aboutsummaryrefslogtreecommitdiff
path: root/db/db_impl.cc
blob: 60f4e66e55796756eff2586ecb1f8a9f688b2783 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
// 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"

namespace leveldb {

const int kNumNonTableCacheFiles = 10;

// 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;

  // 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,    64 + kNumNonTableCacheFiles, 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& raw_options, const std::string& dbname)
    : env_(raw_options.env),
      internal_comparator_(raw_options.comparator),
      internal_filter_policy_(raw_options.filter_policy),
      options_(SanitizeOptions(dbname, &internal_comparator_,
                               &internal_filter_policy_, raw_options)),
      owns_info_log_(options_.info_log != raw_options.info_log),
      owns_cache_(options_.block_cache != raw_options.block_cache),
      dbname_(dbname),
      db_lock_(NULL),
      shutting_down_(NULL),
      bg_cv_(&mutex_),
      mem_(NULL),
      imm_(NULL),
      logfile_(NULL),
      logfile_number_(0),
      log_(NULL),
      seed_(0),
      tmp_batch_(new WriteBatch),
      bg_compaction_scheduled_(false),
      manual_compaction_(NULL) {
  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 - kNumNonTableCacheFiles;
  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;
  }
}

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() {
  if (!bg_error_.ok()) {
    // After a background error, we don't know whether a new version may
    // or may not have been committed, so we cannot safely garbage collect.
    return;
  }

  // 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, bool *save_manifest) {
  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)");
    }
  }

  s = versions_->Recover(save_manifest);
  if (!s.ok()) {
    return s;
  }
  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())));
  }

  // 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], (i == logs.size() - 1), save_manifest, edit,
                       &max_sequence);
    if (!s.ok()) {
      return s;
    }

    // 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 (versions_->LastSequence() < max_sequence) {
    versions_->SetLastSequence(max_sequence);
  }

  return Status::OK();
}

Status DBImpl::RecoverLogFile(uint64_t log_number, bool last_log,
                              bool* save_manifest, 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 intentionally 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;
  int compactions = 0;
  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) {
      compactions++;
      *save_manifest = true;
      status = WriteLevel0Table(mem, edit, NULL);
      mem->Unref();
      mem = NULL;
      if (!status.ok()) {
        // Reflect errors immediately so that conditions like full
        // file-systems cause the DB::Open() to fail.
        break;
      }
    }
  }

  delete file;

  // See if we should keep reusing the last log file.
  if (status.ok() && options_.reuse_logs && last_log && compactions == 0) {
    assert(logfile_ == NULL);
    assert(log_ == NULL);
    assert(mem_ == NULL);
    uint64_t lfile_size;
    if (env_->GetFileSize(fname, &lfile_size).ok() &&
        env_->NewAppendableFile(fname, &logfile_).ok()) {
      Log(options_.info_log, "Reusing old log %s \n", fname.c_str());
      log_ = new log::Writer(logfile_, lfile_size);
      logfile_number_ = log_number;
      if (mem != NULL) {
        mem_ = mem;
        mem = NULL;
      } else {
        // mem can be NULL if lognum exists but was empty.
        mem_ = new MemTable(internal_comparator_);
        mem_->Ref();
      }
    }
  }

  if (mem != NULL) {
    // mem did not get reused; compact it.
    if (status.ok()) {
      *save_manifest = true;
      status = WriteLevel0Table(mem, edit, NULL);
    }
    mem->Unref();
  }

  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;
}

void 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();
  } else {
    RecordBackgroundError(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 && !shutting_down_.Acquire_Load() && bg_error_.ok()) {
    if (manual_compaction_ == NULL) {  // Idle
      manual_compaction_ = &manual;
      MaybeScheduleCompaction();
    } else {  // Running either my compaction or another compaction.
      bg_cv_.Wait();
    }
  }
  if (manual_compaction_ == &manual) {
    // Cancel my manual compaction since we aborted early for some reason.
    manual_compaction_ = NULL;
  }
}

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::RecordBackgroundError(const Status& s) {
  mutex_.AssertHeld();
  if (bg_error_.ok()) {
    bg_error_ = s;
    bg_cv_.SignalAll();
  }
}

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 (!bg_error_.ok()) {
    // Already got an error; no more changes
  } 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()) {
    // No more background work when shutting down.
  } else if (!bg_error_.ok()) {
    // No more background work after a background error.
  } else {
    BackgroundCompaction();
  }

