/
version_set.cc
4579 lines (4204 loc) · 164 KB
/
version_set.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) 2011-present, Facebook, Inc. All rights reserved.
// This source code is licensed under both the GPLv2 (found in the
// COPYING file in the root directory) and Apache 2.0 License
// (found in the LICENSE.Apache file in the root 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 "db/version_set.h"
#ifndef __STDC_FORMAT_MACROS
#define __STDC_FORMAT_MACROS
#endif
#include <inttypes.h>
#include <stdio.h>
#include <algorithm>
#include <list>
#include <map>
#include <set>
#include <string>
#include <unordered_map>
#include <vector>
#include "db/compaction.h"
#include "db/internal_stats.h"
#include "db/log_reader.h"
#include "db/log_writer.h"
#include "db/memtable.h"
#include "db/merge_context.h"
#include "db/merge_helper.h"
#include "db/pinned_iterators_manager.h"
#include "db/table_cache.h"
#include "db/version_builder.h"
#include "monitoring/file_read_sample.h"
#include "monitoring/perf_context_imp.h"
#include "rocksdb/env.h"
#include "rocksdb/merge_operator.h"
#include "rocksdb/write_buffer_manager.h"
#include "table/format.h"
#include "table/get_context.h"
#include "table/internal_iterator.h"
#include "table/merging_iterator.h"
#include "table/meta_blocks.h"
#include "table/plain_table_factory.h"
#include "table/table_reader.h"
#include "table/two_level_iterator.h"
#include "util/coding.h"
#include "util/file_reader_writer.h"
#include "util/filename.h"
#include "util/stop_watch.h"
#include "util/string_util.h"
#include "util/sync_point.h"
namespace rocksdb {
namespace {
// Find File in LevelFilesBrief data structure
// Within an index range defined by left and right
int FindFileInRange(const InternalKeyComparator& icmp,
const LevelFilesBrief& file_level,
const Slice& key,
uint32_t left,
uint32_t right) {
auto cmp = [&](const FdWithKeyRange& f, const Slice& k) -> bool {
return icmp.InternalKeyComparator::Compare(f.largest_key, k) < 0;
};
const auto &b = file_level.files;
return static_cast<int>(std::lower_bound(b + left,
b + right, key, cmp) - b);
}
Status OverlapWithIterator(const Comparator* ucmp,
const Slice& smallest_user_key,
const Slice& largest_user_key,
InternalIterator* iter,
bool* overlap) {
InternalKey range_start(smallest_user_key, kMaxSequenceNumber,
kValueTypeForSeek);
iter->Seek(range_start.Encode());
if (!iter->status().ok()) {
return iter->status();
}
*overlap = false;
if (iter->Valid()) {
ParsedInternalKey seek_result;
if (!ParseInternalKey(iter->key(), &seek_result)) {
return Status::Corruption("DB have corrupted keys");
}
if (ucmp->Compare(seek_result.user_key, largest_user_key) <= 0) {
*overlap = true;
}
}
return iter->status();
}
// Class to help choose the next file to search for the particular key.
// Searches and returns files level by level.
// We can search level-by-level since entries never hop across
// levels. Therefore we are guaranteed that if we find data
// in a smaller level, later levels are irrelevant (unless we
// are MergeInProgress).
class FilePicker {
public:
FilePicker(std::vector<FileMetaData*>* files, const Slice& user_key,
const Slice& ikey, autovector<LevelFilesBrief>* file_levels,
unsigned int num_levels, FileIndexer* file_indexer,
const Comparator* user_comparator,
const InternalKeyComparator* internal_comparator)
: num_levels_(num_levels),
curr_level_(static_cast<unsigned int>(-1)),
returned_file_level_(static_cast<unsigned int>(-1)),
hit_file_level_(static_cast<unsigned int>(-1)),
search_left_bound_(0),
search_right_bound_(FileIndexer::kLevelMaxIndex),
#ifndef NDEBUG
files_(files),
#endif
level_files_brief_(file_levels),
is_hit_file_last_in_level_(false),
curr_file_level_(nullptr),
user_key_(user_key),
ikey_(ikey),
file_indexer_(file_indexer),
user_comparator_(user_comparator),
internal_comparator_(internal_comparator) {
#ifdef NDEBUG
(void)files;
#endif
// Setup member variables to search first level.
