-
Notifications
You must be signed in to change notification settings - Fork 6.4k
/
Copy pathdb_crashtest.py
1486 lines (1385 loc) · 64 KB
/
db_crashtest.py
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
#!/usr/bin/env python3
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
import argparse
import math
import os
import random
import shutil
import subprocess
import sys
import tempfile
import time
# params overwrite priority:
# for default:
# default_params < {blackbox,whitebox}_default_params < args
# for simple:
# default_params < {blackbox,whitebox}_default_params <
# simple_default_params <
# {blackbox,whitebox}_simple_default_params < args
# for cf_consistency:
# default_params < {blackbox,whitebox}_default_params <
# cf_consistency_params < args
# for txn:
# default_params < {blackbox,whitebox}_default_params < txn_params < args
# for ts:
# default_params < {blackbox,whitebox}_default_params < ts_params < args
# for multiops_txn:
# default_params < {blackbox,whitebox}_default_params < multiops_txn_params < args
default_params = {
"acquire_snapshot_one_in": lambda: random.choice([100, 10000]),
"backup_max_size": 100 * 1024 * 1024,
# Consider larger number when backups considered more stable
"backup_one_in": lambda: random.choice([1000, 100000]),
"batch_protection_bytes_per_key": lambda: random.choice([0, 8]),
"memtable_protection_bytes_per_key": lambda: random.choice([0, 1, 2, 4, 8]),
"block_protection_bytes_per_key": lambda: random.choice([0, 1, 2, 4, 8]),
"block_size": 16384,
"bloom_bits": lambda: random.choice(
[random.randint(0, 19), random.lognormvariate(2.3, 1.3)]
),
"cache_index_and_filter_blocks": lambda: random.randint(0, 1),
"cache_size": lambda: random.choice([8388608, 33554432]),
"charge_compression_dictionary_building_buffer": lambda: random.choice([0, 1]),
"charge_filter_construction": lambda: random.choice([0, 1]),
"charge_table_reader": lambda: random.choice([0, 1]),
"charge_file_metadata": lambda: random.choice([0, 1]),
"checkpoint_one_in": lambda: random.choice([0, 0, 10000, 1000000]),
"compression_type": lambda: random.choice(
["none", "snappy", "zlib", "lz4", "lz4hc", "xpress", "zstd"]
),
"bottommost_compression_type": lambda: (
"disable"
if random.randint(0, 1) == 0
else random.choice(["none", "snappy", "zlib", "lz4", "lz4hc", "xpress", "zstd"])
),
"checksum_type": lambda: random.choice(
["kCRC32c", "kxxHash", "kxxHash64", "kXXH3"]
),
"compression_max_dict_bytes": lambda: 16384 * random.randint(0, 1),
"compression_zstd_max_train_bytes": lambda: 65536 * random.randint(0, 1),
"compression_parallel_threads": lambda: random.choice([1] * 3 + [4, 8, 16]),
"compression_max_dict_buffer_bytes": lambda: (1 << random.randint(0, 40)) - 1,
"compression_use_zstd_dict_trainer": lambda: random.randint(0, 1),
"compression_checksum": lambda: random.randint(0, 1),
"clear_column_family_one_in": 0,
"compact_files_one_in": lambda: random.choice([1000, 1000000]),
"compact_range_one_in": lambda: random.choice([1000, 1000000]),
# Disabled because of various likely related failures with
# "Cannot delete table file #N from level 0 since it is on level X"
"promote_l0_one_in": 0,
"compaction_pri": random.randint(0, 4),
"key_may_exist_one_in": lambda: random.choice([100, 100000]),
"data_block_index_type": lambda: random.choice([0, 1]),
"decouple_partitioned_filters": lambda: random.choice([0, 1, 1]),
"delpercent": 4,
"delrangepercent": 1,
"destroy_db_initially": 0,
"enable_pipelined_write": lambda: random.randint(0, 1),
"enable_compaction_filter": lambda: random.choice([0, 0, 0, 1]),
# `inplace_update_support` is incompatible with DB that has delete
# range data in memtables.
# Such data can result from any of the previous db stress runs
# using delete range.
# Since there is no easy way to keep track of whether delete range
# is used in any of the previous runs,
# to simpify our testing, we set `inplace_update_support` across
# runs and to disable delete range accordingly
# (see below `finalize_and_sanitize`).
"inplace_update_support": random.choice([0] * 9 + [1]),
"expected_values_dir": lambda: setup_expected_values_dir(),
"fail_if_options_file_error": lambda: random.randint(0, 1),
"flush_one_in": lambda: random.choice([1000, 1000000]),
"manual_wal_flush_one_in": lambda: random.choice([0, 1000]),
"file_checksum_impl": lambda: random.choice(["none", "crc32c", "xxh64", "big"]),
"get_live_files_apis_one_in": lambda: random.choice([10000, 1000000]),
"get_all_column_family_metadata_one_in": lambda: random.choice([10000, 1000000]),
# Note: the following two are intentionally disabled as the corresponding
# APIs are not guaranteed to succeed.
"get_sorted_wal_files_one_in": 0,
"get_current_wal_file_one_in": 0,
# Temporarily disable hash index
"index_type": lambda: random.choice([0, 0, 0, 2, 2, 3]),
"ingest_external_file_one_in": lambda: random.choice([1000, 1000000]),
"test_ingest_standalone_range_deletion_one_in": lambda: random.choice([0, 5, 10]),
