nbtree.c File Reference

#include "postgres.h"
#include "access/nbtree.h"
#include "access/nbtxlog.h"
#include "access/relscan.h"
#include "access/xlog.h"
#include "commands/progress.h"
#include "commands/vacuum.h"
#include "miscadmin.h"
#include "nodes/execnodes.h"
#include "pgstat.h"
#include "postmaster/autovacuum.h"
#include "storage/condition_variable.h"
#include "storage/indexfsm.h"
#include "storage/ipc.h"
#include "storage/lmgr.h"
#include "storage/smgr.h"
#include "utils/builtins.h"
#include "utils/index_selfuncs.h"
#include "utils/memutils.h"

Include dependency graph for nbtree.c:

Go to the source code of this file.

Data Structures
struct	BTVacState
struct	BTParallelScanDescData

Typedefs
typedef struct BTParallelScanDescData	BTParallelScanDescData
typedef struct BTParallelScanDescData *	BTParallelScanDesc

Enumerations
enum	BTPS_State { BTPARALLEL_NOT_INITIALIZED, BTPARALLEL_ADVANCING, BTPARALLEL_IDLE, BTPARALLEL_DONE }

Functions
static void	btvacuumscan (IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state, BTCycleId cycleid)
static void	btvacuumpage (BTVacState *vstate, BlockNumber scanblkno)
static BTVacuumPosting	btreevacuumposting (BTVacState *vstate, IndexTuple posting, OffsetNumber updatedoffset, int *nremaining)
Datum	bthandler (PG_FUNCTION_ARGS)
void	btbuildempty (Relation index)
bool	btinsert (Relation rel, Datum *values, bool *isnull, ItemPointer ht_ctid, Relation heapRel, IndexUniqueCheck checkUnique, bool indexUnchanged, IndexInfo *indexInfo)
bool	btgettuple (IndexScanDesc scan, ScanDirection dir)
int64	btgetbitmap (IndexScanDesc scan, TIDBitmap *tbm)
IndexScanDesc	btbeginscan (Relation rel, int nkeys, int norderbys)
void	btrescan (IndexScanDesc scan, ScanKey scankey, int nscankeys, ScanKey orderbys, int norderbys)
void	btendscan (IndexScanDesc scan)
void	btmarkpos (IndexScanDesc scan)
void	btrestrpos (IndexScanDesc scan)
Size	btestimateparallelscan (void)
void	btinitparallelscan (void *target)
void	btparallelrescan (IndexScanDesc scan)
bool	_bt_parallel_seize (IndexScanDesc scan, BlockNumber *pageno)
void	_bt_parallel_release (IndexScanDesc scan, BlockNumber scan_page)
void	_bt_parallel_done (IndexScanDesc scan)
void	_bt_parallel_advance_array_keys (IndexScanDesc scan)
static bool	_bt_vacuum_needs_cleanup (IndexVacuumInfo *info)
IndexBulkDeleteResult *	btbulkdelete (IndexVacuumInfo *info, IndexBulkDeleteResult *stats, IndexBulkDeleteCallback callback, void *callback_state)
IndexBulkDeleteResult *	btvacuumcleanup (IndexVacuumInfo *info, IndexBulkDeleteResult *stats)
bool	btcanreturn (Relation index, int attno)

Typedef Documentation

BTParallelScanDesc

typedef struct BTParallelScanDescData* BTParallelScanDesc

Definition at line 90 of file nbtree.c.

BTParallelScanDescData

typedef struct BTParallelScanDescData BTParallelScanDescData

Enumeration Type Documentation

BTPS_State

enum BTPS_State

Enumerator
BTPARALLEL_NOT_INITIALIZED
BTPARALLEL_ADVANCING
BTPARALLEL_IDLE
BTPARALLEL_DONE

Definition at line 66 of file nbtree.c.

{
    BTPARALLEL_NOT_INITIALIZED,
    BTPARALLEL_ADVANCING,
    BTPARALLEL_IDLE,
    BTPARALLEL_DONE
} BTPS_State;

Function Documentation

_bt_parallel_advance_array_keys()

void _bt_parallel_advance_array_keys

(

IndexScanDesc

scan

)

Definition at line 769 of file nbtree.c.

References BTScanOpaqueData::arrayKeyCount, BTPARALLEL_DONE, BTPARALLEL_NOT_INITIALIZED, InvalidBlockNumber, OffsetToPointer, IndexScanDescData::opaque, IndexScanDescData::parallel_scan, SpinLockAcquire, and SpinLockRelease.

Referenced by _bt_advance_array_keys().

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    ParallelIndexScanDesc parallel_scan = scan->parallel_scan;
    BTParallelScanDesc btscan;

    btscan = (BTParallelScanDesc) OffsetToPointer((void *) parallel_scan,
                                                  parallel_scan->ps_offset);

    so->arrayKeyCount++;
    SpinLockAcquire(&btscan->btps_mutex);
    if (btscan->btps_pageStatus == BTPARALLEL_DONE)
    {
        btscan->btps_scanPage = InvalidBlockNumber;
        btscan->btps_pageStatus = BTPARALLEL_NOT_INITIALIZED;
        btscan->btps_arrayKeyCount++;
    }
    SpinLockRelease(&btscan->btps_mutex);
}

_bt_parallel_done()

void _bt_parallel_done

(

IndexScanDesc

scan

)

Definition at line 728 of file nbtree.c.

References BTScanOpaqueData::arrayKeyCount, BTPARALLEL_DONE, ConditionVariableBroadcast(), OffsetToPointer, IndexScanDescData::opaque, IndexScanDescData::parallel_scan, SpinLockAcquire, and SpinLockRelease.

Referenced by _bt_first(), and _bt_readnextpage().

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    ParallelIndexScanDesc parallel_scan = scan->parallel_scan;
    BTParallelScanDesc btscan;
    bool        status_changed = false;

    /* Do nothing, for non-parallel scans */
    if (parallel_scan == NULL)
        return;

    btscan = (BTParallelScanDesc) OffsetToPointer((void *) parallel_scan,
                                                  parallel_scan->ps_offset);

    /*
     * Mark the parallel scan as done for this combination of scan keys,
     * unless some other process already did so.  See also
     * _bt_advance_array_keys.
     */
    SpinLockAcquire(&btscan->btps_mutex);
    if (so->arrayKeyCount >= btscan->btps_arrayKeyCount &&
        btscan->btps_pageStatus != BTPARALLEL_DONE)
    {
        btscan->btps_pageStatus = BTPARALLEL_DONE;
        status_changed = true;
    }
    SpinLockRelease(&btscan->btps_mutex);

    /* wake up all the workers associated with this parallel scan */
    if (status_changed)
        ConditionVariableBroadcast(&btscan->btps_cv);
}

_bt_parallel_release()

void _bt_parallel_release	(	IndexScanDesc	scan,
		BlockNumber	scan_page
	)

Definition at line 705 of file nbtree.c.

References BTPARALLEL_IDLE, BTParallelScanDescData::btps_cv, BTParallelScanDescData::btps_mutex, BTParallelScanDescData::btps_pageStatus, BTParallelScanDescData::btps_scanPage, ConditionVariableSignal(), OffsetToPointer, IndexScanDescData::parallel_scan, ParallelIndexScanDescData::ps_offset, SpinLockAcquire, and SpinLockRelease.

Referenced by _bt_readnextpage(), and _bt_readpage().

{
    ParallelIndexScanDesc parallel_scan = scan->parallel_scan;
    BTParallelScanDesc btscan;

    btscan = (BTParallelScanDesc) OffsetToPointer((void *) parallel_scan,
                                                  parallel_scan->ps_offset);

    SpinLockAcquire(&btscan->btps_mutex);
    btscan->btps_scanPage = scan_page;
    btscan->btps_pageStatus = BTPARALLEL_IDLE;
    SpinLockRelease(&btscan->btps_mutex);
    ConditionVariableSignal(&btscan->btps_cv);
}

_bt_parallel_seize()

bool _bt_parallel_seize	(	IndexScanDesc	scan,
		BlockNumber *	pageno
	)

Definition at line 647 of file nbtree.c.

