PostgreSQL Source Code: src/backend/access/heap/visibilitymap.c Source File

PostgreSQL Source Code git master
visibilitymap.c
Go to the documentation of this file.
1/*-------------------------------------------------------------------------
2 *
3 * visibilitymap.c
4 * bitmap for tracking visibility of heap tuples
5 *
6 * Portions Copyright (c) 1996-2025, PostgreSQL Global Development Group
7 * Portions Copyright (c) 1994, Regents of the University of California
8 *
9 *
10 * IDENTIFICATION
11 * src/backend/access/heap/visibilitymap.c
12 *
13 * INTERFACE ROUTINES
14 * visibilitymap_clear - clear bits for one page in the visibility map
15 * visibilitymap_pin - pin a map page for setting a bit
16 * visibilitymap_pin_ok - check whether correct map page is already pinned
17 * visibilitymap_set - set a bit in a previously pinned page
18 * visibilitymap_get_status - get status of bits
19 * visibilitymap_count - count number of bits set in visibility map
20 * visibilitymap_prepare_truncate -
21 * prepare for truncation of the visibility map
22 *
23 * NOTES
24 *
25 * The visibility map is a bitmap with two bits (all-visible and all-frozen)
26 * per heap page. A set all-visible bit means that all tuples on the page are
27 * known visible to all transactions, and therefore the page doesn't need to
28 * be vacuumed. A set all-frozen bit means that all tuples on the page are
29 * completely frozen, and therefore the page doesn't need to be vacuumed even
30 * if whole table scanning vacuum is required (e.g. anti-wraparound vacuum).
31 * The all-frozen bit must be set only when the page is already all-visible.
32 *
33 * The map is conservative in the sense that we make sure that whenever a bit
34 * is set, we know the condition is true, but if a bit is not set, it might or
35 * might not be true.
36 *
37 * Clearing visibility map bits is not separately WAL-logged. The callers
38 * must make sure that whenever a bit is cleared, the bit is cleared on WAL
39 * replay of the updating operation as well.
40 *
41 * When we *set* a visibility map during VACUUM, we must write WAL. This may
42 * seem counterintuitive, since the bit is basically a hint: if it is clear,
43 * it may still be the case that every tuple on the page is visible to all
44 * transactions; we just don't know that for certain. The difficulty is that
45 * there are two bits which are typically set together: the PD_ALL_VISIBLE bit
46 * on the page itself, and the visibility map bit. If a crash occurs after the
47 * visibility map page makes it to disk and before the updated heap page makes
48 * it to disk, redo must set the bit on the heap page. Otherwise, the next
49 * insert, update, or delete on the heap page will fail to realize that the
50 * visibility map bit must be cleared, possibly causing index-only scans to
51 * return wrong answers.
52 *
53 * VACUUM will normally skip pages for which the visibility map bit is set;
54 * such pages can't contain any dead tuples and therefore don't need vacuuming.
55 *
56 * LOCKING
57 *
58 * In heapam.c, whenever a page is modified so that not all tuples on the
59 * page are visible to everyone anymore, the corresponding bit in the
60 * visibility map is cleared. In order to be crash-safe, we need to do this
61 * while still holding a lock on the heap page and in the same critical
62 * section that logs the page modification. However, we don't want to hold
63 * the buffer lock over any I/O that may be required to read in the visibility
64 * map page. To avoid this, we examine the heap page before locking it;
65 * if the page-level PD_ALL_VISIBLE bit is set, we pin the visibility map
66 * bit. Then, we lock the buffer. But this creates a race condition: there
67 * is a possibility that in the time it takes to lock the buffer, the
68 * PD_ALL_VISIBLE bit gets set. If that happens, we have to unlock the
69 * buffer, pin the visibility map page, and relock the buffer. This shouldn't
70 * happen often, because only VACUUM currently sets visibility map bits,
71 * and the race will only occur if VACUUM processes a given page at almost
72 * exactly the same time that someone tries to further modify it.
73 *
74 * To set a bit, you need to hold a lock on the heap page. That prevents
75 * the race condition where VACUUM sees that all tuples on the page are
76 * visible to everyone, but another backend modifies the page before VACUUM
77 * sets the bit in the visibility map.
