summaryrefslogtreecommitdiff
path: root/src/backend/access/transam/xlogfuncs.c
blob: d4e21f90a8ebc0df950cb51821fe37e71d90ebc7 (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
/*-------------------------------------------------------------------------
 *
 * xlogfuncs.c
 *
 * PostgreSQL write-ahead log manager user interface functions
 *
 * This file contains WAL control and information functions.
 *
 *
 * Portions Copyright (c) 1996-2020, PostgreSQL Global Development Group
 * Portions Copyright (c) 1994, Regents of the University of California
 *
 * src/backend/access/transam/xlogfuncs.c
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include <unistd.h>

#include "access/htup_details.h"
#include "access/xlog.h"
#include "access/xlog_internal.h"
#include "access/xlogutils.h"
#include "catalog/pg_type.h"
#include "funcapi.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "replication/walreceiver.h"
#include "storage/fd.h"
#include "storage/ipc.h"
#include "storage/smgr.h"
#include "utils/builtins.h"
#include "utils/guc.h"
#include "utils/memutils.h"
#include "utils/numeric.h"
#include "utils/pg_lsn.h"
#include "utils/timestamp.h"
#include "utils/tuplestore.h"

/*
 * Store label file and tablespace map during non-exclusive backups.
 */
static StringInfo label_file;
static StringInfo tblspc_map_file;

/*
 * pg_start_backup: set up for taking an on-line backup dump
 *
 * Essentially what this does is to create a backup label file in $PGDATA,
 * where it will be archived as part of the backup dump.  The label file
 * contains the user-supplied label string (typically this would be used
 * to tell where the backup dump will be stored) and the starting time and
 * starting WAL location for the dump.
 *
 * Permission checking for this function is managed through the normal
 * GRANT system.
 */
Datum
pg_start_backup(PG_FUNCTION_ARGS)
{
	text	   *backupid = PG_GETARG_TEXT_PP(0);
	bool		fast = PG_GETARG_BOOL(1);
	bool		exclusive = PG_GETARG_BOOL(2);
	char	   *backupidstr;
	XLogRecPtr	startpoint;
	SessionBackupState status = get_backup_status();

	backupidstr = text_to_cstring(backupid);

	if (status == SESSION_BACKUP_NON_EXCLUSIVE)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("a backup is already in progress in this session")));

	if (exclusive)
	{
		startpoint = do_pg_start_backup(backupidstr, fast, NULL, NULL,
										NULL, NULL, false, true);
	}
	else
	{
		MemoryContext oldcontext;

		/*
		 * Label file and tablespace map file need to be long-lived, since
		 * they are read in pg_stop_backup.
		 */
		oldcontext = MemoryContextSwitchTo(TopMemoryContext);
		label_file = makeStringInfo();
		tblspc_map_file = makeStringInfo();
		MemoryContextSwitchTo(oldcontext);

		register_persistent_abort_backup_handler();

		startpoint = do_pg_start_backup(backupidstr, fast, NULL, label_file,
										NULL, tblspc_map_file, false, true);
	}

	PG_RETURN_LSN(startpoint);
}

/*
 * pg_stop_backup: finish taking an on-line backup dump
 *
 * We write an end-of-backup WAL record, and remove the backup label file
 * created by pg_start_backup, creating a backup history file in pg_wal
 * instead (whence it will immediately be archived). The backup history file
 * contains the same info found in the label file, plus the backup-end time
 * and WAL location. Before 9.0, the backup-end time was read from the backup
 * history file at the beginning of archive recovery, but we now use the WAL
 * record for that and the file is for informational and debug purposes only.
 *
 * Note: different from CancelBackup which just cancels online backup mode.
 *
 * Note: this version is only called to stop an exclusive backup. The function
 *		 pg_stop_backup_v2 (overloaded as pg_stop_backup in SQL) is called to
 *		 stop non-exclusive backups.
 *
 * Permission checking for this function is managed through the normal
 * GRANT system.
 */
Datum
pg_stop_backup(PG_FUNCTION_ARGS)
{
	XLogRecPtr	stoppoint;
	SessionBackupState status = get_backup_status();

	if (status == SESSION_BACKUP_NON_EXCLUSIVE)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("non-exclusive backup in progress"),
				 errhint("Did you mean to use pg_stop_backup('f')?")));

	/*
	 * Exclusive backups were typically started in a different connection, so
	 * don't try to verify that status of backup is set to
	 * SESSION_BACKUP_EXCLUSIVE in this function. Actual verification that an
	 * exclusive backup is in fact running is handled inside
	 * do_pg_stop_backup.
	 */
	stoppoint = do_pg_stop_backup(NULL, true, NULL);

