summaryrefslogtreecommitdiff
path: root/src/backend/storage/smgr/smgr.c
blob: b2bd749d7703b9d2ce61fd907f7f957cedef2cae (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
/*-------------------------------------------------------------------------
 *
 * smgr.c
 *	  public interface routines to storage manager switch.
 *
 *	  All file system operations in POSTGRES dispatch through these
 *	  routines.
 *
 * Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 *
 * IDENTIFICATION
 *	  src/backend/storage/smgr/smgr.c
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "access/xlogutils.h"
#include "lib/ilist.h"
#include "storage/bufmgr.h"
#include "storage/ipc.h"
#include "storage/md.h"
#include "storage/smgr.h"
#include "utils/hsearch.h"
#include "utils/inval.h"


/*
 * This struct of function pointers defines the API between smgr.c and
 * any individual storage manager module.  Note that smgr subfunctions are
 * generally expected to report problems via elog(ERROR).  An exception is
 * that smgr_unlink should use elog(WARNING), rather than erroring out,
 * because we normally unlink relations during post-commit/abort cleanup,
 * and so it's too late to raise an error.  Also, various conditions that
 * would normally be errors should be allowed during bootstrap and/or WAL
 * recovery --- see comments in md.c for details.
 */
typedef struct f_smgr
{
	void		(*smgr_init) (void);	/* may be NULL */
	void		(*smgr_shutdown) (void);	/* may be NULL */
	void		(*smgr_open) (SMgrRelation reln);
	void		(*smgr_close) (SMgrRelation reln, ForkNumber forknum);
	void		(*smgr_create) (SMgrRelation reln, ForkNumber forknum,
								bool isRedo);
	bool		(*smgr_exists) (SMgrRelation reln, ForkNumber forknum);
	void		(*smgr_unlink) (RelFileLocatorBackend rlocator, ForkNumber forknum,
								bool isRedo);
	void		(*smgr_extend) (SMgrRelation reln, ForkNumber forknum,
								BlockNumber blocknum, char *buffer, bool skipFsync);
	bool		(*smgr_prefetch) (SMgrRelation reln, ForkNumber forknum,
								  BlockNumber blocknum);
	void		(*smgr_read) (SMgrRelation reln, ForkNumber forknum,
							  BlockNumber blocknum, char *buffer);
	void		(*smgr_write) (SMgrRelation reln, ForkNumber forknum,
							   BlockNumber blocknum, char *buffer, bool skipFsync);
	void		(*smgr_writeback) (SMgrRelation reln, ForkNumber forknum,
								   BlockNumber blocknum, BlockNumber nblocks);
	BlockNumber (*smgr_nblocks) (SMgrRelation reln, ForkNumber forknum);
	void		(*smgr_truncate) (SMgrRelation reln, ForkNumber forknum,
								  BlockNumber nblocks);
	void		(*smgr_immedsync) (SMgrRelation reln, ForkNumber forknum);
} f_smgr;

static const f_smgr smgrsw[] = {
	/* magnetic disk */
	{
		.smgr_init = mdinit,
		.smgr_shutdown = NULL,
		.smgr_open = mdopen,
		.smgr_close = mdclose,
		.smgr_create = mdcreate,
		.smgr_exists = mdexists,
		.smgr_unlink = mdunlink,
		.smgr_extend = mdextend,
		.smgr_prefetch = mdprefetch,
		.smgr_read = mdread,
		.smgr_write = mdwrite,
		.smgr_writeback = mdwriteback,
		.smgr_nblocks = mdnblocks,
		.smgr_truncate = mdtruncate,
		.smgr_immedsync = mdimmedsync,
	}
};

static const int NSmgr = lengthof(smgrsw);

/*
 * Each backend has a hashtable that stores all extant SMgrRelation objects.
 * In addition, "unowned" SMgrRelation objects are chained together in a list.
 */
static HTAB *SMgrRelationHash = NULL;

static dlist_head unowned_relns;

