summaryrefslogtreecommitdiffstats
path: root/src/backend/executor/nodeIndexonlyscan.c
blob: 45d1a67a7137ece6da210d51f20cb43649765df9 (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
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
/*-------------------------------------------------------------------------
 *
 * nodeIndexonlyscan.c
 *	  Routines to support index-only scans
 *
 * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  src/backend/executor/nodeIndexonlyscan.c
 *
 *-------------------------------------------------------------------------
 */
/*
 * INTERFACE ROUTINES
 *		ExecIndexOnlyScan			scans an index
 *		IndexOnlyNext				retrieve next tuple
 *		ExecInitIndexOnlyScan		creates and initializes state info.
 *		ExecReScanIndexOnlyScan		rescans the indexed relation.
 *		ExecEndIndexOnlyScan		releases all storage.
 *		ExecIndexOnlyMarkPos		marks scan position.
 *		ExecIndexOnlyRestrPos		restores scan position.
 *		ExecIndexOnlyScanEstimate	estimates DSM space needed for
 *						parallel index-only scan
 *		ExecIndexOnlyScanInitializeDSM	initialize DSM for parallel
 *						index-only scan
 *		ExecIndexOnlyScanReInitializeDSM	reinitialize DSM for fresh scan
 *		ExecIndexOnlyScanInitializeWorker attach to DSM info in parallel worker
 */
#include "postgres.h"

#include "access/genam.h"
#include "access/relscan.h"
#include "access/tableam.h"
#include "access/tupdesc.h"
#include "access/visibilitymap.h"
#include "catalog/pg_type.h"
#include "executor/execdebug.h"
#include "executor/nodeIndexonlyscan.h"
#include "executor/nodeIndexscan.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "storage/predicate.h"
#include "utils/builtins.h"
#include "utils/memutils.h"
#include "utils/rel.h"


static TupleTableSlot *IndexOnlyNext(IndexOnlyScanState *node);
static void StoreIndexTuple(IndexOnlyScanState *node, TupleTableSlot *slot,
							IndexTuple itup, TupleDesc itupdesc);


/* ----------------------------------------------------------------
 *		IndexOnlyNext
 *
 *		Retrieve a tuple from the IndexOnlyScan node's index.
 * ----------------------------------------------------------------
 */
static TupleTableSlot *
IndexOnlyNext(IndexOnlyScanState *node)
{
	EState	   *estate;
	ExprContext *econtext;
	ScanDirection direction;
	IndexScanDesc scandesc;
	TupleTableSlot *slot;
	ItemPointer tid;

	/*
	 * extract necessary information from index scan node
	 */
	estate = node->ss.ps.state;

	/*
	 * Determine which direction to scan the index in based on the plan's scan
	 * direction and the current direction of execution.
	 */
	direction = ScanDirectionCombine(estate->es_direction,
									 ((IndexOnlyScan *) node->ss.ps.plan)->indexorderdir);
	scandesc = node->ioss_ScanDesc;
	econtext = node->ss.ps.ps_ExprContext;
	slot = node->ss.ss_ScanTupleSlot;

	if (scandesc == NULL)
	{
		/*
		 * We reach here if the index only scan is not parallel, or if we're
		 * serially executing an index only scan that was planned to be
		 * parallel.
		 */
		scandesc = index_beginscan(node->ss.ss_currentRelation,
								   node->ioss_RelationDesc,
								   estate->es_snapshot,
								   node->ioss_NumScanKeys,
								   node->ioss_NumOrderByKeys);

		node->ioss_ScanDesc = scandesc;


		/* Set it up for index-only scan */
		node->ioss_ScanDesc->xs_want_itup = true;
		node->ioss_VMBuffer = InvalidBuffer;

		/*
		 * If no run-time keys to calculate or they are ready, go ahead and
		 * pass the scankeys to the index AM.
		 */
		if (node->ioss_NumRuntimeKeys == 0 || node->ioss_RuntimeKeysReady)
			index_rescan(scandesc,
						 node->ioss_ScanKeys,
						 node->ioss_NumScanKeys,
						 node->ioss_OrderByKeys,
						 node->ioss_NumOrderByKeys);
	}

