summaryrefslogtreecommitdiffstats
path: root/contrib/pgstattuple/pgstatindex.c
blob: 0bd1a01c72b21b41eccb569fc16095e3c0c825ee (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
/*
 * contrib/pgstattuple/pgstatindex.c
 *
 *
 * pgstatindex
 *
 * Copyright (c) 2006 Satoshi Nagayasu <nagayasus@nttdata.co.jp>
 *
 * Permission to use, copy, modify, and distribute this software and
 * its documentation for any purpose, without fee, and without a
 * written agreement is hereby granted, provided that the above
 * copyright notice and this paragraph and the following two
 * paragraphs appear in all copies.
 *
 * IN NO EVENT SHALL THE AUTHOR BE LIABLE TO ANY PARTY FOR DIRECT,
 * INDIRECT, SPECIAL, INCIDENTAL, OR CONSEQUENTIAL DAMAGES, INCLUDING
 * LOST PROFITS, ARISING OUT OF THE USE OF THIS SOFTWARE AND ITS
 * DOCUMENTATION, EVEN IF THE UNIVERSITY OF CALIFORNIA HAS BEEN ADVISED
 * OF THE POSSIBILITY OF SUCH DAMAGE.
 *
 * THE AUTHOR SPECIFICALLY DISCLAIMS ANY WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 * A PARTICULAR PURPOSE.  THE SOFTWARE PROVIDED HEREUNDER IS ON AN "AS
 * IS" BASIS, AND THE AUTHOR HAS NO OBLIGATIONS TO PROVIDE MAINTENANCE,
 * SUPPORT, UPDATES, ENHANCEMENTS, OR MODIFICATIONS.
 */

#include "postgres.h"

#include "access/gin_private.h"
#include "access/hash.h"
#include "access/htup_details.h"
#include "access/nbtree.h"
#include "access/relation.h"
#include "access/table.h"
#include "catalog/namespace.h"
#include "catalog/pg_am.h"
#include "funcapi.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "storage/lmgr.h"
#include "utils/builtins.h"
#include "utils/rel.h"
#include "utils/varlena.h"


/*
 * Because of backward-compatibility issue, we have decided to have
 * two types of interfaces, with regclass-type input arg and text-type
 * input arg, for each function.
 *
 * Those functions which have text-type input arg will be deprecated
 * in the future release.
 */
PG_FUNCTION_INFO_V1(pgstatindex);
PG_FUNCTION_INFO_V1(pgstatindexbyid);
PG_FUNCTION_INFO_V1(pg_relpages);
PG_FUNCTION_INFO_V1(pg_relpagesbyid);
PG_FUNCTION_INFO_V1(pgstatginindex);
PG_FUNCTION_INFO_V1(pgstathashindex);

PG_FUNCTION_INFO_V1(pgstatindex_v1_5);
PG_FUNCTION_INFO_V1(pgstatindexbyid_v1_5);
PG_FUNCTION_INFO_V1(pg_relpages_v1_5);
PG_FUNCTION_INFO_V1(pg_relpagesbyid_v1_5);
PG_FUNCTION_INFO_V1(pgstatginindex_v1_5);

Datum		pgstatginindex_internal(Oid relid, FunctionCallInfo fcinfo);

#define IS_INDEX(r) ((r)->rd_rel->relkind == RELKIND_INDEX)
#define IS_BTREE(r) ((r)->rd_rel->relam == BTREE_AM_OID)
#define IS_GIN(r) ((r)->rd_rel->relam == GIN_AM_OID)
#define IS_HASH(r) ((r)->rd_rel->relam == HASH_AM_OID)

/* ------------------------------------------------
 * A structure for a whole btree index statistics
 * used by pgstatindex().
 * ------------------------------------------------
 */
typedef struct BTIndexStat
{
	uint32		version;
	uint32		level;
	BlockNumber root_blkno;

	uint64		internal_pages;
	uint64		leaf_pages;
	uint64		empty_pages;
	uint64		deleted_pages;

	uint64		max_avail;
	uint64		free_space;

	uint64		fragments;
} BTIndexStat;

/* ------------------------------------------------
 * A structure for a whole GIN index statistics
 * used by pgstatginindex().
 * ------------------------------------------------
 */
typedef struct GinIndexStat
{
	int32		version;