search_ended_ = !PrepareNextLevel();
if (!search_ended_) {
// Prefetch Level 0 table data to avoid cache miss if possible.
for (unsigned int i = 0; i < (*level_files_brief_)[0].num_files; ++i) {
auto* r = (*level_files_brief_)[0].files[i].fd.table_reader;
if (r) {
r->Prepare(ikey);
}
}
}
}
int GetCurrentLevel() const { return curr_level_; }
FdWithKeyRange* GetNextFile() {
while (!search_ended_) { // Loops over different levels.
while (curr_index_in_curr_level_ < curr_file_level_->num_files) {
// Loops over all files in current level.
FdWithKeyRange* f = &curr_file_level_->files[curr_index_in_curr_level_];
hit_file_level_ = curr_level_;
is_hit_file_last_in_level_ =
curr_index_in_curr_level_ == curr_file_level_->num_files - 1;
int cmp_largest = -1;
// Do key range filtering of files or/and fractional cascading if:
// (1) not all the files are in level 0, or
// (2) there are more than 3 current level files
// If there are only 3 or less current level files in the system, we skip
// the key range filtering. In this case, more likely, the system is
// highly tuned to minimize number of tables queried by each query,
// so it is unlikely that key range filtering is more efficient than
// querying the files.
if (num_levels_ > 1 || curr_file_level_->num_files > 3) {
// Check if key is within a file's range. If search left bound and
// right bound point to the same find, we are sure key falls in
// range.
assert(
curr_level_ == 0 ||
curr_index_in_curr_level_ == start_index_in_curr_level_ ||
user_comparator_->Compare(user_key_,
ExtractUserKey(f->smallest_key)) <= 0);
int cmp_smallest = user_comparator_->Compare(user_key_,
ExtractUserKey(f->smallest_key));
if (cmp_smallest >= 0) {
cmp_largest = user_comparator_->Compare(user_key_,
ExtractUserKey(f->largest_key));
}
// Setup file search bound for the next level based on the
// comparison results
if (curr_level_ > 0) {
file_indexer_->GetNextLevelIndex(curr_level_,
curr_index_in_curr_level_,
cmp_smallest, cmp_largest,
&search_left_bound_,
&search_right_bound_);
}
// Key falls out of current file's range
if (cmp_smallest < 0 || cmp_largest > 0) {
if (curr_level_ == 0) {
++curr_index_in_curr_level_;
continue;
} else {
// Search next level.
break;
}
}
}
#ifndef NDEBUG
// Sanity check to make sure that the files are correctly sorted
if (prev_file_) {
if (curr_level_ != 0) {
int comp_sign = internal_comparator_->Compare(
prev_file_->largest_key, f->smallest_key);
assert(comp_sign < 0);
} else {
// level == 0, the current file cannot be newer than the previous
// one. Use compressed data structure, has no attribute seqNo
assert(curr_index_in_curr_level_ > 0);
assert(!NewestFirstBySeqNo(files_[0][curr_index_in_curr_level_],
files_[0][curr_index_in_curr_level_-1]));
}
}
prev_file_ = f;
#endif
returned_file_level_ = curr_level_;
if (curr_level_ > 0 && cmp_largest < 0) {
// No more files to search in this level.
search_ended_ = !PrepareNextLevel();
} else {
++curr_index_in_curr_level_;
}
return f;
}
// Start searching next level.
search_ended_ = !PrepareNextLevel();
}
// Search ended.
return nullptr;
}
// getter for current file level
// for GET_HIT_L0, GET_HIT_L1 & GET_HIT_L2_AND_UP counts
unsigned int GetHitFileLevel() { return hit_file_level_; }
// Returns true if the most recent "hit file" (i.e., one returned by
// GetNextFile()) is at the last index in its level.
bool IsHitFileLastInLevel() { return is_hit_file_last_in_level_; }
private:
unsigned int num_levels_;
unsigned int curr_level_;
unsigned int returned_file_level_;
unsigned int hit_file_level_;
int32_t search_left_bound_;
int32_t search_right_bound_;
#ifndef NDEBUG
std::vector<FileMetaData*>* files_;
#endif
autovector<LevelFilesBrief>* level_files_brief_;
bool search_ended_;
bool is_hit_file_last_in_level_;
LevelFilesBrief* curr_file_level_;
unsigned int curr_index_in_curr_level_;
unsigned int start_index_in_curr_level_;
Slice user_key_;
Slice ikey_;
FileIndexer* file_indexer_;
const Comparator* user_comparator_;
const InternalKeyComparator* internal_comparator_;
#ifndef NDEBUG
FdWithKeyRange* prev_file_;
#endif
// Setup local variables to search next level.
