-
Notifications
You must be signed in to change notification settings - Fork 2
/
Copy pathdb_impl.cc
1485 lines (1338 loc) · 54.9 KB
/
db_impl.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 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/db_impl.h"
#include <algorithm>
#include <set>
#include <string>
#include <stdint.h>
#include <stdio.h>
#include <vector>
#include "db/builder.h"
#include "db/db_iter.h"
#include "db/dbformat.h"
#include "db/filename.h"
#include "db/log_reader.h"
#include "db/log_writer.h"
#include "db/memtable.h"
#include "db/table_cache.h"
#include "db/version_set.h"
#include "db/write_batch_internal.h"
#include "leveldb/db.h"
#include "leveldb/env.h"
#include "leveldb/status.h"
#include "leveldb/table.h"
#include "leveldb/table_builder.h"
#include "port/port.h"
#include "table/block.h"
#include "table/merger.h"
#include "table/two_level_iterator.h"
#include "util/coding.h"
#include "util/logging.h"
#include "util/mutexlock.h"
// comment by donzell.如果没有compact，leveldb的逻辑真是简单优美.
// write:先把WriteBatch序列化写入LOG,然后插入memtable。
// read:先读memetable，然后level0,然后level 1-7.
// 但是compact是必须的，每次compact生成一个新的version;
namespace leveldb {
// Information kept for every waiting writer
struct DBImpl::Writer {
Status status;
WriteBatch* batch;
bool sync;
bool done;
port::CondVar cv;
explicit Writer(port::Mutex* mu) : cv(mu) { }
};
struct DBImpl::CompactionState {
Compaction* const compaction;
// comment by donzell.所有snapshot里边最小的那个seq，如果一个操作的seq=S，S <= smallest_snapshot，那么相同key的seq<S的都可以丢弃了。
// 因为在S已经<=smallest_snapshot，S之下没有snapshot了，seq < S，之需要保留S即可。
// Sequence numbers < smallest_snapshot are not significant since we
// will never have to service a snapshot below smallest_snapshot.
// Therefore if we have seen a sequence number S <= smallest_snapshot,
// we can drop all entries for the same key with sequence numbers < S.
SequenceNumber smallest_snapshot;
// Files produced by compaction
struct Output {
uint64_t number;
uint64_t file_size;
InternalKey smallest, largest;
};
std::vector<Output> outputs;
// State kept for output being generated
WritableFile* outfile;
TableBuilder* builder;
uint64_t total_bytes;
Output* current_output() { return &outputs[outputs.size()-1]; }
explicit CompactionState(Compaction* c)
: compaction(c),
outfile(NULL),
builder(NULL),
total_bytes(0) {
}
};
// Fix user-supplied options to be reasonable
template <class T,class V>
static void ClipToRange(T* ptr, V minvalue, V maxvalue) {
if (static_cast<V>(*ptr) > maxvalue) *ptr = maxvalue;
if (static_cast<V>(*ptr) < minvalue) *ptr = minvalue;
}
Options SanitizeOptions(const std::string& dbname,
const InternalKeyComparator* icmp,
const InternalFilterPolicy* ipolicy,
const Options& src) {
Options result = src;
result.comparator = icmp;
result.filter_policy = (src.filter_policy != NULL) ? ipolicy : NULL;
ClipToRange(&result.max_open_files, 20, 50000);
ClipToRange(&result.write_buffer_size, 64<<10, 1<<30);
ClipToRange(&result.block_size, 1<<10, 4<<20);
if (result.info_log == NULL) {
// Open a log file in the same directory as the db
src.env->CreateDir(dbname); // In case it does not exist
src.env->RenameFile(InfoLogFileName(dbname), OldInfoLogFileName(dbname));
Status s = src.env->NewLogger(InfoLogFileName(dbname), &result.info_log);
if (!s.ok()) {
// No place suitable for logging
result.info_log = NULL;
}
}
if (result.block_cache == NULL) {
result.block_cache = NewLRUCache(8 << 20);
}
return result;
}
DBImpl::DBImpl(const Options& options, const std::string& dbname)
: env_(options.env),
internal_comparator_(options.comparator),
internal_filter_policy_(options.filter_policy),
options_(SanitizeOptions(
dbname, &internal_comparator_, &internal_filter_policy_, options)),
owns_info_log_(options_.info_log != options.info_log),
owns_cache_(options_.block_cache != options.block_cache),
dbname_(dbname),
db_lock_(NULL),
shutting_down_(NULL),
bg_cv_(&mutex_),
mem_(new MemTable(internal_comparator_)),
imm_(NULL),
logfile_(NULL),
logfile_number_(0),
log_(NULL),
tmp_batch_(new WriteBatch),
bg_compaction_scheduled_(false),
manual_compaction_(NULL) {
mem_->Ref();
has_imm_.Release_Store(NULL);
// Reserve ten files or so for other uses and give the rest to TableCache.
