nbtsearch.c File Reference

#include "postgres.h"
#include "access/nbtree.h"
#include "access/relscan.h"
#include "access/xact.h"
#include "miscadmin.h"
#include "pgstat.h"
#include "storage/predicate.h"
#include "utils/lsyscache.h"
#include "utils/rel.h"

Include dependency graph for nbtsearch.c:

Go to the source code of this file.

Functions
static void	_bt_drop_lock_and_maybe_pin (IndexScanDesc scan, BTScanPos sp)
static OffsetNumber	_bt_binsrch (Relation rel, BTScanInsert key, Buffer buf)
static int	_bt_binsrch_posting (BTScanInsert key, Page page, OffsetNumber offnum)
static bool	_bt_readpage (IndexScanDesc scan, ScanDirection dir, OffsetNumber offnum, bool firstPage)
static void	_bt_saveitem (BTScanOpaque so, int itemIndex, OffsetNumber offnum, IndexTuple itup)
static int	_bt_setuppostingitems (BTScanOpaque so, int itemIndex, OffsetNumber offnum, ItemPointer heapTid, IndexTuple itup)
static void	_bt_savepostingitem (BTScanOpaque so, int itemIndex, OffsetNumber offnum, ItemPointer heapTid, int tupleOffset)
static bool	_bt_steppage (IndexScanDesc scan, ScanDirection dir)
static bool	_bt_readnextpage (IndexScanDesc scan, BlockNumber blkno, ScanDirection dir)
static bool	_bt_parallel_readpage (IndexScanDesc scan, BlockNumber blkno, ScanDirection dir)
static Buffer	_bt_walk_left (Relation rel, Buffer buf)
static bool	_bt_endpoint (IndexScanDesc scan, ScanDirection dir)
static void	_bt_initialize_more_data (BTScanOpaque so, ScanDirection dir)
BTStack	_bt_search (Relation rel, Relation heaprel, BTScanInsert key, Buffer *bufP, int access)
Buffer	_bt_moveright (Relation rel, Relation heaprel, BTScanInsert key, Buffer buf, bool forupdate, BTStack stack, int access)
OffsetNumber	_bt_binsrch_insert (Relation rel, BTInsertState insertstate)
int32	_bt_compare (Relation rel, BTScanInsert key, Page page, OffsetNumber offnum)
bool	_bt_first (IndexScanDesc scan, ScanDirection dir)
bool	_bt_next (IndexScanDesc scan, ScanDirection dir)
Buffer	_bt_get_endpoint (Relation rel, uint32 level, bool rightmost)

Function Documentation

_bt_binsrch()

static OffsetNumber _bt_binsrch ( Relation  rel, BTScanInsert  key, Buffer  buf  )

static

Definition at line 337 of file nbtsearch.c.

{
    Page        page;
    BTPageOpaque opaque;
    OffsetNumber low,
                high;
    int32       result,
                cmpval;
 
    page = BufferGetPage(buf);
    opaque = BTPageGetOpaque(page);
 
    /* Requesting nextkey semantics while using scantid seems nonsensical */
    Assert(!key->nextkey || key->scantid == NULL);
    /* scantid-set callers must use _bt_binsrch_insert() on leaf pages */
    Assert(!P_ISLEAF(opaque) || key->scantid == NULL);
 
    low = P_FIRSTDATAKEY(opaque);
    high = PageGetMaxOffsetNumber(page);
 
    /*
     * If there are no keys on the page, return the first available slot. Note
     * this covers two cases: the page is really empty (no keys), or it
     * contains only a high key.  The latter case is possible after vacuuming.
     * This can never happen on an internal page, however, since they are
     * never empty (an internal page must have at least one child).
     */
    if (unlikely(high < low))
        return low;
 
    /*
     * Binary search to find the first key on the page >= scan key, or first
     * key > scankey when nextkey is true.
     *
     * For nextkey=false (cmpval=1), the loop invariant is: all slots before
     * 'low' are < scan key, all slots at or after 'high' are >= scan key.
     *
     * For nextkey=true (cmpval=0), the loop invariant is: all slots before
     * 'low' are <= scan key, all slots at or after 'high' are > scan key.
     *
     * We can fall out when high == low.
     */
    high++;                     /* establish the loop invariant for high */
 
    cmpval = key->nextkey ? 0 : 1;  /* select comparison value */
 
    while (high > low)
    {
        OffsetNumber mid = low + ((high - low) / 2);
 
        /* We have low <= mid < high, so mid points at a real slot */
 
        result = _bt_compare(rel, key, page, mid);
 
        if (result >= cmpval)
            low = mid + 1;
        else
            high = mid;
    }
 
    /*
     * At this point we have high == low.
     *
     * On a leaf page we always return the first non-pivot tuple >= scan key
     * (resp. > scan key) for forward scan callers.  For backward scans, it's
     * always the _last_ non-pivot tuple < scan key (resp. <= scan key).
     */
    if (P_ISLEAF(opaque))
    {
        /*
         * In the backward scan case we're supposed to locate the last
         * matching tuple on the leaf level -- not the first matching tuple
         * (the last tuple will be the first one returned by the scan).
         *
         * At this point we've located the first non-pivot tuple immediately
         * after the last matching tuple (which might just be maxoff + 1).
         * Compensate by stepping back.
         */
        if (key->backward)
            return OffsetNumberPrev(low);
 
        return low;
    }
 
    /*
     * On a non-leaf page, return the last key < scan key (resp. <= scan key).
     * There must be one if _bt_compare() is playing by the rules.
     *
     * _bt_compare() will seldom see any exactly-matching pivot tuples, since
     * a truncated -inf heap TID is usually enough to prevent it altogether.
     * Even omitted scan key entries are treated as > truncated attributes.
     *
     * However, during backward scans _bt_compare() interprets omitted scan
     * key attributes as == corresponding truncated -inf attributes instead.
     * This works just like < would work here.  Under this scheme, < strategy
     * backward scans will always directly descend to the correct leaf page.
     * In particular, they will never incur an "extra" leaf page access with a
     * scan key that happens to contain the same prefix of values as some
     * pivot tuple's untruncated prefix.  VACUUM relies on this guarantee when
     * it uses a leaf page high key to "re-find" a page undergoing deletion.
     */
    Assert(low > P_FIRSTDATAKEY(opaque));
 
    return OffsetNumberPrev(low);
}

References _bt_compare(), Assert, BTPageGetOpaque, buf, BufferGetPage(), sort-test::key, OffsetNumberPrev, P_FIRSTDATAKEY, P_ISLEAF, PageGetMaxOffsetNumber(), and unlikely.

Referenced by _bt_first(), and _bt_search().

_bt_binsrch_insert()

OffsetNumber _bt_binsrch_insert	(	Relation	rel,
		BTInsertState	insertstate
	)

Definition at line 468 of file nbtsearch.c.

