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
|
/*-------------------------------------------------------------------------
*
* localbuf.c
* local buffer manager. Fast buffer manager for temporary tables,
* which never need to be WAL-logged or checkpointed, etc.
*
* Portions Copyright (c) 1996-2023, PostgreSQL Global Development Group
* Portions Copyright (c) 1994-5, Regents of the University of California
*
*
* IDENTIFICATION
* src/backend/storage/buffer/localbuf.c
*
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/parallel.h"
#include "catalog/catalog.h"
#include "executor/instrument.h"
#include "pgstat.h"
#include "storage/buf_internals.h"
#include "storage/bufmgr.h"
#include "utils/guc_hooks.h"
#include "utils/memutils.h"
#include "utils/resowner_private.h"
/*#define LBDEBUG*/
/* entry for buffer lookup hashtable */
typedef struct
{
BufferTag key; /* Tag of a disk page */
int id; /* Associated local buffer's index */
} LocalBufferLookupEnt;
/* Note: this macro only works on local buffers, not shared ones! */
#define LocalBufHdrGetBlock(bufHdr) \
LocalBufferBlockPointers[-((bufHdr)->buf_id + 2)]
int NLocBuffer = 0; /* until buffers are initialized */
BufferDesc *LocalBufferDescriptors = NULL;
Block *LocalBufferBlockPointers = NULL;
int32 *LocalRefCount = NULL;
static int nextFreeLocalBufId = 0;
static HTAB *LocalBufHash = NULL;
/* number of local buffers pinned at least once */
static int NLocalPinnedBuffers = 0;
static void InitLocalBuffers(void);
static Block GetLocalBufferStorage(void);
static Buffer GetLocalVictimBuffer(void);
/*
* PrefetchLocalBuffer -
* initiate asynchronous read of a block of a relation
*
* Do PrefetchBuffer's work for temporary relations.
* No-op if prefetching isn't compiled in.
*/
PrefetchBufferResult
PrefetchLocalBuffer(SMgrRelation smgr, ForkNumber forkNum,
BlockNumber blockNum)
{
PrefetchBufferResult result = {InvalidBuffer, false};
BufferTag newTag; /* identity of requested block */
LocalBufferLookupEnt *hresult;
InitBufferTag(&newTag, &smgr->smgr_rlocator.locator, forkNum, blockNum);
/* Initialize local buffers if first request in this session */
if (LocalBufHash == NULL)
InitLocalBuffers();
/* See if the desired buffer already exists */
hresult = (LocalBufferLookupEnt *)
hash_search(LocalBufHash, &newTag, HASH_FIND, NULL);
if (hresult)
{
/* Yes, so nothing to do */
result.recent_buffer = -hresult->id - 1;
}
else
{
#ifdef USE_PREFETCH
/* Not in buffers, so initiate prefetch */
if ((io_direct_flags & IO_DIRECT_DATA) == 0 &&
smgrprefetch(smgr, forkNum, blockNum))
{
result.initiated_io = true;
}
#endif /* USE_PREFETCH */
}
return result;
}
/*
* LocalBufferAlloc -
* Find or create a local buffer for the given page of the given relation.
*
* API is similar to bufmgr.c's BufferAlloc, except that we do not need
* to do any locking since this is all local. Also, IO_IN_PROGRESS
* does not get set. Lastly, we support only default access strategy
* (hence, usage_count is always advanced).
*/
BufferDesc *
LocalBufferAlloc(SMgrRelation smgr, ForkNumber forkNum, BlockNumber blockNum,
bool *foundPtr)
{
BufferTag newTag; /* identity of requested block */
LocalBufferLookupEnt *hresult;
BufferDesc *bufHdr;
Buffer victim_buffer;
int bufid;
bool found;
InitBufferTag(&newTag, &smgr->smgr_rlocator.locator, forkNum, blockNum);
/* Initialize local buffers if first request in this session */
if (LocalBufHash == NULL)
InitLocalBuffers();
/* See if the desired buffer already exists */
hresult = (LocalBufferLookupEnt *)
hash_search(LocalBufHash, &newTag, HASH_FIND, NULL);
if (hresult)
{
bufid = hresult->id;
bufHdr = GetLocalBufferDescriptor(bufid);
Assert(BufferTagsEqual(&bufHdr->tag, &newTag));
*foundPtr = PinLocalBuffer(bufHdr, true);
}
else
{
uint32 buf_state;
victim_buffer = GetLocalVictimBuffer();
bufid = -victim_buffer - 1;
bufHdr = GetLocalBufferDescriptor(bufid);
hresult = (LocalBufferLookupEnt *)
hash_search(LocalBufHash, &newTag, HASH_ENTER, &found);
if (found) /* shouldn't happen */
elog(ERROR, "local buffer hash table corrupted");
hresult->id = bufid;
/*
* it's all ours now.
