-
Notifications
You must be signed in to change notification settings - Fork 4.4k
/
brin.c
1918 lines (1675 loc) · 55 KB
/
brin.c
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
/*
* brin.c
* Implementation of BRIN indexes for Postgres
*
* See src/backend/access/brin/README for details.
*
* Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
* IDENTIFICATION
* src/backend/access/brin/brin.c
*
* TODO
* * ScalarArrayOpExpr (amsearcharray -> SK_SEARCHARRAY)
*/
#include "postgres.h"
#include "access/brin.h"
#include "access/brin_page.h"
#include "access/brin_pageops.h"
#include "access/brin_xlog.h"
#include "access/relation.h"
#include "access/reloptions.h"
#include "access/relscan.h"
#include "access/table.h"
#include "access/tableam.h"
#include "access/xloginsert.h"
#include "catalog/index.h"
#include "catalog/pg_am.h"
#include "commands/vacuum.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "postmaster/autovacuum.h"
#include "storage/bufmgr.h"
#include "storage/freespace.h"
#include "utils/acl.h"
#include "utils/builtins.h"
#include "utils/datum.h"
#include "utils/guc.h"
#include "utils/index_selfuncs.h"
#include "utils/memutils.h"
#include "utils/rel.h"
/*
* We use a BrinBuildState during initial construction of a BRIN index.
* The running state is kept in a BrinMemTuple.
*/
typedef struct BrinBuildState
{
Relation bs_irel;
int bs_numtuples;
Buffer bs_currentInsertBuf;
BlockNumber bs_pagesPerRange;
BlockNumber bs_currRangeStart;
BrinRevmap *bs_rmAccess;
BrinDesc *bs_bdesc;
BrinMemTuple *bs_dtuple;
} BrinBuildState;
/*
* Struct used as "opaque" during index scans
*/
typedef struct BrinOpaque
{
BlockNumber bo_pagesPerRange;
BrinRevmap *bo_rmAccess;
BrinDesc *bo_bdesc;
} BrinOpaque;
#define BRIN_ALL_BLOCKRANGES InvalidBlockNumber
static BrinBuildState *initialize_brin_buildstate(Relation idxRel,
BrinRevmap *revmap, BlockNumber pagesPerRange);
static void terminate_brin_buildstate(BrinBuildState *state);
static void brinsummarize(Relation index, Relation heapRel, BlockNumber pageRange,
bool include_partial, double *numSummarized, double *numExisting);
static void form_and_insert_tuple(BrinBuildState *state);
static void union_tuples(BrinDesc *bdesc, BrinMemTuple *a,
BrinTuple *b);
static void brin_vacuum_scan(Relation idxrel, BufferAccessStrategy strategy);
static bool add_values_to_range(Relation idxRel, BrinDesc *bdesc,
BrinMemTuple *dtup, Datum *values, bool *nulls);
static bool check_null_keys(BrinValues *bval, ScanKey *nullkeys, int nnullkeys);
/*
* BRIN handler function: return IndexAmRoutine with access method parameters
* and callbacks.
