Age Owner Branch data TLA Line data Source code
1 : : /*-------------------------------------------------------------------------
2 : : *
3 : : * visibilitymap.c
4 : : * bitmap for tracking visibility of heap tuples
5 : : *
6 : : * Portions Copyright (c) 1996-2026, 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 bit(s) 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 : : * Changes to the visibility map bits are not separately WAL-logged. Callers
38 : : * must make sure that whenever a visibility map bit is cleared, the bit is
39 : : * cleared on WAL replay of the updating operation. And whenever a visibility
40 : : * map bit is set, the bit is set on WAL replay of the operation that rendered
41 : : * the page all-visible/all-frozen.
42 : : *
43 : : * The visibility map bits operate as a hint in one direction: if they are
44 : : * clear, it may still be the case that every tuple on the page is visible to
45 : : * all transactions (we just don't know that for certain). However, if they
46 : : * are set, we may skip vacuuming pages and advance relfrozenxid or skip
47 : : * reading heap pages for an index-only scan. If they are incorrectly set,
48 : : * this can lead to data corruption and wrong results.
49 : : *
50 : : * Additionally, it is critical that the heap-page level PD_ALL_VISIBLE bit be
51 : : * correctly set and cleared along with the VM bits.
52 : : *
53 : : * When clearing the VM, if a crash occurs after the heap page makes it to
54 : : * disk but before the VM page makes it to disk, replay must clear the VM or
55 : : * the next index-only scan can return wrong results or vacuum may incorrectly
56 : : * advance relfrozenxid.
57 : : *
58 : : * When setting the VM, if a crash occurs after the visibility map page makes
59 : : * it to disk and before the updated heap page makes it to disk, redo must set
60 : : * the bit on the heap page. Otherwise, the next insert, update, or delete on
61 : : * the heap page will fail to realize that the visibility map bit must be
62 : : * cleared, possibly causing index-only scans to return wrong answers.
63 : : *
64 : : * VACUUM will normally skip pages for which the visibility map bit is set;
65 : : * such pages can't contain any dead tuples and therefore don't need vacuuming.
66 : : *
67 : : * LOCKING
68 : : *
69 : : * In heapam.c, whenever a page is modified so that not all tuples on the
70 : : * page are visible to everyone anymore, the corresponding bit in the
71 : : * visibility map is cleared. In order to be crash-safe, we need to do this
72 : : * while still holding a lock on the heap page and in the same critical
73 : : * section that logs the page modification. However, we don't want to hold
74 : : * the buffer lock over any I/O that may be required to read in the visibility
75 : : * map page. To avoid this, we examine the heap page before locking it;
76 : : * if the page-level PD_ALL_VISIBLE bit is set, we pin the visibility map
77 : : * bit. Then, we lock the buffer. But this creates a race condition: there
78 : : * is a possibility that in the time it takes to lock the buffer, the
79 : : * PD_ALL_VISIBLE bit gets set. If that happens, we have to unlock the
80 : : * buffer, pin the visibility map page, and relock the buffer. This shouldn't
81 : : * happen often, because only VACUUM currently sets visibility map bits,
82 : : * and the race will only occur if VACUUM processes a given page at almost
83 : : * exactly the same time that someone tries to further modify it.
84 : : *
85 : : * To set a bit, you need to hold a lock on the heap page. That prevents
86 : : * the race condition where VACUUM sees that all tuples on the page are
87 : : * visible to everyone, but another backend modifies the page before VACUUM
88 : : * sets the bit in the visibility map.
89 : : *
90 : : * When a bit is set, the LSN of the visibility map page is updated to make
91 : : * sure that the visibility map update doesn't get written to disk before the
92 : : * WAL record of the changes that made it possible to set the bit is flushed.
93 : : * But when a bit is cleared, we don't have to do that because it's always
94 : : * safe to clear a bit in the map from correctness point of view.
