pruneheap.c File Reference

#include "postgres.h"
#include "access/heapam.h"
#include "access/heapam_xlog.h"
#include "access/htup_details.h"
#include "access/transam.h"
#include "access/xlog.h"
#include "access/xloginsert.h"
#include "catalog/catalog.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "storage/bufmgr.h"
#include "utils/snapmgr.h"
#include "utils/rel.h"

Include dependency graph for pruneheap.c:

Go to the source code of this file.

Data Structures
struct	PruneState

Functions
static HTSV_Result	heap_prune_satisfies_vacuum (PruneState *prstate, HeapTuple tup, Buffer buffer)
static int	heap_prune_chain (Buffer buffer, OffsetNumber rootoffnum, PruneState *prstate)
static void	heap_prune_record_prunable (PruneState *prstate, TransactionId xid)
static void	heap_prune_record_redirect (PruneState *prstate, OffsetNumber offnum, OffsetNumber rdoffnum)
static void	heap_prune_record_dead (PruneState *prstate, OffsetNumber offnum)
static void	heap_prune_record_unused (PruneState *prstate, OffsetNumber offnum)
static void	page_verify_redirects (Page page)
void	heap_page_prune_opt (Relation relation, Buffer buffer)
void	heap_page_prune (Relation relation, Buffer buffer, GlobalVisState *vistest, PruneResult *presult, OffsetNumber *off_loc)
void	heap_page_prune_execute (Buffer buffer, OffsetNumber *redirected, int nredirected, OffsetNumber *nowdead, int ndead, OffsetNumber *nowunused, int nunused)
void	heap_get_root_tuples (Page page, OffsetNumber *root_offsets)

Function Documentation

heap_get_root_tuples()

void heap_get_root_tuples	(	Page	page,
		OffsetNumber *	root_offsets
	)

Definition at line 996 of file pruneheap.c.

{
    OffsetNumber offnum,
                maxoff;
 
    MemSet(root_offsets, InvalidOffsetNumber,
           MaxHeapTuplesPerPage * sizeof(OffsetNumber));
 
    maxoff = PageGetMaxOffsetNumber(page);
    for (offnum = FirstOffsetNumber; offnum <= maxoff; offnum = OffsetNumberNext(offnum))
    {
        ItemId      lp = PageGetItemId(page, offnum);
        HeapTupleHeader htup;
        OffsetNumber nextoffnum;
        TransactionId priorXmax;
 
        /* skip unused and dead items */
        if (!ItemIdIsUsed(lp) || ItemIdIsDead(lp))
            continue;
 
        if (ItemIdIsNormal(lp))
        {
            htup = (HeapTupleHeader) PageGetItem(page, lp);
 
            /*
             * Check if this tuple is part of a HOT-chain rooted at some other
             * tuple. If so, skip it for now; we'll process it when we find
             * its root.
             */
            if (HeapTupleHeaderIsHeapOnly(htup))
                continue;
 
            /*
             * This is either a plain tuple or the root of a HOT-chain.
             * Remember it in the mapping.
             */
            root_offsets[offnum - 1] = offnum;
 
            /* If it's not the start of a HOT-chain, we're done with it */
            if (!HeapTupleHeaderIsHotUpdated(htup))
                continue;
 
            /* Set up to scan the HOT-chain */
            nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
            priorXmax = HeapTupleHeaderGetUpdateXid(htup);
        }
        else
        {
            /* Must be a redirect item. We do not set its root_offsets entry */
            Assert(ItemIdIsRedirected(lp));
            /* Set up to scan the HOT-chain */
            nextoffnum = ItemIdGetRedirect(lp);
            priorXmax = InvalidTransactionId;
        }
 
        /*
         * Now follow the HOT-chain and collect other tuples in the chain.
         *
         * Note: Even though this is a nested loop, the complexity of the
         * function is O(N) because a tuple in the page should be visited not
         * more than twice, once in the outer loop and once in HOT-chain
         * chases.
         */
        for (;;)
        {
            /* Sanity check (pure paranoia) */
            if (offnum < FirstOffsetNumber)
                break;
 
            /*
             * An offset past the end of page's line pointer array is possible
             * when the array was truncated
             */
            if (offnum > maxoff)
                break;
 
            lp = PageGetItemId(page, nextoffnum);
 
            /* Check for broken chains */
            if (!ItemIdIsNormal(lp))
                break;
 
            htup = (HeapTupleHeader) PageGetItem(page, lp);
 
            if (TransactionIdIsValid(priorXmax) &&
                !TransactionIdEquals(priorXmax, HeapTupleHeaderGetXmin(htup)))
                break;
 
            /* Remember the root line pointer for this item */
            root_offsets[nextoffnum - 1] = offnum;
 
            /* Advance to next chain member, if any */
            if (!HeapTupleHeaderIsHotUpdated(htup))
                break;
 
            /* HOT implies it can't have moved to different partition */
            Assert(!HeapTupleHeaderIndicatesMovedPartitions(htup));
 
            nextoffnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
            priorXmax = HeapTupleHeaderGetUpdateXid(htup);
        }
    }
}

References Assert(), FirstOffsetNumber, HeapTupleHeaderGetUpdateXid, HeapTupleHeaderGetXmin, HeapTupleHeaderIndicatesMovedPartitions, HeapTupleHeaderIsHeapOnly, HeapTupleHeaderIsHotUpdated, InvalidOffsetNumber, InvalidTransactionId, ItemIdGetRedirect, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerGetOffsetNumber(), MaxHeapTuplesPerPage, MemSet, OffsetNumberNext, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), HeapTupleHeaderData::t_ctid, TransactionIdEquals, and TransactionIdIsValid.