	BlockNumber pending_pages;
	int64		pending_tuples;
} GinIndexStat;

/* ------------------------------------------------
 * A structure for a whole HASH index statistics
 * used by pgstathashindex().
 * ------------------------------------------------
 */
typedef struct HashIndexStat
{
	int32		version;
	int32		space_per_page;

	BlockNumber bucket_pages;
	BlockNumber overflow_pages;
	BlockNumber bitmap_pages;
	BlockNumber unused_pages;

	int64		live_items;
	int64		dead_items;
	uint64		free_space;
} HashIndexStat;

static Datum pgstatindex_impl(Relation rel, FunctionCallInfo fcinfo);
static int64 pg_relpages_impl(Relation rel);
static void GetHashPageStats(Page page, HashIndexStat *stats);

/* ------------------------------------------------------
 * pgstatindex()
 *
 * Usage: SELECT * FROM pgstatindex('t1_pkey');
 *
 * The superuser() check here must be kept as the library might be upgraded
 * without the extension being upgraded, meaning that in pre-1.5 installations
 * these functions could be called by any user.
 * ------------------------------------------------------
 */
Datum
pgstatindex(PG_FUNCTION_ARGS)
{
	text	   *relname = PG_GETARG_TEXT_PP(0);
	Relation	rel;
	RangeVar   *relrv;

	if (!superuser())
		ereport(ERROR,
				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
				 errmsg("must be superuser to use pgstattuple functions")));

	relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
	rel = relation_openrv(relrv, AccessShareLock);

	PG_RETURN_DATUM(pgstatindex_impl(rel, fcinfo));
}

/*
 * As of pgstattuple version 1.5, we no longer need to check if the user
 * is a superuser because we REVOKE EXECUTE on the function from PUBLIC.
 * Users can then grant access to it based on their policies.
 *
 * Otherwise identical to pgstatindex (above).
 */
Datum
pgstatindex_v1_5(PG_FUNCTION_ARGS)
{
	text	   *relname = PG_GETARG_TEXT_PP(0);
	Relation	rel;
	RangeVar   *relrv;

	relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
	rel = relation_openrv(relrv, AccessShareLock);

	PG_RETURN_DATUM(pgstatindex_impl(rel, fcinfo));
}

/*
 * The superuser() check here must be kept as the library might be upgraded
 * without the extension being upgraded, meaning that in pre-1.5 installations
 * these functions could be called by any user.
 */
Datum
pgstatindexbyid(PG_FUNCTION_ARGS)
{
	Oid			relid = PG_GETARG_OID(0);
	Relation	rel;

	if (!superuser())
		ereport(ERROR,
				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
				 errmsg("must be superuser to use pgstattuple functions")));

	rel = relation_open(relid, AccessShareLock);

	PG_RETURN_DATUM(pgstatindex_impl(rel, fcinfo));
}

/* No need for superuser checks in v1.5, see above */
Datum
pgstatindexbyid_v1_5(PG_FUNCTION_ARGS)
{
	Oid			relid = PG_GETARG_OID(0);
	Relation	rel;

	rel = relation_open(relid, AccessShareLock);

	PG_RETURN_DATUM(pgstatindex_impl(rel, fcinfo));
}

static Datum
pgstatindex_impl(Relation rel, FunctionCallInfo fcinfo)
{
	Datum		result;
	BlockNumber nblocks;
	BlockNumber blkno;
	BTIndexStat indexStat;
	BufferAccessStrategy bstrategy = GetAccessStrategy(BAS_BULKREAD);

	if (!IS_INDEX(rel) || !IS_BTREE(rel))
		ereport(ERROR,
				(errcode(ERRCODE_WRONG_OBJECT_TYPE),
				 errmsg("relation \"%s\" is not a btree index",
						RelationGetRelationName(rel))));

	/*
	 * Reject attempts to read non-local temporary relations; we would be
	 * likely to get wrong data since we have no visibility into the owning
	 * session's local buffers.
	 */
	if (RELATION_IS_OTHER_TEMP(rel))
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 errmsg("cannot access temporary tables of other sessions")));