	PG_RETURN_LSN(stoppoint);
}


/*
 * pg_stop_backup_v2: finish taking exclusive or nonexclusive on-line backup.
 *
 * Works the same as pg_stop_backup, except for non-exclusive backups it returns
 * the backup label and tablespace map files as text fields in as part of the
 * resultset.
 *
 * The first parameter (variable 'exclusive') allows the user to tell us if
 * this is an exclusive or a non-exclusive backup.
 *
 * The second parameter (variable 'waitforarchive'), which is optional,
 * allows the user to choose if they want to wait for the WAL to be archived
 * or if we should just return as soon as the WAL record is written.
 *
 * Permission checking for this function is managed through the normal
 * GRANT system.
 */
Datum
pg_stop_backup_v2(PG_FUNCTION_ARGS)
{
	ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
	TupleDesc	tupdesc;
	Tuplestorestate *tupstore;
	MemoryContext per_query_ctx;
	MemoryContext oldcontext;
	Datum		values[3];
	bool		nulls[3];

	bool		exclusive = PG_GETARG_BOOL(0);
	bool		waitforarchive = PG_GETARG_BOOL(1);
	XLogRecPtr	stoppoint;
	SessionBackupState status = get_backup_status();

	/* check to see if caller supports us returning a tuplestore */
	if (rsinfo == NULL || !IsA(rsinfo, ReturnSetInfo))
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 errmsg("set-valued function called in context that cannot accept a set")));
	if (!(rsinfo->allowedModes & SFRM_Materialize))
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 errmsg("materialize mode required, but it is not allowed in this context")));

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

	per_query_ctx = rsinfo->econtext->ecxt_per_query_memory;
	oldcontext = MemoryContextSwitchTo(per_query_ctx);

	tupstore = tuplestore_begin_heap(true, false, work_mem);
	rsinfo->returnMode = SFRM_Materialize;
	rsinfo->setResult = tupstore;
	rsinfo->setDesc = tupdesc;

	MemoryContextSwitchTo(oldcontext);

	MemSet(values, 0, sizeof(values));
	MemSet(nulls, 0, sizeof(nulls));

	if (exclusive)
	{
		if (status == SESSION_BACKUP_NON_EXCLUSIVE)
			ereport(ERROR,
					(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
					 errmsg("non-exclusive backup in progress"),
					 errhint("Did you mean to use pg_stop_backup('f')?")));

		/*
		 * Stop the exclusive backup, and since we're in an exclusive backup
		 * return NULL for both backup_label and tablespace_map.
		 */
		stoppoint = do_pg_stop_backup(NULL, waitforarchive, NULL);

		nulls[1] = true;
		nulls[2] = true;
	}
	else
	{
		if (status != SESSION_BACKUP_NON_EXCLUSIVE)
			ereport(ERROR,
					(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
					 errmsg("non-exclusive backup is not in progress"),
					 errhint("Did you mean to use pg_stop_backup('t')?")));

		/*
		 * Stop the non-exclusive backup. Return a copy of the backup label
		 * and tablespace map so they can be written to disk by the caller.
		 */
		stoppoint = do_pg_stop_backup(label_file->data, waitforarchive, NULL);

		values[1] = CStringGetTextDatum(label_file->data);
		values[2] = CStringGetTextDatum(tblspc_map_file->data);

		/* Free structures allocated in TopMemoryContext */
		pfree(label_file->data);
		pfree(label_file);
		label_file = NULL;
		pfree(tblspc_map_file->data);
		pfree(tblspc_map_file);
		tblspc_map_file = NULL;
	}

	/* Stoppoint is included on both exclusive and nonexclusive backups */
	values[0] = LSNGetDatum(stoppoint);

	tuplestore_putvalues(tupstore, tupdesc, values, nulls);
	tuplestore_donestoring(tupstore);

	return (Datum) 0;
}

/*
 * pg_switch_wal: switch to next xlog file
 *
 * Permission checking for this function is managed through the normal
 * GRANT system.
 */
Datum
pg_switch_wal(PG_FUNCTION_ARGS)
{
	XLogRecPtr	switchpoint;

	if (RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is in progress"),
				 errhint("WAL control functions cannot be executed during recovery.")));

	switchpoint = RequestXLogSwitch(false);

	/*
	 * As a convenience, return the WAL location of the switch record
	 */
	PG_RETURN_LSN(switchpoint);
}

