summaryrefslogtreecommitdiffstats
path: root/src/backend/replication/slotfuncs.c
blob: 16a35279037657bada54d27d4a3ab2e38d1b2de7 (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
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
/*-------------------------------------------------------------------------
 *
 * slotfuncs.c
 *	   Support functions for replication slots
 *
 * Copyright (c) 2012-2022, PostgreSQL Global Development Group
 *
 * IDENTIFICATION
 *	  src/backend/replication/slotfuncs.c
 *
 *-------------------------------------------------------------------------
 */
#include "postgres.h"

#include "access/htup_details.h"
#include "access/xlog_internal.h"
#include "access/xlogrecovery.h"
#include "access/xlogutils.h"
#include "funcapi.h"
#include "miscadmin.h"
#include "replication/decode.h"
#include "replication/logical.h"
#include "replication/slot.h"
#include "utils/builtins.h"
#include "utils/inval.h"
#include "utils/pg_lsn.h"
#include "utils/resowner.h"

/*
 * Helper function for creating a new physical replication slot with
 * given arguments. Note that this function doesn't release the created
 * slot.
 *
 * If restart_lsn is a valid value, we use it without WAL reservation
 * routine. So the caller must guarantee that WAL is available.
 */
static void
create_physical_replication_slot(char *name, bool immediately_reserve,
								 bool temporary, XLogRecPtr restart_lsn)
{
	Assert(!MyReplicationSlot);

	/* acquire replication slot, this will check for conflicting names */
	ReplicationSlotCreate(name, false,
						  temporary ? RS_TEMPORARY : RS_PERSISTENT, false);

	if (immediately_reserve)
	{
		/* Reserve WAL as the user asked for it */
		if (XLogRecPtrIsInvalid(restart_lsn))
			ReplicationSlotReserveWal();
		else
			MyReplicationSlot->data.restart_lsn = restart_lsn;

		/* Write this slot to disk */
		ReplicationSlotMarkDirty();
		ReplicationSlotSave();
	}
}

/*
 * SQL function for creating a new physical (streaming replication)
 * replication slot.
 */
Datum
pg_create_physical_replication_slot(PG_FUNCTION_ARGS)
{
	Name		name = PG_GETARG_NAME(0);
	bool		immediately_reserve = PG_GETARG_BOOL(1);
	bool		temporary = PG_GETARG_BOOL(2);
	Datum		values[2];
	bool		nulls[2];
	TupleDesc	tupdesc;
	HeapTuple	tuple;
	Datum		result;

	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
		elog(ERROR, "return type must be a row type");

	CheckSlotPermissions();

	CheckSlotRequirements();

	create_physical_replication_slot(NameStr(*name),
									 immediately_reserve,
									 temporary,
									 InvalidXLogRecPtr);

	values[0] = NameGetDatum(&MyReplicationSlot->data.name);
	nulls[0] = false;

	if (immediately_reserve)
	{
		values[1] = LSNGetDatum(MyReplicationSlot->data.restart_lsn);
		nulls[1] = false;
	}
	else
		nulls[1] = true;

	tuple = heap_form_tuple(tupdesc, values, nulls);
	result = HeapTupleGetDatum(tuple);

	ReplicationSlotRelease();

	PG_RETURN_DATUM(result);
}


/*
 * Helper function for creating a new logical replication slot with
 * given arguments. Note that this function doesn't release the created
 * slot.
 *
 * When find_startpoint is false, the slot's confirmed_flush is not set; it's
 * caller's responsibility to ensure it's set to something sensible.
 */
static void
create_logical_replication_slot(char *name, char *plugin,
								bool temporary, bool two_phase,
								XLogRecPtr restart_lsn,
								bool find_startpoint)
{
	LogicalDecodingContext *ctx = NULL;

	Assert(!MyReplicationSlot);

	/*
	 * Acquire a logical decoding slot, this will check for conflicting names.
	 * Initially create persistent slot as ephemeral - that allows us to
	 * nicely handle errors during initialization because it'll get dropped if
	 * this transaction fails. We'll make it persistent at the end. Temporary
	 * slots can be created as temporary from beginning as they get dropped on
	 * error as well.
	 */
	ReplicationSlotCreate(name, true,
						  temporary ? RS_TEMPORARY : RS_EPHEMERAL, two_phase);