78 *
79 * When a bit is set, the LSN of the visibility map page is updated to make
80 * sure that the visibility map update doesn't get written to disk before the
81 * WAL record of the changes that made it possible to set the bit is flushed.
82 * But when a bit is cleared, we don't have to do that because it's always
83 * safe to clear a bit in the map from correctness point of view.
84 *
85 *-------------------------------------------------------------------------
86 */
87#include "postgres.h"
88
89#include "access/heapam_xlog.h"
90#include "access/visibilitymap.h"
91#include "access/xloginsert.h"
92#include "access/xlogutils.h"
93#include "miscadmin.h"
94#include "port/pg_bitutils.h"
95#include "storage/bufmgr.h"
96#include "storage/smgr.h"
97#include "utils/inval.h"
98#include "utils/rel.h"
99
100
101/*#define TRACE_VISIBILITYMAP */
102
103/*
104 * Size of the bitmap on each visibility map page, in bytes. There's no
105 * extra headers, so the whole page minus the standard page header is
106 * used for the bitmap.
107 */
108 #define MAPSIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData))
109
110/* Number of heap blocks we can represent in one byte */
111 #define HEAPBLOCKS_PER_BYTE (BITS_PER_BYTE / BITS_PER_HEAPBLOCK)
112
113/* Number of heap blocks we can represent in one visibility map page. */
114 #define HEAPBLOCKS_PER_PAGE (MAPSIZE * HEAPBLOCKS_PER_BYTE)
115
116/* Mapping from heap block number to the right bit in the visibility map */
117 #define HEAPBLK_TO_MAPBLOCK(x) ((x) / HEAPBLOCKS_PER_PAGE)
118 #define HEAPBLK_TO_MAPBYTE(x) (((x) % HEAPBLOCKS_PER_PAGE) / HEAPBLOCKS_PER_BYTE)
119 #define HEAPBLK_TO_OFFSET(x) (((x) % HEAPBLOCKS_PER_BYTE) * BITS_PER_HEAPBLOCK)
120
121/* Masks for counting subsets of bits in the visibility map. */
122 #define VISIBLE_MASK8 (0x55) /* The lower bit of each bit pair */
123 #define FROZEN_MASK8 (0xaa) /* The upper bit of each bit pair */
124
125/* prototypes for internal routines */
126static Buffer vm_readbuf(Relation rel, BlockNumber blkno, bool extend);
127static Buffer vm_extend(Relation rel, BlockNumber vm_nblocks);
128
129
130/*
131 * visibilitymap_clear - clear specified bits for one page in visibility map
132 *
133 * You must pass a buffer containing the correct map page to this function.
134 * Call visibilitymap_pin first to pin the right one. This function doesn't do
135 * any I/O. Returns true if any bits have been cleared and false otherwise.
136 */
137bool
138 visibilitymap_clear(Relation rel, BlockNumber heapBlk, Buffer vmbuf, uint8 flags)
139{
140 BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
141 int mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
142 int mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
143 uint8 mask = flags << mapOffset;
144 char *map;
145 bool cleared = false;
146
147 /* Must never clear all_visible bit while leaving all_frozen bit set */
148 Assert(flags & VISIBILITYMAP_VALID_BITS);
149 Assert(flags != VISIBILITYMAP_ALL_VISIBLE);
150
151#ifdef TRACE_VISIBILITYMAP
152 elog(DEBUG1, "vm_clear %s %d", RelationGetRelationName(rel), heapBlk);
153#endif
154
155 if (!BufferIsValid(vmbuf) || BufferGetBlockNumber(vmbuf) != mapBlock)
156 elog(ERROR, "wrong buffer passed to visibilitymap_clear");
157
158 LockBuffer(vmbuf, BUFFER_LOCK_EXCLUSIVE);
159 map = PageGetContents(BufferGetPage(vmbuf));
160
161 if (map[mapByte] & mask)
162 {
163 map[mapByte] &= ~mask;
164
165 MarkBufferDirty(vmbuf);
166 cleared = true;
167 }
168
169 LockBuffer(vmbuf, BUFFER_LOCK_UNLOCK);
170
171 return cleared;
172}
173
174/*
175 * visibilitymap_pin - pin a map page for setting a bit
176 *
177 * Setting a bit in the visibility map is a two-phase operation. First, call
178 * visibilitymap_pin, to pin the visibility map page containing the bit for
179 * the heap page. Because that can require I/O to read the map page, you
180 * shouldn't hold a lock on the heap page while doing that. Then, call
181 * visibilitymap_set to actually set the bit.
