pruneheap.c File Reference

#include "postgres.h"
#include "access/heapam.h"
#include "access/heapam_xlog.h"
#include "access/htup_details.h"
#include "access/multixact.h"
#include "access/transam.h"
#include "access/visibilitymapdefs.h"
#include "access/xlog.h"
#include "access/xloginsert.h"
#include "commands/vacuum.h"
#include "executor/instrument.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "storage/bufmgr.h"
#include "utils/rel.h"
#include "utils/snapmgr.h"

Include dependency graph for pruneheap.c:

Go to the source code of this file.

Data Structures
struct	PruneState

Functions
static void	prune_freeze_setup (PruneFreezeParams *params, TransactionId *new_relfrozen_xid, MultiXactId *new_relmin_mxid, PruneFreezeResult *presult, PruneState *prstate)
static void	prune_freeze_plan (PruneState *prstate, OffsetNumber *off_loc)
static HTSV_Result	heap_prune_satisfies_vacuum (PruneState *prstate, HeapTuple tup)
static HTSV_Result	htsv_get_valid_status (int status)
static void	heap_prune_chain (OffsetNumber maxoff, 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, bool was_normal)
static void	heap_prune_record_dead (PruneState *prstate, OffsetNumber offnum, bool was_normal)
static void	heap_prune_record_dead_or_unused (PruneState *prstate, OffsetNumber offnum, bool was_normal)
static void	heap_prune_record_unused (PruneState *prstate, OffsetNumber offnum, bool was_normal)
static void	heap_prune_record_unchanged_lp_unused (PruneState *prstate, OffsetNumber offnum)
static void	heap_prune_record_unchanged_lp_normal (PruneState *prstate, OffsetNumber offnum)
static void	heap_prune_record_unchanged_lp_dead (PruneState *prstate, OffsetNumber offnum)
static void	heap_prune_record_unchanged_lp_redirect (PruneState *prstate, OffsetNumber offnum)
static void	page_verify_redirects (Page page)
static bool	heap_page_will_freeze (bool did_tuple_hint_fpi, bool do_prune, bool do_hint_prune, PruneState *prstate)
void	heap_page_prune_opt (Relation relation, Buffer buffer, Buffer *vmbuffer)
void	heap_page_prune_and_freeze (PruneFreezeParams *params, PruneFreezeResult *presult, OffsetNumber *off_loc, TransactionId *new_relfrozen_xid, MultiXactId *new_relmin_mxid)
void	heap_page_prune_execute (Buffer buffer, bool lp_truncate_only, OffsetNumber *redirected, int nredirected, OffsetNumber *nowdead, int ndead, OffsetNumber *nowunused, int nunused)
void	heap_get_root_tuples (Page page, OffsetNumber *root_offsets)
static bool	heap_log_freeze_eq (xlhp_freeze_plan *plan, HeapTupleFreeze *frz)
static int	heap_log_freeze_cmp (const void *arg1, const void *arg2)
static void	heap_log_freeze_new_plan (xlhp_freeze_plan *plan, HeapTupleFreeze *frz)
static int	heap_log_freeze_plan (HeapTupleFreeze *tuples, int ntuples, xlhp_freeze_plan *plans_out, OffsetNumber *offsets_out)
void	log_heap_prune_and_freeze (Relation relation, Buffer buffer, Buffer vmbuffer, uint8 vmflags, TransactionId conflict_xid, bool cleanup_lock, PruneReason reason, HeapTupleFreeze *frozen, int nfrozen, OffsetNumber *redirected, int nredirected, OffsetNumber *dead, int ndead, OffsetNumber *unused, int nunused)

Function Documentation

heap_get_root_tuples()

void heap_get_root_tuples	(	Page	page,
		OffsetNumber *	root_offsets
	)

Definition at line 1890 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, fb(), 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_log_freeze_cmp()

static int heap_log_freeze_cmp ( const void *  arg1, const void *  arg2  )

static

Definition at line 2017 of file pruneheap.c.

{
    const HeapTupleFreeze *frz1 = arg1;
    const HeapTupleFreeze *frz2 = arg2;
 
    if (frz1->xmax < frz2->xmax)
        return -1;
    else if (frz1->xmax > frz2->xmax)
        return 1;
 
    if (frz1->t_infomask2 < frz2->t_infomask2)
        return -1;
    else if (frz1->t_infomask2 > frz2->t_infomask2)
        return 1;
 
    if (frz1->t_infomask < frz2->t_infomask)
        return -1;
    else if (frz1->t_infomask > frz2->t_infomask)
        return 1;
 
    if (frz1->frzflags < frz2->frzflags)
        return -1;
    else if (frz1->frzflags > frz2->frzflags)
        return 1;
 
    /*
     * heap_log_freeze_eq would consider these tuple-wise plans to be equal.
     * (So the tuples will share a single canonical freeze plan.)
     *
     * We tiebreak on page offset number to keep each freeze plan's page
     * offset number array individually sorted. (Unnecessary, but be tidy.)
     */
    if (frz1->offset < frz2->offset)
        return -1;
    else if (frz1->offset > frz2->offset)
        return 1;
 
    Assert(false);
    return 0;
}

References Assert, and fb().

Referenced by heap_log_freeze_plan().

heap_log_freeze_eq()

static bool heap_log_freeze_eq ( xlhp_freeze_plan *  plan, HeapTupleFreeze *  frz  )

inlinestatic

Definition at line 2001 of file pruneheap.c.

{
    if (plan->xmax == frz->xmax &&
        plan->t_infomask2 == frz->t_infomask2 &&
        plan->t_infomask == frz->t_infomask &&
        plan->frzflags == frz->frzflags)
        return true;
 
    /* Caller must call heap_log_freeze_new_plan again for frz */
    return false;
}

References fb(), and plan.

Referenced by heap_log_freeze_plan().

heap_log_freeze_new_plan()

static void heap_log_freeze_new_plan ( xlhp_freeze_plan *  plan, HeapTupleFreeze *  frz  )

inlinestatic

Definition at line 2063 of file pruneheap.c.

{
    plan->xmax = frz->xmax;
    plan->t_infomask2 = frz->t_infomask2;
    plan->t_infomask = frz->t_infomask;
    plan->frzflags = frz->frzflags;
    plan->ntuples = 1;          /* for now */
}

References fb(), and plan.

Referenced by heap_log_freeze_plan().

heap_log_freeze_plan()

static int heap_log_freeze_plan ( HeapTupleFreeze *  tuples, int  ntuples, xlhp_freeze_plan *  plans_out, OffsetNumber *  offsets_out  )

static

Definition at line 2083 of file pruneheap.c.

{
    int         nplans = 0;
 
    /* Sort tuple-based freeze plans in the order required to deduplicate */
    qsort(tuples, ntuples, sizeof(HeapTupleFreeze), heap_log_freeze_cmp);
 
    for (int i = 0; i < ntuples; i++)
    {
        HeapTupleFreeze *frz = tuples + i;
 
        if (i == 0)
        {
            /* New canonical freeze plan starting with first tup */
            heap_log_freeze_new_plan(plans_out, frz);
            nplans++;
        }
        else if (heap_log_freeze_eq(plans_out, frz))
        {
            /* tup matches open canonical plan -- include tup in it */
            Assert(offsets_out[i - 1] < frz->offset);
            plans_out->ntuples++;
        }
        else
        {
            /* Tup doesn't match current plan -- done with it now */
            plans_out++;
 
            /* New canonical freeze plan starting with this tup */
            heap_log_freeze_new_plan(plans_out, frz);
            nplans++;
        }
 
        /*
         * Save page offset number in dedicated buffer in passing.
         *
         * REDO routine relies on the record's offset numbers array grouping
         * offset numbers by freeze plan.  The sort order within each grouping
         * is ascending offset number order, just to keep things tidy.
         */
        offsets_out[i] = frz->offset;
    }
 
    Assert(nplans > 0 && nplans <= ntuples);
 
    return nplans;
}

References Assert, fb(), heap_log_freeze_cmp(), heap_log_freeze_eq(), heap_log_freeze_new_plan(), i, and qsort.