	/*
	 * Create logical decoding context to find start point or, if we don't
	 * need it, to 1) bump slot's restart_lsn and xmin 2) check plugin sanity.
	 *
	 * Note: when !find_startpoint this is still important, because it's at
	 * this point that the output plugin is validated.
	 */
	ctx = CreateInitDecodingContext(plugin, NIL,
									false,	/* just catalogs is OK */
									restart_lsn,
									XL_ROUTINE(.page_read = read_local_xlog_page,
											   .segment_open = wal_segment_open,
											   .segment_close = wal_segment_close),
									NULL, NULL, NULL);

	/*
	 * If caller needs us to determine the decoding start point, do so now.
	 * This might take a while.
	 */
	if (find_startpoint)
		DecodingContextFindStartpoint(ctx);

	/* don't need the decoding context anymore */
	FreeDecodingContext(ctx);
}

/*
 * SQL function for creating a new logical replication slot.
 */
Datum
pg_create_logical_replication_slot(PG_FUNCTION_ARGS)
{
	Name		name = PG_GETARG_NAME(0);
	Name		plugin = PG_GETARG_NAME(1);
	bool		temporary = PG_GETARG_BOOL(2);
	bool		two_phase = PG_GETARG_BOOL(3);
	Datum		result;
	TupleDesc	tupdesc;
	HeapTuple	tuple;
	Datum		values[2];
	bool		nulls[2];

	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
		elog(ERROR, "return type must be a row type");

	CheckSlotPermissions();

	CheckLogicalDecodingRequirements();

	create_logical_replication_slot(NameStr(*name),
									NameStr(*plugin),
									temporary,
									two_phase,
									InvalidXLogRecPtr,
									true);

	values[0] = NameGetDatum(&MyReplicationSlot->data.name);
	values[1] = LSNGetDatum(MyReplicationSlot->data.confirmed_flush);

	memset(nulls, 0, sizeof(nulls));

	tuple = heap_form_tuple(tupdesc, values, nulls);
	result = HeapTupleGetDatum(tuple);

	/* ok, slot is now fully created, mark it as persistent if needed */
	if (!temporary)
		ReplicationSlotPersist();
	ReplicationSlotRelease();

	PG_RETURN_DATUM(result);
}


/*
 * SQL function for dropping a replication slot.
 */
Datum
pg_drop_replication_slot(PG_FUNCTION_ARGS)
{
	Name		name = PG_GETARG_NAME(0);

	CheckSlotPermissions();

	CheckSlotRequirements();

	ReplicationSlotDrop(NameStr(*name), true);

	PG_RETURN_VOID();
}

/*
 * pg_get_replication_slots - SQL SRF showing active replication slots.
 */
Datum
pg_get_replication_slots(PG_FUNCTION_ARGS)
{
#define PG_GET_REPLICATION_SLOTS_COLS 14
	ReturnSetInfo *rsinfo = (ReturnSetInfo *) fcinfo->resultinfo;
	XLogRecPtr	currlsn;
	int			slotno;

	/*
	 * We don't require any special permission to see this function's data
	 * because nothing should be sensitive. The most critical being the slot
	 * name, which shouldn't contain anything particularly sensitive.
	 */

	InitMaterializedSRF(fcinfo, 0);

	currlsn = GetXLogWriteRecPtr();

	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);
	for (slotno = 0; slotno < max_replication_slots; slotno++)
	{
		ReplicationSlot *slot = &ReplicationSlotCtl->replication_slots[slotno];
		ReplicationSlot slot_contents;
		Datum		values[PG_GET_REPLICATION_SLOTS_COLS];
		bool		nulls[PG_GET_REPLICATION_SLOTS_COLS];
		WALAvailability walstate;
		int			i;

		if (!slot->in_use)
			continue;

		/* Copy slot contents while holding spinlock, then examine at leisure */
		SpinLockAcquire(&slot->mutex);
		slot_contents = *slot;
		SpinLockRelease(&slot->mutex);