182 *
183 * On entry, *vmbuf should be InvalidBuffer or a valid buffer returned by
184 * an earlier call to visibilitymap_pin or visibilitymap_get_status on the same
185 * relation. On return, *vmbuf is a valid buffer with the map page containing
186 * the bit for heapBlk.
187 *
188 * If the page doesn't exist in the map file yet, it is extended.
189 */
190void
191 visibilitymap_pin(Relation rel, BlockNumber heapBlk, Buffer *vmbuf)
192{
193 BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
194
195 /* Reuse the old pinned buffer if possible */
196 if (BufferIsValid(*vmbuf))
197 {
198 if (BufferGetBlockNumber(*vmbuf) == mapBlock)
199 return;
200
201 ReleaseBuffer(*vmbuf);
202 }
203 *vmbuf = vm_readbuf(rel, mapBlock, true);
204}
205
206/*
207 * visibilitymap_pin_ok - do we already have the correct page pinned?
208 *
209 * On entry, vmbuf should be InvalidBuffer or a valid buffer returned by
210 * an earlier call to visibilitymap_pin or visibilitymap_get_status on the same
211 * relation. The return value indicates whether the buffer covers the
212 * given heapBlk.
213 */
214bool
215 visibilitymap_pin_ok(BlockNumber heapBlk, Buffer vmbuf)
216{
217 BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
218
219 return BufferIsValid(vmbuf) && BufferGetBlockNumber(vmbuf) == mapBlock;
220}
221
222/*
223 * visibilitymap_set - set bit(s) on a previously pinned page
224 *
225 * recptr is the LSN of the XLOG record we're replaying, if we're in recovery,
226 * or InvalidXLogRecPtr in normal running. The VM page LSN is advanced to the
227 * one provided; in normal running, we generate a new XLOG record and set the
228 * page LSN to that value (though the heap page's LSN may *not* be updated;
229 * see below). cutoff_xid is the largest xmin on the page being marked
230 * all-visible; it is needed for Hot Standby, and can be InvalidTransactionId
231 * if the page contains no tuples. It can also be set to InvalidTransactionId
232 * when a page that is already all-visible is being marked all-frozen.
233 *
234 * Caller is expected to set the heap page's PD_ALL_VISIBLE bit before calling
235 * this function. Except in recovery, caller should also pass the heap
236 * buffer. When checksums are enabled and we're not in recovery, we must add
237 * the heap buffer to the WAL chain to protect it from being torn.
238 *
239 * You must pass a buffer containing the correct map page to this function.
240 * Call visibilitymap_pin first to pin the right one. This function doesn't do
241 * any I/O.
242 *
243 * Returns the state of the page's VM bits before setting flags.
