rocksdb/file/filename.h

192 lines
7.8 KiB
C
Raw Normal View History

// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root directory).
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
//
// File names used by DB code
#pragma once
#include <stdint.h>
#include <string>
#include <unordered_map>
#include <vector>
#include "options/db_options.h"
#include "port/port.h"
#include "rocksdb/file_system.h"
#include "rocksdb/options.h"
#include "rocksdb/slice.h"
#include "rocksdb/status.h"
#include "rocksdb/transaction_log.h"
namespace ROCKSDB_NAMESPACE {
class Env;
class Directory;
class SystemClock;
class WritableFileWriter;
#ifdef OS_WIN
Add (Live)FileStorageInfo API (#8968) Summary: New classes FileStorageInfo and LiveFileStorageInfo and 'experimental' function DB::GetLiveFilesStorageInfo, which is intended to largely replace several fragmented DB functions needed to create checkpoints and backups. This function is now used to create checkpoints and backups, because it fixes many (probably not all) of the prior complexities of checkpoint not having atomic access to DB metadata. This also ensures strong functional test coverage of the new API. Specifically, much of the old CheckpointImpl::CreateCustomCheckpoint has been migrated to and updated in DBImpl::GetLiveFilesStorageInfo, with the former now calling the latter. Also, the class FileStorageInfo in metadata.h compatibly replaces BackupFileInfo and serves as a new base class for SstFileMetaData. Some old fields of SstFileMetaData are still provided (for now) but deprecated. Although FileStorageInfo::directory is accurate when using db_paths and/or cf_paths, these have never been supported by Checkpoint nor BackupEngine and still are not. This change does now detect these cases and return NotSupported when appropriate. (More work needed for support.) Somehow this change broke ProgressCallbackDuringBackup, but the progress_callback logic was dubious to begin with because it would call the callback based on copy buffer size, not size actually copied. Logic and test updated to track size actually copied per-thread. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8968 Test Plan: tests updated. DB::GetLiveFilesStorageInfo mostly tested by use in CheckpointImpl. DBTest.SnapshotFiles updated to also test GetLiveFilesStorageInfo, including reading the data after DB close. Added CheckpointTest.CheckpointWithDbPath (NotSupported). Reviewed By: siying Differential Revision: D31242045 Pulled By: pdillinger fbshipit-source-id: b183d1ce9799e220daaefd6b3b5365d98de676c0
2021-10-16 17:03:19 +00:00
constexpr char kFilePathSeparator = '\\';
#else
Add (Live)FileStorageInfo API (#8968) Summary: New classes FileStorageInfo and LiveFileStorageInfo and 'experimental' function DB::GetLiveFilesStorageInfo, which is intended to largely replace several fragmented DB functions needed to create checkpoints and backups. This function is now used to create checkpoints and backups, because it fixes many (probably not all) of the prior complexities of checkpoint not having atomic access to DB metadata. This also ensures strong functional test coverage of the new API. Specifically, much of the old CheckpointImpl::CreateCustomCheckpoint has been migrated to and updated in DBImpl::GetLiveFilesStorageInfo, with the former now calling the latter. Also, the class FileStorageInfo in metadata.h compatibly replaces BackupFileInfo and serves as a new base class for SstFileMetaData. Some old fields of SstFileMetaData are still provided (for now) but deprecated. Although FileStorageInfo::directory is accurate when using db_paths and/or cf_paths, these have never been supported by Checkpoint nor BackupEngine and still are not. This change does now detect these cases and return NotSupported when appropriate. (More work needed for support.) Somehow this change broke ProgressCallbackDuringBackup, but the progress_callback logic was dubious to begin with because it would call the callback based on copy buffer size, not size actually copied. Logic and test updated to track size actually copied per-thread. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8968 Test Plan: tests updated. DB::GetLiveFilesStorageInfo mostly tested by use in CheckpointImpl. DBTest.SnapshotFiles updated to also test GetLiveFilesStorageInfo, including reading the data after DB close. Added CheckpointTest.CheckpointWithDbPath (NotSupported). Reviewed By: siying Differential Revision: D31242045 Pulled By: pdillinger fbshipit-source-id: b183d1ce9799e220daaefd6b3b5365d98de676c0
2021-10-16 17:03:19 +00:00
constexpr char kFilePathSeparator = '/';
#endif
// Return the name of the log file with the specified number
// in the db named by "dbname". The result will be prefixed with
// "dbname".
extern std::string LogFileName(const std::string& dbname, uint64_t number);
extern std::string LogFileName(uint64_t number);
extern std::string BlobFileName(uint64_t number);
extern std::string BlobFileName(const std::string& bdirname, uint64_t number);
extern std::string BlobFileName(const std::string& dbname,
const std::string& blob_dir, uint64_t number);
extern std::string ArchivalDirectory(const std::string& dbname);
// Return the name of the archived log file with the specified number
// in the db named by "dbname". The result will be prefixed with "dbname".
