#include "postgres.h"
#include "access/heapam_xlog.h"
#include "access/visibilitymap.h"
#include "access/xloginsert.h"
#include "access/xlogutils.h"
#include "miscadmin.h"
#include "port/pg_bitutils.h"
#include "storage/bufmgr.h"
#include "storage/smgr.h"
#include "utils/inval.h"
#include "utils/rel.h"

Include dependency graph for visibilitymap.c:

Macros
#define	MAPSIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData))

#define	HEAPBLOCKS_PER_BYTE (BITS_PER_BYTE / BITS_PER_HEAPBLOCK)

#define	HEAPBLOCKS_PER_PAGE (MAPSIZE * HEAPBLOCKS_PER_BYTE)

#define	HEAPBLK_TO_MAPBLOCK(x) ((x) / HEAPBLOCKS_PER_PAGE)

#define	HEAPBLK_TO_MAPBLOCK_LIMIT(x) (((x) + HEAPBLOCKS_PER_PAGE - 1) / HEAPBLOCKS_PER_PAGE)

#define	HEAPBLK_TO_MAPBYTE(x) (((x) % HEAPBLOCKS_PER_PAGE) / HEAPBLOCKS_PER_BYTE)

#define	HEAPBLK_TO_OFFSET(x) (((x) % HEAPBLOCKS_PER_BYTE) * BITS_PER_HEAPBLOCK)

#define	VISIBLE_MASK8 (0x55) /* The lower bit of each bit pair */

#define	FROZEN_MASK8 (0xaa) /* The upper bit of each bit pair */

Functions
static Buffer	vm_readbuf (Relation rel, BlockNumber blkno, bool extend)

static Buffer	vm_extend (Relation rel, BlockNumber vm_nblocks)

bool	visibilitymap_clear (Relation rel, BlockNumber heapBlk, Buffer vmbuf, uint8 flags)

void	visibilitymap_pin (Relation rel, BlockNumber heapBlk, Buffer *vmbuf)

bool	visibilitymap_pin_ok (BlockNumber heapBlk, Buffer vmbuf)

void	visibilitymap_set (Relation rel, BlockNumber heapBlk, Buffer heapBuf, XLogRecPtr recptr, Buffer vmBuf, TransactionId cutoff_xid, uint8 flags)

void	visibilitymap_set_vmbits (BlockNumber heapBlk, Buffer vmBuf, uint8 flags, const RelFileLocator rlocator)

uint8	visibilitymap_get_status (Relation rel, BlockNumber heapBlk, Buffer *vmbuf)

void	visibilitymap_count (Relation rel, BlockNumber all_visible, BlockNumber all_frozen)

BlockNumber	visibilitymap_prepare_truncate (Relation rel, BlockNumber nheapblocks)

BlockNumber	visibilitymap_truncation_length (BlockNumber nheapblocks)

Macro Definition Documentation

◆ FROZEN_MASK8

#define FROZEN_MASK8 (0xaa) /* The upper bit of each bit pair */

Definition at line 126 of file visibilitymap.c.

◆ HEAPBLK_TO_MAPBLOCK

#define HEAPBLK_TO_MAPBLOCK ( x ) ((x) / HEAPBLOCKS_PER_PAGE)

Definition at line 118 of file visibilitymap.c.

◆ HEAPBLK_TO_MAPBLOCK_LIMIT

#define HEAPBLK_TO_MAPBLOCK_LIMIT ( x ) (((x) + HEAPBLOCKS_PER_PAGE - 1) / HEAPBLOCKS_PER_PAGE)

Definition at line 119 of file visibilitymap.c.

{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
    int         mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
    int         mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
    uint8       mask = flags << mapOffset;
    char       *map;
    bool        cleared = false;
 
    /* Must never clear all_visible bit while leaving all_frozen bit set */
    Assert(flags & VISIBILITYMAP_VALID_BITS);
    Assert(flags != VISIBILITYMAP_ALL_VISIBLE);
 
#ifdef TRACE_VISIBILITYMAP
    elog(DEBUG1, "vm_clear %s %d", RelationGetRelationName(rel), heapBlk);
#endif
 
    if (!BufferIsValid(vmbuf) || BufferGetBlockNumber(vmbuf) != mapBlock)
        elog(ERROR, "wrong buffer passed to visibilitymap_clear");
 
    LockBuffer(vmbuf, BUFFER_LOCK_EXCLUSIVE);
    map = PageGetContents(BufferGetPage(vmbuf));
 
    if (map[mapByte] & mask)
    {
        map[mapByte] &= ~mask;
 
        MarkBufferDirty(vmbuf);
        cleared = true;
    }
 
    LockBuffer(vmbuf, BUFFER_LOCK_UNLOCK);
 
    return cleared;
}
 
/*
 *  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, *vmbuf should be InvalidBuffer or a valid buffer returned by
 * an earlier call to visibilitymap_pin or visibilitymap_get_status on the same
 * relation. On return, *vmbuf 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 *vmbuf)
{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
 
    /* Reuse the old pinned buffer if possible */
    if (BufferIsValid(*vmbuf))
    {
        if (BufferGetBlockNumber(*vmbuf) == mapBlock)
            return;
 