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

		i = 0;
		values[i++] = NameGetDatum(&slot_contents.data.name);

		if (slot_contents.data.database == InvalidOid)
			nulls[i++] = true;
		else
			values[i++] = NameGetDatum(&slot_contents.data.plugin);

		if (slot_contents.data.database == InvalidOid)
			values[i++] = CStringGetTextDatum("physical");
		else
			values[i++] = CStringGetTextDatum("logical");

		if (slot_contents.data.database == InvalidOid)
			nulls[i++] = true;
		else
			values[i++] = ObjectIdGetDatum(slot_contents.data.database);

		values[i++] = BoolGetDatum(slot_contents.data.persistency == RS_TEMPORARY);
		values[i++] = BoolGetDatum(slot_contents.active_pid != 0);

		if (slot_contents.active_pid != 0)
			values[i++] = Int32GetDatum(slot_contents.active_pid);
		else
			nulls[i++] = true;

		if (slot_contents.data.xmin != InvalidTransactionId)
			values[i++] = TransactionIdGetDatum(slot_contents.data.xmin);
		else
			nulls[i++] = true;

		if (slot_contents.data.catalog_xmin != InvalidTransactionId)
			values[i++] = TransactionIdGetDatum(slot_contents.data.catalog_xmin);
		else
			nulls[i++] = true;

		if (slot_contents.data.restart_lsn != InvalidXLogRecPtr)
			values[i++] = LSNGetDatum(slot_contents.data.restart_lsn);
		else
			nulls[i++] = true;

		if (slot_contents.data.confirmed_flush != InvalidXLogRecPtr)
			values[i++] = LSNGetDatum(slot_contents.data.confirmed_flush);
		else
			nulls[i++] = true;

		/*
		 * If invalidated_at is valid and restart_lsn is invalid, we know for
		 * certain that the slot has been invalidated.  Otherwise, test
		 * availability from restart_lsn.
		 */
		if (XLogRecPtrIsInvalid(slot_contents.data.restart_lsn) &&
			!XLogRecPtrIsInvalid(slot_contents.data.invalidated_at))
			walstate = WALAVAIL_REMOVED;
		else
			walstate = GetWALAvailability(slot_contents.data.restart_lsn);

		switch (walstate)
		{
			case WALAVAIL_INVALID_LSN:
				nulls[i++] = true;
				break;

			case WALAVAIL_RESERVED:
				values[i++] = CStringGetTextDatum("reserved");
				break;

			case WALAVAIL_EXTENDED:
				values[i++] = CStringGetTextDatum("extended");
				break;

			case WALAVAIL_UNRESERVED:
				values[i++] = CStringGetTextDatum("unreserved");
				break;

			case WALAVAIL_REMOVED:

				/*
				 * If we read the restart_lsn long enough ago, maybe that file
				 * has been removed by now.  However, the walsender could have
				 * moved forward enough that it jumped to another file after
				 * we looked.  If checkpointer signalled the process to
				 * termination, then it's definitely lost; but if a process is
				 * still alive, then "unreserved" seems more appropriate.
				 *
				 * If we do change it, save the state for safe_wal_size below.
				 */
				if (!XLogRecPtrIsInvalid(slot_contents.data.restart_lsn))
				{
					int			pid;

					SpinLockAcquire(&slot->mutex);
					pid = slot->active_pid;
					slot_contents.data.restart_lsn = slot->data.restart_lsn;
					SpinLockRelease(&slot->mutex);
					if (pid != 0)
					{
						values[i++] = CStringGetTextDatum("unreserved");
						walstate = WALAVAIL_UNRESERVED;
						break;
					}
				}
				values[i++] = CStringGetTextDatum("lost");
				break;
		}

		/*
		 * safe_wal_size is only computed for slots that have not been lost,
		 * and only if there's a configured maximum size.
		 */
		if (walstate == WALAVAIL_REMOVED || max_slot_wal_keep_size_mb < 0)
			nulls[i++] = true;
		else
		{
			XLogSegNo	targetSeg;
			uint64		slotKeepSegs;
			uint64		keepSegs;
			XLogSegNo	failSeg;
			XLogRecPtr	failLSN;

			XLByteToSeg(slot_contents.data.restart_lsn, targetSeg, wal_segment_size);

			/* determine how many segments can be kept by slots */
			slotKeepSegs = XLogMBVarToSegs(max_slot_wal_keep_size_mb, wal_segment_size);
			/* ditto for wal_keep_size */
			keepSegs = XLogMBVarToSegs(wal_keep_size_mb, wal_segment_size);

			/* if currpos reaches failLSN, we lose our segment */
			failSeg = targetSeg + Max(slotKeepSegs, keepSegs) + 1;
			XLogSegNoOffsetToRecPtr(failSeg, 0, wal_segment_size, failLSN);

			values[i++] = Int64GetDatum(failLSN - currlsn);
		}

		values[i++] = BoolGetDatum(slot_contents.data.two_phase);