// Returns false if there are no more levels to search.
bool PrepareNextLevel() {
curr_level_++;
while (curr_level_ < num_levels_) {
curr_file_level_ = &(*level_files_brief_)[curr_level_];
if (curr_file_level_->num_files == 0) {
// When current level is empty, the search bound generated from upper
// level must be [0, -1] or [0, FileIndexer::kLevelMaxIndex] if it is
// also empty.
assert(search_left_bound_ == 0);
assert(search_right_bound_ == -1 ||
search_right_bound_ == FileIndexer::kLevelMaxIndex);
// Since current level is empty, it will need to search all files in
// the next level
search_left_bound_ = 0;
search_right_bound_ = FileIndexer::kLevelMaxIndex;
curr_level_++;
continue;
}
// Some files may overlap each other. We find
// all files that overlap user_key and process them in order from
// newest to oldest. In the context of merge-operator, this can occur at
// any level. Otherwise, it only occurs at Level-0 (since Put/Deletes
// are always compacted into a single entry).
int32_t start_index;
if (curr_level_ == 0) {
// On Level-0, we read through all files to check for overlap.
start_index = 0;
} else {
// On Level-n (n>=1), files are sorted. Binary search to find the
// earliest file whose largest key >= ikey. Search left bound and
// right bound are used to narrow the range.
if (search_left_bound_ <= search_right_bound_) {
if (search_right_bound_ == FileIndexer::kLevelMaxIndex) {
search_right_bound_ =
static_cast<int32_t>(curr_file_level_->num_files) - 1;
}
// `search_right_bound_` is an inclusive upper-bound, but since it was
// determined based on user key, it is still possible the lookup key
// falls to the right of `search_right_bound_`'s corresponding file.
// So, pass a limit one higher, which allows us to detect this case.
start_index =
FindFileInRange(*internal_comparator_, *curr_file_level_, ikey_,
static_cast<uint32_t>(search_left_bound_),
static_cast<uint32_t>(search_right_bound_) + 1);
if (start_index == search_right_bound_ + 1) {
// `ikey_` comes after `search_right_bound_`. The lookup key does
// not exist on this level, so let's skip this level and do a full
// binary search on the next level.
search_left_bound_ = 0;
search_right_bound_ = FileIndexer::kLevelMaxIndex;
curr_level_++;
continue;
}
} else {
// search_left_bound > search_right_bound, key does not exist in
// this level. Since no comparison is done in this level, it will
// need to search all files in the next level.
search_left_bound_ = 0;
search_right_bound_ = FileIndexer::kLevelMaxIndex;
curr_level_++;
continue;
}
}
start_index_in_curr_level_ = start_index;
curr_index_in_curr_level_ = start_index;
#ifndef NDEBUG
prev_file_ = nullptr;
#endif
return true;
}
// curr_level_ = num_levels_. So, no more levels to search.