*/
bufHdr->tag = newTag;
buf_state = pg_atomic_read_u32(&bufHdr->state);
buf_state &= ~(BUF_FLAG_MASK | BUF_USAGECOUNT_MASK);
buf_state |= BM_TAG_VALID | BUF_USAGECOUNT_ONE;
pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state);
*foundPtr = false;
}
return bufHdr;
}
static Buffer
GetLocalVictimBuffer(void)
{
int victim_bufid;
int trycounter;
uint32 buf_state;
BufferDesc *bufHdr;
ResourceOwnerEnlargeBuffers(CurrentResourceOwner);
/*
* Need to get a new buffer. We use a clock sweep algorithm (essentially
* the same as what freelist.c does now...)
*/
trycounter = NLocBuffer;
for (;;)
{
victim_bufid = nextFreeLocalBufId;
if (++nextFreeLocalBufId >= NLocBuffer)
nextFreeLocalBufId = 0;
bufHdr = GetLocalBufferDescriptor(victim_bufid);
if (LocalRefCount[victim_bufid] == 0)
{
buf_state = pg_atomic_read_u32(&bufHdr->state);
if (BUF_STATE_GET_USAGECOUNT(buf_state) > 0)
{
buf_state -= BUF_USAGECOUNT_ONE;
pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state);
trycounter = NLocBuffer;
}
else
{
/* Found a usable buffer */
PinLocalBuffer(bufHdr, false);
break;
}
}
else if (--trycounter == 0)
ereport(ERROR,
(errcode(ERRCODE_INSUFFICIENT_RESOURCES),
errmsg("no empty local buffer available")));
}
/*
* lazy memory allocation: allocate space on first use of a buffer.
*/
if (LocalBufHdrGetBlock(bufHdr) == NULL)
{
/* Set pointer for use by BufferGetBlock() macro */
LocalBufHdrGetBlock(bufHdr) = GetLocalBufferStorage();
}
/*
* this buffer is not referenced but it might still be dirty. if that's
* the case, write it out before reusing it!
*/
if (buf_state & BM_DIRTY)
{
instr_time io_start;
SMgrRelation oreln;
Page localpage = (char *) LocalBufHdrGetBlock(bufHdr);
/* Find smgr relation for buffer */
oreln = smgropen(BufTagGetRelFileLocator(&bufHdr->tag), MyBackendId);
PageSetChecksumInplace(localpage, bufHdr->tag.blockNum);
io_start = pgstat_prepare_io_time();
/* And write... */
smgrwrite(oreln,
BufTagGetForkNum(&bufHdr->tag),
bufHdr->tag.blockNum,
localpage,
false);
/* Temporary table I/O does not use Buffer Access Strategies */
pgstat_count_io_op_time(IOOBJECT_TEMP_RELATION, IOCONTEXT_NORMAL,
IOOP_WRITE, io_start, 1);
/* Mark not-dirty now in case we error out below */
buf_state &= ~BM_DIRTY;
pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state);
pgBufferUsage.local_blks_written++;
}
/*
* Remove the victim buffer from the hashtable and mark as invalid.
*/
if (buf_state & BM_TAG_VALID)
{
LocalBufferLookupEnt *hresult;
hresult = (LocalBufferLookupEnt *)
hash_search(LocalBufHash, &bufHdr->tag, HASH_REMOVE, NULL);
if (!hresult) /* shouldn't happen */
elog(ERROR, "local buffer hash table corrupted");
/* mark buffer invalid just in case hash insert fails */
ClearBufferTag(&bufHdr->tag);
buf_state &= ~(BUF_FLAG_MASK | BUF_USAGECOUNT_MASK);
pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state);
pgstat_count_io_op(IOOBJECT_TEMP_RELATION, IOCONTEXT_NORMAL, IOOP_EVICT);
}
return BufferDescriptorGetBuffer(bufHdr);
}
/* see LimitAdditionalPins() */
static void
LimitAdditionalLocalPins(uint32 *additional_pins)
{
uint32 max_pins;
if (*additional_pins <= 1)
return;
/*
* In contrast to LimitAdditionalPins() other backends don't play a role
* here. We can allow up to NLocBuffer pins in total.