*/
Datum
brinhandler(PG_FUNCTION_ARGS)
{
IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);
amroutine->amstrategies = 0;
amroutine->amsupport = BRIN_LAST_OPTIONAL_PROCNUM;
amroutine->amoptsprocnum = BRIN_PROCNUM_OPTIONS;
amroutine->amcanorder = false;
amroutine->amcanorderbyop = false;
amroutine->amcanbackward = false;
amroutine->amcanunique = false;
amroutine->amcanmulticol = true;
amroutine->amoptionalkey = true;
amroutine->amsearcharray = false;
amroutine->amsearchnulls = true;
amroutine->amstorage = true;
amroutine->amclusterable = false;
amroutine->ampredlocks = false;
amroutine->amcanparallel = false;
amroutine->amcaninclude = false;
amroutine->amusemaintenanceworkmem = false;
amroutine->amsummarizing = true;
amroutine->amparallelvacuumoptions =
VACUUM_OPTION_PARALLEL_CLEANUP;
amroutine->amkeytype = InvalidOid;
amroutine->ambuild = brinbuild;
amroutine->ambuildempty = brinbuildempty;
amroutine->aminsert = brininsert;
amroutine->ambulkdelete = brinbulkdelete;
amroutine->amvacuumcleanup = brinvacuumcleanup;
amroutine->amcanreturn = NULL;
amroutine->amcostestimate = brincostestimate;
amroutine->amoptions = brinoptions;
amroutine->amproperty = NULL;
amroutine->ambuildphasename = NULL;
amroutine->amvalidate = brinvalidate;
amroutine->amadjustmembers = NULL;
amroutine->ambeginscan = brinbeginscan;
amroutine->amrescan = brinrescan;
amroutine->amgettuple = NULL;
amroutine->amgetbitmap = bringetbitmap;
amroutine->amendscan = brinendscan;
amroutine->ammarkpos = NULL;
amroutine->amrestrpos = NULL;
amroutine->amestimateparallelscan = NULL;
amroutine->aminitparallelscan = NULL;
amroutine->amparallelrescan = NULL;
PG_RETURN_POINTER(amroutine);
}
/*
* A tuple in the heap is being inserted. To keep a brin index up to date,
* we need to obtain the relevant index tuple and compare its stored values
* with those of the new tuple. If the tuple values are not consistent with
* the summary tuple, we need to update the index tuple.
*
* If autosummarization is enabled, check if we need to summarize the previous
* page range.
*
* If the range is not currently summarized (i.e. the revmap returns NULL for
* it), there's nothing to do for this tuple.
*/
bool
brininsert(Relation idxRel, Datum *values, bool *nulls,
ItemPointer heaptid, Relation heapRel,
IndexUniqueCheck checkUnique,
bool indexUnchanged,
IndexInfo *indexInfo)
{
BlockNumber pagesPerRange;
BlockNumber origHeapBlk;
BlockNumber heapBlk;
BrinDesc *bdesc = (BrinDesc *) indexInfo->ii_AmCache;
BrinRevmap *revmap;
Buffer buf = InvalidBuffer;
MemoryContext tupcxt = NULL;
MemoryContext oldcxt = CurrentMemoryContext;
bool autosummarize = BrinGetAutoSummarize(idxRel);
revmap = brinRevmapInitialize(idxRel, &pagesPerRange, NULL);
/*
* origHeapBlk is the block number where the insertion occurred. heapBlk
* is the first block in the corresponding page range.
*/
origHeapBlk = ItemPointerGetBlockNumber(heaptid);
heapBlk = (origHeapBlk / pagesPerRange) * pagesPerRange;
for (;;)
{
bool need_insert = false;
OffsetNumber off;
BrinTuple *brtup;
BrinMemTuple *dtup;
CHECK_FOR_INTERRUPTS();
/*
* If auto-summarization is enabled and we just inserted the first
* tuple into the first block of a new non-first page range, request a
* summarization run of the previous range.