References BTScanOpaqueData::arrayKeyCount, BTPARALLEL_ADVANCING, BTPARALLEL_DONE, ConditionVariableCancelSleep(), ConditionVariableSleep(), OffsetToPointer, IndexScanDescData::opaque, P_NONE, IndexScanDescData::parallel_scan, SpinLockAcquire, SpinLockRelease, status(), and WAIT_EVENT_BTREE_PAGE.

Referenced by _bt_first(), _bt_readnextpage(), and _bt_steppage().

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    BTPS_State  pageStatus;
    bool        exit_loop = false;
    bool        status = true;
    ParallelIndexScanDesc parallel_scan = scan->parallel_scan;
    BTParallelScanDesc btscan;

    *pageno = P_NONE;

    btscan = (BTParallelScanDesc) OffsetToPointer((void *) parallel_scan,
                                                  parallel_scan->ps_offset);

    while (1)
    {
        SpinLockAcquire(&btscan->btps_mutex);
        pageStatus = btscan->btps_pageStatus;

        if (so->arrayKeyCount < btscan->btps_arrayKeyCount)
        {
            /* Parallel scan has already advanced to a new set of scankeys. */
            status = false;
        }
        else if (pageStatus == BTPARALLEL_DONE)
        {
            /*
             * We're done with this set of scankeys.  This may be the end, or
             * there could be more sets to try.
             */
            status = false;
        }
        else if (pageStatus != BTPARALLEL_ADVANCING)
        {
            /*
             * We have successfully seized control of the scan for the purpose
             * of advancing it to a new page!
             */
            btscan->btps_pageStatus = BTPARALLEL_ADVANCING;
            *pageno = btscan->btps_scanPage;
            exit_loop = true;
        }
        SpinLockRelease(&btscan->btps_mutex);
        if (exit_loop || !status)
            break;
        ConditionVariableSleep(&btscan->btps_cv, WAIT_EVENT_BTREE_PAGE);
    }
    ConditionVariableCancelSleep();

    return status;
}

_bt_vacuum_needs_cleanup()

static bool _bt_vacuum_needs_cleanup ( IndexVacuumInfo *  info )

static

Definition at line 800 of file nbtree.c.

References _bt_getbuf(), _bt_relbuf(), BT_READ, BTMetaPageData::btm_last_cleanup_num_heap_tuples, BTMetaPageData::btm_oldest_btpo_xact, BTMetaPageData::btm_version, BTPageGetMeta, BTREE_METAPAGE, BTREE_NOVAC_VERSION, BufferGetPage, GlobalVisCheckRemovableXid(), IndexVacuumInfo::index, IndexVacuumInfo::num_heap_tuples, RelationData::rd_options, TransactionIdIsValid, vacuum_cleanup_index_scale_factor, and BTOptions::vacuum_cleanup_index_scale_factor.

Referenced by btvacuumcleanup().

{
    Buffer      metabuf;
    Page        metapg;
    BTMetaPageData *metad;
    bool        result = false;

    metabuf = _bt_getbuf(info->index, BTREE_METAPAGE, BT_READ);
    metapg = BufferGetPage(metabuf);
    metad = BTPageGetMeta(metapg);

    /*
     * XXX: If IndexVacuumInfo contained the heap relation, we could be more
     * aggressive about vacuuming non catalog relations by passing the table
     * to GlobalVisCheckRemovableXid().
     */

    if (metad->btm_version < BTREE_NOVAC_VERSION)
    {
        /*
         * Do cleanup if metapage needs upgrade, because we don't have
         * cleanup-related meta-information yet.
         */
        result = true;
    }
    else if (TransactionIdIsValid(metad->btm_oldest_btpo_xact) &&
             GlobalVisCheckRemovableXid(NULL, metad->btm_oldest_btpo_xact))
    {
        /*
         * If any oldest btpo.xact from a previously deleted page in the index
         * is visible to everyone, then at least one deleted page can be
         * recycled -- don't skip cleanup.
         */
        result = true;
    }
    else
    {
        BTOptions  *relopts;
        float8      cleanup_scale_factor;
        float8      prev_num_heap_tuples;

        /*
         * If table receives enough insertions and no cleanup was performed,
         * then index would appear have stale statistics.  If scale factor is
         * set, we avoid that by performing cleanup if the number of inserted
         * tuples exceeds vacuum_cleanup_index_scale_factor fraction of
         * original tuples count.
         */
        relopts = (BTOptions *) info->index->rd_options;
        cleanup_scale_factor = (relopts &&
                                relopts->vacuum_cleanup_index_scale_factor >= 0)
            ? relopts->vacuum_cleanup_index_scale_factor
            : vacuum_cleanup_index_scale_factor;
        prev_num_heap_tuples = metad->btm_last_cleanup_num_heap_tuples;

        if (cleanup_scale_factor <= 0 ||
            info->num_heap_tuples < 0 ||
            prev_num_heap_tuples <= 0 ||
            (info->num_heap_tuples - prev_num_heap_tuples) /
            prev_num_heap_tuples >= cleanup_scale_factor)
            result = true;
    }

    _bt_relbuf(info->index, metabuf);
    return result;
}

btbeginscan()

IndexScanDesc btbeginscan	(	Relation	rel,
		int	nkeys,
		int	norderbys
	)

Definition at line 355 of file nbtree.c.

References BTScanOpaqueData::arrayContext, BTScanOpaqueData::arrayKeyData, BTScanOpaqueData::arrayKeys, Assert, BTScanPosInvalidate, BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, BTScanOpaqueData::keyData, BTScanOpaqueData::killedItems, BTScanOpaqueData::markPos, BTScanOpaqueData::markTuples, BTScanOpaqueData::numArrayKeys, IndexScanDescData::numberOfKeys, BTScanOpaqueData::numKilled, IndexScanDescData::opaque, palloc(), RelationGetDescr, RelationGetIndexScan(), and IndexScanDescData::xs_itupdesc.

Referenced by bthandler().

{
    IndexScanDesc scan;
    BTScanOpaque so;

    /* no order by operators allowed */
    Assert(norderbys == 0);

    /* get the scan */
    scan = RelationGetIndexScan(rel, nkeys, norderbys);

    /* allocate private workspace */
    so = (BTScanOpaque) palloc(sizeof(BTScanOpaqueData));
    BTScanPosInvalidate(so->currPos);
    BTScanPosInvalidate(so->markPos);
    if (scan->numberOfKeys > 0)
        so->keyData = (ScanKey) palloc(scan->numberOfKeys * sizeof(ScanKeyData));
    else
        so->keyData = NULL;

    so->arrayKeyData = NULL;    /* assume no array keys for now */
    so->numArrayKeys = 0;
    so->arrayKeys = NULL;
    so->arrayContext = NULL;

    so->killedItems = NULL;     /* until needed */
    so->numKilled = 0;

    /*
     * We don't know yet whether the scan will be index-only, so we do not
     * allocate the tuple workspace arrays until btrescan.  However, we set up
     * scan->xs_itupdesc whether we'll need it or not, since that's so cheap.
     */
    so->currTuples = so->markTuples = NULL;

    scan->xs_itupdesc = RelationGetDescr(rel);

    scan->opaque = so;

    return scan;
}

btbuildempty()

void btbuildempty

(

Relation

index

)

Definition at line 163 of file nbtree.c.

References _bt_allequalimage(), _bt_initmetapage(), BTREE_METAPAGE, INIT_FORKNUM, log_newpage(), RelFileNodeBackend::node, P_NONE, PageSetChecksumInplace(), palloc(), RelationData::rd_smgr, SMgrRelationData::smgr_rnode, smgrimmedsync(), and smgrwrite().

Referenced by bthandler().

