aboutsummaryrefslogtreecommitdiff
path: root/src/backend/access/heap/heapam_handler.c
blob: 00ca71a3d2a27aeba2c206fdacd787beee41297c (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
/*-------------------------------------------------------------------------
 *
 * heapam_handler.c
 *	  heap table access method code
 *
 * Portions Copyright (c) 1996-2019, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  src/backend/access/heap/heapam_handler.c
 *
 *
 * NOTES
 *	  This files wires up the lower level heapam.c et routines with the
 *	  tableam abstraction.
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "access/heapam.h"
#include "access/tableam.h"
#include "access/xact.h"
#include "storage/bufmgr.h"
#include "storage/lmgr.h"
#include "utils/builtins.h"


static const TableAmRoutine heapam_methods;


/* ------------------------------------------------------------------------
 * Slot related callbacks for heap AM
 * ------------------------------------------------------------------------
 */

static const TupleTableSlotOps *
heapam_slot_callbacks(Relation relation)
{
	return &TTSOpsBufferHeapTuple;
}


/* ------------------------------------------------------------------------
 * Index Scan Callbacks for heap AM
 * ------------------------------------------------------------------------
 */

static IndexFetchTableData *
heapam_index_fetch_begin(Relation rel)
{
	IndexFetchHeapData *hscan = palloc0(sizeof(IndexFetchHeapData));

	hscan->xs_base.rel = rel;
	hscan->xs_cbuf = InvalidBuffer;

	return &hscan->xs_base;
}

static void
heapam_index_fetch_reset(IndexFetchTableData *scan)
{
	IndexFetchHeapData *hscan = (IndexFetchHeapData *) scan;

	if (BufferIsValid(hscan->xs_cbuf))
	{
		ReleaseBuffer(hscan->xs_cbuf);
		hscan->xs_cbuf = InvalidBuffer;
	}
}

static void
heapam_index_fetch_end(IndexFetchTableData *scan)
{
	IndexFetchHeapData *hscan = (IndexFetchHeapData *) scan;

	heapam_index_fetch_reset(scan);

	pfree(hscan);
}

static bool
heapam_index_fetch_tuple(struct IndexFetchTableData *scan,
						 ItemPointer tid,
						 Snapshot snapshot,
						 TupleTableSlot *slot,
						 bool *call_again, bool *all_dead)
{
	IndexFetchHeapData *hscan = (IndexFetchHeapData *) scan;
	BufferHeapTupleTableSlot *bslot = (BufferHeapTupleTableSlot *) slot;
	bool		got_heap_tuple;

	Assert(TTS_IS_BUFFERTUPLE(slot));

	/* We can skip the buffer-switching logic if we're in mid-HOT chain. */
	if (!*call_again)
	{
		/* Switch to correct buffer if we don't have it already */
		Buffer		prev_buf = hscan->xs_cbuf;

		hscan->xs_cbuf = ReleaseAndReadBuffer(hscan->xs_cbuf,
											  hscan->xs_base.rel,
											  ItemPointerGetBlockNumber(tid));

		/*
		 * Prune page, but only if we weren't already on this page
		 */
		if (prev_buf != hscan->xs_cbuf)
			heap_page_prune_opt(hscan->xs_base.rel, hscan->xs_cbuf);
	}

	/* Obtain share-lock on the buffer so we can examine visibility */
	LockBuffer(hscan->xs_cbuf, BUFFER_LOCK_SHARE);
	got_heap_tuple = heap_hot_search_buffer(tid,
											hscan->xs_base.rel,
											hscan->xs_cbuf,
											snapshot,
											&bslot->base.tupdata,
											all_dead,
											!*call_again);
	bslot->base.tupdata.t_self = *tid;
	LockBuffer(hscan->xs_cbuf, BUFFER_LOCK_UNLOCK);

	if (got_heap_tuple)
	{
		/*
		 * Only in a non-MVCC snapshot can more than one member of the HOT
		 * chain be visible.
		 */
		*call_again = !IsMVCCSnapshot(snapshot);

		slot->tts_tableOid = RelationGetRelid(scan->rel);
		ExecStoreBufferHeapTuple(&bslot->base.tupdata, slot, hscan->xs_cbuf);
	}
	else
	{
		/* We've reached the end of the HOT chain. */
		*call_again = false;
	}

	return got_heap_tuple;
}


/* ------------------------------------------------------------------------
 * Callbacks for non-modifying operations on individual tuples for heap AM
 * ------------------------------------------------------------------------
 */

static bool
heapam_fetch_row_version(Relation relation,
						 ItemPointer tid,
						 Snapshot snapshot,
						 TupleTableSlot *slot)
{
	BufferHeapTupleTableSlot *bslot = (BufferHeapTupleTableSlot *) slot;
	Buffer		buffer;