*/
if (autosummarize &&
heapBlk > 0 &&
heapBlk == origHeapBlk &&
ItemPointerGetOffsetNumber(heaptid) == FirstOffsetNumber)
{
BlockNumber lastPageRange = heapBlk - 1;
BrinTuple *lastPageTuple;
lastPageTuple =
brinGetTupleForHeapBlock(revmap, lastPageRange, &buf, &off,
NULL, BUFFER_LOCK_SHARE, NULL);
if (!lastPageTuple)
{
bool recorded;
recorded = AutoVacuumRequestWork(AVW_BRINSummarizeRange,
RelationGetRelid(idxRel),
lastPageRange);
if (!recorded)
ereport(LOG,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("request for BRIN range summarization for index \"%s\" page %u was not recorded",
RelationGetRelationName(idxRel),
lastPageRange)));
}
else
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
brtup = brinGetTupleForHeapBlock(revmap, heapBlk, &buf, &off,
NULL, BUFFER_LOCK_SHARE, NULL);
/* if range is unsummarized, there's nothing to do */
if (!brtup)
break;
/* First time through in this statement? */
if (bdesc == NULL)
{
MemoryContextSwitchTo(indexInfo->ii_Context);
bdesc = brin_build_desc(idxRel);
indexInfo->ii_AmCache = (void *) bdesc;
MemoryContextSwitchTo(oldcxt);
}
/* First time through in this brininsert call? */
if (tupcxt == NULL)
{
tupcxt = AllocSetContextCreate(CurrentMemoryContext,
"brininsert cxt",
ALLOCSET_DEFAULT_SIZES);
MemoryContextSwitchTo(tupcxt);
}
dtup = brin_deform_tuple(bdesc, brtup, NULL);
need_insert = add_values_to_range(idxRel, bdesc, dtup, values, nulls);
if (!need_insert)
{
/*
* The tuple is consistent with the new values, so there's nothing
* to do.
*/
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
else
{
Page page = BufferGetPage(buf);
ItemId lp = PageGetItemId(page, off);
Size origsz;
BrinTuple *origtup;
Size newsz;
BrinTuple *newtup;
bool samepage;
/*
* Make a copy of the old tuple, so that we can compare it after
* re-acquiring the lock.
*/
origsz = ItemIdGetLength(lp);
origtup = brin_copy_tuple(brtup, origsz, NULL, NULL);
/*
* Before releasing the lock, check if we can attempt a same-page
* update. Another process could insert a tuple concurrently in
* the same page though, so downstream we must be prepared to cope
* if this turns out to not be possible after all.
*/
newtup = brin_form_tuple(bdesc, heapBlk, dtup, &newsz);
samepage = brin_can_do_samepage_update(buf, origsz, newsz);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
/*
* Try to update the tuple. If this doesn't work for whatever
* reason, we need to restart from the top; the revmap might be
* pointing at a different tuple for this block now, so we need to
* recompute to ensure both our new heap tuple and the other
* inserter's are covered by the combined tuple. It might be that
* we don't need to update at all.
*/
if (!brin_doupdate(idxRel, pagesPerRange, revmap, heapBlk,
buf, off, origtup, origsz, newtup, newsz,
samepage))
{
/* no luck; start over */
MemoryContextResetAndDeleteChildren(tupcxt);
continue;
}
}
/* success! */
break;
}
brinRevmapTerminate(revmap);
if (BufferIsValid(buf))
ReleaseBuffer(buf);
MemoryContextSwitchTo(oldcxt);
if (tupcxt != NULL)
MemoryContextDelete(tupcxt);
return false;
}
/*
* Initialize state for a BRIN index scan.
*
* We read the metapage here to determine the pages-per-range number that this
* index was built with. Note that since this cannot be changed while we're
* holding lock on index, it's not necessary to recompute it during brinrescan.
*/
IndexScanDesc
brinbeginscan(Relation r, int nkeys, int norderbys)
{
IndexScanDesc scan;
BrinOpaque *opaque;
scan = RelationGetIndexScan(r, nkeys, norderbys);
opaque = palloc_object(BrinOpaque);
opaque->bo_rmAccess = brinRevmapInitialize(r, &opaque->bo_pagesPerRange,
scan->xs_snapshot);
opaque->bo_bdesc = brin_build_desc(r);
scan->opaque = opaque;
return scan;
}
/*
* Execute the index scan.
*
* This works by reading index TIDs from the revmap, and obtaining the index
* tuples pointed to by them; the summary values in the index tuples are
* compared to the scan keys. We return into the TID bitmap all the pages in
* ranges corresponding to index tuples that match the scan keys.
*
* If a TID from the revmap is read as InvalidTID, we know that range is
* unsummarized. Pages in those ranges need to be returned regardless of scan
* keys.