/* local function prototypes */
static void smgrshutdown(int code, Datum arg);


/*
 *	smgrinit(), smgrshutdown() -- Initialize or shut down storage
 *								  managers.
 *
 * Note: smgrinit is called during backend startup (normal or standalone
 * case), *not* during postmaster start.  Therefore, any resources created
 * here or destroyed in smgrshutdown are backend-local.
 */
void
smgrinit(void)
{
	int			i;

	for (i = 0; i < NSmgr; i++)
	{
		if (smgrsw[i].smgr_init)
			smgrsw[i].smgr_init();
	}

	/* register the shutdown proc */
	on_proc_exit(smgrshutdown, 0);
}

/*
 * on_proc_exit hook for smgr cleanup during backend shutdown
 */
static void
smgrshutdown(int code, Datum arg)
{
	int			i;

	for (i = 0; i < NSmgr; i++)
	{
		if (smgrsw[i].smgr_shutdown)
			smgrsw[i].smgr_shutdown();
	}
}

/*
 *	smgropen() -- Return an SMgrRelation object, creating it if need be.
 *
 *		This does not attempt to actually open the underlying file.
 */
SMgrRelation
smgropen(RelFileLocator rlocator, BackendId backend)
{
	RelFileLocatorBackend brlocator;
	SMgrRelation reln;
	bool		found;

	if (SMgrRelationHash == NULL)
	{
		/* First time through: initialize the hash table */
		HASHCTL		ctl;

		ctl.keysize = sizeof(RelFileLocatorBackend);
		ctl.entrysize = sizeof(SMgrRelationData);
		SMgrRelationHash = hash_create("smgr relation table", 400,
									   &ctl, HASH_ELEM | HASH_BLOBS);
		dlist_init(&unowned_relns);
	}

	/* Look up or create an entry */
	brlocator.locator = rlocator;
	brlocator.backend = backend;
	reln = (SMgrRelation) hash_search(SMgrRelationHash,
									  &brlocator,
									  HASH_ENTER, &found);

	/* Initialize it if not present before */
	if (!found)
	{
		/* hash_search already filled in the lookup key */
		reln->smgr_owner = NULL;
		reln->smgr_targblock = InvalidBlockNumber;
		for (int i = 0; i <= MAX_FORKNUM; ++i)
			reln->smgr_cached_nblocks[i] = InvalidBlockNumber;
		reln->smgr_which = 0;	/* we only have md.c at present */

		/* implementation-specific initialization */
		smgrsw[reln->smgr_which].smgr_open(reln);

		/* it has no owner yet */
		dlist_push_tail(&unowned_relns, &reln->node);
	}

	return reln;
}

/*
 * smgrsetowner() -- Establish a long-lived reference to an SMgrRelation object
 *
 * There can be only one owner at a time; this is sufficient since currently
 * the only such owners exist in the relcache.
 */
void
smgrsetowner(SMgrRelation *owner, SMgrRelation reln)
{
	/* We don't support "disowning" an SMgrRelation here, use smgrclearowner */
	Assert(owner != NULL);

	/*
	 * First, unhook any old owner.  (Normally there shouldn't be any, but it
	 * seems possible that this can happen during swap_relation_files()
	 * depending on the order of processing.  It's ok to close the old
	 * relcache entry early in that case.)
	 *
	 * If there isn't an old owner, then the reln should be in the unowned
	 * list, and we need to remove it.
	 */
	if (reln->smgr_owner)
		*(reln->smgr_owner) = NULL;
	else
		dlist_delete(&reln->node);

	/* Now establish the ownership relationship. */
	reln->smgr_owner = owner;
	*owner = reln;
}

/*
 * smgrclearowner() -- Remove long-lived reference to an SMgrRelation object
 *					   if one exists
 */
void
smgrclearowner(SMgrRelation *owner, SMgrRelation reln)
{
	/* Do nothing if the SMgrRelation object is not owned by the owner */
	if (reln->smgr_owner != owner)
		return;

