/*------------------------------------------------------------------------- * * visibilitymap.c * bitmap for tracking visibility of heap tuples * * Portions Copyright (c) 1996-2012, PostgreSQL Global Development Group * Portions Copyright (c) 1994, Regents of the University of California * * * IDENTIFICATION * src/backend/access/heap/visibilitymap.c * * INTERFACE ROUTINES * visibilitymap_clear - clear a bit in the visibility map * visibilitymap_pin - pin a map page for setting a bit * visibilitymap_pin_ok - check whether correct map page is already pinned * visibilitymap_set - set a bit in a previously pinned page * visibilitymap_test - test if a bit is set * visibilitymap_count - count number of bits set in visibility map * visibilitymap_truncate - truncate the visibility map * * NOTES * * The visibility map is a bitmap with one bit per heap page. A set bit means * that all tuples on the page are known visible to all transactions, and * therefore the page doesn't need to be vacuumed. The map is conservative in * the sense that we make sure that whenever a bit is set, we know the * condition is true, but if a bit is not set, it might or might not be true. * * Clearing a visibility map bit is not separately WAL-logged. The callers * must make sure that whenever a bit is cleared, the bit is cleared on WAL * replay of the updating operation as well. * * When we *set* a visibility map during VACUUM, we must write WAL. This may * seem counterintuitive, since the bit is basically a hint: if it is clear, * it may still be the case that every tuple on the page is visible to all * transactions; we just don't know that for certain. The difficulty is that * there are two bits which are typically set together: the PD_ALL_VISIBLE bit * on the page itself, and the visibility map bit. If a crash occurs after the * visibility map page makes it to disk and before the updated heap page makes * it to disk, redo must set the bit on the heap page. Otherwise, the next * insert, update, or delete on the heap page will fail to realize that the * visibility map bit must be cleared, possibly causing index-only scans to * return wrong answers. * * VACUUM will normally skip pages for which the visibility map bit is set; * such pages can't contain any dead tuples and therefore don't need vacuuming. * The visibility map is not used for anti-wraparound vacuums, because * an anti-wraparound vacuum needs to freeze tuples and observe the latest xid * present in the table, even on pages that don't have any dead tuples. * * LOCKING * * In heapam.c, whenever a page is modified so that not all tuples on the * page are visible to everyone anymore, the corresponding bit in the * visibility map is cleared. In order to be crash-safe, we need to do this * while still holding a lock on the heap page and in the same critical * section that logs the page modification. However, we don't want to hold * the buffer lock over any I/O that may be required to read in the visibility * map page. To avoid this, we examine the heap page before locking it; * if the page-level PD_ALL_VISIBLE bit is set, we pin the visibility map * bit. Then, we lock the buffer. But this creates a race condition: there * is a possibility that in the time it takes to lock the buffer, the * PD_ALL_VISIBLE bit gets set. If that happens, we have to unlock the * buffer, pin the visibility map page, and relock the buffer. This shouldn't * happen often, because only VACUUM currently sets visibility map bits, * and the race will only occur if VACUUM processes a given page at almost * exactly the same time that someone tries to further modify it. * * To set a bit, you need to hold a lock on the heap page. That prevents * the race condition where VACUUM sees that all tuples on the page are * visible to everyone, but another backend modifies the page before VACUUM * sets the bit in the visibility map. * * When a bit is set, the LSN of the visibility map page is updated to make * sure that the visibility map update doesn't get written to disk before the * WAL record of the changes that made it possible to set the bit is flushed. * But when a bit is cleared, we don't have to do that because it's always * safe to clear a bit in the map from correctness point of view. * *------------------------------------------------------------------------- */ #include "postgres.h" #include "access/heapam.h" #include "access/visibilitymap.h" #include "miscadmin.h" #include "storage/bufmgr.h" #include "storage/lmgr.h" #include "storage/smgr.h" #include "utils/inval.h" /*#define TRACE_VISIBILITYMAP */ /* * Size of the bitmap on each visibility map page, in bytes. There's no * extra headers, so the whole page minus the standard page header is * used for the bitmap. */ #define MAPSIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData)) /* Number of bits allocated for each heap block. */ #define BITS_PER_HEAPBLOCK 1 /* Number of heap blocks we can represent in one byte. */ #define HEAPBLOCKS_PER_BYTE 8 /* Number of heap blocks we can represent in one visibility map page. */ #define HEAPBLOCKS_PER_PAGE (MAPSIZE * HEAPBLOCKS_PER_BYTE) /* Mapping from heap block number to the right bit in the visibility map */ #define HEAPBLK_TO_MAPBLOCK(x) ((x) / HEAPBLOCKS_PER_PAGE) #define HEAPBLK_TO_MAPBYTE(x) (((x) % HEAPBLOCKS_PER_PAGE) / HEAPBLOCKS_PER_BYTE) #define HEAPBLK_TO_MAPBIT(x) ((x) % HEAPBLOCKS_PER_BYTE) /* table for fast counting of set bits */ static const uint8 number_of_ones[256] = { 0, 1, 1, 2, 1, 2, 2, 3, 1, 2, 2, 3, 2, 3, 3, 4, 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5, 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5, 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5, 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7, 1, 2, 2, 3, 2, 3, 3, 4, 2, 3, 3, 4, 3, 4, 4, 5, 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7, 2, 3, 3, 4, 3, 4, 4, 5, 3, 4, 4, 5, 4, 5, 5, 6, 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7, 3, 4, 4, 5, 4, 5, 5, 6, 4, 5, 5, 6, 5, 6, 6, 7, 4, 5, 5, 6, 5, 6, 6, 7, 5, 6, 6, 7, 6, 7, 7, 8 }; /* prototypes for internal routines */ static Buffer vm_readbuf(Relation rel, BlockNumber blkno, bool extend); static void vm_extend(Relation rel, BlockNumber nvmblocks); /* * visibilitymap_clear - clear a bit in visibility map * * You must pass a buffer containing the correct map page to this function. * Call visibilitymap_pin first to pin the right one. This function doesn't do * any I/O. */ void visibilitymap_clear(Relation rel, BlockNumber heapBlk, Buffer buf) { BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk); int mapByte = HEAPBLK_TO_MAPBYTE(heapBlk); int mapBit = HEAPBLK_TO_MAPBIT(heapBlk); uint8 mask = 1 << mapBit; char *map; #ifdef TRACE_VISIBILITYMAP elog(DEBUG1, "vm_clear %s %d", RelationGetRelationName(rel), heapBlk); #endif if (!BufferIsValid(buf) || BufferGetBlockNumber(buf) != mapBlock) elog(ERROR, "wrong buffer passed to visibilitymap_clear"); LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE); map = PageGetContents(BufferGetPage(buf)); if (map[mapByte] & mask) { map[mapByte] &= ~mask; MarkBufferDirty(buf); } LockBuffer(buf, BUFFER_LOCK_UNLOCK); } /* * visibilitymap_pin - pin a map page for setting a bit * * Setting a bit in the visibility map is a two-phase operation. First, call * visibilitymap_pin, to pin the visibility map page containing the bit for * the heap page. Because that can require I/O to read the map page, you * shouldn't hold a lock on the heap page while doing that. Then, call * visibilitymap_set to actually set the bit. * * On entry, *buf should be InvalidBuffer or a valid buffer returned by * an earlier call to visibilitymap_pin or visibilitymap_test on the same * relation. On return, *buf is a valid buffer with the map page containing * the bit for heapBlk. * * If the page doesn't exist in the map file yet, it is extended. */ void visibilitymap_pin(Relation rel, BlockNumber heapBlk, Buffer *buf) { BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk); /* Reuse the old pinned buffer if possible */ if (BufferIsValid(*buf)) { if (BufferGetBlockNumber(*buf) == mapBlock) return; ReleaseBuffer(*buf); } *buf = vm_readbuf(rel, mapBlock, true); } /* * visibilitymap_pin_ok - do we already have the correct page pinned? * * On entry, buf should be InvalidBuffer or a valid buffer returned by * an earlier call to visibilitymap_pin or visibilitymap_test on the same * relation. The return value indicates whether the buffer covers the * given heapBlk. */ bool visibilitymap_pin_ok(BlockNumber heapBlk, Buffer buf) { BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk); return BufferIsValid(buf) && BufferGetBlockNumber(buf) == mapBlock; } /* * visibilitymap_set - set a bit on a previously pinned page * * recptr is the LSN of the XLOG record we're replaying, if we're in recovery, * or InvalidXLogRecPtr in normal running. The page LSN is advanced to the * one provided; in normal running, we generate a new XLOG record and set the * page LSN to that value. * * You must pass a buffer containing the correct map page to this function. * Call visibilitymap_pin first to pin the right one. This function doesn't do * any I/O. */ void visibilitymap_set(Relation rel, BlockNumber heapBlk, XLogRecPtr recptr, Buffer buf) { BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk); uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk); uint8 mapBit = HEAPBLK_TO_MAPBIT(heapBlk); Page page; char *map; #ifdef TRACE_VISIBILITYMAP elog(DEBUG1, "vm_set %s %d", RelationGetRelationName(rel), heapBlk); #endif Assert(InRecovery || XLogRecPtrIsInvalid(recptr)); /* Check that we have the right page pinned */ if (!BufferIsValid(buf) || BufferGetBlockNumber(buf) != mapBlock) elog(ERROR, "wrong buffer passed to visibilitymap_set"); page = BufferGetPage(buf); map = PageGetContents(page); LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE); if (!