		Assert(i == PG_GET_REPLICATION_SLOTS_COLS);

		tuplestore_putvalues(rsinfo->setResult, rsinfo->setDesc,
							 values, nulls);
	}

	LWLockRelease(ReplicationSlotControlLock);

	return (Datum) 0;
}

/*
 * Helper function for advancing our physical replication slot forward.
 *
 * The LSN position to move to is compared simply to the slot's restart_lsn,
 * knowing that any position older than that would be removed by successive
 * checkpoints.
 */
static XLogRecPtr
pg_physical_replication_slot_advance(XLogRecPtr moveto)
{
	XLogRecPtr	startlsn = MyReplicationSlot->data.restart_lsn;
	XLogRecPtr	retlsn = startlsn;

	Assert(moveto != InvalidXLogRecPtr);

	if (startlsn < moveto)
	{
		SpinLockAcquire(&MyReplicationSlot->mutex);
		MyReplicationSlot->data.restart_lsn = moveto;
		SpinLockRelease(&MyReplicationSlot->mutex);
		retlsn = moveto;

		/*
		 * Dirty the slot so as it is written out at the next checkpoint. Note
		 * that the LSN position advanced may still be lost in the event of a
		 * crash, but this makes the data consistent after a clean shutdown.
		 */
		ReplicationSlotMarkDirty();
	}

	return retlsn;
}

/*
 * Helper function for advancing our logical replication slot forward.
 *
 * The slot's restart_lsn is used as start point for reading records, while
 * confirmed_flush is used as base point for the decoding context.
 *
 * We cannot just do LogicalConfirmReceivedLocation to update confirmed_flush,
 * because we need to digest WAL to advance restart_lsn allowing to recycle
 * WAL and removal of old catalog tuples.  As decoding is done in fast_forward
 * mode, no changes are generated anyway.
 */
static XLogRecPtr
pg_logical_replication_slot_advance(XLogRecPtr moveto)
{
	LogicalDecodingContext *ctx;
	ResourceOwner old_resowner = CurrentResourceOwner;
	XLogRecPtr	retlsn;

	Assert(moveto != InvalidXLogRecPtr);

	PG_TRY();
	{
		/*
		 * Create our decoding context in fast_forward mode, passing start_lsn
		 * as InvalidXLogRecPtr, so that we start processing from my slot's
		 * confirmed_flush.
		 */
		ctx = CreateDecodingContext(InvalidXLogRecPtr,
									NIL,
									true,	/* fast_forward */
									XL_ROUTINE(.page_read = read_local_xlog_page,
											   .segment_open = wal_segment_open,
											   .segment_close = wal_segment_close),
									NULL, NULL, NULL);

		/*
		 * Start reading at the slot's restart_lsn, which we know to point to
		 * a valid record.
		 */
		XLogBeginRead(ctx->reader, MyReplicationSlot->data.restart_lsn);

		/* invalidate non-timetravel entries */
		InvalidateSystemCaches();

		/* Decode at least one record, until we run out of records */
		while (ctx->reader->EndRecPtr < moveto)
		{
			char	   *errm = NULL;
			XLogRecord *record;

			/*
			 * Read records.  No changes are generated in fast_forward mode,
			 * but snapbuilder/slot statuses are updated properly.
			 */
			record = XLogReadRecord(ctx->reader, &errm);
			if (errm)
				elog(ERROR, "could not find record while advancing replication slot: %s",
					 errm);

			/*
			 * Process the record.  Storage-level changes are ignored in
			 * fast_forward mode, but other modules (such as snapbuilder)
			 * might still have critical updates to do.
			 */
			if (record)
				LogicalDecodingProcessRecord(ctx, ctx->reader);

			/* Stop once the requested target has been reached */
			if (moveto <= ctx->reader->EndRecPtr)
				break;

			CHECK_FOR_INTERRUPTS();
		}

		/*
		 * Logical decoding could have clobbered CurrentResourceOwner during
		 * transaction management, so restore the executor's value.  (This is
		 * a kluge, but it's not worth cleaning up right now.)
		 */
		CurrentResourceOwner = old_resowner;

		if (ctx->reader->EndRecPtr != InvalidXLogRecPtr)
		{
			LogicalConfirmReceivedLocation(moveto);

