499ebb3ab5
Summary: Throughput: 46k tps in our sysbench settings (filling the details later) The idea is to have the simplest change that gives us a reasonable boost in 2PC throughput. Major design changes: 1. The WAL file internal buffer is not flushed after each write. Instead it is flushed before critical operations (WAL copy via fs) or when FlushWAL is called by MySQL. Flushing the WAL buffer is also protected via mutex_. 2. Use two sequence numbers: last seq, and last seq for write. Last seq is the last visible sequence number for reads. Last seq for write is the next sequence number that should be used to write to WAL/memtable. This allows to have a memtable write be in parallel to WAL writes. 3. BatchGroup is not used for writes. This means that we can have parallel writers which changes a major assumption in the code base. To accommodate for that i) allow only 1 WriteImpl that intends to write to memtable via mem_mutex_--which is fine since in 2PC almost all of the memtable writes come via group commit phase which is serial anyway, ii) make all the parts in the code base that assumed to be the only writer (via EnterUnbatched) to also acquire mem_mutex_, iii) stat updates are protected via a stat_mutex_. Note: the first commit has the approach figured out but is not clean. Submitting the PR anyway to get the early feedback on the approach. If we are ok with the approach I will go ahead with this updates: 0) Rebase with Yi's pipelining changes 1) Currently batching is disabled by default to make sure that it will be consistent with all unit tests. Will make this optional via a config. 2) A couple of unit tests are disabled. They need to be updated with the serial commit of 2PC taken into account. 3) Replacing BatchGroup with mem_mutex_ got a bit ugly as it requires releasing mutex_ beforehand (the same way EnterUnbatched does). This needs to be cleaned up. Closes https://github.com/facebook/rocksdb/pull/2345 Differential Revision: D5210732 Pulled By: maysamyabandeh fbshipit-source-id: 78653bd95a35cd1e831e555e0e57bdfd695355a4
105 lines
3.1 KiB
C++
105 lines
3.1 KiB
C++
// 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 <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 compaction_readahead_size;
|
|
size_t random_access_max_buffer_size;
|
|
size_t writable_file_max_buffer_size;
|
|
bool use_adaptive_mutex;
|
|
uint64_t bytes_per_sync;
|
|
uint64_t wal_bytes_per_sync;
|
|
std::vector<std::shared_ptr<EventListener>> listeners;
|
|
bool enable_thread_tracking;
|
|
bool enable_pipelined_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 concurrent_prepare;
|
|
bool manual_wal_flush;
|
|
};
|
|
|
|
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;
|
|
uint64_t delayed_write_rate;
|
|
uint64_t max_total_wal_size;
|
|
uint64_t delete_obsolete_files_period_micros;
|
|
unsigned int stats_dump_period_sec;
|
|
int max_open_files;
|
|
};
|
|
|
|
} // namespace rocksdb
|