{
    Page        metapage;

    /* Construct metapage. */
    metapage = (Page) palloc(BLCKSZ);
    _bt_initmetapage(metapage, P_NONE, 0, _bt_allequalimage(index, false));

    /*
     * Write the page and log it.  It might seem that an immediate sync would
     * be sufficient to guarantee that the file exists on disk, but recovery
     * itself might remove it while replaying, for example, an
     * XLOG_DBASE_CREATE or XLOG_TBLSPC_CREATE record.  Therefore, we need
     * this even when wal_level=minimal.
     */
    PageSetChecksumInplace(metapage, BTREE_METAPAGE);
    smgrwrite(index->rd_smgr, INIT_FORKNUM, BTREE_METAPAGE,
              (char *) metapage, true);
    log_newpage(&index->rd_smgr->smgr_rnode.node, INIT_FORKNUM,
                BTREE_METAPAGE, metapage, true);

    /*
     * An immediate sync is required even if we xlog'd the page, because the
     * write did not go through shared_buffers and therefore a concurrent
     * checkpoint may have moved the redo pointer past our xlog record.
     */
    smgrimmedsync(index->rd_smgr, INIT_FORKNUM);
}

btbulkdelete()

IndexBulkDeleteResult* btbulkdelete	(	IndexVacuumInfo *	info,
		IndexBulkDeleteResult *	stats,
		IndexBulkDeleteCallback	callback,
		void *	callback_state
	)

Definition at line 875 of file nbtree.c.

References _bt_end_vacuum(), _bt_end_vacuum_callback(), _bt_start_vacuum(), btvacuumscan(), IndexVacuumInfo::index, palloc0(), PG_END_ENSURE_ERROR_CLEANUP, PG_ENSURE_ERROR_CLEANUP, and PointerGetDatum.

Referenced by bthandler().

{
    Relation    rel = info->index;
    BTCycleId   cycleid;

    /* allocate stats if first time through, else re-use existing struct */
    if (stats == NULL)
        stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));

    /* Establish the vacuum cycle ID to use for this scan */
    /* The ENSURE stuff ensures we clean up shared memory on failure */
    PG_ENSURE_ERROR_CLEANUP(_bt_end_vacuum_callback, PointerGetDatum(rel));
    {
        cycleid = _bt_start_vacuum(rel);

        btvacuumscan(info, stats, callback, callback_state, cycleid);
    }
    PG_END_ENSURE_ERROR_CLEANUP(_bt_end_vacuum_callback, PointerGetDatum(rel));
    _bt_end_vacuum(rel);

    return stats;
}

btcanreturn()

bool btcanreturn	(	Relation	index,
		int	attno
	)

Definition at line 1509 of file nbtree.c.

Referenced by bthandler().

{
    return true;
}

btendscan()

void btendscan

(

IndexScanDesc

scan

)

Definition at line 460 of file nbtree.c.

References _bt_killitems(), BTScanOpaqueData::arrayContext, BTScanPosIsValid, BTScanPosUnpinIfPinned, BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, BTScanOpaqueData::keyData, BTScanOpaqueData::killedItems, BTScanOpaqueData::markItemIndex, BTScanOpaqueData::markPos, MemoryContextDelete(), BTScanOpaqueData::numKilled, IndexScanDescData::opaque, and pfree().

Referenced by bthandler().

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;

    /* we aren't holding any read locks, but gotta drop the pins */
    if (BTScanPosIsValid(so->currPos))
    {
        /* Before leaving current page, deal with any killed items */
        if (so->numKilled > 0)
            _bt_killitems(scan);
        BTScanPosUnpinIfPinned(so->currPos);
    }

    so->markItemIndex = -1;
    BTScanPosUnpinIfPinned(so->markPos);

    /* No need to invalidate positions, the RAM is about to be freed. */

    /* Release storage */
    if (so->keyData != NULL)
        pfree(so->keyData);
    /* so->arrayKeyData and so->arrayKeys are in arrayContext */
    if (so->arrayContext != NULL)
        MemoryContextDelete(so->arrayContext);
    if (so->killedItems != NULL)
        pfree(so->killedItems);
    if (so->currTuples != NULL)
        pfree(so->currTuples);
    /* so->markTuples should not be pfree'd, see btrescan */
    pfree(so);
}

btestimateparallelscan()

Size btestimateparallelscan

(

void

)

Definition at line 582 of file nbtree.c.

Referenced by bthandler().

{
    return sizeof(BTParallelScanDescData);
}

btgetbitmap()

int64 btgetbitmap	(	IndexScanDesc	scan,
		TIDBitmap *	tbm
	)

Definition at line 297 of file nbtree.c.

References _bt_advance_array_keys(), _bt_first(), _bt_next(), _bt_start_array_keys(), BTScanOpaqueData::currPos, ForwardScanDirection, BTScanPosItem::heapTid, BTScanPosData::itemIndex, BTScanPosData::items, BTScanPosData::lastItem, BTScanOpaqueData::numArrayKeys, IndexScanDescData::opaque, tbm_add_tuples(), and IndexScanDescData::xs_heaptid.

Referenced by bthandler().

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    int64       ntids = 0;
    ItemPointer heapTid;

    /*
     * If we have any array keys, initialize them.
     */
    if (so->numArrayKeys)
    {
        /* punt if we have any unsatisfiable array keys */
        if (so->numArrayKeys < 0)
            return ntids;

        _bt_start_array_keys(scan, ForwardScanDirection);
    }

    /* This loop handles advancing to the next array elements, if any */
    do
    {
        /* Fetch the first page & tuple */
        if (_bt_first(scan, ForwardScanDirection))
        {
            /* Save tuple ID, and continue scanning */
            heapTid = &scan->xs_heaptid;
            tbm_add_tuples(tbm, heapTid, 1, false);
            ntids++;

            for (;;)
            {
                /*
                 * Advance to next tuple within page.  This is the same as the
                 * easy case in _bt_next().
                 */
                if (++so->currPos.itemIndex > so->currPos.lastItem)
                {
                    /* let _bt_next do the heavy lifting */
                    if (!_bt_next(scan, ForwardScanDirection))
                        break;
                }

                /* Save tuple ID, and continue scanning */
                heapTid = &so->currPos.items[so->currPos.itemIndex].heapTid;
                tbm_add_tuples(tbm, heapTid, 1, false);
                ntids++;
            }
        }
        /* Now see if we have more array keys to deal with */
    } while (so->numArrayKeys && _bt_advance_array_keys(scan, ForwardScanDirection));

    return ntids;
}

btgettuple()

bool btgettuple	(	IndexScanDesc	scan,
		ScanDirection	dir
	)

Definition at line 223 of file nbtree.c.

References _bt_advance_array_keys(), _bt_first(), _bt_next(), _bt_start_array_keys(), BTScanPosIsValid, BTScanOpaqueData::currPos, BTScanPosData::itemIndex, IndexScanDescData::kill_prior_tuple, BTScanOpaqueData::killedItems, MaxTIDsPerBTreePage, BTScanOpaqueData::numArrayKeys, BTScanOpaqueData::numKilled, IndexScanDescData::opaque, palloc(), and IndexScanDescData::xs_recheck.

Referenced by bthandler().