	Assert(TTS_IS_BUFFERTUPLE(slot));

	bslot->base.tupdata.t_self = *tid;
	if (heap_fetch(relation, snapshot, &bslot->base.tupdata, &buffer))
	{
		/* store in slot, transferring existing pin */
		ExecStorePinnedBufferHeapTuple(&bslot->base.tupdata, slot, buffer);
		slot->tts_tableOid = RelationGetRelid(relation);

		return true;
	}

	return false;
}

static bool
heapam_tuple_satisfies_snapshot(Relation rel, TupleTableSlot *slot,
								Snapshot snapshot)
{
	BufferHeapTupleTableSlot *bslot = (BufferHeapTupleTableSlot *) slot;
	bool		res;

	Assert(TTS_IS_BUFFERTUPLE(slot));
	Assert(BufferIsValid(bslot->buffer));

	/*
	 * We need buffer pin and lock to call HeapTupleSatisfiesVisibility.
	 * Caller should be holding pin, but not lock.
	 */
	LockBuffer(bslot->buffer, BUFFER_LOCK_SHARE);
	res = HeapTupleSatisfiesVisibility(bslot->base.tuple, snapshot,
									   bslot->buffer);
	LockBuffer(bslot->buffer, BUFFER_LOCK_UNLOCK);

	return res;
}


/* ----------------------------------------------------------------------------
 *  Functions for manipulations of physical tuples for heap AM.
 * ----------------------------------------------------------------------------
 */

static void
heapam_tuple_insert(Relation relation, TupleTableSlot *slot, CommandId cid,
					int options, BulkInsertState bistate)
{
	bool		shouldFree = true;
	HeapTuple	tuple = ExecFetchSlotHeapTuple(slot, true, &shouldFree);

	/* Update the tuple with table oid */
	slot->tts_tableOid = RelationGetRelid(relation);
	tuple->t_tableOid = slot->tts_tableOid;

	/* Perform the insertion, and copy the resulting ItemPointer */
	heap_insert(relation, tuple, cid, options, bistate);
	ItemPointerCopy(&tuple->t_self, &slot->tts_tid);

	if (shouldFree)
		pfree(tuple);
}

static void
heapam_tuple_insert_speculative(Relation relation, TupleTableSlot *slot, CommandId cid,
								int options, BulkInsertState bistate, uint32 specToken)
{
	bool		shouldFree = true;
	HeapTuple	tuple = ExecFetchSlotHeapTuple(slot, true, &shouldFree);

	/* Update the tuple with table oid */
	slot->tts_tableOid = RelationGetRelid(relation);
	tuple->t_tableOid = slot->tts_tableOid;

	HeapTupleHeaderSetSpeculativeToken(tuple->t_data, specToken);
	options |= HEAP_INSERT_SPECULATIVE;

	/* Perform the insertion, and copy the resulting ItemPointer */
	heap_insert(relation, tuple, cid, options, bistate);
	ItemPointerCopy(&tuple->t_self, &slot->tts_tid);

	if (shouldFree)
		pfree(tuple);
}

static void
heapam_tuple_complete_speculative(Relation relation, TupleTableSlot *slot, uint32 spekToken,
								  bool succeeded)
{
	bool		shouldFree = true;
	HeapTuple	tuple = ExecFetchSlotHeapTuple(slot, true, &shouldFree);

	/* adjust the tuple's state accordingly */
	if (!succeeded)
		heap_finish_speculative(relation, &slot->tts_tid);
	else
		heap_abort_speculative(relation, &slot->tts_tid);

	if (shouldFree)
		pfree(tuple);
}

static TM_Result
heapam_tuple_delete(Relation relation, ItemPointer tid, CommandId cid,
					Snapshot snapshot, Snapshot crosscheck, bool wait,
					TM_FailureData *tmfd, bool changingPart)
{
	/*
	 * Currently Deleting of index tuples are handled at vacuum, in case if
	 * the storage itself is cleaning the dead tuples by itself, it is the
	 * time to call the index tuple deletion also.
	 */
	return heap_delete(relation, tid, cid, crosscheck, wait, tmfd, changingPart);
}


static TM_Result
heapam_tuple_update(Relation relation, ItemPointer otid, TupleTableSlot *slot,
					CommandId cid, Snapshot snapshot, Snapshot crosscheck,
					bool wait, TM_FailureData *tmfd,
					LockTupleMode *lockmode, bool *update_indexes)
{
	bool		shouldFree = true;
	HeapTuple	tuple = ExecFetchSlotHeapTuple(slot, true, &shouldFree);
	TM_Result	result;