	/*
	 * A !indisready index could lead to ERRCODE_DATA_CORRUPTED later, so exit
	 * early.  We're capable of assessing an indisready&&!indisvalid index,
	 * but the results could be confusing.  For example, the index's size
	 * could be too low for a valid index of the table.
	 */
	if (!rel->rd_index->indisvalid)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("index \"%s\" is not valid",
						RelationGetRelationName(rel))));

	/*
	 * Read metapage
	 */
	{
		Buffer		buffer = ReadBufferExtended(rel, MAIN_FORKNUM, 0, RBM_NORMAL, bstrategy);
		Page		page = BufferGetPage(buffer);
		BTMetaPageData *metad = BTPageGetMeta(page);

		indexStat.version = metad->btm_version;
		indexStat.level = metad->btm_level;
		indexStat.root_blkno = metad->btm_root;

		ReleaseBuffer(buffer);
	}

	/* -- init counters -- */
	indexStat.internal_pages = 0;
	indexStat.leaf_pages = 0;
	indexStat.empty_pages = 0;
	indexStat.deleted_pages = 0;

	indexStat.max_avail = 0;
	indexStat.free_space = 0;

	indexStat.fragments = 0;

	/*
	 * Scan all blocks except the metapage
	 */
	nblocks = RelationGetNumberOfBlocks(rel);

	for (blkno = 1; blkno < nblocks; blkno++)
	{
		Buffer		buffer;
		Page		page;
		BTPageOpaque opaque;

		CHECK_FOR_INTERRUPTS();

		/* Read and lock buffer */
		buffer = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL, bstrategy);
		LockBuffer(buffer, BUFFER_LOCK_SHARE);

		page = BufferGetPage(buffer);
		opaque = BTPageGetOpaque(page);

		/*
		 * Determine page type, and update totals.
		 *
		 * Note that we arbitrarily bucket deleted pages together without
		 * considering if they're leaf pages or internal pages.
		 */
		if (P_ISDELETED(opaque))
			indexStat.deleted_pages++;
		else if (P_IGNORE(opaque))
			indexStat.empty_pages++;	/* this is the "half dead" state */
		else if (P_ISLEAF(opaque))
		{
			int			max_avail;

			max_avail = BLCKSZ - (BLCKSZ - ((PageHeader) page)->pd_special + SizeOfPageHeaderData);
			indexStat.max_avail += max_avail;
			indexStat.free_space += PageGetFreeSpace(page);

			indexStat.leaf_pages++;

			/*
			 * If the next leaf is on an earlier block, it means a
			 * fragmentation.
			 */
			if (opaque->btpo_next != P_NONE && opaque->btpo_next < blkno)
				indexStat.fragments++;
		}
		else
			indexStat.internal_pages++;

		/* Unlock and release buffer */
		LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
		ReleaseBuffer(buffer);
	}

	relation_close(rel, AccessShareLock);

	/*----------------------------
	 * Build a result tuple
	 *----------------------------
	 */
	{
		TupleDesc	tupleDesc;
		int			j;
		char	   *values[10];
		HeapTuple	tuple;

		/* Build a tuple descriptor for our result type */
		if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
			elog(ERROR, "return type must be a row type");

		j = 0;
		values[j++] = psprintf("%d", indexStat.version);
		values[j++] = psprintf("%d", indexStat.level);
		values[j++] = psprintf(INT64_FORMAT,
							   (1 + /* include the metapage in index_size */
								indexStat.leaf_pages +
								indexStat.internal_pages +
								indexStat.deleted_pages +
								indexStat.empty_pages) * BLCKSZ);
		values[j++] = psprintf("%u", indexStat.root_blkno);
		values[j++] = psprintf(INT64_FORMAT, indexStat.internal_pages);
		values[j++] = psprintf(INT64_FORMAT, indexStat.leaf_pages);
		values[j++] = psprintf(INT64_FORMAT, indexStat.empty_pages);
		values[j++] = psprintf(INT64_FORMAT, indexStat.deleted_pages);
		if (indexStat.max_avail > 0)
			values[j++] = psprintf("%.2f",
								   100.0 - (double) indexStat.free_space / (double) indexStat.max_avail * 100.0);
		else
			values[j++] = pstrdup("NaN");
		if (indexStat.leaf_pages > 0)
			values[j++] = psprintf("%.2f",
								   (double) indexStat.fragments / (double) indexStat.leaf_pages * 100.0);
		else
			values[j++] = pstrdup("NaN");

