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
|
/*-------------------------------------------------------------------------
*
* pruneheap.c
* heap page pruning and HOT-chain management code
*
* Portions Copyright (c) 1996-2021, PostgreSQL Global Development Group
* Portions Copyright (c) 1994, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/access/heap/pruneheap.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/heapam.h"
#include "access/heapam_xlog.h"
#include "access/htup_details.h"
#include "access/transam.h"
#include "access/xlog.h"
#include "catalog/catalog.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "storage/bufmgr.h"
#include "utils/snapmgr.h"
#include "utils/rel.h"
#include "utils/snapmgr.h"
/* Working data for heap_page_prune and subroutines */
typedef struct
{
Relation rel;
/* tuple visibility test, initialized for the relation */
GlobalVisState *vistest;
/*
* Thresholds set by TransactionIdLimitedForOldSnapshots() if they have
* been computed (done on demand, and only if
* OldSnapshotThresholdActive()). The first time a tuple is about to be
* removed based on the limited horizon, old_snap_used is set to true, and
* SetOldSnapshotThresholdTimestamp() is called. See
* heap_prune_satisfies_vacuum().
*/
TimestampTz old_snap_ts;
TransactionId old_snap_xmin;
bool old_snap_used;
TransactionId new_prune_xid; /* new prune hint value for page */
TransactionId latestRemovedXid; /* latest xid to be removed by this prune */
int nredirected; /* numbers of entries in arrays below */
int ndead;
int nunused;
/* arrays that accumulate indexes of items to be changed */
OffsetNumber redirected[MaxHeapTuplesPerPage * 2];
OffsetNumber nowdead[MaxHeapTuplesPerPage];
OffsetNumber nowunused[MaxHeapTuplesPerPage];
/*
* marked[i] is true if item i is entered in one of the above arrays.
*
* This needs to be MaxHeapTuplesPerPage + 1 long as FirstOffsetNumber is
* 1. Otherwise every access would need to subtract 1.
*/
bool marked[MaxHeapTuplesPerPage + 1];
/*
* Tuple visibility is only computed once for each tuple, for correctness
* and efficiency reasons; see comment in heap_page_prune() for
* details. This is of type int8[,] intead of HTSV_Result[], so we can use
* -1 to indicate no visibility has been computed, e.g. for LP_DEAD items.
*
* Same indexing as ->marked.
*/
int8 htsv[MaxHeapTuplesPerPage + 1];
} PruneState;
/* Local functions */
static HTSV_Result heap_prune_satisfies_vacuum(PruneState *prstate,
HeapTuple tup,
Buffer buffer);
static int heap_prune_chain(Buffer buffer,
OffsetNumber rootoffnum,
PruneState *prstate);
static void heap_prune_record_prunable(PruneState *prstate, TransactionId xid);
static void heap_prune_record_redirect(PruneState *prstate,
OffsetNumber offnum, OffsetNumber rdoffnum);
static void heap_prune_record_dead(PruneState *prstate, OffsetNumber offnum);
static void heap_prune_record_unused(PruneState *prstate, OffsetNumber offnum);
/*
* Optionally prune and repair fragmentation in the specified page.
*
* This is an opportunistic function. It will perform housekeeping
* only if the page heuristically looks like a candidate for pruning and we
* can acquire buffer cleanup lock without blocking.
*
* Note: this is called quite often. It's important that it fall out quickly
* if there's not any use in pruning.
*
* Caller must have pin on the buffer, and must *not* have a lock on it.
*/
void
heap_page_prune_opt(Relation relation, Buffer buffer)
{
Page page = BufferGetPage(buffer);
TransactionId prune_xid;
GlobalVisState *vistest;
TransactionId limited_xmin = InvalidTransactionId;
TimestampTz limited_ts = 0;
Size minfree;
/*
* We can't write WAL in recovery mode, so there's no point trying to
* clean the page. The primary will likely issue a cleaning WAL record
* soon anyway, so this is no particular loss.