{
    BTScanInsert key = insertstate->itup_key;
    Page        page;
    BTPageOpaque opaque;
    OffsetNumber low,
                high,
                stricthigh;
    int32       result,
                cmpval;
 
    page = BufferGetPage(insertstate->buf);
    opaque = BTPageGetOpaque(page);
 
    Assert(P_ISLEAF(opaque));
    Assert(!key->nextkey);
    Assert(insertstate->postingoff == 0);
 
    if (!insertstate->bounds_valid)
    {
        /* Start new binary search */
        low = P_FIRSTDATAKEY(opaque);
        high = PageGetMaxOffsetNumber(page);
    }
    else
    {
        /* Restore result of previous binary search against same page */
        low = insertstate->low;
        high = insertstate->stricthigh;
    }
 
    /* If there are no keys on the page, return the first available slot */
    if (unlikely(high < low))
    {
        /* Caller can't reuse bounds */
        insertstate->low = InvalidOffsetNumber;
        insertstate->stricthigh = InvalidOffsetNumber;
        insertstate->bounds_valid = false;
        return low;
    }
 
    /*
     * Binary search to find the first key on the page >= scan key. (nextkey
     * is always false when inserting).
     *
     * The loop invariant is: all slots before 'low' are < scan key, all slots
     * at or after 'high' are >= scan key.  'stricthigh' is > scan key, and is
     * maintained to save additional search effort for caller.
     *
     * We can fall out when high == low.
     */
    if (!insertstate->bounds_valid)
        high++;                 /* establish the loop invariant for high */
    stricthigh = high;          /* high initially strictly higher */
 
    cmpval = 1;                 /* !nextkey comparison value */
 
    while (high > low)
    {
        OffsetNumber mid = low + ((high - low) / 2);
 
        /* We have low <= mid < high, so mid points at a real slot */
 
        result = _bt_compare(rel, key, page, mid);
 
        if (result >= cmpval)
            low = mid + 1;
        else
        {
            high = mid;
            if (result != 0)
                stricthigh = high;
        }
 
        /*
         * If tuple at offset located by binary search is a posting list whose
         * TID range overlaps with caller's scantid, perform posting list
         * binary search to set postingoff for caller.  Caller must split the
         * posting list when postingoff is set.  This should happen
         * infrequently.
         */
        if (unlikely(result == 0 && key->scantid != NULL))
        {
            /*
             * postingoff should never be set more than once per leaf page
             * binary search.  That would mean that there are duplicate table
             * TIDs in the index, which is never okay.  Check for that here.
             */
            if (insertstate->postingoff != 0)
                ereport(ERROR,
                        (errcode(ERRCODE_INDEX_CORRUPTED),
                         errmsg_internal("table tid from new index tuple (%u,%u) cannot find insert offset between offsets %u and %u of block %u in index \"%s\"",
                                         ItemPointerGetBlockNumber(key->scantid),
                                         ItemPointerGetOffsetNumber(key->scantid),
                                         low, stricthigh,
                                         BufferGetBlockNumber(insertstate->buf),
                                         RelationGetRelationName(rel))));
 
            insertstate->postingoff = _bt_binsrch_posting(key, page, mid);
        }
    }
 
    /*
     * On a leaf page, a binary search always returns the first key >= scan
     * key (at least in !nextkey case), which could be the last slot + 1. This
     * is also the lower bound of cached search.
     *
     * stricthigh may also be the last slot + 1, which prevents caller from
     * using bounds directly, but is still useful to us if we're called a
     * second time with cached bounds (cached low will be < stricthigh when
     * that happens).
     */
    insertstate->low = low;
    insertstate->stricthigh = stricthigh;
    insertstate->bounds_valid = true;
 
    return low;
}

References _bt_binsrch_posting(), _bt_compare(), Assert, BTInsertStateData::bounds_valid, BTPageGetOpaque, BTInsertStateData::buf, BufferGetBlockNumber(), BufferGetPage(), ereport, errcode(), errmsg_internal(), ERROR, InvalidOffsetNumber, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), BTInsertStateData::itup_key, sort-test::key, BTInsertStateData::low, P_FIRSTDATAKEY, P_ISLEAF, PageGetMaxOffsetNumber(), BTInsertStateData::postingoff, RelationGetRelationName, BTInsertStateData::stricthigh, and unlikely.

Referenced by _bt_check_unique(), _bt_findinsertloc(), and bt_rootdescend().

_bt_binsrch_posting()

static int _bt_binsrch_posting ( BTScanInsert  key, Page  page, OffsetNumber  offnum  )

static

Definition at line 596 of file nbtsearch.c.

{
    IndexTuple  itup;
    ItemId      itemid;
    int         low,
                high,
                mid,
                res;
 
    /*
     * If this isn't a posting tuple, then the index must be corrupt (if it is
     * an ordinary non-pivot tuple then there must be an existing tuple with a
     * heap TID that equals inserter's new heap TID/scantid).  Defensively
     * check that tuple is a posting list tuple whose posting list range
     * includes caller's scantid.
     *
     * (This is also needed because contrib/amcheck's rootdescend option needs
     * to be able to relocate a non-pivot tuple using _bt_binsrch_insert().)
     */
    itemid = PageGetItemId(page, offnum);
    itup = (IndexTuple) PageGetItem(page, itemid);
    if (!BTreeTupleIsPosting(itup))
        return 0;
 
    Assert(key->heapkeyspace && key->allequalimage);
 
    /*
     * In the event that posting list tuple has LP_DEAD bit set, indicate this
     * to _bt_binsrch_insert() caller by returning -1, a sentinel value.  A
     * second call to _bt_binsrch_insert() can take place when its caller has
     * removed the dead item.
     */
    if (ItemIdIsDead(itemid))
        return -1;
 
    /* "high" is past end of posting list for loop invariant */
    low = 0;
    high = BTreeTupleGetNPosting(itup);
    Assert(high >= 2);
 
    while (high > low)
    {
        mid = low + ((high - low) / 2);
        res = ItemPointerCompare(key->scantid,
                                 BTreeTupleGetPostingN(itup, mid));
 
        if (res > 0)
            low = mid + 1;
        else if (res < 0)
            high = mid;
        else
            return mid;
    }
 
    /* Exact match not found */
    return low;
}

References Assert, BTreeTupleGetNPosting(), BTreeTupleGetPostingN(), BTreeTupleIsPosting(), ItemIdIsDead, ItemPointerCompare(), sort-test::key, PageGetItem(), PageGetItemId(), and res.

Referenced by _bt_binsrch_insert().

_bt_compare()

int32 _bt_compare	(	Relation	rel,
		BTScanInsert	key,
		Page	page,
		OffsetNumber	offnum
	)

Definition at line 682 of file nbtsearch.c.

{
    TupleDesc   itupdesc = RelationGetDescr(rel);
    BTPageOpaque opaque = BTPageGetOpaque(page);
    IndexTuple  itup;
    ItemPointer heapTid;
    ScanKey     scankey;
    int         ncmpkey;
    int         ntupatts;
    int32       result;
 
    Assert(_bt_check_natts(rel, key->heapkeyspace, page, offnum));
    Assert(key->keysz <= IndexRelationGetNumberOfKeyAttributes(rel));
    Assert(key->heapkeyspace || key->scantid == NULL);
 
    /*
     * Force result ">" if target item is first data item on an internal page
     * --- see NOTE above.
     */
    if (!P_ISLEAF(opaque) && offnum == P_FIRSTDATAKEY(opaque))
        return 1;
 
    itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
    ntupatts = BTreeTupleGetNAtts(itup, rel);
 