/*
 * pg_create_restore_point: a named point for restore
 *
 * Permission checking for this function is managed through the normal
 * GRANT system.
 */
Datum
pg_create_restore_point(PG_FUNCTION_ARGS)
{
	text	   *restore_name = PG_GETARG_TEXT_PP(0);
	char	   *restore_name_str;
	XLogRecPtr	restorepoint;

	if (RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 (errmsg("recovery is in progress"),
				  errhint("WAL control functions cannot be executed during recovery."))));

	if (!XLogIsNeeded())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("WAL level not sufficient for creating a restore point"),
				 errhint("wal_level must be set to \"replica\" or \"logical\" at server start.")));

	restore_name_str = text_to_cstring(restore_name);

	if (strlen(restore_name_str) >= MAXFNAMELEN)
		ereport(ERROR,
				(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
				 errmsg("value too long for restore point (maximum %d characters)", MAXFNAMELEN - 1)));

	restorepoint = XLogRestorePoint(restore_name_str);

	/*
	 * As a convenience, return the WAL location of the restore point record
	 */
	PG_RETURN_LSN(restorepoint);
}

/*
 * Report the current WAL write location (same format as pg_start_backup etc)
 *
 * This is useful for determining how much of WAL is visible to an external
 * archiving process.  Note that the data before this point is written out
 * to the kernel, but is not necessarily synced to disk.
 */
Datum
pg_current_wal_lsn(PG_FUNCTION_ARGS)
{
	XLogRecPtr	current_recptr;

	if (RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is in progress"),
				 errhint("WAL control functions cannot be executed during recovery.")));

	current_recptr = GetXLogWriteRecPtr();

	PG_RETURN_LSN(current_recptr);
}

/*
 * Report the current WAL insert location (same format as pg_start_backup etc)
 *
 * This function is mostly for debugging purposes.
 */
Datum
pg_current_wal_insert_lsn(PG_FUNCTION_ARGS)
{
	XLogRecPtr	current_recptr;

	if (RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is in progress"),
				 errhint("WAL control functions cannot be executed during recovery.")));

	current_recptr = GetXLogInsertRecPtr();

	PG_RETURN_LSN(current_recptr);
}

/*
 * Report the current WAL flush location (same format as pg_start_backup etc)
 *
 * This function is mostly for debugging purposes.
 */
Datum
pg_current_wal_flush_lsn(PG_FUNCTION_ARGS)
{
	XLogRecPtr	current_recptr;

	if (RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is in progress"),
				 errhint("WAL control functions cannot be executed during recovery.")));

	current_recptr = GetFlushRecPtr();

	PG_RETURN_LSN(current_recptr);
}

/*
 * Report the last WAL receive location (same format as pg_start_backup etc)
 *
 * This is useful for determining how much of WAL is guaranteed to be received
 * and synced to disk by walreceiver.
 */
Datum
pg_last_wal_receive_lsn(PG_FUNCTION_ARGS)
{
	XLogRecPtr	recptr;

	recptr = GetWalRcvWriteRecPtr(NULL, NULL);

	if (recptr == 0)
		PG_RETURN_NULL();

	PG_RETURN_LSN(recptr);
}

/*
 * Report the last WAL replay location (same format as pg_start_backup etc)
 *
 * This is useful for determining how much of WAL is visible to read-only
 * connections during recovery.
 */
Datum
pg_last_wal_replay_lsn(PG_FUNCTION_ARGS)
{
	XLogRecPtr	recptr;

	recptr = GetXLogReplayRecPtr(NULL);

	if (recptr == 0)
		PG_RETURN_NULL();

	PG_RETURN_LSN(recptr);
}

/*
 * Compute an xlog file name and decimal byte offset given a WAL location,
 * such as is returned by pg_stop_backup() or pg_switch_wal().
 *
 * Note that a location exactly at a segment boundary is taken to be in
 * the previous segment.  This is usually the right thing, since the
 * expected usage is to determine which xlog file(s) are ready to archive.
 */
Datum
pg_walfile_name_offset(PG_FUNCTION_ARGS)
{
	XLogSegNo	xlogsegno;
	uint32		xrecoff;
	XLogRecPtr	locationpoint = PG_GETARG_LSN(0);
	char		xlogfilename[MAXFNAMELEN];
	Datum		values[2];
	bool		isnull[2];
	TupleDesc	resultTupleDesc;
	HeapTuple	resultHeapTuple;
	Datum		result;

	if (RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is in progress"),
				 errhint("%s cannot be executed during recovery.",
						 "pg_walfile_name_offset()")));