Referenced by heapam_index_build_range_scan(), and heapam_index_validate_scan().

heap_page_prune()

void heap_page_prune	(	Relation	relation,
		Buffer	buffer,
		GlobalVisState *	vistest,
		PruneResult *	presult,
		OffsetNumber *	off_loc
	)

Definition at line 213 of file pruneheap.c.

{
    Page        page = BufferGetPage(buffer);
    BlockNumber blockno = BufferGetBlockNumber(buffer);
    OffsetNumber offnum,
                maxoff;
    PruneState  prstate;
    HeapTupleData tup;
 
    /*
     * Our strategy is to scan the page and make lists of items to change,
     * then apply the changes within a critical section.  This keeps as much
     * logic as possible out of the critical section, and also ensures that
     * WAL replay will work the same as the normal case.
     *
     * First, initialize the new pd_prune_xid value to zero (indicating no
     * prunable tuples).  If we find any tuples which may soon become
     * prunable, we will save the lowest relevant XID in new_prune_xid. Also
     * initialize the rest of our working state.
     */
    prstate.new_prune_xid = InvalidTransactionId;
    prstate.rel = relation;
    prstate.vistest = vistest;
    prstate.snapshotConflictHorizon = InvalidTransactionId;
    prstate.nredirected = prstate.ndead = prstate.nunused = 0;
    memset(prstate.marked, 0, sizeof(prstate.marked));
 
    presult->ndeleted = 0;
    presult->nnewlpdead = 0;
 
    maxoff = PageGetMaxOffsetNumber(page);
    tup.t_tableOid = RelationGetRelid(prstate.rel);
 
    /*
     * Determine HTSV for all tuples.
     *
     * This is required for correctness to deal with cases where running HTSV
     * twice could result in different results (e.g. RECENTLY_DEAD can turn to
     * DEAD if another checked item causes GlobalVisTestIsRemovableFullXid()
     * to update the horizon, INSERT_IN_PROGRESS can change to DEAD if the
     * inserting transaction aborts, ...). That in turn could cause
     * heap_prune_chain() to behave incorrectly if a tuple is reached twice,
     * once directly via a heap_prune_chain() and once following a HOT chain.
     *
     * It's also good for performance. Most commonly tuples within a page are
     * stored at decreasing offsets (while the items are stored at increasing
     * offsets). When processing all tuples on a page this leads to reading
     * memory at decreasing offsets within a page, with a variable stride.
     * That's hard for CPU prefetchers to deal with. Processing the items in
     * reverse order (and thus the tuples in increasing order) increases
     * prefetching efficiency significantly / decreases the number of cache
     * misses.
     */
    for (offnum = maxoff;
         offnum >= FirstOffsetNumber;
         offnum = OffsetNumberPrev(offnum))
    {
        ItemId      itemid = PageGetItemId(page, offnum);
        HeapTupleHeader htup;
 
        /* Nothing to do if slot doesn't contain a tuple */
        if (!ItemIdIsNormal(itemid))
        {
            prstate.htsv[offnum] = -1;
            continue;
        }
 
        htup = (HeapTupleHeader) PageGetItem(page, itemid);
        tup.t_data = htup;
        tup.t_len = ItemIdGetLength(itemid);
        ItemPointerSet(&(tup.t_self), blockno, offnum);
 
        /*
         * Set the offset number so that we can display it along with any
         * error that occurred while processing this tuple.
         */
        if (off_loc)
            *off_loc = offnum;
 
        prstate.htsv[offnum] = heap_prune_satisfies_vacuum(&prstate, &tup,
                                                           buffer);
    }
 
    /* Scan the page */
    for (offnum = FirstOffsetNumber;
         offnum <= maxoff;
         offnum = OffsetNumberNext(offnum))
    {
        ItemId      itemid;
 
        /* Ignore items already processed as part of an earlier chain */
        if (prstate.marked[offnum])
            continue;
 
        /* see preceding loop */
        if (off_loc)
            *off_loc = offnum;
 
        /* Nothing to do if slot is empty or already dead */
        itemid = PageGetItemId(page, offnum);
        if (!ItemIdIsUsed(itemid) || ItemIdIsDead(itemid))
            continue;
 
        /* Process this item or chain of items */
        presult->ndeleted += heap_prune_chain(buffer, offnum, &prstate);
    }
 