    /*
     * The scan key is set up with the attribute number associated with each
     * term in the key.  It is important that, if the index is multi-key, the
     * scan contain the first k key attributes, and that they be in order.  If
     * you think about how multi-key ordering works, you'll understand why
     * this is.
     *
     * We don't test for violation of this condition here, however.  The
     * initial setup for the index scan had better have gotten it right (see
     * _bt_first).
     */
 
    ncmpkey = Min(ntupatts, key->keysz);
    Assert(key->heapkeyspace || ncmpkey == key->keysz);
    Assert(!BTreeTupleIsPosting(itup) || key->allequalimage);
    scankey = key->scankeys;
    for (int i = 1; i <= ncmpkey; i++)
    {
        Datum       datum;
        bool        isNull;
 
        datum = index_getattr(itup, scankey->sk_attno, itupdesc, &isNull);
 
        if (scankey->sk_flags & SK_ISNULL)  /* key is NULL */
        {
            if (isNull)
                result = 0;     /* NULL "=" NULL */
            else if (scankey->sk_flags & SK_BT_NULLS_FIRST)
                result = -1;    /* NULL "<" NOT_NULL */
            else
                result = 1;     /* NULL ">" NOT_NULL */
        }
        else if (isNull)        /* key is NOT_NULL and item is NULL */
        {
            if (scankey->sk_flags & SK_BT_NULLS_FIRST)
                result = 1;     /* NOT_NULL ">" NULL */
            else
                result = -1;    /* NOT_NULL "<" NULL */
        }
        else
        {
            /*
             * The sk_func needs to be passed the index value as left arg and
             * the sk_argument as right arg (they might be of different
             * types).  Since it is convenient for callers to think of
             * _bt_compare as comparing the scankey to the index item, we have
             * to flip the sign of the comparison result.  (Unless it's a DESC
             * column, in which case we *don't* flip the sign.)
             */
            result = DatumGetInt32(FunctionCall2Coll(&scankey->sk_func,
                                                     scankey->sk_collation,
                                                     datum,
                                                     scankey->sk_argument));
 
            if (!(scankey->sk_flags & SK_BT_DESC))
                INVERT_COMPARE_RESULT(result);
        }
 
        /* if the keys are unequal, return the difference */
        if (result != 0)
            return result;
 
        scankey++;
    }
 
    /*
     * All non-truncated attributes (other than heap TID) were found to be
     * equal.  Treat truncated attributes as minus infinity when scankey has a
     * key attribute value that would otherwise be compared directly.
     *
     * Note: it doesn't matter if ntupatts includes non-key attributes;
     * scankey won't, so explicitly excluding non-key attributes isn't
     * necessary.
     */
    if (key->keysz > ntupatts)
        return 1;
 
    /*
     * Use the heap TID attribute and scantid to try to break the tie.  The
     * rules are the same as any other key attribute -- only the
     * representation differs.
     */
    heapTid = BTreeTupleGetHeapTID(itup);
    if (key->scantid == NULL)
    {
        /*
         * Forward scans have a scankey that is considered greater than a
         * truncated pivot tuple if and when the scankey has equal values for
         * attributes up to and including the least significant untruncated
         * attribute in tuple.  Even attributes that were omitted from the
         * scan key are considered greater than -inf truncated attributes.
         * (See _bt_binsrch for an explanation of our backward scan behavior.)
         *
         * For example, if an index has the minimum two attributes (single
         * user key attribute, plus heap TID attribute), and a page's high key
         * is ('foo', -inf), and scankey is ('foo', <omitted>), the search
         * will not descend to the page to the left.  The search will descend
         * right instead.  The truncated attribute in pivot tuple means that
         * all non-pivot tuples on the page to the left are strictly < 'foo',
         * so it isn't necessary to descend left.  In other words, search
         * doesn't have to descend left because it isn't interested in a match
         * that has a heap TID value of -inf.
         *
         * Note: the heap TID part of the test ensures that scankey is being
         * compared to a pivot tuple with one or more truncated -inf key
         * attributes.  The heap TID attribute is the last key attribute in
         * every index, of course, but other than that it isn't special.
         */
        if (!key->backward && key->keysz == ntupatts && heapTid == NULL &&
            key->heapkeyspace)
            return 1;
 
        /* All provided scankey arguments found to be equal */
        return 0;
    }
 
    /*
     * Treat truncated heap TID as minus infinity, since scankey has a key
     * attribute value (scantid) that would otherwise be compared directly
     */
    Assert(key->keysz == IndexRelationGetNumberOfKeyAttributes(rel));
    if (heapTid == NULL)
        return 1;
 
    /*
     * Scankey must be treated as equal to a posting list tuple if its scantid
     * value falls within the range of the posting list.  In all other cases
     * there can only be a single heap TID value, which is compared directly
     * with scantid.
     */
    Assert(ntupatts >= IndexRelationGetNumberOfKeyAttributes(rel));
    result = ItemPointerCompare(key->scantid, heapTid);
    if (result <= 0 || !BTreeTupleIsPosting(itup))
        return result;
    else
    {
        result = ItemPointerCompare(key->scantid,
                                    BTreeTupleGetMaxHeapTID(itup));
        if (result > 0)
            return 1;
    }
 
    return 0;
}

References _bt_check_natts(), Assert, BTPageGetOpaque, BTreeTupleGetHeapTID(), BTreeTupleGetMaxHeapTID(), BTreeTupleGetNAtts, BTreeTupleIsPosting(), DatumGetInt32(), FunctionCall2Coll(), i, index_getattr(), IndexRelationGetNumberOfKeyAttributes, INVERT_COMPARE_RESULT, ItemPointerCompare(), sort-test::key, Min, P_FIRSTDATAKEY, P_ISLEAF, PageGetItem(), PageGetItemId(), RelationGetDescr, ScanKeyData::sk_argument, ScanKeyData::sk_attno, SK_BT_DESC, SK_BT_NULLS_FIRST, ScanKeyData::sk_collation, ScanKeyData::sk_flags, ScanKeyData::sk_func, and SK_ISNULL.

Referenced by _bt_binsrch(), _bt_binsrch_insert(), _bt_check_unique(), _bt_findinsertloc(), _bt_moveright(), _bt_search_insert(), bt_rootdescend(), bt_target_page_check(), invariant_g_offset(), invariant_l_nontarget_offset(), invariant_l_offset(), and invariant_leq_offset().

_bt_drop_lock_and_maybe_pin()

static void _bt_drop_lock_and_maybe_pin ( IndexScanDesc  scan, BTScanPos  sp  )

static

Definition at line 61 of file nbtsearch.c.

{
    _bt_unlockbuf(scan->indexRelation, sp->buf);
 
    if (IsMVCCSnapshot(scan->xs_snapshot) &&
        RelationNeedsWAL(scan->indexRelation) &&
        !scan->xs_want_itup)
    {
        ReleaseBuffer(sp->buf);
        sp->buf = InvalidBuffer;
    }
}

References _bt_unlockbuf(), BTScanPosData::buf, IndexScanDescData::indexRelation, InvalidBuffer, IsMVCCSnapshot, RelationNeedsWAL, ReleaseBuffer(), IndexScanDescData::xs_snapshot, and IndexScanDescData::xs_want_itup.

Referenced by _bt_endpoint(), _bt_first(), _bt_parallel_readpage(), and _bt_steppage().

_bt_endpoint()

static bool _bt_endpoint ( IndexScanDesc  scan, ScanDirection  dir  )

static

Definition at line 2560 of file nbtsearch.c.

