_iter_test.cc
db/db_test.cc
db/db_test2.cc
db/db_logical_block_size_cache_test.cc
db/db_universal_compaction_test.cc
db/db_wal_test.cc
db/db_with_timestamp_compaction_test.cc
db/db_write_test.cc
db/dbformat_test.cc
db/deletefile_test.cc
db/error_handler_fs_test.cc
Fix race condition causing double deletion of ssts Summary: Possible interleaved execution of background compaction thread calling `FindObsoleteFiles (no full scan) / PurgeObsoleteFiles` and user thread calling `FindObsoleteFiles (full scan) / PurgeObsoleteFiles` can lead to race condition on which RocksDB attempts to delete a file twice. The second attempt will fail and return `IO error`. This may occur to other files, but this PR targets sst. Also add a unit test to verify that this PR fixes the issue. The newly added unit test `obsolete_files_test` has a test case for this scenario, implemented in `ObsoleteFilesTest#RaceForObsoleteFileDeletion`. `TestSyncPoint`s are used to coordinate the interleaving the `user_thread` and background compaction thread. They execute as follows ``` timeline user_thread background_compaction thread t1 | FindObsoleteFiles(full_scan=false) t2 | FindObsoleteFiles(full_scan=true) t3 | PurgeObsoleteFiles t4 | PurgeObsoleteFiles V ``` When `user_thread` invokes `FindObsoleteFiles` with full scan, it collects ALL files in RocksDB directory, including the ones that background compaction thread have collected in its job context. Then `user_thread` will see an IO error when trying to delete these files in `PurgeObsoleteFiles` because background compaction thread has already deleted the file in `PurgeObsoleteFiles`. To fix this, we make RocksDB remember which (SST) files have been found by threads after calling `FindObsoleteFiles` (see `DBImpl#files_grabbed_for_purge_`). Therefore, when another thread calls `FindObsoleteFiles` with full scan, it will not collect such files. ajkr could you take a look and comment? Thanks! Closes https://github.com/facebook/rocksdb/pull/3638 Differential Revision: D7384372 Pulled By: riversand963 fbshipit-source-id: 01489516d60012e722ee65a80e1449e589ce26d3
7 years ago
db/obsolete_files_test.cc
db/external_sst_file_basic_test.cc
db/external_sst_file_test.cc
db/fault_injection_test.cc
db/file_indexer_test.cc
db/filename_test.cc
db/flush_job_test.cc
db/listener_test.cc
db/log_test.cc
db/manual_compaction_test.cc
db/memtable_list_test.cc
db/merge_helper_test.cc
db/merge_test.cc
db/options_file_test.cc
db/perf_context_test.cc
db/periodic_work_scheduler_test.cc
db/plain_table_db_test.cc
db/prefix_test.cc
Use only "local" range tombstones during Get (#4449) Summary: Previously, range tombstones were accumulated from every level, which was necessary if a range tombstone in a higher level covered a key in a lower level. However, RangeDelAggregator::AddTombstones's complexity is based on the number of tombstones that are currently stored in it, which is wasteful in the Get case, where we only need to know the highest sequence number of range tombstones that cover the key from higher levels, and compute the highest covering sequence number at the current level. This change introduces this optimization, and removes the use of RangeDelAggregator from the Get path. In the benchmark results, the following command was used to initialize the database: ``` ./db_bench -db=/dev/shm/5k-rts -use_existing_db=false -benchmarks=filluniquerandom -write_buffer_size=1048576 -compression_type=lz4 -target_file_size_base=1048576 -max_bytes_for_level_base=4194304 -value_size=112 -key_size=16 -block_size=4096 -level_compaction_dynamic_level_bytes=true -num=5000000 -max_background_jobs=12 -benchmark_write_rate_limit=20971520 -range_tombstone_width=100 -writes_per_range_tombstone=100 -max_num_range_tombstones=50000 -bloom_bits=8 ``` ...and the following command was used to measure