(map[mapByte] & (1 << mapBit))) { START_CRIT_SECTION(); map[mapByte] |= (1 << mapBit); MarkBufferDirty(buf); if (RelationNeedsWAL(rel)) { if (XLogRecPtrIsInvalid(recptr)) recptr = log_heap_visible(rel->rd_node, heapBlk, buf); PageSetLSN(page, recptr); PageSetTLI(page, ThisTimeLineID); } END_CRIT_SECTION(); } LockBuffer(buf, BUFFER_LOCK_UNLOCK); } /* * visibilitymap_test - test if a bit is set * * Are all tuples on heapBlk visible to all, according to the visibility map? * * On entry, *buf should be InvalidBuffer or a valid buffer returned by an * earlier call to visibilitymap_pin or visibilitymap_test on the same * relation. On return, *buf is a valid buffer with the map page containing * the bit for heapBlk, or InvalidBuffer. The caller is responsible for * releasing *buf after it's done testing and setting bits. */ bool visibilitymap_test(Relation rel, BlockNumber heapBlk, Buffer *buf) { BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk); uint32 mapByte = HEAPBLK_TO_MAPBYTE(heapBlk); uint8 mapBit = HEAPBLK_TO_MAPBIT(heapBlk); bool result; char *map; #ifdef TRACE_VISIBILITYMAP elog(DEBUG1, "vm_test %s %d", RelationGetRelationName(rel), heapBlk); #endif /* Reuse the old pinned buffer if possible */ if (BufferIsValid(*buf)) { if (BufferGetBlockNumber(*buf) != mapBlock) { ReleaseBuffer(*buf); *buf = InvalidBuffer; } } if (!BufferIsValid(*buf)) { *buf = vm_readbuf(rel, mapBlock, false); if (!BufferIsValid(*buf)) return false; } map = PageGetContents(BufferGetPage(*buf)); /* * We don't need to lock the page, as we're only looking at a single bit. */ result = (map[mapByte] & (1 << mapBit)) ? true : false; return result; } /* * visibilitymap_count - count number of bits set in visibility map * * Note: we ignore the possibility of race conditions when the table is being * extended concurrently with the call. New pages added to the table aren't * going to be marked all-visible, so they won't affect the result. */ BlockNumber visibilitymap_count(Relation rel) { BlockNumber result = 0; BlockNumber mapBlock; for (mapBlock = 0; ; mapBlock++) { Buffer mapBuffer; unsigned char *map; int i; /* * Read till we fall off the end of the map. We assume that any * extra bytes in the last page are zeroed, so we don't bother * excluding them from the count. */ mapBuffer = vm_readbuf(rel, mapBlock, false); if (!BufferIsValid(mapBuffer)) break; /* * We choose not to lock the page, since the result is going to be * immediately stale anyway if anyone is concurrently setting or * clearing bits, and we only really need an approximate value. */ map = (unsigned char *) PageGetContents(BufferGetPage(mapBuffer)); for (i = 0; i < MAPSIZE; i++) { result += number_of_ones[map[i]]; } ReleaseBuffer(mapBuffer); } return result; } /* * visibilitymap_truncate - truncate the visibility map * * The caller must hold AccessExclusiveLock on the relation, to ensure that * other backends receive the smgr invalidation event that this function sends * before they access the VM again. * * nheapblocks is the new size of the heap. */ void visibilitymap_truncate(Relation rel, BlockNumber nheapblocks) { BlockNumber newnblocks; /* last remaining block, byte, and bit */ BlockNumber truncBlock = HEAPBLK_TO_MAPBLOCK(nheapblocks); uint32 truncByte = HEAPBLK_TO_MAPBYTE(nheapblocks); uint8 truncBit = HEAPBLK_TO_MAPBIT(nheapblocks); #ifdef TRACE_VISIBILITYMAP elog(DEBUG1, "vm_truncate %s %d", RelationGetRelationName(rel), nheapblocks); #endif RelationOpenSmgr(rel); /* * If no visibility map has been created yet for this relation, there's * nothing to truncate. */ if (!smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM)) return; /* * Unless the new size is exactly at a visibility map page boundary, the * tail bits in the last remaining map page, representing truncated heap * blocks, need to be cleared. This is not only tidy, but also necessary * because we don't get a chance to clear the bits if the heap is extended * again. */ if (truncByte != 0 || truncBit != 0) { Buffer mapBuffer; Page page; char *map; newnblocks = truncBlock + 1; mapBuffer = vm_readbuf(rel, truncBlock, false); if (!BufferIsValid(mapBuffer)) { /* nothing to do, the file was already smaller */ return; } page = BufferGetPage(mapBuffer); map = PageGetContents(page); LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE); /* Clear out the unwanted bytes. */ MemSet(&map[truncByte + 1], 0, MAPSIZE - (truncByte + 1)); /* * Mask out the unwanted bits of the last remaining byte. * * ((1 << 0) - 1) = 00000000 ((1 << 1) - 1) = 00000001 ... ((1 << 6) - * 1) = 00111111 ((1 << 7) - 1) = 01111111 */ map[truncByte] &= (1 << truncBit) - 1; MarkBufferDirty(mapBuffer); UnlockReleaseBuffer(mapBuffer); } else newnblocks = truncBlock; if (smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM) <= newnblocks) { /* nothing to do, the file was already smaller than requested size */ return; } /* Truncate the unused VM pages, and send smgr inval message */ smgrtruncate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, newnblocks); /* * We might as well update the local smgr_vm_nblocks setting. smgrtruncate * sent an smgr cache inval message, which will cause other backends to * invalidate their copy of smgr_vm_nblocks, and this one too at the next * command boundary. But this ensures it isn't outright wrong until then. */ if (rel->rd_smgr) rel->rd_smgr->smgr_vm_nblocks = newnblocks; } /* * Read a visibility map page. * * If the page doesn't exist, InvalidBuffer is returned, or if 'extend' is * true, the visibility map file is extended. */ static Buffer vm_readbuf(Relation rel, BlockNumber blkno, bool extend) { Buffer buf; /* * We might not have opened the relation at the smgr level yet, or we might * have been forced to close it by a sinval message. The code below won't * necessarily notice relation extension immediately when extend = false, * so we rely on sinval messages to ensure that our ideas about the size of * the map aren't too far out of date. */ RelationOpenSmgr(rel); /* * If we haven't cached the size of the visibility map fork yet, check it * first. */ if (rel->rd_smgr->smgr_vm_nblocks == InvalidBlockNumber) { if (smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM)) rel->rd_smgr->smgr_vm_nblocks = smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM); else rel->rd_smgr->smgr_vm_nblocks = 0; } /* Handle requests beyond EOF */ if (blkno >= rel->rd_smgr->smgr_vm_nblocks) { if (extend) vm_extend(rel, blkno + 1); else return InvalidBuffer; } /* * Use ZERO_ON_ERROR mode, and initialize the page if necessary. It's * always safe to clear bits, so it's better to clear corrupt pages than * error out. */ buf = ReadBufferExtended(rel, VISIBILITYMAP_FORKNUM, blkno, RBM_ZERO_ON_ERROR, NULL); if (PageIsNew(BufferGetPage(buf))) PageInit(BufferGetPage(buf), BLCKSZ, 0); return buf; } /* * Ensure that the visibility map fork is at least vm_nblocks long, extending * it if necessary with zeroed pages. */ static void vm_extend(Relation rel, BlockNumber vm_nblocks) { BlockNumber vm_nblocks_now; Page pg; pg = (Page) palloc(BLCKSZ); PageInit(pg, BLCKSZ, 0); /* * We use the relation extension lock to lock out other backends trying to * extend the visibility map at the same time. It also locks out extension * of the main fork, unnecessarily, but extending the visibility map * happens seldom enough that it doesn't seem worthwhile to have a * separate lock tag type for it. * * Note that another backend might have extended or created the relation * by the time we get the lock. */ LockRelationForExtension(rel, ExclusiveLock); /* Might have to re-open if a cache flush happened */ RelationOpenSmgr(rel); /* * Create the file first if it doesn't exist. If smgr_vm_nblocks is * positive then it must exist, no need for an smgrexists call. */ if ((rel->rd_smgr->smgr_vm_nblocks == 0 || rel->rd_smgr->smgr_vm_nblocks == InvalidBlockNumber) && !smgrexists(rel->rd_smgr, VISIBILITYMAP_FORKNUM)) smgrcreate(rel->rd_smgr, VISIBILITYMAP_FORKNUM, false); vm_nblocks_now = smgrnblocks(rel->rd_smgr, VISIBILITYMAP_FORKNUM); /* Now extend the file */ while (vm_nblocks_now < vm_nblocks) { smgrextend(rel->rd_smgr, VISIBILITYMAP_FORKNUM, vm_nblocks_now, (char *) pg, false); vm_nblocks_now++; } /* * Send a shared-inval message to force other backends to close any smgr * references they may have for this rel, which we are about to change. * This is a useful optimization because it means that backends don't have * to keep checking for creation or extension of the file, which happens * infrequently. */ CacheInvalidateSmgr(rel->rd_smgr->smgr_rnode); /* Update local cache with the up-to-date size */ rel->rd_smgr->smgr_vm_nblocks = vm_nblocks_now; UnlockRelationForExtension(rel, ExclusiveLock); pfree(pg); }