	/* unset the owner's reference */
	*owner = NULL;

	/* unset our reference to the owner */
	reln->smgr_owner = NULL;

	/* add to list of unowned relations */
	dlist_push_tail(&unowned_relns, &reln->node);
}

/*
 *	smgrexists() -- Does the underlying file for a fork exist?
 */
bool
smgrexists(SMgrRelation reln, ForkNumber forknum)
{
	return smgrsw[reln->smgr_which].smgr_exists(reln, forknum);
}

/*
 *	smgrclose() -- Close and delete an SMgrRelation object.
 */
void
smgrclose(SMgrRelation reln)
{
	SMgrRelation *owner;
	ForkNumber	forknum;

	for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
		smgrsw[reln->smgr_which].smgr_close(reln, forknum);

	owner = reln->smgr_owner;

	if (!owner)
		dlist_delete(&reln->node);

	if (hash_search(SMgrRelationHash,
					&(reln->smgr_rlocator),
					HASH_REMOVE, NULL) == NULL)
		elog(ERROR, "SMgrRelation hashtable corrupted");

	/*
	 * Unhook the owner pointer, if any.  We do this last since in the remote
	 * possibility of failure above, the SMgrRelation object will still exist.
	 */
	if (owner)
		*owner = NULL;
}

/*
 *	smgrrelease() -- Release all resources used by this object.
 *
 *	The object remains valid.
 */
void
smgrrelease(SMgrRelation reln)
{
	for (ForkNumber forknum = 0; forknum <= MAX_FORKNUM; forknum++)
	{
		smgrsw[reln->smgr_which].smgr_close(reln, forknum);
		reln->smgr_cached_nblocks[forknum] = InvalidBlockNumber;
	}
}

/*
 *	smgrreleaseall() -- Release resources used by all objects.
 *
 *	This is called for PROCSIGNAL_BARRIER_SMGRRELEASE.
 */
void
smgrreleaseall(void)
{
	HASH_SEQ_STATUS status;
	SMgrRelation reln;

	/* Nothing to do if hashtable not set up */
	if (SMgrRelationHash == NULL)
		return;

	hash_seq_init(&status, SMgrRelationHash);

	while ((reln = (SMgrRelation) hash_seq_search(&status)) != NULL)
		smgrrelease(reln);
}

/*
 *	smgrcloseall() -- Close all existing SMgrRelation objects.
 */
void
smgrcloseall(void)
{
	HASH_SEQ_STATUS status;
	SMgrRelation reln;

	/* Nothing to do if hashtable not set up */
	if (SMgrRelationHash == NULL)
		return;

	hash_seq_init(&status, SMgrRelationHash);

	while ((reln = (SMgrRelation) hash_seq_search(&status)) != NULL)
		smgrclose(reln);
}

/*
 *	smgrcloserellocator() -- Close SMgrRelation object for given RelFileLocator,
 *					   if one exists.
 *
 * This has the same effects as smgrclose(smgropen(rlocator)), but it avoids
 * uselessly creating a hashtable entry only to drop it again when no
 * such entry exists already.
 */
void
smgrcloserellocator(RelFileLocatorBackend rlocator)
{
	SMgrRelation reln;

	/* Nothing to do if hashtable not set up */
	if (SMgrRelationHash == NULL)
		return;

	reln = (SMgrRelation) hash_search(SMgrRelationHash,
									  &rlocator,
									  HASH_FIND, NULL);
	if (reln != NULL)
		smgrclose(reln);
}

/*
 *	smgrcreate() -- Create a new relation.
 *
 *		Given an already-created (but presumably unused) SMgrRelation,
 *		cause the underlying disk file or other storage for the fork
 *		to be created.
 */
void
smgrcreate(SMgrRelation reln, ForkNumber forknum, bool isRedo)
{
	smgrsw[reln->smgr_which].smgr_create(reln, forknum, isRedo);
}