const int table_cache_size = options.max_open_files - 10;
table_cache_ = new TableCache(dbname_, &options_, table_cache_size);
versions_ = new VersionSet(dbname_, &options_, table_cache_,
&internal_comparator_);
}
DBImpl::~DBImpl() {
// Wait for background work to finish
mutex_.Lock();
shutting_down_.Release_Store(this); // Any non-NULL value is ok
while (bg_compaction_scheduled_) {
bg_cv_.Wait();
}
mutex_.Unlock();
if (db_lock_ != NULL) {
env_->UnlockFile(db_lock_);
}
delete versions_;
if (mem_ != NULL) mem_->Unref();
if (imm_ != NULL) imm_->Unref();
delete tmp_batch_;
delete log_;
delete logfile_;
delete table_cache_;
if (owns_info_log_) {
delete options_.info_log;
}
if (owns_cache_) {
delete options_.block_cache;
}
}
// comment by donzell.create_if_missing的时候调用。就是用一个空的versionedit作为manifest，然后把current指向此manifest.之后的Recover流程会把它作为Db状态
Status DBImpl::NewDB() {
VersionEdit new_db;
new_db.SetComparatorName(user_comparator()->Name());
new_db.SetLogNumber(0);
new_db.SetNextFile(2);
new_db.SetLastSequence(0);
const std::string manifest = DescriptorFileName(dbname_, 1);
WritableFile* file;
Status s = env_->NewWritableFile(manifest, &file);
if (!s.ok()) {
return s;
}
{
log::Writer log(file);
std::string record;
new_db.EncodeTo(&record);
s = log.AddRecord(record);
if (s.ok()) {
s = file->Close();
}
}
delete file;
if (s.ok()) {
// Make "CURRENT" file that points to the new manifest file.
s = SetCurrentFile(env_, dbname_, 1);
} else {
env_->DeleteFile(manifest);
}
return s;
}
void DBImpl::MaybeIgnoreError(Status* s) const {
if (s->ok() || options_.paranoid_checks) {
// No change needed
} else {
Log(options_.info_log, "Ignoring error %s", s->ToString().c_str());
*s = Status::OK();
}
}
void DBImpl::DeleteObsoleteFiles() {
// Make a set of all of the live files
std::set<uint64_t> live = pending_outputs_;
versions_->AddLiveFiles(&live);
std::vector<std::string> filenames;
env_->GetChildren(dbname_, &filenames); // Ignoring errors on purpose
uint64_t number;
FileType type;
for (size_t i = 0; i < filenames.size(); i++) {
if (ParseFileName(filenames[i], &number, &type)) {
bool keep = true;
switch (type) {
case kLogFile:
keep = ((number >= versions_->LogNumber()) ||
(number == versions_->PrevLogNumber()));
break;
case kDescriptorFile:
// Keep my manifest file, and any newer incarnations'
// (in case there is a race that allows other incarnations)
keep = (number >= versions_->ManifestFileNumber());
break;
case kTableFile:
keep = (live.find(number) != live.end());
break;
case kTempFile:
// Any temp files that are currently being written to must
// be recorded in pending_outputs_, which is inserted into "live"
keep = (live.find(number) != live.end());
break;
case kCurrentFile:
case kDBLockFile:
case kInfoLogFile:
keep = true;
break;
}
if (!keep) {
if (type == kTableFile) {
table_cache_->Evict(number);
}
Log(options_.info_log, "Delete type=%d #%lld\n",
int(type),
static_cast<unsigned long long>(number));
env_->DeleteFile(dbname_ + "/" + filenames[i]);
}
}
}
}
Status DBImpl::Recover(VersionEdit* edit) {
mutex_.AssertHeld();
// Ignore error from CreateDir since the creation of the DB is
// committed only when the descriptor is created, and this directory
// may already exist from a previous failed creation attempt.