*/
int64
bringetbitmap(IndexScanDesc scan, TIDBitmap *tbm)
{
Relation idxRel = scan->indexRelation;
Buffer buf = InvalidBuffer;
BrinDesc *bdesc;
Oid heapOid;
Relation heapRel;
BrinOpaque *opaque;
BlockNumber nblocks;
BlockNumber heapBlk;
int totalpages = 0;
FmgrInfo *consistentFn;
MemoryContext oldcxt;
MemoryContext perRangeCxt;
BrinMemTuple *dtup;
BrinTuple *btup = NULL;
Size btupsz = 0;
ScanKey **keys,
**nullkeys;
int *nkeys,
*nnullkeys;
char *ptr;
Size len;
char *tmp PG_USED_FOR_ASSERTS_ONLY;
opaque = (BrinOpaque *) scan->opaque;
bdesc = opaque->bo_bdesc;
pgstat_count_index_scan(idxRel);
/*
* We need to know the size of the table so that we know how long to
* iterate on the revmap.
*/
heapOid = IndexGetRelation(RelationGetRelid(idxRel), false);
heapRel = table_open(heapOid, AccessShareLock);
nblocks = RelationGetNumberOfBlocks(heapRel);
table_close(heapRel, AccessShareLock);
/*
* Make room for the consistent support procedures of indexed columns. We
* don't look them up here; we do that lazily the first time we see a scan
* key reference each of them. We rely on zeroing fn_oid to InvalidOid.
*/
consistentFn = palloc0_array(FmgrInfo, bdesc->bd_tupdesc->natts);
/*
* Make room for per-attribute lists of scan keys that we'll pass to the
* consistent support procedure. We don't know which attributes have scan
* keys, so we allocate space for all attributes. That may use more memory
* but it's probably cheaper than determining which attributes are used.
*
* We keep null and regular keys separate, so that we can pass just the
* regular keys to the consistent function easily.
*
* To reduce the allocation overhead, we allocate one big chunk and then
* carve it into smaller arrays ourselves. All the pieces have exactly the
* same lifetime, so that's OK.
*
* XXX The widest index can have 32 attributes, so the amount of wasted
* memory is negligible. We could invent a more compact approach (with
* just space for used attributes) but that would make the matching more
* complex so it's not a good trade-off.
*/
len =
MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts) + /* regular keys */
MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys) * bdesc->bd_tupdesc->natts +
MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts) +
MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts) + /* NULL keys */
MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys) * bdesc->bd_tupdesc->natts +
MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts);
ptr = palloc(len);
tmp = ptr;
keys = (ScanKey **) ptr;
ptr += MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts);
nullkeys = (ScanKey **) ptr;
ptr += MAXALIGN(sizeof(ScanKey *) * bdesc->bd_tupdesc->natts);
nkeys = (int *) ptr;
ptr += MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts);
nnullkeys = (int *) ptr;
ptr += MAXALIGN(sizeof(int) * bdesc->bd_tupdesc->natts);
for (int i = 0; i < bdesc->bd_tupdesc->natts; i++)
{
keys[i] = (ScanKey *) ptr;
ptr += MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys);
nullkeys[i] = (ScanKey *) ptr;
ptr += MAXALIGN(sizeof(ScanKey) * scan->numberOfKeys);
}
Assert(tmp + len == ptr);
/* zero the number of keys */
memset(nkeys, 0, sizeof(int) * bdesc->bd_tupdesc->natts);
memset(nnullkeys, 0, sizeof(int) * bdesc->bd_tupdesc->natts);
/* Preprocess the scan keys - split them into per-attribute arrays. */
for (int keyno = 0; keyno < scan->numberOfKeys; keyno++)
{
ScanKey key = &scan->keyData[keyno];
AttrNumber keyattno = key->sk_attno;
/*
* The collation of the scan key must match the collation used in the
* index column (but only if the search is not IS NULL/ IS NOT NULL).