95 : : *
96 : : *-------------------------------------------------------------------------
97 : : */
98 : : #include "postgres.h"
99 : :
100 : : #include "access/heapam_xlog.h"
101 : : #include "access/visibilitymap.h"
102 : : #include "access/xloginsert.h"
103 : : #include "access/xlogutils.h"
104 : : #include "miscadmin.h"
105 : : #include "port/pg_bitutils.h"
106 : : #include "storage/bufmgr.h"
107 : : #include "storage/smgr.h"
108 : : #include "utils/inval.h"
109 : : #include "utils/rel.h"
110 : :
111 : :
112 : : /*#define TRACE_VISIBILITYMAP */
113 : :
114 : : /*
115 : : * Size of the bitmap on each visibility map page, in bytes. There's no
116 : : * extra headers, so the whole page minus the standard page header is
117 : : * used for the bitmap.
118 : : */
119 : : #define MAPSIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData))
120 : :
121 : : /* Number of heap blocks we can represent in one byte */
122 : : #define HEAPBLOCKS_PER_BYTE (BITS_PER_BYTE / BITS_PER_HEAPBLOCK)
123 : :
124 : : /* Number of heap blocks we can represent in one visibility map page. */
125 : : #define HEAPBLOCKS_PER_PAGE (MAPSIZE * HEAPBLOCKS_PER_BYTE)
126 : :
127 : : /* Mapping from heap block number to the right bit in the visibility map */
128 : : #define HEAPBLK_TO_MAPBLOCK(x) ((x) / HEAPBLOCKS_PER_PAGE)
129 : : #define HEAPBLK_TO_MAPBLOCK_LIMIT(x) \
130 : : (((x) + HEAPBLOCKS_PER_PAGE - 1) / HEAPBLOCKS_PER_PAGE)
131 : : #define HEAPBLK_TO_MAPBYTE(x) (((x) % HEAPBLOCKS_PER_PAGE) / HEAPBLOCKS_PER_BYTE)
132 : : #define HEAPBLK_TO_OFFSET(x) (((x) % HEAPBLOCKS_PER_BYTE) * BITS_PER_HEAPBLOCK)
133 : :
134 : : /* Masks for counting subsets of bits in the visibility map. */
135 : : #define VISIBLE_MASK8 (0x55) /* The lower bit of each bit pair */
136 : : #define FROZEN_MASK8 (0xaa) /* The upper bit of each bit pair */
137 : :
138 : : /* prototypes for internal routines */
139 : : static Buffer vm_readbuf(Relation rel, BlockNumber blkno, bool extend);
140 : : static Buffer vm_extend(Relation rel, BlockNumber vm_nblocks);
141 : :
142 : : /*
143 : : * visibilitymap_clear - clear specified bits for one page in visibility map
144 : : *
145 : : * You must pass a buffer containing the correct map page to this function,
146 : : * which already needs to be pinned and locked exclusively.
147 : : *
148 : : * This function doesn't do any I/O. Returns true if any bits have been
149 : : * cleared and false otherwise.
