forked from facebook/rocksdb
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdb_test.cc
5654 lines (4951 loc) · 171 KB
/
db_test.cc
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
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// Copyright (c) 2013, 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.
//
// Copyright (c) 2011 The LevelDB Authors. All rights reserved.
// Use of this source code is governed by a BSD-style license that can be
// found in the LICENSE file. See the AUTHORS file for names of contributors.
#include <algorithm>
#include <set>
#include <unistd.h>
#include <unordered_set>
#include "db/dbformat.h"
#include "db/db_impl.h"
#include "db/filename.h"
#include "db/version_set.h"
#include "db/write_batch_internal.h"
#include "rocksdb/cache.h"
#include "rocksdb/compaction_filter.h"
#include "rocksdb/db.h"
#include "rocksdb/env.h"
#include "rocksdb/filter_policy.h"
#include "rocksdb/perf_context.h"
#include "table/plain_table_factory.h"
#include "rocksdb/slice.h"
#include "rocksdb/slice_transform.h"
#include "rocksdb/table.h"
#include "rocksdb/table_properties.h"
#include "table/block_based_table_factory.h"
#include "util/hash.h"
#include "util/hash_linklist_rep.h"
#include "util/logging.h"
#include "util/mutexlock.h"
#include "util/statistics.h"
#include "util/testharness.h"
#include "util/testutil.h"
#include "utilities/merge_operators.h"
namespace rocksdb {
static bool SnappyCompressionSupported(const CompressionOptions& options) {
std::string out;
Slice in = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
return port::Snappy_Compress(options, in.data(), in.size(), &out);
}
static bool ZlibCompressionSupported(const CompressionOptions& options) {
std::string out;
Slice in = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
return port::Zlib_Compress(options, in.data(), in.size(), &out);
}
static bool BZip2CompressionSupported(const CompressionOptions& options) {
std::string out;
Slice in = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
return port::BZip2_Compress(options, in.data(), in.size(), &out);
}
static bool LZ4CompressionSupported(const CompressionOptions &options) {
std::string out;
Slice in = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
return port::LZ4_Compress(options, in.data(), in.size(), &out);
}
static bool LZ4HCCompressionSupported(const CompressionOptions &options) {
std::string out;
Slice in = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa";
return port::LZ4HC_Compress(options, in.data(), in.size(), &out);
}
static std::string RandomString(Random *rnd, int len) {
std::string r;
test::RandomString(rnd, len, &r);
return r;
}
namespace anon {
class AtomicCounter {
private:
port::Mutex mu_;
int count_;
public:
AtomicCounter() : count_(0) { }
void Increment() {
MutexLock l(&mu_);
count_++;
}
int Read() {
MutexLock l(&mu_);
return count_;
}
void Reset() {
MutexLock l(&mu_);
count_ = 0;
}
};
}
// Special Env used to delay background operations
class SpecialEnv : public EnvWrapper {
public:
// sstable Sync() calls are blocked while this pointer is non-nullptr.
port::AtomicPointer delay_sstable_sync_;
// Simulate no-space errors while this pointer is non-nullptr.