env_->CreateDir(dbname_);
assert(db_lock_ == NULL);
Status s = env_->LockFile(LockFileName(dbname_), &db_lock_);
if (!s.ok()) {
return s;
}
if (!env_->FileExists(CurrentFileName(dbname_))) {
if (options_.create_if_missing) {
s = NewDB();
if (!s.ok()) {
return s;
}
} else {
return Status::InvalidArgument(
dbname_, "does not exist (create_if_missing is false)");
}
} else {
if (options_.error_if_exists) {
return Status::InvalidArgument(
dbname_, "exists (error_if_exists is true)");
}
}
// comment by donzell.成功后，versionset就恢复到了退出前的状态,还需1、检查是否缺少version中的文件2、回放log中的命令。
s = versions_->Recover();
if (s.ok()) {
SequenceNumber max_sequence(0);
// Recover from all newer log files than the ones named in the
// descriptor (new log files may have been added by the previous
// incarnation without registering them in the descriptor).
//
// Note that PrevLogNumber() is no longer used, but we pay
// attention to it in case we are recovering a database
// produced by an older version of leveldb.
const uint64_t min_log = versions_->LogNumber();
const uint64_t prev_log = versions_->PrevLogNumber();
std::vector<std::string> filenames;
s = env_->GetChildren(dbname_, &filenames);
if (!s.ok()) {
return s;
}
std::set<uint64_t> expected;
versions_->AddLiveFiles(&expected);
uint64_t number;
FileType type;
std::vector<uint64_t> logs;
for (size_t i = 0; i < filenames.size(); i++) {
if (ParseFileName(filenames[i], &number, &type)) {
expected.erase(number);
if (type == kLogFile && ((number >= min_log) || (number == prev_log)))
logs.push_back(number);
}
}
if (!expected.empty()) {
char buf[50];
snprintf(buf, sizeof(buf), "%d missing files; e.g.",
static_cast<int>(expected.size()));
return Status::Corruption(buf, TableFileName(dbname_, *(expected.begin())));
}
// comment by donzell.以上代码是要求versionset中出现的文件都必须在磁盘上有，也就是保存versionset时，一定是先把manifest文件刷到磁盘上之后，才能删除旧文件。see Open是在LogAndApply之后才DeleteObsoleteFiles的。
// Recover in the order in which the logs were generated
std::sort(logs.begin(), logs.end());
for (size_t i = 0; i < logs.size(); i++) {
s = RecoverLogFile(logs[i], edit, &max_sequence);
// The previous incarnation may not have written any MANIFEST
// records after allocating this log number. So we manually
// update the file number allocation counter in VersionSet.