			/*
			 * If only the confirmed_flush LSN has changed the slot won't get
			 * marked as dirty by the above. Callers on the walsender
			 * interface are expected to keep track of their own progress and
			 * don't need it written out. But SQL-interface users cannot
			 * specify their own start positions and it's harder for them to
			 * keep track of their progress, so we should make more of an
			 * effort to save it for them.
			 *
			 * Dirty the slot so it is written out at the next checkpoint. The
			 * LSN position advanced to may still be lost on a crash but this
			 * makes the data consistent after a clean shutdown.
			 */
			ReplicationSlotMarkDirty();
		}

		retlsn = MyReplicationSlot->data.confirmed_flush;

		/* free context, call shutdown callback */
		FreeDecodingContext(ctx);

		InvalidateSystemCaches();
	}
	PG_CATCH();
	{
		/* clear all timetravel entries */
		InvalidateSystemCaches();

		PG_RE_THROW();
	}
	PG_END_TRY();

	return retlsn;
}

/*
 * SQL function for moving the position in a replication slot.
 */
Datum
pg_replication_slot_advance(PG_FUNCTION_ARGS)
{
	Name		slotname = PG_GETARG_NAME(0);
	XLogRecPtr	moveto = PG_GETARG_LSN(1);
	XLogRecPtr	endlsn;
	XLogRecPtr	minlsn;
	TupleDesc	tupdesc;
	Datum		values[2];
	bool		nulls[2];
	HeapTuple	tuple;
	Datum		result;

	Assert(!MyReplicationSlot);

	CheckSlotPermissions();

	if (XLogRecPtrIsInvalid(moveto))
		ereport(ERROR,
				(errmsg("invalid target WAL LSN")));

	/* 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");

	/*
	 * We can't move slot past what's been flushed/replayed so clamp the
	 * target position accordingly.
	 */
	if (!RecoveryInProgress())
		moveto = Min(moveto, GetFlushRecPtr(NULL));
	else
		moveto = Min(moveto, GetXLogReplayRecPtr(NULL));

	/* Acquire the slot so we "own" it */
	ReplicationSlotAcquire(NameStr(*slotname), true);

	/* A slot whose restart_lsn has never been reserved cannot be advanced */
	if (XLogRecPtrIsInvalid(MyReplicationSlot->data.restart_lsn))
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("replication slot \"%s\" cannot be advanced",
						NameStr(*slotname)),
				 errdetail("This slot has never previously reserved WAL, or it has been invalidated.")));

	/*
	 * Check if the slot is not moving backwards.  Physical slots rely simply
	 * on restart_lsn as a minimum point, while logical slots have confirmed
	 * consumption up to confirmed_flush, meaning that in both cases data
	 * older than that is not available anymore.
	 */
	if (OidIsValid(MyReplicationSlot->data.database))
		minlsn = MyReplicationSlot->data.confirmed_flush;
	else
		minlsn = MyReplicationSlot->data.restart_lsn;

	if (moveto < minlsn)
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("cannot advance replication slot to %X/%X, minimum is %X/%X",
						LSN_FORMAT_ARGS(moveto), LSN_FORMAT_ARGS(minlsn))));

	/* Do the actual slot update, depending on the slot type */
	if (OidIsValid(MyReplicationSlot->data.database))
		endlsn = pg_logical_replication_slot_advance(moveto);
	else
		endlsn = pg_physical_replication_slot_advance(moveto);

	values[0] = NameGetDatum(&MyReplicationSlot->data.name);
	nulls[0] = false;

	/*
	 * Recompute the minimum LSN and xmin across all slots to adjust with the
	 * advancing potentially done.
	 */
	ReplicationSlotsComputeRequiredXmin(false);
	ReplicationSlotsComputeRequiredLSN();

	ReplicationSlotRelease();

	/* Return the reached position. */
	values[1] = LSNGetDatum(endlsn);
	nulls[1] = false;

	tuple = heap_form_tuple(tupdesc, values, nulls);
	result = HeapTupleGetDatum(tuple);

	PG_RETURN_DATUM(result);
}

/*
 * Helper function of copying a replication slot.
 */
static Datum
copy_replication_slot(FunctionCallInfo fcinfo, bool logical_slot)
{
	Name		src_name = PG_GETARG_NAME(0);
	Name		dst_name = PG_GETARG_NAME(1);
	ReplicationSlot *src = NULL;
	ReplicationSlot first_slot_contents;
	ReplicationSlot second_slot_contents;
	XLogRecPtr	src_restart_lsn;
	bool		src_islogical;
	bool		temporary;
	char	   *plugin;
	Datum		values[2];
	bool		nulls[2];
	Datum		result;
	TupleDesc	tupdesc;
	HeapTuple	tuple;

	if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
		elog(ERROR, "return type must be a row type");