  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();
}

void DBImpl::BackgroundCompaction() {
  mutex_.AssertHeld();

  if (imm_ != NULL) {
    CompactMemTable();
    return;
  }

  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_);
    if (!status.ok()) {
      RecordBackgroundError(status);
    }
    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);
    if (!status.ok()) {
      RecordBackgroundError(status);
    }
    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 (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;
  }
}

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@%d: %lld keys, %lld bytes",
          (unsigned long long) output_number,
          compact->compaction->level(),
          (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);
  }
  if (!status.ok()) {
    RecordBackgroundError(status);
  }
  VersionSet::LevelSummaryStorage tmp;
  Log(options_.info_log,
      "compacted to: %s", versions_->LevelSummary(&tmp));
  return status;
}

namespace {
struct IterState {
  port::Mutex* mu;
  Version* version;
  MemTable* mem;
  MemTable* imm;
};

static void CleanupIteratorState(void* arg1, void* arg2) {
  IterState* state = reinterpret_cast<IterState*>(arg1);
  state->mu->Lock();
  state->mem->Unref();
  if (state->imm != NULL) state->imm->Unref();
  state->version->Unref();
  state->mu->Unlock();
  delete state;
}
}  // namespace

Iterator* DBImpl::NewInternalIterator(const ReadOptions& options,
                                      SequenceNumber* latest_snapshot,
                                      uint32_t* seed) {
  IterState* cleanup = new IterState;
  mutex_.Lock();
  *latest_snapshot = versions_->LastSequence();

  // Collect together all needed child iterators
  std::vector<Iterator*> list;
  list.push_back(mem_->NewIterator());
  mem_->Ref();
  if (imm_ != NULL) {
    list.push_back(imm_->NewIterator());
    imm_->Ref();
  }
  versions_->current()->AddIterators(options, &list);
  Iterator* internal_iter =
      NewMergingIterator(&internal_comparator_, &list[0], list.size());
  versions_->current()->Ref();

  cleanup->mu = &mutex_;
  cleanup->mem = mem_;
  cleanup->imm = imm_;
  cleanup->version = versions_->current();
  internal_iter->RegisterCleanup(CleanupIteratorState, cleanup, NULL);

  *seed = ++seed_;
  mutex_.Unlock();
  return internal_iter;
}

Iterator* DBImpl::TEST_NewInternalIterator() {
  SequenceNumber ignored;
  uint32_t ignored_seed;
  return NewInternalIterator(ReadOptions(), &ignored, &ignored_seed);
}

int64_t DBImpl::TEST_MaxNextLevelOverlappingBytes() {
  MutexLock l(&mutex_);
  return versions_->MaxNextLevelOverlappingBytes();
}

Status DBImpl::Get(const ReadOptions& options,
                   const Slice& key,
                   std::string* value) {
  Status s;
  MutexLock l(&mutex_);
  SequenceNumber snapshot;
  if (options.snapshot != NULL) {
    snapshot = reinterpret_cast<const SnapshotImpl*>(options.snapshot)->number_;
  } else {
    snapshot = versions_->LastSequence();
  }

  MemTable* mem = mem_;
  MemTable* imm = imm_;
  Version* current = versions_->current();
  mem->Ref();
  if (imm != NULL) imm->Ref();
  current->Ref();

  bool have_stat_update = false;
  Version::GetStats stats;

  // Unlock while reading from files and memtables
  {
    mutex_.Unlock();
    // First look in the memtable, then in the immutable memtable (if any).
    LookupKey lkey(key, snapshot);
    if (mem->Get(lkey, value, &s)) {
      // Done
    } else if (imm != NULL && imm->Get(lkey, value, &s)) {
      // Done
    } else {
      s = current->Get(options, lkey, value, &stats);
      have_stat_update = true;
    }
    mutex_.Lock();
  }

  if (have_stat_update && current->UpdateStats(stats)) {
    MaybeScheduleCompaction();
  }
  mem->Unref();
  if (imm != NULL) imm->Unref();
  current->Unref();
  return s;
}