	/*
	 * OK, now that we have what we need, fetch the next tuple.
	 */
	while ((tid = index_getnext_tid(scandesc, direction)) != NULL)
	{
		bool		tuple_from_heap = false;

		CHECK_FOR_INTERRUPTS();

		/*
		 * We can skip the heap fetch if the TID references a heap page on
		 * which all tuples are known visible to everybody.  In any case,
		 * we'll use the index tuple not the heap tuple as the data source.
		 *
		 * Note on Memory Ordering Effects: visibilitymap_get_status does not
		 * lock the visibility map buffer, and therefore the result we read
		 * here could be slightly stale.  However, it can't be stale enough to
		 * matter.
		 *
		 * We need to detect clearing a VM bit due to an insert right away,
		 * because the tuple is present in the index page but not visible. The
		 * reading of the TID by this scan (using a shared lock on the index
		 * buffer) is serialized with the insert of the TID into the index
		 * (using an exclusive lock on the index buffer). Because the VM bit
		 * is cleared before updating the index, and locking/unlocking of the
		 * index page acts as a full memory barrier, we are sure to see the
		 * cleared bit if we see a recently-inserted TID.
		 *
		 * Deletes do not update the index page (only VACUUM will clear out
		 * the TID), so the clearing of the VM bit by a delete is not
		 * serialized with this test below, and we may see a value that is
		 * significantly stale. However, we don't care about the delete right
		 * away, because the tuple is still visible until the deleting
		 * transaction commits or the statement ends (if it's our
		 * transaction). In either case, the lock on the VM buffer will have
		 * been released (acting as a write barrier) after clearing the bit.
		 * And for us to have a snapshot that includes the deleting
		 * transaction (making the tuple invisible), we must have acquired
		 * ProcArrayLock after that time, acting as a read barrier.
		 *
		 * It's worth going through this complexity to avoid needing to lock
		 * the VM buffer, which could cause significant contention.
		 */
		if (!VM_ALL_VISIBLE(scandesc->heapRelation,
							ItemPointerGetBlockNumber(tid),
							&node->ioss_VMBuffer))
		{
			/*
			 * Rats, we have to visit the heap to check visibility.
			 */
			InstrCountTuples2(node, 1);
			if (!index_fetch_heap(scandesc, node->ioss_TableSlot))
				continue;		/* no visible tuple, try next index entry */

			ExecClearTuple(node->ioss_TableSlot);

			/*
			 * Only MVCC snapshots are supported here, so there should be no
			 * need to keep following the HOT chain once a visible entry has
			 * been found.  If we did want to allow that, we'd need to keep
			 * more state to remember not to call index_getnext_tid next time.
			 */
			if (scandesc->xs_heap_continue)
				elog(ERROR, "non-MVCC snapshots are not supported in index-only scans");

			/*
			 * Note: at this point we are holding a pin on the heap page, as
			 * recorded in scandesc->xs_cbuf.  We could release that pin now,
			 * but it's not clear whether it's a win to do so.  The next index
			 * entry might require a visit to the same heap page.
			 */

			tuple_from_heap = true;
		}

		/*
		 * Fill the scan tuple slot with data from the index.  This might be
		 * provided in either HeapTuple or IndexTuple format.  Conceivably an
		 * index AM might fill both fields, in which case we prefer the heap
		 * format, since it's probably a bit cheaper to fill a slot from.
		 */
		if (scandesc->xs_hitup)
		{
			/*
			 * We don't take the trouble to verify that the provided tuple has
			 * exactly the slot's format, but it seems worth doing a quick
			 * check on the number of fields.
			 */
			Assert(slot->tts_tupleDescriptor->natts ==
				   scandesc->xs_hitupdesc->natts);
			ExecForceStoreHeapTuple(scandesc->xs_hitup, slot, false);
		}
		else if (scandesc->xs_itup)
			StoreIndexTuple(node, slot, scandesc->xs_itup, scandesc->xs_itupdesc);
		else
			elog(ERROR, "no data returned for index-only scan");

		/*
		 * If the index was lossy, we have to recheck the index quals.
		 */
		if (scandesc->xs_recheck)
		{
			econtext->ecxt_scantuple = slot;
			if (!ExecQualAndReset(node->recheckqual, econtext))
			{
				/* Fails recheck, so drop it and loop back for another */
				InstrCountFiltered2(node, 1);
				continue;
			}
		}