244 */
245uint8
246 visibilitymap_set(Relation rel, BlockNumber heapBlk, Buffer heapBuf,
247 XLogRecPtr recptr, Buffer vmBuf, TransactionId cutoff_xid,
248 uint8 flags)
249{
250 BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
251 uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
252 uint8 mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
253 Page page;
254 uint8 *map;
255 uint8 status;
256
257#ifdef TRACE_VISIBILITYMAP
258 elog(DEBUG1, "vm_set flags 0x%02X for %s %d",
259 flags, RelationGetRelationName(rel), heapBlk);
260#endif
261
262 Assert(InRecovery || XLogRecPtrIsInvalid(recptr));
263 Assert(InRecovery || PageIsAllVisible(BufferGetPage(heapBuf)));
264 Assert((flags & VISIBILITYMAP_VALID_BITS) == flags);
265
266 /* Must never set all_frozen bit without also setting all_visible bit */
267 Assert(flags != VISIBILITYMAP_ALL_FROZEN);
268
269 /* Check that we have the right heap page pinned, if present */
270 if (BufferIsValid(heapBuf) && BufferGetBlockNumber(heapBuf) != heapBlk)
271 elog(ERROR, "wrong heap buffer passed to visibilitymap_set");
272
273 Assert(!BufferIsValid(heapBuf) || BufferIsExclusiveLocked(heapBuf));
274
275 /* Check that we have the right VM page pinned */
276 if (!BufferIsValid(vmBuf) || BufferGetBlockNumber(vmBuf) != mapBlock)
277 elog(ERROR, "wrong VM buffer passed to visibilitymap_set");
278
279 page = BufferGetPage(vmBuf);
280 map = (uint8 *) PageGetContents(page);
281 LockBuffer(vmBuf, BUFFER_LOCK_EXCLUSIVE);
282
283 status = (map[mapByte] >> mapOffset) & VISIBILITYMAP_VALID_BITS;
284 if (flags != status)
285 {
286 START_CRIT_SECTION();
287
288 map[mapByte] |= (flags << mapOffset);
289 MarkBufferDirty(vmBuf);
290
291 if (RelationNeedsWAL(rel))
292 {
293 if (XLogRecPtrIsInvalid(recptr))
294 {
295 Assert(!InRecovery);
296 recptr = log_heap_visible(rel, heapBuf, vmBuf, cutoff_xid, flags);
297
298 /*
299 * If data checksums are enabled (or wal_log_hints=on), we
300 * need to protect the heap page from being torn.
301 *
302 * If not, then we must *not* update the heap page's LSN. In
303 * this case, the FPI for the heap page was omitted from the
304 * WAL record inserted above, so it would be incorrect to
305 * update the heap page's LSN.
306 */
307 if (XLogHintBitIsNeeded())
308 {
309 Page heapPage = BufferGetPage(heapBuf);
310
311 PageSetLSN(heapPage, recptr);
312 }
313 }
314 PageSetLSN(page, recptr);
315 }
316
317 END_CRIT_SECTION();
318 }
319
320 LockBuffer(vmBuf, BUFFER_LOCK_UNLOCK);
321 return status;
322}
323
324/*
325 * visibilitymap_get_status - get status of bits
326 *
327 * Are all tuples on heapBlk visible to all or are marked frozen, according
328 * to the visibility map?
329 *
330 * On entry, *vmbuf should be InvalidBuffer or a valid buffer returned by an
331 * earlier call to visibilitymap_pin or visibilitymap_get_status on the same
332 * relation. On return, *vmbuf is a valid buffer with the map page containing
333 * the bit for heapBlk, or InvalidBuffer. The caller is responsible for
334 * releasing *vmbuf after it's done testing and setting bits.
335 *
336 * NOTE: This function is typically called without a lock on the heap page,
337 * so somebody else could change the bit just after we look at it. In fact,
338 * since we don't lock the visibility map page either, it's even possible that
339 * someone else could have changed the bit just before we look at it, but yet
340 * we might see the old value. It is the caller's responsibility to deal with
341 * all concurrency issues!
342 */
343uint8
344 visibilitymap_get_status(Relation rel, BlockNumber heapBlk, Buffer *vmbuf)
345{
346 BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
347 uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
348 uint8 mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
349 char *map;
350 uint8 result;
351
352#ifdef TRACE_VISIBILITYMAP
353 elog(DEBUG1, "vm_get_status %s %d", RelationGetRelationName(rel), heapBlk);
354#endif
355
356 /* Reuse the old pinned buffer if possible */
357 if (BufferIsValid(*vmbuf))
358 {
359 if (BufferGetBlockNumber(*vmbuf) != mapBlock)
360 {
361 ReleaseBuffer(*vmbuf);
362 *vmbuf = InvalidBuffer;
363 }
364 }
365
366 if (!BufferIsValid(*vmbuf))
367 {
368 *vmbuf = vm_readbuf(rel, mapBlock, false);
369 if (!BufferIsValid(*vmbuf))
370 return (uint8) 0;
371 }
372
373 map = PageGetContents(BufferGetPage(*vmbuf));
374
375 /*
376 * A single byte read is atomic. There could be memory-ordering effects
377 * here, but for performance reasons we make it the caller's job to worry
378 * about that.
