fb internal: Should also use GCC 4.8.1 for CentOS 7

Summary: Calling Fsync()/Sync() on a file should give the guarantee that whatever you written to the file is now persisted. This is currently not the case, since we might have some data left in application cache as we do Fsync()/Sync(). For example, BuildTable() calls Fsync() without the flush, assuming all sst data is now persisted, but it's actually not. This may result in big inconsistencies.

Test Plan: no test

Reviewers: sdong, dhruba, haobo, ljin, yhchiang

Reviewed By: sdong

CC: leveldb

Differential Revision: https://reviews.facebook.net/D18159

.arcconfig

@@ -3,15 +3,8 @@
   "conduit_uri" : "https://reviews.facebook.net/",
   "copyright_holder" : "Facebook",
   "load" : [
-    "arcanist_util"
+    "linters"
   ],
   "lint.engine" : "FacebookFbcodeLintEngine",
-  "lint.engine.single.linter" : "FbcodeCppLinter",
-  "unit.engine" : "FacebookFbcodeUnitTestEngine",
-  "arcanist_configuration" : "FacebookArcanistConfiguration",
-  "base" : "git:HEAD^, hg:.^",
-  "git.default-relative-commit" : "HEAD^",
-  "git:arc.feature.start.default" : "origin/master",
-  "arc.feature.start.default" : "master",
-  "history.immutable" : false
+  "lint.engine.single.linter" : "FbcodeCppLinter"
 }

.gitignore

@@ -1,5 +1,4 @@
-TARGETS
-make_config.mk
+build_config.mk
 
 *.a
 *.arc
@@ -18,16 +17,6 @@ make_config.mk
 *.jar
 *.*jnilib*
 *.d-e
-*.o-*
-*.swp
-*~
-*.vcxproj
-*.vcxproj.filters
-*.sln
-*.cmake
-CMakeCache.txt
-CMakeFiles/
-build/
 
 ldb
 manifest_dump
@@ -36,31 +25,7 @@ util/build_version.cc
 build_tools/VALGRIND_LOGS/
 coverage/COVERAGE_REPORT
 .gdbhistory
-package/
 .phutil_module_cache
-unity.a
 tags
-rocksdb_dump
-rocksdb_undump
-db_test2
-
-java/out
-java/target
-java/test-libs
 java/*.log
 java/include/org_rocksdb_*.h
-
-.idea/
-*.iml
-
-rocksdb.cc
-rocksdb.h
-unity.cc
-java/crossbuild/.vagrant
-.vagrant/
-java/**.asc
-java/javadoc
-
-scan_build_report/
-t
-LOG

.travis.yml

@@ -1,47 +0,0 @@
-sudo: false
-language: cpp
-os:
-  - linux
-  - osx
-compiler:
-  - clang
-
-addons:
-   apt:
-      sources: ['ubuntu-toolchain-r-test', 'llvm-toolchain-precise-3.6']
-      packages: ['clang-3.6' , 'zlib1g-dev', 'libbz2-dev', 'libsnappy-dev', 'curl']
-env:
-  # Run all tests before db_block_cache_test (db_test, db_test2)
-  - JOB_NAME=unittests ROCKSDBTESTS_END=db_block_cache_test
-  # Run all tests starting from db_block_cache_test (db_block_cache_test, db_iter_test, ...)
-  - JOB_NAME=unittests ROCKSDBTESTS_START=db_block_cache_test
-  # Run java tests
-  - JOB_NAME=java_test
-  # Build ROCKSDB_LITE
-  - JOB_NAME=lite_build
-
-install:
-  # Build gflags
-  # TODO(noetzli): Remove when gflags available through Travis
-  - pushd /tmp/ && curl -L https://github.com/gflags/gflags/archive/v2.1.2.tar.gz -o gflags.tar.gz && tar xfz gflags.tar.gz && cd gflags-2.1.2 && cmake . && make && popd
-
-before_script:
-  # Add gflags to include/library paths
-  # TODO(noetzli): Remove when gflags available through Travis
-  - export LD_LIBRARY_PATH="$LD_LIBRARY_PATH:/tmp/gflags-2.1.2/lib"
-  - export LIBRARY_PATH="$LIBRARY_PATH:/tmp/gflags-2.1.2/lib"
-  - export CPLUS_INCLUDE_PATH="$CPLUS_INCLUDE_PATH:/tmp/gflags-2.1.2/include"
-  - if [[ "${TRAVIS_OS_NAME}" == 'linux' ]]; then CXX=clang++-3.6; fi
-  - if [[ "${TRAVIS_OS_NAME}" == 'osx' ]]; then brew install gflags snappy; fi
-  # Limit the maximum number of open file descriptors to 2000
-  - ulimit -n 2000 || true
-
-script:
-  - if [[ "${JOB_NAME}" == 'unittests' ]]; then OPT=-DTRAVIS V=1 make -j4 check_some; fi
-  - if [[ "${JOB_NAME}" == 'java_test' ]]; then OPT=-DTRAVIS V=1 make clean jclean rocksdbjava jtest; fi
-  - if [[ "${JOB_NAME}" == 'lite_build' ]]; then OPT="-DTRAVIS -DROCKSDB_LITE" V=1 make -j4 static_lib; fi
-notifications:
-    email:
-      - leveldb@fb.com
-    webhooks:
-      - https://buildtimetrend.herokuapp.com/travis

AUTHORS

@@ -1,11 +0,0 @@
-Facebook Inc.
-Facebook Engineering Team
-
-Google Inc.
-# Initial version authors:
-Jeffrey Dean <jeff@google.com>
-Sanjay Ghemawat <sanjay@google.com>
-
-# Partial list of contributors:
-Kevin Regan <kevin.d.regan@gmail.com>
-Johan Bilien <jobi@litl.com>

CMakeLists.txt

@@ -1,489 +0,0 @@
-# This cmake build is for Windows 64-bit only.
-#
-# Prerequisites:
-#     You must have Visual Studio 2013 Update 4 installed. Start the Developer Command Prompt window that is a part of Visual Studio installation.
-#     Run the build commands from within the Developer Command Prompt window to have paths to the compiler and runtime libraries set.
-#     You must have git.exe in your %PATH% environment variable.
-#
-# 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 12 Win64" -DGFLAGS=1 -DSNAPPY=1 -DJEMALLOC=1 -DJNI=1 ..
-#        OR for VS Studio 15 cmake -G "Visual Studio 14 Win64" -DGFLAGS=1 -DSNAPPY=1 -DJEMALLOC=1 -DJNI=1 ..
-# 4. Then build the project in debug mode (you may want to add /m[:<N>] flag to run msbuild in <N> parallel threads
-#                                          or simply /m ot use all avail cores)
-#        msbuild rocksdb.sln
-#
-#        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
-#
-
-cmake_minimum_required(VERSION 2.6)
-project(rocksdb)
-
-include(${CMAKE_CURRENT_SOURCE_DIR}/thirdparty.inc)
-execute_process(COMMAND powershell -Command "Get-Date -format MM_dd_yyyy" OUTPUT_VARIABLE DATE)
-execute_process(COMMAND powershell -Command "Get-Date -format HH:mm:ss" OUTPUT_VARIABLE TIME)
-string(REGEX REPLACE "(..)_(..)_..(..).*" "\\1/\\2/\\3" DATE ${DATE})
-string(REGEX REPLACE "(..):(.....).*" " \\1:\\2" TIME ${TIME})
-string(CONCAT GIT_DATE_TIME ${DATE} ${TIME})
-
-find_package(Git)
-
-if (GIT_FOUND AND EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/.git")
-    execute_process(COMMAND $ENV{COMSPEC} /C ${GIT_EXECUTABLE} -C ${CMAKE_CURRENT_SOURCE_DIR} rev-parse HEAD OUTPUT_VARIABLE GIT_SHA)
-else()
-    set(GIT_SHA 0)
-endif()
-
-string(REGEX REPLACE "[^0-9a-f]+" "" GIT_SHA ${GIT_SHA})
-
-set(BUILD_VERSION_CC ${CMAKE_CURRENT_SOURCE_DIR}/util/build_version.cc)
-
-add_custom_command(OUTPUT ${BUILD_VERSION_CC}
-    COMMAND echo "#include \"build_version.h\"" > ${BUILD_VERSION_CC}
-    COMMAND echo "const char* rocksdb_build_git_sha = \"rocksdb_build_git_sha:${GIT_SHA}\";" >> ${BUILD_VERSION_CC}
-    COMMAND echo "const char* rocksdb_build_git_datetime = \"rocksdb_build_git_datetime:${GIT_DATE_TIME}\";" >> ${BUILD_VERSION_CC}
-    COMMAND echo const char* rocksdb_build_compile_date = __DATE__\; >> ${BUILD_VERSION_CC}
-)
-
-add_custom_target(GenerateBuildVersion DEPENDS ${BUILD_VERSION_CC})
-
-set(CMAKE_CXX_FLAGS "${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+ /W3 /WX /wd4127 /wd4800 /wd4996 /wd4351")
-
-# Used to run CI build and tests so we can run faster
-set(OPTIMIZE_DEBUG_DEFAULT 0)        # Debug build is unoptimized by default use -DOPTDBG=1 to optimize
-
-if(DEFINED OPTDBG)
-   set(OPTIMIZE_DEBUG ${OPTDBG})
-else()
-   set(OPTIMIZE_DEBUG ${OPTIMIZE_DEBUG_DEFAULT})
-endif()
-
-if((${OPTIMIZE_DEBUG} EQUAL 1))
-   message(STATUS "Debug optimization is enabled")
-   set(CMAKE_CXX_FLAGS_DEBUG "/Oxt /MDd")
-else()
-   set(CMAKE_CXX_FLAGS_DEBUG "${CMAKE_CXX_FLAGS_DEBUG} /Od /RTC1 /Gm /MDd")
-endif()
-
-set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} /Oxt /Zp8 /Gm- /Gy /MD")
-
-set(CMAKE_SHARED_LINKER_FLAGS "${CMAKE_SHARED_LINKER_FLAGS} /DEBUG")
-set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} /DEBUG")
-
-add_definitions(-DWIN32 -DOS_WIN -D_MBCS -DWIN64 -DNOMINMAX)
-
-include_directories(${PROJECT_SOURCE_DIR})
-include_directories(${PROJECT_SOURCE_DIR}/include)
-include_directories(${PROJECT_SOURCE_DIR}/third-party/gtest-1.7.0/fused-src)
-
-set(ROCKSDB_LIBS rocksdblib${ARTIFACT_SUFFIX})
-set(THIRDPARTY_LIBS ${THIRDPARTY_LIBS} gtest)
-set(SYSTEM_LIBS ${SYSTEM_LIBS} Shlwapi.lib Rpcrt4.lib)
-
-set(LIBS ${ROCKSDB_LIBS} ${THIRDPARTY_LIBS} ${SYSTEM_LIBS})
-
-add_subdirectory(third-party/gtest-1.7.0/fused-src/gtest)
-
-# Main library source code
-set(SOURCES
-        db/auto_roll_logger.cc
-        db/builder.cc
-        db/c.cc
-        db/column_family.cc
-        db/compacted_db_impl.cc
-        db/compaction.cc
-        db/compaction_iterator.cc
-        db/compaction_job.cc
-        db/compaction_picker.cc
-        db/convenience.cc
-        db/dbformat.cc
-        db/db_filesnapshot.cc
-        db/db_impl.cc
-        db/db_impl_debug.cc
-        db/db_impl_experimental.cc
-        db/db_impl_readonly.cc
-        db/db_info_dumper.cc
-        db/db_iter.cc
-        db/event_helpers.cc
-        db/experimental.cc
-        db/filename.cc
-        db/file_indexer.cc
-        db/flush_job.cc
-        db/flush_scheduler.cc
-        db/forward_iterator.cc
-        db/internal_stats.cc
-        db/log_reader.cc
-        db/log_writer.cc
-        db/managed_iterator.cc
-        db/memtable.cc
-        db/memtable_allocator.cc
-        db/memtable_list.cc
-        db/merge_helper.cc
-        db/merge_operator.cc
-        db/repair.cc
-        db/slice.cc
-        db/snapshot_impl.cc
-        db/table_cache.cc
-        db/table_properties_collector.cc
-        db/transaction_log_impl.cc
-        db/version_builder.cc
-        db/version_edit.cc
-        db/version_set.cc
-        db/wal_manager.cc
-        db/write_batch.cc
-        db/write_batch_base.cc
-        db/write_controller.cc
-        db/write_thread.cc
-        db/xfunc_test_points.cc
-        memtable/hash_cuckoo_rep.cc
-        memtable/hash_linklist_rep.cc
-        memtable/hash_skiplist_rep.cc
-        memtable/skiplistrep.cc
-        memtable/vectorrep.cc
-        port/stack_trace.cc
-        port/win/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/xpress_win.cc
-        table/adaptive_table_factory.cc
-        table/block.cc
-        table/block_based_filter_block.cc
-        table/block_based_table_builder.cc
-        table/block_based_table_factory.cc
-        table/block_based_table_reader.cc
-        table/block_builder.cc
-        table/block_prefix_index.cc
-        table/bloom_block.cc
-        table/cuckoo_table_builder.cc
-        table/cuckoo_table_factory.cc
-        table/cuckoo_table_reader.cc
-        table/flush_block_policy.cc
-        table/format.cc
-        table/full_filter_block.cc
-        table/get_context.cc
-        table/iterator.cc
-        table/merger.cc
-        table/sst_file_writer.cc
-        table/meta_blocks.cc
-        table/plain_table_builder.cc
-        table/plain_table_factory.cc
-        table/plain_table_index.cc
-        table/plain_table_key_coding.cc
-        table/plain_table_reader.cc
-        table/persistent_cache_helper.cc
-        table/table_properties.cc
-        table/two_level_iterator.cc
-        tools/sst_dump_tool.cc
-        tools/db_bench_tool.cc
-        tools/dump/db_dump_tool.cc
-        util/arena.cc
-        util/bloom.cc
-        util/build_version.cc
-        util/cache.cc
-        util/coding.cc
-        util/compaction_job_stats_impl.cc
-        util/comparator.cc
-        util/concurrent_arena.cc
-        util/crc32c.cc
-        util/delete_scheduler.cc
-        util/dynamic_bloom.cc
-        util/env.cc
-        util/env_chroot.cc
-        util/env_hdfs.cc
-        util/event_logger.cc
-        util/file_util.cc
-        util/file_reader_writer.cc
-        util/sst_file_manager_impl.cc
-        util/filter_policy.cc
-        util/hash.cc
-        util/histogram.cc
-        util/histogram_windowing.cc
-        util/instrumented_mutex.cc
-        util/iostats_context.cc
-        tools/ldb_cmd.cc
-        tools/ldb_tool.cc
-        util/logging.cc
-        util/log_buffer.cc
-        util/memenv.cc
-        util/murmurhash.cc
-        util/mutable_cf_options.cc
-        util/options.cc
-        util/options_helper.cc
-        util/options_parser.cc
-        util/options_sanity_check.cc
-        util/perf_context.cc
-        util/perf_level.cc
-        util/random.cc
-        util/rate_limiter.cc
-        util/slice.cc
-        util/statistics.cc
-        util/status.cc
-        util/status_message.cc
-        util/string_util.cc
-        util/sync_point.cc
-        util/testharness.cc
-        util/testutil.cc
-        util/thread_local.cc
-        util/threadpool.cc
-        util/thread_status_impl.cc
-        util/thread_status_updater.cc
-        util/thread_status_util.cc
-        util/thread_status_util_debug.cc
-        util/transaction_test_util.cc
-        util/xfunc.cc
-        util/xxhash.cc
-        utilities/backupable/backupable_db.cc
-        utilities/checkpoint/checkpoint.cc
-        utilities/compaction_filters/remove_emptyvalue_compactionfilter.cc
-        utilities/document/document_db.cc
-        utilities/document/json_document.cc
-        utilities/document/json_document_builder.cc
-        utilities/env_mirror.cc
-        utilities/env_registry.cc
-        utilities/flashcache/flashcache.cc
-        utilities/geodb/geodb_impl.cc
-        utilities/leveldb_options/leveldb_options.cc
-        utilities/memory/memory_util.cc
-        utilities/merge_operators/string_append/stringappend.cc
-        utilities/merge_operators/string_append/stringappend2.cc
-        utilities/merge_operators/put.cc
-        utilities/merge_operators/max.cc
-        utilities/merge_operators/uint64add.cc
-        utilities/options/options_util.cc
-        utilities/persistent_cache/persistent_cache_tier.cc
-        utilities/persistent_cache/volatile_tier_impl.cc
-        utilities/redis/redis_lists.cc
-        utilities/spatialdb/spatial_db.cc
-        utilities/table_properties_collectors/compact_on_deletion_collector.cc
-        utilities/transactions/optimistic_transaction_impl.cc
-        utilities/transactions/optimistic_transaction_db_impl.cc
-        utilities/transactions/transaction_base.cc
-        utilities/transactions/transaction_impl.cc
-        utilities/transactions/transaction_db_impl.cc
-        utilities/transactions/transaction_db_mutex_impl.cc
-        utilities/transactions/transaction_lock_mgr.cc
-        utilities/transactions/transaction_util.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
-)
-
-# For test util library that is build only in DEBUG mode
-# and linked to tests. Add test only code that is not #ifdefed for Release here.
-set(TESTUTIL_SOURCE
-    db/db_test_util.cc
-    table/mock_table.cc
-    util/mock_env.cc
-    util/fault_injection_test_env.cc
-    util/thread_status_updater_debug.cc
-)
-
-add_library(rocksdblib${ARTIFACT_SUFFIX} ${SOURCES})
-set_target_properties(rocksdblib${ARTIFACT_SUFFIX} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/rocksdblib${ARTIFACT_SUFFIX}.pdb")
-add_dependencies(rocksdblib${ARTIFACT_SUFFIX} GenerateBuildVersion)
-
-add_library(rocksdb${ARTIFACT_SUFFIX} SHARED ${SOURCES})
-set_target_properties(rocksdb${ARTIFACT_SUFFIX} PROPERTIES COMPILE_FLAGS "-DROCKSDB_DLL -DROCKSDB_LIBRARY_EXPORTS /Fd${CMAKE_CFG_INTDIR}/rocksdb${ARTIFACT_SUFFIX}.pdb")
-add_dependencies(rocksdb${ARTIFACT_SUFFIX} GenerateBuildVersion)
-target_link_libraries(rocksdb${ARTIFACT_SUFFIX} ${LIBS})
-
-if (DEFINED JNI)
-  if (${JNI} EQUAL 1)
-    message(STATUS "JNI library is enabled")
-    add_subdirectory(${CMAKE_CURRENT_SOURCE_DIR}/java)
-  else()
-    message(STATUS "JNI library is disabled")
-  endif()
-else()
-  message(STATUS "JNI library is disabled")
-endif()
-
-set(APPS
-        tools/db_bench.cc
-        db/memtablerep_bench.cc
-        table/table_reader_bench.cc
-        tools/db_stress.cc
-        tools/write_stress.cc
-        tools/db_repl_stress.cc
-        tools/ldb.cc
-        tools/sst_dump.cc
-        tools/dump/rocksdb_dump.cc
-        tools/dump/rocksdb_undump.cc
-        util/cache_bench.cc
-        utilities/persistent_cache/hash_table_bench.cc
-)
-
-set(C_TESTS db/c_test.c)
-
-set(TESTS
-        db/auto_roll_logger_test.cc
-        db/column_family_test.cc
-        db/compact_files_test.cc
-        db/compaction_iterator_test.cc
-        db/compaction_job_test.cc
-        db/compaction_job_stats_test.cc
-        db/compaction_picker_test.cc
-        db/comparator_db_test.cc
-        db/corruption_test.cc
-        db/cuckoo_table_db_test.cc
-        db/db_compaction_filter_test.cc
-        db/db_compaction_test.cc
-        db/db_dynamic_level_test.cc
-        db/db_inplace_update_test.cc
-        db/db_iter_test.cc
-        db/db_log_iter_test.cc
-        db/db_properties_test.cc
-        db/db_table_properties_test.cc
-        db/db_tailing_iter_test.cc
-        db/db_test.cc
-        db/db_test2.cc
-        db/db_block_cache_test.cc
-        db/db_bloom_filter_test.cc
-        db/db_iterator_test.cc
-        db/db_sst_test.cc
-        db/db_universal_compaction_test.cc
-        db/db_wal_test.cc
-        db/dbformat_test.cc
-        db/deletefile_test.cc
-        db/fault_injection_test.cc
-        db/file_indexer_test.cc
-        db/filename_test.cc
-        db/flush_job_test.cc
-        db/inlineskiplist_test.cc
-        db/listener_test.cc
-        db/log_test.cc
-        db/manual_compaction_test.cc
-        db/memtable_list_test.cc
-        db/merge_test.cc
-        db/merge_helper_test.cc
-        db/options_file_test.cc
-        db/perf_context_test.cc
-        db/plain_table_db_test.cc
-        db/prefix_test.cc
-        db/repair_test.cc
-        db/skiplist_test.cc
-        db/table_properties_collector_test.cc
-        db/version_builder_test.cc
-        db/version_edit_test.cc
-        db/version_set_test.cc
-        db/wal_manager_test.cc
-        db/write_batch_test.cc
-        db/write_callback_test.cc
-        db/write_controller_test.cc
-        db/db_io_failure_test.cc
-        table/block_based_filter_block_test.cc
-        table/block_test.cc
-        table/cuckoo_table_builder_test.cc
-        table/cuckoo_table_reader_test.cc
-        table/full_filter_block_test.cc
-        table/merger_test.cc
-        table/table_test.cc
-        tools/db_sanity_test.cc
-        tools/ldb_cmd_test.cc
-        tools/reduce_levels_test.cc
-        tools/sst_dump_test.cc
-        util/arena_test.cc
-        util/autovector_test.cc
-        util/bloom_test.cc
-        util/cache_test.cc
-        util/coding_test.cc
-        util/crc32c_test.cc
-        util/delete_scheduler_test.cc
-        util/dynamic_bloom_test.cc
-        util/env_basic_test.cc
-        util/env_test.cc
-        util/event_logger_test.cc
-        util/filelock_test.cc
-        util/file_reader_writer_test.cc
-        util/heap_test.cc
-        util/histogram_test.cc
-        util/iostats_context_test.cc
-        util/mock_env_test.cc
-        util/options_settable_test.cc
-        util/options_test.cc
-        util/rate_limiter_test.cc
-        util/slice_transform_test.cc
-        util/thread_list_test.cc
-        util/thread_local_test.cc
-        utilities/backupable/backupable_db_test.cc
-        utilities/checkpoint/checkpoint_test.cc
-        utilities/document/document_db_test.cc
-        utilities/document/json_document_test.cc
-        utilities/env_registry_test.cc
-        utilities/geodb/geodb_test.cc
-        utilities/memory/memory_test.cc
-        utilities/merge_operators/string_append/stringappend_test.cc
-        utilities/options/options_util_test.cc
-        utilities/persistent_cache/hash_table_test.cc
-        utilities/persistent_cache/persistent_cache_test.cc
-        utilities/redis/redis_lists_test.cc
-        utilities/spatialdb/spatial_db_test.cc
-        utilities/table_properties_collectors/compact_on_deletion_collector_test.cc
-        utilities/transactions/optimistic_transaction_test.cc
-        utilities/transactions/transaction_test.cc
-        utilities/ttl/ttl_test.cc
-        utilities/write_batch_with_index/write_batch_with_index_test.cc
-)
-
-set(EXES ${APPS})
-
-foreach(sourcefile ${EXES})
-    string(REPLACE ".cc" "" exename ${sourcefile})
-    string(REGEX REPLACE "^((.+)/)+" "" exename ${exename})
-    add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile})
-    target_link_libraries(${exename}${ARTIFACT_SUFFIX} ${LIBS})
-endforeach(sourcefile ${EXES})
-
-# test utilities are only build in debug
-set(TESTUTILLIB testutillib${ARTIFACT_SUFFIX})
-add_library(${TESTUTILLIB} STATIC ${TESTUTIL_SOURCE})
-set_target_properties(${TESTUTILLIB} PROPERTIES COMPILE_FLAGS "/Fd${CMAKE_CFG_INTDIR}/testutillib${ARTIFACT_SUFFIX}.pdb")
-set_target_properties(${TESTUTILLIB}
-      PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
-      EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
-      EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
-      )
-
-# Tests are excluded from Release builds
-set(TEST_EXES ${TESTS})
-
-foreach(sourcefile ${TEST_EXES})
-    string(REPLACE ".cc" "" exename ${sourcefile})
-    string(REGEX REPLACE "^((.+)/)+" "" exename ${exename})
-    add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile})
-    set_target_properties(${exename}${ARTIFACT_SUFFIX}
-      PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
-      EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
-      EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
-      )
-    target_link_libraries(${exename}${ARTIFACT_SUFFIX} ${LIBS} testutillib${ARTIFACT_SUFFIX})
-endforeach(sourcefile ${TEST_EXES})
-
-# C executables must link to a shared object
-set(C_TEST_EXES ${C_TESTS})
-
-foreach(sourcefile ${C_TEST_EXES})
-    string(REPLACE ".c" "" exename ${sourcefile})
-    string(REGEX REPLACE "^((.+)/)+" "" exename ${exename})
-    add_executable(${exename}${ARTIFACT_SUFFIX} ${sourcefile})
-    set_target_properties(${exename}${ARTIFACT_SUFFIX}
-      PROPERTIES EXCLUDE_FROM_DEFAULT_BUILD_RELEASE 1
-      EXCLUDE_FROM_DEFAULT_BUILD_MINRELEASE 1
-      EXCLUDE_FROM_DEFAULT_BUILD_RELWITHDEBINFO 1
-      )
-    target_link_libraries(${exename}${ARTIFACT_SUFFIX} rocksdb${ARTIFACT_SUFFIX} testutillib${ARTIFACT_SUFFIX})
-endforeach(sourcefile ${C_TEST_EXES})

CONTRIBUTING.md

@@ -8,10 +8,11 @@ open source project, you're good to go. If you are submitting a pull
 request for the first time, just let us know that you have completed
 the CLA and we can cross-check with your GitHub username.
 
-Complete your CLA here: <https://code.facebook.com/cla>
+Complete your CLA here: <https://developers.facebook.com/opensource/cla>
 
-If you prefer to sign a paper copy, we can send you a PDF.  Send us an 
-e-mail or create a new github issue to request the CLA in PDF format.
+If you don't have a Facebook account, we can send you a PDF that you can
+sign offline. Send us an e-mail or create a new github issue to
+request the CLA in PDF format.
 
 ## License
 

DEFAULT_OPTIONS_HISTORY.md

@@ -1,14 +0,0 @@
-# RocksDB default options change log
-## 4.8.0 (5/2/2016)
-* options.max_open_files changes from 5000 to -1. It improves performance, but users need to set file descriptor limit to be large enough and watch memory usage for index and bloom filters.
-* options.base_background_compactions changes from max_background_compactions to 1. When users set higher max_background_compactions but the write throughput is not high, the writes are less spiky to disks.
-* options.wal_recovery_mode changes from kTolerateCorruptedTailRecords to kPointInTimeRecovery. Avoid some false positive when file system or hardware reorder the writes for file data and metadata.
-
-## 4.7.0 (4/8/2016)
-* options.write_buffer_size changes from 4MB to 64MB.
-* options.target_file_size_base changes from 2MB to 64MB.
-* options.max_bytes_for_level_base changes from 10MB to 256MB.
-* options.soft_pending_compaction_bytes_limit changes from 0 (disabled) to 64GB.
-* options.hard_pending_compaction_bytes_limit changes from 0 (disabled) to 256GB.
-* table_cache_numshardbits changes from 4 to 6.
-* max_file_opening_threads changes from 1 to 16.

DUMP_FORMAT.md

@@ -1,16 +0,0 @@
-## RocksDB dump format
-
-The version 1 RocksDB dump format is fairly simple:
-
-1) The dump starts with the magic 8 byte identifier "ROCKDUMP"
-
-2) The magic is followed by an 8 byte big-endian version which is 0x00000001.
-
-3) Next are arbitrarily sized chunks of bytes prepended by 4 byte little endian number indicating how large each chunk is.
-
-4) The first chunk is special and is a json string indicating some things about the creation of this dump.  It contains the following keys:
-* database-path: The path of the database this dump was created from.
-* hostname: The hostname of the machine where the dump was created.
-* creation-time: Unix seconds since epoc when this dump was created.
-
-5) Following the info dump the slices paired into are key/value pairs.

HISTORY.md

@@ -1,333 +1,8 @@
 # Rocksdb Change Log
+
 ## Unreleased
 
-## 4.9.0 (6/9/2016)
 ### Public API changes
-* Add bottommost_compression option, This option can be used to set a specific compression algorithm for the bottommost level (Last level containing files in the DB).
-* Introduce CompactionJobInfo::compression, This field state the compression algorithm used to generate the output files of the compaction.
-* Deprecate BlockBaseTableOptions.hash_index_allow_collision=false
-* Deprecate options builder (GetOptions()).
-
-### New Features
-* Introduce NewSimCache() in rocksdb/utilities/sim_cache.h. This function creates a block cache that is able to give simulation results (mainly hit rate) of simulating block behavior with a configurable cache size.
-
-## 4.8.0 (5/2/2016)
-### Public API Change
-* Allow preset compression dictionary for improved compression of block-based tables. This is supported for zlib, zstd, and lz4. The compression dictionary's size is configurable via CompressionOptions::max_dict_bytes.
-* Delete deprecated classes for creating backups (BackupableDB) and restoring from backups (RestoreBackupableDB). Now, BackupEngine should be used for creating backups, and BackupEngineReadOnly should be used for restorations. For more details, see https://github.com/facebook/rocksdb/wiki/How-to-backup-RocksDB%3F
-* Expose estimate of per-level compression ratio via DB property: "rocksdb.compression-ratio-at-levelN".
-* Added EventListener::OnTableFileCreationStarted. EventListener::OnTableFileCreated will be called on failure case. User can check creation status via TableFileCreationInfo::status.
-
-### New Features
-* Add ReadOptions::readahead_size. If non-zero, NewIterator will create a new table reader which performs reads of the given size.
-
-## 4.7.0 (4/8/2016)
-### Public API Change
-* rename options compaction_measure_io_stats to report_bg_io_stats and include flush too.
-* Change some default options. Now default options will optimize for server-workloads. Also enable slowdown and full stop triggers for pending compaction bytes. These changes may cause sub-optimal performance or significant increase of resource usage. To avoid these risks, users can open existing RocksDB with options extracted from RocksDB option files. See https://github.com/facebook/rocksdb/wiki/RocksDB-Options-File for how to use RocksDB option files. Or you can call Options.OldDefaults() to recover old defaults. DEFAULT_OPTIONS_HISTORY.md will track change history of default options.
-
-## 4.6.0 (3/10/2016)
-### Public API Changes
-* Change default of BlockBasedTableOptions.format_version to 2. It means default DB created by 4.6 or up cannot be opened by RocksDB version 3.9 or earlier.
-* Added strict_capacity_limit option to NewLRUCache. If the flag is set to true, insert to cache will fail if no enough capacity can be free. Signiture of Cache::Insert() is updated accordingly.
-* Tickers [NUMBER_DB_NEXT, NUMBER_DB_PREV, NUMBER_DB_NEXT_FOUND, NUMBER_DB_PREV_FOUND, ITER_BYTES_READ] are not updated immediately. The are updated when the Iterator is deleted.
-* Add monotonically increasing counter (DB property "rocksdb.current-super-version-number") that increments upon any change to the LSM tree.
-
-### New Features
-* Add CompactionPri::kMinOverlappingRatio, a compaction picking mode friendly to write amplification.
-* Deprecate Iterator::IsKeyPinned() and replace it with Iterator::GetProperty() with prop_name="rocksdb.iterator.is.key.pinned"
-
-## 4.5.0 (2/5/2016)
-### Public API Changes
-* Add a new perf context level between kEnableCount and kEnableTime. Level 2 now does not include timers for mutexes.
-* Statistics of mutex operation durations will not be measured by default. If you want to have them enabled, you need to set Statistics::stats_level_ to kAll.
-* DBOptions::delete_scheduler and NewDeleteScheduler() are removed, please use DBOptions::sst_file_manager and NewSstFileManager() instead
-
-### New Features
-* ldb tool now supports operations to non-default column families.
-* Add kPersistedTier to ReadTier.  This option allows Get and MultiGet to read only the persited data and skip mem-tables if writes were done with disableWAL = true.
-* Add DBOptions::sst_file_manager. Use NewSstFileManager() in include/rocksdb/sst_file_manager.h to create a SstFileManager that can be used to track the total size of SST files and control the SST files deletion rate.
-
-## 4.4.0 (1/14/2016)
-### Public API Changes
-* Change names in CompactionPri and add a new one.
-* Deprecate options.soft_rate_limit and add options.soft_pending_compaction_bytes_limit.
-* If options.max_write_buffer_number > 3, writes will be slowed down when writing to the last write buffer to delay a full stop.
-* Introduce CompactionJobInfo::compaction_reason, this field include the reason to trigger the compaction.
-* After slow down is triggered, if estimated pending compaction bytes keep increasing, slowdown more.
-* Increase default options.delayed_write_rate to 2MB/s.
-* Added a new parameter --path to ldb tool. --path accepts the name of either MANIFEST, SST or a WAL file. Either --db or --path can be used when calling ldb.
-
-## 4.3.0 (12/8/2015)
-### New Features
-* CompactionFilter has new member function called IgnoreSnapshots which allows CompactionFilter to be called even if there are snapshots later than the key.
-* RocksDB will now persist options under the same directory as the RocksDB database on successful DB::Open, CreateColumnFamily, DropColumnFamily, and SetOptions.
-* Introduce LoadLatestOptions() in rocksdb/utilities/options_util.h.  This function can construct the latest DBOptions / ColumnFamilyOptions used by the specified RocksDB intance.
-* Introduce CheckOptionsCompatibility() in rocksdb/utilities/options_util.h.  This function checks whether the input set of options is able to open the specified DB successfully.
-
-### Public API Changes
-* When options.db_write_buffer_size triggers, only the column family with the largest column family size will be flushed, not all the column families.
-
-## 4.2.0 (11/9/2015)
-### New Features
-* Introduce CreateLoggerFromOptions(), this function create a Logger for provided DBOptions.
-* Add GetAggregatedIntProperty(), which returns the sum of the GetIntProperty of all the column families.
-* Add MemoryUtil in rocksdb/utilities/memory.h.  It currently offers a way to get the memory usage by type from a list rocksdb instances.
-
-### Public API Changes
-* CompactionFilter::Context includes information of Column Family ID
-* The need-compaction hint given by TablePropertiesCollector::NeedCompact() will be persistent and recoverable after DB recovery. This introduces a breaking format change. If you use this experimental feature, including NewCompactOnDeletionCollectorFactory() in the new version, you may not be able to directly downgrade the DB back to version 4.0 or lower.
-* TablePropertiesCollectorFactory::CreateTablePropertiesCollector() now takes an option Context, containing the information of column family ID for the file being written.
-* Remove DefaultCompactionFilterFactory.
-
-
-## 4.1.0 (10/8/2015)
-### New Features
-* Added single delete operation as a more efficient way to delete keys that have not been overwritten.
-* Added experimental AddFile() to DB interface that allow users to add files created by SstFileWriter into an empty Database, see include/rocksdb/sst_file_writer.h and DB::AddFile() for more info.
-* Added support for opening SST files with .ldb suffix which enables opening LevelDB databases.
-* CompactionFilter now supports filtering of merge operands and merge results.
-
-### Public API Changes
-* Added SingleDelete() to the DB interface.
-* Added AddFile() to DB interface.
-* Added SstFileWriter class.
-* CompactionFilter has a new method FilterMergeOperand() that RocksDB applies to every merge operand during compaction to decide whether to filter the operand.
-* We removed CompactionFilterV2 interfaces from include/rocksdb/compaction_filter.h. The functionality was deprecated already in version 3.13.
-
-## 4.0.0 (9/9/2015)
-### New Features
-* Added support for transactions.  See include/rocksdb/utilities/transaction.h for more info.
-* DB::GetProperty() now accepts "rocksdb.aggregated-table-properties" and "rocksdb.aggregated-table-properties-at-levelN", in which case it returns aggregated table properties of the target column family, or the aggregated table properties of the specified level N if the "at-level" version is used.
-* Add compression option kZSTDNotFinalCompression for people to experiment ZSTD although its format is not finalized.
-* We removed the need for LATEST_BACKUP file in BackupEngine. We still keep writing it when we create new backups (because of backward compatibility), but we don't read it anymore.
-
-### Public API Changes
-* Removed class Env::RandomRWFile and Env::NewRandomRWFile().
-* Renamed DBOptions.num_subcompactions to DBOptions.max_subcompactions to make the name better match the actual functionality of the option.
-* Added Equal() method to the Comparator interface that can optionally be overwritten in cases where equality comparisons can be done more efficiently than three-way comparisons.
-* Previous 'experimental' OptimisticTransaction class has been replaced by Transaction class.
-
-## 3.13.0 (8/6/2015)
-### New Features
-* RollbackToSavePoint() in WriteBatch/WriteBatchWithIndex
-* Add NewCompactOnDeletionCollectorFactory() in utilities/table_properties_collectors, which allows rocksdb to mark a SST file as need-compaction when it observes at least D deletion entries in any N consecutive entries in that SST file.  Note that this feature depends on an experimental NeedCompact() API --- the result of this API will not persist after DB restart.
-* Add DBOptions::delete_scheduler. Use NewDeleteScheduler() in include/rocksdb/delete_scheduler.h to create a DeleteScheduler that can be shared among multiple RocksDB instances to control the file deletion rate of SST files that exist in the first db_path.
-
-### Public API Changes
-* Deprecated WriteOptions::timeout_hint_us. We no longer support write timeout. If you really need this option, talk to us and we might consider returning it.
-* Deprecated purge_redundant_kvs_while_flush option.
-* Removed BackupEngine::NewBackupEngine() and NewReadOnlyBackupEngine() that were deprecated in RocksDB 3.8. Please use BackupEngine::Open() instead.
-* Deprecated Compaction Filter V2. We are not aware of any existing use-cases. If you use this filter, your compile will break with RocksDB 3.13. Please let us know if you use it and we'll put it back in RocksDB 3.14.
-* Env::FileExists now returns a Status instead of a boolean
-* Add statistics::getHistogramString() to print detailed distribution of a histogram metric.
-* Add DBOptions::skip_stats_update_on_db_open.  When it is on, DB::Open() will run faster as it skips the random reads required for loading necessary stats from SST files to optimize compaction.
-
-## 3.12.0 (7/2/2015)
-### New Features
-* Added experimental support for optimistic transactions.  See include/rocksdb/utilities/optimistic_transaction.h for more info.
-* Added a new way to report QPS from db_bench (check out --report_file and --report_interval_seconds)
-* Added a cache for individual rows. See DBOptions::row_cache for more info.
-* Several new features on EventListener (see include/rocksdb/listener.h):
- - OnCompationCompleted() now returns per-compaciton job statistics, defined in include/rocksdb/compaction_job_stats.h.
- - Added OnTableFileCreated() and OnTableFileDeleted().
-* Add compaction_options_universal.enable_trivial_move to true, to allow trivial move while performing universal compaction. Trivial move will happen only when all the input files are non overlapping.
-
-### Public API changes
-* EventListener::OnFlushCompleted() now passes FlushJobInfo instead of a list of parameters.
-* DB::GetDbIdentity() is now a const function.  If this function is overridden in your application, be sure to also make GetDbIdentity() const to avoid compile error.
-* Move listeners from ColumnFamilyOptions to DBOptions.
-* Add max_write_buffer_number_to_maintain option
-* DB::CompactRange()'s parameter reduce_level is changed to change_level, to allow users to move levels to lower levels if allowed. It can be used to migrate a DB from options.level_compaction_dynamic_level_bytes=false to options.level_compaction_dynamic_level_bytes.true.
-* Change default value for options.compaction_filter_factory and options.compaction_filter_factory_v2 to nullptr instead of DefaultCompactionFilterFactory and DefaultCompactionFilterFactoryV2.
-* If CancelAllBackgroundWork is called without doing a flush after doing loads with WAL disabled, the changes which haven't been flushed before the call to CancelAllBackgroundWork will be lost.
-* WBWIIterator::Entry() now returns WriteEntry instead of `const WriteEntry&`
-* options.hard_rate_limit is deprecated.
-* When options.soft_rate_limit or options.level0_slowdown_writes_trigger is triggered, the way to slow down writes is changed to: write rate to DB is limited to to options.delayed_write_rate.
-* DB::GetApproximateSizes() adds a parameter to allow the estimation to include data in mem table, with default to be not to include. It is now only supported in skip list mem table.
-* DB::CompactRange() now accept CompactRangeOptions instead of multiple paramters. CompactRangeOptions is defined in include/rocksdb/options.h.
-* CompactRange() will now skip bottommost level compaction for level based compaction if there is no compaction filter, bottommost_level_compaction is introduced in CompactRangeOptions to control when it's possbile to skip bottommost level compaction. This mean that if you want the compaction to produce a single file you need to set bottommost_level_compaction to BottommostLevelCompaction::kForce.
-* Add Cache.GetPinnedUsage() to get the size of memory occupied by entries that are in use by the system.
-* DB:Open() will fail if the compression specified in Options is not linked with the binary. If you see this failure, recompile RocksDB with compression libraries present on your system. Also, previously our default compression was snappy. This behavior is now changed. Now, the default compression is snappy only if it's available on the system. If it isn't we change the default to kNoCompression.
-* We changed how we account for memory used in block cache. Previously, we only counted the sum of block sizes currently present in block cache. Now, we count the actual memory usage of the blocks. For example, a block of size 4.5KB will use 8KB memory with jemalloc. This might decrease your memory usage and possibly decrease performance. Increase block cache size if you see this happening after an upgrade.
-* Add BackupEngineImpl.options_.max_background_operations to specify the maximum number of operations that may be performed in parallel. Add support for parallelized backup and restore.
-* Add DB::SyncWAL() that does a WAL sync without blocking writers.
-
-## 3.11.0 (5/19/2015)
-### New Features
-* Added a new API Cache::SetCapacity(size_t capacity) to dynamically change the maximum configured capacity of the cache. If the new capacity is less than the existing cache usage, the implementation will try to lower the usage by evicting the necessary number of elements following a strict LRU policy.
-* Added an experimental API for handling flashcache devices (blacklists background threads from caching their reads) -- NewFlashcacheAwareEnv
-* If universal compaction is used and options.num_levels > 1, compact files are tried to be stored in none-L0 with smaller files based on options.target_file_size_base. The limitation of DB size when using universal compaction is greatly mitigated by using more levels. You can set num_levels = 1 to make universal compaction behave as before. If you set num_levels > 1 and want to roll back to a previous version, you need to compact all files to a big file in level 0 (by setting target_file_size_base to be large and CompactRange(<cf_handle>, nullptr, nullptr, true, 0) and reopen the DB with the same version to rewrite the manifest, and then you can open it using previous releases.
-* More information about rocksdb background threads are available in Env::GetThreadList(), including the number of bytes read / written by a compaction job, mem-table size and current number of bytes written by a flush job and many more.  Check include/rocksdb/thread_status.h for more detail.
-
-### Public API changes
-* TablePropertiesCollector::AddUserKey() is added to replace TablePropertiesCollector::Add(). AddUserKey() exposes key type, sequence number and file size up to now to users.
-* DBOptions::bytes_per_sync used to apply to both WAL and table files. As of 3.11 it applies only to table files. If you want to use this option to sync WAL in the background, please use wal_bytes_per_sync
-
-## 3.10.0 (3/24/2015)
-### New Features
-* GetThreadStatus() is now able to report detailed thread status, including:
- - Thread Operation including flush and compaction.
- - The stage of the current thread operation.
- - The elapsed time in micros since the current thread operation started.
- More information can be found in include/rocksdb/thread_status.h.  In addition, when running db_bench with --thread_status_per_interval, db_bench will also report thread status periodically.
-* Changed the LRU caching algorithm so that referenced blocks (by iterators) are never evicted. This change made parameter removeScanCountLimit obsolete. Because of that NewLRUCache doesn't take three arguments anymore. table_cache_remove_scan_limit option is also removed
-* By default we now optimize the compilation for the compilation platform (using -march=native). If you want to build portable binary, use 'PORTABLE=1' before the make command.
-* We now allow level-compaction to place files in different paths by
-  specifying them in db_paths along with the target_size.
-  Lower numbered levels will be placed earlier in the db_paths and higher
-  numbered levels will be placed later in the db_paths vector.
-* Potentially big performance improvements if you're using RocksDB with lots of column families (100-1000)
-* Added BlockBasedTableOptions.format_version option, which allows user to specify which version of block based table he wants. As a general guidline, newer versions have more features, but might not be readable by older versions of RocksDB.
-* Added new block based table format (version 2), which you can enable by setting BlockBasedTableOptions.format_version = 2. This format changes how we encode size information in compressed blocks and should help with memory allocations if you're using Zlib or BZip2 compressions.
-* MemEnv (env that stores data in memory) is now available in default library build. You can create it by calling NewMemEnv().
-* Add SliceTransform.SameResultWhenAppended() to help users determine it is safe to apply prefix bloom/hash.
-* Block based table now makes use of prefix bloom filter if it is a full fulter.
-* Block based table remembers whether a whole key or prefix based bloom filter is supported in SST files. Do a sanity check when reading the file with users' configuration.
-* Fixed a bug in ReadOnlyBackupEngine that deleted corrupted backups in some cases, even though the engine was ReadOnly
-* options.level_compaction_dynamic_level_bytes, a feature to allow RocksDB to pick dynamic base of bytes for levels. With this feature turned on, we will automatically adjust max bytes for each level. The goal of this feature is to have lower bound on size amplification. For more details, see comments in options.h.
-* Added an abstract base class WriteBatchBase for write batches
-* Fixed a bug where we start deleting files of a dropped column families even if there are still live references to it
-
-### Public API changes
-* Deprecated skip_log_error_on_recovery and table_cache_remove_scan_count_limit options.
-* Logger method logv with log level parameter is now virtual
-
-### RocksJava
-* Added compression per level API.
-* MemEnv is now available in RocksJava via RocksMemEnv class.
-* lz4 compression is now included in rocksjava static library when running `make rocksdbjavastatic`.
-* Overflowing a size_t when setting rocksdb options now throws an IllegalArgumentException, which removes the necessity for a developer to catch these Exceptions explicitly.
-
-## 3.9.0 (12/8/2014)
-
-### New Features
-* Add rocksdb::GetThreadList(), which in the future will return the current status of all
-  rocksdb-related threads.  We will have more code instruments in the following RocksDB
-  releases.
-* Change convert function in rocksdb/utilities/convenience.h to return Status instead of boolean.
-  Also add support for nested options in convert function
-
-### Public API changes
-* New API to create a checkpoint added. Given a directory name, creates a new
-  database which is an image of the existing database.
-* New API LinkFile added to Env. If you implement your own Env class, an
-  implementation of the API LinkFile will have to be provided.
-* MemTableRep takes MemTableAllocator instead of Arena
-
-### Improvements
-* RocksDBLite library now becomes smaller and will be compiled with -fno-exceptions flag.
-
-## 3.8.0 (11/14/2014)
-
-### Public API changes
-* BackupEngine::NewBackupEngine() was deprecated; please use BackupEngine::Open() from now on.
-* BackupableDB/RestoreBackupableDB have new GarbageCollect() methods, which will clean up files from corrupt and obsolete backups.
-* BackupableDB/RestoreBackupableDB have new GetCorruptedBackups() methods which list corrupt backups.
-
-### Cleanup
-* Bunch of code cleanup, some extra warnings turned on (-Wshadow, -Wshorten-64-to-32, -Wnon-virtual-dtor)
-
-### New features
-* CompactFiles and EventListener, although they are still in experimental state
-* Full ColumnFamily support in RocksJava.
-
-## 3.7.0 (11/6/2014)
-### Public API changes
-* Introduce SetOptions() API to allow adjusting a subset of options dynamically online
-* Introduce 4 new convenient functions for converting Options from string: GetColumnFamilyOptionsFromMap(), GetColumnFamilyOptionsFromString(), GetDBOptionsFromMap(), GetDBOptionsFromString()
-* Remove WriteBatchWithIndex.Delete() overloads using SliceParts
-* When opening a DB, if options.max_background_compactions is larger than the existing low pri pool of options.env, it will enlarge it. Similarly, options.max_background_flushes is larger than the existing high pri pool of options.env, it will enlarge it.
-
-## 3.6.0 (10/7/2014)
-### Disk format changes
-* If you're using RocksDB on ARM platforms and you're using default bloom filter, there is a disk format change you need to be aware of. There are three steps you need to do when you convert to new release: 1. turn off filter policy, 2. compact the whole database, 3. turn on filter policy
-
-### Behavior changes
-* We have refactored our system of stalling writes.  Any stall-related statistics' meanings are changed. Instead of per-write stall counts, we now count stalls per-epoch, where epochs are periods between flushes and compactions. You'll find more information in our Tuning Perf Guide once we release RocksDB 3.6.
-* When disableDataSync=true, we no longer sync the MANIFEST file.
-* Add identity_as_first_hash property to CuckooTable. SST file needs to be rebuilt to be opened by reader properly.
-
-### Public API changes
-* Change target_file_size_base type to uint64_t from int.
-* Remove allow_thread_local. This feature was proved to be stable, so we are turning it always-on.
-
-## 3.5.0 (9/3/2014)
-### New Features
-* Add include/utilities/write_batch_with_index.h, providing a utilitiy class to query data out of WriteBatch when building it.
-* Move BlockBasedTable related options to BlockBasedTableOptions from Options. Change corresponding JNI interface. Options affected include:
-  no_block_cache, block_cache, block_cache_compressed, block_size, block_size_deviation, block_restart_interval, filter_policy, whole_key_filtering. filter_policy is changed to shared_ptr from a raw pointer.
-* Remove deprecated options: disable_seek_compaction and db_stats_log_interval
-* OptimizeForPointLookup() takes one parameter for block cache size. It now builds hash index, bloom filter, and block cache.
-
-### Public API changes
-* The Prefix Extractor used with V2 compaction filters is now passed user key to SliceTransform::Transform instead of unparsed RocksDB key.
-
-## 3.4.0 (8/18/2014)
-### New Features
-* Support Multiple DB paths in universal style compactions
-* Add feature of storing plain table index and bloom filter in SST file.
-* CompactRange() will never output compacted files to level 0. This used to be the case when all the compaction input files were at level 0.
-* Added iterate_upper_bound to define the extent upto which the forward iterator will return entries. This will prevent iterating over delete markers and overwritten entries for edge cases where you want to break out the iterator anyways. This may improve performance in case there are a large number of delete markers or overwritten entries.
-
-### Public API changes
-* DBOptions.db_paths now is a vector of a DBPath structure which indicates both of path and target size
-* NewPlainTableFactory instead of bunch of parameters now accepts PlainTableOptions, which is defined in include/rocksdb/table.h
-* Moved include/utilities/*.h to include/rocksdb/utilities/*.h
-* Statistics APIs now take uint32_t as type instead of Tickers. Also make two access functions getTickerCount and histogramData const
-* Add DB property rocksdb.estimate-num-keys, estimated number of live keys in DB.
-* Add DB::GetIntProperty(), which returns DB properties that are integer as uint64_t.
-* The Prefix Extractor used with V2 compaction filters is now passed user key to SliceTransform::Transform instead of unparsed RocksDB key.
-
-## 3.3.0 (7/10/2014)
-### New Features
-* Added JSON API prototype.
-* HashLinklist reduces performance outlier caused by skewed bucket by switching data in the bucket from linked list to skip list. Add parameter threshold_use_skiplist in NewHashLinkListRepFactory().
-* RocksDB is now able to reclaim storage space more effectively during the compaction process.  This is done by compensating the size of each deletion entry by the 2X average value size, which makes compaction to be triggerred by deletion entries more easily.
-* Add TimeOut API to write.  Now WriteOptions have a variable called timeout_hint_us.  With timeout_hint_us set to non-zero, any write associated with this timeout_hint_us may be aborted when it runs longer than the specified timeout_hint_us, and it is guaranteed that any write completes earlier than the specified time-out will not be aborted due to the time-out condition.
-* Add a rate_limiter option, which controls total throughput of flush and compaction. The throughput is specified in bytes/sec. Flush always has precedence over compaction when available bandwidth is constrained.
-
-### Public API changes
-* Removed NewTotalOrderPlainTableFactory because it is not used and implemented semantically incorrect.
-
-## 3.2.0 (06/20/2014)
-
-### Public API changes
-* We removed seek compaction as a concept from RocksDB because:
-1) It makes more sense for spinning disk workloads, while RocksDB is primarily designed for flash and memory,
-2) It added some complexity to the important code-paths,
-3) None of our internal customers were really using it.
-Because of that, Options::disable_seek_compaction is now obsolete. It is still a parameter in Options, so it does not break the build, but it does not have any effect. We plan to completely remove it at some point, so we ask users to please remove this option from your code base.
-* Add two paramters to NewHashLinkListRepFactory() for logging on too many entries in a hash bucket when flushing.
-* Added new option BlockBasedTableOptions::hash_index_allow_collision. When enabled, prefix hash index for block-based table will not store prefix and allow hash collision, reducing memory consumption.
-
-### New Features
-* PlainTable now supports a new key encoding: for keys of the same prefix, the prefix is only written once. It can be enabled through encoding_type paramter of NewPlainTableFactory()
-* Add AdaptiveTableFactory, which is used to convert from a DB of PlainTable to BlockBasedTabe, or vise versa. It can be created using NewAdaptiveTableFactory()
-
-### Performance Improvements
-* Tailing Iterator re-implemeted with ForwardIterator + Cascading Search Hint , see ~20% throughput improvement.
-
-## 3.1.0 (05/21/2014)
-
-### Public API changes
-* Replaced ColumnFamilyOptions::table_properties_collectors with ColumnFamilyOptions::table_properties_collector_factories
-
-### New Features
-* Hash index for block-based table will be materialized and reconstructed more efficiently. Previously hash index is constructed by scanning the whole table during every table open.
-* FIFO compaction style
-
-## 3.0.0 (05/05/2014)
-
-### Public API changes
-* Added _LEVEL to all InfoLogLevel enums
-* Deprecated ReadOptions.prefix and ReadOptions.prefix_seek. Seek() defaults to prefix-based seek when Options.prefix_extractor is supplied. More detail is documented in https://github.com/facebook/rocksdb/wiki/Prefix-Seek-API-Changes
-* MemTableRepFactory::CreateMemTableRep() takes info logger as an extra parameter.
-
-### New Features
-* Column family support
-* Added an option to use different checksum functions in BlockBasedTableOptions
-* Added ApplyToAllCacheEntries() function to Cache
 
 ## 2.8.0 (04/04/2014)
 
@@ -343,7 +18,7 @@ Because of that, Options::disable_seek_compaction is now obsolete. It is still a
 * Added Env::GetThreadPoolQueueLen(), which returns the waiting queue length of thread pools
 * Added a command "checkconsistency" in ldb tool, which checks
   if file system state matches DB state (file existence and file sizes)
-* Separate options related to block based table to a new struct BlockBasedTableOptions.
+* Separate options related to block based table to a new struct BlockBasedTableOptions
 * WriteBatch has a new function Count() to return total size in the batch, and Data() now returns a reference instead of a copy
 * Add more counters to perf context.
 * Supports several more DB properties: compaction-pending, background-errors and cur-size-active-mem-table.

INSTALL.md

@@ -1,41 +1,19 @@
-## Compilation
-
-**Important**: If you plan to run RocksDB in production, don't compile using default 
-`make` or `make all`. That will compile RocksDB in debug mode, which is much slower
-than release mode.
-
-RocksDB's library should be able to compile without any dependency installed,
-although we recommend installing some compression libraries (see below).
-We do depend on newer gcc/clang with C++11 support.
-
-There are few options when compiling RocksDB:
-
-* [recommended] `make static_lib` will compile librocksdb.a, RocksDB static library. Compiles static library in release mode.
-
-* `make shared_lib` will compile librocksdb.so, RocksDB shared library. Compiles shared library in release mode.
-
-* `make check` will compile and run all the unit tests. `make check` will compile RocksDB in debug mode.
-
-* `make all` will compile our static library, and all our tools and unit tests. Our tools
-depend on gflags. You will need to have gflags installed to run `make all`. This will compile RocksDB in debug mode. Don't
-use binaries compiled by `make all` in production.
-
-* By default the binary we produce is optimized for the platform you're compiling on
-(-march=native or the equivalent). If you want to build a portable binary, add 'PORTABLE=1' before
-your make commands, like this: `PORTABLE=1 make static_lib`
-
 ## Dependencies
 
-* You can link RocksDB with following compression libraries:
+RocksDB is developed on Linux (CentOS release 5.2), with gcc 4.8.1.
+It depends on gcc with C++11 support.
+
+* RocksDB depends on the following libraries:
   - [zlib](http://www.zlib.net/) - a library for data compression.
   - [bzip2](http://www.bzip.org/) - a library for data compression.
   - [snappy](https://code.google.com/p/snappy/) - a library for fast
       data compression.
+  - [gflags](https://code.google.com/p/gflags/) - a library that handles
+      command line flags processing.
 
-* All our tools depend on:
-  - [gflags](https://gflags.github.io/gflags/) - a library that handles
-      command line flags processing. You can compile rocksdb library even
-      if you don't have gflags installed.
+RocksDB will successfully compile without the compression libraries included,
+but some things may fail. We do not support releases without the compression
+libraries. You are on your own.
 
 ## Supported platforms
 
@@ -80,12 +58,23 @@ your make commands, like this: `PORTABLE=1 make static_lib`
         * Update XCode:  run `xcode-select --install` (or install it from XCode App's settting).
         * Install via [homebrew](http://brew.sh/).
             * If you're first time developer in MacOS, you still need to run: `xcode-select --install` in your command line.
-            * run `brew tap homebrew/versions; brew install gcc47 --use-llvm` to install gcc 4.7 (or higher).
-    * run `brew install rocksdb`
+            * run `brew tap homebrew/dupes; brew install gcc47 --use-llvm` to install gcc 4.7 (or higher).
+    * Install zlib, bzip2 and snappy libraries for compression.
+    * Install gflags. We have included a script
+    `build_tools/mac-install-gflags.sh`, which should automatically install it.
+    If you installed gflags by other means (for example, `brew install gflags`),
+    please set `LIBRARY_PATH` and `CPATH` accordingly.
+    * Please note that some of the optimizations/features are disabled in OSX.
+    We did not run any production workloads on it.
 
 * **iOS**:
-  * Run: `TARGET_OS=IOS make static_lib`. When building the project which uses rocksdb iOS library, make sure to define two important pre-processing macros: `ROCKSDB_LITE` and `IOS_CROSS_COMPILE`.
+  * Run: `TARGET_OS=IOS make static_lib`
 
-* **Windows**:
-  * For building with MS Visual Studio 13 you will need Update 4 installed.
-  * Read and follow the instructions at CMakeLists.txt
+## Compilation
+`make clean; make` will compile librocksdb.a (RocksDB static library) and all
+the unit tests. You can run all unit tests with `make check`.
+
+For shared library builds, exec `make shared_lib` instead.
+
+If you followed the above steps and your compile or unit tests fail,
+please submit an issue: (https://github.com/facebook/rocksdb/issues)

LANGUAGE-BINDINGS.md

@@ -1,11 +0,0 @@
-This is the list of all known third-party language bindings for RocksDB. If something is missing, please open a pull request to add it.
-
-* Java - https://github.com/facebook/rocksdb/tree/master/java
-* Python - http://pyrocksdb.readthedocs.org/en/latest/
-* Perl - https://metacpan.org/pod/RocksDB
-* Node.js - https://npmjs.org/package/rocksdb
-* Go - https://github.com/tecbot/gorocksdb
-* Ruby - http://rubygems.org/gems/rocksdb-ruby
-* Haskell - https://hackage.haskell.org/package/rocksdb-haskell
-* PHP - https://github.com/Photonios/rocksdb-php
-* C# - https://github.com/warrenfalk/rocksdb-sharp

LICENSE

@@ -2,7 +2,7 @@ BSD License
 
 For rocksdb software
 
-Copyright (c) 2011-present, Facebook, Inc.
+Copyright (c) 2014, Facebook, Inc.
 All rights reserved.
 ---------------------------------------------------------------------
 

PATENTS

@@ -1,33 +1,23 @@
-Additional Grant of Patent Rights Version 2
+Additional Grant of Patent Rights
 
-"Software" means the RocksDB software distributed by Facebook, Inc.
+“Software” means the rocksdb software distributed by Facebook, Inc.
 
-Facebook, Inc. ("Facebook") hereby grants to each recipient of the Software
-("you") a perpetual, worldwide, royalty-free, non-exclusive, irrevocable
-(subject to the termination provision below) license under any Necessary
-Claims, to make, have made, use, sell, offer to sell, import, and otherwise
-transfer the Software. For avoidance of doubt, no license is granted under
-Facebook’s rights in any patent claims that are infringed by (i) modifications
-to the Software made by you or any third party or (ii) the Software in
-combination with any software or other technology.
+Facebook hereby grants you a perpetual, worldwide, royalty-free,
+non-exclusive, irrevocable (subject to the termination provision below)
+license under any rights in any patent claims owned by Facebook, to make,
+have made, use, sell, offer to sell, import, and otherwise transfer the
+Software. For avoidance of doubt, no license is granted under Facebook’s
+rights in any patent claims that are infringed by (i) modifications to the
+Software made by you or a third party, or (ii) the Software in combination
+with any software or other technology provided by you or a third party.
 
-The license granted hereunder will terminate, automatically and without notice,
-if you (or any of your subsidiaries, corporate affiliates or agents) initiate
-directly or indirectly, or take a direct financial interest in, any Patent
-Assertion: (i) against Facebook or any of its subsidiaries or corporate
-affiliates, (ii) against any party if such Patent Assertion arises in whole or
-in part from any software, technology, product or service of Facebook or any of
-its subsidiaries or corporate affiliates, or (iii) against any party relating
-to the Software. Notwithstanding the foregoing, if Facebook or any of its
-subsidiaries or corporate affiliates files a lawsuit alleging patent
-infringement against you in the first instance, and you respond by filing a
-patent infringement counterclaim in that lawsuit against that party that is
-unrelated to the Software, the license granted hereunder will not terminate
-under section (i) of this paragraph due to such counterclaim.
-
-A "Necessary Claim" is a claim of a patent owned by Facebook that is
-necessarily infringed by the Software standing alone.
-
-A "Patent Assertion" is any lawsuit or other action alleging direct, indirect,
-or contributory infringement or inducement to infringe any patent, including a
-cross-claim or counterclaim.
+The license granted hereunder will terminate, automatically and without
+notice, for anyone that makes any claim (including by filing any lawsuit,
+assertion or other action) alleging (a) direct, indirect, or contributory
+infringement or inducement to infringe any patent: (i) by Facebook or any
+of its subsidiaries or affiliates, whether or not such claim is related
+to the Software, (ii) by any party if such claim arises in whole or in
+part from any software, product or service of Facebook or any of its
+subsidiaries or affiliates, whether or not such claim is related to the
+Software, or (iii) by any party relating to the Software; or (b) that
+any right in any patent claim of Facebook is invalid or unenforceable.

README

@@ -0,0 +1,82 @@
+rocksdb: A persistent key-value store for flash storage
+Authors: * The Facebook Database Engineering Team
+         * Build on earlier work on leveldb by Sanjay Ghemawat
+           (sanjay@google.com) and Jeff Dean (jeff@google.com)
+
+This code is a library that forms the core building block for a fast
+key value server, especially suited for storing data on flash drives.
+It has an Log-Structured-Merge-Database (LSM) design with flexible tradeoffs
+between Write-Amplification-Factor(WAF), Read-Amplification-Factor (RAF)
+and Space-Amplification-Factor(SAF). It has multi-threaded compactions,
+making it specially suitable for storing multiple terabytes of data in a
+single database.
+
+The core of this code has been derived from open-source leveldb.
+
+The code under this directory implements a system for maintaining a
+persistent key/value store.
+
+See doc/index.html and github wiki (https://github.com/facebook/rocksdb/wiki)
+for more explanation.
+
+The public interface is in include/*.  Callers should not include or
+rely on the details of any other header files in this package.  Those
+internal APIs may be changed without warning.
+
+Guide to header files:
+
+include/rocksdb/db.h
+    Main interface to the DB: Start here
+
+include/rocksdb/options.h
+    Control over the behavior of an entire database, and also
+    control over the behavior of individual reads and writes.
+
+include/rocksdb/comparator.h
+    Abstraction for user-specified comparison function.  If you want
+    just bytewise comparison of keys, you can use the default comparator,
+    but clients can write their own comparator implementations if they
+    want custom ordering (e.g. to handle different character
+    encodings, etc.)
+
+include/rocksdb/iterator.h
+    Interface for iterating over data. You can get an iterator
+    from a DB object.
+
+include/rocksdb/write_batch.h
+    Interface for atomically applying multiple updates to a database.
+
+include/rocksdb/slice.h
+    A simple module for maintaining a pointer and a length into some
+    other byte array.
+
+include/rocksdb/status.h
+    Status is returned from many of the public interfaces and is used
+    to report success and various kinds of errors.
+
+include/rocksdb/env.h
+    Abstraction of the OS environment.  A posix implementation of
+    this interface is in util/env_posix.cc
+
+include/rocksdb/table_builder.h
+    Lower-level modules that most clients probably won't use directly
+
+include/rocksdb/cache.h
+    An API for the block cache.
+
+include/rocksdb/compaction_filter.h
+    An API for a application filter invoked on every compaction.
+
+include/rocksdb/filter_policy.h
+    An API for configuring a bloom filter.
+
+include/rocksdb/memtablerep.h
+    An API for implementing a memtable.
+
+include/rocksdb/statistics.h
+    An API to retrieve various database statistics.
+
+include/rocksdb/transaction_log.h
+    An API to retrieve transaction logs from a database.
+
+Design discussions are conducted in https://www.facebook.com/groups/rocksdb.dev/

README.fb

@@ -0,0 +1,3 @@
+* Detailed instructions on how to compile using fbcode and jemalloc
+
+* Latest release is 2.7.fb

README.md

@@ -1,25 +0,0 @@
-## RocksDB: A Persistent Key-Value Store for Flash and RAM Storage
-
-[![Build Status](https://travis-ci.org/facebook/rocksdb.svg?branch=master)](https://travis-ci.org/facebook/rocksdb)
-
-RocksDB is developed and maintained by Facebook Database Engineering Team.
-It is built on earlier work on LevelDB by Sanjay Ghemawat (sanjay@google.com)
-and Jeff Dean (jeff@google.com)
-
-This code is a library that forms the core building block for a fast
-key value server, especially suited for storing data on flash drives.
-It has a Log-Structured-Merge-Database (LSM) design with flexible tradeoffs
-between Write-Amplification-Factor (WAF), Read-Amplification-Factor (RAF)
-and Space-Amplification-Factor (SAF). It has multi-threaded compactions,
-making it specially suitable for storing multiple terabytes of data in a
-single database.
-
-Start with example usage here: https://github.com/facebook/rocksdb/tree/master/examples
-
-See the [github wiki](https://github.com/facebook/rocksdb/wiki) for more explanation.
-
-The public interface is in `include/`.  Callers should not include or
-rely on the details of any other header files in this package.  Those
-internal APIs may be changed without warning.
-
-Design discussions are conducted in https://www.facebook.com/groups/rocksdb.dev/

ROCKSDB_LITE.md

@@ -1,21 +0,0 @@
-# RocksDBLite
-
-RocksDBLite is a project focused on mobile use cases, which don't need a lot of fancy things we've built for server workloads and they are very sensitive to binary size. For that reason, we added a compile flag ROCKSDB_LITE that comments out a lot of the nonessential code and keeps the binary lean.
-
-Some examples of the features disabled by ROCKSDB_LITE:
-* compiled-in support for LDB tool
-* No backupable DB
-* No support for replication (which we provide in form of TrasactionalIterator)
-* No advanced monitoring tools
-* No special-purpose memtables that are highly optimized for specific use cases
-* No Transactions
-
-When adding a new big feature to RocksDB, please add ROCKSDB_LITE compile guard if:
-* Nobody from mobile really needs your feature,
-* Your feature is adding a lot of weight to the binary.
-
-Don't add ROCKSDB_LITE compile guard if:
-* It would introduce a lot of code complexity. Compile guards make code harder to read. It's a trade-off.
-* Your feature is not adding a lot of weight.
-
-If unsure, ask. :)

USERS.md

@@ -1,61 +0,0 @@
-This document lists users of RocksDB and their use cases. If you are using RocksDB, please open a pull request and add yourself to the list.
-
-## Facebook
-At Facebook, we use RocksDB as a backend for many different stateful services. We're also experimenting with running RocksDB as a storage engine for two databases:
-
-1. MyRocks -- https://github.com/MySQLOnRocksDB/mysql-5.6
-2. MongoRocks -- https://github.com/mongodb-partners/mongo-rocks
-
-## LinkedIn
-Two different use cases at Linkedin are using RocksDB as a storage engine:
-
-1. LinkedIn's follow feed for storing user's activities. Check out the blog post: https://engineering.linkedin.com/blog/2016/03/followfeed--linkedin-s-feed-made-faster-and-smarter
-2. Apache Samza, open source framework for stream processing
-
-Learn more about those use cases in a Tech Talk by Ankit Gupta and Naveen Somasundaram: http://www.youtube.com/watch?v=plqVp_OnSzg
-
-## Yahoo
-Yahoo is using RocksDB as a storage engine for their biggest distributed data store Sherpa. Learn more about it here: http://yahooeng.tumblr.com/post/120730204806/sherpa-scales-new-heights
-
-## CockroachDB
-CockroachDB is an open-source geo-replicated transactional database (still in development). They are using RocksDB as their storage engine. Check out their github: https://github.com/cockroachdb/cockroach
-
-## DNANexus
-DNANexus is using RocksDB to speed up processing of genomics data.
-You can learn more from this great blog post by Mike Lin: http://devblog.dnanexus.com/faster-bam-sorting-with-samtools-and-rocksdb/
-
-## Iron.io
-Iron.io is using RocksDB as a storage engine for their distributed queueing system.
-Learn more from Tech Talk by Reed Allman: http://www.youtube.com/watch?v=HTjt6oj-RL4
-
-## Tango Me
-Tango is using RocksDB as a graph storage to store all users' connection data and other social activity data.
-
-## Turn
-Turn is using RocksDB as a storage layer for their key/value store, serving at peak 2.4MM QPS out of different datacenters.
-Check out our RocksDB Protobuf merge operator at: https://github.com/vladb38/rocksdb_protobuf
-
-## Santanader UK/Cloudera Profession Services
-Check out their blog post: http://blog.cloudera.com/blog/2015/08/inside-santanders-near-real-time-data-ingest-architecture/
-
-## Airbnb
-Airbnb is using RocksDB as a storage engine for their personalized search service. You can learn more about it here: https://www.youtube.com/watch?v=ASQ6XMtogMs
-
-## Pinterest
-Pinterest's Object Retrieval System uses RocksDB for storage: https://www.youtube.com/watch?v=MtFEVEs_2Vo
-
-## Smyte
-[Smyte](https://www.smyte.com/) uses RocksDB as the storage layer for their core key-value storage, high-performance counters and time-windowed HyperLogLog services.
-
-## Rakuten Marketing
-[Rakuten Marketing](https://marketing.rakuten.com/) uses RocksDB as the disk cache layer for the real-time bidding service in their Performance DSP.
-
-## VWO, Wingify
-[VWO's](https://vwo.com/) Smart Code checker and URL helper uses RocksDB to store all the URLs where VWO's Smart Code is installed.
-
-## quasardb
-[quasardb](https://www.quasardb.net) is a high-performance, distributed, transactional key-value database that integrates well with in-memory analytics engines such as Apache Spark. 
-quasardb uses a heavily tuned RocksDB as its persistence layer.
-
-## Netflix
-[Netflix](http://techblog.netflix.com/2016/05/application-data-caching-using-ssds.html) uses RocksDB on spinning disks to cache application data.

