aboutsummaryrefslogtreecommitdiff
path: root/src/backend/access/spgist/spgvacuum.c
blob: 90d59920eb6269ec7a5d2171356c41d7f074559f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
/*-------------------------------------------------------------------------
 *
 * spgvacuum.c
 *	  vacuum for SP-GiST
 *
 *
 * Portions Copyright (c) 1996-2011, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * IDENTIFICATION
 *			src/backend/access/spgist/spgvacuum.c
 *
 *-------------------------------------------------------------------------
 */

#include "postgres.h"

#include "access/genam.h"
#include "access/spgist_private.h"
#include "access/transam.h"
#include "catalog/storage.h"
#include "commands/vacuum.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "storage/indexfsm.h"
#include "storage/lmgr.h"
#include "storage/procarray.h"


/* local state for vacuum operations */
typedef struct spgBulkDeleteState
{
	/* Parameters passed in to spgvacuumscan */
	IndexVacuumInfo *info;
	IndexBulkDeleteResult *stats;
	IndexBulkDeleteCallback callback;
	void	   *callback_state;
	/* Additional working state */
	SpGistState spgstate;
	TransactionId OldestXmin;
	BlockNumber lastFilledBlock;
} spgBulkDeleteState;


/*
 * Vacuum a regular (non-root) leaf page
 *
 * We must delete tuples that are targeted for deletion by the VACUUM,
 * but not move any tuples that are referenced by outside links; we assume
 * those are the ones that are heads of chains.
 */
static void
vacuumLeafPage(spgBulkDeleteState *bds, Relation index, Buffer buffer)
{
	Page		page = BufferGetPage(buffer);
	spgxlogVacuumLeaf xlrec;
	XLogRecData rdata[8];
	OffsetNumber toDead[MaxIndexTuplesPerPage];
	OffsetNumber toPlaceholder[MaxIndexTuplesPerPage];
	OffsetNumber moveSrc[MaxIndexTuplesPerPage];
	OffsetNumber moveDest[MaxIndexTuplesPerPage];
	OffsetNumber chainSrc[MaxIndexTuplesPerPage];
	OffsetNumber chainDest[MaxIndexTuplesPerPage];
	OffsetNumber predecessor[MaxIndexTuplesPerPage + 1];
	bool		deletable[MaxIndexTuplesPerPage + 1];
	int			nDeletable;
	OffsetNumber i,
				max = PageGetMaxOffsetNumber(page);

	memset(predecessor, 0, sizeof(predecessor));
	memset(deletable, 0, sizeof(deletable));
	nDeletable = 0;

	/* Scan page, identify tuples to delete, accumulate stats */
	for (i = FirstOffsetNumber; i <= max; i++)
	{
		SpGistLeafTuple lt;

		lt = (SpGistLeafTuple) PageGetItem(page,
										   PageGetItemId(page, i));
		if (lt->tupstate == SPGIST_LIVE)
		{
			Assert(ItemPointerIsValid(&lt->heapPtr));

			if (bds->callback(&lt->heapPtr, bds->callback_state))
			{
				bds->stats->tuples_removed += 1;
				deletable[i] = true;
				nDeletable++;
			}
			else
			{
				bds->stats->num_index_tuples += 1;
			}

			/* Form predecessor map, too */
			if (lt->nextOffset != InvalidOffsetNumber)
			{
				/* paranoia about corrupted chain links */
				if (lt->nextOffset < FirstOffsetNumber ||
					lt->nextOffset > max ||
					predecessor[lt->nextOffset] != InvalidOffsetNumber)
					elog(ERROR, "inconsistent tuple chain links in page %u of index \"%s\"",
						 BufferGetBlockNumber(buffer),
						 RelationGetRelationName(index));
				predecessor[lt->nextOffset] = i;
			}
		}
		else
		{
			Assert(lt->nextOffset == InvalidOffsetNumber);
		}
	}