        ReleaseBuffer(*vmbuf);
    }
    *vmbuf = vm_readbuf(rel, mapBlock, true);
}
 
/*
 *  visibilitymap_pin_ok - do we already have the correct page pinned?
 *
 * On entry, vmbuf should be InvalidBuffer or a valid buffer returned by
 * an earlier call to visibilitymap_pin or visibilitymap_get_status on the same
 * relation.  The return value indicates whether the buffer covers the
 * given heapBlk.
 */
bool
visibilitymap_pin_ok(BlockNumber heapBlk, Buffer vmbuf)
{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
 
    return BufferIsValid(vmbuf) && BufferGetBlockNumber(vmbuf) == mapBlock;
}
 
/*
 *  visibilitymap_set - set bit(s) 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 VM 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 (though the heap page's LSN may *not* be updated;
 * see below).  cutoff_xid is the largest xmin on the page being marked
 * all-visible; it is needed for Hot Standby, and can be InvalidTransactionId
 * if the page contains no tuples.  It can also be set to InvalidTransactionId
 * when a page that is already all-visible is being marked all-frozen.
 *
 * Caller is expected to set the heap page's PD_ALL_VISIBLE bit before calling
 * this function. Except in recovery, caller should also pass the heap
 * buffer. When checksums are enabled and we're not in recovery, we must add
 * the heap buffer to the WAL chain to protect it from being torn.
 *
 * 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, Buffer heapBuf,
                  XLogRecPtr recptr, Buffer vmBuf, TransactionId cutoff_xid,
                  uint8 flags)
{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
    uint32      mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
    uint8       mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
    Page        page;
    uint8      *map;
    uint8       status;
 
#ifdef TRACE_VISIBILITYMAP
    elog(DEBUG1, "vm_set flags 0x%02X for %s %d",
         flags, RelationGetRelationName(rel), heapBlk);
#endif
 
    Assert(InRecovery || !XLogRecPtrIsValid(recptr));
    Assert(InRecovery || PageIsAllVisible(BufferGetPage(heapBuf)));
    Assert((flags & VISIBILITYMAP_VALID_BITS) == flags);
 
    /* Must never set all_frozen bit without also setting all_visible bit */
    Assert(flags != VISIBILITYMAP_ALL_FROZEN);
 
    /* Check that we have the right heap page pinned, if present */
    if (BufferIsValid(heapBuf) && BufferGetBlockNumber(heapBuf) != heapBlk)
        elog(ERROR, "wrong heap buffer passed to visibilitymap_set");
 
    Assert(!BufferIsValid(heapBuf) ||
           BufferIsLockedByMeInMode(heapBuf, BUFFER_LOCK_EXCLUSIVE));
 
    /* Check that we have the right VM page pinned */
    if (!BufferIsValid(vmBuf) || BufferGetBlockNumber(vmBuf) != mapBlock)
        elog(ERROR, "wrong VM buffer passed to visibilitymap_set");
 
    page = BufferGetPage(vmBuf);
    map = (uint8 *) PageGetContents(page);
    LockBuffer(vmBuf, BUFFER_LOCK_EXCLUSIVE);
 
    status = (map[mapByte] >> mapOffset) & VISIBILITYMAP_VALID_BITS;
    if (flags != status)
    {
        START_CRIT_SECTION();
 
        map[mapByte] |= (flags << mapOffset);
        MarkBufferDirty(vmBuf);
 
        if (RelationNeedsWAL(rel))
        {
            if (!XLogRecPtrIsValid(recptr))
            {
                Assert(!InRecovery);
                recptr = log_heap_visible(rel, heapBuf, vmBuf, cutoff_xid, flags);
 
                /*
                 * If data checksums are enabled (or wal_log_hints=on), we
                 * need to protect the heap page from being torn.
                 *
                 * If not, then we must *not* update the heap page's LSN. In
                 * this case, the FPI for the heap page was omitted from the
                 * WAL record inserted above, so it would be incorrect to
                 * update the heap page's LSN.
                 */
                if (XLogHintBitIsNeeded())
                {
                    Page        heapPage = BufferGetPage(heapBuf);
 
                    PageSetLSN(heapPage, recptr);
                }
            }
            PageSetLSN(page, recptr);
        }
 
        END_CRIT_SECTION();
    }
 
    LockBuffer(vmBuf, BUFFER_LOCK_UNLOCK);
}
 
/*
 * Set VM (visibility map) flags in the VM block in vmBuf.
 *
 * This function is intended for callers that log VM changes together
 * with the heap page modifications that rendered the page all-visible.
 * Callers that log VM changes separately should use visibilitymap_set().
 *
 * vmBuf must be pinned and exclusively locked, and it must cover the VM bits
 * corresponding to heapBlk.
 *
 * In normal operation (not recovery), this must be called inside a critical
 * section that also applies the necessary heap page changes and, if
 * applicable, emits WAL.
 *
 * The caller is responsible for ensuring consistency between the heap page
 * and the VM page by holding a pin and exclusive lock on the buffer
 * containing heapBlk.
 *
 * rlocator is used only for debugging messages.
 */
void
visibilitymap_set_vmbits(BlockNumber heapBlk,
                         Buffer vmBuf, uint8 flags,
                         const RelFileLocator rlocator)
{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
    uint32      mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
    uint8       mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
    Page        page;
    uint8      *map;
    uint8       status;
 