    /* Clear the offset information once we have processed the given page. */
    if (off_loc)
        *off_loc = InvalidOffsetNumber;
 
    /* Any error while applying the changes is critical */
    START_CRIT_SECTION();
 
    /* Have we found any prunable items? */
    if (prstate.nredirected > 0 || prstate.ndead > 0 || prstate.nunused > 0)
    {
        /*
         * Apply the planned item changes, then repair page fragmentation, and
         * update the page's hint bit about whether it has free line pointers.
         */
        heap_page_prune_execute(buffer,
                                prstate.redirected, prstate.nredirected,
                                prstate.nowdead, prstate.ndead,
                                prstate.nowunused, prstate.nunused);
 
        /*
         * Update the page's pd_prune_xid field to either zero, or the lowest
         * XID of any soon-prunable tuple.
         */
        ((PageHeader) page)->pd_prune_xid = prstate.new_prune_xid;
 
        /*
         * Also clear the "page is full" flag, since there's no point in
         * repeating the prune/defrag process until something else happens to
         * the page.
         */
        PageClearFull(page);
 
        MarkBufferDirty(buffer);
 
        /*
         * Emit a WAL XLOG_HEAP2_PRUNE record showing what we did
         */
        if (RelationNeedsWAL(relation))
        {
            xl_heap_prune xlrec;
            XLogRecPtr  recptr;
 
            xlrec.isCatalogRel = RelationIsAccessibleInLogicalDecoding(relation);
            xlrec.snapshotConflictHorizon = prstate.snapshotConflictHorizon;
            xlrec.nredirected = prstate.nredirected;
            xlrec.ndead = prstate.ndead;
 
            XLogBeginInsert();
            XLogRegisterData((char *) &xlrec, SizeOfHeapPrune);
 
            XLogRegisterBuffer(0, buffer, REGBUF_STANDARD);
 
            /*
             * The OffsetNumber arrays are not actually in the buffer, but we
             * pretend that they are.  When XLogInsert stores the whole
             * buffer, the offset arrays need not be stored too.
             */
            if (prstate.nredirected > 0)
                XLogRegisterBufData(0, (char *) prstate.redirected,
                                    prstate.nredirected *
                                    sizeof(OffsetNumber) * 2);
 
            if (prstate.ndead > 0)
                XLogRegisterBufData(0, (char *) prstate.nowdead,
                                    prstate.ndead * sizeof(OffsetNumber));
 
            if (prstate.nunused > 0)
                XLogRegisterBufData(0, (char *) prstate.nowunused,
                                    prstate.nunused * sizeof(OffsetNumber));
 
            recptr = XLogInsert(RM_HEAP2_ID, XLOG_HEAP2_PRUNE);
 
            PageSetLSN(BufferGetPage(buffer), recptr);
        }
    }
    else
    {
        /*
         * If we didn't prune anything, but have found a new value for the
         * pd_prune_xid field, update it and mark the buffer dirty. This is
         * treated as a non-WAL-logged hint.
         *
         * Also clear the "page is full" flag if it is set, since there's no
         * point in repeating the prune/defrag process until something else
         * happens to the page.
         */
        if (((PageHeader) page)->pd_prune_xid != prstate.new_prune_xid ||
            PageIsFull(page))
        {
            ((PageHeader) page)->pd_prune_xid = prstate.new_prune_xid;
            PageClearFull(page);
            MarkBufferDirtyHint(buffer, true);
        }
    }
 
    END_CRIT_SECTION();
 
    /* Record number of newly-set-LP_DEAD items for caller */
    presult->nnewlpdead = prstate.ndead;
}

References BufferGetBlockNumber(), BufferGetPage(), END_CRIT_SECTION, FirstOffsetNumber, heap_page_prune_execute(), heap_prune_chain(), heap_prune_satisfies_vacuum(), PruneState::htsv, InvalidOffsetNumber, InvalidTransactionId, xl_heap_prune::isCatalogRel, ItemIdGetLength, ItemIdIsDead, ItemIdIsNormal, ItemIdIsUsed, ItemPointerSet(), MarkBufferDirty(), MarkBufferDirtyHint(), PruneState::marked, PruneState::ndead, xl_heap_prune::ndead, PruneResult::ndeleted, PruneState::new_prune_xid, PruneResult::nnewlpdead, PruneState::nowdead, PruneState::nowunused, PruneState::nredirected, xl_heap_prune::nredirected, PruneState::nunused, OffsetNumberNext, OffsetNumberPrev, PageClearFull(), PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), PageIsFull(), PageSetLSN(), PruneState::redirected, REGBUF_STANDARD, PruneState::rel, RelationGetRelid, RelationIsAccessibleInLogicalDecoding, RelationNeedsWAL, SizeOfHeapPrune, PruneState::snapshotConflictHorizon, xl_heap_prune::snapshotConflictHorizon, START_CRIT_SECTION, HeapTupleData::t_data, HeapTupleData::t_len, HeapTupleData::t_self, HeapTupleData::t_tableOid, PruneState::vistest, XLOG_HEAP2_PRUNE, XLogBeginInsert(), XLogInsert(), XLogRegisterBufData(), XLogRegisterBuffer(), and XLogRegisterData().