Vagrantfile

@@ -1,33 +0,0 @@
-Vagrant.configure("2") do |config|
-
-  config.vm.provider "virtualbox" do |v|
-    v.memory = 4096
-    v.cpus = 2
-  end
-
-  config.vm.define "ubuntu14" do |box|
-    box.vm.box = "ubuntu/trusty64"
-  end
-
-  config.vm.define "centos65" do |box|
-    box.vm.box = "chef/centos-6.5"
-  end
-
-  config.vm.define "FreeBSD10" do |box|
-    box.vm.guest = :freebsd
-    box.vm.box = "robin/freebsd-10"
-    # FreeBSD does not support 'mount_virtualbox_shared_folder', use NFS
-    box.vm.synced_folder ".", "/vagrant", :nfs => true, id: "vagrant-root"
-    box.vm.network "private_network", ip: "10.0.1.10"
-
-    # build everything after creating VM, skip using --no-provision
-    box.vm.provision "shell", inline: <<-SCRIPT
-      pkg install -y gmake clang35
-      export CXX=/usr/local/bin/clang++35
-      cd /vagrant
-      gmake clean
-      gmake all OPT=-g
-    SCRIPT
-  end
-
-end

WINDOWS_PORT.md

@@ -1,228 +0,0 @@
-# Microsoft Contribution Notes
-
-## Contributors
-* Alexander Zinoviev https://github.com/zinoale
-* Dmitri Smirnov https://github.com/yuslepukhin
-* Praveen Rao  https://github.com/PraveenSinghRao
-* Sherlock Huang  https://github.com/SherlockNoMad
-
-## Introduction
-RocksDB is a well proven open source key-value persistent store, optimized for fast storage. It provides scalability with number of CPUs and storage IOPS, to support IO-bound, in-memory and write-once workloads, most importantly, to be flexible to allow for innovation.
-
-As Microsoft Bing team we have been continuously pushing hard to improve the scalability, efficiency of platform and eventually benefit Bing end-user satisfaction.  We would like to explore the opportunity to embrace open source, RocksDB here, to use, enhance and customize for our usage, and also contribute back to the RocksDB community. Herein, we are pleased to offer this RocksDB port for Windows platform.
-
-These notes describe some decisions and changes we had to make with regards to porting RocksDB on Windows. We hope this will help both reviewers and users of the Windows port.
-We are open for comments and improvements.
-
-## OS specifics
-All of the porting, testing and benchmarking was done on Windows Server 2012 R2 Datacenter 64-bit but to the best of our knowledge there is not a specific API we used during porting that is unsupported on other Windows OS after Vista.
-
-## Porting goals
-We strive to achieve the following goals:
-* make use of the existing porting interface of RocksDB
-* make minimum [WY2]modifications within platform independent code.
-* make all unit test pass both in debug and release builds. 
-  * Note: latest introduction of SyncPoint seems to disable running db_test in Release.
-* make performance on par with published benchmarks accounting for HW differences
-* we would like to keep the port code inline with the master branch with no forking
-
-## Build system
-We have chosen CMake as a widely accepted build system to build the Windows port. It is very fast and convenient. 
-
-At the same time it generates Visual Studio projects that are both usable from a command line and IDE.
-
-The top-level CMakeLists.txt file contains description of all targets and build rules. It also provides brief instructions on how to build the software for Windows. One more build related file is thirdparty.inc that also resides on the top level. This file must be edited to point to actual third party libraries location.
-We think that it would be beneficial to merge the existing make-based build system and the new cmake-based build system into a single one to use on all platforms.
-
-All building and testing was done for 64-bit. We have not conducted any testing for 32-bit and early reports indicate that it will not run on 32-bit.
-
-## C++ and STL notes
-We had to make some minimum changes within the portable files that either account for OS differences or the shortcomings of C++11 support in the current version of the MS compiler. Most or all of them are expected to be fixed in the upcoming compiler releases.
-
-We plan to use this port for our business purposes here at Bing and this provided business justification for this port. This also means, we do not have at present to choose the compiler version at will.
-
-* Certain headers that are not present and not necessary on Windows were simply `#ifndef OS_WIN` in a few places (`unistd.h`)
-* All posix specific headers were replaced to port/port.h which worked well
-* Replaced `dirent.h` for `port/dirent.h` (very few places) with the implementation of the relevant interfaces within `rocksdb::port` namespace
-* Replaced `sys/time.h` to `port/sys_time.h` (few places) implemented equivalents within `rocksdb::port`
-* `printf %z` specification is not supported on Windows. To imitate existing standards we came up with a string macro `ROCKSDB_PRIszt` which expands to `%z` on posix systems and to Iu on windows.
-* in class member initialization were moved to a __ctors in some cases
-* `constexpr` is not supported. We had to replace `std::numeric_limits<>::max/min()` to its C macros for constants. Sometimes we had to make class members `static const` and place a definition within a .cc file.
-* `constexpr` for functions was replaced to a template specialization (1 place)
-* Union members that have non-trivial constructors were replaced to `char[]` in one place along with bug fixes (spatial experimental feature)
-* Zero-sized arrays are deemed a non-standard extension which we converted to 1 size array and that should work well for the purposes of these classes.
-* `std::chrono` lacks nanoseconds support (fixed in the upcoming release of the STL) and we had to use `QueryPerfCounter()` within env_win.cc
-* Function local statics initialization is still not safe. Used `std::once` to mitigate within WinEnv.
-
-## Windows Environments notes
-We endeavored to make it functionally on par with posix_env. This means we replicated the functionality of the thread pool and other things as precise as possible, including:
-* Replicate posix logic using std:thread primitives.
-* Implement all posix_env disk access functionality.
-* Set `use_os_buffer=false` to disable OS disk buffering for WinWritableFile and WinRandomAccessFile.
-* Replace `pread/pwrite` with `WriteFile/ReadFile` with `OVERLAPPED` structure.
-* Use `SetFileInformationByHandle` to compensate absence of `fallocate`.
-
-### In detail
-Even though Windows provides its own efficient thread-pool implementation we chose to replicate posix logic using `std::thread` primitives. This allows anyone to quickly detect any changes within the posix source code and replicate them within windows env. This has proven to work very well. At the same time for anyone who wishes to replace the built-in thread-pool can do so using RocksDB stackable environments.
-
-For disk access we implemented all of the functionality present within the posix_env which includes memory mapped files, random access, rate-limiter support etc.
-The `use_os_buffer` flag on Posix platforms currently denotes disabling read-ahead log via `fadvise` mechanism. Windows does not have `fadvise` system call. What is more, it implements disk cache in a way that differs from Linux greatly. It’s not an uncommon practice on Windows to perform un-buffered disk access to gain control of the memory consumption. We think that in our use case this may also be a good configuration option at the expense of disk throughput. To compensate one may increase the configured in-memory cache size instead. Thus we have chosen  `use_os_buffer=false` to disable OS disk buffering for `WinWritableFile` and `WinRandomAccessFile`. The OS imposes restrictions on the alignment of the disk offsets, buffers used and the amount of data that is read/written when accessing files in un-buffered mode. When the option is true, the classes behave in a standard way. This allows to perform writes and reads in cases when un-buffered access does not make sense such as WAL and MANIFEST.
-
-We have replaced `pread/pwrite` with `WriteFile/ReadFile` with `OVERLAPPED` structure so we can atomically seek to the position of the disk operation but still perform the operation synchronously. Thus we able to emulate that functionality of `pread/pwrite` reasonably well. The only difference is that the file pointer is not returned to its original position but that hardly matters given the random nature of access.
-
-We used `SetFileInformationByHandle` both to truncate files after writing a full final page to disk and to pre-allocate disk space for faster I/O thus compensating for the absence of `fallocate` although some differences remain. For example, the pre-allocated space is not filled with zeros like on Linux, however, on a positive note, the end of file position is also not modified after pre-allocation.
-
-RocksDB renames, copies and deletes files at will even though they may be opened with another handle at the same time. We had to relax and allow nearly all the concurrent access permissions possible.
-
-## Thread-Local Storage
-Thread-Local storage plays a significant role for RocksDB performance. Rather than creating a separate implementation we chose to create inline wrappers that forward `pthread_specific` calls to Windows `Tls` interfaces within `rocksdb::port` namespace. This leaves the existing meat of the logic in tact and unchanged and just as maintainable.
-
-To mitigate the lack of thread local storage cleanup on thread-exit we added a limited amount of windows specific code within the same thread_local.cc file that injects a cleanup callback into a `"__tls"` structure within `".CRT$XLB"` data segment. This approach guarantees that the callback is invoked regardless of whether RocksDB used within an executable, standalone DLL or within another DLL.
-
-## Jemalloc usage
-
-When RocksDB is used with Jemalloc the latter needs to be initialized before any of the C++ globals or statics. To accomplish that we injected an initialization routine into `".CRT$XCT"` that is automatically invoked by the runtime before initializing static objects. je-uninit is queued to `atexit()`. 
-
-The jemalloc redirecting `new/delete` global operators are used by the linker providing certain conditions are met. See build section in these notes.
-
-## Stack Trace and Unhandled Exception Handler
-
-We decided not to implement these two features because the hosting program as a rule has these two things in it.
-We experienced no inconveniences debugging issues in the debugger or analyzing process dumps if need be and thus we did not
-see this as a priority.
-
-## Performance results
-### Setup
-All of the benchmarks are run on the same set of machines. Here are the details of the test setup:
-* 2 Intel(R) Xeon(R) E5 2450 0 @ 2.10 GHz (total 16 cores)
-* 2 XK0480GDQPH SSD Device, total 894GB free disk
-* Machine has 128 GB of RAM
-* Operating System: Windows Server 2012 R2 Datacenter
-* 100 Million keys; each key is of size 10 bytes, each value is of size 800 bytes
-* total database size is ~76GB
-* The performance result is based on RocksDB 3.11.
-* The parameters used, unless specified, were exactly the same as published in the GitHub Wiki page. 
-
-### RocksDB on flash storage
-
-#### Test 1. Bulk Load of keys in Random Order
-
-Version 3.11 
-
-* Total Run Time: 17.6 min
-* Fillrandom: 5.480 micros/op 182465 ops/sec;  142.0 MB/s
-* Compact: 486056544.000 micros/op 0 ops/sec
-
-Version 3.10 
-
-* Total Run Time: 16.2 min 
-* Fillrandom: 5.018 micros/op 199269 ops/sec;  155.1 MB/s 
-* Compact: 441313173.000 micros/op 0 ops/sec; 
-
-
-#### Test 2. Bulk Load of keys in Sequential Order
-
-Version 3.11 
-
-* Fillseq: 4.944 micros/op 202k ops/sec;  157.4 MB/s
-
-Version 3.10
-
-* Fillseq: 4.105 micros/op 243.6k ops/sec;  189.6 MB/s 
-
-
-#### Test 3. Random Write
-
-Version 3.11 
-
-* Unbuffered I/O enabled
-* Overwrite: 52.661 micros/op 18.9k ops/sec;   14.8 MB/s
-
-Version 3.10
-
-* Unbuffered I/O enabled 
-* Overwrite: 52.661 micros/op 18.9k ops/sec; 
-
-
-#### Test 4. Random Read
-
-Version 3.11 
-
-* Unbuffered I/O enabled
-* Readrandom: 15.716 micros/op 63.6k ops/sec; 49.5 MB/s 
-
-Version 3.10
-
-* Unbuffered I/O enabled 
-* Readrandom: 15.548 micros/op 64.3k ops/sec; 
-
-
-#### Test 5. Multi-threaded read and single-threaded write
-
-Version 3.11
-
-* Unbuffered I/O enabled
-* Readwhilewriting: 25.128 micros/op 39.7k ops/sec; 
-
-Version 3.10
-
-* Unbuffered I/O enabled 
-* Readwhilewriting: 24.854 micros/op 40.2k ops/sec; 
-
-
-### RocksDB In Memory 
-
-#### Test 1. Point Lookup
-
-Version 3.11
-
-80K writes/sec
-* Write Rate Achieved: 40.5k write/sec;
-* Readwhilewriting: 0.314 micros/op 3187455 ops/sec;  364.8 MB/s (715454999 of 715454999 found)
-
-Version 3.10
-
-* Write Rate Achieved:  50.6k write/sec 
-* Readwhilewriting: 0.316 micros/op 3162028 ops/sec; (719576999 of 719576999 found) 
-
-
-*10K writes/sec*
-
-Version 3.11
-
-* Write Rate Achieved: 5.8k/s write/sec
-* Readwhilewriting: 0.246 micros/op 4062669 ops/sec;  464.9 MB/s (915481999 of 915481999 found)
-
-Version 3.10
-
-* Write Rate Achieved: 5.8k/s write/sec 
-* Readwhilewriting: 0.244 micros/op 4106253 ops/sec; (927986999 of 927986999 found) 
-
-
-#### Test 2. Prefix Range Query
-
-Version 3.11
-
-80K writes/sec
-* Write Rate Achieved:  46.3k/s write/sec
-* Readwhilewriting: 0.362 micros/op 2765052 ops/sec;  316.4 MB/s (611549999 of 611549999 found)
-
-Version 3.10
-
-* Write Rate Achieved: 45.8k/s write/sec 
-* Readwhilewriting: 0.317 micros/op 3154941 ops/sec; (708158999 of 708158999 found) 
-
-Version 3.11
-
-10K writes/sec
-* Write Rate Achieved: 5.78k write/sec
-* Readwhilewriting: 0.269 micros/op 3716692 ops/sec;  425.3 MB/s (837401999 of 837401999 found)
-
-Version 3.10
-
-* Write Rate Achieved: 5.7k write/sec 
-* Readwhilewriting: 0.261 micros/op 3830152 ops/sec; (863482999 of 863482999 found) 
-
-
-We think that there is still big room to improve the performance, which will be an ongoing effort for us.
-

appveyor.yml

@@ -1,16 +0,0 @@
-version: 1.0.{build}
-before_build:
-- md %APPVEYOR_BUILD_FOLDER%\build
-- cd %APPVEYOR_BUILD_FOLDER%\build
-- cmake -G "Visual Studio 12 Win64" -DOPTDBG=1 -DXPRESS=1 ..
-- cd ..
-build:
-  project: build\rocksdb.sln
-  parallel: true
-  verbosity: minimal
-test:
-test_script:
-- ps: build_tools\run_ci_db_test.ps1 -EnableRerun -Run db_test2 -Concurrency 8
-- ps: build_tools\run_ci_db_test.ps1 -EnableRerun -Run db_test -Exclude DBTest.GroupCommitTest -Concurrency 10
-- ps: build_tools\run_ci_db_test.ps1 -Run env_test -Concurrency 1
-

arcanist_util/__phutil_library_init__.php

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

arcanist_util/__phutil_library_map__.php

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

arcanist_util/config/FacebookArcanistConfiguration.php

@@ -1,206 +0,0 @@
-<?php
-// Copyright 2004-present Facebook. All Rights Reserved.
-// This source code is licensed under the BSD-style license found in the
-// LICENSE file in the root directory of this source tree. An additional grant
-// of patent rights can be found in the PATENTS file in the same directory.
-
-class FacebookArcanistConfiguration extends ArcanistConfiguration {
-
-  public function didRunWorkflow($command,
-                                 ArcanistBaseWorkflow $workflow,
-                                 $error_code) {
-    if ($command == 'diff' && !$workflow->isRawDiffSource()) {
-      $this->startTestsInJenkins($workflow);
-      $this->startTestsInSandcastle($workflow);
-    }
-  }
-
-  //////////////////////////////////////////////////////////////////////
-  /*  Run tests in sandcastle */
-  function postURL($diffID, $url) {
-    $cmd = 'echo \'{"diff_id": "' . $diffID . '", '
-           . '"name":"click here for sandcastle tests for D' . $diffID . '", '
-           . '"link":"' . $url . '"}\' | '
-           . 'http_proxy=fwdproxy.any.facebook.com:8080 '
-           . 'https_proxy=fwdproxy.any.facebook.com:8080 arc call-conduit '
-           . 'differential.updateunitresults';
-    shell_exec($cmd);
-  }
-
-  function updateTestCommand($diffID, $test, $status) {
-    $cmd = 'echo \'{"diff_id": "' . $diffID . '", '
-           . '"name":"' . $test . '", '
-           . '"result":"' . $status . '"}\' | '
-           . 'http_proxy=fwdproxy.any.facebook.com:8080 '
-           . 'https_proxy=fwdproxy.any.facebook.com:8080 arc call-conduit '
-           . 'differential.updateunitresults';
-    return $cmd;
-  }
-
-  function updateTest($diffID, $test) {
-    shell_exec($this->updateTestCommand($diffID, $test, "waiting"));
-  }
-
-  function getSteps($diffID, $username, $test) {
-    $arcrc_content = exec("cat ~/.arcrc | gzip -f | base64 -w0");
-
-    // Sandcastle machines don't have arc setup. We copy the user certificate
-    // and authenticate using that in sandcastle
-    $setup = array(
-      "name" => "Setup arcrc",
-      "shell" => "echo " . $arcrc_content . " | base64 --decode"
-                 . " | gzip -d > ~/.arcrc",
-      "user" => "root"
-    );
-
-    // arc demands certain permission on its config
-    $fix_permission = array(
-      "name" => "Fix environment",
-      "shell" => "chmod 600 ~/.arcrc",
-      "user" => "root"
-    );
-
-    // fbcode is a sub-repo. We cannot patch until we add it to ignore otherwise
-    // git thinks it is uncommited change
-    $fix_git_ignore = array(
-      "name" => "Fix git ignore",
-      "shell" => "echo fbcode >> .git/info/exclude",
-      "user" => "root"
-    );
-
-    // Patch the code (keep your fingures crossed)
-    $patch = array(
-      "name" => "Patch " . $diffID,
-      "shell" => "HTTPS_PROXY=fwdproxy:8080 arc --arcrc-file ~/.arcrc "
-                  . "patch --diff " . $diffID,
-      "user" => "root"
-    );
-
-    // Clean up the user arc config we are using
-    $cleanup = array(
-      "name" => "Arc cleanup",
-      "shell" => "rm -f ~/.arcrc",
-      "user" => "root"
-    );
-
-    // Construct the steps in the order of execution
-    $steps[] = $setup;
-    $steps[] = $fix_permission;
-    $steps[] = $fix_git_ignore;
-    $steps[] = $patch;
-
-    // Run the actual command
-    $this->updateTest($diffID, $test);
-    $cmd = $this->updateTestCommand($diffID, $test, "running") . ";"
-           . "./build_tools/precommit_checker.py " . $test
-           . "; exit_code=$?; ([[ \$exit_code -eq 0 ]] &&"
-           . $this->updateTestCommand($diffID, $test, "pass") . ")"
-           . "||" . $this->updateTestCommand($diffID, $test, "fail")
-           . "; cat /tmp/precommit-check.log"
-           . "; for f in `ls t/log-*`; do echo \$f; cat \$f; done;"
-           . "[[ \$exit_code -eq 0 ]]";
-
-    $run_test = array(
-      "name" => "Run " . $test,
-      "shell" => $cmd,
-      "user" => "root",
-    );
-
-    $steps[] = $run_test;
-    $steps[] = $cleanup;
-
-    return $steps;
-  }
-
-  function startTestsInSandcastle($workflow) {
-    // extract information we need from workflow or CLI
-    $diffID = $workflow->getDiffId();
-    $username = exec("whoami");
-
-    if ($diffID == null || $username == null) {
-      // there is no diff and we can't extract username
-      // we cannot schedule sandcasstle job
-      return;
-    }
-
-    if (strcmp(getenv("ROCKSDB_CHECK_ALL"), 1) == 0) {
-      // extract all tests from the CI definition
-      $output = file_get_contents("build_tools/rocksdb-lego-determinator");
-      preg_match_all('/[ ]{2}([a-zA-Z0-9_]+)[\)]{1}/', $output, $matches);
-      $tests = $matches[1];
-    } else {
-      // manually list of tests we want to run in sandcastle
-      $tests = array(
-        "unit", "unit_481", "clang_unit", "tsan", "asan", "lite_test", "valgrind"
-      );
-    }
-
-    // construct a job definition for each test and add it to the master plan
-    foreach ($tests as $test) {
-      $arg[] = array(
-        "name" => "RocksDB diff " . $diffID . " test " . $test,
-        "steps" => $this->getSteps($diffID, $username, $test)
-      );
-    }
-
-    // we cannot submit the parallel execution master plan to sandcastle
-    // we need supply the job plan as a determinator
-    // so we construct a small job that will spit out the master job plan
-    // which sandcastle will parse and execute
-    // Why compress ? Otherwise we run over the max string size.
-    $cmd = "echo " . base64_encode(json_encode($arg))
-           . " | gzip -f | base64 -w0";
-    $arg_encoded = shell_exec($cmd);
-
-    $command = array(
-      "name" => "Run diff " . $diffID . "for user " . $username,
-      "steps" => array()
-    );
-
-    $command["steps"][] = array(
-      "name" => "Generate determinator",
-      "shell" => "echo " . $arg_encoded . " | base64 --decode | gzip -d"
-                 . " | base64 --decode",
-      "determinator" => true,
-      "user" => "root"
-    );
-
-    // submit to sandcastle
-    $url = 'https://interngraph.intern.facebook.com/sandcastle/generate?'
-            .'command=SandcastleUniversalCommand'
-            .'&vcs=rocksdb-git&revision=origin%2Fmaster&type=lego'
-            .'&user=krad&alias=rocksdb-precommit'
-            .'&command-args=' . urlencode(json_encode($command));
-
-    $cmd = 'https_proxy= HTTPS_PROXY= curl -s -k -F app=659387027470559 '
-            . '-F token=AeO_3f2Ya3TujjnxGD4 "' . $url . '"';
-
-    $output = shell_exec($cmd);
-
-    // extract sandcastle URL from the response
-    preg_match('/url": "(.+)"/', $output, $sandcastle_url);
-
-    echo "\nSandcastle URL: " . $sandcastle_url[1] . "\n";
-
-    // Ask phabricator to display it on the diff UI
-    $this->postURL($diffID, $sandcastle_url[1]);
-  }
-
-  //////////////////////////////////////////////////////////////////////
-  /* Send off builds to jenkins */
-  function startTestsInJenkins($workflow) {
-    $diffID = $workflow->getDiffID();
-    if ($diffID === null) {
-      return;
-    }
-
-    $results = $workflow->getTestResults();
-    if (!$results) {
-      return;
-    }
-
-    $url = "https://ci-builds.fb.com/view/rocksdb/job/rocksdb_diff_check/"
-               ."buildWithParameters?token=AUTH&DIFF_ID=$diffID";
-    system("curl --noproxy '*' \"$url\" > /dev/null 2>&1");
-  }
-}

arcanist_util/cpp_linter/BaseDirectoryScopedFormatLinter.php

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

arcanist_util/cpp_linter/FacebookHowtoevenLinter.php

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

arcanist_util/cpp_linter/FbcodeClangFormatLinter.php

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

arcanist_util/cpp_linter/FbcodeCppLinter.php

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

arcanist_util/lint_engine/FacebookHowtoevenLintEngine.php

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

arcanist_util/unit_engine/FacebookFbcodeUnitTestEngine.php

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

build_tools/amalgamate.py

@@ -1,110 +0,0 @@
-#!/usr/bin/python
-
-# amalgamate.py creates an amalgamation from a unity build.
-# It can be run with either Python 2 or 3.
-# An amalgamation consists of a header that includes the contents of all public
-# headers and a source file that includes the contents of all source files and
-# private headers.
-#
-# This script works by starting with the unity build file and recursively expanding
-# #include directives. If the #include is found in a public include directory,
-# that header is expanded into the amalgamation header.
-#
-# A particular header is only expanded once, so this script will
-# break if there are multiple inclusions of the same header that are expected to
-# expand differently. Similarly, this type of code causes issues:
-#
-# #ifdef FOO
-#   #include "bar.h"
-#   // code here
-# #else
-#   #include "bar.h"            // oops, doesn't get expanded
-#   // different code here
-# #endif
-#
-# The solution is to move the include out of the #ifdef.
-
-from __future__ import print_function
-
-import argparse
-from os import path
-import re
-import sys
-
-include_re = re.compile('^[ \t]*#include[ \t]+"(.*)"[ \t]*$')
-included = set()
-excluded = set()
-
-def find_header(name, abs_path, include_paths):
-    samedir = path.join(path.dirname(abs_path), name)
-    if path.exists(samedir):
-        return samedir
-    for include_path in include_paths:
-        include_path = path.join(include_path, name)
-        if path.exists(include_path):
-            return include_path
-    return None
-
-def expand_include(include_path, f, abs_path, source_out, header_out, include_paths, public_include_paths):
-    if include_path in included:
-        return False
-
-    included.add(include_path)
-    with open(include_path) as f:
-        print('#line 1 "{}"'.format(include_path), file=source_out)
-        process_file(f, include_path, source_out, header_out, include_paths, public_include_paths)
-    return True
-
-def process_file(f, abs_path, source_out, header_out, include_paths, public_include_paths):
-    for (line, text) in enumerate(f):
-        m = include_re.match(text)
-        if m:
-            filename = m.groups()[0]
-            # first check private headers
-            include_path = find_header(filename, abs_path, include_paths)
-            if include_path:
-                if include_path in excluded:
-                    source_out.write(text)
-                    expanded = False
-                else:
-                    expanded = expand_include(include_path, f, abs_path, source_out, header_out, include_paths, public_include_paths)
-            else:
-                # now try public headers
-                include_path = find_header(filename, abs_path, public_include_paths)
-                if include_path:
-                    # found public header
-                    expanded = False
-                    if include_path in excluded:
-                        source_out.write(text)
-                    else:
-                        expand_include(include_path, f, abs_path, header_out, None, public_include_paths, [])
-                else:
-                    sys.exit("unable to find {}, included in {} on line {}".format(filename, abs_path, line))
-
-            if expanded:
-                print('#line {} "{}"'.format(line+1, abs_path), file=source_out)
-        elif text != "#pragma once\n":
-            source_out.write(text)
-
-def main():
-    parser = argparse.ArgumentParser(description="Transform a unity build into an amalgamation")
-    parser.add_argument("source", help="source file")
-    parser.add_argument("-I", action="append", dest="include_paths", help="include paths for private headers")
-    parser.add_argument("-i", action="append", dest="public_include_paths", help="include paths for public headers")
-    parser.add_argument("-x", action="append", dest="excluded", help="excluded header files")
-    parser.add_argument("-o", dest="source_out", help="output C++ file", required=True)
-    parser.add_argument("-H", dest="header_out", help="output C++ header file", required=True)
-    args = parser.parse_args()
-
-    include_paths = list(map(path.abspath, args.include_paths or []))
-    public_include_paths = list(map(path.abspath, args.public_include_paths or []))
-    excluded.update(map(path.abspath, args.excluded or []))
-    filename = args.source
-    abs_path = path.abspath(filename)
-    with open(filename) as f, open(args.source_out, 'w') as source_out, open(args.header_out, 'w') as header_out:
-        print('#line 1 "{}"'.format(filename), file=source_out)
-        print('#include "{}"'.format(header_out.name), file=source_out)
-        process_file(f, abs_path, source_out, header_out, include_paths, public_include_paths)
-
-if __name__ == "__main__":
-    main()

build_tools/build_detect_platform

@@ -7,8 +7,6 @@
 #   CC                          C Compiler path
 #   CXX                         C++ Compiler path
 #   PLATFORM_LDFLAGS            Linker flags
-#   JAVA_LDFLAGS                Linker flags for RocksDBJava
-#   JAVA_STATIC_LDFLAGS         Linker flags for RocksDBJava static build
 #   PLATFORM_SHARED_EXT         Extension for shared libraries
 #   PLATFORM_SHARED_LDFLAGS     Flags for building shared library
 #   PLATFORM_SHARED_CFLAGS      Flags for compiling objects for shared library
@@ -23,8 +21,6 @@
 #       -DLEVELDB_PLATFORM_NOATOMIC if it is not
 #       -DSNAPPY                    if the Snappy library is present
 #       -DLZ4                       if the LZ4 library is present
-#       -DZSTD                      if the ZSTD library is present
-#       -DNUMA                      if the NUMA library is present
 #
 # Using gflags in rocksdb:
 # Our project depends on gflags, which requires users to take some extra steps
@@ -34,7 +30,7 @@
 #   2. Once install, add the include path/lib path for gflags to CPATH and
 #      LIBRARY_PATH respectively. If installed with default mode, the
 #      lib and include path will be /usr/local/lib and /usr/local/include
-# Mac user can do this by having brew installed and running brew install gflags
+# Mac user can do this by running build_tools/mac-install-gflags.sh
 
 OUTPUT=$1
 if test -z "$OUTPUT"; then
@@ -45,24 +41,27 @@ fi
 # we depend on C++11
 PLATFORM_CXXFLAGS="-std=c++11"
 # we currently depend on POSIX platform
-COMMON_FLAGS="-DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX"
+COMMON_FLAGS="-DROCKSDB_PLATFORM_POSIX"
 
 # Default to fbcode gcc on internal fb machines
-if [ -z "$ROCKSDB_NO_FBCODE" -a -d /mnt/gvfs/third-party ]; then
+if [ -d /mnt/gvfs/third-party -a -z "$CXX" ]; then
     FBCODE_BUILD="true"
-    # If we're compiling with TSAN we need pic build
-    PIC_BUILD=$COMPILE_WITH_TSAN
-    if [ -z "$ROCKSDB_FBCODE_BUILD_WITH_481" ]; then
-      source "$PWD/build_tools/fbcode_config.sh"
+    if [ -z "$USE_CLANG" ]; then
+        CENTOS_VERSION=`rpm -q --qf "%{VERSION}" \
+          $(rpm -q --whatprovides redhat-release)`
+        if [ "$CENTOS_VERSION" -ge "6" ]; then
+          source $PWD/build_tools/fbcode.gcc481.sh
+        else
+          source $PWD/build_tools/fbcode.gcc471.sh
+        fi
     else
-      # we need this to build with MySQL. Don't use for other purposes.
-      source "$PWD/build_tools/fbcode_config4.8.1.sh"
+        source $PWD/build_tools/fbcode.clang31.sh
     fi
 fi
 
 # Delete existing output, if it exists
-rm -f "$OUTPUT"
-touch "$OUTPUT"
+rm -f $OUTPUT
+touch $OUTPUT
 
 if test -z "$CC"; then
    CC=cc
@@ -77,29 +76,18 @@ if test -z "$TARGET_OS"; then
     TARGET_OS=`uname -s`
 fi
 
-if test -z "$TARGET_ARCHITECTURE"; then
-    TARGET_ARCHITECTURE=`uname -m`
-fi
-
-if test -z "$CLANG_SCAN_BUILD"; then
-    CLANG_SCAN_BUILD=scan-build
-fi
-
-if test -z "$CLANG_ANALYZER"; then
-    CLANG_ANALYZER=$(which clang++ 2> /dev/null)
-fi
-
 COMMON_FLAGS="$COMMON_FLAGS ${CFLAGS}"
 CROSS_COMPILE=
 PLATFORM_CCFLAGS=
+PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS ${CXXFLAGS}"
 PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS"
 PLATFORM_SHARED_EXT="so"
-PLATFORM_SHARED_LDFLAGS="-Wl,--no-as-needed -shared -Wl,-soname -Wl,"
+PLATFORM_SHARED_LDFLAGS="-shared -Wl,-soname -Wl,"
 PLATFORM_SHARED_CFLAGS="-fPIC"
-PLATFORM_SHARED_VERSIONED=true
+PLATFORM_SHARED_VERSIONED=false
 
 # generic port files (working on all platform by #ifdef) go directly in /port
-GENERIC_PORT_FILES=`cd "$ROCKSDB_ROOT"; find port -name '*.cc' | tr "\n" " "`
+GENERIC_PORT_FILES=`cd $ROCKSDB_ROOT; find port -name '*.cc' | tr "\n" " "`
 
 # On GCC, we pick libc's memcmp over GCC's memcmp via -fno-builtin-memcmp
 case "$TARGET_OS" in
@@ -112,11 +100,10 @@ case "$TARGET_OS" in
         ;;
     IOS)
         PLATFORM=IOS
-        COMMON_FLAGS="$COMMON_FLAGS -DOS_MACOSX -DIOS_CROSS_COMPILE -DROCKSDB_LITE"
+        COMMON_FLAGS="$COMMON_FLAGS -DOS_MACOSX -DIOS_CROSS_COMPILE"
         PLATFORM_SHARED_EXT=dylib
         PLATFORM_SHARED_LDFLAGS="-dynamiclib -install_name "
         CROSS_COMPILE=true
-        PLATFORM_SHARED_VERSIONED=
         ;;
     Linux)
         PLATFORM=OS_LINUX
@@ -157,17 +144,6 @@ case "$TARGET_OS" in
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread"
         # PORT_FILES=port/dragonfly/dragonfly_specific.cc
         ;;
-    Cygwin)
-        PLATFORM=CYGWIN
-        PLATFORM_SHARED_CFLAGS=""
-        PLATFORM_CXXFLAGS="-std=gnu++11"
-        COMMON_FLAGS="$COMMON_FLAGS -DCYGWIN"
-        if [ -z "$USE_CLANG" ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp"
-        fi
-        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lpthread -lrt"
-        # PORT_FILES=port/linux/linux_specific.cc
-        ;;
     OS_ANDROID_CROSSCOMPILE)
         PLATFORM=OS_ANDROID
 	COMMON_FLAGS="$COMMON_FLAGS -fno-builtin-memcmp -D_REENTRANT -DOS_ANDROID -DLEVELDB_PLATFORM_POSIX"
@@ -180,28 +156,57 @@ case "$TARGET_OS" in
         exit 1
 esac
 
-PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS ${CXXFLAGS}"
-JAVA_LDFLAGS="$PLATFORM_LDFLAGS"
-JAVA_STATIC_LDFLAGS="$PLATFORM_LDFLAGS"
+$PWD/build_tools/build_detect_version
+
+# We want to make a list of all cc files within util, db, table, and helpers
+# except for the test and benchmark files. By default, find will output a list
+# of all files matching either rule, so we need to append -print to make the
+# prune take effect.
+DIRS="util db table utilities"
+
+set -f # temporarily disable globbing so that our patterns arent expanded
+PRUNE_TEST="-name *test*.cc -prune"
+PRUNE_BENCH="-name *_bench.cc -prune"
+PORTABLE_FILES=`cd $ROCKSDB_ROOT; find $DIRS $PRUNE_TEST -o $PRUNE_BENCH -o -name '*.cc' -print | sort | tr "\n" " "`
+PORTABLE_CPP=`cd $ROCKSDB_ROOT; find $DIRS $PRUNE_TEST -o $PRUNE_BENCH -o -name '*.cpp' -print | sort | tr "\n" " "`
+set +f # re-enable globbing
+
+# The sources consist of the portable files, plus the platform-specific port
+# file.
+echo "SOURCES=$PORTABLE_FILES $GENERIC_PORT_FILES $PORT_FILES" >> $OUTPUT
+echo "SOURCESCPP=$PORTABLE_CPP" >> $OUTPUT
+echo "MEMENV_SOURCES=helpers/memenv/memenv.cc" >> $OUTPUT
 
 if [ "$CROSS_COMPILE" = "true" -o "$FBCODE_BUILD" = "true" ]; then
     # Cross-compiling; do not try any compilation tests.
     # Also don't need any compilation tests if compiling on fbcode
     true
 else
-    if ! test $ROCKSDB_DISABLE_FALLOCATE; then
-        # Test whether fallocate is available
-        $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <fcntl.h>
-          #include <linux/falloc.h>
-          int main() {
-      int fd = open("/dev/null", 0);
-      fallocate(fd, FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE, 0, 1024);
-          }
+    # do fPIC on 64 bit in non-fbcode environment
+    case "$TARGET_OS" in
+        x86_64)
+            PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS -fPIC"
+    esac
+
+    # If -std=c++0x works, use <atomic>.  Otherwise use port_posix.h.
+    $CXX $CFLAGS -std=c++0x -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <atomic>
+      int main() {}
 EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_FALLOCATE_PRESENT"
-        fi
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_ATOMIC_PRESENT"
+    fi
+
+    # Test whether fallocate is available
+    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
+      #include <fcntl.h>
+      int main() {
+	int fd = open("/dev/null", 0);
+	fallocate(fd, 0, 0, 1024);
+      }
+EOF
+    if [ "$?" = 0 ]; then
+        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_FALLOCATE_PRESENT"
     fi
 
     # Test whether Snappy library is installed
@@ -213,31 +218,18 @@ EOF
     if [ "$?" = 0 ]; then
         COMMON_FLAGS="$COMMON_FLAGS -DSNAPPY"
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lsnappy"
-        JAVA_LDFLAGS="$JAVA_LDFLAGS -lsnappy"
     fi
 
+
     # Test whether gflags library is installed
-    # http://gflags.github.io/gflags/
-    # check if the namespace is gflags
-    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
+    # http://code.google.com/p/gflags/
+    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
       #include <gflags/gflags.h>
-      using namespace gflags;
       int main() {}
 EOF
     if [ "$?" = 0 ]; then
-        COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=gflags"
+        COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS"
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
-    else
-      # check if namespace is google
-      $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null << EOF
-        #include <gflags/gflags.h>
-        using namespace google;
-        int main() {}
-EOF
-      if [ "$?" = 0 ]; then
-          COMMON_FLAGS="$COMMON_FLAGS -DGFLAGS=google"
-          PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lgflags"
-      fi
     fi
 
     # Test whether zlib library is installed
@@ -248,7 +240,6 @@ EOF
     if [ "$?" = 0 ]; then
         COMMON_FLAGS="$COMMON_FLAGS -DZLIB"
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lz"
-        JAVA_LDFLAGS="$JAVA_LDFLAGS -lz"
     fi
 
     # Test whether bzip library is installed
@@ -259,7 +250,6 @@ EOF
     if [ "$?" = 0 ]; then
         COMMON_FLAGS="$COMMON_FLAGS -DBZIP2"
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lbz2"
-        JAVA_LDFLAGS="$JAVA_LDFLAGS -lbz2"
     fi
 
     # Test whether lz4 library is installed
@@ -271,119 +261,15 @@ EOF
     if [ "$?" = 0 ]; then
         COMMON_FLAGS="$COMMON_FLAGS -DLZ4"
         PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -llz4"
-        JAVA_LDFLAGS="$JAVA_LDFLAGS -llz4"
     fi
 
-    # Test whether zstd library is installed
-    $CXX $CFLAGS $COMMON_FLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-      #include <zstd.h>
+    # Test whether tcmalloc is available
+    $CXX $CFLAGS -x c++ - -o /dev/null -ltcmalloc 2>/dev/null  <<EOF
       int main() {}
 EOF
     if [ "$?" = 0 ]; then
-        COMMON_FLAGS="$COMMON_FLAGS -DZSTD"
-        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lzstd"
-        JAVA_LDFLAGS="$JAVA_LDFLAGS -lzstd"
+        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltcmalloc"
     fi
-
-    # Test whether numa is available
-    $CXX $CFLAGS -x c++ - -o /dev/null -lnuma 2>/dev/null  <<EOF
-      #include <numa.h>
-      #inlcude <numaif.h>
-      int main() {}
-EOF
-    if [ "$?" = 0 ]; then
-        COMMON_FLAGS="$COMMON_FLAGS -DNUMA"
-        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lnuma"
-        JAVA_LDFLAGS="$JAVA_LDFLAGS -lnuma"
-    fi
-
-    # Test whether jemalloc is available
-    if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null -ljemalloc \
-      2>/dev/null; then
-        PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ljemalloc"
-        JAVA_LDFLAGS="$JAVA_LDFLAGS -ljemalloc"
-        JEMALLOC=1
-    else
-        # jemalloc is not available. Let's try tcmalloc
-        if echo 'int main() {}' | $CXX $CFLAGS -x c++ - -o /dev/null \
-          -ltcmalloc 2>/dev/null; then
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -ltcmalloc"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -ltcmalloc"
-        fi
-    fi
-
-    # Test whether malloc_usable_size is available
-    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-      #include <malloc.h>
-      int main() {
-        size_t res = malloc_usable_size(0);
-        return 0;
-      }
-EOF
-    if [ "$?" = 0 ]; then
-        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_MALLOC_USABLE_SIZE"
-    fi
-
-    # Test whether PTHREAD_MUTEX_ADAPTIVE_NP mutex type is available
-    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-      #include <pthread.h>
-      int main() {
-        int x = PTHREAD_MUTEX_ADAPTIVE_NP;
-        return 0;
-      }
-EOF
-    if [ "$?" = 0 ]; then
-        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_PTHREAD_ADAPTIVE_MUTEX"
-    fi
-
-    # Test whether backtrace is available
-    $CXX $CFLAGS -x c++ - -o /dev/null 2>/dev/null  <<EOF
-      #include <execinfo.h>>
-      int main() {
-        void* frames[1];
-        backtrace_symbols(frames, backtrace(frames, 1));
-        return 0;
-      }
-EOF
-    if [ "$?" = 0 ]; then
-        COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
-    else
-        # Test whether execinfo library is installed
-        $CXX $CFLAGS -lexecinfo -x c++ - -o /dev/null 2>/dev/null  <<EOF
-          #include <execinfo.h>
-          int main() {
-            void* frames[1];
-            backtrace_symbols(frames, backtrace(frames, 1));
-          }
-EOF
-        if [ "$?" = 0 ]; then
-            COMMON_FLAGS="$COMMON_FLAGS -DROCKSDB_BACKTRACE"
-            PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS -lexecinfo"
-            JAVA_LDFLAGS="$JAVA_LDFLAGS -lexecinfo"
-        fi
-    fi
-
-    # Test if -pg is supported
-    $CXX $CFLAGS -pg -x c++ - -o /dev/null 2>/dev/null  <<EOF
-      int main() {
-        return 0;
-      }
-EOF
-    if [ "$?" = 0 ]; then
-        PROFILING_FLAGS=-pg
-    fi
-fi
-
-# TODO(tec): Fix -Wshorten-64-to-32 errors on FreeBSD and enable the warning.
-# -Wshorten-64-to-32 breaks compilation on FreeBSD i386
-if ! [ "$TARGET_OS" = FreeBSD -a "$TARGET_ARCHITECTURE" = i386 ]; then
-  # Test whether -Wshorten-64-to-32 is available
-  $CXX $CFLAGS -x c++ - -o /dev/null -Wshorten-64-to-32 2>/dev/null  <<EOF
-    int main() {}
-EOF
-  if [ "$?" = 0 ]; then
-    COMMON_FLAGS="$COMMON_FLAGS -Wshorten-64-to-32"
-  fi
 fi
 
 # shall we use HDFS?
@@ -394,65 +280,32 @@ if test "$USE_HDFS"; then
     exit 1
   fi
   HDFS_CCFLAGS="$HDFS_CCFLAGS -I$JAVA_HOME/include -I$JAVA_HOME/include/linux -DUSE_HDFS"
-  HDFS_LDFLAGS="$HDFS_LDFLAGS -lhdfs -L$JAVA_HOME/jre/lib/amd64"
+  HDFS_LDFLAGS="$HDFS_LDFLAGS -Wl,--no-whole-archive hdfs/libhdfs.a -L$JAVA_HOME/jre/lib/amd64"
   HDFS_LDFLAGS="$HDFS_LDFLAGS -L$JAVA_HOME/jre/lib/amd64/server -L$GLIBC_RUNTIME_PATH/lib"
   HDFS_LDFLAGS="$HDFS_LDFLAGS -ldl -lverify -ljava -ljvm"
   COMMON_FLAGS="$COMMON_FLAGS $HDFS_CCFLAGS"
   PLATFORM_LDFLAGS="$PLATFORM_LDFLAGS $HDFS_LDFLAGS"
-  JAVA_LDFLAGS="$JAVA_LDFLAGS $HDFS_LDFLAGS"
 fi
 
-if [ "$TARGET_OS" = FreeBSD -a "$TARGET_ARCHITECTURE" = i386 ]; then
-  # Intel SSE instructions breaks compilation on FreeBSD i386
-  unset USE_SSE
-fi
-
-if test "$USE_SSE"; then
-  # if Intel SSE instruction set is supported, set USE_SSE=1
-  COMMON_FLAGS="$COMMON_FLAGS -msse -msse4.2 "
-elif test -z "$PORTABLE"; then
-  if test -n "`echo $TARGET_ARCHITECTURE | grep ^ppc64`"; then
-    # Tune for this POWER processor, treating '+' models as base models
-    POWER=`LD_SHOW_AUXV=1 /bin/true | grep AT_PLATFORM | grep -E -o power[0-9]+`
-    COMMON_FLAGS="$COMMON_FLAGS -mcpu=$POWER -mtune=$POWER "
-  elif test -n "`echo $TARGET_ARCHITECTURE | grep ^s390x`"; then
-    COMMON_FLAGS="$COMMON_FLAGS -march=z10 "
-  else
-    COMMON_FLAGS="$COMMON_FLAGS -march=native "
-  fi
-fi
+# if Intel SSE instruction set is supported, set USE_SSE=" -msse -msse4.2 "
+COMMON_FLAGS="$COMMON_FLAGS $USE_SSE"
 
 PLATFORM_CCFLAGS="$PLATFORM_CCFLAGS $COMMON_FLAGS"
 PLATFORM_CXXFLAGS="$PLATFORM_CXXFLAGS $COMMON_FLAGS"
 
 VALGRIND_VER="$VALGRIND_VER"
 
-ROCKSDB_MAJOR=`build_tools/version.sh major`
-ROCKSDB_MINOR=`build_tools/version.sh minor`
-ROCKSDB_PATCH=`build_tools/version.sh patch`
-
-echo "CC=$CC" >> "$OUTPUT"
-echo "CXX=$CXX" >> "$OUTPUT"
-echo "PLATFORM=$PLATFORM" >> "$OUTPUT"
-echo "PLATFORM_LDFLAGS=$PLATFORM_LDFLAGS" >> "$OUTPUT"
-echo "JAVA_LDFLAGS=$JAVA_LDFLAGS" >> "$OUTPUT"
-echo "JAVA_STATIC_LDFLAGS=$JAVA_STATIC_LDFLAGS" >> "$OUTPUT"
-echo "VALGRIND_VER=$VALGRIND_VER" >> "$OUTPUT"
-echo "PLATFORM_CCFLAGS=$PLATFORM_CCFLAGS" >> "$OUTPUT"
-echo "PLATFORM_CXXFLAGS=$PLATFORM_CXXFLAGS" >> "$OUTPUT"
-echo "PLATFORM_SHARED_CFLAGS=$PLATFORM_SHARED_CFLAGS" >> "$OUTPUT"
-echo "PLATFORM_SHARED_EXT=$PLATFORM_SHARED_EXT" >> "$OUTPUT"
-echo "PLATFORM_SHARED_LDFLAGS=$PLATFORM_SHARED_LDFLAGS" >> "$OUTPUT"
-echo "PLATFORM_SHARED_VERSIONED=$PLATFORM_SHARED_VERSIONED" >> "$OUTPUT"
-echo "EXEC_LDFLAGS=$EXEC_LDFLAGS" >> "$OUTPUT"
-echo "JEMALLOC_INCLUDE=$JEMALLOC_INCLUDE" >> "$OUTPUT"
-echo "JEMALLOC_LIB=$JEMALLOC_LIB" >> "$OUTPUT"
-echo "ROCKSDB_MAJOR=$ROCKSDB_MAJOR" >> "$OUTPUT"
-echo "ROCKSDB_MINOR=$ROCKSDB_MINOR" >> "$OUTPUT"
-echo "ROCKSDB_PATCH=$ROCKSDB_PATCH" >> "$OUTPUT"
-echo "CLANG_SCAN_BUILD=$CLANG_SCAN_BUILD" >> "$OUTPUT"
-echo "CLANG_ANALYZER=$CLANG_ANALYZER" >> "$OUTPUT"
-echo "PROFILING_FLAGS=$PROFILING_FLAGS" >> "$OUTPUT"
-if test -n "$JEMALLOC"; then
-  echo "JEMALLOC=1" >> "$OUTPUT"
-fi
+echo "CC=$CC" >> $OUTPUT
+echo "CXX=$CXX" >> $OUTPUT
+echo "PLATFORM=$PLATFORM" >> $OUTPUT
+echo "PLATFORM_LDFLAGS=$PLATFORM_LDFLAGS" >> $OUTPUT
+echo "VALGRIND_VER=$VALGRIND_VER" >> $OUTPUT
+echo "PLATFORM_CCFLAGS=$PLATFORM_CCFLAGS" >> $OUTPUT
+echo "PLATFORM_CXXFLAGS=$PLATFORM_CXXFLAGS" >> $OUTPUT
+echo "PLATFORM_SHARED_CFLAGS=$PLATFORM_SHARED_CFLAGS" >> $OUTPUT
+echo "PLATFORM_SHARED_EXT=$PLATFORM_SHARED_EXT" >> $OUTPUT
+echo "PLATFORM_SHARED_LDFLAGS=$PLATFORM_SHARED_LDFLAGS" >> $OUTPUT
+echo "PLATFORM_SHARED_VERSIONED=$PLATFORM_SHARED_VERSIONED" >> $OUTPUT
+echo "EXEC_LDFLAGS=$EXEC_LDFLAGS" >> $OUTPUT
+echo "JEMALLOC_INCLUDE=$JEMALLOC_INCLUDE" >> $OUTPUT
+echo "JEMALLOC_LIB=$JEMALLOC_LIB" >> $OUTPUT

build_tools/build_detect_version

@@ -0,0 +1,22 @@
+#!/bin/sh
+#
+# Record the version of the source that we are compiling.
+# We keep a record of the git revision in util/version.cc. This source file
+# is then built as a regular source file as part of the compilation process.
+# One can run "strings executable_filename | grep _build_" to find the version of
+# the source that we used to build the executable file.
+
+OUTFILE="$PWD/util/build_version.cc"
+
+GIT_SHA=""
+if command -v git >/dev/null 2>&1; then
+    GIT_SHA=$(git rev-parse HEAD 2>/dev/null)
+fi
+
+cat > "${OUTFILE}" <<EOF
+#include "build_version.h"
+const char* rocksdb_build_git_sha = "rocksdb_build_git_sha:${GIT_SHA}";
+const char* rocksdb_build_git_datetime = "rocksdb_build_git_datetime:$(date)";
+const char* rocksdb_build_compile_date = __DATE__;
+const char* rocksdb_build_compile_time = __TIME__;
+EOF

build_tools/dependencies.sh

@@ -1,16 +0,0 @@
-GCC_BASE=/mnt/gvfs/third-party2/gcc/ebc96bc2fb751b5a0300b8d91a95bdf24ac1d88b/4.9.x/centos6-native/108cf83
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/b91de48a4974ec839946d824402b098d43454cef/stable/centos6-native/7aaccbe
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/53e0eac8911888a105aa98b9a35fe61cf1d8b278/4.9.x/gcc-4.9-glibc-2.20/024dbc3
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/ee36ac9a72dfac4a995f1b215bb4c0fc8a0f6f91/2.20/gcc-4.9-glibc-2.20/500e281
-SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/8c38a4c1e52b4c2cc8a9cdc31b9c947ed7dbfcb4/1.1.3/gcc-4.9-glibc-2.20/e9936bf
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2b24f1e99454f9ca7b0301720f94836dae1bf71b/1.2.8/gcc-5-glibc-2.23/9bc6787
-BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/af7c14c9b652cdd5ec34eadd25c3f38a9b306c5d/1.0.6/gcc-5-glibc-2.23/9bc6787
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/0e790b441e2d9acd68d51e1d2e028f88c6a79ddf/r131/gcc-5-glibc-2.23/9bc6787
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/1408484d03b15492aa54b10356104e9dc22e1cc5/0.6.1/gcc-5-glibc-2.23/9bc6787
-GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/5a5c7a6608cb32f1e1e7f814023d5bdfbd136370/2.1.1/gcc-4.8.1-glibc-2.17/c3f970a
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/a4c2adecffcaa68d5585d06be2252e3efa52555b/master/gcc-5-glibc-2.23/1c32b4b
-NUMA_BASE=/mnt/gvfs/third-party2/numa/1abc0d3c01743b854676423cf2d3629912f34930/2.0.8/gcc-5-glibc-2.23/9bc6787
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/ad576de2a1ea560c4d3434304f0fc4e079bede42/trunk/gcc-5-glibc-2.23/b1847cb
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/f24be37d170e04be6e469af487644d4d62e1c6c1/4.0.9-36_fbk5_2933_gd092e3f/gcc-5-glibc-2.23/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/9d65c666b9adf8f2a989fd4b98a9a5e7d3afa233/2.26/centos6-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/9cee5a3628dc9d4b93897972c58eba865e25b270/3.10.0/gcc-4.9-glibc-2.20/e9936bf

build_tools/dependencies_4.8.1.sh

@@ -1,16 +0,0 @@
-GCC_BASE=/mnt/gvfs/third-party2/gcc/ebc96bc2fb751b5a0300b8d91a95bdf24ac1d88b/4.8.1/centos6-native/cc6c9dc
-CLANG_BASE=/mnt/gvfs/third-party2/llvm-fb/b91de48a4974ec839946d824402b098d43454cef/stable/centos6-native/7aaccbe
-LIBGCC_BASE=/mnt/gvfs/third-party2/libgcc/53e0eac8911888a105aa98b9a35fe61cf1d8b278/4.8.1/gcc-4.8.1-glibc-2.17/8aac7fc
-GLIBC_BASE=/mnt/gvfs/third-party2/glibc/ee36ac9a72dfac4a995f1b215bb4c0fc8a0f6f91/2.17/gcc-4.8.1-glibc-2.17/99df8fc
-SNAPPY_BASE=/mnt/gvfs/third-party2/snappy/8c38a4c1e52b4c2cc8a9cdc31b9c947ed7dbfcb4/1.1.3/gcc-4.8.1-glibc-2.17/c3f970a
-ZLIB_BASE=/mnt/gvfs/third-party2/zlib/2b24f1e99454f9ca7b0301720f94836dae1bf71b/1.2.8/gcc-4.8.1-glibc-2.17/c3f970a
-BZIP2_BASE=/mnt/gvfs/third-party2/bzip2/af7c14c9b652cdd5ec34eadd25c3f38a9b306c5d/1.0.6/gcc-4.8.1-glibc-2.17/c3f970a
-LZ4_BASE=/mnt/gvfs/third-party2/lz4/0e790b441e2d9acd68d51e1d2e028f88c6a79ddf/r131/gcc-4.8.1-glibc-2.17/c3f970a
-ZSTD_BASE=/mnt/gvfs/third-party2/zstd/1408484d03b15492aa54b10356104e9dc22e1cc5/0.6.1/gcc-4.8.1-glibc-2.17/c3f970a
-GFLAGS_BASE=/mnt/gvfs/third-party2/gflags/5a5c7a6608cb32f1e1e7f814023d5bdfbd136370/2.1.1/gcc-4.8.1-glibc-2.17/c3f970a
-JEMALLOC_BASE=/mnt/gvfs/third-party2/jemalloc/a4c2adecffcaa68d5585d06be2252e3efa52555b/master/gcc-4.8.1-glibc-2.17/8d31e51
-NUMA_BASE=/mnt/gvfs/third-party2/numa/1abc0d3c01743b854676423cf2d3629912f34930/2.0.8/gcc-4.8.1-glibc-2.17/c3f970a
-LIBUNWIND_BASE=/mnt/gvfs/third-party2/libunwind/ad576de2a1ea560c4d3434304f0fc4e079bede42/trunk/gcc-4.8.1-glibc-2.17/675d945
-KERNEL_HEADERS_BASE=/mnt/gvfs/third-party2/kernel-headers/f24be37d170e04be6e469af487644d4d62e1c6c1/4.0.9-36_fbk5_2933_gd092e3f/gcc-4.8.1-glibc-2.17/da39a3e
-BINUTILS_BASE=/mnt/gvfs/third-party2/binutils/9d65c666b9adf8f2a989fd4b98a9a5e7d3afa233/2.26/centos6-native/da39a3e
-VALGRIND_BASE=/mnt/gvfs/third-party2/valgrind/9cee5a3628dc9d4b93897972c58eba865e25b270/3.8.1/gcc-4.8.1-glibc-2.17/c3f970a

build_tools/dockerbuild.sh

@@ -1,2 +0,0 @@
-#!/bin/bash
-docker run -v $PWD:/rocks -w /rocks buildpack-deps make

build_tools/error_filter.py

@@ -1,164 +0,0 @@
-# Copyright (c) 2016-present, Facebook, Inc.  All rights reserved.
-# This source code is licensed under the BSD-style license found in the
-# LICENSE file in the root directory of this source tree. An additional grant
-# of patent rights can be found in the PATENTS file in the same directory.
-
-'''Filter for error messages in test output:
-    - Receives merged stdout/stderr from test on stdin
-    - Finds patterns of known error messages for test name (first argument)
-    - Prints those error messages to stdout
-'''
-
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-from __future__ import unicode_literals
-
-import re
-import sys
-
-
-class ErrorParserBase(object):
-    def parse_error(self, line):
-        '''Parses a line of test output. If it contains an error, returns a
-        formatted message describing the error; otherwise, returns None.
-        Subclasses must override this method.
-        '''
-        raise NotImplementedError
-
-
-class GTestErrorParser(ErrorParserBase):
-    '''A parser that remembers the last test that began running so it can print
-    that test's name upon detecting failure.
-    '''
-    _GTEST_NAME_PATTERN = re.compile(r'\[ RUN      \] (\S+)$')
-    # format: '<filename or "unknown file">:<line #>: Failure'
-    _GTEST_FAIL_PATTERN = re.compile(r'(unknown file|\S+:\d+): Failure$')
-
-    def __init__(self):
-        self._last_gtest_name = 'Unknown test'
-
-    def parse_error(self, line):
-        gtest_name_match = self._GTEST_NAME_PATTERN.match(line)
-        if gtest_name_match:
-            self._last_gtest_name = gtest_name_match.group(1)
-            return None
-        gtest_fail_match = self._GTEST_FAIL_PATTERN.match(line)
-        if gtest_fail_match:
-            return '%s failed: %s' % (
-                    self._last_gtest_name, gtest_fail_match.group(1))
-        return None
-
-
-class MatchErrorParser(ErrorParserBase):
-    '''A simple parser that returns the whole line if it matches the pattern.
-    '''
-    def __init__(self, pattern):
-        self._pattern = re.compile(pattern)
-
-    def parse_error(self, line):
-        if self._pattern.match(line):
-            return line
-        return None
-
-
-class CompilerErrorParser(MatchErrorParser):
-    def __init__(self):
-        # format: '<filename>:<line #>:<column #>: error: <error msg>'
-        super(CompilerErrorParser, self).__init__(r'\S+:\d+:\d+: error:')
-
-
-class ScanBuildErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(ScanBuildErrorParser, self).__init__(
-                r'scan-build: \d+ bugs found.$')
-
-
-class DbCrashErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(DbCrashErrorParser, self).__init__(r'\*\*\*.*\^$|TEST FAILED.')
-
-
-class WriteStressErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(WriteStressErrorParser, self).__init__(
-                r'ERROR: write_stress died with exitcode=\d+')
-
-
-class AsanErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(AsanErrorParser, self).__init__(
-                r'==\d+==ERROR: AddressSanitizer:')
-
-
-class UbsanErrorParser(MatchErrorParser):
-    def __init__(self):
-        # format: '<filename>:<line #>:<column #>: runtime error: <error msg>'
-        super(UbsanErrorParser, self).__init__(r'\S+:\d+:\d+: runtime error:')
-
-
-class ValgrindErrorParser(MatchErrorParser):
-    def __init__(self):
-        # just grab the summary, valgrind doesn't clearly distinguish errors
-        # from other log messages.
-        super(ValgrindErrorParser, self).__init__(r'==\d+== ERROR SUMMARY:')
-
-
-class CompatErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(CompatErrorParser, self).__init__(r'==== .*[Ee]rror.* ====$')
-
-
-class TsanErrorParser(MatchErrorParser):
-    def __init__(self):
-        super(TsanErrorParser, self).__init__(r'WARNING: ThreadSanitizer:')
-
-
-_TEST_NAME_TO_PARSERS = {
-    'punit': [CompilerErrorParser, GTestErrorParser],
-    'unit': [CompilerErrorParser, GTestErrorParser],
-    'unit_481': [CompilerErrorParser, GTestErrorParser],
-    'clang_unit': [CompilerErrorParser, GTestErrorParser],
-    'clang_analyze': [CompilerErrorParser, ScanBuildErrorParser],
-    'code_cov': [CompilerErrorParser, GTestErrorParser],
-    'unity': [CompilerErrorParser, GTestErrorParser],
-    'lite': [CompilerErrorParser],
-    'lite_test': [CompilerErrorParser, GTestErrorParser],
-    'stress_crash': [CompilerErrorParser, DbCrashErrorParser],
-    'write_stress': [CompilerErrorParser, WriteStressErrorParser],
-    'asan': [CompilerErrorParser, GTestErrorParser, AsanErrorParser],
-    'asan_crash': [CompilerErrorParser, AsanErrorParser, DbCrashErrorParser],
-    'ubsan': [CompilerErrorParser, GTestErrorParser, UbsanErrorParser],
-    'ubsan_crash': [CompilerErrorParser, UbsanErrorParser, DbCrashErrorParser],
-    'valgrind': [CompilerErrorParser, GTestErrorParser, ValgrindErrorParser],
-    'tsan': [CompilerErrorParser, GTestErrorParser, TsanErrorParser],
-    'format_compatible': [CompilerErrorParser, CompatErrorParser],
-    'run_format_compatible': [CompilerErrorParser, CompatErrorParser],
-    'no_compression': [CompilerErrorParser, GTestErrorParser],
-    'run_no_compression': [CompilerErrorParser, GTestErrorParser],
-    'regression': [CompilerErrorParser],
-    'run_regression': [CompilerErrorParser],
-}
-
-
-def main():
-    if len(sys.argv) != 2:
-        return 'Usage: %s <test name>' % sys.argv[0]
-    test_name = sys.argv[1]
-    if test_name not in _TEST_NAME_TO_PARSERS:
-        return 'Unknown test name: %s' % test_name
-
-    error_parsers = []
-    for parser_cls in _TEST_NAME_TO_PARSERS[test_name]:
-        error_parsers.append(parser_cls())
-
-    for line in sys.stdin:
-        line = line.strip()
-        for error_parser in error_parsers:
-            error_msg = error_parser.parse_error(line)
-            if error_msg is not None:
-                print(error_msg)
-
-
-if __name__ == '__main__':
-    sys.exit(main())

build_tools/fb_compile_mongo.sh

@@ -1,55 +0,0 @@
-#!/bin/sh
-
-# fail early
-set -e
-
-if test -z $ROCKSDB_PATH; then
-  ROCKSDB_PATH=~/rocksdb
-fi
-source $ROCKSDB_PATH/build_tools/fbcode_config4.8.1.sh
-
-EXTRA_LDFLAGS=""
-
-if test -z $ALLOC; then
-  # default
-  ALLOC=tcmalloc
-elif [[ $ALLOC == "jemalloc" ]]; then
-  ALLOC=system
-  EXTRA_LDFLAGS+=" -Wl,--whole-archive $JEMALLOC_LIB -Wl,--no-whole-archive"
-fi
-
-# we need to force mongo to use static library, not shared
-STATIC_LIB_DEP_DIR='build/static_library_dependencies'
-test -d $STATIC_LIB_DEP_DIR || mkdir $STATIC_LIB_DEP_DIR
-test -h $STATIC_LIB_DEP_DIR/`basename $SNAPPY_LIBS` || ln -s $SNAPPY_LIBS $STATIC_LIB_DEP_DIR
-test -h $STATIC_LIB_DEP_DIR/`basename $LZ4_LIBS` || ln -s $LZ4_LIBS $STATIC_LIB_DEP_DIR
-
-EXTRA_LDFLAGS+=" -L $STATIC_LIB_DEP_DIR"
-
-set -x
-
-EXTRA_CMD=""
-if ! test -e version.json; then
-  # this is Mongo 3.0
-  EXTRA_CMD="--rocksdb \
-    --variant-dir=linux2/norm
-    --cxx=${CXX} \
-    --cc=${CC} \
-    --use-system-zlib"  # add this line back to normal code path
-                        # when https://jira.mongodb.org/browse/SERVER-19123 is resolved
-fi
-
-scons \
-  LINKFLAGS="$EXTRA_LDFLAGS $EXEC_LDFLAGS $PLATFORM_LDFLAGS" \
-  CCFLAGS="$CXXFLAGS -L $STATIC_LIB_DEP_DIR" \
-  LIBS="lz4 gcc stdc++" \
-  LIBPATH="$ROCKSDB_PATH" \
-  CPPPATH="$ROCKSDB_PATH/include" \
-  -j32 \
-  --allocator=$ALLOC \
-  --nostrip \
-  --opt=on \
-  --disable-minimum-compiler-version-enforcement \
-  --use-system-snappy \
-  --disable-warnings-as-errors \
-  $EXTRA_CMD $*

build_tools/fbcode.clang31.sh

@@ -0,0 +1,74 @@
+#!/bin/sh
+#
+# Set environment variables so that we can compile leveldb using
+# fbcode settings.  It uses the latest g++ compiler and also
+# uses jemalloc
+
+TOOLCHAIN_REV=fbe3b095a4cc4a3713730050d182b7b4a80c342f
+TOOLCHAIN_EXECUTABLES="/mnt/gvfs/third-party/$TOOLCHAIN_REV/centos5.2-native"
+TOOLCHAIN_LIB_BASE="/mnt/gvfs/third-party/$TOOLCHAIN_REV/gcc-4.7.1-glibc-2.14.1"
+TOOL_JEMALLOC=jemalloc-3.3.1/9202ce3
+GLIBC_RUNTIME_PATH=/usr/local/fbcode/gcc-4.7.1-glibc-2.14.1
+
+# location of libgcc
+LIBGCC_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/libgcc/libgcc-4.7.1/afc21dc/include"
+LIBGCC_LIBS=" -L $TOOLCHAIN_LIB_BASE/libgcc/libgcc-4.7.1/afc21dc/libs"
+
+# location of glibc
+GLIBC_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/glibc/glibc-2.14.1/99df8fc/include"
+GLIBC_LIBS=" -L $TOOLCHAIN_LIB_BASE/glibc/glibc-2.14.1/99df8fc/lib"
+
+# location of snappy headers and libraries
+SNAPPY_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/snappy/snappy-1.0.3/7518bbe/include"
+SNAPPY_LIBS=" $TOOLCHAIN_LIB_BASE/snappy/snappy-1.0.3/7518bbe/lib/libsnappy.a"
+
+# location of zlib headers and libraries
+ZLIB_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/zlib/zlib-1.2.5/91ddd43/include"
+ZLIB_LIBS=" $TOOLCHAIN_LIB_BASE/zlib/zlib-1.2.5/91ddd43/lib/libz.a"
+
+# location of gflags headers and libraries
+GFLAGS_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/gflags/gflags-1.6/91ddd43/include"
+GFLAGS_LIBS=" $TOOLCHAIN_LIB_BASE/gflags/gflags-1.6/91ddd43/lib/libgflags.a"
+
+# location of bzip headers and libraries
+BZIP_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/bzip2/bzip2-1.0.6/91ddd43/include"
+BZIP_LIBS=" $TOOLCHAIN_LIB_BASE/bzip2/bzip2-1.0.6/91ddd43/lib/libbz2.a"
+
+# location of gflags headers and libraries
+GFLAGS_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/gflags/gflags-1.6/91ddd43/include"
+GFLAGS_LIBS=" $TOOLCHAIN_LIB_BASE/gflags/gflags-1.6/91ddd43/lib/libgflags.a"
+
+# use Intel SSE support for checksum calculations
+export USE_SSE=" -msse -msse4.2 "
+
+CC="$TOOLCHAIN_EXECUTABLES/clang/clang-3.2/0b7c69d/bin/clang $CLANG_INCLUDES"
+CXX="$TOOLCHAIN_EXECUTABLES/clang/clang-3.2/0b7c69d/bin/clang++ $CLANG_INCLUDES $JINCLUDE $SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $GFLAGS_INCLUDE"
+AR=$TOOLCHAIN_EXECUTABLES/binutils/binutils-2.21.1/da39a3e/bin/ar
+RANLIB=$TOOLCHAIN_EXECUTABLES/binutils/binutils-2.21.1/da39a3e/bin/ranlib
+
+CFLAGS="-B$TOOLCHAIN_EXECUTABLES/binutils/binutils-2.21.1/da39a3e/bin -nostdlib "
+CFLAGS+=" -nostdinc -isystem $TOOLCHAIN_LIB_BASE/libgcc/libgcc-4.7.1/afc21dc/include/c++/4.7.1 "
+CFLAGS+=" -isystem $TOOLCHAIN_LIB_BASE/libgcc/libgcc-4.7.1/afc21dc/include/c++/4.7.1/x86_64-facebook-linux "
+CFLAGS+=" -isystem $TOOLCHAIN_LIB_BASE/libgcc/libgcc-4.7.1/afc21dc/include/c++/4.7.1/backward "
+CFLAGS+=" -isystem $TOOLCHAIN_LIB_BASE/glibc/glibc-2.14.1/99df8fc/include "
+CFLAGS+=" -isystem $TOOLCHAIN_LIB_BASE/libgcc/libgcc-4.7.1/afc21dc/include "
+CFLAGS+=" -isystem $TOOLCHAIN_LIB_BASE/clang/clang-3.2/0b7c69d/lib/clang/3.2/include "
+CFLAGS+=" -isystem $TOOLCHAIN_LIB_BASE/kernel-headers/kernel-headers-3.2.18_70_fbk11_00129_gc8882d0/da39a3e/include/linux "
+CFLAGS+=" -isystem $TOOLCHAIN_LIB_BASE/kernel-headers/kernel-headers-3.2.18_70_fbk11_00129_gc8882d0/da39a3e/include "
+CFLAGS+=" -Wall -Wno-sign-compare -Wno-unused-variable -Winvalid-pch -Wno-deprecated -Woverloaded-virtual"
+CFLAGS+=" $LIBGCC_INCLUDE $GLIBC_INCLUDE"
+CXXFLAGS="$CFLAGS -nostdinc++"
+
+CFLAGS+=" -I $TOOLCHAIN_LIB_BASE/jemalloc/$TOOL_JEMALLOC/include -DHAVE_JEMALLOC"
+
+EXEC_LDFLAGS=" -Wl,--whole-archive $TOOLCHAIN_LIB_BASE/jemalloc/$TOOL_JEMALLOC/lib/libjemalloc.a"
+EXEC_LDFLAGS+=" -Wl,--no-whole-archive $TOOLCHAIN_LIB_BASE/libunwind/libunwind-1.0.1/350336c/lib/libunwind.a"
+EXEC_LDFLAGS+=" $HDFSLIB $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $GFLAGS_LIBS"
+EXEC_LDFLAGS+=" -Wl,--dynamic-linker,$GLIBC_RUNTIME_PATH/lib/ld-linux-x86-64.so.2"
+EXEC_LDFLAGS+=" -B$TOOLCHAIN_EXECUTABLES/binutils/binutils-2.21.1/da39a3e/bin"
+
+PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS "
+
+EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $GFLAGS_LIBS"
+
+export CC CXX AR RANLIB CFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED 

build_tools/fbcode.gcc471.sh

@@ -0,0 +1,70 @@
+#!/bin/sh
+#
+# Set environment variables so that we can compile leveldb using
+# fbcode settings.  It uses the latest g++ compiler and also
+# uses jemalloc
+
+TOOLCHAIN_REV=fbe3b095a4cc4a3713730050d182b7b4a80c342f
+TOOLCHAIN_EXECUTABLES="/mnt/gvfs/third-party/$TOOLCHAIN_REV/centos5.2-native"
+TOOLCHAIN_LIB_BASE="/mnt/gvfs/third-party/$TOOLCHAIN_REV/gcc-4.7.1-glibc-2.14.1"
+TOOL_JEMALLOC=jemalloc-3.3.1/9202ce3
+
+# location of libhdfs libraries
+if test "$USE_HDFS"; then
+  JAVA_HOME="/usr/local/jdk-6u22-64"
+  JINCLUDE="-I$JAVA_HOME/include -I$JAVA_HOME/include/linux"
+  GLIBC_RUNTIME_PATH="/usr/local/fbcode/gcc-4.7.1-glibc-2.14.1"
+  HDFSLIB=" -Wl,--no-whole-archive hdfs/libhdfs.a -L$JAVA_HOME/jre/lib/amd64 "
+  HDFSLIB+=" -L$JAVA_HOME/jre/lib/amd64/server -L$GLIBC_RUNTIME_PATH/lib "
+  HDFSLIB+=" -ldl -lverify -ljava -ljvm "
+fi
+
+# location of libgcc
+LIBGCC_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/libgcc/libgcc-4.7.1/afc21dc/include"
+LIBGCC_LIBS=" -L $TOOLCHAIN_LIB_BASE/libgcc/libgcc-4.7.1/afc21dc/libs"
+
+# location of glibc
+GLIBC_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/glibc/glibc-2.14.1/99df8fc/include"
+GLIBC_LIBS=" -L $TOOLCHAIN_LIB_BASE/glibc/glibc-2.14.1/99df8fc/lib"
+
+# location of snappy headers and libraries
+SNAPPY_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/snappy/snappy-1.0.3/7518bbe/include"
+SNAPPY_LIBS=" $TOOLCHAIN_LIB_BASE/snappy/snappy-1.0.3/7518bbe/lib/libsnappy.a"
+
+# location of zlib headers and libraries
+ZLIB_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/zlib/zlib-1.2.5/91ddd43/include"
+ZLIB_LIBS=" $TOOLCHAIN_LIB_BASE/zlib/zlib-1.2.5/91ddd43/lib/libz.a"
+
+# location of bzip headers and libraries
+BZIP_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/bzip2/bzip2-1.0.6/91ddd43/include"
+BZIP_LIBS=" $TOOLCHAIN_LIB_BASE/bzip2/bzip2-1.0.6/91ddd43/lib/libbz2.a"
+
+# location of gflags headers and libraries
+GFLAGS_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/gflags/gflags-1.6/91ddd43/include"
+GFLAGS_LIBS=" $TOOLCHAIN_LIB_BASE/gflags/gflags-1.6/91ddd43/lib/libgflags.a"
+
+# use Intel SSE support for checksum calculations
+export USE_SSE=" -msse -msse4.2 "
+
+CC="$TOOLCHAIN_EXECUTABLES/gcc/gcc-4.7.1-glibc-2.14.1/bin/gcc"
+CXX="$TOOLCHAIN_EXECUTABLES/gcc/gcc-4.7.1-glibc-2.14.1/bin/g++ $JINCLUDE $SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $GFLAGS_INCLUDE"
+AR=$TOOLCHAIN_EXECUTABLES/binutils/binutils-2.21.1/da39a3e/bin/ar
+RANLIB=$TOOLCHAIN_EXECUTABLES/binutils/binutils-2.21.1/da39a3e/bin/ranlib
+
+CFLAGS="-B$TOOLCHAIN_EXECUTABLES/binutils/binutils-2.21.1/da39a3e/bin/gold -m64 -mtune=generic"
+CFLAGS+=" -I $TOOLCHAIN_LIB_BASE/jemalloc/$TOOL_JEMALLOC/include -DHAVE_JEMALLOC"
+CFLAGS+=" $LIBGCC_INCLUDE $GLIBC_INCLUDE"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_ATOMIC_PRESENT -DROCKSDB_FALLOCATE_PRESENT"
+CFLAGS+=" -DSNAPPY -DGFLAGS -DZLIB -DBZIP2"
+
+EXEC_LDFLAGS=" -Wl,--whole-archive $TOOLCHAIN_LIB_BASE/jemalloc/$TOOL_JEMALLOC/lib/libjemalloc.a"
+EXEC_LDFLAGS+=" -Wl,--no-whole-archive $TOOLCHAIN_LIB_BASE/libunwind/libunwind-1.0.1/350336c/lib/libunwind.a"
+EXEC_LDFLAGS+=" $HDFSLIB $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $GFLAGS_LIBS"
+
+PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS "
+
+EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $GFLAGS_LIBS"
+
+VALGRIND_VER="$TOOLCHAIN_LIB_BASE/valgrind/valgrind-3.8.1/91ddd43/bin/"
+
+export CC CXX AR RANLIB CFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER

build_tools/fbcode.gcc481.sh

@@ -0,0 +1,77 @@
+#!/bin/sh
+#
+# Set environment variables so that we can compile rocksdb using
+# fbcode settings.  It uses the latest g++ compiler and also
+# uses jemalloc
+
+TOOLCHAIN_REV=53dc1fe83f84e9145b9ffb81b81aa7f6a49c87cc
+CENTOS_VERSION=`rpm -q --qf "%{VERSION}" $(rpm -q --whatprovides redhat-release)`
+if [ "$CENTOS_VERSION" = "6" ]; then
+  TOOLCHAIN_EXECUTABLES="/mnt/gvfs/third-party/$TOOLCHAIN_REV/centos6-native"
+else
+  TOOLCHAIN_EXECUTABLES="/mnt/gvfs/third-party/$TOOLCHAIN_REV/centos5.2-native"
+fi
+TOOLCHAIN_LIB_BASE="/mnt/gvfs/third-party/$TOOLCHAIN_REV/gcc-4.8.1-glibc-2.17"
+
+# location of libhdfs libraries
+if test "$USE_HDFS"; then
+  JAVA_HOME="/usr/local/jdk-6u22-64"
+  JINCLUDE="-I$JAVA_HOME/include -I$JAVA_HOME/include/linux"
+  GLIBC_RUNTIME_PATH="/usr/local/fbcode/gcc-4.8.1-glibc-2.17"
+  HDFSLIB=" -Wl,--no-whole-archive hdfs/libhdfs.a -L$JAVA_HOME/jre/lib/amd64 "
+  HDFSLIB+=" -L$JAVA_HOME/jre/lib/amd64/server -L$GLIBC_RUNTIME_PATH/lib "
+  HDFSLIB+=" -ldl -lverify -ljava -ljvm "
+fi
+
+# location of libgcc
+LIBGCC_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/libgcc/libgcc-4.8.1/8aac7fc/include"
+LIBGCC_LIBS=" -L $TOOLCHAIN_LIB_BASE/libgcc/libgcc-4.8.1/8aac7fc/libs"
+
+# location of glibc
+GLIBC_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/glibc/glibc-2.17/99df8fc/include"
+GLIBC_LIBS=" -L $TOOLCHAIN_LIB_BASE/glibc/glibc-2.17/99df8fc/lib"
+
+# location of snappy headers and libraries
+SNAPPY_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/snappy/snappy-1.0.3/43d84e2/include"
+SNAPPY_LIBS=" $TOOLCHAIN_LIB_BASE/snappy/snappy-1.0.3/43d84e2/lib/libsnappy.a"
+
+# location of zlib headers and libraries
+ZLIB_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/zlib/zlib-1.2.5/c3f970a/include"
+ZLIB_LIBS=" $TOOLCHAIN_LIB_BASE/zlib/zlib-1.2.5/c3f970a/lib/libz.a"
+
+# location of bzip headers and libraries
+BZIP_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/bzip2/bzip2-1.0.6/c3f970a/include"
+BZIP_LIBS=" $TOOLCHAIN_LIB_BASE/bzip2/bzip2-1.0.6/c3f970a/lib/libbz2.a"
+
+# location of gflags headers and libraries
+GFLAGS_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/gflags/gflags-1.6/c3f970a/include"
+GFLAGS_LIBS=" $TOOLCHAIN_LIB_BASE/gflags/gflags-1.6/c3f970a/lib/libgflags.a"
+
+# location of jemalloc
+JEMALLOC_INCLUDE=" -I $TOOLCHAIN_LIB_BASE/jemalloc/jemalloc-3.4.1/4d53c6f/include/"
+JEMALLOC_LIB=" -Wl,--whole-archive $TOOLCHAIN_LIB_BASE/jemalloc/jemalloc-3.4.1/4d53c6f/lib/libjemalloc.a"
+
+# use Intel SSE support for checksum calculations
+export USE_SSE=" -msse -msse4.2 "
+
+CC="$TOOLCHAIN_EXECUTABLES/gcc/gcc-4.8.1/cc6c9dc/bin/gcc"
+CXX="$TOOLCHAIN_EXECUTABLES/gcc/gcc-4.8.1/cc6c9dc/bin/g++ $JINCLUDE $SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $GFLAGS_INCLUDE"
+AR=$TOOLCHAIN_EXECUTABLES/binutils/binutils-2.21.1/da39a3e/bin/ar
+RANLIB=$TOOLCHAIN_EXECUTABLES/binutils/binutils-2.21.1/da39a3e/bin/ranlib
+
+CFLAGS="-B$TOOLCHAIN_EXECUTABLES/binutils/binutils-2.21.1/da39a3e/bin/gold -m64 -mtune=generic"
+CFLAGS+=" $LIBGCC_INCLUDE $GLIBC_INCLUDE"
+CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_ATOMIC_PRESENT -DROCKSDB_FALLOCATE_PRESENT"
+CFLAGS+=" -DSNAPPY -DGFLAGS -DZLIB -DBZIP2"
+
+EXEC_LDFLAGS="-Wl,--dynamic-linker,/usr/local/fbcode/gcc-4.8.1-glibc-2.17/lib/ld.so"
+EXEC_LDFLAGS+=" -Wl,--no-whole-archive $TOOLCHAIN_LIB_BASE/libunwind/libunwind-1.0.1/675d945/lib/libunwind.a"
+EXEC_LDFLAGS+=" $HDFSLIB $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $GFLAGS_LIBS"
+
+PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS "
+
+EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $GFLAGS_LIBS"
+
+VALGRIND_VER="$TOOLCHAIN_LIB_BASE/valgrind/valgrind-3.8.1/c3f970a/bin/"
+
+export CC CXX AR RANLIB CFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE

build_tools/fbcode_config.sh

@@ -1,136 +0,0 @@
-#!/bin/sh
-#
-# Set environment variables so that we can compile rocksdb using
-# fbcode settings.  It uses the latest g++ and clang compilers and also
-# uses jemalloc
-# Environment variables that change the behavior of this script:
-# PIC_BUILD -- if true, it will only take pic versions of libraries from fbcode. libraries that don't have pic variant will not be included
-
-
-BASEDIR=`dirname $BASH_SOURCE`
-source "$BASEDIR/dependencies.sh"
-
-CFLAGS=""
-
-# libgcc
-LIBGCC_INCLUDE="$LIBGCC_BASE/include"
-LIBGCC_LIBS=" -L $LIBGCC_BASE/libs"
-
-# glibc
-GLIBC_INCLUDE="$GLIBC_BASE/include"
-GLIBC_LIBS=" -L $GLIBC_BASE/lib"
-
-# snappy
-SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include/"
-if test -z $PIC_BUILD; then
-  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy.a"
-else
-  SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy_pic.a"
-fi
-CFLAGS+=" -DSNAPPY"
-
-if test -z $PIC_BUILD; then
-  # location of zlib headers and libraries
-  ZLIB_INCLUDE=" -I $ZLIB_BASE/include/"
-  ZLIB_LIBS=" $ZLIB_BASE/lib/libz.a"
-  CFLAGS+=" -DZLIB"
-
-  # location of bzip headers and libraries
-  BZIP_INCLUDE=" -I $BZIP2_BASE/include/"
-  BZIP_LIBS=" $BZIP2_BASE/lib/libbz2.a"
-  CFLAGS+=" -DBZIP2"
-
-  LZ4_INCLUDE=" -I $LZ4_BASE/include/"
-  LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
-  CFLAGS+=" -DLZ4"
-
-  ZSTD_INCLUDE=" -I $ZSTD_BASE/include/"
-  ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
-  CFLAGS+=" -DZSTD"
-fi
-
-# location of gflags headers and libraries
-GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
-if test -z $PIC_BUILD; then
-  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags.a"
-else
-  GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags_pic.a"
-fi
-CFLAGS+=" -DGFLAGS=google"
-
-# location of jemalloc
-JEMALLOC_INCLUDE=" -I $JEMALLOC_BASE/include/"
-JEMALLOC_LIB=" $JEMALLOC_BASE/lib/libjemalloc.a"
-
-if test -z $PIC_BUILD; then
-  # location of numa
-  NUMA_INCLUDE=" -I $NUMA_BASE/include/"
-  NUMA_LIB=" $NUMA_BASE/lib/libnuma.a"
-  CFLAGS+=" -DNUMA"
-
-  # location of libunwind
-  LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
-fi
-
-# use Intel SSE support for checksum calculations
-export USE_SSE=1
-
-BINUTILS="$BINUTILS_BASE/bin"
-AR="$BINUTILS/ar"
-
-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE"
-
-STDLIBS="-L $GCC_BASE/lib64"
-
-CLANG_BIN="$CLANG_BASE/bin"
-CLANG_LIB="$CLANG_BASE/lib"
-CLANG_SRC="$CLANG_BASE/../../src"
-
-CLANG_ANALYZER="$CLANG_BIN/clang++"
-CLANG_SCAN_BUILD="$CLANG_SRC/clang/tools/scan-build/scan-build"
-
-if [ -z "$USE_CLANG" ]; then
-  # gcc
-  CC="$GCC_BASE/bin/gcc"
-  CXX="$GCC_BASE/bin/g++"
-
-  CFLAGS+=" -B$BINUTILS/gold"
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  JEMALLOC=1
-else
-  # clang
-  CLANG_INCLUDE="$CLANG_LIB/clang/stable/include"
-  CC="$CLANG_BIN/clang"
-  CXX="$CLANG_BIN/clang++"
-
-  KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include"
-
-  CFLAGS+=" -B$BINUTILS/gold -nostdinc -nostdlib"
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/4.9.x "
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/4.9.x/x86_64-facebook-linux "
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  CFLAGS+=" -isystem $CLANG_INCLUDE"
-  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
-  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
-  CFLAGS+=" -Wno-expansion-to-defined "
-  CXXFLAGS="-nostdinc++"
-fi
-
-CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE"
-CXXFLAGS+=" $CFLAGS"
-
-EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB"
-EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/gcc-4.9-glibc-2.20/lib/ld.so"
-EXEC_LDFLAGS+=" $LIBUNWIND"
-EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/gcc-4.9-glibc-2.20/lib"
-
-PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
-
-EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS"
-
-VALGRIND_VER="$VALGRIND_BASE/bin/"
-
-export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE CLANG_ANALYZER CLANG_SCAN_BUILD

build_tools/fbcode_config4.8.1.sh

@@ -1,107 +0,0 @@
-#!/bin/sh
-#
-# Set environment variables so that we can compile rocksdb using
-# fbcode settings.  It uses the latest g++ compiler and also
-# uses jemalloc
-
-BASEDIR=`dirname $BASH_SOURCE`
-source "$BASEDIR/dependencies_4.8.1.sh"
-
-# location of libgcc
-LIBGCC_INCLUDE="$LIBGCC_BASE/include"
-LIBGCC_LIBS=" -L $LIBGCC_BASE/libs"
-
-# location of glibc
-GLIBC_INCLUDE="$GLIBC_BASE/include"
-GLIBC_LIBS=" -L $GLIBC_BASE/lib"
-
-# location of snappy headers and libraries
-SNAPPY_INCLUDE=" -I $SNAPPY_BASE/include"
-SNAPPY_LIBS=" $SNAPPY_BASE/lib/libsnappy.a"
-
-# location of zlib headers and libraries
-ZLIB_INCLUDE=" -I $ZLIB_BASE/include"
-ZLIB_LIBS=" $ZLIB_BASE/lib/libz.a"
-
-# location of bzip headers and libraries
-BZIP2_INCLUDE=" -I $BZIP2_BASE/include/"
-BZIP2_LIBS=" $BZIP2_BASE/lib/libbz2.a"
-
-LZ4_INCLUDE=" -I $LZ4_BASE/include"
-LZ4_LIBS=" $LZ4_BASE/lib/liblz4.a"
-
-ZSTD_INCLUDE=" -I $ZSTD_BASE/include"
-ZSTD_LIBS=" $ZSTD_BASE/lib/libzstd.a"
-
-# location of gflags headers and libraries
-GFLAGS_INCLUDE=" -I $GFLAGS_BASE/include/"
-GFLAGS_LIBS=" $GFLAGS_BASE/lib/libgflags.a"
-
-# location of jemalloc
-JEMALLOC_INCLUDE=" -I $JEMALLOC_BASE/include"
-JEMALLOC_LIB="$JEMALLOC_BASE/lib/libjemalloc.a"
-
-# location of numa
-NUMA_INCLUDE=" -I $NUMA_BASE/include/"
-NUMA_LIB=" $NUMA_BASE/lib/libnuma.a"
-
-# location of libunwind
-LIBUNWIND="$LIBUNWIND_BASE/lib/libunwind.a"
-
-# use Intel SSE support for checksum calculations
-export USE_SSE=1
-
-BINUTILS="$BINUTILS_BASE/bin"
-AR="$BINUTILS/ar"
-
-DEPS_INCLUDE="$SNAPPY_INCLUDE $ZLIB_INCLUDE $BZIP2_INCLUDE $LZ4_INCLUDE $ZSTD_INCLUDE $GFLAGS_INCLUDE $NUMA_INCLUDE"
-
-STDLIBS="-L $GCC_BASE/lib64"
-
-if [ -z "$USE_CLANG" ]; then
-  # gcc
-  CC="$GCC_BASE/bin/gcc"
-  CXX="$GCC_BASE/bin/g++"
-
-  CFLAGS="-B$BINUTILS/gold -m64 -mtune=generic"
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  JEMALLOC=1
-else
-  # clang
-  CLANG_BIN="$CLANG_BASE/bin"
-  CLANG_LIB="$CLANG_BASE/lib"
-  CLANG_INCLUDE="$CLANG_LIB/clang/*/include"
-  CC="$CLANG_BIN/clang"
-  CXX="$CLANG_BIN/clang++"
-
-  KERNEL_HEADERS_INCLUDE="$KERNEL_HEADERS_BASE/include/"
-
-  CFLAGS="-B$BINUTILS/gold -nostdinc -nostdlib"
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/4.8.1 "
-  CFLAGS+=" -isystem $LIBGCC_BASE/include/c++/4.8.1/x86_64-facebook-linux "
-  CFLAGS+=" -isystem $GLIBC_INCLUDE"
-  CFLAGS+=" -isystem $LIBGCC_INCLUDE"
-  CFLAGS+=" -isystem $CLANG_INCLUDE"
-  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE/linux "
-  CFLAGS+=" -isystem $KERNEL_HEADERS_INCLUDE "
-  CXXFLAGS="-nostdinc++"
-fi
-
-CFLAGS+=" $DEPS_INCLUDE"
-CFLAGS+=" -DROCKSDB_PLATFORM_POSIX -DROCKSDB_LIB_IO_POSIX -DROCKSDB_FALLOCATE_PRESENT -DROCKSDB_MALLOC_USABLE_SIZE"
-CFLAGS+=" -DSNAPPY -DGFLAGS=google -DZLIB -DBZIP2 -DLZ4 -DZSTD -DNUMA"
-CXXFLAGS+=" $CFLAGS"
-
-EXEC_LDFLAGS=" $SNAPPY_LIBS $ZLIB_LIBS $BZIP2_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS $NUMA_LIB"
-EXEC_LDFLAGS+=" -Wl,--dynamic-linker,/usr/local/fbcode/gcc-4.8.1-glibc-2.17/lib/ld.so"
-EXEC_LDFLAGS+=" $LIBUNWIND"
-EXEC_LDFLAGS+=" -Wl,-rpath=/usr/local/fbcode/gcc-4.8.1-glibc-2.17/lib"
-
-PLATFORM_LDFLAGS="$LIBGCC_LIBS $GLIBC_LIBS $STDLIBS -lgcc -lstdc++"
-
-EXEC_LDFLAGS_SHARED="$SNAPPY_LIBS $ZLIB_LIBS $BZIP2_LIBS $LZ4_LIBS $ZSTD_LIBS $GFLAGS_LIBS"
-
-VALGRIND_VER="$VALGRIND_BASE/bin/"
-
-export CC CXX AR CFLAGS CXXFLAGS EXEC_LDFLAGS EXEC_LDFLAGS_SHARED VALGRIND_VER JEMALLOC_LIB JEMALLOC_INCLUDE

build_tools/format-diff.sh

@@ -79,12 +79,6 @@ echo -e "Detect lines that doesn't follow the format rules:\r"
 echo "$diffs" | 
   sed -e "s/\(^-.*$\)/`echo -e \"$COLOR_RED\1$COLOR_END\"`/" |
   sed -e "s/\(^+.*$\)/`echo -e \"$COLOR_GREEN\1$COLOR_END\"`/"
-
-if [[ "$OPT" == *"-DTRAVIS"* ]]
-then
-  exit 1
-fi
-
 echo -e "Would you like to fix the format automatically (y/n): \c"
 
 # Make sure under any mode, we can read user input.

build_tools/mac-install-gflags.sh

@@ -0,0 +1,25 @@
+#!/bin/sh
+# Install gflags for mac developers.
+
+set -e
+
+DIR=`mktemp -d /tmp/rocksdb_gflags_XXXX`
+
+cd $DIR
+wget https://gflags.googlecode.com/files/gflags-2.0.tar.gz
+tar xvfz gflags-2.0.tar.gz
+cd gflags-2.0
+
+./configure
+make
+make install
+
+# Add include/lib path for g++
+echo 'export LIBRARY_PATH+=":/usr/local/lib"' >> ~/.bash_profile
+echo 'export CPATH+=":/usr/local/include"' >> ~/.bash_profile
+
+echo ""
+echo "-----------------------------------------------------------------------------"
+echo "|                         Installation Completed                            |"
+echo "-----------------------------------------------------------------------------"
+echo "Please run `. ~/bash_profile` to be able to compile with gflags"

build_tools/make_new_version.sh

@@ -1,5 +1,5 @@
 #!/bin/bash
-#  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+#  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
 #  This source code is licensed under the BSD-style license found in the
 #  LICENSE file in the root directory of this source tree. An additional grant
 #  of patent rights can be found in the PATENTS file in the same directory.
@@ -10,7 +10,7 @@ then
   GIT="git"
 fi
 
-# Print out the colored progress info so that it can be brainlessly
+# Print out the colored progress info so that it can be brainlessly 
 # distinguished by users.
 function title() {
   echo -e "\033[1;32m$*\033[0m"
@@ -28,19 +28,17 @@ fi
 ROCKSDB_VERSION=$1
 
 GIT_BRANCH=`git rev-parse --abbrev-ref HEAD`
-echo $GIT_BRANCH
-
 if [ $GIT_BRANCH != "master" ]; then
   echo "Error: Current branch is '$GIT_BRANCH', Please switch to master branch."
-  exit 1
 fi
 
 title "Adding new tag for this release ..."
-BRANCH="$ROCKSDB_VERSION.fb"
-$GIT checkout -b $BRANCH
+TAG="$ROCKSDB_VERSION.fb"
+$GIT tag -a "$TAG" -m "RocksDB $ROCKSDB_VERSION"
 
 # Setting up the proxy for remote repo access
-title "Pushing new branch to remote repo ..."
-git push origin --set-upstream $BRANCH
+title "Pushing new tag to remote repo ..."
+$GIT push origin --tags
 
-title "Branch $BRANCH is pushed to github;"
+title "Tag $TAG is pushed to github; if you want to delete it, please run"
+title "git tags -d $TAG && git push origin :refs/tags/$TAG"

build_tools/make_package.sh

@@ -1,116 +0,0 @@
-#/usr/bin/env bash
-
-set -e
-
-function log() {
-  echo "[+] $1"
-}
-
-function fatal() {
-  echo "[!] $1"
-  exit 1
-}
-
-function platform() {
-  local  __resultvar=$1
-  if [[ -f "/etc/yum.conf" ]]; then
-    eval $__resultvar="centos"
-  elif [[ -f "/etc/dpkg/dpkg.cfg" ]]; then
-    eval $__resultvar="ubuntu"
-  else
-    fatal "Unknwon operating system"
-  fi
-}
-platform OS
-
-function package() {
-  if [[ $OS = "ubuntu" ]]; then
-    if dpkg --get-selections | grep --quiet $1; then
-      log "$1 is already installed. skipping."
-    else
-      apt-get install $@ -y
-    fi
-  elif [[ $OS = "centos" ]]; then
-    if rpm -qa | grep --quiet $1; then
-      log "$1 is already installed. skipping."
-    else
-      yum install $@ -y
-    fi
-  fi
-}
-
-function detect_fpm_output() {
-  if [[ $OS = "ubuntu" ]]; then
-    export FPM_OUTPUT=deb
-  elif [[ $OS = "centos" ]]; then
-    export FPM_OUTPUT=rpm
-  fi
-}
-detect_fpm_output
-
-function gem_install() {
-  if gem list | grep --quiet $1; then
-    log "$1 is already installed. skipping."
-  else
-    gem install $@
-  fi
-}
-
-function main() {
-  if [[ $# -ne 1 ]]; then
-    fatal "Usage: $0 <rocksdb_version>"
-  else
-    log "using rocksdb version: $1"
-  fi
-
-  if [[ -d /vagrant ]]; then
-    if [[ $OS = "ubuntu" ]]; then
-      package g++-4.7
-      export CXX=g++-4.7
-
-      # the deb would depend on libgflags2, but the static lib is the only thing
-      # installed by make install
-      package libgflags-dev
-
-      package ruby-all-dev
-    elif [[ $OS = "centos" ]]; then
-      pushd /etc/yum.repos.d
-      if [[ ! -f /etc/yum.repos.d/devtools-1.1.repo ]]; then
-        wget http://people.centos.org/tru/devtools-1.1/devtools-1.1.repo
-      fi
-      package devtoolset-1.1-gcc --enablerepo=testing-1.1-devtools-6
-      package devtoolset-1.1-gcc-c++ --enablerepo=testing-1.1-devtools-6
-      export CC=/opt/centos/devtoolset-1.1/root/usr/bin/gcc
-      export CPP=/opt/centos/devtoolset-1.1/root/usr/bin/cpp
-      export CXX=/opt/centos/devtoolset-1.1/root/usr/bin/c++
-      export PATH=$PATH:/opt/centos/devtoolset-1.1/root/usr/bin
-      popd
-      if ! rpm -qa | grep --quiet gflags; then
-        rpm -i https://github.com/schuhschuh/gflags/releases/download/v2.1.0/gflags-devel-2.1.0-1.amd64.rpm
-      fi
-
-      package ruby
-      package ruby-devel
-      package rubygems
-      package rpm-build
-    fi
-  fi
-  gem_install fpm
-
-  make static_lib
-  make install INSTALL_PATH=package
-  fpm \
-    -s dir \
-    -t $FPM_OUTPUT \
-    -n rocksdb \
-    -v $1 \
-    --prefix /usr \
-    --url http://rocksdb.org/ \
-    -m rocksdb@fb.com \
-    --license BSD \
-    --vendor Facebook \
-    --description "RocksDB is an embeddable persistent key-value store for fast storage." \
-    package
-}
-
-main $@

build_tools/precommit_checker.py

@@ -1,198 +0,0 @@
-#!/usr/local/fbcode/gcc-4.8.1-glibc-2.17-fb/bin/python2.7
-
-from __future__ import absolute_import
-from __future__ import division
-from __future__ import print_function
-from __future__ import unicode_literals
-import argparse
-import commands
-import subprocess
-import sys
-import re
-import os
-import time
-
-#
-# Simple logger
-#
-
-
-class Log:
-
-    LOG_FILE = "/tmp/precommit-check.log"
-
-    def __init__(self):
-        self.filename = Log.LOG_FILE
-        self.f = open(self.filename, 'w+', 0)
-
-    def caption(self, str):
-        line = "\n##### %s #####\n" % str
-        if self.f:
-            self.f.write("%s \n" % line)
-        else:
-            print(line)
-
-    def error(self, str):
-        data = "\n\n##### ERROR ##### %s" % str
-        if self.f:
-            self.f.write("%s \n" % data)
-        else:
-            print(data)
-
-    def log(self, str):
-        if self.f:
-            self.f.write("%s \n" % str)
-        else:
-            print(str)
-
-#
-# Shell Environment
-#
-
-
-class Env(object):
-
-    def __init__(self, tests):
-        self.tests = tests
-        self.log = Log()
-
-    def shell(self, cmd, path=os.getcwd()):
-        if path:
-            os.chdir(path)
-
-        self.log.log("==== shell session ===========================")
-        self.log.log("%s> %s" % (path, cmd))
-        status = subprocess.call("cd %s; %s" % (path, cmd), shell=True,
-                                 stdout=self.log.f, stderr=self.log.f)
-        self.log.log("status = %s" % status)
-        self.log.log("============================================== \n\n")
-        return status
-
-    def GetOutput(self, cmd, path=os.getcwd()):
-        if path:
-            os.chdir(path)
-
-        self.log.log("==== shell session ===========================")
-        self.log.log("%s> %s" % (path, cmd))
-        status, out = commands.getstatusoutput(cmd)
-        self.log.log("status = %s" % status)
-        self.log.log("out = %s" % out)
-        self.log.log("============================================== \n\n")
-        return status, out
-
-#
-# Pre-commit checker
-#
-
-
-class PreCommitChecker(Env):
-
-    def __init__(self, tests):
-        Env.__init__(self, tests)
-
-    #
-    #   Get commands for a given job from the determinator file
-    #
-    def get_commands(self, test):
-        status, out = self.GetOutput(
-            "build_tools/rocksdb-lego-determinator %s" % test, ".")
-        return status, out
-
-    #
-    # Run a specific CI job
-    #
-    def run_test(self, test):
-        self.log.caption("Running test %s locally" % test)
-
-        # get commands for the CI job determinator
-        status, cmds = self.get_commands(test)
-        if status != 0:
-            self.log.error("Error getting commands for test %s" % test)
-            return False
-
-        # Parse the JSON to extract the commands to run
-        cmds = re.findall("'shell':'([^\']*)'", cmds)
-
-        if len(cmds) == 0:
-            self.log.log("No commands found")
-            return False
-
-        # Run commands
-        for cmd in cmds:
-            # Replace J=<..> with the local environment variable
-            if "J" in os.environ:
-                cmd = cmd.replace("J=1", "J=%s" % os.environ["J"])
-                cmd = cmd.replace("make ", "make -j%s " % os.environ["J"])
-            # Run the command
-            status = self.shell(cmd, ".")
-            if status != 0:
-                self.log.error("Error running command %s for test %s"
-                               % (cmd, test))
-                return False
-
-        return True
-
-    #
-    # Run specified CI jobs
-    #
-    def run_tests(self):
-        if not self.tests:
-            self.log.error("Invalid args. Please provide tests")
-            return False
-
-        self.print_separator()
-        self.print_row("TEST", "RESULT")
-        self.print_separator()
-
-        for test in self.tests:
-            start_time = time.time()
-            self.print_test(test)
-            result = self.run_test(test)
-            elapsed_min = (time.time() - start_time) / 60
-            if not result:
-                self.log.error("Error running test %s" % test)
-                self.print_result("FAIL (%dm)" % elapsed_min)
-                return False
-            self.print_result("PASS (%dm)" % elapsed_min)
-
-        self.print_separator()
-        return True
-
-    #
-    # Print a line
-    #
-    def print_separator(self):
-        print("".ljust(60, "-"))
-
-    #
-    # Print two colums
-    #
-    def print_row(self, c0, c1):
-        print("%s%s" % (c0.ljust(40), c1.ljust(20)))
-
-    def print_test(self, test):
-        print(test.ljust(40), end="")
-        sys.stdout.flush()
-
-    def print_result(self, result):
-        print(result.ljust(20))
-
-#
-# Main
-#
-parser = argparse.ArgumentParser(description='RocksDB pre-commit checker.')
-
-# <test ....>
-parser.add_argument('test', nargs='+',
-                    help='CI test(s) to run. e.g: unit punit asan tsan ubsan')
-
-print("Please follow log %s" % Log.LOG_FILE)
-
-args = parser.parse_args()
-checker = PreCommitChecker(args.test)
-
-if not checker.run_tests():
-    print("Error running tests. Please check log file %s" % Log.LOG_FILE)
-    sys.exit(1)
-
-sys.exit(0)

build_tools/regression_build_test.sh

@@ -109,6 +109,7 @@ make release
     --cache_numshardbits=6 \
     --table_cache_numshardbits=4 \
     --open_files=55000 \
+    --disable_seek_compaction=1 \
     --statistics=1 \
     --histogram=1 \
     --disable_data_sync=1 \
@@ -128,6 +129,7 @@ make release
     --cache_numshardbits=6 \
     --table_cache_numshardbits=4 \
     --open_files=55000 \
+    --disable_seek_compaction=1 \
     --use_tailing_iterator=1 \
     --statistics=1 \
     --histogram=1 \
@@ -148,6 +150,7 @@ make release
     --cache_numshardbits=6 \
     --table_cache_numshardbits=4 \
     --open_files=55000 \
+    --disable_seek_compaction=1 \
     --statistics=1 \
     --histogram=1 \
     --disable_data_sync=1 \
@@ -169,6 +172,7 @@ make release
     --table_cache_numshardbits=4 \
     --write_buffer_size=1000000000 \
     --open_files=55000 \
+    --disable_seek_compaction=1 \
     --statistics=1 \
     --histogram=1 \
     --disable_data_sync=1 \
@@ -227,6 +231,7 @@ make release
     --cache_numshardbits=6 \
     --table_cache_numshardbits=4 \
     --open_files=55000 \
+    --disable_seek_compaction=1 \
     --disable_auto_compactions=1 \
     --statistics=1 \
     --histogram=1 \
@@ -243,12 +248,13 @@ make release
     --bloom_bits=10 \
     --num=$((NUM / 4)) \
     --reads=$((NUM / 4)) \
-    --benchmark_write_rate_limit=$(( 110 * 1024 )) \
+    --writes_per_second=1000 \
     --write_buffer_size=100000000 \
     --cache_size=6442450944 \
     --cache_numshardbits=6 \
     --table_cache_numshardbits=4 \
     --open_files=55000 \
+    --disable_seek_compaction=1 \
     --statistics=1 \
     --histogram=1 \
     --disable_data_sync=1 \
@@ -268,6 +274,7 @@ make release
     --table_cache_numshardbits=4 \
     --write_buffer_size=1000000000 \
     --open_files=55000 \
+    --disable_seek_compaction=1 \
     --statistics=1 \
     --histogram=1 \
     --disable_data_sync=1 \
@@ -276,107 +283,6 @@ make release
     --value_size=10 \
     --threads=16 > ${STAT_FILE}.memtablefillreadrandom
 
-common_in_mem_args="--db=/dev/shm/rocksdb \
-    --num_levels=6 \
-    --key_size=20 \
-    --prefix_size=12 \
-    --keys_per_prefix=10 \
-    --value_size=100 \
-    --compression_type=none \
-    --compression_ratio=1 \
-    --hard_rate_limit=2 \
-    --write_buffer_size=134217728 \
-    --max_write_buffer_number=4 \
-    --level0_file_num_compaction_trigger=8 \
-    --level0_slowdown_writes_trigger=16 \
-    --level0_stop_writes_trigger=24 \
-    --target_file_size_base=134217728 \
-    --max_bytes_for_level_base=1073741824 \
-    --disable_wal=0 \
-    --wal_dir=/dev/shm/rocksdb \
-    --sync=0 \
-    --disable_data_sync=1 \
-    --verify_checksum=1 \
-    --delete_obsolete_files_period_micros=314572800 \
-    --max_grandparent_overlap_factor=10 \
-    --use_plain_table=1 \
-    --open_files=-1 \
-    --mmap_read=1 \
-    --mmap_write=0 \
-    --memtablerep=prefix_hash \
-    --bloom_bits=10 \
-    --bloom_locality=1 \
-    --perf_level=0"
-
-# prepare a in-memory DB with 50M keys, total DB size is ~6G
-./db_bench \
-    $common_in_mem_args \
-    --statistics=0 \
-    --max_background_compactions=16 \
-    --max_background_flushes=16 \
-    --benchmarks=filluniquerandom \
-    --use_existing_db=0 \
-    --num=52428800 \
-    --threads=1 > /dev/null
-
-# Readwhilewriting
-./db_bench \
-    $common_in_mem_args \
-    --statistics=1 \
-    --max_background_compactions=4 \
-    --max_background_flushes=0 \
-    --benchmarks=readwhilewriting\
-    --use_existing_db=1 \
-    --duration=600 \
-    --threads=32 \
-    --benchmark_write_rate_limit=9502720 > ${STAT_FILE}.readwhilewriting_in_ram
-
-# Seekrandomwhilewriting
-./db_bench \
-    $common_in_mem_args \
-    --statistics=1 \
-    --max_background_compactions=4 \
-    --max_background_flushes=0 \
-    --benchmarks=seekrandomwhilewriting \
-    --use_existing_db=1 \
-    --use_tailing_iterator=1 \
-    --duration=600 \
-    --threads=32 \
-    --benchmark_write_rate_limit=9502720 > ${STAT_FILE}.seekwhilewriting_in_ram
-
-# measure fillseq with bunch of column families
-./db_bench \
-    --benchmarks=fillseq \
-    --num_column_families=500 \
-    --write_buffer_size=1048576 \
-    --db=$DATA_DIR \
-    --use_existing_db=0 \
-    --num=$NUM \
-    --writes=$NUM \
-    --open_files=55000 \
-    --statistics=1 \
-    --histogram=1 \
-    --disable_data_sync=1 \
-    --disable_wal=1 \
-    --sync=0  > ${STAT_FILE}.fillseq_lots_column_families
-
-# measure overwrite performance with bunch of column families
-./db_bench \
-    --benchmarks=overwrite \
-    --num_column_families=500 \
-    --write_buffer_size=1048576 \
-    --db=$DATA_DIR \
-    --use_existing_db=1 \
-    --num=$NUM \
-    --writes=$((NUM / 10)) \
-    --open_files=55000 \
-    --statistics=1 \
-    --histogram=1 \
-    --disable_data_sync=1 \
-    --disable_wal=1 \
-    --sync=0 \
-    --threads=8 > ${STAT_FILE}.overwrite_lots_column_families
-
 # send data to ods
 function send_to_ods {
   key="$1"
@@ -402,9 +308,9 @@ function send_benchmark_to_ods {
   file="$3"
 
   QPS=$(grep $bench $file | awk '{print $5}')
-  P50_MICROS=$(grep $bench $file -A 6 | grep "Percentiles" | awk '{print $3}' )
-  P75_MICROS=$(grep $bench $file -A 6 | grep "Percentiles" | awk '{print $5}' )
-  P99_MICROS=$(grep $bench $file -A 6 | grep "Percentiles" | awk '{print $7}' )
+  P50_MICROS=$(grep $bench $file -A 4 | tail -n1 | awk '{print $3}' )
+  P75_MICROS=$(grep $bench $file -A 4 | tail -n1 | awk '{print $5}' )
+  P99_MICROS=$(grep $bench $file -A 4 | tail -n1 | awk '{print $7}' )
 
   send_to_ods rocksdb.build.$bench_key.qps $QPS
   send_to_ods rocksdb.build.$bench_key.p50_micros $P50_MICROS
@@ -422,7 +328,3 @@ send_benchmark_to_ods readrandom readrandom_fillunique_random $STAT_FILE.readran
 send_benchmark_to_ods fillrandom memtablefillrandom $STAT_FILE.memtablefillreadrandom
 send_benchmark_to_ods readrandom memtablereadrandom $STAT_FILE.memtablefillreadrandom
 send_benchmark_to_ods readwhilewriting readwhilewriting $STAT_FILE.readwhilewriting
-send_benchmark_to_ods readwhilewriting readwhilewriting_in_ram ${STAT_FILE}.readwhilewriting_in_ram
-send_benchmark_to_ods seekrandomwhilewriting seekwhilewriting_in_ram ${STAT_FILE}.seekwhilewriting_in_ram
-send_benchmark_to_ods fillseq fillseq_lots_column_families ${STAT_FILE}.fillseq_lots_column_families
-send_benchmark_to_ods overwrite overwrite_lots_column_families ${STAT_FILE}.overwrite_lots_column_families

build_tools/rocksdb-lego-determinator

@@ -1,740 +0,0 @@
-#!/bin/bash
-# This script is executed by Sandcastle
-# to determine next steps to run
-
-# Usage:
-# EMAIL=<email> ONCALL=<email> TRIGGER=<trigger> SUBSCRIBER=<email> rocks_ci.py <test-name>
-#
-# Input         Value
-# -------------------------------------------------------------------------
-# EMAIL         Email address to report on trigger conditions
-# ONCAL         Email address to raise a task on failure
-# TRIGGER       Trigger conditions for email. Valid values are fail, warn, all
-# SUBSCRIBER    Email addresss to add as subscriber for task
-#
-
-#
-# Report configuration
-#
-REPORT_EMAIL=
-if [ ! -z $EMAIL ]; then
-  if [ -z $TRIGGER ]; then
-    TRIGGER="fail"
-  fi
-
-  REPORT_EMAIL="
-  {
-      'type':'email',
-      'triggers': [ '$TRIGGER' ],
-      'emails':['$EMAIL']
-  },"
-fi
-
-CREATE_TASK=
-if [ ! -z $ONCALL ]; then
-  CREATE_TASK="
-  {
-      'type':'task',
-      'triggers':[ 'fail' ],
-      'priority':0,
-      'subscribers':[ '$SUBSCRIBER' ],
-      'tags':[ 'rocksdb', 'ci' ],
-  },"
-fi
-
-REPORT=
-if [[ ! -z $REPORT_EMAIL || ! -z $CREATE_TASK ]]; then
-  REPORT="'report': [
-    $REPORT_EMAIL
-    $CREATE_TASK
-  ]"
-fi
-
-#
-# Helper variables
-#
-CLEANUP_ENV="
-{
-    'name':'Cleanup environment',
-    'shell':'rm -rf /dev/shm/rocksdb && mkdir /dev/shm/rocksdb && make clean',
-    'user':'root'
-}"
-
-DEBUG="OPT=-g"
-SHM="TEST_TMPDIR=/dev/shm/rocksdb"
-GCC_481="ROCKSDB_FBCODE_BUILD_WITH_481=1"
-ASAN="COMPILE_WITH_ASAN=1"
-CLANG="USE_CLANG=1"
-LITE="OPT=\"-DROCKSDB_LITE -g\""
-TSAN="COMPILE_WITH_TSAN=1"
-UBSAN="COMPILE_WITH_UBSAN=1"
-DISABLE_JEMALLOC="DISABLE_JEMALLOC=1"
-HTTP_PROXY="https_proxy=http://fwdproxy.29.prn1:8080 http_proxy=http://fwdproxy.29.prn1:8080 ftp_proxy=http://fwdproxy.29.prn1:8080"
-SETUP_JAVA_ENV="export $HTTP_PROXY; export JAVA_HOME=/usr/local/jdk-7u10-64/; export PATH=\$PATH:\$JAVA_HOME/bin"
-PARSER="'parser':'python build_tools/error_filter.py $1'"
-
-ARTIFACTS=" 'artifacts': [
-    {
-        'name':'database',
-        'paths':[ '/dev/shm/rocksdb' ],
-    }
-]"
-
-#
-# A mechanism to disable tests temporarily
-#
-DISABLE_COMMANDS="[
-    {
-        'name':'Disable test',
-        'oncall':'$ONCALL',
-        'steps': [
-            {
-              'name':'Job disabled. Please contact test owner',
-              'shell':'exit 1',
-              'user':'root'
-            },
-        ],
-    }
-]"
-
-#
-# RocksDB unit test in parallel
-# Currently we always have noise in our parallel runs. This job is to help
-# manage the noise
-#
-PARALLEL_UNIT_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Parallel Unit Test',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and test RocksDB debug version',
-                'shell':'$DEBUG make -j$(nproc) all && $SHM make check > /dev/null 2>&1 || cat t/log-*',
-                'user':'root',
-                $PARSER
-            },
-            $CLEANUP_ENV,
-            {
-                'name':'Build and test RocksDB debug version under gcc-4.8.1',
-                'shell':'$GCC_481 $DEBUG make -j$(nproc) all && $SHM make check > /dev/null 2>&1 || cat t/log-*',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB unit test
-#
-UNIT_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Unit Test',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and test RocksDB debug version',
-                'shell':'$SHM $DEBUG make J=1 check',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB unit test on gcc-4.8.1
-#
-UNIT_TEST_COMMANDS_481="[
-    {
-        'name':'Rocksdb Unit Test on GCC 4.8.1',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and test RocksDB debug version',
-                'shell':'$SHM $GCC_481 $DEBUG make J=1 check',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB unit test with CLANG
-#
-CLANG_UNIT_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Unit Test',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and test RocksDB debug',
-                'shell':'$CLANG $SHM $DEBUG make J=1 check',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB analyze
-#
-CLANG_ANALYZE_COMMANDS="[
-    {
-        'name':'Rocksdb analyze',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'RocksDB build and analyze',
-                'shell':'$CLANG $SHM $DEBUG make J=1 analyze',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB code coverage
-#
-CODE_COV_COMMANDS="[
-    {
-        'name':'Rocksdb Unit Test Code Coverage',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build, test and collect code coverage info',
-                'shell':'$SHM $DEBUG make J=1 coverage',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB unity
-#
-UNITY_COMMANDS="[
-    {
-        'name':'Rocksdb Unity',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build, test unity test',
-                'shell':'$SHM $DEBUG V=1 make J=1 unity_test',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# Build RocksDB lite
-#
-LITE_BUILD_COMMANDS="[
-    {
-        'name':'Rocksdb Lite build',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build RocksDB debug version',
-                'shell':'$LITE make J=1 static_lib',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB lite tests
-#
-LITE_UNIT_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Lite Unit Test',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build RocksDB debug version',
-                'shell':'$SHM $LITE make J=1 check',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB stress/crash test
-#
-STRESS_CRASH_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Stress/Crash Test',
-        'oncall':'$ONCALL',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug stress tests',
-                'shell':'$SHM $DEBUG make J=1 db_stress',
-                'user':'root',
-                $PARSER
-            },
-            {
-                'name':'Build and run RocksDB debug crash tests',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG make J=1 crash_test',
-                'user':'root',
-                $PARSER
-            }
-        ],
-        $ARTIFACTS,
-        $REPORT
-    }
-]"
-
-# RocksDB write stress test.
-# We run on disk device on purpose (i.e. no $SHM)
-# because we want to add some randomness to fsync commands
-WRITE_STRESS_COMMANDS="[
-    {
-        'name':'Rocksdb Write Stress Test',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB write stress tests',
-                'shell':'make write_stress && python tools/write_stress_runner.py --runtime_sec=3600 --db=/tmp/rocksdb_write_stress',
-                'user':'root',
-                $PARSER
-            }
-        ],
-        'artifacts': [{'name': 'database', 'paths': ['/tmp/rocksdb_write_stress']}],
-        $REPORT
-    }
-]"
-
-
-#
-# RocksDB test under address sanitizer
-#
-ASAN_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Unit Test under ASAN',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Test RocksDB debug under ASAN',
-                'shell':'set -o pipefail && $SHM $ASAN $DEBUG make J=1 asan_check |& /usr/facebook/ops/scripts/asan_symbolize.py -d',
-                'user':'root',
-                $PARSER
-            }
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash testing under address sanitizer
-#
-ASAN_CRASH_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb crash test under ASAN',
-        'oncall':'$ONCALL',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug asan_crash_test',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG make J=1 asan_crash_test',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB test under undefined behavior sanitizer
-#
-UBSAN_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Unit Test under UBSAN',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Test RocksDB debug under UBSAN',
-                'shell':'set -o pipefail && $SHM $UBSAN $DEBUG make J=1 ubsan_check',
-                'user':'root',
-                $PARSER
-            }
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash testing under udnefined behavior sanitizer
-#
-UBSAN_CRASH_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb crash test under UBSAN',
-        'oncall':'$ONCALL',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build and run RocksDB debug ubsan_crash_test',
-                'timeout': 86400,
-                'shell':'$SHM $DEBUG make J=1 ubsan_crash_test',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB unit test under valgrind
-#
-VALGRIND_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Unit Test under valgrind',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Run RocksDB debug unit tests',
-                'shell':'$DISABLE_JEMALLOC $SHM $DEBUG make valgrind_check',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB test under TSAN
-#
-TSAN_UNIT_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Unit Test under TSAN',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Run RocksDB debug unit test',
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN make J=1 check',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB crash test under TSAN
-#
-TSAN_CRASH_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Crash Test under TSAN',
-        'oncall':'$ONCALL',
-        'timeout': 86400,
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Compile and run',
-                'timeout': 86400,
-                'shell':'set -o pipefail && $SHM $DEBUG $TSAN make J=1 crash_test',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-TSAN_CRASH_TEST_COMMANDS=$DISABLE_COMMANDS
-
-#
-# RocksDB format compatible
-#
-
-run_format_compatible()
-{
-  export TEST_TMPDIR=/dev/shm/rocksdb
-  rm -rf /dev/shm/rocksdb
-  mkdir /dev/shm/rocksdb
-
-  echo '
-  if [ -e "build_tools/build_detect_platform" ]
-  then
-    sed "s/tcmalloc/nothingnothingnothing/g" build_tools/build_detect_platform > $TEST_TMPDIR/temp_build_file
-    rm -rf build_tools/build_detect_platform
-    cp $TEST_TMPDIR/temp_build_file build_tools/build_detect_platform
-    chmod +x build_tools/build_detect_platform
-  fi
-
-  if [ -e "build_detect_platform" ]
-  then
-    sed "s/tcmalloc/nothingnothingnothing/g" build_detect_platform > $TEST_TMPDIR/temp_build_file
-    rm -rf build_detect_platform
-    cp $TEST_TMPDIR/temp_build_file build_detect_platform
-    chmod +x build_detect_platform
-  fi
-
-  make ldb -j32
-
-  if [ -e "build_detect_platform" ]
-  then
-    git checkout -- build_detect_platform
-  fi
-
-  if [ -e "build_tools/build_detect_platform" ]
-  then
-    git checkout -- build_tools/build_detect_platform
-  fi
-  ' > temp_build_ldb.sh
-
-  sed "s/make ldb -j32/source temp_build_ldb.sh/g" tools/check_format_compatible.sh > tools/temp_check_format_compatible.sh
-  chmod +x tools/temp_check_format_compatible.sh
-  tools/temp_check_format_compatible.sh
-}
-
-FORMAT_COMPATIBLE_COMMANDS="[
-    {
-        'name':'Rocksdb Format Compatible tests',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Run RocksDB debug unit test',
-                'shell':'build_tools/rocksdb-lego-determinator run_format_compatible',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB no compression
-#
-run_no_compression()
-{
-  export TEST_TMPDIR=/dev/shm/rocksdb
-  rm -rf /dev/shm/rocksdb
-  mkdir /dev/shm/rocksdb
-  make clean
-  cat build_tools/fbcode_config.sh | grep -iv dzlib | grep -iv dlz4 | grep -iv dsnappy | grep -iv dbzip2 > .tmp.fbcode_config.sh
-  mv .tmp.fbcode_config.sh build_tools/fbcode_config.sh
-  cat Makefile | grep -v tools/ldb_test.py > .tmp.Makefile
-  mv .tmp.Makefile Makefile
-  make $DEBUG J=1 check
-}
-
-NO_COMPRESSION_COMMANDS="[
-    {
-        'name':'Rocksdb No Compression tests',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Run RocksDB debug unit test',
-                'shell':'build_tools/rocksdb-lego-determinator run_no_compression',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB regression
-#
-run_regression()
-{
-  time -v bash -vx ./build_tools/regression_build_test.sh $(mktemp -d  $WORKSPACE/leveldb.XXXX) $(mktemp leveldb_test_stats.XXXX)
-
-  # ======= report size to ODS ========
-
-  # parameters: $1 -- key, $2 -- value
-  function send_size_to_ods {
-    curl -s "https://www.intern.facebook.com/intern/agent/ods_set.php?entity=rocksdb_build&key=rocksdb.build_size.$1&value=$2" \
-      --connect-timeout 60
-  }
-
-  # === normal build ===
-  make clean
-  make -j$(nproc) static_lib
-  send_size_to_ods static_lib $(stat --printf="%s" librocksdb.a)
-  strip librocksdb.a
-  send_size_to_ods static_lib_stripped $(stat --printf="%s" librocksdb.a)
-
-  make -j$(nproc) shared_lib
-  send_size_to_ods shared_lib $(stat --printf="%s" `readlink -f librocksdb.so`)
-  strip `readlink -f librocksdb.so`
-  send_size_to_ods shared_lib_stripped $(stat --printf="%s" `readlink -f librocksdb.so`)
-
-  # === lite build ===
-  make clean
-  OPT=-DROCKSDB_LITE make -j$(nproc) static_lib
-  send_size_to_ods static_lib_lite $(stat --printf="%s" librocksdb.a)
-  strip librocksdb.a
-  send_size_to_ods static_lib_lite_stripped $(stat --printf="%s" librocksdb.a)
-
-  OPT=-DROCKSDB_LITE make -j$(nproc) shared_lib
-  send_size_to_ods shared_lib_lite $(stat --printf="%s" `readlink -f librocksdb.so`)
-  strip `readlink -f librocksdb.so`
-  send_size_to_ods shared_lib_lite_stripped $(stat --printf="%s" `readlink -f librocksdb.so`)
-}
-
-REGRESSION_COMMANDS="[
-    {
-        'name':'Rocksdb regression commands',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Make and run script',
-                'shell':'build_tools/rocksdb-lego-determinator run_regression',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-#
-# RocksDB Java build
-#
-JAVA_BUILD_TEST_COMMANDS="[
-    {
-        'name':'Rocksdb Java Build',
-        'oncall':'$ONCALL',
-        'steps': [
-            $CLEANUP_ENV,
-            {
-                'name':'Build RocksDB for Java',
-                'shell':'$SETUP_JAVA_ENV; $SHM make rocksdbjava',
-                'user':'root',
-                $PARSER
-            },
-        ],
-        $REPORT
-    }
-]"
-
-
-case $1 in
-  punit)
-    echo $PARALLEL_UNIT_TEST_COMMANDS
-    ;;
-  unit)
-    echo $UNIT_TEST_COMMANDS
-    ;;
-  unit_481)
-    echo $UNIT_TEST_COMMANDS_481
-    ;;
-  clang_unit)
-    echo $CLANG_UNIT_TEST_COMMANDS
-    ;;
-  clang_analyze)
-    echo $CLANG_ANALYZE_COMMANDS
-    ;;
-  code_cov)
-    echo $CODE_COV_COMMANDS
-    ;;
-  unity)
-    echo $UNITY_COMMANDS
-    ;;
-  lite)
-    echo $LITE_BUILD_COMMANDS
-    ;;
-  lite_test)
-    echo $LITE_UNIT_TEST_COMMANDS
-    ;;
-  stress_crash)
-    echo $STRESS_CRASH_TEST_COMMANDS
-    ;;
-  write_stress)
-    echo $WRITE_STRESS_COMMANDS
-    ;;
-  asan)
-    echo $ASAN_TEST_COMMANDS
-    ;;
-  asan_crash)
-    echo $ASAN_CRASH_TEST_COMMANDS
-    ;;
-  ubsan)
-    echo $UBSAN_TEST_COMMANDS
-    ;;
-  ubsan_crash)
-    echo $UBSAN_CRASH_TEST_COMMANDS
-    ;;
-  valgrind)
-    echo $VALGRIND_TEST_COMMANDS
-    ;;
-  tsan)
-    echo $TSAN_UNIT_TEST_COMMANDS
-    ;;
-  tsan_crash)
-    echo $TSAN_CRASH_TEST_COMMANDS
-    ;;
-  format_compatible)
-    echo $FORMAT_COMPATIBLE_COMMANDS
-    ;;
-  run_format_compatible)
-    run_format_compatible
-    ;;
-  no_compression)
-    echo $NO_COMPRESSION_COMMANDS
-    ;;
-  run_no_compression)
-    run_no_compression
-    ;;
-  regression)
-    echo $REGRESSION_COMMANDS
-    ;;
-  run_regression)
-    run_regression
-    ;;
-  java_build)
-    echo $JAVA_BUILD_TEST_COMMANDS
-    ;;
-  *)
-    echo "Invalid determinator command"
-    ;;
-esac

build_tools/run_ci_db_test.ps1

@@ -1,330 +0,0 @@
-# This script enables you running RocksDB tests by running
-# All the tests in parallel and utilizing all the cores
-# For db_test the script first lists and parses the tests
-# and then fires them up in parallel using async PS Job functionality
-# Run the script from the enlistment
-Param(
-  [switch]$EnableJE = $false,  # Use je executable
-  [switch]$EnableRerun = $false, # Rerun failed tests sequentially at the end
-  [string]$WorkFolder = "",  # Direct tests to use that folder
-  [int]$Limit = -1, # -1 means run all otherwise limit for testing purposes
-  [string]$Exclude = "", # Expect a comma separated list, no spaces
-  [string]$Run = "db_test",  # Run db_test|db_test2|tests|testname1,testname2...
-   # Number of async tasks that would run concurrently. Recommend a number below 64.
-   # However, CPU utlization really depends on the storage media. Recommend ram based disk.
-   # a value of 1 will run everything serially
-  [int]$Concurrency = 16
-)
-
-# Folders and commands must be fullpath to run assuming
-# the current folder is at the root of the git enlistment
-Get-Date
-
-# If running under Appveyor assume that root
-[string]$Appveyor = $Env:APPVEYOR_BUILD_FOLDER
-if($Appveyor -ne "") {
-    $RootFolder = $Appveyor
-} else {
-    $RootFolder = $PSScriptRoot -replace '\\build_tools', ''
-}
-
-$LogFolder = -Join($RootFolder, "\db_logs\")
-$BinariesFolder = -Join($RootFolder, "\build\Debug\")
-
-if($WorkFolder -eq "") {
-
-    # If TEST_TMPDIR is set use it    
-    [string]$var = $Env:TEST_TMPDIR
-    if($var -eq "") {
-        $WorkFolder = -Join($RootFolder, "\db_tests\")
-        $Env:TEST_TMPDIR = $WorkFolder
-    } else {
-        $WorkFolder = $var
-    }
-} else {
-# Override from a command line
-  $Env:TEST_TMPDIR = $WorkFolder
-}
-
-Write-Output "Root: $RootFolder, WorkFolder: $WorkFolder"
-
-# Use JEMALLOC executables
-if($Run -ceq "db_test" -or
-   $Run -ceq "db_test2" ) {
-
-   $file_name = $Run
-
-   if($EnableJE) {
-     $file_name += "_je"
-   }
-
-   $file_name += ".exe"
-
-   $db_test = -Join ($BinariesFolder, $file_name)
-
-   Write-Output "Binaries: $BinariesFolder db_test: $db_test"
-}
-
-
-#Exclusions that we do not want to run
-$ExcludeTests = New-Object System.Collections.Generic.HashSet[string]
-
-
-if($Exclude -ne "") {
-    Write-Host "Exclude: $Exclude"
-    $l = $Exclude -split ' '
-    ForEach($t in $l) { $ExcludeTests.Add($t) | Out-Null }
-}
-
-# Create test directories in the current folder
-md -Path $WorkFolder -ErrorAction Ignore | Out-Null
-md -Path $LogFolder -ErrorAction Ignore | Out-Null
-
-# Extract the names of its tests by running db_test with --gtest_list_tests.
-# This filter removes the "#"-introduced comments, and expands to
-# fully-qualified names by changing input like this:
-#
-#   DBTest.
-#     Empty
-#     WriteEmptyBatch
-#   MultiThreaded/MultiThreadedDBTest.
-#     MultiThreaded/0  # GetParam() = 0
-#     MultiThreaded/1  # GetParam() = 1
-#
-# into this:
-#
-#   DBTest.Empty
-#   DBTest.WriteEmptyBatch
-#   MultiThreaded/MultiThreadedDBTest.MultiThreaded/0
-#   MultiThreaded/MultiThreadedDBTest.MultiThreaded/1
-# Output into the parameter in a form TestName -> Log File Name
-function Normalize-DbTests($HashTable) {
-
-    $Tests = @()
-# Run db_test to get a list of tests and store it into $a array
-    &$db_test --gtest_list_tests | tee -Variable Tests | Out-Null
-
-    # Current group
-    $Group=""
-
-    ForEach( $l in $Tests) {
-      # Trailing dot is a test group
-      if( $l -match "\.$") {
-        $Group = $l
-      }  else {
-        # Otherwise it is a test name, remove leading space
-        $test = $l -replace '^\s+',''
-        # remove trailing comment if any and create a log name
-        $test = $test -replace '\s+\#.*',''
-        $test = "$Group$test"
-
-        if($ExcludeTests.Contains($test)) {
-            continue
-        }
-
-        $test_log = $test -replace '[\./]','_'
-        $test_log += ".log"
-        $log_path = -join ($LogFolder, $test_log)
-
-        # Add to a hashtable
-        $HashTable.Add($test, $log_path);
-      }
-    }
-}
-
-# The function removes trailing .exe siffix if any,
-# creates a name for the log file
-function MakeAndAdd([string]$token, $HashTable) {
-    $test_name = $token -replace '.exe$', ''
-    $log_name =  -join ($test_name, ".log")
-    $log_path = -join ($LogFolder, $log_name)
-    if(!$ExcludeTests.Contains($test_name)) {
-        $HashTable.Add($test_name, $log_path)
-    } else {
-        Write-Warning "Test $test_name is excluded"
-    }
-}
-
-# The function scans build\Debug folder to discover
-# Test executables. It then populates a table with
-# Test executable name -> Log file
-function Discover-TestBinaries([string]$Pattern, $HashTable) {
-
-    $Exclusions = @("db_test*", "db_sanity_test*")
-
-    $p = -join ($BinariesFolder, $pattern)
-
-    Write-Host "Path: $p"
-
-    dir -Path $p -Exclude $Exclusions | ForEach-Object {
-       MakeAndAdd -token ($_.Name) -HashTable $HashTable
-    }
-}
-
-$TestsToRun = [ordered]@{}
-
-if($Run -ceq "db_test" -or
-   $Run -ceq "db_test2") {
-    Normalize-DbTests -HashTable $TestsToRun
-} elseif($Run -ceq "tests") {
-    if($EnableJE) {
-        $pattern = "*_test_je.exe"
-    } else {
-        $pattern = "*_test.exe"
-    }
-    Discover-TestBinaries -Pattern $pattern -HashTable $TestsToRun
-} else {
-
-    $test_list = $Run -split ' '
-
-    ForEach($t in $test_list) {
-       MakeAndAdd -token $t -HashTable $TestsToRun
-    }
-}
-
-$NumTestsToStart = $TestsToRun.Count
-if($Limit -ge 0 -and $NumTestsToStart -gt $Limit) {
-    $NumTestsToStart = $Limit
-}
-
-Write-Host "Attempting to start: $NumTestsToStart tests"
-
-# Invoke a test with a filter and redirect all output
-$InvokeTestCase = {
-    param($exe, $test, $log);
-    &$exe --gtest_filter=$test > $log 2>&1
-}
-
-# Invoke all tests and redirect output
-$InvokeTestAsync = {
-    param($exe, $log)
-    &$exe > $log 2>&1
-}
-
-# Hash that contains tests to rerun if any failed
-# Those tests will be rerun sequentially
-$Rerun = [ordered]@{}
-# Test limiting factor here
-$count = 0
-# Overall status
-[bool]$success = $true;
-
-function RunJobs($TestToLog, [int]$ConcurrencyVal, [bool]$AddForRerun)
-{
-    # Array to wait for any of the running jobs
-    $jobs = @()
-    # Hash JobToLog
-    $JobToLog = @{}
-
-    # Wait for all to finish and get the results
-    while(($JobToLog.Count -gt 0) -or
-          ($TestToLog.Count -gt 0)) {
-
-        # Make sure we have maximum concurrent jobs running if anything
-        # and the $Limit either not set or allows to proceed
-        while(($JobToLog.Count -lt $ConcurrencyVal) -and
-              (($TestToLog.Count -gt 0) -and
-              (($Limit -lt 0) -or ($count -lt $Limit)))) {
-
-
-            # We only need the first key
-            foreach($key in $TestToLog.keys) {
-                $k = $key
-                break
-            }
-
-            Write-Host "Starting $k"
-            $log_path = ($TestToLog.$k)
-
-            if($Run -ceq "db_test" -or
-               $Run -ceq "db_test2") {
-              $job = Start-Job -Name $k -ScriptBlock $InvokeTestCase -ArgumentList @($db_test,$k,$log_path)
-            } else {
-              [string]$Exe =  -Join ($BinariesFolder, $k)
-               $job = Start-Job -Name $k -ScriptBlock $InvokeTestAsync -ArgumentList @($exe,$log_path)
-            }
-
-            $JobToLog.Add($job, $log_path)
-            $TestToLog.Remove($k)
-
-            ++$count
-        }
-
-        if($JobToLog.Count -lt 1) {
-          break
-        }
-
-        $jobs = @()
-        foreach($k in $JobToLog.Keys) { $jobs += $k }
-
-        $completed = Wait-Job -Job $jobs -Any
-        $log = $JobToLog[$completed]
-        $JobToLog.Remove($completed)
-
-        $message = -join @($completed.Name, " State: ", ($completed.State))
-
-        $log_content = @(Get-Content $log)
-
-        if($completed.State -ne "Completed") {
-            $success = $false
-            Write-Warning $message
-            $log_content | Write-Warning
-        } else {
-            # Scan the log. If we find PASSED and no occurrence of FAILED
-            # then it is a success
-            [bool]$pass_found = $false
-            ForEach($l in $log_content) {
-
-                if(($l -match "^\[\s+FAILED") -or
-                   ($l -match "Assertion failed:")) {
-                    $pass_found = $false
-                    break
-                }
-
-                if(($l -match "^\[\s+PASSED") -or
-                   ($l -match " : PASSED$") -or
-                    ($l -match "^PASS$") -or   # Special c_test case
-                    ($l -match "Passed all tests!") ) {
-                    $pass_found = $true
-                }
-            }
-
-            if(!$pass_found) {
-                $success = $false;
-                Write-Warning $message
-                $log_content | Write-Warning
-                if($AddForRerun) {
-                    $Rerun.Add($completed.Name, $log)
-                }
-            } else {
-                Write-Host $message
-            }
-        }
-
-        # Remove cached job info from the system
-        # Should be no output
-        Receive-Job -Job $completed | Out-Null
-    }
-}
-
-RunJobs -TestToLog $TestsToRun -ConcurrencyVal $Concurrency -AddForRerun $EnableRerun
-
-if($Rerun.Count -gt 0) {
-    Write-Host "Rerunning " ($Rerun.Count) " tests sequentially"
-    $success = $true
-    $count = 0
-    RunJobs -TestToLog $Rerun -ConcurrencyVal 1 -AddForRerun $false
-}
-
-Get-Date
-
-
-if(!$success) {
-# This does not succeed killing off jobs quick
-# So we simply exit
-#    Remove-Job -Job $jobs -Force
-# indicate failure using this exit code
-    exit 12345
- }
-
- 

build_tools/update_dependencies.sh

@@ -1,127 +0,0 @@
-#!/bin/sh
-#
-# Update dependencies.sh file with the latest avaliable versions
-
-BASEDIR=$(dirname $0)
-OUTPUT=""
-
-function log_variable()
-{
-  echo "$1=${!1}" >> "$OUTPUT"
-}
-
-
-TP2_LATEST="/mnt/vol/engshare/fbcode/third-party2"
-## $1 => lib name
-## $2 => lib version (if not provided, will try to pick latest)
-## $3 => platform (if not provided, will try to pick latest gcc)
-##
-## get_lib_base will set a variable named ${LIB_NAME}_BASE to the lib location
-function get_lib_base()
-{
-  local lib_name=$1
-  local lib_version=$2
-  local lib_platform=$3
-
-  local result="$TP2_LATEST/$lib_name/"
-  
-  # Lib Version
-  if [ -z "$lib_version" ] || [ "$lib_version" = "LATEST" ]; then
-    # version is not provided, use latest
-    result=`ls -dr1v $result/*/ | head -n1`
-  else
-    result="$result/$lib_version/"
-  fi
-  
-  # Lib Platform
-  if [ -z "$lib_platform" ]; then
-    # platform is not provided, use latest gcc
-    result=`ls -dr1v $result/gcc-*[^fb]/ | head -n1`
-  else
-    result="$result/$lib_platform/"
-  fi
-  
-  result=`ls -1d $result/*/ | head -n1`
-  
-  # lib_name => LIB_NAME_BASE
-  local __res_var=${lib_name^^}"_BASE"
-  __res_var=`echo $__res_var | tr - _`
-  # LIB_NAME_BASE=$result
-  eval $__res_var=`readlink -f $result`
-  
-  log_variable $__res_var
-}
-
-###########################################################
-#                   4.9.x dependencies                    #
-###########################################################
-
-OUTPUT="$BASEDIR/dependencies.sh"
-
-rm -f "$OUTPUT"
-touch "$OUTPUT"
-
-echo "Writing dependencies to $OUTPUT"
-
-# Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/4.9.x/centos6-native/*/`
-CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`
-
-log_variable GCC_BASE
-log_variable CLANG_BASE
-
-# Libraries locations
-get_lib_base libgcc     4.9.x
-get_lib_base glibc      2.20
-get_lib_base snappy     LATEST gcc-4.9-glibc-2.20
-get_lib_base zlib       LATEST
-get_lib_base bzip2      LATEST
-get_lib_base lz4        LATEST
-get_lib_base zstd       LATEST
-get_lib_base gflags     LATEST
-get_lib_base jemalloc   LATEST
-get_lib_base numa       LATEST
-get_lib_base libunwind  LATEST
-
-get_lib_base kernel-headers LATEST 
-get_lib_base binutils   LATEST centos6-native 
-get_lib_base valgrind   3.10.0 gcc-4.9-glibc-2.20
-
-git diff $OUTPUT
-
-###########################################################
-#                   4.8.1 dependencies                    #
-###########################################################
-
-OUTPUT="$BASEDIR/dependencies_4.8.1.sh"
-
-rm -f "$OUTPUT"
-touch "$OUTPUT"
-
-echo "Writing 4.8.1 dependencies to $OUTPUT"
-
-# Compilers locations
-GCC_BASE=`readlink -f $TP2_LATEST/gcc/4.8.1/centos6-native/*/`
-CLANG_BASE=`readlink -f $TP2_LATEST/llvm-fb/stable/centos6-native/*/`
-
-log_variable GCC_BASE
-log_variable CLANG_BASE
-
-# Libraries locations
-get_lib_base libgcc     4.8.1  gcc-4.8.1-glibc-2.17
-get_lib_base glibc      2.17   gcc-4.8.1-glibc-2.17  
-get_lib_base snappy     LATEST gcc-4.8.1-glibc-2.17
-get_lib_base zlib       LATEST gcc-4.8.1-glibc-2.17
-get_lib_base bzip2      LATEST gcc-4.8.1-glibc-2.17
-get_lib_base lz4        LATEST gcc-4.8.1-glibc-2.17
-get_lib_base zstd       LATEST gcc-4.8.1-glibc-2.17
-get_lib_base gflags     LATEST gcc-4.8.1-glibc-2.17
-get_lib_base jemalloc   LATEST gcc-4.8.1-glibc-2.17
-get_lib_base numa       LATEST gcc-4.8.1-glibc-2.17
-get_lib_base libunwind  LATEST gcc-4.8.1-glibc-2.17
-
-get_lib_base kernel-headers LATEST gcc-4.8.1-glibc-2.17 
-get_lib_base binutils   LATEST centos6-native 
-get_lib_base valgrind   3.8.1  gcc-4.8.1-glibc-2.17
-
-git diff $OUTPUT

build_tools/valgrind_test.sh

@@ -0,0 +1,15 @@
+#!/bin/bash
+#A shell script for Jenknis to run valgrind on rocksdb tests
+#Returns 0 on success when there are no failed tests 
+
+VALGRIND_DIR=build_tools/VALGRIND_LOGS
+make clean
+make -j$(nproc) valgrind_check
+NUM_FAILED_TESTS=$((`wc -l $VALGRIND_DIR/valgrind_failed_tests | awk '{print $1}'` - 1))
+if [ $NUM_FAILED_TESTS -lt 1 ]; then
+  echo No tests have valgrind errors
+  exit 0
+else
+  cat $VALGRIND_DIR/valgrind_failed_tests
+  exit 1
+fi

build_tools/version.sh

@@ -1,14 +0,0 @@
-#!/bin/sh
-if [ "$#" = "0" ]; then
-  echo "Usage: $0 major|minor|patch"
-  exit 1
-fi
-if [ "$1" = "major" ]; then
-  cat include/rocksdb/version.h  | grep MAJOR | head -n1 | awk '{print $3}'
-fi
-if [ "$1" = "minor" ]; then
-  cat include/rocksdb/version.h  | grep MINOR | head -n1 | awk '{print $3}'
-fi
-if [ "$1" = "patch" ]; then
-  cat include/rocksdb/version.h  | grep PATCH | head -n1 | awk '{print $3}'
-fi

coverage/coverage_test.sh

@@ -11,8 +11,8 @@ fi
 ROOT=".."
 # Fetch right version of gcov
 if [ -d /mnt/gvfs/third-party -a -z "$CXX" ]; then
-  source $ROOT/build_tools/fbcode_config.sh
-  GCOV=$GCC_BASE/bin/gcov
+  source $ROOT/build_tools/fbcode.gcc471.sh
+  GCOV=$TOOLCHAIN_EXECUTABLES/gcc/gcc-4.7.1/cc6c9dc/bin/gcov
 else
   GCOV=$(which gcov)
 fi

