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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952
|
/*-------------------------------------------------------------------------
*
* pg_visibility.c
* display visibility map information and page-level visibility bits
*
* Copyright (c) 2016-2025, PostgreSQL Global Development Group
*
* contrib/pg_visibility/pg_visibility.c
*-------------------------------------------------------------------------
*/
#include "postgres.h"
#include "access/heapam.h"
#include "access/htup_details.h"
#include "access/visibilitymap.h"
#include "access/xloginsert.h"
#include "catalog/pg_type.h"
#include "catalog/storage_xlog.h"
#include "funcapi.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "storage/proc.h"
#include "storage/procarray.h"
#include "storage/read_stream.h"
#include "storage/smgr.h"
#include "utils/rel.h"
PG_MODULE_MAGIC_EXT(
.name = "pg_visibility",
.version = PG_VERSION
);
typedef struct vbits
{
BlockNumber next;
BlockNumber count;
uint8 bits[FLEXIBLE_ARRAY_MEMBER];
} vbits;
typedef struct corrupt_items
{
BlockNumber next;
BlockNumber count;
ItemPointer tids;
} corrupt_items;
/* for collect_corrupt_items_read_stream_next_block */
struct collect_corrupt_items_read_stream_private
{
bool all_frozen;
bool all_visible;
BlockNumber current_blocknum;
BlockNumber last_exclusive;
Relation rel;
Buffer vmbuffer;
};
PG_FUNCTION_INFO_V1(pg_visibility_map);
PG_FUNCTION_INFO_V1(pg_visibility_map_rel);
PG_FUNCTION_INFO_V1(pg_visibility);
PG_FUNCTION_INFO_V1(pg_visibility_rel);
PG_FUNCTION_INFO_V1(pg_visibility_map_summary);
PG_FUNCTION_INFO_V1(pg_check_frozen);
PG_FUNCTION_INFO_V1(pg_check_visible);
PG_FUNCTION_INFO_V1(pg_truncate_visibility_map);
static TupleDesc pg_visibility_tupdesc(bool include_blkno, bool include_pd);
static vbits *collect_visibility_data(Oid relid, bool include_pd);
static corrupt_items *collect_corrupt_items(Oid relid, bool all_visible,
bool all_frozen);
static void record_corrupt_item(corrupt_items *items, ItemPointer tid);
static bool tuple_all_visible(HeapTuple tup, TransactionId OldestXmin,
Buffer buffer);
static void check_relation_relkind(Relation rel);
/*
* Visibility map information for a single block of a relation.
*
* Note: the VM code will silently return zeroes for pages past the end
* of the map, so we allow probes up to MaxBlockNumber regardless of the
* actual relation size.
*/
Datum
pg_visibility_map(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 blkno = PG_GETARG_INT64(1);
int32 mapbits;
Relation rel;
Buffer vmbuffer = InvalidBuffer;
TupleDesc tupdesc;
Datum values[2];
bool nulls[2] = {0};
rel = relation_open(relid, AccessShareLock);
/* Only some relkinds have a visibility map */
check_relation_relkind(rel);
if (blkno < 0 || blkno > MaxBlockNumber)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid block number")));
tupdesc = pg_visibility_tupdesc(false, false);
mapbits = (int32) visibilitymap_get_status(rel, blkno, &vmbuffer);
if (vmbuffer != InvalidBuffer)
ReleaseBuffer(vmbuffer);
values[0] = BoolGetDatum((mapbits & VISIBILITYMAP_ALL_VISIBLE) != 0);
values[1] = BoolGetDatum((mapbits & VISIBILITYMAP_ALL_FROZEN) != 0);
relation_close(rel, AccessShareLock);
PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
}
/*
* Visibility map information for a single block of a relation, plus the
* page-level information for the same block.