versions_->MarkFileNumberUsed(logs[i]);
}
if (s.ok()) {
if (versions_->LastSequence() < max_sequence) {
versions_->SetLastSequence(max_sequence);
}
}
}
return s;
}
Status DBImpl::RecoverLogFile(uint64_t log_number,
VersionEdit* edit,
SequenceNumber* max_sequence) {
struct LogReporter : public log::Reader::Reporter {
Env* env;
Logger* info_log;
const char* fname;
Status* status; // NULL if options_.paranoid_checks==false
virtual void Corruption(size_t bytes, const Status& s) {
Log(info_log, "%s%s: dropping %d bytes; %s",
(this->status == NULL ? "(ignoring error) " : ""),
fname, static_cast<int>(bytes), s.ToString().c_str());
if (this->status != NULL && this->status->ok()) *this->status = s;
}
};
mutex_.AssertHeld();
// Open the log file
std::string fname = LogFileName(dbname_, log_number);
SequentialFile* file;
Status status = env_->NewSequentialFile(fname, &file);
if (!status.ok()) {
MaybeIgnoreError(&status);
return status;
}
// Create the log reader.
LogReporter reporter;
reporter.env = env_;
reporter.info_log = options_.info_log;
reporter.fname = fname.c_str();
reporter.status = (options_.paranoid_checks ? &status : NULL);
// We intentially make log::Reader do checksumming even if
// paranoid_checks==false so that corruptions cause entire commits
// to be skipped instead of propagating bad information (like overly
// large sequence numbers).
log::Reader reader(file, &reporter, true/*checksum*/,
0/*initial_offset*/);
Log(options_.info_log, "Recovering log #%llu",
(unsigned long long) log_number);
// Read all the records and add to a memtable
std::string scratch;
Slice record;
WriteBatch batch;
MemTable* mem = NULL;
while (reader.ReadRecord(&record, &scratch) &&
status.ok()) {
if (record.size() < 12) {
reporter.Corruption(
record.size(), Status::Corruption("log record too small"));
continue;
}
WriteBatchInternal::SetContents(&batch, record);
if (mem == NULL) {
mem = new MemTable(internal_comparator_);
mem->Ref();
}
status = WriteBatchInternal::InsertInto(&batch, mem);
MaybeIgnoreError(&status);
if (!status.ok()) {
break;
}
const SequenceNumber last_seq =
WriteBatchInternal::Sequence(&batch) +
WriteBatchInternal::Count(&batch) - 1;
if (last_seq > *max_sequence) {
*max_sequence = last_seq;
}
if (mem->ApproximateMemoryUsage() > options_.write_buffer_size) {
status = WriteLevel0Table(mem, edit, NULL);
if (!status.ok()) {
// Reflect errors immediately so that conditions like full
// file-systems cause the DB::Open() to fail.
break;
}
mem->Unref();
mem = NULL;
}
}
if (status.ok() && mem != NULL) {
status = WriteLevel0Table(mem, edit, NULL);
// Reflect errors immediately so that conditions like full
// file-systems cause the DB::Open() to fail.
}
if (mem != NULL) mem->Unref();
delete file;
return status;
}
Status DBImpl::WriteLevel0Table(MemTable* mem, VersionEdit* edit,
Version* base) {
mutex_.AssertHeld();
const uint64_t start_micros = env_->NowMicros();
FileMetaData meta;
meta.number = versions_->NewFileNumber();
pending_outputs_.insert(meta.number);
Iterator* iter = mem->NewIterator();
Log(options_.info_log, "Level-0 table #%llu: started",
(unsigned long long) meta.number);
Status s;
{
mutex_.Unlock();
s = BuildTable(dbname_, env_, options_, table_cache_, iter, &meta);
mutex_.Lock();
}
Log(options_.info_log, "Level-0 table #%llu: %lld bytes %s",
(unsigned long long) meta.number,
(unsigned long long) meta.file_size,
s.ToString().c_str());
delete iter;
pending_outputs_.erase(meta.number);
// Note that if file_size is zero, the file has been deleted and
// should not be added to the manifest.