Referenced by log_heap_prune_and_freeze().

heap_page_prune_and_freeze()

void heap_page_prune_and_freeze	(	PruneFreezeParams *	params,
		PruneFreezeResult *	presult,
		OffsetNumber *	off_loc,
		TransactionId *	new_relfrozen_xid,
		MultiXactId *	new_relmin_mxid
	)

Definition at line 815 of file pruneheap.c.

{
    PruneState  prstate;
    bool        do_freeze;
    bool        do_prune;
    bool        do_hint_prune;
    bool        did_tuple_hint_fpi;
    int64       fpi_before = pgWalUsage.wal_fpi;
 
    /* Initialize prstate */
    prune_freeze_setup(params,
                       new_relfrozen_xid, new_relmin_mxid,
                       presult, &prstate);
 
    /*
     * Examine all line pointers and tuple visibility information to determine
     * which line pointers should change state and which tuples may be frozen.
     * Prepare queue of state changes to later be executed in a critical
     * section.
     */
    prune_freeze_plan(&prstate, off_loc);
 
    /*
     * If checksums are enabled, calling heap_prune_satisfies_vacuum() while
     * checking tuple visibility information in prune_freeze_plan() may have
     * caused an FPI to be emitted.
     */
    did_tuple_hint_fpi = fpi_before != pgWalUsage.wal_fpi;
 
    do_prune = prstate.nredirected > 0 ||
        prstate.ndead > 0 ||
        prstate.nunused > 0;
 
    /*
     * Even if we don't prune anything, if we found a new value for the
     * pd_prune_xid field or the page was marked full, we will update the hint
     * bit.
     */
    do_hint_prune = PageGetPruneXid(prstate.page) != prstate.new_prune_xid ||
        PageIsFull(prstate.page);
 
    /*
     * Decide if we want to go ahead with freezing according to the freeze
     * plans we prepared, or not.
     */
    do_freeze = heap_page_will_freeze(did_tuple_hint_fpi,
                                      do_prune,
                                      do_hint_prune,
                                      &prstate);
 
    /*
     * While scanning the line pointers, we did not clear
     * set_all_visible/set_all_frozen when encountering LP_DEAD items because
     * we wanted the decision whether or not to freeze the page to be
     * unaffected by the short-term presence of LP_DEAD items.  These LP_DEAD
     * items are effectively assumed to be LP_UNUSED items in the making.  It
     * doesn't matter which vacuum heap pass (initial pass or final pass) ends
     * up setting the page all-frozen, as long as the ongoing VACUUM does it.
     *
     * Now that we finished determining whether or not to freeze the page,
     * update set_all_visible and set_all_frozen so that they reflect the true
     * state of the page for setting PD_ALL_VISIBLE and VM bits.
     */
    if (prstate.lpdead_items > 0)
        prstate.set_all_visible = prstate.set_all_frozen = false;
 
    Assert(!prstate.set_all_frozen || prstate.set_all_visible);
 
    /* Any error while applying the changes is critical */
    START_CRIT_SECTION();
 
    if (do_hint_prune)
    {
        /*
         * Update the page's pd_prune_xid field to either zero, or the lowest
         * XID of any soon-prunable tuple.
         */
        ((PageHeader) prstate.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(prstate.page);
 
        /*
         * If that's all we had to do to the page, this is a non-WAL-logged
         * hint.  If we are going to freeze or prune the page, we will mark
         * the buffer dirty below.
         */
        if (!do_freeze && !do_prune)
            MarkBufferDirtyHint(prstate.buffer, true);
    }
 
    if (do_prune || do_freeze)
    {
        /* Apply the planned item changes and repair page fragmentation. */
        if (do_prune)
        {
            heap_page_prune_execute(prstate.buffer, false,
                                    prstate.redirected, prstate.nredirected,
                                    prstate.nowdead, prstate.ndead,
                                    prstate.nowunused, prstate.nunused);
        }
 
        if (do_freeze)
            heap_freeze_prepared_tuples(prstate.buffer, prstate.frozen, prstate.nfrozen);
 
        MarkBufferDirty(prstate.buffer);
 
        /*
         * Emit a WAL XLOG_HEAP2_PRUNE* record showing what we did
         */
        if (RelationNeedsWAL(prstate.relation))
        {
            /*
             * The snapshotConflictHorizon for the whole record should be the
             * most conservative of all the horizons calculated for any of the
             * possible modifications. If this record will prune tuples, any
             * queries on the standby older than the newest xid of the most
             * recently removed tuple this record will prune will conflict. If
             * this record will freeze tuples, any queries on the standby with
             * xids older than the newest tuple this record will freeze will
             * conflict.
             */
            TransactionId conflict_xid;
 
            if (TransactionIdFollows(prstate.pagefrz.FreezePageConflictXid,
                                     prstate.latest_xid_removed))
                conflict_xid = prstate.pagefrz.FreezePageConflictXid;
            else
                conflict_xid = prstate.latest_xid_removed;
 
            log_heap_prune_and_freeze(prstate.relation, prstate.buffer,
                                      InvalidBuffer,    /* vmbuffer */
                                      0,    /* vmflags */
                                      conflict_xid,
                                      true, params->reason,
                                      prstate.frozen, prstate.nfrozen,
                                      prstate.redirected, prstate.nredirected,
                                      prstate.nowdead, prstate.ndead,
                                      prstate.nowunused, prstate.nunused);
        }
    }
 
    END_CRIT_SECTION();
 
    /* Copy information back for caller */
    presult->ndeleted = prstate.ndeleted;
    presult->nnewlpdead = prstate.ndead;
    presult->nfrozen = prstate.nfrozen;
    presult->live_tuples = prstate.live_tuples;
    presult->recently_dead_tuples = prstate.recently_dead_tuples;
    presult->set_all_visible = prstate.set_all_visible;
    presult->set_all_frozen = prstate.set_all_frozen;
    presult->hastup = prstate.hastup;
 
    /*
     * For callers planning to update the visibility map, the conflict horizon
     * for that record must be the newest xmin on the page.  However, if the
     * page is completely frozen, there can be no conflict and the
     * vm_conflict_horizon should remain InvalidTransactionId.  This includes
     * the case that we just froze all the tuples; the prune-freeze record
     * included the conflict XID already so the caller doesn't need it.
     */
    if (presult->set_all_frozen)
        presult->vm_conflict_horizon = InvalidTransactionId;
    else
        presult->vm_conflict_horizon = prstate.visibility_cutoff_xid;
 
    presult->lpdead_items = prstate.lpdead_items;
    /* the presult->deadoffsets array was already filled in */
 
    if (prstate.attempt_freeze)
    {
        if (presult->nfrozen > 0)
        {
            *new_relfrozen_xid = prstate.pagefrz.FreezePageRelfrozenXid;
            *new_relmin_mxid = prstate.pagefrz.FreezePageRelminMxid;
        }
        else
        {
            *new_relfrozen_xid = prstate.pagefrz.NoFreezePageRelfrozenXid;
            *new_relmin_mxid = prstate.pagefrz.NoFreezePageRelminMxid;
        }
    }
}

References Assert, END_CRIT_SECTION, fb(), heap_freeze_prepared_tuples(), heap_page_prune_execute(), heap_page_will_freeze(), InvalidBuffer, InvalidTransactionId, log_heap_prune_and_freeze(), MarkBufferDirty(), MarkBufferDirtyHint(), PageClearFull(), PageGetPruneXid(), PageIsFull(), pgWalUsage, prune_freeze_plan(), prune_freeze_setup(), PruneFreezeParams::reason, RelationNeedsWAL, START_CRIT_SECTION, TransactionIdFollows(), and WalUsage::wal_fpi.

Referenced by heap_page_prune_opt(), and lazy_scan_prune().

heap_page_prune_execute()

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

Definition at line 1666 of file pruneheap.c.