	CheckSlotPermissions();

	if (logical_slot)
		CheckLogicalDecodingRequirements();
	else
		CheckSlotRequirements();

	LWLockAcquire(ReplicationSlotControlLock, LW_SHARED);

	/*
	 * We need to prevent the source slot's reserved WAL from being removed,
	 * but we don't want to lock that slot for very long, and it can advance
	 * in the meantime.  So obtain the source slot's data, and create a new
	 * slot using its restart_lsn.  Afterwards we lock the source slot again
	 * and verify that the data we copied (name, type) has not changed
	 * incompatibly.  No inconvenient WAL removal can occur once the new slot
	 * is created -- but since WAL removal could have occurred before we
	 * managed to create the new slot, we advance the new slot's restart_lsn
	 * to the source slot's updated restart_lsn the second time we lock it.
	 */
	for (int i = 0; i < max_replication_slots; i++)
	{
		ReplicationSlot *s = &ReplicationSlotCtl->replication_slots[i];

		if (s->in_use && strcmp(NameStr(s->data.name), NameStr(*src_name)) == 0)
		{
			/* Copy the slot contents while holding spinlock */
			SpinLockAcquire(&s->mutex);
			first_slot_contents = *s;
			SpinLockRelease(&s->mutex);
			src = s;
			break;
		}
	}

	LWLockRelease(ReplicationSlotControlLock);

	if (src == NULL)
		ereport(ERROR,
				(errcode(ERRCODE_UNDEFINED_OBJECT),
				 errmsg("replication slot \"%s\" does not exist", NameStr(*src_name))));

	src_islogical = SlotIsLogical(&first_slot_contents);
	src_restart_lsn = first_slot_contents.data.restart_lsn;
	temporary = (first_slot_contents.data.persistency == RS_TEMPORARY);
	plugin = logical_slot ? NameStr(first_slot_contents.data.plugin) : NULL;

	/* Check type of replication slot */
	if (src_islogical != logical_slot)
		ereport(ERROR,
				(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
				 src_islogical ?
				 errmsg("cannot copy physical replication slot \"%s\" as a logical replication slot",
						NameStr(*src_name)) :
				 errmsg("cannot copy logical replication slot \"%s\" as a physical replication slot",
						NameStr(*src_name))));

	/* Copying non-reserved slot doesn't make sense */
	if (XLogRecPtrIsInvalid(src_restart_lsn))
		ereport(ERROR,
				(errcode(ERRCODE_OBJECT_NOT_IN_PREREQUISITE_STATE),
				 errmsg("cannot copy a replication slot that doesn't reserve WAL")));

	/* Overwrite params from optional arguments */
	if (PG_NARGS() >= 3)
		temporary = PG_GETARG_BOOL(2);
	if (PG_NARGS() >= 4)
	{
		Assert(logical_slot);
		plugin = NameStr(*(PG_GETARG_NAME(3)));
	}

	/* Create new slot and acquire it */
	if (logical_slot)
	{
		/*
		 * We must not try to read WAL, since we haven't reserved it yet --
		 * hence pass find_startpoint false.  confirmed_flush will be set
		 * below, by copying from the source slot.
		 */
		create_logical_replication_slot(NameStr(*dst_name),
										plugin,
										temporary,
										false,
										src_restart_lsn,
										false);
	}
	else
		create_physical_replication_slot(NameStr(*dst_name),
										 true,
										 temporary,
										 src_restart_lsn);

	/*
	 * Update the destination slot to current values of the source slot;
	 * recheck that the source slot is still the one we saw previously.
	 */
	{
		TransactionId copy_effective_xmin;
		TransactionId copy_effective_catalog_xmin;
		TransactionId copy_xmin;
		TransactionId copy_catalog_xmin;
		XLogRecPtr	copy_restart_lsn;
		XLogRecPtr	copy_confirmed_flush;
		bool		copy_islogical;
		char	   *copy_name;