379 */
380 result = ((map[mapByte] >> mapOffset) & VISIBILITYMAP_VALID_BITS);
381 return result;
382}
383
384/*
385 * visibilitymap_count - count number of bits set in visibility map
386 *
387 * Note: we ignore the possibility of race conditions when the table is being
388 * extended concurrently with the call. New pages added to the table aren't
389 * going to be marked all-visible or all-frozen, so they won't affect the result.
390 */
391void
392 visibilitymap_count(Relation rel, BlockNumber *all_visible, BlockNumber *all_frozen)
393{
394 BlockNumber mapBlock;
395 BlockNumber nvisible = 0;
396 BlockNumber nfrozen = 0;
397
398 /* all_visible must be specified */
399 Assert(all_visible);
400
401 for (mapBlock = 0;; mapBlock++)
402 {
403 Buffer mapBuffer;
404 uint64 *map;
405
406 /*
407 * Read till we fall off the end of the map. We assume that any extra
408 * bytes in the last page are zeroed, so we don't bother excluding
409 * them from the count.
410 */
411 mapBuffer = vm_readbuf(rel, mapBlock, false);
412 if (!BufferIsValid(mapBuffer))
413 break;
414
415 /*
416 * We choose not to lock the page, since the result is going to be
417 * immediately stale anyway if anyone is concurrently setting or
418 * clearing bits, and we only really need an approximate value.
419 */
420 map = (uint64 *) PageGetContents(BufferGetPage(mapBuffer));
421
422 nvisible += pg_popcount_masked((const char *) map, MAPSIZE, VISIBLE_MASK8);
423 if (all_frozen)
424 nfrozen += pg_popcount_masked((const char *) map, MAPSIZE, FROZEN_MASK8);
425
426 ReleaseBuffer(mapBuffer);
427 }
428
429 *all_visible = nvisible;
430 if (all_frozen)
431 *all_frozen = nfrozen;
432}
433
434/*
435 * visibilitymap_prepare_truncate -
436 * prepare for truncation of the visibility map
437 *
438 * nheapblocks is the new size of the heap.
439 *
440 * Return the number of blocks of new visibility map.
441 * If it's InvalidBlockNumber, there is nothing to truncate;
442 * otherwise the caller is responsible for calling smgrtruncate()
443 * to truncate the visibility map pages.
444 */
445BlockNumber
446 visibilitymap_prepare_truncate(Relation rel, BlockNumber nheapblocks)
447{
448 BlockNumber newnblocks;
449
450 /* last remaining block, byte, and bit */
451 BlockNumber truncBlock = HEAPBLK_TO_MAPBLOCK(nheapblocks);
452 uint32 truncByte = HEAPBLK_TO_MAPBYTE(nheapblocks);
453 uint8 truncOffset = HEAPBLK_TO_OFFSET(nheapblocks);
454
455#ifdef TRACE_VISIBILITYMAP
456 elog(DEBUG1, "vm_truncate %s %d", RelationGetRelationName(rel), nheapblocks);
457#endif
458
459 /*
460 * If no visibility map has been created yet for this relation, there's
461 * nothing to truncate.
462 */
463 if (!smgrexists(RelationGetSmgr(rel), VISIBILITYMAP_FORKNUM))
464 return InvalidBlockNumber;
465
466 /*
467 * Unless the new size is exactly at a visibility map page boundary, the
468 * tail bits in the last remaining map page, representing truncated heap
469 * blocks, need to be cleared. This is not only tidy, but also necessary
470 * because we don't get a chance to clear the bits if the heap is extended
471 * again.
472 */
473 if (truncByte != 0 || truncOffset != 0)
474 {
475 Buffer mapBuffer;
476 Page page;
477 char *map;
478
479 newnblocks = truncBlock + 1;
480
481 mapBuffer = vm_readbuf(rel, truncBlock, false);
482 if (!BufferIsValid(mapBuffer))
483 {
484 /* nothing to do, the file was already smaller */
485 return InvalidBlockNumber;
486 }
487
488 page = BufferGetPage(mapBuffer);
489 map = PageGetContents(page);
490
491 LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE);
492
493 /* NO EREPORT(ERROR) from here till changes are logged */
494 START_CRIT_SECTION();
495
496 /* Clear out the unwanted bytes. */
497 MemSet(&map[truncByte + 1], 0, MAPSIZE - (truncByte + 1));
498
499 /*----
500 * Mask out the unwanted bits of the last remaining byte.