	/*
	 * Construct a tuple descriptor for the result row.  This must match this
	 * function's pg_proc entry!
	 */
	resultTupleDesc = CreateTemplateTupleDesc(2);
	TupleDescInitEntry(resultTupleDesc, (AttrNumber) 1, "file_name",
					   TEXTOID, -1, 0);
	TupleDescInitEntry(resultTupleDesc, (AttrNumber) 2, "file_offset",
					   INT4OID, -1, 0);

	resultTupleDesc = BlessTupleDesc(resultTupleDesc);

	/*
	 * xlogfilename
	 */
	XLByteToPrevSeg(locationpoint, xlogsegno, wal_segment_size);
	XLogFileName(xlogfilename, ThisTimeLineID, xlogsegno, wal_segment_size);

	values[0] = CStringGetTextDatum(xlogfilename);
	isnull[0] = false;

	/*
	 * offset
	 */
	xrecoff = XLogSegmentOffset(locationpoint, wal_segment_size);

	values[1] = UInt32GetDatum(xrecoff);
	isnull[1] = false;

	/*
	 * Tuple jam: Having first prepared your Datums, then squash together
	 */
	resultHeapTuple = heap_form_tuple(resultTupleDesc, values, isnull);

	result = HeapTupleGetDatum(resultHeapTuple);

	PG_RETURN_DATUM(result);
}

/*
 * Compute an xlog file name given a WAL location,
 * such as is returned by pg_stop_backup() or pg_switch_wal().
 */
Datum
pg_walfile_name(PG_FUNCTION_ARGS)
{
	XLogSegNo	xlogsegno;
	XLogRecPtr	locationpoint = PG_GETARG_LSN(0);
	char		xlogfilename[MAXFNAMELEN];

	if (RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is in progress"),
				 errhint("%s cannot be executed during recovery.",
						 "pg_walfile_name()")));

	XLByteToPrevSeg(locationpoint, xlogsegno, wal_segment_size);
	XLogFileName(xlogfilename, ThisTimeLineID, xlogsegno, wal_segment_size);

	PG_RETURN_TEXT_P(cstring_to_text(xlogfilename));
}

/*
 * pg_wal_replay_pause - pause recovery now
 *
 * Permission checking for this function is managed through the normal
 * GRANT system.
 */
Datum
pg_wal_replay_pause(PG_FUNCTION_ARGS)
{
	if (!RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is not in progress"),
				 errhint("Recovery control functions can only be executed during recovery.")));

	SetRecoveryPause(true);

	PG_RETURN_VOID();
}

/*
 * pg_wal_replay_resume - resume recovery now
 *
 * Permission checking for this function is managed through the normal
 * GRANT system.
 */
Datum
pg_wal_replay_resume(PG_FUNCTION_ARGS)
{
	if (!RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is not in progress"),
				 errhint("Recovery control functions can only be executed during recovery.")));

	SetRecoveryPause(false);

	PG_RETURN_VOID();
}

/*
 * pg_is_wal_replay_paused
 */
Datum
pg_is_wal_replay_paused(PG_FUNCTION_ARGS)
{
	if (!RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is not in progress"),
				 errhint("Recovery control functions can only be executed during recovery.")));

	PG_RETURN_BOOL(RecoveryIsPaused());
}

/*
 * Returns timestamp of latest processed commit/abort record.
 *
 * When the server has been started normally without recovery the function
 * returns NULL.
 */
Datum
pg_last_xact_replay_timestamp(PG_FUNCTION_ARGS)
{
	TimestampTz xtime;

	xtime = GetLatestXTime();
	if (xtime == 0)
		PG_RETURN_NULL();

	PG_RETURN_TIMESTAMPTZ(xtime);
}

/*
 * Returns bool with current recovery mode, a global state.
 */
Datum
pg_is_in_recovery(PG_FUNCTION_ARGS)
{
	PG_RETURN_BOOL(RecoveryInProgress());
}

/*
 * Compute the difference in bytes between two WAL locations.
 */
Datum
pg_wal_lsn_diff(PG_FUNCTION_ARGS)
{
	Datum		result;

	result = DirectFunctionCall2(pg_lsn_mi,
								 PG_GETARG_DATUM(0),
								 PG_GETARG_DATUM(1));

	PG_RETURN_NUMERIC(result);
}

/*
 * Returns bool with current on-line backup mode, a global state.
 */
Datum
pg_is_in_backup(PG_FUNCTION_ARGS)
{
	PG_RETURN_BOOL(BackupInProgress());
}