"iterpercent": 10,
"lock_wal_one_in": lambda: random.choice([10000, 1000000]),
"mark_for_compaction_one_file_in": lambda: 10 * random.randint(0, 1),
"max_background_compactions": 20,
"max_bytes_for_level_base": 10485760,
# max_key has to be the same across invocations for verification to work, hence no lambda
"max_key": random.choice([100000, 25000000]),
"max_sequential_skip_in_iterations": lambda: random.choice([1, 2, 8, 16]),
"max_write_buffer_number": 3,
"mmap_read": lambda: random.randint(0, 1),
# Setting `nooverwritepercent > 0` is only possible because we do not vary
# the random seed, so the same keys are chosen by every run for disallowing
# overwrites.
"nooverwritepercent": 1,
"open_files": lambda: random.choice([-1, -1, 100, 500000]),
"optimize_filters_for_memory": lambda: random.randint(0, 1),
"partition_filters": lambda: random.randint(0, 1),
"partition_pinning": lambda: random.randint(0, 3),
"reset_stats_one_in": lambda: random.choice([10000, 1000000]),
"pause_background_one_in": lambda: random.choice([10000, 1000000]),
"disable_file_deletions_one_in": lambda: random.choice([10000, 1000000]),
"disable_manual_compaction_one_in": lambda: random.choice([10000, 1000000]),
"prefix_size": lambda: random.choice([-1, 1, 5, 7, 8]),
"prefixpercent": 5,
"progress_reports": 0,
"readpercent": 45,
# See disabled DBWALTest.RecycleMultipleWalsCrash
"recycle_log_file_num": 0,
"snapshot_hold_ops": 100000,
"sqfc_name": lambda: random.choice(["foo", "bar"]),
# 0 = disable writing SstQueryFilters
"sqfc_version": lambda: random.choice([0, 1, 1, 2, 2]),
"sst_file_manager_bytes_per_sec": lambda: random.choice([0, 104857600]),
"sst_file_manager_bytes_per_truncate": lambda: random.choice([0, 1048576]),
"long_running_snapshots": lambda: random.randint(0, 1),
"subcompactions": lambda: random.randint(1, 4),
"target_file_size_base": lambda: random.choice([512 * 1024, 2048 * 1024]),
"target_file_size_multiplier": 2,
"test_batches_snapshots": random.randint(0, 1),
"top_level_index_pinning": lambda: random.randint(0, 3),
"unpartitioned_pinning": lambda: random.randint(0, 3),
"use_direct_reads": lambda: random.randint(0, 1),
"use_direct_io_for_flush_and_compaction": lambda: random.randint(0, 1),
"use_sqfc_for_range_queries": lambda: random.choice([0, 1, 1, 1]),
"mock_direct_io": False,
"cache_type": lambda: random.choice(
[
"lru_cache",
"fixed_hyper_clock_cache",
"auto_hyper_clock_cache",
"auto_hyper_clock_cache",
"tiered_lru_cache",
"tiered_fixed_hyper_clock_cache",
"tiered_auto_hyper_clock_cache",
"tiered_auto_hyper_clock_cache",
]
),
"uncache_aggressiveness": lambda: int(math.pow(10, 4.0 * random.random()) - 1.0),
"use_full_merge_v1": lambda: random.randint(0, 1),
"use_merge": lambda: random.randint(0, 1),
# use_put_entity_one_in has to be the same across invocations for verification to work, hence no lambda
"use_put_entity_one_in": random.choice([0] * 7 + [1, 5, 10]),
"use_attribute_group": lambda: random.randint(0, 1),
"use_multi_cf_iterator": lambda: random.randint(0, 1),
# 999 -> use Bloom API
"bloom_before_level": lambda: random.choice(
[random.randint(-1, 2), random.randint(-1, 10), 0x7FFFFFFF - 1, 0x7FFFFFFF]
),
"value_size_mult": 32,
"verification_only": 0,
"verify_checksum": 1,
"write_buffer_size": lambda: random.choice([1024 * 1024, 4 * 1024 * 1024]),
"writepercent": 35,
"format_version": lambda: random.choice([2, 3, 4, 5, 6, 6]),
"index_block_restart_interval": lambda: random.choice(range(1, 16)),
"use_multiget": lambda: random.randint(0, 1),
"use_get_entity": lambda: random.choice([0] * 7 + [1]),
"use_multi_get_entity": lambda: random.choice([0] * 7 + [1]),
"periodic_compaction_seconds": lambda: random.choice([0, 0, 1, 2, 10, 100, 1000]),
"daily_offpeak_time_utc": lambda: random.choice(
["", "", "00:00-23:59", "04:00-08:00", "23:30-03:15"]
),
# 0 = never (used by some), 10 = often (for threading bugs), 600 = default
"stats_dump_period_sec": lambda: random.choice([0, 10, 600]),
"compaction_ttl": lambda: random.choice([0, 0, 1, 2, 10, 100, 1000]),
"fifo_allow_compaction": lambda: random.randint(0, 1),
# Test small max_manifest_file_size in a smaller chance, as most of the
# time we wnat manifest history to be preserved to help debug
"max_manifest_file_size": lambda: random.choice(
[t * 16384 if t < 3 else 1024 * 1024 * 1024 for t in range(1, 30)]
),
# Sync mode might make test runs slower so running it in a smaller chance
"sync": lambda: random.choice([1 if t == 0 else 0 for t in range(0, 20)]),
"bytes_per_sync": lambda: random.choice([0, 262144]),
# TODO(hx235): Enable `wal_bytes_per_sync` after fixing the DB recovery such
# that it won't recover past the WAL data hole created by this option
"wal_bytes_per_sync": 0,
"compaction_readahead_size": lambda: random.choice([0, 0, 1024 * 1024]),
"db_write_buffer_size": lambda: random.choice(
[0, 0, 0, 1024 * 1024, 8 * 1024 * 1024, 128 * 1024 * 1024]
),
"use_write_buffer_manager": lambda: random.randint(0, 1),
"avoid_unnecessary_blocking_io": random.randint(0, 1),