*/
if (RecoveryInProgress())
return;
/*
* XXX: Magic to keep old_snapshot_threshold tests appear "working". They
* currently are broken, and discussion of what to do about them is
* ongoing. See
* https://www.postgresql.org/message-id/20200403001235.e6jfdll3gh2ygbuc%40alap3.anarazel.de
*/
if (old_snapshot_threshold == 0)
SnapshotTooOldMagicForTest();
/*
* First check whether there's any chance there's something to prune,
* determining the appropriate horizon is a waste if there's no prune_xid
* (i.e. no updates/deletes left potentially dead tuples around).
*/
prune_xid = ((PageHeader) page)->pd_prune_xid;
if (!TransactionIdIsValid(prune_xid))
return;
/*
* Check whether prune_xid indicates that there may be dead rows that can
* be cleaned up.
*
* It is OK to check the old snapshot limit before acquiring the cleanup
* lock because the worst that can happen is that we are not quite as
* aggressive about the cleanup (by however many transaction IDs are
* consumed between this point and acquiring the lock). This allows us to
* save significant overhead in the case where the page is found not to be
* prunable.
*
* Even if old_snapshot_threshold is set, we first check whether the page
* can be pruned without. Both because
* TransactionIdLimitedForOldSnapshots() is not cheap, and because not
* unnecessarily relying on old_snapshot_threshold avoids causing
* conflicts.
*/
vistest = GlobalVisTestFor(relation);
if (!GlobalVisTestIsRemovableXid(vistest, prune_xid))
{
if (!OldSnapshotThresholdActive())
return;
if (!TransactionIdLimitedForOldSnapshots(GlobalVisTestNonRemovableHorizon(vistest),
relation,
&limited_xmin, &limited_ts))
return;
if (!TransactionIdPrecedes(prune_xid, limited_xmin))
return;
}
/*
* We prune when a previous UPDATE failed to find enough space on the page
* for a new tuple version, or when free space falls below the relation's
* fill-factor target (but not less than 10%).
*
* Checking free space here is questionable since we aren't holding any
* lock on the buffer; in the worst case we could get a bogus answer. It's
* unlikely to be *seriously* wrong, though, since reading either pd_lower
* or pd_upper is probably atomic. Avoiding taking a lock seems more
* important than sometimes getting a wrong answer in what is after all
* just a heuristic estimate.
*/
minfree = RelationGetTargetPageFreeSpace(relation,
HEAP_DEFAULT_FILLFACTOR);
minfree = Max(minfree, BLCKSZ / 10);
if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree)
{
/* OK, try to get exclusive buffer lock */
if (!ConditionalLockBufferForCleanup(buffer))
return;
/*
* Now that we have buffer lock, get accurate information about the
* page's free space, and recheck the heuristic about whether to
* prune. (We needn't recheck PageIsPrunable, since no one else could
* have pruned while we hold pin.)
*/
if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree)
{
/* OK to prune */
(void) heap_page_prune(relation, buffer, vistest,
limited_xmin, limited_ts,
true, NULL);
}
/* And release buffer lock */
LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
}
}
/*
* Prune and repair fragmentation in the specified page.
*
* Caller must have pin and buffer cleanup lock on the page.
*
* vistest is used to distinguish whether tuples are DEAD or RECENTLY_DEAD
* (see heap_prune_satisfies_vacuum and
* HeapTupleSatisfiesVacuum). old_snap_xmin / old_snap_ts need to
* either have been set by TransactionIdLimitedForOldSnapshots, or
* InvalidTransactionId/0 respectively.
*
* If report_stats is true then we send the number of reclaimed heap-only
* tuples to pgstats. (This must be false during vacuum, since vacuum will
* send its own new total to pgstats, and we don't want this delta applied
* on top of that.)
*
* off_loc is the offset location required by the caller to use in error
* callback.
*
* Returns the number of tuples deleted from the page during this call.
*/
int
heap_page_prune(Relation relation, Buffer buffer,
GlobalVisState *vistest,
TransactionId old_snap_xmin,
TimestampTz old_snap_ts,
bool report_stats,
OffsetNumber *off_loc)
{
int ndeleted = 0;
Page page = BufferGetPage(buffer);
OffsetNumber offnum,
maxoff;
PruneState prstate;
HeapTupleData tup;
/*
* Our strategy is to scan the page and make lists of items to change,
* then apply the changes within a critical section. This keeps as much
* logic as possible out of the critical section, and also ensures that
* WAL replay will work the same as the normal case.
