3bfd3d39a3
Summary: Currently, transactions can fail even if there is no actual write conflict. This is due to relying on only the memtables to check for write-conflicts. Users have to tune memtable settings to try to avoid this, but it's hard to figure out exactly how to tune these settings. With this diff, TransactionDB will use both memtables and SST files to determine if there are any write conflicts. This relies on the fact that BlockBasedTable stores sequence numbers for all writes that happen after any open snapshot. Also, D50295 is needed to prevent SingleDelete from disappearing writes (the TODOs in this test code will be fixed once the other diff is approved and merged). Note that Optimistic transactions will still rely on tuning memtable settings as we do not want to read from SST while on the write thread. Also, memtable settings can still be used to reduce how often TransactionDB needs to read SST files. Test Plan: unit tests, db bench Reviewers: rven, yhchiang, kradhakrishnan, IslamAbdelRahman, sdong Reviewed By: sdong Subscribers: dhruba, leveldb, yoshinorim Differential Revision: https://reviews.facebook.net/D50475
99 lines
3.2 KiB
C++
99 lines
3.2 KiB
C++
// 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) 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 <limits>
|
|
#include <set>
|
|
#include <utility>
|
|
#include <vector>
|
|
#include <string>
|
|
|
|
#include "db/dbformat.h"
|
|
#include "db/column_family.h"
|
|
#include "db/log_writer.h"
|
|
#include "db/memtable_list.h"
|
|
#include "db/snapshot_impl.h"
|
|
#include "db/version_edit.h"
|
|
#include "port/port.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/instrumented_mutex.h"
|
|
#include "util/stop_watch.h"
|
|
#include "util/thread_local.h"
|
|
#include "db/internal_stats.h"
|
|
#include "db/write_controller.h"
|
|
#include "db/flush_scheduler.h"
|
|
#include "db/write_thread.h"
|
|
#include "db/job_context.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
class MemTable;
|
|
class TableCache;
|
|
class Version;
|
|
class VersionEdit;
|
|
class VersionSet;
|
|
class Arena;
|
|
|
|
class FlushJob {
|
|
public:
|
|
// TODO(icanadi) make effort to reduce number of parameters here
|
|
// IMPORTANT: mutable_cf_options needs to be alive while FlushJob is alive
|
|
FlushJob(const std::string& dbname, ColumnFamilyData* cfd,
|
|
const DBOptions& db_options,
|
|
const MutableCFOptions& mutable_cf_options,
|
|
const EnvOptions& env_options, VersionSet* versions,
|
|
InstrumentedMutex* db_mutex, std::atomic<bool>* shutting_down,
|
|
std::vector<SequenceNumber> existing_snapshots,
|
|
SequenceNumber earliest_write_conflict_snapshot,
|
|
JobContext* job_context, LogBuffer* log_buffer,
|
|
Directory* db_directory, Directory* output_file_directory,
|
|
CompressionType output_compression, Statistics* stats,
|
|
EventLogger* event_logger);
|
|
|
|
~FlushJob();
|
|
|
|
Status Run(FileMetaData* file_meta = nullptr);
|
|
TableProperties GetTableProperties() const { return table_properties_; }
|
|
|
|
private:
|
|
void ReportStartedFlush();
|
|
void ReportFlushInputSize(const autovector<MemTable*>& mems);
|
|
void RecordFlushIOStats();
|
|
Status WriteLevel0Table(const autovector<MemTable*>& mems, VersionEdit* edit,
|
|
FileMetaData* meta);
|
|
const std::string& dbname_;
|
|
ColumnFamilyData* cfd_;
|
|
const DBOptions& db_options_;
|
|
const MutableCFOptions& mutable_cf_options_;
|
|
const EnvOptions& env_options_;
|
|
VersionSet* versions_;
|
|
InstrumentedMutex* db_mutex_;
|
|
std::atomic<bool>* shutting_down_;
|
|
std::vector<SequenceNumber> existing_snapshots_;
|
|
SequenceNumber earliest_write_conflict_snapshot_;
|
|
JobContext* job_context_;
|
|
LogBuffer* log_buffer_;
|
|
Directory* db_directory_;
|
|
Directory* output_file_directory_;
|
|
CompressionType output_compression_;
|
|
Statistics* stats_;
|
|
EventLogger* event_logger_;
|
|
TableProperties table_properties_;
|
|
};
|
|
|
|
} // namespace rocksdb
|