#ifdef TRACE_VISIBILITYMAP
    elog(DEBUG1, "vm_set flags 0x%02X for %s %d",
         flags,
         relpathbackend(rlocator, MyProcNumber, MAIN_FORKNUM).str,
         heapBlk);
#endif
 
    /* Call in same critical section where WAL is emitted. */
    Assert(InRecovery || CritSectionCount > 0);
 
    /* Flags should be valid. Also never clear bits with this function */
    Assert((flags & VISIBILITYMAP_VALID_BITS) == flags);
 
    /* Must never set all_frozen bit without also setting all_visible bit */
    Assert(flags != VISIBILITYMAP_ALL_FROZEN);
 
    /* Check that we have the right VM page pinned */
    if (!BufferIsValid(vmBuf) || BufferGetBlockNumber(vmBuf) != mapBlock)
        elog(ERROR, "wrong VM buffer passed to visibilitymap_set");
 
    Assert(BufferIsLockedByMeInMode(vmBuf, BUFFER_LOCK_EXCLUSIVE));
 
    page = BufferGetPage(vmBuf);
    map = (uint8 *) PageGetContents(page);
 
    status = (map[mapByte] >> mapOffset) & VISIBILITYMAP_VALID_BITS;
    if (flags != status)
    {
        map[mapByte] |= (flags << mapOffset);
        MarkBufferDirty(vmBuf);
    }
}
 
/*
 *  visibilitymap_get_status - get status of bits
 *
 * Are all tuples on heapBlk visible to all or are marked frozen, according
 * to the visibility map?
 *
 * On entry, *vmbuf should be InvalidBuffer or a valid buffer returned by an
 * earlier call to visibilitymap_pin or visibilitymap_get_status on the same
 * relation. On return, *vmbuf is a valid buffer with the map page containing
 * the bit for heapBlk, or InvalidBuffer. The caller is responsible for
 * releasing *vmbuf after it's done testing and setting bits.
 *
 * NOTE: This function is typically called without a lock on the heap page,
 * so somebody else could change the bit just after we look at it.  In fact,
 * since we don't lock the visibility map page either, it's even possible that
 * someone else could have changed the bit just before we look at it, but yet
 * we might see the old value.  It is the caller's responsibility to deal with
 * all concurrency issues!
 */
uint8
visibilitymap_get_status(Relation rel, BlockNumber heapBlk, Buffer *vmbuf)
{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
    uint32      mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
    uint8       mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
    char       *map;
    uint8       result;
 
#ifdef TRACE_VISIBILITYMAP
    elog(DEBUG1, "vm_get_status %s %d", RelationGetRelationName(rel), heapBlk);
#endif
 
    /* Reuse the old pinned buffer if possible */
    if (BufferIsValid(*vmbuf))
    {
        if (BufferGetBlockNumber(*vmbuf) != mapBlock)
        {
            ReleaseBuffer(*vmbuf);
            *vmbuf = InvalidBuffer;
        }
    }
 
    if (!BufferIsValid(*vmbuf))
    {
        *vmbuf = vm_readbuf(rel, mapBlock, false);
        if (!BufferIsValid(*vmbuf))
            return (uint8) 0;
    }
 
    map = PageGetContents(BufferGetPage(*vmbuf));
 
    /*
     * A single byte read is atomic.  There could be memory-ordering effects
     * here, but for performance reasons we make it the caller's job to worry
     * about that.
     */
    result = ((map[mapByte] >> mapOffset) & VISIBILITYMAP_VALID_BITS);
    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 or all-frozen, so they won't affect the result.
 */
void
visibilitymap_count(Relation rel, BlockNumber *all_visible, BlockNumber *all_frozen)
{
    BlockNumber mapBlock;
    BlockNumber nvisible = 0;
    BlockNumber nfrozen = 0;
 
    /* all_visible must be specified */
    Assert(all_visible);
 
    for (mapBlock = 0;; mapBlock++)
    {
        Buffer      mapBuffer;
        uint64     *map;
 
        /*
         * 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 = (uint64 *) PageGetContents(BufferGetPage(mapBuffer));
 
        nvisible += pg_popcount_masked((const char *) map, MAPSIZE, VISIBLE_MASK8);
        if (all_frozen)
            nfrozen += pg_popcount_masked((const char *) map, MAPSIZE, FROZEN_MASK8);
 
        ReleaseBuffer(mapBuffer);
    }
 
    *all_visible = nvisible;
    if (all_frozen)
        *all_frozen = nfrozen;
}
 
/*
 *  visibilitymap_prepare_truncate -
 *          prepare for truncation of the visibility map
 *
 * nheapblocks is the new size of the heap.
 *
 * Return the number of blocks of new visibility map.
 * If it's InvalidBlockNumber, there is nothing to truncate;
 * otherwise the caller is responsible for calling smgrtruncate()
 * to truncate the visibility map pages.
 */
BlockNumber
visibilitymap_prepare_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       truncOffset = HEAPBLK_TO_OFFSET(nheapblocks);
 