Iterator* DBImpl::NewIterator(const ReadOptions& options) {
  SequenceNumber latest_snapshot;
  uint32_t seed;
  Iterator* iter = NewInternalIterator(options, &latest_snapshot, &seed);
  return NewDBIterator(
      this, user_comparator(), iter,
      (options.snapshot != NULL
       ? reinterpret_cast<const SnapshotImpl*>(options.snapshot)->number_
       : latest_snapshot),
      seed);
}

void DBImpl::RecordReadSample(Slice key) {
  MutexLock l(&mutex_);
  if (versions_->current()->RecordReadSample(key)) {
    MaybeScheduleCompaction();
  }
}

const Snapshot* DBImpl::GetSnapshot() {
  MutexLock l(&mutex_);
  return snapshots_.New(versions_->LastSequence());
}

void DBImpl::ReleaseSnapshot(const Snapshot* s) {
  MutexLock l(&mutex_);
  snapshots_.Delete(reinterpret_cast<const SnapshotImpl*>(s));
}

// Convenience methods
Status DBImpl::Put(const WriteOptions& o, const Slice& key, const Slice& val) {
  return DB::Put(o, key, val);
}

Status DBImpl::Delete(const WriteOptions& options, const Slice& key) {
  return DB::Delete(options, key);
}

Status DBImpl::Write(const WriteOptions& options, WriteBatch* my_batch) {
  Writer w(&mutex_);
  w.batch = my_batch;
  w.sync = options.sync;
  w.done = false;

  MutexLock l(&mutex_);
  writers_.push_back(&w);
  while (!w.done && &w != writers_.front()) {
    w.cv.Wait();
  }
  if (w.done) {
    return w.status;
  }

  // May temporarily unlock and wait.
  Status status = MakeRoomForWrite(my_batch == NULL);
  uint64_t last_sequence = versions_->LastSequence();
  Writer* last_writer = &w;
  if (status.ok() && my_batch != NULL) {  // NULL batch is for compactions
    WriteBatch* updates = BuildBatchGroup(&last_writer);
    WriteBatchInternal::SetSequence(updates, last_sequence + 1);
    last_sequence += WriteBatchInternal::Count(updates);

    // Add to log and apply to memtable.  We can release the lock
    // during this phase since &w is currently responsible for logging
    // and protects against concurrent loggers and concurrent writes
    // into mem_.
    {
      mutex_.Unlock();
      status = log_->AddRecord(WriteBatchInternal::Contents(updates));
      bool sync_error = false;
      if (status.ok() && options.sync) {
        status = logfile_->Sync();
        if (!status.ok()) {
          sync_error = true;
        }
      }
      if (status.ok()) {
        status = WriteBatchInternal::InsertInto(updates, mem_);
      }
      mutex_.Lock();
      if (sync_error) {
        // The state of the log file is indeterminate: the log record we
        // just added may or may not show up when the DB is re-opened.
        // So we force the DB into a mode where all future writes fail.
        RecordBackgroundError(status);
      }
    }
    if (updates == tmp_batch_) tmp_batch_->Clear();

    versions_->SetLastSequence(last_sequence);
  }

  while (true) {
    Writer* ready = writers_.front();
    writers_.pop_front();
    if (ready != &w) {
      ready->status = status;
      ready->done = true;
      ready->cv.Signal();
    }
    if (ready == last_writer) break;
  }

  // Notify new head of write queue
  if (!writers_.empty()) {
    writers_.front()->cv.Signal();
  }

  return status;
}

// REQUIRES: Writer list must be non-empty
// REQUIRES: First writer must have a non-NULL batch
WriteBatch* DBImpl::BuildBatchGroup(Writer** last_writer) {
  assert(!writers_.empty());
  Writer* first = writers_.front();
  WriteBatch* result = first->batch;
  assert(result != NULL);

  size_t size = WriteBatchInternal::ByteSize(first->batch);

  // Allow the group to grow up to a maximum size, but if the
  // original write is small, limit the growth so we do not slow
  // down the small write too much.
  size_t max_size = 1 << 20;
  if (size <= (128<<10)) {
    max_size = size + (128<<10);
  }

  *last_writer = first;
  std::deque<Writer*>::iterator iter = writers_.begin();
  ++iter;  // Advance past "first"
  for (; iter != writers_.end(); ++iter) {
    Writer* w = *iter;
    if (w->sync && !first->sync) {
      // Do not include a sync write into a batch handled by a non-sync write.
      break;
    }

    if (w->batch != NULL) {
      size += WriteBatchInternal::ByteSize(w->batch);
      if (size > max_size) {
        // Do not make batch too big
        break;
      }