db/auto_roll_logger_test.cc

@@ -1,482 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-#include <string>
-#include <thread>
-#include <vector>
-#include <cmath>
-#include <iostream>
-#include <fstream>
-#include <iterator>
-#include <algorithm>
-#include "db/auto_roll_logger.h"
-#include "port/port.h"
-#include "util/sync_point.h"
-#include "util/testharness.h"
-#include "rocksdb/db.h"
-#include <sys/stat.h>
-#include <errno.h>
-
-namespace rocksdb {
-
-class AutoRollLoggerTest : public testing::Test {
- public:
-  static void InitTestDb() {
-#ifdef OS_WIN
-    // Replace all slashes in the path so windows CompSpec does not
-    // become confused
-    std::string testDir(kTestDir);
-    std::replace_if(testDir.begin(), testDir.end(),
-                    [](char ch) { return ch == '/'; }, '\\');
-    std::string deleteCmd = "if exist " + testDir + " rd /s /q " + testDir;
-#else
-    std::string deleteCmd = "rm -rf " + kTestDir;
-#endif
-    ASSERT_TRUE(system(deleteCmd.c_str()) == 0);
-    Env::Default()->CreateDir(kTestDir);
-  }
-
-  void RollLogFileBySizeTest(AutoRollLogger* logger, size_t log_max_size,
-                             const std::string& log_message);
-  uint64_t RollLogFileByTimeTest(AutoRollLogger* logger, size_t time,
-                                 const std::string& log_message);
-
-  static const std::string kSampleMessage;
-  static const std::string kTestDir;
-  static const std::string kLogFile;
-  static Env* env;
-};
-
-const std::string AutoRollLoggerTest::kSampleMessage(
-    "this is the message to be written to the log file!!");
-const std::string AutoRollLoggerTest::kTestDir(test::TmpDir() + "/db_log_test");
-const std::string AutoRollLoggerTest::kLogFile(test::TmpDir() +
-                                               "/db_log_test/LOG");
-Env* AutoRollLoggerTest::env = Env::Default();
-
-// In this test we only want to Log some simple log message with
-// no format. LogMessage() provides such a simple interface and
-// avoids the [format-security] warning which occurs when you
-// call Log(logger, log_message) directly.
-namespace {
-void LogMessage(Logger* logger, const char* message) {
-  Log(logger, "%s", message);
-}
-
-void LogMessage(const InfoLogLevel log_level, Logger* logger,
-                const char* message) {
-  Log(log_level, logger, "%s", message);
-}
-}  // namespace
-
-namespace {
-void GetFileCreateTime(const std::string& fname, uint64_t* file_ctime) {
-  struct stat s;
-  if (stat(fname.c_str(), &s) != 0) {
-    *file_ctime = (uint64_t)0;
-  }
-  *file_ctime = static_cast<uint64_t>(s.st_ctime);
-}
-}  // namespace
-
-void AutoRollLoggerTest::RollLogFileBySizeTest(AutoRollLogger* logger,
-                                               size_t log_max_size,
-                                               const std::string& log_message) {
-  logger->SetInfoLogLevel(InfoLogLevel::INFO_LEVEL);
-  // measure the size of each message, which is supposed
-  // to be equal or greater than log_message.size()
-  LogMessage(logger, log_message.c_str());
-  size_t message_size = logger->GetLogFileSize();
-  size_t current_log_size = message_size;
-
-  // Test the cases when the log file will not be rolled.
-  while (current_log_size + message_size < log_max_size) {
-    LogMessage(logger, log_message.c_str());
-    current_log_size += message_size;
-    ASSERT_EQ(current_log_size, logger->GetLogFileSize());
-  }
-
-  // Now the log file will be rolled
-  LogMessage(logger, log_message.c_str());
-  // Since rotation is checked before actual logging, we need to
-  // trigger the rotation by logging another message.
-  LogMessage(logger, log_message.c_str());
-
-  ASSERT_TRUE(message_size == logger->GetLogFileSize());
-}
-
-uint64_t AutoRollLoggerTest::RollLogFileByTimeTest(
-    AutoRollLogger* logger, size_t time, const std::string& log_message) {
-  uint64_t expected_create_time;
-  uint64_t actual_create_time;
-  uint64_t total_log_size;
-  EXPECT_OK(env->GetFileSize(kLogFile, &total_log_size));
-  GetFileCreateTime(kLogFile, &expected_create_time);
-  logger->SetCallNowMicrosEveryNRecords(0);
-
-  // -- Write to the log for several times, which is supposed
-  // to be finished before time.
-  for (int i = 0; i < 10; ++i) {
-     LogMessage(logger, log_message.c_str());
-     EXPECT_OK(logger->GetStatus());
-     // Make sure we always write to the same log file (by
-     // checking the create time);
-     GetFileCreateTime(kLogFile, &actual_create_time);
-
-     // Also make sure the log size is increasing.
-     EXPECT_EQ(expected_create_time, actual_create_time);
-     EXPECT_GT(logger->GetLogFileSize(), total_log_size);
-     total_log_size = logger->GetLogFileSize();
-  }
-
-  // -- Make the log file expire
-#ifdef OS_WIN
-  Sleep(static_cast<unsigned int>(time) * 1000);
-#else
-  sleep(static_cast<unsigned int>(time));
-#endif
-  LogMessage(logger, log_message.c_str());
-
-  // At this time, the new log file should be created.
-  GetFileCreateTime(kLogFile, &actual_create_time);
-  EXPECT_GT(actual_create_time, expected_create_time);
-  EXPECT_LT(logger->GetLogFileSize(), total_log_size);
-  expected_create_time = actual_create_time;
-
-  return expected_create_time;
-}
-
-TEST_F(AutoRollLoggerTest, RollLogFileBySize) {
-    InitTestDb();
-    size_t log_max_size = 1024 * 5;
-
-    AutoRollLogger logger(Env::Default(), kTestDir, "", log_max_size, 0);
-
-    RollLogFileBySizeTest(&logger, log_max_size,
-                          kSampleMessage + ":RollLogFileBySize");
-}
-
-TEST_F(AutoRollLoggerTest, RollLogFileByTime) {
-    size_t time = 2;
-    size_t log_size = 1024 * 5;
-
-    InitTestDb();
-    // -- Test the existence of file during the server restart.
-    ASSERT_EQ(Status::NotFound(), env->FileExists(kLogFile));
-    AutoRollLogger logger(Env::Default(), kTestDir, "", log_size, time);
-    ASSERT_OK(env->FileExists(kLogFile));
-
-    RollLogFileByTimeTest(&logger, time, kSampleMessage + ":RollLogFileByTime");
-}
-
-TEST_F(AutoRollLoggerTest, OpenLogFilesMultipleTimesWithOptionLog_max_size) {
-  // If only 'log_max_size' options is specified, then every time
-  // when rocksdb is restarted, a new empty log file will be created.
-  InitTestDb();
-  // WORKAROUND:
-  // avoid complier's complaint of "comparison between signed
-  // and unsigned integer expressions" because literal 0 is
-  // treated as "singed".
-  size_t kZero = 0;
-  size_t log_size = 1024;
-
-  AutoRollLogger* logger = new AutoRollLogger(
-    Env::Default(), kTestDir, "", log_size, 0);
-
-  LogMessage(logger, kSampleMessage.c_str());
-  ASSERT_GT(logger->GetLogFileSize(), kZero);
-  delete logger;
-
-  // reopens the log file and an empty log file will be created.
-  logger = new AutoRollLogger(
-    Env::Default(), kTestDir, "", log_size, 0);
-  ASSERT_EQ(logger->GetLogFileSize(), kZero);
-  delete logger;
-}
-
-TEST_F(AutoRollLoggerTest, CompositeRollByTimeAndSizeLogger) {
-  size_t time = 2, log_max_size = 1024 * 5;
-
-  InitTestDb();
-
-  AutoRollLogger logger(Env::Default(), kTestDir, "", log_max_size, time);
-
-  // Test the ability to roll by size
-  RollLogFileBySizeTest(
-      &logger, log_max_size,
-      kSampleMessage + ":CompositeRollByTimeAndSizeLogger");
-
-  // Test the ability to roll by Time
-  RollLogFileByTimeTest( &logger, time,
-      kSampleMessage + ":CompositeRollByTimeAndSizeLogger");
-}
-
-#ifndef OS_WIN
-// TODO: does not build for Windows because of PosixLogger use below. Need to
-// port
-TEST_F(AutoRollLoggerTest, CreateLoggerFromOptions) {
-  DBOptions options;
-  shared_ptr<Logger> logger;
-
-  // Normal logger
-  ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
-  ASSERT_TRUE(dynamic_cast<PosixLogger*>(logger.get()));
-
-  // Only roll by size
-  InitTestDb();
-  options.max_log_file_size = 1024;
-  ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
-  AutoRollLogger* auto_roll_logger =
-    dynamic_cast<AutoRollLogger*>(logger.get());
-  ASSERT_TRUE(auto_roll_logger);
-  RollLogFileBySizeTest(
-      auto_roll_logger, options.max_log_file_size,
-      kSampleMessage + ":CreateLoggerFromOptions - size");
-
-  // Only roll by Time
-  InitTestDb();
-  options.max_log_file_size = 0;
-  options.log_file_time_to_roll = 2;
-  ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
-  auto_roll_logger =
-    dynamic_cast<AutoRollLogger*>(logger.get());
-  RollLogFileByTimeTest(
-      auto_roll_logger, options.log_file_time_to_roll,
-      kSampleMessage + ":CreateLoggerFromOptions - time");
-
-  // roll by both Time and size
-  InitTestDb();
-  options.max_log_file_size = 1024 * 5;
-  options.log_file_time_to_roll = 2;
-  ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
-  auto_roll_logger =
-    dynamic_cast<AutoRollLogger*>(logger.get());
-  RollLogFileBySizeTest(
-      auto_roll_logger, options.max_log_file_size,
-      kSampleMessage + ":CreateLoggerFromOptions - both");
-  RollLogFileByTimeTest(
-      auto_roll_logger, options.log_file_time_to_roll,
-      kSampleMessage + ":CreateLoggerFromOptions - both");
-}
-
-TEST_F(AutoRollLoggerTest, LogFlushWhileRolling) {
-  DBOptions options;
-  shared_ptr<Logger> logger;
-
-  InitTestDb();
-  options.max_log_file_size = 1024 * 5;
-  ASSERT_OK(CreateLoggerFromOptions(kTestDir, options, &logger));
-  AutoRollLogger* auto_roll_logger =
-      dynamic_cast<AutoRollLogger*>(logger.get());
-  ASSERT_TRUE(auto_roll_logger);
-  std::thread flush_thread;
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency({
-      // Need to pin the old logger before beginning the roll, as rolling grabs
-      // the mutex, which would prevent us from accessing the old logger.
-      {"AutoRollLogger::Flush:PinnedLogger",
-       "AutoRollLoggerTest::LogFlushWhileRolling:PreRollAndPostThreadInit"},
-      // Need to finish the flush thread init before this callback because the
-      // callback accesses flush_thread.get_id() in order to apply certain sync
-      // points only to the flush thread.
-      {"AutoRollLoggerTest::LogFlushWhileRolling:PreRollAndPostThreadInit",
-       "AutoRollLoggerTest::LogFlushWhileRolling:FlushCallbackBegin"},
-      // Need to reset logger at this point in Flush() to exercise a race
-      // condition case, which is executing the flush with the pinned (old)
-      // logger after the roll has cut over to a new logger.
-      {"AutoRollLoggerTest::LogFlushWhileRolling:FlushCallback1",
-       "AutoRollLogger::ResetLogger:BeforeNewLogger"},
-      {"AutoRollLogger::ResetLogger:AfterNewLogger",
-       "AutoRollLoggerTest::LogFlushWhileRolling:FlushCallback2"},
-  });
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "PosixLogger::Flush:BeginCallback", [&](void* arg) {
-        TEST_SYNC_POINT(
-            "AutoRollLoggerTest::LogFlushWhileRolling:FlushCallbackBegin");
-        if (std::this_thread::get_id() == flush_thread.get_id()) {
-          TEST_SYNC_POINT(
-              "AutoRollLoggerTest::LogFlushWhileRolling:FlushCallback1");
-          TEST_SYNC_POINT(
-              "AutoRollLoggerTest::LogFlushWhileRolling:FlushCallback2");
-        }
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  flush_thread = std::thread([&]() { auto_roll_logger->Flush(); });
-  TEST_SYNC_POINT(
-      "AutoRollLoggerTest::LogFlushWhileRolling:PreRollAndPostThreadInit");
-  RollLogFileBySizeTest(auto_roll_logger, options.max_log_file_size,
-                        kSampleMessage + ":LogFlushWhileRolling");
-  flush_thread.join();
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-}
-
-#endif  // OS_WIN
-
-TEST_F(AutoRollLoggerTest, InfoLogLevel) {
-  InitTestDb();
-
-  size_t log_size = 8192;
-  size_t log_lines = 0;
-  // an extra-scope to force the AutoRollLogger to flush the log file when it
-  // becomes out of scope.
-  {
-    AutoRollLogger logger(Env::Default(), kTestDir, "", log_size, 0);
-    for (int log_level = InfoLogLevel::HEADER_LEVEL;
-         log_level >= InfoLogLevel::DEBUG_LEVEL; log_level--) {
-      logger.SetInfoLogLevel((InfoLogLevel)log_level);
-      for (int log_type = InfoLogLevel::DEBUG_LEVEL;
-           log_type <= InfoLogLevel::HEADER_LEVEL; log_type++) {
-        // log messages with log level smaller than log_level will not be
-        // logged.
-        LogMessage((InfoLogLevel)log_type, &logger, kSampleMessage.c_str());
-      }
-      log_lines += InfoLogLevel::HEADER_LEVEL - log_level + 1;
-    }
-    for (int log_level = InfoLogLevel::HEADER_LEVEL;
-         log_level >= InfoLogLevel::DEBUG_LEVEL; log_level--) {
-      logger.SetInfoLogLevel((InfoLogLevel)log_level);
-
-      // again, messages with level smaller than log_level will not be logged.
-      Log(InfoLogLevel::HEADER_LEVEL, &logger, "%s", kSampleMessage.c_str());
-      Debug(&logger, "%s", kSampleMessage.c_str());
-      Info(&logger, "%s", kSampleMessage.c_str());
-      Warn(&logger, "%s", kSampleMessage.c_str());
-      Error(&logger, "%s", kSampleMessage.c_str());
-      Fatal(&logger, "%s", kSampleMessage.c_str());
-      log_lines += InfoLogLevel::HEADER_LEVEL - log_level + 1;
-    }
-  }
-  std::ifstream inFile(AutoRollLoggerTest::kLogFile.c_str());
-  size_t lines = std::count(std::istreambuf_iterator<char>(inFile),
-                         std::istreambuf_iterator<char>(), '\n');
-  ASSERT_EQ(log_lines, lines);
-  inFile.close();
-}
-
-// Test the logger Header function for roll over logs
-// We expect the new logs creates as roll over to carry the headers specified
-static std::vector<std::string> GetOldFileNames(const std::string& path) {
-  std::vector<std::string> ret;
-
-  const std::string dirname = path.substr(/*start=*/0, path.find_last_of("/"));
-  const std::string fname = path.substr(path.find_last_of("/") + 1);
-
-  std::vector<std::string> children;
-  Env::Default()->GetChildren(dirname, &children);
-
-  // We know that the old log files are named [path]<something>
-  // Return all entities that match the pattern
-  for (auto& child : children) {
-    if (fname != child && child.find(fname) == 0) {
-      ret.push_back(dirname + "/" + child);
-    }
-  }
-
-  return ret;
-}
-
-// Return the number of lines where a given pattern was found in the file
-static size_t GetLinesCount(const std::string& fname,
-                            const std::string& pattern) {
-  std::stringstream ssbuf;
-  std::string line;
-  size_t count = 0;
-
-  std::ifstream inFile(fname.c_str());
-  ssbuf << inFile.rdbuf();
-
-  while (getline(ssbuf, line)) {
-    if (line.find(pattern) != std::string::npos) {
-      count++;
-    }
-  }
-
-  return count;
-}
-
-TEST_F(AutoRollLoggerTest, LogHeaderTest) {
-  static const size_t MAX_HEADERS = 10;
-  static const size_t LOG_MAX_SIZE = 1024 * 5;
-  static const std::string HEADER_STR = "Log header line";
-
-  // test_num == 0 -> standard call to Header()
-  // test_num == 1 -> call to Log() with InfoLogLevel::HEADER_LEVEL
-  for (int test_num = 0; test_num < 2; test_num++) {
-
-    InitTestDb();
-
-    AutoRollLogger logger(Env::Default(), kTestDir, /*db_log_dir=*/ "",
-                          LOG_MAX_SIZE, /*log_file_time_to_roll=*/ 0);
-
-    if (test_num == 0) {
-      // Log some headers explicitly using Header()
-      for (size_t i = 0; i < MAX_HEADERS; i++) {
-        Header(&logger, "%s %d", HEADER_STR.c_str(), i);
-      }
-    } else if (test_num == 1) {
-      // HEADER_LEVEL should make this behave like calling Header()
-      for (size_t i = 0; i < MAX_HEADERS; i++) {
-        Log(InfoLogLevel::HEADER_LEVEL, &logger, "%s %d",
-            HEADER_STR.c_str(), i);
-      }
-    }
-
-    const std::string newfname = logger.TEST_log_fname();
-
-    // Log enough data to cause a roll over
-    int i = 0;
-    for (size_t iter = 0; iter < 2; iter++) {
-      while (logger.GetLogFileSize() < LOG_MAX_SIZE) {
-        Info(&logger, (kSampleMessage + ":LogHeaderTest line %d").c_str(), i);
-        ++i;
-      }
-
-      Info(&logger, "Rollover");
-    }
-
-    // Flush the log for the latest file
-    LogFlush(&logger);
-
-    const auto oldfiles = GetOldFileNames(newfname);
-
-    ASSERT_EQ(oldfiles.size(), (size_t) 2);
-
-    for (auto& oldfname : oldfiles) {
-      // verify that the files rolled over
-      ASSERT_NE(oldfname, newfname);
-      // verify that the old log contains all the header logs
-      ASSERT_EQ(GetLinesCount(oldfname, HEADER_STR), MAX_HEADERS);
-    }
-  }
-}
-
-TEST_F(AutoRollLoggerTest, LogFileExistence) {
-  rocksdb::DB* db;
-  rocksdb::Options options;
-#ifdef OS_WIN
-  // Replace all slashes in the path so windows CompSpec does not
-  // become confused
-  std::string testDir(kTestDir);
-  std::replace_if(testDir.begin(), testDir.end(),
-    [](char ch) { return ch == '/'; }, '\\');
-  std::string deleteCmd = "if exist " + testDir + " rd /s /q " + testDir;
-#else
-  std::string deleteCmd = "rm -rf " + kTestDir;
-#endif
-  ASSERT_EQ(system(deleteCmd.c_str()), 0);
-  options.max_log_file_size = 100 * 1024 * 1024;
-  options.create_if_missing = true;
-  ASSERT_OK(rocksdb::DB::Open(options, kTestDir, &db));
-  ASSERT_OK(env->FileExists(kLogFile));
-  delete db;
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/builder.cc

@@ -1,4 +1,4 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -9,15 +9,8 @@
 
 #include "db/builder.h"
 
-#include <algorithm>
-#include <deque>
-#include <vector>
-
-#include "db/compaction_iterator.h"
 #include "db/dbformat.h"
-#include "db/event_helpers.h"
 #include "db/filename.h"
-#include "db/internal_stats.h"
 #include "db/merge_helper.h"
 #include "db/table_cache.h"
 #include "db/version_edit.h"
@@ -27,159 +20,191 @@
 #include "rocksdb/options.h"
 #include "rocksdb/table.h"
 #include "table/block_based_table_builder.h"
-#include "table/internal_iterator.h"
-#include "util/file_reader_writer.h"
-#include "util/iostats_context_imp.h"
 #include "util/stop_watch.h"
-#include "util/thread_status_util.h"
 
 namespace rocksdb {
 
 class TableFactory;
 
-TableBuilder* NewTableBuilder(
-    const ImmutableCFOptions& ioptions,
-    const InternalKeyComparator& internal_comparator,
-    const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
-        int_tbl_prop_collector_factories,
-    uint32_t column_family_id, const std::string& column_family_name,
-    WritableFileWriter* file, const CompressionType compression_type,
-    const CompressionOptions& compression_opts,
-    const std::string* compression_dict, const bool skip_filters) {
-  assert((column_family_id ==
-          TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
-         column_family_name.empty());
-  return ioptions.table_factory->NewTableBuilder(
-      TableBuilderOptions(ioptions, internal_comparator,
-                          int_tbl_prop_collector_factories, compression_type,
-                          compression_opts, compression_dict, skip_filters,
-                          column_family_name),
-      column_family_id, file);
+TableBuilder* NewTableBuilder(const Options& options,
+                              const InternalKeyComparator& internal_comparator,
+                              WritableFile* file,
+                              CompressionType compression_type) {
+  return options.table_factory->NewTableBuilder(options, internal_comparator,
+                                                file, compression_type);
 }
 
-Status BuildTable(
-    const std::string& dbname, Env* env, const ImmutableCFOptions& ioptions,
-    const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
-    TableCache* table_cache, InternalIterator* iter, FileMetaData* meta,
-    const InternalKeyComparator& internal_comparator,
-    const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
-        int_tbl_prop_collector_factories,
-    uint32_t column_family_id, const std::string& column_family_name,
-    std::vector<SequenceNumber> snapshots,
-    SequenceNumber earliest_write_conflict_snapshot,
-    const CompressionType compression,
-    const CompressionOptions& compression_opts, bool paranoid_file_checks,
-    InternalStats* internal_stats, TableFileCreationReason reason,
-    EventLogger* event_logger, int job_id, const Env::IOPriority io_priority,
-    TableProperties* table_properties, int level) {
-  assert((column_family_id ==
-          TablePropertiesCollectorFactory::Context::kUnknownColumnFamily) ==
-         column_family_name.empty());
-  // Reports the IOStats for flush for every following bytes.
-  const size_t kReportFlushIOStatsEvery = 1048576;
+Status BuildTable(const std::string& dbname, Env* env, const Options& options,
+                  const EnvOptions& soptions, TableCache* table_cache,
+                  Iterator* iter, FileMetaData* meta,
+                  const InternalKeyComparator& internal_comparator,
+                  const SequenceNumber newest_snapshot,
+                  const SequenceNumber earliest_seqno_in_memtable,
+                  const CompressionType compression) {
   Status s;
-  meta->fd.file_size = 0;
+  meta->file_size = 0;
+  meta->smallest_seqno = meta->largest_seqno = 0;
   iter->SeekToFirst();
 
-  std::string fname = TableFileName(ioptions.db_paths, meta->fd.GetNumber(),
-                                    meta->fd.GetPathId());
-#ifndef ROCKSDB_LITE
-  EventHelpers::NotifyTableFileCreationStarted(
-      ioptions.listeners, dbname, column_family_name, fname, job_id, reason);
-#endif  // !ROCKSDB_LITE
-  TableProperties tp;
+  // If the sequence number of the smallest entry in the memtable is
+  // smaller than the most recent snapshot, then we do not trigger
+  // removal of duplicate/deleted keys as part of this builder.
+  bool purge = options.purge_redundant_kvs_while_flush;
+  if (earliest_seqno_in_memtable <= newest_snapshot) {
+    purge = false;
+  }
 
+  std::string fname = TableFileName(dbname, meta->number);
   if (iter->Valid()) {
-    TableBuilder* builder;
-    unique_ptr<WritableFileWriter> file_writer;
-    {
-      unique_ptr<WritableFile> file;
-      s = NewWritableFile(env, fname, &file, env_options);
-      if (!s.ok()) {
-        EventHelpers::LogAndNotifyTableFileCreationFinished(
-            event_logger, ioptions.listeners, dbname, column_family_name, fname,
-            job_id, meta->fd, tp, reason, s);
-        return s;
-      }
-      file->SetIOPriority(io_priority);
-
-      file_writer.reset(new WritableFileWriter(std::move(file), env_options));
-
-      builder = NewTableBuilder(
-          ioptions, internal_comparator, int_tbl_prop_collector_factories,
-          column_family_id, column_family_name, file_writer.get(), compression,
-          compression_opts);
+    unique_ptr<WritableFile> file;
+    s = env->NewWritableFile(fname, &file, soptions);
+    if (!s.ok()) {
+      return s;
     }
 
-    MergeHelper merge(env, internal_comparator.user_comparator(),
-                      ioptions.merge_operator, nullptr, ioptions.info_log,
-                      mutable_cf_options.min_partial_merge_operands,
-                      true /* internal key corruption is not ok */,
-                      snapshots.empty() ? 0 : snapshots.back());
+    TableBuilder* builder =
+        NewTableBuilder(options, internal_comparator, file.get(), compression);
 
-    CompactionIterator c_iter(iter, internal_comparator.user_comparator(),
-                              &merge, kMaxSequenceNumber, &snapshots,
-                              earliest_write_conflict_snapshot, env,
-                              true /* internal key corruption is not ok */);
-    c_iter.SeekToFirst();
-    for (; c_iter.Valid(); c_iter.Next()) {
-      const Slice& key = c_iter.key();
-      const Slice& value = c_iter.value();
-      builder->Add(key, value);
-      meta->UpdateBoundaries(key, c_iter.ikey().sequence);
+    // the first key is the smallest key
+    Slice key = iter->key();
+    meta->smallest.DecodeFrom(key);
+    meta->smallest_seqno = GetInternalKeySeqno(key);
+    meta->largest_seqno = meta->smallest_seqno;
 
-      // TODO(noetzli): Update stats after flush, too.
-      if (io_priority == Env::IO_HIGH &&
-          IOSTATS(bytes_written) >= kReportFlushIOStatsEvery) {
-        ThreadStatusUtil::SetThreadOperationProperty(
-            ThreadStatus::FLUSH_BYTES_WRITTEN, IOSTATS(bytes_written));
+    MergeHelper merge(internal_comparator.user_comparator(),
+                      options.merge_operator.get(), options.info_log.get(),
+                      options.min_partial_merge_operands,
+                      true /* internal key corruption is not ok */);
+
+    if (purge) {
+      // Ugly walkaround to avoid compiler error for release build
+      bool ok __attribute__((unused)) = true;
+
+      // Will write to builder if current key != prev key
+      ParsedInternalKey prev_ikey;
+      std::string prev_key;
+      bool is_first_key = true;    // Also write if this is the very first key
+
+      while (iter->Valid()) {
+        bool iterator_at_next = false;
+
+        // Get current key
+        ParsedInternalKey this_ikey;
+        Slice key = iter->key();
+        Slice value = iter->value();
+
+        // In-memory key corruption is not ok;
+        // TODO: find a clean way to treat in memory key corruption
+        ok = ParseInternalKey(key, &this_ikey);
+        assert(ok);
+        assert(this_ikey.sequence >= earliest_seqno_in_memtable);
+
+        // If the key is the same as the previous key (and it is not the
+        // first key), then we skip it, since it is an older version.
+        // Otherwise we output the key and mark it as the "new" previous key.
+        if (!is_first_key && !internal_comparator.user_comparator()->Compare(
+                                  prev_ikey.user_key, this_ikey.user_key)) {
+          // seqno within the same key are in decreasing order
+          assert(this_ikey.sequence < prev_ikey.sequence);
+        } else {
+          is_first_key = false;
+
+          if (this_ikey.type == kTypeMerge) {
+            // Handle merge-type keys using the MergeHelper
+            // TODO: pass statistics to MergeUntil
+            merge.MergeUntil(iter, 0 /* don't worry about snapshot */);
+            iterator_at_next = true;
+            if (merge.IsSuccess()) {
+              // Merge completed correctly.
+              // Add the resulting merge key/value and continue to next
+              builder->Add(merge.key(), merge.value());
+              prev_key.assign(merge.key().data(), merge.key().size());
+              ok = ParseInternalKey(Slice(prev_key), &prev_ikey);
+              assert(ok);
+            } else {
+              // Merge did not find a Put/Delete.
+              // Can not compact these merges into a kValueType.
+              // Write them out one-by-one. (Proceed back() to front())
+              const std::deque<std::string>& keys = merge.keys();
+              const std::deque<std::string>& values = merge.values();
+              assert(keys.size() == values.size() && keys.size() >= 1);
+              std::deque<std::string>::const_reverse_iterator key_iter;
+              std::deque<std::string>::const_reverse_iterator value_iter;
+              for (key_iter=keys.rbegin(), value_iter = values.rbegin();
+                   key_iter != keys.rend() && value_iter != values.rend();
+                   ++key_iter, ++value_iter) {
+
+                builder->Add(Slice(*key_iter), Slice(*value_iter));
+              }
+
+              // Sanity check. Both iterators should end at the same time
+              assert(key_iter == keys.rend() && value_iter == values.rend());
+
+              prev_key.assign(keys.front());
+              ok = ParseInternalKey(Slice(prev_key), &prev_ikey);
+              assert(ok);
+            }
+          } else {
+            // Handle Put/Delete-type keys by simply writing them
+            builder->Add(key, value);
+            prev_key.assign(key.data(), key.size());
+            ok = ParseInternalKey(Slice(prev_key), &prev_ikey);
+            assert(ok);
+          }
+        }
+
+        if (!iterator_at_next) iter->Next();
+      }
+
+      // The last key is the largest key
+      meta->largest.DecodeFrom(Slice(prev_key));
+      SequenceNumber seqno = GetInternalKeySeqno(Slice(prev_key));
+      meta->smallest_seqno = std::min(meta->smallest_seqno, seqno);
+      meta->largest_seqno = std::max(meta->largest_seqno, seqno);
+
+    } else {
+      for (; iter->Valid(); iter->Next()) {
+        Slice key = iter->key();
+        meta->largest.DecodeFrom(key);
+        builder->Add(key, iter->value());
+        SequenceNumber seqno = GetInternalKeySeqno(key);
+        meta->smallest_seqno = std::min(meta->smallest_seqno, seqno);
+        meta->largest_seqno = std::max(meta->largest_seqno, seqno);
       }
     }
 
     // Finish and check for builder errors
-    bool empty = builder->NumEntries() == 0;
-    s = c_iter.status();
-    if (!s.ok() || empty) {
-      builder->Abandon();
-    } else {
+    if (s.ok()) {
       s = builder->Finish();
-    }
-
-    if (s.ok() && !empty) {
-      uint64_t file_size = builder->FileSize();
-      meta->fd.file_size = file_size;
-      meta->marked_for_compaction = builder->NeedCompact();
-      assert(meta->fd.GetFileSize() > 0);
-      tp = builder->GetTableProperties();
-      if (table_properties) {
-        *table_properties = tp;
+      if (s.ok()) {
+        meta->file_size = builder->FileSize();
+        assert(meta->file_size > 0);
       }
+    } else {
+      builder->Abandon();
     }
     delete builder;
 
     // Finish and check for file errors
-    if (s.ok() && !empty && !ioptions.disable_data_sync) {
-      StopWatch sw(env, ioptions.statistics, TABLE_SYNC_MICROS);
-      file_writer->Sync(ioptions.use_fsync);
+    if (s.ok() && !options.disableDataSync) {
+      if (options.use_fsync) {
+        StopWatch sw(env, options.statistics.get(), TABLE_SYNC_MICROS);
+        s = file->Fsync();
+      } else {
+        StopWatch sw(env, options.statistics.get(), TABLE_SYNC_MICROS);
+        s = file->Sync();
+      }
     }
-    if (s.ok() && !empty) {
-      s = file_writer->Close();
+    if (s.ok()) {
+      s = file->Close();
     }
 
-    if (s.ok() && !empty) {
+    if (s.ok()) {
       // Verify that the table is usable
-      std::unique_ptr<InternalIterator> it(table_cache->NewIterator(
-          ReadOptions(), env_options, internal_comparator, meta->fd, nullptr,
-          (internal_stats == nullptr) ? nullptr
-                                      : internal_stats->GetFileReadHist(0),
-          false /* for_compaction */, nullptr /* arena */,
-          false /* skip_filter */, level));
+      Iterator* it = table_cache->NewIterator(ReadOptions(), soptions,
+                                              internal_comparator, *meta);
       s = it->status();
-      if (s.ok() && paranoid_file_checks) {
-        for (it->SeekToFirst(); it->Valid(); it->Next()) {
-        }
-        s = it->status();
-      }
+      delete it;
     }
   }
 
@@ -188,15 +213,11 @@ Status BuildTable(
     s = iter->status();
   }
 
-  if (!s.ok() || meta->fd.GetFileSize() == 0) {
+  if (s.ok() && meta->file_size > 0) {
+    // Keep it
+  } else {
     env->DeleteFile(fname);
   }
-
-  // Output to event logger and fire events.
-  EventHelpers::LogAndNotifyTableFileCreationFinished(
-      event_logger, ioptions.listeners, dbname, column_family_name, fname,
-      job_id, meta->fd, tp, reason, s);
-
   return s;
 }
 

db/builder.h

@@ -1,4 +1,4 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -6,20 +6,10 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 #pragma once
-#include <string>
-#include <utility>
-#include <vector>
-#include "db/table_properties_collector.h"
 #include "rocksdb/comparator.h"
-#include "rocksdb/env.h"
-#include "rocksdb/immutable_options.h"
-#include "rocksdb/listener.h"
-#include "rocksdb/options.h"
 #include "rocksdb/status.h"
-#include "rocksdb/table_properties.h"
 #include "rocksdb/types.h"
-#include "util/event_logger.h"
-#include "util/mutable_cf_options.h"
+#include "rocksdb/options.h"
 
 namespace rocksdb {
 
@@ -32,49 +22,24 @@ class Iterator;
 class TableCache;
 class VersionEdit;
 class TableBuilder;
-class WritableFileWriter;
-class InternalStats;
-class InternalIterator;
+class WritableFile;
 
-// @param column_family_name Name of the column family that is also identified
-//    by column_family_id, or empty string if unknown. It must outlive the
-//    TableBuilder returned by this function.
-// @param compression_dict Data for presetting the compression library's
-//    dictionary, or nullptr.
-TableBuilder* NewTableBuilder(
-    const ImmutableCFOptions& options,
-    const InternalKeyComparator& internal_comparator,
-    const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
-        int_tbl_prop_collector_factories,
-    uint32_t column_family_id, const std::string& column_family_name,
-    WritableFileWriter* file, const CompressionType compression_type,
-    const CompressionOptions& compression_opts,
-    const std::string* compression_dict = nullptr,
-    const bool skip_filters = false);
+extern TableBuilder* NewTableBuilder(
+    const Options& options, const InternalKeyComparator& internal_comparator,
+    WritableFile* file, CompressionType compression_type);
 
 // Build a Table file from the contents of *iter.  The generated file
-// will be named according to number specified in meta. On success, the rest of
+// will be named according to meta->number.  On success, the rest of
 // *meta will be filled with metadata about the generated table.
 // If no data is present in *iter, meta->file_size will be set to
 // zero, and no Table file will be produced.
-//
-// @param column_family_name Name of the column family that is also identified
-//    by column_family_id, or empty string if unknown.
-extern Status BuildTable(
-    const std::string& dbname, Env* env, const ImmutableCFOptions& options,
-    const MutableCFOptions& mutable_cf_options, const EnvOptions& env_options,
-    TableCache* table_cache, InternalIterator* iter, FileMetaData* meta,
-    const InternalKeyComparator& internal_comparator,
-    const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
-        int_tbl_prop_collector_factories,
-    uint32_t column_family_id, const std::string& column_family_name,
-    std::vector<SequenceNumber> snapshots,
-    SequenceNumber earliest_write_conflict_snapshot,
-    const CompressionType compression,
-    const CompressionOptions& compression_opts, bool paranoid_file_checks,
-    InternalStats* internal_stats, TableFileCreationReason reason,
-    EventLogger* event_logger = nullptr, int job_id = 0,
-    const Env::IOPriority io_priority = Env::IO_HIGH,
-    TableProperties* table_properties = nullptr, int level = -1);
+extern Status BuildTable(const std::string& dbname, Env* env,
+                         const Options& options, const EnvOptions& soptions,
+                         TableCache* table_cache, Iterator* iter,
+                         FileMetaData* meta,
+                         const InternalKeyComparator& internal_comparator,
+                         const SequenceNumber newest_snapshot,
+                         const SequenceNumber earliest_seqno_in_memtable,
+                         const CompressionType compression);
 
 }  // namespace rocksdb

db/c_test.c

@@ -2,8 +2,6 @@
    Use of this source code is governed by a BSD-style license that can be
    found in the LICENSE file. See the AUTHORS file for names of contributors. */
 
-#ifndef ROCKSDB_LITE  // Lite does not support C API
-
 #include "rocksdb/c.h"
 
 #include <stddef.h>
@@ -11,34 +9,10 @@
 #include <stdlib.h>
 #include <string.h>
 #include <sys/types.h>
-#ifndef OS_WIN
-#  include <unistd.h>
-#endif
-#include <inttypes.h>
-
-// Can not use port/port.h macros as this is a c file
-#ifdef OS_WIN
-
-#include <Windows.h>
-
-# define snprintf _snprintf
-
-// Ok for uniqueness
-int geteuid() {
-
-  int result = 0;
-
-  result = ((int)GetCurrentProcessId() << 16);
-  result |= (int)GetCurrentThreadId();
-
-  return result;
-}
-
-#endif
+#include <unistd.h>
 
 const char* phase = "";
 static char dbname[200];
-static char dbbackupname[200];
 
 static void StartPhase(const char* name) {
   fprintf(stderr, "=== Test %s\n", name);
@@ -101,22 +75,6 @@ static void CheckGet(
   Free(&val);
 }
 
-static void CheckGetCF(
-    rocksdb_t* db,
-    const rocksdb_readoptions_t* options,
-    rocksdb_column_family_handle_t* handle,
-    const char* key,
-    const char* expected) {
-  char* err = NULL;
-  size_t val_len;
-  char* val;
-  val = rocksdb_get_cf(db, options, handle, key, strlen(key), &val_len, &err);
-  CheckNoError(err);
-  CheckEqual(expected, val, val_len);
-  Free(&val);
-}
-
-
 static void CheckIter(rocksdb_iterator_t* iter,
                       const char* key, const char* val) {
   size_t len;
@@ -158,7 +116,7 @@ static void CmpDestroy(void* arg) { }
 
 static int CmpCompare(void* arg, const char* a, size_t alen,
                       const char* b, size_t blen) {
-  size_t n = (alen < blen) ? alen : blen;
+  int n = (alen < blen) ? alen : blen;
   int r = memcmp(a, b, n);
   if (r == 0) {
     if (alen < blen) r = -1;
@@ -187,7 +145,7 @@ static char* FilterCreate(
   memcpy(result, "fake", 4);
   return result;
 }
-static unsigned char FilterKeyMatch(
+unsigned char FilterKeyMatch(
     void* arg,
     const char* key, size_t length,
     const char* filter, size_t filter_length) {
@@ -196,61 +154,6 @@ static unsigned char FilterKeyMatch(
   return fake_filter_result;
 }
 
-// Custom compaction filter
-static void CFilterDestroy(void* arg) {}
-static const char* CFilterName(void* arg) { return "foo"; }
-static unsigned char CFilterFilter(void* arg, int level, const char* key,
-                                   size_t key_length,
-                                   const char* existing_value,
-                                   size_t value_length, char** new_value,
-                                   size_t* new_value_length,
-                                   unsigned char* value_changed) {
-  if (key_length == 3) {
-    if (memcmp(key, "bar", key_length) == 0) {
-      return 1;
-    } else if (memcmp(key, "baz", key_length) == 0) {
-      *value_changed = 1;
-      *new_value = "newbazvalue";
-      *new_value_length = 11;
-      return 0;
-    }
-  }
-  return 0;
-}
-
-static void CFilterFactoryDestroy(void* arg) {}
-static const char* CFilterFactoryName(void* arg) { return "foo"; }
-static rocksdb_compactionfilter_t* CFilterCreate(
-    void* arg, rocksdb_compactionfiltercontext_t* context) {
-  return rocksdb_compactionfilter_create(NULL, CFilterDestroy, CFilterFilter,
-                                         CFilterName);
-}
-
-static rocksdb_t* CheckCompaction(rocksdb_t* db, rocksdb_options_t* options,
-                                  rocksdb_readoptions_t* roptions,
-                                  rocksdb_writeoptions_t* woptions) {
-  char* err = NULL;
-  db = rocksdb_open(options, dbname, &err);
-  CheckNoError(err);
-  rocksdb_put(db, woptions, "foo", 3, "foovalue", 8, &err);
-  CheckNoError(err);
-  CheckGet(db, roptions, "foo", "foovalue");
-  rocksdb_put(db, woptions, "bar", 3, "barvalue", 8, &err);
-  CheckNoError(err);
-  CheckGet(db, roptions, "bar", "barvalue");
-  rocksdb_put(db, woptions, "baz", 3, "bazvalue", 8, &err);
-  CheckNoError(err);
-  CheckGet(db, roptions, "baz", "bazvalue");
-
-  // Force compaction
-  rocksdb_compact_range(db, NULL, 0, NULL, 0);
-  // should have filtered bar, but not foo
-  CheckGet(db, roptions, "foo", "foovalue");
-  CheckGet(db, roptions, "bar", NULL);
-  CheckGet(db, roptions, "baz", "newbazvalue");
-  return db;
-}
-
 // Custom merge operator
 static void MergeOperatorDestroy(void* arg) { }
 static const char* MergeOperatorName(void* arg) {
@@ -288,7 +191,6 @@ int main(int argc, char** argv) {
   rocksdb_cache_t* cache;
   rocksdb_env_t* env;
   rocksdb_options_t* options;
-  rocksdb_block_based_table_options_t* table_options;
   rocksdb_readoptions_t* roptions;
   rocksdb_writeoptions_t* woptions;
   char* err = NULL;
@@ -299,11 +201,6 @@ int main(int argc, char** argv) {
            GetTempDir(),
            ((int) geteuid()));
 
-  snprintf(dbbackupname, sizeof(dbbackupname),
-           "%s/rocksdb_c_test-%d-backup",
-           GetTempDir(),
-           ((int) geteuid()));
-
   StartPhase("create_objects");
   cmp = rocksdb_comparator_create(NULL, CmpDestroy, CmpCompare, CmpName);
   env = rocksdb_create_default_env();
@@ -312,17 +209,16 @@ int main(int argc, char** argv) {
   options = rocksdb_options_create();
   rocksdb_options_set_comparator(options, cmp);
   rocksdb_options_set_error_if_exists(options, 1);
+  rocksdb_options_set_cache(options, cache);
   rocksdb_options_set_env(options, env);
   rocksdb_options_set_info_log(options, NULL);
   rocksdb_options_set_write_buffer_size(options, 100000);
   rocksdb_options_set_paranoid_checks(options, 1);
   rocksdb_options_set_max_open_files(options, 10);
-  table_options = rocksdb_block_based_options_create();
-  rocksdb_block_based_options_set_block_cache(table_options, cache);
-  rocksdb_options_set_block_based_table_factory(options, table_options);
-
+  rocksdb_options_set_block_size(options, 1024);
+  rocksdb_options_set_block_restart_interval(options, 8);
   rocksdb_options_set_compression(options, rocksdb_no_compression);
-  rocksdb_options_set_compression_options(options, -14, -1, 0, 0);
+  rocksdb_options_set_compression_options(options, -14, -1, 0);
   int compression_levels[] = {rocksdb_no_compression, rocksdb_no_compression,
                               rocksdb_no_compression, rocksdb_no_compression};
   rocksdb_options_set_compression_per_level(options, compression_levels, 4);
@@ -339,7 +235,7 @@ int main(int argc, char** argv) {
   Free(&err);
 
   StartPhase("open_error");
-  rocksdb_open(options, dbname, &err);
+  db = rocksdb_open(options, dbname, &err);
   CheckCondition(err != NULL);
   Free(&err);
 
@@ -354,59 +250,6 @@ int main(int argc, char** argv) {
   CheckNoError(err);
   CheckGet(db, roptions, "foo", "hello");
 
-  StartPhase("backup_and_restore");
-  {
-    rocksdb_destroy_db(options, dbbackupname, &err);
-    CheckNoError(err);
-
-    rocksdb_backup_engine_t *be = rocksdb_backup_engine_open(options, dbbackupname, &err);
-    CheckNoError(err);
-
-    rocksdb_backup_engine_create_new_backup(be, db, &err);
-    CheckNoError(err);
-
-    // need a change to trigger a new backup
-    rocksdb_delete(db, woptions, "does-not-exist", 14, &err);
-    CheckNoError(err);
-
-    rocksdb_backup_engine_create_new_backup(be, db, &err);
-    CheckNoError(err);
-
-    const rocksdb_backup_engine_info_t* bei = rocksdb_backup_engine_get_backup_info(be);
-    CheckCondition(rocksdb_backup_engine_info_count(bei) > 1);
-    rocksdb_backup_engine_info_destroy(bei);
-
-    rocksdb_backup_engine_purge_old_backups(be, 1, &err);
-    CheckNoError(err);
-
-    bei = rocksdb_backup_engine_get_backup_info(be);
-    CheckCondition(rocksdb_backup_engine_info_count(bei) == 1);
-    rocksdb_backup_engine_info_destroy(bei);
-
-    rocksdb_delete(db, woptions, "foo", 3, &err);
-    CheckNoError(err);
-
-    rocksdb_close(db);
-
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_restore_options_t *restore_options = rocksdb_restore_options_create();
-    rocksdb_restore_options_set_keep_log_files(restore_options, 0);
-    rocksdb_backup_engine_restore_db_from_latest_backup(be, dbname, dbname, restore_options, &err);
-    CheckNoError(err);
-    rocksdb_restore_options_destroy(restore_options);
-
-    rocksdb_options_set_error_if_exists(options, 0);
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-    rocksdb_options_set_error_if_exists(options, 1);
-
-    CheckGet(db, roptions, "foo", "hello");
-
-    rocksdb_backup_engine_close(be);
-  }
-
   StartPhase("compactall");
   rocksdb_compact_range(db, NULL, 0, NULL, 0);
   CheckGet(db, roptions, "foo", "hello");
@@ -434,42 +277,6 @@ int main(int argc, char** argv) {
     rocksdb_writebatch_destroy(wb);
   }
 
-  StartPhase("writebatch_vectors");
-  {
-    rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
-    const char* k_list[2] = { "z", "ap" };
-    const size_t k_sizes[2] = { 1, 2 };
-    const char* v_list[3] = { "x", "y", "z" };
-    const size_t v_sizes[3] = { 1, 1, 1 };
-    rocksdb_writebatch_putv(wb, 2, k_list, k_sizes, 3, v_list, v_sizes);
-    rocksdb_write(db, woptions, wb, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "zap", "xyz");
-    rocksdb_writebatch_delete(wb, "zap", 3);
-    rocksdb_write(db, woptions, wb, &err);
-    CheckNoError(err);
-    CheckGet(db, roptions, "zap", NULL);
-    rocksdb_writebatch_destroy(wb);
-  }
-
-  StartPhase("writebatch_rep");
-  {
-    rocksdb_writebatch_t* wb1 = rocksdb_writebatch_create();
-    rocksdb_writebatch_put(wb1, "baz", 3, "d", 1);
-    rocksdb_writebatch_put(wb1, "quux", 4, "e", 1);
-    rocksdb_writebatch_delete(wb1, "quux", 4);
-    size_t repsize1 = 0;
-    const char* rep = rocksdb_writebatch_data(wb1, &repsize1);
-    rocksdb_writebatch_t* wb2 = rocksdb_writebatch_create_from(rep, repsize1);
-    CheckCondition(rocksdb_writebatch_count(wb1) ==
-                   rocksdb_writebatch_count(wb2));
-    size_t repsize2 = 0;
-    CheckCondition(
-        memcmp(rep, rocksdb_writebatch_data(wb2, &repsize2), repsize1) == 0);
-    rocksdb_writebatch_destroy(wb1);
-    rocksdb_writebatch_destroy(wb2);
-  }
-
   StartPhase("iter");
   {
     rocksdb_iterator_t* iter = rocksdb_create_iterator(db, roptions);
@@ -492,33 +299,6 @@ int main(int argc, char** argv) {
     rocksdb_iter_destroy(iter);
   }
 
-  StartPhase("multiget");
-  {
-    const char* keys[3] = { "box", "foo", "notfound" };
-    const size_t keys_sizes[3] = { 3, 3, 8 };
-    char* vals[3];
-    size_t vals_sizes[3];
-    char* errs[3];
-    rocksdb_multi_get(db, roptions, 3, keys, keys_sizes, vals, vals_sizes, errs);
-
-    int i;
-    for (i = 0; i < 3; i++) {
-      CheckEqual(NULL, errs[i], 0);
-      switch (i) {
-      case 0:
-        CheckEqual("c", vals[i], vals_sizes[i]);
-        break;
-      case 1:
-        CheckEqual("hello", vals[i], vals_sizes[i]);
-        break;
-      case 2:
-        CheckEqual(NULL, vals[i], vals_sizes[i]);
-        break;
-      }
-      Free(&vals[i]);
-    }
-  }
-
   StartPhase("approximate_sizes");
   {
     int i;
@@ -598,12 +378,10 @@ int main(int argc, char** argv) {
       policy = rocksdb_filterpolicy_create_bloom(10);
     }
 
-    rocksdb_block_based_options_set_filter_policy(table_options, policy);
-
     // Create new database
     rocksdb_close(db);
     rocksdb_destroy_db(options, dbname, &err);
-    rocksdb_options_set_block_based_table_factory(options, table_options);
+    rocksdb_options_set_filter_policy(options, policy);
     db = rocksdb_open(options, dbname, &err);
     CheckNoError(err);
     rocksdb_put(db, woptions, "foo", 3, "foovalue", 8, &err);
@@ -625,46 +403,8 @@ int main(int argc, char** argv) {
       CheckGet(db, roptions, "foo", "foovalue");
       CheckGet(db, roptions, "bar", "barvalue");
     }
-    // Reset the policy
-    rocksdb_block_based_options_set_filter_policy(table_options, NULL);
-    rocksdb_options_set_block_based_table_factory(options, table_options);
-  }
-
-  StartPhase("compaction_filter");
-  {
-    rocksdb_options_t* options_with_filter = rocksdb_options_create();
-    rocksdb_options_set_create_if_missing(options_with_filter, 1);
-    rocksdb_compactionfilter_t* cfilter;
-    cfilter = rocksdb_compactionfilter_create(NULL, CFilterDestroy,
-                                              CFilterFilter, CFilterName);
-    // Create new database
-    rocksdb_close(db);
-    rocksdb_destroy_db(options_with_filter, dbname, &err);
-    rocksdb_options_set_compaction_filter(options_with_filter, cfilter);
-    db = CheckCompaction(db, options_with_filter, roptions, woptions);
-
-    rocksdb_options_set_compaction_filter(options_with_filter, NULL);
-    rocksdb_compactionfilter_destroy(cfilter);
-    rocksdb_options_destroy(options_with_filter);
-  }
-
-  StartPhase("compaction_filter_factory");
-  {
-    rocksdb_options_t* options_with_filter_factory = rocksdb_options_create();
-    rocksdb_options_set_create_if_missing(options_with_filter_factory, 1);
-    rocksdb_compactionfilterfactory_t* factory;
-    factory = rocksdb_compactionfilterfactory_create(
-        NULL, CFilterFactoryDestroy, CFilterCreate, CFilterFactoryName);
-    // Create new database
-    rocksdb_close(db);
-    rocksdb_destroy_db(options_with_filter_factory, dbname, &err);
-    rocksdb_options_set_compaction_filter_factory(options_with_filter_factory,
-                                                  factory);
-    db = CheckCompaction(db, options_with_filter_factory, roptions, woptions);
-
-    rocksdb_options_set_compaction_filter_factory(
-        options_with_filter_factory, NULL);
-    rocksdb_options_destroy(options_with_filter_factory);
+    rocksdb_options_set_filter_policy(options, NULL);
+    rocksdb_filterpolicy_destroy(policy);
   }
 
   StartPhase("merge_operator");
@@ -693,140 +433,16 @@ int main(int argc, char** argv) {
 
   }
 
-  StartPhase("columnfamilies");
-  {
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err)
-
-    rocksdb_options_t* db_options = rocksdb_options_create();
-    rocksdb_options_set_create_if_missing(db_options, 1);
-    db = rocksdb_open(db_options, dbname, &err);
-    CheckNoError(err)
-    rocksdb_column_family_handle_t* cfh;
-    cfh = rocksdb_create_column_family(db, db_options, "cf1", &err);
-    rocksdb_column_family_handle_destroy(cfh);
-    CheckNoError(err);
-    rocksdb_close(db);
-
-    size_t cflen;
-    char** column_fams = rocksdb_list_column_families(db_options, dbname, &cflen, &err);
-    CheckNoError(err);
-    CheckEqual("default", column_fams[0], 7);
-    CheckEqual("cf1", column_fams[1], 3);
-    CheckCondition(cflen == 2);
-    rocksdb_list_column_families_destroy(column_fams, cflen);
-
-    rocksdb_options_t* cf_options = rocksdb_options_create();
-
-    const char* cf_names[2] = {"default", "cf1"};
-    const rocksdb_options_t* cf_opts[2] = {cf_options, cf_options};
-    rocksdb_column_family_handle_t* handles[2];
-    db = rocksdb_open_column_families(db_options, dbname, 2, cf_names, cf_opts, handles, &err);
-    CheckNoError(err);
-
-    rocksdb_put_cf(db, woptions, handles[1], "foo", 3, "hello", 5, &err);
-    CheckNoError(err);
-
-    CheckGetCF(db, roptions, handles[1], "foo", "hello");
-
-    rocksdb_delete_cf(db, woptions, handles[1], "foo", 3, &err);
-    CheckNoError(err);
-
-    CheckGetCF(db, roptions, handles[1], "foo", NULL);
-
-    rocksdb_writebatch_t* wb = rocksdb_writebatch_create();
-    rocksdb_writebatch_put_cf(wb, handles[1], "baz", 3, "a", 1);
-    rocksdb_writebatch_clear(wb);
-    rocksdb_writebatch_put_cf(wb, handles[1], "bar", 3, "b", 1);
-    rocksdb_writebatch_put_cf(wb, handles[1], "box", 3, "c", 1);
-    rocksdb_writebatch_delete_cf(wb, handles[1], "bar", 3);
-    rocksdb_write(db, woptions, wb, &err);
-    CheckNoError(err);
-    CheckGetCF(db, roptions, handles[1], "baz", NULL);
-    CheckGetCF(db, roptions, handles[1], "bar", NULL);
-    CheckGetCF(db, roptions, handles[1], "box", "c");
-    rocksdb_writebatch_destroy(wb);
-
-    const char* keys[3] = { "box", "box", "barfooxx" };
-    const rocksdb_column_family_handle_t* get_handles[3] = { handles[0], handles[1], handles[1] };
-    const size_t keys_sizes[3] = { 3, 3, 8 };
-    char* vals[3];
-    size_t vals_sizes[3];
-    char* errs[3];
-    rocksdb_multi_get_cf(db, roptions, get_handles, 3, keys, keys_sizes, vals, vals_sizes, errs);
-
-    int i;
-    for (i = 0; i < 3; i++) {
-      CheckEqual(NULL, errs[i], 0);
-      switch (i) {
-      case 0:
-        CheckEqual(NULL, vals[i], vals_sizes[i]); // wrong cf
-        break;
-      case 1:
-        CheckEqual("c", vals[i], vals_sizes[i]); // bingo
-        break;
-      case 2:
-        CheckEqual(NULL, vals[i], vals_sizes[i]); // normal not found
-        break;
-      }
-      Free(&vals[i]);
-    }
-
-    rocksdb_iterator_t* iter = rocksdb_create_iterator_cf(db, roptions, handles[1]);
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_first(iter);
-    CheckCondition(rocksdb_iter_valid(iter));
-
-    for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
-      i++;
-    }
-    CheckCondition(i == 1);
-    rocksdb_iter_get_error(iter, &err);
-    CheckNoError(err);
-    rocksdb_iter_destroy(iter);
-
-    rocksdb_column_family_handle_t* iters_cf_handles[2] = { handles[0], handles[1] };
-    rocksdb_iterator_t* iters_handles[2];
-    rocksdb_create_iterators(db, roptions, iters_cf_handles, iters_handles, 2, &err);
-    CheckNoError(err);
-
-    iter = iters_handles[0];
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_first(iter);
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_destroy(iter);
-
-    iter = iters_handles[1];
-    CheckCondition(!rocksdb_iter_valid(iter));
-    rocksdb_iter_seek_to_first(iter);
-    CheckCondition(rocksdb_iter_valid(iter));
-
-    for (i = 0; rocksdb_iter_valid(iter) != 0; rocksdb_iter_next(iter)) {
-      i++;
-    }
-    CheckCondition(i == 1);
-    rocksdb_iter_get_error(iter, &err);
-    CheckNoError(err);
-    rocksdb_iter_destroy(iter);
-
-    rocksdb_drop_column_family(db, handles[1], &err);
-    CheckNoError(err);
-    for (i = 0; i < 2; i++) {
-      rocksdb_column_family_handle_destroy(handles[i]);
-    }
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    rocksdb_options_destroy(db_options);
-    rocksdb_options_destroy(cf_options);
-  }
-
   StartPhase("prefix");
   {
     // Create new database
-    rocksdb_options_set_allow_mmap_reads(options, 1);
+    rocksdb_close(db);
+    rocksdb_destroy_db(options, dbname, &err);
+
+    rocksdb_filterpolicy_t* policy = rocksdb_filterpolicy_create_bloom(10);
+    rocksdb_options_set_filter_policy(options, policy);
     rocksdb_options_set_prefix_extractor(options, rocksdb_slicetransform_create_fixed_prefix(3));
-    rocksdb_options_set_hash_skip_list_rep(options, 5000, 4, 4);
+    rocksdb_options_set_hash_skip_list_rep(options, 50000, 4, 4);
     rocksdb_options_set_plain_table_factory(options, 4, 10, 0.75, 16);
 
     db = rocksdb_open(options, dbname, &err);
@@ -845,6 +461,8 @@ int main(int argc, char** argv) {
     rocksdb_put(db, woptions, "bar3", 4, "bar", 3, &err);
     CheckNoError(err);
 
+    rocksdb_readoptions_set_prefix_seek(roptions, 1);
+
     rocksdb_iterator_t* iter = rocksdb_create_iterator(db, roptions);
     CheckCondition(!rocksdb_iter_valid(iter));
 
@@ -861,92 +479,12 @@ int main(int argc, char** argv) {
     rocksdb_iter_get_error(iter, &err);
     CheckNoError(err);
     rocksdb_iter_destroy(iter);
-
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-  }
-
-  StartPhase("cuckoo_options");
-  {
-    rocksdb_cuckoo_table_options_t* cuckoo_options;
-    cuckoo_options = rocksdb_cuckoo_options_create();
-    rocksdb_cuckoo_options_set_hash_ratio(cuckoo_options, 0.5);
-    rocksdb_cuckoo_options_set_max_search_depth(cuckoo_options, 200);
-    rocksdb_cuckoo_options_set_cuckoo_block_size(cuckoo_options, 10);
-    rocksdb_cuckoo_options_set_identity_as_first_hash(cuckoo_options, 1);
-    rocksdb_cuckoo_options_set_use_module_hash(cuckoo_options, 0);
-    rocksdb_options_set_cuckoo_table_factory(options, cuckoo_options);
-
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_cuckoo_options_destroy(cuckoo_options);
-  }
-
-  StartPhase("iterate_upper_bound");
-  {
-    // Create new empty database
-    rocksdb_close(db);
-    rocksdb_destroy_db(options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_options_set_prefix_extractor(options, NULL);
-    db = rocksdb_open(options, dbname, &err);
-    CheckNoError(err);
-
-    rocksdb_put(db, woptions, "a",    1, "0",    1, &err); CheckNoError(err);
-    rocksdb_put(db, woptions, "foo",  3, "bar",  3, &err); CheckNoError(err);
-    rocksdb_put(db, woptions, "foo1", 4, "bar1", 4, &err); CheckNoError(err);
-    rocksdb_put(db, woptions, "g1",   2, "0",    1, &err); CheckNoError(err);
-
-    // testing basic case with no iterate_upper_bound and no prefix_extractor
-    {
-       rocksdb_readoptions_set_iterate_upper_bound(roptions, NULL, 0);
-       rocksdb_iterator_t* iter = rocksdb_create_iterator(db, roptions);
-
-       rocksdb_iter_seek(iter, "foo", 3);
-       CheckCondition(rocksdb_iter_valid(iter));
-       CheckIter(iter, "foo", "bar");
-
-       rocksdb_iter_next(iter);
-       CheckCondition(rocksdb_iter_valid(iter));
-       CheckIter(iter, "foo1", "bar1");
-
-       rocksdb_iter_next(iter);
-       CheckCondition(rocksdb_iter_valid(iter));
-       CheckIter(iter, "g1", "0");
-
-       rocksdb_iter_destroy(iter);
-    }
-
-    // testing iterate_upper_bound and forward iterator
-    // to make sure it stops at bound
-    {
-       // iterate_upper_bound points beyond the last expected entry
-       rocksdb_readoptions_set_iterate_upper_bound(roptions, "foo2", 4);
-
-       rocksdb_iterator_t* iter = rocksdb_create_iterator(db, roptions);
-
-       rocksdb_iter_seek(iter, "foo", 3);
-       CheckCondition(rocksdb_iter_valid(iter));
-       CheckIter(iter, "foo", "bar");
-
-       rocksdb_iter_next(iter);
-       CheckCondition(rocksdb_iter_valid(iter));
-       CheckIter(iter, "foo1", "bar1");
-
-       rocksdb_iter_next(iter);
-       // should stop here...
-       CheckCondition(!rocksdb_iter_valid(iter));
-
-       rocksdb_iter_destroy(iter);
-    }
+    rocksdb_filterpolicy_destroy(policy);
   }
 
   StartPhase("cleanup");
   rocksdb_close(db);
   rocksdb_options_destroy(options);
-  rocksdb_block_based_options_destroy(table_options);
   rocksdb_readoptions_destroy(roptions);
   rocksdb_writeoptions_destroy(woptions);
   rocksdb_cache_destroy(cache);
@@ -956,13 +494,3 @@ int main(int argc, char** argv) {
   fprintf(stderr, "PASS\n");
   return 0;
 }
-
-#else
-#include <stdio.h>
-
-int main() {
-  fprintf(stderr, "SKIPPED\n");
-  return 0;
-}
-
-#endif  // !ROCKSDB_LITE

db/column_family.h

@@ -1,550 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#pragma once
-
-#include <unordered_map>
-#include <string>
-#include <vector>
-#include <atomic>
-
-#include "db/memtable_list.h"
-#include "db/write_batch_internal.h"
-#include "db/write_controller.h"
-#include "db/table_cache.h"
-#include "db/table_properties_collector.h"
-#include "rocksdb/compaction_job_stats.h"
-#include "rocksdb/db.h"
-#include "rocksdb/env.h"
-#include "rocksdb/options.h"
-#include "util/mutable_cf_options.h"
-#include "util/thread_local.h"
-
-namespace rocksdb {
-
-class Version;
-class VersionSet;
-class MemTable;
-class MemTableListVersion;
-class CompactionPicker;
-class Compaction;
-class InternalKey;
-class InternalStats;
-class ColumnFamilyData;
-class DBImpl;
-class LogBuffer;
-class InstrumentedMutex;
-class InstrumentedMutexLock;
-
-extern const double kSlowdownRatio;
-
-// ColumnFamilyHandleImpl is the class that clients use to access different
-// column families. It has non-trivial destructor, which gets called when client
-// is done using the column family
-class ColumnFamilyHandleImpl : public ColumnFamilyHandle {
- public:
-  // create while holding the mutex
-  ColumnFamilyHandleImpl(
-      ColumnFamilyData* cfd, DBImpl* db, InstrumentedMutex* mutex);
-  // destroy without mutex
-  virtual ~ColumnFamilyHandleImpl();
-  virtual ColumnFamilyData* cfd() const { return cfd_; }
-  virtual const Comparator* user_comparator() const;
-
-  virtual uint32_t GetID() const override;
-  virtual const std::string& GetName() const override;
-  virtual Status GetDescriptor(ColumnFamilyDescriptor* desc) override;
-
- private:
-  ColumnFamilyData* cfd_;
-  DBImpl* db_;
-  InstrumentedMutex* mutex_;
-};
-
-// Does not ref-count ColumnFamilyData
-// We use this dummy ColumnFamilyHandleImpl because sometimes MemTableInserter
-// calls DBImpl methods. When this happens, MemTableInserter need access to
-// ColumnFamilyHandle (same as the client would need). In that case, we feed
-// MemTableInserter dummy ColumnFamilyHandle and enable it to call DBImpl
-// methods
-class ColumnFamilyHandleInternal : public ColumnFamilyHandleImpl {
- public:
-  ColumnFamilyHandleInternal()
-      : ColumnFamilyHandleImpl(nullptr, nullptr, nullptr) {}
-
-  void SetCFD(ColumnFamilyData* _cfd) { internal_cfd_ = _cfd; }
-  virtual ColumnFamilyData* cfd() const override { return internal_cfd_; }
-
- private:
-  ColumnFamilyData* internal_cfd_;
-};
-
-// holds references to memtable, all immutable memtables and version
-struct SuperVersion {
-  // Accessing members of this class is not thread-safe and requires external
-  // synchronization (ie db mutex held or on write thread).
-  MemTable* mem;
-  MemTableListVersion* imm;
-  Version* current;
-  MutableCFOptions mutable_cf_options;
-  // Version number of the current SuperVersion
-  uint64_t version_number;
-
-  InstrumentedMutex* db_mutex;
-
-  // should be called outside the mutex
-  SuperVersion() = default;
-  ~SuperVersion();
-  SuperVersion* Ref();
-  // If Unref() returns true, Cleanup() should be called with mutex held
-  // before deleting this SuperVersion.
-  bool Unref();
-
-  // call these two methods with db mutex held
-  // Cleanup unrefs mem, imm and current. Also, it stores all memtables
-  // that needs to be deleted in to_delete vector. Unrefing those
-  // objects needs to be done in the mutex
-  void Cleanup();
-  void Init(MemTable* new_mem, MemTableListVersion* new_imm,
-            Version* new_current);
-
-  // The value of dummy is not actually used. kSVInUse takes its address as a
-  // mark in the thread local storage to indicate the SuperVersion is in use
-  // by thread. This way, the value of kSVInUse is guaranteed to have no
-  // conflict with SuperVersion object address and portable on different
-  // platform.
-  static int dummy;
-  static void* const kSVInUse;
-  static void* const kSVObsolete;
-
- private:
-  std::atomic<uint32_t> refs;
-  // We need to_delete because during Cleanup(), imm->Unref() returns
-  // all memtables that we need to free through this vector. We then
-  // delete all those memtables outside of mutex, during destruction
-  autovector<MemTable*> to_delete;
-};
-
-extern Status CheckCompressionSupported(const ColumnFamilyOptions& cf_options);
-
-extern Status CheckConcurrentWritesSupported(
-    const ColumnFamilyOptions& cf_options);
-
-extern ColumnFamilyOptions SanitizeOptions(const DBOptions& db_options,
-                                           const InternalKeyComparator* icmp,
-                                           const ColumnFamilyOptions& src);
-// Wrap user defined table proproties collector factories `from cf_options`
-// into internal ones in int_tbl_prop_collector_factories. Add a system internal
-// one too.
-extern void GetIntTblPropCollectorFactory(
-    const ColumnFamilyOptions& cf_options,
-    std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
-        int_tbl_prop_collector_factories);
-
-class ColumnFamilySet;
-
-// This class keeps all the data that a column family needs.
-// Most methods require DB mutex held, unless otherwise noted
-class ColumnFamilyData {
- public:
-  ~ColumnFamilyData();
-
-  // thread-safe
-  uint32_t GetID() const { return id_; }
-  // thread-safe
-  const std::string& GetName() const { return name_; }
-
-  // Ref() can only be called from a context where the caller can guarantee
-  // that ColumnFamilyData is alive (while holding a non-zero ref already,
-  // holding a DB mutex, or as the leader in a write batch group).
-  void Ref() { refs_.fetch_add(1, std::memory_order_relaxed); }
-
-  // Unref decreases the reference count, but does not handle deletion
-  // when the count goes to 0.  If this method returns true then the
-  // caller should delete the instance immediately, or later, by calling
-  // FreeDeadColumnFamilies().  Unref() can only be called while holding
-  // a DB mutex, or during single-threaded recovery.
-  bool Unref() {
-    int old_refs = refs_.fetch_sub(1, std::memory_order_relaxed);
-    assert(old_refs > 0);
-    return old_refs == 1;
-  }
-
-  // SetDropped() can only be called under following conditions:
-  // 1) Holding a DB mutex,
-  // 2) from single-threaded write thread, AND
-  // 3) from single-threaded VersionSet::LogAndApply()
-  // After dropping column family no other operation on that column family
-  // will be executed. All the files and memory will be, however, kept around
-  // until client drops the column family handle. That way, client can still
-  // access data from dropped column family.
-  // Column family can be dropped and still alive. In that state:
-  // *) Compaction and flush is not executed on the dropped column family.
-  // *) Client can continue reading from column family. Writes will fail unless
-  // WriteOptions::ignore_missing_column_families is true
-  // When the dropped column family is unreferenced, then we:
-  // *) Remove column family from the linked list maintained by ColumnFamilySet
-  // *) delete all memory associated with that column family
-  // *) delete all the files associated with that column family
-  void SetDropped();
-  bool IsDropped() const { return dropped_; }
-
-  // thread-safe
-  int NumberLevels() const { return ioptions_.num_levels; }
-
-  void SetLogNumber(uint64_t log_number) { log_number_ = log_number; }
-  uint64_t GetLogNumber() const { return log_number_; }
-
-  // !!! To be deprecated! Please don't not use this function anymore!
-  const Options* options() const { return &options_; }
-
-  // thread-safe
-  const EnvOptions* soptions() const;
-  const ImmutableCFOptions* ioptions() const { return &ioptions_; }
-  // REQUIRES: DB mutex held
-  // This returns the MutableCFOptions used by current SuperVersion
-  // You should use this API to reference MutableCFOptions most of the time.
-  const MutableCFOptions* GetCurrentMutableCFOptions() const {
-    return &(super_version_->mutable_cf_options);
-  }
-  // REQUIRES: DB mutex held
-  // This returns the latest MutableCFOptions, which may be not in effect yet.
-  const MutableCFOptions* GetLatestMutableCFOptions() const {
-    return &mutable_cf_options_;
-  }
-#ifndef ROCKSDB_LITE
-  // REQUIRES: DB mutex held
-  Status SetOptions(
-      const std::unordered_map<std::string, std::string>& options_map);
-#endif  // ROCKSDB_LITE
-
-  InternalStats* internal_stats() { return internal_stats_.get(); }
-
-  MemTableList* imm() { return &imm_; }
-  MemTable* mem() { return mem_; }
-  Version* current() { return current_; }
-  Version* dummy_versions() { return dummy_versions_; }
-  void SetCurrent(Version* _current);
-  uint64_t GetNumLiveVersions() const;  // REQUIRE: DB mutex held
-  uint64_t GetTotalSstFilesSize() const;  // REQUIRE: DB mutex held
-  void SetMemtable(MemTable* new_mem) { mem_ = new_mem; }
-
-  // See Memtable constructor for explanation of earliest_seq param.
-  MemTable* ConstructNewMemtable(const MutableCFOptions& mutable_cf_options,
-                                 SequenceNumber earliest_seq);
-  void CreateNewMemtable(const MutableCFOptions& mutable_cf_options,
-                         SequenceNumber earliest_seq);
-
-  TableCache* table_cache() const { return table_cache_.get(); }
-
-  // See documentation in compaction_picker.h
-  // REQUIRES: DB mutex held
-  bool NeedsCompaction() const;
-  // REQUIRES: DB mutex held
-  Compaction* PickCompaction(const MutableCFOptions& mutable_options,
-                             LogBuffer* log_buffer);
-  // A flag to tell a manual compaction is to compact all levels together
-  // instad of for specific level.
-  static const int kCompactAllLevels;
-  // A flag to tell a manual compaction's output is base level.
-  static const int kCompactToBaseLevel;
-  // REQUIRES: DB mutex held
-  Compaction* CompactRange(const MutableCFOptions& mutable_cf_options,
-                           int input_level, int output_level,
-                           uint32_t output_path_id, const InternalKey* begin,
-                           const InternalKey* end, InternalKey** compaction_end,
-                           bool* manual_conflict);
-
-  CompactionPicker* compaction_picker() { return compaction_picker_.get(); }
-  // thread-safe
-  const Comparator* user_comparator() const {
-    return internal_comparator_.user_comparator();
-  }
-  // thread-safe
-  const InternalKeyComparator& internal_comparator() const {
-    return internal_comparator_;
-  }
-
-  const std::vector<std::unique_ptr<IntTblPropCollectorFactory>>*
-  int_tbl_prop_collector_factories() const {
-    return &int_tbl_prop_collector_factories_;
-  }
-
-  SuperVersion* GetSuperVersion() { return super_version_; }
-  // thread-safe
-  // Return a already referenced SuperVersion to be used safely.
-  SuperVersion* GetReferencedSuperVersion(InstrumentedMutex* db_mutex);
-  // thread-safe
-  // Get SuperVersion stored in thread local storage. If it does not exist,
-  // get a reference from a current SuperVersion.
-  SuperVersion* GetThreadLocalSuperVersion(InstrumentedMutex* db_mutex);
-  // Try to return SuperVersion back to thread local storage. Retrun true on
-  // success and false on failure. It fails when the thread local storage
-  // contains anything other than SuperVersion::kSVInUse flag.
-  bool ReturnThreadLocalSuperVersion(SuperVersion* sv);
-  // thread-safe
-  uint64_t GetSuperVersionNumber() const {
-    return super_version_number_.load();
-  }
-  // will return a pointer to SuperVersion* if previous SuperVersion
-  // if its reference count is zero and needs deletion or nullptr if not
-  // As argument takes a pointer to allocated SuperVersion to enable
-  // the clients to allocate SuperVersion outside of mutex.
-  // IMPORTANT: Only call this from DBImpl::InstallSuperVersion()
-  SuperVersion* InstallSuperVersion(SuperVersion* new_superversion,
-                                    InstrumentedMutex* db_mutex,
-                                    const MutableCFOptions& mutable_cf_options);
-  SuperVersion* InstallSuperVersion(SuperVersion* new_superversion,
-                                    InstrumentedMutex* db_mutex);
-
-  void ResetThreadLocalSuperVersions();
-
-  // Protected by DB mutex
-  void set_pending_flush(bool value) { pending_flush_ = value; }
-  void set_pending_compaction(bool value) { pending_compaction_ = value; }
-  bool pending_flush() { return pending_flush_; }
-  bool pending_compaction() { return pending_compaction_; }
-
-  // Recalculate some small conditions, which are changed only during
-  // compaction, adding new memtable and/or
-  // recalculation of compaction score. These values are used in
-  // DBImpl::MakeRoomForWrite function to decide, if it need to make
-  // a write stall
-  void RecalculateWriteStallConditions(
-      const MutableCFOptions& mutable_cf_options);
-
- private:
-  friend class ColumnFamilySet;
-  ColumnFamilyData(uint32_t id, const std::string& name,
-                   Version* dummy_versions, Cache* table_cache,
-                   WriteBuffer* write_buffer,
-                   const ColumnFamilyOptions& options,
-                   const DBOptions* db_options, const EnvOptions& env_options,
-                   ColumnFamilySet* column_family_set);
-
-  uint32_t id_;
-  const std::string name_;
-  Version* dummy_versions_;  // Head of circular doubly-linked list of versions.
-  Version* current_;         // == dummy_versions->prev_
-
-  std::atomic<int> refs_;      // outstanding references to ColumnFamilyData
-  bool dropped_;               // true if client dropped it
-
-  const InternalKeyComparator internal_comparator_;
-  std::vector<std::unique_ptr<IntTblPropCollectorFactory>>
-      int_tbl_prop_collector_factories_;
-
-  const Options options_;
-  const ImmutableCFOptions ioptions_;
-  MutableCFOptions mutable_cf_options_;
-
-  std::unique_ptr<TableCache> table_cache_;
-
-  std::unique_ptr<InternalStats> internal_stats_;
-
-  WriteBuffer* write_buffer_;
-
-  MemTable* mem_;
-  MemTableList imm_;
-  SuperVersion* super_version_;
-
-  // An ordinal representing the current SuperVersion. Updated by
-  // InstallSuperVersion(), i.e. incremented every time super_version_
-  // changes.
-  std::atomic<uint64_t> super_version_number_;
-
-  // Thread's local copy of SuperVersion pointer
-  // This needs to be destructed before mutex_
-  std::unique_ptr<ThreadLocalPtr> local_sv_;
-
-  // pointers for a circular linked list. we use it to support iterations over
-  // all column families that are alive (note: dropped column families can also
-  // be alive as long as client holds a reference)
-  ColumnFamilyData* next_;
-  ColumnFamilyData* prev_;
-
-  // This is the earliest log file number that contains data from this
-  // Column Family. All earlier log files must be ignored and not
-  // recovered from
-  uint64_t log_number_;
-
-  // An object that keeps all the compaction stats
-  // and picks the next compaction
-  std::unique_ptr<CompactionPicker> compaction_picker_;
-
-  ColumnFamilySet* column_family_set_;
-
-  std::unique_ptr<WriteControllerToken> write_controller_token_;
-
-  // If true --> this ColumnFamily is currently present in DBImpl::flush_queue_
-  bool pending_flush_;
-
-  // If true --> this ColumnFamily is currently present in
-  // DBImpl::compaction_queue_
-  bool pending_compaction_;
-
-  uint64_t prev_compaction_needed_bytes_;
-};
-
-// ColumnFamilySet has interesting thread-safety requirements
-// * CreateColumnFamily() or RemoveColumnFamily() -- need to be protected by DB
-// mutex AND executed in the write thread.
-// CreateColumnFamily() should ONLY be called from VersionSet::LogAndApply() AND
-// single-threaded write thread. It is also called during Recovery and in
-// DumpManifest().
-// RemoveColumnFamily() is only called from SetDropped(). DB mutex needs to be
-// held and it needs to be executed from the write thread. SetDropped() also
-// guarantees that it will be called only from single-threaded LogAndApply(),
-// but this condition is not that important.
-// * Iteration -- hold DB mutex, but you can release it in the body of
-// iteration. If you release DB mutex in body, reference the column
-// family before the mutex and unreference after you unlock, since the column
-// family might get dropped when the DB mutex is released
-// * GetDefault() -- thread safe
-// * GetColumnFamily() -- either inside of DB mutex or from a write thread
-// * GetNextColumnFamilyID(), GetMaxColumnFamily(), UpdateMaxColumnFamily(),
-// NumberOfColumnFamilies -- inside of DB mutex
-class ColumnFamilySet {
- public:
-  // ColumnFamilySet supports iteration
-  class iterator {
-   public:
-    explicit iterator(ColumnFamilyData* cfd)
-        : current_(cfd) {}
-    iterator& operator++() {
-      // dropped column families might still be included in this iteration
-      // (we're only removing them when client drops the last reference to the
-      // column family).
-      // dummy is never dead, so this will never be infinite
-      do {
-        current_ = current_->next_;
-      } while (current_->refs_.load(std::memory_order_relaxed) == 0);
-      return *this;
-    }
-    bool operator!=(const iterator& other) {
-      return this->current_ != other.current_;
-    }
-    ColumnFamilyData* operator*() { return current_; }
-
-   private:
-    ColumnFamilyData* current_;
-  };
-
-  ColumnFamilySet(const std::string& dbname, const DBOptions* db_options,
-                  const EnvOptions& env_options, Cache* table_cache,
-                  WriteBuffer* write_buffer, WriteController* write_controller);
-  ~ColumnFamilySet();
-
-  ColumnFamilyData* GetDefault() const;
-  // GetColumnFamily() calls return nullptr if column family is not found
-  ColumnFamilyData* GetColumnFamily(uint32_t id) const;
-  ColumnFamilyData* GetColumnFamily(const std::string& name) const;
-  // this call will return the next available column family ID. it guarantees
-  // that there is no column family with id greater than or equal to the
-  // returned value in the current running instance or anytime in RocksDB
-  // instance history.
-  uint32_t GetNextColumnFamilyID();
-  uint32_t GetMaxColumnFamily();
-  void UpdateMaxColumnFamily(uint32_t new_max_column_family);
-  size_t NumberOfColumnFamilies() const;
-
-  ColumnFamilyData* CreateColumnFamily(const std::string& name, uint32_t id,
-                                       Version* dummy_version,
-                                       const ColumnFamilyOptions& options);
-
-  iterator begin() { return iterator(dummy_cfd_->next_); }
-  iterator end() { return iterator(dummy_cfd_); }
-
-  // REQUIRES: DB mutex held
-  // Don't call while iterating over ColumnFamilySet
-  void FreeDeadColumnFamilies();
-
-  Cache* get_table_cache() { return table_cache_; }
-
- private:
-  friend class ColumnFamilyData;
-  // helper function that gets called from cfd destructor
-  // REQUIRES: DB mutex held
-  void RemoveColumnFamily(ColumnFamilyData* cfd);
-
-  // column_families_ and column_family_data_ need to be protected:
-  // * when mutating both conditions have to be satisfied:
-  // 1. DB mutex locked
-  // 2. thread currently in single-threaded write thread
-  // * when reading, at least one condition needs to be satisfied:
-  // 1. DB mutex locked
-  // 2. accessed from a single-threaded write thread
-  std::unordered_map<std::string, uint32_t> column_families_;
-  std::unordered_map<uint32_t, ColumnFamilyData*> column_family_data_;
-
-  uint32_t max_column_family_;
-  ColumnFamilyData* dummy_cfd_;
-  // We don't hold the refcount here, since default column family always exists
-  // We are also not responsible for cleaning up default_cfd_cache_. This is
-  // just a cache that makes common case (accessing default column family)
-  // faster
-  ColumnFamilyData* default_cfd_cache_;
-
-  const std::string db_name_;
-  const DBOptions* const db_options_;
-  const EnvOptions env_options_;
-  Cache* table_cache_;
-  WriteBuffer* write_buffer_;
-  WriteController* write_controller_;
-};
-
-// We use ColumnFamilyMemTablesImpl to provide WriteBatch a way to access
-// memtables of different column families (specified by ID in the write batch)
-class ColumnFamilyMemTablesImpl : public ColumnFamilyMemTables {
- public:
-  explicit ColumnFamilyMemTablesImpl(ColumnFamilySet* column_family_set)
-      : column_family_set_(column_family_set), current_(nullptr) {}
-
-  // Constructs a ColumnFamilyMemTablesImpl equivalent to one constructed
-  // with the arguments used to construct *orig.
-  explicit ColumnFamilyMemTablesImpl(ColumnFamilyMemTablesImpl* orig)
-      : column_family_set_(orig->column_family_set_), current_(nullptr) {}
-
-  // sets current_ to ColumnFamilyData with column_family_id
-  // returns false if column family doesn't exist
-  // REQUIRES: use this function of DBImpl::column_family_memtables_ should be
-  //           under a DB mutex OR from a write thread
-  bool Seek(uint32_t column_family_id) override;
-
-  // Returns log number of the selected column family
-  // REQUIRES: under a DB mutex OR from a write thread
-  uint64_t GetLogNumber() const override;
-
-  // REQUIRES: Seek() called first
-  // REQUIRES: use this function of DBImpl::column_family_memtables_ should be
-  //           under a DB mutex OR from a write thread
-  virtual MemTable* GetMemTable() const override;
-
-  // Returns column family handle for the selected column family
-  // REQUIRES: use this function of DBImpl::column_family_memtables_ should be
-  //           under a DB mutex OR from a write thread
-  virtual ColumnFamilyHandle* GetColumnFamilyHandle() override;
-
-  // Cannot be called while another thread is calling Seek().
-  // REQUIRES: use this function of DBImpl::column_family_memtables_ should be
-  //           under a DB mutex OR from a write thread
-  virtual ColumnFamilyData* current() override { return current_; }
-
- private:
-  ColumnFamilySet* column_family_set_;
-  ColumnFamilyData* current_;
-  ColumnFamilyHandleInternal handle_;
-};
-
-extern uint32_t GetColumnFamilyID(ColumnFamilyHandle* column_family);
-
-extern const Comparator* GetColumnFamilyUserComparator(
-    ColumnFamilyHandle* column_family);
-
-}  // namespace rocksdb