#ifdef TRACE_VISIBILITYMAP
    elog(DEBUG1, "vm_truncate %s %d", RelationGetRelationName(rel), nheapblocks);
#endif
 
    /*
     * If no visibility map has been created yet for this relation, there's
     * nothing to truncate.
     */
    if (!smgrexists(RelationGetSmgr(rel), VISIBILITYMAP_FORKNUM))
        return InvalidBlockNumber;
 
    /*
     * 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 || truncOffset != 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 InvalidBlockNumber;
        }
 
        page = BufferGetPage(mapBuffer);
        map = PageGetContents(page);
 
        LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE);
 
        /* NO EREPORT(ERROR) from here till changes are logged */
        START_CRIT_SECTION();
 
        /* 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 << truncOffset) - 1;
 
        /*
         * Truncation of a relation is WAL-logged at a higher-level, and we
         * will be called at WAL replay. But if checksums are enabled, we need
         * to still write a WAL record to protect against a torn page, if the
         * page is flushed to disk before the truncation WAL record. We cannot
         * use MarkBufferDirtyHint here, because that will not dirty the page
         * during recovery.
         */
        MarkBufferDirty(mapBuffer);
        if (!InRecovery && RelationNeedsWAL(rel) && XLogHintBitIsNeeded())
            log_newpage_buffer(mapBuffer, false);
 
        END_CRIT_SECTION();
 
        UnlockReleaseBuffer(mapBuffer);
    }
    else
        newnblocks = truncBlock;
 
    if (smgrnblocks(RelationGetSmgr(rel), VISIBILITYMAP_FORKNUM) <= newnblocks)
    {
        /* nothing to do, the file was already smaller than requested size */
        return InvalidBlockNumber;
    }
 
    return newnblocks;
}
 
/*
 *  visibilitymap_truncation_length -
 *          compute truncation length for visibility map
 *
 * Given a proposed truncation length for the main fork, compute the
 * correct truncation length for the visibility map. Should return the
 * same answer as visibilitymap_prepare_truncate(), but without modifying
 * anything.
 */
BlockNumber
visibilitymap_truncation_length(BlockNumber nheapblocks)
{
    return HEAPBLK_TO_MAPBLOCK_LIMIT(nheapblocks);
}
 
/*
 * 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;
    SMgrRelation reln;
 
    /*
     * Caution: re-using this smgr pointer could fail if the relcache entry
     * gets closed.  It's safe as long as we only do smgr-level operations
     * between here and the last use of the pointer.
     */
    reln = RelationGetSmgr(rel);
 
    /*
     * If we haven't cached the size of the visibility map fork yet, check it
     * first.
     */
    if (reln->smgr_cached_nblocks[VISIBILITYMAP_FORKNUM] == InvalidBlockNumber)
    {
        if (smgrexists(reln, VISIBILITYMAP_FORKNUM))
            smgrnblocks(reln, VISIBILITYMAP_FORKNUM);
        else
            reln->smgr_cached_nblocks[VISIBILITYMAP_FORKNUM] = 0;
    }
 
    /*
     * For reading we 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.
     *
     * We use the same path below to initialize pages when extending the
     * relation, as a concurrent extension can end up with vm_extend()
     * returning an already-initialized page.
     */
    if (blkno >= reln->smgr_cached_nblocks[VISIBILITYMAP_FORKNUM])
    {
        if (extend)
            buf = vm_extend(rel, blkno + 1);
        else
            return InvalidBuffer;
    }
    else
        buf = ReadBufferExtended(rel, VISIBILITYMAP_FORKNUM, blkno,
                                 RBM_ZERO_ON_ERROR, NULL);
 
    /*
     * Initializing the page when needed is trickier than it looks, because of
     * the possibility of multiple backends doing this concurrently, and our
     * desire to not uselessly take the buffer lock in the normal path where
     * the page is OK.  We must take the lock to initialize the page, so
     * recheck page newness after we have the lock, in case someone else
     * already did it.  Also, because we initially check PageIsNew with no
     * lock, it's possible to fall through and return the buffer while someone
     * else is still initializing the page (i.e., we might see pd_upper as set
     * but other page header fields are still zeroes).  This is harmless for
     * callers that will take a buffer lock themselves, but some callers
     * inspect the page without any lock at all.  The latter is OK only so
     * long as it doesn't depend on the page header having correct contents.
     * Current usage is safe because PageGetContents() does not require that.
     */
    if (PageIsNew(BufferGetPage(buf)))
    {
        LockBuffer(buf, BUFFER_LOCK_EXCLUSIVE);
        if (PageIsNew(BufferGetPage(buf)))
            PageInit(BufferGetPage(buf), BLCKSZ, 0);
        LockBuffer(buf, BUFFER_LOCK_UNLOCK);
    }
    return buf;
}
 
/*
 * Ensure that the visibility map fork is at least vm_nblocks long, extending
 * it if necessary with zeroed pages.
 */
static Buffer
vm_extend(Relation rel, BlockNumber vm_nblocks)
{
    Buffer      buf;
 
    buf = ExtendBufferedRelTo(BMR_REL(rel), VISIBILITYMAP_FORKNUM, NULL,
                              EB_CREATE_FORK_IF_NEEDED |
                              EB_CLEAR_SIZE_CACHE,
                              vm_nblocks,
                              RBM_ZERO_ON_ERROR);
 
    /*
     * 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(RelationGetSmgr(rel)->smgr_rlocator);
 
    return buf;
}

◆ HEAPBLK_TO_MAPBYTE

#define HEAPBLK_TO_MAPBYTE ( x ) (((x) % HEAPBLOCKS_PER_PAGE) / HEAPBLOCKS_PER_BYTE)

Definition at line 121 of file visibilitymap.c.