      // Append to *result
      if (result == first->batch) {
        // Switch to temporary batch instead of disturbing caller's batch
        result = tmp_batch_;
        assert(WriteBatchInternal::Count(result) == 0);
        WriteBatchInternal::Append(result, first->batch);
      }
      WriteBatchInternal::Append(result, w->batch);
    }
    *last_writer = w;
  }
  return result;
}

// REQUIRES: mutex_ is held
// REQUIRES: this thread is currently at the front of the writer queue
Status DBImpl::MakeRoomForWrite(bool force) {
  mutex_.AssertHeld();
  assert(!writers_.empty());
  bool allow_delay = !force;
  Status s;
  while (true) {
    if (!bg_error_.ok()) {
      // Yield previous error
      s = bg_error_;
      break;
    } else if (
        allow_delay &&
        versions_->NumLevelFiles(0) >= config::kL0_SlowdownWritesTrigger) {
      // We are getting close to hitting a hard limit on the number of
      // L0 files.  Rather than delaying a single write by several
      // seconds when we hit the hard limit, start delaying each
      // individual write by 1ms to reduce latency variance.  Also,
      // this delay hands over some CPU to the compaction thread in
      // case it is sharing the same core as the writer.
      mutex_.Unlock();
      env_->SleepForMicroseconds(1000);
      allow_delay = false;  // Do not delay a single write more than once
      mutex_.Lock();
    } else if (!force &&
               (mem_->ApproximateMemoryUsage() <= options_.write_buffer_size)) {
      // There is room in current memtable
      break;
    } else if (imm_ != NULL) {
      // We have filled up the current memtable, but the previous
      // one is still being compacted, so we wait.
      Log(options_.info_log, "Current memtable full; waiting...\n");
      bg_cv_.Wait();
    } else if (versions_->NumLevelFiles(0) >= config::kL0_StopWritesTrigger) {
      // There are too many level-0 files.
      Log(options_.info_log, "Too many L0 files; waiting...\n");
      bg_cv_.Wait();
    } else {
      // Attempt to switch to a new memtable and trigger compaction of old
      assert(versions_->PrevLogNumber() == 0);
      uint64_t new_log_number = versions_->NewFileNumber();
      WritableFile* lfile = NULL;
      s = env_->NewWritableFile(LogFileName(dbname_, new_log_number), &lfile);
      if (!s.ok()) {
        // Avoid chewing through file number space in a tight loop.
        versions_->ReuseFileNumber(new_log_number);
        break;
      }
      delete log_;
      delete logfile_;
      logfile_ = lfile;
      logfile_number_ = new_log_number;
      log_ = new log::Writer(lfile);
      imm_ = mem_;
      has_imm_.Release_Store(imm_);
      mem_ = new MemTable(internal_comparator_);
      mem_->Ref();
      force = false;   // Do not force another compaction if have room
      MaybeScheduleCompaction();
    }
  }
  return s;
}

bool DBImpl::GetProperty(const Slice& property, std::string* value) {
  value->clear();

  MutexLock l(&mutex_);
  Slice in = property;
  Slice prefix("leveldb.");
  if (!in.starts_with(prefix)) return false;
  in.remove_prefix(prefix.size());

  if (in.starts_with("num-files-at-level")) {
    in.remove_prefix(strlen("num-files-at-level"));
    uint64_t level;
    bool ok = ConsumeDecimalNumber(&in, &level) && in.empty();
    if (!ok || level >= config::kNumLevels) {
      return false;
    } else {
      char buf[100];
      snprintf(buf, sizeof(buf), "%d",
               versions_->NumLevelFiles(static_cast<int>(level)));
      *value = buf;
      return true;
    }
  } else if (in == "stats") {
    char buf[200];
    snprintf(buf, sizeof(buf),
             "                               Compactions\n"
             "Level  Files Size(MB) Time(sec) Read(MB) Write(MB)\n"
             "--------------------------------------------------\n"
             );
    value->append(buf);
    for (int level = 0; level < config::kNumLevels; level++) {
      int files = versions_->NumLevelFiles(level);
      if (stats_[level].micros > 0 || files > 0) {
        snprintf(
            buf, sizeof(buf),
            "%3d %8d %8.0f %9.0f %8.0f %9.0f\n",
            level,
            files,
            versions_->NumLevelBytes(level) / 1048576.0,
            stats_[level].micros / 1e6,
            stats_[level].bytes_read / 1048576.0,
            stats_[level].bytes_written / 1048576.0);
        value->append(buf);
      }
    }
    return true;
  } else if (in == "sstables") {
    *value = versions_->current()->DebugString();
    return true;
  } else if (in == "approximate-memory-usage") {
    size_t total_usage = options_.block_cache->TotalCharge();
    if (mem_) {
      total_usage += mem_->ApproximateMemoryUsage();
    }
    if (imm_) {
      total_usage += imm_->ApproximateMemoryUsage();
    }
    char buf[50];
    snprintf(buf, sizeof(buf), "%llu",
             static_cast<unsigned long long>(total_usage));
    value->append(buf);
    return true;
  }