* Otherwise we shouldn't be using this index ...
*/
Assert((key->sk_flags & SK_ISNULL) ||
(key->sk_collation ==
TupleDescAttr(bdesc->bd_tupdesc,
keyattno - 1)->attcollation));
/*
* First time we see this index attribute, so init as needed.
*
* This is a bit of an overkill - we don't know how many scan keys are
* there for this attribute, so we simply allocate the largest number
* possible (as if all keys were for this attribute). This may waste a
* bit of memory, but we only expect small number of scan keys in
* general, so this should be negligible, and repeated repalloc calls
* are not free either.
*/
if (consistentFn[keyattno - 1].fn_oid == InvalidOid)
{
FmgrInfo *tmp;
/* First time we see this attribute, so no key/null keys. */
Assert(nkeys[keyattno - 1] == 0);
Assert(nnullkeys[keyattno - 1] == 0);
tmp = index_getprocinfo(idxRel, keyattno,
BRIN_PROCNUM_CONSISTENT);
fmgr_info_copy(&consistentFn[keyattno - 1], tmp,
CurrentMemoryContext);
}
/* Add key to the proper per-attribute array. */
if (key->sk_flags & SK_ISNULL)
{
nullkeys[keyattno - 1][nnullkeys[keyattno - 1]] = key;
nnullkeys[keyattno - 1]++;
}
else
{
keys[keyattno - 1][nkeys[keyattno - 1]] = key;
nkeys[keyattno - 1]++;
}
}
/* allocate an initial in-memory tuple, out of the per-range memcxt */
dtup = brin_new_memtuple(bdesc);
/*
* Setup and use a per-range memory context, which is reset every time we
* loop below. This avoids having to free the tuples within the loop.
*/
perRangeCxt = AllocSetContextCreate(CurrentMemoryContext,
"bringetbitmap cxt",
ALLOCSET_DEFAULT_SIZES);
oldcxt = MemoryContextSwitchTo(perRangeCxt);
/*
* Now scan the revmap. We start by querying for heap page 0,
* incrementing by the number of pages per range; this gives us a full
* view of the table.
*/
for (heapBlk = 0; heapBlk < nblocks; heapBlk += opaque->bo_pagesPerRange)
{
bool addrange;
bool gottuple = false;
BrinTuple *tup;
OffsetNumber off;
Size size;
CHECK_FOR_INTERRUPTS();
MemoryContextResetAndDeleteChildren(perRangeCxt);
tup = brinGetTupleForHeapBlock(opaque->bo_rmAccess, heapBlk, &buf,
&off, &size, BUFFER_LOCK_SHARE,
scan->xs_snapshot);
if (tup)
{
gottuple = true;
btup = brin_copy_tuple(tup, size, btup, &btupsz);
LockBuffer(buf, BUFFER_LOCK_UNLOCK);
}
/*
* For page ranges with no indexed tuple, we must return the whole
* range; otherwise, compare it to the scan keys.
*/
if (!gottuple)
{
addrange = true;
}
else
{
dtup = brin_deform_tuple(bdesc, btup, dtup);
if (dtup->bt_placeholder)
{
/*
* Placeholder tuples are always returned, regardless of the
* values stored in them.
*/
addrange = true;
}
else
{
int attno;
/*
* Compare scan keys with summary values stored for the range.
* If scan keys are matched, the page range must be added to
* the bitmap. We initially assume the range needs to be
* added; in particular this serves the case where there are
* no keys.
*/
addrange = true;
for (attno = 1; attno <= bdesc->bd_tupdesc->natts; attno++)
{
BrinValues *bval;
Datum add;
Oid collation;
/*
* skip attributes without any scan keys (both regular and
* IS [NOT] NULL)
*/
if (nkeys[attno - 1] == 0 && nnullkeys[attno - 1] == 0)
continue;
bval = &dtup->bt_columns[attno - 1];
/*
* If the BRIN tuple indicates that this range is empty,
* we can skip it: there's nothing to match. We don't
* need to examine the next columns.