501 *
502 * ((1 << 0) - 1) = 00000000
503 * ((1 << 1) - 1) = 00000001
504 * ...
505 * ((1 << 6) - 1) = 00111111
506 * ((1 << 7) - 1) = 01111111
507 *----
508 */
509 map[truncByte] &= (1 << truncOffset) - 1;
510
511 /*
512 * Truncation of a relation is WAL-logged at a higher-level, and we
513 * will be called at WAL replay. But if checksums are enabled, we need
514 * to still write a WAL record to protect against a torn page, if the
515 * page is flushed to disk before the truncation WAL record. We cannot
516 * use MarkBufferDirtyHint here, because that will not dirty the page
517 * during recovery.
518 */
519 MarkBufferDirty(mapBuffer);
520 if (!InRecovery && RelationNeedsWAL(rel) && XLogHintBitIsNeeded())
521 log_newpage_buffer(mapBuffer, false);
522
523 END_CRIT_SECTION();
524
525 UnlockReleaseBuffer(mapBuffer);
526 }
527 else
528 newnblocks = truncBlock;
529
530 if (smgrnblocks(RelationGetSmgr(rel), VISIBILITYMAP_FORKNUM) <= newnblocks)
531 {
532 /* nothing to do, the file was already smaller than requested size */
533 return InvalidBlockNumber;
534 }
535
536 return newnblocks;
537}
538
539/*
540 * Read a visibility map page.
541 *
542 * If the page doesn't exist, InvalidBuffer is returned, or if 'extend' is
543 * true, the visibility map file is extended.
544 */
545static Buffer
546 vm_readbuf(Relation rel, BlockNumber blkno, bool extend)
547{
548 Buffer buf;
549 SMgrRelation reln;
550
551 /*
552 * Caution: re-using this smgr pointer could fail if the relcache entry
553 * gets closed. It's safe as long as we only do smgr-level operations
554 * between here and the last use of the pointer.
555 */
556 reln = RelationGetSmgr(rel);
557
558 /*
559 * If we haven't cached the size of the visibility map fork yet, check it
560 * first.
561 */
562 if (reln->smgr_cached_nblocks[VISIBILITYMAP_FORKNUM] == InvalidBlockNumber)
563 {
564 if (smgrexists(reln, VISIBILITYMAP_FORKNUM))
565 smgrnblocks(reln, VISIBILITYMAP_FORKNUM);
566 else
567 reln->smgr_cached_nblocks[VISIBILITYMAP_FORKNUM] = 0;
568 }
569
570 /*
571 * For reading we use ZERO_ON_ERROR mode, and initialize the page if
572 * necessary. It's always safe to clear bits, so it's better to clear
573 * corrupt pages than error out.
574 *
575 * We use the same path below to initialize pages when extending the
576 * relation, as a concurrent extension can end up with vm_extend()
577 * returning an already-initialized page.
578 */
579 if (blkno >= reln->smgr_cached_nblocks[VISIBILITYMAP_FORKNUM])
580 {
581 if (extend)
582 buf = vm_extend(rel, blkno + 1);
583 else
584 return InvalidBuffer;
585 }
586 else
587 buf = ReadBufferExtended(rel, VISIBILITYMAP_FORKNUM, blkno,
588 RBM_ZERO_ON_ERROR, NULL);
589
590 /*
591 * Initializing the page when needed is trickier than it looks, because of
592 * the possibility of multiple backends doing this concurrently, and our
593 * desire to not uselessly take the buffer lock in the normal path where
594 * the page is OK. We must take the lock to initialize the page, so
595 * recheck page newness after we have the lock, in case someone else
596 * already did it. Also, because we initially check PageIsNew with no
597 * lock, it's possible to fall through and return the buffer while someone
598 * else is still initializing the page (i.e., we might see pd_upper as set
599 * but other page header fields are still zeroes). This is harmless for
600 * callers that will take a buffer lock themselves, but some callers
601 * inspect the page without any lock at all. The latter is OK only so
602 * long as it doesn't depend on the page header having correct contents.