*
* First, initialize the new pd_prune_xid value to zero (indicating no
* prunable tuples). If we find any tuples which may soon become
* prunable, we will save the lowest relevant XID in new_prune_xid. Also
* initialize the rest of our working state.
*/
prstate.new_prune_xid = InvalidTransactionId;
prstate.rel = relation;
prstate.vistest = vistest;
prstate.old_snap_xmin = old_snap_xmin;
prstate.old_snap_ts = old_snap_ts;
prstate.old_snap_used = false;
prstate.latestRemovedXid = InvalidTransactionId;
prstate.nredirected = prstate.ndead = prstate.nunused = 0;
memset(prstate.marked, 0, sizeof(prstate.marked));
maxoff = PageGetMaxOffsetNumber(page);
tup.t_tableOid = RelationGetRelid(prstate.rel);
/*
* Determine HTSV for all tuples.
*
* This is required for correctness to deal with cases where running HTSV
* twice could result in different results (e.g. RECENTLY_DEAD can turn to
* DEAD if another checked item causes GlobalVisTestIsRemovableFullXid()
* to update the horizon, INSERT_IN_PROGRESS can change to DEAD if the
* inserting transaction aborts, ...). That in turn could cause
* heap_prune_chain() to behave incorrectly if a tuple is reached twice,
* once directly via a heap_prune_chain() and once following a HOT chain.
*
* It's also good for performance. Most commonly tuples within a page are
* stored at decreasing offsets (while the items are stored at increasing
* offsets). When processing all tuples on a page this leads to reading
* memory at decreasing offsets within a page, with a variable stride.
* That's hard for CPU prefetchers to deal with. Processing the items in
* reverse order (and thus the tuples in increasing order) increases
* prefetching efficiency significantly / decreases the number of cache
* misses.
*/
for (offnum = maxoff;
offnum >= FirstOffsetNumber;
offnum = OffsetNumberPrev(offnum))
{
ItemId itemid = PageGetItemId(page, offnum);
HeapTupleHeader htup;
/* Nothing to do if slot doesn't contain a tuple */
if (!ItemIdIsNormal(itemid))
{
prstate.htsv[offnum] = -1;
continue;
}
htup = (HeapTupleHeader) PageGetItem(page, itemid);
tup.t_data = htup;
tup.t_len = ItemIdGetLength(itemid);
ItemPointerSet(&(tup.t_self), BufferGetBlockNumber(buffer), offnum);
/*
* Set the offset number so that we can display it along with any
* error that occurred while processing this tuple.
*/
if (off_loc)
*off_loc = offnum;
prstate.htsv[offnum] = heap_prune_satisfies_vacuum(&prstate, &tup,
buffer);
}
/* Scan the page */
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
ItemId itemid;
/* Ignore items already processed as part of an earlier chain */
if (prstate.marked[offnum])
continue;
/* see preceding loop */
if (off_loc)
*off_loc = offnum;
/* Nothing to do if slot is empty or already dead */
itemid = PageGetItemId(page, offnum);
if (!ItemIdIsUsed(itemid) || ItemIdIsDead(itemid))
continue;
/* Process this item or chain of items */
ndeleted += heap_prune_chain(buffer, offnum, &prstate);
}
/* Clear the offset information once we have processed the given page. */
if (off_loc)
*off_loc = InvalidOffsetNumber;
/* Any error while applying the changes is critical */
START_CRIT_SECTION();
/* Have we found any prunable items? */
if (prstate.nredirected > 0 || prstate.ndead > 0 || prstate.nunused > 0)
{
/*
* Apply the planned item changes, then repair page fragmentation, and
* update the page's hint bit about whether it has free line pointers.
*/
heap_page_prune_execute(buffer,
prstate.redirected, prstate.nredirected,
prstate.nowdead, prstate.ndead,
prstate.nowunused, prstate.nunused);
/*
* Update the page's pd_prune_xid field to either zero, or the lowest
* XID of any soon-prunable tuple.
*/
((PageHeader) page)->pd_prune_xid = prstate.new_prune_xid;
/*
* Also clear the "page is full" flag, since there's no point in
* repeating the prune/defrag process until something else happens to
* the page.
