f383641a1d
Summary: Performing unordered writes in rocksdb when unordered_write option is set to true. When enabled the writes to memtable are done without joining any write thread. This offers much higher write throughput since the upcoming writes would not have to wait for the slowest memtable write to finish. The tradeoff is that the writes visible to a snapshot might change over time. If the application cannot tolerate that, it should implement its own mechanisms to work around that. Using TransactionDB with WRITE_PREPARED write policy is one way to achieve that. Doing so increases the max throughput by 2.2x without however compromising the snapshot guarantees. The patch is prepared based on an original by siying Existing unit tests are extended to include unordered_write option. Benchmark Results: ``` TEST_TMPDIR=/dev/shm/ ./db_bench_unordered --benchmarks=fillrandom --threads=32 --num=10000000 -max_write_buffer_number=16 --max_background_jobs=64 --batch_size=8 --writes=3000000 -level0_file_num_compaction_trigger=99999 --level0_slowdown_writes_trigger=99999 --level0_stop_writes_trigger=99999 -enable_pipelined_write=false -disable_auto_compactions --unordered_write=1 ``` With WAL - Vanilla RocksDB: 78.6 MB/s - WRITER_PREPARED with unordered_write: 177.8 MB/s (2.2x) - unordered_write: 368.9 MB/s (4.7x with relaxed snapshot guarantees) Without WAL - Vanilla RocksDB: 111.3 MB/s - WRITER_PREPARED with unordered_write: 259.3 MB/s MB/s (2.3x) - unordered_write: 645.6 MB/s (5.8x with relaxed snapshot guarantees) - WRITER_PREPARED with unordered_write disable concurrency control: 185.3 MB/s MB/s (2.35x) Limitations: - The feature is not yet extended to `max_successive_merges` > 0. The feature is also incompatible with `enable_pipelined_write` = true as well as with `allow_concurrent_memtable_write` = false. Pull Request resolved: https://github.com/facebook/rocksdb/pull/5218 Differential Revision: D15219029 Pulled By: maysamyabandeh fbshipit-source-id: 38f2abc4af8780148c6128acdba2b3227bc81759
112 lines
3.2 KiB
C++
112 lines
3.2 KiB
C++
// Copyright (c) 2011-present, Facebook, Inc. All rights reserved.
|
|
// This source code is licensed under both the GPLv2 (found in the
|
|
// COPYING file in the root directory) and Apache 2.0 License
|
|
// (found in the LICENSE.Apache file in the root directory).
|
|
|
|
#pragma once
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
#include "rocksdb/options.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
struct ImmutableDBOptions {
|
|
ImmutableDBOptions();
|
|
explicit ImmutableDBOptions(const DBOptions& options);
|
|
|
|
void Dump(Logger* log) const;
|
|
|
|
bool create_if_missing;
|
|
bool create_missing_column_families;
|
|
bool error_if_exists;
|
|
bool paranoid_checks;
|
|
Env* env;
|
|
std::shared_ptr<RateLimiter> rate_limiter;
|
|
std::shared_ptr<SstFileManager> sst_file_manager;
|
|
std::shared_ptr<Logger> info_log;
|
|
InfoLogLevel info_log_level;
|
|
int max_file_opening_threads;
|
|
std::shared_ptr<Statistics> statistics;
|
|
bool use_fsync;
|
|
std::vector<DbPath> db_paths;
|
|
std::string db_log_dir;
|
|
std::string wal_dir;
|
|
uint32_t max_subcompactions;
|
|
int max_background_flushes;
|
|
size_t max_log_file_size;
|
|
size_t log_file_time_to_roll;
|
|
size_t keep_log_file_num;
|
|
size_t recycle_log_file_num;
|
|
uint64_t max_manifest_file_size;
|
|
int table_cache_numshardbits;
|
|
uint64_t wal_ttl_seconds;
|
|
uint64_t wal_size_limit_mb;
|
|
size_t manifest_preallocation_size;
|
|
bool allow_mmap_reads;
|
|
bool allow_mmap_writes;
|
|
bool use_direct_reads;
|
|
bool use_direct_io_for_flush_and_compaction;
|
|
bool allow_fallocate;
|
|
bool is_fd_close_on_exec;
|
|
bool advise_random_on_open;
|
|
size_t db_write_buffer_size;
|
|
std::shared_ptr<WriteBufferManager> write_buffer_manager;
|
|
DBOptions::AccessHint access_hint_on_compaction_start;
|
|
bool new_table_reader_for_compaction_inputs;
|
|
size_t random_access_max_buffer_size;
|
|
bool use_adaptive_mutex;
|
|
std::vector<std::shared_ptr<EventListener>> listeners;
|
|
bool enable_thread_tracking;
|
|
bool enable_pipelined_write;
|
|
bool unordered_write;
|
|
bool allow_concurrent_memtable_write;
|
|
bool enable_write_thread_adaptive_yield;
|
|
uint64_t write_thread_max_yield_usec;
|
|
uint64_t write_thread_slow_yield_usec;
|
|
bool skip_stats_update_on_db_open;
|
|
WALRecoveryMode wal_recovery_mode;
|
|
bool allow_2pc;
|
|
std::shared_ptr<Cache> row_cache;
|
|
#ifndef ROCKSDB_LITE
|
|
WalFilter* wal_filter;
|
|
#endif // ROCKSDB_LITE
|
|
bool fail_if_options_file_error;
|
|
bool dump_malloc_stats;
|
|
bool avoid_flush_during_recovery;
|
|
bool allow_ingest_behind;
|
|
bool preserve_deletes;
|
|
bool two_write_queues;
|
|
bool manual_wal_flush;
|
|
bool atomic_flush;
|
|
bool avoid_unnecessary_blocking_io;
|
|
};
|
|
|
|
struct MutableDBOptions {
|
|
MutableDBOptions();
|
|
explicit MutableDBOptions(const MutableDBOptions& options) = default;
|
|
explicit MutableDBOptions(const DBOptions& options);
|
|
|
|
void Dump(Logger* log) const;
|
|
|
|
int max_background_jobs;
|
|
int base_background_compactions;
|
|
int max_background_compactions;
|
|
bool avoid_flush_during_shutdown;
|
|
size_t writable_file_max_buffer_size;
|
|
uint64_t delayed_write_rate;
|
|
uint64_t max_total_wal_size;
|
|
uint64_t delete_obsolete_files_period_micros;
|
|
unsigned int stats_dump_period_sec;
|
|
unsigned int stats_persist_period_sec;
|
|
size_t stats_history_buffer_size;
|
|
int max_open_files;
|
|
uint64_t bytes_per_sync;
|
|
uint64_t wal_bytes_per_sync;
|
|
bool strict_bytes_per_sync;
|
|
size_t compaction_readahead_size;
|
|
};
|
|
|
|
} // namespace rocksdb
|