◆ HEAPBLK_TO_OFFSET

#define HEAPBLK_TO_OFFSET ( x ) (((x) % HEAPBLOCKS_PER_BYTE) * BITS_PER_HEAPBLOCK)

Definition at line 122 of file visibilitymap.c.

◆ HEAPBLOCKS_PER_BYTE

#define HEAPBLOCKS_PER_BYTE (BITS_PER_BYTE / BITS_PER_HEAPBLOCK)

Definition at line 112 of file visibilitymap.c.

◆ HEAPBLOCKS_PER_PAGE

#define HEAPBLOCKS_PER_PAGE (MAPSIZE * HEAPBLOCKS_PER_BYTE)

Definition at line 115 of file visibilitymap.c.

◆ MAPSIZE

#define MAPSIZE (BLCKSZ - MAXALIGN(SizeOfPageHeaderData))

Definition at line 109 of file visibilitymap.c.

◆ VISIBLE_MASK8

#define VISIBLE_MASK8 (0x55) /* The lower bit of each bit pair */

Definition at line 125 of file visibilitymap.c.

Function Documentation

◆ visibilitymap_clear()

bool visibilitymap_clear	(	Relation	rel,
		BlockNumber	heapBlk,
		Buffer	vmbuf,
		uint8	flags
	)

Definition at line 141 of file visibilitymap.c.

{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
    int         mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
    int         mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
    uint8       mask = flags << mapOffset;
    char       *map;
    bool        cleared = false;
 
    /* Must never clear all_visible bit while leaving all_frozen bit set */
    Assert(flags & VISIBILITYMAP_VALID_BITS);
    Assert(flags != VISIBILITYMAP_ALL_VISIBLE);
 
#ifdef TRACE_VISIBILITYMAP
    elog(DEBUG1, "vm_clear %s %d", RelationGetRelationName(rel), heapBlk);
#endif
 
    if (!BufferIsValid(vmbuf) || BufferGetBlockNumber(vmbuf) != mapBlock)
        elog(ERROR, "wrong buffer passed to visibilitymap_clear");
 
    LockBuffer(vmbuf, BUFFER_LOCK_EXCLUSIVE);
    map = PageGetContents(BufferGetPage(vmbuf));
 
    if (map[mapByte] & mask)
    {
        map[mapByte] &= ~mask;
 
        MarkBufferDirty(vmbuf);
        cleared = true;
    }
 
    LockBuffer(vmbuf, BUFFER_LOCK_UNLOCK);
 
    return cleared;
}

References Assert, BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferGetBlockNumber(), BufferGetPage(), BufferIsValid(), DEBUG1, elog, ERROR, fb(), HEAPBLK_TO_MAPBLOCK, HEAPBLK_TO_MAPBYTE, HEAPBLK_TO_OFFSET, LockBuffer(), MarkBufferDirty(), PageGetContents(), RelationGetRelationName, VISIBILITYMAP_ALL_VISIBLE, and VISIBILITYMAP_VALID_BITS.

Referenced by heap_delete(), heap_force_common(), heap_insert(), heap_lock_tuple(), heap_lock_updated_tuple_rec(), heap_multi_insert(), heap_page_fix_vm_corruption(), heap_update(), heap_xlog_delete(), heap_xlog_insert(), heap_xlog_lock(), heap_xlog_lock_updated(), heap_xlog_multi_insert(), and heap_xlog_update().

◆ visibilitymap_count()

void visibilitymap_count	(	Relation	rel,
		BlockNumber *	all_visible,
		BlockNumber *	all_frozen
	)

Definition at line 458 of file visibilitymap.c.

{
    BlockNumber mapBlock;
    BlockNumber nvisible = 0;
    BlockNumber nfrozen = 0;
 
    /* all_visible must be specified */
    Assert(all_visible);
 
    for (mapBlock = 0;; mapBlock++)
    {
        Buffer      mapBuffer;
        uint64     *map;
 
        /*
         * 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 = (uint64 *) PageGetContents(BufferGetPage(mapBuffer));
 
        nvisible += pg_popcount_masked((const char *) map, MAPSIZE, VISIBLE_MASK8);
        if (all_frozen)
            nfrozen += pg_popcount_masked((const char *) map, MAPSIZE, FROZEN_MASK8);
 
        ReleaseBuffer(mapBuffer);
    }
 
    *all_visible = nvisible;
    if (all_frozen)
        *all_frozen = nfrozen;
}

References Assert, BufferGetPage(), BufferIsValid(), fb(), FROZEN_MASK8, MAPSIZE, PageGetContents(), pg_popcount_masked(), ReleaseBuffer(), VISIBLE_MASK8, and vm_readbuf().