return false;
}
};
} // anonymous namespace
VersionStorageInfo::~VersionStorageInfo() { delete[] files_; }
Version::~Version() {
assert(refs_ == 0);
// Remove from linked list
prev_->next_ = next_;
next_->prev_ = prev_;
// Drop references to files
for (int level = 0; level < storage_info_.num_levels_; level++) {
for (size_t i = 0; i < storage_info_.files_[level].size(); i++) {
FileMetaData* f = storage_info_.files_[level][i];
assert(f->refs > 0);
f->refs--;
if (f->refs <= 0) {
assert(cfd_ != nullptr);
uint32_t path_id = f->fd.GetPathId();
assert(path_id < cfd_->ioptions()->cf_paths.size());
vset_->obsolete_files_.push_back(
ObsoleteFileInfo(f, cfd_->ioptions()->cf_paths[path_id].path));
}
}
}
}
int FindFile(const InternalKeyComparator& icmp,
const LevelFilesBrief& file_level,
const Slice& key) {
return FindFileInRange(icmp, file_level, key, 0,
static_cast<uint32_t>(file_level.num_files));
}
void DoGenerateLevelFilesBrief(LevelFilesBrief* file_level,
const std::vector<FileMetaData*>& files,
Arena* arena) {
assert(file_level);
assert(arena);
size_t num = files.size();
file_level->num_files = num;
char* mem = arena->AllocateAligned(num * sizeof(FdWithKeyRange));
file_level->files = new (mem)FdWithKeyRange[num];
for (size_t i = 0; i < num; i++) {
Slice smallest_key = files[i]->smallest.Encode();
Slice largest_key = files[i]->largest.Encode();
// Copy key slice to sequential memory
size_t smallest_size = smallest_key.size();
size_t largest_size = largest_key.size();
mem = arena->AllocateAligned(smallest_size + largest_size);
memcpy(mem, smallest_key.data(), smallest_size);
memcpy(mem + smallest_size, largest_key.data(), largest_size);
FdWithKeyRange& f = file_level->files[i];
f.fd = files[i]->fd;
f.file_metadata = files[i];
f.smallest_key = Slice(mem, smallest_size);
f.largest_key = Slice(mem + smallest_size, largest_size);
}
}
static bool AfterFile(const Comparator* ucmp,
const Slice* user_key, const FdWithKeyRange* f) {
// nullptr user_key occurs before all keys and is therefore never after *f
return (user_key != nullptr &&
ucmp->Compare(*user_key, ExtractUserKey(f->largest_key)) > 0);
}
static bool BeforeFile(const Comparator* ucmp,
const Slice* user_key, const FdWithKeyRange* f) {
// nullptr user_key occurs after all keys and is therefore never before *f
return (user_key != nullptr &&
ucmp->Compare(*user_key, ExtractUserKey(f->smallest_key)) < 0);
}
bool SomeFileOverlapsRange(
const InternalKeyComparator& icmp,
bool disjoint_sorted_files,
const LevelFilesBrief& file_level,
const Slice* smallest_user_key,
const Slice* largest_user_key) {
const Comparator* ucmp = icmp.user_comparator();
if (!disjoint_sorted_files) {
// Need to check against all files
for (size_t i = 0; i < file_level.num_files; i++) {
const FdWithKeyRange* f = &(file_level.files[i]);
if (AfterFile(ucmp, smallest_user_key, f) ||
BeforeFile(ucmp, largest_user_key, f)) {
// No overlap
} else {
return true; // Overlap
}
}
return false;
}
// Binary search over file list
uint32_t index = 0;
if (smallest_user_key != nullptr) {
// Find the leftmost possible internal key for smallest_user_key
InternalKey small;
small.SetMinPossibleForUserKey(*smallest_user_key);
index = FindFile(icmp, file_level, small.Encode());
}
if (index >= file_level.num_files) {
// beginning of range is after all files, so no overlap.
return false;
}
return !BeforeFile(ucmp, largest_user_key, &file_level.files[index]);
}
namespace {
class LevelIterator final : public InternalIterator {
public:
LevelIterator(
TableCache* table_cache, const ReadOptions& read_options,
const EnvOptions& env_options, const InternalKeyComparator& icomparator,
const LevelFilesBrief* flevel, const SliceTransform* prefix_extractor,
bool should_sample, HistogramImpl* file_read_hist, bool for_compaction,
bool skip_filters, int level, RangeDelAggregator* range_del_agg,
const std::vector<AtomicCompactionUnitBoundary>* compaction_boundaries =
nullptr)
: table_cache_(table_cache),
read_options_(read_options),
env_options_(env_options),
icomparator_(icomparator),
flevel_(flevel),
prefix_extractor_(prefix_extractor),
file_read_hist_(file_read_hist),
should_sample_(should_sample),
for_compaction_(for_compaction),
skip_filters_(skip_filters),
file_index_(flevel_->num_files),
level_(level),
range_del_agg_(range_del_agg),
pinned_iters_mgr_(nullptr),
compaction_boundaries_(compaction_boundaries) {
// Empty level is not supported.