{
    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);
 
    /* If 'lp_truncate_only', we can only remove already-dead line pointers */
    Assert(!lp_truncate_only || (nredirected == 0 && ndead == 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
 
        if (lp_truncate_only)
        {
            /* Setting LP_DEAD to LP_UNUSED in vacuum's second pass */
            Assert(ItemIdIsDead(lp) && !ItemIdHasStorage(lp));
        }
        else
        {
            /*
             * When heap_page_prune_and_freeze() was called, mark_unused_now
             * may have been passed as true, which allows would-be LP_DEAD
             * items to be made LP_UNUSED instead.  This is only possible if
             * the relation has no indexes.  If there are any dead items, then
             * mark_unused_now was not true and every item being marked
             * LP_UNUSED must refer to a heap-only tuple.
             */
            if (ndead > 0)
            {
                Assert(ItemIdHasStorage(lp) && ItemIdIsNormal(lp));
                htup = (HeapTupleHeader) PageGetItem(page, lp);
                Assert(HeapTupleHeaderIsHeapOnly(htup));
            }
            else
                Assert(ItemIdIsUsed(lp));
        }
 
#endif
 
        ItemIdSetUnused(lp);
    }
 
    if (lp_truncate_only)
        PageTruncateLinePointerArray(page);
    else
    {
        /*
         * 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(), fb(), HeapTupleHeaderIsHeapOnly(), i, ItemIdGetRedirect, ItemIdHasStorage, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemIdSetDead, ItemIdSetRedirect, ItemIdSetUnused, page_verify_redirects(), PageGetItem(), PageGetItemId(), PageRepairFragmentation(), PageTruncateLinePointerArray(), and PG_USED_FOR_ASSERTS_ONLY.

Referenced by heap_page_prune_and_freeze(), and heap_xlog_prune_freeze().

heap_page_prune_opt()

void heap_page_prune_opt	(	Relation	relation,
		Buffer	buffer,
		Buffer *	vmbuffer
	)

Definition at line 216 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 = PageGetPruneXid(page);
    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)
        {
            OffsetNumber dummy_off_loc;
            PruneFreezeResult presult;
 
            /*
             * We don't pass the HEAP_PAGE_PRUNE_MARK_UNUSED_NOW option
             * regardless of whether or not the relation has indexes, since we
             * cannot safely determine that during on-access pruning with the
             * current implementation.
             */
            PruneFreezeParams params = {
                .relation = relation,
                .buffer = buffer,
                .reason = PRUNE_ON_ACCESS,
                .options = 0,
                .vistest = vistest,
                .cutoffs = NULL,
            };
 
            heap_page_prune_and_freeze(&params, &presult, &dummy_off_loc,
                                       NULL, 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(), fb(), GlobalVisTestFor(), GlobalVisTestIsRemovableXid(), HEAP_DEFAULT_FILLFACTOR, heap_page_prune_and_freeze(), LockBuffer(), Max, PageGetHeapFreeSpace(), PageGetPruneXid(), PageIsFull(), pgstat_update_heap_dead_tuples(), PRUNE_ON_ACCESS, RecoveryInProgress(), PruneFreezeParams::relation, RelationGetTargetPageFreeSpace, and TransactionIdIsValid.

Referenced by BitmapHeapScanNextBlock(), heap_prepare_pagescan(), and heapam_index_fetch_tuple().

heap_page_will_freeze()

static bool heap_page_will_freeze ( bool  did_tuple_hint_fpi, bool  do_prune, bool  do_hint_prune, PruneState *  prstate  )

static

Definition at line 672 of file pruneheap.c.

{
    bool        do_freeze = false;
 
    /*
     * If the caller specified we should not attempt to freeze any tuples,
     * validate that everything is in the right state and return.
     */
    if (!prstate->attempt_freeze)
    {
        Assert(!prstate->set_all_frozen && prstate->nfrozen == 0);
        Assert(prstate->lpdead_items == 0 || !prstate->set_all_visible);
        return false;
    }
 
    if (prstate->pagefrz.freeze_required)
    {
        /*
         * heap_prepare_freeze_tuple indicated that at least one XID/MXID from
         * before FreezeLimit/MultiXactCutoff is present.  Must freeze to
         * advance relfrozenxid/relminmxid.
         */
        do_freeze = true;
    }
    else
    {
        /*
         * Opportunistically freeze the page if we are generating an FPI
         * anyway and if doing so means that we can set the page all-frozen
         * afterwards (might not happen until VACUUM's final heap pass).
         *
         * XXX: Previously, we knew if pruning emitted an FPI by checking
         * pgWalUsage.wal_fpi before and after pruning.  Once the freeze and
         * prune records were combined, this heuristic couldn't be used
         * anymore.  The opportunistic freeze heuristic must be improved;
         * however, for now, try to approximate the old logic.
         */
        if (prstate->set_all_frozen && prstate->nfrozen > 0)
        {
            Assert(prstate->set_all_visible);
 
            /*
             * Freezing would make the page all-frozen.  Have already emitted
             * an FPI or will do so anyway?
             */
            if (RelationNeedsWAL(prstate->relation))
            {
                if (did_tuple_hint_fpi)
                    do_freeze = true;
                else if (do_prune)
                {
                    if (XLogCheckBufferNeedsBackup(prstate->buffer))
                        do_freeze = true;
                }
                else if (do_hint_prune)
                {
                    if (XLogHintBitIsNeeded() &&
                        XLogCheckBufferNeedsBackup(prstate->buffer))
                        do_freeze = true;
                }
            }
        }
    }
 
    if (do_freeze)
    {
        /*
         * Validate the tuples we will be freezing before entering the
         * critical section.
         */
        heap_pre_freeze_checks(prstate->buffer, prstate->frozen, prstate->nfrozen);
        Assert(TransactionIdPrecedes(prstate->pagefrz.FreezePageConflictXid,
                                     prstate->cutoffs->OldestXmin));
    }
    else if (prstate->nfrozen > 0)
    {
        /*
         * The page contained some tuples that were not already frozen, and we
         * chose not to freeze them now.  The page won't be all-frozen then.
         */
        Assert(!prstate->pagefrz.freeze_required);
 
        prstate->set_all_frozen = false;
        prstate->nfrozen = 0;   /* avoid miscounts in instrumentation */
    }
    else
    {
        /*
         * We have no freeze plans to execute.  The page might already be
         * all-frozen (perhaps only following pruning), though.  Such pages
         * can be marked all-frozen in the VM by our caller, even though none
         * of its tuples were newly frozen here.
         */
    }
 
    return do_freeze;
}

References Assert, fb(), heap_pre_freeze_checks(), RelationNeedsWAL, TransactionIdPrecedes(), XLogCheckBufferNeedsBackup(), and XLogHintBitIsNeeded.

Referenced by heap_page_prune_and_freeze().

heap_prune_chain()

static void heap_prune_chain ( OffsetNumber  maxoff, OffsetNumber  rootoffnum, PruneState *  prstate  )

static

Definition at line 1095 of file pruneheap.c.