*/
PageClearFull(page);
MarkBufferDirty(buffer);
/*
* Emit a WAL XLOG_HEAP2_PRUNE record showing what we did
*/
if (RelationNeedsWAL(relation))
{
xl_heap_prune xlrec;
XLogRecPtr recptr;
xlrec.latestRemovedXid = prstate.latestRemovedXid;
xlrec.nredirected = prstate.nredirected;
xlrec.ndead = prstate.ndead;
XLogBeginInsert();
XLogRegisterData((char *) &xlrec, SizeOfHeapPrune);
XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
/*
* The OffsetNumber arrays are not actually in the buffer, but we
* pretend that they are. When XLogInsert stores the whole
* buffer, the offset arrays need not be stored too.
*/
if (prstate.nredirected > 0)
XLogRegisterBufData(0, (char *) prstate.redirected,
prstate.nredirected *
sizeof(OffsetNumber) * 2);
if (prstate.ndead > 0)
XLogRegisterBufData(0, (char *) prstate.nowdead,
prstate.ndead * sizeof(OffsetNumber));
if (prstate.nunused > 0)
XLogRegisterBufData(0, (char *) prstate.nowunused,
prstate.nunused * sizeof(OffsetNumber));
recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_PRUNE);
PageSetLSN(BufferGetPage(buffer), recptr);
}
}
else
{
/*
* If we didn't prune anything, but have found a new value for the
* pd_prune_xid field, update it and mark the buffer dirty. This is
* treated as a non-WAL-logged hint.
*
* Also clear the "page is full" flag if it is set, since there's no
* point in repeating the prune/defrag process until something else
* happens to the page.
*/
if (((PageHeader) page)->pd_prune_xid != prstate.new_prune_xid ||
PageIsFull(page))
{
((PageHeader) page)->pd_prune_xid = prstate.new_prune_xid;
PageClearFull(page);
MarkBufferDirtyHint(buffer, true);
}
}
END_CRIT_SECTION();
/*
* If requested, report the number of tuples reclaimed to pgstats. This is
* ndeleted minus ndead, because we don't want to count a now-DEAD root
* item as a deletion for this purpose.
*/
if (report_stats && ndeleted > prstate.ndead)
pgstat_update_heap_dead_tuples(relation, ndeleted - prstate.ndead);
/*
* XXX Should we update the FSM information of this page ?
*
* There are two schools of thought here. We may not want to update FSM
* information so that the page is not used for unrelated UPDATEs/INSERTs
* and any free space in this page will remain available for further
* UPDATEs in *this* page, thus improving chances for doing HOT updates.
*
* But for a large table and where a page does not receive further UPDATEs
* for a long time, we might waste this space by not updating the FSM
* information. The relation may get extended and fragmented further.
*
* One possibility is to leave "fillfactor" worth of space in this page
* and update FSM with the remaining space.
*/
return ndeleted;
}
/*
* Perform visibility checks for heap pruning.
*
* This is more complicated than just using GlobalVisTestIsRemovableXid()
* because of old_snapshot_threshold. We only want to increase the threshold
* that triggers errors for old snapshots when we actually decide to remove a
* row based on the limited horizon.
*
* Due to its cost we also only want to call
* TransactionIdLimitedForOldSnapshots() if necessary, i.e. we might not have
* done so in heap_hot_prune_opt() if pd_prune_xid was old enough. But we
* still want to be able to remove rows that are too new to be removed
* according to prstate->vistest, but that can be removed based on
* old_snapshot_threshold. So we call TransactionIdLimitedForOldSnapshots() on
* demand in here, if appropriate.
*/
static HTSV_Result
heap_prune_satisfies_vacuum(PruneState *prstate, HeapTuple tup, Buffer buffer)
{
HTSV_Result res;
TransactionId dead_after;
res = HeapTupleSatisfiesVacuumHorizon(tup, buffer, &dead_after);
if (res != HEAPTUPLE_RECENTLY_DEAD)
return res;
/*
* If we are already relying on the limited xmin, there is no need to
* delay doing so anymore.