db/compact_files_test.cc

@@ -1,227 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-
-#ifndef ROCKSDB_LITE
-
-#include <mutex>
-#include <string>
-#include <thread>
-#include <vector>
-
-#include "rocksdb/db.h"
-#include "rocksdb/env.h"
-#include "util/string_util.h"
-#include "util/sync_point.h"
-#include "util/testharness.h"
-
-namespace rocksdb {
-
-class CompactFilesTest : public testing::Test {
- public:
-  CompactFilesTest() {
-    env_ = Env::Default();
-    db_name_ = test::TmpDir(env_) + "/compact_files_test";
-  }
-
-  std::string db_name_;
-  Env* env_;
-};
-
-// A class which remembers the name of each flushed file.
-class FlushedFileCollector : public EventListener {
- public:
-  FlushedFileCollector() {}
-  ~FlushedFileCollector() {}
-
-  virtual void OnFlushCompleted(
-      DB* db, const FlushJobInfo& info) override {
-    std::lock_guard<std::mutex> lock(mutex_);
-    flushed_files_.push_back(info.file_path);
-  }
-
-  std::vector<std::string> GetFlushedFiles() {
-    std::lock_guard<std::mutex> lock(mutex_);
-    std::vector<std::string> result;
-    for (auto fname : flushed_files_) {
-      result.push_back(fname);
-    }
-    return result;
-  }
-
- private:
-  std::vector<std::string> flushed_files_;
-  std::mutex mutex_;
-};
-
-TEST_F(CompactFilesTest, L0ConflictsFiles) {
-  Options options;
-  // to trigger compaction more easily
-  const int kWriteBufferSize = 10000;
-  const int kLevel0Trigger = 2;
-  options.create_if_missing = true;
-  options.compaction_style = kCompactionStyleLevel;
-  // Small slowdown and stop trigger for experimental purpose.
-  options.level0_slowdown_writes_trigger = 20;
-  options.level0_stop_writes_trigger = 20;
-  options.level0_stop_writes_trigger = 20;
-  options.write_buffer_size = kWriteBufferSize;
-  options.level0_file_num_compaction_trigger = kLevel0Trigger;
-  options.compression = kNoCompression;
-
-  DB* db = nullptr;
-  DestroyDB(db_name_, options);
-  Status s = DB::Open(options, db_name_, &db);
-  assert(s.ok());
-  assert(db);
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency({
-      {"CompactFilesImpl:0", "BackgroundCallCompaction:0"},
-      {"BackgroundCallCompaction:1", "CompactFilesImpl:1"},
-  });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  // create couple files
-  // Background compaction starts and waits in BackgroundCallCompaction:0
-  for (int i = 0; i < kLevel0Trigger * 4; ++i) {
-    db->Put(WriteOptions(), ToString(i), "");
-    db->Put(WriteOptions(), ToString(100 - i), "");
-    db->Flush(FlushOptions());
-  }
-
-  rocksdb::ColumnFamilyMetaData meta;
-  db->GetColumnFamilyMetaData(&meta);
-  std::string file1;
-  for (auto& file : meta.levels[0].files) {
-    ASSERT_EQ(0, meta.levels[0].level);
-    if (file1 == "") {
-      file1 = file.db_path + "/" + file.name;
-    } else {
-      std::string file2 = file.db_path + "/" + file.name;
-      // Another thread starts a compact files and creates an L0 compaction
-      // The background compaction then notices that there is an L0 compaction
-      // already in progress and doesn't do an L0 compaction
-      // Once the background compaction finishes, the compact files finishes
-      ASSERT_OK(
-          db->CompactFiles(rocksdb::CompactionOptions(), {file1, file2}, 0));
-      break;
-    }
-  }
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-  delete db;
-}
-
-TEST_F(CompactFilesTest, ObsoleteFiles) {
-  Options options;
-  // to trigger compaction more easily
-  const int kWriteBufferSize = 10000;
-  options.create_if_missing = true;
-  // Disable RocksDB background compaction.
-  options.compaction_style = kCompactionStyleNone;
-  // Small slowdown and stop trigger for experimental purpose.
-  options.level0_slowdown_writes_trigger = 20;
-  options.level0_stop_writes_trigger = 20;
-  options.write_buffer_size = kWriteBufferSize;
-  options.max_write_buffer_number = 2;
-  options.compression = kNoCompression;
-
-  // Add listener
-  FlushedFileCollector* collector = new FlushedFileCollector();
-  options.listeners.emplace_back(collector);
-
-  DB* db = nullptr;
-  DestroyDB(db_name_, options);
-  Status s = DB::Open(options, db_name_, &db);
-  assert(s.ok());
-  assert(db);
-
-  // create couple files
-  for (int i = 1000; i < 2000; ++i) {
-    db->Put(WriteOptions(), ToString(i),
-            std::string(kWriteBufferSize / 10, 'a' + (i % 26)));
-  }
-
-  auto l0_files = collector->GetFlushedFiles();
-  ASSERT_OK(db->CompactFiles(CompactionOptions(), l0_files, 1));
-
-  // verify all compaction input files are deleted
-  for (auto fname : l0_files) {
-    ASSERT_EQ(Status::NotFound(), env_->FileExists(fname));
-  }
-  delete db;
-}
-
-TEST_F(CompactFilesTest, CapturingPendingFiles) {
-  Options options;
-  options.create_if_missing = true;
-  // Disable RocksDB background compaction.
-  options.compaction_style = kCompactionStyleNone;
-  // Always do full scans for obsolete files (needed to reproduce the issue).
-  options.delete_obsolete_files_period_micros = 0;
-
-  // Add listener.
-  FlushedFileCollector* collector = new FlushedFileCollector();
-  options.listeners.emplace_back(collector);
-
-  DB* db = nullptr;
-  DestroyDB(db_name_, options);
-  Status s = DB::Open(options, db_name_, &db);
-  assert(s.ok());
-  assert(db);
-
-  // Create 5 files.
-  for (int i = 0; i < 5; ++i) {
-    db->Put(WriteOptions(), "key" + ToString(i), "value");
-    db->Flush(FlushOptions());
-  }
-
-  auto l0_files = collector->GetFlushedFiles();
-  EXPECT_EQ(5, l0_files.size());
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency({
-      {"CompactFilesImpl:2", "CompactFilesTest.CapturingPendingFiles:0"},
-      {"CompactFilesTest.CapturingPendingFiles:1", "CompactFilesImpl:3"},
-  });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  // Start compacting files.
-  std::thread compaction_thread(
-      [&] { EXPECT_OK(db->CompactFiles(CompactionOptions(), l0_files, 1)); });
-
-  // In the meantime flush another file.
-  TEST_SYNC_POINT("CompactFilesTest.CapturingPendingFiles:0");
-  db->Put(WriteOptions(), "key5", "value");
-  db->Flush(FlushOptions());
-  TEST_SYNC_POINT("CompactFilesTest.CapturingPendingFiles:1");
-
-  compaction_thread.join();
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-
-  delete db;
-
-  // Make sure we can reopen the DB.
-  s = DB::Open(options, db_name_, &db);
-  ASSERT_TRUE(s.ok());
-  assert(db);
-  delete db;
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
-
-#else
-#include <stdio.h>
-
-int main(int argc, char** argv) {
-  fprintf(stderr,
-          "SKIPPED as DBImpl::CompactFiles is not supported in ROCKSDB_LITE\n");
-  return 0;
-}
-
-#endif  // !ROCKSDB_LITE

db/compacted_db_impl.cc

@@ -1,163 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-
-#ifndef ROCKSDB_LITE
-#include "db/compacted_db_impl.h"
-#include "db/db_impl.h"
-#include "db/version_set.h"
-#include "table/get_context.h"
-
-namespace rocksdb {
-
-extern void MarkKeyMayExist(void* arg);
-extern bool SaveValue(void* arg, const ParsedInternalKey& parsed_key,
-                      const Slice& v, bool hit_and_return);
-
-CompactedDBImpl::CompactedDBImpl(
-  const DBOptions& options, const std::string& dbname)
-  : DBImpl(options, dbname) {
-}
-
-CompactedDBImpl::~CompactedDBImpl() {
-}
-
-size_t CompactedDBImpl::FindFile(const Slice& key) {
-  size_t left = 0;
-  size_t right = files_.num_files - 1;
-  while (left < right) {
-    size_t mid = (left + right) >> 1;
-    const FdWithKeyRange& f = files_.files[mid];
-    if (user_comparator_->Compare(ExtractUserKey(f.largest_key), key) < 0) {
-      // Key at "mid.largest" is < "target".  Therefore all
-      // files at or before "mid" are uninteresting.
-      left = mid + 1;
-    } else {
-      // Key at "mid.largest" is >= "target".  Therefore all files
-      // after "mid" are uninteresting.
-      right = mid;
-    }
-  }
-  return right;
-}
-
-Status CompactedDBImpl::Get(const ReadOptions& options,
-     ColumnFamilyHandle*, const Slice& key, std::string* value) {
-  GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
-                         GetContext::kNotFound, key, value, nullptr, nullptr,
-                         nullptr);
-  LookupKey lkey(key, kMaxSequenceNumber);
-  files_.files[FindFile(key)].fd.table_reader->Get(
-      options, lkey.internal_key(), &get_context);
-  if (get_context.State() == GetContext::kFound) {
-    return Status::OK();
-  }
-  return Status::NotFound();
-}
-
-std::vector<Status> CompactedDBImpl::MultiGet(const ReadOptions& options,
-    const std::vector<ColumnFamilyHandle*>&,
-    const std::vector<Slice>& keys, std::vector<std::string>* values) {
-  autovector<TableReader*, 16> reader_list;
-  for (const auto& key : keys) {
-    const FdWithKeyRange& f = files_.files[FindFile(key)];
-    if (user_comparator_->Compare(key, ExtractUserKey(f.smallest_key)) < 0) {
-      reader_list.push_back(nullptr);
-    } else {
-      LookupKey lkey(key, kMaxSequenceNumber);
-      f.fd.table_reader->Prepare(lkey.internal_key());
-      reader_list.push_back(f.fd.table_reader);
-    }
-  }
-  std::vector<Status> statuses(keys.size(), Status::NotFound());
-  values->resize(keys.size());
-  int idx = 0;
-  for (auto* r : reader_list) {
-    if (r != nullptr) {
-      GetContext get_context(user_comparator_, nullptr, nullptr, nullptr,
-                             GetContext::kNotFound, keys[idx], &(*values)[idx],
-                             nullptr, nullptr, nullptr);
-      LookupKey lkey(keys[idx], kMaxSequenceNumber);
-      r->Get(options, lkey.internal_key(), &get_context);
-      if (get_context.State() == GetContext::kFound) {
-        statuses[idx] = Status::OK();
-      }
-    }
-    ++idx;
-  }
-  return statuses;
-}
-
-Status CompactedDBImpl::Init(const Options& options) {
-  mutex_.Lock();
-  ColumnFamilyDescriptor cf(kDefaultColumnFamilyName,
-                            ColumnFamilyOptions(options));
-  Status s = Recover({cf}, true /* read only */, false, true);
-  if (s.ok()) {
-    cfd_ = reinterpret_cast<ColumnFamilyHandleImpl*>(
-              DefaultColumnFamily())->cfd();
-    delete cfd_->InstallSuperVersion(new SuperVersion(), &mutex_);
-  }
-  mutex_.Unlock();
-  if (!s.ok()) {
-    return s;
-  }
-  NewThreadStatusCfInfo(cfd_);
-  version_ = cfd_->GetSuperVersion()->current;
-  user_comparator_ = cfd_->user_comparator();
-  auto* vstorage = version_->storage_info();
-  if (vstorage->num_non_empty_levels() == 0) {
-    return Status::NotSupported("no file exists");
-  }
-  const LevelFilesBrief& l0 = vstorage->LevelFilesBrief(0);
-  // L0 should not have files
-  if (l0.num_files > 1) {
-    return Status::NotSupported("L0 contain more than 1 file");
-  }
-  if (l0.num_files == 1) {
-    if (vstorage->num_non_empty_levels() > 1) {
-      return Status::NotSupported("Both L0 and other level contain files");
-    }
-    files_ = l0;
-    return Status::OK();
-  }
-
-  for (int i = 1; i < vstorage->num_non_empty_levels() - 1; ++i) {
-    if (vstorage->LevelFilesBrief(i).num_files > 0) {
-      return Status::NotSupported("Other levels also contain files");
-    }
-  }
-
-  int level = vstorage->num_non_empty_levels() - 1;
-  if (vstorage->LevelFilesBrief(level).num_files > 0) {
-    files_ = vstorage->LevelFilesBrief(level);
-    return Status::OK();
-  }
-  return Status::NotSupported("no file exists");
-}
-
-Status CompactedDBImpl::Open(const Options& options,
-                             const std::string& dbname, DB** dbptr) {
-  *dbptr = nullptr;
-
-  if (options.max_open_files != -1) {
-    return Status::InvalidArgument("require max_open_files = -1");
-  }
-  if (options.merge_operator.get() != nullptr) {
-    return Status::InvalidArgument("merge operator is not supported");
-  }
-  DBOptions db_options(options);
-  std::unique_ptr<CompactedDBImpl> db(new CompactedDBImpl(db_options, dbname));
-  Status s = db->Init(options);
-  if (s.ok()) {
-    Log(INFO_LEVEL, db->db_options_.info_log,
-        "Opened the db as fully compacted mode");
-    LogFlush(db->db_options_.info_log);
-    *dbptr = db.release();
-  }
-  return s;
-}
-
-}   // namespace rocksdb
-#endif  // ROCKSDB_LITE

db/compacted_db_impl.h

@@ -1,95 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-
-#pragma once
-#ifndef ROCKSDB_LITE
-#include "db/db_impl.h"
-#include <vector>
-#include <string>
-
-namespace rocksdb {
-
-class CompactedDBImpl : public DBImpl {
- public:
-  CompactedDBImpl(const DBOptions& options, const std::string& dbname);
-  virtual ~CompactedDBImpl();
-
-  static Status Open(const Options& options, const std::string& dbname,
-                     DB** dbptr);
-
-  // Implementations of the DB interface
-  using DB::Get;
-  virtual Status Get(const ReadOptions& options,
-                     ColumnFamilyHandle* column_family, const Slice& key,
-                     std::string* value) override;
-  using DB::MultiGet;
-  virtual std::vector<Status> MultiGet(
-      const ReadOptions& options,
-      const std::vector<ColumnFamilyHandle*>&,
-      const std::vector<Slice>& keys, std::vector<std::string>* values)
-    override;
-
-  using DBImpl::Put;
-  virtual Status Put(const WriteOptions& options,
-                     ColumnFamilyHandle* column_family, const Slice& key,
-                     const Slice& value) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
-  using DBImpl::Merge;
-  virtual Status Merge(const WriteOptions& options,
-                       ColumnFamilyHandle* column_family, const Slice& key,
-                       const Slice& value) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
-  using DBImpl::Delete;
-  virtual Status Delete(const WriteOptions& options,
-                        ColumnFamilyHandle* column_family,
-                        const Slice& key) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
-  virtual Status Write(const WriteOptions& options,
-                       WriteBatch* updates) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
-  using DBImpl::CompactRange;
-  virtual Status CompactRange(const CompactRangeOptions& options,
-                              ColumnFamilyHandle* column_family,
-                              const Slice* begin, const Slice* end) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
-
-  virtual Status DisableFileDeletions() override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
-  virtual Status EnableFileDeletions(bool force) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
-  virtual Status GetLiveFiles(std::vector<std::string>&,
-                              uint64_t* manifest_file_size,
-                              bool flush_memtable = true) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
-  using DBImpl::Flush;
-  virtual Status Flush(const FlushOptions& options,
-                       ColumnFamilyHandle* column_family) override {
-    return Status::NotSupported("Not supported in compacted db mode.");
-  }
-
- private:
-  friend class DB;
-  inline size_t FindFile(const Slice& key);
-  Status Init(const Options& options);
-
-  ColumnFamilyData* cfd_;
-  Version* version_;
-  const Comparator* user_comparator_;
-  LevelFilesBrief files_;
-
-  // No copying allowed
-  CompactedDBImpl(const CompactedDBImpl&);
-  void operator=(const CompactedDBImpl&);
-};
-}
-#endif  // ROCKSDB_LITE

db/compaction.cc

@@ -1,4 +1,4 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -9,435 +9,237 @@
 
 #include "db/compaction.h"
 
-#ifndef __STDC_FORMAT_MACROS
-#define __STDC_FORMAT_MACROS
-#endif
-
-#include <inttypes.h>
-#include <vector>
-
-#include "db/column_family.h"
-#include "rocksdb/compaction_filter.h"
-#include "util/logging.h"
-#include "util/sync_point.h"
-
 namespace rocksdb {
 
-uint64_t TotalFileSize(const std::vector<FileMetaData*>& files) {
+static uint64_t TotalFileSize(const std::vector<FileMetaData*>& files) {
   uint64_t sum = 0;
   for (size_t i = 0; i < files.size() && files[i]; i++) {
-    sum += files[i]->fd.GetFileSize();
+    sum += files[i]->file_size;
   }
   return sum;
 }
 
-void Compaction::SetInputVersion(Version* _input_version) {
-  input_version_ = _input_version;
-  cfd_ = input_version_->cfd();
+Compaction::Compaction(Version* input_version, int level, int out_level,
+                       uint64_t target_file_size,
+                       uint64_t max_grandparent_overlap_bytes,
+                       bool seek_compaction, bool enable_compression)
+    : level_(level),
+      out_level_(out_level),
+      max_output_file_size_(target_file_size),
+      max_grandparent_overlap_bytes_(max_grandparent_overlap_bytes),
+      input_version_(input_version),
+      number_levels_(input_version_->NumberLevels()),
+      seek_compaction_(seek_compaction),
+      enable_compression_(enable_compression),
+      grandparent_index_(0),
+      seen_key_(false),
+      overlapped_bytes_(0),
+      base_index_(-1),
+      parent_index_(-1),
+      score_(0),
+      bottommost_level_(false),
+      is_full_compaction_(false),
+      is_manual_compaction_(false),
+      level_ptrs_(std::vector<size_t>(number_levels_)) {
 
-  cfd_->Ref();
   input_version_->Ref();
-  edit_.SetColumnFamily(cfd_->GetID());
-}
-
-void Compaction::GetBoundaryKeys(
-    VersionStorageInfo* vstorage,
-    const std::vector<CompactionInputFiles>& inputs, Slice* smallest_user_key,
-    Slice* largest_user_key) {
-  bool initialized = false;
-  const Comparator* ucmp = vstorage->InternalComparator()->user_comparator();
-  for (size_t i = 0; i < inputs.size(); ++i) {
-    if (inputs[i].files.empty()) {
-      continue;
-    }
-    if (inputs[i].level == 0) {
-      // we need to consider all files on level 0
-      for (const auto* f : inputs[i].files) {
-        const Slice& start_user_key = f->smallest.user_key();
-        if (!initialized ||
-            ucmp->Compare(start_user_key, *smallest_user_key) < 0) {
-          *smallest_user_key = start_user_key;
-        }
-        const Slice& end_user_key = f->largest.user_key();
-        if (!initialized ||
-            ucmp->Compare(end_user_key, *largest_user_key) > 0) {
-          *largest_user_key = end_user_key;
-        }
-        initialized = true;
-      }
-    } else {
-      // we only need to consider the first and last file
-      const Slice& start_user_key = inputs[i].files[0]->smallest.user_key();
-      if (!initialized ||
-          ucmp->Compare(start_user_key, *smallest_user_key) < 0) {
-        *smallest_user_key = start_user_key;
-      }
-      const Slice& end_user_key = inputs[i].files.back()->largest.user_key();
-      if (!initialized || ucmp->Compare(end_user_key, *largest_user_key) > 0) {
-        *largest_user_key = end_user_key;
-      }
-      initialized = true;
-    }
+  edit_ = new VersionEdit();
+  for (int i = 0; i < number_levels_; i++) {
+    level_ptrs_[i] = 0;
   }
 }
 
-// helper function to determine if compaction is creating files at the
-// bottommost level
-bool Compaction::IsBottommostLevel(
-    int output_level, VersionStorageInfo* vstorage,
-    const std::vector<CompactionInputFiles>& inputs) {
-  if (inputs[0].level == 0 &&
-      inputs[0].files.back() != vstorage->LevelFiles(0).back()) {
-    return false;
-  }
-
-  Slice smallest_key, largest_key;
-  GetBoundaryKeys(vstorage, inputs, &smallest_key, &largest_key);
-
-  // Checks whether there are files living beyond the output_level.
-  // If lower levels have files, it checks for overlap between files
-  // if the compaction process and those files.
-  // Bottomlevel optimizations can be made if there are no files in
-  // lower levels or if there is no overlap with the files in
-  // the lower levels.
-  for (int i = output_level + 1; i < vstorage->num_levels(); i++) {
-    // It is not the bottommost level if there are files in higher
-    // levels when the output level is 0 or if there are files in
-    // higher levels which overlap with files to be compacted.
-    // output_level == 0 means that we want it to be considered
-    // s the bottommost level only if the last file on the level
-    // is a part of the files to be compacted - this is verified by
-    // the first if condition in this function
-    if (vstorage->NumLevelFiles(i) > 0 &&
-        (output_level == 0 ||
-         vstorage->OverlapInLevel(i, &smallest_key, &largest_key))) {
-      return false;
-    }
-  }
-  return true;
-}
-
-// test function to validate the functionality of IsBottommostLevel()
-// function -- determines if compaction with inputs and storage is bottommost
-bool Compaction::TEST_IsBottommostLevel(
-    int output_level, VersionStorageInfo* vstorage,
-    const std::vector<CompactionInputFiles>& inputs) {
-  return IsBottommostLevel(output_level, vstorage, inputs);
-}
-
-bool Compaction::IsFullCompaction(
-    VersionStorageInfo* vstorage,
-    const std::vector<CompactionInputFiles>& inputs) {
-  size_t num_files_in_compaction = 0;
-  size_t total_num_files = 0;
-  for (int l = 0; l < vstorage->num_levels(); l++) {
-    total_num_files += vstorage->NumLevelFiles(l);
-  }
-  for (size_t i = 0; i < inputs.size(); i++) {
-    num_files_in_compaction += inputs[i].size();
-  }
-  return num_files_in_compaction == total_num_files;
-}
-
-Compaction::Compaction(VersionStorageInfo* vstorage,
-                       const MutableCFOptions& _mutable_cf_options,
-                       std::vector<CompactionInputFiles> _inputs,
-                       int _output_level, uint64_t _target_file_size,
-                       uint64_t _max_grandparent_overlap_bytes,
-                       uint32_t _output_path_id, CompressionType _compression,
-                       std::vector<FileMetaData*> _grandparents,
-                       bool _manual_compaction, double _score,
-                       bool _deletion_compaction,
-                       CompactionReason _compaction_reason)
-    : start_level_(_inputs[0].level),
-      output_level_(_output_level),
-      max_output_file_size_(_target_file_size),
-      max_grandparent_overlap_bytes_(_max_grandparent_overlap_bytes),
-      mutable_cf_options_(_mutable_cf_options),
-      input_version_(nullptr),
-      number_levels_(vstorage->num_levels()),
-      cfd_(nullptr),
-      output_path_id_(_output_path_id),
-      output_compression_(_compression),
-      deletion_compaction_(_deletion_compaction),
-      inputs_(std::move(_inputs)),
-      grandparents_(std::move(_grandparents)),
-      score_(_score),
-      bottommost_level_(IsBottommostLevel(output_level_, vstorage, inputs_)),
-      is_full_compaction_(IsFullCompaction(vstorage, inputs_)),
-      is_manual_compaction_(_manual_compaction),
-      compaction_reason_(_compaction_reason) {
-  MarkFilesBeingCompacted(true);
-  if (is_manual_compaction_) {
-    compaction_reason_ = CompactionReason::kManualCompaction;
-  }
-
-#ifndef NDEBUG
-  for (size_t i = 1; i < inputs_.size(); ++i) {
-    assert(inputs_[i].level > inputs_[i - 1].level);
-  }
-#endif
-
-  // setup input_levels_
-  {
-    input_levels_.resize(num_input_levels());
-    for (size_t which = 0; which < num_input_levels(); which++) {
-      DoGenerateLevelFilesBrief(&input_levels_[which], inputs_[which].files,
-                                &arena_);
-    }
-  }
-
-  Slice smallest_user_key;
-  GetBoundaryKeys(vstorage, inputs_, &smallest_user_key, &largest_user_key_);
-}
-
 Compaction::~Compaction() {
+  delete edit_;
   if (input_version_ != nullptr) {
     input_version_->Unref();
   }
-  if (cfd_ != nullptr) {
-    if (cfd_->Unref()) {
-      delete cfd_;
-    }
-  }
-}
-
-bool Compaction::InputCompressionMatchesOutput() const {
-  VersionStorageInfo* vstorage = input_version_->storage_info();
-  int base_level = vstorage->base_level();
-  bool matches =
-      (GetCompressionType(*cfd_->ioptions(), vstorage, mutable_cf_options_,
-                          start_level_, base_level) == output_compression_);
-  if (matches) {
-    TEST_SYNC_POINT("Compaction::InputCompressionMatchesOutput:Matches");
-    return true;
-  }
-  TEST_SYNC_POINT("Compaction::InputCompressionMatchesOutput:DidntMatch");
-  return matches;
 }
 
 bool Compaction::IsTrivialMove() const {
   // Avoid a move if there is lots of overlapping grandparent data.
   // Otherwise, the move could create a parent file that will require
   // a very expensive merge later on.
-  // If start_level_== output_level_, the purpose is to force compaction
-  // filter to be applied to that level, and thus cannot be a trivial move.
-
-  // Check if start level have files with overlapping ranges
-  if (start_level_ == 0 &&
-      input_version_->storage_info()->level0_non_overlapping() == false) {
-    // We cannot move files from L0 to L1 if the files are overlapping
-    return false;
-  }
-
-  if (is_manual_compaction_ &&
-      (cfd_->ioptions()->compaction_filter != nullptr ||
-       cfd_->ioptions()->compaction_filter_factory != nullptr)) {
-    // This is a manual compaction and we have a compaction filter that should
-    // be executed, we cannot do a trivial move
-    return false;
-  }
-
-  // Used in universal compaction, where trivial move can be done if the
-  // input files are non overlapping
-  if ((cfd_->ioptions()->compaction_options_universal.allow_trivial_move) &&
-      (output_level_ != 0)) {
-    return is_trivial_move_;
-  }
-
-  return (start_level_ != output_level_ && num_input_levels() == 1 &&
-          input(0, 0)->fd.GetPathId() == output_path_id() &&
-          InputCompressionMatchesOutput() &&
+  // If level_== out_level_, the purpose is to force compaction filter to be
+  // applied to that level, and thus cannot be a trivia move.
+  return (level_ != out_level_ &&
+          num_input_files(0) == 1 &&
+          num_input_files(1) == 0 &&
           TotalFileSize(grandparents_) <= max_grandparent_overlap_bytes_);
 }
 
-void Compaction::AddInputDeletions(VersionEdit* out_edit) {
-  for (size_t which = 0; which < num_input_levels(); which++) {
+void Compaction::AddInputDeletions(VersionEdit* edit) {
+  for (int which = 0; which < 2; which++) {
     for (size_t i = 0; i < inputs_[which].size(); i++) {
-      out_edit->DeleteFile(level(which), inputs_[which][i]->fd.GetNumber());
+      edit->DeleteFile(level_ + which, inputs_[which][i]->number);
     }
   }
 }
 
-bool Compaction::KeyNotExistsBeyondOutputLevel(
-    const Slice& user_key, std::vector<size_t>* level_ptrs) const {
-  assert(input_version_ != nullptr);
-  assert(level_ptrs != nullptr);
-  assert(level_ptrs->size() == static_cast<size_t>(number_levels_));
-  assert(cfd_->ioptions()->compaction_style != kCompactionStyleFIFO);
-  if (cfd_->ioptions()->compaction_style == kCompactionStyleUniversal) {
+bool Compaction::IsBaseLevelForKey(const Slice& user_key) {
+  if (input_version_->vset_->options_->compaction_style ==
+      kCompactionStyleUniversal) {
     return bottommost_level_;
   }
   // Maybe use binary search to find right entry instead of linear search?
-  const Comparator* user_cmp = cfd_->user_comparator();
-  for (int lvl = output_level_ + 1; lvl < number_levels_; lvl++) {
-    const std::vector<FileMetaData*>& files =
-        input_version_->storage_info()->LevelFiles(lvl);
-    for (; level_ptrs->at(lvl) < files.size(); level_ptrs->at(lvl)++) {
-      auto* f = files[level_ptrs->at(lvl)];
+  const Comparator* user_cmp = input_version_->vset_->icmp_.user_comparator();
+  for (int lvl = level_ + 2; lvl < number_levels_; lvl++) {
+    const std::vector<FileMetaData*>& files = input_version_->files_[lvl];
+    for (; level_ptrs_[lvl] < files.size(); ) {
+      FileMetaData* f = files[level_ptrs_[lvl]];
       if (user_cmp->Compare(user_key, f->largest.user_key()) <= 0) {
         // We've advanced far enough
         if (user_cmp->Compare(user_key, f->smallest.user_key()) >= 0) {
-          // Key falls in this file's range, so definitely
-          // exists beyond output level
+          // Key falls in this file's range, so definitely not base level
           return false;
         }
         break;
       }
+      level_ptrs_[lvl]++;
     }
   }
   return true;
 }
 
+bool Compaction::ShouldStopBefore(const Slice& internal_key) {
+  // Scan to find earliest grandparent file that contains key.
+  const InternalKeyComparator* icmp = &input_version_->vset_->icmp_;
+  while (grandparent_index_ < grandparents_.size() &&
+      icmp->Compare(internal_key,
+                    grandparents_[grandparent_index_]->largest.Encode()) > 0) {
+    if (seen_key_) {
+      overlapped_bytes_ += grandparents_[grandparent_index_]->file_size;
+    }
+    assert(grandparent_index_ + 1 >= grandparents_.size() ||
+           icmp->Compare(grandparents_[grandparent_index_]->largest.Encode(),
+                         grandparents_[grandparent_index_+1]->smallest.Encode())
+                         < 0);
+    grandparent_index_++;
+  }
+  seen_key_ = true;
+
+  if (overlapped_bytes_ > max_grandparent_overlap_bytes_) {
+    // Too much overlap for current output; start new output
+    overlapped_bytes_ = 0;
+    return true;
+  } else {
+    return false;
+  }
+}
+
 // Mark (or clear) each file that is being compacted
-void Compaction::MarkFilesBeingCompacted(bool mark_as_compacted) {
-  for (size_t i = 0; i < num_input_levels(); i++) {
-    for (size_t j = 0; j < inputs_[i].size(); j++) {
-      assert(mark_as_compacted ? !inputs_[i][j]->being_compacted
-                               : inputs_[i][j]->being_compacted);
-      inputs_[i][j]->being_compacted = mark_as_compacted;
+void Compaction::MarkFilesBeingCompacted(bool value) {
+  for (int i = 0; i < 2; i++) {
+    std::vector<FileMetaData*> v = inputs_[i];
+    for (unsigned int j = 0; j < inputs_[i].size(); j++) {
+      assert(value ? !inputs_[i][j]->being_compacted :
+                      inputs_[i][j]->being_compacted);
+      inputs_[i][j]->being_compacted = value;
     }
   }
 }
 
-// Sample output:
-// If compacting 3 L0 files, 2 L3 files and 1 L4 file, and outputting to L5,
-// print: "3@0 + 2@3 + 1@4 files to L5"
-const char* Compaction::InputLevelSummary(
-    InputLevelSummaryBuffer* scratch) const {
-  int len = 0;
-  bool is_first = true;
-  for (auto& input_level : inputs_) {
-    if (input_level.empty()) {
-      continue;
+// Is this compaction producing files at the bottommost level?
+void Compaction::SetupBottomMostLevel(bool isManual) {
+  if (input_version_->vset_->options_->compaction_style  ==
+         kCompactionStyleUniversal) {
+    // If universal compaction style is used and manual
+    // compaction is occuring, then we are guaranteed that
+    // all files will be picked in a single compaction
+    // run. We can safely set bottommost_level_ = true.
+    // If it is not manual compaction, then bottommost_level_
+    // is already set when the Compaction was created.
+    if (isManual) {
+      bottommost_level_ = true;
     }
-    if (!is_first) {
-      len +=
-          snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len, " + ");
-    } else {
-      is_first = false;
-    }
-    len += snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len,
-                    "%" ROCKSDB_PRIszt "@%d", input_level.size(),
-                    input_level.level);
+    return;
   }
-  snprintf(scratch->buffer + len, sizeof(scratch->buffer) - len,
-           " files to L%d", output_level());
-
-  return scratch->buffer;
-}
-
-uint64_t Compaction::CalculateTotalInputSize() const {
-  uint64_t size = 0;
-  for (auto& input_level : inputs_) {
-    for (auto f : input_level.files) {
-      size += f->fd.GetFileSize();
+  bottommost_level_ = true;
+  int num_levels = input_version_->vset_->NumberLevels();
+  for (int i = output_level() + 1; i < num_levels; i++) {
+    if (input_version_->NumLevelFiles(i) > 0) {
+      bottommost_level_ = false;
+      break;
     }
   }
-  return size;
 }
 
-void Compaction::ReleaseCompactionFiles(Status status) {
-  MarkFilesBeingCompacted(false);
-  cfd_->compaction_picker()->ReleaseCompactionFiles(this, status);
+void Compaction::ReleaseInputs() {
+  if (input_version_ != nullptr) {
+    input_version_->Unref();
+    input_version_ = nullptr;
+  }
 }
 
 void Compaction::ResetNextCompactionIndex() {
-  assert(input_version_ != nullptr);
-  input_version_->storage_info()->ResetNextCompactionIndex(start_level_);
+  input_version_->ResetNextCompactionIndex(level_);
 }
 
-namespace {
-int InputSummary(const std::vector<FileMetaData*>& files, char* output,
-                 int len) {
+/*
+for sizes >=10TB, print "XXTB"
+for sizes >=10GB, print "XXGB"
+etc.
+*/
+static void FileSizeSummary(unsigned long long sz, char* output, int len) {
+  const unsigned long long ull10 = 10;
+  if (sz >= ull10<<40) {
+    snprintf(output, len, "%lluTB", sz>>40);
+  } else if (sz >= ull10<<30) {
+    snprintf(output, len, "%lluGB", sz>>30);
+  } else if (sz >= ull10<<20) {
+    snprintf(output, len, "%lluMB", sz>>20);
+  } else if (sz >= ull10<<10) {
+    snprintf(output, len, "%lluKB", sz>>10);
+  } else {
+    snprintf(output, len, "%lluB", sz);
+  }
+}
+
+static int InputSummary(std::vector<FileMetaData*>& files, char* output,
+                         int len) {
   *output = '\0';
   int write = 0;
-  for (size_t i = 0; i < files.size(); i++) {
+  for (unsigned int i = 0; i < files.size(); i++) {
     int sz = len - write;
     int ret;
     char sztxt[16];
-    AppendHumanBytes(files.at(i)->fd.GetFileSize(), sztxt, 16);
-    ret = snprintf(output + write, sz, "%" PRIu64 "(%s) ",
-                   files.at(i)->fd.GetNumber(), sztxt);
-    if (ret < 0 || ret >= sz) break;
+    FileSizeSummary((unsigned long long)files.at(i)->file_size, sztxt, 16);
+    ret = snprintf(output + write, sz, "%lu(%s) ",
+                   (unsigned long)files.at(i)->number,
+                   sztxt);
+    if (ret < 0 || ret >= sz)
+      break;
     write += ret;
   }
-  // if files.size() is non-zero, overwrite the last space
-  return write - !!files.size();
+  return write;
 }
-}  // namespace
 
 void Compaction::Summary(char* output, int len) {
-  int write =
-      snprintf(output, len, "Base version %" PRIu64 " Base level %d, inputs: [",
-               input_version_->GetVersionNumber(), start_level_);
+  int write = snprintf(output, len,
+      "Base version %lu Base level %d, seek compaction:%d, inputs: [",
+      (unsigned long)input_version_->GetVersionNumber(),
+      level_,
+      seek_compaction_);
   if (write < 0 || write >= len) {
     return;
   }
 
-  for (size_t level_iter = 0; level_iter < num_input_levels(); ++level_iter) {
-    if (level_iter > 0) {
-      write += snprintf(output + write, len - write, "], [");
-      if (write < 0 || write >= len) {
-        return;
-      }
-    }
-    write +=
-        InputSummary(inputs_[level_iter].files, output + write, len - write);
-    if (write < 0 || write >= len) {
-      return;
-    }
+  write += InputSummary(inputs_[0], output+write, len-write);
+  if (write < 0 || write >= len) {
+    return;
   }
 
-  snprintf(output + write, len - write, "]");
-}
-
-uint64_t Compaction::OutputFilePreallocationSize() const {
-  uint64_t preallocation_size = 0;
-
-  if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel ||
-      output_level() > 0) {
-    preallocation_size = max_output_file_size_;
-  } else {
-    // output_level() == 0
-    assert(num_input_levels() > 0);
-    for (const auto& f : inputs_[0].files) {
-      preallocation_size += f->fd.GetFileSize();
-    }
-  }
-  // Over-estimate slightly so we don't end up just barely crossing
-  // the threshold
-  return preallocation_size + (preallocation_size / 10);
-}
-
-std::unique_ptr<CompactionFilter> Compaction::CreateCompactionFilter() const {
-  if (!cfd_->ioptions()->compaction_filter_factory) {
-    return nullptr;
+  write += snprintf(output+write, len-write, "],[");
+  if (write < 0 || write >= len) {
+    return;
   }
 
-  CompactionFilter::Context context;
-  context.is_full_compaction = is_full_compaction_;
-  context.is_manual_compaction = is_manual_compaction_;
-  context.column_family_id = cfd_->GetID();
-  return cfd_->ioptions()->compaction_filter_factory->CreateCompactionFilter(
-      context);
-}
-
-bool Compaction::IsOutputLevelEmpty() const {
-  return inputs_.back().level != output_level_ || inputs_.back().empty();
-}
-
-bool Compaction::ShouldFormSubcompactions() const {
-  if (mutable_cf_options_.max_subcompactions <= 1 || cfd_ == nullptr) {
-    return false;
-  }
-  if (cfd_->ioptions()->compaction_style == kCompactionStyleLevel) {
-    return start_level_ == 0 && !IsOutputLevelEmpty();
-  } else if (cfd_->ioptions()->compaction_style == kCompactionStyleUniversal) {
-    return number_levels_ > 1 && output_level_ > 0;
-  } else {
-    return false;
+  write += InputSummary(inputs_[1], output+write, len-write);
+  if (write < 0 || write >= len) {
+    return;
   }
+
+  snprintf(output+write, len-write, "]");
 }
 
 }  // namespace rocksdb

db/compaction.h

@@ -1,4 +1,4 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -8,300 +8,136 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
 #pragma once
-#include "util/arena.h"
-#include "util/autovector.h"
-#include "util/mutable_cf_options.h"
 #include "db/version_set.h"
 
 namespace rocksdb {
 
-// The structure that manages compaction input files associated
-// with the same physical level.
-struct CompactionInputFiles {
-  int level;
-  std::vector<FileMetaData*> files;
-  inline bool empty() const { return files.empty(); }
-  inline size_t size() const { return files.size(); }
-  inline void clear() { files.clear(); }
-  inline FileMetaData* operator[](size_t i) const { return files[i]; }
-};
-
 class Version;
-class ColumnFamilyData;
-class VersionStorageInfo;
-class CompactionFilter;
 
 // A Compaction encapsulates information about a compaction.
 class Compaction {
  public:
-  Compaction(VersionStorageInfo* input_version,
-             const MutableCFOptions& mutable_cf_options,
-             std::vector<CompactionInputFiles> inputs, int output_level,
-             uint64_t target_file_size, uint64_t max_grandparent_overlap_bytes,
-             uint32_t output_path_id, CompressionType compression,
-             std::vector<FileMetaData*> grandparents,
-             bool manual_compaction = false, double score = -1,
-             bool deletion_compaction = false,
-             CompactionReason compaction_reason = CompactionReason::kUnknown);
-
-  // No copying allowed
-  Compaction(const Compaction&) = delete;
-  void operator=(const Compaction&) = delete;
-
   ~Compaction();
 
-  // Returns the level associated to the specified compaction input level.
-  // If compaction_input_level is not specified, then input_level is set to 0.
-  int level(size_t compaction_input_level = 0) const {
-    return inputs_[compaction_input_level].level;
-  }
-
-  int start_level() const { return start_level_; }
+  // Return the level that is being compacted.  Inputs from "level"
+  // will be merged.
+  int level() const { return level_; }
 
   // Outputs will go to this level
-  int output_level() const { return output_level_; }
-
-  // Returns the number of input levels in this compaction.
-  size_t num_input_levels() const { return inputs_.size(); }
+  int output_level() const { return out_level_; }
 
   // Return the object that holds the edits to the descriptor done
   // by this compaction.
-  VersionEdit* edit() { return &edit_; }
+  VersionEdit* edit() { return edit_; }
 
-  // Returns the number of input files associated to the specified
-  // compaction input level.
-  // The function will return 0 if when "compaction_input_level" < 0
-  // or "compaction_input_level" >= "num_input_levels()".
-  size_t num_input_files(size_t compaction_input_level) const {
-    if (compaction_input_level < inputs_.size()) {
-      return inputs_[compaction_input_level].size();
-    }
-    return 0;
-  }
+  // "which" must be either 0 or 1
+  int num_input_files(int which) const { return inputs_[which].size(); }
 
   // Returns input version of the compaction
   Version* input_version() const { return input_version_; }
 
-  // Returns the ColumnFamilyData associated with the compaction.
-  ColumnFamilyData* column_family_data() const { return cfd_; }
+  // Return the ith input file at "level()+which" ("which" must be 0 or 1).
+  FileMetaData* input(int which, int i) const { return inputs_[which][i]; }
 
-  // Returns the file meta data of the 'i'th input file at the
-  // specified compaction input level.
-  // REQUIREMENT: "compaction_input_level" must be >= 0 and
-  //              < "input_levels()"
-  FileMetaData* input(size_t compaction_input_level, size_t i) const {
-    assert(compaction_input_level < inputs_.size());
-    return inputs_[compaction_input_level][i];
-  }
-
-  // Returns the list of file meta data of the specified compaction
-  // input level.
-  // REQUIREMENT: "compaction_input_level" must be >= 0 and
-  //              < "input_levels()"
-  const std::vector<FileMetaData*>* inputs(size_t compaction_input_level) {
-    assert(compaction_input_level < inputs_.size());
-    return &inputs_[compaction_input_level].files;
-  }
-
-  // Returns the LevelFilesBrief of the specified compaction input level.
-  const LevelFilesBrief* input_levels(size_t compaction_input_level) const {
-    return &input_levels_[compaction_input_level];
-  }
+  std::vector<FileMetaData*>* inputs(int which) { return &inputs_[which]; }
 
   // Maximum size of files to build during this compaction.
-  uint64_t max_output_file_size() const { return max_output_file_size_; }
+  uint64_t MaxOutputFileSize() const { return max_output_file_size_; }
 
-  // What compression for output
-  CompressionType output_compression() const { return output_compression_; }
-
-  // Whether need to write output file to second DB path.
-  uint32_t output_path_id() const { return output_path_id_; }
+  // Whether compression will be enabled for compaction outputs
+  bool enable_compression() const { return enable_compression_; }
 
   // Is this a trivial compaction that can be implemented by just
   // moving a single input file to the next level (no merging or splitting)
   bool IsTrivialMove() const;
 
-  // If true, then the compaction can be done by simply deleting input files.
-  bool deletion_compaction() const { return deletion_compaction_; }
-
   // Add all inputs to this compaction as delete operations to *edit.
   void AddInputDeletions(VersionEdit* edit);
 
-  // Returns true if the available information we have guarantees that
-  // the input "user_key" does not exist in any level beyond "output_level()".
-  bool KeyNotExistsBeyondOutputLevel(const Slice& user_key,
-                                     std::vector<size_t>* level_ptrs) const;
+  // Returns true if the information we have available guarantees that
+  // the compaction is producing data in "level+1" for which no data exists
+  // in levels greater than "level+1".
+  bool IsBaseLevelForKey(const Slice& user_key);
 
-  // Clear all files to indicate that they are not being compacted
-  // Delete this compaction from the list of running compactions.
-  //
-  // Requirement: DB mutex held
-  void ReleaseCompactionFiles(Status status);
+  // Returns true iff we should stop building the current output
+  // before processing "internal_key".
+  bool ShouldStopBefore(const Slice& internal_key);
+
+  // Release the input version for the compaction, once the compaction
+  // is successful.
+  void ReleaseInputs();
 
-  // Returns the summary of the compaction in "output" with maximum "len"
-  // in bytes.  The caller is responsible for the memory management of
-  // "output".
   void Summary(char* output, int len);
 
   // Return the score that was used to pick this compaction run.
   double score() const { return score_; }
 
   // Is this compaction creating a file in the bottom most level?
-  bool bottommost_level() const { return bottommost_level_; }
+  bool BottomMostLevel() { return bottommost_level_; }
 
   // Does this compaction include all sst files?
-  bool is_full_compaction() const { return is_full_compaction_; }
+  bool IsFullCompaction() { return is_full_compaction_; }
 
   // Was this compaction triggered manually by the client?
-  bool is_manual_compaction() const { return is_manual_compaction_; }
+  bool IsManualCompaction() { return is_manual_compaction_; }
 
-  // Used when allow_trivial_move option is set in
-  // Universal compaction. If all the input files are
-  // non overlapping, then is_trivial_move_ variable
-  // will be set true, else false
-  void set_is_trivial_move(bool trivial_move) {
-    is_trivial_move_ = trivial_move;
-  }
+ private:
+  friend class CompactionPicker;
+  friend class UniversalCompactionPicker;
+  friend class LevelCompactionPicker;
 
-  // Used when allow_trivial_move option is set in
-  // Universal compaction. Returns true, if the input files
-  // are non-overlapping and can be trivially moved.
-  bool is_trivial_move() const { return is_trivial_move_; }
+  Compaction(Version* input_version, int level, int out_level,
+             uint64_t target_file_size, uint64_t max_grandparent_overlap_bytes,
+             bool seek_compaction = false, bool enable_compression = true);
 
-  // How many total levels are there?
-  int number_levels() const { return number_levels_; }
+  int level_;
+  int out_level_; // levels to which output files are stored
+  uint64_t max_output_file_size_;
+  uint64_t max_grandparent_overlap_bytes_;
+  Version* input_version_;
+  VersionEdit* edit_;
+  int number_levels_;
 
-  // Return the MutableCFOptions that should be used throughout the compaction
-  // procedure
-  const MutableCFOptions* mutable_cf_options() const {
-    return &mutable_cf_options_;
-  }
+  bool seek_compaction_;
+  bool enable_compression_;
 
-  // Returns the size in bytes that the output file should be preallocated to.
-  // In level compaction, that is max_file_size_. In universal compaction, that
-  // is the sum of all input file sizes.
-  uint64_t OutputFilePreallocationSize() const;
+  // Each compaction reads inputs from "level_" and "level_+1"
+  std::vector<FileMetaData*> inputs_[2];      // The two sets of inputs
 
-  void SetInputVersion(Version* input_version);
+  // State used to check for number of of overlapping grandparent files
+  // (parent == level_ + 1, grandparent == level_ + 2)
+  std::vector<FileMetaData*> grandparents_;
+  size_t grandparent_index_;  // Index in grandparent_starts_
+  bool seen_key_;             // Some output key has been seen
+  uint64_t overlapped_bytes_;  // Bytes of overlap between current output
+                              // and grandparent files
+  int base_index_;   // index of the file in files_[level_]
+  int parent_index_; // index of some file with same range in files_[level_+1]
+  double score_;     // score that was used to pick this compaction.
 
-  struct InputLevelSummaryBuffer {
-    char buffer[128];
-  };
+  // Is this compaction creating a file in the bottom most level?
+  bool bottommost_level_;
+  // Does this compaction include all sst files?
+  bool is_full_compaction_;
 
-  const char* InputLevelSummary(InputLevelSummaryBuffer* scratch) const;
+  // Is this compaction requested by the client?
+  bool is_manual_compaction_;
 
-  uint64_t CalculateTotalInputSize() const;
+  // level_ptrs_ holds indices into input_version_->levels_: our state
+  // is that we are positioned at one of the file ranges for each
+  // higher level than the ones involved in this compaction (i.e. for
+  // all L >= level_ + 2).
+  std::vector<size_t> level_ptrs_;
+
+  // mark (or clear) all files that are being compacted
+  void MarkFilesBeingCompacted(bool);
+
+  // Initialize whether compaction producing files at the bottommost level
+  void SetupBottomMostLevel(bool isManual);
 
   // In case of compaction error, reset the nextIndex that is used
   // to pick up the next file to be compacted from files_by_size_
   void ResetNextCompactionIndex();
-
-  // Create a CompactionFilter from compaction_filter_factory
-  std::unique_ptr<CompactionFilter> CreateCompactionFilter() const;
-
-  // Is the input level corresponding to output_level_ empty?
-  bool IsOutputLevelEmpty() const;
-
-  // Should this compaction be broken up into smaller ones run in parallel?
-  bool ShouldFormSubcompactions() const;
-
-  // test function to validate the functionality of IsBottommostLevel()
-  // function -- determines if compaction with inputs and storage is bottommost
-  static bool TEST_IsBottommostLevel(
-      int output_level, VersionStorageInfo* vstorage,
-      const std::vector<CompactionInputFiles>& inputs);
-
-  TablePropertiesCollection GetOutputTableProperties() const {
-    return output_table_properties_;
-  }
-
-  void SetOutputTableProperties(TablePropertiesCollection tp) {
-    output_table_properties_ = std::move(tp);
-  }
-
-  Slice GetLargestUserKey() const { return largest_user_key_; }
-
-  CompactionReason compaction_reason() { return compaction_reason_; }
-
-  const std::vector<FileMetaData*>& grandparents() const {
-    return grandparents_;
-  }
-
-  uint64_t max_grandparent_overlap_bytes() const {
-    return max_grandparent_overlap_bytes_;
-  }
-
- private:
-  // mark (or clear) all files that are being compacted
-  void MarkFilesBeingCompacted(bool mark_as_compacted);
-
-  // get the smallest and largest key present in files to be compacted
-  static void GetBoundaryKeys(VersionStorageInfo* vstorage,
-                              const std::vector<CompactionInputFiles>& inputs,
-                              Slice* smallest_key, Slice* largest_key);
-
-  // helper function to determine if compaction with inputs and storage is
-  // bottommost
-  static bool IsBottommostLevel(
-      int output_level, VersionStorageInfo* vstorage,
-      const std::vector<CompactionInputFiles>& inputs);
-
-  static bool IsFullCompaction(VersionStorageInfo* vstorage,
-                               const std::vector<CompactionInputFiles>& inputs);
-
-  const int start_level_;    // the lowest level to be compacted
-  const int output_level_;  // levels to which output files are stored
-  uint64_t max_output_file_size_;
-  uint64_t max_grandparent_overlap_bytes_;
-  MutableCFOptions mutable_cf_options_;
-  Version* input_version_;
-  VersionEdit edit_;
-  const int number_levels_;
-  ColumnFamilyData* cfd_;
-  Arena arena_;          // Arena used to allocate space for file_levels_
-
-  const uint32_t output_path_id_;
-  CompressionType output_compression_;
-  // If true, then the comaction can be done by simply deleting input files.
-  const bool deletion_compaction_;
-
-  // Compaction input files organized by level. Constant after construction
-  const std::vector<CompactionInputFiles> inputs_;
-
-  // A copy of inputs_, organized more closely in memory
-  autovector<LevelFilesBrief, 2> input_levels_;
-
-  // State used to check for number of overlapping grandparent files
-  // (grandparent == "output_level_ + 1")
-  std::vector<FileMetaData*> grandparents_;
-  const double score_;         // score that was used to pick this compaction.
-
-  // Is this compaction creating a file in the bottom most level?
-  const bool bottommost_level_;
-  // Does this compaction include all sst files?
-  const bool is_full_compaction_;
-
-  // Is this compaction requested by the client?
-  const bool is_manual_compaction_;
-
-  // True if we can do trivial move in Universal multi level
-  // compaction
-  bool is_trivial_move_;
-
-  // Does input compression match the output compression?
-  bool InputCompressionMatchesOutput() const;
-
-  // table properties of output files
-  TablePropertiesCollection output_table_properties_;
-
-  // largest user keys in compaction
-  Slice largest_user_key_;
-
-  // Reason for compaction
-  CompactionReason compaction_reason_;
 };
 
-// Utility function
-extern uint64_t TotalFileSize(const std::vector<FileMetaData*>& files);
-
 }  // namespace rocksdb

db/compaction_iterator.cc

@@ -1,440 +0,0 @@
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-
-#include "db/compaction_iterator.h"
-#include "table/internal_iterator.h"
-
-namespace rocksdb {
-
-CompactionIterator::CompactionIterator(
-    InternalIterator* input, const Comparator* cmp, MergeHelper* merge_helper,
-    SequenceNumber last_sequence, std::vector<SequenceNumber>* snapshots,
-    SequenceNumber earliest_write_conflict_snapshot, Env* env,
-    bool expect_valid_internal_key, const Compaction* compaction,
-    const CompactionFilter* compaction_filter, LogBuffer* log_buffer)
-    : input_(input),
-      cmp_(cmp),
-      merge_helper_(merge_helper),
-      snapshots_(snapshots),
-      earliest_write_conflict_snapshot_(earliest_write_conflict_snapshot),
-      env_(env),
-      expect_valid_internal_key_(expect_valid_internal_key),
-      compaction_(compaction),
-      compaction_filter_(compaction_filter),
-      log_buffer_(log_buffer),
-      merge_out_iter_(merge_helper_) {
-  assert(compaction_filter_ == nullptr || compaction_ != nullptr);
-  bottommost_level_ =
-      compaction_ == nullptr ? false : compaction_->bottommost_level();
-  if (compaction_ != nullptr) {
-    level_ptrs_ = std::vector<size_t>(compaction_->number_levels(), 0);
-  }
-
-  if (snapshots_->size() == 0) {
-    // optimize for fast path if there are no snapshots
-    visible_at_tip_ = last_sequence;
-    earliest_snapshot_ = visible_at_tip_;
-    latest_snapshot_ = 0;
-  } else {
-    visible_at_tip_ = 0;
-    earliest_snapshot_ = snapshots_->at(0);
-    latest_snapshot_ = snapshots_->back();
-  }
-  if (compaction_filter_ != nullptr && compaction_filter_->IgnoreSnapshots()) {
-    ignore_snapshots_ = true;
-  } else {
-    ignore_snapshots_ = false;
-  }
-}
-
-void CompactionIterator::ResetRecordCounts() {
-  iter_stats_.num_record_drop_user = 0;
-  iter_stats_.num_record_drop_hidden = 0;
-  iter_stats_.num_record_drop_obsolete = 0;
-}
-
-void CompactionIterator::SeekToFirst() {
-  NextFromInput();
-  PrepareOutput();
-}
-
-void CompactionIterator::Next() {
-  // If there is a merge output, return it before continuing to process the
-  // input.
-  if (merge_out_iter_.Valid()) {
-    merge_out_iter_.Next();
-
-    // Check if we returned all records of the merge output.
-    if (merge_out_iter_.Valid()) {
-      key_ = merge_out_iter_.key();
-      value_ = merge_out_iter_.value();
-      bool valid_key __attribute__((__unused__)) =
-          ParseInternalKey(key_, &ikey_);
-      // MergeUntil stops when it encounters a corrupt key and does not
-      // include them in the result, so we expect the keys here to be valid.
-      assert(valid_key);
-      // Keep current_key_ in sync.
-      current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
-      key_ = current_key_.GetKey();
-      ikey_.user_key = current_key_.GetUserKey();
-      valid_ = true;
-    } else {
-      // MergeHelper moves the iterator to the first record after the merged
-      // records, so even though we reached the end of the merge output, we do
-      // not want to advance the iterator.
-      NextFromInput();
-    }
-  } else {
-    // Only advance the input iterator if there is no merge output and the
-    // iterator is not already at the next record.
-    if (!at_next_) {
-      input_->Next();
-    }
-    NextFromInput();
-  }
-
-  if (valid_) {
-    // Record that we've ouputted a record for the current key.
-    has_outputted_key_ = true;
-  }
-
-  PrepareOutput();
-}
-
-void CompactionIterator::NextFromInput() {
-  at_next_ = false;
-  valid_ = false;
-
-  while (!valid_ && input_->Valid()) {
-    key_ = input_->key();
-    value_ = input_->value();
-    iter_stats_.num_input_records++;
-
-    if (!ParseInternalKey(key_, &ikey_)) {
-      // If `expect_valid_internal_key_` is false, return the corrupted key
-      // and let the caller decide what to do with it.
-      // TODO(noetzli): We should have a more elegant solution for this.
-      if (expect_valid_internal_key_) {
-        assert(!"Corrupted internal key not expected.");
-        status_ = Status::Corruption("Corrupted internal key not expected.");
-        break;
-      }
-      key_ = current_key_.SetKey(key_);
-      has_current_user_key_ = false;
-      current_user_key_sequence_ = kMaxSequenceNumber;
-      current_user_key_snapshot_ = 0;
-      iter_stats_.num_input_corrupt_records++;
-      valid_ = true;
-      break;
-    }
-
-    // Update input statistics
-    if (ikey_.type == kTypeDeletion || ikey_.type == kTypeSingleDeletion) {
-      iter_stats_.num_input_deletion_records++;
-    }
-    iter_stats_.total_input_raw_key_bytes += key_.size();
-    iter_stats_.total_input_raw_value_bytes += value_.size();
-
-    // Check whether the user key changed. After this if statement current_key_
-    // is a copy of the current input key (maybe converted to a delete by the
-    // compaction filter). ikey_.user_key is pointing to the copy.
-    if (!has_current_user_key_ ||
-        !cmp_->Equal(ikey_.user_key, current_user_key_)) {
-      // First occurrence of this user key
-      key_ = current_key_.SetKey(key_, &ikey_);
-      current_user_key_ = ikey_.user_key;
-      has_current_user_key_ = true;
-      has_outputted_key_ = false;
-      current_user_key_sequence_ = kMaxSequenceNumber;
-      current_user_key_snapshot_ = 0;
-
-      // apply the compaction filter to the first occurrence of the user key
-      if (compaction_filter_ != nullptr && ikey_.type == kTypeValue &&
-          (visible_at_tip_ || ikey_.sequence > latest_snapshot_ ||
-           ignore_snapshots_)) {
-        // If the user has specified a compaction filter and the sequence
-        // number is greater than any external snapshot, then invoke the
-        // filter. If the return value of the compaction filter is true,
-        // replace the entry with a deletion marker.
-        bool value_changed = false;
-        bool to_delete = false;
-        compaction_filter_value_.clear();
-        {
-          StopWatchNano timer(env_, true);
-          to_delete = compaction_filter_->Filter(
-              compaction_->level(), ikey_.user_key, value_,
-              &compaction_filter_value_, &value_changed);
-          iter_stats_.total_filter_time +=
-              env_ != nullptr ? timer.ElapsedNanos() : 0;
-        }
-        if (to_delete) {
-          // convert the current key to a delete
-          ikey_.type = kTypeDeletion;
-          current_key_.UpdateInternalKey(ikey_.sequence, kTypeDeletion);
-          // no value associated with delete
-          value_.clear();
-          iter_stats_.num_record_drop_user++;
-        } else if (value_changed) {
-          value_ = compaction_filter_value_;
-        }
-      }
-    } else {
-      // Update the current key to reflect the new sequence number/type without
-      // copying the user key.
-      // TODO(rven): Compaction filter does not process keys in this path
-      // Need to have the compaction filter process multiple versions
-      // if we have versions on both sides of a snapshot
-      current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
-      key_ = current_key_.GetKey();
-      ikey_.user_key = current_key_.GetUserKey();
-    }
-
-    // If there are no snapshots, then this kv affect visibility at tip.
-    // Otherwise, search though all existing snapshots to find the earliest
-    // snapshot that is affected by this kv.
-    SequenceNumber last_sequence __attribute__((__unused__)) =
-        current_user_key_sequence_;
-    current_user_key_sequence_ = ikey_.sequence;
-    SequenceNumber last_snapshot = current_user_key_snapshot_;
-    SequenceNumber prev_snapshot = 0;  // 0 means no previous snapshot
-    current_user_key_snapshot_ =
-        visible_at_tip_ ? visible_at_tip_ : findEarliestVisibleSnapshot(
-                                                ikey_.sequence, &prev_snapshot);
-
-    if (clear_and_output_next_key_) {
-      // In the previous iteration we encountered a single delete that we could
-      // not compact out.  We will keep this Put, but can drop it's data.
-      // (See Optimization 3, below.)
-      assert(ikey_.type == kTypeValue);
-      assert(current_user_key_snapshot_ == last_snapshot);
-
-      value_.clear();
-      valid_ = true;
-      clear_and_output_next_key_ = false;
-    } else if (ikey_.type == kTypeSingleDeletion) {
-      // We can compact out a SingleDelete if:
-      // 1) We encounter the corresponding PUT -OR- we know that this key
-      //    doesn't appear past this output level
-      // =AND=
-      // 2) We've already returned a record in this snapshot -OR-
-      //    there are no earlier earliest_write_conflict_snapshot.
-      //
-      // Rule 1 is needed for SingleDelete correctness.  Rule 2 is needed to
-      // allow Transactions to do write-conflict checking (if we compacted away
-      // all keys, then we wouldn't know that a write happened in this
-      // snapshot).  If there is no earlier snapshot, then we know that there
-      // are no active transactions that need to know about any writes.
-      //
-      // Optimization 3:
-      // If we encounter a SingleDelete followed by a PUT and Rule 2 is NOT
-      // true, then we must output a SingleDelete.  In this case, we will decide
-      // to also output the PUT.  While we are compacting less by outputting the
-      // PUT now, hopefully this will lead to better compaction in the future
-      // when Rule 2 is later true (Ie, We are hoping we can later compact out
-      // both the SingleDelete and the Put, while we couldn't if we only
-      // outputted the SingleDelete now).
-      // In this case, we can save space by removing the PUT's value as it will
-      // never be read.
-      //
-      // Deletes and Merges are not supported on the same key that has a
-      // SingleDelete as it is not possible to correctly do any partial
-      // compaction of such a combination of operations.  The result of mixing
-      // those operations for a given key is documented as being undefined.  So
-      // we can choose how to handle such a combinations of operations.  We will
-      // try to compact out as much as we can in these cases.
-
-      // The easiest way to process a SingleDelete during iteration is to peek
-      // ahead at the next key.
-      ParsedInternalKey next_ikey;
-      input_->Next();
-
-      // Check whether the next key exists, is not corrupt, and is the same key
-      // as the single delete.
-      if (input_->Valid() && ParseInternalKey(input_->key(), &next_ikey) &&
-          cmp_->Equal(ikey_.user_key, next_ikey.user_key)) {
-        // Check whether the next key belongs to the same snapshot as the
-        // SingleDelete.
-        if (prev_snapshot == 0 || next_ikey.sequence > prev_snapshot) {
-          if (next_ikey.type == kTypeSingleDeletion) {
-            // We encountered two SingleDeletes in a row.  This could be due to
-            // unexpected user input.
-            // Skip the first SingleDelete and let the next iteration decide how
-            // to handle the second SingleDelete
-
-            // First SingleDelete has been skipped since we already called
-            // input_->Next().
-            ++iter_stats_.num_record_drop_obsolete;
-          } else if ((ikey_.sequence <= earliest_write_conflict_snapshot_) ||
-                     has_outputted_key_) {
-            // Found a matching value, we can drop the single delete and the
-            // value.  It is safe to drop both records since we've already
-            // outputted a key in this snapshot, or there is no earlier
-            // snapshot (Rule 2 above).
-
-            // Note: it doesn't matter whether the second key is a Put or if it
-            // is an unexpected Merge or Delete.  We will compact it out
-            // either way.
-            ++iter_stats_.num_record_drop_hidden;
-            ++iter_stats_.num_record_drop_obsolete;
-            // Already called input_->Next() once.  Call it a second time to
-            // skip past the second key.
-            input_->Next();
-          } else {
-            // Found a matching value, but we cannot drop both keys since
-            // there is an earlier snapshot and we need to leave behind a record
-            // to know that a write happened in this snapshot (Rule 2 above).
-            // Clear the value and output the SingleDelete. (The value will be
-            // outputted on the next iteration.)
-            ++iter_stats_.num_record_drop_hidden;
-
-            // Setting valid_ to true will output the current SingleDelete
-            valid_ = true;
-
-            // Set up the Put to be outputted in the next iteration.
-            // (Optimization 3).
-            clear_and_output_next_key_ = true;
-          }
-        } else {
-          // We hit the next snapshot without hitting a put, so the iterator
-          // returns the single delete.
-          valid_ = true;
-        }
-      } else {
-        // We are at the end of the input, could not parse the next key, or hit
-        // the next key. The iterator returns the single delete if the key
-        // possibly exists beyond the current output level.  We set
-        // has_current_user_key to false so that if the iterator is at the next
-        // key, we do not compare it again against the previous key at the next
-        // iteration. If the next key is corrupt, we return before the
-        // comparison, so the value of has_current_user_key does not matter.
-        has_current_user_key_ = false;
-        if (compaction_ != nullptr && ikey_.sequence <= earliest_snapshot_ &&
-            compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
-                                                       &level_ptrs_)) {
-          // Key doesn't exist outside of this range.
-          // Can compact out this SingleDelete.
-          ++iter_stats_.num_record_drop_obsolete;
-        } else {
-          // Output SingleDelete
-          valid_ = true;
-        }
-      }
-
-      if (valid_) {
-        at_next_ = true;
-      }
-    } else if (last_snapshot == current_user_key_snapshot_) {
-      // If the earliest snapshot is which this key is visible in
-      // is the same as the visibility of a previous instance of the
-      // same key, then this kv is not visible in any snapshot.
-      // Hidden by an newer entry for same user key
-      // TODO: why not > ?
-      //
-      // Note: Dropping this key will not affect TransactionDB write-conflict
-      // checking since there has already been a record returned for this key
-      // in this snapshot.
-      assert(last_sequence >= current_user_key_sequence_);
-      ++iter_stats_.num_record_drop_hidden;  // (A)
-      input_->Next();
-    } else if (compaction_ != nullptr && ikey_.type == kTypeDeletion &&
-               ikey_.sequence <= earliest_snapshot_ &&
-               compaction_->KeyNotExistsBeyondOutputLevel(ikey_.user_key,
-                                                          &level_ptrs_)) {
-      // TODO(noetzli): This is the only place where we use compaction_
-      // (besides the constructor). We should probably get rid of this
-      // dependency and find a way to do similar filtering during flushes.
-      //
-      // For this user key:
-      // (1) there is no data in higher levels
-      // (2) data in lower levels will have larger sequence numbers
-      // (3) data in layers that are being compacted here and have
-      //     smaller sequence numbers will be dropped in the next
-      //     few iterations of this loop (by rule (A) above).
-      // Therefore this deletion marker is obsolete and can be dropped.
-      //
-      // Note:  Dropping this Delete will not affect TransactionDB
-      // write-conflict checking since it is earlier than any snapshot.
-      ++iter_stats_.num_record_drop_obsolete;
-      input_->Next();
-    } else if (ikey_.type == kTypeMerge) {
-      if (!merge_helper_->HasOperator()) {
-        LogToBuffer(log_buffer_, "Options::merge_operator is null.");
-        status_ = Status::InvalidArgument(
-            "merge_operator is not properly initialized.");
-        return;
-      }
-
-      // We know the merge type entry is not hidden, otherwise we would
-      // have hit (A)
-      // We encapsulate the merge related state machine in a different
-      // object to minimize change to the existing flow.
-      merge_helper_->MergeUntil(input_, prev_snapshot, bottommost_level_);
-      merge_out_iter_.SeekToFirst();
-
-      if (merge_out_iter_.Valid()) {
-        // NOTE: key, value, and ikey_ refer to old entries.
-        //       These will be correctly set below.
-        key_ = merge_out_iter_.key();
-        value_ = merge_out_iter_.value();
-        bool valid_key __attribute__((__unused__)) =
-            ParseInternalKey(key_, &ikey_);
-        // MergeUntil stops when it encounters a corrupt key and does not
-        // include them in the result, so we expect the keys here to valid.
-        assert(valid_key);
-        // Keep current_key_ in sync.
-        current_key_.UpdateInternalKey(ikey_.sequence, ikey_.type);
-        key_ = current_key_.GetKey();
-        ikey_.user_key = current_key_.GetUserKey();
-        valid_ = true;
-      } else {
-        // all merge operands were filtered out. reset the user key, since the
-        // batch consumed by the merge operator should not shadow any keys
-        // coming after the merges
-        has_current_user_key_ = false;
-      }
-    } else {
-      valid_ = true;
-    }
-  }
-}
-
-void CompactionIterator::PrepareOutput() {
-  // Zeroing out the sequence number leads to better compression.
-  // If this is the bottommost level (no files in lower levels)
-  // and the earliest snapshot is larger than this seqno
-  // and the userkey differs from the last userkey in compaction
-  // then we can squash the seqno to zero.
-
-  // This is safe for TransactionDB write-conflict checking since transactions
-  // only care about sequence number larger than any active snapshots.
-  if (bottommost_level_ && valid_ && ikey_.sequence < earliest_snapshot_ &&
-      ikey_.type != kTypeMerge &&
-      !cmp_->Equal(compaction_->GetLargestUserKey(), ikey_.user_key)) {
-    assert(ikey_.type != kTypeDeletion && ikey_.type != kTypeSingleDeletion);
-    ikey_.sequence = 0;
-    current_key_.UpdateInternalKey(0, ikey_.type);
-  }
-}
-
-inline SequenceNumber CompactionIterator::findEarliestVisibleSnapshot(
-    SequenceNumber in, SequenceNumber* prev_snapshot) {
-  assert(snapshots_->size());
-  SequenceNumber prev __attribute__((__unused__)) = kMaxSequenceNumber;
-  for (const auto cur : *snapshots_) {
-    assert(prev == kMaxSequenceNumber || prev <= cur);
-    if (cur >= in) {
-      *prev_snapshot = prev == kMaxSequenceNumber ? 0 : prev;
-      return cur;
-    }
-    prev = cur;
-    assert(prev < kMaxSequenceNumber);
-  }
-  *prev_snapshot = prev;
-  return kMaxSequenceNumber;
-}
-
-}  // namespace rocksdb

db/compaction_iterator.h

@@ -1,149 +0,0 @@
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-#pragma once
-
-#include <algorithm>
-#include <deque>
-#include <string>
-#include <vector>
-
-#include "db/compaction.h"
-#include "db/merge_helper.h"
-#include "rocksdb/compaction_filter.h"
-#include "util/log_buffer.h"
-
-namespace rocksdb {
-
-struct CompactionIteratorStats {
-  // Compaction statistics
-  int64_t num_record_drop_user = 0;
-  int64_t num_record_drop_hidden = 0;
-  int64_t num_record_drop_obsolete = 0;
-  uint64_t total_filter_time = 0;
-
-  // Input statistics
-  // TODO(noetzli): The stats are incomplete. They are lacking everything
-  // consumed by MergeHelper.
-  uint64_t num_input_records = 0;
-  uint64_t num_input_deletion_records = 0;
-  uint64_t num_input_corrupt_records = 0;
-  uint64_t total_input_raw_key_bytes = 0;
-  uint64_t total_input_raw_value_bytes = 0;
-};
-
-class CompactionIterator {
- public:
-  CompactionIterator(InternalIterator* input, const Comparator* cmp,
-                     MergeHelper* merge_helper, SequenceNumber last_sequence,
-                     std::vector<SequenceNumber>* snapshots,
-                     SequenceNumber earliest_write_conflict_snapshot, Env* env,
-                     bool expect_valid_internal_key,
-                     const Compaction* compaction = nullptr,
-                     const CompactionFilter* compaction_filter = nullptr,
-                     LogBuffer* log_buffer = nullptr);
-
-  void ResetRecordCounts();
-
-  // Seek to the beginning of the compaction iterator output.
-  //
-  // REQUIRED: Call only once.
-  void SeekToFirst();
-
-  // Produces the next record in the compaction.
-  //
-  // REQUIRED: SeekToFirst() has been called.
-  void Next();
-
-  // Getters
-  const Slice& key() const { return key_; }
-  const Slice& value() const { return value_; }
-  const Status& status() const { return status_; }
-  const ParsedInternalKey& ikey() const { return ikey_; }
-  bool Valid() const { return valid_; }
-  const Slice& user_key() const { return current_user_key_; }
-  const CompactionIteratorStats& iter_stats() const { return iter_stats_; }
-
- private:
-  // Processes the input stream to find the next output
-  void NextFromInput();
-
-  // Do last preparations before presenting the output to the callee. At this
-  // point this only zeroes out the sequence number if possible for better
-  // compression.
-  void PrepareOutput();
-
-  // Given a sequence number, return the sequence number of the
-  // earliest snapshot that this sequence number is visible in.
-  // The snapshots themselves are arranged in ascending order of
-  // sequence numbers.
-  // Employ a sequential search because the total number of
-  // snapshots are typically small.
-  inline SequenceNumber findEarliestVisibleSnapshot(
-      SequenceNumber in, SequenceNumber* prev_snapshot);
-
-  InternalIterator* input_;
-  const Comparator* cmp_;
-  MergeHelper* merge_helper_;
-  const std::vector<SequenceNumber>* snapshots_;
-  const SequenceNumber earliest_write_conflict_snapshot_;
-  Env* env_;
-  bool expect_valid_internal_key_;
-  const Compaction* compaction_;
-  const CompactionFilter* compaction_filter_;
-  LogBuffer* log_buffer_;
-  bool bottommost_level_;
-  bool valid_ = false;
-  SequenceNumber visible_at_tip_;
-  SequenceNumber earliest_snapshot_;
-  SequenceNumber latest_snapshot_;
-  bool ignore_snapshots_;
-
-  // State
-  //
-  // Points to a copy of the current compaction iterator output (current_key_)
-  // if valid_.
-  Slice key_;
-  // Points to the value in the underlying iterator that corresponds to the
-  // current output.
-  Slice value_;
-  // The status is OK unless compaction iterator encounters a merge operand
-  // while not having a merge operator defined.
-  Status status_;
-  // Stores the user key, sequence number and type of the current compaction
-  // iterator output (or current key in the underlying iterator during
-  // NextFromInput()).
-  ParsedInternalKey ikey_;
-  // Stores whether ikey_.user_key is valid. If set to false, the user key is
-  // not compared against the current key in the underlying iterator.
-  bool has_current_user_key_ = false;
-  bool at_next_ = false;  // If false, the iterator
-  // Holds a copy of the current compaction iterator output (or current key in
-  // the underlying iterator during NextFromInput()).
-  IterKey current_key_;
-  Slice current_user_key_;
-  SequenceNumber current_user_key_sequence_;
-  SequenceNumber current_user_key_snapshot_;
-
-  // True if the iterator has already returned a record for the current key.
-  bool has_outputted_key_ = false;
-
-  // truncated the value of the next key and output it without applying any
-  // compaction rules.  This is used for outputting a put after a single delete.
-  bool clear_and_output_next_key_ = false;
-
-  MergeOutputIterator merge_out_iter_;
-  std::string compaction_filter_value_;
-  // "level_ptrs" holds indices that remember which file of an associated
-  // level we were last checking during the last call to compaction->
-  // KeyNotExistsBeyondOutputLevel(). This allows future calls to the function
-  // to pick off where it left off since each subcompaction's key range is
-  // increasing so a later call to the function must be looking for a key that
-  // is in or beyond the last file checked during the previous call
-  std::vector<size_t> level_ptrs_;
-  CompactionIteratorStats iter_stats_;
-};
-}  // namespace rocksdb

db/compaction_iterator_test.cc

@@ -1,71 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-
-#include "db/compaction_iterator.h"
-#include "util/testharness.h"
-#include "util/testutil.h"
-
-namespace rocksdb {
-
-class CompactionIteratorTest : public testing::Test {
- public:
-  CompactionIteratorTest() : cmp_(BytewiseComparator()), snapshots_({}) {}
-
-  void InitIterator(const std::vector<std::string>& ks,
-                    const std::vector<std::string>& vs,
-                    SequenceNumber last_sequence) {
-    merge_helper_.reset(new MergeHelper(Env::Default(), cmp_, nullptr, nullptr,
-                                        nullptr, 0U, false, 0));
-    iter_.reset(new test::VectorIterator(ks, vs));
-    iter_->SeekToFirst();
-    c_iter_.reset(new CompactionIterator(
-        iter_.get(), cmp_, merge_helper_.get(), last_sequence, &snapshots_,
-        kMaxSequenceNumber, Env::Default(), false));
-  }
-
-  const Comparator* cmp_;
-  std::vector<SequenceNumber> snapshots_;
-  std::unique_ptr<MergeHelper> merge_helper_;
-  std::unique_ptr<test::VectorIterator> iter_;
-  std::unique_ptr<CompactionIterator> c_iter_;
-};
-
-// It is possible that the output of the compaction iterator is empty even if
-// the input is not.
-TEST_F(CompactionIteratorTest, EmptyResult) {
-  InitIterator({test::KeyStr("a", 5, kTypeSingleDeletion),
-                test::KeyStr("a", 3, kTypeValue)},
-               {"", "val"}, 5);
-  c_iter_->SeekToFirst();
-  ASSERT_FALSE(c_iter_->Valid());
-}
-
-// If there is a corruption after a single deletion, the corrupted key should
-// be preserved.
-TEST_F(CompactionIteratorTest, CorruptionAfterSingleDeletion) {
-  InitIterator({test::KeyStr("a", 5, kTypeSingleDeletion),
-                test::KeyStr("a", 3, kTypeValue, true),
-                test::KeyStr("b", 10, kTypeValue)},
-               {"", "val", "val2"}, 10);
-  c_iter_->SeekToFirst();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("a", 5, kTypeSingleDeletion),
-            c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("a", 3, kTypeValue, true), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_TRUE(c_iter_->Valid());
-  ASSERT_EQ(test::KeyStr("b", 10, kTypeValue), c_iter_->key().ToString());
-  c_iter_->Next();
-  ASSERT_FALSE(c_iter_->Valid());
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/compaction_job.h

