summaryrefslogtreecommitdiff
path: root/src/mongo/db/repl/collection_cloner.cpp
blob: 1f71fe762e7f07ce0d84531f40f1be48f4db6978 (plain)
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
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
/**
 *    Copyright (C) 2015 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::kReplication

#include "mongo/platform/basic.h"

#include "mongo/db/repl/collection_cloner.h"

#include "mongo/util/assert_util.h"
#include "mongo/util/log.h"
#include "mongo/util/mongoutils/str.h"

namespace mongo {
namespace repl {

CollectionCloner::CollectionCloner(ReplicationExecutor* executor,
                                   const HostAndPort& source,
                                   const NamespaceString& sourceNss,
                                   const CollectionOptions& options,
                                   const CallbackFn& onCompletion,
                                   StorageInterface* storageInterface)
    : _executor(executor),
      _source(source),
      _sourceNss(sourceNss),
      _destNss(_sourceNss),
      _options(options),
      _onCompletion(onCompletion),
      _storageInterface(storageInterface),
      _active(false),
      _listIndexesFetcher(_executor,
                          _source,
                          _sourceNss.db().toString(),
                          BSON("listIndexes" << _sourceNss.coll()),
                          stdx::bind(&CollectionCloner::_listIndexesCallback,
                                     this,
                                     stdx::placeholders::_1,
                                     stdx::placeholders::_2,
                                     stdx::placeholders::_3)),
      _findFetcher(_executor,
                   _source,
                   _sourceNss.db().toString(),
                   BSON("find" << _sourceNss.coll() << "noCursorTimeout" << true),  // SERVER-1387
                   stdx::bind(&CollectionCloner::_findCallback,
                              this,
                              stdx::placeholders::_1,
                              stdx::placeholders::_2,
                              stdx::placeholders::_3)),
      _indexSpecs(),
      _documents(),
      _dbWorkCallbackHandle(),
      _scheduleDbWorkFn([this](const ReplicationExecutor::CallbackFn& work) {
          return _executor->scheduleDBWork(work);
      }) {
    uassert(ErrorCodes::BadValue, "null replication executor", executor);
    uassert(ErrorCodes::BadValue,
            "invalid collection namespace: " + sourceNss.ns(),
            sourceNss.isValid());
    uassertStatusOK(options.validate());
    uassert(ErrorCodes::BadValue, "callback function cannot be null", onCompletion);
    uassert(ErrorCodes::BadValue, "null storage interface", storageInterface);
}

CollectionCloner::~CollectionCloner() {
    DESTRUCTOR_GUARD(cancel(); wait(););
}

const NamespaceString& CollectionCloner::getSourceNamespace() const {
    return _sourceNss;
}

std::string CollectionCloner::getDiagnosticString() const {
    stdx::lock_guard<stdx::mutex> lk(_mutex);
    str::stream output;
    output << "CollectionCloner";
    output << " executor: " << _executor->getDiagnosticString();
    output << " source: " << _source.toString();
    output << " source namespace: " << _sourceNss.toString();
    output << " destination namespace: " << _destNss.toString();
    output << " collection options: " << _options.toBSON();
    output << " active: " << _active;
    output << " listIndexes fetcher: " << _listIndexesFetcher.getDiagnosticString();
    output << " find fetcher: " << _findFetcher.getDiagnosticString();
    output << " database worked callback handle: " << (_dbWorkCallbackHandle.isValid() ? "valid"
                                                                                       : "invalid");
    return output;
}

bool CollectionCloner::isActive() const {
    stdx::lock_guard<stdx::mutex> lk(_mutex);
    return _active;
}

Status CollectionCloner::start() {
    stdx::lock_guard<stdx::mutex> lk(_mutex);

    if (_active) {
        return Status(ErrorCodes::IllegalOperation, "collection cloner already started");
    }

    Status scheduleResult = _listIndexesFetcher.schedule();
    if (!scheduleResult.isOK()) {
        return scheduleResult;
    }

    _active = true;

    return Status::OK();
}

void CollectionCloner::cancel() {
    ReplicationExecutor::CallbackHandle dbWorkCallbackHandle;
    {
        stdx::lock_guard<stdx::mutex> lk(_mutex);

        if (!_active) {
            return;
        }

        dbWorkCallbackHandle = _dbWorkCallbackHandle;
    }

    _listIndexesFetcher.cancel();
    _findFetcher.cancel();

    if (dbWorkCallbackHandle.isValid()) {
        _executor->cancel(dbWorkCallbackHandle);
    }
}

void CollectionCloner::wait() {
    stdx::unique_lock<stdx::mutex> lk(_mutex);
    _condition.wait(lk, [this]() { return !_active; });
}

void CollectionCloner::waitForDbWorker() {
    ReplicationExecutor::CallbackHandle dbWorkCallbackHandle;
    {
        stdx::lock_guard<stdx::mutex> lk(_mutex);

        if (!_active) {
            return;
        }

        dbWorkCallbackHandle = _dbWorkCallbackHandle;
    }

    if (dbWorkCallbackHandle.isValid()) {
        _executor->wait(dbWorkCallbackHandle);
    }
}

void CollectionCloner::setScheduleDbWorkFn(const ScheduleDbWorkFn& scheduleDbWorkFn) {
    stdx::lock_guard<stdx::mutex> lk(_mutex);