{
    Relation    rel = scan->indexRelation;
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    Buffer      buf;
    Page        page;
    BTPageOpaque opaque;
    OffsetNumber start;
    BTScanPosItem *currItem;
 
    /*
     * Scan down to the leftmost or rightmost leaf page.  This is a simplified
     * version of _bt_search().  We don't maintain a stack since we know we
     * won't need it.
     */
    buf = _bt_get_endpoint(rel, 0, ScanDirectionIsBackward(dir));
 
    if (!BufferIsValid(buf))
    {
        /*
         * Empty index. Lock the whole relation, as nothing finer to lock
         * exists.
         */
        PredicateLockRelation(rel, scan->xs_snapshot);
        BTScanPosInvalidate(so->currPos);
        return false;
    }
 
    PredicateLockPage(rel, BufferGetBlockNumber(buf), scan->xs_snapshot);
    page = BufferGetPage(buf);
    opaque = BTPageGetOpaque(page);
    Assert(P_ISLEAF(opaque));
 
    if (ScanDirectionIsForward(dir))
    {
        /* There could be dead pages to the left, so not this: */
        /* Assert(P_LEFTMOST(opaque)); */
 
        start = P_FIRSTDATAKEY(opaque);
    }
    else if (ScanDirectionIsBackward(dir))
    {
        Assert(P_RIGHTMOST(opaque));
 
        start = PageGetMaxOffsetNumber(page);
    }
    else
    {
        elog(ERROR, "invalid scan direction: %d", (int) dir);
        start = 0;              /* keep compiler quiet */
    }
 
    /* remember which buffer we have pinned */
    so->currPos.buf = buf;
 
    _bt_initialize_more_data(so, dir);
 
    /*
     * Now load data from the first page of the scan.
     */
    if (!_bt_readpage(scan, dir, start, true))
    {
        /*
         * There's no actually-matching data on this page.  Try to advance to
         * the next page.  Return false if there's no matching data at all.
         */
        _bt_unlockbuf(scan->indexRelation, so->currPos.buf);
        if (!_bt_steppage(scan, dir))
            return false;
    }
    else
    {
        /* We have at least one item to return as scan's first item */
        _bt_drop_lock_and_maybe_pin(scan, &so->currPos);
    }
 
    /* OK, itemIndex says what to return */
    currItem = &so->currPos.items[so->currPos.itemIndex];
    scan->xs_heaptid = currItem->heapTid;
    if (scan->xs_want_itup)
        scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);
 
    return true;
}

References _bt_drop_lock_and_maybe_pin(), _bt_get_endpoint(), _bt_initialize_more_data(), _bt_readpage(), _bt_steppage(), _bt_unlockbuf(), Assert, BTPageGetOpaque, BTScanPosInvalidate, buf, BTScanPosData::buf, BufferGetBlockNumber(), BufferGetPage(), BufferIsValid(), BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, elog, ERROR, IndexScanDescData::indexRelation, BTScanPosData::itemIndex, BTScanPosData::items, IndexScanDescData::opaque, P_FIRSTDATAKEY, P_ISLEAF, P_RIGHTMOST, PageGetMaxOffsetNumber(), PredicateLockPage(), PredicateLockRelation(), ScanDirectionIsBackward, ScanDirectionIsForward, start, IndexScanDescData::xs_heaptid, IndexScanDescData::xs_itup, IndexScanDescData::xs_snapshot, and IndexScanDescData::xs_want_itup.

Referenced by _bt_first().

_bt_first()

bool _bt_first	(	IndexScanDesc	scan,
		ScanDirection	dir
	)

Definition at line 876 of file nbtsearch.c.

{
    Relation    rel = scan->indexRelation;
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    Buffer      buf;
    BTStack     stack;
    OffsetNumber offnum;
    StrategyNumber strat;
    BTScanInsertData inskey;
    ScanKey     startKeys[INDEX_MAX_KEYS];
    ScanKeyData notnullkeys[INDEX_MAX_KEYS];
    int         keysz = 0;
    int         i;
    bool        status;
    StrategyNumber strat_total;
    BTScanPosItem *currItem;
    BlockNumber blkno;
 
    Assert(!BTScanPosIsValid(so->currPos));
 
    pgstat_count_index_scan(rel);
 
    /*
     * Examine the scan keys and eliminate any redundant keys; also mark the
     * keys that must be matched to continue the scan.
     */
    _bt_preprocess_keys(scan);
 
    /*
     * Quit now if _bt_preprocess_keys() discovered that the scan keys can
     * never be satisfied (eg, x == 1 AND x > 2).
     */
    if (!so->qual_ok)
    {
        _bt_parallel_done(scan);
        return false;
    }
 
    /*
     * For parallel scans, get the starting page from shared state. If the
     * scan has not started, proceed to find out first leaf page in the usual
     * way while keeping other participating processes waiting.  If the scan
     * has already begun, use the page number from the shared structure.
     *
     * When a parallel scan has another primitive index scan scheduled, a
     * parallel worker will seize the scan for that purpose now.  This is
     * similar to the case where the top-level scan hasn't started.
     */
    if (scan->parallel_scan != NULL)
    {
        status = _bt_parallel_seize(scan, &blkno, true);
 
        /*
         * Initialize arrays (when _bt_parallel_seize didn't already set up
         * the next primitive index scan)
         */
        if (so->numArrayKeys && !so->needPrimScan)
            _bt_start_array_keys(scan, dir);
 
        if (!status)
            return false;
        else if (blkno == P_NONE)
        {
            _bt_parallel_done(scan);
            return false;
        }
        else if (blkno != InvalidBlockNumber)
        {
            if (!_bt_parallel_readpage(scan, blkno, dir))
                return false;
            goto readcomplete;
        }
    }
    else if (so->numArrayKeys && !so->needPrimScan)
    {
        /*
         * First _bt_first call (for current btrescan) without parallelism.
         *
         * Initialize arrays, and the corresponding scan keys that were just
         * output by _bt_preprocess_keys.
         */
        _bt_start_array_keys(scan, dir);
    }
 
    /*----------
     * Examine the scan keys to discover where we need to start the scan.
     *
     * We want to identify the keys that can be used as starting boundaries;
     * these are =, >, or >= keys for a forward scan or =, <, <= keys for
     * a backwards scan.  We can use keys for multiple attributes so long as
     * the prior attributes had only =, >= (resp. =, <=) keys.  Once we accept
     * a > or < boundary or find an attribute with no boundary (which can be
     * thought of as the same as "> -infinity"), we can't use keys for any
     * attributes to its right, because it would break our simplistic notion
     * of what initial positioning strategy to use.
     *
     * When the scan keys include cross-type operators, _bt_preprocess_keys
     * may not be able to eliminate redundant keys; in such cases we will
     * arbitrarily pick a usable one for each attribute.  This is correct
     * but possibly not optimal behavior.  (For example, with keys like
     * "x >= 4 AND x >= 5" we would elect to scan starting at x=4 when
     * x=5 would be more efficient.)  Since the situation only arises given
     * a poorly-worded query plus an incomplete opfamily, live with it.
     *
     * When both equality and inequality keys appear for a single attribute
     * (again, only possible when cross-type operators appear), we *must*
     * select one of the equality keys for the starting point, because
     * _bt_checkkeys() will stop the scan as soon as an equality qual fails.
     * For example, if we have keys like "x >= 4 AND x = 10" and we elect to
     * start at x=4, we will fail and stop before reaching x=10.  If multiple
     * equality quals survive preprocessing, however, it doesn't matter which
     * one we use --- by definition, they are either redundant or
     * contradictory.
     *
     * Any regular (not SK_SEARCHNULL) key implies a NOT NULL qualifier.
     * If the index stores nulls at the end of the index we'll be starting
     * from, and we have no boundary key for the column (which means the key
     * we deduced NOT NULL from is an inequality key that constrains the other
     * end of the index), then we cons up an explicit SK_SEARCHNOTNULL key to
     * use as a boundary key.  If we didn't do this, we might find ourselves
     * traversing a lot of null entries at the start of the scan.
     *
     * In this loop, row-comparison keys are treated the same as keys on their
     * first (leftmost) columns.  We'll add on lower-order columns of the row
     * comparison below, if possible.
     *
     * The selected scan keys (at most one per index column) are remembered by
     * storing their addresses into the local startKeys[] array.
     *
     * _bt_checkkeys/_bt_advance_array_keys decide whether and when to start
     * the next primitive index scan (for scans with array keys) based in part
     * on an understanding of how it'll enable us to reposition the scan.
     * They're directly aware of how we'll sometimes cons up an explicit
     * SK_SEARCHNOTNULL key.  They'll even end primitive scans by applying a
     * symmetric "deduce NOT NULL" rule of their own.  This allows top-level
     * scans to skip large groups of NULLs through repeated deductions about
     * key strictness (for a required inequality key) and whether NULLs in the
     * key's index column are stored last or first (relative to non-NULLs).
     * If you update anything here, _bt_checkkeys/_bt_advance_array_keys might
     * need to be kept in sync.
     *----------
     */
    strat_total = BTEqualStrategyNumber;
    if (so->numberOfKeys > 0)
    {
        AttrNumber  curattr;
        ScanKey     chosen;
        ScanKey     impliesNN;
        ScanKey     cur;
 