		tuple = BuildTupleFromCStrings(TupleDescGetAttInMetadata(tupleDesc),
									   values);

		result = HeapTupleGetDatum(tuple);
	}

	return result;
}

/* --------------------------------------------------------
 * pg_relpages()
 *
 * Get the number of pages of the table/index.
 *
 * Usage: SELECT pg_relpages('t1');
 *		  SELECT pg_relpages('t1_pkey');
 *
 * Must keep superuser() check, see above.
 * --------------------------------------------------------
 */
Datum
pg_relpages(PG_FUNCTION_ARGS)
{
	text	   *relname = PG_GETARG_TEXT_PP(0);
	Relation	rel;
	RangeVar   *relrv;

	if (!superuser())
		ereport(ERROR,
				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
				 errmsg("must be superuser to use pgstattuple functions")));

	relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
	rel = relation_openrv(relrv, AccessShareLock);

	PG_RETURN_INT64(pg_relpages_impl(rel));
}

/* No need for superuser checks in v1.5, see above */
Datum
pg_relpages_v1_5(PG_FUNCTION_ARGS)
{
	text	   *relname = PG_GETARG_TEXT_PP(0);
	Relation	rel;
	RangeVar   *relrv;

	relrv = makeRangeVarFromNameList(textToQualifiedNameList(relname));
	rel = relation_openrv(relrv, AccessShareLock);

	PG_RETURN_INT64(pg_relpages_impl(rel));
}

/* Must keep superuser() check, see above. */
Datum
pg_relpagesbyid(PG_FUNCTION_ARGS)
{
	Oid			relid = PG_GETARG_OID(0);
	Relation	rel;

	if (!superuser())
		ereport(ERROR,
				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
				 errmsg("must be superuser to use pgstattuple functions")));

	rel = relation_open(relid, AccessShareLock);

	PG_RETURN_INT64(pg_relpages_impl(rel));
}

/* No need for superuser checks in v1.5, see above */
Datum
pg_relpagesbyid_v1_5(PG_FUNCTION_ARGS)
{
	Oid			relid = PG_GETARG_OID(0);
	Relation	rel;

	rel = relation_open(relid, AccessShareLock);

	PG_RETURN_INT64(pg_relpages_impl(rel));
}

static int64
pg_relpages_impl(Relation rel)
{
	int64		relpages;

	if (!RELKIND_HAS_STORAGE(rel->rd_rel->relkind))
		ereport(ERROR,
				(errcode(ERRCODE_WRONG_OBJECT_TYPE),
				 errmsg("cannot get page count of relation \"%s\"",
						RelationGetRelationName(rel)),
				 errdetail_relkind_not_supported(rel->rd_rel->relkind)));

	/* note: this will work OK on non-local temp tables */

	relpages = RelationGetNumberOfBlocks(rel);

	relation_close(rel, AccessShareLock);

	return relpages;
}

/* ------------------------------------------------------
 * pgstatginindex()
 *
 * Usage: SELECT * FROM pgstatginindex('ginindex');
 *
 * Must keep superuser() check, see above.
 * ------------------------------------------------------
 */
Datum
pgstatginindex(PG_FUNCTION_ARGS)
{
	Oid			relid = PG_GETARG_OID(0);

	if (!superuser())
		ereport(ERROR,
				(errcode(ERRCODE_INSUFFICIENT_PRIVILEGE),
				 errmsg("must be superuser to use pgstattuple functions")));

	PG_RETURN_DATUM(pgstatginindex_internal(relid, fcinfo));
}

/* No need for superuser checks in v1.5, see above */
Datum
pgstatginindex_v1_5(PG_FUNCTION_ARGS)
{
	Oid			relid = PG_GETARG_OID(0);