		/*
		 * We don't currently support rechecking ORDER BY distances.  (In
		 * principle, if the index can support retrieval of the originally
		 * indexed value, it should be able to produce an exact distance
		 * calculation too.  So it's not clear that adding code here for
		 * recheck/re-sort would be worth the trouble.  But we should at least
		 * throw an error if someone tries it.)
		 */
		if (scandesc->numberOfOrderBys > 0 && scandesc->xs_recheckorderby)
			ereport(ERROR,
					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
					 errmsg("lossy distance functions are not supported in index-only scans")));

		/*
		 * If we didn't access the heap, then we'll need to take a predicate
		 * lock explicitly, as if we had.  For now we do that at page level.
		 */
		if (!tuple_from_heap)
			PredicateLockPage(scandesc->heapRelation,
							  ItemPointerGetBlockNumber(tid),
							  estate->es_snapshot);

		return slot;
	}

	/*
	 * if we get here it means the index scan failed so we are at the end of
	 * the scan..
	 */
	return ExecClearTuple(slot);
}

/*
 * StoreIndexTuple
 *		Fill the slot with data from the index tuple.
 *
 * At some point this might be generally-useful functionality, but
 * right now we don't need it elsewhere.
 */
static void
StoreIndexTuple(IndexOnlyScanState *node, TupleTableSlot *slot,
				IndexTuple itup, TupleDesc itupdesc)
{
	/*
	 * Note: we must use the tupdesc supplied by the AM in index_deform_tuple,
	 * not the slot's tupdesc, in case the latter has different datatypes
	 * (this happens for btree name_ops in particular).  They'd better have
	 * the same number of columns though, as well as being datatype-compatible
	 * which is something we can't so easily check.
	 */
	Assert(slot->tts_tupleDescriptor->natts == itupdesc->natts);

	ExecClearTuple(slot);
	index_deform_tuple(itup, itupdesc, slot->tts_values, slot->tts_isnull);

	/*
	 * Copy all name columns stored as cstrings back into a NAMEDATALEN byte
	 * sized allocation.  We mark this branch as unlikely as generally "name"
	 * is used only for the system catalogs and this would have to be a user
	 * query running on those or some other user table with an index on a name
	 * column.
	 */
	if (unlikely(node->ioss_NameCStringAttNums != NULL))
	{
		int			attcount = node->ioss_NameCStringCount;

		for (int idx = 0; idx < attcount; idx++)
		{
			int			attnum = node->ioss_NameCStringAttNums[idx];
			Name		name;

			/* skip null Datums */
			if (slot->tts_isnull[attnum])
				continue;

			/* allocate the NAMEDATALEN and copy the datum into that memory */
			name = (Name) MemoryContextAlloc(node->ss.ps.ps_ExprContext->ecxt_per_tuple_memory,
											 NAMEDATALEN);

			/* use namestrcpy to zero-pad all trailing bytes */
			namestrcpy(name, DatumGetCString(slot->tts_values[attnum]));
			slot->tts_values[attnum] = NameGetDatum(name);
		}
	}

	ExecStoreVirtualTuple(slot);
}

/*
 * IndexOnlyRecheck -- access method routine to recheck a tuple in EvalPlanQual
 *
 * This can't really happen, since an index can't supply CTID which would
 * be necessary data for any potential EvalPlanQual target relation.  If it
 * did happen, the EPQ code would pass us the wrong data, namely a heap
 * tuple not an index tuple.  So throw an error.
 */
static bool
IndexOnlyRecheck(IndexOnlyScanState *node, TupleTableSlot *slot)
{
	elog(ERROR, "EvalPlanQual recheck is not supported in index-only scans");
	return false;				/* keep compiler quiet */
}

/* ----------------------------------------------------------------
 *		ExecIndexOnlyScan(node)
 * ----------------------------------------------------------------
 */
static TupleTableSlot *
ExecIndexOnlyScan(PlanState *pstate)
{
	IndexOnlyScanState *node = castNode(IndexOnlyScanState, pstate);

	/*
	 * If we have runtime keys and they've not already been set up, do it now.
	 */
	if (node->ioss_NumRuntimeKeys != 0 && !node->ioss_RuntimeKeysReady)
		ExecReScan((PlanState *) node);

	return ExecScan(&node->ss,
					(ExecScanAccessMtd) IndexOnlyNext,
					(ExecScanRecheckMtd) IndexOnlyRecheck);
}