extern std::string ArchivedLogFileName(const std::string& dbname, uint64_t num);
extern std::string MakeTableFileName(const std::string& name, uint64_t number);
extern std::string MakeTableFileName(uint64_t number);
// Return the name of sstable with LevelDB suffix
// created from RocksDB sstable suffixed name
extern std::string Rocks2LevelTableFileName(const std::string& fullname);
// the reverse function of MakeTableFileName
// TODO(yhchiang): could merge this function with ParseFileName()
extern uint64_t TableFileNameToNumber(const std::string& name);
// Return the name of the sstable with the specified number
// in the db named by "dbname". The result will be prefixed with
// "dbname".
extern std::string TableFileName(const std::vector<DbPath>& db_paths,
uint64_t number, uint32_t path_id);
// Sufficient buffer size for FormatFileNumber.
const size_t kFormatFileNumberBufSize = 38;
extern void FormatFileNumber(uint64_t number, uint32_t path_id, char* out_buf,
size_t out_buf_size);
// Return the name of the descriptor file for the db named by
// "dbname" and the specified incarnation number. The result will be
// prefixed with "dbname".
extern std::string DescriptorFileName(const std::string& dbname,
uint64_t number);
Add (Live)FileStorageInfo API (#8968) Summary: New classes FileStorageInfo and LiveFileStorageInfo and 'experimental' function DB::GetLiveFilesStorageInfo, which is intended to largely replace several fragmented DB functions needed to create checkpoints and backups. This function is now used to create checkpoints and backups, because it fixes many (probably not all) of the prior complexities of checkpoint not having atomic access to DB metadata. This also ensures strong functional test coverage of the new API. Specifically, much of the old CheckpointImpl::CreateCustomCheckpoint has been migrated to and updated in DBImpl::GetLiveFilesStorageInfo, with the former now calling the latter. Also, the class FileStorageInfo in metadata.h compatibly replaces BackupFileInfo and serves as a new base class for SstFileMetaData. Some old fields of SstFileMetaData are still provided (for now) but deprecated. Although FileStorageInfo::directory is accurate when using db_paths and/or cf_paths, these have never been supported by Checkpoint nor BackupEngine and still are not. This change does now detect these cases and return NotSupported when appropriate. (More work needed for support.) Somehow this change broke ProgressCallbackDuringBackup, but the progress_callback logic was dubious to begin with because it would call the callback based on copy buffer size, not size actually copied. Logic and test updated to track size actually copied per-thread. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8968 Test Plan: tests updated. DB::GetLiveFilesStorageInfo mostly tested by use in CheckpointImpl. DBTest.SnapshotFiles updated to also test GetLiveFilesStorageInfo, including reading the data after DB close. Added CheckpointTest.CheckpointWithDbPath (NotSupported). Reviewed By: siying Differential Revision: D31242045 Pulled By: pdillinger fbshipit-source-id: b183d1ce9799e220daaefd6b3b5365d98de676c0
2021-10-16 17:03:19 +00:00
extern std::string DescriptorFileName(uint64_t number);
extern const std::string kCurrentFileName; // = "CURRENT"
// Return the name of the current file. This file contains the name
// of the current manifest file. The result will be prefixed with
// "dbname".
extern std::string CurrentFileName(const std::string& dbname);
// Return the name of the lock file for the db named by
// "dbname". The result will be prefixed with "dbname".
extern std::string LockFileName(const std::string& dbname);
// Return the name of a temporary file owned by the db named "dbname".
// The result will be prefixed with "dbname".
extern std::string TempFileName(const std::string& dbname, uint64_t number);
// A helper structure for prefix of info log names.
struct InfoLogPrefix {
char buf[260];
Slice prefix;
// Prefix with DB absolute path encoded
explicit InfoLogPrefix(bool has_log_dir, const std::string& db_absolute_path);
// Default Prefix
explicit InfoLogPrefix();
};
// Return the name of the info log file for "dbname".
extern std::string InfoLogFileName(const std::string& dbname,
const std::string& db_path = "",
const std::string& log_dir = "");
// Return the name of the old info log file for "dbname".