Referenced by heap_page_prune_opt(), and lazy_scan_prune().

heap_page_prune_execute()

void heap_page_prune_execute	(	Buffer	buffer,
		OffsetNumber *	redirected,
		int	nredirected,
		OffsetNumber *	nowdead,
		int	ndead,
		OffsetNumber *	nowunused,
		int	nunused
	)

Definition at line 797 of file pruneheap.c.

{
    Page        page = (Page) BufferGetPage(buffer);
    OffsetNumber *offnum;
    HeapTupleHeader htup PG_USED_FOR_ASSERTS_ONLY;
 
    /* Shouldn't be called unless there's something to do */
    Assert(nredirected > 0 || ndead > 0 || nunused > 0);
 
    /* Update all redirected line pointers */
    offnum = redirected;
    for (int i = 0; i < nredirected; i++)
    {
        OffsetNumber fromoff = *offnum++;
        OffsetNumber tooff = *offnum++;
        ItemId      fromlp = PageGetItemId(page, fromoff);
        ItemId      tolp PG_USED_FOR_ASSERTS_ONLY;
 
#ifdef USE_ASSERT_CHECKING
 
        /*
         * Any existing item that we set as an LP_REDIRECT (any 'from' item)
         * must be the first item from a HOT chain.  If the item has tuple
         * storage then it can't be a heap-only tuple.  Otherwise we are just
         * maintaining an existing LP_REDIRECT from an existing HOT chain that
         * has been pruned at least once before now.
         */
        if (!ItemIdIsRedirected(fromlp))
        {
            Assert(ItemIdHasStorage(fromlp) && ItemIdIsNormal(fromlp));
 
            htup = (HeapTupleHeader) PageGetItem(page, fromlp);
            Assert(!HeapTupleHeaderIsHeapOnly(htup));
        }
        else
        {
            /* We shouldn't need to redundantly set the redirect */
            Assert(ItemIdGetRedirect(fromlp) != tooff);
        }
 
        /*
         * The item that we're about to set as an LP_REDIRECT (the 'from'
         * item) will point to an existing item (the 'to' item) that is
         * already a heap-only tuple.  There can be at most one LP_REDIRECT
         * item per HOT chain.
         *
         * We need to keep around an LP_REDIRECT item (after original
         * non-heap-only root tuple gets pruned away) so that it's always
         * possible for VACUUM to easily figure out what TID to delete from
         * indexes when an entire HOT chain becomes dead.  A heap-only tuple
         * can never become LP_DEAD; an LP_REDIRECT item or a regular heap
         * tuple can.
         *
         * This check may miss problems, e.g. the target of a redirect could
         * be marked as unused subsequently. The page_verify_redirects() check
         * below will catch such problems.
         */
        tolp = PageGetItemId(page, tooff);
        Assert(ItemIdHasStorage(tolp) && ItemIdIsNormal(tolp));
        htup = (HeapTupleHeader) PageGetItem(page, tolp);
        Assert(HeapTupleHeaderIsHeapOnly(htup));
#endif
 
        ItemIdSetRedirect(fromlp, tooff);
    }
 
    /* Update all now-dead line pointers */
    offnum = nowdead;
    for (int i = 0; i < ndead; i++)
    {
        OffsetNumber off = *offnum++;
        ItemId      lp = PageGetItemId(page, off);
 
#ifdef USE_ASSERT_CHECKING
 
        /*
         * An LP_DEAD line pointer must be left behind when the original item
         * (which is dead to everybody) could still be referenced by a TID in
         * an index.  This should never be necessary with any individual
         * heap-only tuple item, though. (It's not clear how much of a problem
         * that would be, but there is no reason to allow it.)
         */
        if (ItemIdHasStorage(lp))
        {
            Assert(ItemIdIsNormal(lp));
            htup = (HeapTupleHeader) PageGetItem(page, lp);
            Assert(!HeapTupleHeaderIsHeapOnly(htup));
        }
        else
        {
            /* Whole HOT chain becomes dead */
            Assert(ItemIdIsRedirected(lp));
        }
#endif
 
        ItemIdSetDead(lp);
    }
 
    /* Update all now-unused line pointers */
    offnum = nowunused;
    for (int i = 0; i < nunused; i++)
    {
        OffsetNumber off = *offnum++;
        ItemId      lp = PageGetItemId(page, off);
 
#ifdef USE_ASSERT_CHECKING
 
        /*
         * Only heap-only tuples can become LP_UNUSED during pruning.  They
         * don't need to be left in place as LP_DEAD items until VACUUM gets
         * around to doing index vacuuming.
         */
        Assert(ItemIdHasStorage(lp) && ItemIdIsNormal(lp));
        htup = (HeapTupleHeader) PageGetItem(page, lp);
        Assert(HeapTupleHeaderIsHeapOnly(htup));
#endif
 