*/
Datum
pg_visibility(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
int64 blkno = PG_GETARG_INT64(1);
int32 mapbits;
Relation rel;
Buffer vmbuffer = InvalidBuffer;
Buffer buffer;
Page page;
TupleDesc tupdesc;
Datum values[3];
bool nulls[3] = {0};
rel = relation_open(relid, AccessShareLock);
/* Only some relkinds have a visibility map */
check_relation_relkind(rel);
if (blkno < 0 || blkno > MaxBlockNumber)
ereport(ERROR,
(errcode(ERRCODE_INVALID_PARAMETER_VALUE),
errmsg("invalid block number")));
tupdesc = pg_visibility_tupdesc(false, true);
mapbits = (int32) visibilitymap_get_status(rel, blkno, &vmbuffer);
if (vmbuffer != InvalidBuffer)
ReleaseBuffer(vmbuffer);
values[0] = BoolGetDatum((mapbits & VISIBILITYMAP_ALL_VISIBLE) != 0);
values[1] = BoolGetDatum((mapbits & VISIBILITYMAP_ALL_FROZEN) != 0);
/* Here we have to explicitly check rel size ... */
if (blkno < RelationGetNumberOfBlocks(rel))
{
buffer = ReadBuffer(rel, blkno);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
values[2] = BoolGetDatum(PageIsAllVisible(page));
UnlockReleaseBuffer(buffer);
}
else
{
/* As with the vismap, silently return 0 for pages past EOF */
values[2] = BoolGetDatum(false);
}
relation_close(rel, AccessShareLock);
PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
}
/*
* Visibility map information for every block in a relation.
*/
Datum
pg_visibility_map_rel(PG_FUNCTION_ARGS)
{
FuncCallContext *funcctx;
vbits *info;
if (SRF_IS_FIRSTCALL())
{
Oid relid = PG_GETARG_OID(0);
MemoryContext oldcontext;
funcctx = SRF_FIRSTCALL_INIT();
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
funcctx->tuple_desc = pg_visibility_tupdesc(true, false);
/* collect_visibility_data will verify the relkind */
funcctx->user_fctx = collect_visibility_data(relid, false);
MemoryContextSwitchTo(oldcontext);
}
funcctx = SRF_PERCALL_SETUP();
info = (vbits *) funcctx->user_fctx;
if (info->next < info->count)
{
Datum values[3];
bool nulls[3] = {0};
HeapTuple tuple;
values[0] = Int64GetDatum(info->next);
values[1] = BoolGetDatum((info->bits[info->next] & (1 << 0)) != 0);
values[2] = BoolGetDatum((info->bits[info->next] & (1 << 1)) != 0);
info->next++;
tuple = heap_form_tuple(funcctx->tuple_desc, values, nulls);
SRF_RETURN_NEXT(funcctx, HeapTupleGetDatum(tuple));
}
SRF_RETURN_DONE(funcctx);
}
/*
* Visibility map information for every block in a relation, plus the page
* level information for each block.
*/
Datum
pg_visibility_rel(PG_FUNCTION_ARGS)
{
FuncCallContext *funcctx;
vbits *info;
if (SRF_IS_FIRSTCALL())
{
Oid relid = PG_GETARG_OID(0);
MemoryContext oldcontext;
funcctx = SRF_FIRSTCALL_INIT();
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
funcctx->tuple_desc = pg_visibility_tupdesc(true, true);
/* collect_visibility_data will verify the relkind */
funcctx->user_fctx = collect_visibility_data(relid, true);
MemoryContextSwitchTo(oldcontext);
}
funcctx = SRF_PERCALL_SETUP();
info = (vbits *) funcctx->user_fctx;
if (info->next < info->count)
{
Datum values[4];
bool nulls[4] = {0};
HeapTuple tuple;
values[0] = Int64GetDatum(info->next);
values[1] = BoolGetDatum((info->bits[info->next] & (1 << 0)) != 0);
values[2] = BoolGetDatum((info->bits[info->next] & (1 << 1)) != 0);
values[3] = BoolGetDatum((info->bits[info->next] & (1 << 2)) != 0);
info->next++;
tuple = heap_form_tuple(funcctx->tuple_desc, values, nulls);
SRF_RETURN_NEXT(funcctx, HeapTupleGetDatum(tuple));
}
SRF_RETURN_DONE(funcctx);
}
/*
* Count the number of all-visible and all-frozen pages in the visibility
* map for a particular relation.