*/
if (dtup->bt_empty_range)
{
addrange = false;
break;
}
/*
* First check if there are any IS [NOT] NULL scan keys,
* and if we're violating them. In that case we can
* terminate early, without invoking the support function.
*
* As there may be more keys, we can only determine
* mismatch within this loop.
*/
if (bdesc->bd_info[attno - 1]->oi_regular_nulls &&
!check_null_keys(bval, nullkeys[attno - 1],
nnullkeys[attno - 1]))
{
/*
* If any of the IS [NOT] NULL keys failed, the page
* range as a whole can't pass. So terminate the loop.
*/
addrange = false;
break;
}
/*
* So either there are no IS [NOT] NULL keys, or all
* passed. If there are no regular scan keys, we're done -
* the page range matches. If there are regular keys, but
* the page range is marked as 'all nulls' it can't
* possibly pass (we're assuming the operators are
* strict).
*/
/* No regular scan keys - page range as a whole passes. */
if (!nkeys[attno - 1])
continue;
Assert((nkeys[attno - 1] > 0) &&
(nkeys[attno - 1] <= scan->numberOfKeys));
/* If it is all nulls, it cannot possibly be consistent. */
if (bval->bv_allnulls)
{
addrange = false;
break;
}
/*
* Collation from the first key (has to be the same for
* all keys for the same attribute).
*/
collation = keys[attno - 1][0]->sk_collation;
/*
* Check whether the scan key is consistent with the page
* range values; if so, have the pages in the range added
* to the output bitmap.
*
* The opclass may or may not support processing of
* multiple scan keys. We can determine that based on the
* number of arguments - functions with extra parameter
* (number of scan keys) do support this, otherwise we
* have to simply pass the scan keys one by one.
*/
if (consistentFn[attno - 1].fn_nargs >= 4)
{
/* Check all keys at once */
add = FunctionCall4Coll(&consistentFn[attno - 1],
collation,
PointerGetDatum(bdesc),
PointerGetDatum(bval),
PointerGetDatum(keys[attno - 1]),
Int32GetDatum(nkeys[attno - 1]));
addrange = DatumGetBool(add);
}
else
{
/*
* Check keys one by one
*
* When there are multiple scan keys, failure to meet
* the criteria for a single one of them is enough to
* discard the range as a whole, so break out of the
* loop as soon as a false return value is obtained.
*/
int keyno;
for (keyno = 0; keyno < nkeys[attno - 1]; keyno++)
{
add = FunctionCall3Coll(&consistentFn[attno - 1],
keys[attno - 1][keyno]->sk_collation,
PointerGetDatum(bdesc),
PointerGetDatum(bval),
PointerGetDatum(keys[attno - 1][keyno]));
addrange = DatumGetBool(add);
if (!addrange)
break;
}
}
/*
* If we found a scan key eliminating the range, no need
* to check additional ones.
*/
if (!addrange)
break;
}
}
}
/* add the pages in the range to the output bitmap, if needed */
if (addrange)
{
BlockNumber pageno;
for (pageno = heapBlk;
pageno <= Min(nblocks, heapBlk + opaque->bo_pagesPerRange) - 1;
pageno++)
{
MemoryContextSwitchTo(oldcxt);
tbm_add_page(tbm, pageno);
totalpages++;
MemoryContextSwitchTo(perRangeCxt);
}
}
}
MemoryContextSwitchTo(oldcxt);
MemoryContextDelete(perRangeCxt);
if (buf != InvalidBuffer)
ReleaseBuffer(buf);
/*
* XXX We have an approximation of the number of *pages* that our scan
* returns, but we don't have a precise idea of the number of heap tuples
* involved.