	PG_RETURN_DATUM(pgstatginindex_internal(relid, fcinfo));
}

Datum
pgstatginindex_internal(Oid relid, FunctionCallInfo fcinfo)
{
	Relation	rel;
	Buffer		buffer;
	Page		page;
	GinMetaPageData *metadata;
	GinIndexStat stats;
	HeapTuple	tuple;
	TupleDesc	tupleDesc;
	Datum		values[3];
	bool		nulls[3] = {false, false, false};
	Datum		result;

	rel = relation_open(relid, AccessShareLock);

	if (!IS_INDEX(rel) || !IS_GIN(rel))
		ereport(ERROR,
				(errcode(ERRCODE_WRONG_OBJECT_TYPE),
				 errmsg("relation \"%s\" is not a GIN index",
						RelationGetRelationName(rel))));

	/*
	 * Reject attempts to read non-local temporary relations; we would be
	 * likely to get wrong data since we have no visibility into the owning
	 * session's local buffers.
	 */
	if (RELATION_IS_OTHER_TEMP(rel))
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 errmsg("cannot access temporary indexes of other sessions")));

	/* see pgstatindex_impl */
	if (!rel->rd_index->indisvalid)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("index \"%s\" is not valid",
						RelationGetRelationName(rel))));

	/*
	 * Read metapage
	 */
	buffer = ReadBuffer(rel, GIN_METAPAGE_BLKNO);
	LockBuffer(buffer, GIN_SHARE);
	page = BufferGetPage(buffer);
	metadata = GinPageGetMeta(page);

	stats.version = metadata->ginVersion;
	stats.pending_pages = metadata->nPendingPages;
	stats.pending_tuples = metadata->nPendingHeapTuples;

	UnlockReleaseBuffer(buffer);
	relation_close(rel, AccessShareLock);

	/*
	 * Build a tuple descriptor for our result type
	 */
	if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
		elog(ERROR, "return type must be a row type");

	values[0] = Int32GetDatum(stats.version);
	values[1] = UInt32GetDatum(stats.pending_pages);
	values[2] = Int64GetDatum(stats.pending_tuples);

	/*
	 * Build and return the tuple
	 */
	tuple = heap_form_tuple(tupleDesc, values, nulls);
	result = HeapTupleGetDatum(tuple);

	return result;
}

/* ------------------------------------------------------
 * pgstathashindex()
 *
 * Usage: SELECT * FROM pgstathashindex('hashindex');
 * ------------------------------------------------------
 */
Datum
pgstathashindex(PG_FUNCTION_ARGS)
{
	Oid			relid = PG_GETARG_OID(0);
	BlockNumber nblocks;
	BlockNumber blkno;
	Relation	rel;
	HashIndexStat stats;
	BufferAccessStrategy bstrategy;
	HeapTuple	tuple;
	TupleDesc	tupleDesc;
	Datum		values[8];
	bool		nulls[8];
	Buffer		metabuf;
	HashMetaPage metap;
	float8		free_percent;
	uint64		total_space;

	rel = relation_open(relid, AccessShareLock);

	if (!IS_INDEX(rel) || !IS_HASH(rel))
		ereport(ERROR,
				(errcode(ERRCODE_WRONG_OBJECT_TYPE),
				 errmsg("relation \"%s\" is not a hash index",
						RelationGetRelationName(rel))));

	/*
	 * Reject attempts to read non-local temporary relations; we would be
	 * likely to get wrong data since we have no visibility into the owning
	 * session's local buffers.
	 */
	if (RELATION_IS_OTHER_TEMP(rel))
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 errmsg("cannot access temporary indexes of other sessions")));

	/* see pgstatindex_impl */
	if (!rel->rd_index->indisvalid)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("index \"%s\" is not valid",
						RelationGetRelationName(rel))));

	/* Get the information we need from the metapage. */
	memset(&stats, 0, sizeof(stats));
	metabuf = _hash_getbuf(rel, HASH_METAPAGE, HASH_READ, LH_META_PAGE);
	metap = HashPageGetMeta(BufferGetPage(metabuf));
	stats.version = metap->hashm_version;
	stats.space_per_page = metap->hashm_bsize;
	_hash_relbuf(rel, metabuf);

	/* Get the current relation length */
	nblocks = RelationGetNumberOfBlocks(rel);