/*
 *	smgrdosyncall() -- Immediately sync all forks of all given relations
 *
 *		All forks of all given relations are synced out to the store.
 *
 *		This is equivalent to FlushRelationBuffers() for each smgr relation,
 *		then calling smgrimmedsync() for all forks of each relation, but it's
 *		significantly quicker so should be preferred when possible.
 */
void
smgrdosyncall(SMgrRelation *rels, int nrels)
{
	int			i = 0;
	ForkNumber	forknum;

	if (nrels == 0)
		return;

	FlushRelationsAllBuffers(rels, nrels);

	/*
	 * Sync the physical file(s).
	 */
	for (i = 0; i < nrels; i++)
	{
		int			which = rels[i]->smgr_which;

		for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
		{
			if (smgrsw[which].smgr_exists(rels[i], forknum))
				smgrsw[which].smgr_immedsync(rels[i], forknum);
		}
	}
}

/*
 *	smgrdounlinkall() -- Immediately unlink all forks of all given relations
 *
 *		All forks of all given relations are removed from the store.  This
 *		should not be used during transactional operations, since it can't be
 *		undone.
 *
 *		If isRedo is true, it is okay for the underlying file(s) to be gone
 *		already.
 */
void
smgrdounlinkall(SMgrRelation *rels, int nrels, bool isRedo)
{
	int			i = 0;
	RelFileLocatorBackend *rlocators;
	ForkNumber	forknum;

	if (nrels == 0)
		return;

	/*
	 * Get rid of any remaining buffers for the relations.  bufmgr will just
	 * drop them without bothering to write the contents.
	 */
	DropRelationsAllBuffers(rels, nrels);

	/*
	 * create an array which contains all relations to be dropped, and close
	 * each relation's forks at the smgr level while at it
	 */
	rlocators = palloc(sizeof(RelFileLocatorBackend) * nrels);
	for (i = 0; i < nrels; i++)
	{
		RelFileLocatorBackend rlocator = rels[i]->smgr_rlocator;
		int			which = rels[i]->smgr_which;

		rlocators[i] = rlocator;

		/* Close the forks at smgr level */
		for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
			smgrsw[which].smgr_close(rels[i], forknum);
	}

	/*
	 * Send a shared-inval message to force other backends to close any
	 * dangling smgr references they may have for these rels.  We should do
	 * this before starting the actual unlinking, in case we fail partway
	 * through that step.  Note that the sinval messages will eventually come
	 * back to this backend, too, and thereby provide a backstop that we
	 * closed our own smgr rel.
	 */
	for (i = 0; i < nrels; i++)
		CacheInvalidateSmgr(rlocators[i]);

	/*
	 * Delete the physical file(s).
	 *
	 * Note: smgr_unlink must treat deletion failure as a WARNING, not an
	 * ERROR, because we've already decided to commit or abort the current
	 * xact.
	 */

	for (i = 0; i < nrels; i++)
	{
		int			which = rels[i]->smgr_which;

		for (forknum = 0; forknum <= MAX_FORKNUM; forknum++)
			smgrsw[which].smgr_unlink(rlocators[i], forknum, isRedo);
	}

	pfree(rlocators);
}


/*
 *	smgrextend() -- Add a new block to a file.
 *
 *		The semantics are nearly the same as smgrwrite(): write at the
 *		specified position.  However, this is to be used for the case of
 *		extending a relation (i.e., blocknum is at or beyond the current
 *		EOF).  Note that we assume writing a block beyond current EOF
 *		causes intervening file space to become filled with zeroes.
 */
void
smgrextend(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
		   char *buffer, bool skipFsync)
{
	smgrsw[reln->smgr_which].smgr_extend(reln, forknum, blocknum,
										 buffer, skipFsync);