"write_dbid_to_manifest": random.randint(0, 1),
"write_identity_file": random.randint(0, 1),
"avoid_flush_during_recovery": lambda: random.choice(
[1 if t == 0 else 0 for t in range(0, 8)]
),
"max_write_batch_group_size_bytes": lambda: random.choice(
[16, 64, 1024 * 1024, 16 * 1024 * 1024]
),
"level_compaction_dynamic_level_bytes": lambda: random.randint(0, 1),
"verify_checksum_one_in": lambda: random.choice([1000, 1000000]),
"verify_file_checksums_one_in": lambda: random.choice([1000, 1000000]),
"verify_db_one_in": lambda: random.choice([10000, 100000]),
"continuous_verification_interval": 0,
"max_key_len": 3,
"key_len_percent_dist": "1,30,69",
"error_recovery_with_no_fault_injection": lambda: random.randint(0, 1),
"metadata_read_fault_one_in": lambda: random.choice([0, 32, 1000]),
"metadata_write_fault_one_in": lambda: random.choice([0, 128, 1000]),
"read_fault_one_in": lambda: random.choice([0, 32, 1000]),
"write_fault_one_in": lambda: random.choice([0, 128, 1000]),
"exclude_wal_from_write_fault_injection": 0,
"open_metadata_write_fault_one_in": lambda: random.choice([0, 0, 8]),
"open_metadata_read_fault_one_in": lambda: random.choice([0, 0, 8]),
"open_write_fault_one_in": lambda: random.choice([0, 0, 16]),
"open_read_fault_one_in": lambda: random.choice([0, 0, 32]),
"sync_fault_injection": lambda: random.randint(0, 1),
"get_property_one_in": lambda: random.choice([100000, 1000000]),
"get_properties_of_all_tables_one_in": lambda: random.choice([100000, 1000000]),
"paranoid_file_checks": lambda: random.choice([0, 1, 1, 1]),
"max_write_buffer_size_to_maintain": lambda: random.choice(
[0, 1024 * 1024, 2 * 1024 * 1024, 4 * 1024 * 1024, 8 * 1024 * 1024]
),
"user_timestamp_size": 0,
"secondary_cache_fault_one_in": lambda: random.choice([0, 0, 32]),
"compressed_secondary_cache_size": lambda: random.choice([8388608, 16777216]),
"prepopulate_block_cache": lambda: random.choice([0, 1]),
"memtable_prefix_bloom_size_ratio": lambda: random.choice([0.001, 0.01, 0.1, 0.5]),
"memtable_whole_key_filtering": lambda: random.randint(0, 1),
"detect_filter_construct_corruption": lambda: random.choice([0, 1]),
"adaptive_readahead": lambda: random.choice([0, 1]),
"async_io": lambda: random.choice([0, 1]),
"wal_compression": lambda: random.choice(["none", "zstd"]),
"verify_sst_unique_id_in_manifest": 1, # always do unique_id verification
"secondary_cache_uri": lambda: random.choice(
[
"",
"",
"",
"compressed_secondary_cache://capacity=8388608;enable_custom_split_merge=true",
]
),
"allow_data_in_errors": True,
"enable_thread_tracking": lambda: random.choice([0, 1]),
"readahead_size": lambda: random.choice([0, 16384, 524288]),
"initial_auto_readahead_size": lambda: random.choice([0, 16384, 524288]),
"max_auto_readahead_size": lambda: random.choice([0, 16384, 524288]),
"num_file_reads_for_auto_readahead": lambda: random.choice([0, 1, 2]),
"min_write_buffer_number_to_merge": lambda: random.choice([1, 2]),
"preserve_internal_time_seconds": lambda: random.choice([0, 60, 3600, 36000]),
"memtable_max_range_deletions": lambda: random.choice([0] * 6 + [100, 1000]),
# 0 (disable) is the default and more commonly used value.
"bottommost_file_compaction_delay": lambda: random.choice(
[0, 0, 0, 600, 3600, 86400]
),
"auto_readahead_size": lambda: random.choice([0, 1]),
"verify_iterator_with_expected_state_one_in": 5,
"allow_fallocate": lambda: random.choice([0, 1]),
"table_cache_numshardbits": lambda: random.choice([6] * 3 + [-1] * 2 + [0]),
"enable_write_thread_adaptive_yield": lambda: random.choice([0, 1]),
"log_readahead_size": lambda: random.choice([0, 16 * 1024 * 1024]),
"bgerror_resume_retry_interval": lambda: random.choice([100, 1000000]),
"delete_obsolete_files_period_micros": lambda: random.choice(
[6 * 60 * 60 * 1000000, 30 * 1000000]
),
"max_log_file_size": lambda: random.choice([0, 1024 * 1024]),
"log_file_time_to_roll": lambda: random.choice([0, 60]),
"use_adaptive_mutex": lambda: random.choice([0, 1]),
"advise_random_on_open": lambda: random.choice([0] + [1] * 3),
"WAL_ttl_seconds": lambda: random.choice([0, 60]),
"WAL_size_limit_MB": lambda: random.choice([0, 1]),
"strict_bytes_per_sync": lambda: random.choice([0, 1]),
"avoid_flush_during_shutdown": lambda: random.choice([0, 1]),
"fill_cache": lambda: random.choice([0, 1]),
"optimize_multiget_for_io": lambda: random.choice([0, 1]),
"memtable_insert_hint_per_batch": lambda: random.choice([0, 1]),
"dump_malloc_stats": lambda: random.choice([0, 1]),
"stats_history_buffer_size": lambda: random.choice([0, 1024 * 1024]),
"skip_stats_update_on_db_open": lambda: random.choice([0, 1]),
"optimize_filters_for_hits": lambda: random.choice([0, 1]),
"sample_for_compression": lambda: random.choice([0, 5]),
"report_bg_io_stats": lambda: random.choice([0, 1]),
"cache_index_and_filter_blocks_with_high_priority": lambda: random.choice([0, 1]),
"use_delta_encoding": lambda: random.choice([0, 1]),
"verify_compression": lambda: random.choice([0, 1]),