	if (nDeletable == 0)
		return;					/* nothing more to do */

	/*----------
	 * Figure out exactly what we have to do.  We do this separately from
	 * actually modifying the page, mainly so that we have a representation
	 * that can be dumped into WAL and then the replay code can do exactly
	 * the same thing.  The output of this step consists of six arrays
	 * describing four kinds of operations, to be performed in this order:
	 *
	 * toDead[]: tuple numbers to be replaced with DEAD tuples
	 * toPlaceholder[]: tuple numbers to be replaced with PLACEHOLDER tuples
	 * moveSrc[]: tuple numbers that need to be relocated to another offset
	 * (replacing the tuple there) and then replaced with PLACEHOLDER tuples
	 * moveDest[]: new locations for moveSrc tuples
	 * chainSrc[]: tuple numbers whose chain links (nextOffset) need updates
	 * chainDest[]: new values of nextOffset for chainSrc members
	 *
	 * It's easiest to figure out what we have to do by processing tuple
	 * chains, so we iterate over all the tuples (not just the deletable
	 * ones!) to identify chain heads, then chase down each chain and make
	 * work item entries for deletable tuples within the chain.
	 *----------
	 */
	xlrec.nDead = xlrec.nPlaceholder = xlrec.nMove = xlrec.nChain = 0;

	for (i = FirstOffsetNumber; i <= max; i++)
	{
		SpGistLeafTuple head;
		bool		interveningDeletable;
		OffsetNumber prevLive;
		OffsetNumber j;

		head = (SpGistLeafTuple) PageGetItem(page,
											 PageGetItemId(page, i));
		if (head->tupstate != SPGIST_LIVE)
			continue;			/* can't be a chain member */
		if (predecessor[i] != 0)
			continue;			/* not a chain head */

		/* initialize ... */
		interveningDeletable = false;
		prevLive = deletable[i] ? InvalidOffsetNumber : i;

		/* scan down the chain ... */
		j = head->nextOffset;
		while (j != InvalidOffsetNumber)
		{
			SpGistLeafTuple lt;

			lt = (SpGistLeafTuple) PageGetItem(page,
											   PageGetItemId(page, j));
			if (lt->tupstate != SPGIST_LIVE)
			{
				/* all tuples in chain should be live */
				elog(ERROR, "unexpected SPGiST tuple state: %d",
					 lt->tupstate);
			}

			if (deletable[j])
			{
				/* This tuple should be replaced by a placeholder */
				toPlaceholder[xlrec.nPlaceholder] = j;
				xlrec.nPlaceholder++;
				/* previous live tuple's chain link will need an update */
				interveningDeletable = true;
			}
			else if (prevLive == InvalidOffsetNumber)
			{
				/*
				 * This is the first live tuple in the chain.  It has
				 * to move to the head position.
				 */
				moveSrc[xlrec.nMove] = j;
				moveDest[xlrec.nMove] = i;
				xlrec.nMove++;
				/* Chain updates will be applied after the move */
				prevLive = i;
				interveningDeletable = false;
			}
			else
			{
				/*
				 * Second or later live tuple.  Arrange to re-chain it to the
				 * previous live one, if there was a gap.
				 */
				if (interveningDeletable)
				{
					chainSrc[xlrec.nChain] = prevLive;
					chainDest[xlrec.nChain] = j;
					xlrec.nChain++;
				}
				prevLive = j;
				interveningDeletable = false;
			}

			j = lt->nextOffset;
		}

		if (prevLive == InvalidOffsetNumber)
		{
			/* The chain is entirely removable, so we need a DEAD tuple */
			toDead[xlrec.nDead] = i;
			xlrec.nDead++;
		}
		else if (interveningDeletable)
		{
			/* One or more deletions at end of chain, so close it off */
			chainSrc[xlrec.nChain] = prevLive;
			chainDest[xlrec.nChain] = InvalidOffsetNumber;
			xlrec.nChain++;
		}
	}

	/* sanity check ... */
	if (nDeletable != xlrec.nDead + xlrec.nPlaceholder + xlrec.nMove)
		elog(ERROR, "inconsistent counts of deletable tuples");

	/* Prepare WAL record */
	xlrec.node = index->rd_node;
	xlrec.blkno = BufferGetBlockNumber(buffer);
	STORE_STATE(&bds->spgstate, xlrec.stateSrc);