extern std::string OldInfoLogFileName(const std::string& dbname, uint64_t ts,
const std::string& db_path = "",
const std::string& log_dir = "");
Add (Live)FileStorageInfo API (#8968) Summary: New classes FileStorageInfo and LiveFileStorageInfo and 'experimental' function DB::GetLiveFilesStorageInfo, which is intended to largely replace several fragmented DB functions needed to create checkpoints and backups. This function is now used to create checkpoints and backups, because it fixes many (probably not all) of the prior complexities of checkpoint not having atomic access to DB metadata. This also ensures strong functional test coverage of the new API. Specifically, much of the old CheckpointImpl::CreateCustomCheckpoint has been migrated to and updated in DBImpl::GetLiveFilesStorageInfo, with the former now calling the latter. Also, the class FileStorageInfo in metadata.h compatibly replaces BackupFileInfo and serves as a new base class for SstFileMetaData. Some old fields of SstFileMetaData are still provided (for now) but deprecated. Although FileStorageInfo::directory is accurate when using db_paths and/or cf_paths, these have never been supported by Checkpoint nor BackupEngine and still are not. This change does now detect these cases and return NotSupported when appropriate. (More work needed for support.) Somehow this change broke ProgressCallbackDuringBackup, but the progress_callback logic was dubious to begin with because it would call the callback based on copy buffer size, not size actually copied. Logic and test updated to track size actually copied per-thread. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8968 Test Plan: tests updated. DB::GetLiveFilesStorageInfo mostly tested by use in CheckpointImpl. DBTest.SnapshotFiles updated to also test GetLiveFilesStorageInfo, including reading the data after DB close. Added CheckpointTest.CheckpointWithDbPath (NotSupported). Reviewed By: siying Differential Revision: D31242045 Pulled By: pdillinger fbshipit-source-id: b183d1ce9799e220daaefd6b3b5365d98de676c0
2021-10-16 17:03:19 +00:00
extern const std::string kOptionsFileNamePrefix; // = "OPTIONS-"
extern const std::string kTempFileNameSuffix; // = "dbtmp"
// Return a options file name given the "dbname" and file number.
// Format: OPTIONS-[number].dbtmp
extern std::string OptionsFileName(const std::string& dbname,
uint64_t file_num);
Add (Live)FileStorageInfo API (#8968) Summary: New classes FileStorageInfo and LiveFileStorageInfo and 'experimental' function DB::GetLiveFilesStorageInfo, which is intended to largely replace several fragmented DB functions needed to create checkpoints and backups. This function is now used to create checkpoints and backups, because it fixes many (probably not all) of the prior complexities of checkpoint not having atomic access to DB metadata. This also ensures strong functional test coverage of the new API. Specifically, much of the old CheckpointImpl::CreateCustomCheckpoint has been migrated to and updated in DBImpl::GetLiveFilesStorageInfo, with the former now calling the latter. Also, the class FileStorageInfo in metadata.h compatibly replaces BackupFileInfo and serves as a new base class for SstFileMetaData. Some old fields of SstFileMetaData are still provided (for now) but deprecated. Although FileStorageInfo::directory is accurate when using db_paths and/or cf_paths, these have never been supported by Checkpoint nor BackupEngine and still are not. This change does now detect these cases and return NotSupported when appropriate. (More work needed for support.) Somehow this change broke ProgressCallbackDuringBackup, but the progress_callback logic was dubious to begin with because it would call the callback based on copy buffer size, not size actually copied. Logic and test updated to track size actually copied per-thread. Pull Request resolved: https://github.com/facebook/rocksdb/pull/8968 Test Plan: tests updated. DB::GetLiveFilesStorageInfo mostly tested by use in CheckpointImpl. DBTest.SnapshotFiles updated to also test GetLiveFilesStorageInfo, including reading the data after DB close. Added CheckpointTest.CheckpointWithDbPath (NotSupported). Reviewed By: siying Differential Revision: D31242045 Pulled By: pdillinger fbshipit-source-id: b183d1ce9799e220daaefd6b3b5365d98de676c0
2021-10-16 17:03:19 +00:00
extern std::string OptionsFileName(uint64_t file_num);
// Return a temp options file name given the "dbname" and file number.
// Format: OPTIONS-[number]
extern std::string TempOptionsFileName(const std::string& dbname,
uint64_t file_num);
// Return the name to use for a metadatabase. The result will be prefixed with
// "dbname".
extern std::string MetaDatabaseName(const std::string& dbname, uint64_t number);
Dbid feature Summary: Create a new type of file on startup if it doesn't already exist called DBID. This will store a unique number generated from boost library's uuid header file. The use-case is to identify the case of a db losing all its data and coming back up either empty or from an image(backup/live replica's recovery) the key point to note is that DBID is not stored in a backup or db snapshot It's preferable to use Boost for uuid because: 1) A non-standard way of generating uuid is not good 2) /proc/sys/kernel/random/uuid generates a uuid but only on linux environments and the solution would not be clean 3) c++ doesn't have any direct way to get a uuid 4) Boost is a very good library that was already having linkage in rocksdb from third-party Note: I had to update the TOOLCHAIN_REV in build files to get latest verison of boost from third-party as the older version had a bug. I had to put Wno-uninitialized in Makefile because boost-1.51 has an unitialized variable and rocksdb would not comiple otherwise. Latet open-source for boost is 1.54 but is not there in third-party. I have notified the concerned people in fbcode about it. @kailiu : While releasing to third-party, an additional dependency will need to be created for boost in TARGETS file. I can help identify. Test Plan: Expand db_test to test 2 cases 1) Restarting db with Id file present - verify that no change to Id 2)Restarting db with Id file deleted - verify that a different Id is there after reopen Also run make all check Reviewers: dhruba, haobo, kailiu, sdong Reviewed By: dhruba CC: leveldb Differential Revision: https://reviews.facebook.net/D13587
2013-10-18 21:50:54 +00:00
// Return the name of the Identity file which stores a unique number for the db
// that will get regenerated if the db loses all its data and is recreated fresh
// either from a backup-image or empty
extern std::string IdentityFileName(const std::string& dbname);
// If filename is a rocksdb file, store the type of the file in *type.
