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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
|
// rocks_recovery_unit.cpp
/**
* Copyright (C) 2014 MongoDB Inc.
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License, version 3,
* as published by the Free Software Foundation.
*
* 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
* GNU Affero General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*
* 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 GNU Affero General 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.
*/
#define MONGO_LOG_DEFAULT_COMPONENT ::mongo::logger::LogComponent::kStorage
#include "mongo/db/storage/rocks/rocks_recovery_unit.h"
#include <rocksdb/comparator.h>
#include <rocksdb/db.h>
#include <rocksdb/iterator.h>
#include <rocksdb/slice.h>
#include <rocksdb/options.h>
#include <rocksdb/write_batch.h>
#include <rocksdb/utilities/write_batch_with_index.h>
#include "mongo/db/operation_context.h"
#include "mongo/util/log.h"
namespace mongo {
RocksRecoveryUnit::RocksRecoveryUnit(rocksdb::DB* db, bool defaultCommit)
: _db(db),
_defaultCommit(defaultCommit),
_writeBatch(),
_snapshot(NULL),
_destroyed(false) {}
RocksRecoveryUnit::~RocksRecoveryUnit() {
if (!_destroyed) {
destroy();
}
}
void RocksRecoveryUnit::beginUnitOfWork() {}
void RocksRecoveryUnit::commitUnitOfWork() {
invariant(!_destroyed);
if ( !_writeBatch ) {
// nothing to be committed
return;
}
rocksdb::Status status = _db->Write(rocksdb::WriteOptions(), _writeBatch->GetWriteBatch());
if ( !status.ok() ) {
log() << "uh oh: " << status.ToString();
invariant( !"rocks write batch commit failed" );
}
for (auto& change : _changes) {
change->commit();
delete change;
}
_changes.clear();
_writeBatch.reset();
if ( _snapshot ) {
_db->ReleaseSnapshot( _snapshot );
_snapshot = _db->GetSnapshot();
}
}
void RocksRecoveryUnit::endUnitOfWork() {}
bool RocksRecoveryUnit::awaitCommit() {
// TODO
return true;
}
void* RocksRecoveryUnit::writingPtr(void* data, size_t len) {
warning() << "RocksRecoveryUnit::writingPtr doesn't work";
return data;
}
void RocksRecoveryUnit::syncDataAndTruncateJournal() {
log() << "RocksRecoveryUnit::syncDataAndTruncateJournal() does nothing";
}
// lazily initialized because Recovery Units are sometimes initialized just for reading,
// which does not require write batches
rocksdb::WriteBatchWithIndex* RocksRecoveryUnit::writeBatch() {
if (!_writeBatch) {
// this assumes that default column family uses default comparator. change this if you
// change default column family's comparator
_writeBatch.reset(
new rocksdb::WriteBatchWithIndex(rocksdb::BytewiseComparator(), 0, true));
}
return _writeBatch.get();
}
void RocksRecoveryUnit::registerChange(Change* change) { _changes.emplace_back(change); }
void RocksRecoveryUnit::destroy() {
if (_defaultCommit) {
commitUnitOfWork();
}
if (_writeBatch && _writeBatch->GetWriteBatch()->Count() > 0) {
for (auto& change : _changes) {
change->rollback();
delete change;
}
}
releaseSnapshot();
_destroyed = true;
}
// XXX lazily initialized for now
// This is lazily initialized for simplicity so long as we still
// have database-level locking. If a method needs to access the snapshot,
// and it has not been initialized, then it knows it is the first
// method to access the snapshot, and can initialize it before using it.
const rocksdb::Snapshot* RocksRecoveryUnit::snapshot() {
if ( !_snapshot ) {
_snapshot = _db->GetSnapshot();
}
return _snapshot;
}
void RocksRecoveryUnit::releaseSnapshot() {
if (_snapshot) {
_db->ReleaseSnapshot(_snapshot);
_snapshot = nullptr;
}
}
rocksdb::Status RocksRecoveryUnit::Get(rocksdb::ColumnFamilyHandle* columnFamily,
const rocksdb::Slice& key, std::string* value) {
if (_writeBatch && _writeBatch->GetWriteBatch()->Count() > 0) {
boost::scoped_ptr<rocksdb::WBWIIterator> wb_iterator(
_writeBatch->NewIterator(columnFamily));
wb_iterator->Seek(key);
if (wb_iterator->Valid() && wb_iterator->Entry().key == key) {
const auto& entry = wb_iterator->Entry();
if (entry.type == rocksdb::WriteType::kDeleteRecord) {
return rocksdb::Status::NotFound();
}
// TODO avoid double copy
*value = std::string(entry.value.data(), entry.value.size());
return rocksdb::Status::OK();
}
}
rocksdb::ReadOptions options;
options.snapshot = snapshot();
return _db->Get(options, columnFamily, key, value);
}
rocksdb::Iterator* RocksRecoveryUnit::NewIterator(rocksdb::ColumnFamilyHandle* columnFamily) {
rocksdb::ReadOptions options;
options.snapshot = snapshot();
auto iterator = _db->NewIterator(options, columnFamily);
if (_writeBatch && _writeBatch->GetWriteBatch()->Count() > 0) {
iterator = _writeBatch->NewIteratorWithBase(columnFamily, iterator);
}
return iterator;
}
RocksRecoveryUnit* RocksRecoveryUnit::getRocksRecoveryUnit(OperationContext* opCtx) {
return dynamic_cast<RocksRecoveryUnit*>(opCtx->recoveryUnit());
}
}
|