/*
 * Returns start time of an online exclusive backup.
 *
 * When there's no exclusive backup in progress, the function
 * returns NULL.
 */
Datum
pg_backup_start_time(PG_FUNCTION_ARGS)
{
	Datum		xtime;
	FILE	   *lfp;
	char		fline[MAXPGPATH];
	char		backup_start_time[30];

	/*
	 * See if label file is present
	 */
	lfp = AllocateFile(BACKUP_LABEL_FILE, "r");
	if (lfp == NULL)
	{
		if (errno != ENOENT)
			ereport(ERROR,
					(errcode_for_file_access(),
					 errmsg("could not read file \"%s\": %m",
							BACKUP_LABEL_FILE)));
		PG_RETURN_NULL();
	}

	/*
	 * Parse the file to find the START TIME line.
	 */
	backup_start_time[0] = '\0';
	while (fgets(fline, sizeof(fline), lfp) != NULL)
	{
		if (sscanf(fline, "START TIME: %25[^\n]\n", backup_start_time) == 1)
			break;
	}

	/* Check for a read error. */
	if (ferror(lfp))
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not read file \"%s\": %m", BACKUP_LABEL_FILE)));

	/* Close the backup label file. */
	if (FreeFile(lfp))
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not close file \"%s\": %m", BACKUP_LABEL_FILE)));

	if (strlen(backup_start_time) == 0)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("invalid data in file \"%s\"", BACKUP_LABEL_FILE)));

	/*
	 * Convert the time string read from file to TimestampTz form.
	 */
	xtime = DirectFunctionCall3(timestamptz_in,
								CStringGetDatum(backup_start_time),
								ObjectIdGetDatum(InvalidOid),
								Int32GetDatum(-1));

	PG_RETURN_DATUM(xtime);
}

/*
 * Promotes a standby server.
 *
 * A result of "true" means that promotion has been completed if "wait" is
 * "true", or initiated if "wait" is false.
 */
Datum
pg_promote(PG_FUNCTION_ARGS)
{
	bool		wait = PG_GETARG_BOOL(0);
	int			wait_seconds = PG_GETARG_INT32(1);
	FILE	   *promote_file;
	int			i;

	if (!RecoveryInProgress())
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("recovery is not in progress"),
				 errhint("Recovery control functions can only be executed during recovery.")));

	if (wait_seconds <= 0)
		ereport(ERROR,
				(errcode(ERRCODE_NUMERIC_VALUE_OUT_OF_RANGE),
				 errmsg("\"wait_seconds\" must not be negative or zero")));

	/* create the promote signal file */
	promote_file = AllocateFile(PROMOTE_SIGNAL_FILE, "w");
	if (!promote_file)
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not create file \"%s\": %m",
						PROMOTE_SIGNAL_FILE)));

	if (FreeFile(promote_file))
		ereport(ERROR,
				(errcode_for_file_access(),
				 errmsg("could not write file \"%s\": %m",
						PROMOTE_SIGNAL_FILE)));

	/* signal the postmaster */
	if (kill(PostmasterPid, SIGUSR1) != 0)
	{
		ereport(WARNING,
				(errmsg("failed to send signal to postmaster: %m")));
		(void) unlink(PROMOTE_SIGNAL_FILE);
		PG_RETURN_BOOL(false);
	}

	/* return immediately if waiting was not requested */
	if (!wait)
		PG_RETURN_BOOL(true);

	/* wait for the amount of time wanted until promotion */
#define WAITS_PER_SECOND 10
	for (i = 0; i < WAITS_PER_SECOND * wait_seconds; i++)
	{
		int			rc;

		ResetLatch(MyLatch);

		if (!RecoveryInProgress())
			PG_RETURN_BOOL(true);

		CHECK_FOR_INTERRUPTS();

		rc = WaitLatch(MyLatch,
					   WL_LATCH_SET | WL_TIMEOUT | WL_POSTMASTER_DEATH,
					   1000L / WAITS_PER_SECOND,
					   WAIT_EVENT_PROMOTE);

		/*
		 * Emergency bailout if postmaster has died.  This is to avoid the
		 * necessity for manual cleanup of all postmaster children.
		 */
		if (rc & WL_POSTMASTER_DEATH)
			PG_RETURN_BOOL(false);
	}

	ereport(WARNING,
			(errmsg("server did not promote within %d seconds", wait_seconds)));
	PG_RETURN_BOOL(false);
}