*/
Datum
pg_visibility_map_summary(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
Relation rel;
BlockNumber nblocks;
BlockNumber blkno;
Buffer vmbuffer = InvalidBuffer;
int64 all_visible = 0;
int64 all_frozen = 0;
TupleDesc tupdesc;
Datum values[2];
bool nulls[2] = {0};
rel = relation_open(relid, AccessShareLock);
/* Only some relkinds have a visibility map */
check_relation_relkind(rel);
nblocks = RelationGetNumberOfBlocks(rel);
for (blkno = 0; blkno < nblocks; ++blkno)
{
int32 mapbits;
/* Make sure we are interruptible. */
CHECK_FOR_INTERRUPTS();
/* Get map info. */
mapbits = (int32) visibilitymap_get_status(rel, blkno, &vmbuffer);
if ((mapbits & VISIBILITYMAP_ALL_VISIBLE) != 0)
++all_visible;
if ((mapbits & VISIBILITYMAP_ALL_FROZEN) != 0)
++all_frozen;
}
/* Clean up. */
if (vmbuffer != InvalidBuffer)
ReleaseBuffer(vmbuffer);
relation_close(rel, AccessShareLock);
if (get_call_result_type(fcinfo, NULL, &tupdesc) != TYPEFUNC_COMPOSITE)
elog(ERROR, "return type must be a row type");
values[0] = Int64GetDatum(all_visible);
values[1] = Int64GetDatum(all_frozen);
PG_RETURN_DATUM(HeapTupleGetDatum(heap_form_tuple(tupdesc, values, nulls)));
}
/*
* Return the TIDs of non-frozen tuples present in pages marked all-frozen
* in the visibility map. We hope no one will ever find any, but there could
* be bugs, database corruption, etc.
*/
Datum
pg_check_frozen(PG_FUNCTION_ARGS)
{
FuncCallContext *funcctx;
corrupt_items *items;
if (SRF_IS_FIRSTCALL())
{
Oid relid = PG_GETARG_OID(0);
MemoryContext oldcontext;
funcctx = SRF_FIRSTCALL_INIT();
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
/* collect_corrupt_items will verify the relkind */
funcctx->user_fctx = collect_corrupt_items(relid, false, true);
MemoryContextSwitchTo(oldcontext);
}
funcctx = SRF_PERCALL_SETUP();
items = (corrupt_items *) funcctx->user_fctx;
if (items->next < items->count)
SRF_RETURN_NEXT(funcctx, PointerGetDatum(&items->tids[items->next++]));
SRF_RETURN_DONE(funcctx);
}
/*
* Return the TIDs of not-all-visible tuples in pages marked all-visible
* in the visibility map. We hope no one will ever find any, but there could
* be bugs, database corruption, etc.
*/
Datum
pg_check_visible(PG_FUNCTION_ARGS)
{
FuncCallContext *funcctx;
corrupt_items *items;
if (SRF_IS_FIRSTCALL())
{
Oid relid = PG_GETARG_OID(0);
MemoryContext oldcontext;
funcctx = SRF_FIRSTCALL_INIT();
oldcontext = MemoryContextSwitchTo(funcctx->multi_call_memory_ctx);
/* collect_corrupt_items will verify the relkind */
funcctx->user_fctx = collect_corrupt_items(relid, true, false);
MemoryContextSwitchTo(oldcontext);
}
funcctx = SRF_PERCALL_SETUP();
items = (corrupt_items *) funcctx->user_fctx;
if (items->next < items->count)
SRF_RETURN_NEXT(funcctx, PointerGetDatum(&items->tids[items->next++]));
SRF_RETURN_DONE(funcctx);
}
/*
* Remove the visibility map fork for a relation. If there turn out to be
* any bugs in the visibility map code that require rebuilding the VM, this
* provides users with a way to do it that is cleaner than shutting down the
* server and removing files by hand.
*
* This is a cut-down version of RelationTruncate.
*/
Datum
pg_truncate_visibility_map(PG_FUNCTION_ARGS)
{
Oid relid = PG_GETARG_OID(0);
Relation rel;
ForkNumber fork;
BlockNumber block;
BlockNumber old_block;
rel = relation_open(relid, AccessExclusiveLock);
/* Only some relkinds have a visibility map */
check_relation_relkind(rel);
/* Forcibly reset cached file size */
RelationGetSmgr(rel)->smgr_cached_nblocks[VISIBILITYMAP_FORKNUM] = InvalidBlockNumber;
/* Compute new and old size before entering critical section. */
fork = VISIBILITYMAP_FORKNUM;
block = visibilitymap_prepare_truncate(rel, 0);
old_block = BlockNumberIsValid(block) ? smgrnblocks(RelationGetSmgr(rel), fork) : 0;
/*
* WAL-logging, buffer dropping, file truncation must be atomic and all on
* one side of a checkpoint. See RelationTruncate() for discussion.