        ItemIdSetUnused(lp);
    }
 
    /*
     * Finally, repair any fragmentation, and update the page's hint bit about
     * whether it has free pointers.
     */
    PageRepairFragmentation(page);
 
    /*
     * Now that the page has been modified, assert that redirect items still
     * point to valid targets.
     */
    page_verify_redirects(page);
}

References Assert(), BufferGetPage(), HeapTupleHeaderIsHeapOnly, i, ItemIdGetRedirect, ItemIdHasStorage, ItemIdIsNormal, ItemIdIsRedirected, ItemIdSetDead, ItemIdSetRedirect, ItemIdSetUnused, page_verify_redirects(), PageGetItem(), PageGetItemId(), PageRepairFragmentation(), and PG_USED_FOR_ASSERTS_ONLY.

Referenced by heap_page_prune(), and heap_xlog_prune().

heap_page_prune_opt()

void heap_page_prune_opt	(	Relation	relation,
		Buffer	buffer
	)

Definition at line 96 of file pruneheap.c.

{
    Page        page = BufferGetPage(buffer);
    TransactionId prune_xid;
    GlobalVisState *vistest;
    Size        minfree;
 
    /*
     * We can't write WAL in recovery mode, so there's no point trying to
     * clean the page. The primary will likely issue a cleaning WAL record
     * soon anyway, so this is no particular loss.
     */
    if (RecoveryInProgress())
        return;
 
    /*
     * First check whether there's any chance there's something to prune,
     * determining the appropriate horizon is a waste if there's no prune_xid
     * (i.e. no updates/deletes left potentially dead tuples around).
     */
    prune_xid = ((PageHeader) page)->pd_prune_xid;
    if (!TransactionIdIsValid(prune_xid))
        return;
 
    /*
     * Check whether prune_xid indicates that there may be dead rows that can
     * be cleaned up.
     */
    vistest = GlobalVisTestFor(relation);
 
    if (!GlobalVisTestIsRemovableXid(vistest, prune_xid))
        return;
 
    /*
     * We prune when a previous UPDATE failed to find enough space on the page
     * for a new tuple version, or when free space falls below the relation's
     * fill-factor target (but not less than 10%).
     *
     * Checking free space here is questionable since we aren't holding any
     * lock on the buffer; in the worst case we could get a bogus answer. It's
     * unlikely to be *seriously* wrong, though, since reading either pd_lower
     * or pd_upper is probably atomic.  Avoiding taking a lock seems more
     * important than sometimes getting a wrong answer in what is after all
     * just a heuristic estimate.
     */
    minfree = RelationGetTargetPageFreeSpace(relation,
                                             HEAP_DEFAULT_FILLFACTOR);
    minfree = Max(minfree, BLCKSZ / 10);
 
    if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree)
    {
        /* OK, try to get exclusive buffer lock */
        if (!ConditionalLockBufferForCleanup(buffer))
            return;
 
        /*
         * Now that we have buffer lock, get accurate information about the
         * page's free space, and recheck the heuristic about whether to
         * prune.
         */
        if (PageIsFull(page) || PageGetHeapFreeSpace(page) < minfree)
        {
            PruneResult presult;
 
            heap_page_prune(relation, buffer, vistest, &presult, NULL);
 
            /*
             * Report the number of tuples reclaimed to pgstats.  This is
             * presult.ndeleted minus the number of newly-LP_DEAD-set items.
             *
             * We derive the number of dead tuples like this to avoid totally
             * forgetting about items that were set to LP_DEAD, since they
             * still need to be cleaned up by VACUUM.  We only want to count
             * heap-only tuples that just became LP_UNUSED in our report,
             * which don't.
             *
             * VACUUM doesn't have to compensate in the same way when it
             * tracks ndeleted, since it will set the same LP_DEAD items to
             * LP_UNUSED separately.
             */
            if (presult.ndeleted > presult.nnewlpdead)
                pgstat_update_heap_dead_tuples(relation,
                                               presult.ndeleted - presult.nnewlpdead);
        }
 
        /* And release buffer lock */
        LockBuffer(buffer, BUFFER_LOCK_UNLOCK);
 
        /*
         * We avoid reuse of any free space created on the page by unrelated
         * UPDATEs/INSERTs by opting to not update the FSM at this point.  The
         * free space should be reused by UPDATEs to *this* page.
         */
    }
}

References BUFFER_LOCK_UNLOCK, BufferGetPage(), ConditionalLockBufferForCleanup(), GlobalVisTestFor(), GlobalVisTestIsRemovableXid(), HEAP_DEFAULT_FILLFACTOR, heap_page_prune(), LockBuffer(), Max, PruneResult::ndeleted, PruneResult::nnewlpdead, PageGetHeapFreeSpace(), PageIsFull(), pgstat_update_heap_dead_tuples(), RecoveryInProgress(), RelationGetTargetPageFreeSpace, and TransactionIdIsValid.