assert(flevel_ != nullptr && flevel_->num_files > 0);
}
virtual ~LevelIterator() { delete file_iter_.Set(nullptr); }
virtual void Seek(const Slice& target) override;
virtual void SeekForPrev(const Slice& target) override;
virtual void SeekToFirst() override;
virtual void SeekToLast() override;
virtual void Next() override;
virtual void Prev() override;
virtual bool Valid() const override { return file_iter_.Valid(); }
virtual Slice key() const override {
assert(Valid());
return file_iter_.key();
}
virtual Slice value() const override {
assert(Valid());
return file_iter_.value();
}
virtual Status status() const override {
return file_iter_.iter() ? file_iter_.status() : Status::OK();
}
virtual void SetPinnedItersMgr(
PinnedIteratorsManager* pinned_iters_mgr) override {
pinned_iters_mgr_ = pinned_iters_mgr;
if (file_iter_.iter()) {
file_iter_.SetPinnedItersMgr(pinned_iters_mgr);
}
}
virtual bool IsKeyPinned() const override {
return pinned_iters_mgr_ && pinned_iters_mgr_->PinningEnabled() &&
file_iter_.iter() && file_iter_.IsKeyPinned();
}
virtual bool IsValuePinned() const override {
return pinned_iters_mgr_ && pinned_iters_mgr_->PinningEnabled() &&
file_iter_.iter() && file_iter_.IsValuePinned();
}
private:
void SkipEmptyFileForward();
void SkipEmptyFileBackward();
void SetFileIterator(InternalIterator* iter);
void InitFileIterator(size_t new_file_index);
const Slice& file_smallest_key(size_t file_index) {
assert(file_index < flevel_->num_files);
return flevel_->files[file_index].smallest_key;
}
bool KeyReachedUpperBound(const Slice& internal_key) {
return read_options_.iterate_upper_bound != nullptr &&
icomparator_.user_comparator()->Compare(
ExtractUserKey(internal_key),
*read_options_.iterate_upper_bound) >= 0;
}
InternalIterator* NewFileIterator() {
assert(file_index_ < flevel_->num_files);
auto file_meta = flevel_->files[file_index_];
if (should_sample_) {
sample_file_read_inc(file_meta.file_metadata);
}
const InternalKey* smallest_compaction_key = nullptr;
const InternalKey* largest_compaction_key = nullptr;
if (compaction_boundaries_ != nullptr) {
smallest_compaction_key = (*compaction_boundaries_)[file_index_].smallest;
largest_compaction_key = (*compaction_boundaries_)[file_index_].largest;
}
return table_cache_->NewIterator(
read_options_, env_options_, icomparator_, *file_meta.file_metadata,
range_del_agg_, prefix_extractor_,
nullptr /* don't need reference to table */,
file_read_hist_, for_compaction_, nullptr /* arena */, skip_filters_,
level_, smallest_compaction_key, largest_compaction_key);
}
TableCache* table_cache_;
const ReadOptions read_options_;
const EnvOptions& env_options_;
const InternalKeyComparator& icomparator_;
const LevelFilesBrief* flevel_;
mutable FileDescriptor current_value_;
const SliceTransform* prefix_extractor_;
HistogramImpl* file_read_hist_;
bool should_sample_;
bool for_compaction_;
bool skip_filters_;
size_t file_index_;
int level_;
RangeDelAggregator* range_del_agg_;
IteratorWrapper file_iter_; // May be nullptr
PinnedIteratorsManager* pinned_iters_mgr_;
// To be propagated to RangeDelAggregator in order to safely truncate range
// tombstones.