*/
if (prstate->old_snap_used)
{
Assert(TransactionIdIsValid(prstate->old_snap_xmin));
if (TransactionIdPrecedes(dead_after, prstate->old_snap_xmin))
res = HEAPTUPLE_DEAD;
return res;
}
/*
* First check if GlobalVisTestIsRemovableXid() is sufficient to find the
* row dead. If not, and old_snapshot_threshold is enabled, try to use the
* lowered horizon.
*/
if (GlobalVisTestIsRemovableXid(prstate->vistest, dead_after))
res = HEAPTUPLE_DEAD;
else if (OldSnapshotThresholdActive())
{
/* haven't determined limited horizon yet, requests */
if (!TransactionIdIsValid(prstate->old_snap_xmin))
{
TransactionId horizon =
GlobalVisTestNonRemovableHorizon(prstate->vistest);
TransactionIdLimitedForOldSnapshots(horizon, prstate->rel,
&prstate->old_snap_xmin,
&prstate->old_snap_ts);
}
if (TransactionIdIsValid(prstate->old_snap_xmin) &&
TransactionIdPrecedes(dead_after, prstate->old_snap_xmin))
{
/*
* About to remove row based on snapshot_too_old. Need to raise
* the threshold so problematic accesses would error.
*/
Assert(!prstate->old_snap_used);
SetOldSnapshotThresholdTimestamp(prstate->old_snap_ts,
prstate->old_snap_xmin);
prstate->old_snap_used = true;
res = HEAPTUPLE_DEAD;
}
}
return res;
}
/*
* Prune specified line pointer or a HOT chain originating at line pointer.
*
* If the item is an index-referenced tuple (i.e. not a heap-only tuple),
* the HOT chain is pruned by removing all DEAD tuples at the start of the HOT
* chain. We also prune any RECENTLY_DEAD tuples preceding a DEAD tuple.
* This is OK because a RECENTLY_DEAD tuple preceding a DEAD tuple is really
* DEAD, our visibility test is just too coarse to detect it.
*
* The root line pointer is redirected to the tuple immediately after the
* latest DEAD tuple. If all tuples in the chain are DEAD, the root line
* pointer is marked LP_DEAD. (This includes the case of a DEAD simple
* tuple, which we treat as a chain of length 1.)
*
* We don't actually change the page here. We just add entries to the arrays in
* prstate showing the changes to be made. Items to be redirected are added
* to the redirected[] array (two entries per redirection); items to be set to
* LP_DEAD state are added to nowdead[]; and items to be set to LP_UNUSED
* state are added to nowunused[].
*
* Returns the number of tuples (to be) deleted from the page.
*/
static int
heap_prune_chain(Buffer buffer, OffsetNumber rootoffnum, PruneState *prstate)
{
int ndeleted = 0;
Page dp = (Page) BufferGetPage(buffer);
TransactionId priorXmax = InvalidTransactionId;
ItemId rootlp;
HeapTupleHeader htup;
OffsetNumber latestdead = InvalidOffsetNumber,
maxoff = PageGetMaxOffsetNumber(dp),
offnum;
OffsetNumber chainitems[MaxHeapTuplesPerPage];
int nchain = 0,
i;
rootlp = PageGetItemId(dp, rootoffnum);
/*
* If it's a heap-only tuple, then it is not the start of a HOT chain.
*/
if (ItemIdIsNormal(rootlp))
{
Assert(prstate->htsv[rootoffnum] != -1);
htup = (HeapTupleHeader) PageGetItem(dp, rootlp);
if (HeapTupleHeaderIsHeapOnly(htup))
{
/*
* If the tuple is DEAD and doesn't chain to anything else, mark
* it unused immediately. (If it does chain, we can only remove
* it as part of pruning its chain.)
*
* We need this primarily to handle aborted HOT updates, that is,
* XMIN_INVALID heap-only tuples. Those might not be linked to by
* any chain, since the parent tuple might be re-updated before
* any pruning occurs. So we have to be able to reap them
* separately from chain-pruning. (Note that
* HeapTupleHeaderIsHotUpdated will never return true for an
* XMIN_INVALID tuple, so this code will work even when there were
* sequential updates within the aborted transaction.)
*
* Note that we might first arrive at a dead heap-only tuple
* either here or while following a chain below. Whichever path
* gets there first will mark the tuple unused.