        /*
         * chosen is the so-far-chosen key for the current attribute, if any.
         * We don't cast the decision in stone until we reach keys for the
         * next attribute.
         */
        curattr = 1;
        chosen = NULL;
        /* Also remember any scankey that implies a NOT NULL constraint */
        impliesNN = NULL;
 
        /*
         * Loop iterates from 0 to numberOfKeys inclusive; we use the last
         * pass to handle after-last-key processing.  Actual exit from the
         * loop is at one of the "break" statements below.
         */
        for (cur = so->keyData, i = 0;; cur++, i++)
        {
            if (i >= so->numberOfKeys || cur->sk_attno != curattr)
            {
                /*
                 * Done looking at keys for curattr.  If we didn't find a
                 * usable boundary key, see if we can deduce a NOT NULL key.
                 */
                if (chosen == NULL && impliesNN != NULL &&
                    ((impliesNN->sk_flags & SK_BT_NULLS_FIRST) ?
                     ScanDirectionIsForward(dir) :
                     ScanDirectionIsBackward(dir)))
                {
                    /* Yes, so build the key in notnullkeys[keysz] */
                    chosen = &notnullkeys[keysz];
                    ScanKeyEntryInitialize(chosen,
                                           (SK_SEARCHNOTNULL | SK_ISNULL |
                                            (impliesNN->sk_flags &
                                             (SK_BT_DESC | SK_BT_NULLS_FIRST))),
                                           curattr,
                                           ((impliesNN->sk_flags & SK_BT_NULLS_FIRST) ?
                                            BTGreaterStrategyNumber :
                                            BTLessStrategyNumber),
                                           InvalidOid,
                                           InvalidOid,
                                           InvalidOid,
                                           (Datum) 0);
                }
 
                /*
                 * If we still didn't find a usable boundary key, quit; else
                 * save the boundary key pointer in startKeys.
                 */
                if (chosen == NULL)
                    break;
                startKeys[keysz++] = chosen;
 
                /*
                 * Adjust strat_total, and quit if we have stored a > or <
                 * key.
                 */
                strat = chosen->sk_strategy;
                if (strat != BTEqualStrategyNumber)
                {
                    strat_total = strat;
                    if (strat == BTGreaterStrategyNumber ||
                        strat == BTLessStrategyNumber)
                        break;
                }
 
                /*
                 * Done if that was the last attribute, or if next key is not
                 * in sequence (implying no boundary key is available for the
                 * next attribute).
                 */
                if (i >= so->numberOfKeys ||
                    cur->sk_attno != curattr + 1)
                    break;
 
                /*
                 * Reset for next attr.
                 */
                curattr = cur->sk_attno;
                chosen = NULL;
                impliesNN = NULL;
            }
 
            /*
             * Can we use this key as a starting boundary for this attr?
             *
             * If not, does it imply a NOT NULL constraint?  (Because
             * SK_SEARCHNULL keys are always assigned BTEqualStrategyNumber,
             * *any* inequality key works for that; we need not test.)
             */
            switch (cur->sk_strategy)
            {
                case BTLessStrategyNumber:
                case BTLessEqualStrategyNumber:
                    if (chosen == NULL)
                    {
                        if (ScanDirectionIsBackward(dir))
                            chosen = cur;
                        else
                            impliesNN = cur;
                    }
                    break;
                case BTEqualStrategyNumber:
                    /* override any non-equality choice */
                    chosen = cur;
                    break;
                case BTGreaterEqualStrategyNumber:
                case BTGreaterStrategyNumber:
                    if (chosen == NULL)
                    {
                        if (ScanDirectionIsForward(dir))
                            chosen = cur;
                        else
                            impliesNN = cur;
                    }
                    break;
            }
        }
    }
 
    /*
     * If we found no usable boundary keys, we have to start from one end of
     * the tree.  Walk down that edge to the first or last key, and scan from
     * there.
     */
    if (keysz == 0)
    {
        bool        match;
 
        match = _bt_endpoint(scan, dir);
 
        if (!match)
        {
            /* No match, so mark (parallel) scan finished */
            _bt_parallel_done(scan);
        }
 
        return match;
    }
 
    /*
     * We want to start the scan somewhere within the index.  Set up an
     * insertion scankey we can use to search for the boundary point we
     * identified above.  The insertion scankey is built using the keys
     * identified by startKeys[].  (Remaining insertion scankey fields are
     * initialized after initial-positioning strategy is finalized.)
     */
    Assert(keysz <= INDEX_MAX_KEYS);
    for (i = 0; i < keysz; i++)
    {
        ScanKey     cur = startKeys[i];
 
        Assert(cur->sk_attno == i + 1);
 
        if (cur->sk_flags & SK_ROW_HEADER)
        {
            /*
             * Row comparison header: look to the first row member instead.
             *
             * The member scankeys are already in insertion format (ie, they
             * have sk_func = 3-way-comparison function), but we have to watch
             * out for nulls, which _bt_preprocess_keys didn't check. A null
             * in the first row member makes the condition unmatchable, just
             * like qual_ok = false.
             */
            ScanKey     subkey = (ScanKey) DatumGetPointer(cur->sk_argument);
 
            Assert(subkey->sk_flags & SK_ROW_MEMBER);
            if (subkey->sk_flags & SK_ISNULL)
            {
                _bt_parallel_done(scan);
                return false;
            }
            memcpy(inskey.scankeys + i, subkey, sizeof(ScanKeyData));
 
            /*
             * If the row comparison is the last positioning key we accepted,
             * try to add additional keys from the lower-order row members.
             * (If we accepted independent conditions on additional index
             * columns, we use those instead --- doesn't seem worth trying to
             * determine which is more restrictive.)  Note that this is OK
             * even if the row comparison is of ">" or "<" type, because the
             * condition applied to all but the last row member is effectively
             * ">=" or "<=", and so the extra keys don't break the positioning
             * scheme.  But, by the same token, if we aren't able to use all
             * the row members, then the part of the row comparison that we
             * did use has to be treated as just a ">=" or "<=" condition, and
             * so we'd better adjust strat_total accordingly.
             */
            if (i == keysz - 1)
            {
                bool        used_all_subkeys = false;
 