port::AtomicPointer no_space_;
// Simulate non-writable file system while this pointer is non-nullptr
port::AtomicPointer non_writable_;
// Force sync of manifest files to fail while this pointer is non-nullptr
port::AtomicPointer manifest_sync_error_;
// Force write to manifest files to fail while this pointer is non-nullptr
port::AtomicPointer manifest_write_error_;
// Force write to log files to fail while this pointer is non-nullptr
port::AtomicPointer log_write_error_;
bool count_random_reads_;
anon::AtomicCounter random_read_counter_;
anon::AtomicCounter sleep_counter_;
explicit SpecialEnv(Env* base) : EnvWrapper(base) {
delay_sstable_sync_.Release_Store(nullptr);
no_space_.Release_Store(nullptr);
non_writable_.Release_Store(nullptr);
count_random_reads_ = false;
manifest_sync_error_.Release_Store(nullptr);
manifest_write_error_.Release_Store(nullptr);
log_write_error_.Release_Store(nullptr);
}
Status NewWritableFile(const std::string& f, unique_ptr<WritableFile>* r,
const EnvOptions& soptions) {
class SSTableFile : public WritableFile {
private:
SpecialEnv* env_;
unique_ptr<WritableFile> base_;
public:
SSTableFile(SpecialEnv* env, unique_ptr<WritableFile>&& base)
: env_(env),
base_(std::move(base)) {
}
Status Append(const Slice& data) {
if (env_->no_space_.Acquire_Load() != nullptr) {
// Drop writes on the floor
return Status::OK();
} else {
return base_->Append(data);
}
}
Status Close() { return base_->Close(); }
Status Flush() { return base_->Flush(); }
Status Sync() {
while (env_->delay_sstable_sync_.Acquire_Load() != nullptr) {
env_->SleepForMicroseconds(100000);
}
return base_->Sync();
}
};
class ManifestFile : public WritableFile {
private:
SpecialEnv* env_;
unique_ptr<WritableFile> base_;
public:
ManifestFile(SpecialEnv* env, unique_ptr<WritableFile>&& b)
: env_(env), base_(std::move(b)) { }
Status Append(const Slice& data) {
if (env_->manifest_write_error_.Acquire_Load() != nullptr) {
return Status::IOError("simulated writer error");
} else {
return base_->Append(data);
}
}
Status Close() { return base_->Close(); }
Status Flush() { return base_->Flush(); }
Status Sync() {
if (env_->manifest_sync_error_.Acquire_Load() != nullptr) {
return Status::IOError("simulated sync error");
} else {
return base_->Sync();
}
}
};
class LogFile : public WritableFile {
private:
SpecialEnv* env_;
unique_ptr<WritableFile> base_;
public:
LogFile(SpecialEnv* env, unique_ptr<WritableFile>&& b)
: env_(env), base_(std::move(b)) { }
Status Append(const Slice& data) {
if (env_->log_write_error_.Acquire_Load() != nullptr) {
return Status::IOError("simulated writer error");
} else {
return base_->Append(data);
}
}
Status Close() { return base_->Close(); }
Status Flush() { return base_->Flush(); }
Status Sync() { return base_->Sync(); }
};
if (non_writable_.Acquire_Load() != nullptr) {
return Status::IOError("simulated write error");
}
Status s = target()->NewWritableFile(f, r, soptions);
if (s.ok()) {
if (strstr(f.c_str(), ".sst") != nullptr) {
r->reset(new SSTableFile(this, std::move(*r)));
} else if (strstr(f.c_str(), "MANIFEST") != nullptr) {
r->reset(new ManifestFile(this, std::move(*r)));
} else if (strstr(f.c_str(), "log") != nullptr) {
r->reset(new LogFile(this, std::move(*r)));
}
}
return s;
}
Status NewRandomAccessFile(const std::string& f,
unique_ptr<RandomAccessFile>* r,
const EnvOptions& soptions) {
class CountingFile : public RandomAccessFile {
private:
unique_ptr<RandomAccessFile> target_;
anon::AtomicCounter* counter_;
public:
CountingFile(unique_ptr<RandomAccessFile>&& target,
anon::AtomicCounter* counter)
: target_(std::move(target)), counter_(counter) {
}
virtual Status Read(uint64_t offset, size_t n, Slice* result,
char* scratch) const {
counter_->Increment();
return target_->Read(offset, n, result, scratch);
}
};
Status s = target()->NewRandomAccessFile(f, r, soptions);
if (s.ok() && count_random_reads_) {
r->reset(new CountingFile(std::move(*r), &random_read_counter_));
}
return s;
}
virtual void SleepForMicroseconds(int micros) {
sleep_counter_.Increment();
target()->SleepForMicroseconds(micros);
}
};
class DBTest {
private:
const FilterPolicy* filter_policy_;
static std::unique_ptr<const SliceTransform> prefix_1_transform;
static std::unique_ptr<const SliceTransform> noop_transform;
protected:
// Sequence of option configurations to try
enum OptionConfig {
kDefault,
kPlainTableFirstBytePrefix,
kPlainTableAllBytesPrefix,
kVectorRep,
kHashLinkList,
kMergePut,
kFilter,
kUncompressed,
kNumLevel_3,
kDBLogDir,
kWalDir,
kManifestFileSize,
kCompactOnFlush,
kPerfOptions,
kDeletesFilterFirst,
kHashSkipList,
kUniversalCompaction,
kCompressedBlockCache,
kInfiniteMaxOpenFiles,
kEnd
};
int option_config_;
public:
std::string dbname_;
SpecialEnv* env_;
DB* db_;
Options last_options_;
// Skip some options, as they may not be applicable to a specific test.