Referenced by do_analyze_rel(), heap_vacuum_eager_scan_setup(), heap_vacuum_rel(), index_update_stats(), and pg_visibility_map_summary().

◆ visibilitymap_get_status()

uint8 visibilitymap_get_status	(	Relation	rel,
		BlockNumber	heapBlk,
		Buffer *	vmbuf
	)

Definition at line 410 of file visibilitymap.c.

{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
    uint32      mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
    uint8       mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
    char       *map;
    uint8       result;
 
#ifdef TRACE_VISIBILITYMAP
    elog(DEBUG1, "vm_get_status %s %d", RelationGetRelationName(rel), heapBlk);
#endif
 
    /* Reuse the old pinned buffer if possible */
    if (BufferIsValid(*vmbuf))
    {
        if (BufferGetBlockNumber(*vmbuf) != mapBlock)
        {
            ReleaseBuffer(*vmbuf);
            *vmbuf = InvalidBuffer;
        }
    }
 
    if (!BufferIsValid(*vmbuf))
    {
        *vmbuf = vm_readbuf(rel, mapBlock, false);
        if (!BufferIsValid(*vmbuf))
            return (uint8) 0;
    }
 
    map = PageGetContents(BufferGetPage(*vmbuf));
 
    /*
     * A single byte read is atomic.  There could be memory-ordering effects
     * here, but for performance reasons we make it the caller's job to worry
     * about that.
     */
    result = ((map[mapByte] >> mapOffset) & VISIBILITYMAP_VALID_BITS);
    return result;
}

References BufferGetBlockNumber(), BufferGetPage(), BufferIsValid(), DEBUG1, elog, fb(), HEAPBLK_TO_MAPBLOCK, HEAPBLK_TO_MAPBYTE, HEAPBLK_TO_OFFSET, InvalidBuffer, PageGetContents(), RelationGetRelationName, ReleaseBuffer(), VISIBILITYMAP_VALID_BITS, and vm_readbuf().

Referenced by collect_visibility_data(), find_next_unskippable_block(), heapcheck_read_stream_next_unskippable(), pg_visibility(), pg_visibility_map(), and prune_freeze_setup().

◆ visibilitymap_pin()

void visibilitymap_pin	(	Relation	rel,
		BlockNumber	heapBlk,
		Buffer *	vmbuf
	)

Definition at line 194 of file visibilitymap.c.

{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
 
    /* Reuse the old pinned buffer if possible */
    if (BufferIsValid(*vmbuf))
    {
        if (BufferGetBlockNumber(*vmbuf) == mapBlock)
            return;
 
        ReleaseBuffer(*vmbuf);
    }
    *vmbuf = vm_readbuf(rel, mapBlock, true);
}

References BufferGetBlockNumber(), BufferIsValid(), fb(), HEAPBLK_TO_MAPBLOCK, ReleaseBuffer(), and vm_readbuf().

Referenced by GetVisibilityMapPins(), heap_delete(), heap_force_common(), heap_lock_tuple(), heap_lock_updated_tuple_rec(), heap_page_prune_opt(), heap_update(), heap_xlog_delete(), heap_xlog_insert(), heap_xlog_lock(), heap_xlog_lock_updated(), heap_xlog_multi_insert(), heap_xlog_update(), lazy_scan_heap(), lazy_vacuum_heap_rel(), and RelationGetBufferForTuple().

◆ visibilitymap_pin_ok()

bool visibilitymap_pin_ok	(	BlockNumber	heapBlk,
		Buffer	vmbuf
	)

Definition at line 218 of file visibilitymap.c.

{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
 
    return BufferIsValid(vmbuf) && BufferGetBlockNumber(vmbuf) == mapBlock;
}

References BufferGetBlockNumber(), BufferIsValid(), fb(), and HEAPBLK_TO_MAPBLOCK.

Referenced by GetVisibilityMapPins(), and RelationGetBufferForTuple().

◆ visibilitymap_prepare_truncate()

BlockNumber visibilitymap_prepare_truncate	(	Relation	rel,
		BlockNumber	nheapblocks
	)

Definition at line 512 of file visibilitymap.c.

{
    BlockNumber newnblocks;
 
    /* last remaining block, byte, and bit */
    BlockNumber truncBlock = HEAPBLK_TO_MAPBLOCK(nheapblocks);
    uint32      truncByte = HEAPBLK_TO_MAPBYTE(nheapblocks);
    uint8       truncOffset = HEAPBLK_TO_OFFSET(nheapblocks);
 
#ifdef TRACE_VISIBILITYMAP
    elog(DEBUG1, "vm_truncate %s %d", RelationGetRelationName(rel), nheapblocks);
#endif
 
    /*
     * If no visibility map has been created yet for this relation, there's
     * nothing to truncate.
     */
    if (!smgrexists(RelationGetSmgr(rel), VISIBILITYMAP_FORKNUM))
        return InvalidBlockNumber;
 
    /*
     * 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 || truncOffset != 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 InvalidBlockNumber;
        }
 
        page = BufferGetPage(mapBuffer);
        map = PageGetContents(page);
 
        LockBuffer(mapBuffer, BUFFER_LOCK_EXCLUSIVE);
 
        /* NO EREPORT(ERROR) from here till changes are logged */
        START_CRIT_SECTION();
 