{
    TransactionId priorXmax = InvalidTransactionId;
    ItemId      rootlp;
    OffsetNumber offnum;
    OffsetNumber chainitems[MaxHeapTuplesPerPage];
    Page        page = prstate->page;
 
    /*
     * After traversing the HOT chain, ndeadchain is the index in chainitems
     * of the first live successor after the last dead item.
     */
    int         ndeadchain = 0,
                nchain = 0;
 
    rootlp = PageGetItemId(page, rootoffnum);
 
    /* Start from the root tuple */
    offnum = rootoffnum;
 
    /* while not end of the chain */
    for (;;)
    {
        HeapTupleHeader htup;
        ItemId      lp;
 
        /* 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->processed[offnum])
            break;
 
        lp = PageGetItemId(page, offnum);
 
        /*
         * Unused item obviously isn't part of the chain. Likewise, a dead
         * line pointer can't be part of the chain.  Both of those cases were
         * already marked as processed.
         */
        Assert(ItemIdIsUsed(lp));
        Assert(!ItemIdIsDead(lp));
 
        /*
         * 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;
        }
 
        Assert(ItemIdIsNormal(lp));
 
        htup = (HeapTupleHeader) PageGetItem(page, 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;
 
        switch (htsv_get_valid_status(prstate->htsv[offnum]))
        {
            case HEAPTUPLE_DEAD:
 
                /* Remember the last DEAD tuple seen */
                ndeadchain = nchain;
                HeapTupleHeaderAdvanceConflictHorizon(htup,
                                                      &prstate->latest_xid_removed);
                /* Advance to next chain member */
                break;
 
            case HEAPTUPLE_RECENTLY_DEAD:
 
                /*
                 * We don't need to advance the conflict horizon for
                 * RECENTLY_DEAD tuples, even if we are removing them.  This
                 * is because we only remove RECENTLY_DEAD tuples if they
                 * precede a DEAD tuple, and the DEAD tuple must have been
                 * inserted by a newer transaction than the RECENTLY_DEAD
                 * tuple by virtue of being later in the chain.  We will have
                 * advanced the conflict horizon for the DEAD tuple.
                 */
 
                /*
                 * Advance past RECENTLY_DEAD tuples just in case there's a
                 * DEAD one after them.  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.
                 */
                break;
 
            case HEAPTUPLE_DELETE_IN_PROGRESS:
            case HEAPTUPLE_LIVE:
            case HEAPTUPLE_INSERT_IN_PROGRESS:
                goto process_chain;
 
            default:
                elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result");
                goto process_chain;
        }
 
        /*
         * If the tuple is not HOT-updated, then we are at the end of this
         * HOT-update chain.
         */
        if (!HeapTupleHeaderIsHotUpdated(htup))
            goto process_chain;
 
        /* HOT implies it can't have moved to different partition */
        Assert(!HeapTupleHeaderIndicatesMovedPartitions(htup));
 
        /*
         * Advance to next chain member.
         */
        Assert(ItemPointerGetBlockNumber(&htup->t_ctid) == prstate->block);
        offnum = ItemPointerGetOffsetNumber(&htup->t_ctid);
        priorXmax = HeapTupleHeaderGetUpdateXid(htup);
    }
 
    if (ItemIdIsRedirected(rootlp) && nchain < 2)
    {
        /*
         * 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_and_freeze()
         * 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 LP_DEAD state or LP_UNUSED if the caller
         * indicated.
         */
        heap_prune_record_dead_or_unused(prstate, rootoffnum, false);
        return;
    }
 
process_chain:
 
    if (ndeadchain == 0)
    {
        /*
         * No DEAD tuple was found, so the chain is entirely composed of
         * normal, unchanged tuples.  Leave it alone.
         */
        int         i = 0;
 
        if (ItemIdIsRedirected(rootlp))
        {
            heap_prune_record_unchanged_lp_redirect(prstate, rootoffnum);
            i++;
        }
        for (; i < nchain; i++)
            heap_prune_record_unchanged_lp_normal(prstate, chainitems[i]);
    }
    else if (ndeadchain == nchain)
    {
        /*
         * The entire chain is dead.  Mark the root line pointer LP_DEAD, and
         * fully remove the other tuples in the chain.
         */
        heap_prune_record_dead_or_unused(prstate, rootoffnum, ItemIdIsNormal(rootlp));
        for (int i = 1; i < nchain; i++)
            heap_prune_record_unused(prstate, chainitems[i], true);
    }
    else
    {
        /*
         * We found a DEAD tuple in the chain.  Redirect the root line pointer
         * to the first non-DEAD tuple, and mark as unused each intermediate
         * item that we are able to remove from the chain.
         */
        heap_prune_record_redirect(prstate, rootoffnum, chainitems[ndeadchain],
                                   ItemIdIsNormal(rootlp));
        for (int i = 1; i < ndeadchain; i++)
            heap_prune_record_unused(prstate, chainitems[i], true);
 
        /* the rest of tuples in the chain are normal, unchanged tuples */
        for (int i = ndeadchain; i < nchain; i++)
            heap_prune_record_unchanged_lp_normal(prstate, chainitems[i]);
    }
}

References Assert, elog, ERROR, fb(), FirstOffsetNumber, heap_prune_record_dead_or_unused(), heap_prune_record_redirect(), heap_prune_record_unchanged_lp_normal(), heap_prune_record_unchanged_lp_redirect(), heap_prune_record_unused(), HEAPTUPLE_DEAD, HEAPTUPLE_DELETE_IN_PROGRESS, HEAPTUPLE_INSERT_IN_PROGRESS, HEAPTUPLE_LIVE, HEAPTUPLE_RECENTLY_DEAD, HeapTupleHeaderAdvanceConflictHorizon(), HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderGetXmin(), HeapTupleHeaderIndicatesMovedPartitions(), HeapTupleHeaderIsHotUpdated(), htsv_get_valid_status(), i, InvalidTransactionId, ItemIdGetRedirect, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), MaxHeapTuplesPerPage, PageGetItem(), PageGetItemId(), HeapTupleHeaderData::t_ctid, TransactionIdEquals, and TransactionIdIsValid.

Referenced by prune_freeze_plan().

heap_prune_record_dead()

static void heap_prune_record_dead ( PruneState *  prstate, OffsetNumber  offnum, bool  was_normal  )

static

Definition at line 1343 of file pruneheap.c.

{
    Assert(!prstate->processed[offnum]);
    prstate->processed[offnum] = true;
 
    Assert(prstate->ndead < MaxHeapTuplesPerPage);
    prstate->nowdead[prstate->ndead] = offnum;
    prstate->ndead++;
 
    /*
     * Deliberately delay unsetting set_all_visible and set_all_frozen until
     * later during pruning. Removable dead tuples shouldn't preclude freezing
     * the page.
     */
 
    /* Record the dead offset for vacuum */
    prstate->deadoffsets[prstate->lpdead_items++] = offnum;
 
    /*
     * 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 (was_normal)
        prstate->ndeleted++;
}

References Assert, fb(), and MaxHeapTuplesPerPage.

Referenced by heap_prune_record_dead_or_unused().

heap_prune_record_dead_or_unused()

static void heap_prune_record_dead_or_unused ( PruneState *  prstate, OffsetNumber  offnum, bool  was_normal  )

static

Definition at line 1378 of file pruneheap.c.

{
    /*
     * If the caller set mark_unused_now to true, we can remove dead tuples
     * during pruning instead of marking their line pointers dead. Set this
     * tuple's line pointer LP_UNUSED. We hint that this option is less
     * likely.
     */
    if (unlikely(prstate->mark_unused_now))
        heap_prune_record_unused(prstate, offnum, was_normal);
    else
        heap_prune_record_dead(prstate, offnum, was_normal);
}

References fb(), heap_prune_record_dead(), heap_prune_record_unused(), and unlikely.

Referenced by heap_prune_chain().

heap_prune_record_prunable()

static void heap_prune_record_prunable ( PruneState *  prstate, TransactionId  xid  )

static

Definition at line 1298 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, fb(), TransactionIdIsNormal, TransactionIdIsValid, and TransactionIdPrecedes().

Referenced by heap_prune_record_unchanged_lp_normal().

heap_prune_record_redirect()

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

static

Definition at line 1312 of file pruneheap.c.

{
    Assert(!prstate->processed[offnum]);
    prstate->processed[offnum] = true;
 
    /*
     * Do not mark the redirect target here.  It needs to be counted
     * separately as an unchanged tuple.
     */
 
    Assert(prstate->nredirected < MaxHeapTuplesPerPage);
    prstate->redirected[prstate->nredirected * 2] = offnum;
    prstate->redirected[prstate->nredirected * 2 + 1] = rdoffnum;
 
    prstate->nredirected++;
 
    /*
     * 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 (was_normal)
        prstate->ndeleted++;
 
    prstate->hastup = true;
}

References Assert, fb(), and MaxHeapTuplesPerPage.

Referenced by heap_prune_chain().

heap_prune_record_unchanged_lp_dead()

static void heap_prune_record_unchanged_lp_dead ( PruneState *  prstate, OffsetNumber  offnum  )

static

Definition at line 1613 of file pruneheap.c.