	/*
	 * Normally we expect this to increase nblocks by one, but if the cached
	 * value isn't as expected, just invalidate it so the next call asks the
	 * kernel.
	 */
	if (reln->smgr_cached_nblocks[forknum] == blocknum)
		reln->smgr_cached_nblocks[forknum] = blocknum + 1;
	else
		reln->smgr_cached_nblocks[forknum] = InvalidBlockNumber;
}

/*
 *	smgrprefetch() -- Initiate asynchronous read of the specified block of a relation.
 *
 *		In recovery only, this can return false to indicate that a file
 *		doesn't	exist (presumably it has been dropped by a later WAL
 *		record).
 */
bool
smgrprefetch(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum)
{
	return smgrsw[reln->smgr_which].smgr_prefetch(reln, forknum, blocknum);
}

/*
 *	smgrread() -- read a particular block from a relation into the supplied
 *				  buffer.
 *
 *		This routine is called from the buffer manager in order to
 *		instantiate pages in the shared buffer cache.  All storage managers
 *		return pages in the format that POSTGRES expects.
 */
void
smgrread(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
		 char *buffer)
{
	smgrsw[reln->smgr_which].smgr_read(reln, forknum, blocknum, buffer);
}

/*
 *	smgrwrite() -- Write the supplied buffer out.
 *
 *		This is to be used only for updating already-existing blocks of a
 *		relation (ie, those before the current EOF).  To extend a relation,
 *		use smgrextend().
 *
 *		This is not a synchronous write -- the block is not necessarily
 *		on disk at return, only dumped out to the kernel.  However,
 *		provisions will be made to fsync the write before the next checkpoint.
 *
 *		skipFsync indicates that the caller will make other provisions to
 *		fsync the relation, so we needn't bother.  Temporary relations also
 *		do not require fsync.
 */
void
smgrwrite(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
		  char *buffer, bool skipFsync)
{
	smgrsw[reln->smgr_which].smgr_write(reln, forknum, blocknum,
										buffer, skipFsync);
}


/*
 *	smgrwriteback() -- Trigger kernel writeback for the supplied range of
 *					   blocks.
 */
void
smgrwriteback(SMgrRelation reln, ForkNumber forknum, BlockNumber blocknum,
			  BlockNumber nblocks)
{
	smgrsw[reln->smgr_which].smgr_writeback(reln, forknum, blocknum,
											nblocks);
}

/*
 *	smgrnblocks() -- Calculate the number of blocks in the
 *					 supplied relation.
 */
BlockNumber
smgrnblocks(SMgrRelation reln, ForkNumber forknum)
{
	BlockNumber result;

	/* Check and return if we get the cached value for the number of blocks. */
	result = smgrnblocks_cached(reln, forknum);
	if (result != InvalidBlockNumber)
		return result;

	result = smgrsw[reln->smgr_which].smgr_nblocks(reln, forknum);

	reln->smgr_cached_nblocks[forknum] = result;

	return result;
}

/*
 *	smgrnblocks_cached() -- Get the cached number of blocks in the supplied
 *							relation.
 *
 * Returns an InvalidBlockNumber when not in recovery and when the relation
 * fork size is not cached.
 */
BlockNumber
smgrnblocks_cached(SMgrRelation reln, ForkNumber forknum)
{
	/*
	 * For now, we only use cached values in recovery due to lack of a shared
	 * invalidation mechanism for changes in file size.
	 */
	if (InRecovery && reln->smgr_cached_nblocks[forknum] != InvalidBlockNumber)
		return reln->smgr_cached_nblocks[forknum];

	return InvalidBlockNumber;
}

/*
 *	smgrtruncate() -- Truncate the given forks of supplied relation to
 *					  each specified numbers of blocks
 *
 * The truncation is done immediately, so this can't be rolled back.
 *
 * The caller must hold AccessExclusiveLock on the relation, to ensure that
 * other backends receive the smgr invalidation event that this function sends
 * before they access any forks of the relation again.
 */
void
smgrtruncate(SMgrRelation reln, ForkNumber *forknum, int nforks, BlockNumber *nblocks)
{
	int			i;