int level = 0;
if (s.ok() && meta.file_size > 0) {
const Slice min_user_key = meta.smallest.user_key();
const Slice max_user_key = meta.largest.user_key();
if (base != NULL) {
level = base->PickLevelForMemTableOutput(min_user_key, max_user_key);
}
edit->AddFile(level, meta.number, meta.file_size,
meta.smallest, meta.largest);
}
CompactionStats stats;
stats.micros = env_->NowMicros() - start_micros;
stats.bytes_written = meta.file_size;
stats_[level].Add(stats);
return s;
}
Status DBImpl::CompactMemTable() {
mutex_.AssertHeld();
assert(imm_ != NULL);
// Save the contents of the memtable as a new Table
VersionEdit edit;
Version* base = versions_->current();
base->Ref();
Status s = WriteLevel0Table(imm_, &edit, base);
base->Unref();
if (s.ok() && shutting_down_.Acquire_Load()) {
s = Status::IOError("Deleting DB during memtable compaction");
}
// Replace immutable memtable with the generated Table
if (s.ok()) {
edit.SetPrevLogNumber(0);
edit.SetLogNumber(logfile_number_); // Earlier logs no longer needed
s = versions_->LogAndApply(&edit, &mutex_);
}
if (s.ok()) {
// Commit to the new state
imm_->Unref();
imm_ = NULL;
has_imm_.Release_Store(NULL);
DeleteObsoleteFiles();
}
return s;
}
void DBImpl::CompactRange(const Slice* begin, const Slice* end) {
int max_level_with_files = 1;
{
MutexLock l(&mutex_);
Version* base = versions_->current();
for (int level = 1; level < config::kNumLevels; level++) {
if (base->OverlapInLevel(level, begin, end)) {
max_level_with_files = level;
}
}
}
TEST_CompactMemTable(); // TODO(sanjay): Skip if memtable does not overlap
for (int level = 0; level < max_level_with_files; level++) {
TEST_CompactRange(level, begin, end);
}
}
void DBImpl::TEST_CompactRange(int level, const Slice* begin,const Slice* end) {
assert(level >= 0);
assert(level + 1 < config::kNumLevels);
InternalKey begin_storage, end_storage;
ManualCompaction manual;
manual.level = level;
manual.done = false;
if (begin == NULL) {
manual.begin = NULL;
} else {
begin_storage = InternalKey(*begin, kMaxSequenceNumber, kValueTypeForSeek);
manual.begin = &begin_storage;
}
if (end == NULL) {
manual.end = NULL;
} else {
end_storage = InternalKey(*end, 0, static_cast<ValueType>(0));
manual.end = &end_storage;
}
MutexLock l(&mutex_);
while (!manual.done) {
while (manual_compaction_ != NULL) {
bg_cv_.Wait();
}
manual_compaction_ = &manual;
MaybeScheduleCompaction();
while (manual_compaction_ == &manual) {
bg_cv_.Wait();
}
}
}
Status DBImpl::TEST_CompactMemTable() {
// NULL batch means just wait for earlier writes to be done
Status s = Write(WriteOptions(), NULL);
if (s.ok()) {
// Wait until the compaction completes
MutexLock l(&mutex_);
while (imm_ != NULL && bg_error_.ok()) {
bg_cv_.Wait();
}
if (imm_ != NULL) {
s = bg_error_;
}
}
return s;
}
void DBImpl::MaybeScheduleCompaction() {
mutex_.AssertHeld();
if (bg_compaction_scheduled_) {
// Already scheduled
} else if (shutting_down_.Acquire_Load()) {
// DB is being deleted; no more background compactions
} else if (imm_ == NULL &&
manual_compaction_ == NULL &&
!versions_->NeedsCompaction()) {
// No work to be done
} else {
bg_compaction_scheduled_ = true;
env_->Schedule(&DBImpl::BGWork, this);
}
}
void DBImpl::BGWork(void* db) {
reinterpret_cast<DBImpl*>(db)->BackgroundCall();
}
void DBImpl::BackgroundCall() {
MutexLock l(&mutex_);
assert(bg_compaction_scheduled_);
if (!shutting_down_.Acquire_Load()) {
Status s = BackgroundCompaction();
if (s.ok()) {
// Success
} else if (shutting_down_.Acquire_Load()) {
// Error most likely due to shutdown; do not wait
} else {
// Wait a little bit before retrying background compaction in
// case this is an environmental problem and we do not want to
// chew up resources for failed compactions for the duration of
// the problem.