/* ----------------------------------------------------------------
 *		ExecReScanIndexOnlyScan(node)
 *
 *		Recalculates the values of any scan keys whose value depends on
 *		information known at runtime, then rescans the indexed relation.
 *
 *		Updating the scan key was formerly done separately in
 *		ExecUpdateIndexScanKeys. Integrating it into ReScan makes
 *		rescans of indices and relations/general streams more uniform.
 * ----------------------------------------------------------------
 */
void
ExecReScanIndexOnlyScan(IndexOnlyScanState *node)
{
	/*
	 * If we are doing runtime key calculations (ie, any of the index key
	 * values weren't simple Consts), compute the new key values.  But first,
	 * reset the context so we don't leak memory as each outer tuple is
	 * scanned.  Note this assumes that we will recalculate *all* runtime keys
	 * on each call.
	 */
	if (node->ioss_NumRuntimeKeys != 0)
	{
		ExprContext *econtext = node->ioss_RuntimeContext;

		ResetExprContext(econtext);
		ExecIndexEvalRuntimeKeys(econtext,
								 node->ioss_RuntimeKeys,
								 node->ioss_NumRuntimeKeys);
	}
	node->ioss_RuntimeKeysReady = true;

	/* reset index scan */
	if (node->ioss_ScanDesc)
		index_rescan(node->ioss_ScanDesc,
					 node->ioss_ScanKeys, node->ioss_NumScanKeys,
					 node->ioss_OrderByKeys, node->ioss_NumOrderByKeys);

	ExecScanReScan(&node->ss);
}


/* ----------------------------------------------------------------
 *		ExecEndIndexOnlyScan
 * ----------------------------------------------------------------
 */
void
ExecEndIndexOnlyScan(IndexOnlyScanState *node)
{
	Relation	indexRelationDesc;
	IndexScanDesc indexScanDesc;

	/*
	 * extract information from the node
	 */
	indexRelationDesc = node->ioss_RelationDesc;
	indexScanDesc = node->ioss_ScanDesc;

	/* Release VM buffer pin, if any. */
	if (node->ioss_VMBuffer != InvalidBuffer)
	{
		ReleaseBuffer(node->ioss_VMBuffer);
		node->ioss_VMBuffer = InvalidBuffer;
	}

	/*
	 * Free the exprcontext(s) ... now dead code, see ExecFreeExprContext
	 */
#ifdef NOT_USED
	ExecFreeExprContext(&node->ss.ps);
	if (node->ioss_RuntimeContext)
		FreeExprContext(node->ioss_RuntimeContext, true);
#endif

	/*
	 * clear out tuple table slots
	 */
	if (node->ss.ps.ps_ResultTupleSlot)
		ExecClearTuple(node->ss.ps.ps_ResultTupleSlot);
	ExecClearTuple(node->ss.ss_ScanTupleSlot);

	/*
	 * close the index relation (no-op if we didn't open it)
	 */
	if (indexScanDesc)
		index_endscan(indexScanDesc);
	if (indexRelationDesc)
		index_close(indexRelationDesc, NoLock);
}

/* ----------------------------------------------------------------
 *		ExecIndexOnlyMarkPos
 *
 * Note: we assume that no caller attempts to set a mark before having read
 * at least one tuple.  Otherwise, ioss_ScanDesc might still be NULL.
 * ----------------------------------------------------------------
 */
void
ExecIndexOnlyMarkPos(IndexOnlyScanState *node)
{
	EState	   *estate = node->ss.ps.state;
	EPQState   *epqstate = estate->es_epq_active;

	if (epqstate != NULL)
	{
		/*
		 * We are inside an EvalPlanQual recheck.  If a test tuple exists for
		 * this relation, then we shouldn't access the index at all.  We would
		 * instead need to save, and later restore, the state of the
		 * relsubs_done flag, so that re-fetching the test tuple is possible.
		 * However, given the assumption that no caller sets a mark at the
		 * start of the scan, we can only get here with relsubs_done[i]
		 * already set, and so no state need be saved.
		 */
		Index		scanrelid = ((Scan *) node->ss.ps.plan)->scanrelid;