	/*
	 * Get rid of any buffers for the about-to-be-deleted blocks. bufmgr will
	 * just drop them without bothering to write the contents.
	 */
	DropRelationBuffers(reln, forknum, nforks, nblocks);

	/*
	 * Send a shared-inval message to force other backends to close any smgr
	 * references they may have for this rel.  This is useful because they
	 * might have open file pointers to segments that got removed, and/or
	 * smgr_targblock variables pointing past the new rel end.  (The inval
	 * message will come back to our backend, too, causing a
	 * probably-unnecessary local smgr flush.  But we don't expect that this
	 * is a performance-critical path.)  As in the unlink code, we want to be
	 * sure the message is sent before we start changing things on-disk.
	 */
	CacheInvalidateSmgr(reln->smgr_rlocator);

	/* Do the truncation */
	for (i = 0; i < nforks; i++)
	{
		/* Make the cached size is invalid if we encounter an error. */
		reln->smgr_cached_nblocks[forknum[i]] = InvalidBlockNumber;

		smgrsw[reln->smgr_which].smgr_truncate(reln, forknum[i], nblocks[i]);

		/*
		 * We might as well update the local smgr_cached_nblocks values. The
		 * smgr cache inval message that this function sent will cause other
		 * backends to invalidate their copies of smgr_fsm_nblocks and
		 * smgr_vm_nblocks, and these ones too at the next command boundary.
		 * But these ensure they aren't outright wrong until then.
		 */
		reln->smgr_cached_nblocks[forknum[i]] = nblocks[i];
	}
}

/*
 *	smgrimmedsync() -- Force the specified relation to stable storage.
 *
 *		Synchronously force all previous writes to the specified relation
 *		down to disk.
 *
 *		This is useful for building completely new relations (eg, new
 *		indexes).  Instead of incrementally WAL-logging the index build
 *		steps, we can just write completed index pages to disk with smgrwrite
 *		or smgrextend, and then fsync the completed index file before
 *		committing the transaction.  (This is sufficient for purposes of
 *		crash recovery, since it effectively duplicates forcing a checkpoint
 *		for the completed index.  But it is *not* sufficient if one wishes
 *		to use the WAL log for PITR or replication purposes: in that case
 *		we have to make WAL entries as well.)
 *
 *		The preceding writes should specify skipFsync = true to avoid
 *		duplicative fsyncs.
 *
 *		Note that you need to do FlushRelationBuffers() first if there is
 *		any possibility that there are dirty buffers for the relation;
 *		otherwise the sync is not very meaningful.
 */
void
smgrimmedsync(SMgrRelation reln, ForkNumber forknum)
{
	smgrsw[reln->smgr_which].smgr_immedsync(reln, forknum);
}

/*
 * AtEOXact_SMgr
 *
 * This routine is called during transaction commit or abort (it doesn't
 * particularly care which).  All transient SMgrRelation objects are closed.
 *
 * We do this as a compromise between wanting transient SMgrRelations to
 * live awhile (to amortize the costs of blind writes of multiple blocks)
 * and needing them to not live forever (since we're probably holding open
 * a kernel file descriptor for the underlying file, and we need to ensure
 * that gets closed reasonably soon if the file gets deleted).
 */
void
AtEOXact_SMgr(void)
{
	dlist_mutable_iter iter;

	/*
	 * Zap all unowned SMgrRelations.  We rely on smgrclose() to remove each
	 * one from the list.
	 */
	dlist_foreach_modify(iter, &unowned_relns)
	{
		SMgrRelation rel = dlist_container(SMgrRelationData, node,
										   iter.cur);

		Assert(rel->smgr_owner == NULL);

		smgrclose(rel);
	}
}

/*
 * This routine is called when we are ordered to release all open files by a
 * ProcSignalBarrier.
 */
bool
ProcessBarrierSmgrRelease(void)
{
	smgrreleaseall();
	return true;
}