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    bool        res;

    /* btree indexes are never lossy */
    scan->xs_recheck = false;

    /*
     * If we have any array keys, initialize them during first call for a
     * scan.  We can't do this in btrescan because we don't know the scan
     * direction at that time.
     */
    if (so->numArrayKeys && !BTScanPosIsValid(so->currPos))
    {
        /* punt if we have any unsatisfiable array keys */
        if (so->numArrayKeys < 0)
            return false;

        _bt_start_array_keys(scan, dir);
    }

    /* This loop handles advancing to the next array elements, if any */
    do
    {
        /*
         * If we've already initialized this scan, we can just advance it in
         * the appropriate direction.  If we haven't done so yet, we call
         * _bt_first() to get the first item in the scan.
         */
        if (!BTScanPosIsValid(so->currPos))
            res = _bt_first(scan, dir);
        else
        {
            /*
             * Check to see if we should kill the previously-fetched tuple.
             */
            if (scan->kill_prior_tuple)
            {
                /*
                 * Yes, remember it for later. (We'll deal with all such
                 * tuples at once right before leaving the index page.)  The
                 * test for numKilled overrun is not just paranoia: if the
                 * caller reverses direction in the indexscan then the same
                 * item might get entered multiple times. It's not worth
                 * trying to optimize that, so we don't detect it, but instead
                 * just forget any excess entries.
                 */
                if (so->killedItems == NULL)
                    so->killedItems = (int *)
                        palloc(MaxTIDsPerBTreePage * sizeof(int));
                if (so->numKilled < MaxTIDsPerBTreePage)
                    so->killedItems[so->numKilled++] = so->currPos.itemIndex;
            }

            /*
             * Now continue the scan.
             */
            res = _bt_next(scan, dir);
        }

        /* If we have a tuple, return it ... */
        if (res)
            break;
        /* ... otherwise see if we have more array keys to deal with */
    } while (so->numArrayKeys && _bt_advance_array_keys(scan, dir));

    return res;
}

bthandler()

Datum bthandler

(

PG_FUNCTION_ARGS

)

Definition at line 108 of file nbtree.c.

References IndexAmRoutine::amadjustmembers, IndexAmRoutine::ambeginscan, IndexAmRoutine::ambuild, IndexAmRoutine::ambuildempty, IndexAmRoutine::ambuildphasename, IndexAmRoutine::ambulkdelete, IndexAmRoutine::amcanbackward, IndexAmRoutine::amcaninclude, IndexAmRoutine::amcanmulticol, IndexAmRoutine::amcanorder, IndexAmRoutine::amcanorderbyop, IndexAmRoutine::amcanparallel, IndexAmRoutine::amcanreturn, IndexAmRoutine::amcanunique, IndexAmRoutine::amclusterable, IndexAmRoutine::amcostestimate, IndexAmRoutine::amendscan, IndexAmRoutine::amestimateparallelscan, IndexAmRoutine::amgetbitmap, IndexAmRoutine::amgettuple, IndexAmRoutine::aminitparallelscan, IndexAmRoutine::aminsert, IndexAmRoutine::amkeytype, IndexAmRoutine::ammarkpos, IndexAmRoutine::amoptionalkey, IndexAmRoutine::amoptions, IndexAmRoutine::amoptsprocnum, IndexAmRoutine::amparallelrescan, IndexAmRoutine::amparallelvacuumoptions, IndexAmRoutine::ampredlocks, IndexAmRoutine::amproperty, IndexAmRoutine::amrescan, IndexAmRoutine::amrestrpos, IndexAmRoutine::amsearcharray, IndexAmRoutine::amsearchnulls, IndexAmRoutine::amstorage, IndexAmRoutine::amstrategies, IndexAmRoutine::amsupport, IndexAmRoutine::amusemaintenanceworkmem, IndexAmRoutine::amvacuumcleanup, IndexAmRoutine::amvalidate, btadjustmembers(), btbeginscan(), btbuild(), btbuildempty(), btbuildphasename(), btbulkdelete(), btcanreturn(), btcostestimate(), btendscan(), btestimateparallelscan(), btgetbitmap(), btgettuple(), btinitparallelscan(), btinsert(), btmarkpos(), BTMaxStrategyNumber, BTNProcs, btoptions(), BTOPTIONS_PROC, btparallelrescan(), btproperty(), btrescan(), btrestrpos(), btvacuumcleanup(), btvalidate(), InvalidOid, makeNode, PG_RETURN_POINTER, VACUUM_OPTION_PARALLEL_BULKDEL, and VACUUM_OPTION_PARALLEL_COND_CLEANUP.

{
    IndexAmRoutine *amroutine = makeNode(IndexAmRoutine);

    amroutine->amstrategies = BTMaxStrategyNumber;
    amroutine->amsupport = BTNProcs;
    amroutine->amoptsprocnum = BTOPTIONS_PROC;
    amroutine->amcanorder = true;
    amroutine->amcanorderbyop = false;
    amroutine->amcanbackward = true;
    amroutine->amcanunique = true;
    amroutine->amcanmulticol = true;
    amroutine->amoptionalkey = true;
    amroutine->amsearcharray = true;
    amroutine->amsearchnulls = true;
    amroutine->amstorage = false;
    amroutine->amclusterable = true;
    amroutine->ampredlocks = true;
    amroutine->amcanparallel = true;
    amroutine->amcaninclude = true;
    amroutine->amusemaintenanceworkmem = false;
    amroutine->amparallelvacuumoptions =
        VACUUM_OPTION_PARALLEL_BULKDEL | VACUUM_OPTION_PARALLEL_COND_CLEANUP;
    amroutine->amkeytype = InvalidOid;

    amroutine->ambuild = btbuild;
    amroutine->ambuildempty = btbuildempty;
    amroutine->aminsert = btinsert;
    amroutine->ambulkdelete = btbulkdelete;
    amroutine->amvacuumcleanup = btvacuumcleanup;
    amroutine->amcanreturn = btcanreturn;
    amroutine->amcostestimate = btcostestimate;
    amroutine->amoptions = btoptions;
    amroutine->amproperty = btproperty;
    amroutine->ambuildphasename = btbuildphasename;
    amroutine->amvalidate = btvalidate;
    amroutine->amadjustmembers = btadjustmembers;
    amroutine->ambeginscan = btbeginscan;
    amroutine->amrescan = btrescan;
    amroutine->amgettuple = btgettuple;
    amroutine->amgetbitmap = btgetbitmap;
    amroutine->amendscan = btendscan;
    amroutine->ammarkpos = btmarkpos;
    amroutine->amrestrpos = btrestrpos;
    amroutine->amestimateparallelscan = btestimateparallelscan;
    amroutine->aminitparallelscan = btinitparallelscan;
    amroutine->amparallelrescan = btparallelrescan;

    PG_RETURN_POINTER(amroutine);
}

btinitparallelscan()

void btinitparallelscan

(

void *

target

)

Definition at line 591 of file nbtree.c.

References BTPARALLEL_NOT_INITIALIZED, BTParallelScanDescData::btps_arrayKeyCount, BTParallelScanDescData::btps_cv, BTParallelScanDescData::btps_mutex, BTParallelScanDescData::btps_pageStatus, BTParallelScanDescData::btps_scanPage, ConditionVariableInit(), InvalidBlockNumber, and SpinLockInit.

Referenced by bthandler().

{
    BTParallelScanDesc bt_target = (BTParallelScanDesc) target;

    SpinLockInit(&bt_target->btps_mutex);
    bt_target->btps_scanPage = InvalidBlockNumber;
    bt_target->btps_pageStatus = BTPARALLEL_NOT_INITIALIZED;
    bt_target->btps_arrayKeyCount = 0;
    ConditionVariableInit(&bt_target->btps_cv);
}

btinsert()

bool btinsert	(	Relation	rel,
		Datum *	values,
		bool *	isnull,
		ItemPointer	ht_ctid,
		Relation	heapRel,
		IndexUniqueCheck	checkUnique,
		bool	indexUnchanged,
		IndexInfo *	indexInfo
	)

Definition at line 199 of file nbtree.c.

References _bt_doinsert(), index_form_tuple(), pfree(), RelationGetDescr, and IndexTupleData::t_tid.

Referenced by bthandler().

{
    bool        result;
    IndexTuple  itup;

    /* generate an index tuple */
    itup = index_form_tuple(RelationGetDescr(rel), values, isnull);
    itup->t_tid = *ht_ctid;

    result = _bt_doinsert(rel, itup, checkUnique, indexUnchanged, heapRel);

    pfree(itup);

    return result;
}

btmarkpos()

void btmarkpos

(

IndexScanDesc

scan

)

Definition at line 496 of file nbtree.c.

