1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
|
/**
* Copyright (C) 2018-present MongoDB, Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the Server Side Public License, version 1,
* as published by MongoDB, Inc.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* Server Side Public License for more details.
*
* You should have received a copy of the Server Side Public License
* along with this program. If not, see
* <http://www.mongodb.com/licensing/server-side-public-license>.
*
* As a special exception, the copyright holders give permission to link the
* code of portions of this program with the OpenSSL library under certain
* conditions as described in each individual source file and distribute
* linked combinations including the program with the OpenSSL library. You
* must comply with the Server Side Public License in all respects for
* all of the code used other than as permitted herein. If you modify file(s)
* with this exception, you may extend this exception to your version of the
* file(s), but you are not obligated to do so. If you do not wish to do so,
* delete this exception statement from your version. If you delete this
* exception statement from all source files in the program, then also delete
* it in the license file.
*/
#pragma once
#include <boost/optional.hpp>
#include "mongo/db/storage/wiredtiger/wiredtiger_record_store.h"
#include "mongo/platform/atomic_word.h"
#include "mongo/stdx/condition_variable.h"
#include "mongo/stdx/mutex.h"
namespace mongo {
class OperationContext;
class RecordId;
// Keep "milestones" against the oplog to efficiently remove the old records when the collection
// grows beyond its desired maximum size.
class WiredTigerRecordStore::OplogStones {
public:
struct Stone {
int64_t records; // Approximate number of records in a chunk of the oplog.
int64_t bytes; // Approximate size of records in a chunk of the oplog.
RecordId lastRecord; // RecordId of the last record in a chunk of the oplog.
};
OplogStones(OperationContext* opCtx, WiredTigerRecordStore* rs);
bool isDead();
void kill();
bool hasExcessStones_inlock() const {
int64_t total_bytes = 0;
for (std::deque<OplogStones::Stone>::const_iterator it = _stones.begin();
it != _stones.end();
++it) {
total_bytes += it->bytes;
}
return total_bytes > _rs->cappedMaxSize();
}
void awaitHasExcessStonesOrDead();
boost::optional<OplogStones::Stone> peekOldestStoneIfNeeded() const;
void popOldestStone();
void createNewStoneIfNeeded(RecordId lastRecord);
void updateCurrentStoneAfterInsertOnCommit(OperationContext* opCtx,
int64_t bytesInserted,
RecordId highestInserted,
int64_t countInserted);
void clearStonesOnCommit(OperationContext* opCtx);
// Updates the metadata about the oplog stones after a rollback occurs.
void updateStonesAfterCappedTruncateAfter(int64_t recordsRemoved,
int64_t bytesRemoved,
RecordId firstRemovedId);
// Resize oplog size
void adjust(int64_t maxSize);
// The start point of where to truncate next. Used by the background reclaim thread to
// efficiently truncate records with WiredTiger by skipping over tombstones, etc.
RecordId firstRecord;
//
// The following methods are public only for use in tests.
//
size_t numStones() const {
stdx::lock_guard<stdx::mutex> lk(_mutex);
return _stones.size();
}
int64_t currentBytes() const {
return _currentBytes.load();
}
int64_t currentRecords() const {
return _currentRecords.load();
}
void setMinBytesPerStone(int64_t size);
private:
class InsertChange;
class TruncateChange;
void _calculateStones(OperationContext* opCtx, size_t size);
void _calculateStonesByScanning(OperationContext* opCtx);
void _calculateStonesBySampling(OperationContext* opCtx,
int64_t estRecordsPerStone,
int64_t estBytesPerStone);
void _pokeReclaimThreadIfNeeded();
static const uint64_t kRandomSamplesPerStone = 10;
WiredTigerRecordStore* _rs;
stdx::mutex _oplogReclaimMutex;
stdx::condition_variable _oplogReclaimCv;
// True if '_rs' has been destroyed, e.g. due to repairDatabase being called on the "local"
// database, and false otherwise.
bool _isDead = false;
// Minimum number of bytes the stone being filled should contain before it gets added to the
// deque of oplog stones.
int64_t _minBytesPerStone;
AtomicInt64 _currentRecords; // Number of records in the stone being filled.
AtomicInt64 _currentBytes; // Number of bytes in the stone being filled.
mutable stdx::mutex _mutex; // Protects against concurrent access to the deque of oplog stones.
std::deque<OplogStones::Stone> _stones; // front = oldest, back = newest.
};
} // namespace mongo
|