Referenced by heapam_index_fetch_tuple(), heapam_scan_bitmap_next_block(), and heapgetpage().

heap_prune_chain()

static int heap_prune_chain ( Buffer  buffer, OffsetNumber  rootoffnum, PruneState *  prstate  )

static

Definition at line 476 of file pruneheap.c.

{
    int         ndeleted = 0;
    Page        dp = (Page) BufferGetPage(buffer);
    TransactionId priorXmax = InvalidTransactionId;
    ItemId      rootlp;
    HeapTupleHeader htup;
    OffsetNumber latestdead = InvalidOffsetNumber,
                maxoff = PageGetMaxOffsetNumber(dp),
                offnum;
    OffsetNumber chainitems[MaxHeapTuplesPerPage];
    int         nchain = 0,
                i;
 
    rootlp = PageGetItemId(dp, rootoffnum);
 
    /*
     * If it's a heap-only tuple, then it is not the start of a HOT chain.
     */
    if (ItemIdIsNormal(rootlp))
    {
        Assert(prstate->htsv[rootoffnum] != -1);
        htup = (HeapTupleHeader) PageGetItem(dp, rootlp);
 
        if (HeapTupleHeaderIsHeapOnly(htup))
        {
            /*
             * If the tuple is DEAD and doesn't chain to anything else, mark
             * it unused immediately.  (If it does chain, we can only remove
             * it as part of pruning its chain.)
             *
             * We need this primarily to handle aborted HOT updates, that is,
             * XMIN_INVALID heap-only tuples.  Those might not be linked to by
             * any chain, since the parent tuple might be re-updated before
             * any pruning occurs.  So we have to be able to reap them
             * separately from chain-pruning.  (Note that
             * HeapTupleHeaderIsHotUpdated will never return true for an
             * XMIN_INVALID tuple, so this code will work even when there were
             * sequential updates within the aborted transaction.)
             *
             * Note that we might first arrive at a dead heap-only tuple
             * either here or while following a chain below.  Whichever path
             * gets there first will mark the tuple unused.
             */
            if (prstate->htsv[rootoffnum] == HEAPTUPLE_DEAD &&
                !HeapTupleHeaderIsHotUpdated(htup))
            {
                heap_prune_record_unused(prstate, rootoffnum);
                HeapTupleHeaderAdvanceConflictHorizon(htup,
                                                      &prstate->snapshotConflictHorizon);
                ndeleted++;
            }
 
            /* Nothing more to do */
            return ndeleted;
        }
    }
 
    /* Start from the root tuple */
    offnum = rootoffnum;
 
    /* while not end of the chain */
    for (;;)
    {
        ItemId      lp;
        bool        tupdead,
                    recent_dead;
 
        /* Sanity check (pure paranoia) */
        if (offnum < FirstOffsetNumber)
            break;
 
        /*
         * An offset past the end of page's line pointer array is possible
         * when the array was truncated (original item must have been unused)
         */
        if (offnum > maxoff)
            break;
 
        /* If item is already processed, stop --- it must not be same chain */
        if (prstate->marked[offnum])
            break;
 
        lp = PageGetItemId(dp, offnum);
 
        /* Unused item obviously isn't part of the chain */
        if (!ItemIdIsUsed(lp))
            break;
 
        /*
         * If we are looking at the redirected root line pointer, jump to the
         * first normal tuple in the chain.  If we find a redirect somewhere
         * else, stop --- it must not be same chain.
         */
        if (ItemIdIsRedirected(lp))
        {
            if (nchain > 0)
                break;          /* not at start of chain */
            chainitems[nchain++] = offnum;
            offnum = ItemIdGetRedirect(rootlp);
            continue;
        }
 
        /*
         * Likewise, a dead line pointer can't be part of the chain. (We
         * already eliminated the case of dead root tuple outside this
         * function.)
         */
        if (ItemIdIsDead(lp))
            break;
 
        Assert(ItemIdIsNormal(lp));
        Assert(prstate->htsv[offnum] != -1);
        htup = (HeapTupleHeader) PageGetItem(dp, lp);
 
        /*
         * Check the tuple XMIN against prior XMAX, if any
         */
        if (TransactionIdIsValid(priorXmax) &&
            !TransactionIdEquals(HeapTupleHeaderGetXmin(htup), priorXmax))
            break;
 
        /*
         * OK, this tuple is indeed a member of the chain.
         */
        chainitems[nchain++] = offnum;
 
        /*
         * Check tuple's visibility status.
         */
        tupdead = recent_dead = false;
 
        switch ((HTSV_Result) prstate->htsv[offnum])
        {
            case HEAPTUPLE_DEAD:
                tupdead = true;
                break;
 
            case HEAPTUPLE_RECENTLY_DEAD:
                recent_dead = true;
 
                /*
                 * This tuple may soon become DEAD.  Update the hint field so
                 * that the page is reconsidered for pruning in future.
                 */
                heap_prune_record_prunable(prstate,
                                           HeapTupleHeaderGetUpdateXid(htup));
                break;
 
            case HEAPTUPLE_DELETE_IN_PROGRESS:
 