*/
Assert((MyProc->delayChkptFlags & (DELAY_CHKPT_START | DELAY_CHKPT_COMPLETE)) == 0);
MyProc->delayChkptFlags |= DELAY_CHKPT_START | DELAY_CHKPT_COMPLETE;
START_CRIT_SECTION();
if (RelationNeedsWAL(rel))
{
XLogRecPtr lsn;
xl_smgr_truncate xlrec;
xlrec.blkno = 0;
xlrec.rlocator = rel->rd_locator;
xlrec.flags = SMGR_TRUNCATE_VM;
XLogBeginInsert();
XLogRegisterData(&xlrec, sizeof(xlrec));
lsn = XLogInsert(RM_SMGR_ID,
XLOG_SMGR_TRUNCATE | XLR_SPECIAL_REL_UPDATE);
XLogFlush(lsn);
}
if (BlockNumberIsValid(block))
smgrtruncate(RelationGetSmgr(rel), &fork, 1, &old_block, &block);
END_CRIT_SECTION();
MyProc->delayChkptFlags &= ~(DELAY_CHKPT_START | DELAY_CHKPT_COMPLETE);
/*
* Release the lock right away, not at commit time.
*
* It would be a problem to release the lock prior to commit if this
* truncate operation sends any transactional invalidation messages. Other
* backends would potentially be able to lock the relation without
* processing them in the window of time between when we release the lock
* here and when we sent the messages at our eventual commit. However,
* we're currently only sending a non-transactional smgr invalidation,
* which will have been posted to shared memory immediately from within
* smgr_truncate. Therefore, there should be no race here.
*
* The reason why it's desirable to release the lock early here is because
* of the possibility that someone will need to use this to blow away many
* visibility map forks at once. If we can't release the lock until
* commit time, the transaction doing this will accumulate
* AccessExclusiveLocks on all of those relations at the same time, which
* is undesirable. However, if this turns out to be unsafe we may have no
* choice...
*/
relation_close(rel, AccessExclusiveLock);
/* Nothing to return. */
PG_RETURN_VOID();
}
/*
* Helper function to construct whichever TupleDesc we need for a particular
* call.
*/
static TupleDesc
pg_visibility_tupdesc(bool include_blkno, bool include_pd)
{
TupleDesc tupdesc;
AttrNumber maxattr = 2;
AttrNumber a = 0;
if (include_blkno)
++maxattr;
if (include_pd)
++maxattr;
tupdesc = CreateTemplateTupleDesc(maxattr);
if (include_blkno)
TupleDescInitEntry(tupdesc, ++a, "blkno", INT8OID, -1, 0);
TupleDescInitEntry(tupdesc, ++a, "all_visible", BOOLOID, -1, 0);
TupleDescInitEntry(tupdesc, ++a, "all_frozen", BOOLOID, -1, 0);
if (include_pd)
TupleDescInitEntry(tupdesc, ++a, "pd_all_visible", BOOLOID, -1, 0);
Assert(a == maxattr);
return BlessTupleDesc(tupdesc);
}
/*
* Collect visibility data about a relation.
*
* Checks relkind of relid and will throw an error if the relation does not
* have a VM.
*/
static vbits *
collect_visibility_data(Oid relid, bool include_pd)
{
Relation rel;
BlockNumber nblocks;
vbits *info;
BlockNumber blkno;
Buffer vmbuffer = InvalidBuffer;
BufferAccessStrategy bstrategy = GetAccessStrategy(BAS_BULKREAD);
BlockRangeReadStreamPrivate p;
ReadStream *stream = NULL;
rel = relation_open(relid, AccessShareLock);
/* Only some relkinds have a visibility map */
check_relation_relkind(rel);
nblocks = RelationGetNumberOfBlocks(rel);
info = palloc0(offsetof(vbits, bits) + nblocks);
info->next = 0;
info->count = nblocks;
/* Create a stream if reading main fork. */
if (include_pd)
{
p.current_blocknum = 0;
p.last_exclusive = nblocks;
/*
* It is safe to use batchmode as block_range_read_stream_cb takes no
* locks.