{
    Assert(!prstate->processed[offnum]);
    prstate->processed[offnum] = true;
 
    /*
     * Deliberately don't set hastup for LP_DEAD items.  We make the soft
     * assumption that any LP_DEAD items encountered here will become
     * LP_UNUSED later on, before count_nondeletable_pages is reached.  If we
     * don't make this assumption then rel truncation will only happen every
     * other VACUUM, at most.  Besides, VACUUM must treat
     * hastup/nonempty_pages as provisional no matter how LP_DEAD items are
     * handled (handled here, or handled later on).
     *
     * Similarly, don't unset set_all_visible and set_all_frozen until later,
     * at the end of heap_page_prune_and_freeze().  This will allow us to
     * attempt to freeze the page after pruning.  As long as we unset it
     * before updating the visibility map, this will be correct.
     */
 
    /* Record the dead offset for vacuum */
    prstate->deadoffsets[prstate->lpdead_items++] = offnum;
}

References Assert, and fb().

Referenced by prune_freeze_plan().

heap_prune_record_unchanged_lp_normal()

static void heap_prune_record_unchanged_lp_normal ( PruneState *  prstate, OffsetNumber  offnum  )

static

Definition at line 1428 of file pruneheap.c.

{
    HeapTupleHeader htup;
    Page        page = prstate->page;
 
    Assert(!prstate->processed[offnum]);
    prstate->processed[offnum] = true;
 
    prstate->hastup = true;     /* the page is not empty */
 
    /*
     * The criteria for counting a tuple as live in this block need to match
     * what analyze.c's acquire_sample_rows() does, otherwise VACUUM and
     * ANALYZE may produce wildly different reltuples values, e.g. when there
     * are many recently-dead tuples.
     *
     * The logic here is a bit simpler than acquire_sample_rows(), as VACUUM
     * can't run inside a transaction block, which makes some cases impossible
     * (e.g. in-progress insert from the same transaction).
     *
     * HEAPTUPLE_DEAD are handled by the other heap_prune_record_*()
     * subroutines.  They don't count dead items like acquire_sample_rows()
     * does, because we assume that all dead items will become LP_UNUSED
     * before VACUUM finishes.  This difference is only superficial.  VACUUM
     * effectively agrees with ANALYZE about DEAD items, in the end.  VACUUM
     * won't remember LP_DEAD items, but only because they're not supposed to
     * be left behind when it is done. (Cases where we bypass index vacuuming
     * will violate this optimistic assumption, but the overall impact of that
     * should be negligible.)
     */
    htup = (HeapTupleHeader) PageGetItem(page, PageGetItemId(page, offnum));
 
    switch (prstate->htsv[offnum])
    {
        case HEAPTUPLE_LIVE:
 
            /*
             * Count it as live.  Not only is this natural, but it's also what
             * acquire_sample_rows() does.
             */
            prstate->live_tuples++;
 
            /*
             * Is the tuple definitely visible to all transactions?
             *
             * NB: Like with per-tuple hint bits, we can't set the
             * PD_ALL_VISIBLE flag if the inserter committed asynchronously.
             * See SetHintBits for more info.  Check that the tuple is hinted
             * xmin-committed because of that.
             */
            if (prstate->set_all_visible)
            {
                TransactionId xmin;
 
                if (!HeapTupleHeaderXminCommitted(htup))
                {
                    prstate->set_all_visible = false;
                    prstate->set_all_frozen = false;
                    break;
                }
 
                /*
                 * The inserter definitely committed.  But is it old enough
                 * that everyone sees it as committed?  A FrozenTransactionId
                 * is seen as committed to everyone.  Otherwise, we check if
                 * there is a snapshot that considers this xid to still be
                 * running, and if so, we don't consider the page all-visible.
                 */
                xmin = HeapTupleHeaderGetXmin(htup);
 
                /*
                 * For now always use prstate->cutoffs for this test, because
                 * we only update 'set_all_visible' and 'set_all_frozen' when
                 * freezing is requested. We could use
                 * GlobalVisTestIsRemovableXid instead, if a non-freezing
                 * caller wanted to set the VM bit.
                 */
                Assert(prstate->cutoffs);
                if (!TransactionIdPrecedes(xmin, prstate->cutoffs->OldestXmin))
                {
                    prstate->set_all_visible = false;
                    prstate->set_all_frozen = false;
                    break;
                }
 
                /* Track newest xmin on page. */
                if (TransactionIdFollows(xmin, prstate->visibility_cutoff_xid) &&
                    TransactionIdIsNormal(xmin))
                    prstate->visibility_cutoff_xid = xmin;
            }
            break;
 
        case HEAPTUPLE_RECENTLY_DEAD:
            prstate->recently_dead_tuples++;
            prstate->set_all_visible = false;
            prstate->set_all_frozen = false;
 
            /*
             * This tuple will 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_INSERT_IN_PROGRESS:
 
            /*
             * We do not count these rows as live, because we expect the
             * inserting transaction to update the counters at commit, and we
             * assume that will happen only after we report our results.  This
             * assumption is a bit shaky, but it is what acquire_sample_rows()
             * does, so be consistent.
             */
            prstate->set_all_visible = false;
            prstate->set_all_frozen = false;
 
            /*
             * 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;
 
        case HEAPTUPLE_DELETE_IN_PROGRESS:
 
            /*
             * This an expected case during concurrent vacuum.  Count such
             * rows as live.  As above, we assume the deleting transaction
             * will commit and update the counters after we report.
             */
            prstate->live_tuples++;
            prstate->set_all_visible = false;
            prstate->set_all_frozen = false;
 
            /*
             * 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;
 
        default:
 
            /*
             * DEAD tuples should've been passed to heap_prune_record_dead()
             * or heap_prune_record_unused() instead.
             */
            elog(ERROR, "unexpected HeapTupleSatisfiesVacuum result %d",
                 prstate->htsv[offnum]);
            break;
    }
 
    /* Consider freezing any normal tuples which will not be removed */
    if (prstate->attempt_freeze)
    {
        bool        totally_frozen;
 
        if ((heap_prepare_freeze_tuple(htup,
                                       prstate->cutoffs,
                                       &prstate->pagefrz,
                                       &prstate->frozen[prstate->nfrozen],
                                       &totally_frozen)))
        {
            /* Save prepared freeze plan for later */
            prstate->frozen[prstate->nfrozen++].offset = offnum;
        }
 
        /*
         * If any tuple isn't either totally frozen already or eligible to
         * become totally frozen (according to its freeze plan), then the page
         * definitely cannot be set all-frozen in the visibility map later on.
         */
        if (!totally_frozen)
            prstate->set_all_frozen = false;
    }
}

References Assert, elog, ERROR, fb(), heap_prepare_freeze_tuple(), heap_prune_record_prunable(), HEAPTUPLE_DELETE_IN_PROGRESS, HEAPTUPLE_INSERT_IN_PROGRESS, HEAPTUPLE_LIVE, HEAPTUPLE_RECENTLY_DEAD, HeapTupleHeaderGetUpdateXid(), HeapTupleHeaderGetXmin(), HeapTupleHeaderXminCommitted(), PageGetItem(), PageGetItemId(), TransactionIdFollows(), TransactionIdIsNormal, and TransactionIdPrecedes().

Referenced by heap_prune_chain(), and prune_freeze_plan().

heap_prune_record_unchanged_lp_redirect()

static void heap_prune_record_unchanged_lp_redirect ( PruneState *  prstate, OffsetNumber  offnum  )

static

Definition at line 1641 of file pruneheap.c.

{
    /*
     * A redirect line pointer doesn't count as a live tuple.
     *
     * If we leave a redirect line pointer in place, there will be another
     * tuple on the page that it points to.  We will do the bookkeeping for
     * that separately.  So we have nothing to do here, except remember that
     * we processed this item.
     */
    Assert(!prstate->processed[offnum]);
    prstate->processed[offnum] = true;
}

References Assert, and fb().