*/
if (prstate->htsv[rootoffnum] == HEAPTUPLE_DEAD &&
!HeapTupleHeaderIsHotUpdated(htup))
{
heap_prune_record_unused(prstate, rootoffnum);
HeapTupleHeaderAdvanceLatestRemovedXid(htup,
&prstate->latestRemovedXid);
ndeleted++;
}
/* Nothing more to do */
return ndeleted;
}
}
/* Start from the root tuple */
offnum = rootoffnum;
/* while not end of the chain */
for (;;)
{
ItemId lp;
bool tupdead,
recent_dead;
/* Some sanity checks */
if (offnum < FirstOffsetNumber || offnum > maxoff)
break;
/* If item is already processed, stop --- it must not be same chain */
if (prstate->marked[offnum])
break;
lp = PageGetItemId(dp, offnum);
/* Unused item obviously isn't part of the chain */
if (!ItemIdIsUsed(lp))
break;
/*
* If we are looking at the redirected root line pointer, jump to the
* first normal tuple in the chain. If we find a redirect somewhere
* else, stop --- it must not be same chain.
*/
if (ItemIdIsRedirected(lp))
{
if (nchain > 0)
break; /* not at start of chain */
chainitems[nchain++] = offnum;
offnum = ItemIdGetRedirect(rootlp);
continue;
}
/*
* Likewise, a dead line pointer can't be part of the chain. (We
* already eliminated the case of dead root tuple outside this
* function.)
*/
if (ItemIdIsDead(lp))
break;
Assert(ItemIdIsNormal(lp));
Assert(prstate->htsv[offnum] != -1);
htup = (HeapTupleHeader) PageGetItem(dp, lp);
/*
* Check the tuple XMIN against prior XMAX, if any
*/
if (TransactionIdIsValid(priorXmax) &&
!TransactionIdEquals(HeapTupleHeaderGetXmin(htup), priorXmax))
break;
/*
* OK, this tuple is indeed a member of the chain.
*/
chainitems[nchain++] = offnum;
/*
* Check tuple's visibility status.
*/
tupdead = recent_dead = false;
switch ((HTSV_Result) prstate->htsv[offnum])
{
case HEAPTUPLE_DEAD:
tupdead = true;
break;
case HEAPTUPLE_RECENTLY_DEAD:
recent_dead = true;
/*
* This tuple may soon become DEAD. Update the hint field so
* that the page is reconsidered for pruning in future.
*/
heap_prune_record_prunable(prstate,
HeapTupleHeaderGetUpdateXid(htup));
break;
case HEAPTUPLE_DELETE_IN_PROGRESS:
/*
* This tuple may soon become DEAD. Update the hint field so
* that the page is reconsidered for pruning in future.
*/
heap_prune_record_prunable(prstate,
HeapTupleHeaderGetUpdateXid(htup));
break;
case HEAPTUPLE_LIVE:
case HEAPTUPLE_INSERT_IN_PROGRESS:
/*
* If we wanted to optimize for aborts, we might consider
* marking the page prunable when we see INSERT_IN_PROGRESS.
* But we don't. See related decisions about when to mark the
* page prunable in heapam.c.
*/
break;
default:
elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
break;
}
/*
* Remember the last DEAD tuple seen. We will advance past
* RECENTLY_DEAD tuples just in case there's a DEAD one after them;
* but we can't advance past anything else. (XXX is it really worth
* continuing to scan beyond RECENTLY_DEAD? The case where we will
* find another DEAD tuple is a fairly unusual corner case.)
*/
if (tupdead)
{
latestdead = offnum;
HeapTupleHeaderAdvanceLatestRemovedXid(htup,
&prstate->latestRemovedXid);
}
else if (!recent_dead)
break;
/*
* If the tuple is not HOT-updated, then we are at the end of this
* HOT-update chain.
*/
if (!HeapTupleHeaderIsHotUpdated(htup))
break;
/* HOT implies it can't have moved to different partition */
Assert(!HeapTupleHeaderIndicatesMovedPartitions(htup));
/*
* Advance to next chain member.
*/
Assert(ItemPointerGetBlockNumber(&htup->t_ctid) ==
BufferGetBlockNumber(buffer));
offnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetUpdateXid(htup);
}
/*
* If we found a DEAD tuple in the chain, adjust the HOT chain so that all
* the DEAD tuples at the start of the chain are removed and the root line
* pointer is appropriately redirected.
