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
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
|
/**
* 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.
*/
#include "mongo/platform/basic.h"
#include "mongo/db/catalog/collection_catalog_entry.h"
#include "mongo/db/catalog/multi_index_block.h"
#include "mongo/db/catalog_raii.h"
#include "mongo/db/concurrency/d_concurrency.h"
#include "mongo/db/curop.h"
#include "mongo/db/dbhelpers.h"
#include "mongo/db/index/duplicate_key_tracker.h"
#include "mongo/db/operation_context_noop.h"
#include "mongo/db/repl/replication_coordinator_mock.h"
#include "mongo/db/service_context_d_test_fixture.h"
#include "mongo/unittest/unittest.h"
namespace mongo {
namespace {
static const StringData kConstraintNsPrefix = "local.system.indexBuildConstraints"_sd;
class DuplicateKeyTrackerTest : public ServiceContextMongoDTest {
public:
DuplicateKeyTrackerTest()
: ServiceContextMongoDTest("ephemeralForTest"), _opCtx(cc().makeOperationContext()) {
repl::ReplicationCoordinator::set(
getServiceContext(),
stdx::make_unique<repl::ReplicationCoordinatorMock>(getServiceContext()));
}
std::unique_ptr<DuplicateKeyTracker> makeTracker(OperationContext* opCtx,
const IndexCatalogEntry* entry) {
NamespaceString tempNss = DuplicateKeyTracker::makeTempNamespace();
makeTempCollection(opCtx, tempNss);
auto tracker = std::make_unique<DuplicateKeyTracker>(entry, tempNss);
AutoGetCollection autoColl(opCtx, tracker->nss(), MODE_IS);
ASSERT(autoColl.getCollection());
return tracker;
};
OperationContext* opCtx() {
return _opCtx.get();
}
void tearDown() {}
void makeTempCollection(OperationContext* opCtx, const NamespaceString& nss) {
WriteUnitOfWork wuow(opCtx);
AutoGetOrCreateDb autoDb(opCtx, nss.db(), MODE_X);
auto db = autoDb.getDb();
invariant(db);
ASSERT(!db->getCollection(opCtx, nss));
CollectionOptions options;
options.setNoIdIndex();
// Create the temp collection
auto coll = db->createCollection(opCtx, nss.ns(), options);
invariant(coll);
wuow.commit();
}
void destroyTempCollection(OperationContext* opCtx, const NamespaceString& nss) {
WriteUnitOfWork wuow(opCtx);
AutoGetDb autoDb(opCtx, nss.db(), MODE_X);
auto db = autoDb.getDb();
invariant(db);
ASSERT_OK(db->dropCollectionEvenIfSystem(opCtx, nss));
wuow.commit();
}
private:
int _numIndexesCreated = 0;
ServiceContext::UniqueOperationContext _opCtx;
};
TEST_F(DuplicateKeyTrackerTest, IndexBuild) {
std::unique_ptr<DuplicateKeyTracker> tracker;
const NamespaceString collNs("test.myCollection");
const BSONObj doc1 = BSON("_id" << 1 << "a" << 1);
const BSONObj doc2 = BSON("_id" << 2 << "a" << 1);
// Create the collection with a two documents that have the same key for 'a'.
{
AutoGetOrCreateDb dbRaii(opCtx(), collNs.db(), LockMode::MODE_X);
WriteUnitOfWork wunit(opCtx());
CollectionOptions options;
options.uuid = UUID::gen();
auto coll = dbRaii.getDb()->createCollection(opCtx(), collNs.ns(), options);
ASSERT(coll);
ASSERT_OK(coll->insertDocument(opCtx(), InsertStatement(doc1), nullptr));
ASSERT_OK(coll->insertDocument(opCtx(), InsertStatement(doc2), nullptr));
wunit.commit();
}
const std::string indexName = "a_1";
const BSONObj spec =
BSON("ns" << collNs.ns() << "v" << 2 << "name" << indexName << "key" << BSON("a" << 1)
<< "unique"
<< true
<< "background"
<< true);
// Create the index build block. Insert two different documents, but each with the same value
// for 'a'. This will cause the index insert to allow inserting a duplicate key.