// The number encoded in the filename is stored in *number. If the
// filename was successfully parsed, returns true. Else return false.
// info_log_name_prefix is the path of info logs.
extern bool ParseFileName(const std::string& filename, uint64_t* number,
const Slice& info_log_name_prefix, FileType* type,
WalFileType* log_type = nullptr);
// Same as previous function, but skip info log files.
extern bool ParseFileName(const std::string& filename, uint64_t* number,
FileType* type, WalFileType* log_type = nullptr);
// Make the CURRENT file point to the descriptor file with the
Sync dir containing CURRENT after RenameFile on CURRENT as much as possible (#10573) Summary: **Context:** Below crash test revealed a bug that directory containing CURRENT file (short for `dir_contains_current_file` below) was not always get synced after a new CURRENT is created and being called with `RenameFile` as part of the creation. This bug exposes a risk that such un-synced directory containing the updated CURRENT can’t survive a host crash (e.g, power loss) hence get corrupted. This then will be followed by a recovery from a corrupted CURRENT that we don't want. The root-cause is that a nullptr `FSDirectory* dir_contains_current_file` sometimes gets passed-down to `SetCurrentFile()` hence in those case `dir_contains_current_file->FSDirectory::FsyncWithDirOptions()` will be skipped (which otherwise will internally call`Env/FS::SyncDic()` ) ``` ./db_stress --acquire_snapshot_one_in=10000 --adaptive_readahead=1 --allow_data_in_errors=True --avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=100000 --batch_protection_bytes_per_key=8 --block_size=16384 --bloom_bits=134.8015470676662 --bottommost_compression_type=disable --cache_size=8388608 --checkpoint_one_in=1000000 --checksum_type=kCRC32c --clear_column_family_one_in=0 --compact_files_one_in=1000000 --compact_range_one_in=1000000 --compaction_pri=2 --compaction_ttl=100 --compression_max_dict_buffer_bytes=511 --compression_max_dict_bytes=16384 --compression_type=zstd --compression_use_zstd_dict_trainer=1 --compression_zstd_max_train_bytes=65536 --continuous_verification_interval=0 --data_block_index_type=0 --db=$db --db_write_buffer_size=1048576 --delpercent=5 --delrangepercent=0 --destroy_db_initially=0 --disable_wal=0 --enable_compaction_filter=0 --enable_pipelined_write=1 --expected_values_dir=$exp --fail_if_options_file_error=1 --file_checksum_impl=none --flush_one_in=1000000 --get_current_wal_file_one_in=0 --get_live_files_one_in=1000000 --get_property_one_in=1000000 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=4 --ingest_external_file_one_in=0 --iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True --mark_for_compaction_one_file_in=10 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=10000 --max_key_len=3 --max_manifest_file_size=16384 --max_write_batch_group_size_bytes=64 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=0 --memtable_prefix_bloom_size_ratio=0.001 --memtable_protection_bytes_per_key=1 --memtable_whole_key_filtering=1 --mmap_read=1 --nooverwritepercent=1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=0 --open_write_fault_one_in=0 --ops_per_thread=100000000 --optimize_filters_for_memory=1 --paranoid_file_checks=1 --partition_pinning=2 --pause_background_one_in=1000000 --periodic_compaction_seconds=0 --prefix_size=5 --prefixpercent=5 --prepopulate_block_cache=1 --progress_reports=0 --read_fault_one_in=1000 --readpercent=45 --recycle_log_file_num=0 --reopen=0 --ribbon_starting_level=999 --secondary_cache_fault_one_in=32 --secondary_cache_uri=compressed_secondary_cache://capacity=8388608 --set_options_one_in=10000 --snapshot_hold_ops=100000 --sst_file_manager_bytes_per_sec=0 --sst_file_manager_bytes_per_truncate=0 --subcompactions=3 --sync_fault_injection=1 --target_file_size_base=2097 --target_file_size_multiplier=2 --test_batches_snapshots=1 --top_level_index_pinning=1 --use_full_merge_v1=1 --use_merge=1 --value_size_mult=32 --verify_checksum=1 --verify_checksum_one_in=1000000 --verify_db_one_in=100000 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=524288 --write_buffer_size=4194 --writepercent=35 ``` ``` stderr: WARNING: prefix_size is non-zero but memtablerep != prefix_hash db_stress: utilities/fault_injection_fs.cc:748: virtual rocksdb::IOStatus rocksdb::FaultInjectionTestFS::RenameFile(const std::string &, const std::string &, const rocksdb::IOOptions &, rocksdb::IODebugContext *): Assertion `tlist.find(tdn.second) == tlist.end()' failed.