const std::vector<AtomicCompactionUnitBoundary>* compaction_boundaries_;
};
void LevelIterator::Seek(const Slice& target) {
size_t new_file_index = FindFile(icomparator_, *flevel_, target);
InitFileIterator(new_file_index);
if (file_iter_.iter() != nullptr) {
file_iter_.Seek(target);
}
SkipEmptyFileForward();
}
void LevelIterator::SeekForPrev(const Slice& target) {
size_t new_file_index = FindFile(icomparator_, *flevel_, target);
if (new_file_index >= flevel_->num_files) {
new_file_index = flevel_->num_files - 1;
}
InitFileIterator(new_file_index);
if (file_iter_.iter() != nullptr) {
file_iter_.SeekForPrev(target);
SkipEmptyFileBackward();
}
}
void LevelIterator::SeekToFirst() {
InitFileIterator(0);
if (file_iter_.iter() != nullptr) {
file_iter_.SeekToFirst();
}
SkipEmptyFileForward();
}
void LevelIterator::SeekToLast() {
InitFileIterator(flevel_->num_files - 1);
if (file_iter_.iter() != nullptr) {
file_iter_.SeekToLast();
}
SkipEmptyFileBackward();
}
void LevelIterator::Next() {
assert(Valid());
file_iter_.Next();
SkipEmptyFileForward();
}
void LevelIterator::Prev() {
assert(Valid());
file_iter_.Prev();
SkipEmptyFileBackward();
}
void LevelIterator::SkipEmptyFileForward() {
while (file_iter_.iter() == nullptr ||
(!file_iter_.Valid() && file_iter_.status().ok() &&
!file_iter_.iter()->IsOutOfBound())) {
// Move to next file
if (file_index_ >= flevel_->num_files - 1) {
// Already at the last file
SetFileIterator(nullptr);
return;
}
if (KeyReachedUpperBound(file_smallest_key(file_index_ + 1))) {
SetFileIterator(nullptr);
return;
}
InitFileIterator(file_index_ + 1);
if (file_iter_.iter() != nullptr) {
file_iter_.SeekToFirst();
}
}
}
void LevelIterator::SkipEmptyFileBackward() {
while (file_iter_.iter() == nullptr ||
(!file_iter_.Valid() && file_iter_.status().ok())) {
// Move to previous file
if (file_index_ == 0) {
// Already the first file
SetFileIterator(nullptr);
return;
}
InitFileIterator(file_index_ - 1);
if (file_iter_.iter() != nullptr) {
file_iter_.SeekToLast();
}
}
}
void LevelIterator::SetFileIterator(InternalIterator* iter) {
if (pinned_iters_mgr_ && iter) {
iter->SetPinnedItersMgr(pinned_iters_mgr_);
}
InternalIterator* old_iter = file_iter_.Set(iter);
if (pinned_iters_mgr_ && pinned_iters_mgr_->PinningEnabled()) {
pinned_iters_mgr_->PinIterator(old_iter);
} else {
delete old_iter;
}
}
void LevelIterator::InitFileIterator(size_t new_file_index) {
if (new_file_index >= flevel_->num_files) {
file_index_ = new_file_index;
SetFileIterator(nullptr);
return;
} else {
// If the file iterator shows incomplete, we try it again if users seek
// to the same file, as this time we may go to a different data block
// which is cached in block cache.
//
if (file_iter_.iter() != nullptr && !file_iter_.status().IsIncomplete() &&
new_file_index == file_index_) {
// file_iter_ is already constructed with this iterator, so
// no need to change anything
} else {
file_index_ = new_file_index;
InternalIterator* iter = NewFileIterator();
SetFileIterator(iter);
}
}
}
// A wrapper of version builder which references the current version in
// constructor and unref it in the destructor.
// Both of the constructor and destructor need to be called inside DB Mutex.
class BaseReferencedVersionBuilder {
public:
explicit BaseReferencedVersionBuilder(ColumnFamilyData* cfd)
: version_builder_(new VersionBuilder(
cfd->current()->version_set()->env_options(), cfd->table_cache(),
cfd->current()->storage_info(), cfd->ioptions()->info_log)),
version_(cfd->current()) {
version_->Ref();
}
~BaseReferencedVersionBuilder() {
delete version_builder_;
version_->Unref();
}
VersionBuilder* version_builder() { return version_builder_; }
private:
VersionBuilder* version_builder_;
Version* version_;
};
} // anonymous namespace
Status Version::GetTableProperties(std::shared_ptr<const TableProperties>* tp,
const FileMetaData* file_meta,
const std::string* fname) const {
auto table_cache = cfd_->table_cache();
auto ioptions = cfd_->ioptions();
Status s = table_cache->GetTableProperties(
env_options_, cfd_->internal_comparator(), file_meta->fd, tp,
mutable_cf_options_.prefix_extractor.get(), true /* no io */);
if (s.ok()) {
return s;
}
// We only ignore error type `Incomplete` since it's by design that we
// disallow table when it's not in table cache.