                /*
                 * This tuple may soon become DEAD.  Update the hint field so
                 * that the page is reconsidered for pruning in future.
                 */
                heap_prune_record_prunable(prstate,
                                           HeapTupleHeaderGetUpdateXid(htup));
                break;
 
            case HEAPTUPLE_LIVE:
            case HEAPTUPLE_INSERT_IN_PROGRESS:
 
                /*
                 * If we wanted to optimize for aborts, we might consider
                 * marking the page prunable when we see INSERT_IN_PROGRESS.
                 * But we don't.  See related decisions about when to mark the
                 * page prunable in heapam.c.
                 */
                break;
 
            default:
                elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
                break;
        }
 
        /*
         * Remember the last DEAD tuple seen.  We will advance past
         * RECENTLY_DEAD tuples just in case there's a DEAD one after them;
         * but we can't advance past anything else.  We have to make sure that
         * we don't miss any DEAD tuples, since DEAD tuples that still have
         * tuple storage after pruning will confuse VACUUM.
         */
        if (tupdead)
        {
            latestdead = offnum;
            HeapTupleHeaderAdvanceConflictHorizon(htup,
                                                  &prstate->snapshotConflictHorizon);
        }
        else if (!recent_dead)
            break;
 
        /*
         * If the tuple is not HOT-updated, then we are at the end of this
         * HOT-update chain.
         */
        if (!HeapTupleHeaderIsHotUpdated(htup))
            break;
 
        /* HOT implies it can't have moved to different partition */
        Assert(!HeapTupleHeaderIndicatesMovedPartitions(htup));
 
        /*
         * Advance to next chain member.
         */
        Assert(ItemPointerGetBlockNumber(&htup->t_ctid) ==
               BufferGetBlockNumber(buffer));
        offnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
        priorXmax = HeapTupleHeaderGetUpdateXid(htup);
    }
 
    /*
     * If we found a DEAD tuple in the chain, adjust the HOT chain so that all
     * the DEAD tuples at the start of the chain are removed and the root line
     * pointer is appropriately redirected.
     */
    if (OffsetNumberIsValid(latestdead))
    {
        /*
         * Mark as unused each intermediate item that we are able to remove
         * from the chain.
         *
         * When the previous item is the last dead tuple seen, we are at the
         * right candidate for redirection.
         */
        for (i = 1; (i < nchain) && (chainitems[i - 1] != latestdead); i++)
        {
            heap_prune_record_unused(prstate, chainitems[i]);
            ndeleted++;
        }
 
        /*
         * If the root entry had been a normal tuple, we are deleting it, so
         * count it in the result.  But changing a redirect (even to DEAD
         * state) doesn't count.
         */
        if (ItemIdIsNormal(rootlp))
            ndeleted++;
 
        /*
         * If the DEAD tuple is at the end of the chain, the entire chain is
         * dead and the root line pointer can be marked dead.  Otherwise just
         * redirect the root to the correct chain member.
         */
        if (i >= nchain)
            heap_prune_record_dead(prstate, rootoffnum);
        else
            heap_prune_record_redirect(prstate, rootoffnum, chainitems[i]);
    }
    else if (nchain < 2 && ItemIdIsRedirected(rootlp))
    {
        /*
         * We found a redirect item that doesn't point to a valid follow-on
         * item.  This can happen if the loop in heap_page_prune caused us to
         * visit the dead successor of a redirect item before visiting the
         * redirect item.  We can clean up by setting the redirect item to
         * DEAD state.
         */
        heap_prune_record_dead(prstate, rootoffnum);
    }
 
    return ndeleted;
}

References Assert(), BufferGetBlockNumber(), BufferGetPage(), elog(), ERROR, FirstOffsetNumber, heap_prune_record_dead(), heap_prune_record_prunable(), heap_prune_record_redirect(), heap_prune_record_unused(), HEAPTUPLE_DEAD, HEAPTUPLE_DELETE_IN_PROGRESS, HEAPTUPLE_INSERT_IN_PROGRESS, HEAPTUPLE_LIVE, HEAPTUPLE_RECENTLY_DEAD, HeapTupleHeaderAdvanceConflictHorizon(), HeapTupleHeaderGetUpdateXid, HeapTupleHeaderGetXmin, HeapTupleHeaderIndicatesMovedPartitions, HeapTupleHeaderIsHeapOnly, HeapTupleHeaderIsHotUpdated, PruneState::htsv, i, InvalidOffsetNumber, InvalidTransactionId, ItemIdGetRedirect, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), PruneState::marked, MaxHeapTuplesPerPage, OffsetNumberIsValid, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), PruneState::snapshotConflictHorizon, HeapTupleHeaderData::t_ctid, TransactionIdEquals, and TransactionIdIsValid.

Referenced by heap_page_prune().

heap_prune_record_dead()

static void heap_prune_record_dead ( PruneState *  prstate, OffsetNumber  offnum  )

static

Definition at line 770 of file pruneheap.c.