read throughput: ``` ./db_bench -db=/dev/shm/5k-rts/ -use_existing_db=true -benchmarks=readrandom -disable_auto_compactions=true -num=5000000 -reads=100000 -threads=32 ``` The filluniquerandom command was only run once, and the resulting database was used to measure read performance before and after the PR. Both binaries were compiled with `DEBUG_LEVEL=0`. Readrandom results before PR: ``` readrandom : 4.544 micros/op 220090 ops/sec; 16.9 MB/s (63103 of 100000 found) ``` Readrandom results after PR: ``` readrandom : 11.147 micros/op 89707 ops/sec; 6.9 MB/s (63103 of 100000 found) ``` So it's actually slower right now, but this PR paves the way for future optimizations (see #4493). ---- Pull Request resolved: https://github.com/facebook/rocksdb/pull/4449 Differential Revision: D10370575 Pulled By: abhimadan fbshipit-source-id: 9a2e152be1ef36969055c0e9eb4beb0d96c11f4d
6 years ago
db/range_del_aggregator_test.cc
db/range_tombstone_fragmenter_test.cc
db/repair_test.cc
db/table_properties_collector_test.cc
db/version_builder_test.cc
db/version_edit_test.cc
db/version_set_test.cc
db/wal_manager_test.cc
Define WAL related classes to be used in VersionEdit and VersionSet (#7164) Summary: `WalAddition`, `WalDeletion` are defined in `wal_version.h` and used in `VersionEdit`. `WalAddition` is used to represent events of creating a new WAL (no size, just log number), or closing a WAL (with size). `WalDeletion` is used to represent events of deleting or archiving a WAL, it means the WAL is no longer alive (won't be replayed during recovery). `WalSet` is the set of alive WALs kept in `VersionSet`. 1. Why use `WalDeletion` instead of relying on `MinLogNumber` to identify outdated WALs On recovery, we can compute `MinLogNumber()` based on the log numbers kept in MANIFEST, any log with number < MinLogNumber can be ignored. So it seems that we don't need to persist `WalDeletion` to MANIFEST, since we can ignore the WALs based on MinLogNumber. But the `MinLogNumber()` is actually a lower bound, it does not exactly mean that logs starting from MinLogNumber must exist. This is because in a corner case, when a column family is empty and never flushed, its log number is set to the largest log number, but not persisted in MANIFEST. So let's say there are 2 column families, when creating the DB, the first WAL has log number 1, so it's persisted to MANIFEST for both column families. Then CF 0 is empty and never flushed, CF 1 is updated and flushed, so a new WAL with log number 2 is created and persisted to MANIFEST for CF 1. But CF 0's log number in MANIFEST is still 1. So on recovery, MinLogNumber is 1, but since log 1 only contains data for CF 1, and CF 1 is flushed, log 1 might have already been deleted from disk. We can make `MinLogNumber()` be the exactly minimum log number that must exist, by persisting the most recent log number for empty column families that are not flushed. But if there are N such column families, then every time a new WAL is created, we need to add N records to MANIFEST. In current design, a record is persisted to MANIFEST only when WAL is created, closed, or deleted/archived, so the number of WAL related records are bounded to 3x number of WALs. 2. Why keep `WalSet` in `VersionSet` instead of applying the `VersionEdit`s to `VersionStorageInfo` `VersionEdit`s are originally designed to track the addition and deletion of SST files. The SST files are related to column families, each column family has a list of `Version`s, and each `Version` keeps the set of active SST files in `VersionStorageInfo`. But WALs are a concept of DB, they are not bounded to specific column families. So logically it does not make sense to store WALs in a column family's `Version`s. Also, `Version`'s purpose is to keep reference to SST / blob files, so that they are not deleted until there is no version referencing them. But a WAL is deleted regardless of version references. So we keep the WALs in `VersionSet` for the purpose of writing out the DB state's snapshot when creating new MANIFESTs. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7164 Test Plan: make version_edit_test && ./version_edit_test make wal_edit_test && ./wal_edit_test Reviewed By: ltamasi Differential Revision: D22677936 Pulled By: cheng-chang fbshipit-source-id: 5a3b6890140e572ffd79eb37e6e4c3c32361a859