*/
max_pins = (NLocBuffer - NLocalPinnedBuffers);
if (*additional_pins >= max_pins)
*additional_pins = max_pins;
}
/*
* Implementation of ExtendBufferedRelBy() and ExtendBufferedRelTo() for
* temporary buffers.
*/
BlockNumber
ExtendBufferedRelLocal(ExtendBufferedWhat eb,
ForkNumber fork,
uint32 flags,
uint32 extend_by,
BlockNumber extend_upto,
Buffer *buffers,
uint32 *extended_by)
{
BlockNumber first_block;
instr_time io_start;
/* Initialize local buffers if first request in this session */
if (LocalBufHash == NULL)
InitLocalBuffers();
LimitAdditionalLocalPins(&extend_by);
for (uint32 i = 0; i < extend_by; i++)
{
BufferDesc *buf_hdr;
Block buf_block;
buffers[i] = GetLocalVictimBuffer();
buf_hdr = GetLocalBufferDescriptor(-buffers[i] - 1);
buf_block = LocalBufHdrGetBlock(buf_hdr);
/* new buffers are zero-filled */
MemSet((char *) buf_block, 0, BLCKSZ);
}
first_block = smgrnblocks(eb.smgr, fork);
if (extend_upto != InvalidBlockNumber)
{
/*
* In contrast to shared relations, nothing could change the relation
* size concurrently. Thus we shouldn't end up finding that we don't
* need to do anything.
*/
Assert(first_block <= extend_upto);
Assert((uint64) first_block + extend_by <= extend_upto);
}
/* Fail if relation is already at maximum possible length */
if ((uint64) first_block + extend_by >= MaxBlockNumber)
ereport(ERROR,
(errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
errmsg("cannot extend relation %s beyond %u blocks",
relpath(eb.smgr->smgr_rlocator, fork),
MaxBlockNumber)));
for (int i = 0; i < extend_by; i++)
{
int victim_buf_id;
BufferDesc *victim_buf_hdr;
BufferTag tag;
LocalBufferLookupEnt *hresult;
bool found;
victim_buf_id = -buffers[i] - 1;
victim_buf_hdr = GetLocalBufferDescriptor(victim_buf_id);
InitBufferTag(&tag, &eb.smgr->smgr_rlocator.locator, fork, first_block + i);
hresult = (LocalBufferLookupEnt *)
hash_search(LocalBufHash, (void *) &tag, HASH_ENTER, &found);
if (found)
{
BufferDesc *existing_hdr = GetLocalBufferDescriptor(hresult->id);
uint32 buf_state;
UnpinLocalBuffer(BufferDescriptorGetBuffer(victim_buf_hdr));
existing_hdr = GetLocalBufferDescriptor(hresult->id);
PinLocalBuffer(existing_hdr, false);
buffers[i] = BufferDescriptorGetBuffer(existing_hdr);
buf_state = pg_atomic_read_u32(&existing_hdr->state);
Assert(buf_state & BM_TAG_VALID);
Assert(!(buf_state & BM_DIRTY));
buf_state &= BM_VALID;
pg_atomic_unlocked_write_u32(&existing_hdr->state, buf_state);
}
else
{
uint32 buf_state = pg_atomic_read_u32(&victim_buf_hdr->state);
Assert(!(buf_state & (BM_VALID | BM_TAG_VALID | BM_DIRTY | BM_JUST_DIRTIED)));
victim_buf_hdr->tag = tag;
buf_state |= BM_TAG_VALID | BUF_USAGECOUNT_ONE;
pg_atomic_unlocked_write_u32(&victim_buf_hdr->state, buf_state);
hresult->id = victim_buf_id;
}
}
io_start = pgstat_prepare_io_time();
/* actually extend relation */