150 : : */
151 : : bool
10 melanieplageman@gmai 152 :GNC 30803 : visibilitymap_clear(RelFileLocator rlocator, BlockNumber heapBlk,
153 : : Buffer vmbuf, uint8 flags)
154 : : {
6443 heikki.linnakangas@i 155 :CBC 30803 : int mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
3704 rhaas@postgresql.org 156 : 30803 : int mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
10 melanieplageman@gmai 157 : 30803 : BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
3659 andres@anarazel.de 158 : 30803 : uint8 mask = flags << mapOffset;
159 : : Page page;
160 : : char *map;
161 : 30803 : bool cleared = false;
162 : :
163 : : /* Must never clear all_visible bit while leaving all_frozen bit set */
164 [ - + ]: 30803 : Assert(flags & VISIBILITYMAP_VALID_BITS);
1286 pg@bowt.ie 165 [ - + ]: 30803 : Assert(flags != VISIBILITYMAP_ALL_VISIBLE);
166 : :
167 : : #ifdef TRACE_VISIBILITYMAP
168 : : elog(DEBUG1, "vm_clear %s %d",
169 : : relpathbackend(rlocator, MyProcNumber, MAIN_FORKNUM).str,
170 : : heapBlk);
171 : : #endif
172 : :
8 melanieplageman@gmai 173 [ + - - + ]: 30803 : if (!BufferIsValid(vmbuf) || BufferGetBlockNumber(vmbuf) != mapBlock)
8 melanieplageman@gmai 174 [ # # ]:UBC 0 : elog(ERROR, "wrong buffer passed to visibilitymap_clear");
175 : :
10 melanieplageman@gmai 176 [ - + ]:CBC 30803 : Assert(BufferIsLockedByMeInMode(vmbuf, BUFFER_LOCK_EXCLUSIVE));
177 : :
178 : 30803 : page = BufferGetPage(vmbuf);
179 : 30803 : map = PageGetContents(page);
180 : :
6443 heikki.linnakangas@i 181 [ + + ]: 30803 : if (map[mapByte] & mask)
182 : : {
183 : 26041 : map[mapByte] &= ~mask;
184 : :
1405 pg@bowt.ie 185 : 26041 : MarkBufferDirty(vmbuf);
3659 andres@anarazel.de 186 : 26041 : cleared = true;
187 : : }
188 : :
189 : 30803 : return cleared;
190 : : }
191 : :
192 : : /*
193 : : * visibilitymap_pin - pin a map page for setting a bit
194 : : *
195 : : * Setting a bit in the visibility map is a two-phase operation. First, call
196 : : * visibilitymap_pin, to pin the visibility map page containing the bit for
197 : : * the heap page. Because that can require I/O to read the map page, you
198 : : * shouldn't hold a lock on the heap page while doing that. Then, call
199 : : * visibilitymap_set to actually set the bit.
200 : : *
201 : : * On entry, *vmbuf should be InvalidBuffer or a valid buffer returned by
202 : : * an earlier call to visibilitymap_pin or visibilitymap_get_status on the same
203 : : * relation. On return, *vmbuf is a valid buffer with the map page containing
204 : : * the bit for heapBlk.
205 : : *
206 : : * If the page doesn't exist in the map file yet, it is extended.
207 : : */
208 : : void
1405 pg@bowt.ie 209 : 703786 : visibilitymap_pin(Relation rel, BlockNumber heapBlk, Buffer *vmbuf)
210 : : {
6443 heikki.linnakangas@i 211 : 703786 : BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
212 : :
213 : : /* Reuse the old pinned buffer if possible */
1405 pg@bowt.ie 214 [ + + ]: 703786 : if (BufferIsValid(*vmbuf))
215 : : {
216 [ + - ]: 198513 : if (BufferGetBlockNumber(*vmbuf) == mapBlock)
6443 heikki.linnakangas@i 217 : 198513 : return;
218 : :
1405 pg@bowt.ie 219 :UBC 0 : ReleaseBuffer(*vmbuf);
220 : : }
1405 pg@bowt.ie 221 :CBC 505273 : *vmbuf = vm_readbuf(rel, mapBlock, true);
222 : : }
223 : :
224 : : /*
225 : : * visibilitymap_pin_ok - do we already have the correct page pinned?
226 : : *
227 : : * On entry, vmbuf should be InvalidBuffer or a valid buffer returned by
228 : : * an earlier call to visibilitymap_pin or visibilitymap_get_status on the same
229 : : * relation. The return value indicates whether the buffer covers the
230 : : * given heapBlk.
231 : : */
232 : : bool
233 : 22248 : visibilitymap_pin_ok(BlockNumber heapBlk, Buffer vmbuf)
234 : : {
5513 rhaas@postgresql.org 235 : 22248 : BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
236 : :
1405 pg@bowt.ie 237 [ + + + - ]: 22248 : return BufferIsValid(vmbuf) && BufferGetBlockNumber(vmbuf) == mapBlock;
238 : : }
239 : :
240 : : /*
241 : : * Set VM (visibility map) flags in the VM block in vmBuf.
242 : : *
243 : : * This function is intended for callers that log VM changes together
244 : : * with the heap page modifications that rendered the page all-visible.