*/
stream = read_stream_begin_relation(READ_STREAM_FULL |
READ_STREAM_USE_BATCHING,
bstrategy,
rel,
MAIN_FORKNUM,
block_range_read_stream_cb,
&p,
0);
}
for (blkno = 0; blkno < nblocks; ++blkno)
{
int32 mapbits;
/* Make sure we are interruptible. */
CHECK_FOR_INTERRUPTS();
/* Get map info. */
mapbits = (int32) visibilitymap_get_status(rel, blkno, &vmbuffer);
if ((mapbits & VISIBILITYMAP_ALL_VISIBLE) != 0)
info->bits[blkno] |= (1 << 0);
if ((mapbits & VISIBILITYMAP_ALL_FROZEN) != 0)
info->bits[blkno] |= (1 << 1);
/*
* Page-level data requires reading every block, so only get it if the
* caller needs it. Use a buffer access strategy, too, to prevent
* cache-trashing.
*/
if (include_pd)
{
Buffer buffer;
Page page;
buffer = read_stream_next_buffer(stream, NULL);
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
if (PageIsAllVisible(page))
info->bits[blkno] |= (1 << 2);
UnlockReleaseBuffer(buffer);
}
}
if (include_pd)
{
Assert(read_stream_next_buffer(stream, NULL) == InvalidBuffer);
read_stream_end(stream);
}
/* Clean up. */
if (vmbuffer != InvalidBuffer)
ReleaseBuffer(vmbuffer);
relation_close(rel, AccessShareLock);
return info;
}
/*
* The "strict" version of GetOldestNonRemovableTransactionId(). The
* pg_visibility check can tolerate false positives (don't report some of the
* errors), but can't tolerate false negatives (report false errors). Normally,
* horizons move forwards, but there are cases when it could move backward
* (see comment for ComputeXidHorizons()).
*
* This is why we have to implement our own function for xid horizon, which
* would be guaranteed to be newer or equal to any xid horizon computed before.
* We have to do the following to achieve this.
*
* 1. Ignore processes xmin's, because they consider connection to other
* databases that were ignored before.
* 2. Ignore KnownAssignedXids, as they are not database-aware. Although we
* now perform minimal checking on a standby by always using nextXid, this
* approach is better than nothing and will at least catch extremely broken
* cases where a xid is in the future.
* 3. Ignore walsender xmin, because it could go backward if some replication
* connections don't use replication slots.
*
* While it might seem like we could use KnownAssignedXids for shared
* catalogs, since shared catalogs rely on a global horizon rather than a
* database-specific one - there are potential edge cases. For example, a
* transaction may crash on the primary without writing a commit/abort record.
* This would lead to a situation where it appears to still be running on the
* standby, even though it has already ended on the primary. For this reason,
* it's safer to ignore KnownAssignedXids, even for shared catalogs.
*
* As a result, we're using only currently running xids to compute the horizon.
* Surely these would significantly sacrifice accuracy. But we have to do so
* to avoid reporting false errors.
*/
static TransactionId
GetStrictOldestNonRemovableTransactionId(Relation rel)
{
RunningTransactions runningTransactions;
if (RecoveryInProgress())
{
TransactionId result;
/* As we ignore KnownAssignedXids on standby, just pick nextXid */
LWLockAcquire(XidGenLock, LW_SHARED);
result = XidFromFullTransactionId(TransamVariables->nextXid);
LWLockRelease(XidGenLock);
return result;
}
else if (rel == NULL || rel->rd_rel->relisshared)
{
/* Shared relation: take into account all running xids */
runningTransactions = GetRunningTransactionData();
LWLockRelease(ProcArrayLock);
LWLockRelease(XidGenLock);
return runningTransactions->oldestRunningXid;
}
else if (!RELATION_IS_LOCAL(rel))
{
/*
* Normal relation: take into account xids running within the current
* database
*/
runningTransactions = GetRunningTransactionData();
LWLockRelease(ProcArrayLock);
LWLockRelease(XidGenLock);
return runningTransactions->oldestDatabaseRunningXid;
}
else
{
/*
* For temporary relations, ComputeXidHorizons() uses only
* TransamVariables->latestCompletedXid and MyProc->xid. These two
* shouldn't go backwards. So we're fine with this horizon.
*/
return GetOldestNonRemovableTransactionId(rel);
}
}
/*
* Callback function to get next block for read stream object used in
* collect_corrupt_items() function.