"read_amp_bytes_per_bit": lambda: random.choice([0, 32]),
"enable_index_compression": lambda: random.choice([0, 1]),
"index_shortening": lambda: random.choice([0, 1, 2]),
"metadata_charge_policy": lambda: random.choice([0, 1]),
"use_adaptive_mutex_lru": lambda: random.choice([0, 1]),
"compress_format_version": lambda: random.choice([1, 2]),
"manifest_preallocation_size": lambda: random.choice([0, 5 * 1024]),
"enable_checksum_handoff": lambda: random.choice([0, 1]),
"max_total_wal_size": lambda: random.choice([0] * 4 + [64 * 1024 * 1024]),
"high_pri_pool_ratio": lambda: random.choice([0, 0.5]),
"low_pri_pool_ratio": lambda: random.choice([0, 0.5]),
"soft_pending_compaction_bytes_limit": lambda: random.choice(
[1024 * 1024] + [64 * 1073741824] * 4
),
"hard_pending_compaction_bytes_limit": lambda: random.choice(
[2 * 1024 * 1024] + [256 * 1073741824] * 4
),
"enable_sst_partitioner_factory": lambda: random.choice([0, 1]),
"enable_do_not_compress_roles": lambda: random.choice([0, 1]),
"block_align": lambda: random.choice([0, 1]),
"lowest_used_cache_tier": lambda: random.choice([0, 1, 2]),
"enable_custom_split_merge": lambda: random.choice([0, 1]),
"adm_policy": lambda: random.choice([0, 1, 2, 3]),
"last_level_temperature": lambda: random.choice(
["kUnknown", "kHot", "kWarm", "kCold"]
),
"default_write_temperature": lambda: random.choice(
["kUnknown", "kHot", "kWarm", "kCold"]
),
"default_temperature": lambda: random.choice(
["kUnknown", "kHot", "kWarm", "kCold"]
),
# TODO(hx235): enable `enable_memtable_insert_with_hint_prefix_extractor`
# after fixing the surfaced issue with delete range
"enable_memtable_insert_with_hint_prefix_extractor": 0,
"check_multiget_consistency": lambda: random.choice([0, 0, 0, 1]),
"check_multiget_entity_consistency": lambda: random.choice([0, 0, 0, 1]),
"use_timed_put_one_in": lambda: random.choice([0] * 7 + [1, 5, 10]),
"universal_max_read_amp": lambda: random.choice([-1] * 3 + [0, 4, 10]),
"paranoid_memory_checks": lambda: random.choice([0] * 7 + [1]),
"allow_unprepared_value": lambda: random.choice([0, 1]),
# TODO(hx235): enable `track_and_verify_wals` again after resolving the issues
# it has with write fault injection and TXN
"track_and_verify_wals": 0,
"enable_remote_compaction": lambda: random.choice([0, 1]),
"auto_refresh_iterator_with_snapshot": lambda: random.choice([0, 1]),
}
_TEST_DIR_ENV_VAR = "TEST_TMPDIR"
# If TEST_TMPDIR_EXPECTED is not specified, default value will be TEST_TMPDIR
_TEST_EXPECTED_DIR_ENV_VAR = "TEST_TMPDIR_EXPECTED"
_DEBUG_LEVEL_ENV_VAR = "DEBUG_LEVEL"
stress_cmd = "./db_stress"
cleanup_cmd = None
def is_release_mode():
return os.environ.get(_DEBUG_LEVEL_ENV_VAR) == "0"
def get_dbname(test_name):
test_dir_name = "rocksdb_crashtest_" + test_name
test_tmpdir = os.environ.get(_TEST_DIR_ENV_VAR)
if test_tmpdir is None or test_tmpdir == "":
dbname = tempfile.mkdtemp(prefix=test_dir_name)
else:
dbname = test_tmpdir + "/" + test_dir_name
shutil.rmtree(dbname, True)
if cleanup_cmd is not None:
print("Running DB cleanup command - %s\n" % cleanup_cmd)
# Ignore failure
os.system(cleanup_cmd)
try:
os.mkdir(dbname)
except OSError:
pass
return dbname
expected_values_dir = None
def setup_expected_values_dir():
global expected_values_dir
if expected_values_dir is not None:
return expected_values_dir
expected_dir_prefix = "rocksdb_crashtest_expected_"
test_exp_tmpdir = os.environ.get(_TEST_EXPECTED_DIR_ENV_VAR)
# set the value to _TEST_DIR_ENV_VAR if _TEST_EXPECTED_DIR_ENV_VAR is not
# specified.
if test_exp_tmpdir is None or test_exp_tmpdir == "":
test_exp_tmpdir = os.environ.get(_TEST_DIR_ENV_VAR)
if test_exp_tmpdir is None or test_exp_tmpdir == "":
expected_values_dir = tempfile.mkdtemp(prefix=expected_dir_prefix)
else:
# if tmpdir is specified, store the expected_values_dir under that dir
expected_values_dir = test_exp_tmpdir + "/rocksdb_crashtest_expected"
if os.path.exists(expected_values_dir):
shutil.rmtree(expected_values_dir)
os.mkdir(expected_values_dir)
return expected_values_dir
multiops_txn_key_spaces_file = None
def setup_multiops_txn_key_spaces_file():
global multiops_txn_key_spaces_file
if multiops_txn_key_spaces_file is not None:
return multiops_txn_key_spaces_file
key_spaces_file_prefix = "rocksdb_crashtest_multiops_txn_key_spaces"
test_exp_tmpdir = os.environ.get(_TEST_EXPECTED_DIR_ENV_VAR)
# set the value to _TEST_DIR_ENV_VAR if _TEST_EXPECTED_DIR_ENV_VAR is not
# specified.
if test_exp_tmpdir is None or test_exp_tmpdir == "":
test_exp_tmpdir = os.environ.get(_TEST_DIR_ENV_VAR)
if test_exp_tmpdir is None or test_exp_tmpdir == "":
multiops_txn_key_spaces_file = tempfile.mkstemp(prefix=key_spaces_file_prefix)[
1
]
else:
if not os.path.exists(test_exp_tmpdir):
os.mkdir(test_exp_tmpdir)
multiops_txn_key_spaces_file = tempfile.mkstemp(
prefix=key_spaces_file_prefix, dir=test_exp_tmpdir
)[1]
return multiops_txn_key_spaces_file
def is_direct_io_supported(dbname):
with tempfile.NamedTemporaryFile(dir=dbname) as f:
try:
os.open(f.name, os.O_DIRECT)
except BaseException:
return False
return True
blackbox_default_params = {
"disable_wal": lambda: random.choice([0, 0, 0, 1]),
# total time for this script to test db_stress
"duration": 6000,
# time for one db_stress instance to run
"interval": 120,
# time for the final verification step
"verify_timeout": 1200,
# since we will be killing anyway, use large value for ops_per_thread
"ops_per_thread": 100000000,
"reopen": 0,
"set_options_one_in": 1000,
}
whitebox_default_params = {
# TODO: enable this at random once we figure out two things. First, we need
# to ensure the kill odds in WAL-disabled runs result in regular crashing
# before the fifteen minute timeout. When WAL is disabled there are very few
# calls to write functions since writes to SST files are buffered and other
# writes (e.g., MANIFEST) are infrequent. Crashing in reasonable time might
# currently assume killpoints in write functions are reached frequently.
#
# Second, we need to make sure disabling WAL works with `-reopen > 0`.
"disable_wal": 0,
"duration": 10000,
"log2_keys_per_lock": 10,
"ops_per_thread": 200000,
"random_kill_odd": 888887,
"reopen": 20,
}
simple_default_params = {
"allow_concurrent_memtable_write": lambda: random.randint(0, 1),
"column_families": 1,
# TODO: re-enable once internal task T124324915 is fixed.
# "experimental_mempurge_threshold": lambda: 10.0*random.random(),
"max_background_compactions": 1,
"max_bytes_for_level_base": 67108864,
"memtablerep": "skip_list",
"target_file_size_base": 16777216,
"target_file_size_multiplier": 1,
"test_batches_snapshots": 0,
"write_buffer_size": 32 * 1024 * 1024,
"level_compaction_dynamic_level_bytes": lambda: random.randint(0, 1),
"paranoid_file_checks": lambda: random.choice([0, 1, 1, 1]),
"test_secondary": lambda: random.choice([0, 1]),
}
blackbox_simple_default_params = {
"open_files": -1,
"set_options_one_in": 0,
}
whitebox_simple_default_params = {}
cf_consistency_params = {
"disable_wal": lambda: random.randint(0, 1),
"reopen": 0,
"test_cf_consistency": 1,
# use small value for write_buffer_size so that RocksDB triggers flush
# more frequently
"write_buffer_size": 1024 * 1024,
"enable_pipelined_write": lambda: random.randint(0, 1),
# Snapshots are used heavily in this test mode, while they are incompatible
# with compaction filter, inplace_update_support
"enable_compaction_filter": 0,
"inplace_update_support": 0,
# `CfConsistencyStressTest::TestIngestExternalFile()` is not implemented.
"ingest_external_file_one_in": 0,
# `CfConsistencyStressTest::TestIterateAgainstExpected()` is not implemented.
"verify_iterator_with_expected_state_one_in": 0,
}
# For pessimistic transaction db
txn_params = {
"use_txn": 1,
"use_optimistic_txn": 0,
# Avoid lambda to set it once for the entire test
"txn_write_policy": random.randint(0, 2),
"unordered_write": random.randint(0, 1),
# TODO: there is such a thing as transactions with WAL disabled. We should
# cover that case.
"disable_wal": 0,
# OpenReadOnly after checkpoint is not currnetly compatible with WritePrepared txns
"checkpoint_one_in": 0,
# pipeline write is not currnetly compatible with WritePrepared txns
"enable_pipelined_write": 0,
"create_timestamped_snapshot_one_in": random.choice([0, 20]),
# Should not be used with TransactionDB which uses snapshot.
"inplace_update_support": 0,
# TimedPut is not supported in transaction
"use_timed_put_one_in": 0,
# txn commit with this option will create a new memtable, keep the
# frequency low to reduce stalls
"commit_bypass_memtable_one_in": random.choice([0] * 2 + [500, 1000]),
"two_write_queues": lambda: random.choice([0, 1]),
}
# For optimistic transaction db
optimistic_txn_params = {
"use_txn": 1,
"use_optimistic_txn": 1,
"occ_validation_policy": random.randint(0, 1),
"share_occ_lock_buckets": random.randint(0, 1),
"occ_lock_bucket_count": lambda: random.choice([10, 100, 500]),
# Should not be used with OptimisticTransactionDB which uses snapshot.
"inplace_update_support": 0,
# TimedPut is not supported in transaction
"use_timed_put_one_in": 0,
}
best_efforts_recovery_params = {
"best_efforts_recovery": 1,
"disable_wal": 1,
"column_families": 1,
"skip_verifydb": 1,
"verify_db_one_in": 0,
}
blob_params = {
"allow_setting_blob_options_dynamically": 1,
# Enable blob files and GC with a 75% chance initially; note that they might still be
# enabled/disabled during the test via SetOptions
"enable_blob_files": lambda: random.choice([0] + [1] * 3),
"min_blob_size": lambda: random.choice([0, 8, 16]),
"blob_file_size": lambda: random.choice([1048576, 16777216, 268435456, 1073741824]),
"blob_compression_type": lambda: random.choice(["none", "snappy", "lz4", "zstd"]),
"enable_blob_garbage_collection": lambda: random.choice([0] + [1] * 3),
"blob_garbage_collection_age_cutoff": lambda: random.choice(
[0.0, 0.25, 0.5, 0.75, 1.0]
),
"blob_garbage_collection_force_threshold": lambda: random.choice([0.5, 0.75, 1.0]),
"blob_compaction_readahead_size": lambda: random.choice([0, 1048576, 4194304]),
"blob_file_starting_level": lambda: random.choice(
[0] * 4 + [1] * 3 + [2] * 2 + [3]