*/
if (OffsetNumberIsValid(latestdead))
{
/*
* Mark as unused each intermediate item that we are able to remove
* from the chain.
*
* When the previous item is the last dead tuple seen, we are at the
* right candidate for redirection.
*/
for (i = 1; (i < nchain) && (chainitems[i - 1] != latestdead); i++)
{
heap_prune_record_unused(prstate, chainitems[i]);
ndeleted++;
}
/*
* If the root entry had been a normal tuple, we are deleting it, so
* count it in the result. But changing a redirect (even to DEAD
* state) doesn't count.
*/
if (ItemIdIsNormal(rootlp))
ndeleted++;
/*
* If the DEAD tuple is at the end of the chain, the entire chain is
* dead and the root line pointer can be marked dead. Otherwise just
* redirect the root to the correct chain member.
*/
if (i >= nchain)
heap_prune_record_dead(prstate, rootoffnum);
else
heap_prune_record_redirect(prstate, rootoffnum, chainitems[i]);
}
else if (nchain < 2 && ItemIdIsRedirected(rootlp))
{
/*
* We found a redirect item that doesn't point to a valid follow-on
* item. This can happen if the loop in heap_page_prune caused us to
* visit the dead successor of a redirect item before visiting the
* redirect item. We can clean up by setting the redirect item to
* DEAD state.
*/
heap_prune_record_dead(prstate, rootoffnum);
}
return ndeleted;
}
/* Record lowest soon-prunable XID */
static void
heap_prune_record_prunable(PruneState *prstate, TransactionId xid)
{
/*
* This should exactly match the PageSetPrunable macro. We can't store
* directly into the page header yet, so we update working state.
*/
Assert(TransactionIdIsNormal(xid));
if (!TransactionIdIsValid(prstate->new_prune_xid) ||
TransactionIdPrecedes(xid, prstate->new_prune_xid))
prstate->new_prune_xid = xid;
}
/* Record line pointer to be redirected */
static void
heap_prune_record_redirect(PruneState *prstate,
OffsetNumber offnum, OffsetNumber rdoffnum)
{
Assert(prstate->nredirected < MaxHeapTuplesPerPage);
prstate->redirected[prstate->nredirected * 2] = offnum;
prstate->redirected[prstate->nredirected * 2 + 1] = rdoffnum;
prstate->nredirected++;
Assert(!prstate->marked[offnum]);
prstate->marked[offnum] = true;
Assert(!prstate->marked[rdoffnum]);
prstate->marked[rdoffnum] = true;
}
/* Record line pointer to be marked dead */
static void
heap_prune_record_dead(PruneState *prstate, OffsetNumber offnum)
{
Assert(prstate->ndead < MaxHeapTuplesPerPage);
prstate->nowdead[prstate->ndead] = offnum;
prstate->ndead++;
Assert(!prstate->marked[offnum]);
prstate->marked[offnum] = true;
}
/* Record line pointer to be marked unused */
static void
heap_prune_record_unused(PruneState *prstate, OffsetNumber offnum)
{
Assert(prstate->nunused < MaxHeapTuplesPerPage);
prstate->nowunused[prstate->nunused] = offnum;
prstate->nunused++;
Assert(!prstate->marked[offnum]);
prstate->marked[offnum] = true;
}
/*
* Perform the actual page changes needed by heap_page_prune.
* It is expected that the caller has a super-exclusive lock on the
* buffer.