		Assert(scanrelid > 0);
		if (epqstate->relsubs_slot[scanrelid - 1] != NULL ||
			epqstate->relsubs_rowmark[scanrelid - 1] != NULL)
		{
			/* Verify the claim above */
			if (!epqstate->relsubs_done[scanrelid - 1])
				elog(ERROR, "unexpected ExecIndexOnlyMarkPos call in EPQ recheck");
			return;
		}
	}

	index_markpos(node->ioss_ScanDesc);
}

/* ----------------------------------------------------------------
 *		ExecIndexOnlyRestrPos
 * ----------------------------------------------------------------
 */
void
ExecIndexOnlyRestrPos(IndexOnlyScanState *node)
{
	EState	   *estate = node->ss.ps.state;
	EPQState   *epqstate = estate->es_epq_active;

	if (estate->es_epq_active != NULL)
	{
		/* See comments in ExecIndexMarkPos */
		Index		scanrelid = ((Scan *) node->ss.ps.plan)->scanrelid;

		Assert(scanrelid > 0);
		if (epqstate->relsubs_slot[scanrelid - 1] != NULL ||
			epqstate->relsubs_rowmark[scanrelid - 1] != NULL)
		{
			/* Verify the claim above */
			if (!epqstate->relsubs_done[scanrelid - 1])
				elog(ERROR, "unexpected ExecIndexOnlyRestrPos call in EPQ recheck");
			return;
		}
	}

	index_restrpos(node->ioss_ScanDesc);
}

/* ----------------------------------------------------------------
 *		ExecInitIndexOnlyScan
 *
 *		Initializes the index scan's state information, creates
 *		scan keys, and opens the base and index relations.
 *
 *		Note: index scans have 2 sets of state information because
 *			  we have to keep track of the base relation and the
 *			  index relation.
 * ----------------------------------------------------------------
 */
IndexOnlyScanState *
ExecInitIndexOnlyScan(IndexOnlyScan *node, EState *estate, int eflags)
{
	IndexOnlyScanState *indexstate;
	Relation	currentRelation;
	Relation	indexRelation;
	LOCKMODE	lockmode;
	TupleDesc	tupDesc;
	int			indnkeyatts;
	int			namecount;

	/*
	 * create state structure
	 */
	indexstate = makeNode(IndexOnlyScanState);
	indexstate->ss.ps.plan = (Plan *) node;
	indexstate->ss.ps.state = estate;
	indexstate->ss.ps.ExecProcNode = ExecIndexOnlyScan;

	/*
	 * Miscellaneous initialization
	 *
	 * create expression context for node
	 */
	ExecAssignExprContext(estate, &indexstate->ss.ps);

	/*
	 * open the scan relation
	 */
	currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid, eflags);

	indexstate->ss.ss_currentRelation = currentRelation;
	indexstate->ss.ss_currentScanDesc = NULL;	/* no heap scan here */

	/*
	 * Build the scan tuple type using the indextlist generated by the
	 * planner.  We use this, rather than the index's physical tuple
	 * descriptor, because the latter contains storage column types not the
	 * types of the original datums.  (It's the AM's responsibility to return
	 * suitable data anyway.)
	 */
	tupDesc = ExecTypeFromTL(node->indextlist);
	ExecInitScanTupleSlot(estate, &indexstate->ss, tupDesc,
						  &TTSOpsVirtual);

	/*
	 * We need another slot, in a format that's suitable for the table AM, for
	 * when we need to fetch a tuple from the table for rechecking visibility.
	 */
	indexstate->ioss_TableSlot =
		ExecAllocTableSlot(&estate->es_tupleTable,
						   RelationGetDescr(currentRelation),
						   table_slot_callbacks(currentRelation));

	/*
	 * Initialize result type and projection info.  The node's targetlist will
	 * contain Vars with varno = INDEX_VAR, referencing the scan tuple.
	 */
	ExecInitResultTypeTL(&indexstate->ss.ps);
	ExecAssignScanProjectionInfoWithVarno(&indexstate->ss, INDEX_VAR);