References _bt_mark_array_keys(), BTScanPosInvalidate, BTScanPosIsValid, BTScanPosUnpinIfPinned, BTScanOpaqueData::currPos, BTScanPosData::itemIndex, BTScanOpaqueData::markItemIndex, BTScanOpaqueData::markPos, and IndexScanDescData::opaque.

Referenced by bthandler().

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;

    /* There may be an old mark with a pin (but no lock). */
    BTScanPosUnpinIfPinned(so->markPos);

    /*
     * Just record the current itemIndex.  If we later step to next page
     * before releasing the marked position, _bt_steppage makes a full copy of
     * the currPos struct in markPos.  If (as often happens) the mark is moved
     * before we leave the page, we don't have to do that work.
     */
    if (BTScanPosIsValid(so->currPos))
        so->markItemIndex = so->currPos.itemIndex;
    else
    {
        BTScanPosInvalidate(so->markPos);
        so->markItemIndex = -1;
    }

    /* Also record the current positions of any array keys */
    if (so->numArrayKeys)
        _bt_mark_array_keys(scan);
}

btparallelrescan()

void btparallelrescan

(

IndexScanDesc

scan

)

Definition at line 606 of file nbtree.c.

References Assert, BTPARALLEL_NOT_INITIALIZED, BTParallelScanDescData::btps_arrayKeyCount, BTParallelScanDescData::btps_mutex, BTParallelScanDescData::btps_pageStatus, BTParallelScanDescData::btps_scanPage, InvalidBlockNumber, OffsetToPointer, IndexScanDescData::parallel_scan, ParallelIndexScanDescData::ps_offset, SpinLockAcquire, and SpinLockRelease.

Referenced by bthandler().

{
    BTParallelScanDesc btscan;
    ParallelIndexScanDesc parallel_scan = scan->parallel_scan;

    Assert(parallel_scan);

    btscan = (BTParallelScanDesc) OffsetToPointer((void *) parallel_scan,
                                                  parallel_scan->ps_offset);

    /*
     * In theory, we don't need to acquire the spinlock here, because there
     * shouldn't be any other workers running at this point, but we do so for
     * consistency.
     */
    SpinLockAcquire(&btscan->btps_mutex);
    btscan->btps_scanPage = InvalidBlockNumber;
    btscan->btps_pageStatus = BTPARALLEL_NOT_INITIALIZED;
    btscan->btps_arrayKeyCount = 0;
    SpinLockRelease(&btscan->btps_mutex);
}

btreevacuumposting()

static BTVacuumPosting btreevacuumposting ( BTVacState *  vstate, IndexTuple  posting, OffsetNumber  updatedoffset, int *  nremaining  )

static

Definition at line 1460 of file nbtree.c.

References BTreeTupleGetNPosting(), BTreeTupleGetPosting(), BTVacState::callback, BTVacState::callback_state, BTVacuumPostingData::deletetids, i, BTVacuumPostingData::itup, BTVacuumPostingData::ndeletedtids, offsetof, palloc(), and BTVacuumPostingData::updatedoffset.

Referenced by btvacuumpage().

{
    int         live = 0;
    int         nitem = BTreeTupleGetNPosting(posting);
    ItemPointer items = BTreeTupleGetPosting(posting);
    BTVacuumPosting vacposting = NULL;

    for (int i = 0; i < nitem; i++)
    {
        if (!vstate->callback(items + i, vstate->callback_state))
        {
            /* Live table TID */
            live++;
        }
        else if (vacposting == NULL)
        {
            /*
             * First dead table TID encountered.
             *
             * It's now clear that we need to delete one or more dead table
             * TIDs, so start maintaining metadata describing how to update
             * existing posting list tuple.
             */
            vacposting = palloc(offsetof(BTVacuumPostingData, deletetids) +
                                nitem * sizeof(uint16));

            vacposting->itup = posting;
            vacposting->updatedoffset = updatedoffset;
            vacposting->ndeletedtids = 0;
            vacposting->deletetids[vacposting->ndeletedtids++] = i;
        }
        else
        {
            /* Second or subsequent dead table TID */
            vacposting->deletetids[vacposting->ndeletedtids++] = i;
        }
    }

    *nremaining = live;
    return vacposting;
}

btrescan()

void btrescan	(	IndexScanDesc	scan,
		ScanKey	scankey,
		int	nscankeys,
		ScanKey	orderbys,
		int	norderbys
	)

Definition at line 401 of file nbtree.c.

References _bt_killitems(), _bt_preprocess_array_keys(), BTScanOpaqueData::arrayKeyCount, BTScanPosInvalidate, BTScanPosIsValid, BTScanPosUnpinIfPinned, BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, IndexScanDescData::keyData, BTScanOpaqueData::markItemIndex, BTScanOpaqueData::markPos, BTScanOpaqueData::markTuples, IndexScanDescData::numberOfKeys, BTScanOpaqueData::numberOfKeys, BTScanOpaqueData::numKilled, IndexScanDescData::opaque, palloc(), and IndexScanDescData::xs_want_itup.

Referenced by bthandler().

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;

    /* we aren't holding any read locks, but gotta drop the pins */
    if (BTScanPosIsValid(so->currPos))
    {
        /* Before leaving current page, deal with any killed items */
        if (so->numKilled > 0)
            _bt_killitems(scan);
        BTScanPosUnpinIfPinned(so->currPos);
        BTScanPosInvalidate(so->currPos);
    }

    so->markItemIndex = -1;
    so->arrayKeyCount = 0;
    BTScanPosUnpinIfPinned(so->markPos);
    BTScanPosInvalidate(so->markPos);

    /*
     * Allocate tuple workspace arrays, if needed for an index-only scan and
     * not already done in a previous rescan call.  To save on palloc
     * overhead, both workspaces are allocated as one palloc block; only this
     * function and btendscan know that.
     *
     * NOTE: this data structure also makes it safe to return data from a
     * "name" column, even though btree name_ops uses an underlying storage
     * datatype of cstring.  The risk there is that "name" is supposed to be
     * padded to NAMEDATALEN, but the actual index tuple is probably shorter.
     * However, since we only return data out of tuples sitting in the
     * currTuples array, a fetch of NAMEDATALEN bytes can at worst pull some
     * data out of the markTuples array --- running off the end of memory for
     * a SIGSEGV is not possible.  Yeah, this is ugly as sin, but it beats
     * adding special-case treatment for name_ops elsewhere.
     */
    if (scan->xs_want_itup && so->currTuples == NULL)
    {
        so->currTuples = (char *) palloc(BLCKSZ * 2);
        so->markTuples = so->currTuples + BLCKSZ;
    }

    /*
     * Reset the scan keys
     */
    if (scankey && scan->numberOfKeys > 0)
        memmove(scan->keyData,
                scankey,
                scan->numberOfKeys * sizeof(ScanKeyData));
    so->numberOfKeys = 0;       /* until _bt_preprocess_keys sets it */

    /* If any keys are SK_SEARCHARRAY type, set up array-key info */
    _bt_preprocess_array_keys(scan);
}

btrestrpos()

void btrestrpos

(

IndexScanDesc

scan

)

Definition at line 526 of file nbtree.c.

References _bt_killitems(), _bt_restore_array_keys(), BTScanPosInvalidate, BTScanPosIsPinned, BTScanPosIsValid, BTScanPosUnpinIfPinned, BTScanPosData::buf, BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, IncrBufferRefCount(), BTScanPosData::itemIndex, BTScanPosData::lastItem, BTScanOpaqueData::markItemIndex, BTScanOpaqueData::markPos, BTScanOpaqueData::markTuples, BTScanPosData::nextTupleOffset, BTScanOpaqueData::numArrayKeys, BTScanOpaqueData::numKilled, offsetof, and IndexScanDescData::opaque.

Referenced by bthandler().