bg_cv_.SignalAll(); // In case a waiter can proceed despite the error
Log(options_.info_log, "Waiting after background compaction error: %s",
s.ToString().c_str());
mutex_.Unlock();
env_->SleepForMicroseconds(1000000);
mutex_.Lock();
}
}
bg_compaction_scheduled_ = false;
// Previous compaction may have produced too many files in a level,
// so reschedule another compaction if needed.
MaybeScheduleCompaction();
bg_cv_.SignalAll();
}
Status DBImpl::BackgroundCompaction() {
mutex_.AssertHeld();
if (imm_ != NULL) {
return CompactMemTable();
}
Compaction* c;
bool is_manual = (manual_compaction_ != NULL);
InternalKey manual_end;
if (is_manual) {
ManualCompaction* m = manual_compaction_;
c = versions_->CompactRange(m->level, m->begin, m->end);
m->done = (c == NULL);
if (c != NULL) {
manual_end = c->input(0, c->num_input_files(0) - 1)->largest;
}
Log(options_.info_log,
"Manual compaction at level-%d from %s .. %s; will stop at %s\n",
m->level,
(m->begin ? m->begin->DebugString().c_str() : "(begin)"),
(m->end ? m->end->DebugString().c_str() : "(end)"),
(m->done ? "(end)" : manual_end.DebugString().c_str()));
} else {
c = versions_->PickCompaction();
}
Status status;
if (c == NULL) {
// Nothing to do
} else if (!is_manual && c->IsTrivialMove()) {
// Move file to next level
assert(c->num_input_files(0) == 1);
FileMetaData* f = c->input(0, 0);
c->edit()->DeleteFile(c->level(), f->number);
c->edit()->AddFile(c->level() + 1, f->number, f->file_size,
f->smallest, f->largest);
status = versions_->LogAndApply(c->edit(), &mutex_);
VersionSet::LevelSummaryStorage tmp;
Log(options_.info_log, "Moved #%lld to level-%d %lld bytes %s: %s\n",
static_cast<unsigned long long>(f->number),
c->level() + 1,
static_cast<unsigned long long>(f->file_size),
status.ToString().c_str(),
versions_->LevelSummary(&tmp));
} else {
CompactionState* compact = new CompactionState(c);
status = DoCompactionWork(compact);
CleanupCompaction(compact);
c->ReleaseInputs();
DeleteObsoleteFiles();
}
delete c;
if (status.ok()) {
// Done
} else if (shutting_down_.Acquire_Load()) {
// Ignore compaction errors found during shutting down
} else {
Log(options_.info_log,
"Compaction error: %s", status.ToString().c_str());
if (options_.paranoid_checks && bg_error_.ok()) {
bg_error_ = status;
}
}
if (is_manual) {
ManualCompaction* m = manual_compaction_;
if (!status.ok()) {
m->done = true;
}
if (!m->done) {
// We only compacted part of the requested range. Update *m
// to the range that is left to be compacted.