*/
void
heap_page_prune_execute(Buffer buffer,
OffsetNumber *redirected, int nredirected,
OffsetNumber *nowdead, int ndead,
OffsetNumber *nowunused, int nunused)
{
Page page = (Page) BufferGetPage(buffer);
OffsetNumber *offnum;
int i;
/* Shouldn't be called unless there's something to do */
Assert(nredirected > 0 || ndead > 0 || nunused > 0);
/* Update all redirected line pointers */
offnum = redirected;
for (i = 0; i < nredirected; i++)
{
OffsetNumber fromoff = *offnum++;
OffsetNumber tooff = *offnum++;
ItemId fromlp = PageGetItemId(page, fromoff);
ItemIdSetRedirect(fromlp, tooff);
}
/* Update all now-dead line pointers */
offnum = nowdead;
for (i = 0; i < ndead; i++)
{
OffsetNumber off = *offnum++;
ItemId lp = PageGetItemId(page, off);
ItemIdSetDead(lp);
}
/* Update all now-unused line pointers */
offnum = nowunused;
for (i = 0; i < nunused; i++)
{
OffsetNumber off = *offnum++;
ItemId lp = PageGetItemId(page, off);
ItemIdSetUnused(lp);
}
/*
* Finally, repair any fragmentation, and update the page's hint bit about
* whether it has free pointers.
*/
PageRepairFragmentation(page);
}
/*
* For all items in this page, find their respective root line pointers.
* If item k is part of a HOT-chain with root at item j, then we set
* root_offsets[k - 1] = j.
*
* The passed-in root_offsets array must have MaxHeapTuplesPerPage entries.
* Unused entries are filled with InvalidOffsetNumber (zero).
*
* The function must be called with at least share lock on the buffer, to
* prevent concurrent prune operations.
*
* Note: The information collected here is valid only as long as the caller
* holds a pin on the buffer. Once pin is released, a tuple might be pruned
* and reused by a completely unrelated tuple.
*/
void
heap_get_root_tuples(Page page, OffsetNumber *root_offsets)
{
OffsetNumber offnum,
maxoff;
MemSet(root_offsets, InvalidOffsetNumber,
MaxHeapTuplesPerPage * sizeof(OffsetNumber));
maxoff = PageGetMaxOffsetNumber(page);
for (offnum = FirstOffsetNumber; offnum <= maxoff; offnum = OffsetNumberNext(offnum))
{
ItemId lp = PageGetItemId(page, offnum);
HeapTupleHeader htup;
OffsetNumber nextoffnum;
TransactionId priorXmax;
/* skip unused and dead items */
if (!ItemIdIsUsed(lp) || ItemIdIsDead(lp))
continue;
if (ItemIdIsNormal(lp))
{
htup = (HeapTupleHeader) PageGetItem(page, lp);
/*
* Check if this tuple is part of a HOT-chain rooted at some other
* tuple. If so, skip it for now; we'll process it when we find
* its root.
*/
if (HeapTupleHeaderIsHeapOnly(htup))
continue;
/*
* This is either a plain tuple or the root of a HOT-chain.
* Remember it in the mapping.
*/
root_offsets[offnum - 1] = offnum;
/* If it's not the start of a HOT-chain, we're done with it */
if (!HeapTupleHeaderIsHotUpdated(htup))
continue;
/* Set up to scan the HOT-chain */
nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetUpdateXid(htup);
}
else
{
/* Must be a redirect item. We do not set its root_offsets entry */
Assert(ItemIdIsRedirected(lp));
/* Set up to scan the HOT-chain */
nextoffnum = ItemIdGetRedirect(lp);
priorXmax = InvalidTransactionId;
}
/*
* Now follow the HOT-chain and collect other tuples in the chain.
*
* Note: Even though this is a nested loop, the complexity of the
* function is O(N) because a tuple in the page should be visited not
* more than twice, once in the outer loop and once in HOT-chain
* chases.
*/
for (;;)
{
/* Sanity check */
if (nextoffnum < FirstOffsetNumber || nextoffnum > maxoff)
break;
lp = PageGetItemId(page, nextoffnum);
/* Check for broken chains */
if (!ItemIdIsNormal(lp))
break;
htup = (HeapTupleHeader) PageGetItem(page, lp);
if (TransactionIdIsValid(priorXmax) &&
!TransactionIdEquals(priorXmax, HeapTupleHeaderGetXmin(htup)))
break;
/* Remember the root line pointer for this item */
root_offsets[nextoffnum - 1] = offnum;
/* Advance to next chain member, if any */
if (!HeapTupleHeaderIsHotUpdated(htup))
break;
/* HOT implies it can't have moved to different partition */
Assert(!HeapTupleHeaderIndicatesMovedPartitions(htup));
nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
priorXmax = HeapTupleHeaderGetUpdateXid(htup);
}
}
}
|