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;

    /* Restore the marked positions of any array keys */
    if (so->numArrayKeys)
        _bt_restore_array_keys(scan);

    if (so->markItemIndex >= 0)
    {
        /*
         * The scan has never moved to a new page since the last mark.  Just
         * restore the itemIndex.
         *
         * NB: In this case we can't count on anything in so->markPos to be
         * accurate.
         */
        so->currPos.itemIndex = so->markItemIndex;
    }
    else
    {
        /*
         * The scan moved to a new page after last mark or restore, and we are
         * now restoring to the marked page.  We aren't holding any read
         * locks, but if we're still holding the pin for the current position,
         * we must drop it.
         */
        if (BTScanPosIsValid(so->currPos))
        {
            /* Before leaving current page, deal with any killed items */
            if (so->numKilled > 0)
                _bt_killitems(scan);
            BTScanPosUnpinIfPinned(so->currPos);
        }

        if (BTScanPosIsValid(so->markPos))
        {
            /* bump pin on mark buffer for assignment to current buffer */
            if (BTScanPosIsPinned(so->markPos))
                IncrBufferRefCount(so->markPos.buf);
            memcpy(&so->currPos, &so->markPos,
                   offsetof(BTScanPosData, items[1]) +
                   so->markPos.lastItem * sizeof(BTScanPosItem));
            if (so->currTuples)
                memcpy(so->currTuples, so->markTuples,
                       so->markPos.nextTupleOffset);
        }
        else
            BTScanPosInvalidate(so->currPos);
    }
}

btvacuumcleanup()

IndexBulkDeleteResult* btvacuumcleanup	(	IndexVacuumInfo *	info,
		IndexBulkDeleteResult *	stats
	)

Definition at line 905 of file nbtree.c.

References _bt_vacuum_needs_cleanup(), IndexVacuumInfo::analyze_only, btvacuumscan(), IndexVacuumInfo::estimated_count, IndexVacuumInfo::num_heap_tuples, IndexBulkDeleteResult::num_index_tuples, and palloc0().

Referenced by bthandler().

{
    /* No-op in ANALYZE ONLY mode */
    if (info->analyze_only)
        return stats;

    /*
     * If btbulkdelete was called, we need not do anything, just return the
     * stats from the latest btbulkdelete call.  If it wasn't called, we might
     * still need to do a pass over the index, to recycle any newly-recyclable
     * pages or to obtain index statistics.  _bt_vacuum_needs_cleanup
     * determines if either are needed.
     *
     * Since we aren't going to actually delete any leaf items, there's no
     * need to go through all the vacuum-cycle-ID pushups.
     */
    if (stats == NULL)
    {
        /* Check if we need a cleanup */
        if (!_bt_vacuum_needs_cleanup(info))
            return NULL;

        stats = (IndexBulkDeleteResult *) palloc0(sizeof(IndexBulkDeleteResult));
        btvacuumscan(info, stats, NULL, NULL, 0);
    }

    /*
     * It's quite possible for us to be fooled by concurrent page splits into
     * double-counting some index tuples, so disbelieve any total that exceeds
     * the underlying heap's count ... if we know that accurately.  Otherwise
     * this might just make matters worse.
     *
     * Posting list tuples are another source of inaccuracy.  Cleanup-only
     * btvacuumscan calls assume that the number of index tuples can be used
     * as num_index_tuples, even though num_index_tuples is supposed to
     * represent the number of TIDs in the index.  This naive approach can
     * underestimate the number of tuples in the index.
     */
    if (!info->estimated_count)
    {
        if (stats->num_index_tuples > info->num_heap_tuples)
            stats->num_index_tuples = info->num_heap_tuples;
    }

    return stats;
}

btvacuumpage()

static void btvacuumpage ( BTVacState *  vstate, BlockNumber  scanblkno  )

static

Definition at line 1099 of file nbtree.c.

References _bt_checkpage(), _bt_delitems_vacuum(), _bt_lockbuf(), _bt_page_recyclable(), _bt_pagedel(), _bt_relbuf(), _bt_upgradelockbufcleanup(), Assert, BT_READ, BTP_SPLIT_END, BTPageOpaqueData::btpo, BTPageOpaqueData::btpo_cycleid, BTPageOpaqueData::btpo_flags, BTPageOpaqueData::btpo_next, BTreeTupleGetNPosting(), BTreeTupleIsPivot(), BTreeTupleIsPosting(), btreevacuumposting(), buf, BufferGetPage, BTVacState::callback, callback(), BTVacState::callback_state, BTVacState::cycleid, ereport, errcode(), errmsg_internal(), i, IndexVacuumInfo::index, BTVacState::info, LOG, MAIN_FORKNUM, MarkBufferDirtyHint(), MaxIndexTuplesPerPage, MemoryContextReset(), MemoryContextSwitchTo(), IndexBulkDeleteResult::num_index_tuples, OffsetNumberNext, BTVacState::oldestBtpoXact, P_FIRSTDATAKEY, P_ISDELETED, P_ISHALFDEAD, P_ISLEAF, P_NONE, P_RIGHTMOST, BTVacState::pagedelcontext, PageGetItem, PageGetItemId, PageGetMaxOffsetNumber, PageGetSpecialPointer, PageIsNew, IndexBulkDeleteResult::pages_deleted, pfree(), RBM_NORMAL, ReadBufferExtended(), RecordFreeIndexPage(), RelationGetRelationName, BTVacState::stats, IndexVacuumInfo::strategy, IndexTupleData::t_tid, BTVacState::totFreePages, TransactionIdIsValid, TransactionIdPrecedes(), IndexBulkDeleteResult::tuples_removed, vacuum_delay_point(), and BTPageOpaqueData::xact.

Referenced by btvacuumscan().

{
    IndexVacuumInfo *info = vstate->info;
    IndexBulkDeleteResult *stats = vstate->stats;
    IndexBulkDeleteCallback callback = vstate->callback;
    void       *callback_state = vstate->callback_state;
    Relation    rel = info->index;
    bool        attempt_pagedel;
    BlockNumber blkno,
                backtrack_to;
    Buffer      buf;
    Page        page;
    BTPageOpaque opaque;

    blkno = scanblkno;

backtrack:

    attempt_pagedel = false;
    backtrack_to = P_NONE;

    /* call vacuum_delay_point while not holding any buffer lock */
    vacuum_delay_point();

    /*
     * We can't use _bt_getbuf() here because it always applies
     * _bt_checkpage(), which will barf on an all-zero page. We want to
     * recycle all-zero pages, not fail.  Also, we want to use a nondefault
     * buffer access strategy.
     */
    buf = ReadBufferExtended(rel, MAIN_FORKNUM, blkno, RBM_NORMAL,
                             info->strategy);
    _bt_lockbuf(rel, buf, BT_READ);
    page = BufferGetPage(buf);
    opaque = NULL;
    if (!PageIsNew(page))
    {
        _bt_checkpage(rel, buf);
        opaque = (BTPageOpaque) PageGetSpecialPointer(page);
    }

    Assert(blkno <= scanblkno);
    if (blkno != scanblkno)
    {
        /*
         * We're backtracking.
         *
         * We followed a right link to a sibling leaf page (a page that
         * happens to be from a block located before scanblkno).  The only
         * case we want to do anything with is a live leaf page having the
         * current vacuum cycle ID.
         *
         * The page had better be in a state that's consistent with what we
         * expect.  Check for conditions that imply corruption in passing.  It
         * can't be half-dead because only an interrupted VACUUM process can
         * leave pages in that state, so we'd definitely have dealt with it
         * back when the page was the scanblkno page (half-dead pages are
         * always marked fully deleted by _bt_pagedel()).  This assumes that
         * there can be only one vacuum process running at a time.
         */
        if (!opaque || !P_ISLEAF(opaque) || P_ISHALFDEAD(opaque))
        {
            Assert(false);
            ereport(LOG,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg_internal("right sibling %u of scanblkno %u unexpectedly in an inconsistent state in index \"%s\"",
                                     blkno, scanblkno, RelationGetRelationName(rel))));
            _bt_relbuf(rel, buf);
            return;
        }