@@ -1,159 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-#pragma once
-
-#include <atomic>
-#include <deque>
-#include <functional>
-#include <limits>
-#include <set>
-#include <string>
-#include <utility>
-#include <vector>
-
-#include "db/column_family.h"
-#include "db/compaction_iterator.h"
-#include "db/dbformat.h"
-#include "db/flush_scheduler.h"
-#include "db/internal_stats.h"
-#include "db/job_context.h"
-#include "db/log_writer.h"
-#include "db/memtable_list.h"
-#include "db/version_edit.h"
-#include "db/write_controller.h"
-#include "db/write_thread.h"
-#include "port/port.h"
-#include "rocksdb/compaction_filter.h"
-#include "rocksdb/compaction_job_stats.h"
-#include "rocksdb/db.h"
-#include "rocksdb/env.h"
-#include "rocksdb/memtablerep.h"
-#include "rocksdb/transaction_log.h"
-#include "table/scoped_arena_iterator.h"
-#include "util/autovector.h"
-#include "util/event_logger.h"
-#include "util/stop_watch.h"
-#include "util/thread_local.h"
-
-namespace rocksdb {
-
-class MemTable;
-class TableCache;
-class Version;
-class VersionEdit;
-class VersionSet;
-class Arena;
-
-class CompactionJob {
- public:
-  CompactionJob(int job_id, Compaction* compaction, const DBOptions& db_options,
-                const EnvOptions& env_options, VersionSet* versions,
-                std::atomic<bool>* shutting_down, LogBuffer* log_buffer,
-                Directory* db_directory, Directory* output_directory,
-                Statistics* stats, InstrumentedMutex* db_mutex,
-                Status* db_bg_error,
-                std::vector<SequenceNumber> existing_snapshots,
-                SequenceNumber earliest_write_conflict_snapshot,
-                std::shared_ptr<Cache> table_cache, EventLogger* event_logger,
-                bool paranoid_file_checks, bool measure_io_stats,
-                const std::string& dbname,
-                CompactionJobStats* compaction_job_stats);
-
-  ~CompactionJob();
-
-  // no copy/move
-  CompactionJob(CompactionJob&& job) = delete;
-  CompactionJob(const CompactionJob& job) = delete;
-  CompactionJob& operator=(const CompactionJob& job) = delete;
-
-  // REQUIRED: mutex held
-  void Prepare();
-  // REQUIRED mutex not held
-  Status Run();
-
-  // REQUIRED: mutex held
-  Status Install(const MutableCFOptions& mutable_cf_options);
-
- private:
-  struct SubcompactionState;
-
-  void AggregateStatistics();
-  void GenSubcompactionBoundaries();
-
-  // update the thread status for starting a compaction.
-  void ReportStartedCompaction(Compaction* compaction);
-  void AllocateCompactionOutputFileNumbers();
-  // Call compaction filter. Then iterate through input and compact the
-  // kv-pairs
-  void ProcessKeyValueCompaction(SubcompactionState* sub_compact);
-
-  Status FinishCompactionOutputFile(const Status& input_status,
-                                    SubcompactionState* sub_compact);
-  Status InstallCompactionResults(const MutableCFOptions& mutable_cf_options);
-  void RecordCompactionIOStats();
-  Status OpenCompactionOutputFile(SubcompactionState* sub_compact);
-  void CleanupCompaction();
-  void UpdateCompactionJobStats(
-    const InternalStats::CompactionStats& stats) const;
-  void RecordDroppedKeys(const CompactionIteratorStats& c_iter_stats,
-                         CompactionJobStats* compaction_job_stats = nullptr);
-
-  void UpdateCompactionStats();
-  void UpdateCompactionInputStatsHelper(
-      int* num_files, uint64_t* bytes_read, int input_level);
-
-  void LogCompaction();
-
-  int job_id_;
-
-  // CompactionJob state
-  struct CompactionState;
-  CompactionState* compact_;
-  CompactionJobStats* compaction_job_stats_;
-  InternalStats::CompactionStats compaction_stats_;
-
-  // DBImpl state
-  const std::string& dbname_;
-  const DBOptions& db_options_;
-  const EnvOptions& env_options_;
-
-  Env* env_;
-  VersionSet* versions_;
-  std::atomic<bool>* shutting_down_;
-  LogBuffer* log_buffer_;
-  Directory* db_directory_;
-  Directory* output_directory_;
-  Statistics* stats_;
-  InstrumentedMutex* db_mutex_;
-  Status* db_bg_error_;
-  // If there were two snapshots with seq numbers s1 and
-  // s2 and s1 < s2, and if we find two instances of a key k1 then lies
-  // entirely within s1 and s2, then the earlier version of k1 can be safely
-  // deleted because that version is not visible in any snapshot.
-  std::vector<SequenceNumber> existing_snapshots_;
-
-  // This is the earliest snapshot that could be used for write-conflict
-  // checking by a transaction.  For any user-key newer than this snapshot, we
-  // should make sure not to remove evidence that a write occurred.
-  SequenceNumber earliest_write_conflict_snapshot_;
-
-  std::shared_ptr<Cache> table_cache_;
-
-  EventLogger* event_logger_;
-
-  bool bottommost_level_;
-  bool paranoid_file_checks_;
-  bool measure_io_stats_;
-  // Stores the Slices that designate the boundaries for each subcompaction
-  std::vector<Slice> boundaries_;
-  // Stores the approx size of keys covered in the range of each subcompaction
-  std::vector<uint64_t> sizes_;
-};
-
-}  // namespace rocksdb

db/compaction_job_test.cc

@@ -1,929 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-
-#ifndef ROCKSDB_LITE
-
-#include <algorithm>
-#include <map>
-#include <string>
-#include <tuple>
-
-#include "db/compaction_job.h"
-#include "db/column_family.h"
-#include "db/version_set.h"
-#include "db/writebuffer.h"
-#include "rocksdb/cache.h"
-#include "rocksdb/db.h"
-#include "rocksdb/options.h"
-#include "table/mock_table.h"
-#include "util/file_reader_writer.h"
-#include "util/string_util.h"
-#include "util/testharness.h"
-#include "util/testutil.h"
-#include "utilities/merge_operators.h"
-
-namespace rocksdb {
-
-namespace {
-
-void VerifyInitializationOfCompactionJobStats(
-      const CompactionJobStats& compaction_job_stats) {
-#if !defined(IOS_CROSS_COMPILE)
-  ASSERT_EQ(compaction_job_stats.elapsed_micros, 0U);
-
-  ASSERT_EQ(compaction_job_stats.num_input_records, 0U);
-  ASSERT_EQ(compaction_job_stats.num_input_files, 0U);
-  ASSERT_EQ(compaction_job_stats.num_input_files_at_output_level, 0U);
-
-  ASSERT_EQ(compaction_job_stats.num_output_records, 0U);
-  ASSERT_EQ(compaction_job_stats.num_output_files, 0U);
-
-  ASSERT_EQ(compaction_job_stats.is_manual_compaction, true);
-
-  ASSERT_EQ(compaction_job_stats.total_input_bytes, 0U);
-  ASSERT_EQ(compaction_job_stats.total_output_bytes, 0U);
-
-  ASSERT_EQ(compaction_job_stats.total_input_raw_key_bytes, 0U);
-  ASSERT_EQ(compaction_job_stats.total_input_raw_value_bytes, 0U);
-
-  ASSERT_EQ(compaction_job_stats.smallest_output_key_prefix[0], 0);
-  ASSERT_EQ(compaction_job_stats.largest_output_key_prefix[0], 0);
-
-  ASSERT_EQ(compaction_job_stats.num_records_replaced, 0U);
-
-  ASSERT_EQ(compaction_job_stats.num_input_deletion_records, 0U);
-  ASSERT_EQ(compaction_job_stats.num_expired_deletion_records, 0U);
-
-  ASSERT_EQ(compaction_job_stats.num_corrupt_keys, 0U);
-#endif  // !defined(IOS_CROSS_COMPILE)
-}
-
-}  // namespace
-
-// TODO(icanadi) Make it simpler once we mock out VersionSet
-class CompactionJobTest : public testing::Test {
- public:
-  CompactionJobTest()
-      : env_(Env::Default()),
-        dbname_(test::TmpDir() + "/compaction_job_test"),
-        mutable_cf_options_(Options(), ImmutableCFOptions(Options())),
-        table_cache_(NewLRUCache(50000, 16)),
-        write_buffer_(db_options_.db_write_buffer_size),
-        versions_(new VersionSet(dbname_, &db_options_, env_options_,
-                                 table_cache_.get(), &write_buffer_,
-                                 &write_controller_)),
-        shutting_down_(false),
-        mock_table_factory_(new mock::MockTableFactory()) {
-    EXPECT_OK(env_->CreateDirIfMissing(dbname_));
-    db_options_.db_paths.emplace_back(dbname_,
-                                      std::numeric_limits<uint64_t>::max());
-  }
-
-  std::string GenerateFileName(uint64_t file_number) {
-    FileMetaData meta;
-    std::vector<DbPath> db_paths;
-    db_paths.emplace_back(dbname_, std::numeric_limits<uint64_t>::max());
-    meta.fd = FileDescriptor(file_number, 0, 0);
-    return TableFileName(db_paths, meta.fd.GetNumber(), meta.fd.GetPathId());
-  }
-
-  std::string KeyStr(const std::string& user_key, const SequenceNumber seq_num,
-      const ValueType t) {
-    return InternalKey(user_key, seq_num, t).Encode().ToString();
-  }
-
-  void AddMockFile(const stl_wrappers::KVMap& contents, int level = 0) {
-    assert(contents.size() > 0);
-
-    bool first_key = true;
-    std::string smallest, largest;
-    InternalKey smallest_key, largest_key;
-    SequenceNumber smallest_seqno = kMaxSequenceNumber;
-    SequenceNumber largest_seqno = 0;
-    for (auto kv : contents) {
-      ParsedInternalKey key;
-      std::string skey;
-      std::string value;
-      std::tie(skey, value) = kv;
-      ParseInternalKey(skey, &key);
-
-      smallest_seqno = std::min(smallest_seqno, key.sequence);
-      largest_seqno = std::max(largest_seqno, key.sequence);
-
-      if (first_key ||
-          cfd_->user_comparator()->Compare(key.user_key, smallest) < 0) {
-        smallest.assign(key.user_key.data(), key.user_key.size());
-        smallest_key.DecodeFrom(skey);
-      }
-      if (first_key ||
-          cfd_->user_comparator()->Compare(key.user_key, largest) > 0) {
-        largest.assign(key.user_key.data(), key.user_key.size());
-        largest_key.DecodeFrom(skey);
-      }
-
-      first_key = false;
-    }
-
-    uint64_t file_number = versions_->NewFileNumber();
-    EXPECT_OK(mock_table_factory_->CreateMockTable(
-        env_, GenerateFileName(file_number), std::move(contents)));
-
-    VersionEdit edit;
-    edit.AddFile(level, file_number, 0, 10, smallest_key, largest_key,
-        smallest_seqno, largest_seqno, false);
-
-    mutex_.Lock();
-    versions_->LogAndApply(versions_->GetColumnFamilySet()->GetDefault(),
-                           mutable_cf_options_, &edit, &mutex_);
-    mutex_.Unlock();
-  }
-
-  void SetLastSequence(const SequenceNumber sequence_number) {
-    versions_->SetLastSequence(sequence_number + 1);
-  }
-
-  // returns expected result after compaction
-  stl_wrappers::KVMap CreateTwoFiles(bool gen_corrupted_keys) {
-    auto expected_results = mock::MakeMockFile();
-    const int kKeysPerFile = 10000;
-    const int kCorruptKeysPerFile = 200;
-    const int kMatchingKeys = kKeysPerFile / 2;
-    SequenceNumber sequence_number = 0;
-
-    auto corrupt_id = [&](int id) {
-      return gen_corrupted_keys && id > 0 && id <= kCorruptKeysPerFile;
-    };
-
-    for (int i = 0; i < 2; ++i) {
-      auto contents = mock::MakeMockFile();
-      for (int k = 0; k < kKeysPerFile; ++k) {
-        auto key = ToString(i * kMatchingKeys + k);
-        auto value = ToString(i * kKeysPerFile + k);
-        InternalKey internal_key(key, ++sequence_number, kTypeValue);
-
-        // This is how the key will look like once it's written in bottommost
-        // file
-        InternalKey bottommost_internal_key(
-            key, (key == "9999") ? sequence_number : 0, kTypeValue);
-
-        if (corrupt_id(k)) {
-          test::CorruptKeyType(&internal_key);
-          test::CorruptKeyType(&bottommost_internal_key);
-        }
-        contents.insert({ internal_key.Encode().ToString(), value });
-        if (i == 1 || k < kMatchingKeys || corrupt_id(k - kMatchingKeys)) {
-          expected_results.insert(
-              { bottommost_internal_key.Encode().ToString(), value });
-        }
-      }
-
-      AddMockFile(contents);
-    }
-
-    SetLastSequence(sequence_number);
-
-    return expected_results;
-  }
-
-  void NewDB() {
-    VersionEdit new_db;
-    new_db.SetLogNumber(0);
-    new_db.SetNextFile(2);
-    new_db.SetLastSequence(0);
-
-    const std::string manifest = DescriptorFileName(dbname_, 1);
-    unique_ptr<WritableFile> file;
-    Status s = env_->NewWritableFile(
-        manifest, &file, env_->OptimizeForManifestWrite(env_options_));
-    ASSERT_OK(s);
-    unique_ptr<WritableFileWriter> file_writer(
-        new WritableFileWriter(std::move(file), env_options_));
-    {
-      log::Writer log(std::move(file_writer), 0, false);
-      std::string record;
-      new_db.EncodeTo(&record);
-      s = log.AddRecord(record);
-    }
-    ASSERT_OK(s);
-    // Make "CURRENT" file that points to the new manifest file.
-    s = SetCurrentFile(env_, dbname_, 1, nullptr);
-
-    std::vector<ColumnFamilyDescriptor> column_families;
-    cf_options_.table_factory = mock_table_factory_;
-    cf_options_.merge_operator = merge_op_;
-    cf_options_.compaction_filter = compaction_filter_.get();
-    column_families.emplace_back(kDefaultColumnFamilyName, cf_options_);
-
-    EXPECT_OK(versions_->Recover(column_families, false));
-    cfd_ = versions_->GetColumnFamilySet()->GetDefault();
-  }
-
-  void RunCompaction(
-      const std::vector<std::vector<FileMetaData*>>& input_files,
-      const stl_wrappers::KVMap& expected_results,
-      const std::vector<SequenceNumber>& snapshots = {},
-      SequenceNumber earliest_write_conflict_snapshot = kMaxSequenceNumber) {
-    auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-
-    size_t num_input_files = 0;
-    std::vector<CompactionInputFiles> compaction_input_files;
-    for (size_t level = 0; level < input_files.size(); level++) {
-      auto level_files = input_files[level];
-      CompactionInputFiles compaction_level;
-      compaction_level.level = static_cast<int>(level);
-      compaction_level.files.insert(compaction_level.files.end(),
-          level_files.begin(), level_files.end());
-      compaction_input_files.push_back(compaction_level);
-      num_input_files += level_files.size();
-    }
-
-    Compaction compaction(cfd->current()->storage_info(),
-                          *cfd->GetLatestMutableCFOptions(),
-                          compaction_input_files, 1, 1024 * 1024, 10, 0,
-                          kNoCompression, {}, true);
-    compaction.SetInputVersion(cfd->current());
-
-    LogBuffer log_buffer(InfoLogLevel::INFO_LEVEL, db_options_.info_log.get());
-    mutex_.Lock();
-    EventLogger event_logger(db_options_.info_log.get());
-    CompactionJob compaction_job(
-        0, &compaction, db_options_, env_options_, versions_.get(),
-        &shutting_down_, &log_buffer, nullptr, nullptr, nullptr, &mutex_,
-        &bg_error_, snapshots, earliest_write_conflict_snapshot, table_cache_,
-        &event_logger, false, false, dbname_, &compaction_job_stats_);
-
-    VerifyInitializationOfCompactionJobStats(compaction_job_stats_);
-
-    compaction_job.Prepare();
-    mutex_.Unlock();
-    Status s;
-    s = compaction_job.Run();
-    ASSERT_OK(s);
-    mutex_.Lock();
-    ASSERT_OK(compaction_job.Install(*cfd->GetLatestMutableCFOptions()));
-    mutex_.Unlock();
-
-    if (expected_results.size() == 0) {
-      ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
-      ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
-      ASSERT_EQ(compaction_job_stats_.num_output_files, 0U);
-    } else {
-      ASSERT_GE(compaction_job_stats_.elapsed_micros, 0U);
-      ASSERT_EQ(compaction_job_stats_.num_input_files, num_input_files);
-      ASSERT_EQ(compaction_job_stats_.num_output_files, 1U);
-      mock_table_factory_->AssertLatestFile(expected_results);
-    }
-  }
-
-  Env* env_;
-  std::string dbname_;
-  EnvOptions env_options_;
-  MutableCFOptions mutable_cf_options_;
-  std::shared_ptr<Cache> table_cache_;
-  WriteController write_controller_;
-  DBOptions db_options_;
-  ColumnFamilyOptions cf_options_;
-  WriteBuffer write_buffer_;
-  std::unique_ptr<VersionSet> versions_;
-  InstrumentedMutex mutex_;
-  std::atomic<bool> shutting_down_;
-  std::shared_ptr<mock::MockTableFactory> mock_table_factory_;
-  CompactionJobStats compaction_job_stats_;
-  ColumnFamilyData* cfd_;
-  std::unique_ptr<CompactionFilter> compaction_filter_;
-  std::shared_ptr<MergeOperator> merge_op_;
-  Status bg_error_;
-};
-
-TEST_F(CompactionJobTest, Simple) {
-  NewDB();
-
-  auto expected_results = CreateTwoFiles(false);
-  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-  auto files = cfd->current()->storage_info()->LevelFiles(0);
-  ASSERT_EQ(2U, files.size());
-  RunCompaction({ files }, expected_results);
-}
-
-TEST_F(CompactionJobTest, SimpleCorrupted) {
-  NewDB();
-
-  auto expected_results = CreateTwoFiles(true);
-  auto cfd = versions_->GetColumnFamilySet()->GetDefault();
-  auto files = cfd->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-  ASSERT_EQ(compaction_job_stats_.num_corrupt_keys, 400U);
-}
-
-TEST_F(CompactionJobTest, SimpleDeletion) {
-  NewDB();
-
-  auto file1 = mock::MakeMockFile({{KeyStr("c", 4U, kTypeDeletion), ""},
-                                   {KeyStr("c", 3U, kTypeValue), "val"}});
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile({{KeyStr("b", 2U, kTypeValue), "val"},
-                                   {KeyStr("b", 1U, kTypeValue), "val"}});
-  AddMockFile(file2);
-
-  auto expected_results =
-      mock::MakeMockFile({{KeyStr("b", 0U, kTypeValue), "val"}});
-
-  SetLastSequence(4U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-}
-
-TEST_F(CompactionJobTest, SimpleOverwrite) {
-  NewDB();
-
-  auto file1 = mock::MakeMockFile({
-      {KeyStr("a", 3U, kTypeValue), "val2"},
-      {KeyStr("b", 4U, kTypeValue), "val3"},
-  });
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile({{KeyStr("a", 1U, kTypeValue), "val"},
-                                   {KeyStr("b", 2U, kTypeValue), "val"}});
-  AddMockFile(file2);
-
-  auto expected_results =
-      mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "val2"},
-                          {KeyStr("b", 4U, kTypeValue), "val3"}});
-
-  SetLastSequence(4U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-}
-
-TEST_F(CompactionJobTest, SimpleNonLastLevel) {
-  NewDB();
-
-  auto file1 = mock::MakeMockFile({
-      {KeyStr("a", 5U, kTypeValue), "val2"},
-      {KeyStr("b", 6U, kTypeValue), "val3"},
-  });
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile({{KeyStr("a", 3U, kTypeValue), "val"},
-                                   {KeyStr("b", 4U, kTypeValue), "val"}});
-  AddMockFile(file2, 1);
-
-  auto file3 = mock::MakeMockFile({{KeyStr("a", 1U, kTypeValue), "val"},
-                                   {KeyStr("b", 2U, kTypeValue), "val"}});
-  AddMockFile(file3, 2);
-
-  // Because level 1 is not the last level, the sequence numbers of a and b
-  // cannot be set to 0
-  auto expected_results =
-      mock::MakeMockFile({{KeyStr("a", 5U, kTypeValue), "val2"},
-                          {KeyStr("b", 6U, kTypeValue), "val3"}});
-
-  SetLastSequence(6U);
-  auto lvl0_files = cfd_->current()->storage_info()->LevelFiles(0);
-  auto lvl1_files = cfd_->current()->storage_info()->LevelFiles(1);
-  RunCompaction({lvl0_files, lvl1_files}, expected_results);
-}
-
-TEST_F(CompactionJobTest, SimpleMerge) {
-  merge_op_ = MergeOperators::CreateStringAppendOperator();
-  NewDB();
-
-  auto file1 = mock::MakeMockFile({
-      {KeyStr("a", 5U, kTypeMerge), "5"},
-      {KeyStr("a", 4U, kTypeMerge), "4"},
-      {KeyStr("a", 3U, kTypeValue), "3"},
-  });
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile(
-      {{KeyStr("b", 2U, kTypeMerge), "2"}, {KeyStr("b", 1U, kTypeValue), "1"}});
-  AddMockFile(file2);
-
-  auto expected_results =
-      mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "3,4,5"},
-                          {KeyStr("b", 2U, kTypeValue), "1,2"}});
-
-  SetLastSequence(5U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-}
-
-TEST_F(CompactionJobTest, NonAssocMerge) {
-  merge_op_ = MergeOperators::CreateStringAppendTESTOperator();
-  NewDB();
-
-  auto file1 = mock::MakeMockFile({
-      {KeyStr("a", 5U, kTypeMerge), "5"},
-      {KeyStr("a", 4U, kTypeMerge), "4"},
-      {KeyStr("a", 3U, kTypeMerge), "3"},
-  });
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile(
-      {{KeyStr("b", 2U, kTypeMerge), "2"}, {KeyStr("b", 1U, kTypeMerge), "1"}});
-  AddMockFile(file2);
-
-  auto expected_results =
-      mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), "3,4,5"},
-                          {KeyStr("b", 2U, kTypeMerge), "2"},
-                          {KeyStr("b", 1U, kTypeMerge), "1"}});
-
-  SetLastSequence(5U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-}
-
-// Filters merge operands with value 10.
-TEST_F(CompactionJobTest, MergeOperandFilter) {
-  merge_op_ = MergeOperators::CreateUInt64AddOperator();
-  compaction_filter_.reset(new test::FilterNumber(10U));
-  NewDB();
-
-  auto file1 = mock::MakeMockFile(
-      {{KeyStr("a", 5U, kTypeMerge), test::EncodeInt(5U)},
-       {KeyStr("a", 4U, kTypeMerge), test::EncodeInt(10U)},  // Filtered
-       {KeyStr("a", 3U, kTypeMerge), test::EncodeInt(3U)}});
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile({
-      {KeyStr("b", 2U, kTypeMerge), test::EncodeInt(2U)},
-      {KeyStr("b", 1U, kTypeMerge), test::EncodeInt(10U)}  // Filtered
-  });
-  AddMockFile(file2);
-
-  auto expected_results =
-      mock::MakeMockFile({{KeyStr("a", 0U, kTypeValue), test::EncodeInt(8U)},
-                          {KeyStr("b", 2U, kTypeMerge), test::EncodeInt(2U)}});
-
-  SetLastSequence(5U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-}
-
-TEST_F(CompactionJobTest, FilterSomeMergeOperands) {
-  merge_op_ = MergeOperators::CreateUInt64AddOperator();
-  compaction_filter_.reset(new test::FilterNumber(10U));
-  NewDB();
-
-  auto file1 = mock::MakeMockFile(
-      {{KeyStr("a", 5U, kTypeMerge), test::EncodeInt(5U)},
-       {KeyStr("a", 4U, kTypeMerge), test::EncodeInt(10U)},  // Filtered
-       {KeyStr("a", 3U, kTypeValue), test::EncodeInt(5U)},
-       {KeyStr("d", 8U, kTypeMerge), test::EncodeInt(10U)}});
-  AddMockFile(file1);
-
-  auto file2 =
-      mock::MakeMockFile({{KeyStr("b", 2U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("b", 1U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("c", 2U, kTypeMerge), test::EncodeInt(3U)},
-                          {KeyStr("c", 1U, kTypeValue), test::EncodeInt(7U)},
-                          {KeyStr("d", 1U, kTypeValue), test::EncodeInt(6U)}});
-  AddMockFile(file2);
-
-  auto file3 =
-      mock::MakeMockFile({{KeyStr("a", 1U, kTypeMerge), test::EncodeInt(3U)}});
-  AddMockFile(file3, 2);
-
-  auto expected_results = mock::MakeMockFile({
-      {KeyStr("a", 5U, kTypeValue), test::EncodeInt(10U)},
-      {KeyStr("c", 2U, kTypeValue), test::EncodeInt(10U)},
-      {KeyStr("d", 1U, kTypeValue), test::EncodeInt(6U)}
-      // b does not appear because the operands are filtered
-  });
-
-  SetLastSequence(5U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-}
-
-// Test where all operands/merge results are filtered out.
-TEST_F(CompactionJobTest, FilterAllMergeOperands) {
-  merge_op_ = MergeOperators::CreateUInt64AddOperator();
-  compaction_filter_.reset(new test::FilterNumber(10U));
-  NewDB();
-
-  auto file1 =
-      mock::MakeMockFile({{KeyStr("a", 11U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("a", 10U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("a", 9U, kTypeMerge), test::EncodeInt(10U)}});
-  AddMockFile(file1);
-
-  auto file2 =
-      mock::MakeMockFile({{KeyStr("b", 8U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("b", 7U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("b", 6U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("b", 5U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("b", 4U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("b", 3U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("b", 2U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("c", 2U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("c", 1U, kTypeMerge), test::EncodeInt(10U)}});
-  AddMockFile(file2);
-
-  auto file3 =
-      mock::MakeMockFile({{KeyStr("a", 2U, kTypeMerge), test::EncodeInt(10U)},
-                          {KeyStr("b", 1U, kTypeMerge), test::EncodeInt(10U)}});
-  AddMockFile(file3, 2);
-
-  SetLastSequence(11U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-
-  stl_wrappers::KVMap empty_map;
-  RunCompaction({files}, empty_map);
-}
-
-TEST_F(CompactionJobTest, SimpleSingleDelete) {
-  NewDB();
-
-  auto file1 = mock::MakeMockFile({
-      {KeyStr("a", 5U, kTypeDeletion), ""},
-      {KeyStr("b", 6U, kTypeSingleDeletion), ""},
-  });
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile({{KeyStr("a", 3U, kTypeValue), "val"},
-                                   {KeyStr("b", 4U, kTypeValue), "val"}});
-  AddMockFile(file2);
-
-  auto file3 = mock::MakeMockFile({
-      {KeyStr("a", 1U, kTypeValue), "val"},
-  });
-  AddMockFile(file3, 2);
-
-  auto expected_results =
-      mock::MakeMockFile({{KeyStr("a", 5U, kTypeDeletion), ""}});
-
-  SetLastSequence(6U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-}
-
-TEST_F(CompactionJobTest, SingleDeleteSnapshots) {
-  NewDB();
-
-  auto file1 = mock::MakeMockFile({
-      {KeyStr("A", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("a", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("b", 21U, kTypeSingleDeletion), ""},
-      {KeyStr("c", 22U, kTypeSingleDeletion), ""},
-      {KeyStr("d", 9U, kTypeSingleDeletion), ""},
-      {KeyStr("f", 21U, kTypeSingleDeletion), ""},
-      {KeyStr("j", 11U, kTypeSingleDeletion), ""},
-      {KeyStr("j", 9U, kTypeSingleDeletion), ""},
-      {KeyStr("k", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("k", 11U, kTypeSingleDeletion), ""},
-      {KeyStr("l", 3U, kTypeSingleDeletion), ""},
-      {KeyStr("l", 2U, kTypeSingleDeletion), ""},
-  });
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile({
-      {KeyStr("0", 2U, kTypeSingleDeletion), ""},
-      {KeyStr("a", 11U, kTypeValue), "val1"},
-      {KeyStr("b", 11U, kTypeValue), "val2"},
-      {KeyStr("c", 21U, kTypeValue), "val3"},
-      {KeyStr("d", 8U, kTypeValue), "val4"},
-      {KeyStr("e", 2U, kTypeSingleDeletion), ""},
-      {KeyStr("f", 1U, kTypeValue), "val1"},
-      {KeyStr("g", 11U, kTypeSingleDeletion), ""},
-      {KeyStr("h", 2U, kTypeSingleDeletion), ""},
-      {KeyStr("m", 12U, kTypeValue), "val1"},
-      {KeyStr("m", 11U, kTypeSingleDeletion), ""},
-      {KeyStr("m", 8U, kTypeValue), "val2"},
-  });
-  AddMockFile(file2);
-
-  auto file3 = mock::MakeMockFile({
-      {KeyStr("A", 1U, kTypeValue), "val"},
-      {KeyStr("e", 1U, kTypeValue), "val"},
-  });
-  AddMockFile(file3, 2);
-
-  auto expected_results = mock::MakeMockFile({
-      {KeyStr("A", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("a", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("a", 11U, kTypeValue), ""},
-      {KeyStr("b", 21U, kTypeSingleDeletion), ""},
-      {KeyStr("b", 11U, kTypeValue), "val2"},
-      {KeyStr("c", 22U, kTypeSingleDeletion), ""},
-      {KeyStr("c", 21U, kTypeValue), ""},
-      {KeyStr("e", 2U, kTypeSingleDeletion), ""},
-      {KeyStr("f", 21U, kTypeSingleDeletion), ""},
-      {KeyStr("f", 1U, kTypeValue), "val1"},
-      {KeyStr("g", 11U, kTypeSingleDeletion), ""},
-      {KeyStr("j", 11U, kTypeSingleDeletion), ""},
-      {KeyStr("k", 11U, kTypeSingleDeletion), ""},
-      {KeyStr("m", 12U, kTypeValue), "val1"},
-      {KeyStr("m", 11U, kTypeSingleDeletion), ""},
-      {KeyStr("m", 8U, kTypeValue), "val2"},
-  });
-
-  SetLastSequence(22U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results, {10U, 20U}, 10U);
-}
-
-TEST_F(CompactionJobTest, EarliestWriteConflictSnapshot) {
-  NewDB();
-
-  // Test multiple snapshots where the earliest snapshot is not a
-  // write-conflic-snapshot.
-
-  auto file1 = mock::MakeMockFile({
-      {KeyStr("A", 24U, kTypeSingleDeletion), ""},
-      {KeyStr("A", 23U, kTypeValue), "val"},
-      {KeyStr("B", 24U, kTypeSingleDeletion), ""},
-      {KeyStr("B", 23U, kTypeValue), "val"},
-      {KeyStr("D", 24U, kTypeSingleDeletion), ""},
-      {KeyStr("G", 32U, kTypeSingleDeletion), ""},
-      {KeyStr("G", 31U, kTypeValue), "val"},
-      {KeyStr("G", 24U, kTypeSingleDeletion), ""},
-      {KeyStr("G", 23U, kTypeValue), "val2"},
-      {KeyStr("H", 31U, kTypeValue), "val"},
-      {KeyStr("H", 24U, kTypeSingleDeletion), ""},
-      {KeyStr("H", 23U, kTypeValue), "val"},
-      {KeyStr("I", 35U, kTypeSingleDeletion), ""},
-      {KeyStr("I", 34U, kTypeValue), "val2"},
-      {KeyStr("I", 33U, kTypeSingleDeletion), ""},
-      {KeyStr("I", 32U, kTypeValue), "val3"},
-      {KeyStr("I", 31U, kTypeSingleDeletion), ""},
-      {KeyStr("J", 34U, kTypeValue), "val"},
-      {KeyStr("J", 33U, kTypeSingleDeletion), ""},
-      {KeyStr("J", 25U, kTypeValue), "val2"},
-      {KeyStr("J", 24U, kTypeSingleDeletion), ""},
-  });
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile({
-      {KeyStr("A", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("A", 13U, kTypeValue), "val2"},
-      {KeyStr("C", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("C", 13U, kTypeValue), "val"},
-      {KeyStr("E", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("F", 4U, kTypeSingleDeletion), ""},
-      {KeyStr("F", 3U, kTypeValue), "val"},
-      {KeyStr("G", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("G", 13U, kTypeValue), "val3"},
-      {KeyStr("H", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("H", 13U, kTypeValue), "val2"},
-      {KeyStr("I", 13U, kTypeValue), "val4"},
-      {KeyStr("I", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("I", 11U, kTypeValue), "val5"},
-      {KeyStr("J", 15U, kTypeValue), "val3"},
-      {KeyStr("J", 14U, kTypeSingleDeletion), ""},
-  });
-  AddMockFile(file2);
-
-  auto expected_results = mock::MakeMockFile({
-      {KeyStr("A", 24U, kTypeSingleDeletion), ""},
-      {KeyStr("A", 23U, kTypeValue), ""},
-      {KeyStr("B", 24U, kTypeSingleDeletion), ""},
-      {KeyStr("B", 23U, kTypeValue), ""},
-      {KeyStr("D", 24U, kTypeSingleDeletion), ""},
-      {KeyStr("E", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("G", 32U, kTypeSingleDeletion), ""},
-      {KeyStr("G", 31U, kTypeValue), ""},
-      {KeyStr("H", 31U, kTypeValue), "val"},
-      {KeyStr("I", 35U, kTypeSingleDeletion), ""},
-      {KeyStr("I", 34U, kTypeValue), ""},
-      {KeyStr("I", 31U, kTypeSingleDeletion), ""},
-      {KeyStr("I", 13U, kTypeValue), "val4"},
-      {KeyStr("J", 34U, kTypeValue), "val"},
-      {KeyStr("J", 33U, kTypeSingleDeletion), ""},
-      {KeyStr("J", 25U, kTypeValue), "val2"},
-      {KeyStr("J", 24U, kTypeSingleDeletion), ""},
-      {KeyStr("J", 15U, kTypeValue), "val3"},
-      {KeyStr("J", 14U, kTypeSingleDeletion), ""},
-  });
-
-  SetLastSequence(24U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results, {10U, 20U, 30U}, 20U);
-}
-
-TEST_F(CompactionJobTest, SingleDeleteZeroSeq) {
-  NewDB();
-
-  auto file1 = mock::MakeMockFile({
-      {KeyStr("A", 10U, kTypeSingleDeletion), ""},
-      {KeyStr("dummy", 5U, kTypeValue), "val2"},
-  });
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile({
-      {KeyStr("A", 0U, kTypeValue), "val"},
-  });
-  AddMockFile(file2);
-
-  auto expected_results = mock::MakeMockFile({
-      {KeyStr("dummy", 5U, kTypeValue), "val2"},
-  });
-
-  SetLastSequence(22U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results, {});
-}
-
-TEST_F(CompactionJobTest, MultiSingleDelete) {
-  // Tests three scenarios involving multiple single delete/put pairs:
-  //
-  // A: Put Snapshot SDel Put SDel -> Put Snapshot SDel
-  // B: Snapshot Put SDel Put SDel Snapshot -> Snapshot SDel Snapshot
-  // C: SDel Put SDel Snapshot Put -> Snapshot Put
-  // D: (Put) SDel Snapshot Put SDel -> (Put) SDel Snapshot SDel
-  // E: Put SDel Snapshot Put SDel -> Snapshot SDel
-  // F: Put SDel Put Sdel Snapshot -> removed
-  // G: Snapshot SDel Put SDel Put -> Snapshot Put SDel
-  // H: (Put) Put SDel Put Sdel Snapshot -> Removed
-  // I: (Put) Snapshot Put SDel Put SDel -> SDel
-  // J: Put Put SDel Put SDel SDel Snapshot Put Put SDel SDel Put
-  //      -> Snapshot Put
-  // K: SDel SDel Put SDel Put Put Snapshot SDel Put SDel SDel Put SDel
-  //      -> Snapshot Put Snapshot SDel
-  // L: SDel Put Del Put SDel Snapshot Del Put Del SDel Put SDel
-  //      -> Snapshot SDel
-  // M: (Put) SDel Put Del Put SDel Snapshot Put Del SDel Put SDel Del
-  //      -> SDel Snapshot Del
-  NewDB();
-
-  auto file1 = mock::MakeMockFile({
-      {KeyStr("A", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("A", 13U, kTypeValue), "val5"},
-      {KeyStr("A", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("B", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("B", 13U, kTypeValue), "val2"},
-      {KeyStr("C", 14U, kTypeValue), "val3"},
-      {KeyStr("D", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("D", 11U, kTypeValue), "val4"},
-      {KeyStr("G", 15U, kTypeValue), "val"},
-      {KeyStr("G", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("G", 13U, kTypeValue), "val"},
-      {KeyStr("I", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("I", 13U, kTypeValue), "val"},
-      {KeyStr("J", 15U, kTypeValue), "val"},
-      {KeyStr("J", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("J", 13U, kTypeSingleDeletion), ""},
-      {KeyStr("J", 12U, kTypeValue), "val"},
-      {KeyStr("J", 11U, kTypeValue), "val"},
-      {KeyStr("K", 16U, kTypeSingleDeletion), ""},
-      {KeyStr("K", 15U, kTypeValue), "val1"},
-      {KeyStr("K", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("K", 13U, kTypeSingleDeletion), ""},
-      {KeyStr("K", 12U, kTypeValue), "val2"},
-      {KeyStr("K", 11U, kTypeSingleDeletion), ""},
-      {KeyStr("L", 16U, kTypeSingleDeletion), ""},
-      {KeyStr("L", 15U, kTypeValue), "val"},
-      {KeyStr("L", 14U, kTypeSingleDeletion), ""},
-      {KeyStr("L", 13U, kTypeDeletion), ""},
-      {KeyStr("L", 12U, kTypeValue), "val"},
-      {KeyStr("L", 11U, kTypeDeletion), ""},
-      {KeyStr("M", 16U, kTypeDeletion), ""},
-      {KeyStr("M", 15U, kTypeSingleDeletion), ""},
-      {KeyStr("M", 14U, kTypeValue), "val"},
-      {KeyStr("M", 13U, kTypeSingleDeletion), ""},
-      {KeyStr("M", 12U, kTypeDeletion), ""},
-      {KeyStr("M", 11U, kTypeValue), "val"},
-  });
-  AddMockFile(file1);
-
-  auto file2 = mock::MakeMockFile({
-      {KeyStr("A", 10U, kTypeValue), "val"},
-      {KeyStr("B", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("B", 11U, kTypeValue), "val2"},
-      {KeyStr("C", 10U, kTypeSingleDeletion), ""},
-      {KeyStr("C", 9U, kTypeValue), "val6"},
-      {KeyStr("C", 8U, kTypeSingleDeletion), ""},
-      {KeyStr("D", 10U, kTypeSingleDeletion), ""},
-      {KeyStr("E", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("E", 11U, kTypeValue), "val"},
-      {KeyStr("E", 5U, kTypeSingleDeletion), ""},
-      {KeyStr("E", 4U, kTypeValue), "val"},
-      {KeyStr("F", 6U, kTypeSingleDeletion), ""},
-      {KeyStr("F", 5U, kTypeValue), "val"},
-      {KeyStr("F", 4U, kTypeSingleDeletion), ""},
-      {KeyStr("F", 3U, kTypeValue), "val"},
-      {KeyStr("G", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("H", 6U, kTypeSingleDeletion), ""},
-      {KeyStr("H", 5U, kTypeValue), "val"},
-      {KeyStr("H", 4U, kTypeSingleDeletion), ""},
-      {KeyStr("H", 3U, kTypeValue), "val"},
-      {KeyStr("I", 12U, kTypeSingleDeletion), ""},
-      {KeyStr("I", 11U, kTypeValue), "val"},
-      {KeyStr("J", 6U, kTypeSingleDeletion), ""},
-      {KeyStr("J", 5U, kTypeSingleDeletion), ""},
-      {KeyStr("J", 4U, kTypeValue), "val"},
-      {KeyStr("J", 3U, kTypeSingleDeletion), ""},
-      {KeyStr("J", 2U, kTypeValue), "val"},
-      {KeyStr("K", 8U, kTypeValue), "val3"},
-      {KeyStr("K", 7U, kTypeValue), "val4"},
-      {KeyStr("K", 6U, kTypeSingleDeletion), ""},
-      {KeyStr("K", 5U, kTypeValue), "val5"},
-      {KeyStr("K", 2U, kTypeSingleDeletion), ""},
-      {KeyStr("K", 1U, kTypeSingleDeletion), ""},
-      {KeyStr("L", 5U, kTypeSingleDeletion), ""},
-      {KeyStr("L", 4U, kTypeValue), "val"},
-      {KeyStr("L", 3U, kTypeDeletion), ""},
-      {KeyStr("L", 2U, kTypeValue), "val"},
-      {KeyStr("L", 1U, kTypeSingleDeletion), ""},
-      {KeyStr("M", 10U, kTypeSingleDeletion), ""},
-      {KeyStr("M", 7U, kTypeValue), "val"},
-      {KeyStr("M", 5U, kTypeDeletion), ""},
-      {KeyStr("M", 4U, kTypeValue), "val"},
-      {KeyStr("M", 3U, kTypeSingleDeletion), ""},
-  });
-  AddMockFile(file2);
-
-  auto file3 = mock::MakeMockFile({
-      {KeyStr("D", 1U, kTypeValue), "val"},
-      {KeyStr("H", 1U, kTypeValue), "val"},
-      {KeyStr("I", 2U, kTypeValue), "val"},
-  });
-  AddMockFile(file3, 2);
-
-  auto file4 = mock::MakeMockFile({
-      {KeyStr("M", 1U, kTypeValue), "val"},
-  });
-  AddMockFile(file4, 2);
-
-  auto expected_results =
-      mock::MakeMockFile({{KeyStr("A", 14U, kTypeSingleDeletion), ""},
-                          {KeyStr("A", 13U, kTypeValue), ""},
-                          {KeyStr("A", 12U, kTypeSingleDeletion), ""},
-                          {KeyStr("A", 10U, kTypeValue), "val"},
-                          {KeyStr("B", 14U, kTypeSingleDeletion), ""},
-                          {KeyStr("B", 13U, kTypeValue), ""},
-                          {KeyStr("C", 14U, kTypeValue), "val3"},
-                          {KeyStr("D", 12U, kTypeSingleDeletion), ""},
-                          {KeyStr("D", 11U, kTypeValue), ""},
-                          {KeyStr("D", 10U, kTypeSingleDeletion), ""},
-                          {KeyStr("E", 12U, kTypeSingleDeletion), ""},
-                          {KeyStr("E", 11U, kTypeValue), ""},
-                          {KeyStr("G", 15U, kTypeValue), "val"},
-                          {KeyStr("G", 12U, kTypeSingleDeletion), ""},
-                          {KeyStr("I", 14U, kTypeSingleDeletion), ""},
-                          {KeyStr("I", 13U, kTypeValue), ""},
-                          {KeyStr("J", 15U, kTypeValue), "val"},
-                          {KeyStr("K", 16U, kTypeSingleDeletion), ""},
-                          {KeyStr("K", 15U, kTypeValue), ""},
-                          {KeyStr("K", 11U, kTypeSingleDeletion), ""},
-                          {KeyStr("K", 8U, kTypeValue), "val3"},
-                          {KeyStr("L", 16U, kTypeSingleDeletion), ""},
-                          {KeyStr("L", 15U, kTypeValue), ""},
-                          {KeyStr("M", 16U, kTypeDeletion), ""},
-                          {KeyStr("M", 3U, kTypeSingleDeletion), ""}});
-
-  SetLastSequence(22U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results, {10U}, 10U);
-}
-
-// This test documents the behavior where a corrupt key follows a deletion or a
-// single deletion and the (single) deletion gets removed while the corrupt key
-// gets written out. TODO(noetzli): We probably want a better way to treat
-// corrupt keys.
-TEST_F(CompactionJobTest, CorruptionAfterDeletion) {
-  NewDB();
-
-  auto file1 =
-      mock::MakeMockFile({{test::KeyStr("A", 6U, kTypeValue), "val3"},
-                          {test::KeyStr("a", 5U, kTypeDeletion), ""},
-                          {test::KeyStr("a", 4U, kTypeValue, true), "val"}});
-  AddMockFile(file1);
-
-  auto file2 =
-      mock::MakeMockFile({{test::KeyStr("b", 3U, kTypeSingleDeletion), ""},
-                          {test::KeyStr("b", 2U, kTypeValue, true), "val"},
-                          {test::KeyStr("c", 1U, kTypeValue), "val2"}});
-  AddMockFile(file2);
-
-  auto expected_results =
-      mock::MakeMockFile({{test::KeyStr("A", 0U, kTypeValue), "val3"},
-                          {test::KeyStr("a", 0U, kTypeValue, true), "val"},
-                          {test::KeyStr("b", 0U, kTypeValue, true), "val"},
-                          {test::KeyStr("c", 1U, kTypeValue), "val2"}});
-
-  SetLastSequence(6U);
-  auto files = cfd_->current()->storage_info()->LevelFiles(0);
-  RunCompaction({files}, expected_results);
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
-
-#else
-#include <stdio.h>
-
-int main(int argc, char** argv) {
-  fprintf(stderr,
-          "SKIPPED as CompactionJobStats is not supported in ROCKSDB_LITE\n");
-  return 0;
-}
-
-#endif  // ROCKSDB_LITE

db/compaction_picker.h

@@ -1,4 +1,4 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -8,41 +8,31 @@
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
 #pragma once
+#include "db/version_set.h"
+#include "db/compaction.h"
+#include "rocksdb/status.h"
+#include "rocksdb/options.h"
 
+#include <vector>
 #include <memory>
 #include <set>
-#include <string>
-#include <unordered_set>
-#include <vector>
-
-#include "db/compaction.h"
-#include "db/version_set.h"
-#include "rocksdb/env.h"
-#include "rocksdb/options.h"
-#include "rocksdb/status.h"
-#include "util/mutable_cf_options.h"
-
 
 namespace rocksdb {
 
 class LogBuffer;
 class Compaction;
-class VersionStorageInfo;
-struct CompactionInputFiles;
+class Version;
 
 class CompactionPicker {
  public:
-  CompactionPicker(const ImmutableCFOptions& ioptions,
-                   const InternalKeyComparator* icmp);
+  CompactionPicker(const Options* options, const InternalKeyComparator* icmp);
   virtual ~CompactionPicker();
 
   // Pick level and inputs for a new compaction.
   // Returns nullptr if there is no compaction to be done.
   // Otherwise returns a pointer to a heap-allocated object that
   // describes the compaction.  Caller should delete the result.
-  virtual Compaction* PickCompaction(const std::string& cf_name,
-                                     const MutableCFOptions& mutable_cf_options,
-                                     VersionStorageInfo* vstorage,
+  virtual Compaction* PickCompaction(Version* version,
                                      LogBuffer* log_buffer) = 0;
 
   // Return a compaction object for compacting the range [begin,end] in
@@ -56,79 +46,43 @@ class CompactionPicker {
   // compaction_end will be set to nullptr.
   // Client is responsible for compaction_end storage -- when called,
   // *compaction_end should point to valid InternalKey!
-  virtual Compaction* CompactRange(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, int input_level, int output_level,
-      uint32_t output_path_id, const InternalKey* begin, const InternalKey* end,
-      InternalKey** compaction_end, bool* manual_conflict);
-
-  // The maximum allowed output level.  Default value is NumberLevels() - 1.
-  virtual int MaxOutputLevel() const { return NumberLevels() - 1; }
-
-  virtual bool NeedsCompaction(const VersionStorageInfo* vstorage) const = 0;
-
-// Sanitize the input set of compaction input files.
-// When the input parameters do not describe a valid compaction, the
-// function will try to fix the input_files by adding necessary
-// files.  If it's not possible to conver an invalid input_files
-// into a valid one by adding more files, the function will return a
-// non-ok status with specific reason.
-#ifndef ROCKSDB_LITE
-  Status SanitizeCompactionInputFiles(std::unordered_set<uint64_t>* input_files,
-                                      const ColumnFamilyMetaData& cf_meta,
-                                      const int output_level) const;
-#endif  // ROCKSDB_LITE
+  Compaction* CompactRange(Version* version, int input_level, int output_level,
+                           const InternalKey* begin, const InternalKey* end,
+                           InternalKey** compaction_end);
 
   // Free up the files that participated in a compaction
-  //
-  // Requirement: DB mutex held
   void ReleaseCompactionFiles(Compaction* c, Status status);
 
-  // Returns true if any one of the specified files are being compacted
-  bool FilesInCompaction(const std::vector<FileMetaData*>& files);
+  // Return the total amount of data that is undergoing
+  // compactions per level
+  void SizeBeingCompacted(std::vector<uint64_t>& sizes);
 
-  // Takes a list of CompactionInputFiles and returns a (manual) Compaction
-  // object.
-  Compaction* FormCompaction(
-      const CompactionOptions& compact_options,
-      const std::vector<CompactionInputFiles>& input_files, int output_level,
-      VersionStorageInfo* vstorage, const MutableCFOptions& mutable_cf_options,
-      uint32_t output_path_id);
+  // Returns maximum total overlap bytes with grandparent
+  // level (i.e., level+2) before we stop building a single
+  // file in level->level+1 compaction.
+  uint64_t MaxGrandParentOverlapBytes(int level);
 
-  // Converts a set of compaction input file numbers into
-  // a list of CompactionInputFiles.
-  Status GetCompactionInputsFromFileNumbers(
-      std::vector<CompactionInputFiles>* input_files,
-      std::unordered_set<uint64_t>* input_set,
-      const VersionStorageInfo* vstorage,
-      const CompactionOptions& compact_options) const;
+  // Returns maximum total bytes of data on a given level.
+  double MaxBytesForLevel(int level);
 
-  // Used in universal compaction when the enabled_trivial_move
-  // option is set. Checks whether there are any overlapping files
-  // in the input. Returns true if the input files are non
-  // overlapping.
-  bool IsInputNonOverlapping(Compaction* c);
-
-  // Is there currently a compaction involving level 0 taking place
-  bool IsLevel0CompactionInProgress() const {
-    return !level0_compactions_in_progress_.empty();
-  }
+  // Get the max file size in a given level.
+  uint64_t MaxFileSizeForLevel(int level) const;
 
  protected:
-  int NumberLevels() const { return ioptions_.num_levels; }
+  int NumberLevels() const { return num_levels_; }
 
   // Stores the minimal range that covers all entries in inputs in
   // *smallest, *largest.
   // REQUIRES: inputs is not empty
-  void GetRange(const CompactionInputFiles& inputs, InternalKey* smallest,
+  void GetRange(const std::vector<FileMetaData*>& inputs, InternalKey* smallest,
                 InternalKey* largest);
 
   // Stores the minimal range that covers all entries in inputs1 and inputs2
   // in *smallest, *largest.
   // REQUIRES: inputs is not empty
-  void GetRange(const CompactionInputFiles& inputs1,
-                const CompactionInputFiles& inputs2, InternalKey* smallest,
-                InternalKey* largest);
+  void GetRange(const std::vector<FileMetaData*>& inputs1,
+                const std::vector<FileMetaData*>& inputs2,
+                InternalKey* smallest, InternalKey* largest);
 
   // Add more files to the inputs on "level" to make sure that
   // no newer version of a key is compacted to "level+1" while leaving an older
@@ -140,213 +94,70 @@ class CompactionPicker {
   // populated.
   //
   // Will return false if it is impossible to apply this compaction.
-  bool ExpandWhileOverlapping(const std::string& cf_name,
-                              VersionStorageInfo* vstorage,
-                              CompactionInputFiles* inputs);
+  bool ExpandWhileOverlapping(Compaction* c);
+
+  uint64_t ExpandedCompactionByteSizeLimit(int level);
+
+  // Returns true if any one of the specified files are being compacted
+  bool FilesInCompaction(std::vector<FileMetaData*>& files);
 
   // Returns true if any one of the parent files are being compacted
-  bool RangeInCompaction(VersionStorageInfo* vstorage,
-                         const InternalKey* smallest,
-                         const InternalKey* largest, int level, int* index);
+  bool ParentRangeInCompaction(Version* version, const InternalKey* smallest,
+                               const InternalKey* largest, int level,
+                               int* index);
 
-  bool SetupOtherInputs(const std::string& cf_name,
-                        const MutableCFOptions& mutable_cf_options,
-                        VersionStorageInfo* vstorage,
-                        CompactionInputFiles* inputs,
-                        CompactionInputFiles* output_level_inputs,
-                        int* parent_index, int base_index);
+  void SetupOtherInputs(Compaction* c);
 
-  void GetGrandparents(VersionStorageInfo* vstorage,
-                       const CompactionInputFiles& inputs,
-                       const CompactionInputFiles& output_level_inputs,
-                       std::vector<FileMetaData*>* grandparents);
+  // record all the ongoing compactions for all levels
+  std::vector<std::set<Compaction*>> compactions_in_progress_;
 
-  const ImmutableCFOptions& ioptions_;
+  // Per-level target file size.
+  std::unique_ptr<uint64_t[]> max_file_size_;
 
-// A helper function to SanitizeCompactionInputFiles() that
-// sanitizes "input_files" by adding necessary files.
-#ifndef ROCKSDB_LITE
-  virtual Status SanitizeCompactionInputFilesForAllLevels(
-      std::unordered_set<uint64_t>* input_files,
-      const ColumnFamilyMetaData& cf_meta, const int output_level) const;
-#endif  // ROCKSDB_LITE
+  // Per-level max bytes
+  std::unique_ptr<uint64_t[]> level_max_bytes_;
 
-  // Keeps track of all compactions that are running on Level0.
-  // It is protected by DB mutex
-  std::set<Compaction*> level0_compactions_in_progress_;
+  const Options* const options_;
+ private:
+  int num_levels_;
 
   const InternalKeyComparator* const icmp_;
 };
 
-class LevelCompactionPicker : public CompactionPicker {
- public:
-  LevelCompactionPicker(const ImmutableCFOptions& ioptions,
-                        const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-  virtual Compaction* PickCompaction(const std::string& cf_name,
-                                     const MutableCFOptions& mutable_cf_options,
-                                     VersionStorageInfo* vstorage,
-                                     LogBuffer* log_buffer) override;
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-
-  // Pick a path ID to place a newly generated file, with its level
-  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
-                            const MutableCFOptions& mutable_cf_options,
-                            int level);
-
- private:
-  // For the specfied level, pick a file that we want to compact.
-  // Returns false if there is no file to compact.
-  // If it returns true, inputs->files.size() will be exactly one.
-  // If level is 0 and there is already a compaction on that level, this
-  // function will return false.
-  bool PickCompactionBySize(VersionStorageInfo* vstorage, int level,
-                            int output_level, CompactionInputFiles* inputs,
-                            int* parent_index, int* base_index);
-
-  // If there is any file marked for compaction, put put it into inputs.
-  // This is still experimental. It will return meaningful results only if
-  // clients call experimental feature SuggestCompactRange()
-  void PickFilesMarkedForCompactionExperimental(const std::string& cf_name,
-                                                VersionStorageInfo* vstorage,
-                                                CompactionInputFiles* inputs,
-                                                int* level, int* output_level);
-};
-
-#ifndef ROCKSDB_LITE
 class UniversalCompactionPicker : public CompactionPicker {
  public:
-  UniversalCompactionPicker(const ImmutableCFOptions& ioptions,
+  UniversalCompactionPicker(const Options* options,
                             const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-  virtual Compaction* PickCompaction(const std::string& cf_name,
-                                     const MutableCFOptions& mutable_cf_options,
-                                     VersionStorageInfo* vstorage,
+      : CompactionPicker(options, icmp) {}
+  virtual Compaction* PickCompaction(Version* version,
                                      LogBuffer* log_buffer) override;
 
-  virtual int MaxOutputLevel() const override { return NumberLevels() - 1; }
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
-
  private:
-  struct SortedRun {
-    SortedRun(int _level, FileMetaData* _file, uint64_t _size,
-              uint64_t _compensated_file_size, bool _being_compacted)
-        : level(_level),
-          file(_file),
-          size(_size),
-          compensated_file_size(_compensated_file_size),
-          being_compacted(_being_compacted) {
-      assert(compensated_file_size > 0);
-      assert(level != 0 || file != nullptr);
-    }
-
-    void Dump(char* out_buf, size_t out_buf_size,
-              bool print_path = false) const;
-
-    // sorted_run_count is added into the string to print
-    void DumpSizeInfo(char* out_buf, size_t out_buf_size,
-                      size_t sorted_run_count) const;
-
-    int level;
-    // `file` Will be null for level > 0. For level = 0, the sorted run is
-    // for this file.
-    FileMetaData* file;
-    // For level > 0, `size` and `compensated_file_size` are sum of sizes all
-    // files in the level. `being_compacted` should be the same for all files
-    // in a non-zero level. Use the value here.
-    uint64_t size;
-    uint64_t compensated_file_size;
-    bool being_compacted;
-  };
-
   // Pick Universal compaction to limit read amplification
-  Compaction* PickCompactionUniversalReadAmp(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, double score, unsigned int ratio,
-      unsigned int num_files, const std::vector<SortedRun>& sorted_runs,
-      LogBuffer* log_buffer);
+  Compaction* PickCompactionUniversalReadAmp(Version* version, double score,
+                                             unsigned int ratio,
+                                             unsigned int num_files,
+                                             LogBuffer* log_buffer);
 
   // Pick Universal compaction to limit space amplification.
-  Compaction* PickCompactionUniversalSizeAmp(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, double score,
-      const std::vector<SortedRun>& sorted_runs, LogBuffer* log_buffer);
-
-  static std::vector<SortedRun> CalculateSortedRuns(
-      const VersionStorageInfo& vstorage, const ImmutableCFOptions& ioptions);
-
-  // Pick a path ID to place a newly generated file, with its estimated file
-  // size.
-  static uint32_t GetPathId(const ImmutableCFOptions& ioptions,
-                            uint64_t file_size);
+  Compaction* PickCompactionUniversalSizeAmp(Version* version, double score,
+                                             LogBuffer* log_buffer);
 };
 
-class FIFOCompactionPicker : public CompactionPicker {
+class LevelCompactionPicker : public CompactionPicker {
  public:
-  FIFOCompactionPicker(const ImmutableCFOptions& ioptions,
-                       const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-
-  virtual Compaction* PickCompaction(const std::string& cf_name,
-                                     const MutableCFOptions& mutable_cf_options,
-                                     VersionStorageInfo* version,
+  LevelCompactionPicker(const Options* options,
+                        const InternalKeyComparator* icmp)
+      : CompactionPicker(options, icmp) {}
+  virtual Compaction* PickCompaction(Version* version,
                                      LogBuffer* log_buffer) override;
 
-  virtual Compaction* CompactRange(
-      const std::string& cf_name, const MutableCFOptions& mutable_cf_options,
-      VersionStorageInfo* vstorage, int input_level, int output_level,
-      uint32_t output_path_id, const InternalKey* begin, const InternalKey* end,
-      InternalKey** compaction_end, bool* manual_conflict) override;
-
-  // The maximum allowed output level.  Always returns 0.
-  virtual int MaxOutputLevel() const override { return 0; }
-
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override;
+ private:
+  // For the specfied level, pick a compaction.
+  // Returns nullptr if there is no compaction to be done.
+  // If level is 0 and there is already a compaction on that level, this
+  // function will return nullptr.
+  Compaction* PickCompactionBySize(Version* version, int level, double score);
 };
 
-class NullCompactionPicker : public CompactionPicker {
- public:
-  NullCompactionPicker(const ImmutableCFOptions& ioptions,
-                       const InternalKeyComparator* icmp)
-      : CompactionPicker(ioptions, icmp) {}
-  virtual ~NullCompactionPicker() {}
-
-  // Always return "nullptr"
-  Compaction* PickCompaction(const std::string& cf_name,
-                             const MutableCFOptions& mutable_cf_options,
-                             VersionStorageInfo* vstorage,
-                             LogBuffer* log_buffer) override {
-    return nullptr;
-  }
-
-  // Always return "nullptr"
-  Compaction* CompactRange(const std::string& cf_name,
-                           const MutableCFOptions& mutable_cf_options,
-                           VersionStorageInfo* vstorage, int input_level,
-                           int output_level, uint32_t output_path_id,
-                           const InternalKey* begin, const InternalKey* end,
-                           InternalKey** compaction_end,
-                           bool* manual_conflict) override {
-    return nullptr;
-  }
-
-  // Always returns false.
-  virtual bool NeedsCompaction(
-      const VersionStorageInfo* vstorage) const override {
-    return false;
-  }
-};
-#endif  // !ROCKSDB_LITE
-
-CompressionType GetCompressionType(const ImmutableCFOptions& ioptions,
-                                   const VersionStorageInfo* vstorage,
-                                   const MutableCFOptions& mutable_cf_options,
-                                   int level, int base_level,
-                                   const bool enable_compression = true);
-
 }  // namespace rocksdb

db/comparator_db_test.cc

@@ -1,439 +0,0 @@
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-#include <map>
-#include <string>
-
-#include "memtable/stl_wrappers.h"
-#include "rocksdb/db.h"
-#include "rocksdb/env.h"
-#include "util/hash.h"
-#include "util/kv_map.h"
-#include "util/string_util.h"
-#include "util/testharness.h"
-#include "util/testutil.h"
-#include "utilities/merge_operators.h"
-
-using std::unique_ptr;
-
-namespace rocksdb {
-namespace {
-
-static const Comparator* comparator;
-
-class KVIter : public Iterator {
- public:
-  explicit KVIter(const stl_wrappers::KVMap* map)
-      : map_(map), iter_(map_->end()) {}
-  virtual bool Valid() const override { return iter_ != map_->end(); }
-  virtual void SeekToFirst() override { iter_ = map_->begin(); }
-  virtual void SeekToLast() override {
-    if (map_->empty()) {
-      iter_ = map_->end();
-    } else {
-      iter_ = map_->find(map_->rbegin()->first);
-    }
-  }
-  virtual void Seek(const Slice& k) override {
-    iter_ = map_->lower_bound(k.ToString());
-  }
-  virtual void Next() override { ++iter_; }
-  virtual void Prev() override {
-    if (iter_ == map_->begin()) {
-      iter_ = map_->end();
-      return;
-    }
-    --iter_;
-  }
-
-  virtual Slice key() const override { return iter_->first; }
-  virtual Slice value() const override { return iter_->second; }
-  virtual Status status() const override { return Status::OK(); }
-
- private:
-  const stl_wrappers::KVMap* const map_;
-  stl_wrappers::KVMap::const_iterator iter_;
-};
-
-void AssertItersEqual(Iterator* iter1, Iterator* iter2) {
-  ASSERT_EQ(iter1->Valid(), iter2->Valid());
-  if (iter1->Valid()) {
-    ASSERT_EQ(iter1->key().ToString(), iter2->key().ToString());
-    ASSERT_EQ(iter1->value().ToString(), iter2->value().ToString());
-  }
-}
-
-// Measuring operations on DB (expect to be empty).
-// source_strings are candidate keys
-void DoRandomIteraratorTest(DB* db, std::vector<std::string> source_strings,
-                            Random* rnd, int num_writes, int num_iter_ops,
-                            int num_trigger_flush) {
-  stl_wrappers::KVMap map((stl_wrappers::LessOfComparator(comparator)));
-
-  for (int i = 0; i < num_writes; i++) {
-    if (num_trigger_flush > 0 && i != 0 && i % num_trigger_flush == 0) {
-      db->Flush(FlushOptions());
-    }
-
-    int type = rnd->Uniform(2);
-    int index = rnd->Uniform(static_cast<int>(source_strings.size()));
-    auto& key = source_strings[index];
-    switch (type) {
-      case 0:
-        // put
-        map[key] = key;
-        ASSERT_OK(db->Put(WriteOptions(), key, key));
-        break;
-      case 1:
-        // delete
-        if (map.find(key) != map.end()) {
-          map.erase(key);
-        }
-        ASSERT_OK(db->Delete(WriteOptions(), key));
-        break;
-      default:
-        assert(false);
-    }
-  }
-
-  std::unique_ptr<Iterator> iter(db->NewIterator(ReadOptions()));
-  std::unique_ptr<Iterator> result_iter(new KVIter(&map));
-
-  bool is_valid = false;
-  for (int i = 0; i < num_iter_ops; i++) {
-    // Random walk and make sure iter and result_iter returns the
-    // same key and value
-    int type = rnd->Uniform(6);
-    ASSERT_OK(iter->status());
-    switch (type) {
-      case 0:
-        // Seek to First
-        iter->SeekToFirst();
-        result_iter->SeekToFirst();
-        break;
-      case 1:
-        // Seek to last
-        iter->SeekToLast();
-        result_iter->SeekToLast();
-        break;
-      case 2: {
-        // Seek to random key
-        auto key_idx = rnd->Uniform(static_cast<int>(source_strings.size()));
-        auto key = source_strings[key_idx];
-        iter->Seek(key);
-        result_iter->Seek(key);
-        break;
-      }
-      case 3:
-        // Next
-        if (is_valid) {
-          iter->Next();
-          result_iter->Next();
-        } else {
-          continue;
-        }
-        break;
-      case 4:
-        // Prev
-        if (is_valid) {
-          iter->Prev();
-          result_iter->Prev();
-        } else {
-          continue;
-        }
-        break;
-      default: {
-        assert(type == 5);
-        auto key_idx = rnd->Uniform(static_cast<int>(source_strings.size()));
-        auto key = source_strings[key_idx];
-        std::string result;
-        auto status = db->Get(ReadOptions(), key, &result);
-        if (map.find(key) == map.end()) {
-          ASSERT_TRUE(status.IsNotFound());
-        } else {
-          ASSERT_EQ(map[key], result);
-        }
-        break;
-      }
-    }
-    AssertItersEqual(iter.get(), result_iter.get());
-    is_valid = iter->Valid();
-  }
-}
-
-class DoubleComparator : public Comparator {
- public:
-  DoubleComparator() {}
-
-  virtual const char* Name() const override { return "DoubleComparator"; }
-
-  virtual int Compare(const Slice& a, const Slice& b) const override {
-#ifndef CYGWIN
-    double da = std::stod(a.ToString());
-    double db = std::stod(b.ToString());
-#else
-    double da = std::strtod(a.ToString().c_str(), 0 /* endptr */);
-    double db = std::strtod(a.ToString().c_str(), 0 /* endptr */);
-#endif
-    if (da == db) {
-      return a.compare(b);
-    } else if (da > db) {
-      return 1;
-    } else {
-      return -1;
-    }
-  }
-  virtual void FindShortestSeparator(std::string* start,
-                                     const Slice& limit) const override {}
-
-  virtual void FindShortSuccessor(std::string* key) const override {}
-};
-
-class HashComparator : public Comparator {
- public:
-  HashComparator() {}
-
-  virtual const char* Name() const override { return "HashComparator"; }
-
-  virtual int Compare(const Slice& a, const Slice& b) const override {
-    uint32_t ha = Hash(a.data(), a.size(), 66);
-    uint32_t hb = Hash(b.data(), b.size(), 66);
-    if (ha == hb) {
-      return a.compare(b);
-    } else if (ha > hb) {
-      return 1;
-    } else {
-      return -1;
-    }
-  }
-  virtual void FindShortestSeparator(std::string* start,
-                                     const Slice& limit) const override {}
-
-  virtual void FindShortSuccessor(std::string* key) const override {}
-};
-
-class TwoStrComparator : public Comparator {
- public:
-  TwoStrComparator() {}
-
-  virtual const char* Name() const override { return "TwoStrComparator"; }
-
-  virtual int Compare(const Slice& a, const Slice& b) const override {
-    assert(a.size() >= 2);
-    assert(b.size() >= 2);
-    size_t size_a1 = static_cast<size_t>(a[0]);
-    size_t size_b1 = static_cast<size_t>(b[0]);
-    size_t size_a2 = static_cast<size_t>(a[1]);
-    size_t size_b2 = static_cast<size_t>(b[1]);
-    assert(size_a1 + size_a2 + 2 == a.size());
-    assert(size_b1 + size_b2 + 2 == b.size());
-
-    Slice a1 = Slice(a.data() + 2, size_a1);
-    Slice b1 = Slice(b.data() + 2, size_b1);
-    Slice a2 = Slice(a.data() + 2 + size_a1, size_a2);
-    Slice b2 = Slice(b.data() + 2 + size_b1, size_b2);
-
-    if (a1 != b1) {
-      return a1.compare(b1);
-    }
-    return a2.compare(b2);
-  }
-  virtual void FindShortestSeparator(std::string* start,
-                                     const Slice& limit) const override {}
-
-  virtual void FindShortSuccessor(std::string* key) const override {}
-};
-}  // namespace
-
-class ComparatorDBTest : public testing::Test {
- private:
-  std::string dbname_;
-  Env* env_;
-  DB* db_;
-  Options last_options_;
-  std::unique_ptr<const Comparator> comparator_guard;
-
- public:
-  ComparatorDBTest() : env_(Env::Default()), db_(nullptr) {
-    comparator = BytewiseComparator();
-    dbname_ = test::TmpDir() + "/comparator_db_test";
-    EXPECT_OK(DestroyDB(dbname_, last_options_));
-  }
-
-  ~ComparatorDBTest() {
-    delete db_;
-    EXPECT_OK(DestroyDB(dbname_, last_options_));
-    comparator = BytewiseComparator();
-  }
-
-  DB* GetDB() { return db_; }
-
-  void SetOwnedComparator(const Comparator* cmp) {
-    comparator_guard.reset(cmp);
-    comparator = cmp;
-    last_options_.comparator = cmp;
-  }
-
-  // Return the current option configuration.
-  Options* GetOptions() { return &last_options_; }
-
-  void DestroyAndReopen() {
-    // Destroy using last options
-    Destroy();
-    ASSERT_OK(TryReopen());
-  }
-
-  void Destroy() {
-    delete db_;
-    db_ = nullptr;
-    ASSERT_OK(DestroyDB(dbname_, last_options_));
-  }
-
-  Status TryReopen() {
-    delete db_;
-    db_ = nullptr;
-    last_options_.create_if_missing = true;
-
-    return DB::Open(last_options_, dbname_, &db_);
-  }
-};
-
-TEST_F(ComparatorDBTest, Bytewise) {
-  for (int rand_seed = 301; rand_seed < 306; rand_seed++) {
-    DestroyAndReopen();
-    Random rnd(rand_seed);
-    DoRandomIteraratorTest(GetDB(),
-                           {"a", "b", "c", "d", "e", "f", "g", "h", "i"}, &rnd,
-                           8, 100, 3);
-  }
-}
-
-TEST_F(ComparatorDBTest, SimpleSuffixReverseComparator) {
-  SetOwnedComparator(new test::SimpleSuffixReverseComparator());
-
-  for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
-    Options* opt = GetOptions();
-    opt->comparator = comparator;
-    DestroyAndReopen();
-    Random rnd(rnd_seed);
-
-    std::vector<std::string> source_strings;
-    std::vector<std::string> source_prefixes;
-    // Randomly generate 5 prefixes
-    for (int i = 0; i < 5; i++) {
-      source_prefixes.push_back(test::RandomHumanReadableString(&rnd, 8));
-    }
-    for (int j = 0; j < 20; j++) {
-      int prefix_index = rnd.Uniform(static_cast<int>(source_prefixes.size()));
-      std::string key = source_prefixes[prefix_index] +
-                        test::RandomHumanReadableString(&rnd, rnd.Uniform(8));
-      source_strings.push_back(key);
-    }
-
-    DoRandomIteraratorTest(GetDB(), source_strings, &rnd, 30, 600, 66);
-  }
-}
-
-TEST_F(ComparatorDBTest, Uint64Comparator) {
-  SetOwnedComparator(test::Uint64Comparator());
-
-  for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
-    Options* opt = GetOptions();
-    opt->comparator = comparator;
-    DestroyAndReopen();
-    Random rnd(rnd_seed);
-    Random64 rnd64(rnd_seed);
-
-    std::vector<std::string> source_strings;
-    // Randomly generate source keys
-    for (int i = 0; i < 100; i++) {
-      uint64_t r = rnd64.Next();
-      std::string str;
-      str.resize(8);
-      memcpy(&str[0], static_cast<void*>(&r), 8);
-      source_strings.push_back(str);
-    }
-
-    DoRandomIteraratorTest(GetDB(), source_strings, &rnd, 200, 1000, 66);
-  }
-}
-
-TEST_F(ComparatorDBTest, DoubleComparator) {
-  SetOwnedComparator(new DoubleComparator());
-
-  for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
-    Options* opt = GetOptions();
-    opt->comparator = comparator;
-    DestroyAndReopen();
-    Random rnd(rnd_seed);
-
-    std::vector<std::string> source_strings;
-    // Randomly generate source keys
-    for (int i = 0; i < 100; i++) {
-      uint32_t r = rnd.Next();
-      uint32_t divide_order = rnd.Uniform(8);
-      double to_divide = 1.0;
-      for (uint32_t j = 0; j < divide_order; j++) {
-        to_divide *= 10.0;
-      }
-      source_strings.push_back(ToString(r / to_divide));
-    }
-
-    DoRandomIteraratorTest(GetDB(), source_strings, &rnd, 200, 1000, 66);
-  }
-}
-
-TEST_F(ComparatorDBTest, HashComparator) {
-  SetOwnedComparator(new HashComparator());
-
-  for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
-    Options* opt = GetOptions();
-    opt->comparator = comparator;
-    DestroyAndReopen();
-    Random rnd(rnd_seed);
-
-    std::vector<std::string> source_strings;
-    // Randomly generate source keys
-    for (int i = 0; i < 100; i++) {
-      source_strings.push_back(test::RandomKey(&rnd, 8));
-    }
-
-    DoRandomIteraratorTest(GetDB(), source_strings, &rnd, 200, 1000, 66);
-  }
-}
-
-TEST_F(ComparatorDBTest, TwoStrComparator) {
-  SetOwnedComparator(new TwoStrComparator());
-
-  for (int rnd_seed = 301; rnd_seed < 316; rnd_seed++) {
-    Options* opt = GetOptions();
-    opt->comparator = comparator;
-    DestroyAndReopen();
-    Random rnd(rnd_seed);
-
-    std::vector<std::string> source_strings;
-    // Randomly generate source keys
-    for (int i = 0; i < 100; i++) {
-      std::string str;
-      uint32_t size1 = rnd.Uniform(8);
-      uint32_t size2 = rnd.Uniform(8);
-      str.append(1, static_cast<char>(size1));
-      str.append(1, static_cast<char>(size2));
-      str.append(test::RandomKey(&rnd, size1));
-      str.append(test::RandomKey(&rnd, size2));
-      source_strings.push_back(str);
-    }
-
-    DoRandomIteraratorTest(GetDB(), source_strings, &rnd, 200, 1000, 66);
-  }
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/convenience.cc

@@ -1,30 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-// Copyright (c) 2012 Facebook.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file.
-
-#ifndef ROCKSDB_LITE
-
-#include "rocksdb/convenience.h"
-
-#include "db/db_impl.h"
-
-namespace rocksdb {
-
-void CancelAllBackgroundWork(DB* db, bool wait) {
-  (dynamic_cast<DBImpl*>(db))->CancelAllBackgroundWork(wait);
-}
-
-Status DeleteFilesInRange(DB* db, ColumnFamilyHandle* column_family,
-                          const Slice* begin, const Slice* end) {
-  return (dynamic_cast<DBImpl*>(db))
-      ->DeleteFilesInRange(column_family, begin, end);
-}
-
-}  // namespace rocksdb
-
-#endif  // ROCKSDB_LITE

db/corruption_test.cc

@@ -1,4 +1,4 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -7,11 +7,8 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file. See the AUTHORS file for names of contributors.
 