*/
return totalpages * 10;
}
/*
* Re-initialize state for a BRIN index scan
*/
void
brinrescan(IndexScanDesc scan, ScanKey scankey, int nscankeys,
ScanKey orderbys, int norderbys)
{
/*
* Other index AMs preprocess the scan keys at this point, or sometime
* early during the scan; this lets them optimize by removing redundant
* keys, or doing early returns when they are impossible to satisfy; see
* _bt_preprocess_keys for an example. Something like that could be added
* here someday, too.
*/
if (scankey && scan->numberOfKeys > 0)
memmove(scan->keyData, scankey,
scan->numberOfKeys * sizeof(ScanKeyData));
}
/*
* Close down a BRIN index scan
*/
void
brinendscan(IndexScanDesc scan)
{
BrinOpaque *opaque = (BrinOpaque *) scan->opaque;
brinRevmapTerminate(opaque->bo_rmAccess);
brin_free_desc(opaque->bo_bdesc);
pfree(opaque);
}
/*
* Per-heap-tuple callback for table_index_build_scan.
*
* Note we don't worry about the page range at the end of the table here; it is
* present in the build state struct after we're called the last time, but not
* inserted into the index. Caller must ensure to do so, if appropriate.
*/
static void
brinbuildCallback(Relation index,
ItemPointer tid,
Datum *values,
bool *isnull,
bool tupleIsAlive,
void *brstate)
{
BrinBuildState *state = (BrinBuildState *) brstate;
BlockNumber thisblock;
thisblock = ItemPointerGetBlockNumber(tid);
/*
* If we're in a block that belongs to a future range, summarize what
* we've got and start afresh. Note the scan might have skipped many
* pages, if they were devoid of live tuples; make sure to insert index
* tuples for those too.
*/
while (thisblock > state->bs_currRangeStart + state->bs_pagesPerRange - 1)
{
BRIN_elog((DEBUG2,
"brinbuildCallback: completed a range: %u--%u",
state->bs_currRangeStart,
state->bs_currRangeStart + state->bs_pagesPerRange));
/* create the index tuple and insert it */
form_and_insert_tuple(state);
/* set state to correspond to the next range */
state->bs_currRangeStart += state->bs_pagesPerRange;
/* re-initialize state for it */
brin_memtuple_initialize(state->bs_dtuple, state->bs_bdesc);
}
/* Accumulate the current tuple into the running state */
(void) add_values_to_range(index, state->bs_bdesc, state->bs_dtuple,
values, isnull);
}
/*
* brinbuild() -- build a new BRIN index.
*/
IndexBuildResult *
brinbuild(Relation heap, Relation index, IndexInfo *indexInfo)
{
IndexBuildResult *result;
double reltuples;
double idxtuples;
BrinRevmap *revmap;
BrinBuildState *state;
Buffer meta;
BlockNumber pagesPerRange;
/*
* We expect to be called exactly once for any index relation.
*/
if (RelationGetNumberOfBlocks(index) != 0)
elog(ERROR, "index \"%s\" already contains data",
RelationGetRelationName(index));
/*
* Critical section not required, because on error the creation of the
* whole relation will be rolled back.
*/
meta = ExtendBufferedRel(BMR_REL(index), MAIN_FORKNUM, NULL,
EB_LOCK_FIRST | EB_SKIP_EXTENSION_LOCK);
Assert(BufferGetBlockNumber(meta) == BRIN_METAPAGE_BLKNO);
brin_metapage_init(BufferGetPage(meta), BrinGetPagesPerRange(index),
BRIN_CURRENT_VERSION);
MarkBufferDirty(meta);
if (RelationNeedsWAL(index))
{
xl_brin_createidx xlrec;
XLogRecPtr recptr;
Page page;
xlrec.version = BRIN_CURRENT_VERSION;
xlrec.pagesPerRange = BrinGetPagesPerRange(index);
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, SizeOfBrinCreateIdx);
XLogRegisterBuffer(0, meta, REGBUF_WILL_INIT | REGBUF_STANDARD);
recptr = XLogInsert(RM_BRIN_ID, XLOG_BRIN_CREATE_INDEX);
page = BufferGetPage(meta);
PageSetLSN(page, recptr);
}
UnlockReleaseBuffer(meta);
/*
* Initialize our state, including the deformed tuple state.