                Assert(!(subkey->sk_flags & SK_ROW_END));
                for (;;)
                {
                    subkey++;
                    Assert(subkey->sk_flags & SK_ROW_MEMBER);
                    if (subkey->sk_attno != keysz + 1)
                        break;  /* out-of-sequence, can't use it */
                    if (subkey->sk_strategy != cur->sk_strategy)
                        break;  /* wrong direction, can't use it */
                    if (subkey->sk_flags & SK_ISNULL)
                        break;  /* can't use null keys */
                    Assert(keysz < INDEX_MAX_KEYS);
                    memcpy(inskey.scankeys + keysz, subkey,
                           sizeof(ScanKeyData));
                    keysz++;
                    if (subkey->sk_flags & SK_ROW_END)
                    {
                        used_all_subkeys = true;
                        break;
                    }
                }
                if (!used_all_subkeys)
                {
                    switch (strat_total)
                    {
                        case BTLessStrategyNumber:
                            strat_total = BTLessEqualStrategyNumber;
                            break;
                        case BTGreaterStrategyNumber:
                            strat_total = BTGreaterEqualStrategyNumber;
                            break;
                    }
                }
                break;          /* done with outer loop */
            }
        }
        else
        {
            /*
             * Ordinary comparison key.  Transform the search-style scan key
             * to an insertion scan key by replacing the sk_func with the
             * appropriate btree comparison function.
             *
             * If scankey operator is not a cross-type comparison, we can use
             * the cached comparison function; otherwise gotta look it up in
             * the catalogs.  (That can't lead to infinite recursion, since no
             * indexscan initiated by syscache lookup will use cross-data-type
             * operators.)
             *
             * We support the convention that sk_subtype == InvalidOid means
             * the opclass input type; this is a hack to simplify life for
             * ScanKeyInit().
             */
            if (cur->sk_subtype == rel->rd_opcintype[i] ||
                cur->sk_subtype == InvalidOid)
            {
                FmgrInfo   *procinfo;
 
                procinfo = index_getprocinfo(rel, cur->sk_attno, BTORDER_PROC);
                ScanKeyEntryInitializeWithInfo(inskey.scankeys + i,
                                               cur->sk_flags,
                                               cur->sk_attno,
                                               InvalidStrategy,
                                               cur->sk_subtype,
                                               cur->sk_collation,
                                               procinfo,
                                               cur->sk_argument);
            }
            else
            {
                RegProcedure cmp_proc;
 
                cmp_proc = get_opfamily_proc(rel->rd_opfamily[i],
                                             rel->rd_opcintype[i],
                                             cur->sk_subtype,
                                             BTORDER_PROC);
                if (!RegProcedureIsValid(cmp_proc))
                    elog(ERROR, "missing support function %d(%u,%u) for attribute %d of index \"%s\"",
                         BTORDER_PROC, rel->rd_opcintype[i], cur->sk_subtype,
                         cur->sk_attno, RelationGetRelationName(rel));
                ScanKeyEntryInitialize(inskey.scankeys + i,
                                       cur->sk_flags,
                                       cur->sk_attno,
                                       InvalidStrategy,
                                       cur->sk_subtype,
                                       cur->sk_collation,
                                       cmp_proc,
                                       cur->sk_argument);
            }
        }
    }
 
    /*----------
     * Examine the selected initial-positioning strategy to determine exactly
     * where we need to start the scan, and set flag variables to control the
     * initial descent by _bt_search (and our _bt_binsrch call for the leaf
     * page _bt_search returns).
     *----------
     */
    _bt_metaversion(rel, &inskey.heapkeyspace, &inskey.allequalimage);
    inskey.anynullkeys = false; /* unused */
    inskey.scantid = NULL;
    inskey.keysz = keysz;
    switch (strat_total)
    {
        case BTLessStrategyNumber:
 
            inskey.nextkey = false;
            inskey.backward = true;
            break;
 
        case BTLessEqualStrategyNumber:
 
            inskey.nextkey = true;
            inskey.backward = true;
            break;
 
        case BTEqualStrategyNumber:
 
            /*
             * If a backward scan was specified, need to start with last equal
             * item not first one.
             */
            if (ScanDirectionIsBackward(dir))
            {
                /*
                 * This is the same as the <= strategy
                 */
                inskey.nextkey = true;
                inskey.backward = true;
            }
            else
            {
                /*
                 * This is the same as the >= strategy
                 */
                inskey.nextkey = false;
                inskey.backward = false;
            }
            break;
 
        case BTGreaterEqualStrategyNumber:
 
            /*
             * Find first item >= scankey
             */
            inskey.nextkey = false;
            inskey.backward = false;
            break;
 
        case BTGreaterStrategyNumber:
 
            /*
             * Find first item > scankey
             */
            inskey.nextkey = true;
            inskey.backward = false;
            break;
 
        default:
            /* can't get here, but keep compiler quiet */
            elog(ERROR, "unrecognized strat_total: %d", (int) strat_total);
            return false;
    }
 
    /*
     * Use the manufactured insertion scan key to descend the tree and
     * position ourselves on the target leaf page.
     */
    Assert(ScanDirectionIsBackward(dir) == inskey.backward);
    stack = _bt_search(rel, NULL, &inskey, &buf, BT_READ);
 
    /* don't need to keep the stack around... */
    _bt_freestack(stack);
 
    if (!BufferIsValid(buf))
    {
        /*
         * We only get here if the index is completely empty. Lock relation
         * because nothing finer to lock exists.  Without a buffer lock, it's
         * possible for another transaction to insert data between
         * _bt_search() and PredicateLockRelation().  We have to try again
         * after taking the relation-level predicate lock, to close a narrow
         * window where we wouldn't scan concurrently inserted tuples, but the
         * writer wouldn't see our predicate lock.
         */
        if (IsolationIsSerializable())
        {
            PredicateLockRelation(rel, scan->xs_snapshot);
            stack = _bt_search(rel, NULL, &inskey, &buf, BT_READ);
            _bt_freestack(stack);
        }
 
        if (!BufferIsValid(buf))
        {
            /*
             * Mark parallel scan as done, so that all the workers can finish
             * their scan.
             */
            _bt_parallel_done(scan);
            BTScanPosInvalidate(so->currPos);
            return false;
        }
    }
 
    PredicateLockPage(rel, BufferGetBlockNumber(buf), scan->xs_snapshot);
 
    _bt_initialize_more_data(so, dir);
 
    /* position to the precise item on the page */
    offnum = _bt_binsrch(rel, &inskey, buf);
    Assert(!BTScanPosIsValid(so->currPos));
    so->currPos.buf = buf;
 
    /*
     * Now load data from the first page of the scan.
     *
     * If inskey.nextkey = false and inskey.backward = false, offnum is
     * positioned at the first non-pivot tuple >= inskey.scankeys.
     *
     * If inskey.nextkey = false and inskey.backward = true, offnum is
     * positioned at the last non-pivot tuple < inskey.scankeys.
     *
     * If inskey.nextkey = true and inskey.backward = false, offnum is
     * positioned at the first non-pivot tuple > inskey.scankeys.
     *
     * If inskey.nextkey = true and inskey.backward = true, offnum is
     * positioned at the last non-pivot tuple <= inskey.scankeys.
     *
     * It's possible that _bt_binsrch returned an offnum that is out of bounds
     * for the page.  For example, when inskey is both < the leaf page's high
     * key and > all of its non-pivot tuples, offnum will be "maxoff + 1".
     */
    if (!_bt_readpage(scan, dir, offnum, true))
    {
        /*
         * There's no actually-matching data on this page.  Try to advance to
         * the next page.  Return false if there's no matching data at all.
         */
        _bt_unlockbuf(scan->indexRelation, so->currPos.buf);
        if (!_bt_steppage(scan, dir))
            return false;
    }
    else
    {
        /* We have at least one item to return as scan's first item */
        _bt_drop_lock_and_maybe_pin(scan, &so->currPos);
    }
 
readcomplete:
    /* OK, itemIndex says what to return */
    currItem = &so->currPos.items[so->currPos.itemIndex];
    scan->xs_heaptid = currItem->heapTid;
    if (scan->xs_want_itup)
        scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);
 