*/
static BlockNumber
collect_corrupt_items_read_stream_next_block(ReadStream *stream,
void *callback_private_data,
void *per_buffer_data)
{
struct collect_corrupt_items_read_stream_private *p = callback_private_data;
for (; p->current_blocknum < p->last_exclusive; p->current_blocknum++)
{
bool check_frozen = false;
bool check_visible = false;
/* Make sure we are interruptible. */
CHECK_FOR_INTERRUPTS();
if (p->all_frozen && VM_ALL_FROZEN(p->rel, p->current_blocknum, &p->vmbuffer))
check_frozen = true;
if (p->all_visible && VM_ALL_VISIBLE(p->rel, p->current_blocknum, &p->vmbuffer))
check_visible = true;
if (!check_visible && !check_frozen)
continue;
return p->current_blocknum++;
}
return InvalidBlockNumber;
}
/*
* Returns a list of items whose visibility map information does not match
* the status of the tuples on the page.
*
* If all_visible is passed as true, this will include all items which are
* on pages marked as all-visible in the visibility map but which do not
* seem to in fact be all-visible.
*
* If all_frozen is passed as true, this will include all items which are
* on pages marked as all-frozen but which do not seem to in fact be frozen.
*
* Checks relkind of relid and will throw an error if the relation does not
* have a VM.
*/
static corrupt_items *
collect_corrupt_items(Oid relid, bool all_visible, bool all_frozen)
{
Relation rel;
corrupt_items *items;
Buffer vmbuffer = InvalidBuffer;
BufferAccessStrategy bstrategy = GetAccessStrategy(BAS_BULKREAD);
TransactionId OldestXmin = InvalidTransactionId;
struct collect_corrupt_items_read_stream_private p;
ReadStream *stream;
Buffer buffer;
rel = relation_open(relid, AccessShareLock);
/* Only some relkinds have a visibility map */
check_relation_relkind(rel);
if (all_visible)
OldestXmin = GetStrictOldestNonRemovableTransactionId(rel);
/*
* Guess an initial array size. We don't expect many corrupted tuples, so
* start with a small array. This function uses the "next" field to track
* the next offset where we can store an item (which is the same thing as
* the number of items found so far) and the "count" field to track the
* number of entries allocated. We'll repurpose these fields before
* returning.
*/
items = palloc0(sizeof(corrupt_items));
items->next = 0;
items->count = 64;
items->tids = palloc(items->count * sizeof(ItemPointerData));
p.current_blocknum = 0;
p.last_exclusive = RelationGetNumberOfBlocks(rel);
p.rel = rel;
p.vmbuffer = InvalidBuffer;
p.all_frozen = all_frozen;
p.all_visible = all_visible;
stream = read_stream_begin_relation(READ_STREAM_FULL,
bstrategy,
rel,
MAIN_FORKNUM,
collect_corrupt_items_read_stream_next_block,
&p,
0);
/* Loop over every block in the relation. */
while ((buffer = read_stream_next_buffer(stream, NULL)) != InvalidBuffer)
{
bool check_frozen = all_frozen;
bool check_visible = all_visible;
Page page;
OffsetNumber offnum,
maxoff;
BlockNumber blkno;
/* Make sure we are interruptible. */
CHECK_FOR_INTERRUPTS();
LockBuffer(buffer, BUFFER_LOCK_SHARE);
page = BufferGetPage(buffer);
maxoff = PageGetMaxOffsetNumber(page);
blkno = BufferGetBlockNumber(buffer);
/*
* The visibility map bits might have changed while we were acquiring
* the page lock. Recheck to avoid returning spurious results.
*/
if (check_frozen && !VM_ALL_FROZEN(rel, blkno, &vmbuffer))
check_frozen = false;
if (check_visible && !VM_ALL_VISIBLE(rel, blkno, &vmbuffer))
check_visible = false;
if (!check_visible && !check_frozen)
{
UnlockReleaseBuffer(buffer);
continue;
}
/* Iterate over each tuple on the page. */
for (offnum = FirstOffsetNumber;
offnum <= maxoff;
offnum = OffsetNumberNext(offnum))
{
HeapTupleData tuple;
ItemId itemid;
itemid = PageGetItemId(page, offnum);
/* Unused or redirect line pointers are of no interest. */
if (!ItemIdIsUsed(itemid) || ItemIdIsRedirected(itemid))
continue;
/* Dead line pointers are neither all-visible nor frozen. */
if (ItemIdIsDead(itemid))
{
ItemPointerSet(&(tuple.t_self), blkno, offnum);
record_corrupt_item(items, &tuple.t_self);
continue;
}
/* Initialize a HeapTupleData structure for checks below. */
ItemPointerSet(&(tuple.t_self), blkno, offnum);
tuple.t_data = (HeapTupleHeader) PageGetItem(page, itemid);
tuple.t_len = ItemIdGetLength(itemid);
tuple.t_tableOid = relid;
/*
* If we're checking whether the page is all-visible, we expect
* the tuple to be all-visible.