Referenced by heap_prune_chain().

heap_prune_record_unchanged_lp_unused()

static void heap_prune_record_unchanged_lp_unused ( PruneState *  prstate, OffsetNumber  offnum  )

static

Definition at line 1417 of file pruneheap.c.

{
    Assert(!prstate->processed[offnum]);
    prstate->processed[offnum] = true;
}

References Assert, and fb().

Referenced by prune_freeze_plan().

heap_prune_record_unused()

static void heap_prune_record_unused ( PruneState *  prstate, OffsetNumber  offnum, bool  was_normal  )

static

Definition at line 1395 of file pruneheap.c.

{
    Assert(!prstate->processed[offnum]);
    prstate->processed[offnum] = true;
 
    Assert(prstate->nunused < MaxHeapTuplesPerPage);
    prstate->nowunused[prstate->nunused] = offnum;
    prstate->nunused++;
 
    /*
     * 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 (was_normal)
        prstate->ndeleted++;
}

References Assert, fb(), and MaxHeapTuplesPerPage.

Referenced by heap_prune_chain(), heap_prune_record_dead_or_unused(), and prune_freeze_plan().

heap_prune_satisfies_vacuum()

static HTSV_Result heap_prune_satisfies_vacuum ( PruneState *  prstate, HeapTuple  tup  )

static

Definition at line 1013 of file pruneheap.c.

{
    HTSV_Result res;
    TransactionId dead_after;
 
    res = HeapTupleSatisfiesVacuumHorizon(tup, prstate->buffer, &dead_after);
 
    if (res != HEAPTUPLE_RECENTLY_DEAD)
        return res;
 
    /*
     * For VACUUM, we must be sure to prune tuples with xmax older than
     * OldestXmin -- a visibility cutoff determined at the beginning of
     * vacuuming the relation. OldestXmin is used for freezing determination
     * and we cannot freeze dead tuples' xmaxes.
     */
    if (prstate->cutoffs &&
        TransactionIdIsValid(prstate->cutoffs->OldestXmin) &&
        NormalTransactionIdPrecedes(dead_after, prstate->cutoffs->OldestXmin))
        return HEAPTUPLE_DEAD;
 
    /*
     * Determine whether or not the tuple is considered dead when compared
     * with the provided GlobalVisState. On-access pruning does not provide
     * VacuumCutoffs. And for vacuum, even if the tuple's xmax is not older
     * than OldestXmin, GlobalVisTestIsRemovableXid() could find the row dead
     * if the GlobalVisState has been updated since the beginning of vacuuming
     * the relation.
     */
    if (GlobalVisTestIsRemovableXid(prstate->vistest, dead_after))
        return HEAPTUPLE_DEAD;
 
    return res;
}

References fb(), GlobalVisTestIsRemovableXid(), HEAPTUPLE_DEAD, HEAPTUPLE_RECENTLY_DEAD, HeapTupleSatisfiesVacuumHorizon(), NormalTransactionIdPrecedes, and TransactionIdIsValid.

Referenced by prune_freeze_plan().

htsv_get_valid_status()

static HTSV_Result htsv_get_valid_status ( int  status )

inlinestatic

Definition at line 1056 of file pruneheap.c.

{
    Assert(status >= HEAPTUPLE_DEAD &&
           status <= HEAPTUPLE_DELETE_IN_PROGRESS);
    return (HTSV_Result) status;
}

References Assert, HEAPTUPLE_DEAD, and HEAPTUPLE_DELETE_IN_PROGRESS.

Referenced by heap_prune_chain().

log_heap_prune_and_freeze()

void log_heap_prune_and_freeze	(	Relation	relation,
		Buffer	buffer,
		Buffer	vmbuffer,
		uint8	vmflags,
		TransactionId	conflict_xid,
		bool	cleanup_lock,
		PruneReason	reason,
		HeapTupleFreeze *	frozen,
		int	nfrozen,
		OffsetNumber *	redirected,
		int	nredirected,
		OffsetNumber *	dead,
		int	ndead,
		OffsetNumber *	unused,
		int	nunused
	)

Definition at line 2162 of file pruneheap.c.

{
    xl_heap_prune xlrec;
    XLogRecPtr  recptr;
    uint8       info;
    uint8       regbuf_flags_heap;
 
    /* The following local variables hold data registered in the WAL record: */
    xlhp_freeze_plan plans[MaxHeapTuplesPerPage];
    xlhp_freeze_plans freeze_plans;
    xlhp_prune_items redirect_items;
    xlhp_prune_items dead_items;
    xlhp_prune_items unused_items;
    OffsetNumber frz_offsets[MaxHeapTuplesPerPage];
    bool        do_prune = nredirected > 0 || ndead > 0 || nunused > 0;
    bool        do_set_vm = vmflags & VISIBILITYMAP_VALID_BITS;
 
    Assert((vmflags & VISIBILITYMAP_VALID_BITS) == vmflags);
 
    xlrec.flags = 0;
    regbuf_flags_heap = REGBUF_STANDARD;
 
    /*
     * We can avoid an FPI of the heap page if the only modification we are
     * making to it is to set PD_ALL_VISIBLE and checksums/wal_log_hints are
     * disabled. Note that if we explicitly skip an FPI, we must not stamp the
     * heap page with this record's LSN. Recovery skips records <= the stamped
     * LSN, so this could lead to skipping an earlier FPI needed to repair a
     * torn page.
     */
    if (!do_prune &&
        nfrozen == 0 &&
        (!do_set_vm || !XLogHintBitIsNeeded()))
        regbuf_flags_heap |= REGBUF_NO_IMAGE;
 
    /*
     * Prepare data for the buffer.  The arrays are not actually in the
     * buffer, but we pretend that they are.  When XLogInsert stores a full
     * page image, the arrays can be omitted.
     */
    XLogBeginInsert();
    XLogRegisterBuffer(0, buffer, regbuf_flags_heap);
 
    if (do_set_vm)
        XLogRegisterBuffer(1, vmbuffer, 0);
 
    if (nfrozen > 0)
    {
        int         nplans;
 
        xlrec.flags |= XLHP_HAS_FREEZE_PLANS;
 
        /*
         * Prepare deduplicated representation for use in the WAL record. This
         * destructively sorts frozen tuples array in-place.
         */
        nplans = heap_log_freeze_plan(frozen, nfrozen, plans, frz_offsets);
 
        freeze_plans.nplans = nplans;
        XLogRegisterBufData(0, &freeze_plans,
                            offsetof(xlhp_freeze_plans, plans));
        XLogRegisterBufData(0, plans,
                            sizeof(xlhp_freeze_plan) * nplans);
    }
    if (nredirected > 0)
    {
        xlrec.flags |= XLHP_HAS_REDIRECTIONS;
 
        redirect_items.ntargets = nredirected;
        XLogRegisterBufData(0, &redirect_items,
                            offsetof(xlhp_prune_items, data));
        XLogRegisterBufData(0, redirected,
                            sizeof(OffsetNumber[2]) * nredirected);
    }
    if (ndead > 0)
    {
        xlrec.flags |= XLHP_HAS_DEAD_ITEMS;
 
        dead_items.ntargets = ndead;
        XLogRegisterBufData(0, &dead_items,
                            offsetof(xlhp_prune_items, data));
        XLogRegisterBufData(0, dead,
                            sizeof(OffsetNumber) * ndead);
    }
    if (nunused > 0)
    {
        xlrec.flags |= XLHP_HAS_NOW_UNUSED_ITEMS;
 
        unused_items.ntargets = nunused;
        XLogRegisterBufData(0, &unused_items,
                            offsetof(xlhp_prune_items, data));
        XLogRegisterBufData(0, unused,
                            sizeof(OffsetNumber) * nunused);
    }
    if (nfrozen > 0)
        XLogRegisterBufData(0, frz_offsets,
                            sizeof(OffsetNumber) * nfrozen);
 