-#ifndef ROCKSDB_LITE
-
 #include "rocksdb/db.h"
 
-#include <inttypes.h>
 #include <errno.h>
 #include <fcntl.h>
 #include <sys/stat.h>
@@ -32,7 +29,7 @@ namespace rocksdb {
 
 static const int kValueSize = 1000;
 
-class CorruptionTest : public testing::Test {
+class CorruptionTest {
  public:
   test::ErrorEnv env_;
   std::string dbname_;
@@ -42,16 +39,13 @@ class CorruptionTest : public testing::Test {
 
   CorruptionTest() {
     tiny_cache_ = NewLRUCache(100);
-    options_.wal_recovery_mode = WALRecoveryMode::kTolerateCorruptedTailRecords;
     options_.env = &env_;
-    dbname_ = test::TmpDir() + "/corruption_test";
+    dbname_ = test::TmpDir() + "/db_test";
     DestroyDB(dbname_, options_);
 
     db_ = nullptr;
     options_.create_if_missing = true;
-    BlockBasedTableOptions table_options;
-    table_options.block_size_deviation = 0;  // make unit test pass for now
-    options_.table_factory.reset(NewBlockBasedTableFactory(table_options));
+    options_.block_size_deviation = 0; // make unit test pass for now
     Reopen();
     options_.create_if_missing = false;
   }
@@ -61,21 +55,14 @@ class CorruptionTest : public testing::Test {
      DestroyDB(dbname_, Options());
   }
 
-  void CloseDb() {
-    delete db_;
-    db_ = nullptr;
-  }
-
   Status TryReopen(Options* options = nullptr) {
     delete db_;
     db_ = nullptr;
     Options opt = (options ? *options : options_);
     opt.env = &env_;
+    opt.block_cache = tiny_cache_;
+    opt.block_size_deviation = 0;
     opt.arena_block_size = 4096;
-    BlockBasedTableOptions table_options;
-    table_options.block_cache = tiny_cache_;
-    table_options.block_size_deviation = 0;
-    opt.table_factory.reset(NewBlockBasedTableFactory(table_options));
     return DB::Open(opt, dbname_, &db_);
   }
 
@@ -89,14 +76,10 @@ class CorruptionTest : public testing::Test {
     ASSERT_OK(::rocksdb::RepairDB(dbname_, options_));
   }
 
-  void Build(int n, int flush_every = 0) {
+  void Build(int n) {
     std::string key_space, value_space;
     WriteBatch batch;
     for (int i = 0; i < n; i++) {
-      if (flush_every != 0 && i != 0 && i % flush_every == 0) {
-        DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
-        dbi->TEST_FlushMemTable();
-      }
       //if ((i % 100) == 0) fprintf(stderr, "@ %d of %d\n", i, n);
       Slice key = Key(i, &key_space);
       batch.Clear();
@@ -106,8 +89,8 @@ class CorruptionTest : public testing::Test {
   }
 
   void Check(int min_expected, int max_expected) {
-    uint64_t next_expected = 0;
-    uint64_t missed = 0;
+    unsigned int next_expected = 0;
+    int missed = 0;
     int bad_keys = 0;
     int bad_values = 0;
     int correct = 0;
@@ -116,7 +99,7 @@ class CorruptionTest : public testing::Test {
     // db itself will raise errors because data is corrupted.
     // Instead, we want the reads to be successful and this test
     // will detect whether the appropriate corruptions have
-    // occurred.
+    // occured.
     Iterator* iter = db_->NewIterator(ReadOptions(false, true));
     for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
       uint64_t key;
@@ -129,7 +112,7 @@ class CorruptionTest : public testing::Test {
       }
       missed += (key - next_expected);
       next_expected = key + 1;
-      if (iter->value() != Value(static_cast<int>(key), &value_space)) {
+      if (iter->value() != Value(key, &value_space)) {
         bad_values++;
       } else {
         correct++;
@@ -138,14 +121,30 @@ class CorruptionTest : public testing::Test {
     delete iter;
 
     fprintf(stderr,
-      "expected=%d..%d; got=%d; bad_keys=%d; bad_values=%d; missed=%llu\n",
-            min_expected, max_expected, correct, bad_keys, bad_values,
-            static_cast<unsigned long long>(missed));
+            "expected=%d..%d; got=%d; bad_keys=%d; bad_values=%d; missed=%d\n",
+            min_expected, max_expected, correct, bad_keys, bad_values, missed);
     ASSERT_LE(min_expected, correct);
     ASSERT_GE(max_expected, correct);
   }
 
-  void CorruptFile(const std::string& fname, int offset, int bytes_to_corrupt) {
+  void Corrupt(FileType filetype, int offset, int bytes_to_corrupt) {
+    // Pick file to corrupt
+    std::vector<std::string> filenames;
+    ASSERT_OK(env_.GetChildren(dbname_, &filenames));
+    uint64_t number;
+    FileType type;
+    std::string fname;
+    int picked_number = -1;
+    for (unsigned int i = 0; i < filenames.size(); i++) {
+      if (ParseFileName(filenames[i], &number, &type) &&
+          type == filetype &&
+          int(number) > picked_number) {  // Pick latest file
+        fname = dbname_ + "/" + filenames[i];
+        picked_number = number;
+      }
+    }
+    ASSERT_TRUE(!fname.empty()) << filetype;
+
     struct stat sbuf;
     if (stat(fname.c_str(), &sbuf) != 0) {
       const char* msg = strerror(errno);
@@ -157,14 +156,14 @@ class CorruptionTest : public testing::Test {
       if (-offset > sbuf.st_size) {
         offset = 0;
       } else {
-        offset = static_cast<int>(sbuf.st_size + offset);
+        offset = sbuf.st_size + offset;
       }
     }
     if (offset > sbuf.st_size) {
-      offset = static_cast<int>(sbuf.st_size);
+      offset = sbuf.st_size;
     }
     if (offset + bytes_to_corrupt > sbuf.st_size) {
-      bytes_to_corrupt = static_cast<int>(sbuf.st_size - offset);
+      bytes_to_corrupt = sbuf.st_size - offset;
     }
 
     // Do it
@@ -178,42 +177,6 @@ class CorruptionTest : public testing::Test {
     ASSERT_TRUE(s.ok()) << s.ToString();
   }
 
-  void Corrupt(FileType filetype, int offset, int bytes_to_corrupt) {
-    // Pick file to corrupt
-    std::vector<std::string> filenames;
-    ASSERT_OK(env_.GetChildren(dbname_, &filenames));
-    uint64_t number;
-    FileType type;
-    std::string fname;
-    int picked_number = -1;
-    for (size_t i = 0; i < filenames.size(); i++) {
-      if (ParseFileName(filenames[i], &number, &type) &&
-          type == filetype &&
-          static_cast<int>(number) > picked_number) {  // Pick latest file
-        fname = dbname_ + "/" + filenames[i];
-        picked_number = static_cast<int>(number);
-      }
-    }
-    ASSERT_TRUE(!fname.empty()) << filetype;
-
-    CorruptFile(fname, offset, bytes_to_corrupt);
-  }
-
-  // corrupts exactly one file at level `level`. if no file found at level,
-  // asserts
-  void CorruptTableFileAtLevel(int level, int offset, int bytes_to_corrupt) {
-    std::vector<LiveFileMetaData> metadata;
-    db_->GetLiveFilesMetaData(&metadata);
-    for (const auto& m : metadata) {
-      if (m.level == level) {
-        CorruptFile(dbname_ + "/" + m.name, offset, bytes_to_corrupt);
-        return;
-      }
-    }
-    ASSERT_TRUE(false) << "no file found at level";
-  }
-
-
   int Property(const std::string& name) {
     std::string property;
     int result;
@@ -235,53 +198,32 @@ class CorruptionTest : public testing::Test {
 
   // Return the value to associate with the specified key
   Slice Value(int k, std::string* storage) {
-    if (k == 0) {
-      // Ugh.  Random seed of 0 used to produce no entropy.  This code
-      // preserves the implementation that was in place when all of the
-      // magic values in this file were picked.
-      *storage = std::string(kValueSize, ' ');
-      return Slice(*storage);
-    } else {
-      Random r(k);
-      return test::RandomString(&r, kValueSize, storage);
-    }
+    Random r(k);
+    return test::RandomString(&r, kValueSize, storage);
   }
 };
 
-TEST_F(CorruptionTest, Recovery) {
+TEST(CorruptionTest, Recovery) {
   Build(100);
   Check(100, 100);
-#ifdef OS_WIN
-  // On Wndows OS Disk cache does not behave properly
-  // We do not call FlushBuffers on every Flush. If we do not close
-  // the log file prior to the corruption we end up with the first
-  // block not corrupted but only the second. However, under the debugger
-  // things work just fine but never pass when running normally
-  // For that reason people may want to run with unbuffered I/O. That option
-  // is not available for WAL though.
-  CloseDb();
-#endif
   Corrupt(kLogFile, 19, 1);      // WriteBatch tag for first record
   Corrupt(kLogFile, log::kBlockSize + 1000, 1);  // Somewhere in second block
-  ASSERT_TRUE(!TryReopen().ok());
-  options_.paranoid_checks = false;
-  Reopen(&options_);
+  Reopen();
 
   // The 64 records in the first two log blocks are completely lost.
   Check(36, 36);
 }
 
-TEST_F(CorruptionTest, RecoverWriteError) {
+TEST(CorruptionTest, RecoverWriteError) {
   env_.writable_file_error_ = true;
   Status s = TryReopen();
   ASSERT_TRUE(!s.ok());
 }
 
-TEST_F(CorruptionTest, NewFileErrorDuringWrite) {
+TEST(CorruptionTest, NewFileErrorDuringWrite) {
   // Do enough writing to force minor compaction
   env_.writable_file_error_ = true;
-  const int num =
-      static_cast<int>(3 + (Options().write_buffer_size / kValueSize));
+  const int num = 3 + (Options().write_buffer_size / kValueSize);
   std::string value_storage;
   Status s;
   bool failed = false;
@@ -300,7 +242,7 @@ TEST_F(CorruptionTest, NewFileErrorDuringWrite) {
   Reopen();
 }
 
-TEST_F(CorruptionTest, TableFile) {
+TEST(CorruptionTest, TableFile) {
   Build(100);
   DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
   dbi->TEST_FlushMemTable();
@@ -311,32 +253,24 @@ TEST_F(CorruptionTest, TableFile) {
   Check(99, 99);
 }
 
-TEST_F(CorruptionTest, TableFileIndexData) {
-  Options options;
-  // very big, we'll trigger flushes manually
-  options.write_buffer_size = 100 * 1024 * 1024;
-  Reopen(&options);
-  // build 2 tables, flush at 5000
-  Build(10000, 5000);
+TEST(CorruptionTest, TableFileIndexData) {
+  Build(10000);  // Enough to build multiple Tables
   DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
   dbi->TEST_FlushMemTable();
 
-  // corrupt an index block of an entire file
   Corrupt(kTableFile, -2000, 500);
   Reopen();
-  // one full file should be readable, since only one was corrupted
-  // the other file should be fully non-readable, since index was corrupted
-  Check(5000, 5000);
+  Check(5000, 9999);
 }
 
-TEST_F(CorruptionTest, MissingDescriptor) {
+TEST(CorruptionTest, MissingDescriptor) {
   Build(1000);
   RepairDB();
   Reopen();
   Check(1000, 1000);
 }
 
-TEST_F(CorruptionTest, SequenceNumberRecovery) {
+TEST(CorruptionTest, SequenceNumberRecovery) {
   ASSERT_OK(db_->Put(WriteOptions(), "foo", "v1"));
   ASSERT_OK(db_->Put(WriteOptions(), "foo", "v2"));
   ASSERT_OK(db_->Put(WriteOptions(), "foo", "v3"));
@@ -357,7 +291,7 @@ TEST_F(CorruptionTest, SequenceNumberRecovery) {
   ASSERT_EQ("v6", v);
 }
 
-TEST_F(CorruptionTest, CorruptedDescriptor) {
+TEST(CorruptionTest, CorruptedDescriptor) {
   ASSERT_OK(db_->Put(WriteOptions(), "foo", "hello"));
   DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
   dbi->TEST_FlushMemTable();
@@ -374,15 +308,12 @@ TEST_F(CorruptionTest, CorruptedDescriptor) {
   ASSERT_EQ("hello", v);
 }
 
-TEST_F(CorruptionTest, CompactionInputError) {
-  Options options;
-  Reopen(&options);
+TEST(CorruptionTest, CompactionInputError) {
   Build(10);
   DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
   dbi->TEST_FlushMemTable();
-  dbi->TEST_CompactRange(0, nullptr, nullptr);
-  dbi->TEST_CompactRange(1, nullptr, nullptr);
-  ASSERT_EQ(1, Property("rocksdb.num-files-at-level2"));
+  const int last = dbi->MaxMemCompactionLevel();
+  ASSERT_EQ(1, Property("rocksdb.num-files-at-level" + NumberToString(last)));
 
   Corrupt(kTableFile, 100, 1);
   Check(9, 9);
@@ -392,41 +323,33 @@ TEST_F(CorruptionTest, CompactionInputError) {
   Check(10000, 10000);
 }
 
-TEST_F(CorruptionTest, CompactionInputErrorParanoid) {
+TEST(CorruptionTest, CompactionInputErrorParanoid) {
   Options options;
   options.paranoid_checks = true;
-  options.write_buffer_size = 131072;
-  options.max_write_buffer_number = 2;
+  options.write_buffer_size = 1048576;
   Reopen(&options);
   DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
 
-  // Fill levels >= 1
+  // Fill levels >= 1 so memtable compaction outputs to level 1
   for (int level = 1; level < dbi->NumberLevels(); level++) {
     dbi->Put(WriteOptions(), "", "begin");
     dbi->Put(WriteOptions(), "~", "end");
     dbi->TEST_FlushMemTable();
-    for (int comp_level = 0; comp_level < dbi->NumberLevels() - level;
-         ++comp_level) {
-      dbi->TEST_CompactRange(comp_level, nullptr, nullptr);
-    }
   }
 
-  Reopen(&options);
-
-  dbi = reinterpret_cast<DBImpl*>(db_);
   Build(10);
   dbi->TEST_FlushMemTable();
   dbi->TEST_WaitForCompact();
   ASSERT_EQ(1, Property("rocksdb.num-files-at-level0"));
 
-  CorruptTableFileAtLevel(0, 100, 1);
+  Corrupt(kTableFile, 100, 1);
   Check(9, 9);
 
   // Write must eventually fail because of corrupted table
   Status s;
   std::string tmp1, tmp2;
   bool failed = false;
-  for (int i = 0; i < 10000; i++) {
+  for (int i = 0; i < 10000 && s.ok(); i++) {
     s = db_->Put(WriteOptions(), Key(i, &tmp1), Value(i, &tmp2));
     if (!s.ok()) {
       failed = true;
@@ -437,7 +360,7 @@ TEST_F(CorruptionTest, CompactionInputErrorParanoid) {
   ASSERT_TRUE(!s.ok()) << "write did not fail in corrupted paranoid db";
 }
 
-TEST_F(CorruptionTest, UnrelatedKeys) {
+TEST(CorruptionTest, UnrelatedKeys) {
   Build(10);
   DBImpl* dbi = reinterpret_cast<DBImpl*>(db_);
   dbi->TEST_FlushMemTable();
@@ -453,7 +376,7 @@ TEST_F(CorruptionTest, UnrelatedKeys) {
   ASSERT_EQ(Value(1000, &tmp2).ToString(), v);
 }
 
-TEST_F(CorruptionTest, FileSystemStateCorrupted) {
+TEST(CorruptionTest, FileSystemStateCorrupted) {
   for (int iter = 0; iter < 2; ++iter) {
     Options options;
     options.paranoid_checks = true;
@@ -489,16 +412,5 @@ TEST_F(CorruptionTest, FileSystemStateCorrupted) {
 }  // namespace rocksdb
 
 int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
+  return rocksdb::test::RunAllTests();
 }
-
-#else
-#include <stdio.h>
-
-int main(int argc, char** argv) {
-  fprintf(stderr, "SKIPPED as RepairDB() is not supported in ROCKSDB_LITE\n");
-  return 0;
-}
-
-#endif  // !ROCKSDB_LITE

db/cuckoo_table_db_test.cc

@@ -1,333 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-
-#ifndef ROCKSDB_LITE
-
-#include "db/db_impl.h"
-#include "rocksdb/db.h"
-#include "rocksdb/env.h"
-#include "table/meta_blocks.h"
-#include "table/cuckoo_table_factory.h"
-#include "table/cuckoo_table_reader.h"
-#include "util/testharness.h"
-#include "util/testutil.h"
-
-namespace rocksdb {
-
-class CuckooTableDBTest : public testing::Test {
- private:
-  std::string dbname_;
-  Env* env_;
-  DB* db_;
-
- public:
-  CuckooTableDBTest() : env_(Env::Default()) {
-    dbname_ = test::TmpDir() + "/cuckoo_table_db_test";
-    EXPECT_OK(DestroyDB(dbname_, Options()));
-    db_ = nullptr;
-    Reopen();
-  }
-
-  ~CuckooTableDBTest() {
-    delete db_;
-    EXPECT_OK(DestroyDB(dbname_, Options()));
-  }
-
-  Options CurrentOptions() {
-    Options options;
-    options.table_factory.reset(NewCuckooTableFactory());
-    options.memtable_factory.reset(NewHashLinkListRepFactory(4, 0, 3, true));
-    options.allow_mmap_reads = true;
-    options.create_if_missing = true;
-    return options;
-  }
-
-  DBImpl* dbfull() {
-    return reinterpret_cast<DBImpl*>(db_);
-  }
-
-  // The following util methods are copied from plain_table_db_test.
-  void Reopen(Options* options = nullptr) {
-    delete db_;
-    db_ = nullptr;
-    Options opts;
-    if (options != nullptr) {
-      opts = *options;
-    } else {
-      opts = CurrentOptions();
-      opts.create_if_missing = true;
-    }
-    ASSERT_OK(DB::Open(opts, dbname_, &db_));
-  }
-
-  Status Put(const Slice& k, const Slice& v) {
-    return db_->Put(WriteOptions(), k, v);
-  }
-
-  Status Delete(const std::string& k) {
-    return db_->Delete(WriteOptions(), k);
-  }
-
-  std::string Get(const std::string& k) {
-    ReadOptions options;
-    std::string result;
-    Status s = db_->Get(options, k, &result);
-    if (s.IsNotFound()) {
-      result = "NOT_FOUND";
-    } else if (!s.ok()) {
-      result = s.ToString();
-    }
-    return result;
-  }
-
-  int NumTableFilesAtLevel(int level) {
-    std::string property;
-    EXPECT_TRUE(db_->GetProperty(
-        "rocksdb.num-files-at-level" + NumberToString(level), &property));
-    return atoi(property.c_str());
-  }
-
-  // Return spread of files per level
-  std::string FilesPerLevel() {
-    std::string result;
-    size_t last_non_zero_offset = 0;
-    for (int level = 0; level < db_->NumberLevels(); level++) {
-      int f = NumTableFilesAtLevel(level);
-      char buf[100];
-      snprintf(buf, sizeof(buf), "%s%d", (level ? "," : ""), f);
-      result += buf;
-      if (f > 0) {
-        last_non_zero_offset = result.size();
-      }
-    }
-    result.resize(last_non_zero_offset);
-    return result;
-  }
-};
-
-TEST_F(CuckooTableDBTest, Flush) {
-  // Try with empty DB first.
-  ASSERT_TRUE(dbfull() != nullptr);
-  ASSERT_EQ("NOT_FOUND", Get("key2"));
-
-  // Add some values to db.
-  Options options = CurrentOptions();
-  Reopen(&options);
-
-  ASSERT_OK(Put("key1", "v1"));
-  ASSERT_OK(Put("key2", "v2"));
-  ASSERT_OK(Put("key3", "v3"));
-  dbfull()->TEST_FlushMemTable();
-
-  TablePropertiesCollection ptc;
-  reinterpret_cast<DB*>(dbfull())->GetPropertiesOfAllTables(&ptc);
-  ASSERT_EQ(1U, ptc.size());
-  ASSERT_EQ(3U, ptc.begin()->second->num_entries);
-  ASSERT_EQ("1", FilesPerLevel());
-
-  ASSERT_EQ("v1", Get("key1"));
-  ASSERT_EQ("v2", Get("key2"));
-  ASSERT_EQ("v3", Get("key3"));
-  ASSERT_EQ("NOT_FOUND", Get("key4"));
-
-  // Now add more keys and flush.
-  ASSERT_OK(Put("key4", "v4"));
-  ASSERT_OK(Put("key5", "v5"));
-  ASSERT_OK(Put("key6", "v6"));
-  dbfull()->TEST_FlushMemTable();
-
-  reinterpret_cast<DB*>(dbfull())->GetPropertiesOfAllTables(&ptc);
-  ASSERT_EQ(2U, ptc.size());
-  auto row = ptc.begin();
-  ASSERT_EQ(3U, row->second->num_entries);
-  ASSERT_EQ(3U, (++row)->second->num_entries);
-  ASSERT_EQ("2", FilesPerLevel());
-  ASSERT_EQ("v1", Get("key1"));
-  ASSERT_EQ("v2", Get("key2"));
-  ASSERT_EQ("v3", Get("key3"));
-  ASSERT_EQ("v4", Get("key4"));
-  ASSERT_EQ("v5", Get("key5"));
-  ASSERT_EQ("v6", Get("key6"));
-
-  ASSERT_OK(Delete("key6"));
-  ASSERT_OK(Delete("key5"));
-  ASSERT_OK(Delete("key4"));
-  dbfull()->TEST_FlushMemTable();
-  reinterpret_cast<DB*>(dbfull())->GetPropertiesOfAllTables(&ptc);
-  ASSERT_EQ(3U, ptc.size());
-  row = ptc.begin();
-  ASSERT_EQ(3U, row->second->num_entries);
-  ASSERT_EQ(3U, (++row)->second->num_entries);
-  ASSERT_EQ(3U, (++row)->second->num_entries);
-  ASSERT_EQ("3", FilesPerLevel());
-  ASSERT_EQ("v1", Get("key1"));
-  ASSERT_EQ("v2", Get("key2"));
-  ASSERT_EQ("v3", Get("key3"));
-  ASSERT_EQ("NOT_FOUND", Get("key4"));
-  ASSERT_EQ("NOT_FOUND", Get("key5"));
-  ASSERT_EQ("NOT_FOUND", Get("key6"));
-}
-
-TEST_F(CuckooTableDBTest, FlushWithDuplicateKeys) {
-  Options options = CurrentOptions();
-  Reopen(&options);
-  ASSERT_OK(Put("key1", "v1"));
-  ASSERT_OK(Put("key2", "v2"));
-  ASSERT_OK(Put("key1", "v3"));  // Duplicate
-  dbfull()->TEST_FlushMemTable();
-
-  TablePropertiesCollection ptc;
-  reinterpret_cast<DB*>(dbfull())->GetPropertiesOfAllTables(&ptc);
-  ASSERT_EQ(1U, ptc.size());
-  ASSERT_EQ(2U, ptc.begin()->second->num_entries);
-  ASSERT_EQ("1", FilesPerLevel());
-  ASSERT_EQ("v3", Get("key1"));
-  ASSERT_EQ("v2", Get("key2"));
-}
-
-namespace {
-static std::string Key(int i) {
-  char buf[100];
-  snprintf(buf, sizeof(buf), "key_______%06d", i);
-  return std::string(buf);
-}
-static std::string Uint64Key(uint64_t i) {
-  std::string str;
-  str.resize(8);
-  memcpy(&str[0], static_cast<void*>(&i), 8);
-  return str;
-}
-}  // namespace.
-
-TEST_F(CuckooTableDBTest, Uint64Comparator) {
-  Options options = CurrentOptions();
-  options.comparator = test::Uint64Comparator();
-  Reopen(&options);
-
-  ASSERT_OK(Put(Uint64Key(1), "v1"));
-  ASSERT_OK(Put(Uint64Key(2), "v2"));
-  ASSERT_OK(Put(Uint64Key(3), "v3"));
-  dbfull()->TEST_FlushMemTable();
-
-  ASSERT_EQ("v1", Get(Uint64Key(1)));
-  ASSERT_EQ("v2", Get(Uint64Key(2)));
-  ASSERT_EQ("v3", Get(Uint64Key(3)));
-  ASSERT_EQ("NOT_FOUND", Get(Uint64Key(4)));
-
-  // Add more keys.
-  ASSERT_OK(Delete(Uint64Key(2)));  // Delete.
-  dbfull()->TEST_FlushMemTable();
-  ASSERT_OK(Put(Uint64Key(3), "v0"));  // Update.
-  ASSERT_OK(Put(Uint64Key(4), "v4"));
-  dbfull()->TEST_FlushMemTable();
-  ASSERT_EQ("v1", Get(Uint64Key(1)));
-  ASSERT_EQ("NOT_FOUND", Get(Uint64Key(2)));
-  ASSERT_EQ("v0", Get(Uint64Key(3)));
-  ASSERT_EQ("v4", Get(Uint64Key(4)));
-}
-
-TEST_F(CuckooTableDBTest, CompactionIntoMultipleFiles) {
-  // Create a big L0 file and check it compacts into multiple files in L1.
-  Options options = CurrentOptions();
-  options.write_buffer_size = 270 << 10;
-  // Two SST files should be created, each containing 14 keys.
-  // Number of buckets will be 16. Total size ~156 KB.
-  options.target_file_size_base = 160 << 10;
-  Reopen(&options);
-
-  // Write 28 values, each 10016 B ~ 10KB
-  for (int idx = 0; idx < 28; ++idx) {
-    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + idx)));
-  }
-  dbfull()->TEST_WaitForFlushMemTable();
-  ASSERT_EQ("1", FilesPerLevel());
-
-  dbfull()->TEST_CompactRange(0, nullptr, nullptr, nullptr,
-                              true /* disallow trivial move */);
-  ASSERT_EQ("0,2", FilesPerLevel());
-  for (int idx = 0; idx < 28; ++idx) {
-    ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
-  }
-}
-
-TEST_F(CuckooTableDBTest, SameKeyInsertedInTwoDifferentFilesAndCompacted) {
-  // Insert same key twice so that they go to different SST files. Then wait for
-  // compaction and check if the latest value is stored and old value removed.
-  Options options = CurrentOptions();
-  options.write_buffer_size = 100 << 10;  // 100KB
-  options.level0_file_num_compaction_trigger = 2;
-  Reopen(&options);
-
-  // Write 11 values, each 10016 B
-  for (int idx = 0; idx < 11; ++idx) {
-    ASSERT_OK(Put(Key(idx), std::string(10000, 'a')));
-  }
-  dbfull()->TEST_WaitForFlushMemTable();
-  ASSERT_EQ("1", FilesPerLevel());
-
-  // Generate one more file in level-0, and should trigger level-0 compaction
-  for (int idx = 0; idx < 11; ++idx) {
-    ASSERT_OK(Put(Key(idx), std::string(10000, 'a' + idx)));
-  }
-  dbfull()->TEST_WaitForFlushMemTable();
-  dbfull()->TEST_CompactRange(0, nullptr, nullptr);
-
-  ASSERT_EQ("0,1", FilesPerLevel());
-  for (int idx = 0; idx < 11; ++idx) {
-    ASSERT_EQ(std::string(10000, 'a' + idx), Get(Key(idx)));
-  }
-}
-
-TEST_F(CuckooTableDBTest, AdaptiveTable) {
-  Options options = CurrentOptions();
-
-  // Write some keys using cuckoo table.
-  options.table_factory.reset(NewCuckooTableFactory());
-  Reopen(&options);
-
-  ASSERT_OK(Put("key1", "v1"));
-  ASSERT_OK(Put("key2", "v2"));
-  ASSERT_OK(Put("key3", "v3"));
-  dbfull()->TEST_FlushMemTable();
-
-  // Write some keys using plain table.
-  options.create_if_missing = false;
-  options.table_factory.reset(NewPlainTableFactory());
-  Reopen(&options);
-  ASSERT_OK(Put("key4", "v4"));
-  ASSERT_OK(Put("key1", "v5"));
-  dbfull()->TEST_FlushMemTable();
-
-  // Write some keys using block based table.
-  std::shared_ptr<TableFactory> block_based_factory(
-      NewBlockBasedTableFactory());
-  options.table_factory.reset(NewAdaptiveTableFactory(block_based_factory));
-  Reopen(&options);
-  ASSERT_OK(Put("key5", "v6"));
-  ASSERT_OK(Put("key2", "v7"));
-  dbfull()->TEST_FlushMemTable();
-
-  ASSERT_EQ("v5", Get("key1"));
-  ASSERT_EQ("v7", Get("key2"));
-  ASSERT_EQ("v3", Get("key3"));
-  ASSERT_EQ("v4", Get("key4"));
-  ASSERT_EQ("v6", Get("key5"));
-}
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}
-
-#else
-#include <stdio.h>
-
-int main(int argc, char** argv) {
-  fprintf(stderr, "SKIPPED as Cuckoo table is not supported in ROCKSDB_LITE\n");
-  return 0;
-}
-
-#endif  // ROCKSDB_LITE

db/db_block_cache_test.cc

@@ -1,495 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-#include <cstdlib>
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-
-namespace rocksdb {
-
-class DBBlockCacheTest : public DBTestBase {
- private:
-  size_t miss_count_ = 0;
-  size_t hit_count_ = 0;
-  size_t insert_count_ = 0;
-  size_t failure_count_ = 0;
-  size_t compressed_miss_count_ = 0;
-  size_t compressed_hit_count_ = 0;
-  size_t compressed_insert_count_ = 0;
-  size_t compressed_failure_count_ = 0;
-
- public:
-  const size_t kNumBlocks = 10;
-  const size_t kValueSize = 100;
-
-  DBBlockCacheTest() : DBTestBase("/db_block_cache_test") {}
-
-  BlockBasedTableOptions GetTableOptions() {
-    BlockBasedTableOptions table_options;
-    // Set a small enough block size so that each key-value get its own block.
-    table_options.block_size = 1;
-    return table_options;
-  }
-
-  Options GetOptions(const BlockBasedTableOptions& table_options) {
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    // options.compression = kNoCompression;
-    options.statistics = rocksdb::CreateDBStatistics();
-    options.table_factory.reset(new BlockBasedTableFactory(table_options));
-    return options;
-  }
-
-  void InitTable(const Options& options) {
-    std::string value(kValueSize, 'a');
-    for (size_t i = 0; i < kNumBlocks; i++) {
-      ASSERT_OK(Put(ToString(i), value.c_str()));
-    }
-  }
-
-  void RecordCacheCounters(const Options& options) {
-    miss_count_ = TestGetTickerCount(options, BLOCK_CACHE_MISS);
-    hit_count_ = TestGetTickerCount(options, BLOCK_CACHE_HIT);
-    insert_count_ = TestGetTickerCount(options, BLOCK_CACHE_ADD);
-    failure_count_ = TestGetTickerCount(options, BLOCK_CACHE_ADD_FAILURES);
-    compressed_miss_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS);
-    compressed_hit_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_HIT);
-    compressed_insert_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD);
-    compressed_failure_count_ =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD_FAILURES);
-  }
-
-  void CheckCacheCounters(const Options& options, size_t expected_misses,
-                          size_t expected_hits, size_t expected_inserts,
-                          size_t expected_failures) {
-    size_t new_miss_count = TestGetTickerCount(options, BLOCK_CACHE_MISS);
-    size_t new_hit_count = TestGetTickerCount(options, BLOCK_CACHE_HIT);
-    size_t new_insert_count = TestGetTickerCount(options, BLOCK_CACHE_ADD);
-    size_t new_failure_count =
-        TestGetTickerCount(options, BLOCK_CACHE_ADD_FAILURES);
-    ASSERT_EQ(miss_count_ + expected_misses, new_miss_count);
-    ASSERT_EQ(hit_count_ + expected_hits, new_hit_count);
-    ASSERT_EQ(insert_count_ + expected_inserts, new_insert_count);
-    ASSERT_EQ(failure_count_ + expected_failures, new_failure_count);
-    miss_count_ = new_miss_count;
-    hit_count_ = new_hit_count;
-    insert_count_ = new_insert_count;
-    failure_count_ = new_failure_count;
-  }
-
-  void CheckCompressedCacheCounters(const Options& options,
-                                    size_t expected_misses,
-                                    size_t expected_hits,
-                                    size_t expected_inserts,
-                                    size_t expected_failures) {
-    size_t new_miss_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS);
-    size_t new_hit_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_HIT);
-    size_t new_insert_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD);
-    size_t new_failure_count =
-        TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_ADD_FAILURES);
-    ASSERT_EQ(compressed_miss_count_ + expected_misses, new_miss_count);
-    ASSERT_EQ(compressed_hit_count_ + expected_hits, new_hit_count);
-    ASSERT_EQ(compressed_insert_count_ + expected_inserts, new_insert_count);
-    ASSERT_EQ(compressed_failure_count_ + expected_failures, new_failure_count);
-    compressed_miss_count_ = new_miss_count;
-    compressed_hit_count_ = new_hit_count;
-    compressed_insert_count_ = new_insert_count;
-    compressed_failure_count_ = new_failure_count;
-  }
-};
-
-TEST_F(DBBlockCacheTest, TestWithoutCompressedBlockCache) {
-  ReadOptions read_options;
-  auto table_options = GetTableOptions();
-  auto options = GetOptions(table_options);
-  InitTable(options);
-
-  std::shared_ptr<Cache> cache = NewLRUCache(0, 0, false);
-  table_options.block_cache = cache;
-  options.table_factory.reset(new BlockBasedTableFactory(table_options));
-  Reopen(options);
-  RecordCacheCounters(options);
-
-  std::vector<std::unique_ptr<Iterator>> iterators(kNumBlocks - 1);
-  Iterator* iter = nullptr;
-
-  // Load blocks into cache.
-  for (size_t i = 0; i < kNumBlocks - 1; i++) {
-    iter = db_->NewIterator(read_options);
-    iter->Seek(ToString(i));
-    ASSERT_OK(iter->status());
-    CheckCacheCounters(options, 1, 0, 1, 0);
-    iterators[i].reset(iter);
-  }
-  size_t usage = cache->GetUsage();
-  ASSERT_LT(0, usage);
-  cache->SetCapacity(usage);
-  ASSERT_EQ(usage, cache->GetPinnedUsage());
-
-  // Test with strict capacity limit.
-  cache->SetStrictCapacityLimit(true);
-  iter = db_->NewIterator(read_options);
-  iter->Seek(ToString(kNumBlocks - 1));
-  ASSERT_TRUE(iter->status().IsIncomplete());
-  CheckCacheCounters(options, 1, 0, 0, 1);
-  delete iter;
-  iter = nullptr;
-
-  // Release interators and access cache again.
-  for (size_t i = 0; i < kNumBlocks - 1; i++) {
-    iterators[i].reset();
-    CheckCacheCounters(options, 0, 0, 0, 0);
-  }
-  ASSERT_EQ(0, cache->GetPinnedUsage());
-  for (size_t i = 0; i < kNumBlocks - 1; i++) {
-    iter = db_->NewIterator(read_options);
-    iter->Seek(ToString(i));
-    ASSERT_OK(iter->status());
-    CheckCacheCounters(options, 0, 1, 0, 0);
-    iterators[i].reset(iter);
-  }
-}
-
-#ifdef SNAPPY
-TEST_F(DBBlockCacheTest, TestWithCompressedBlockCache) {
-  ReadOptions read_options;
-  auto table_options = GetTableOptions();
-  auto options = GetOptions(table_options);
-  options.compression = CompressionType::kSnappyCompression;
-  InitTable(options);
-
-  std::shared_ptr<Cache> cache = NewLRUCache(0, 0, false);
-  std::shared_ptr<Cache> compressed_cache = NewLRUCache(0, 0, false);
-  table_options.block_cache = cache;
-  table_options.block_cache_compressed = compressed_cache;
-  options.table_factory.reset(new BlockBasedTableFactory(table_options));
-  Reopen(options);
-  RecordCacheCounters(options);
-
-  std::vector<std::unique_ptr<Iterator>> iterators(kNumBlocks - 1);
-  Iterator* iter = nullptr;
-
-  // Load blocks into cache.
-  for (size_t i = 0; i < kNumBlocks - 1; i++) {
-    iter = db_->NewIterator(read_options);
-    iter->Seek(ToString(i));
-    ASSERT_OK(iter->status());
-    CheckCacheCounters(options, 1, 0, 1, 0);
-    CheckCompressedCacheCounters(options, 1, 0, 1, 0);
-    iterators[i].reset(iter);
-  }
-  size_t usage = cache->GetUsage();
-  ASSERT_LT(0, usage);
-  ASSERT_EQ(usage, cache->GetPinnedUsage());
-  size_t compressed_usage = compressed_cache->GetUsage();
-  ASSERT_LT(0, compressed_usage);
-  // Compressed block cache cannot be pinned.
-  ASSERT_EQ(0, compressed_cache->GetPinnedUsage());
-
-  // Set strict capacity limit flag. Now block will only load into compressed
-  // block cache.
-  cache->SetCapacity(usage);
-  cache->SetStrictCapacityLimit(true);
-  ASSERT_EQ(usage, cache->GetPinnedUsage());
-  // compressed_cache->SetCapacity(compressed_usage);
-  compressed_cache->SetCapacity(0);
-  // compressed_cache->SetStrictCapacityLimit(true);
-  iter = db_->NewIterator(read_options);
-  iter->Seek(ToString(kNumBlocks - 1));
-  ASSERT_TRUE(iter->status().IsIncomplete());
-  CheckCacheCounters(options, 1, 0, 0, 1);
-  CheckCompressedCacheCounters(options, 1, 0, 1, 0);
-  delete iter;
-  iter = nullptr;
-
-  // Clear strict capacity limit flag. This time we shall hit compressed block
-  // cache.
-  cache->SetStrictCapacityLimit(false);
-  iter = db_->NewIterator(read_options);
-  iter->Seek(ToString(kNumBlocks - 1));
-  ASSERT_OK(iter->status());
-  CheckCacheCounters(options, 1, 0, 1, 0);
-  CheckCompressedCacheCounters(options, 0, 1, 0, 0);
-  delete iter;
-  iter = nullptr;
-}
-#endif  // SNAPPY
-
-#ifndef ROCKSDB_LITE
-
-// Make sure that when options.block_cache is set, after a new table is
-// created its index/filter blocks are added to block cache.
-TEST_F(DBBlockCacheTest, IndexAndFilterBlocksOfNewTableAddedToCache) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.statistics = rocksdb::CreateDBStatistics();
-  BlockBasedTableOptions table_options;
-  table_options.cache_index_and_filter_blocks = true;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(20));
-  options.table_factory.reset(new BlockBasedTableFactory(table_options));
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  ASSERT_OK(Put(1, "key", "val"));
-  // Create a new table.
-  ASSERT_OK(Flush(1));
-
-  // index/filter blocks added to block cache right after table creation.
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
-  ASSERT_EQ(2, /* only index/filter were added */
-            TestGetTickerCount(options, BLOCK_CACHE_ADD));
-  ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_DATA_MISS));
-  uint64_t int_num;
-  ASSERT_TRUE(
-      dbfull()->GetIntProperty("rocksdb.estimate-table-readers-mem", &int_num));
-  ASSERT_EQ(int_num, 0U);
-
-  // Make sure filter block is in cache.
-  std::string value;
-  ReadOptions ropt;
-  db_->KeyMayExist(ReadOptions(), handles_[1], "key", &value);
-
-  // Miss count should remain the same.
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
-
-  db_->KeyMayExist(ReadOptions(), handles_[1], "key", &value);
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
-  ASSERT_EQ(2, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
-
-  // Make sure index block is in cache.
-  auto index_block_hit = TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT);
-  value = Get(1, "key");
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
-  ASSERT_EQ(index_block_hit + 1,
-            TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
-
-  value = Get(1, "key");
-  ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
-  ASSERT_EQ(index_block_hit + 2,
-            TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
-}
-
-TEST_F(DBBlockCacheTest, IndexAndFilterBlocksStats) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.statistics = rocksdb::CreateDBStatistics();
-  BlockBasedTableOptions table_options;
-  table_options.cache_index_and_filter_blocks = true;
-  // 200 bytes are enough to hold the first two blocks
-  std::shared_ptr<Cache> cache = NewLRUCache(200, 0, false);
-  table_options.block_cache = cache;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(20));
-  options.table_factory.reset(new BlockBasedTableFactory(table_options));
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  ASSERT_OK(Put(1, "key", "val"));
-  // Create a new table
-  ASSERT_OK(Flush(1));
-  size_t index_bytes_insert =
-      TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_INSERT);
-  size_t filter_bytes_insert =
-      TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_INSERT);
-  ASSERT_GT(index_bytes_insert, 0);
-  ASSERT_GT(filter_bytes_insert, 0);
-  ASSERT_EQ(cache->GetUsage(), index_bytes_insert + filter_bytes_insert);
-  // set the cache capacity to the current usage
-  cache->SetCapacity(index_bytes_insert + filter_bytes_insert);
-  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT), 0);
-  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT), 0);
-  ASSERT_OK(Put(1, "key2", "val"));
-  // Create a new table
-  ASSERT_OK(Flush(1));
-  // cache evicted old index and block entries
-  ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_INSERT),
-            index_bytes_insert);
-  ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_INSERT),
-            filter_bytes_insert);
-  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_INDEX_BYTES_EVICT),
-            index_bytes_insert);
-  ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_FILTER_BYTES_EVICT),
-            filter_bytes_insert);
-}
-
-TEST_F(DBBlockCacheTest, ParanoidFileChecks) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.statistics = rocksdb::CreateDBStatistics();
-  options.level0_file_num_compaction_trigger = 2;
-  options.paranoid_file_checks = true;
-  BlockBasedTableOptions table_options;
-  table_options.cache_index_and_filter_blocks = false;
-  table_options.filter_policy.reset(NewBloomFilterPolicy(20));
-  options.table_factory.reset(new BlockBasedTableFactory(table_options));
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  ASSERT_OK(Put(1, "1_key", "val"));
-  ASSERT_OK(Put(1, "9_key", "val"));
-  // Create a new table.
-  ASSERT_OK(Flush(1));
-  ASSERT_EQ(1, /* read and cache data block */
-            TestGetTickerCount(options, BLOCK_CACHE_ADD));
-
-  ASSERT_OK(Put(1, "1_key2", "val2"));
-  ASSERT_OK(Put(1, "9_key2", "val2"));
-  // Create a new SST file. This will further trigger a compaction
-  // and generate another file.
-  ASSERT_OK(Flush(1));
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(3, /* Totally 3 files created up to now */
-            TestGetTickerCount(options, BLOCK_CACHE_ADD));
-
-  // After disabling options.paranoid_file_checks. NO further block
-  // is added after generating a new file.
-  ASSERT_OK(
-      dbfull()->SetOptions(handles_[1], {{"paranoid_file_checks", "false"}}));
-
-  ASSERT_OK(Put(1, "1_key3", "val3"));
-  ASSERT_OK(Put(1, "9_key3", "val3"));
-  ASSERT_OK(Flush(1));
-  ASSERT_OK(Put(1, "1_key4", "val4"));
-  ASSERT_OK(Put(1, "9_key4", "val4"));
-  ASSERT_OK(Flush(1));
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_EQ(3, /* Totally 3 files created up to now */
-            TestGetTickerCount(options, BLOCK_CACHE_ADD));
-}
-
-TEST_F(DBBlockCacheTest, CompressedCache) {
-  if (!Snappy_Supported()) {
-    return;
-  }
-  int num_iter = 80;
-
-  // Run this test three iterations.
-  // Iteration 1: only a uncompressed block cache
-  // Iteration 2: only a compressed block cache
-  // Iteration 3: both block cache and compressed cache
-  // Iteration 4: both block cache and compressed cache, but DB is not
-  // compressed
-  for (int iter = 0; iter < 4; iter++) {
-    Options options = CurrentOptions();
-    options.write_buffer_size = 64 * 1024;  // small write buffer
-    options.statistics = rocksdb::CreateDBStatistics();
-
-    BlockBasedTableOptions table_options;
-    switch (iter) {
-      case 0:
-        // only uncompressed block cache
-        table_options.block_cache = NewLRUCache(8 * 1024);
-        table_options.block_cache_compressed = nullptr;
-        options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-        break;
-      case 1:
-        // no block cache, only compressed cache
-        table_options.no_block_cache = true;
-        table_options.block_cache = nullptr;
-        table_options.block_cache_compressed = NewLRUCache(8 * 1024);
-        options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-        break;
-      case 2:
-        // both compressed and uncompressed block cache
-        table_options.block_cache = NewLRUCache(1024);
-        table_options.block_cache_compressed = NewLRUCache(8 * 1024);
-        options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-        break;
-      case 3:
-        // both block cache and compressed cache, but DB is not compressed
-        // also, make block cache sizes bigger, to trigger block cache hits
-        table_options.block_cache = NewLRUCache(1024 * 1024);
-        table_options.block_cache_compressed = NewLRUCache(8 * 1024 * 1024);
-        options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-        options.compression = kNoCompression;
-        break;
-      default:
-        ASSERT_TRUE(false);
-    }
-    CreateAndReopenWithCF({"pikachu"}, options);
-    // default column family doesn't have block cache
-    Options no_block_cache_opts;
-    no_block_cache_opts.statistics = options.statistics;
-    no_block_cache_opts = CurrentOptions(no_block_cache_opts);
-    BlockBasedTableOptions table_options_no_bc;
-    table_options_no_bc.no_block_cache = true;
-    no_block_cache_opts.table_factory.reset(
-        NewBlockBasedTableFactory(table_options_no_bc));
-    ReopenWithColumnFamilies(
-        {"default", "pikachu"},
-        std::vector<Options>({no_block_cache_opts, options}));
-
-    Random rnd(301);
-
-    // Write 8MB (80 values, each 100K)
-    ASSERT_EQ(NumTableFilesAtLevel(0, 1), 0);
-    std::vector<std::string> values;
-    std::string str;
-    for (int i = 0; i < num_iter; i++) {
-      if (i % 4 == 0) {  // high compression ratio
-        str = RandomString(&rnd, 1000);
-      }
-      values.push_back(str);
-      ASSERT_OK(Put(1, Key(i), values[i]));
-    }
-
-    // flush all data from memtable so that reads are from block cache
-    ASSERT_OK(Flush(1));
-
-    for (int i = 0; i < num_iter; i++) {
-      ASSERT_EQ(Get(1, Key(i)), values[i]);
-    }
-
-    // check that we triggered the appropriate code paths in the cache
-    switch (iter) {
-      case 0:
-        // only uncompressed block cache
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_MISS), 0);
-        ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS), 0);
-        break;
-      case 1:
-        // no block cache, only compressed cache
-        ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_MISS), 0);
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS), 0);
-        break;
-      case 2:
-        // both compressed and uncompressed block cache
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_MISS), 0);
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS), 0);
-        break;
-      case 3:
-        // both compressed and uncompressed block cache
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_MISS), 0);
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_HIT), 0);
-        ASSERT_GT(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_MISS), 0);
-        // compressed doesn't have any hits since blocks are not compressed on
-        // storage
-        ASSERT_EQ(TestGetTickerCount(options, BLOCK_CACHE_COMPRESSED_HIT), 0);
-        break;
-      default:
-        ASSERT_TRUE(false);
-    }
-
-    options.create_if_missing = true;
-    DestroyAndReopen(options);
-  }
-}
-
-#endif  // ROCKSDB_LITE
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_compaction_filter_test.cc

@@ -1,721 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-
-namespace rocksdb {
-
-static int cfilter_count = 0;
-
-// This is a static filter used for filtering
-// kvs during the compaction process.
-static std::string NEW_VALUE = "NewValue";
-
-class DBTestCompactionFilter : public DBTestBase {
- public:
-  DBTestCompactionFilter() : DBTestBase("/db_compaction_filter_test") {}
-};
-
-class KeepFilter : public CompactionFilter {
- public:
-  virtual bool Filter(int level, const Slice& key, const Slice& value,
-                      std::string* new_value, bool* value_changed) const
-      override {
-    cfilter_count++;
-    return false;
-  }
-
-  virtual const char* Name() const override { return "KeepFilter"; }
-};
-
-class DeleteFilter : public CompactionFilter {
- public:
-  virtual bool Filter(int level, const Slice& key, const Slice& value,
-                      std::string* new_value, bool* value_changed) const
-      override {
-    cfilter_count++;
-    return true;
-  }
-
-  virtual const char* Name() const override { return "DeleteFilter"; }
-};
-
-class DeleteISFilter : public CompactionFilter {
- public:
-  virtual bool Filter(int level, const Slice& key, const Slice& value,
-                      std::string* new_value,
-                      bool* value_changed) const override {
-    cfilter_count++;
-    int i = std::stoi(key.ToString());
-    if (i > 5 && i <= 105) {
-      return true;
-    }
-    return false;
-  }
-
-  virtual bool IgnoreSnapshots() const override { return true; }
-
-  virtual const char* Name() const override { return "DeleteFilter"; }
-};
-
-class DelayFilter : public CompactionFilter {
- public:
-  explicit DelayFilter(DBTestBase* d) : db_test(d) {}
-  virtual bool Filter(int level, const Slice& key, const Slice& value,
-                      std::string* new_value,
-                      bool* value_changed) const override {
-    db_test->env_->addon_time_.fetch_add(1000);
-    return true;
-  }
-
-  virtual const char* Name() const override { return "DelayFilter"; }
-
- private:
-  DBTestBase* db_test;
-};
-
-class ConditionalFilter : public CompactionFilter {
- public:
-  explicit ConditionalFilter(const std::string* filtered_value)
-      : filtered_value_(filtered_value) {}
-  virtual bool Filter(int level, const Slice& key, const Slice& value,
-                      std::string* new_value,
-                      bool* value_changed) const override {
-    return value.ToString() == *filtered_value_;
-  }
-
-  virtual const char* Name() const override { return "ConditionalFilter"; }
-
- private:
-  const std::string* filtered_value_;
-};
-
-class ChangeFilter : public CompactionFilter {
- public:
-  explicit ChangeFilter() {}
-
-  virtual bool Filter(int level, const Slice& key, const Slice& value,
-                      std::string* new_value, bool* value_changed) const
-      override {
-    assert(new_value != nullptr);
-    *new_value = NEW_VALUE;
-    *value_changed = true;
-    return false;
-  }
-
-  virtual const char* Name() const override { return "ChangeFilter"; }
-};
-
-class KeepFilterFactory : public CompactionFilterFactory {
- public:
-  explicit KeepFilterFactory(bool check_context = false,
-                             bool check_context_cf_id = false)
-      : check_context_(check_context),
-        check_context_cf_id_(check_context_cf_id),
-        compaction_filter_created_(false) {}
-
-  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
-      const CompactionFilter::Context& context) override {
-    if (check_context_) {
-      EXPECT_EQ(expect_full_compaction_.load(), context.is_full_compaction);
-      EXPECT_EQ(expect_manual_compaction_.load(), context.is_manual_compaction);
-    }
-    if (check_context_cf_id_) {
-      EXPECT_EQ(expect_cf_id_.load(), context.column_family_id);
-    }
-    compaction_filter_created_ = true;
-    return std::unique_ptr<CompactionFilter>(new KeepFilter());
-  }
-
-  bool compaction_filter_created() const { return compaction_filter_created_; }
-
-  virtual const char* Name() const override { return "KeepFilterFactory"; }
-  bool check_context_;
-  bool check_context_cf_id_;
-  std::atomic_bool expect_full_compaction_;
-  std::atomic_bool expect_manual_compaction_;
-  std::atomic<uint32_t> expect_cf_id_;
-  bool compaction_filter_created_;
-};
-
-class DeleteFilterFactory : public CompactionFilterFactory {
- public:
-  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
-      const CompactionFilter::Context& context) override {
-    if (context.is_manual_compaction) {
-      return std::unique_ptr<CompactionFilter>(new DeleteFilter());
-    } else {
-      return std::unique_ptr<CompactionFilter>(nullptr);
-    }
-  }
-
-  virtual const char* Name() const override { return "DeleteFilterFactory"; }
-};
-
-// Delete Filter Factory which ignores snapshots
-class DeleteISFilterFactory : public CompactionFilterFactory {
- public:
-  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
-      const CompactionFilter::Context& context) override {
-    if (context.is_manual_compaction) {
-      return std::unique_ptr<CompactionFilter>(new DeleteISFilter());
-    } else {
-      return std::unique_ptr<CompactionFilter>(nullptr);
-    }
-  }
-
-  virtual const char* Name() const override { return "DeleteFilterFactory"; }
-};
-
-class DelayFilterFactory : public CompactionFilterFactory {
- public:
-  explicit DelayFilterFactory(DBTestBase* d) : db_test(d) {}
-  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
-      const CompactionFilter::Context& context) override {
-    return std::unique_ptr<CompactionFilter>(new DelayFilter(db_test));
-  }
-
-  virtual const char* Name() const override { return "DelayFilterFactory"; }
-
- private:
-  DBTestBase* db_test;
-};
-
-class ConditionalFilterFactory : public CompactionFilterFactory {
- public:
-  explicit ConditionalFilterFactory(const Slice& filtered_value)
-      : filtered_value_(filtered_value.ToString()) {}
-
-  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
-      const CompactionFilter::Context& context) override {
-    return std::unique_ptr<CompactionFilter>(
-        new ConditionalFilter(&filtered_value_));
-  }
-
-  virtual const char* Name() const override {
-    return "ConditionalFilterFactory";
-  }
-
- private:
-  std::string filtered_value_;
-};
-
-class ChangeFilterFactory : public CompactionFilterFactory {
- public:
-  explicit ChangeFilterFactory() {}
-
-  virtual std::unique_ptr<CompactionFilter> CreateCompactionFilter(
-      const CompactionFilter::Context& context) override {
-    return std::unique_ptr<CompactionFilter>(new ChangeFilter());
-  }
-
-  virtual const char* Name() const override { return "ChangeFilterFactory"; }
-};
-
-#ifndef ROCKSDB_LITE
-TEST_F(DBTestCompactionFilter, CompactionFilter) {
-  Options options = CurrentOptions();
-  options.max_open_files = -1;
-  options.num_levels = 3;
-  options.compaction_filter_factory = std::make_shared<KeepFilterFactory>();
-  options = CurrentOptions(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  // Write 100K keys, these are written to a few files in L0.
-  const std::string value(10, 'x');
-  for (int i = 0; i < 100000; i++) {
-    char key[100];
-    snprintf(key, sizeof(key), "B%010d", i);
-    Put(1, key, value);
-  }
-  ASSERT_OK(Flush(1));
-
-  // Push all files to the highest level L2. Verify that
-  // the compaction is each level invokes the filter for
-  // all the keys in that level.
-  cfilter_count = 0;
-  dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
-  ASSERT_EQ(cfilter_count, 100000);
-  cfilter_count = 0;
-  dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
-  ASSERT_EQ(cfilter_count, 100000);
-
-  ASSERT_EQ(NumTableFilesAtLevel(0, 1), 0);
-  ASSERT_EQ(NumTableFilesAtLevel(1, 1), 0);
-  ASSERT_NE(NumTableFilesAtLevel(2, 1), 0);
-  cfilter_count = 0;
-
-  // All the files are in the lowest level.
-  // Verify that all but the 100001st record
-  // has sequence number zero. The 100001st record
-  // is at the tip of this snapshot and cannot
-  // be zeroed out.
-  int count = 0;
-  int total = 0;
-  Arena arena;
-  {
-    ScopedArenaIterator iter(
-        dbfull()->NewInternalIterator(&arena, handles_[1]));
-    iter->SeekToFirst();
-    ASSERT_OK(iter->status());
-    while (iter->Valid()) {
-      ParsedInternalKey ikey(Slice(), 0, kTypeValue);
-      ikey.sequence = -1;
-      ASSERT_EQ(ParseInternalKey(iter->key(), &ikey), true);
-      total++;
-      if (ikey.sequence != 0) {
-        count++;
-      }
-      iter->Next();
-    }
-  }
-  ASSERT_EQ(total, 100000);
-  ASSERT_EQ(count, 1);
-
-  // overwrite all the 100K keys once again.
-  for (int i = 0; i < 100000; i++) {
-    char key[100];
-    snprintf(key, sizeof(key), "B%010d", i);
-    ASSERT_OK(Put(1, key, value));
-  }
-  ASSERT_OK(Flush(1));
-
-  // push all files to the highest level L2. This
-  // means that all keys should pass at least once
-  // via the compaction filter
-  cfilter_count = 0;
-  dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
-  ASSERT_EQ(cfilter_count, 100000);
-  cfilter_count = 0;
-  dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
-  ASSERT_EQ(cfilter_count, 100000);
-  ASSERT_EQ(NumTableFilesAtLevel(0, 1), 0);
-  ASSERT_EQ(NumTableFilesAtLevel(1, 1), 0);
-  ASSERT_NE(NumTableFilesAtLevel(2, 1), 0);
-
-  // create a new database with the compaction
-  // filter in such a way that it deletes all keys
-  options.compaction_filter_factory = std::make_shared<DeleteFilterFactory>();
-  options.create_if_missing = true;
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  // write all the keys once again.
-  for (int i = 0; i < 100000; i++) {
-    char key[100];
-    snprintf(key, sizeof(key), "B%010d", i);
-    ASSERT_OK(Put(1, key, value));
-  }
-  ASSERT_OK(Flush(1));
-  ASSERT_NE(NumTableFilesAtLevel(0, 1), 0);
-  ASSERT_EQ(NumTableFilesAtLevel(1, 1), 0);
-  ASSERT_EQ(NumTableFilesAtLevel(2, 1), 0);
-
-  // Push all files to the highest level L2. This
-  // triggers the compaction filter to delete all keys,
-  // verify that at the end of the compaction process,
-  // nothing is left.
-  cfilter_count = 0;
-  dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
-  ASSERT_EQ(cfilter_count, 100000);
-  cfilter_count = 0;
-  dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
-  ASSERT_EQ(cfilter_count, 0);
-  ASSERT_EQ(NumTableFilesAtLevel(0, 1), 0);
-  ASSERT_EQ(NumTableFilesAtLevel(1, 1), 0);
-
-  {
-    // Scan the entire database to ensure that nothing is left
-    std::unique_ptr<Iterator> iter(
-        db_->NewIterator(ReadOptions(), handles_[1]));
-    iter->SeekToFirst();
-    count = 0;
-    while (iter->Valid()) {
-      count++;
-      iter->Next();
-    }
-    ASSERT_EQ(count, 0);
-  }
-
-  // The sequence number of the remaining record
-  // is not zeroed out even though it is at the
-  // level Lmax because this record is at the tip
-  count = 0;
-  {
-    ScopedArenaIterator iter(
-        dbfull()->NewInternalIterator(&arena, handles_[1]));
-    iter->SeekToFirst();
-    ASSERT_OK(iter->status());
-    while (iter->Valid()) {
-      ParsedInternalKey ikey(Slice(), 0, kTypeValue);
-      ASSERT_EQ(ParseInternalKey(iter->key(), &ikey), true);
-      ASSERT_NE(ikey.sequence, (unsigned)0);
-      count++;
-      iter->Next();
-    }
-    ASSERT_EQ(count, 0);
-  }
-}
-
-// Tests the edge case where compaction does not produce any output -- all
-// entries are deleted. The compaction should create bunch of 'DeleteFile'
-// entries in VersionEdit, but none of the 'AddFile's.
-TEST_F(DBTestCompactionFilter, CompactionFilterDeletesAll) {
-  Options options = CurrentOptions();
-  options.compaction_filter_factory = std::make_shared<DeleteFilterFactory>();
-  options.disable_auto_compactions = true;
-  options.create_if_missing = true;
-  DestroyAndReopen(options);
-
-  // put some data
-  for (int table = 0; table < 4; ++table) {
-    for (int i = 0; i < 10 + table; ++i) {
-      Put(ToString(table * 100 + i), "val");
-    }
-    Flush();
-  }
-
-  // this will produce empty file (delete compaction filter)
-  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  ASSERT_EQ(0U, CountLiveFiles());
-
-  Reopen(options);
-
-  Iterator* itr = db_->NewIterator(ReadOptions());
-  itr->SeekToFirst();
-  // empty db
-  ASSERT_TRUE(!itr->Valid());
-
-  delete itr;
-}
-#endif  // ROCKSDB_LITE
-
-TEST_F(DBTestCompactionFilter, CompactionFilterWithValueChange) {
-  do {
-    Options options = CurrentOptions();
-    options.num_levels = 3;
-    options.compaction_filter_factory =
-      std::make_shared<ChangeFilterFactory>();
-    CreateAndReopenWithCF({"pikachu"}, options);
-
-    // Write 100K+1 keys, these are written to a few files
-    // in L0. We do this so that the current snapshot points
-    // to the 100001 key.The compaction filter is  not invoked
-    // on keys that are visible via a snapshot because we
-    // anyways cannot delete it.
-    const std::string value(10, 'x');
-    for (int i = 0; i < 100001; i++) {
-      char key[100];
-      snprintf(key, sizeof(key), "B%010d", i);
-      Put(1, key, value);
-    }
-
-    // push all files to  lower levels
-    ASSERT_OK(Flush(1));
-    if (option_config_ != kUniversalCompactionMultiLevel &&
-        option_config_ != kUniversalSubcompactions) {
-      dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
-      dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
-    } else {
-      dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                             nullptr);
-    }
-
-    // re-write all data again
-    for (int i = 0; i < 100001; i++) {
-      char key[100];
-      snprintf(key, sizeof(key), "B%010d", i);
-      Put(1, key, value);
-    }
-
-    // push all files to  lower levels. This should
-    // invoke the compaction filter for all 100000 keys.
-    ASSERT_OK(Flush(1));
-    if (option_config_ != kUniversalCompactionMultiLevel &&
-        option_config_ != kUniversalSubcompactions) {
-      dbfull()->TEST_CompactRange(0, nullptr, nullptr, handles_[1]);
-      dbfull()->TEST_CompactRange(1, nullptr, nullptr, handles_[1]);
-    } else {
-      dbfull()->CompactRange(CompactRangeOptions(), handles_[1], nullptr,
-                             nullptr);
-    }
-
-    // verify that all keys now have the new value that
-    // was set by the compaction process.
-    for (int i = 0; i < 100001; i++) {
-      char key[100];
-      snprintf(key, sizeof(key), "B%010d", i);
-      std::string newvalue = Get(1, key);
-      ASSERT_EQ(newvalue.compare(NEW_VALUE), 0);
-    }
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBTestCompactionFilter, CompactionFilterWithMergeOperator) {
-  std::string one, two, three, four;
-  PutFixed64(&one, 1);
-  PutFixed64(&two, 2);
-  PutFixed64(&three, 3);
-  PutFixed64(&four, 4);
-
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.merge_operator = MergeOperators::CreateUInt64AddOperator();
-  options.num_levels = 3;
-  // Filter out keys with value is 2.
-  options.compaction_filter_factory =
-      std::make_shared<ConditionalFilterFactory>(two);
-  DestroyAndReopen(options);
-
-  // In the same compaction, a value type needs to be deleted based on
-  // compaction filter, and there is a merge type for the key. compaction
-  // filter result is ignored.
-  ASSERT_OK(db_->Put(WriteOptions(), "foo", two));
-  ASSERT_OK(Flush());
-  ASSERT_OK(db_->Merge(WriteOptions(), "foo", one));
-  ASSERT_OK(Flush());
-  std::string newvalue = Get("foo");
-  ASSERT_EQ(newvalue, three);
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  newvalue = Get("foo");
-  ASSERT_EQ(newvalue, three);
-
-  // value key can be deleted based on compaction filter, leaving only
-  // merge keys.
-  ASSERT_OK(db_->Put(WriteOptions(), "bar", two));
-  ASSERT_OK(Flush());
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  newvalue = Get("bar");
-  ASSERT_EQ("NOT_FOUND", newvalue);
-  ASSERT_OK(db_->Merge(WriteOptions(), "bar", two));
-  ASSERT_OK(Flush());
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  newvalue = Get("bar");
-  ASSERT_EQ(two, two);
-
-  // Compaction filter never applies to merge keys.
-  ASSERT_OK(db_->Put(WriteOptions(), "foobar", one));
-  ASSERT_OK(Flush());
-  ASSERT_OK(db_->Merge(WriteOptions(), "foobar", two));
-  ASSERT_OK(Flush());
-  newvalue = Get("foobar");
-  ASSERT_EQ(newvalue, three);
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  newvalue = Get("foobar");
-  ASSERT_EQ(newvalue, three);
-
-  // In the same compaction, both of value type and merge type keys need to be
-  // deleted based on compaction filter, and there is a merge type for the key.
-  // For both keys, compaction filter results are ignored.
-  ASSERT_OK(db_->Put(WriteOptions(), "barfoo", two));
-  ASSERT_OK(Flush());
-  ASSERT_OK(db_->Merge(WriteOptions(), "barfoo", two));
-  ASSERT_OK(Flush());
-  newvalue = Get("barfoo");
-  ASSERT_EQ(newvalue, four);
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  newvalue = Get("barfoo");
-  ASSERT_EQ(newvalue, four);
-}
-
-#ifndef ROCKSDB_LITE
-TEST_F(DBTestCompactionFilter, CompactionFilterContextManual) {
-  KeepFilterFactory* filter = new KeepFilterFactory(true, true);
-
-  Options options = CurrentOptions();
-  options.compaction_style = kCompactionStyleUniversal;
-  options.compaction_filter_factory.reset(filter);
-  options.compression = kNoCompression;
-  options.level0_file_num_compaction_trigger = 8;
-  Reopen(options);
-  int num_keys_per_file = 400;
-  for (int j = 0; j < 3; j++) {
-    // Write several keys.
-    const std::string value(10, 'x');
-    for (int i = 0; i < num_keys_per_file; i++) {
-      char key[100];
-      snprintf(key, sizeof(key), "B%08d%02d", i, j);
-      Put(key, value);
-    }
-    dbfull()->TEST_FlushMemTable();
-    // Make sure next file is much smaller so automatic compaction will not
-    // be triggered.
-    num_keys_per_file /= 2;
-  }
-  dbfull()->TEST_WaitForCompact();
-
-  // Force a manual compaction
-  cfilter_count = 0;
-  filter->expect_manual_compaction_.store(true);
-  filter->expect_full_compaction_.store(true);
-  filter->expect_cf_id_.store(0);
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  ASSERT_EQ(cfilter_count, 700);
-  ASSERT_EQ(NumSortedRuns(0), 1);
-  ASSERT_TRUE(filter->compaction_filter_created());
-
-  // Verify total number of keys is correct after manual compaction.
-  {
-    int count = 0;
-    int total = 0;
-    Arena arena;
-    ScopedArenaIterator iter(dbfull()->NewInternalIterator(&arena));
-    iter->SeekToFirst();
-    ASSERT_OK(iter->status());
-    while (iter->Valid()) {
-      ParsedInternalKey ikey(Slice(), 0, kTypeValue);
-      ikey.sequence = -1;
-      ASSERT_EQ(ParseInternalKey(iter->key(), &ikey), true);
-      total++;
-      if (ikey.sequence != 0) {
-        count++;
-      }
-      iter->Next();
-    }
-    ASSERT_EQ(total, 700);
-    ASSERT_EQ(count, 2);
-  }
-}
-#endif  // ROCKSDB_LITE
-
-TEST_F(DBTestCompactionFilter, CompactionFilterContextCfId) {
-  KeepFilterFactory* filter = new KeepFilterFactory(false, true);
-  filter->expect_cf_id_.store(1);
-
-  Options options = CurrentOptions();
-  options.compaction_filter_factory.reset(filter);
-  options.compression = kNoCompression;
-  options.level0_file_num_compaction_trigger = 2;
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  int num_keys_per_file = 400;
-  for (int j = 0; j < 3; j++) {
-    // Write several keys.
-    const std::string value(10, 'x');
-    for (int i = 0; i < num_keys_per_file; i++) {
-      char key[100];
-      snprintf(key, sizeof(key), "B%08d%02d", i, j);
-      Put(1, key, value);
-    }
-    Flush(1);
-    // Make sure next file is much smaller so automatic compaction will not
-    // be triggered.
-    num_keys_per_file /= 2;
-  }
-  dbfull()->TEST_WaitForCompact();
-
-  ASSERT_TRUE(filter->compaction_filter_created());
-}
-
-#ifndef ROCKSDB_LITE
-// Compaction filters should only be applied to records that are newer than the
-// latest snapshot. This test inserts records and applies a delete filter.
-TEST_F(DBTestCompactionFilter, CompactionFilterSnapshot) {
-  Options options = CurrentOptions();
-  options.compaction_filter_factory = std::make_shared<DeleteFilterFactory>();
-  options.disable_auto_compactions = true;
-  options.create_if_missing = true;
-  DestroyAndReopen(options);
-
-  // Put some data.
-  const Snapshot* snapshot = nullptr;
-  for (int table = 0; table < 4; ++table) {
-    for (int i = 0; i < 10; ++i) {
-      Put(ToString(table * 100 + i), "val");
-    }
-    Flush();
-
-    if (table == 0) {
-      snapshot = db_->GetSnapshot();
-    }
-  }
-  assert(snapshot != nullptr);
-
-  cfilter_count = 0;
-  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  // The filter should delete 10 records.
-  ASSERT_EQ(30U, cfilter_count);
-
-  // Release the snapshot and compact again -> now all records should be
-  // removed.
-  db_->ReleaseSnapshot(snapshot);
-  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  ASSERT_EQ(0U, CountLiveFiles());
-}
-
-// Compaction filters should only be applied to records that are newer than the
-// latest snapshot. However, if the compaction filter asks to ignore snapshots
-// records newer than the snapshot will also be processed
-TEST_F(DBTestCompactionFilter, CompactionFilterIgnoreSnapshot) {
-  std::string five = ToString(5);
-  Options options = CurrentOptions();
-  options.compaction_filter_factory = std::make_shared<DeleteISFilterFactory>();
-  options.disable_auto_compactions = true;
-  options.create_if_missing = true;
-  DestroyAndReopen(options);
-
-  // Put some data.
-  const Snapshot* snapshot = nullptr;
-  for (int table = 0; table < 4; ++table) {
-    for (int i = 0; i < 10; ++i) {
-      Put(ToString(table * 100 + i), "val");
-    }
-    Flush();
-
-    if (table == 0) {
-      snapshot = db_->GetSnapshot();
-    }
-  }
-  assert(snapshot != nullptr);
-
-  cfilter_count = 0;
-  ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-  // The filter should delete 40 records.
-  ASSERT_EQ(40U, cfilter_count);
-
-  {
-    // Scan the entire database as of the snapshot to ensure
-    // that nothing is left
-    ReadOptions read_options;
-    read_options.snapshot = snapshot;
-    std::unique_ptr<Iterator> iter(db_->NewIterator(read_options));
-    iter->SeekToFirst();
-    int count = 0;
-    while (iter->Valid()) {
-      count++;
-      iter->Next();
-    }
-    ASSERT_EQ(count, 6);
-    read_options.snapshot = 0;
-    std::unique_ptr<Iterator> iter1(db_->NewIterator(read_options));
-    iter1->SeekToFirst();
-    count = 0;
-    while (iter1->Valid()) {
-      count++;
-      iter1->Next();
-    }
-    // We have deleted 10 keys from 40 using the compaction filter
-    //  Keys 6-9 before the snapshot and 100-105 after the snapshot
-    ASSERT_EQ(count, 30);
-  }
-
-  // Release the snapshot and compact again -> now all records should be
-  // removed.
-  db_->ReleaseSnapshot(snapshot);
-}
-#endif  // ROCKSDB_LITE
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_dynamic_level_test.cc