	/* Update the tuple with table oid */
	slot->tts_tableOid = RelationGetRelid(relation);
	tuple->t_tableOid = slot->tts_tableOid;

	result = heap_update(relation, otid, tuple, cid, crosscheck, wait,
						 tmfd, lockmode);
	ItemPointerCopy(&tuple->t_self, &slot->tts_tid);

	/*
	 * Decide whether new index entries are needed for the tuple
	 *
	 * Note: heap_update returns the tid (location) of the new tuple in the
	 * t_self field.
	 *
	 * If it's a HOT update, we mustn't insert new index entries.
	 */
	*update_indexes = result == TM_Ok && !HeapTupleIsHeapOnly(tuple);

	if (shouldFree)
		pfree(tuple);

	return result;
}

static TM_Result
heapam_tuple_lock(Relation relation, ItemPointer tid, Snapshot snapshot,
				  TupleTableSlot *slot, CommandId cid, LockTupleMode mode,
				  LockWaitPolicy wait_policy, uint8 flags,
				  TM_FailureData *tmfd)
{
	BufferHeapTupleTableSlot *bslot = (BufferHeapTupleTableSlot *) slot;
	TM_Result	result;
	Buffer		buffer;
	HeapTuple	tuple = &bslot->base.tupdata;
	bool		follow_updates;

	follow_updates = (flags & TUPLE_LOCK_FLAG_LOCK_UPDATE_IN_PROGRESS) != 0;
	tmfd->traversed = false;

	Assert(TTS_IS_BUFFERTUPLE(slot));

tuple_lock_retry:
	tuple->t_self = *tid;
	result = heap_lock_tuple(relation, tuple, cid, mode, wait_policy,
							 follow_updates, &buffer, tmfd);

	if (result == TM_Updated &&
		(flags & TUPLE_LOCK_FLAG_FIND_LAST_VERSION))
	{
		ReleaseBuffer(buffer);
		/* Should not encounter speculative tuple on recheck */
		Assert(!HeapTupleHeaderIsSpeculative(tuple->t_data));

		if (!ItemPointerEquals(&tmfd->ctid, &tuple->t_self))
		{
			SnapshotData SnapshotDirty;
			TransactionId priorXmax;

			/* it was updated, so look at the updated version */
			*tid = tmfd->ctid;
			/* updated row should have xmin matching this xmax */
			priorXmax = tmfd->xmax;

			/* signal that a tuple later in the chain is getting locked */
			tmfd->traversed = true;

			/*
			 * fetch target tuple
			 *
			 * Loop here to deal with updated or busy tuples
			 */
			InitDirtySnapshot(SnapshotDirty);
			for (;;)
			{
				if (ItemPointerIndicatesMovedPartitions(tid))
					ereport(ERROR,
							(errcode(ERRCODE_T_R_SERIALIZATION_FAILURE),
							 errmsg("tuple to be locked was already moved to another partition due to concurrent update")));

				tuple->t_self = *tid;
				if (heap_fetch(relation, &SnapshotDirty, tuple, &buffer))
				{
					/*
					 * If xmin isn't what we're expecting, the slot must have
					 * been recycled and reused for an unrelated tuple.  This
					 * implies that the latest version of the row was deleted,
					 * so we need do nothing.  (Should be safe to examine xmin
					 * without getting buffer's content lock.  We assume
					 * reading a TransactionId to be atomic, and Xmin never
					 * changes in an existing tuple, except to invalid or
					 * frozen, and neither of those can match priorXmax.)
					 */
					if (!TransactionIdEquals(HeapTupleHeaderGetXmin(tuple->t_data),
											 priorXmax))
					{
						ReleaseBuffer(buffer);
						return TM_Deleted;
					}

					/* otherwise xmin should not be dirty... */
					if (TransactionIdIsValid(SnapshotDirty.xmin))
						elog(ERROR, "t_xmin is uncommitted in tuple to be updated");

					/*
					 * If tuple is being updated by other transaction then we
					 * have to wait for its commit/abort, or die trying.
					 */
					if (TransactionIdIsValid(SnapshotDirty.xmax))
					{
						ReleaseBuffer(buffer);
						switch (wait_policy)
						{
							case LockWaitBlock:
								XactLockTableWait(SnapshotDirty.xmax,
												  relation, &tuple->t_self,
												  XLTW_FetchUpdated);
								break;
							case LockWaitSkip:
								if (!ConditionalXactLockTableWait(SnapshotDirty.xmax))
									/* skip instead of waiting */
									return TM_WouldBlock;
								break;
							case LockWaitError:
								if (!ConditionalXactLockTableWait(SnapshotDirty.xmax))
									ereport(ERROR,
											(errcode(ERRCODE_LOCK_NOT_AVAILABLE),
											 errmsg("could not obtain lock on row in relation \"%s\"",
													RelationGetRelationName(relation))));
								break;
						}
						continue;	/* loop back to repeat heap_fetch */
					}