    /*
     * Prepare the main xl_heap_prune record.  We already set the XLHP_HAS_*
     * flag above.
     */
    if (vmflags & VISIBILITYMAP_ALL_VISIBLE)
    {
        xlrec.flags |= XLHP_VM_ALL_VISIBLE;
        if (vmflags & VISIBILITYMAP_ALL_FROZEN)
            xlrec.flags |= XLHP_VM_ALL_FROZEN;
    }
    if (RelationIsAccessibleInLogicalDecoding(relation))
        xlrec.flags |= XLHP_IS_CATALOG_REL;
    if (TransactionIdIsValid(conflict_xid))
        xlrec.flags |= XLHP_HAS_CONFLICT_HORIZON;
    if (cleanup_lock)
        xlrec.flags |= XLHP_CLEANUP_LOCK;
    else
    {
        Assert(nredirected == 0 && ndead == 0);
        /* also, any items in 'unused' must've been LP_DEAD previously */
    }
    XLogRegisterData(&xlrec, SizeOfHeapPrune);
    if (TransactionIdIsValid(conflict_xid))
        XLogRegisterData(&conflict_xid, sizeof(TransactionId));
 
    switch (reason)
    {
        case PRUNE_ON_ACCESS:
            info = XLOG_HEAP2_PRUNE_ON_ACCESS;
            break;
        case PRUNE_VACUUM_SCAN:
            info = XLOG_HEAP2_PRUNE_VACUUM_SCAN;
            break;
        case PRUNE_VACUUM_CLEANUP:
            info = XLOG_HEAP2_PRUNE_VACUUM_CLEANUP;
            break;
        default:
            elog(ERROR, "unrecognized prune reason: %d", (int) reason);
            break;
    }
    recptr = XLogInsert(RM_HEAP2_ID, info);
 
    if (do_set_vm)
    {
        Assert(BufferIsDirty(vmbuffer));
        PageSetLSN(BufferGetPage(vmbuffer), recptr);
    }
 
    /*
     * See comment at the top of the function about regbuf_flags_heap for
     * details on when we can advance the page LSN.
     */
    if (do_prune || nfrozen > 0 || (do_set_vm && XLogHintBitIsNeeded()))
    {
        Assert(BufferIsDirty(buffer));
        PageSetLSN(BufferGetPage(buffer), recptr);
    }
}

References Assert, BufferGetPage(), BufferIsDirty(), data, elog, ERROR, fb(), heap_log_freeze_plan(), MaxHeapTuplesPerPage, xlhp_prune_items::ntargets, PageSetLSN(), PRUNE_ON_ACCESS, PRUNE_VACUUM_CLEANUP, PRUNE_VACUUM_SCAN, REGBUF_NO_IMAGE, REGBUF_STANDARD, RelationIsAccessibleInLogicalDecoding, SizeOfHeapPrune, TransactionIdIsValid, VISIBILITYMAP_ALL_FROZEN, VISIBILITYMAP_ALL_VISIBLE, VISIBILITYMAP_VALID_BITS, XLHP_CLEANUP_LOCK, XLHP_HAS_CONFLICT_HORIZON, XLHP_HAS_DEAD_ITEMS, XLHP_HAS_FREEZE_PLANS, XLHP_HAS_NOW_UNUSED_ITEMS, XLHP_HAS_REDIRECTIONS, XLHP_IS_CATALOG_REL, XLHP_VM_ALL_FROZEN, XLHP_VM_ALL_VISIBLE, XLOG_HEAP2_PRUNE_ON_ACCESS, XLOG_HEAP2_PRUNE_VACUUM_CLEANUP, XLOG_HEAP2_PRUNE_VACUUM_SCAN, XLogBeginInsert(), XLogHintBitIsNeeded, XLogInsert(), XLogRegisterBufData(), XLogRegisterBuffer(), and XLogRegisterData().

Referenced by heap_page_prune_and_freeze(), and lazy_vacuum_heap_page().

page_verify_redirects()

static void page_verify_redirects ( Page  page )

static

Definition at line 1842 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, fb(), FirstOffsetNumber, HeapTupleHeaderIsHeapOnly(), ItemIdGetRedirect, ItemIdHasStorage, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, OffsetNumberNext, PageGetItem(), PageGetItemId(), and PageGetMaxOffsetNumber().

Referenced by heap_page_prune_execute().

prune_freeze_plan()

static void prune_freeze_plan ( PruneState *  prstate, OffsetNumber *  off_loc  )

static

Definition at line 469 of file pruneheap.c.

{
    Page        page = prstate->page;
    BlockNumber blockno = prstate->block;
    OffsetNumber maxoff = PageGetMaxOffsetNumber(prstate->page);
    OffsetNumber offnum;
    HeapTupleData tup;
 
    tup.t_tableOid = RelationGetRelid(prstate->relation);
 
    /*
     * Determine HTSV for all tuples, and queue them up for processing as HOT
     * chain roots or as heap-only items.
     *
     * Determining HTSV only once for each tuple is required for correctness,
     * to deal with cases where running HTSV twice could result in different
     * results.  For example, RECENTLY_DEAD can turn to DEAD if another
     * checked item causes GlobalVisTestIsRemovableFullXid() to update the
     * horizon, or INSERT_IN_PROGRESS can change to DEAD if the inserting
     * transaction aborts.
     *
     * 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;
 
        /*
         * Set the offset number so that we can display it along with any
         * error that occurred while processing this tuple.
         */
        *off_loc = offnum;
 
        prstate->processed[offnum] = false;
        prstate->htsv[offnum] = -1;
 
        /* Nothing to do if slot doesn't contain a tuple */
        if (!ItemIdIsUsed(itemid))
        {
            heap_prune_record_unchanged_lp_unused(prstate, offnum);
            continue;
        }
 
        if (ItemIdIsDead(itemid))
        {
            /*
             * If the caller set mark_unused_now true, we can set dead line
             * pointers LP_UNUSED now.
             */
            if (unlikely(prstate->mark_unused_now))
                heap_prune_record_unused(prstate, offnum, false);
            else
                heap_prune_record_unchanged_lp_dead(prstate, offnum);
            continue;
        }
 
        if (ItemIdIsRedirected(itemid))
        {
            /* This is the start of a HOT chain */
            prstate->root_items[prstate->nroot_items++] = offnum;
            continue;
        }
 
        Assert(ItemIdIsNormal(itemid));
 
        /*
         * Get the tuple's visibility status and queue it up for processing.
         */
        htup = (HeapTupleHeader) PageGetItem(page, itemid);
        tup.t_data = htup;
        tup.t_len = ItemIdGetLength(itemid);
        ItemPointerSet(&tup.t_self, blockno, offnum);
 
        prstate->htsv[offnum] = heap_prune_satisfies_vacuum(prstate, &tup);
 
        if (!HeapTupleHeaderIsHeapOnly(htup))
            prstate->root_items[prstate->nroot_items++] = offnum;
        else
            prstate->heaponly_items[prstate->nheaponly_items++] = offnum;
    }
 
    /*
     * Process HOT chains.
     *
     * We added the items to the array starting from 'maxoff', so by
     * processing the array in reverse order, we process the items in
     * ascending offset number order.  The order doesn't matter for
     * correctness, but some quick micro-benchmarking suggests that this is
     * faster.  (Earlier PostgreSQL versions, which scanned all the items on
     * the page instead of using the root_items array, also did it in
     * ascending offset number order.)
     */
    for (int i = prstate->nroot_items - 1; i >= 0; i--)
    {
        offnum = prstate->root_items[i];
 
        /* Ignore items already processed as part of an earlier chain */
        if (prstate->processed[offnum])
            continue;
 
        /* see preceding loop */
        *off_loc = offnum;
 
        /* Process this item or chain of items */
        heap_prune_chain(maxoff, offnum, prstate);
    }
 
    /*
     * Process any heap-only tuples that were not already processed as part of
     * a HOT chain.
     */
    for (int i = prstate->nheaponly_items - 1; i >= 0; i--)
    {
        offnum = prstate->heaponly_items[i];
 
        if (prstate->processed[offnum])
            continue;
 
        /* see preceding loop */
        *off_loc = offnum;
 