	ACCEPT_RDATA_DATA(&xlrec, sizeof(xlrec), 0);
	/* sizeof(xlrec) should be a multiple of sizeof(OffsetNumber) */
	ACCEPT_RDATA_DATA(toDead, sizeof(OffsetNumber) * xlrec.nDead, 1);
	ACCEPT_RDATA_DATA(toPlaceholder, sizeof(OffsetNumber) * xlrec.nPlaceholder, 2);
	ACCEPT_RDATA_DATA(moveSrc, sizeof(OffsetNumber) * xlrec.nMove, 3);
	ACCEPT_RDATA_DATA(moveDest, sizeof(OffsetNumber) * xlrec.nMove, 4);
	ACCEPT_RDATA_DATA(chainSrc, sizeof(OffsetNumber) * xlrec.nChain, 5);
	ACCEPT_RDATA_DATA(chainDest, sizeof(OffsetNumber) * xlrec.nChain, 6);
	ACCEPT_RDATA_BUFFER(buffer, 7);

	/* Do the updates */
	START_CRIT_SECTION();

	spgPageIndexMultiDelete(&bds->spgstate, page,
							toDead, xlrec.nDead,
							SPGIST_DEAD, SPGIST_DEAD,
							InvalidBlockNumber, InvalidOffsetNumber);

	spgPageIndexMultiDelete(&bds->spgstate, page,
							toPlaceholder, xlrec.nPlaceholder,
							SPGIST_PLACEHOLDER, SPGIST_PLACEHOLDER,
							InvalidBlockNumber, InvalidOffsetNumber);

	/*
	 * We implement the move step by swapping the item pointers of the
	 * source and target tuples, then replacing the newly-source tuples
	 * with placeholders.  This is perhaps unduly friendly with the page
	 * data representation, but it's fast and doesn't risk page overflow
	 * when a tuple to be relocated is large.
	 */
	for (i = 0; i < xlrec.nMove; i++)
	{
		ItemId		idSrc = PageGetItemId(page, moveSrc[i]);
		ItemId		idDest = PageGetItemId(page, moveDest[i]);
		ItemIdData	tmp;

		tmp = *idSrc;
		*idSrc = *idDest;
		*idDest = tmp;
	}

	spgPageIndexMultiDelete(&bds->spgstate, page,
							moveSrc, xlrec.nMove,
							SPGIST_PLACEHOLDER, SPGIST_PLACEHOLDER,
							InvalidBlockNumber, InvalidOffsetNumber);

	for (i = 0; i < xlrec.nChain; i++)
	{
		SpGistLeafTuple lt;

		lt = (SpGistLeafTuple) PageGetItem(page,
										   PageGetItemId(page, chainSrc[i]));
		Assert(lt->tupstate == SPGIST_LIVE);
		lt->nextOffset = chainDest[i];
	}

	MarkBufferDirty(buffer);

	if (RelationNeedsWAL(index))
	{
		XLogRecPtr	recptr;

		recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_VACUUM_LEAF, rdata);

		PageSetLSN(page, recptr);
		PageSetTLI(page, ThisTimeLineID);
	}

	END_CRIT_SECTION();
}

/*
 * Vacuum the root page when it is a leaf
 *
 * On the root, we just delete any dead leaf tuples; no fancy business
 */
static void
vacuumLeafRoot(spgBulkDeleteState *bds, Relation index, Buffer buffer)
{
	Page		page = BufferGetPage(buffer);
	spgxlogVacuumRoot xlrec;
	XLogRecData rdata[3];
	OffsetNumber toDelete[MaxIndexTuplesPerPage];
	OffsetNumber i,
				max = PageGetMaxOffsetNumber(page);

	xlrec.nDelete = 0;

	/* Scan page, identify tuples to delete, accumulate stats */
	for (i = FirstOffsetNumber; i <= max; i++)
	{
		SpGistLeafTuple lt;

		lt = (SpGistLeafTuple) PageGetItem(page,
										   PageGetItemId(page, i));
		if (lt->tupstate == SPGIST_LIVE)
		{
			Assert(ItemPointerIsValid(&lt->heapPtr));

			if (bds->callback(&lt->heapPtr, bds->callback_state))
			{
				bds->stats->tuples_removed += 1;
				toDelete[xlrec.nDelete] = i;
				xlrec.nDelete++;
			}
			else
			{
				bds->stats->num_index_tuples += 1;
			}
		}
		else
		{
			/* all tuples on root should be live */
			elog(ERROR, "unexpected SPGiST tuple state: %d",
				 lt->tupstate);
		}
	}

	if (xlrec.nDelete == 0)
		return;					/* nothing more to do */

	/* Prepare WAL record */
	xlrec.node = index->rd_node;
	STORE_STATE(&bds->spgstate, xlrec.stateSrc);