4 years ago
db/wal_edit_test.cc
db/write_batch_test.cc
db/write_callback_test.cc
db/write_controller_test.cc
env/env_test.cc
env/io_posix_test.cc
env/mock_env_test.cc
file/delete_scheduler_test.cc
file/prefetch_test.cc
file/random_access_file_reader_test.cc
logging/auto_roll_logger_test.cc
logging/env_logger_test.cc
logging/event_logger_test.cc
memory/arena_test.cc
Provide an allocator for new memory type to be used with RocksDB block cache (#6214) Summary: New memory technologies are being developed by various hardware vendors (Intel DCPMM is one such technology currently available). These new memory types require different libraries for allocation and management (such as PMDK and memkind). The high capacities available make it possible to provision large caches (up to several TBs in size), beyond what is achievable with DRAM. The new allocator provided in this PR uses the memkind library to allocate memory on different media. **Performance** We tested the new allocator using db_bench. - For each test, we vary the size of the block cache (relative to the size of the uncompressed data in the database). - The database is filled sequentially. Throughput is then measured with a readrandom benchmark. - We use a uniform distribution as a worst-case scenario. The plot shows throughput (ops/s) relative to a configuration with no block cache and default allocator. For all tests, p99 latency is below 500 us. ![image](https://user-images.githubusercontent.com/26400080/71108594-42479100-2178-11ea-8231-8a775bbc92db.png) **Changes** - Add MemkindKmemAllocator - Add --use_cache_memkind_kmem_allocator db_bench option (to create an LRU block cache with the new allocator) - Add detection of memkind library with KMEM DAX support - Add test for MemkindKmemAllocator **Minimum Requirements** - kernel 5.3.12 - ndctl v67 - https://github.com/pmem/ndctl - memkind v1.10.0 - https://github.com/memkind/memkind **Memory Configuration** The allocator uses the MEMKIND_DAX_KMEM memory kind. Follow the instructions on[ memkind’s GitHub page](https://github.com/memkind/memkind) to set up NVDIMM memory accordingly. Note on memory allocation with NVDIMM memory exposed as system memory. - The MemkindKmemAllocator will only allocate from NVDIMM memory (using memkind_malloc with MEMKIND_DAX_KMEM kind). - The default allocator is not restricted to RAM by default. Based on NUMA node latency, the kernel should allocate from local RAM preferentially, but it’s a kernel decision. numactl --preferred/--membind can be used to allocate preferentially/exclusively from the local RAM node. **Usage** When creating an LRU cache, pass a MemkindKmemAllocator object as argument. For example (replace capacity with the desired value in bytes): ``` #include "rocksdb/cache.h" #include "memory/memkind_kmem_allocator.h" NewLRUCache( capacity /*size_t*/, 6 /*cache_numshardbits*/, false /*strict_capacity_limit*/, false /*cache_high_pri_pool_ratio*/, std::make_shared<MemkindKmemAllocator>()); ``` Refer to [RocksDB’s block cache documentation](https://github.com/facebook/rocksdb/wiki/Block-Cache) to assign the LRU cache as block cache for a database. Pull Request resolved: https://github.com/facebook/rocksdb/pull/6214 Reviewed By: cheng-chang Differential Revision: D19292435 fbshipit-source-id: 7202f47b769e7722b539c86c2ffd669f64d7b4e1