),
"use_blob_cache": lambda: random.randint(0, 1),
"use_shared_block_and_blob_cache": lambda: random.randint(0, 1),
"blob_cache_size": lambda: random.choice([1048576, 2097152, 4194304, 8388608]),
"prepopulate_blob_cache": lambda: random.randint(0, 1),
}
ts_params = {
"test_cf_consistency": 0,
"test_batches_snapshots": 0,
"user_timestamp_size": 8,
# Below flag is randomly picked once and kept consistent in following runs.
"persist_user_defined_timestamps": random.choice([0, 1, 1]),
"use_merge": 0,
"use_full_merge_v1": 0,
"use_txn": 0,
"ingest_external_file_one_in": 0,
# PutEntity with timestamps is not yet implemented
"use_put_entity_one_in": 0,
# TimedPut is not compatible with user-defined timestamps yet.
"use_timed_put_one_in": 0,
}
tiered_params = {
# For Leveled/Universal compaction (ignored for FIFO)
# Bias toward times that can elapse during a crash test run series
# NOTE: -1 means starting disabled but dynamically changing
"preclude_last_level_data_seconds": lambda: random.choice(
[-1, -1, 10, 60, 1200, 86400]
),
"last_level_temperature": "kCold",
# For FIFO compaction (ignored otherwise)
"file_temperature_age_thresholds": lambda: random.choice(
[
"{{temperature=kWarm;age=30}:{temperature=kCold;age=300}}",
"{{temperature=kCold;age=100}}",
]
),
# tiered storage doesn't support blob db yet
"enable_blob_files": 0,
"use_blob_db": 0,
"default_write_temperature": lambda: random.choice(["kUnknown", "kHot", "kWarm"]),
}
multiops_txn_default_params = {
"test_cf_consistency": 0,
"test_batches_snapshots": 0,
"test_multi_ops_txns": 1,
"use_txn": 1,
"two_write_queues": lambda: random.choice([0, 1]),
# TODO: enable write-prepared
"disable_wal": 0,
"use_only_the_last_commit_time_batch_for_recovery": lambda: random.choice([0, 1]),
"clear_column_family_one_in": 0,
"column_families": 1,
"enable_pipelined_write": lambda: random.choice([0, 1]),
# This test already acquires snapshots in reads
"acquire_snapshot_one_in": 0,
"backup_one_in": 0,
"writepercent": 0,
"delpercent": 0,
"delrangepercent": 0,
"customopspercent": 80,
"readpercent": 5,
"iterpercent": 15,
"prefixpercent": 0,
"verify_db_one_in": 1000,
"continuous_verification_interval": 1000,
"delay_snapshot_read_one_in": 3,
# 65536 is the smallest possible value for write_buffer_size. Smaller
# values will be sanitized to 65536 during db open. SetOptions currently
# does not sanitize options, but very small write_buffer_size may cause
# assertion failure in
# https://github.com/facebook/rocksdb/blob/7.0.fb/db/memtable.cc#L117.
"write_buffer_size": 65536,
# flush more frequently to generate more files, thus trigger more
# compactions.
"flush_one_in": 1000,
"key_spaces_path": setup_multiops_txn_key_spaces_file(),
"rollback_one_in": 4,
# Re-enable once we have a compaction for MultiOpsTxnStressTest
"enable_compaction_filter": 0,
"create_timestamped_snapshot_one_in": 50,
"sync_fault_injection": 0,
"metadata_write_fault_one_in": 0,
"manual_wal_flush_one_in": 0,
# This test has aggressive flush frequency and small write buffer size.
# Disabling write fault to avoid writes being stopped.
"write_fault_one_in": 0,
"metadata_write_fault_one_in": 0,
# PutEntity in transactions is not yet implemented
"use_put_entity_one_in": 0,
"use_get_entity": 0,
"use_multi_get_entity": 0,
# `MultiOpsTxnsStressTest::TestIterateAgainstExpected()` is not implemented.
"verify_iterator_with_expected_state_one_in": 0,
# This test uses snapshot heavily which is incompatible with this option.
"inplace_update_support": 0,
# TimedPut not supported in transaction
"use_timed_put_one_in": 0,
# AttributeGroup not yet supported
"use_attribute_group": 0,
}
multiops_wc_txn_params = {
"txn_write_policy": 0,
# TODO re-enable pipelined write. Not well tested atm
"enable_pipelined_write": 0,
"commit_bypass_memtable_one_in": random.choice([0] * 4 + [100]),
}
multiops_wp_txn_params = {
"txn_write_policy": 1,
"wp_snapshot_cache_bits": 1,
# try small wp_commit_cache_bits, e.g. 0 once we explore storing full
# commit sequence numbers in commit cache
"wp_commit_cache_bits": 10,
# pipeline write is not currnetly compatible with WritePrepared txns
"enable_pipelined_write": 0,
# OpenReadOnly after checkpoint is not currnetly compatible with WritePrepared txns
"checkpoint_one_in": 0,
# Required to be 1 in order to use commit-time-batch
"use_only_the_last_commit_time_batch_for_recovery": 1,
"clear_wp_commit_cache_one_in": 10,
"create_timestamped_snapshot_one_in": 0,
# sequence number can be advanced in SwitchMemtable::WriteRecoverableState() for WP.
# disable it for now until we find another way to test LockWAL().
"lock_wal_one_in": 0,
}
def finalize_and_sanitize(src_params):
dest_params = {k: v() if callable(v) else v for (k, v) in src_params.items()}
if is_release_mode():
dest_params["read_fault_one_in"] = 0
if dest_params.get("compression_max_dict_bytes") == 0:
dest_params["compression_zstd_max_train_bytes"] = 0
dest_params["compression_max_dict_buffer_bytes"] = 0
if dest_params.get("compression_type") != "zstd":
dest_params["compression_zstd_max_train_bytes"] = 0
if dest_params["mmap_read"] == 1:
dest_params["use_direct_io_for_flush_and_compaction"] = 0
dest_params["use_direct_reads"] = 0
if (
dest_params["use_direct_io_for_flush_and_compaction"] == 1
or dest_params["use_direct_reads"] == 1
) and not is_direct_io_supported(dest_params["db"]):
if is_release_mode():
print(
"{} does not support direct IO. Disabling use_direct_reads and "
"use_direct_io_for_flush_and_compaction.\n".format(dest_params["db"])
)
dest_params["use_direct_reads"] = 0
dest_params["use_direct_io_for_flush_and_compaction"] = 0
else:
dest_params["mock_direct_io"] = True
if dest_params["test_batches_snapshots"] == 1:
dest_params["enable_compaction_filter"] = 0
dest_params["inplace_update_support"] = 0
# TODO(hx235): enable test_batches_snapshots with fault injection after stabilizing the CI
dest_params["write_fault_one_in"] = 0
dest_params["metadata_write_fault_one_in"] = 0
dest_params["read_fault_one_in"] = 0
dest_params["metadata_read_fault_one_in"] = 0
if dest_params["prefix_size"] < 0:
dest_params["prefix_size"] = 1
# BER disables WAL and tests unsynced data loss which
# does not work with inplace_update_support.
if dest_params.get("best_efforts_recovery") == 1:
dest_params["inplace_update_support"] = 0
# Multi-key operations are not currently compatible with transactions or
# timestamp.
if (
dest_params.get("test_batches_snapshots") == 1
or dest_params.get("use_txn") == 1
or dest_params.get("user_timestamp_size") > 0
):
dest_params["ingest_external_file_one_in"] = 0
if (
dest_params.get("test_batches_snapshots") == 1
or dest_params.get("use_txn") == 1
):
dest_params["delpercent"] += dest_params["delrangepercent"]
dest_params["delrangepercent"] = 0
# Since the value of inplace_update_support needs to be fixed across runs,
# we disable other incompatible options here instead of disabling
# inplace_update_support based on other option values, which may change
# across runs.
if dest_params["inplace_update_support"] == 1:
dest_params["delpercent"] += dest_params["delrangepercent"]
dest_params["delrangepercent"] = 0
dest_params["readpercent"] += dest_params["prefixpercent"]
dest_params["prefixpercent"] = 0
dest_params["allow_concurrent_memtable_write"] = 0
# inplace_update_support does not update sequence number. Our stress test recovery
# logic for unsynced data loss relies on max sequence number stored
# in MANIFEST, so they don't work together.
dest_params["sync_fault_injection"] = 0
dest_params["disable_wal"] = 0
dest_params["manual_wal_flush_one_in"] = 0
if (
dest_params.get("sync_fault_injection") == 1
or dest_params.get("disable_wal") == 1
or dest_params.get("manual_wal_flush_one_in") > 0
):
# File ingestion does not guarantee prefix-recoverability when unsynced
# data can be lost. Ingesting a file syncs data immediately that is
# newer than unsynced memtable data that can be lost on restart.
#
# Even if the above issue is fixed or worked around, our
# trace-and-replay does not trace file ingestion, so in its current form
# it would not recover the expected state to the correct point in time.
dest_params["ingest_external_file_one_in"] = 0
# The `DbStressCompactionFilter` can apply memtable updates to SST
# files, which would be problematic when unsynced data can be lost in
# crash recoveries.
dest_params["enable_compaction_filter"] = 0
# Remove the following once write-prepared/write-unprepared with/without
# unordered write supports timestamped snapshots
if dest_params.get("create_timestamped_snapshot_one_in", 0) > 0:
dest_params["txn_write_policy"] = 0
dest_params["unordered_write"] = 0
# Only under WritePrepared txns, unordered_write would provide the same guarnatees as vanilla rocksdb
# unordered_write is only enabled with --txn, and txn_params disables inplace_update_support, so
# setting allow_concurrent_memtable_write=1 won't conflcit with inplace_update_support.
# don't overwrite txn_write_policy
if dest_params.get("unordered_write", 0) == 1:
if dest_params.get("txn_write_policy", 0) == 1:
dest_params["allow_concurrent_memtable_write"] = 1
else:
dest_params["unordered_write"] = 0
if dest_params.get("disable_wal", 0) == 1:
dest_params["atomic_flush"] = 1
dest_params["sync"] = 0
dest_params["write_fault_one_in"] = 0
dest_params["reopen"] = 0
dest_params["manual_wal_flush_one_in"] = 0
# disableWAL and recycle_log_file_num options are not mutually
# compatible at the moment
dest_params["recycle_log_file_num"] = 0
if dest_params.get("open_files", 1) != -1:
# Compaction TTL and periodic compactions are only compatible
# with open_files = -1
dest_params["compaction_ttl"] = 0
dest_params["periodic_compaction_seconds"] = 0
if dest_params.get("compaction_style", 0) == 2:
# Disable compaction TTL in FIFO compaction, because right
# now assertion failures are triggered.
dest_params["compaction_ttl"] = 0
dest_params["periodic_compaction_seconds"] = 0
# Disable irrelevant tiering options
dest_params["preclude_last_level_data_seconds"] = 0
dest_params["last_level_temperature"] = "kUnknown"
else:
# Disable irrelevant tiering options
dest_params["file_temperature_age_thresholds"] = ""
if dest_params["partition_filters"] == 1:
if dest_params["index_type"] != 2:
dest_params["partition_filters"] = 0
if dest_params.get("atomic_flush", 0) == 1:
# disable pipelined write when atomic flush is used.
dest_params["enable_pipelined_write"] = 0
# Truncating SST files in primary DB is incompatible
# with secondary DB since the latter can't read the shared
# and truncated SST file correctly
if (
dest_params.get("sst_file_manager_bytes_per_sec", 0) == 0
or dest_params.get("test_secondary") == 1
):
dest_params["sst_file_manager_bytes_per_truncate"] = 0
if dest_params.get("prefix_size") == -1:
dest_params["readpercent"] += dest_params.get("prefixpercent", 20)
dest_params["prefixpercent"] = 0
if (
dest_params.get("prefix_size") == -1
and dest_params.get("memtable_whole_key_filtering") == 0
):
dest_params["memtable_prefix_bloom_size_ratio"] = 0
if dest_params.get("two_write_queues") == 1:
dest_params["enable_pipelined_write"] = 0
if dest_params.get("best_efforts_recovery") == 1:
dest_params["disable_wal"] = 1
dest_params["enable_compaction_filter"] = 0
dest_params["sync"] = 0
dest_params["write_fault_one_in"] = 0
dest_params["skip_verifydb"] = 1
dest_params["verify_db_one_in"] = 0
# For TransactionDB, correctness testing with unsync data loss is currently
# compatible with only write committed policy
if dest_params.get("use_txn") == 1 and dest_params.get("txn_write_policy", 0) != 0:
dest_params["sync_fault_injection"] = 0
dest_params["disable_wal"] = 0
dest_params["manual_wal_flush_one_in"] = 0
# Wide-column pessimistic transaction APIs are initially supported for
# WriteCommitted only
dest_params["use_put_entity_one_in"] = 0
# MultiCfIterator is currently only compatible with write committed policy
dest_params["use_multi_cf_iterator"] = 0
# only works with write committed policy
dest_params["commit_bypass_memtable_one_in"] = 0
# TODO(hx235): enable test_multi_ops_txns with fault injection after stabilizing the CI
if dest_params.get("test_multi_ops_txns") == 1:
dest_params["write_fault_one_in"] = 0
dest_params["metadata_write_fault_one_in"] = 0
dest_params["read_fault_one_in"] = 0
dest_params["metadata_read_fault_one_in"] = 0
# Wide column stress tests require FullMergeV3
if dest_params["use_put_entity_one_in"] != 0:
dest_params["use_full_merge_v1"] = 0
if dest_params["file_checksum_impl"] == "none":
dest_params["verify_file_checksums_one_in"] = 0
if dest_params["write_fault_one_in"] > 0:
# background work may be disabled while DB is resuming after some error
dest_params["max_write_buffer_number"] = max(
dest_params["max_write_buffer_number"], 10
)
if dest_params["secondary_cache_uri"].find("compressed_secondary_cache") >= 0:
dest_params["compressed_secondary_cache_size"] = 0
dest_params["compressed_secondary_cache_ratio"] = 0.0
if dest_params["cache_type"].find("tiered_") >= 0:
if dest_params["compressed_secondary_cache_size"] > 0:
dest_params["compressed_secondary_cache_ratio"] = float(
dest_params["compressed_secondary_cache_size"]
/ (
dest_params["cache_size"]
+ dest_params["compressed_secondary_cache_size"]
)
)
dest_params["compressed_secondary_cache_size"] = 0
else:
dest_params["compressed_secondary_cache_ratio"] = 0.0
dest_params["cache_type"] = dest_params["cache_type"].replace("tiered_", "")
else:
if dest_params["secondary_cache_uri"]:
dest_params["compressed_secondary_cache_size"] = 0
dest_params["compressed_secondary_cache_ratio"] = 0.0
if dest_params["use_write_buffer_manager"]:
if dest_params["cache_size"] <= 0 or dest_params["db_write_buffer_size"] <= 0:
dest_params["use_write_buffer_manager"] = 0
if (
dest_params["user_timestamp_size"] > 0
and dest_params["persist_user_defined_timestamps"] == 0
):
# Features that are not compatible with UDT in memtable only feature.
dest_params["enable_blob_files"] = 0
dest_params["allow_setting_blob_options_dynamically"] = 0
dest_params["atomic_flush"] = 0
dest_params["allow_concurrent_memtable_write"] = 0
dest_params["block_protection_bytes_per_key"] = 0
# TODO(yuzhangyu): make stress test logic handle this and enable testing
# these APIs.
# These operations need to compare side to side one operation with another.
# It's hard to guarantee their consistency because when timestamps can be
# collapsed, only operations using the same SuperVersion can be consistent
# with each other. There is no external APIs to ensure that.
dest_params["use_multiget"] = 0
dest_params["use_multi_get_entity"] = 0
dest_params["readpercent"] += dest_params.get("iterpercent", 10)
dest_params["iterpercent"] = 0
# Only best efforts recovery test support disabling wal and
# disable atomic flush.
if dest_params["test_best_efforts_recovery"] == 0:
dest_params["disable_wal"] = 0
if dest_params.get("allow_concurrent_memtable_write", 1) == 1:
dest_params["memtablerep"] = "skip_list"
if (
dest_params.get("enable_compaction_filter", 0) == 1
or dest_params.get("inplace_update_support", 0) == 1
):
# Compaction filter, inplace update support are incompatible with snapshots. Need to avoid taking
# snapshots, as well as avoid operations that use snapshots for
# verification.
dest_params["acquire_snapshot_one_in"] = 0
dest_params["compact_range_one_in"] = 0
# Redistribute to maintain 100% total
dest_params["readpercent"] += dest_params.get(
"iterpercent", 10
) + dest_params.get("prefixpercent", 20)
dest_params["iterpercent"] = 0
dest_params["prefixpercent"] = 0
dest_params["check_multiget_consistency"] = 0
dest_params["check_multiget_entity_consistency"] = 0
if dest_params.get("disable_wal") == 0:
if dest_params.get("reopen") > 0 or (
dest_params.get("manual_wal_flush_one_in")
and dest_params.get("column_families") != 1
):
# Reopen with WAL currently requires persisting WAL data before closing for reopen.
# Previous injected WAL write errors may not be cleared by the time of closing and ready
# for persisting WAL.
# To simplify, we disable any WAL write error injection.
# TODO(hx235): support WAL write error injection with reopen
# TODO(hx235): support excluding WAL from metadata write fault injection so we don't
# have to disable metadata write fault injection to other file
#
# WAL write failure can drop buffered WAL data. This can cause
# inconsistency when one CF has a successful flush during auto
# recovery. Disable the fault injection in this path for now until
# we have a fix that allows auto recovery.
dest_params["exclude_wal_from_write_fault_injection"] = 1
dest_params["metadata_write_fault_one_in"] = 0
# Enabling block_align with compression is not supported
if dest_params.get("block_align") == 1:
dest_params["compression_type"] = "none"
dest_params["bottommost_compression_type"] = "none"
# If periodic_compaction_seconds is not set, daily_offpeak_time_utc doesn't do anything
if dest_params.get("periodic_compaction_seconds") == 0:
dest_params["daily_offpeak_time_utc"] = ""
# `use_put_entity_one_in` cannot be enabled/disabled across runs, modify
# `use_timed_put_one_in` option so that they make sense together.
if dest_params.get("use_put_entity_one_in") == 1:
dest_params["use_timed_put_one_in"] = 0
elif (
dest_params.get("use_put_entity_one_in") > 1
and dest_params.get("use_timed_put_one_in") == 1
):