m->tmp_storage = manual_end;
m->begin = &m->tmp_storage;
}
manual_compaction_ = NULL;
}
return status;
}
void DBImpl::CleanupCompaction(CompactionState* compact) {
mutex_.AssertHeld();
if (compact->builder != NULL) {
// May happen if we get a shutdown call in the middle of compaction
compact->builder->Abandon();
delete compact->builder;
} else {
assert(compact->outfile == NULL);
}
delete compact->outfile;
for (size_t i = 0; i < compact->outputs.size(); i++) {
const CompactionState::Output& out = compact->outputs[i];
pending_outputs_.erase(out.number);
}
delete compact;
}
Status DBImpl::OpenCompactionOutputFile(CompactionState* compact) {
assert(compact != NULL);
assert(compact->builder == NULL);
uint64_t file_number;
{
mutex_.Lock();
file_number = versions_->NewFileNumber();
pending_outputs_.insert(file_number);
CompactionState::Output out;
out.number = file_number;
out.smallest.Clear();
out.largest.Clear();
compact->outputs.push_back(out);
mutex_.Unlock();
}
// Make the output file
std::string fname = TableFileName(dbname_, file_number);
Status s = env_->NewWritableFile(fname, &compact->outfile);
if (s.ok()) {
compact->builder = new TableBuilder(options_, compact->outfile);
}
return s;
}
Status DBImpl::FinishCompactionOutputFile(CompactionState* compact,
Iterator* input) {
assert(compact != NULL);
assert(compact->outfile != NULL);
assert(compact->builder != NULL);
const uint64_t output_number = compact->current_output()->number;
assert(output_number != 0);
// Check for iterator errors
Status s = input->status();
const uint64_t current_entries = compact->builder->NumEntries();
if (s.ok()) {
s = compact->builder->Finish();
} else {
compact->builder->Abandon();
}
const uint64_t current_bytes = compact->builder->FileSize();
compact->current_output()->file_size = current_bytes;
compact->total_bytes += current_bytes;
delete compact->builder;
compact->builder = NULL;
// Finish and check for file errors
if (s.ok()) {
s = compact->outfile->Sync();
}
if (s.ok()) {
s = compact->outfile->Close();
}
delete compact->outfile;
compact->outfile = NULL;
if (s.ok() && current_entries > 0) {
// Verify that the table is usable
Iterator* iter = table_cache_->NewIterator(ReadOptions(),
output_number,
current_bytes);
s = iter->status();
delete iter;
if (s.ok()) {
Log(options_.info_log,
"Generated table #%llu: %lld keys, %lld bytes",
(unsigned long long) output_number,
(unsigned long long) current_entries,
(unsigned long long) current_bytes);
}
}
return s;
}
Status DBImpl::InstallCompactionResults(CompactionState* compact) {
mutex_.AssertHeld();
Log(options_.info_log, "Compacted %d@%d + %d@%d files => %lld bytes",
compact->compaction->num_input_files(0),
compact->compaction->level(),
compact->compaction->num_input_files(1),
compact->compaction->level() + 1,
static_cast<long long>(compact->total_bytes));
// Add compaction outputs
compact->compaction->AddInputDeletions(compact->compaction->edit());
const int level = compact->compaction->level();
for (size_t i = 0; i < compact->outputs.size(); i++) {
const CompactionState::Output& out = compact->outputs[i];
compact->compaction->edit()->AddFile(
level + 1,
out.number, out.file_size, out.smallest, out.largest);
}
return versions_->LogAndApply(compact->compaction->edit(), &mutex_);
}
Status DBImpl::DoCompactionWork(CompactionState* compact) {
const uint64_t start_micros = env_->NowMicros();
int64_t imm_micros = 0; // Micros spent doing imm_ compactions
Log(options_.info_log, "Compacting %d@%d + %d@%d files",
compact->compaction->num_input_files(0),
compact->compaction->level(),
compact->compaction->num_input_files(1),
compact->compaction->level() + 1);
assert(versions_->NumLevelFiles(compact->compaction->level()) > 0);
assert(compact->builder == NULL);
assert(compact->outfile == NULL);
if (snapshots_.empty()) {
compact->smallest_snapshot = versions_->LastSequence();
} else {
compact->smallest_snapshot = snapshots_.oldest()->number_;
}
// Release mutex while we're actually doing the compaction work
mutex_.Unlock();
Iterator* input = versions_->MakeInputIterator(compact->compaction);
input->SeekToFirst();
Status status;
ParsedInternalKey ikey;
std::string current_user_key;
bool has_current_user_key = false;
SequenceNumber last_sequence_for_key = kMaxSequenceNumber;
for (; input->Valid() && !shutting_down_.Acquire_Load(); ) {
// Prioritize immutable compaction work
if (has_imm_.NoBarrier_Load() != NULL) {
const uint64_t imm_start = env_->NowMicros();
mutex_.Lock();
if (imm_ != NULL) {
CompactMemTable();
bg_cv_.SignalAll(); // Wakeup MakeRoomForWrite() if necessary
}
mutex_.Unlock();
imm_micros += (env_->NowMicros() - imm_start);
}
Slice key = input->key();
if (compact->compaction->ShouldStopBefore(key) &&
compact->builder != NULL) {
status = FinishCompactionOutputFile(compact, input);
if (!status.ok()) {
break;
}
}
// Handle key/value, add to state, etc.