        /* 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 << truncOffset) - 1;
 
        /*
         * Truncation of a relation is WAL-logged at a higher-level, and we
         * will be called at WAL replay. But if checksums are enabled, we need
         * to still write a WAL record to protect against a torn page, if the
         * page is flushed to disk before the truncation WAL record. We cannot
         * use MarkBufferDirtyHint here, because that will not dirty the page
         * during recovery.
         */
        MarkBufferDirty(mapBuffer);
        if (!InRecovery && RelationNeedsWAL(rel) && XLogHintBitIsNeeded())
            log_newpage_buffer(mapBuffer, false);
 
        END_CRIT_SECTION();
 
        UnlockReleaseBuffer(mapBuffer);
    }
    else
        newnblocks = truncBlock;
 
    if (smgrnblocks(RelationGetSmgr(rel), VISIBILITYMAP_FORKNUM) <= newnblocks)
    {
        /* nothing to do, the file was already smaller than requested size */
        return InvalidBlockNumber;
    }
 
    return newnblocks;
}

References BUFFER_LOCK_EXCLUSIVE, BufferGetPage(), BufferIsValid(), DEBUG1, elog, END_CRIT_SECTION, fb(), HEAPBLK_TO_MAPBLOCK, HEAPBLK_TO_MAPBYTE, HEAPBLK_TO_OFFSET, InRecovery, InvalidBlockNumber, LockBuffer(), log_newpage_buffer(), MAPSIZE, MarkBufferDirty(), MemSet, PageGetContents(), RelationGetRelationName, RelationGetSmgr(), RelationNeedsWAL, smgrexists(), smgrnblocks(), START_CRIT_SECTION, UnlockReleaseBuffer(), VISIBILITYMAP_FORKNUM, vm_readbuf(), and XLogHintBitIsNeeded.

Referenced by pg_truncate_visibility_map(), RelationTruncate(), and smgr_redo().

◆ visibilitymap_set()

void visibilitymap_set	(	Relation	rel,
		BlockNumber	heapBlk,
		Buffer	heapBuf,
		XLogRecPtr	recptr,
		Buffer	vmBuf,
		TransactionId	cutoff_xid,
		uint8	flags
	)

Definition at line 247 of file visibilitymap.c.

{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
    uint32      mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
    uint8       mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
    Page        page;
    uint8      *map;
    uint8       status;
 
#ifdef TRACE_VISIBILITYMAP
    elog(DEBUG1, "vm_set flags 0x%02X for %s %d",
         flags, RelationGetRelationName(rel), heapBlk);
#endif
 
    Assert(InRecovery || !XLogRecPtrIsValid(recptr));
    Assert(InRecovery || PageIsAllVisible(BufferGetPage(heapBuf)));
    Assert((flags & VISIBILITYMAP_VALID_BITS) == flags);
 
    /* Must never set all_frozen bit without also setting all_visible bit */
    Assert(flags != VISIBILITYMAP_ALL_FROZEN);
 
    /* Check that we have the right heap page pinned, if present */
    if (BufferIsValid(heapBuf) && BufferGetBlockNumber(heapBuf) != heapBlk)
        elog(ERROR, "wrong heap buffer passed to visibilitymap_set");
 
    Assert(!BufferIsValid(heapBuf) ||
           BufferIsLockedByMeInMode(heapBuf, BUFFER_LOCK_EXCLUSIVE));
 
    /* Check that we have the right VM page pinned */
    if (!BufferIsValid(vmBuf) || BufferGetBlockNumber(vmBuf) != mapBlock)
        elog(ERROR, "wrong VM buffer passed to visibilitymap_set");
 
    page = BufferGetPage(vmBuf);
    map = (uint8 *) PageGetContents(page);
    LockBuffer(vmBuf, BUFFER_LOCK_EXCLUSIVE);
 
    status = (map[mapByte] >> mapOffset) & VISIBILITYMAP_VALID_BITS;
    if (flags != status)
    {
        START_CRIT_SECTION();
 
        map[mapByte] |= (flags << mapOffset);
        MarkBufferDirty(vmBuf);
 
        if (RelationNeedsWAL(rel))
        {
            if (!XLogRecPtrIsValid(recptr))
            {
                Assert(!InRecovery);
                recptr = log_heap_visible(rel, heapBuf, vmBuf, cutoff_xid, flags);
 
                /*
                 * If data checksums are enabled (or wal_log_hints=on), we
                 * need to protect the heap page from being torn.
                 *
                 * If not, then we must *not* update the heap page's LSN. In
                 * this case, the FPI for the heap page was omitted from the
                 * WAL record inserted above, so it would be incorrect to
                 * update the heap page's LSN.
                 */
                if (XLogHintBitIsNeeded())
                {
                    Page        heapPage = BufferGetPage(heapBuf);
 
                    PageSetLSN(heapPage, recptr);
                }
            }
            PageSetLSN(page, recptr);
        }
 
        END_CRIT_SECTION();
    }
 
    LockBuffer(vmBuf, BUFFER_LOCK_UNLOCK);
}

References Assert, BUFFER_LOCK_EXCLUSIVE, BUFFER_LOCK_UNLOCK, BufferGetBlockNumber(), BufferGetPage(), BufferIsLockedByMeInMode(), BufferIsValid(), DEBUG1, elog, END_CRIT_SECTION, ERROR, fb(), HEAPBLK_TO_MAPBLOCK, HEAPBLK_TO_MAPBYTE, HEAPBLK_TO_OFFSET, InRecovery, LockBuffer(), log_heap_visible(), MarkBufferDirty(), PageGetContents(), PageIsAllVisible(), PageSetLSN(), RelationGetRelationName, RelationNeedsWAL, START_CRIT_SECTION, VISIBILITYMAP_ALL_FROZEN, VISIBILITYMAP_VALID_BITS, XLogHintBitIsNeeded, and XLogRecPtrIsValid.