const IndexCatalogEntry* entry;
boost::optional<Record> record1;
boost::optional<Record> record2;
{
AutoGetCollection autoColl(opCtx(), collNs, MODE_X);
auto coll = autoColl.getCollection();
MultiIndexBlock indexer;
ON_BLOCK_EXIT([&] { indexer.cleanUpAfterBuild(opCtx(), coll); });
// Don't use the bulk builder, which does not insert directly into the IAM for the index.
indexer.allowBackgroundBuilding();
// Allow duplicates.
indexer.ignoreUniqueConstraint();
ASSERT_OK(indexer.init(opCtx(), coll, spec).getStatus());
IndexDescriptor* desc = coll->getIndexCatalog()->findIndexByName(
opCtx(), indexName, true /* includeUnfinished */);
ASSERT(desc);
entry = coll->getIndexCatalog()->getEntry(desc);
// Construct the tracker.
tracker = makeTracker(opCtx(), entry);
// Index the documents.
WriteUnitOfWork wunit(opCtx());
auto cursor = coll->getCursor(opCtx());
record1 = cursor->next();
ASSERT(record1);
std::vector<BSONObj> dupsInserted;
// The insert of the first document should return no duplicates.
ASSERT_OK(indexer.insert(
opCtx(), coll, record1->data.releaseToBson(), record1->id, &dupsInserted));
ASSERT_EQ(0u, dupsInserted.size());
// The insert of the second document should return that a duplicate key was inserted.
record2 = cursor->next();
ASSERT(record2);
ASSERT_OK(indexer.insert(
opCtx(), coll, record2->data.releaseToBson(), record2->id, &dupsInserted));
ASSERT_EQ(1u, dupsInserted.size());
// Record that duplicates were inserted.
AutoGetCollection tempColl(opCtx(), tracker->nss(), MODE_IX);
ASSERT_OK(tracker->recordDuplicates(opCtx(), tempColl.getCollection(), dupsInserted));
ASSERT_OK(indexer.commit(opCtx(), coll));
wunit.commit();
}
// Confirm that the keys + RecordId of the duplicate are recorded.
{
AutoGetCollection tempColl(opCtx(), tracker->nss(), MODE_IS);
Status s = tracker->constraintsSatisfiedForIndex(opCtx(), tempColl.getCollection());
ASSERT_EQ(ErrorCodes::DuplicateKey, s.code());
}
// Now remove the document and index key to confirm the conflicts are resolved.
{
AutoGetCollection autoColl(opCtx(), collNs, MODE_IX);
auto coll = autoColl.getCollection();
WriteUnitOfWork wunit(opCtx());
OpDebug opDebug;
coll->deleteDocument(opCtx(), kUninitializedStmtId, record2->id, &opDebug);
wunit.commit();
// One key deleted for each index (includes _id)
ASSERT_EQ(2u, *opDebug.additiveMetrics.keysDeleted);
AutoGetCollection tempColl(opCtx(), tracker->nss(), MODE_IS);
Status s = tracker->constraintsSatisfiedForIndex(opCtx(), tempColl.getCollection());
ASSERT_OK(s);
}
destroyTempCollection(opCtx(), tracker->nss());
}
TEST_F(DuplicateKeyTrackerTest, BulkIndexBuild) {
std::unique_ptr<DuplicateKeyTracker> tracker;
const NamespaceString collNs("test.myCollection");
const BSONObj doc1 = BSON("_id" << 1 << "a" << 1);
const BSONObj doc2 = BSON("_id" << 2 << "a" << 1);
// Create the collection with a two documents that have the same key for 'a'.