    return true;
}

References _bt_binsrch(), _bt_drop_lock_and_maybe_pin(), _bt_endpoint(), _bt_freestack(), _bt_initialize_more_data(), _bt_metaversion(), _bt_parallel_done(), _bt_parallel_readpage(), _bt_parallel_seize(), _bt_preprocess_keys(), _bt_readpage(), _bt_search(), _bt_start_array_keys(), _bt_steppage(), _bt_unlockbuf(), Assert, BT_READ, BTEqualStrategyNumber, BTGreaterEqualStrategyNumber, BTGreaterStrategyNumber, BTLessEqualStrategyNumber, BTLessStrategyNumber, BTORDER_PROC, BTScanPosInvalidate, BTScanPosIsValid, buf, BTScanPosData::buf, BufferGetBlockNumber(), BufferIsValid(), cur, BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, DatumGetPointer(), elog, ERROR, get_opfamily_proc(), i, index_getprocinfo(), INDEX_MAX_KEYS, IndexScanDescData::indexRelation, InvalidBlockNumber, InvalidOid, InvalidStrategy, IsolationIsSerializable, BTScanPosData::itemIndex, BTScanPosData::items, BTScanOpaqueData::keyData, BTScanOpaqueData::needPrimScan, BTScanOpaqueData::numArrayKeys, BTScanOpaqueData::numberOfKeys, IndexScanDescData::opaque, P_NONE, IndexScanDescData::parallel_scan, pgstat_count_index_scan, PredicateLockPage(), PredicateLockRelation(), BTScanOpaqueData::qual_ok, RelationData::rd_opcintype, RelationData::rd_opfamily, RegProcedureIsValid, RelationGetRelationName, ScanDirectionIsBackward, ScanDirectionIsForward, ScanKeyEntryInitialize(), ScanKeyEntryInitializeWithInfo(), ScanKeyData::sk_attno, SK_BT_DESC, SK_BT_NULLS_FIRST, ScanKeyData::sk_flags, SK_ISNULL, SK_ROW_END, SK_ROW_HEADER, SK_ROW_MEMBER, SK_SEARCHNOTNULL, ScanKeyData::sk_strategy, IndexScanDescData::xs_heaptid, IndexScanDescData::xs_itup, IndexScanDescData::xs_snapshot, and IndexScanDescData::xs_want_itup.

Referenced by btgetbitmap(), and btgettuple().

_bt_get_endpoint()

Buffer _bt_get_endpoint	(	Relation	rel,
		uint32	level,
		bool	rightmost
	)

Definition at line 2479 of file nbtsearch.c.

{
    Buffer      buf;
    Page        page;
    BTPageOpaque opaque;
    OffsetNumber offnum;
    BlockNumber blkno;
    IndexTuple  itup;
 
    /*
     * If we are looking for a leaf page, okay to descend from fast root;
     * otherwise better descend from true root.  (There is no point in being
     * smarter about intermediate levels.)
     */
    if (level == 0)
        buf = _bt_getroot(rel, NULL, BT_READ);
    else
        buf = _bt_gettrueroot(rel);
 
    if (!BufferIsValid(buf))
        return InvalidBuffer;
 
    page = BufferGetPage(buf);
    opaque = BTPageGetOpaque(page);
 
    for (;;)
    {
        /*
         * If we landed on a deleted page, step right to find a live page
         * (there must be one).  Also, if we want the rightmost page, step
         * right if needed to get to it (this could happen if the page split
         * since we obtained a pointer to it).
         */
        while (P_IGNORE(opaque) ||
               (rightmost && !P_RIGHTMOST(opaque)))
        {
            blkno = opaque->btpo_next;
            if (blkno == P_NONE)
                elog(ERROR, "fell off the end of index \"%s\"",
                     RelationGetRelationName(rel));
            buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
            page = BufferGetPage(buf);
            opaque = BTPageGetOpaque(page);
        }
 
        /* Done? */
        if (opaque->btpo_level == level)
            break;
        if (opaque->btpo_level < level)
            ereport(ERROR,
                    (errcode(ERRCODE_INDEX_CORRUPTED),
                     errmsg_internal("btree level %u not found in index \"%s\"",
                                     level, RelationGetRelationName(rel))));
 
        /* Descend to leftmost or rightmost child page */
        if (rightmost)
            offnum = PageGetMaxOffsetNumber(page);
        else
            offnum = P_FIRSTDATAKEY(opaque);
 
        itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
        blkno = BTreeTupleGetDownLink(itup);
 
        buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
        page = BufferGetPage(buf);
        opaque = BTPageGetOpaque(page);
    }
 
    return buf;
}

References _bt_getroot(), _bt_gettrueroot(), _bt_relandgetbuf(), BT_READ, BTPageGetOpaque, BTPageOpaqueData::btpo_level, BTPageOpaqueData::btpo_next, BTreeTupleGetDownLink(), buf, BufferGetPage(), BufferIsValid(), elog, ereport, errcode(), errmsg_internal(), ERROR, InvalidBuffer, P_FIRSTDATAKEY, P_IGNORE, P_NONE, P_RIGHTMOST, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), and RelationGetRelationName.

Referenced by _bt_endpoint(), and _bt_insert_parent().

_bt_initialize_more_data()

static void _bt_initialize_more_data ( BTScanOpaque  so, ScanDirection  dir  )

inlinestatic

Definition at line 2650 of file nbtsearch.c.

{
    so->currPos.dir = dir;
    if (so->needPrimScan)
    {
        Assert(so->numArrayKeys);
 
        so->currPos.moreLeft = true;
        so->currPos.moreRight = true;
        so->needPrimScan = false;
    }
    else if (ScanDirectionIsForward(dir))
    {
        so->currPos.moreLeft = false;
        so->currPos.moreRight = true;
    }
    else
    {
        so->currPos.moreLeft = true;
        so->currPos.moreRight = false;
    }
    so->numKilled = 0;          /* just paranoia */
    so->markItemIndex = -1;     /* ditto */
}

References Assert, BTScanOpaqueData::currPos, BTScanPosData::dir, BTScanOpaqueData::markItemIndex, BTScanPosData::moreLeft, BTScanPosData::moreRight, BTScanOpaqueData::needPrimScan, BTScanOpaqueData::numArrayKeys, BTScanOpaqueData::numKilled, and ScanDirectionIsForward.

Referenced by _bt_endpoint(), _bt_first(), and _bt_parallel_readpage().

_bt_moveright()

Buffer _bt_moveright	(	Relation	rel,
		Relation	heaprel,
		BTScanInsert	key,
		Buffer	buf,
		bool	forupdate,
		BTStack	stack,
		int	access
	)

Definition at line 235 of file nbtsearch.c.