smgrzeroextend(eb.smgr, fork, first_block, extend_by, false);
pgstat_count_io_op_time(IOOBJECT_TEMP_RELATION, IOCONTEXT_NORMAL, IOOP_EXTEND,
io_start, extend_by);
for (int i = 0; i < extend_by; i++)
{
Buffer buf = buffers[i];
BufferDesc *buf_hdr;
uint32 buf_state;
buf_hdr = GetLocalBufferDescriptor(-buf - 1);
buf_state = pg_atomic_read_u32(&buf_hdr->state);
buf_state |= BM_VALID;
pg_atomic_unlocked_write_u32(&buf_hdr->state, buf_state);
}
*extended_by = extend_by;
pgBufferUsage.temp_blks_written += extend_by;
return first_block;
}
/*
* MarkLocalBufferDirty -
* mark a local buffer dirty
*/
void
MarkLocalBufferDirty(Buffer buffer)
{
int bufid;
BufferDesc *bufHdr;
uint32 buf_state;
Assert(BufferIsLocal(buffer));
#ifdef LBDEBUG
fprintf(stderr, "LB DIRTY %d\n", buffer);
#endif
bufid = -buffer - 1;
Assert(LocalRefCount[bufid] > 0);
bufHdr = GetLocalBufferDescriptor(bufid);
buf_state = pg_atomic_read_u32(&bufHdr->state);
if (!(buf_state & BM_DIRTY))
pgBufferUsage.local_blks_dirtied++;
buf_state |= BM_DIRTY;
pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state);
}
/*
* DropRelationLocalBuffers
* This function removes from the buffer pool all the pages of the
* specified relation that have block numbers >= firstDelBlock.
* (In particular, with firstDelBlock = 0, all pages are removed.)
* Dirty pages are simply dropped, without bothering to write them
* out first. Therefore, this is NOT rollback-able, and so should be
* used only with extreme caution!
*
* See DropRelationBuffers in bufmgr.c for more notes.
*/
void
DropRelationLocalBuffers(RelFileLocator rlocator, ForkNumber forkNum,
BlockNumber firstDelBlock)
{
int i;
for (i = 0; i < NLocBuffer; i++)
{
BufferDesc *bufHdr = GetLocalBufferDescriptor(i);
LocalBufferLookupEnt *hresult;
uint32 buf_state;
buf_state = pg_atomic_read_u32(&bufHdr->state);
if ((buf_state & BM_TAG_VALID) &&
BufTagMatchesRelFileLocator(&bufHdr->tag, &rlocator) &&
BufTagGetForkNum(&bufHdr->tag) == forkNum &&
bufHdr->tag.blockNum >= firstDelBlock)
{
if (LocalRefCount[i] != 0)
elog(ERROR, "block %u of %s is still referenced (local %u)",
bufHdr->tag.blockNum,
relpathbackend(BufTagGetRelFileLocator(&bufHdr->tag),
MyBackendId,
BufTagGetForkNum(&bufHdr->tag)),
LocalRefCount[i]);
/* Remove entry from hashtable */
hresult = (LocalBufferLookupEnt *)
hash_search(LocalBufHash, &bufHdr->tag, HASH_REMOVE, NULL);
if (!hresult) /* shouldn't happen */
elog(ERROR, "local buffer hash table corrupted");
/* Mark buffer invalid */
ClearBufferTag(&bufHdr->tag);
buf_state &= ~BUF_FLAG_MASK;
buf_state &= ~BUF_USAGECOUNT_MASK;
pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state);
}
}
}
/*
* DropRelationAllLocalBuffers
* This function removes from the buffer pool all pages of all forks
* of the specified relation.
*
* See DropRelationsAllBuffers in bufmgr.c for more notes.