5 years ago
memory/memkind_kmem_allocator_test.cc
memtable/inlineskiplist_test.cc
memtable/skiplist_test.cc
memtable/write_buffer_manager_test.cc
monitoring/histogram_test.cc
monitoring/iostats_context_test.cc
monitoring/statistics_test.cc
monitoring/stats_history_test.cc
options/configurable_test.cc
options/customizable_test.cc
options/options_settable_test.cc
options/options_test.cc
table/block_based/block_based_filter_block_test.cc
table/block_based/block_based_table_reader_test.cc
table/block_based/block_test.cc
table/block_based/data_block_hash_index_test.cc
table/block_based/full_filter_block_test.cc
table/block_based/partitioned_filter_block_test.cc
table/cleanable_test.cc
table/cuckoo/cuckoo_table_builder_test.cc
table/cuckoo/cuckoo_table_reader_test.cc
table/merger_test.cc
table/sst_file_reader_test.cc
table/table_test.cc
table/block_fetcher_test.cc
test_util/testutil_test.cc
trace_replay/block_cache_tracer_test.cc
trace_replay/io_tracer_test.cc
tools/block_cache_analyzer/block_cache_trace_analyzer_test.cc
tools/io_tracer_parser_test.cc
tools/ldb_cmd_test.cc
tools/reduce_levels_test.cc
tools/sst_dump_test.cc
RocksDB Trace Analyzer (#4091) Summary: A framework of trace analyzing for RocksDB After collecting the trace by using the tool of [PR #3837](https://github.com/facebook/rocksdb/pull/3837). User can use the Trace Analyzer to interpret, analyze, and characterize the collected workload. **Input:** 1. trace file 2. Whole keys space file **Statistics:** 1. Access count of each operation (Get, Put, Delete, SingleDelete, DeleteRange, Merge) in each column family. 2. Key hotness (access count) of each one 3. Key space separation based on given prefix 4. Key size distribution 5. Value size distribution if appliable 6. Top K accessed keys 7. QPS statistics including the average QPS and peak QPS 8. Top K accessed prefix 9. The query correlation analyzing, output the number of X after Y and the corresponding average time intervals **Output:** 1. key access heat map (either in the accessed key space or whole key space) 2. trace sequence file (interpret the raw trace file to line base text file for future use) 3. Time serial (The key space ID and its access time) 4. Key access count distritbution 5. Key size distribution 6. Value size distribution (in each intervals) 7. whole key space separation by the prefix 8. Accessed key space separation by the prefix 9. QPS of each operation and each column family 10. Top K QPS and their accessed prefix range **Test:** 1. Added the unit test of analyzing Get, Put, Delete, SingleDelete, DeleteRange, Merge 2. Generated the trace and analyze the trace **Implemented but not tested (due to the limitation of trace_replay):** 1. Analyzing Iterator, supporting Seek() and SeekForPrev() analyzing 2. Analyzing the number of Key found by Get **Future Work:** 1. Support execution time analyzing of each requests 2. Support cache hit situation and block read situation of Get Pull Request resolved: https://github.com/facebook/rocksdb/pull/4091 Differential Revision: D9256157 Pulled By: zhichao-cao fbshipit-source-id: f0ceacb7eedbc43a3eee6e85b76087d7832a8fe6
6 years ago
tools/trace_analyzer_test.cc
util/autovector_test.cc
util/bloom_test.cc
util/coding_test.cc
util/crc32c_test.cc
util/defer_test.cc
util/dynamic_bloom_test.cc
util/file_reader_writer_test.cc
util/filelock_test.cc
util/hash_test.cc
util/heap_test.cc
util/random_test.cc
util/rate_limiter_test.cc
util/repeatable_thread_test.cc