245 : : *
246 : : * vmBuf must be pinned and exclusively locked, and it must cover the VM bits
247 : : * corresponding to heapBlk.
248 : : *
249 : : * In normal operation (not recovery), this must be called inside a critical
250 : : * section that also applies the necessary heap page changes and, if
251 : : * applicable, emits WAL.
252 : : *
253 : : * The caller is responsible for ensuring consistency between the heap page
254 : : * and the VM page by holding a pin and exclusive lock on the buffer
255 : : * containing heapBlk.
256 : : *
257 : : * rlocator is used only for debugging messages.
258 : : */
259 : : void
123 melanieplageman@gmai 260 : 101053 : visibilitymap_set(BlockNumber heapBlk,
261 : : Buffer vmBuf, uint8 flags,
262 : : RelFileLocator rlocator)
263 : : {
289 264 : 101053 : BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
265 : 101053 : uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
266 : 101053 : uint8 mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
267 : : Page page;
268 : : uint8 *map;
269 : : uint8 status;
270 : :
271 : : #ifdef TRACE_VISIBILITYMAP
272 : : elog(DEBUG1, "vm_set flags 0x%02X for %s %d",
273 : : flags,
274 : : relpathbackend(rlocator, MyProcNumber, MAIN_FORKNUM).str,
275 : : heapBlk);
276 : : #endif
277 : :
278 : : /* Call in same critical section where WAL is emitted. */
279 [ + + - + ]: 101053 : Assert(InRecovery || CritSectionCount > 0);
280 : :
281 : : /* Flags should be valid. Also never clear bits with this function */
282 [ - + ]: 101053 : Assert((flags & VISIBILITYMAP_VALID_BITS) == flags);
283 : :
284 : : /* Must never set all_frozen bit without also setting all_visible bit */
285 [ - + ]: 101053 : Assert(flags != VISIBILITYMAP_ALL_FROZEN);
286 : :
287 : : /* Check that we have the right VM page pinned */
288 [ + - - + ]: 101053 : if (!BufferIsValid(vmBuf) || BufferGetBlockNumber(vmBuf) != mapBlock)
289 melanieplageman@gmai 289 [ # # ]:UBC 0 : elog(ERROR, "wrong VM buffer passed to visibilitymap_set");
290 : :
289 melanieplageman@gmai 291 [ - + ]:CBC 101053 : Assert(BufferIsLockedByMeInMode(vmBuf, BUFFER_LOCK_EXCLUSIVE));
292 : :
293 : 101053 : page = BufferGetPage(vmBuf);
294 : 101053 : map = (uint8 *) PageGetContents(page);
295 : :
296 : 101053 : status = (map[mapByte] >> mapOffset) & VISIBILITYMAP_VALID_BITS;
297 [ + - ]: 101053 : if (flags != status)
298 : : {
299 : 101053 : map[mapByte] |= (flags << mapOffset);
300 : 101053 : MarkBufferDirty(vmBuf);
301 : : }
302 : 101053 : }
303 : :
304 : : /*
305 : : * visibilitymap_get_status - get status of bits
306 : : *
307 : : * Are all tuples on heapBlk visible to all or are marked frozen, according
308 : : * to the visibility map?
309 : : *
310 : : * On entry, *vmbuf should be InvalidBuffer or a valid buffer returned by an
311 : : * earlier call to visibilitymap_pin or visibilitymap_get_status on the same
312 : : * relation. On return, *vmbuf is a valid buffer with the map page containing
313 : : * the bit for heapBlk, or InvalidBuffer. The caller is responsible for
314 : : * releasing *vmbuf after it's done testing and setting bits.
315 : : *
316 : : * NOTE: This function is typically called without a lock on the heap page,
317 : : * so somebody else could change the bit just after we look at it. In fact,
318 : : * since we don't lock the visibility map page either, it's even possible that
319 : : * someone else could have changed the bit just before we look at it, but yet
320 : : * we might see the old value. It is the caller's responsibility to deal with
321 : : * all concurrency issues!