*/
void
DropRelationAllLocalBuffers(RelFileLocator rlocator)
{
int i;
for (i = 0; i < NLocBuffer; i++)
{
BufferDesc *bufHdr = GetLocalBufferDescriptor(i);
LocalBufferLookupEnt *hresult;
uint32 buf_state;
buf_state = pg_atomic_read_u32(&bufHdr->state);
if ((buf_state & BM_TAG_VALID) &&
BufTagMatchesRelFileLocator(&bufHdr->tag, &rlocator))
{
if (LocalRefCount[i] != 0)
elog(ERROR, "block %u of %s is still referenced (local %u)",
bufHdr->tag.blockNum,
relpathbackend(BufTagGetRelFileLocator(&bufHdr->tag),
MyBackendId,
BufTagGetForkNum(&bufHdr->tag)),
LocalRefCount[i]);
/* Remove entry from hashtable */
hresult = (LocalBufferLookupEnt *)
hash_search(LocalBufHash, &bufHdr->tag, HASH_REMOVE, NULL);
if (!hresult) /* shouldn't happen */
elog(ERROR, "local buffer hash table corrupted");
/* Mark buffer invalid */
ClearBufferTag(&bufHdr->tag);
buf_state &= ~BUF_FLAG_MASK;
buf_state &= ~BUF_USAGECOUNT_MASK;
pg_atomic_unlocked_write_u32(&bufHdr->state, buf_state);
}
}
}
/*
* InitLocalBuffers -
* init the local buffer cache. Since most queries (esp. multi-user ones)
* don't involve local buffers, we delay allocating actual memory for the
* buffers until we need them; just make the buffer headers here.
*/
static void
InitLocalBuffers(void)
{
int nbufs = num_temp_buffers;
HASHCTL info;
int i;
/*
* Parallel workers can't access data in temporary tables, because they
* have no visibility into the local buffers of their leader. This is a
* convenient, low-cost place to provide a backstop check for that. Note
* that we don't wish to prevent a parallel worker from accessing catalog
* metadata about a temp table, so checks at higher levels would be
* inappropriate.
*/
if (IsParallelWorker())
ereport(ERROR,
(errcode(ERRCODE_INVALID_TRANSACTION_STATE),
errmsg("cannot access temporary tables during a parallel operation")));
/* Allocate and zero buffer headers and auxiliary arrays */
LocalBufferDescriptors = (BufferDesc *) calloc(nbufs, sizeof(BufferDesc));
LocalBufferBlockPointers = (Block *) calloc(nbufs, sizeof(Block));
LocalRefCount = (int32 *) calloc(nbufs, sizeof(int32));
if (!LocalBufferDescriptors || !LocalBufferBlockPointers || !LocalRefCount)
ereport(FATAL,
(errcode(ERRCODE_OUT_OF_MEMORY),
errmsg("out of memory")));
nextFreeLocalBufId = 0;
/* initialize fields that need to start off nonzero */
for (i = 0; i < nbufs; i++)
{
BufferDesc *buf = GetLocalBufferDescriptor(i);
/*
* negative to indicate local buffer. This is tricky: shared buffers
* start with 0. We have to start with -2. (Note that the routine
* BufferDescriptorGetBuffer adds 1 to buf_id so our first buffer id
* is -1.)
*/
buf->buf_id = -i - 2;
/*
* Intentionally do not initialize the buffer's atomic variable
* (besides zeroing the underlying memory above). That way we get
* errors on platforms without atomics, if somebody (re-)introduces
* atomic operations for local buffers.
*/
}
/* Create the lookup hash table */
info.keysize = sizeof(BufferTag);
info.entrysize = sizeof(LocalBufferLookupEnt);
LocalBufHash = hash_create("Local Buffer Lookup Table",
nbufs,
&info,
HASH_ELEM | HASH_BLOBS);
if (!LocalBufHash)
elog(ERROR, "could not initialize local buffer hash table");
/* Initialization done, mark buffers allocated */
NLocBuffer = nbufs;
}
/*
* XXX: We could have a slightly more efficient version of PinLocalBuffer()
* that does not support adjusting the usagecount - but so far it does not
* seem worth the trouble.
*/
bool
PinLocalBuffer(BufferDesc *buf_hdr, bool adjust_usagecount)
{
uint32 buf_state;
Buffer buffer = BufferDescriptorGetBuffer(buf_hdr);
int bufid = -buffer - 1;
buf_state = pg_atomic_read_u32(&buf_hdr->state);
if (LocalRefCount[bufid] == 0)
{
NLocalPinnedBuffers++;
if (adjust_usagecount &&
BUF_STATE_GET_USAGECOUNT(buf_state) < BM_MAX_USAGE_COUNT)
{
buf_state += BUF_USAGECOUNT_ONE;
pg_atomic_unlocked_write_u32(&buf_hdr->state, buf_state);
}
}
LocalRefCount[bufid]++;
ResourceOwnerRememberBuffer(CurrentResourceOwner,
BufferDescriptorGetBuffer(buf_hdr));
return buf_state & BM_VALID;
}
void
UnpinLocalBuffer(Buffer buffer)
{
int buffid = -buffer - 1;
Assert(BufferIsLocal(buffer));
Assert(LocalRefCount[buffid] > 0);
Assert(NLocalPinnedBuffers > 0);
ResourceOwnerForgetBuffer(CurrentResourceOwner, buffer);
if (--LocalRefCount[buffid] == 0)
NLocalPinnedBuffers--;
}
/*
* GUC check_hook for temp_buffers
*/
bool
check_temp_buffers(int *newval, void **extra, GucSource source)
{
/*
* Once local buffers have been initialized, it's too late to change this.