	/* prepare access strategy for this index */
	bstrategy = GetAccessStrategy(BAS_BULKREAD);

	/* Start from blkno 1 as 0th block is metapage */
	for (blkno = 1; blkno < nblocks; blkno++)
	{
		Buffer		buf;
		Page		page;

		CHECK_FOR_INTERRUPTS();

		buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
								 bstrategy);
		LockBuffer(buf, BUFFER_LOCK_SHARE);
		page = (Page) BufferGetPage(buf);

		if (PageIsNew(page))
			stats.unused_pages++;
		else if (PageGetSpecialSize(page) !=
				 MAXALIGN(sizeof(HashPageOpaqueData)))
			ereport(ERROR,
					(errcode(ERRCODE_INDEX_CORRUPTED),
					 errmsg("index \"%s\" contains corrupted page at block %u",
							RelationGetRelationName(rel),
							BufferGetBlockNumber(buf))));
		else
		{
			HashPageOpaque opaque;
			int			pagetype;

			opaque = HashPageGetOpaque(page);
			pagetype = opaque->hasho_flag & LH_PAGE_TYPE;

			if (pagetype == LH_BUCKET_PAGE)
			{
				stats.bucket_pages++;
				GetHashPageStats(page, &stats);
			}
			else if (pagetype == LH_OVERFLOW_PAGE)
			{
				stats.overflow_pages++;
				GetHashPageStats(page, &stats);
			}
			else if (pagetype == LH_BITMAP_PAGE)
				stats.bitmap_pages++;
			else if (pagetype == LH_UNUSED_PAGE)
				stats.unused_pages++;
			else
				ereport(ERROR,
						(errcode(ERRCODE_INDEX_CORRUPTED),
						 errmsg("unexpected page type 0x%04X in HASH index \"%s\" block %u",
								opaque->hasho_flag, RelationGetRelationName(rel),
								BufferGetBlockNumber(buf))));
		}
		UnlockReleaseBuffer(buf);
	}

	/* Done accessing the index */
	index_close(rel, AccessShareLock);

	/* Count unused pages as free space. */
	stats.free_space += (uint64) stats.unused_pages * stats.space_per_page;

	/*
	 * Total space available for tuples excludes the metapage and the bitmap
	 * pages.
	 */
	total_space = (uint64) (nblocks - (stats.bitmap_pages + 1)) *
		stats.space_per_page;

	if (total_space == 0)
		free_percent = 0.0;
	else
		free_percent = 100.0 * stats.free_space / total_space;

	/*
	 * Build a tuple descriptor for our result type
	 */
	if (get_call_result_type(fcinfo, NULL, &tupleDesc) != TYPEFUNC_COMPOSITE)
		elog(ERROR, "return type must be a row type");

	tupleDesc = BlessTupleDesc(tupleDesc);

	/*
	 * Build and return the tuple
	 */
	MemSet(nulls, 0, sizeof(nulls));
	values[0] = Int32GetDatum(stats.version);
	values[1] = Int64GetDatum((int64) stats.bucket_pages);
	values[2] = Int64GetDatum((int64) stats.overflow_pages);
	values[3] = Int64GetDatum((int64) stats.bitmap_pages);
	values[4] = Int64GetDatum((int64) stats.unused_pages);
	values[5] = Int64GetDatum(stats.live_items);
	values[6] = Int64GetDatum(stats.dead_items);
	values[7] = Float8GetDatum(free_percent);
	tuple = heap_form_tuple(tupleDesc, values, nulls);

	PG_RETURN_DATUM(HeapTupleGetDatum(tuple));
}

/* -------------------------------------------------
 * GetHashPageStats()
 *
 * Collect statistics of single hash page
 * -------------------------------------------------
 */
static void
GetHashPageStats(Page page, HashIndexStat *stats)
{
	OffsetNumber maxoff = PageGetMaxOffsetNumber(page);
	int			off;

	/* count live and dead tuples, and free space */
	for (off = FirstOffsetNumber; off <= maxoff; off++)
	{
		ItemId		id = PageGetItemId(page, off);

		if (!ItemIdIsDead(id))
			stats->live_items++;
		else
			stats->dead_items++;
	}
	stats->free_space += PageGetExactFreeSpace(page);
}