// To add more skip constants, use values 4, 8, 16, etc.
enum OptionSkip {
kNoSkip = 0,
kSkipDeletesFilterFirst = 1,
kSkipUniversalCompaction = 2,
kSkipMergePut = 4,
kSkipPlainTable = 8
};
DBTest() : option_config_(kDefault),
env_(new SpecialEnv(Env::Default())) {
filter_policy_ = NewBloomFilterPolicy(10);
dbname_ = test::TmpDir() + "/db_test";
ASSERT_OK(DestroyDB(dbname_, Options()));
db_ = nullptr;
Reopen();
}
~DBTest() {
delete db_;
ASSERT_OK(DestroyDB(dbname_, Options()));
delete env_;
delete filter_policy_;
}
// Switch to a fresh database with the next option configuration to
// test. Return false if there are no more configurations to test.
bool ChangeOptions(int skip_mask = kNoSkip) {
// skip some options
for(option_config_++; option_config_ < kEnd; option_config_++) {
if ((skip_mask & kSkipDeletesFilterFirst) &&
option_config_ == kDeletesFilterFirst) {
continue;
}
if ((skip_mask & kSkipUniversalCompaction) &&
option_config_ == kUniversalCompaction) {
continue;
}
if ((skip_mask & kSkipMergePut) && option_config_ == kMergePut) {
continue;
}
if ((skip_mask & kSkipPlainTable)
&& (option_config_ == kPlainTableAllBytesPrefix
|| option_config_ == kPlainTableFirstBytePrefix)) {
continue;
}
break;
}
if (option_config_ >= kEnd) {
Destroy(&last_options_);
return false;
} else {
DestroyAndReopen();
return true;
}
}
// Switch between different compaction styles (we have only 2 now).
bool ChangeCompactOptions(Options* prev_options = nullptr) {
if (option_config_ == kDefault) {
option_config_ = kUniversalCompaction;
if (prev_options == nullptr) {
prev_options = &last_options_;
}
Destroy(prev_options);
TryReopen();
return true;
} else {
return false;
}
}
// Return the current option configuration.
Options CurrentOptions() {
Options options;
switch (option_config_) {
case kHashSkipList:
options.memtable_factory.reset(
NewHashSkipListRepFactory(NewFixedPrefixTransform(1)));
break;
case kPlainTableFirstBytePrefix:
options.table_factory.reset(new PlainTableFactory());
options.prefix_extractor = prefix_1_transform.get();
options.allow_mmap_reads = true;
options.max_sequential_skip_in_iterations = 999999;
break;
case kPlainTableAllBytesPrefix:
options.table_factory.reset(new PlainTableFactory());
options.prefix_extractor = noop_transform.get();
options.allow_mmap_reads = true;
options.max_sequential_skip_in_iterations = 999999;
break;
case kMergePut:
options.merge_operator = MergeOperators::CreatePutOperator();
break;
case kFilter:
options.filter_policy = filter_policy_;
break;
case kUncompressed:
options.compression = kNoCompression;
break;
case kNumLevel_3:
options.num_levels = 3;
break;
case kDBLogDir:
options.db_log_dir = test::TmpDir();
break;
case kWalDir:
options.wal_dir = "/tmp/wal";
break;
case kManifestFileSize:
options.max_manifest_file_size = 50; // 50 bytes
case kCompactOnFlush:
options.purge_redundant_kvs_while_flush =
!options.purge_redundant_kvs_while_flush;
break;
case kPerfOptions:
options.hard_rate_limit = 2.0;
options.rate_limit_delay_max_milliseconds = 2;
// TODO -- test more options
break;
case kDeletesFilterFirst:
options.filter_deletes = true;
break;
case kVectorRep:
options.memtable_factory.reset(new VectorRepFactory(100));
break;
case kHashLinkList:
options.memtable_factory.reset(
NewHashLinkListRepFactory(NewFixedPrefixTransform(1), 4));
break;
case kUniversalCompaction:
options.compaction_style = kCompactionStyleUniversal;
break;
case kCompressedBlockCache:
options.block_cache_compressed = NewLRUCache(8*1024*1024);
break;
case kInfiniteMaxOpenFiles:
options.max_open_files = -1;
break;
default:
break;
}
return options;
}
DBImpl* dbfull() {
return reinterpret_cast<DBImpl*>(db_);
}
void Reopen(Options* options = nullptr) {
ASSERT_OK(TryReopen(options));
}
void Close() {
delete db_;
db_ = nullptr;
}
void DestroyAndReopen(Options* options = nullptr) {
//Destroy using last options
Destroy(&last_options_);
ASSERT_OK(TryReopen(options));
}
void Destroy(Options* options) {
delete db_;
db_ = nullptr;
ASSERT_OK(DestroyDB(dbname_, *options));
}
Status PureReopen(Options* options, DB** db) {
return DB::Open(*options, dbname_, db);
}
Status ReadOnlyReopen(Options* options) {
return DB::OpenForReadOnly(*options, dbname_, &db_);
}
Status TryReopen(Options* options = nullptr) {
delete db_;
db_ = nullptr;
Options opts;
if (options != nullptr) {
opts = *options;
} else {
opts = CurrentOptions();
opts.create_if_missing = true;
}
last_options_ = opts;
return DB::Open(opts, dbname_, &db_);
}
Status Put(const Slice& k, const Slice& v, WriteOptions wo = WriteOptions()) {
if (kMergePut == option_config_ ) {
return db_->Merge(wo, k, v);
} else {
return db_->Put(wo, k, v);
}
}
Status Delete(const std::string& k) {
return db_->Delete(WriteOptions(), k);
}
std::string Get(const std::string& k, const Snapshot* snapshot = nullptr) {
ReadOptions options;
options.verify_checksums = true;
options.snapshot = snapshot;
std::string result;
Status s = db_->Get(options, k, &result);
if (s.IsNotFound()) {
result = "NOT_FOUND";
} else if (!s.ok()) {
result = s.ToString();
}
return result;
}
// Return a string that contains all key,value pairs in order,
// formatted like "(k1->v1)(k2->v2)".
std::string Contents() {
std::vector<std::string> forward;
std::string result;
Iterator* iter = db_->NewIterator(ReadOptions());
for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
std::string s = IterStatus(iter);
result.push_back('(');
result.append(s);
result.push_back(')');
forward.push_back(s);
}
// Check reverse iteration results are the reverse of forward results
unsigned int matched = 0;
for (iter->SeekToLast(); iter->Valid(); iter->Prev()) {
ASSERT_LT(matched, forward.size());
ASSERT_EQ(IterStatus(iter), forward[forward.size() - matched - 1]);
matched++;
}
ASSERT_EQ(matched, forward.size());
delete iter;
return result;
}
std::string AllEntriesFor(const Slice& user_key) {
Iterator* iter = dbfull()->TEST_NewInternalIterator();
InternalKey target(user_key, kMaxSequenceNumber, kTypeValue);
iter->Seek(target.Encode());
std::string result;
if (!iter->status().ok()) {
result = iter->status().ToString();
} else {
result = "[ ";
bool first = true;
while (iter->Valid()) {
ParsedInternalKey ikey(Slice(), 0, kTypeValue);
if (!ParseInternalKey(iter->key(), &ikey)) {
result += "CORRUPTED";
} else {
if (last_options_.comparator->Compare(ikey.user_key, user_key) != 0) {
break;
}
if (!first) {
result += ", ";
}
first = false;
switch (ikey.type) {
case kTypeValue:
result += iter->value().ToString();
break;
case kTypeMerge:
// keep it the same as kTypeValue for testing kMergePut
result += iter->value().ToString();
break;
case kTypeDeletion:
result += "DEL";
break;
default:
assert(false);
break;
}
}
iter->Next();
}
if (!first) {
result += " ";
}
result += "]";
}
delete iter;
return result;
}
int NumTableFilesAtLevel(int level) {
std::string property;
ASSERT_TRUE(
db_->GetProperty("rocksdb.num-files-at-level" + NumberToString(level),