if (!s.IsIncomplete()) {
return s;
}
// 2. Table is not present in table cache, we'll read the table properties
// directly from the properties block in the file.
std::unique_ptr<RandomAccessFile> file;
std::string file_name;
if (fname != nullptr) {
file_name = *fname;
} else {
file_name =
TableFileName(ioptions->cf_paths, file_meta->fd.GetNumber(),
file_meta->fd.GetPathId());
}
s = ioptions->env->NewRandomAccessFile(file_name, &file, env_options_);
if (!s.ok()) {
return s;
}
TableProperties* raw_table_properties;
// By setting the magic number to kInvalidTableMagicNumber, we can by
// pass the magic number check in the footer.
std::unique_ptr<RandomAccessFileReader> file_reader(
new RandomAccessFileReader(
std::move(file), file_name, nullptr /* env */, nullptr /* stats */,
0 /* hist_type */, nullptr /* file_read_hist */,
nullptr /* rate_limiter */, false /* for_compaction*/,
ioptions->listeners));
s = ReadTableProperties(
file_reader.get(), file_meta->fd.GetFileSize(),
Footer::kInvalidTableMagicNumber /* table's magic number */, *ioptions,
&raw_table_properties, false /* compression_type_missing */);
if (!s.ok()) {
return s;
}
RecordTick(ioptions->statistics, NUMBER_DIRECT_LOAD_TABLE_PROPERTIES);
*tp = std::shared_ptr<const TableProperties>(raw_table_properties);
return s;
}
Status Version::GetPropertiesOfAllTables(TablePropertiesCollection* props) {
Status s;
for (int level = 0; level < storage_info_.num_levels_; level++) {
s = GetPropertiesOfAllTables(props, level);
if (!s.ok()) {
return s;
}
}
return Status::OK();
}
Status Version::GetPropertiesOfAllTables(TablePropertiesCollection* props,
int level) {
for (const auto& file_meta : storage_info_.files_[level]) {
auto fname =
TableFileName(cfd_->ioptions()->cf_paths, file_meta->fd.GetNumber(),
file_meta->fd.GetPathId());
// 1. If the table is already present in table cache, load table
// properties from there.
std::shared_ptr<const TableProperties> table_properties;
Status s = GetTableProperties(&table_properties, file_meta, &fname);
if (s.ok()) {
props->insert({fname, table_properties});
} else {
return s;
}
}
return Status::OK();
}
Status Version::GetPropertiesOfTablesInRange(
const Range* range, std::size_t n, TablePropertiesCollection* props) const {
for (int level = 0; level < storage_info_.num_non_empty_levels(); level++) {
for (decltype(n) i = 0; i < n; i++) {
// Convert user_key into a corresponding internal key.
InternalKey k1(range[i].start, kMaxSequenceNumber, kValueTypeForSeek);
InternalKey k2(range[i].limit, kMaxSequenceNumber, kValueTypeForSeek);
std::vector<FileMetaData*> files;
storage_info_.GetOverlappingInputs(level, &k1, &k2, &files, -1, nullptr,
false);
for (const auto& file_meta : files) {
auto fname =
TableFileName(cfd_->ioptions()->cf_paths,
file_meta->fd.GetNumber(), file_meta->fd.GetPathId());
if (props->count(fname) == 0) {
// 1. If the table is already present in table cache, load table
// properties from there.