603 * Current usage is safe because PageGetContents() does not require that.
604 */
605 if (PageIsNew(BufferGetPage(buf)))
606 {
607 LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
608 if (PageIsNew(BufferGetPage(buf)))
609 PageInit(BufferGetPage(buf), BLCKSZ, 0);
610 LockBuffer(buf, BUFFER_LOCK_UNLOCK);
611 }
612 return buf;
613}
614
615/*
616 * Ensure that the visibility map fork is at least vm_nblocks long, extending
617 * it if necessary with zeroed pages.
618 */
619static Buffer
620 vm_extend(Relation rel, BlockNumber vm_nblocks)
621{
622 Buffer buf;
623
624 buf = ExtendBufferedRelTo(BMR_REL(rel), VISIBILITYMAP_FORKNUM, NULL,
625 EB_CREATE_FORK_IF_NEEDED |
626 EB_CLEAR_SIZE_CACHE,
627 vm_nblocks,
628 RBM_ZERO_ON_ERROR);
629
630 /*
631 * Send a shared-inval message to force other backends to close any smgr
632 * references they may have for this rel, which we are about to change.
633 * This is a useful optimization because it means that backends don't have
634 * to keep checking for creation or extension of the file, which happens
635 * infrequently.
636 */
637 CacheInvalidateSmgr(RelationGetSmgr(rel)->smgr_rlocator);
638
639 return buf;
640}
uint32 BlockNumber
Definition: block.h:31
#define InvalidBlockNumber
Definition: block.h:33
int Buffer
Definition: buf.h:23
#define InvalidBuffer
Definition: buf.h:25
bool BufferIsExclusiveLocked(Buffer buffer)
Definition: bufmgr.c:2860
BlockNumber BufferGetBlockNumber(Buffer buffer)
Definition: bufmgr.c:4198
Buffer ExtendBufferedRelTo(BufferManagerRelation bmr, ForkNumber fork, BufferAccessStrategy strategy, uint32 flags, BlockNumber extend_to, ReadBufferMode mode)
Definition: bufmgr.c:922
void ReleaseBuffer(Buffer buffer)
Definition: bufmgr.c:5338
void UnlockReleaseBuffer(Buffer buffer)
Definition: bufmgr.c:5355
void MarkBufferDirty(Buffer buffer)
Definition: bufmgr.c:2921
void LockBuffer(Buffer buffer, int mode)
Definition: bufmgr.c:5572
Buffer ReadBufferExtended(Relation reln, ForkNumber forkNum, BlockNumber blockNum, ReadBufferMode mode, BufferAccessStrategy strategy)
Definition: bufmgr.c:805
#define BUFFER_LOCK_UNLOCK
Definition: bufmgr.h:196
static Page BufferGetPage(Buffer buffer)
Definition: bufmgr.h:417
@ EB_CLEAR_SIZE_CACHE
Definition: bufmgr.h:90
@ EB_CREATE_FORK_IF_NEEDED
Definition: bufmgr.h:84
#define BUFFER_LOCK_EXCLUSIVE
Definition: bufmgr.h:198
@ RBM_ZERO_ON_ERROR
Definition: bufmgr.h:51
#define BMR_REL(p_rel)
Definition: bufmgr.h:111
static bool BufferIsValid(Buffer bufnum)
Definition: bufmgr.h:368
void PageInit(Page page, Size pageSize, Size specialSize)
Definition: bufpage.c:42
static bool PageIsAllVisible(const PageData *page)
Definition: bufpage.h:429
static bool PageIsNew(const PageData *page)
Definition: bufpage.h:234
static char * PageGetContents(Page page)
Definition: bufpage.h:258
static void PageSetLSN(Page page, XLogRecPtr lsn)
Definition: bufpage.h:391
PageData * Page
Definition: bufpage.h:82
uint8_t uint8
Definition: c.h:536
uint64_t uint64
Definition: c.h:539
uint32_t uint32
Definition: c.h:538
#define MemSet(start, val, len)
Definition: c.h:1019
uint32 TransactionId
Definition: c.h:657
#define DEBUG1
Definition: elog.h:30
#define ERROR
Definition: elog.h:39
#define elog(elevel,...)