*/
if (check_visible &&
!tuple_all_visible(&tuple, OldestXmin, buffer))
{
TransactionId RecomputedOldestXmin;
/*
* Time has passed since we computed OldestXmin, so it's
* possible that this tuple is all-visible in reality even
* though it doesn't appear so based on our
* previously-computed value. Let's compute a new value so we
* can be certain whether there is a problem.
*
* From a concurrency point of view, it sort of sucks to
* retake ProcArrayLock here while we're holding the buffer
* exclusively locked, but it should be safe against
* deadlocks, because surely
* GetStrictOldestNonRemovableTransactionId() should never
* take a buffer lock. And this shouldn't happen often, so
* it's worth being careful so as to avoid false positives.
*/
RecomputedOldestXmin = GetStrictOldestNonRemovableTransactionId(rel);
if (!TransactionIdPrecedes(OldestXmin, RecomputedOldestXmin))
record_corrupt_item(items, &tuple.t_self);
else
{
OldestXmin = RecomputedOldestXmin;
if (!tuple_all_visible(&tuple, OldestXmin, buffer))
record_corrupt_item(items, &tuple.t_self);
}
}
/*
* If we're checking whether the page is all-frozen, we expect the
* tuple to be in a state where it will never need freezing.
*/
if (check_frozen)
{
if (heap_tuple_needs_eventual_freeze(tuple.t_data))
record_corrupt_item(items, &tuple.t_self);
}
}
UnlockReleaseBuffer(buffer);
}
read_stream_end(stream);
/* Clean up. */
if (vmbuffer != InvalidBuffer)
ReleaseBuffer(vmbuffer);
if (p.vmbuffer != InvalidBuffer)
ReleaseBuffer(p.vmbuffer);
relation_close(rel, AccessShareLock);
/*
* Before returning, repurpose the fields to match caller's expectations.
* next is now the next item that should be read (rather than written) and
* count is now the number of items we wrote (rather than the number we
* allocated).
*/
items->count = items->next;
items->next = 0;
return items;
}
/*
* Remember one corrupt item.
*/
static void
record_corrupt_item(corrupt_items *items, ItemPointer tid)
{
/* enlarge output array if needed. */
if (items->next >= items->count)
{
items->count *= 2;
items->tids = repalloc(items->tids,
items->count * sizeof(ItemPointerData));
}
/* and add the new item */
items->tids[items->next++] = *tid;
}
/*
* Check whether a tuple is all-visible relative to a given OldestXmin value.
* The buffer should contain the tuple and should be locked and pinned.
*/
static bool
tuple_all_visible(HeapTuple tup, TransactionId OldestXmin, Buffer buffer)
{
HTSV_Result state;
TransactionId xmin;
state = HeapTupleSatisfiesVacuum(tup, OldestXmin, buffer);
if (state != HEAPTUPLE_LIVE)
return false; /* all-visible implies live */
/*
* Neither lazy_scan_heap nor heap_page_is_all_visible will mark a page
* all-visible unless every tuple is hinted committed. However, those hint
* bits could be lost after a crash, so we can't be certain that they'll
* be set here. So just check the xmin.
*/
xmin = HeapTupleHeaderGetXmin(tup->t_data);
if (!TransactionIdPrecedes(xmin, OldestXmin))
return false; /* xmin not old enough for all to see */
return true;
}
/*
* check_relation_relkind - convenience routine to check that relation
* is of the relkind supported by the callers
*/
static void
check_relation_relkind(Relation rel)
{
if (!RELKIND_HAS_TABLE_AM(rel->rd_rel->relkind))
ereport(ERROR,
(errcode(ERRCODE_WRONG_OBJECT_TYPE),
errmsg("relation \"%s\" is of wrong relation kind",
RelationGetRelationName(rel)),
errdetail_relkind_not_supported(rel->rd_rel->relkind)));
}
|