	ACCEPT_RDATA_DATA(&xlrec, sizeof(xlrec), 0);
	/* sizeof(xlrec) should be a multiple of sizeof(OffsetNumber) */
	ACCEPT_RDATA_DATA(toDelete, sizeof(OffsetNumber) * xlrec.nDelete, 1);
	ACCEPT_RDATA_BUFFER(buffer, 2);

	/* Do the update */
	START_CRIT_SECTION();

	/* The tuple numbers are in order, so we can use PageIndexMultiDelete */
	PageIndexMultiDelete(page, toDelete, xlrec.nDelete);

	MarkBufferDirty(buffer);

	if (RelationNeedsWAL(index))
	{
		XLogRecPtr	recptr;

		recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_VACUUM_ROOT, rdata);

		PageSetLSN(page, recptr);
		PageSetTLI(page, ThisTimeLineID);
	}

	END_CRIT_SECTION();
}

/*
 * Clean up redirect and placeholder tuples on the given page
 *
 * Redirect tuples can be marked placeholder once they're old enough.
 * Placeholder tuples can be removed if it won't change the offsets of
 * non-placeholder ones.
 *
 * Unlike the routines above, this works on both leaf and inner pages.
 */
static void
vacuumRedirectAndPlaceholder(Relation index, Buffer buffer,
							 TransactionId OldestXmin)
{
	Page		page = BufferGetPage(buffer);
	SpGistPageOpaque opaque = SpGistPageGetOpaque(page);
	OffsetNumber i,
				max = PageGetMaxOffsetNumber(page),
				firstPlaceholder = InvalidOffsetNumber;
	bool		hasNonPlaceholder = false;
	bool		hasUpdate = false;
	OffsetNumber itemToPlaceholder[MaxIndexTuplesPerPage];
	OffsetNumber itemnos[MaxIndexTuplesPerPage];
	spgxlogVacuumRedirect xlrec;
	XLogRecData rdata[3];

	xlrec.node = index->rd_node;
	xlrec.blkno = BufferGetBlockNumber(buffer);
	xlrec.nToPlaceholder = 0;

	START_CRIT_SECTION();

	/*
	 * Scan backwards to convert old redirection tuples to placeholder tuples,
	 * and identify location of last non-placeholder tuple while at it.
	 */
	for (i = max;
		 i >= FirstOffsetNumber &&
			 (opaque->nRedirection > 0 || !hasNonPlaceholder);
		 i--)
	{
		SpGistDeadTuple dt;

		dt = (SpGistDeadTuple) PageGetItem(page, PageGetItemId(page, i));

		if (dt->tupstate == SPGIST_REDIRECT &&
			TransactionIdPrecedes(dt->xid, OldestXmin))
		{
			dt->tupstate = SPGIST_PLACEHOLDER;
			Assert(opaque->nRedirection > 0);
			opaque->nRedirection--;
			opaque->nPlaceholder++;

			ItemPointerSetInvalid(&dt->pointer);

			itemToPlaceholder[xlrec.nToPlaceholder] = i;
			xlrec.nToPlaceholder++;

			hasUpdate = true;
		}

		if (dt->tupstate == SPGIST_PLACEHOLDER)
		{
			if (!hasNonPlaceholder)
				firstPlaceholder = i;
		}
		else
		{
			hasNonPlaceholder = true;
		}
	}

	/*
	 * Any placeholder tuples at the end of page can safely be removed.  We
	 * can't remove ones before the last non-placeholder, though, because we
	 * can't alter the offset numbers of non-placeholder tuples.
	 */
	if (firstPlaceholder != InvalidOffsetNumber)
	{
		/*
		 * We do not store this array to rdata because it's easy to recreate.
		 */
		for (i = firstPlaceholder; i <= max; i++)
			itemnos[i - firstPlaceholder] = i;

		i = max - firstPlaceholder + 1;
		Assert(opaque->nPlaceholder >= i);
		opaque->nPlaceholder -= i;

		/* The array is surely sorted, so can use PageIndexMultiDelete */
		PageIndexMultiDelete(page, itemnos, i);

		hasUpdate = true;
	}

	xlrec.firstPlaceholder = firstPlaceholder;

	if (hasUpdate)
		MarkBufferDirty(buffer);

	if (hasUpdate && RelationNeedsWAL(index))
	{
		XLogRecPtr	recptr;