	/*
	 * initialize child expressions
	 *
	 * Note: we don't initialize all of the indexorderby expression, only the
	 * sub-parts corresponding to runtime keys (see below).
	 */
	indexstate->ss.ps.qual =
		ExecInitQual(node->scan.plan.qual, (PlanState *) indexstate);
	indexstate->recheckqual =
		ExecInitQual(node->recheckqual, (PlanState *) indexstate);

	/*
	 * If we are just doing EXPLAIN (ie, aren't going to run the plan), stop
	 * here.  This allows an index-advisor plugin to EXPLAIN a plan containing
	 * references to nonexistent indexes.
	 */
	if (eflags & EXEC_FLAG_EXPLAIN_ONLY)
		return indexstate;

	/* Open the index relation. */
	lockmode = exec_rt_fetch(node->scan.scanrelid, estate)->rellockmode;
	indexRelation = index_open(node->indexid, lockmode);
	indexstate->ioss_RelationDesc = indexRelation;

	/*
	 * Initialize index-specific scan state
	 */
	indexstate->ioss_RuntimeKeysReady = false;
	indexstate->ioss_RuntimeKeys = NULL;
	indexstate->ioss_NumRuntimeKeys = 0;

	/*
	 * build the index scan keys from the index qualification
	 */
	ExecIndexBuildScanKeys((PlanState *) indexstate,
						   indexRelation,
						   node->indexqual,
						   false,
						   &indexstate->ioss_ScanKeys,
						   &indexstate->ioss_NumScanKeys,
						   &indexstate->ioss_RuntimeKeys,
						   &indexstate->ioss_NumRuntimeKeys,
						   NULL,	/* no ArrayKeys */
						   NULL);

	/*
	 * any ORDER BY exprs have to be turned into scankeys in the same way
	 */
	ExecIndexBuildScanKeys((PlanState *) indexstate,
						   indexRelation,
						   node->indexorderby,
						   true,
						   &indexstate->ioss_OrderByKeys,
						   &indexstate->ioss_NumOrderByKeys,
						   &indexstate->ioss_RuntimeKeys,
						   &indexstate->ioss_NumRuntimeKeys,
						   NULL,	/* no ArrayKeys */
						   NULL);

	/*
	 * If we have runtime keys, we need an ExprContext to evaluate them. The
	 * node's standard context won't do because we want to reset that context
	 * for every tuple.  So, build another context just like the other one...
	 * -tgl 7/11/00
	 */
	if (indexstate->ioss_NumRuntimeKeys != 0)
	{
		ExprContext *stdecontext = indexstate->ss.ps.ps_ExprContext;

		ExecAssignExprContext(estate, &indexstate->ss.ps);
		indexstate->ioss_RuntimeContext = indexstate->ss.ps.ps_ExprContext;
		indexstate->ss.ps.ps_ExprContext = stdecontext;
	}
	else
	{
		indexstate->ioss_RuntimeContext = NULL;
	}

	indexstate->ioss_NameCStringAttNums = NULL;
	indnkeyatts = indexRelation->rd_index->indnkeyatts;
	namecount = 0;

	/*
	 * The "name" type for btree uses text_ops which results in storing
	 * cstrings in the indexed keys rather than names.  Here we detect that in
	 * a generic way in case other index AMs want to do the same optimization.
	 * Check for opclasses with an opcintype of NAMEOID and an index tuple
	 * descriptor with CSTRINGOID.  If any of these are found, create an array
	 * marking the index attribute number of each of them.  StoreIndexTuple()
	 * handles copying the name Datums into a NAMEDATALEN-byte allocation.
	 */

	/* First, count the number of such index keys */
	for (int attnum = 0; attnum < indnkeyatts; attnum++)
	{
		if (indexRelation->rd_att->attrs[attnum].atttypid == CSTRINGOID &&
			indexRelation->rd_opcintype[attnum] == NAMEOID)
			namecount++;
	}

	if (namecount > 0)
	{
		int			idx = 0;

		/*
		 * Now create an array to mark the attribute numbers of the keys that
		 * need to be converted from cstring to name.
		 */
		indexstate->ioss_NameCStringAttNums = (AttrNumber *)
									palloc(sizeof(AttrNumber) * namecount);

		for (int attnum = 0; attnum < indnkeyatts; attnum++)
		{
			if (indexRelation->rd_att->attrs[attnum].atttypid == CSTRINGOID &&
				indexRelation->rd_opcintype[attnum] == NAMEOID)
				indexstate->ioss_NameCStringAttNums[idx++] = (AttrNumber) attnum;
		}
	}

	indexstate->ioss_NameCStringCount = namecount;