        /*
         * We may have already processed the page in an earlier call, when the
         * page was scanblkno.  This happens when the leaf page split occurred
         * after the scan began, but before the right sibling page became the
         * scanblkno.
         *
         * Page may also have been deleted by current btvacuumpage() call,
         * since _bt_pagedel() sometimes deletes the right sibling page of
         * scanblkno in passing (it does so after we decided where to
         * backtrack to).  We don't need to process this page as a deleted
         * page a second time now (in fact, it would be wrong to count it as a
         * deleted page in the bulk delete statistics a second time).
         */
        if (opaque->btpo_cycleid != vstate->cycleid || P_ISDELETED(opaque))
        {
            /* Done with current scanblkno (and all lower split pages) */
            _bt_relbuf(rel, buf);
            return;
        }
    }

    /* Page is valid, see what to do with it */
    if (_bt_page_recyclable(page))
    {
        /* Okay to recycle this page (which could be leaf or internal) */
        RecordFreeIndexPage(rel, blkno);
        vstate->totFreePages++;
        stats->pages_deleted++;
    }
    else if (P_ISDELETED(opaque))
    {
        /*
         * Already deleted page (which could be leaf or internal).  Can't
         * recycle yet.
         */
        stats->pages_deleted++;

        /* Maintain the oldest btpo.xact */
        if (!TransactionIdIsValid(vstate->oldestBtpoXact) ||
            TransactionIdPrecedes(opaque->btpo.xact, vstate->oldestBtpoXact))
            vstate->oldestBtpoXact = opaque->btpo.xact;
    }
    else if (P_ISHALFDEAD(opaque))
    {
        /*
         * Half-dead leaf page.  Try to delete now.  Might update
         * oldestBtpoXact and pages_deleted below.
         */
        attempt_pagedel = true;
    }
    else if (P_ISLEAF(opaque))
    {
        OffsetNumber deletable[MaxIndexTuplesPerPage];
        int         ndeletable;
        BTVacuumPosting updatable[MaxIndexTuplesPerPage];
        int         nupdatable;
        OffsetNumber offnum,
                    minoff,
                    maxoff;
        int         nhtidsdead,
                    nhtidslive;

        /*
         * Trade in the initial read lock for a super-exclusive write lock on
         * this page.  We must get such a lock on every leaf page over the
         * course of the vacuum scan, whether or not it actually contains any
         * deletable tuples --- see nbtree/README.
         */
        _bt_upgradelockbufcleanup(rel, buf);

        /*
         * Check whether we need to backtrack to earlier pages.  What we are
         * concerned about is a page split that happened since we started the
         * vacuum scan.  If the split moved tuples on the right half of the
         * split (i.e. the tuples that sort high) to a block that we already
         * passed over, then we might have missed the tuples.  We need to
         * backtrack now.  (Must do this before possibly clearing btpo_cycleid
         * or deleting scanblkno page below!)
         */
        if (vstate->cycleid != 0 &&
            opaque->btpo_cycleid == vstate->cycleid &&
            !(opaque->btpo_flags & BTP_SPLIT_END) &&
            !P_RIGHTMOST(opaque) &&
            opaque->btpo_next < scanblkno)
            backtrack_to = opaque->btpo_next;

        /*
         * When each VACUUM begins, it determines an OldestXmin cutoff value.
         * Tuples before the cutoff are removed by VACUUM.  Scan over all
         * items to see which ones need to be deleted according to cutoff
         * point using callback.
         */
        ndeletable = 0;
        nupdatable = 0;
        minoff = P_FIRSTDATAKEY(opaque);
        maxoff = PageGetMaxOffsetNumber(page);
        nhtidsdead = 0;
        nhtidslive = 0;
        if (callback)
        {
            for (offnum = minoff;
                 offnum <= maxoff;
                 offnum = OffsetNumberNext(offnum))
            {
                IndexTuple  itup;

                itup = (IndexTuple) PageGetItem(page,
                                                PageGetItemId(page, offnum));

                /*
                 * Hot Standby assumes that it's okay that XLOG_BTREE_VACUUM
                 * records do not produce their own conflicts.  This is safe
                 * as long as the callback function only considers whether the
                 * index tuple refers to pre-cutoff heap tuples that were
                 * certainly already pruned away during VACUUM's initial heap
                 * scan by the time we get here. (heapam's XLOG_HEAP2_CLEAN
                 * and XLOG_HEAP2_CLEANUP_INFO records produce conflicts using
                 * a latestRemovedXid value for the pointed-to heap tuples, so
                 * there is no need to produce our own conflict now.)
                 *
                 * Backends with snapshots acquired after a VACUUM starts but
                 * before it finishes could have visibility cutoff with a
                 * later xid than VACUUM's OldestXmin cutoff.  These backends
                 * might happen to opportunistically mark some index tuples
                 * LP_DEAD before we reach them, even though they may be after
                 * our cutoff.  We don't try to kill these "extra" index
                 * tuples in _bt_delitems_vacuum().  This keep things simple,
                 * and allows us to always avoid generating our own conflicts.
                 */
                Assert(!BTreeTupleIsPivot(itup));
                if (!BTreeTupleIsPosting(itup))
                {
                    /* Regular tuple, standard table TID representation */
                    if (callback(&itup->t_tid, callback_state))
                    {
                        deletable[ndeletable++] = offnum;
                        nhtidsdead++;
                    }
                    else
                        nhtidslive++;
                }
                else
                {
                    BTVacuumPosting vacposting;
                    int         nremaining;

                    /* Posting list tuple */
                    vacposting = btreevacuumposting(vstate, itup, offnum,
                                                    &nremaining);
                    if (vacposting == NULL)
                    {
                        /*
                         * All table TIDs from the posting tuple remain, so no
                         * delete or update required
                         */
                        Assert(nremaining == BTreeTupleGetNPosting(itup));
                    }
                    else if (nremaining > 0)
                    {

                        /*
                         * Store metadata about posting list tuple in
                         * updatable array for entire page.  Existing tuple
                         * will be updated during the later call to
                         * _bt_delitems_vacuum().
                         */
                        Assert(nremaining < BTreeTupleGetNPosting(itup));
                        updatable[nupdatable++] = vacposting;
                        nhtidsdead += BTreeTupleGetNPosting(itup) - nremaining;
                    }
                    else
                    {
                        /*
                         * All table TIDs from the posting list must be
                         * deleted.  We'll delete the index tuple completely
                         * (no update required).
                         */
                        Assert(nremaining == 0);
                        deletable[ndeletable++] = offnum;
                        nhtidsdead += BTreeTupleGetNPosting(itup);
                        pfree(vacposting);
                    }

                    nhtidslive += nremaining;
                }
            }
        }

        /*
         * Apply any needed deletes or updates.  We issue just one
         * _bt_delitems_vacuum() call per page, so as to minimize WAL traffic.
         */
        if (ndeletable > 0 || nupdatable > 0)
        {
            Assert(nhtidsdead >= ndeletable + nupdatable);
            _bt_delitems_vacuum(rel, buf, deletable, ndeletable, updatable,
                                nupdatable);

            stats->tuples_removed += nhtidsdead;
            /* must recompute maxoff */
            maxoff = PageGetMaxOffsetNumber(page);

            /* can't leak memory here */
            for (int i = 0; i < nupdatable; i++)
                pfree(updatable[i]);
        }
        else
        {
            /*
             * If the leaf page has been split during this vacuum cycle, it
             * seems worth expending a write to clear btpo_cycleid even if we
             * don't have any deletions to do.  (If we do, _bt_delitems_vacuum
             * takes care of this.)  This ensures we won't process the page
             * again.
             *
             * We treat this like a hint-bit update because there's no need to
             * WAL-log it.
             */
            Assert(nhtidsdead == 0);
            if (vstate->cycleid != 0 &&
                opaque->btpo_cycleid == vstate->cycleid)
            {
                opaque->btpo_cycleid = 0;
                MarkBufferDirtyHint(buf, true);
            }
        }

