mirror of
https://github.com/facebook/rocksdb.git
synced 2024-11-27 02:44:18 +00:00
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
77 lines
2.5 KiB
C++
77 lines
2.5 KiB
C++
// Copyright (c) 2014, 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 "db/merge_context.h"
|
|
#include "rocksdb/env.h"
|
|
#include "rocksdb/types.h"
|
|
|
|
namespace rocksdb {
|
|
class MergeContext;
|
|
|
|
class GetContext {
|
|
public:
|
|
enum GetState {
|
|
kNotFound,
|
|
kFound,
|
|
kDeleted,
|
|
kCorrupt,
|
|
kMerge // saver contains the current merge result (the operands)
|
|
};
|
|
|
|
GetContext(const Comparator* ucmp, const MergeOperator* merge_operator,
|
|
Logger* logger, Statistics* statistics, GetState init_state,
|
|
const Slice& user_key, std::string* ret_value, bool* value_found,
|
|
MergeContext* merge_context, Env* env,
|
|
SequenceNumber* seq = nullptr);
|
|
|
|
void MarkKeyMayExist();
|
|
|
|
// Records this key, value, and any meta-data (such as sequence number and
|
|
// state) into this GetContext.
|
|
//
|
|
// Returns True if more keys need to be read (due to merges) or
|
|
// False if the complete value has been found.
|
|
bool SaveValue(const ParsedInternalKey& parsed_key, const Slice& value);
|
|
|
|
// Simplified version of the previous function. Should only be used when we
|
|
// know that the operation is a Put.
|
|
void SaveValue(const Slice& value, SequenceNumber seq);
|
|
|
|
GetState State() const { return state_; }
|
|
|
|
// If a non-null string is passed, all the SaveValue calls will be
|
|
// logged into the string. The operations can then be replayed on
|
|
// another GetContext with replayGetContextLog.
|
|
void SetReplayLog(std::string* replay_log) { replay_log_ = replay_log; }
|
|
|
|
// Do we need to fetch the SequenceNumber for this key?
|
|
bool NeedToReadSequence() const { return (seq_ != nullptr); }
|
|
|
|
private:
|
|
const Comparator* ucmp_;
|
|
const MergeOperator* merge_operator_;
|
|
// the merge operations encountered;
|
|
Logger* logger_;
|
|
Statistics* statistics_;
|
|
|
|
GetState state_;
|
|
Slice user_key_;
|
|
std::string* value_;
|
|
bool* value_found_; // Is value set correctly? Used by KeyMayExist
|
|
MergeContext* merge_context_;
|
|
Env* env_;
|
|
// If a key is found, seq_ will be set to the SequenceNumber of most recent
|
|
// write to the key or kMaxSequenceNumber if unknown
|
|
SequenceNumber* seq_;
|
|
std::string* replay_log_;
|
|
};
|
|
|
|
void replayGetContextLog(const Slice& replay_log, const Slice& user_key,
|
|
GetContext* get_context);
|
|
|
|
} // namespace rocksdb
|