` ``` **Summary:** The PR ensured the non-test path pass down a non-null dir containing CURRENT (which is by current RocksDB assumption just db_dir) by doing the following: - Renamed `directory_to_fsync` as `dir_contains_current_file` in `SetCurrentFile()` to tighten the association between this directory and CURRENT file - Changed `SetCurrentFile()` API to require `dir_contains_current_file` being passed-in, instead of making it by default nullptr. - Because `SetCurrentFile()`'s `dir_contains_current_file` is passed down from `VersionSet::LogAndApply()` then `VersionSet::ProcessManifestWrites()` (i.e, think about this as a chain of 3 functions related to MANIFEST update), these 2 functions also got refactored to require `dir_contains_current_file` - Updated the non-test-path callers of these 3 functions to obtain and pass in non-nullptr `dir_contains_current_file`, which by current assumption of RocksDB, is the `FSDirectory* db_dir`. - `db_impl` path will obtain `DBImpl::directories_.getDbDir()` while others with no access to such `directories_` are obtained on the fly by creating such object `FileSystem::NewDirectory(..)` and manage it by unique pointers to ensure short life time. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10573 Test Plan: - `make check` - Passed the repro db_stress command - For future improvement, since we currently don't assert dir containing CURRENT to be non-nullptr due to https://github.com/facebook/rocksdb/pull/10573#pullrequestreview-1087698899, there is still chances that future developers mistakenly pass down nullptr dir containing CURRENT thus resulting skipped sync dir and cause the bug again. Therefore a smarter test (e.g, such as quoted from ajkr "(make) unsynced data loss to be dropping files corresponding to unsynced directory entries") is still needed. Reviewed By: ajkr Differential Revision: D39005886 Pulled By: hx235 fbshipit-source-id: 336fb9090d0cfa6ca3dd580db86268007dde7f5a
2022-08-30 00:35:21 +00:00
// specified number. On its success and when dir_contains_current_file is not
// nullptr, the function will fsync the directory containing the CURRENT file
// when
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
extern IOStatus SetCurrentFile(const WriteOptions& write_options,
FileSystem* fs, const std::string& dbname,
uint64_t descriptor_number,
Sync dir containing CURRENT after RenameFile on CURRENT as much as possible (#10573) Summary: **Context:** Below crash test revealed a bug that directory containing CURRENT file (short for `dir_contains_current_file` below) was not always get synced after a new CURRENT is created and being called with `RenameFile` as part of the creation. This bug exposes a risk that such un-synced directory containing the updated CURRENT can’t survive a host crash (e.g, power loss) hence get corrupted. This then will be followed by a recovery from a corrupted CURRENT that we don't want. The root-cause is that a nullptr `FSDirectory* dir_contains_current_file` sometimes gets passed-down to `SetCurrentFile()` hence in those case `dir_contains_current_file->FSDirectory::FsyncWithDirOptions()` will be skipped (which otherwise will internally call`Env/FS::SyncDic()` ) ``` ./db_stress --acquire_snapshot_one_in=10000 --adaptive_readahead=1 --allow_data_in_errors=True --avoid_unnecessary_blocking_io=0 --backup_max_size=104857600 --backup_one_in=100000 --batch_protection_bytes_per_key=8 --block_size=16384 --bloom_bits=134.8015470676662 --bottommost_compression_type=disable --cache_size=8388608 --checkpoint_one_in=1000000 --checksum_type=kCRC32c --clear_column_family_one_in=0 --compact_files_one_in=1000000 --compact_range_one_in=1000000 --compaction_pri=2 --compaction_ttl=100 --compression_max_dict_buffer_bytes=511 --compression_max_dict_bytes=16384 --compression_type=zstd --compression_use_zstd_dict_trainer=1 --compression_zstd_max_train_bytes=65536 --continuous_verification_interval=0 --data_block_index_type=0 --db=$db --db_write_buffer_size=1048576 --delpercent=5 --delrangepercent=0 --destroy_db_initially=0 --disable_wal=0 --enable_compaction_filter=0 --enable_pipelined_write=1 --expected_values_dir=$exp --fail_if_options_file_error=1 --file_checksum_impl=none --flush_one_in=1000000 --get_current_wal_file_one_in=0 --get_live_files_one_in=1000000 --get_property_one_in=1000000 --get_sorted_wal_files_one_in=0 --index_block_restart_interval=4 --ingest_external_file_one_in=0 --iterpercent=10 --key_len_percent_dist=1,30,69 --level_compaction_dynamic_level_bytes=True --mark_for_compaction_one_file_in=10 --max_background_compactions=20 --max_bytes_for_level_base=10485760 --max_key=10000 --max_key_len=3 --max_manifest_file_size=16384 --max_write_batch_group_size_bytes=64 --max_write_buffer_number=3 --max_write_buffer_size_to_maintain=0 --memtable_prefix_bloom_size_ratio=0.001 --memtable_protection_bytes_per_key=1 --memtable_whole_key_filtering=1 --mmap_read=1 --nooverwritepercent=1 --open_metadata_write_fault_one_in=0 --open_read_fault_one_in=0 --open_write_fault_one_in=0 --ops_per_thread=100000000 --optimize_filters_for_memory=1 --paranoid_file_checks=1 --partition_pinning=2 --pause_background_one_in=1000000 --periodic_compaction_seconds=0 --prefix_size=5 --prefixpercent=5 --prepopulate_block_cache=1 --progress_reports=0 --read_fault_one_in=1000 --readpercent=45 --recycle_log_file_num=0 --reopen=0 --ribbon_starting_level=999 --secondary_cache_fault_one_in=32 --secondary_cache_uri=compressed_secondary_cache://capacity=8388608 --set_options_one_in=10000 --snapshot_hold_ops=100000 --sst_file_manager_bytes_per_sec=0 --sst_file_manager_bytes_per_truncate=0 --subcompactions=3 --sync_fault_injection=1 --target_file_size_base=2097 --target_file_size_multiplier=2 --test_batches_snapshots=1 --top_level_index_pinning=1 --use_full_merge_v1=1 --use_merge=1 --value_size_mult=32 --verify_checksum=1 --verify_checksum_one_in=1000000 --verify_db_one_in=100000 --verify_sst_unique_id_in_manifest=1 --wal_bytes_per_sync=524288 --write_buffer_size=4194 --writepercent=35 ``` ``` stderr: WARNING: prefix_size is non-zero but memtablerep != prefix_hash db_stress: utilities/fault_injection_fs.cc:748: virtual rocksdb::IOStatus rocksdb::FaultInjectionTestFS::RenameFile(const std::string &, const std::string &, const rocksdb::IOOptions &, rocksdb::IODebugContext *): Assertion `tlist.find(tdn.second) == tlist.end()' failed.` ``` **Summary:** The PR ensured the non-test path pass down a non-null dir containing CURRENT (which is by current RocksDB assumption just db_dir) by doing the following: - Renamed `directory_to_fsync` as `dir_contains_current_file` in `SetCurrentFile()` to tighten the association between this directory and CURRENT file - Changed `SetCurrentFile()` API to require `dir_contains_current_file` being passed-in, instead of making it by default nullptr. - Because `SetCurrentFile()`'s `dir_contains_current_file` is passed down from `VersionSet::LogAndApply()` then `VersionSet::ProcessManifestWrites()` (i.e, think about this as a chain of 3 functions related to MANIFEST update), these 2 functions also got refactored to require `dir_contains_current_file` - Updated the non-test-path callers of these 3 functions to obtain and pass in non-nullptr `dir_contains_current_file`, which by current assumption of RocksDB, is the `FSDirectory* db_dir`. - `db_impl` path will obtain `DBImpl::directories_.getDbDir()` while others with no access to such `directories_` are obtained on the fly by creating such object `FileSystem::NewDirectory(..)` and manage it by unique pointers to ensure short life time. Pull Request resolved: https://github.com/facebook/rocksdb/pull/10573 Test Plan: - `make check` - Passed the repro db_stress command - For future improvement, since we currently don't assert dir containing CURRENT to be non-nullptr due to https://github.com/facebook/rocksdb/pull/10573#pullrequestreview-1087698899, there is still chances that future developers mistakenly pass down nullptr dir containing CURRENT thus resulting skipped sync dir and cause the bug again. Therefore a smarter test (e.g, such as quoted from ajkr "(make) unsynced data loss to be dropping files corresponding to unsynced directory entries") is still needed. Reviewed By: ajkr Differential Revision: D39005886 Pulled By: hx235 fbshipit-source-id: 336fb9090d0cfa6ca3dd580db86268007dde7f5a
2022-08-30 00:35:21 +00:00
FSDirectory* dir_contains_current_file);