{
AutoGetOrCreateDb dbRaii(opCtx(), collNs.db(), LockMode::MODE_X);
WriteUnitOfWork wunit(opCtx());
CollectionOptions options;
options.uuid = UUID::gen();
auto coll = dbRaii.getDb()->createCollection(opCtx(), collNs.ns(), options);
ASSERT(coll);
ASSERT_OK(coll->insertDocument(opCtx(), InsertStatement(doc1), nullptr));
ASSERT_OK(coll->insertDocument(opCtx(), InsertStatement(doc2), nullptr));
wunit.commit();
}
const std::string indexName = "a_1";
const BSONObj spec =
BSON("ns" << collNs.ns() << "v" << 2 << "name" << indexName << "key" << BSON("a" << 1)
<< "unique"
<< true
<< "background"
<< true);
// Create the bulk build block. Insert two different documents, but each with the same value
// for 'a'. This will cause the index insert to allow inserting a duplicate key.
const IndexCatalogEntry* entry;
boost::optional<Record> record1;
boost::optional<Record> record2;
{
AutoGetCollection autoColl(opCtx(), collNs, MODE_X);
auto coll = autoColl.getCollection();
MultiIndexBlock indexer;
ON_BLOCK_EXIT([&] { indexer.cleanUpAfterBuild(opCtx(), coll); });
// Allow duplicates.
indexer.ignoreUniqueConstraint();
ASSERT_OK(indexer.init(opCtx(), coll, spec).getStatus());
IndexDescriptor* desc = coll->getIndexCatalog()->findIndexByName(
opCtx(), indexName, true /* includeUnfinished */);
entry = coll->getIndexCatalog()->getEntry(desc);
// Construct the tracker.
tracker = makeTracker(opCtx(), entry);
auto cursor = coll->getCursor(opCtx());
record1 = cursor->next();
ASSERT(record1);
std::vector<BSONObj> dupsInserted;
// Neither of these inserts will recognize duplicates because the bulk inserter does not
// detect them until dumpInsertsFromBulk() is called.
ASSERT_OK(indexer.insert(
opCtx(), coll, record1->data.releaseToBson(), record1->id, &dupsInserted));
ASSERT_EQ(0u, dupsInserted.size());
record2 = cursor->next();
ASSERT(record2);
ASSERT_OK(indexer.insert(
opCtx(), coll, record2->data.releaseToBson(), record2->id, &dupsInserted));
ASSERT_EQ(0u, dupsInserted.size());
ASSERT_OK(indexer.dumpInsertsFromBulk(opCtx(), coll, &dupsInserted));
ASSERT_EQ(1u, dupsInserted.size());
// Record that duplicates were inserted.
WriteUnitOfWork wunit(opCtx());
AutoGetCollection tempColl(opCtx(), tracker->nss(), MODE_IX);
ASSERT_OK(tracker->recordDuplicates(opCtx(), tempColl.getCollection(), dupsInserted));
ASSERT_OK(indexer.commit(opCtx(), coll));
wunit.commit();
}
// Confirm that the keys + RecordId of the duplicate are recorded.
{
AutoGetCollection tempColl(opCtx(), tracker->nss(), MODE_IS);
Status s = tracker->constraintsSatisfiedForIndex(opCtx(), tempColl.getCollection());
ASSERT_EQ(ErrorCodes::DuplicateKey, s.code());
}
// Now remove the document and index key to confirm the conflicts are resolved.
{
AutoGetCollection autoColl(opCtx(), collNs, MODE_IX);
auto coll = autoColl.getCollection();
WriteUnitOfWork wunit(opCtx());
OpDebug opDebug;
coll->deleteDocument(opCtx(), kUninitializedStmtId, record2->id, &opDebug);
wunit.commit();
// One key deleted for each index (includes _id)
ASSERT_EQ(2u, *opDebug.additiveMetrics.keysDeleted);
AutoGetCollection tempColl(opCtx(), tracker->nss(), MODE_IS);
Status s = tracker->constraintsSatisfiedForIndex(opCtx(), tempColl.getCollection());
ASSERT_OK(s);
}
destroyTempCollection(opCtx(), tracker->nss());
}
} // namespace
} // namespace mongo
|