  return false;
}

void DBImpl::GetApproximateSizes(
    const Range* range, int n,
    uint64_t* sizes) {
  // TODO(opt): better implementation
  Version* v;
  {
    MutexLock l(&mutex_);
    versions_->current()->Ref();
    v = versions_->current();
  }

  for (int 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);
    uint64_t start = versions_->ApproximateOffsetOf(v, k1);
    uint64_t limit = versions_->ApproximateOffsetOf(v, k2);
    sizes[i] = (limit >= start ? limit - start : 0);
  }

  {
    MutexLock l(&mutex_);
    v->Unref();
  }
}

// Default implementations of convenience methods that subclasses of DB
// can call if they wish
Status DB::Put(const WriteOptions& opt, const Slice& key, const Slice& value) {
  WriteBatch batch;
  batch.Put(key, value);
  return Write(opt, &batch);
}

Status DB::Delete(const WriteOptions& opt, const Slice& key) {
  WriteBatch batch;
  batch.Delete(key);
  return Write(opt, &batch);
}

DB::~DB() { }

Status DB::Open(const Options& options, const std::string& dbname,
                DB** dbptr) {
  *dbptr = NULL;

  DBImpl* impl = new DBImpl(options, dbname);
  impl->mutex_.Lock();
  VersionEdit edit;
  // Recover handles create_if_missing, error_if_exists
  bool save_manifest = false;
  Status s = impl->Recover(&edit, &save_manifest);
  if (s.ok() && impl->mem_ == NULL) {
    // Create new log and a corresponding memtable.
    uint64_t new_log_number = impl->versions_->NewFileNumber();
    WritableFile* lfile;
    s = options.env->NewWritableFile(LogFileName(dbname, new_log_number),
                                     &lfile);
    if (s.ok()) {
      edit.SetLogNumber(new_log_number);
      impl->logfile_ = lfile;
      impl->logfile_number_ = new_log_number;
      impl->log_ = new log::Writer(lfile);
      impl->mem_ = new MemTable(impl->internal_comparator_);
      impl->mem_->Ref();
    }
  }
  if (s.ok() && save_manifest) {
    edit.SetPrevLogNumber(0);  // No older logs needed after recovery.
    edit.SetLogNumber(impl->logfile_number_);
    s = impl->versions_->LogAndApply(&edit, &impl->mutex_);
  }
  if (s.ok()) {
    impl->DeleteObsoleteFiles();
    impl->MaybeScheduleCompaction();
  }
  impl->mutex_.Unlock();
  if (s.ok()) {
    assert(impl->mem_ != NULL);
    *dbptr = impl;
  } else {
    delete impl;
  }
  return s;
}

Snapshot::~Snapshot() {
}

Status DestroyDB(const std::string& dbname, const Options& options) {
  Env* env = options.env;
  std::vector<std::string> filenames;
  // Ignore error in case directory does not exist
  env->GetChildren(dbname, &filenames);
  if (filenames.empty()) {
    return Status::OK();
  }

  FileLock* lock;
  const std::string lockname = LockFileName(dbname);
  Status result = env->LockFile(lockname, &lock);
  if (result.ok()) {
    uint64_t number;
    FileType type;
    for (size_t i = 0; i < filenames.size(); i++) {
      if (ParseFileName(filenames[i], &number, &type) &&
          type != kDBLockFile) {  // Lock file will be deleted at end
        Status del = env->DeleteFile(dbname + "/" + filenames[i]);
        if (result.ok() && !del.ok()) {
          result = del;
        }
      }
    }
    env->UnlockFile(lock);  // Ignore error since state is already gone
    env->DeleteFile(lockname);
    env->DeleteDir(dbname);  // Ignore error in case dir contains other files
  }
  return result;
}

}  // namespace leveldb