*/
revmap = brinRevmapInitialize(index, &pagesPerRange, NULL);
state = initialize_brin_buildstate(index, revmap, pagesPerRange);
/*
* Now scan the relation. No syncscan allowed here because we want the
* heap blocks in physical order.
*/
reltuples = table_index_build_scan(heap, index, indexInfo, false, true,
brinbuildCallback, (void *) state, NULL);
/* process the final batch */
form_and_insert_tuple(state);
/* release resources */
idxtuples = state->bs_numtuples;
brinRevmapTerminate(state->bs_rmAccess);
terminate_brin_buildstate(state);
/*
* Return statistics
*/
result = palloc_object(IndexBuildResult);
result->heap_tuples = reltuples;
result->index_tuples = idxtuples;
return result;
}
void
brinbuildempty(Relation index)
{
Buffer metabuf;
/* An empty BRIN index has a metapage only. */
metabuf = ExtendBufferedRel(BMR_REL(index), INIT_FORKNUM, NULL,
EB_LOCK_FIRST | EB_SKIP_EXTENSION_LOCK);
/* Initialize and xlog metabuffer. */
START_CRIT_SECTION();
brin_metapage_init(BufferGetPage(metabuf), BrinGetPagesPerRange(index),
BRIN_CURRENT_VERSION);
MarkBufferDirty(metabuf);
log_newpage_buffer(metabuf, true);
END_CRIT_SECTION();
UnlockReleaseBuffer(metabuf);
}
/*
* brinbulkdelete
* Since there are no per-heap-tuple index tuples in BRIN indexes,
* there's not a lot we can do here.
*
* XXX we could mark item tuples as "dirty" (when a minimum or maximum heap
* tuple is deleted), meaning the need to re-run summarization on the affected
* range. Would need to add an extra flag in brintuples for that.
*/
IndexBulkDeleteResult *
brinbulkdelete(IndexVacuumInfo *info, IndexBulkDeleteResult *stats,
IndexBulkDeleteCallback callback, void *callback_state)
{
/* allocate stats if first time through, else re-use existing struct */
if (stats == NULL)
stats = palloc0_object(IndexBulkDeleteResult);
return stats;
}
/*
* This routine is in charge of "vacuuming" a BRIN index: we just summarize
* ranges that are currently unsummarized.
*/
IndexBulkDeleteResult *
brinvacuumcleanup(IndexVacuumInfo *info, IndexBulkDeleteResult *stats)
{
Relation heapRel;
/* No-op in ANALYZE ONLY mode */
if (info->analyze_only)
return stats;
if (!stats)
stats = palloc0_object(IndexBulkDeleteResult);
stats->num_pages = RelationGetNumberOfBlocks(info->index);
/* rest of stats is initialized by zeroing */
heapRel = table_open(IndexGetRelation(RelationGetRelid(info->index), false),
AccessShareLock);
brin_vacuum_scan(info->index, info->strategy);
brinsummarize(info->index, heapRel, BRIN_ALL_BLOCKRANGES, false,
&stats->num_index_tuples, &stats->num_index_tuples);
table_close(heapRel, AccessShareLock);
return stats;
}
/*
* reloptions processor for BRIN indexes
*/
bytea *
brinoptions(Datum reloptions, bool validate)
{
static const relopt_parse_elt tab[] = {
{"pages_per_range", RELOPT_TYPE_INT, offsetof(BrinOptions, pagesPerRange)},
{"autosummarize", RELOPT_TYPE_BOOL, offsetof(BrinOptions, autosummarize)}
};
return (bytea *) build_reloptions(reloptions, validate,
RELOPT_KIND_BRIN,
sizeof(BrinOptions),
tab, lengthof(tab));
}
/*