		ACCEPT_RDATA_DATA(&xlrec, sizeof(xlrec), 0);
		ACCEPT_RDATA_DATA(itemToPlaceholder, sizeof(OffsetNumber) * xlrec.nToPlaceholder, 1);
		ACCEPT_RDATA_BUFFER(buffer, 2);

		recptr = XLogInsert(RM_SPGIST_ID, XLOG_SPGIST_VACUUM_REDIRECT, rdata);

		PageSetLSN(page, recptr);
		PageSetTLI(page, ThisTimeLineID);
	}

	END_CRIT_SECTION();
}

/*
 * Process one page during a bulkdelete scan
 */
static void
spgvacuumpage(spgBulkDeleteState *bds, BlockNumber blkno)
{
	Relation	index = bds->info->index;
	Buffer		buffer;
	Page		page;

	/* call vacuum_delay_point while not holding any buffer lock */
	vacuum_delay_point();

	buffer = ReadBufferExtended(index, MAIN_FORKNUM, blkno,
								RBM_NORMAL, bds->info->strategy);
	LockBuffer(buffer, BUFFER_LOCK_EXCLUSIVE);
	page = (Page) BufferGetPage(buffer);

	if (PageIsNew(page))
	{
		/*
		 * We found an all-zero page, which could happen if the database
		 * crashed just after extending the file.  Initialize and recycle it.
		 */
		SpGistInitBuffer(buffer, 0);
		SpGistPageSetDeleted(page);
		/* We don't bother to WAL-log this action; easy to redo */
		MarkBufferDirty(buffer);
	}
	else if (SpGistPageIsDeleted(page))
	{
		/* nothing to do */
	}
	else if (SpGistPageIsLeaf(page))
	{
		if (blkno == SPGIST_HEAD_BLKNO)
		{
			vacuumLeafRoot(bds, index, buffer);
			/* no need for vacuumRedirectAndPlaceholder */
		}
		else
		{
			vacuumLeafPage(bds, index, buffer);
			vacuumRedirectAndPlaceholder(index, buffer, bds->OldestXmin);
		}
	}
	else
	{
		/* inner page */
		vacuumRedirectAndPlaceholder(index, buffer, bds->OldestXmin);
	}

	/*
	 * The root page must never be deleted, nor marked as available in FSM,
	 * because we don't want it ever returned by a search for a place to
	 * put a new tuple.  Otherwise, check for empty/deletable page, and
	 * make sure FSM knows about it.
	 */
	if (blkno != SPGIST_HEAD_BLKNO)
	{
		/* If page is now empty, mark it deleted */
		if (PageIsEmpty(page) && !SpGistPageIsDeleted(page))
		{
			SpGistPageSetDeleted(page);
			/* We don't bother to WAL-log this action; easy to redo */
			MarkBufferDirty(buffer);
		}

		if (SpGistPageIsDeleted(page))
		{
			RecordFreeIndexPage(index, blkno);
			bds->stats->pages_deleted++;
		}
		else
			bds->lastFilledBlock = blkno;
	}

	SpGistSetLastUsedPage(index, buffer);

	UnlockReleaseBuffer(buffer);
}

/*
 * Perform a bulkdelete scan
 */
static void
spgvacuumscan(spgBulkDeleteState *bds)
{
	Relation	index = bds->info->index;
	bool		needLock;
	BlockNumber num_pages,
				blkno;

	/* Finish setting up spgBulkDeleteState */
	initSpGistState(&bds->spgstate, index);
	bds->OldestXmin = GetOldestXmin(true, false);
	bds->lastFilledBlock = SPGIST_HEAD_BLKNO;

	/*
	 * Reset counts that will be incremented during the scan; needed in case
	 * of multiple scans during a single VACUUM command
	 */
	bds->stats->estimated_count = false;
	bds->stats->num_index_tuples = 0;
	bds->stats->pages_deleted = 0;

	/* We can skip locking for new or temp relations */
	needLock = !RELATION_IS_LOCAL(index);

	/*
	 * The outer loop iterates over all index pages except the metapage, in
	 * physical order (we hope the kernel will cooperate in providing
	 * read-ahead for speed).  It is critical that we visit all leaf pages,
	 * including ones added after we start the scan, else we might fail to
	 * delete some deletable tuples.  See more extensive comments about
	 * this in btvacuumscan().
	 */
	blkno = SPGIST_HEAD_BLKNO;
	for (;;)
	{
		/* Get the current relation length */
		if (needLock)
			LockRelationForExtension(index, ExclusiveLock);
		num_pages = RelationGetNumberOfBlocks(index);
		if (needLock)
			UnlockRelationForExtension(index, ExclusiveLock);

