d1b74b0c82
Summary: Update Compaction/Flush to support WritePreparedTxnDB: Add SnapshotChecker which is a proxy to query WritePreparedTxnDB::IsInSnapshot. Pass SnapshotChecker to DBImpl on WritePreparedTxnDB open. CompactionIterator use it to check if a key has been committed and if it is visible to a snapshot. In CompactionIterator: * check if key has been committed. If not, output uncommitted keys AS-IS. * use SnapshotChecker to check if key is visible to a snapshot when in need. * do not output key with seq = 0 if the key is not committed. Closes https://github.com/facebook/rocksdb/pull/2926 Differential Revision: D5902907 Pulled By: yiwu-arbug fbshipit-source-id: 945e037fdf0aa652dc5ba0ad879461040baa0320
113 lines
3.6 KiB
C++
113 lines
3.6 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).
|
|
//
|
|
// 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/column_family.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/snapshot_impl.h"
|
|
#include "db/version_edit.h"
|
|
#include "db/write_controller.h"
|
|
#include "db/write_thread.h"
|
|
#include "monitoring/instrumented_mutex.h"
|
|
#include "options/db_options.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/stop_watch.h"
|
|
#include "util/thread_local.h"
|
|
|
|
namespace rocksdb {
|
|
|
|
class MemTable;
|
|
class SnapshotChecker;
|
|
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 ImmutableDBOptions& 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,
|
|
SnapshotChecker* snapshot_checker, JobContext* job_context,
|
|
LogBuffer* log_buffer, Directory* db_directory,
|
|
Directory* output_file_directory, CompressionType output_compression,
|
|
Statistics* stats, EventLogger* event_logger, bool measure_io_stats);
|
|
|
|
~FlushJob();
|
|
|
|
// Require db_mutex held.
|
|
// Once PickMemTable() is called, either Run() or Cancel() has to be called.
|
|
void PickMemTable();
|
|
Status Run(FileMetaData* file_meta = nullptr);
|
|
void Cancel();
|
|
TableProperties GetTableProperties() const { return table_properties_; }
|
|
|
|
private:
|
|
void ReportStartedFlush();
|
|
void ReportFlushInputSize(const autovector<MemTable*>& mems);
|
|
void RecordFlushIOStats();
|
|
Status WriteLevel0Table();
|
|
const std::string& dbname_;
|
|
ColumnFamilyData* cfd_;
|
|
const ImmutableDBOptions& 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_;
|
|
SnapshotChecker* snapshot_checker_;
|
|
JobContext* job_context_;
|
|
LogBuffer* log_buffer_;
|
|
Directory* db_directory_;
|
|
Directory* output_file_directory_;
|
|
CompressionType output_compression_;
|
|
Statistics* stats_;
|
|
EventLogger* event_logger_;
|
|
TableProperties table_properties_;
|
|
bool measure_io_stats_;
|
|
|
|
// Variables below are set by PickMemTable():
|
|
FileMetaData meta_;
|
|
autovector<MemTable*> mems_;
|
|
VersionEdit* edit_;
|
|
Version* base_;
|
|
bool pick_memtable_called;
|
|
};
|
|
|
|
} // namespace rocksdb
|