322 : : */
323 : : uint8
1405 pg@bowt.ie 324 : 4310710 : visibilitymap_get_status(Relation rel, BlockNumber heapBlk, Buffer *vmbuf)
325 : : {
6443 heikki.linnakangas@i 326 : 4310710 : BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
327 : 4310710 : uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
3704 rhaas@postgresql.org 328 : 4310710 : uint8 mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
329 : : char *map;
330 : : uint8 result;
331 : :
332 : : #ifdef TRACE_VISIBILITYMAP
333 : : elog(DEBUG1, "vm_get_status %s %d", RelationGetRelationName(rel), heapBlk);
334 : : #endif
335 : :
336 : : /* Reuse the old pinned buffer if possible */
1405 pg@bowt.ie 337 [ + + ]: 4310710 : if (BufferIsValid(*vmbuf))
338 : : {
339 [ - + ]: 4175504 : if (BufferGetBlockNumber(*vmbuf) != mapBlock)
340 : : {
1405 pg@bowt.ie 341 :UBC 0 : ReleaseBuffer(*vmbuf);
342 : 0 : *vmbuf = InvalidBuffer;
343 : : }
344 : : }
345 : :
1405 pg@bowt.ie 346 [ + + ]:CBC 4310710 : if (!BufferIsValid(*vmbuf))
347 : : {
348 : 135206 : *vmbuf = vm_readbuf(rel, mapBlock, false);
349 [ + + ]: 135206 : if (!BufferIsValid(*vmbuf))
366 nathan@postgresql.or 350 : 49737 : return (uint8) 0;
351 : : }
352 : :
1405 pg@bowt.ie 353 : 4260973 : map = PageGetContents(BufferGetPage(*vmbuf));
354 : :
355 : : /*
356 : : * A single byte read is atomic. There could be memory-ordering effects
357 : : * here, but for performance reasons we make it the caller's job to worry
358 : : * about that.
359 : : */
3704 rhaas@postgresql.org 360 : 4260973 : result = ((map[mapByte] >> mapOffset) & VISIBILITYMAP_VALID_BITS);
361 : 4260973 : return result;
362 : : }
363 : :
364 : : /*
365 : : * visibilitymap_count - count number of bits set in visibility map
366 : : *
367 : : * Note: we ignore the possibility of race conditions when the table is being
368 : : * extended concurrently with the call. New pages added to the table aren't
369 : : * going to be marked all-visible or all-frozen, so they won't affect the result.
370 : : */
371 : : void
3798 372 : 34458 : visibilitymap_count(Relation rel, BlockNumber *all_visible, BlockNumber *all_frozen)
373 : : {
374 : : BlockNumber mapBlock;
2717 tgl@sss.pgh.pa.us 375 : 34458 : BlockNumber nvisible = 0;
376 : 34458 : BlockNumber nfrozen = 0;
377 : :
378 : : /* all_visible must be specified */
3798 rhaas@postgresql.org 379 [ - + ]: 34458 : Assert(all_visible);
380 : :
5158 bruce@momjian.us 381 : 34458 : for (mapBlock = 0;; mapBlock++)
5398 tgl@sss.pgh.pa.us 382 : 10999 : {
383 : : Buffer mapBuffer;
384 : : uint64 *map;
385 : :
386 : : /*
387 : : * Read till we fall off the end of the map. We assume that any extra
388 : : * bytes in the last page are zeroed, so we don't bother excluding
389 : : * them from the count.
390 : : */
391 : 45457 : mapBuffer = vm_readbuf(rel, mapBlock, false);
392 [ + + ]: 45457 : if (!BufferIsValid(mapBuffer))
393 : 34458 : break;
394 : :
395 : : /*
396 : : * We choose not to lock the page, since the result is going to be
397 : : * immediately stale anyway if anyone is concurrently setting or
398 : : * clearing bits, and we only really need an approximate value.