&property));
return atoi(property.c_str());
}
int TotalTableFiles() {
int result = 0;
for (int level = 0; level < db_->NumberLevels(); level++) {
result += NumTableFilesAtLevel(level);
}
return result;
}
// Return spread of files per level
std::string FilesPerLevel() {
std::string result;
int last_non_zero_offset = 0;
for (int level = 0; level < db_->NumberLevels(); level++) {
int f = NumTableFilesAtLevel(level);
char buf[100];
snprintf(buf, sizeof(buf), "%s%d", (level ? "," : ""), f);
result += buf;
if (f > 0) {
last_non_zero_offset = result.size();
}
}
result.resize(last_non_zero_offset);
return result;
}
int CountFiles() {
std::vector<std::string> files;
env_->GetChildren(dbname_, &files);
std::vector<std::string> logfiles;
if (dbname_ != last_options_.wal_dir) {
env_->GetChildren(last_options_.wal_dir, &logfiles);
}
return static_cast<int>(files.size() + logfiles.size());
}
int CountLiveFiles() {
std::vector<std::string> files;
uint64_t manifest_file_size;
db_->GetLiveFiles(files, &manifest_file_size);
return files.size();
}
uint64_t Size(const Slice& start, const Slice& limit) {
Range r(start, limit);
uint64_t size;
db_->GetApproximateSizes(&r, 1, &size);
return size;
}
void Compact(const Slice& start, const Slice& limit) {
db_->CompactRange(&start, &limit);
}
// Do n memtable compactions, each of which produces an sstable
// covering the range [small,large].
void MakeTables(int n, const std::string& small, const std::string& large) {
for (int i = 0; i < n; i++) {
Put(small, "begin");
Put(large, "end");
dbfull()->TEST_FlushMemTable();
}
}
// Prevent pushing of new sstables into deeper levels by adding
// tables that cover a specified range to all levels.
void FillLevels(const std::string& smallest, const std::string& largest) {
MakeTables(db_->NumberLevels(), smallest, largest);
}
void DumpFileCounts(const char* label) {
fprintf(stderr, "---\n%s:\n", label);
fprintf(stderr, "maxoverlap: %lld\n",
static_cast<long long>(
dbfull()->TEST_MaxNextLevelOverlappingBytes()));
for (int level = 0; level < db_->NumberLevels(); level++) {
int num = NumTableFilesAtLevel(level);
if (num > 0) {
fprintf(stderr, " level %3d : %d files\n", level, num);
}
}
}
std::string DumpSSTableList() {
std::string property;
db_->GetProperty("rocksdb.sstables", &property);
return property;
}
std::string IterStatus(Iterator* iter) {
std::string result;
if (iter->Valid()) {
result = iter->key().ToString() + "->" + iter->value().ToString();
} else {
result = "(invalid)";
}
return result;
}
Options OptionsForLogIterTest() {
Options options = CurrentOptions();
options.create_if_missing = true;
options.WAL_ttl_seconds = 1000;
return options;
}
std::unique_ptr<TransactionLogIterator> OpenTransactionLogIter(
const SequenceNumber seq) {
unique_ptr<TransactionLogIterator> iter;
Status status = dbfull()->GetUpdatesSince(seq, &iter);
ASSERT_OK(status);
ASSERT_TRUE(iter->Valid());
return std::move(iter);
}
std::string DummyString(size_t len, char c = 'a') {
return std::string(len, c);
}
void VerifyIterLast(std::string expected_key) {
Iterator* iter = db_->NewIterator(ReadOptions());
iter->SeekToLast();
ASSERT_EQ(IterStatus(iter), expected_key);
delete iter;
}
// Used to test InplaceUpdate
// If previous value is nullptr or delta is > than previous value,
// sets newValue with delta
// If previous value is not empty,
// updates previous value with 'b' string of previous value size - 1.