Definition: elog.h:226
Assert(PointerIsAligned(start, uint64))
XLogRecPtr log_heap_visible(Relation rel, Buffer heap_buffer, Buffer vm_buffer, TransactionId snapshotConflictHorizon, uint8 vmflags)
Definition: heapam.c:8804
void CacheInvalidateSmgr(RelFileLocatorBackend rlocator)
Definition: inval.c:1751
#define START_CRIT_SECTION()
Definition: miscadmin.h:149
#define END_CRIT_SECTION()
Definition: miscadmin.h:151
static uint64 pg_popcount_masked(const char *buf, int bytes, bits8 mask)
Definition: pg_bitutils.h:394
static char * buf
Definition: pg_test_fsync.c:72
static SMgrRelation RelationGetSmgr(Relation rel)
Definition: rel.h:576
#define RelationGetRelationName(relation)
Definition: rel.h:548
#define RelationNeedsWAL(relation)
Definition: rel.h:637
@ VISIBILITYMAP_FORKNUM
Definition: relpath.h:60
BlockNumber smgrnblocks(SMgrRelation reln, ForkNumber forknum)
Definition: smgr.c:819
bool smgrexists(SMgrRelation reln, ForkNumber forknum)
Definition: smgr.c:462
Definition: rel.h:56
BlockNumber smgr_cached_nblocks[MAX_FORKNUM+1]
Definition: smgr.h:47
#define MAPSIZE
Definition: visibilitymap.c:108
#define FROZEN_MASK8
Definition: visibilitymap.c:123
bool visibilitymap_pin_ok(BlockNumber heapBlk, Buffer vmbuf)
Definition: visibilitymap.c:215
bool visibilitymap_clear(Relation rel, BlockNumber heapBlk, Buffer vmbuf, uint8 flags)
Definition: visibilitymap.c:138
#define VISIBLE_MASK8
Definition: visibilitymap.c:122
#define HEAPBLK_TO_OFFSET(x)
Definition: visibilitymap.c:119
void visibilitymap_pin(Relation rel, BlockNumber heapBlk, Buffer *vmbuf)
Definition: visibilitymap.c:191
uint8 visibilitymap_get_status(Relation rel, BlockNumber heapBlk, Buffer *vmbuf)
Definition: visibilitymap.c:344
static Buffer vm_extend(Relation rel, BlockNumber vm_nblocks)
Definition: visibilitymap.c:620
BlockNumber visibilitymap_prepare_truncate(Relation rel, BlockNumber nheapblocks)
Definition: visibilitymap.c:446
void visibilitymap_count(Relation rel, BlockNumber *all_visible, BlockNumber *all_frozen)
Definition: visibilitymap.c:392
static Buffer vm_readbuf(Relation rel, BlockNumber blkno, bool extend)
Definition: visibilitymap.c:546
uint8 visibilitymap_set(Relation rel, BlockNumber heapBlk, Buffer heapBuf, XLogRecPtr recptr, Buffer vmBuf, TransactionId cutoff_xid, uint8 flags)
Definition: visibilitymap.c:246
#define HEAPBLK_TO_MAPBLOCK(x)
Definition: visibilitymap.c:117
#define HEAPBLK_TO_MAPBYTE(x)
Definition: visibilitymap.c:118
#define VISIBILITYMAP_VALID_BITS
#define VISIBILITYMAP_ALL_FROZEN
#define VISIBILITYMAP_ALL_VISIBLE
#define XLogHintBitIsNeeded()
Definition: xlog.h:120
#define XLogRecPtrIsInvalid(r)
Definition: xlogdefs.h:29
uint64 XLogRecPtr
Definition: xlogdefs.h:21
XLogRecPtr log_newpage_buffer(Buffer buffer, bool page_std)
Definition: xloginsert.c:1249
bool InRecovery
Definition: xlogutils.c:50

AltStyle によって変換されたページ (->オリジナル) /