{
    Assert(prstate->ndead < MaxHeapTuplesPerPage);
    prstate->nowdead[prstate->ndead] = offnum;
    prstate->ndead++;
    Assert(!prstate->marked[offnum]);
    prstate->marked[offnum] = true;
}

References Assert(), PruneState::marked, MaxHeapTuplesPerPage, PruneState::ndead, and PruneState::nowdead.

Referenced by heap_prune_chain().

heap_prune_record_prunable()

static void heap_prune_record_prunable ( PruneState *  prstate, TransactionId  xid  )

static

Definition at line 741 of file pruneheap.c.

{
    /*
     * This should exactly match the PageSetPrunable macro.  We can't store
     * directly into the page header yet, so we update working state.
     */
    Assert(TransactionIdIsNormal(xid));
    if (!TransactionIdIsValid(prstate->new_prune_xid) ||
        TransactionIdPrecedes(xid, prstate->new_prune_xid))
        prstate->new_prune_xid = xid;
}

References Assert(), PruneState::new_prune_xid, TransactionIdIsNormal, TransactionIdIsValid, and TransactionIdPrecedes().

Referenced by heap_prune_chain().

heap_prune_record_redirect()

static void heap_prune_record_redirect ( PruneState *  prstate, OffsetNumber  offnum, OffsetNumber  rdoffnum  )

static

Definition at line 755 of file pruneheap.c.

{
    Assert(prstate->nredirected < MaxHeapTuplesPerPage);
    prstate->redirected[prstate->nredirected * 2] = offnum;
    prstate->redirected[prstate->nredirected * 2 + 1] = rdoffnum;
    prstate->nredirected++;
    Assert(!prstate->marked[offnum]);
    prstate->marked[offnum] = true;
    Assert(!prstate->marked[rdoffnum]);
    prstate->marked[rdoffnum] = true;
}

References Assert(), PruneState::marked, MaxHeapTuplesPerPage, PruneState::nredirected, and PruneState::redirected.

Referenced by heap_prune_chain().

heap_prune_record_unused()

static void heap_prune_record_unused ( PruneState *  prstate, OffsetNumber  offnum  )

static

Definition at line 781 of file pruneheap.c.

{
    Assert(prstate->nunused < MaxHeapTuplesPerPage);
    prstate->nowunused[prstate->nunused] = offnum;
    prstate->nunused++;
    Assert(!prstate->marked[offnum]);
    prstate->marked[offnum] = true;
}

References Assert(), PruneState::marked, MaxHeapTuplesPerPage, PruneState::nowunused, and PruneState::nunused.

Referenced by heap_prune_chain().

heap_prune_satisfies_vacuum()

static HTSV_Result heap_prune_satisfies_vacuum ( PruneState *  prstate, HeapTuple  tup, Buffer  buffer  )

static

Definition at line 429 of file pruneheap.c.

{
    HTSV_Result res;
    TransactionId dead_after;
 
    res = HeapTupleSatisfiesVacuumHorizon(tup, buffer, &dead_after);
 
    if (res != HEAPTUPLE_RECENTLY_DEAD)
        return res;
 
    if (GlobalVisTestIsRemovableXid(prstate->vistest, dead_after))
        res = HEAPTUPLE_DEAD;
 
    return res;
}

References GlobalVisTestIsRemovableXid(), HEAPTUPLE_DEAD, HEAPTUPLE_RECENTLY_DEAD, HeapTupleSatisfiesVacuumHorizon(), res, and PruneState::vistest.

Referenced by heap_page_prune().

page_verify_redirects()

static void page_verify_redirects ( Page  page )

static

Definition at line 948 of file pruneheap.c.

{
#ifdef USE_ASSERT_CHECKING
    OffsetNumber offnum;
    OffsetNumber maxoff;
 
    maxoff = PageGetMaxOffsetNumber(page);
    for (offnum = FirstOffsetNumber;
         offnum <= maxoff;
         offnum = OffsetNumberNext(offnum))
    {
        ItemId      itemid = PageGetItemId(page, offnum);
        OffsetNumber targoff;
        ItemId      targitem;
        HeapTupleHeader htup;
 
        if (!ItemIdIsRedirected(itemid))
            continue;
 
        targoff = ItemIdGetRedirect(itemid);
        targitem = PageGetItemId(page, targoff);
 
        Assert(ItemIdIsUsed(targitem));
        Assert(ItemIdIsNormal(targitem));
        Assert(ItemIdHasStorage(targitem));
        htup = (HeapTupleHeader) PageGetItem(page, targitem);
        Assert(HeapTupleHeaderIsHeapOnly(htup));
    }
#endif
}

References Assert(), FirstOffsetNumber, HeapTupleHeaderIsHeapOnly, ItemIdGetRedirect, ItemIdHasStorage, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, OffsetNumberNext, PageGetItem(), PageGetItemId(), and PageGetMaxOffsetNumber().

Referenced by heap_page_prune_execute().