static UpdateStatus
updateInPlaceSmallerSize(char* prevValue, uint32_t* prevSize,
Slice delta, std::string* newValue) {
if (prevValue == nullptr) {
*newValue = std::string(delta.size(), 'c');
return UpdateStatus::UPDATED;
} else {
*prevSize = *prevSize - 1;
std::string str_b = std::string(*prevSize, 'b');
memcpy(prevValue, str_b.c_str(), str_b.size());
return UpdateStatus::UPDATED_INPLACE;
}
}
static UpdateStatus
updateInPlaceSmallerVarintSize(char* prevValue, uint32_t* prevSize,
Slice delta, std::string* newValue) {
if (prevValue == nullptr) {
*newValue = std::string(delta.size(), 'c');
return UpdateStatus::UPDATED;
} else {
*prevSize = 1;
std::string str_b = std::string(*prevSize, 'b');
memcpy(prevValue, str_b.c_str(), str_b.size());
return UpdateStatus::UPDATED_INPLACE;
}
}
static UpdateStatus
updateInPlaceLargerSize(char* prevValue, uint32_t* prevSize,
Slice delta, std::string* newValue) {
*newValue = std::string(delta.size(), 'c');
return UpdateStatus::UPDATED;
}
static UpdateStatus
updateInPlaceNoAction(char* prevValue, uint32_t* prevSize,
Slice delta, std::string* newValue) {
return UpdateStatus::UPDATE_FAILED;
}
// Utility method to test InplaceUpdate
void validateNumberOfEntries(int numValues) {
Iterator* iter = dbfull()->TEST_NewInternalIterator();
iter->SeekToFirst();
ASSERT_EQ(iter->status().ok(), true);
int seq = numValues;
while (iter->Valid()) {
ParsedInternalKey ikey;
ikey.sequence = -1;
ASSERT_EQ(ParseInternalKey(iter->key(), &ikey), true);
// checks sequence number for updates
ASSERT_EQ(ikey.sequence, (unsigned)seq--);
iter->Next();
}
delete iter;
ASSERT_EQ(0, seq);
}
void CopyFile(const std::string& source, const std::string& destination,
uint64_t size = 0) {
const EnvOptions soptions;
unique_ptr<SequentialFile> srcfile;
ASSERT_OK(env_->NewSequentialFile(source, &srcfile, soptions));
unique_ptr<WritableFile> destfile;
ASSERT_OK(env_->NewWritableFile(destination, &destfile, soptions));
if (size == 0) {
// default argument means copy everything
ASSERT_OK(env_->GetFileSize(source, &size));
}
char buffer[4096];
Slice slice;
while (size > 0) {
uint64_t one = std::min(uint64_t(sizeof(buffer)), size);
ASSERT_OK(srcfile->Read(one, &slice, buffer));
ASSERT_OK(destfile->Append(slice));
size -= slice.size();
}
ASSERT_OK(destfile->Close());
}
};
std::unique_ptr<const SliceTransform> DBTest::prefix_1_transform(
NewFixedPrefixTransform(1));
std::unique_ptr<const SliceTransform> DBTest::noop_transform(
NewNoopTransform());
static std::string Key(int i) {
char buf[100];
snprintf(buf, sizeof(buf), "key%06d", i);
return std::string(buf);
}
static long TestGetTickerCount(const Options& options, Tickers ticker_type) {
return options.statistics->getTickerCount(ticker_type);
}
// A helper function that ensures the table properties returned in
// `GetPropertiesOfAllTablesTest` is correct.
// This test assumes entries size is differnt for each of the tables.
void VerifyTableProperties(DB* db, uint64_t expected_entries_size) {
TablePropertiesCollection props;
ASSERT_OK(db->GetPropertiesOfAllTables(&props));
assert(props.size() == 4);
ASSERT_EQ(4U, props.size());
std::unordered_set<uint64_t> unique_entries;
// Indirect test
uint64_t sum = 0;
for (const auto& item : props) {
unique_entries.insert(item.second->num_entries);
sum += item.second->num_entries;
}
ASSERT_EQ(props.size(), unique_entries.size());
ASSERT_EQ(expected_entries_size, sum);
}
TEST(DBTest, Empty) {
do {
Options options = CurrentOptions();
options.env = env_;
options.write_buffer_size = 100000; // Small write buffer
Reopen(&options);
ASSERT_OK(Put("foo", "v1"));
ASSERT_EQ("v1", Get("foo"));
env_->delay_sstable_sync_.Release_Store(env_); // Block sync calls
Put("k1", std::string(100000, 'x')); // Fill memtable
Put("k2", std::string(100000, 'y')); // Trigger compaction
ASSERT_EQ("v1", Get("foo"));
env_->delay_sstable_sync_.Release_Store(nullptr); // Release sync calls
} while (ChangeOptions());
}
TEST(DBTest, ReadOnlyDB) {
ASSERT_OK(Put("foo", "v1"));
ASSERT_OK(Put("bar", "v2"));
ASSERT_OK(Put("foo", "v3"));
Close();
Options options;
ASSERT_OK(ReadOnlyReopen(&options));
ASSERT_EQ("v3", Get("foo"));
ASSERT_EQ("v2", Get("bar"));
Iterator* iter = db_->NewIterator(ReadOptions());
int count = 0;
for (iter->SeekToFirst(); iter->Valid(); iter->Next()) {
ASSERT_OK(iter->status());
++count;
}
ASSERT_EQ(count, 2);
delete iter;
}
// Make sure that when options.block_cache is set, after a new table is
// created its index/filter blocks are added to block cache.