		/* Quit if we've scanned the whole relation */
		if (blkno >= num_pages)
			break;
		/* Iterate over pages, then loop back to recheck length */
		for (; blkno < num_pages; blkno++)
		{
			spgvacuumpage(bds, blkno);
		}
	}

	/* Propagate local lastUsedPage cache to metablock */
	SpGistUpdateMetaPage(index);

	/*
	 * Truncate index if possible
	 *
	 * XXX disabled because it's unsafe due to possible concurrent inserts.
	 * We'd have to rescan the pages to make sure they're still empty, and it
	 * doesn't seem worth it.  Note that btree doesn't do this either.
	 */
#ifdef NOT_USED
	if (num_pages > bds->lastFilledBlock + 1)
	{
		BlockNumber lastBlock = num_pages - 1;

		num_pages = bds->lastFilledBlock + 1;
		RelationTruncate(index, num_pages);
		bds->stats->pages_removed += lastBlock - bds->lastFilledBlock;
		bds->stats->pages_deleted -= lastBlock - bds->lastFilledBlock;
	}
#endif

	/* Report final stats */
	bds->stats->num_pages = num_pages;
	bds->stats->pages_free = bds->stats->pages_deleted;
}

/*
 * Bulk deletion of all index entries pointing to a set of heap tuples.
 * The set of target tuples is specified via a callback routine that tells
 * whether any given heap tuple (identified by ItemPointer) is being deleted.
 *
 * Result: a palloc'd struct containing statistical info for VACUUM displays.
 */
Datum
spgbulkdelete(PG_FUNCTION_ARGS)
{
	IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
	IndexBulkDeleteResult *stats = (IndexBulkDeleteResult *) PG_GETARG_POINTER(1);
	IndexBulkDeleteCallback callback = (IndexBulkDeleteCallback) PG_GETARG_POINTER(2);
	void	   *callback_state = (void *) PG_GETARG_POINTER(3);
	spgBulkDeleteState bds;

	/* allocate stats if first time through, else re-use existing struct */
	if (stats == NULL)
		stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
	bds.info = info;
	bds.stats = stats;
	bds.callback = callback;
	bds.callback_state = callback_state;

	spgvacuumscan(&bds);

	PG_RETURN_POINTER(stats);
}

/* Dummy callback to delete no tuples during spgvacuumcleanup */
static bool
dummy_callback(ItemPointer itemptr, void *state)
{
	return false;
}

/*
 * Post-VACUUM cleanup.
 *
 * Result: a palloc'd struct containing statistical info for VACUUM displays.
 */
Datum
spgvacuumcleanup(PG_FUNCTION_ARGS)
{
	IndexVacuumInfo *info = (IndexVacuumInfo *) PG_GETARG_POINTER(0);
	IndexBulkDeleteResult *stats = (IndexBulkDeleteResult *) PG_GETARG_POINTER(1);
	Relation	index = info->index;
	spgBulkDeleteState bds;

	/* No-op in ANALYZE ONLY mode */
	if (info->analyze_only)
		PG_RETURN_POINTER(stats);

	/*
	 * We don't need to scan the index if there was a preceding bulkdelete
	 * pass.  Otherwise, make a pass that won't delete any live tuples, but
	 * might still accomplish useful stuff with redirect/placeholder cleanup,
	 * and in any case will provide stats.
	 */
	if (stats == NULL)
	{
		stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
		bds.info = info;
		bds.stats = stats;
		bds.callback = dummy_callback;
		bds.callback_state = NULL;

		spgvacuumscan(&bds);
	}

	/* Finally, vacuum the FSM */
	IndexFreeSpaceMapVacuum(index);

	/*
	 * It's quite possible for us to be fooled by concurrent page splits into
	 * double-counting some index tuples, so disbelieve any total that exceeds
	 * the underlying heap's count ... if we know that accurately.  Otherwise
	 * this might just make matters worse.
	 */
	if (!info->estimated_count)
	{
		if (stats->num_index_tuples > info->num_heap_tuples)
			stats->num_index_tuples = info->num_heap_tuples;
	}

	PG_RETURN_POINTER(stats);
}