Ribbon: initial (general) algorithms and basic unit test (#7491) Summary: This is intended as the first commit toward a near-optimal alternative to static Bloom filters for SSTs. Stephan Walzer and I have agreed upon the name "Ribbon" for a PHSF based on his linear system construction in "Efficient Gauss Elimination for Near-Quadratic Matrices with One Short Random Block per Row, with Applications" ("SGauss") and my much faster "on the fly" algorithm for gaussian elimination (or for this linear system, "banding"), which can be faster than peeling while also more compact and flexible. See util/ribbon_alg.h for more detailed introduction and background. RIBBON = Rapid Incremental Boolean Banding ON-the-fly This commit just adds generic (templatized) core algorithms and a basic unit test showing some features, including the ability to construct structures within 2.5% space overhead vs. information theoretic lower bound. (Compare to cache-local Bloom filter's ~50% space overhead -> ~30% reduction anticipated.) This commit does not include the storage scheme necessary to make queries fast, especially for filter queries, nor fractional "result bits", but there is some description already and those implementations will come soon. Nor does this commit add FilterPolicy support, for use in SST files, but that will also come soon. Pull Request resolved: https://github.com/facebook/rocksdb/pull/7491 Reviewed By: jay-zhuang Differential Revision: D24517954 Pulled By: pdillinger fbshipit-source-id: 0119ee597e250d7e0edd38ada2ba50d755606fa7
4 years ago
util/ribbon_test.cc
util/slice_test.cc
util/slice_transform_test.cc
util/timer_queue_test.cc
util/timer_test.cc
util/thread_list_test.cc
util/thread_local_test.cc
util/work_queue_test.cc
utilities/backupable/backupable_db_test.cc
utilities/blob_db/blob_db_test.cc
utilities/cassandra/cassandra_functional_test.cc
utilities/cassandra/cassandra_format_test.cc
utilities/cassandra/cassandra_row_merge_test.cc
utilities/cassandra/cassandra_serialize_test.cc
utilities/checkpoint/checkpoint_test.cc
utilities/memory/memory_test.cc
utilities/merge_operators/string_append/stringappend_test.cc
utilities/object_registry_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/simulator_cache/cache_simulator_test.cc
utilities/simulator_cache/sim_cache_test.cc
utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
utilities/transactions/optimistic_transaction_test.cc
utilities/transactions/transaction_test.cc
utilities/transactions/lock/point/point_lock_manager_test.cc
utilities/transactions/write_prepared_transaction_test.cc
utilities/transactions/write_unprepared_transaction_test.cc
utilities/transactions/lock/range/range_locking_test.cc
utilities/ttl/ttl_test.cc
utilities/write_batch_with_index/write_batch_with_index_test.cc
)
endif()
if(WITH_LIBRADOS)
list(APPEND TESTS utilities/env_librados_test.cc)
endif()
if(WITH_FOLLY_DISTRIBUTED_MUTEX)
list(APPEND TESTS third-party/folly/folly/synchronization/test/DistributedMutexTest.cpp)
endif()
set(TESTUTIL_SOURCE
db/db_test_util.cc
monitoring/thread_status_updater_debug.cc
table/mock_table.cc
utilities/cassandra/test_utils.cc
)
enable_testing()
add_custom_target(check COMMAND ${CMAKE_CTEST_COMMAND})
set(TESTUTILLIB testutillib${ARTIFACT_SUFFIX})
add_library(${TESTUTILLIB} STATIC ${TESTUTIL_SOURCE})
target_link_libraries(${TESTUTILLIB} ${ROCKSDB_LIB})
if(MSVC)
set_target_properties(${TESTUTILLIB} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/testutillib${ARTIFACT_SUFFIX}.pdb")
endif()
set_target_properties(${TESTUTILLIB}
PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
)
foreach(sourcefile ${TESTS})
get_filename_component(exename ${sourcefile} NAME_WE)
add_executable(${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
OUTPUT_NAME ${exename}${ARTIFACT_SUFFIX}
)
target_link_libraries(${exename}${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX} testharness gtest ${THIRDPARTY_LIBS} ${ROCKSDB_LIB})
if(NOT "${exename}" MATCHES "db_sanity_test")
gtest_discover_tests(${exename} DISCOVERY_TIMEOUT 120)
add_dependencies(check ${exename}${ARTIFACT_SUFFIX})
endif()
if("${exename}" MATCHES "env_librados_test")