bool drop = false;
if (!ParseInternalKey(key, &ikey)) {
// Do not hide error keys
current_user_key.clear();
has_current_user_key = false;
last_sequence_for_key = kMaxSequenceNumber;
} else {
if (!has_current_user_key ||
user_comparator()->Compare(ikey.user_key,
Slice(current_user_key)) != 0) {
// First occurrence of this user key
current_user_key.assign(ikey.user_key.data(), ikey.user_key.size());
has_current_user_key = true;
last_sequence_for_key = kMaxSequenceNumber;
}
if (last_sequence_for_key <= compact->smallest_snapshot) {
// Hidden by an newer entry for same user key
drop = true; // (A)
} else if (ikey.type == kTypeDeletion &&
ikey.sequence <= compact->smallest_snapshot &&
compact->compaction->IsBaseLevelForKey(ikey.user_key)) {
// For this user key:
// (1) there is no data in higher levels
// (2) data in lower levels will have larger sequence numbers
// (3) data in layers that are being compacted here and have
// smaller sequence numbers will be dropped in the next
// few iterations of this loop (by rule (A) above).
// Therefore this deletion marker is obsolete and can be dropped.
drop = true;
}
last_sequence_for_key = ikey.sequence;
}
#if 0
Log(options_.info_log,
" Compact: %s, seq %d, type: %d %d, drop: %d, is_base: %d, "
"%d smallest_snapshot: %d",
ikey.user_key.ToString().c_str(),
(int)ikey.sequence, ikey.type, kTypeValue, drop,
compact->compaction->IsBaseLevelForKey(ikey.user_key),
(int)last_sequence_for_key, (int)compact->smallest_snapshot);
#endif
if (!drop) {
// Open output file if necessary
if (compact->builder == NULL) {
status = OpenCompactionOutputFile(compact);
if (!status.ok()) {
break;
}
}
if (compact->builder->NumEntries() == 0) {
compact->current_output()->smallest.DecodeFrom(key);
}
compact->current_output()->largest.DecodeFrom(key);
compact->builder->Add(key, input->value());
// Close output file if it is big enough
if (compact->builder->FileSize() >=
compact->compaction->MaxOutputFileSize()) {
status = FinishCompactionOutputFile(compact, input);
if (!status.ok()) {
break;
}
}
}
input->Next();
}
if (status.ok() && shutting_down_.Acquire_Load()) {
status = Status::IOError("Deleting DB during compaction");
}
if (status.ok() && compact->builder != NULL) {
status = FinishCompactionOutputFile(compact, input);
}
if (status.ok()) {
status = input->status();
}
delete input;
input = NULL;
CompactionStats stats;
stats.micros = env_->NowMicros() - start_micros - imm_micros;
for (int which = 0; which < 2; which++) {
for (int i = 0; i < compact->compaction->num_input_files(which); i++) {
stats.bytes_read += compact->compaction->input(which, i)->file_size;
}
}
for (size_t i = 0; i < compact->outputs.size(); i++) {
stats.bytes_written += compact->outputs[i].file_size;
}
mutex_.Lock();
stats_[compact->compaction->level() + 1].Add(stats);
if (status.ok()) {
status = InstallCompactionResults(compact);