@@ -1,507 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-// Introduction of SyncPoint effectively disabled building and running this test
-// in Release build.
-// which is a pity, it is a good test
-#if !defined(ROCKSDB_LITE)
-
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-
-namespace rocksdb {
-class DBTestDynamicLevel : public DBTestBase {
- public:
-  DBTestDynamicLevel() : DBTestBase("/db_dynamic_level_test") {}
-};
-
-TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase) {
-  if (!Snappy_Supported() || !LZ4_Supported()) {
-    return;
-  }
-  // Use InMemoryEnv, or it would be too slow.
-  unique_ptr<Env> env(new MockEnv(env_));
-
-  const int kNKeys = 1000;
-  int keys[kNKeys];
-
-  auto verify_func = [&]() {
-    for (int i = 0; i < kNKeys; i++) {
-      ASSERT_NE("NOT_FOUND", Get(Key(i)));
-      ASSERT_NE("NOT_FOUND", Get(Key(kNKeys * 2 + i)));
-      if (i < kNKeys / 10) {
-        ASSERT_EQ("NOT_FOUND", Get(Key(kNKeys + keys[i])));
-      } else {
-        ASSERT_NE("NOT_FOUND", Get(Key(kNKeys + keys[i])));
-      }
-    }
-  };
-
-  Random rnd(301);
-  for (int ordered_insert = 0; ordered_insert <= 1; ordered_insert++) {
-    for (int i = 0; i < kNKeys; i++) {
-      keys[i] = i;
-    }
-    if (ordered_insert == 0) {
-      std::random_shuffle(std::begin(keys), std::end(keys));
-    }
-    for (int max_background_compactions = 1; max_background_compactions < 4;
-         max_background_compactions += 2) {
-      Options options;
-      options.env = env.get();
-      options.create_if_missing = true;
-      options.db_write_buffer_size = 2048;
-      options.write_buffer_size = 2048;
-      options.max_write_buffer_number = 2;
-      options.level0_file_num_compaction_trigger = 2;
-      options.level0_slowdown_writes_trigger = 2;
-      options.level0_stop_writes_trigger = 2;
-      options.target_file_size_base = 2048;
-      options.level_compaction_dynamic_level_bytes = true;
-      options.max_bytes_for_level_base = 10240;
-      options.max_bytes_for_level_multiplier = 4;
-      options.soft_rate_limit = 1.1;
-      options.max_background_compactions = max_background_compactions;
-      options.num_levels = 5;
-
-      options.compression_per_level.resize(3);
-      options.compression_per_level[0] = kNoCompression;
-      options.compression_per_level[1] = kLZ4Compression;
-      options.compression_per_level[2] = kSnappyCompression;
-
-      DestroyAndReopen(options);
-
-      for (int i = 0; i < kNKeys; i++) {
-        int key = keys[i];
-        ASSERT_OK(Put(Key(kNKeys + key), RandomString(&rnd, 102)));
-        ASSERT_OK(Put(Key(key), RandomString(&rnd, 102)));
-        ASSERT_OK(Put(Key(kNKeys * 2 + key), RandomString(&rnd, 102)));
-        ASSERT_OK(Delete(Key(kNKeys + keys[i / 10])));
-        env_->SleepForMicroseconds(5000);
-      }
-
-      uint64_t int_prop;
-      ASSERT_TRUE(db_->GetIntProperty("rocksdb.background-errors", &int_prop));
-      ASSERT_EQ(0U, int_prop);
-
-      // Verify DB
-      for (int j = 0; j < 2; j++) {
-        verify_func();
-        if (j == 0) {
-          Reopen(options);
-        }
-      }
-
-      // Test compact range works
-      dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-      // All data should be in the last level.
-      ColumnFamilyMetaData cf_meta;
-      db_->GetColumnFamilyMetaData(&cf_meta);
-      ASSERT_EQ(5U, cf_meta.levels.size());
-      for (int i = 0; i < 4; i++) {
-        ASSERT_EQ(0U, cf_meta.levels[i].files.size());
-      }
-      ASSERT_GT(cf_meta.levels[4U].files.size(), 0U);
-      verify_func();
-
-      Close();
-    }
-  }
-
-  env_->SetBackgroundThreads(1, Env::LOW);
-  env_->SetBackgroundThreads(1, Env::HIGH);
-}
-
-// Test specific cases in dynamic max bytes
-TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBase2) {
-  Random rnd(301);
-  int kMaxKey = 1000000;
-
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.db_write_buffer_size = 204800;
-  options.write_buffer_size = 20480;
-  options.max_write_buffer_number = 2;
-  options.level0_file_num_compaction_trigger = 2;
-  options.level0_slowdown_writes_trigger = 9999;
-  options.level0_stop_writes_trigger = 9999;
-  options.target_file_size_base = 9102;
-  options.level_compaction_dynamic_level_bytes = true;
-  options.max_bytes_for_level_base = 40960;
-  options.max_bytes_for_level_multiplier = 4;
-  options.max_background_compactions = 2;
-  options.num_levels = 5;
-  options.expanded_compaction_factor = 0;  // Force not expanding in compactions
-  BlockBasedTableOptions table_options;
-  table_options.block_size = 1024;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-
-  DestroyAndReopen(options);
-  ASSERT_OK(dbfull()->SetOptions({
-      {"disable_auto_compactions", "true"},
-  }));
-
-  uint64_t int_prop;
-  std::string str_prop;
-
-  // Initial base level is the last level
-  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
-  ASSERT_EQ(4U, int_prop);
-
-  // Put about 28K to L0
-  for (int i = 0; i < 70; i++) {
-    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 380)));
-  }
-  ASSERT_OK(dbfull()->SetOptions({
-      {"disable_auto_compactions", "false"},
-  }));
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
-  ASSERT_EQ(4U, int_prop);
-
-  // Insert extra about 28K to L0. After they are compacted to L4, base level
-  // should be changed to L3.
-  ASSERT_OK(dbfull()->SetOptions({
-      {"disable_auto_compactions", "true"},
-  }));
-  for (int i = 0; i < 70; i++) {
-    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 380)));
-  }
-
-  ASSERT_OK(dbfull()->SetOptions({
-      {"disable_auto_compactions", "false"},
-  }));
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
-  ASSERT_EQ(3U, int_prop);
-  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level1", &str_prop));
-  ASSERT_EQ("0", str_prop);
-  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level2", &str_prop));
-  ASSERT_EQ("0", str_prop);
-
-  // Trigger parallel compaction, and the first one would change the base
-  // level.
-  // Hold compaction jobs to make sure
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionJob::Run():Start",
-      [&](void* arg) { env_->SleepForMicroseconds(100000); });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-  ASSERT_OK(dbfull()->SetOptions({
-      {"disable_auto_compactions", "true"},
-  }));
-  // Write about 40K more
-  for (int i = 0; i < 100; i++) {
-    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 380)));
-  }
-  ASSERT_OK(dbfull()->SetOptions({
-      {"disable_auto_compactions", "false"},
-  }));
-  Flush();
-  // Wait for 200 milliseconds before proceeding compactions to make sure two
-  // parallel ones are executed.
-  env_->SleepForMicroseconds(200000);
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
-  ASSERT_EQ(3U, int_prop);
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-
-  // Trigger a condition that the compaction changes base level and L0->Lbase
-  // happens at the same time.
-  // We try to make last levels' targets to be 40K, 160K, 640K, add triggers
-  // another compaction from 40K->160K.
-  ASSERT_OK(dbfull()->SetOptions({
-      {"disable_auto_compactions", "true"},
-  }));
-  // Write about 600K more
-  for (int i = 0; i < 1500; i++) {
-    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 380)));
-  }
-  ASSERT_OK(dbfull()->SetOptions({
-      {"disable_auto_compactions", "false"},
-  }));
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
-  ASSERT_EQ(2U, int_prop);
-
-  // A manual compaction will trigger the base level to become L2
-  // Keep Writing data until base level changed 2->1. There will be L0->L2
-  // compaction going on at the same time.
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
-
-  rocksdb::SyncPoint::GetInstance()->LoadDependency({
-      {"CompactionJob::Run():Start", "DynamicLevelMaxBytesBase2:0"},
-      {"DynamicLevelMaxBytesBase2:1", "CompactionJob::Run():End"},
-      {"DynamicLevelMaxBytesBase2:compact_range_finish",
-       "FlushJob::WriteLevel0Table"},
-  });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  std::thread thread([this] {
-    TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:compact_range_start");
-    ASSERT_OK(db_->CompactRange(CompactRangeOptions(), nullptr, nullptr));
-    TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:compact_range_finish");
-  });
-
-  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:0");
-  for (int i = 0; i < 2; i++) {
-    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 380)));
-  }
-  TEST_SYNC_POINT("DynamicLevelMaxBytesBase2:1");
-
-  Flush();
-
-  thread.join();
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
-
-  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
-  ASSERT_EQ(1U, int_prop);
-}
-
-// Test specific cases in dynamic max bytes
-TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesCompactRange) {
-  Random rnd(301);
-  int kMaxKey = 1000000;
-
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.db_write_buffer_size = 2048;
-  options.write_buffer_size = 2048;
-  options.max_write_buffer_number = 2;
-  options.level0_file_num_compaction_trigger = 2;
-  options.level0_slowdown_writes_trigger = 9999;
-  options.level0_stop_writes_trigger = 9999;
-  options.target_file_size_base = 2;
-  options.level_compaction_dynamic_level_bytes = true;
-  options.max_bytes_for_level_base = 10240;
-  options.max_bytes_for_level_multiplier = 4;
-  options.max_background_compactions = 1;
-  const int kNumLevels = 5;
-  options.num_levels = kNumLevels;
-  options.expanded_compaction_factor = 0;  // Force not expanding in compactions
-  BlockBasedTableOptions table_options;
-  table_options.block_size = 1024;
-  options.table_factory.reset(NewBlockBasedTableFactory(table_options));
-
-  DestroyAndReopen(options);
-
-  // Compact against empty DB
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-
-  uint64_t int_prop;
-  std::string str_prop;
-
-  // Initial base level is the last level
-  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
-  ASSERT_EQ(4U, int_prop);
-
-  // Put about 7K to L0
-  for (int i = 0; i < 140; i++) {
-    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 80)));
-  }
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  if (NumTableFilesAtLevel(0) == 0) {
-    // Make sure level 0 is not empty
-    ASSERT_OK(Put(Key(static_cast<int>(rnd.Uniform(kMaxKey))),
-                  RandomString(&rnd, 80)));
-    Flush();
-  }
-
-  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
-  ASSERT_EQ(3U, int_prop);
-  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level1", &str_prop));
-  ASSERT_EQ("0", str_prop);
-  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level2", &str_prop));
-  ASSERT_EQ("0", str_prop);
-
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-  rocksdb::SyncPoint::GetInstance()->ClearAllCallBacks();
-
-  std::set<int> output_levels;
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "CompactionPicker::CompactRange:Return", [&](void* arg) {
-        Compaction* compaction = reinterpret_cast<Compaction*>(arg);
-        output_levels.insert(compaction->output_level());
-      });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-  ASSERT_EQ(output_levels.size(), 2);
-  ASSERT_TRUE(output_levels.find(3) != output_levels.end());
-  ASSERT_TRUE(output_levels.find(4) != output_levels.end());
-  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level0", &str_prop));
-  ASSERT_EQ("0", str_prop);
-  ASSERT_TRUE(db_->GetProperty("rocksdb.num-files-at-level3", &str_prop));
-  ASSERT_EQ("0", str_prop);
-  // Base level is still level 3.
-  ASSERT_TRUE(db_->GetIntProperty("rocksdb.base-level", &int_prop));
-  ASSERT_EQ(3U, int_prop);
-}
-
-TEST_F(DBTestDynamicLevel, DynamicLevelMaxBytesBaseInc) {
-  Options options = CurrentOptions();
-  options.create_if_missing = true;
-  options.db_write_buffer_size = 2048;
-  options.write_buffer_size = 2048;
-  options.max_write_buffer_number = 2;
-  options.level0_file_num_compaction_trigger = 2;
-  options.level0_slowdown_writes_trigger = 2;
-  options.level0_stop_writes_trigger = 2;
-  options.target_file_size_base = 2048;
-  options.level_compaction_dynamic_level_bytes = true;
-  options.max_bytes_for_level_base = 10240;
-  options.max_bytes_for_level_multiplier = 4;
-  options.soft_rate_limit = 1.1;
-  options.max_background_compactions = 2;
-  options.num_levels = 5;
-
-  DestroyAndReopen(options);
-
-  int non_trivial = 0;
-  rocksdb::SyncPoint::GetInstance()->SetCallBack(
-      "DBImpl::BackgroundCompaction:NonTrivial",
-      [&](void* arg) { non_trivial++; });
-  rocksdb::SyncPoint::GetInstance()->EnableProcessing();
-
-  Random rnd(301);
-  const int total_keys = 3000;
-  const int random_part_size = 100;
-  for (int i = 0; i < total_keys; i++) {
-    std::string value = RandomString(&rnd, random_part_size);
-    PutFixed32(&value, static_cast<uint32_t>(i));
-    ASSERT_OK(Put(Key(i), value));
-  }
-  Flush();
-  dbfull()->TEST_WaitForCompact();
-  rocksdb::SyncPoint::GetInstance()->DisableProcessing();
-
-  ASSERT_EQ(non_trivial, 0);
-
-  for (int i = 0; i < total_keys; i++) {
-    std::string value = Get(Key(i));
-    ASSERT_EQ(DecodeFixed32(value.c_str() + random_part_size),
-              static_cast<uint32_t>(i));
-  }
-
-  env_->SetBackgroundThreads(1, Env::LOW);
-  env_->SetBackgroundThreads(1, Env::HIGH);
-}
-
-TEST_F(DBTestDynamicLevel, MigrateToDynamicLevelMaxBytesBase) {
-  Random rnd(301);
-  const int kMaxKey = 2000;
-
-  Options options;
-  options.create_if_missing = true;
-  options.db_write_buffer_size = 2048;
-  options.write_buffer_size = 2048;
-  options.max_write_buffer_number = 8;
-  options.level0_file_num_compaction_trigger = 4;
-  options.level0_slowdown_writes_trigger = 4;
-  options.level0_stop_writes_trigger = 8;
-  options.target_file_size_base = 2048;
-  options.level_compaction_dynamic_level_bytes = false;
-  options.max_bytes_for_level_base = 10240;
-  options.max_bytes_for_level_multiplier = 4;
-  options.soft_rate_limit = 1.1;
-  options.num_levels = 8;
-
-  DestroyAndReopen(options);
-
-  auto verify_func = [&](int num_keys, bool if_sleep) {
-    for (int i = 0; i < num_keys; i++) {
-      ASSERT_NE("NOT_FOUND", Get(Key(kMaxKey + i)));
-      if (i < num_keys / 10) {
-        ASSERT_EQ("NOT_FOUND", Get(Key(i)));
-      } else {
-        ASSERT_NE("NOT_FOUND", Get(Key(i)));
-      }
-      if (if_sleep && i % 1000 == 0) {
-        // Without it, valgrind may choose not to give another
-        // thread a chance to run before finishing the function,
-        // causing the test to be extremely slow.
-        env_->SleepForMicroseconds(1);
-      }
-    }
-  };
-
-  int total_keys = 1000;
-  for (int i = 0; i < total_keys; i++) {
-    ASSERT_OK(Put(Key(i), RandomString(&rnd, 102)));
-    ASSERT_OK(Put(Key(kMaxKey + i), RandomString(&rnd, 102)));
-    ASSERT_OK(Delete(Key(i / 10)));
-  }
-  verify_func(total_keys, false);
-  dbfull()->TEST_WaitForCompact();
-
-  options.level_compaction_dynamic_level_bytes = true;
-  options.disable_auto_compactions = true;
-  Reopen(options);
-  verify_func(total_keys, false);
-
-  std::atomic_bool compaction_finished;
-  compaction_finished = false;
-  // Issue manual compaction in one thread and still verify DB state
-  // in main thread.
-  std::thread t([&]() {
-    CompactRangeOptions compact_options;
-    compact_options.change_level = true;
-    compact_options.target_level = options.num_levels - 1;
-    dbfull()->CompactRange(compact_options, nullptr, nullptr);
-    compaction_finished.store(true);
-  });
-  do {
-    verify_func(total_keys, true);
-  } while (!compaction_finished.load());
-  t.join();
-
-  ASSERT_OK(dbfull()->SetOptions({
-      {"disable_auto_compactions", "false"},
-  }));
-
-  int total_keys2 = 2000;
-  for (int i = total_keys; i < total_keys2; i++) {
-    ASSERT_OK(Put(Key(i), RandomString(&rnd, 102)));
-    ASSERT_OK(Put(Key(kMaxKey + i), RandomString(&rnd, 102)));
-    ASSERT_OK(Delete(Key(i / 10)));
-  }
-
-  verify_func(total_keys2, false);
-  dbfull()->TEST_WaitForCompact();
-  verify_func(total_keys2, false);
-
-  // Base level is not level 1
-  ASSERT_EQ(NumTableFilesAtLevel(1), 0);
-  ASSERT_EQ(NumTableFilesAtLevel(2), 0);
-}
-}  // namespace rocksdb
-
-#endif  // !defined(ROCKSDB_LITE)
-
-int main(int argc, char** argv) {
-#if !defined(ROCKSDB_LITE)
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-#else
-  return 0;
-#endif
-}

db/db_filesnapshot.cc

@@ -1,4 +1,4 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
@@ -7,50 +7,37 @@
 // Use of this source code is governed by a BSD-style license that can be
 // found in the LICENSE file.
 
-#ifndef ROCKSDB_LITE
-
-#ifndef __STDC_FORMAT_MACROS
 #define __STDC_FORMAT_MACROS
-#endif
-
 #include <inttypes.h>
 #include <algorithm>
 #include <string>
 #include <stdint.h>
 #include "db/db_impl.h"
 #include "db/filename.h"
-#include "db/job_context.h"
 #include "db/version_set.h"
 #include "rocksdb/db.h"
 #include "rocksdb/env.h"
 #include "port/port.h"
 #include "util/mutexlock.h"
 #include "util/sync_point.h"
-#include "util/file_util.h"
 
 namespace rocksdb {
 
 Status DBImpl::DisableFileDeletions() {
-  InstrumentedMutexLock l(&mutex_);
+  MutexLock l(&mutex_);
   ++disable_delete_obsolete_files_;
   if (disable_delete_obsolete_files_ == 1) {
-    Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
-        "File Deletions Disabled");
-  } else {
-    Log(InfoLogLevel::WARN_LEVEL, db_options_.info_log,
-        "File Deletions Disabled, but already disabled. Counter: %d",
-        disable_delete_obsolete_files_);
+    // if not, it has already been disabled, so don't log anything
+    Log(options_.info_log, "File Deletions Disabled");
   }
   return Status::OK();
 }
 
 Status DBImpl::EnableFileDeletions(bool force) {
-  // Job id == 0 means that this is not our background process, but rather
-  // user thread
-  JobContext job_context(0);
+  DeletionState deletion_state;
   bool should_purge_files = false;
   {
-    InstrumentedMutexLock l(&mutex_);
+    MutexLock l(&mutex_);
     if (force) {
       // if force, we need to enable file deletions right away
       disable_delete_obsolete_files_ = 0;
@@ -58,72 +45,39 @@ Status DBImpl::EnableFileDeletions(bool force) {
       --disable_delete_obsolete_files_;
     }
     if (disable_delete_obsolete_files_ == 0)  {
-      Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
-          "File Deletions Enabled");
+      Log(options_.info_log, "File Deletions Enabled");
       should_purge_files = true;
-      FindObsoleteFiles(&job_context, true);
-    } else {
-      Log(InfoLogLevel::WARN_LEVEL, db_options_.info_log,
-          "File Deletions Enable, but not really enabled. Counter: %d",
-          disable_delete_obsolete_files_);
+      FindObsoleteFiles(deletion_state, true);
     }
   }
   if (should_purge_files)  {
-    PurgeObsoleteFiles(job_context);
+    PurgeObsoleteFiles(deletion_state);
   }
-  job_context.Clean();
-  LogFlush(db_options_.info_log);
+  LogFlush(options_.info_log);
   return Status::OK();
 }
 
-int DBImpl::IsFileDeletionsEnabled() const {
-  return disable_delete_obsolete_files_;
-}
-
 Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
                             uint64_t* manifest_file_size,
                             bool flush_memtable) {
 
   *manifest_file_size = 0;
 
-  mutex_.Lock();
-
   if (flush_memtable) {
     // flush all dirty data to disk.
-    Status status;
-    for (auto cfd : *versions_->GetColumnFamilySet()) {
-      if (cfd->IsDropped()) {
-        continue;
-      }
-      cfd->Ref();
-      mutex_.Unlock();
-      status = FlushMemTable(cfd, FlushOptions());
-      TEST_SYNC_POINT("DBImpl::GetLiveFiles:1");
-      TEST_SYNC_POINT("DBImpl::GetLiveFiles:2");
-      mutex_.Lock();
-      cfd->Unref();
-      if (!status.ok()) {
-        break;
-      }
-    }
-    versions_->GetColumnFamilySet()->FreeDeadColumnFamilies();
-
+    Status status =  Flush(FlushOptions());
     if (!status.ok()) {
-      mutex_.Unlock();
-      Log(InfoLogLevel::ERROR_LEVEL, db_options_.info_log,
-          "Cannot Flush data %s\n", status.ToString().c_str());
+      Log(options_.info_log, "Cannot Flush data %s\n",
+          status.ToString().c_str());
       return status;
     }
   }
 
+  MutexLock l(&mutex_);
+
   // Make a set of all of the live *.sst files
-  std::vector<FileDescriptor> live;
-  for (auto cfd : *versions_->GetColumnFamilySet()) {
-    if (cfd->IsDropped()) {
-      continue;
-    }
-    cfd->current()->AddLiveFiles(&live);
-  }
+  std::set<uint64_t> live;
+  versions_->current()->AddLiveFiles(&live);
 
   ret.clear();
   ret.reserve(live.size() + 2); //*.sst + CURRENT + MANIFEST
@@ -131,23 +85,68 @@ Status DBImpl::GetLiveFiles(std::vector<std::string>& ret,
   // create names of the live files. The names are not absolute
   // paths, instead they are relative to dbname_;
   for (auto live_file : live) {
-    ret.push_back(MakeTableFileName("", live_file.GetNumber()));
+    ret.push_back(TableFileName("", live_file));
   }
 
   ret.push_back(CurrentFileName(""));
-  ret.push_back(DescriptorFileName("", versions_->manifest_file_number()));
+  ret.push_back(DescriptorFileName("", versions_->ManifestFileNumber()));
 
   // find length of manifest file while holding the mutex lock
-  *manifest_file_size = versions_->manifest_file_size();
+  *manifest_file_size = versions_->ManifestFileSize();
 
-  mutex_.Unlock();
   return Status::OK();
 }
 
 Status DBImpl::GetSortedWalFiles(VectorLogPtr& files) {
-  return wal_manager_.GetSortedWalFiles(files);
+  // First get sorted files in db dir, then get sorted files from archived
+  // dir, to avoid a race condition where a log file is moved to archived
+  // dir in between.
+  Status s;
+  // list wal files in main db dir.
+  VectorLogPtr logs;
+  s = GetSortedWalsOfType(options_.wal_dir, logs, kAliveLogFile);
+  if (!s.ok()) {
+    return s;
+  }
+
+  // Reproduce the race condition where a log file is moved
+  // to archived dir, between these two sync points, used in
+  // (DBTest,TransactionLogIteratorRace)
+  TEST_SYNC_POINT("DBImpl::GetSortedWalFiles:1");
+  TEST_SYNC_POINT("DBImpl::GetSortedWalFiles:2");
+
+  files.clear();
+  // list wal files in archive dir.
+  std::string archivedir = ArchivalDirectory(options_.wal_dir);
+  if (env_->FileExists(archivedir)) {
+    s = GetSortedWalsOfType(archivedir, files, kArchivedLogFile);
+    if (!s.ok()) {
+      return s;
+    }
+  }
+
+  uint64_t latest_archived_log_number = 0;
+  if (!files.empty()) {
+    latest_archived_log_number = files.back()->LogNumber();
+    Log(options_.info_log, "Latest Archived log: %" PRIu64,
+        latest_archived_log_number);
+  }
+
+  files.reserve(files.size() + logs.size());
+  for (auto& log : logs) {
+    if (log->LogNumber() > latest_archived_log_number) {
+      files.push_back(std::move(log));
+    } else {
+      // When the race condition happens, we could see the
+      // same log in both db dir and archived dir. Simply
+      // ignore the one in db dir. Note that, if we read
+      // archived dir first, we would have missed the log file.
+      Log(options_.info_log, "%s already moved to archive",
+          log->PathName().c_str());
+    }
+  }
+
+  return s;
 }
 
 }
-
-#endif  // ROCKSDB_LITE

db/db_impl_debug.cc

@@ -1,182 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#ifndef NDEBUG
-
-#include "db/db_impl.h"
-#include "util/thread_status_updater.h"
-
-namespace rocksdb {
-
-uint64_t DBImpl::TEST_GetLevel0TotalSize() {
-  InstrumentedMutexLock l(&mutex_);
-  return default_cf_handle_->cfd()->current()->storage_info()->NumLevelBytes(0);
-}
-
-int64_t DBImpl::TEST_MaxNextLevelOverlappingBytes(
-    ColumnFamilyHandle* column_family) {
-  ColumnFamilyData* cfd;
-  if (column_family == nullptr) {
-    cfd = default_cf_handle_->cfd();
-  } else {
-    auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
-    cfd = cfh->cfd();
-  }
-  InstrumentedMutexLock l(&mutex_);
-  return cfd->current()->storage_info()->MaxNextLevelOverlappingBytes();
-}
-
-void DBImpl::TEST_GetFilesMetaData(
-    ColumnFamilyHandle* column_family,
-    std::vector<std::vector<FileMetaData>>* metadata) {
-  auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
-  auto cfd = cfh->cfd();
-  InstrumentedMutexLock l(&mutex_);
-  metadata->resize(NumberLevels());
-  for (int level = 0; level < NumberLevels(); level++) {
-    const std::vector<FileMetaData*>& files =
-        cfd->current()->storage_info()->LevelFiles(level);
-
-    (*metadata)[level].clear();
-    for (const auto& f : files) {
-      (*metadata)[level].push_back(*f);
-    }
-  }
-}
-
-uint64_t DBImpl::TEST_Current_Manifest_FileNo() {
-  return versions_->manifest_file_number();
-}
-
-Status DBImpl::TEST_CompactRange(int level, const Slice* begin,
-                                 const Slice* end,
-                                 ColumnFamilyHandle* column_family,
-                                 bool disallow_trivial_move) {
-  ColumnFamilyData* cfd;
-  if (column_family == nullptr) {
-    cfd = default_cf_handle_->cfd();
-  } else {
-    auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
-    cfd = cfh->cfd();
-  }
-  int output_level =
-      (cfd->ioptions()->compaction_style == kCompactionStyleUniversal ||
-       cfd->ioptions()->compaction_style == kCompactionStyleFIFO)
-          ? level
-          : level + 1;
-  return RunManualCompaction(cfd, level, output_level, 0, begin, end, true,
-                             disallow_trivial_move);
-}
-
-Status DBImpl::TEST_FlushMemTable(bool wait, ColumnFamilyHandle* cfh) {
-  FlushOptions fo;
-  fo.wait = wait;
-  ColumnFamilyData* cfd;
-  if (cfh == nullptr) {
-    cfd = default_cf_handle_->cfd();
-  } else {
-    auto cfhi = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh);
-    cfd = cfhi->cfd();
-  }
-  return FlushMemTable(cfd, fo);
-}
-
-Status DBImpl::TEST_WaitForFlushMemTable(ColumnFamilyHandle* column_family) {
-  ColumnFamilyData* cfd;
-  if (column_family == nullptr) {
-    cfd = default_cf_handle_->cfd();
-  } else {
-    auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
-    cfd = cfh->cfd();
-  }
-  return WaitForFlushMemTable(cfd);
-}
-
-Status DBImpl::TEST_WaitForCompact() {
-  // Wait until the compaction completes
-
-  // TODO: a bug here. This function actually does not necessarily
-  // wait for compact. It actually waits for scheduled compaction
-  // OR flush to finish.
-
-  InstrumentedMutexLock l(&mutex_);
-  while ((bg_compaction_scheduled_ || bg_flush_scheduled_) && bg_error_.ok()) {
-    bg_cv_.Wait();
-  }
-  return bg_error_;
-}
-
-void DBImpl::TEST_LockMutex() {
-  mutex_.Lock();
-}
-
-void DBImpl::TEST_UnlockMutex() {
-  mutex_.Unlock();
-}
-
-void* DBImpl::TEST_BeginWrite() {
-  auto w = new WriteThread::Writer();
-  write_thread_.EnterUnbatched(w, &mutex_);
-  return reinterpret_cast<void*>(w);
-}
-
-void DBImpl::TEST_EndWrite(void* w) {
-  auto writer = reinterpret_cast<WriteThread::Writer*>(w);
-  write_thread_.ExitUnbatched(writer);
-  delete writer;
-}
-
-size_t DBImpl::TEST_LogsToFreeSize() {
-  InstrumentedMutexLock l(&mutex_);
-  return logs_to_free_.size();
-}
-
-uint64_t DBImpl::TEST_LogfileNumber() {
-  InstrumentedMutexLock l(&mutex_);
-  return logfile_number_;
-}
-
-Status DBImpl::TEST_GetAllImmutableCFOptions(
-    std::unordered_map<std::string, const ImmutableCFOptions*>* iopts_map) {
-  std::vector<std::string> cf_names;
-  std::vector<const ImmutableCFOptions*> iopts;
-  {
-    InstrumentedMutexLock l(&mutex_);
-    for (auto cfd : *versions_->GetColumnFamilySet()) {
-      cf_names.push_back(cfd->GetName());
-      iopts.push_back(cfd->ioptions());
-    }
-  }
-  iopts_map->clear();
-  for (size_t i = 0; i < cf_names.size(); ++i) {
-    iopts_map->insert({cf_names[i], iopts[i]});
-  }
-
-  return Status::OK();
-}
-
-uint64_t DBImpl::TEST_FindMinLogContainingOutstandingPrep() {
-  return FindMinLogContainingOutstandingPrep();
-}
-
-uint64_t DBImpl::TEST_FindMinPrepLogReferencedByMemTable() {
-  return FindMinPrepLogReferencedByMemTable();
-}
-
-Status DBImpl::TEST_GetLatestMutableCFOptions(
-    ColumnFamilyHandle* column_family, MutableCFOptions* mutable_cf_options) {
-  InstrumentedMutexLock l(&mutex_);
-
-  auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
-  *mutable_cf_options = *cfh->cfd()->GetLatestMutableCFOptions();
-  return Status::OK();
-}
-
-}  // namespace rocksdb
-#endif  // NDEBUG

db/db_impl_experimental.cc

@@ -1,150 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include "db/db_impl.h"
-
-#ifndef __STDC_FORMAT_MACROS
-#define __STDC_FORMAT_MACROS
-#endif
-
-#include <inttypes.h>
-#include <vector>
-
-#include "db/column_family.h"
-#include "db/job_context.h"
-#include "db/version_set.h"
-#include "rocksdb/status.h"
-
-namespace rocksdb {
-
-#ifndef ROCKSDB_LITE
-Status DBImpl::SuggestCompactRange(ColumnFamilyHandle* column_family,
-                                   const Slice* begin, const Slice* end) {
-  auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
-  auto cfd = cfh->cfd();
-  InternalKey start_key, end_key;
-  if (begin != nullptr) {
-    start_key.SetMaxPossibleForUserKey(*begin);
-  }
-  if (end != nullptr) {
-    end_key.SetMinPossibleForUserKey(*end);
-  }
-  {
-    InstrumentedMutexLock l(&mutex_);
-    auto vstorage = cfd->current()->storage_info();
-    for (int level = 0; level < vstorage->num_non_empty_levels() - 1; ++level) {
-      std::vector<FileMetaData*> inputs;
-      vstorage->GetOverlappingInputs(
-          level, begin == nullptr ? nullptr : &start_key,
-          end == nullptr ? nullptr : &end_key, &inputs);
-      for (auto f : inputs) {
-        f->marked_for_compaction = true;
-      }
-    }
-    // Since we have some more files to compact, we should also recompute
-    // compaction score
-    vstorage->ComputeCompactionScore(*cfd->GetLatestMutableCFOptions());
-    SchedulePendingCompaction(cfd);
-    MaybeScheduleFlushOrCompaction();
-  }
-  return Status::OK();
-}
-
-Status DBImpl::PromoteL0(ColumnFamilyHandle* column_family, int target_level) {
-  assert(column_family);
-
-  if (target_level < 1) {
-    Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
-        "PromoteL0 FAILED. Invalid target level %d\n", target_level);
-    return Status::InvalidArgument("Invalid target level");
-  }
-
-  Status status;
-  VersionEdit edit;
-  JobContext job_context(next_job_id_.fetch_add(1), true);
-  {
-    InstrumentedMutexLock l(&mutex_);
-    auto* cfd = static_cast<ColumnFamilyHandleImpl*>(column_family)->cfd();
-    const auto* vstorage = cfd->current()->storage_info();
-
-    if (target_level >= vstorage->num_levels()) {
-      Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
-          "PromoteL0 FAILED. Target level %d does not exist\n", target_level);
-      job_context.Clean();
-      return Status::InvalidArgument("Target level does not exist");
-    }
-
-    // Sort L0 files by range.
-    const InternalKeyComparator* icmp = &cfd->internal_comparator();
-    auto l0_files = vstorage->LevelFiles(0);
-    std::sort(l0_files.begin(), l0_files.end(),
-              [icmp](FileMetaData* f1, FileMetaData* f2) {
-                return icmp->Compare(f1->largest, f2->largest) < 0;
-              });
-
-    // Check that no L0 file is being compacted and that they have
-    // non-overlapping ranges.
-    for (size_t i = 0; i < l0_files.size(); ++i) {
-      auto f = l0_files[i];
-      if (f->being_compacted) {
-        Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
-            "PromoteL0 FAILED. File %" PRIu64 " being compacted\n",
-            f->fd.GetNumber());
-        job_context.Clean();
-        return Status::InvalidArgument("PromoteL0 called during L0 compaction");
-      }
-
-      if (i == 0) continue;
-      auto prev_f = l0_files[i - 1];
-      if (icmp->Compare(prev_f->largest, f->smallest) >= 0) {
-        Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
-            "PromoteL0 FAILED. Files %" PRIu64 " and %" PRIu64
-            " have overlapping ranges\n",
-            prev_f->fd.GetNumber(), f->fd.GetNumber());
-        job_context.Clean();
-        return Status::InvalidArgument("L0 has overlapping files");
-      }
-    }
-
-    // Check that all levels up to target_level are empty.
-    for (int level = 1; level <= target_level; ++level) {
-      if (vstorage->NumLevelFiles(level) > 0) {
-        Log(InfoLogLevel::INFO_LEVEL, db_options_.info_log,
-            "PromoteL0 FAILED. Level %d not empty\n", level);
-        job_context.Clean();
-        return Status::InvalidArgument(
-            "All levels up to target_level "
-            "must be empty");
-      }
-    }
-
-    edit.SetColumnFamily(cfd->GetID());
-    for (const auto& f : l0_files) {
-      edit.DeleteFile(0, f->fd.GetNumber());
-      edit.AddFile(target_level, f->fd.GetNumber(), f->fd.GetPathId(),
-                   f->fd.GetFileSize(), f->smallest, f->largest,
-                   f->smallest_seqno, f->largest_seqno,
-                   f->marked_for_compaction);
-    }
-
-    status = versions_->LogAndApply(cfd, *cfd->GetLatestMutableCFOptions(),
-                                    &edit, &mutex_, directories_.GetDbDir());
-    if (status.ok()) {
-      InstallSuperVersionAndScheduleWorkWrapper(
-          cfd, &job_context, *cfd->GetLatestMutableCFOptions());
-    }
-  }  // lock released here
-  LogFlush(db_options_.info_log);
-  job_context.Clean();
-
-  return status;
-}
-#endif  // ROCKSDB_LITE
-
-}  // namespace rocksdb

db/db_impl_readonly.cc

@@ -1,189 +1,102 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
-
+//
+// Copyright (c) 2012 Facebook. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
 
 #include "db/db_impl_readonly.h"
-
-#include "db/compacted_db_impl.h"
 #include "db/db_impl.h"
-#include "db/merge_context.h"
+
+#include <algorithm>
+#include <set>
+#include <string>
+#include <stdint.h>
+#include <stdio.h>
+#include <vector>
+#include <algorithm>
 #include "db/db_iter.h"
-#include "util/perf_context_imp.h"
+#include "db/dbformat.h"
+#include "db/filename.h"
+#include "db/log_reader.h"
+#include "db/log_writer.h"
+#include "db/memtable.h"
+#include "db/merge_context.h"
+#include "db/table_cache.h"
+#include "db/version_set.h"
+#include "db/write_batch_internal.h"
+#include "rocksdb/db.h"
+#include "rocksdb/env.h"
+#include "rocksdb/status.h"
+#include "rocksdb/table.h"
+#include "rocksdb/merge_operator.h"
+#include "port/port.h"
+#include "table/block.h"
+#include "table/merger.h"
+#include "table/two_level_iterator.h"
+#include "util/coding.h"
+#include "util/logging.h"
+#include "util/build_version.h"
 
 namespace rocksdb {
 
-#ifndef ROCKSDB_LITE
-
-DBImplReadOnly::DBImplReadOnly(const DBOptions& db_options,
-                               const std::string& dbname)
-    : DBImpl(db_options, dbname) {
-  Log(INFO_LEVEL, db_options_.info_log, "Opening the db in read only mode");
-  LogFlush(db_options_.info_log);
+DBImplReadOnly::DBImplReadOnly(const Options& options,
+    const std::string& dbname)
+    : DBImpl(options, dbname) {
+  Log(options_.info_log, "Opening the db in read only mode");
 }
 
 DBImplReadOnly::~DBImplReadOnly() {
 }
 
 // Implementations of the DB interface
-Status DBImplReadOnly::Get(const ReadOptions& read_options,
-                           ColumnFamilyHandle* column_family, const Slice& key,
-                           std::string* value) {
+Status DBImplReadOnly::Get(const ReadOptions& options,
+                   const Slice& key,
+                   std::string* value) {
   Status s;
   SequenceNumber snapshot = versions_->LastSequence();
-  auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
-  auto cfd = cfh->cfd();
-  SuperVersion* super_version = cfd->GetSuperVersion();
+  SuperVersion* super_version = GetSuperVersion();
   MergeContext merge_context;
   LookupKey lkey(key, snapshot);
-  if (super_version->mem->Get(lkey, value, &s, &merge_context)) {
+  if (super_version->mem->Get(lkey, value, &s, merge_context, options_)) {
   } else {
-    PERF_TIMER_GUARD(get_from_output_files_time);
-    super_version->current->Get(read_options, lkey, value, &s, &merge_context);
+    Version::GetStats stats;
+    super_version->current->Get(options, lkey, value, &s, &merge_context,
+                                &stats, options_);
   }
   return s;
 }
 
-Iterator* DBImplReadOnly::NewIterator(const ReadOptions& read_options,
-                                      ColumnFamilyHandle* column_family) {
-  auto cfh = reinterpret_cast<ColumnFamilyHandleImpl*>(column_family);
-  auto cfd = cfh->cfd();
-  SuperVersion* super_version = cfd->GetSuperVersion()->Ref();
-  SequenceNumber latest_snapshot = versions_->LastSequence();
-  auto db_iter = NewArenaWrappedDbIterator(
-      env_, *cfd->ioptions(), cfd->user_comparator(),
-      (read_options.snapshot != nullptr
-           ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
-                 ->number_
-           : latest_snapshot),
-      super_version->mutable_cf_options.max_sequential_skip_in_iterations,
-      super_version->version_number);
-  auto internal_iter = NewInternalIterator(
-      read_options, cfd, super_version, db_iter->GetArena());
-  db_iter->SetIterUnderDBIter(internal_iter);
-  return db_iter;
+Iterator* DBImplReadOnly::NewIterator(const ReadOptions& options) {
+  SequenceNumber latest_snapshot;
+  Iterator* internal_iter = NewInternalIterator(options, &latest_snapshot);
+  return NewDBIterator(
+    &dbname_, env_, options_,  user_comparator(),internal_iter,
+      (options.snapshot != nullptr
+      ? reinterpret_cast<const SnapshotImpl*>(options.snapshot)->number_
+      : latest_snapshot));
 }
 
-Status DBImplReadOnly::NewIterators(
-    const ReadOptions& read_options,
-    const std::vector<ColumnFamilyHandle*>& column_families,
-    std::vector<Iterator*>* iterators) {
-  if (iterators == nullptr) {
-    return Status::InvalidArgument("iterators not allowed to be nullptr");
-  }
-  iterators->clear();
-  iterators->reserve(column_families.size());
-  SequenceNumber latest_snapshot = versions_->LastSequence();
-
-  for (auto cfh : column_families) {
-    auto* cfd = reinterpret_cast<ColumnFamilyHandleImpl*>(cfh)->cfd();
-    auto* sv = cfd->GetSuperVersion()->Ref();
-    auto* db_iter = NewArenaWrappedDbIterator(
-        env_, *cfd->ioptions(), cfd->user_comparator(),
-        (read_options.snapshot != nullptr
-             ? reinterpret_cast<const SnapshotImpl*>(read_options.snapshot)
-                   ->number_
-             : latest_snapshot),
-        sv->mutable_cf_options.max_sequential_skip_in_iterations,
-        sv->version_number);
-    auto* internal_iter = NewInternalIterator(
-        read_options, cfd, sv, db_iter->GetArena());
-    db_iter->SetIterUnderDBIter(internal_iter);
-    iterators->push_back(db_iter);
-  }
-
-  return Status::OK();
-}
 
 Status DB::OpenForReadOnly(const Options& options, const std::string& dbname,
-                           DB** dbptr, bool error_if_log_file_exist) {
+                DB** dbptr, bool error_if_log_file_exist) {
   *dbptr = nullptr;
 
-  // Try to first open DB as fully compacted DB
-  Status s;
-  s = CompactedDBImpl::Open(options, dbname, dbptr);
-  if (s.ok()) {
-    return s;
-  }
-
-  DBOptions db_options(options);
-  ColumnFamilyOptions cf_options(options);
-  std::vector<ColumnFamilyDescriptor> column_families;
-  column_families.push_back(
-      ColumnFamilyDescriptor(kDefaultColumnFamilyName, cf_options));
-  std::vector<ColumnFamilyHandle*> handles;
-
-  s = DB::OpenForReadOnly(db_options, dbname, column_families, &handles, dbptr);
-  if (s.ok()) {
-    assert(handles.size() == 1);
-    // i can delete the handle since DBImpl is always holding a
-    // reference to default column family
-    delete handles[0];
-  }
-  return s;
-}
-
-Status DB::OpenForReadOnly(
-    const DBOptions& db_options, const std::string& dbname,
-    const std::vector<ColumnFamilyDescriptor>& column_families,
-    std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
-    bool error_if_log_file_exist) {
-  *dbptr = nullptr;
-  handles->clear();
-
-  DBImplReadOnly* impl = new DBImplReadOnly(db_options, dbname);
+  DBImplReadOnly* impl = new DBImplReadOnly(options, dbname);
   impl->mutex_.Lock();
-  Status s = impl->Recover(column_families, true /* read only */,
-                           error_if_log_file_exist);
+  Status s = impl->Recover(true /* read only */, error_if_log_file_exist);
   if (s.ok()) {
-    // set column family handles
-    for (auto cf : column_families) {
-      auto cfd =
-          impl->versions_->GetColumnFamilySet()->GetColumnFamily(cf.name);
-      if (cfd == nullptr) {
-        s = Status::InvalidArgument("Column family not found: ", cf.name);
-        break;
-      }
-      handles->push_back(new ColumnFamilyHandleImpl(cfd, impl, &impl->mutex_));
-    }
-  }
-  if (s.ok()) {
-    for (auto cfd : *impl->versions_->GetColumnFamilySet()) {
-      delete cfd->InstallSuperVersion(new SuperVersion(), &impl->mutex_);
-    }
+    delete impl->InstallSuperVersion(new DBImpl::SuperVersion());
   }
   impl->mutex_.Unlock();
   if (s.ok()) {
     *dbptr = impl;
-    for (auto* h : *handles) {
-      impl->NewThreadStatusCfInfo(
-          reinterpret_cast<ColumnFamilyHandleImpl*>(h)->cfd());
-    }
   } else {
-    for (auto h : *handles) {
-      delete h;
-    }
-    handles->clear();
     delete impl;
   }
   return s;
 }
 
-#else  // !ROCKSDB_LITE
-
-Status DB::OpenForReadOnly(const Options& options, const std::string& dbname,
-                           DB** dbptr, bool error_if_log_file_exist) {
-  return Status::NotSupported("Not supported in ROCKSDB_LITE.");
-}
-
-Status DB::OpenForReadOnly(
-    const DBOptions& db_options, const std::string& dbname,
-    const std::vector<ColumnFamilyDescriptor>& column_families,
-    std::vector<ColumnFamilyHandle*>* handles, DB** dbptr,
-    bool error_if_log_file_exist) {
-  return Status::NotSupported("Not supported in ROCKSDB_LITE.");
-}
-#endif  // !ROCKSDB_LITE
-
 }   // namespace rocksdb

db/db_impl_readonly.h

@@ -1,117 +1,79 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
+//  Copyright (c) 2013, Facebook, Inc.  All rights reserved.
 //  This source code is licensed under the BSD-style license found in the
 //  LICENSE file in the root directory of this source tree. An additional grant
 //  of patent rights can be found in the PATENTS file in the same directory.
+//
+// Copyright (c) 2012 Facebook. All rights reserved.
+// Use of this source code is governed by a BSD-style license that can be
+// found in the LICENSE file.
 
 #pragma once
-
-#ifndef ROCKSDB_LITE
-
 #include "db/db_impl.h"
-#include <vector>
-#include <string>
+
+#include <deque>
+#include <set>
+#include "db/dbformat.h"
+#include "db/log_writer.h"
+#include "db/snapshot.h"
+#include "rocksdb/db.h"
+#include "rocksdb/env.h"
+#include "port/port.h"
+#include "util/stats_logger.h"
 
 namespace rocksdb {
 
 class DBImplReadOnly : public DBImpl {
- public:
-  DBImplReadOnly(const DBOptions& options, const std::string& dbname);
-  virtual ~DBImplReadOnly();
+public:
+  DBImplReadOnly(const Options& options, const std::string& dbname);
+ virtual ~DBImplReadOnly();
 
-  // Implementations of the DB interface
-  using DB::Get;
-  virtual Status Get(const ReadOptions& options,
-                     ColumnFamilyHandle* column_family, const Slice& key,
-                     std::string* value) override;
+ // Implementations of the DB interface
+ virtual Status Get(const ReadOptions& options,
+                    const Slice& key,
+                    std::string* value);
 
-  // TODO: Implement ReadOnly MultiGet?
+ // TODO: Implement ReadOnly MultiGet?
 
-  using DBImpl::NewIterator;
-  virtual Iterator* NewIterator(const ReadOptions&,
-                                ColumnFamilyHandle* column_family) override;
+ virtual Iterator* NewIterator(const ReadOptions&);
 
-  virtual Status NewIterators(
-      const ReadOptions& options,
-      const std::vector<ColumnFamilyHandle*>& column_families,
-      std::vector<Iterator*>* iterators) override;
+ virtual Status Put(const WriteOptions&, const Slice& key, const Slice& value) {
+   return Status::NotSupported("Not supported operation in read only mode.");
+ }
+ virtual Status Merge(const WriteOptions&, const Slice& key,
+                      const Slice& value) {
+   return Status::NotSupported("Not supported operation in read only mode.");
+ }
+ virtual Status Delete(const WriteOptions&, const Slice& key) {
+   return Status::NotSupported("Not supported operation in read only mode.");
+ }
+ virtual Status Write(const WriteOptions& options, WriteBatch* updates) {
+   return Status::NotSupported("Not supported operation in read only mode.");
+ }
+ virtual Status CompactRange(const Slice* begin, const Slice* end,
+                             bool reduce_level = false, int target_level = -1) {
+   return Status::NotSupported("Not supported operation in read only mode.");
+ }
+ virtual Status DisableFileDeletions() {
+   return Status::NotSupported("Not supported operation in read only mode.");
+ }
+ virtual Status EnableFileDeletions(bool force) {
+   return Status::NotSupported("Not supported operation in read only mode.");
+ }
+ virtual Status GetLiveFiles(std::vector<std::string>&,
+                             uint64_t* manifest_file_size,
+                             bool flush_memtable = true) {
+   return Status::NotSupported("Not supported operation in read only mode.");
+ }
+ virtual Status Flush(const FlushOptions& options) {
+   return Status::NotSupported("Not supported operation in read only mode.");
+ }
 
-  using DBImpl::Put;
-  virtual Status Put(const WriteOptions& options,
-                     ColumnFamilyHandle* column_family, const Slice& key,
-                     const Slice& value) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-  using DBImpl::Merge;
-  virtual Status Merge(const WriteOptions& options,
-                       ColumnFamilyHandle* column_family, const Slice& key,
-                       const Slice& value) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-  using DBImpl::Delete;
-  virtual Status Delete(const WriteOptions& options,
-                        ColumnFamilyHandle* column_family,
-                        const Slice& key) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-  using DBImpl::SingleDelete;
-  virtual Status SingleDelete(const WriteOptions& options,
-                              ColumnFamilyHandle* column_family,
-                              const Slice& key) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-  virtual Status Write(const WriteOptions& options,
-                       WriteBatch* updates) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-  using DBImpl::CompactRange;
-  virtual Status CompactRange(const CompactRangeOptions& options,
-                              ColumnFamilyHandle* column_family,
-                              const Slice* begin, const Slice* end) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
+private:
+ friend class DB;
 
-  using DBImpl::CompactFiles;
-  virtual Status CompactFiles(
-      const CompactionOptions& compact_options,
-      ColumnFamilyHandle* column_family,
-      const std::vector<std::string>& input_file_names,
-      const int output_level, const int output_path_id = -1) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-
-#ifndef ROCKSDB_LITE
-  virtual Status DisableFileDeletions() override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-
-  virtual Status EnableFileDeletions(bool force) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-  virtual Status GetLiveFiles(std::vector<std::string>&,
-                              uint64_t* manifest_file_size,
-                              bool flush_memtable = true) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-#endif  // ROCKSDB_LITE
-
-  using DBImpl::Flush;
-  virtual Status Flush(const FlushOptions& options,
-                       ColumnFamilyHandle* column_family) override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-
-  using DBImpl::SyncWAL;
-  virtual Status SyncWAL() override {
-    return Status::NotSupported("Not supported operation in read only mode.");
-  }
-
- private:
-  friend class DB;
-
-  // No copying allowed
-  DBImplReadOnly(const DBImplReadOnly&);
-  void operator=(const DBImplReadOnly&);
+ // No copying allowed
+ DBImplReadOnly(const DBImplReadOnly&);
+ void operator=(const DBImplReadOnly&);
 };
-}
 
-#endif  // !ROCKSDB_LITE
+}

db/db_info_dumper.cc

@@ -1,127 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-
-#ifndef __STDC_FORMAT_MACROS
-#define __STDC_FORMAT_MACROS
-#endif
-
-#include "db/db_info_dumper.h"
-
-#include <inttypes.h>
-#include <stdio.h>
-#include <string>
-#include <algorithm>
-#include <vector>
-
-#include "db/filename.h"
-#include "rocksdb/options.h"
-#include "rocksdb/env.h"
-
-namespace rocksdb {
-
-void DumpDBFileSummary(const DBOptions& options, const std::string& dbname) {
-  if (options.info_log == nullptr) {
-    return;
-  }
-
-  auto* env = options.env;
-  uint64_t number = 0;
-  FileType type = kInfoLogFile;
-
-  std::vector<std::string> files;
-  uint64_t file_num = 0;
-  uint64_t file_size;
-  std::string file_info, wal_info;
-
-  Header(options.info_log, "DB SUMMARY\n");
-  // Get files in dbname dir
-  if (!env->GetChildren(dbname, &files).ok()) {
-    Error(options.info_log,
-          "Error when reading %s dir\n", dbname.c_str());
-  }
-  std::sort(files.begin(), files.end());
-  for (std::string file : files) {
-    if (!ParseFileName(file, &number, &type)) {
-      continue;
-    }
-    switch (type) {
-      case kCurrentFile:
-        Header(options.info_log, "CURRENT file:  %s\n", file.c_str());
-        break;
-      case kIdentityFile:
-        Header(options.info_log, "IDENTITY file:  %s\n", file.c_str());
-        break;
-      case kDescriptorFile:
-        env->GetFileSize(dbname + "/" + file, &file_size);
-        Header(options.info_log, "MANIFEST file:  %s size: %" PRIu64 " Bytes\n",
-               file.c_str(), file_size);
-        break;
-      case kLogFile:
-        env->GetFileSize(dbname + "/" + file, &file_size);
-        char str[16];
-        snprintf(str, sizeof(str), "%" PRIu64, file_size);
-        wal_info.append(file).append(" size: ").
-            append(str).append(" ; ");
-        break;
-      case kTableFile:
-        if (++file_num < 10) {
-          file_info.append(file).append(" ");
-        }
-        break;
-      default:
-        break;
-    }
-  }
-
-  // Get sst files in db_path dir
-  for (auto& db_path : options.db_paths) {
-    if (dbname.compare(db_path.path) != 0) {
-      if (!env->GetChildren(db_path.path, &files).ok()) {
-        Error(options.info_log,
-            "Error when reading %s dir\n",
-            db_path.path.c_str());
-        continue;
-      }
-      std::sort(files.begin(), files.end());
-      for (std::string file : files) {
-        if (ParseFileName(file, &number, &type)) {
-          if (type == kTableFile && ++file_num < 10) {
-            file_info.append(file).append(" ");
-          }
-        }
-      }
-    }
-    Header(options.info_log,
-           "SST files in %s dir, Total Num: %" PRIu64 ", files: %s\n",
-           db_path.path.c_str(), file_num, file_info.c_str());
-    file_num = 0;
-    file_info.clear();
-  }
-
-  // Get wal file in wal_dir
-  if (dbname.compare(options.wal_dir) != 0) {
-    if (!env->GetChildren(options.wal_dir, &files).ok()) {
-      Error(options.info_log,
-          "Error when reading %s dir\n",
-          options.wal_dir.c_str());
-      return;
-    }
-    wal_info.clear();
-    for (std::string file : files) {
-      if (ParseFileName(file, &number, &type)) {
-        if (type == kLogFile) {
-          env->GetFileSize(options.wal_dir + "/" + file, &file_size);
-          char str[16];
-          snprintf(str, sizeof(str), "%" PRIu64, file_size);
-          wal_info.append(file).append(" size: ").
-              append(str).append(" ; ");
-        }
-      }
-    }
-  }
-  Header(options.info_log, "Write Ahead Log file in %s: %s\n",
-         options.wal_dir.c_str(), wal_info.c_str());
-}
-}  // namespace rocksdb

db/db_info_dumper.h

@@ -1,13 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-#pragma once
-
-#include <string>
-
-#include "rocksdb/options.h"
-
-namespace rocksdb {
-void DumpDBFileSummary(const DBOptions& options, const std::string& dbname);
-}  // namespace rocksdb

db/db_inplace_update_test.cc

@@ -1,165 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-
-namespace rocksdb {
-
-class DBTestInPlaceUpdate : public DBTestBase {
- public:
-  DBTestInPlaceUpdate() : DBTestBase("/db_inplace_update_test") {}
-};
-
-TEST_F(DBTestInPlaceUpdate, InPlaceUpdate) {
-  do {
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    options.inplace_update_support = true;
-    options.env = env_;
-    options.write_buffer_size = 100000;
-    CreateAndReopenWithCF({"pikachu"}, options);
-
-    // Update key with values of smaller size
-    int numValues = 10;
-    for (int i = numValues; i > 0; i--) {
-      std::string value = DummyString(i, 'a');
-      ASSERT_OK(Put(1, "key", value));
-      ASSERT_EQ(value, Get(1, "key"));
-    }
-
-    // Only 1 instance for that key.
-    validateNumberOfEntries(1, 1);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBTestInPlaceUpdate, InPlaceUpdateLargeNewValue) {
-  do {
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    options.inplace_update_support = true;
-    options.env = env_;
-    options.write_buffer_size = 100000;
-    CreateAndReopenWithCF({"pikachu"}, options);
-
-    // Update key with values of larger size
-    int numValues = 10;
-    for (int i = 0; i < numValues; i++) {
-      std::string value = DummyString(i, 'a');
-      ASSERT_OK(Put(1, "key", value));
-      ASSERT_EQ(value, Get(1, "key"));
-    }
-
-    // All 10 updates exist in the internal iterator
-    validateNumberOfEntries(numValues, 1);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackSmallerSize) {
-  do {
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    options.inplace_update_support = true;
-
-    options.env = env_;
-    options.write_buffer_size = 100000;
-    options.inplace_callback =
-      rocksdb::DBTestInPlaceUpdate::updateInPlaceSmallerSize;
-    CreateAndReopenWithCF({"pikachu"}, options);
-
-    // Update key with values of smaller size
-    int numValues = 10;
-    ASSERT_OK(Put(1, "key", DummyString(numValues, 'a')));
-    ASSERT_EQ(DummyString(numValues, 'c'), Get(1, "key"));
-
-    for (int i = numValues; i > 0; i--) {
-      ASSERT_OK(Put(1, "key", DummyString(i, 'a')));
-      ASSERT_EQ(DummyString(i - 1, 'b'), Get(1, "key"));
-    }
-
-    // Only 1 instance for that key.
-    validateNumberOfEntries(1, 1);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackSmallerVarintSize) {
-  do {
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    options.inplace_update_support = true;
-
-    options.env = env_;
-    options.write_buffer_size = 100000;
-    options.inplace_callback =
-      rocksdb::DBTestInPlaceUpdate::updateInPlaceSmallerVarintSize;
-    CreateAndReopenWithCF({"pikachu"}, options);
-
-    // Update key with values of smaller varint size
-    int numValues = 265;
-    ASSERT_OK(Put(1, "key", DummyString(numValues, 'a')));
-    ASSERT_EQ(DummyString(numValues, 'c'), Get(1, "key"));
-
-    for (int i = numValues; i > 0; i--) {
-      ASSERT_OK(Put(1, "key", DummyString(i, 'a')));
-      ASSERT_EQ(DummyString(1, 'b'), Get(1, "key"));
-    }
-
-    // Only 1 instance for that key.
-    validateNumberOfEntries(1, 1);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackLargeNewValue) {
-  do {
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    options.inplace_update_support = true;
-
-    options.env = env_;
-    options.write_buffer_size = 100000;
-    options.inplace_callback =
-      rocksdb::DBTestInPlaceUpdate::updateInPlaceLargerSize;
-    CreateAndReopenWithCF({"pikachu"}, options);
-
-    // Update key with values of larger size
-    int numValues = 10;
-    for (int i = 0; i < numValues; i++) {
-      ASSERT_OK(Put(1, "key", DummyString(i, 'a')));
-      ASSERT_EQ(DummyString(i, 'c'), Get(1, "key"));
-    }
-
-    // No inplace updates. All updates are puts with new seq number
-    // All 10 updates exist in the internal iterator
-    validateNumberOfEntries(numValues, 1);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBTestInPlaceUpdate, InPlaceUpdateCallbackNoAction) {
-  do {
-    Options options = CurrentOptions();
-    options.create_if_missing = true;
-    options.inplace_update_support = true;
-
-    options.env = env_;
-    options.write_buffer_size = 100000;
-    options.inplace_callback =
-      rocksdb::DBTestInPlaceUpdate::updateInPlaceNoAction;
-    CreateAndReopenWithCF({"pikachu"}, options);
-
-    // Callback function requests no actions from db
-    ASSERT_OK(Put(1, "key", DummyString(1, 'a')));
-    ASSERT_EQ(Get(1, "key"), "NOT_FOUND");
-  } while (ChangeCompactOptions());
-}
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}

db/db_io_failure_test.cc

@@ -1,259 +0,0 @@
-//  Copyright (c) 2011-present, Facebook, Inc.  All rights reserved.
-//  This source code is licensed under the BSD-style license found in the
-//  LICENSE file in the root directory of this source tree. An additional grant
-//  of patent rights can be found in the PATENTS file in the same directory.
-//
-// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
-// Use of this source code is governed by a BSD-style license that can be
-// found in the LICENSE file. See the AUTHORS file for names of contributors.
-
-#include "db/db_test_util.h"
-#include "port/stack_trace.h"
-
-namespace rocksdb {
-
-class DBIOFailureTest : public DBTestBase {
- public:
-  DBIOFailureTest() : DBTestBase("/db_io_failure_test") {}
-};
-
-#ifndef ROCKSDB_LITE
-// Check that number of files does not grow when writes are dropped
-TEST_F(DBIOFailureTest, DropWrites) {
-  do {
-    Options options = CurrentOptions();
-    options.env = env_;
-    options.paranoid_checks = false;
-    Reopen(options);
-
-    ASSERT_OK(Put("foo", "v1"));
-    ASSERT_EQ("v1", Get("foo"));
-    Compact("a", "z");
-    const size_t num_files = CountFiles();
-    // Force out-of-space errors
-    env_->drop_writes_.store(true, std::memory_order_release);
-    env_->sleep_counter_.Reset();
-    env_->no_sleep_ = true;
-    for (int i = 0; i < 5; i++) {
-      if (option_config_ != kUniversalCompactionMultiLevel &&
-          option_config_ != kUniversalSubcompactions) {
-        for (int level = 0; level < dbfull()->NumberLevels(); level++) {
-          if (level > 0 && level == dbfull()->NumberLevels() - 1) {
-            break;
-          }
-          dbfull()->TEST_CompactRange(level, nullptr, nullptr, nullptr,
-                                      true /* disallow trivial move */);
-        }
-      } else {
-        dbfull()->CompactRange(CompactRangeOptions(), nullptr, nullptr);
-      }
-    }
-
-    std::string property_value;
-    ASSERT_TRUE(db_->GetProperty("rocksdb.background-errors", &property_value));
-    ASSERT_EQ("5", property_value);
-
-    env_->drop_writes_.store(false, std::memory_order_release);
-    ASSERT_LT(CountFiles(), num_files + 3);
-
-    // Check that compaction attempts slept after errors
-    // TODO @krad: Figure out why ASSERT_EQ 5 keeps failing in certain compiler
-    // versions
-    ASSERT_GE(env_->sleep_counter_.Read(), 4);
-  } while (ChangeCompactOptions());
-}
-
-// Check background error counter bumped on flush failures.
-TEST_F(DBIOFailureTest, DropWritesFlush) {
-  do {
-    Options options = CurrentOptions();
-    options.env = env_;
-    options.max_background_flushes = 1;
-    Reopen(options);
-
-    ASSERT_OK(Put("foo", "v1"));
-    // Force out-of-space errors
-    env_->drop_writes_.store(true, std::memory_order_release);
-
-    std::string property_value;
-    // Background error count is 0 now.
-    ASSERT_TRUE(db_->GetProperty("rocksdb.background-errors", &property_value));
-    ASSERT_EQ("0", property_value);
-
-    dbfull()->TEST_FlushMemTable(true);
-
-    ASSERT_TRUE(db_->GetProperty("rocksdb.background-errors", &property_value));
-    ASSERT_EQ("1", property_value);
-
-    env_->drop_writes_.store(false, std::memory_order_release);
-  } while (ChangeCompactOptions());
-}
-#endif  // ROCKSDB_LITE
-
-// Check that CompactRange() returns failure if there is not enough space left
-// on device
-TEST_F(DBIOFailureTest, NoSpaceCompactRange) {
-  do {
-    Options options = CurrentOptions();
-    options.env = env_;
-    options.disable_auto_compactions = true;
-    Reopen(options);
-
-    // generate 5 tables
-    for (int i = 0; i < 5; ++i) {
-      ASSERT_OK(Put(Key(i), Key(i) + "v"));
-      ASSERT_OK(Flush());
-    }
-
-    // Force out-of-space errors
-    env_->no_space_.store(true, std::memory_order_release);
-
-    Status s = dbfull()->TEST_CompactRange(0, nullptr, nullptr, nullptr,
-                                           true /* disallow trivial move */);
-    ASSERT_TRUE(s.IsIOError());
-
-    env_->no_space_.store(false, std::memory_order_release);
-  } while (ChangeCompactOptions());
-}
-
-TEST_F(DBIOFailureTest, NonWritableFileSystem) {
-  do {
-    Options options = CurrentOptions();
-    options.write_buffer_size = 4096;
-    options.arena_block_size = 4096;
-    options.env = env_;
-    Reopen(options);
-    ASSERT_OK(Put("foo", "v1"));
-    env_->non_writeable_rate_.store(100);
-    std::string big(100000, 'x');
-    int errors = 0;
-    for (int i = 0; i < 20; i++) {
-      if (!Put("foo", big).ok()) {
-        errors++;
-        env_->SleepForMicroseconds(100000);
-      }
-    }
-    ASSERT_GT(errors, 0);
-    env_->non_writeable_rate_.store(0);
-  } while (ChangeCompactOptions());
-}
-
-#ifndef ROCKSDB_LITE
-TEST_F(DBIOFailureTest, ManifestWriteError) {
-  // Test for the following problem:
-  // (a) Compaction produces file F
-  // (b) Log record containing F is written to MANIFEST file, but Sync() fails
-  // (c) GC deletes F
-  // (d) After reopening DB, reads fail since deleted F is named in log record
-
-  // We iterate twice.  In the second iteration, everything is the
-  // same except the log record never makes it to the MANIFEST file.
-  for (int iter = 0; iter < 2; iter++) {
-    std::atomic<bool>* error_type = (iter == 0) ? &env_->manifest_sync_error_
-                                                : &env_->manifest_write_error_;
-
-    // Insert foo=>bar mapping
-    Options options = CurrentOptions();
-    options.env = env_;
-    options.create_if_missing = true;
-    options.error_if_exists = false;
-    options.paranoid_checks = true;
-    DestroyAndReopen(options);
-    ASSERT_OK(Put("foo", "bar"));
-    ASSERT_EQ("bar", Get("foo"));
-
-    // Memtable compaction (will succeed)
-    Flush();
-    ASSERT_EQ("bar", Get("foo"));
-    const int last = 2;
-    MoveFilesToLevel(2);
-    ASSERT_EQ(NumTableFilesAtLevel(last), 1);  // foo=>bar is now in last level
-
-    // Merging compaction (will fail)
-    error_type->store(true, std::memory_order_release);
-    dbfull()->TEST_CompactRange(last, nullptr, nullptr);  // Should fail
-    ASSERT_EQ("bar", Get("foo"));
-
-    error_type->store(false, std::memory_order_release);
-
-    // Since paranoid_checks=true, writes should fail
-    ASSERT_NOK(Put("foo2", "bar2"));
-
-    // Recovery: should not lose data
-    ASSERT_EQ("bar", Get("foo"));
-
-    // Try again with paranoid_checks=false
-    Close();
-    options.paranoid_checks = false;
-    Reopen(options);
-
-    // Merging compaction (will fail)
-    error_type->store(true, std::memory_order_release);
-    dbfull()->TEST_CompactRange(last, nullptr, nullptr);  // Should fail
-    ASSERT_EQ("bar", Get("foo"));
-
-    // Recovery: should not lose data
-    error_type->store(false, std::memory_order_release);
-    Reopen(options);
-    ASSERT_EQ("bar", Get("foo"));
-
-    // Since paranoid_checks=false, writes should succeed
-    ASSERT_OK(Put("foo2", "bar2"));
-    ASSERT_EQ("bar", Get("foo"));
-    ASSERT_EQ("bar2", Get("foo2"));
-  }
-}
-#endif  // ROCKSDB_LITE
-
-TEST_F(DBIOFailureTest, PutFailsParanoid) {
-  // Test the following:
-  // (a) A random put fails in paranoid mode (simulate by sync fail)
-  // (b) All other puts have to fail, even if writes would succeed
-  // (c) All of that should happen ONLY if paranoid_checks = true
-
-  Options options = CurrentOptions();
-  options.env = env_;
-  options.create_if_missing = true;
-  options.error_if_exists = false;
-  options.paranoid_checks = true;
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-  Status s;
-
-  ASSERT_OK(Put(1, "foo", "bar"));
-  ASSERT_OK(Put(1, "foo1", "bar1"));
-  // simulate error
-  env_->log_write_error_.store(true, std::memory_order_release);
-  s = Put(1, "foo2", "bar2");
-  ASSERT_TRUE(!s.ok());
-  env_->log_write_error_.store(false, std::memory_order_release);
-  s = Put(1, "foo3", "bar3");
-  // the next put should fail, too
-  ASSERT_TRUE(!s.ok());
-  // but we're still able to read
-  ASSERT_EQ("bar", Get(1, "foo"));
-
-  // do the same thing with paranoid checks off
-  options.paranoid_checks = false;
-  DestroyAndReopen(options);
-  CreateAndReopenWithCF({"pikachu"}, options);
-
-  ASSERT_OK(Put(1, "foo", "bar"));
-  ASSERT_OK(Put(1, "foo1", "bar1"));
-  // simulate error
-  env_->log_write_error_.store(true, std::memory_order_release);
-  s = Put(1, "foo2", "bar2");
-  ASSERT_TRUE(!s.ok());
-  env_->log_write_error_.store(false, std::memory_order_release);
-  s = Put(1, "foo3", "bar3");
-  // the next put should NOT fail
-  ASSERT_TRUE(s.ok());
-}
-
-}  // namespace rocksdb
-
-int main(int argc, char** argv) {
-  rocksdb::port::InstallStackTraceHandler();
-  ::testing::InitGoogleTest(&argc, argv);
-  return RUN_ALL_TESTS();
-}