399 : : */
2717 400 : 10999 : map = (uint64 *) PageGetContents(BufferGetPage(mapBuffer));
401 : :
840 nathan@postgresql.or 402 : 10999 : nvisible += pg_popcount_masked((const char *) map, MAPSIZE, VISIBLE_MASK8);
403 [ + - ]: 10999 : if (all_frozen)
404 : 10999 : nfrozen += pg_popcount_masked((const char *) map, MAPSIZE, FROZEN_MASK8);
405 : :
5398 tgl@sss.pgh.pa.us 406 : 10999 : ReleaseBuffer(mapBuffer);
407 : : }
408 : :
2717 409 : 34458 : *all_visible = nvisible;
410 [ + - ]: 34458 : if (all_frozen)
411 : 34458 : *all_frozen = nfrozen;
5398 412 : 34458 : }
413 : :
414 : : /*
415 : : * visibilitymap_prepare_truncate -
416 : : * prepare for truncation of the visibility map
417 : : *
418 : : * nheapblocks is the new size of the heap.
419 : : *
420 : : * Return the number of blocks of new visibility map.
421 : : * If it's InvalidBlockNumber, there is nothing to truncate;
422 : : * otherwise the caller is responsible for calling smgrtruncate()
423 : : * to truncate the visibility map pages.
424 : : */
425 : : BlockNumber
2496 fujii@postgresql.org 426 : 280 : visibilitymap_prepare_truncate(Relation rel, BlockNumber nheapblocks)
427 : : {
428 : : BlockNumber newnblocks;
429 : :
430 : : /* last remaining block, byte, and bit */
6443 heikki.linnakangas@i 431 : 280 : BlockNumber truncBlock = HEAPBLK_TO_MAPBLOCK(nheapblocks);
6253 bruce@momjian.us 432 : 280 : uint32 truncByte = HEAPBLK_TO_MAPBYTE(nheapblocks);
3704 rhaas@postgresql.org 433 : 280 : uint8 truncOffset = HEAPBLK_TO_OFFSET(nheapblocks);
434 : :
435 : : #ifdef TRACE_VISIBILITYMAP
436 : : elog(DEBUG1, "vm_truncate %s %d", RelationGetRelationName(rel), nheapblocks);
437 : : #endif
438 : :
439 : : /*
440 : : * If no visibility map has been created yet for this relation, there's
441 : : * nothing to truncate.
442 : : */
1839 tgl@sss.pgh.pa.us 443 [ - + ]: 280 : if (!smgrexists(RelationGetSmgr(rel), VISIBILITYMAP_FORKNUM))
2496 fujii@postgresql.org 444 :UBC 0 : return InvalidBlockNumber;
445 : :
446 : : /*
447 : : * Unless the new size is exactly at a visibility map page boundary, the
448 : : * tail bits in the last remaining map page, representing truncated heap
449 : : * blocks, need to be cleared. This is not only tidy, but also necessary
450 : : * because we don't get a chance to clear the bits if the heap is extended
451 : : * again.
452 : : */
3704 rhaas@postgresql.org 453 [ + + + + ]:CBC 280 : if (truncByte != 0 || truncOffset != 0)
6443 heikki.linnakangas@i 454 : 173 : {
455 : : Buffer mapBuffer;
456 : : Page page;
457 : : char *map;
458 : :
459 : 173 : newnblocks = truncBlock + 1;
460 : :
461 : 173 : mapBuffer = vm_readbuf(rel, truncBlock, false);
462 [ - + ]: 173 : if (!BufferIsValid(mapBuffer))
463 : : {
464 : : /* nothing to do, the file was already smaller */
2496 fujii@postgresql.org 465 :UBC 0 : return InvalidBlockNumber;
466 : : }
467 : :
3748 kgrittn@postgresql.o 468 :CBC 173 : page = BufferGetPage(mapBuffer);
6443 heikki.linnakangas@i 469 : 173 : map = PageGetContents(page);
470 : :
471 : 173 : LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE);
472 : :
473 : : /* NO EREPORT(ERROR) from here till changes are logged */
3566 474 : 173 : START_CRIT_SECTION();
475 : :
476 : : /* Clear out the unwanted bytes. */
6443 477 [ + + + - : 173 : MemSet(&map[truncByte + 1], 0, MAPSIZE - (truncByte + 1));
+ - - + -
- ]
478 : :
479 : : /*----
480 : : * Mask out the unwanted bits of the last remaining byte.