Dbid feature Summary: Create a new type of file on startup if it doesn't already exist called DBID. This will store a unique number generated from boost library's uuid header file. The use-case is to identify the case of a db losing all its data and coming back up either empty or from an image(backup/live replica's recovery) the key point to note is that DBID is not stored in a backup or db snapshot It's preferable to use Boost for uuid because: 1) A non-standard way of generating uuid is not good 2) /proc/sys/kernel/random/uuid generates a uuid but only on linux environments and the solution would not be clean 3) c++ doesn't have any direct way to get a uuid 4) Boost is a very good library that was already having linkage in rocksdb from third-party Note: I had to update the TOOLCHAIN_REV in build files to get latest verison of boost from third-party as the older version had a bug. I had to put Wno-uninitialized in Makefile because boost-1.51 has an unitialized variable and rocksdb would not comiple otherwise. Latet open-source for boost is 1.54 but is not there in third-party. I have notified the concerned people in fbcode about it. @kailiu : While releasing to third-party, an additional dependency will need to be created for boost in TARGETS file. I can help identify. Test Plan: Expand db_test to test 2 cases 1) Restarting db with Id file present - verify that no change to Id 2)Restarting db with Id file deleted - verify that a different Id is there after reopen Also run make all check Reviewers: dhruba, haobo, kailiu, sdong Reviewed By: dhruba CC: leveldb Differential Revision: https://reviews.facebook.net/D13587
2013-10-18 21:50:54 +00:00
// Make the IDENTITY file for the db
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
extern Status SetIdentityFile(const WriteOptions& write_options, Env* env,
const std::string& dbname,
const std::string& db_id = {});
// Sync manifest file `file`.
extern IOStatus SyncManifest(const ImmutableDBOptions* db_options,
Group SST write in flush, compaction and db open with new stats (#11910) Summary: ## Context/Summary Similar to https://github.com/facebook/rocksdb/pull/11288, https://github.com/facebook/rocksdb/pull/11444, categorizing SST/blob file write according to different io activities allows more insight into the activity. For that, this PR does the following: - Tag different write IOs by passing down and converting WriteOptions to IOOptions - Add new SST_WRITE_MICROS histogram in WritableFileWriter::Append() and breakdown FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS Some related code refactory to make implementation cleaner: - Blob stats - Replace high-level write measurement with low-level WritableFileWriter::Append() measurement for BLOB_DB_BLOB_FILE_WRITE_MICROS. This is to make FILE_WRITE_{FLUSH|COMPACTION|DB_OPEN}_MICROS include blob file. As a consequence, this introduces some behavioral changes on it, see HISTORY and db bench test plan below for more info. - Fix bugs where BLOB_DB_BLOB_FILE_SYNCED/BLOB_DB_BLOB_FILE_BYTES_WRITTEN include file failed to sync and bytes failed to write. - Refactor WriteOptions constructor for easier construction with io_activity and rate_limiter_priority - Refactor DBImpl::~DBImpl()/BlobDBImpl::Close() to bypass thread op verification - Build table - TableBuilderOptions now includes Read/WriteOpitons so BuildTable() do not need to take these two variables - Replace the io_priority passed into BuildTable() with TableBuilderOptions::WriteOpitons::rate_limiter_priority. Similar for BlobFileBuilder. This parameter is used for dynamically changing file io priority for flush, see https://github.com/facebook/rocksdb/pull/9988?fbclid=IwAR1DtKel6c-bRJAdesGo0jsbztRtciByNlvokbxkV6h_L-AE9MACzqRTT5s for more - Update ThreadStatus::FLUSH_BYTES_WRITTEN to use io_activity to track flush IO in flush job and db open instead of io_priority ## Test ### db bench Flush ``` ./db_bench --statistics=1 --benchmarks=fillseq --num=100000 --write_buffer_size=100 rocksdb.sst.write.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.flush.micros P50 : 1.830863 P95 : 4.094720 P99 : 6.578947 P100 : 26.000000 COUNT : 7875 SUM : 20377 rocksdb.file.write.compaction.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.db.open.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 ``` compaction, db oopen ``` Setup: ./db_bench --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 rocksdb.sst.write.micros P50 : 2.675325 P95 : 9.578788 P99 : 18.780000 P100 : 314.000000 COUNT : 638 SUM : 3279 rocksdb.file.write.flush.micros P50 : 0.000000 P95 : 0.000000 P99 : 0.000000 P100 : 0.000000 COUNT : 0 SUM : 0 rocksdb.file.write.compaction.micros P50 : 2.757353 P95 : 9.610687 P99 : 19.316667 P100 : 314.000000 COUNT : 615 SUM : 3213 rocksdb.file.write.db.open.micros P50 : 2.055556 P95 : 3.925000 P99 : 9.000000 P100 : 9.000000 COUNT : 23 SUM : 66 ``` blob stats - just to make sure they aren't broken by this PR ``` Integrated