    _scheduleDbWorkFn = scheduleDbWorkFn;
}

void CollectionCloner::_listIndexesCallback(const Fetcher::QueryResponseStatus& fetchResult,
                                            Fetcher::NextAction* nextAction,
                                            BSONObjBuilder* getMoreBob) {
    if (!fetchResult.isOK()) {
        _finishCallback(nullptr, fetchResult.getStatus());
        return;
    }

    auto batchData(fetchResult.getValue());
    auto&& documents = batchData.documents;

    if (documents.empty()) {
        warning() << "No indexes found for collection " << _sourceNss.ns() << " while cloning from "
                  << _source;
    }

    // We may be called with multiple batches leading to a need to grow _indexSpecs.
    _indexSpecs.reserve(_indexSpecs.size() + documents.size());
    _indexSpecs.insert(_indexSpecs.end(), documents.begin(), documents.end());

    // The fetcher will continue to call with kGetMore until an error or the last batch.
    if (*nextAction == Fetcher::NextAction::kGetMore) {
        invariant(getMoreBob);
        getMoreBob->append("getMore", batchData.cursorId);
        getMoreBob->append("collection", batchData.nss.coll());
        return;
    }

    // We have all of the indexes now, so we can start cloning the collection data.
    auto&& scheduleResult = _scheduleDbWorkFn(
        stdx::bind(&CollectionCloner::_beginCollectionCallback, this, stdx::placeholders::_1));
    if (!scheduleResult.isOK()) {
        _finishCallback(nullptr, scheduleResult.getStatus());
        return;
    }

    _dbWorkCallbackHandle = scheduleResult.getValue();
}

void CollectionCloner::_findCallback(const StatusWith<Fetcher::QueryResponse>& fetchResult,
                                     Fetcher::NextAction* nextAction,
                                     BSONObjBuilder* getMoreBob) {
    if (!fetchResult.isOK()) {
        _finishCallback(nullptr, fetchResult.getStatus());
        return;
    }

    auto batchData(fetchResult.getValue());
    _documents = batchData.documents;

    bool lastBatch = *nextAction == Fetcher::NextAction::kNoAction;
    auto&& scheduleResult = _scheduleDbWorkFn(stdx::bind(
        &CollectionCloner::_insertDocumentsCallback, this, stdx::placeholders::_1, lastBatch));
    if (!scheduleResult.isOK()) {
        _finishCallback(nullptr, scheduleResult.getStatus());
        return;
    }

    if (*nextAction == Fetcher::NextAction::kGetMore) {
        invariant(getMoreBob);
        getMoreBob->append("getMore", batchData.cursorId);
        getMoreBob->append("collection", batchData.nss.coll());
    }

    _dbWorkCallbackHandle = scheduleResult.getValue();
}

void CollectionCloner::_beginCollectionCallback(const ReplicationExecutor::CallbackArgs& cbd) {
    OperationContext* txn = cbd.txn;
    if (!cbd.status.isOK()) {
        _finishCallback(txn, cbd.status);
        return;
    }

    Status status = _storageInterface->beginCollection(txn, _destNss, _options, _indexSpecs);
    if (!status.isOK()) {
        _finishCallback(txn, status);
        return;
    }

    Status scheduleStatus = _findFetcher.schedule();
    if (!scheduleStatus.isOK()) {
        _finishCallback(txn, scheduleStatus);
        return;
    }
}

void CollectionCloner::_insertDocumentsCallback(const ReplicationExecutor::CallbackArgs& cbd,
                                                bool lastBatch) {
    OperationContext* txn = cbd.txn;
    if (!cbd.status.isOK()) {
        _finishCallback(txn, cbd.status);
        return;
    }

    Status status = _storageInterface->insertDocuments(txn, _destNss, _documents);
    if (!status.isOK()) {
        _finishCallback(txn, status);
        return;
    }

    if (!lastBatch) {
        return;
    }

    _finishCallback(txn, Status::OK());
}

void CollectionCloner::_finishCallback(OperationContext* txn, const Status& status) {
    if (status.isOK()) {
        auto commitStatus = _storageInterface->commitCollection(txn, _destNss);
        if (!commitStatus.isOK()) {
            warning() << "Failed to commit changes to collection " << _destNss.ns() << ": "
                      << commitStatus;
        }
    }
    _onCompletion(status);
    stdx::lock_guard<stdx::mutex> lk(_mutex);
    _active = false;
    _condition.notify_all();
}

}  // namespace repl
}  // namespace mongo