481 : : *
482 : : * ((1 << 0) - 1) = 00000000
483 : : * ((1 << 1) - 1) = 00000001
484 : : * ...
485 : : * ((1 << 6) - 1) = 00111111
486 : : * ((1 << 7) - 1) = 01111111
487 : : *----
488 : : */
3704 rhaas@postgresql.org 489 : 173 : map[truncByte] &= (1 << truncOffset) - 1;
490 : :
491 : : /*
492 : : * Truncation of a relation is WAL-logged at a higher-level, and we
493 : : * will be called at WAL replay. But if checksums are enabled, we need
494 : : * to still write a WAL record to protect against a torn page, if the
495 : : * page is flushed to disk before the truncation WAL record. We cannot
496 : : * use MarkBufferDirtyHint here, because that will not dirty the page
497 : : * during recovery.
498 : : */
6443 heikki.linnakangas@i 499 : 173 : MarkBufferDirty(mapBuffer);
3566 500 [ + + + + : 173 : if (!InRecovery && RelationNeedsWAL(rel) && XLogHintBitIsNeeded())
+ + + - +
- + + +
- ]
501 : 151 : log_newpage_buffer(mapBuffer, false);
502 : :
503 [ - + ]: 173 : END_CRIT_SECTION();
504 : :
6443 505 : 173 : UnlockReleaseBuffer(mapBuffer);
506 : : }
507 : : else
508 : 107 : newnblocks = truncBlock;
509 : :
1839 tgl@sss.pgh.pa.us 510 [ + + ]: 280 : if (smgrnblocks(RelationGetSmgr(rel), VISIBILITYMAP_FORKNUM) <= newnblocks)
511 : : {
512 : : /* nothing to do, the file was already smaller than requested size */
2496 fujii@postgresql.org 513 : 173 : return InvalidBlockNumber;
514 : : }
515 : :
516 : 107 : return newnblocks;
517 : : }
518 : :
519 : : /*
520 : : * visibilitymap_truncation_length -
521 : : * compute truncation length for visibility map
522 : : *
523 : : * Given a proposed truncation length for the main fork, compute the
524 : : * correct truncation length for the visibility map. Should return the
525 : : * same answer as visibilitymap_prepare_truncate(), but without modifying
526 : : * anything.
527 : : */
528 : : BlockNumber
138 rhaas@postgresql.org 529 : 1 : visibilitymap_truncation_length(BlockNumber nheapblocks)
530 : : {
531 : 1 : return HEAPBLK_TO_MAPBLOCK_LIMIT(nheapblocks);
532 : : }
533 : :
534 : : /*
535 : : * Read a visibility map page.
536 : : *
537 : : * If the page doesn't exist, InvalidBuffer is returned, or if 'extend' is
538 : : * true, the visibility map file is extended.
539 : : */
540 : : static Buffer
6443 heikki.linnakangas@i 541 : 686109 : vm_readbuf(Relation rel, BlockNumber blkno, bool extend)
542 : : {
543 : : Buffer buf;
544 : : SMgrRelation reln;
545 : :
546 : : /*
547 : : * Caution: re-using this smgr pointer could fail if the relcache entry
548 : : * gets closed. It's safe as long as we only do smgr-level operations
549 : : * between here and the last use of the pointer.
550 : : */
1839 tgl@sss.pgh.pa.us 551 : 686109 : reln = RelationGetSmgr(rel);
552 : :
553 : : /*
554 : : * If we haven't cached the size of the visibility map fork yet, check it
555 : : * first.