	/*
	 * all done.
	 */
	return indexstate;
}

/* ----------------------------------------------------------------
 *		Parallel Index-only Scan Support
 * ----------------------------------------------------------------
 */

/* ----------------------------------------------------------------
 *		ExecIndexOnlyScanEstimate
 *
 *		Compute the amount of space we'll need in the parallel
 *		query DSM, and inform pcxt->estimator about our needs.
 * ----------------------------------------------------------------
 */
void
ExecIndexOnlyScanEstimate(IndexOnlyScanState *node,
						  ParallelContext *pcxt)
{
	EState	   *estate = node->ss.ps.state;

	node->ioss_PscanLen = index_parallelscan_estimate(node->ioss_RelationDesc,
													  estate->es_snapshot);
	shm_toc_estimate_chunk(&pcxt->estimator, node->ioss_PscanLen);
	shm_toc_estimate_keys(&pcxt->estimator, 1);
}

/* ----------------------------------------------------------------
 *		ExecIndexOnlyScanInitializeDSM
 *
 *		Set up a parallel index-only scan descriptor.
 * ----------------------------------------------------------------
 */
void
ExecIndexOnlyScanInitializeDSM(IndexOnlyScanState *node,
							   ParallelContext *pcxt)
{
	EState	   *estate = node->ss.ps.state;
	ParallelIndexScanDesc piscan;

	piscan = shm_toc_allocate(pcxt->toc, node->ioss_PscanLen);
	index_parallelscan_initialize(node->ss.ss_currentRelation,
								  node->ioss_RelationDesc,
								  estate->es_snapshot,
								  piscan);
	shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id, piscan);
	node->ioss_ScanDesc =
		index_beginscan_parallel(node->ss.ss_currentRelation,
								 node->ioss_RelationDesc,
								 node->ioss_NumScanKeys,
								 node->ioss_NumOrderByKeys,
								 piscan);
	node->ioss_ScanDesc->xs_want_itup = true;
	node->ioss_VMBuffer = InvalidBuffer;

	/*
	 * If no run-time keys to calculate or they are ready, go ahead and pass
	 * the scankeys to the index AM.
	 */
	if (node->ioss_NumRuntimeKeys == 0 || node->ioss_RuntimeKeysReady)
		index_rescan(node->ioss_ScanDesc,
					 node->ioss_ScanKeys, node->ioss_NumScanKeys,
					 node->ioss_OrderByKeys, node->ioss_NumOrderByKeys);
}

/* ----------------------------------------------------------------
 *		ExecIndexOnlyScanReInitializeDSM
 *
 *		Reset shared state before beginning a fresh scan.
 * ----------------------------------------------------------------
 */
void
ExecIndexOnlyScanReInitializeDSM(IndexOnlyScanState *node,
								 ParallelContext *pcxt)
{
	index_parallelrescan(node->ioss_ScanDesc);
}

/* ----------------------------------------------------------------
 *		ExecIndexOnlyScanInitializeWorker
 *
 *		Copy relevant information from TOC into planstate.
 * ----------------------------------------------------------------
 */
void
ExecIndexOnlyScanInitializeWorker(IndexOnlyScanState *node,
								  ParallelWorkerContext *pwcxt)
{
	ParallelIndexScanDesc piscan;

	piscan = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
	node->ioss_ScanDesc =
		index_beginscan_parallel(node->ss.ss_currentRelation,
								 node->ioss_RelationDesc,
								 node->ioss_NumScanKeys,
								 node->ioss_NumOrderByKeys,
								 piscan);
	node->ioss_ScanDesc->xs_want_itup = true;

	/*
	 * If no run-time keys to calculate or they are ready, go ahead and pass
	 * the scankeys to the index AM.
	 */
	if (node->ioss_NumRuntimeKeys == 0 || node->ioss_RuntimeKeysReady)
		index_rescan(node->ioss_ScanDesc,
					 node->ioss_ScanKeys, node->ioss_NumScanKeys,
					 node->ioss_OrderByKeys, node->ioss_NumOrderByKeys);
}