Blob DB Setup: ./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench Run:./db_bench --enable_blob_files=1 --statistics=1 --benchmarks=compact --db=../db_bench --use_existing_db=1 pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 7.298246 P95 : 9.771930 P99 : 9.991813 P100 : 16.000000 COUNT : 235 SUM : 1600 rocksdb.blobdb.blob.file.synced COUNT : 1 rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 2.000000 P95 : 2.829360 P99 : 2.993779 P100 : 9.000000 COUNT : 707 SUM : 1614 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 1 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 34842 (stay the same) ``` ``` Stacked Blob DB Run: ./db_bench --use_blob_db=1 --statistics=1 --benchmarks=fillseq --num=10000 --disable_auto_compactions=1 -write_buffer_size=100 --db=../db_bench pre-PR: rocksdb.blobdb.blob.file.write.micros P50 : 12.808042 P95 : 19.674497 P99 : 28.539683 P100 : 51.000000 COUNT : 10000 SUM : 140876 rocksdb.blobdb.blob.file.synced COUNT : 8 rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 post-PR: rocksdb.blobdb.blob.file.write.micros P50 : 1.657370 P95 : 2.952175 P99 : 3.877519 P100 : 24.000000 COUNT : 30001 SUM : 67924 - COUNT is higher and values are smaller as it includes header and footer write - COUNT is 3X higher due to each Append() count as one post-PR, while in pre-PR, 3 Append()s counts as one. See https://github.com/facebook/rocksdb/pull/11910/files#diff-32b811c0a1c000768cfb2532052b44dc0b3bf82253f3eab078e15ff201a0dabfL157-L164 rocksdb.blobdb.blob.file.synced COUNT : 8 (stay the same) rocksdb.blobdb.blob.file.bytes.written COUNT : 1043445 (stay the same) ``` ### Rehearsal CI stress test Trigger 3 full runs of all our CI stress tests ### Performance Flush ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=ManualFlush/key_num:524288/per_key_size:256 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark; enable_statistics = true Pre-pr: avg 507515519.3 ns 497686074,499444327,500862543,501389862,502994471,503744435,504142123,504224056,505724198,506610393,506837742,506955122,507695561,507929036,508307733,508312691,508999120,509963561,510142147,510698091,510743096,510769317,510957074,511053311,511371367,511409911,511432960,511642385,511691964,511730908, Post-pr: avg 511971266.5 ns, regressed 0.88% 502744835,506502498,507735420,507929724,508313335,509548582,509994942,510107257,510715603,511046955,511352639,511458478,512117521,512317380,512766303,512972652,513059586,513804934,513808980,514059409,514187369,514389494,514447762,514616464,514622882,514641763,514666265,514716377,514990179,515502408, ``` Compaction ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_{pre|post}_pr --benchmark_filter=ManualCompaction/comp_style:0/max_data:134217728/per_key_size:256/enable_statistics:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 495346098.30 ns 492118301,493203526,494201411,494336607,495269217,495404950,496402598,497012157,497358370,498153846 Post-pr: avg 504528077.20, regressed 1.85%. "ManualCompaction" include flush so the isolated regression for compaction should be around 1.85-0.88 = 0.97% 502465338,502485945,502541789,502909283,503438601,504143885,506113087,506629423,507160414,507393007 ``` Put with WAL (in case passing WriteOptions slows down this path even without collecting SST write stats) ``` TEST_TMPDIR=/dev/shm ./db_basic_bench_pre_pr --benchmark_filter=DBPut/comp_style:0/max_data:107374182400/per_key_size:256/enable_statistics:1/wal:1 --benchmark_repetitions=1000 -- default: 1 thread is used to run benchmark Pre-pr: avg 3848.10 ns 3814,3838,3839,3848,3854,3854,3854,3860,3860,3860 Post-pr: avg 3874.20 ns, regressed 0.68% 3863,3867,3871,3874,3875,3877,3877,3877,3880,3881 ``` Pull Request resolved: https://github.com/facebook/rocksdb/pull/11910 Reviewed By: ajkr Differential Revision: D49788060 Pulled By: hx235 fbshipit-source-id: 79e73699cda5be3b66461687e5147c2484fc5eff
2023-12-29 23:29:23 +00:00
const WriteOptions& write_options,
WritableFileWriter* file);
// Return list of file names of info logs in `file_names`.
// The list only contains file name. The parent directory name is stored
// in `parent_dir`.
// `db_log_dir` should be the one as in options.db_log_dir
extern Status GetInfoLogFiles(const std::shared_ptr<FileSystem>& fs,
const std::string& db_log_dir,
const std::string& dbname,
std::string* parent_dir,
std::vector<std::string>* file_names);
extern std::string NormalizePath(const std::string& path);
} // namespace ROCKSDB_NAMESPACE