* However, if this is only a test call, allow it.
*/
if (source != PGC_S_TEST && NLocBuffer && NLocBuffer != *newval)
{
GUC_check_errdetail("\"temp_buffers\" cannot be changed after any temporary tables have been accessed in the session.");
return false;
}
return true;
}
/*
* GetLocalBufferStorage - allocate memory for a local buffer
*
* The idea of this function is to aggregate our requests for storage
* so that the memory manager doesn't see a whole lot of relatively small
* requests. Since we'll never give back a local buffer once it's created
* within a particular process, no point in burdening memmgr with separately
* managed chunks.
*/
static Block
GetLocalBufferStorage(void)
{
static char *cur_block = NULL;
static int next_buf_in_block = 0;
static int num_bufs_in_block = 0;
static int total_bufs_allocated = 0;
static MemoryContext LocalBufferContext = NULL;
char *this_buf;
Assert(total_bufs_allocated < NLocBuffer);
if (next_buf_in_block >= num_bufs_in_block)
{
/* Need to make a new request to memmgr */
int num_bufs;
/*
* We allocate local buffers in a context of their own, so that the
* space eaten for them is easily recognizable in MemoryContextStats
* output. Create the context on first use.
*/
if (LocalBufferContext == NULL)
LocalBufferContext =
AllocSetContextCreate(TopMemoryContext,
"LocalBufferContext",
ALLOCSET_DEFAULT_SIZES);
/* Start with a 16-buffer request; subsequent ones double each time */
num_bufs = Max(num_bufs_in_block * 2, 16);
/* But not more than what we need for all remaining local bufs */
num_bufs = Min(num_bufs, NLocBuffer - total_bufs_allocated);
/* And don't overflow MaxAllocSize, either */
num_bufs = Min(num_bufs, MaxAllocSize / BLCKSZ);
/* Buffers should be I/O aligned. */
cur_block = (char *)
TYPEALIGN(PG_IO_ALIGN_SIZE,
MemoryContextAlloc(LocalBufferContext,
num_bufs * BLCKSZ + PG_IO_ALIGN_SIZE));
next_buf_in_block = 0;
num_bufs_in_block = num_bufs;
}
/* Allocate next buffer in current memory block */
this_buf = cur_block + next_buf_in_block * BLCKSZ;
next_buf_in_block++;
total_bufs_allocated++;
return (Block) this_buf;
}
/*
* CheckForLocalBufferLeaks - ensure this backend holds no local buffer pins
*
* This is just like CheckForBufferLeaks(), but for local buffers.
*/
static void
CheckForLocalBufferLeaks(void)
{
#ifdef USE_ASSERT_CHECKING
if (LocalRefCount)
{
int RefCountErrors = 0;
int i;
for (i = 0; i < NLocBuffer; i++)
{
if (LocalRefCount[i] != 0)
{
Buffer b = -i - 1;
PrintBufferLeakWarning(b);
RefCountErrors++;
}
}
Assert(RefCountErrors == 0);
}
#endif
}
/*
* AtEOXact_LocalBuffers - clean up at end of transaction.
*
* This is just like AtEOXact_Buffers, but for local buffers.
*/
void
AtEOXact_LocalBuffers(bool isCommit)
{
CheckForLocalBufferLeaks();
}
/*
* AtProcExit_LocalBuffers - ensure we have dropped pins during backend exit.
*
* This is just like AtProcExit_Buffers, but for local buffers.
*/
void
AtProcExit_LocalBuffers(void)
{
/*
* We shouldn't be holding any remaining pins; if we are, and assertions
* aren't enabled, we'll fail later in DropRelationBuffers while trying to
* drop the temp rels.
*/
CheckForLocalBufferLeaks();
}
|