        /*
         * If the tuple is DEAD and doesn't chain to anything else, mark it
         * unused.  (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.)
         */
        if (prstate->htsv[offnum] == HEAPTUPLE_DEAD)
        {
            ItemId      itemid = PageGetItemId(page, offnum);
            HeapTupleHeader htup = (HeapTupleHeader) PageGetItem(page, itemid);
 
            if (likely(!HeapTupleHeaderIsHotUpdated(htup)))
            {
                HeapTupleHeaderAdvanceConflictHorizon(htup,
                                                      &prstate->latest_xid_removed);
                heap_prune_record_unused(prstate, offnum, true);
            }
            else
            {
                /*
                 * This tuple should've been processed and removed as part of
                 * a HOT chain, so something's wrong.  To preserve evidence,
                 * we don't dare to remove it.  We cannot leave behind a DEAD
                 * tuple either, because that will cause VACUUM to error out.
                 * Throwing an error with a distinct error message seems like
                 * the least bad option.
                 */
                elog(ERROR, "dead heap-only tuple (%u, %d) is not linked to from any HOT chain",
                     blockno, offnum);
            }
        }
        else
            heap_prune_record_unchanged_lp_normal(prstate, offnum);
    }
 
    /* We should now have processed every tuple exactly once  */
#ifdef USE_ASSERT_CHECKING
    for (offnum = FirstOffsetNumber;
         offnum <= maxoff;
         offnum = OffsetNumberNext(offnum))
    {
        *off_loc = offnum;
 
        Assert(prstate->processed[offnum]);
    }
#endif
 
    /* Clear the offset information once we have processed the given page. */
    *off_loc = InvalidOffsetNumber;
}

References Assert, elog, ERROR, fb(), FirstOffsetNumber, heap_prune_chain(), heap_prune_record_unchanged_lp_dead(), heap_prune_record_unchanged_lp_normal(), heap_prune_record_unchanged_lp_unused(), heap_prune_record_unused(), heap_prune_satisfies_vacuum(), HEAPTUPLE_DEAD, HeapTupleHeaderAdvanceConflictHorizon(), HeapTupleHeaderIsHeapOnly(), HeapTupleHeaderIsHotUpdated(), i, InvalidOffsetNumber, ItemIdGetLength, ItemIdIsDead, ItemIdIsNormal, ItemIdIsRedirected, ItemIdIsUsed, ItemPointerSet(), likely, OffsetNumberNext, OffsetNumberPrev, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), RelationGetRelid, HeapTupleData::t_tableOid, and unlikely.

Referenced by heap_page_prune_and_freeze().

prune_freeze_setup()

static void prune_freeze_setup ( PruneFreezeParams *  params, TransactionId *  new_relfrozen_xid, MultiXactId *  new_relmin_mxid, PruneFreezeResult *  presult, PruneState *  prstate  )

static

Definition at line 337 of file pruneheap.c.

{
    /* Copy parameters to prstate */
    prstate->vistest = params->vistest;
    prstate->mark_unused_now =
        (params->options & HEAP_PAGE_PRUNE_MARK_UNUSED_NOW) != 0;
 
    /* cutoffs must be provided if we will attempt freezing */
    Assert(!(params->options & HEAP_PAGE_PRUNE_FREEZE) || params->cutoffs);
    prstate->attempt_freeze = (params->options & HEAP_PAGE_PRUNE_FREEZE) != 0;
    prstate->cutoffs = params->cutoffs;
    prstate->relation = params->relation;
    prstate->block = BufferGetBlockNumber(params->buffer);
    prstate->buffer = params->buffer;
    prstate->page = BufferGetPage(params->buffer);
 
    /*
     * 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->latest_xid_removed = InvalidTransactionId;
    prstate->nredirected = prstate->ndead = prstate->nunused = 0;
    prstate->nfrozen = 0;
    prstate->nroot_items = 0;
    prstate->nheaponly_items = 0;
 
    /* initialize page freezing working state */
    prstate->pagefrz.freeze_required = false;
    prstate->pagefrz.FreezePageConflictXid = InvalidTransactionId;
    if (prstate->attempt_freeze)
    {
        Assert(new_relfrozen_xid && new_relmin_mxid);
        prstate->pagefrz.FreezePageRelfrozenXid = *new_relfrozen_xid;
        prstate->pagefrz.NoFreezePageRelfrozenXid = *new_relfrozen_xid;
        prstate->pagefrz.FreezePageRelminMxid = *new_relmin_mxid;
        prstate->pagefrz.NoFreezePageRelminMxid = *new_relmin_mxid;
    }
    else
    {
        Assert(!new_relfrozen_xid && !new_relmin_mxid);
        prstate->pagefrz.FreezePageRelminMxid = InvalidMultiXactId;
        prstate->pagefrz.NoFreezePageRelminMxid = InvalidMultiXactId;
        prstate->pagefrz.FreezePageRelfrozenXid = InvalidTransactionId;
        prstate->pagefrz.NoFreezePageRelfrozenXid = InvalidTransactionId;
    }
 
    prstate->ndeleted = 0;
    prstate->live_tuples = 0;
    prstate->recently_dead_tuples = 0;
    prstate->hastup = false;
    prstate->lpdead_items = 0;
 
    /*
     * deadoffsets are filled in during pruning but are only used to populate
     * PruneFreezeResult->deadoffsets. To avoid needing two copies of the
     * array, just save a pointer to the result offsets array in the
     * PruneState.
     */
    prstate->deadoffsets = presult->deadoffsets;
 
    /*
     * Vacuum may update the VM after we're done.  We can keep track of
     * whether the page will be all-visible and all-frozen after pruning and
     * freezing to help the caller to do that.
     *
     * Currently, only VACUUM sets the VM bits.  To save the effort, only do
     * the bookkeeping if the caller needs it.  Currently, that's tied to
     * HEAP_PAGE_PRUNE_FREEZE, but it could be a separate flag if you wanted
     * to update the VM bits without also freezing or freeze without also
     * setting the VM bits.
     *
     * In addition to telling the caller whether it can set the VM bit, we
     * also use 'set_all_visible' and 'set_all_frozen' for our own
     * decision-making. If the whole page would become frozen, we consider
     * opportunistically freezing tuples.  We will not be able to freeze the
     * whole page if there are tuples present that are not visible to everyone
     * or if there are dead tuples which are not yet removable.  However, dead
     * tuples which will be removed by the end of vacuuming should not
     * preclude us from opportunistically freezing.  Because of that, we do
     * not immediately clear set_all_visible and set_all_frozen when we see
     * LP_DEAD items.  We fix that after scanning the line pointers. We must
     * correct set_all_visible and set_all_frozen before we return them to the
     * caller, so that the caller doesn't set the VM bits incorrectly.
     */
    if (prstate->attempt_freeze)
    {
        prstate->set_all_visible = true;
        prstate->set_all_frozen = true;
    }
    else
    {
        /*
         * Initializing to false allows skipping the work to update them in
         * heap_prune_record_unchanged_lp_normal().
         */
        prstate->set_all_visible = false;
        prstate->set_all_frozen = false;
    }
 
    /*
     * The visibility cutoff xid is the newest xmin of live tuples on the
     * page.  In the common case, this will be set as the conflict horizon the
     * caller can use for updating the VM.  If, at the end of freezing and
     * pruning, the page is all-frozen, there is no possibility that any
     * running transaction on the standby does not see tuples on the page as
     * all-visible, so the conflict horizon remains InvalidTransactionId.
     */
    prstate->visibility_cutoff_xid = InvalidTransactionId;
}

References Assert, PruneFreezeParams::buffer, BufferGetBlockNumber(), BufferGetPage(), PruneFreezeParams::cutoffs, fb(), HEAP_PAGE_PRUNE_FREEZE, HEAP_PAGE_PRUNE_MARK_UNUSED_NOW, InvalidMultiXactId, InvalidTransactionId, PruneFreezeParams::options, PruneFreezeParams::relation, and PruneFreezeParams::vistest.

Referenced by heap_page_prune_and_freeze().