TEST(DBTest, IndexAndFilterBlocksOfNewTableAddedToCache) {
Options options = CurrentOptions();
std::unique_ptr<const FilterPolicy> filter_policy(NewBloomFilterPolicy(20));
options.filter_policy = filter_policy.get();
options.create_if_missing = true;
options.statistics = rocksdb::CreateDBStatistics();
BlockBasedTableOptions table_options;
table_options.cache_index_and_filter_blocks = true;
options.table_factory.reset(new BlockBasedTableFactory(table_options));
DestroyAndReopen(&options);
ASSERT_OK(db_->Put(WriteOptions(), "key", "val"));
// Create a new talbe.
ASSERT_OK(dbfull()->Flush(FlushOptions()));
// index/filter blocks added to block cache right after table creation.
ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_INDEX_MISS));
ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
ASSERT_EQ(2, /* only index/filter were added */
TestGetTickerCount(options, BLOCK_CACHE_ADD));
ASSERT_EQ(0, TestGetTickerCount(options, BLOCK_CACHE_DATA_MISS));
// Make sure filter block is in cache.
std::string value;
ReadOptions ropt;
db_->KeyMayExist(ReadOptions(), "key", &value);
// Miss count should remain the same.
ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
db_->KeyMayExist(ReadOptions(), "key", &value);
ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
ASSERT_EQ(2, TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
// Make sure index block is in cache.
auto index_block_hit = TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT);
value = Get("key");
ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
ASSERT_EQ(index_block_hit + 1,
TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
value = Get("key");
ASSERT_EQ(1, TestGetTickerCount(options, BLOCK_CACHE_FILTER_MISS));
ASSERT_EQ(index_block_hit + 2,
TestGetTickerCount(options, BLOCK_CACHE_FILTER_HIT));
}
TEST(DBTest, GetPropertiesOfAllTablesTest) {
Options options = CurrentOptions();
Reopen(&options);
// Create 4 tables
for (int table = 0; table < 4; ++table) {
for (int i = 0; i < 10 + table; ++i) {
db_->Put(WriteOptions(), std::to_string(table * 100 + i), "val");
}
db_->Flush(FlushOptions());
}
// 1. Read table properties directly from file
Reopen(&options);
VerifyTableProperties(db_, 10 + 11 + 12 + 13);
// 2. Put two tables to table cache and
Reopen(&options);
// fetch key from 1st and 2nd table, which will internally place that table to
// the table cache.
for (int i = 0; i < 2; ++i) {
Get(std::to_string(i * 100 + 0));
}
VerifyTableProperties(db_, 10 + 11 + 12 + 13);
// 3. Put all tables to table cache
Reopen(&options);
// fetch key from 1st and 2nd table, which will internally place that table to
// the table cache.
for (int i = 0; i < 4; ++i) {
Get(std::to_string(i * 100 + 0));
}
VerifyTableProperties(db_, 10 + 11 + 12 + 13);
}
TEST(DBTest, LevelLimitReopen) {
Options options = CurrentOptions();
Reopen(&options);
const std::string value(1024 * 1024, ' ');
int i = 0;
while (NumTableFilesAtLevel(2) == 0) {
ASSERT_OK(Put(Key(i++), value));
}
options.num_levels = 1;
options.max_bytes_for_level_multiplier_additional.resize(1, 1);
Status s = TryReopen(&options);
ASSERT_EQ(s.IsInvalidArgument(), true);
ASSERT_EQ(s.ToString(),
"Invalid argument: db has more levels than options.num_levels");
options.num_levels = 10;
options.max_bytes_for_level_multiplier_additional.resize(10, 1);