					/*
					 * If tuple was inserted by our own transaction, we have
					 * to check cmin against cid: cmin >= current CID means
					 * our command cannot see the tuple, so we should ignore
					 * it. Otherwise heap_lock_tuple() will throw an error,
					 * and so would any later attempt to update or delete the
					 * tuple.  (We need not check cmax because
					 * HeapTupleSatisfiesDirty will consider a tuple deleted
					 * by our transaction dead, regardless of cmax.)  We just
					 * checked that priorXmax == xmin, so we can test that
					 * variable instead of doing HeapTupleHeaderGetXmin again.
					 */
					if (TransactionIdIsCurrentTransactionId(priorXmax) &&
						HeapTupleHeaderGetCmin(tuple->t_data) >= cid)
					{
						ReleaseBuffer(buffer);
						return TM_Invisible;
					}

					/*
					 * This is a live tuple, so try to lock it again.
					 */
					ReleaseBuffer(buffer);
					goto tuple_lock_retry;
				}

				/*
				 * If the referenced slot was actually empty, the latest
				 * version of the row must have been deleted, so we need do
				 * nothing.
				 */
				if (tuple->t_data == NULL)
				{
					return TM_Deleted;
				}

				/*
				 * As above, if xmin isn't what we're expecting, do nothing.
				 */
				if (!TransactionIdEquals(HeapTupleHeaderGetXmin(tuple->t_data),
										 priorXmax))
				{
					if (BufferIsValid(buffer))
						ReleaseBuffer(buffer);
					return TM_Deleted;
				}

				/*
				 * If we get here, the tuple was found but failed
				 * SnapshotDirty. Assuming the xmin is either a committed xact
				 * or our own xact (as it certainly should be if we're trying
				 * to modify the tuple), this must mean that the row was
				 * updated or deleted by either a committed xact or our own
				 * xact.  If it was deleted, we can ignore it; if it was
				 * updated then chain up to the next version and repeat the
				 * whole process.
				 *
				 * As above, it should be safe to examine xmax and t_ctid
				 * without the buffer content lock, because they can't be
				 * changing.
				 */
				if (ItemPointerEquals(&tuple->t_self, &tuple->t_data->t_ctid))
				{
					/* deleted, so forget about it */
					if (BufferIsValid(buffer))
						ReleaseBuffer(buffer);
					return TM_Deleted;
				}

				/* updated, so look at the updated row */
				*tid = tuple->t_data->t_ctid;
				/* updated row should have xmin matching this xmax */
				priorXmax = HeapTupleHeaderGetUpdateXid(tuple->t_data);
				if (BufferIsValid(buffer))
					ReleaseBuffer(buffer);
				/* loop back to fetch next in chain */
			}
		}
		else
		{
			/* tuple was deleted, so give up */
			return TM_Deleted;
		}
	}

	slot->tts_tableOid = RelationGetRelid(relation);
	tuple->t_tableOid = slot->tts_tableOid;

	/* store in slot, transferring existing pin */
	ExecStorePinnedBufferHeapTuple(tuple, slot, buffer);

	return result;
}


/* ------------------------------------------------------------------------
 * Definition of the heap table access method.
 * ------------------------------------------------------------------------
 */

static const TableAmRoutine heapam_methods = {
	.type = T_TableAmRoutine,

	.slot_callbacks = heapam_slot_callbacks,

	.scan_begin = heap_beginscan,
	.scan_end = heap_endscan,
	.scan_rescan = heap_rescan,
	.scan_getnextslot = heap_getnextslot,

	.parallelscan_estimate = table_block_parallelscan_estimate,
	.parallelscan_initialize = table_block_parallelscan_initialize,
	.parallelscan_reinitialize = table_block_parallelscan_reinitialize,

	.index_fetch_begin = heapam_index_fetch_begin,
	.index_fetch_reset = heapam_index_fetch_reset,
	.index_fetch_end = heapam_index_fetch_end,
	.index_fetch_tuple = heapam_index_fetch_tuple,

	.tuple_insert = heapam_tuple_insert,
	.tuple_insert_speculative = heapam_tuple_insert_speculative,
	.tuple_complete_speculative = heapam_tuple_complete_speculative,
	.tuple_delete = heapam_tuple_delete,
	.tuple_update = heapam_tuple_update,
	.tuple_lock = heapam_tuple_lock,

	.tuple_fetch_row_version = heapam_fetch_row_version,
	.tuple_satisfies_snapshot = heapam_tuple_satisfies_snapshot,
};


const TableAmRoutine *
GetHeapamTableAmRoutine(void)
{
	return &heapam_methods;
}

Datum
heap_tableam_handler(PG_FUNCTION_ARGS)
{
	PG_RETURN_POINTER(&heapam_methods);
}