Referenced by heap_xlog_visible(), lazy_scan_new_or_empty(), and lazy_scan_prune().

◆ visibilitymap_set_vmbits()

void visibilitymap_set_vmbits	(	BlockNumber	heapBlk,
		Buffer	vmBuf,
		uint8	flags,
		const RelFileLocator	rlocator
	)

Definition at line 346 of file visibilitymap.c.

{
    BlockNumber mapBlock = HEAPBLK_TO_MAPBLOCK(heapBlk);
    uint32      mapByte = HEAPBLK_TO_MAPBYTE(heapBlk);
    uint8       mapOffset = HEAPBLK_TO_OFFSET(heapBlk);
    Page        page;
    uint8      *map;
    uint8       status;
 
#ifdef TRACE_VISIBILITYMAP
    elog(DEBUG1, "vm_set flags 0x%02X for %s %d",
         flags,
         relpathbackend(rlocator, MyProcNumber, MAIN_FORKNUM).str,
         heapBlk);
#endif
 
    /* Call in same critical section where WAL is emitted. */
    Assert(InRecovery || CritSectionCount > 0);
 
    /* Flags should be valid. Also never clear bits with this function */
    Assert((flags & VISIBILITYMAP_VALID_BITS) == flags);
 
    /* Must never set all_frozen bit without also setting all_visible bit */
    Assert(flags != VISIBILITYMAP_ALL_FROZEN);
 
    /* Check that we have the right VM page pinned */
    if (!BufferIsValid(vmBuf) || BufferGetBlockNumber(vmBuf) != mapBlock)
        elog(ERROR, "wrong VM buffer passed to visibilitymap_set");
 
    Assert(BufferIsLockedByMeInMode(vmBuf, BUFFER_LOCK_EXCLUSIVE));
 
    page = BufferGetPage(vmBuf);
    map = (uint8 *) PageGetContents(page);
 
    status = (map[mapByte] >> mapOffset) & VISIBILITYMAP_VALID_BITS;
    if (flags != status)
    {
        map[mapByte] |= (flags << mapOffset);
        MarkBufferDirty(vmBuf);
    }
}

References Assert, BUFFER_LOCK_EXCLUSIVE, BufferGetBlockNumber(), BufferGetPage(), BufferIsLockedByMeInMode(), BufferIsValid(), CritSectionCount, DEBUG1, elog, ERROR, fb(), HEAPBLK_TO_MAPBLOCK, HEAPBLK_TO_MAPBYTE, HEAPBLK_TO_OFFSET, InRecovery, MAIN_FORKNUM, MarkBufferDirty(), MyProcNumber, PageGetContents(), relpathbackend, str, VISIBILITYMAP_ALL_FROZEN, and VISIBILITYMAP_VALID_BITS.

Referenced by heap_multi_insert(), heap_xlog_multi_insert(), heap_xlog_prune_freeze(), and lazy_vacuum_heap_page().

◆ visibilitymap_truncation_length()

BlockNumber visibilitymap_truncation_length ( BlockNumber nheapblocks )

Definition at line 615 of file visibilitymap.c.

{
    return HEAPBLK_TO_MAPBLOCK_LIMIT(nheapblocks);
}

References fb(), and HEAPBLK_TO_MAPBLOCK_LIMIT.

Referenced by SummarizeSmgrRecord().

◆ vm_extend()

static Buffer vm_extend	(	Relation	rel,
		BlockNumber	vm_nblocks
	)

static

Definition at line 701 of file visibilitymap.c.

{
    Buffer      buf;
 
    buf = ExtendBufferedRelTo(BMR_REL(rel), VISIBILITYMAP_FORKNUM, NULL,
                              EB_CREATE_FORK_IF_NEEDED |
                              EB_CLEAR_SIZE_CACHE,
                              vm_nblocks,
                              RBM_ZERO_ON_ERROR);
 
    /*
     * 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(RelationGetSmgr(rel)->smgr_rlocator);
 
    return buf;
}

References BMR_REL, buf, CacheInvalidateSmgr(), EB_CLEAR_SIZE_CACHE, EB_CREATE_FORK_IF_NEEDED, ExtendBufferedRelTo(), fb(), RBM_ZERO_ON_ERROR, RelationGetSmgr(), and VISIBILITYMAP_FORKNUM.

Referenced by vm_readbuf().

◆ vm_readbuf()

static Buffer vm_readbuf	(	Relation	rel,
		BlockNumber	blkno,
		bool	extend
	)