std::shared_ptr<const TableProperties> table_properties;
Status s = GetTableProperties(&table_properties, file_meta, &fname);
if (s.ok()) {
props->insert({fname, table_properties});
} else {
return s;
}
}
}
}
}
return Status::OK();
}
Status Version::GetAggregatedTableProperties(
std::shared_ptr<const TableProperties>* tp, int level) {
TablePropertiesCollection props;
Status s;
if (level < 0) {
s = GetPropertiesOfAllTables(&props);
} else {
s = GetPropertiesOfAllTables(&props, level);
}
if (!s.ok()) {
return s;
}
auto* new_tp = new TableProperties();
for (const auto& item : props) {
new_tp->Add(*item.second);
}
tp->reset(new_tp);
return Status::OK();
}
size_t Version::GetMemoryUsageByTableReaders() {
size_t total_usage = 0;
for (auto& file_level : storage_info_.level_files_brief_) {
for (size_t i = 0; i < file_level.num_files; i++) {
total_usage += cfd_->table_cache()->GetMemoryUsageByTableReader(
env_options_, cfd_->internal_comparator(), file_level.files[i].fd,
mutable_cf_options_.prefix_extractor.get());
}
}
return total_usage;
}
void Version::GetColumnFamilyMetaData(ColumnFamilyMetaData* cf_meta) {
assert(cf_meta);
assert(cfd_);
cf_meta->name = cfd_->GetName();
cf_meta->size = 0;
cf_meta->file_count = 0;
cf_meta->levels.clear();
auto* ioptions = cfd_->ioptions();
auto* vstorage = storage_info();
for (int level = 0; level < cfd_->NumberLevels(); level++) {
uint64_t level_size = 0;
cf_meta->file_count += vstorage->LevelFiles(level).size();
std::vector<SstFileMetaData> files;
for (const auto& file : vstorage->LevelFiles(level)) {
uint32_t path_id = file->fd.GetPathId();
std::string file_path;
if (path_id < ioptions->cf_paths.size()) {
file_path = ioptions->cf_paths[path_id].path;
} else {
assert(!ioptions->cf_paths.empty());
file_path = ioptions->cf_paths.back().path;
}
files.emplace_back(SstFileMetaData{
MakeTableFileName("", file->fd.GetNumber()),
file_path,
static_cast<size_t>(file->fd.GetFileSize()),
file->fd.smallest_seqno,
file->fd.largest_seqno,
file->smallest.user_key().ToString(),
file->largest.user_key().ToString(),
file->stats.num_reads_sampled.load(std::memory_order_relaxed),
file->being_compacted});
files.back().num_entries = file->num_entries;
files.back().num_deletions = file->num_deletions;
level_size += file->fd.GetFileSize();
}
cf_meta->levels.emplace_back(
level, level_size, std::move(files));
cf_meta->size += level_size;
}
}
uint64_t Version::GetSstFilesSize() {
uint64_t sst_files_size = 0;
for (int level = 0; level < storage_info_.num_levels_; level++) {
for (const auto& file_meta : storage_info_.LevelFiles(level)) {
sst_files_size += file_meta->fd.GetFileSize();
}
}
return sst_files_size;
}
uint64_t VersionStorageInfo::GetEstimatedActiveKeys() const {
// Estimation will be inaccurate when:
// (1) there exist merge keys
// (2) keys are directly overwritten
// (3) deletion on non-existing keys
// (4) low number of samples
if (current_num_samples_ == 0) {
return 0;
}
if (current_num_non_deletions_ <= current_num_deletions_) {
return 0;
}
uint64_t est = current_num_non_deletions_ - current_num_deletions_;
uint64_t file_count = 0;
for (int level = 0; level < num_levels_; ++level) {
file_count += files_[level].size();
}
if (current_num_samples_ < file_count) {
// casting to avoid overflowing
return
static_cast<uint64_t>(
(est * static_cast<double>(file_count) / current_num_samples_)
);
} else {
return est;
}
}
double VersionStorageInfo::GetEstimatedCompressionRatioAtLevel(
int level) const {
assert(level < num_levels_);
uint64_t sum_file_size_bytes = 0;
uint64_t sum_data_size_bytes = 0;
for (auto* file_meta : files_[level]) {
sum_file_size_bytes += file_meta->fd.GetFileSize();
sum_data_size_bytes += file_meta->raw_key_size + file_meta->raw_value_size;
}
if (sum_file_size_bytes == 0) {
return -1.0;
}
return static_cast<double>(sum_data_size_bytes) / sum_file_size_bytes;
}
void Version::AddIterators(const ReadOptions& read_options,
const EnvOptions& soptions,
MergeIteratorBuilder* merge_iter_builder,
RangeDelAggregator* range_del_agg) {
assert(storage_info_.finalized_);