        /*
         * If the leaf page is now empty, try to delete it; else count the
         * live tuples (live table TIDs in posting lists are counted as
         * separate live tuples).  We don't delete when backtracking, though,
         * since that would require teaching _bt_pagedel() about backtracking
         * (doesn't seem worth adding more complexity to deal with that).
         *
         * We don't count the number of live TIDs during cleanup-only calls to
         * btvacuumscan (i.e. when callback is not set).  We count the number
         * of index tuples directly instead.  This avoids the expense of
         * directly examining all of the tuples on each page.
         */
        if (minoff > maxoff)
            attempt_pagedel = (blkno == scanblkno);
        else if (callback)
            stats->num_index_tuples += nhtidslive;
        else
            stats->num_index_tuples += maxoff - minoff + 1;

        Assert(!attempt_pagedel || nhtidslive == 0);
    }

    if (attempt_pagedel)
    {
        MemoryContext oldcontext;

        /* Run pagedel in a temp context to avoid memory leakage */
        MemoryContextReset(vstate->pagedelcontext);
        oldcontext = MemoryContextSwitchTo(vstate->pagedelcontext);

        /*
         * We trust the _bt_pagedel return value because it does not include
         * any page that a future call here from btvacuumscan is expected to
         * count.  There will be no double-counting.
         */
        Assert(blkno == scanblkno);
        stats->pages_deleted += _bt_pagedel(rel, buf, &vstate->oldestBtpoXact);

        MemoryContextSwitchTo(oldcontext);
        /* pagedel released buffer, so we shouldn't */
    }
    else
        _bt_relbuf(rel, buf);

    if (backtrack_to != P_NONE)
    {
        blkno = backtrack_to;
        goto backtrack;
    }
}

btvacuumscan()

static void btvacuumscan ( IndexVacuumInfo *  info, IndexBulkDeleteResult *  stats, IndexBulkDeleteCallback  callback, void *  callback_state, BTCycleId  cycleid  )

static

Definition at line 967 of file nbtree.c.

References _bt_update_meta_cleanup_info(), ALLOCSET_DEFAULT_SIZES, AllocSetContextCreate, BTREE_METAPAGE, btvacuumpage(), BTVacState::callback, callback(), BTVacState::callback_state, CurrentMemoryContext, BTVacState::cycleid, IndexBulkDeleteResult::estimated_count, ExclusiveLock, IndexVacuumInfo::index, IndexFreeSpaceMapVacuum(), BTVacState::info, InvalidTransactionId, LockRelationForExtension(), MemoryContextDelete(), IndexVacuumInfo::num_heap_tuples, IndexBulkDeleteResult::num_index_tuples, IndexBulkDeleteResult::num_pages, BTVacState::oldestBtpoXact, BTVacState::pagedelcontext, IndexBulkDeleteResult::pages_deleted, IndexBulkDeleteResult::pages_free, pgstat_progress_update_param(), PROGRESS_SCAN_BLOCKS_DONE, PROGRESS_SCAN_BLOCKS_TOTAL, RELATION_IS_LOCAL, RelationGetNumberOfBlocks, IndexVacuumInfo::report_progress, BTVacState::stats, BTVacState::totFreePages, and UnlockRelationForExtension().

Referenced by btbulkdelete(), and btvacuumcleanup().

{
    Relation    rel = info->index;
    BTVacState  vstate;
    BlockNumber num_pages;
    BlockNumber scanblkno;
    bool        needLock;

    /*
     * Reset counts that will be incremented during the scan; needed in case
     * of multiple scans during a single VACUUM command
     */
    stats->estimated_count = false;
    stats->num_index_tuples = 0;
    stats->pages_deleted = 0;

    /* Set up info to pass down to btvacuumpage */
    vstate.info = info;
    vstate.stats = stats;
    vstate.callback = callback;
    vstate.callback_state = callback_state;
    vstate.cycleid = cycleid;
    vstate.totFreePages = 0;
    vstate.oldestBtpoXact = InvalidTransactionId;

    /* Create a temporary memory context to run _bt_pagedel in */
    vstate.pagedelcontext = AllocSetContextCreate(CurrentMemoryContext,
                                                  "_bt_pagedel",
                                                  ALLOCSET_DEFAULT_SIZES);

    /*
     * The outer loop iterates over all index pages except the metapage, in
     * physical order (we hope the kernel will cooperate in providing
     * read-ahead for speed).  It is critical that we visit all leaf pages,
     * including ones added after we start the scan, else we might fail to
     * delete some deletable tuples.  Hence, we must repeatedly check the
     * relation length.  We must acquire the relation-extension lock while
     * doing so to avoid a race condition: if someone else is extending the
     * relation, there is a window where bufmgr/smgr have created a new
     * all-zero page but it hasn't yet been write-locked by _bt_getbuf(). If
     * we manage to scan such a page here, we'll improperly assume it can be
     * recycled.  Taking the lock synchronizes things enough to prevent a
     * problem: either num_pages won't include the new page, or _bt_getbuf
     * already has write lock on the buffer and it will be fully initialized
     * before we can examine it.  (See also vacuumlazy.c, which has the same
     * issue.)  Also, we need not worry if a page is added immediately after
     * we look; the page splitting code already has write-lock on the left
     * page before it adds a right page, so we must already have processed any
     * tuples due to be moved into such a page.
     *
     * We can skip locking for new or temp relations, however, since no one
     * else could be accessing them.
     */
    needLock = !RELATION_IS_LOCAL(rel);

    scanblkno = BTREE_METAPAGE + 1;
    for (;;)
    {
        /* Get the current relation length */
        if (needLock)
            LockRelationForExtension(rel, ExclusiveLock);
        num_pages = RelationGetNumberOfBlocks(rel);
        if (needLock)
            UnlockRelationForExtension(rel, ExclusiveLock);

        if (info->report_progress)
            pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_TOTAL,
                                         num_pages);

        /* Quit if we've scanned the whole relation */
        if (scanblkno >= num_pages)
            break;
        /* Iterate over pages, then loop back to recheck length */
        for (; scanblkno < num_pages; scanblkno++)
        {
            btvacuumpage(&vstate, scanblkno);
            if (info->report_progress)
                pgstat_progress_update_param(PROGRESS_SCAN_BLOCKS_DONE,
                                             scanblkno);
        }
    }

    MemoryContextDelete(vstate.pagedelcontext);

    /*
     * If we found any recyclable pages (and recorded them in the FSM), then
     * forcibly update the upper-level FSM pages to ensure that searchers can
     * find them.  It's possible that the pages were also found during
     * previous scans and so this is a waste of time, but it's cheap enough
     * relative to scanning the index that it shouldn't matter much, and
     * making sure that free pages are available sooner not later seems
     * worthwhile.
     *
     * Note that if no recyclable pages exist, we don't bother vacuuming the
     * FSM at all.
     */
    if (vstate.totFreePages > 0)
        IndexFreeSpaceMapVacuum(rel);

    /*
     * Maintain the oldest btpo.xact and a count of the current number of heap
     * tuples in the metapage (for the benefit of _bt_vacuum_needs_cleanup).
     *
     * The page with the oldest btpo.xact is typically a page deleted by this
     * VACUUM operation, since pages deleted by a previous VACUUM operation
     * tend to be placed in the FSM (by the current VACUUM operation) -- such
     * pages are not candidates to be the oldest btpo.xact.  (Note that pages
     * placed in the FSM are reported as deleted pages in the bulk delete
     * statistics, despite not counting as deleted pages for the purposes of
     * determining the oldest btpo.xact.)
     */
    _bt_update_meta_cleanup_info(rel, vstate.oldestBtpoXact,
                                 info->num_heap_tuples);

    /* update statistics */
    stats->num_pages = num_pages;
    stats->pages_free = vstate.totFreePages;
}