# env_librados_test.cc uses librados directly
target_link_libraries(${exename}${ARTIFACT_SUFFIX} rados)
endif()
endforeach(sourcefile ${TESTS})
if(WIN32)
# C executables must link to a shared object
if(ROCKSDB_BUILD_SHARED)
set(ROCKSDB_LIB_FOR_C ${ROCKSDB_SHARED_LIB})
else()
set(ROCKSDB_LIB_FOR_C OFF)
endif()
else()
set(ROCKSDB_LIB_FOR_C ${ROCKSDB_LIB})
endif()
if(ROCKSDB_LIB_FOR_C)
set(C_TESTS db/c_test.c)
add_executable(c_test db/c_test.c)
Fix cmake build on MacOS (#7205) Summary: 1. `std::random_shuffle` is deprecated and now we can use `std::shuffle` ``` /rocksdb/db/prefix_test.cc:590:12: error: 'random_shuffle<std::__1::__wrap_iter<unsigned long long *> >' is deprecated [-Werror,-Wdeprecated-declarations] std::random_shuffle(prefixes.begin(), prefixes.end()); ^ /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/algorithm:2982:1: note: 'random_shuffle<std::__1::__wrap_iter<unsigned long long *> >' has been explicitly marked deprecated here _LIBCPP_DEPRECATED_IN_CXX14 void ^ /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/__config:1107:39: note: expanded from macro '_LIBCPP_DEPRECATED_IN_CXX14' # define _LIBCPP_DEPRECATED_IN_CXX14 _LIBCPP_DEPRECATED ^ /Applications/Xcode.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/bin/../include/c++/v1/__config:1090:48: note: expanded from macro '_LIBCPP_DEPRECATED' # define _LIBCPP_DEPRECATED __attribute__ ((deprecated)) ``` 2. `c_test` link error with `-DROCKSDB_BUILD_SHARED=OFF`: ``` [ 7%] Linking CXX executable c_test ld: library not found for -lrocksdb-shared clang: error: linker command failed with exit code 1 (use -v to see invocation) make[5]: *** [c_test] Error 1 make[4]: *** [CMakeFiles/c_test.dir/all] Error 2 make[4]: *** Waiting for unfinished jobs.... ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/7205 Reviewed By: ajkr Differential Revision: D23030641 Pulled By: pdillinger fbshipit-source-id: f270e50fc0b824ca1a0876ec5c65d33f55a72dd0
4 years ago
target_link_libraries(c_test ${ROCKSDB_LIB_FOR_C} testharness)
add_test(NAME c_test COMMAND c_test${ARTIFACT_SUFFIX})
add_dependencies(check c_test)
endif()
endif()
if(WITH_BENCHMARK_TOOLS)
add_executable(db_bench${ARTIFACT_SUFFIX}
tools/simulated_hybrid_file_system.cc
tools/db_bench.cc
tools/db_bench_tool.cc)
target_link_libraries(db_bench${ARTIFACT_SUFFIX}
${ROCKSDB_LIB} ${THIRDPARTY_LIBS})
add_executable(cache_bench${ARTIFACT_SUFFIX}
cache/cache_bench.cc
cache/cache_bench_tool.cc)
target_link_libraries(cache_bench${ARTIFACT_SUFFIX}
${ROCKSDB_LIB} ${GFLAGS_LIB})
add_executable(memtablerep_bench${ARTIFACT_SUFFIX}
memtable/memtablerep_bench.cc)
target_link_libraries(memtablerep_bench${ARTIFACT_SUFFIX}
${ROCKSDB_LIB} ${GFLAGS_LIB})
add_executable(range_del_aggregator_bench${ARTIFACT_SUFFIX}
db/range_del_aggregator_bench.cc)
target_link_libraries(range_del_aggregator_bench${ARTIFACT_SUFFIX}
${ROCKSDB_LIB} ${GFLAGS_LIB})
add_executable(table_reader_bench${ARTIFACT_SUFFIX}
table/table_reader_bench.cc)
target_link_libraries(table_reader_bench${ARTIFACT_SUFFIX}
${ROCKSDB_LIB} testharness ${GFLAGS_LIB})
add_executable(filter_bench${ARTIFACT_SUFFIX}
util/filter_bench.cc)
target_link_libraries(filter_bench${ARTIFACT_SUFFIX}
${ROCKSDB_LIB} ${GFLAGS_LIB})
add_executable(hash_table_bench${ARTIFACT_SUFFIX}
utilities/persistent_cache/hash_table_bench.cc)
target_link_libraries(hash_table_bench${ARTIFACT_SUFFIX}
${ROCKSDB_LIB} ${GFLAGS_LIB})
endif()
if(WITH_CORE_TOOLS OR WITH_TOOLS)
add_subdirectory(tools)
add_custom_target(core_tools
DEPENDS ${core_tool_deps})
endif()
if(WITH_TOOLS)
add_subdirectory(db_stress_tool)
add_custom_target(tools
DEPENDS ${tool_deps})
endif()
option(WITH_EXAMPLES "build with examples" OFF)
if(WITH_EXAMPLES)
add_subdirectory(examples)
endif()
option(WITH_BENCHMARK "build benchmark tests" OFF)
if(WITH_BENCHMARK)
add_subdirectory(${PROJECT_SOURCE_DIR}/microbench/)
endif()