556 : : */
557 [ + + ]: 686109 : if (reln->smgr_cached_nblocks[VISIBILITYMAP_FORKNUM] == InvalidBlockNumber)
558 : : {
559 [ + + ]: 55773 : if (smgrexists(reln, VISIBILITYMAP_FORKNUM))
560 : 29505 : smgrnblocks(reln, VISIBILITYMAP_FORKNUM);
561 : : else
562 : 26268 : reln->smgr_cached_nblocks[VISIBILITYMAP_FORKNUM] = 0;
563 : : }
564 : :
565 : : /*
566 : : * For reading we use ZERO_ON_ERROR mode, and initialize the page if
567 : : * necessary. It's always safe to clear bits, so it's better to clear
568 : : * corrupt pages than error out.
569 : : *
570 : : * We use the same path below to initialize pages when extending the
571 : : * relation, as a concurrent extension can end up with vm_extend()
572 : : * returning an already-initialized page.
573 : : */
574 [ + + ]: 686109 : if (blkno >= reln->smgr_cached_nblocks[VISIBILITYMAP_FORKNUM])
575 : : {
6443 heikki.linnakangas@i 576 [ + + ]: 88727 : if (extend)
1207 andres@anarazel.de 577 : 4532 : buf = vm_extend(rel, blkno + 1);
578 : : else
6443 heikki.linnakangas@i 579 : 84195 : return InvalidBuffer;
580 : : }
581 : : else
1207 andres@anarazel.de 582 : 597382 : buf = ReadBufferExtended(rel, VISIBILITYMAP_FORKNUM, blkno,
583 : : RBM_ZERO_ON_ERROR, NULL);
584 : :
585 : : /*
586 : : * Initializing the page when needed is trickier than it looks, because of
587 : : * the possibility of multiple backends doing this concurrently, and our
588 : : * desire to not uselessly take the buffer lock in the normal path where
589 : : * the page is OK. We must take the lock to initialize the page, so
590 : : * recheck page newness after we have the lock, in case someone else
591 : : * already did it. Also, because we initially check PageIsNew with no
592 : : * lock, it's possible to fall through and return the buffer while someone
593 : : * else is still initializing the page (i.e., we might see pd_upper as set
594 : : * but other page header fields are still zeroes). This is harmless for
595 : : * callers that will take a buffer lock themselves, but some callers
596 : : * inspect the page without any lock at all. The latter is OK only so
597 : : * long as it doesn't depend on the page header having correct contents.
598 : : * Current usage is safe because PageGetContents() does not require that.
599 : : */
3748 kgrittn@postgresql.o 600 [ + + ]: 601914 : if (PageIsNew(BufferGetPage(buf)))
601 : : {
2934 tgl@sss.pgh.pa.us 602 : 4934 : LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
603 [ + - ]: 4934 : if (PageIsNew(BufferGetPage(buf)))
604 : 4934 : PageInit(BufferGetPage(buf), BLCKSZ, 0);
605 : 4934 : LockBuffer(buf, BUFFER_LOCK_UNLOCK);
606 : : }
6443 heikki.linnakangas@i 607 : 601914 : return buf;
608 : : }
609 : :
610 : : /*
611 : : * Ensure that the visibility map fork is at least vm_nblocks long, extending
612 : : * it if necessary with zeroed pages.
613 : : */
614 : : static Buffer
615 : 4532 : vm_extend(Relation rel, BlockNumber vm_nblocks)
616 : : {
617 : : Buffer buf;
618 : :
1067 tmunro@postgresql.or 619 : 4532 : buf = ExtendBufferedRelTo(BMR_REL(rel), VISIBILITYMAP_FORKNUM, NULL,
620 : : EB_CREATE_FORK_IF_NEEDED |
621 : : EB_CLEAR_SIZE_CACHE,
622 : : vm_nblocks,
623 : : RBM_ZERO_ON_ERROR);
624 : :
625 : : /*
626 : : * Send a shared-inval message to force other backends to close any smgr
627 : : * references they may have for this rel, which we are about to change.
628 : : * This is a useful optimization because it means that backends don't have
629 : : * to keep checking for creation or extension of the file, which happens
630 : : * infrequently.
631 : : */
1207 andres@anarazel.de 632 : 4532 : CacheInvalidateSmgr(RelationGetSmgr(rel)->smgr_rlocator);
633 : :
634 : 4532 : return buf;
635 : : }
|