		/* Copy data of source slot again */
		SpinLockAcquire(&src->mutex);
		second_slot_contents = *src;
		SpinLockRelease(&src->mutex);

		copy_effective_xmin = second_slot_contents.effective_xmin;
		copy_effective_catalog_xmin = second_slot_contents.effective_catalog_xmin;

		copy_xmin = second_slot_contents.data.xmin;
		copy_catalog_xmin = second_slot_contents.data.catalog_xmin;
		copy_restart_lsn = second_slot_contents.data.restart_lsn;
		copy_confirmed_flush = second_slot_contents.data.confirmed_flush;

		/* for existence check */
		copy_name = NameStr(second_slot_contents.data.name);
		copy_islogical = SlotIsLogical(&second_slot_contents);

		/*
		 * Check if the source slot still exists and is valid. We regard it as
		 * invalid if the type of replication slot or name has been changed,
		 * or the restart_lsn either is invalid or has gone backward. (The
		 * restart_lsn could go backwards if the source slot is dropped and
		 * copied from an older slot during installation.)
		 *
		 * Since erroring out will release and drop the destination slot we
		 * don't need to release it here.
		 */
		if (copy_restart_lsn < src_restart_lsn ||
			src_islogical != copy_islogical ||
			strcmp(copy_name, NameStr(*src_name)) != 0)
			ereport(ERROR,
					(errmsg("could not copy replication slot \"%s\"",
							NameStr(*src_name)),
					 errdetail("The source replication slot was modified incompatibly during the copy operation.")));

		/* The source slot must have a consistent snapshot */
		if (src_islogical && XLogRecPtrIsInvalid(copy_confirmed_flush))
			ereport(ERROR,
					(errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
					 errmsg("cannot copy unfinished logical replication slot \"%s\"",
							NameStr(*src_name)),
					 errhint("Retry when the source replication slot's confirmed_flush_lsn is valid.")));

		/* Install copied values again */
		SpinLockAcquire(&MyReplicationSlot->mutex);
		MyReplicationSlot->effective_xmin = copy_effective_xmin;
		MyReplicationSlot->effective_catalog_xmin = copy_effective_catalog_xmin;

		MyReplicationSlot->data.xmin = copy_xmin;
		MyReplicationSlot->data.catalog_xmin = copy_catalog_xmin;
		MyReplicationSlot->data.restart_lsn = copy_restart_lsn;
		MyReplicationSlot->data.confirmed_flush = copy_confirmed_flush;
		SpinLockRelease(&MyReplicationSlot->mutex);

		ReplicationSlotMarkDirty();
		ReplicationSlotsComputeRequiredXmin(false);
		ReplicationSlotsComputeRequiredLSN();
		ReplicationSlotSave();

#ifdef USE_ASSERT_CHECKING
		/* Check that the restart_lsn is available */
		{
			XLogSegNo	segno;

			XLByteToSeg(copy_restart_lsn, segno, wal_segment_size);
			Assert(XLogGetLastRemovedSegno() < segno);
		}
#endif
	}

	/* target slot fully created, mark as persistent if needed */
	if (logical_slot && !temporary)
		ReplicationSlotPersist();

	/* All done.  Set up the return values */
	values[0] = NameGetDatum(dst_name);
	nulls[0] = false;
	if (!XLogRecPtrIsInvalid(MyReplicationSlot->data.confirmed_flush))
	{
		values[1] = LSNGetDatum(MyReplicationSlot->data.confirmed_flush);
		nulls[1] = false;
	}
	else
		nulls[1] = true;

	tuple = heap_form_tuple(tupdesc, values, nulls);
	result = HeapTupleGetDatum(tuple);

	ReplicationSlotRelease();

	PG_RETURN_DATUM(result);
}

/* The wrappers below are all to appease opr_sanity */
Datum
pg_copy_logical_replication_slot_a(PG_FUNCTION_ARGS)
{
	return copy_replication_slot(fcinfo, true);
}

Datum
pg_copy_logical_replication_slot_b(PG_FUNCTION_ARGS)
{
	return copy_replication_slot(fcinfo, true);
}

Datum
pg_copy_logical_replication_slot_c(PG_FUNCTION_ARGS)
{
	return copy_replication_slot(fcinfo, true);
}

Datum
pg_copy_physical_replication_slot_a(PG_FUNCTION_ARGS)
{
	return copy_replication_slot(fcinfo, false);
}

Datum
pg_copy_physical_replication_slot_b(PG_FUNCTION_ARGS)
{
	return copy_replication_slot(fcinfo, false);
}