{
    Page        page;
    BTPageOpaque opaque;
    int32       cmpval;
 
    Assert(!forupdate || heaprel != NULL);
 
    /*
     * When nextkey = false (normal case): if the scan key that brought us to
     * this page is > the high key stored on the page, then the page has split
     * and we need to move right.  (pg_upgrade'd !heapkeyspace indexes could
     * have some duplicates to the right as well as the left, but that's
     * something that's only ever dealt with on the leaf level, after
     * _bt_search has found an initial leaf page.)
     *
     * When nextkey = true: move right if the scan key is >= page's high key.
     * (Note that key.scantid cannot be set in this case.)
     *
     * The page could even have split more than once, so scan as far as
     * needed.
     *
     * We also have to move right if we followed a link that brought us to a
     * dead page.
     */
    cmpval = key->nextkey ? 0 : 1;
 
    for (;;)
    {
        page = BufferGetPage(buf);
        opaque = BTPageGetOpaque(page);
 
        if (P_RIGHTMOST(opaque))
            break;
 
        /*
         * Finish any incomplete splits we encounter along the way.
         */
        if (forupdate && P_INCOMPLETE_SPLIT(opaque))
        {
            BlockNumber blkno = BufferGetBlockNumber(buf);
 
            /* upgrade our lock if necessary */
            if (access == BT_READ)
            {
                _bt_unlockbuf(rel, buf);
                _bt_lockbuf(rel, buf, BT_WRITE);
            }
 
            if (P_INCOMPLETE_SPLIT(opaque))
                _bt_finish_split(rel, heaprel, buf, stack);
            else
                _bt_relbuf(rel, buf);
 
            /* re-acquire the lock in the right mode, and re-check */
            buf = _bt_getbuf(rel, blkno, access);
            continue;
        }
 
        if (P_IGNORE(opaque) || _bt_compare(rel, key, page, P_HIKEY) >= cmpval)
        {
            /* step right one page */
            buf = _bt_relandgetbuf(rel, buf, opaque->btpo_next, access);
            continue;
        }
        else
            break;
    }
 
    if (P_IGNORE(opaque))
        elog(ERROR, "fell off the end of index \"%s\"",
             RelationGetRelationName(rel));
 
    return buf;
}

References _bt_compare(), _bt_finish_split(), _bt_getbuf(), _bt_lockbuf(), _bt_relandgetbuf(), _bt_relbuf(), _bt_unlockbuf(), Assert, BT_READ, BT_WRITE, BTPageGetOpaque, BTPageOpaqueData::btpo_next, buf, BufferGetBlockNumber(), BufferGetPage(), elog, ERROR, sort-test::key, P_HIKEY, P_IGNORE, P_INCOMPLETE_SPLIT, P_RIGHTMOST, and RelationGetRelationName.

Referenced by _bt_search().

_bt_next()

bool _bt_next	(	IndexScanDesc	scan,
		ScanDirection	dir
	)

Definition at line 1492 of file nbtsearch.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    BTScanPosItem *currItem;
 
    /*
     * Advance to next tuple on current page; or if there's no more, try to
     * step to the next page with data.
     */
    if (ScanDirectionIsForward(dir))
    {
        if (++so->currPos.itemIndex > so->currPos.lastItem)
        {
            if (!_bt_steppage(scan, dir))
                return false;
        }
    }
    else
    {
        if (--so->currPos.itemIndex < so->currPos.firstItem)
        {
            if (!_bt_steppage(scan, dir))
                return false;
        }
    }
 
    /* OK, itemIndex says what to return */
    currItem = &so->currPos.items[so->currPos.itemIndex];
    scan->xs_heaptid = currItem->heapTid;
    if (scan->xs_want_itup)
        scan->xs_itup = (IndexTuple) (so->currTuples + currItem->tupleOffset);
 
    return true;
}

References _bt_steppage(), BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, BTScanPosData::firstItem, if(), BTScanPosData::itemIndex, BTScanPosData::items, BTScanPosData::lastItem, IndexScanDescData::opaque, ScanDirectionIsForward, IndexScanDescData::xs_heaptid, IndexScanDescData::xs_itup, and IndexScanDescData::xs_want_itup.

Referenced by btgetbitmap(), and btgettuple().

_bt_parallel_readpage()

static bool _bt_parallel_readpage ( IndexScanDesc  scan, BlockNumber  blkno, ScanDirection  dir  )

static

Definition at line 2334 of file nbtsearch.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
 
    Assert(!so->needPrimScan);
 
    _bt_initialize_more_data(so, dir);
 
    if (!_bt_readnextpage(scan, blkno, dir))
        return false;
 
    /* We have at least one item to return as scan's next item */
    _bt_drop_lock_and_maybe_pin(scan, &so->currPos);
 
    return true;
}

References _bt_drop_lock_and_maybe_pin(), _bt_initialize_more_data(), _bt_readnextpage(), Assert, BTScanOpaqueData::currPos, BTScanOpaqueData::needPrimScan, and IndexScanDescData::opaque.

Referenced by _bt_first().

_bt_readnextpage()

static bool _bt_readnextpage ( IndexScanDesc  scan, BlockNumber  blkno, ScanDirection  dir  )

static

Definition at line 2168 of file nbtsearch.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    Relation    rel;
    Page        page;
    BTPageOpaque opaque;
    bool        status;
 
    rel = scan->indexRelation;
 
    if (ScanDirectionIsForward(dir))
    {
        for (;;)
        {
            /*
             * if we're at end of scan, give up and mark parallel scan as
             * done, so that all the workers can finish their scan
             */
            if (blkno == P_NONE || !so->currPos.moreRight)
            {
                _bt_parallel_done(scan);
                BTScanPosInvalidate(so->currPos);
                return false;
            }
            /* check for interrupts while we're not holding any buffer lock */
            CHECK_FOR_INTERRUPTS();
            /* step right one page */
            so->currPos.buf = _bt_getbuf(rel, blkno, BT_READ);
            page = BufferGetPage(so->currPos.buf);
            opaque = BTPageGetOpaque(page);
            /* check for deleted page */
            if (!P_IGNORE(opaque))
            {
                PredicateLockPage(rel, blkno, scan->xs_snapshot);
                /* see if there are any matches on this page */
                /* note that this will clear moreRight if we can stop */
                if (_bt_readpage(scan, dir, P_FIRSTDATAKEY(opaque), false))
                    break;
            }
            else if (scan->parallel_scan != NULL)
            {
                /* allow next page be processed by parallel worker */
                _bt_parallel_release(scan, opaque->btpo_next);
            }
 
            /* nope, keep going */
            if (scan->parallel_scan != NULL)
            {
                _bt_relbuf(rel, so->currPos.buf);
                status = _bt_parallel_seize(scan, &blkno, false);
                if (!status)
                {
                    BTScanPosInvalidate(so->currPos);
                    return false;
                }
            }
            else
            {
                blkno = opaque->btpo_next;
                _bt_relbuf(rel, so->currPos.buf);
            }
        }
    }
    else
    {
        /*
         * Should only happen in parallel cases, when some other backend
         * advanced the scan.
         */
        if (so->currPos.currPage != blkno)
        {
            BTScanPosUnpinIfPinned(so->currPos);
            so->currPos.currPage = blkno;
        }
 
        /*
         * Walk left to the next page with data.  This is much more complex
         * than the walk-right case because of the possibility that the page
         * to our left splits while we are in flight to it, plus the
         * possibility that the page we were on gets deleted after we leave
         * it.  See nbtree/README for details.
         *
         * It might be possible to rearrange this code to have less overhead
         * in pinning and locking, but that would require capturing the left
         * sibling block number when the page is initially read, and then
         * optimistically starting there (rather than pinning the page twice).
         * It is not clear that this would be worth the complexity.
         */
        if (BTScanPosIsPinned(so->currPos))
            _bt_lockbuf(rel, so->currPos.buf, BT_READ);
        else
            so->currPos.buf = _bt_getbuf(rel, so->currPos.currPage, BT_READ);
 
        for (;;)
        {
            /* Done if we know there are no matching keys to the left */
            if (!so->currPos.moreLeft)
            {
                _bt_relbuf(rel, so->currPos.buf);
                _bt_parallel_done(scan);
                BTScanPosInvalidate(so->currPos);
                return false;
            }
 
            /* Step to next physical page */
            so->currPos.buf = _bt_walk_left(rel, so->currPos.buf);
 
            /* if we're physically at end of index, return failure */
            if (so->currPos.buf == InvalidBuffer)
            {
                _bt_parallel_done(scan);
                BTScanPosInvalidate(so->currPos);
                return false;
            }
 
            /*
             * Okay, we managed to move left to a non-deleted page. Done if
             * it's not half-dead and contains matching tuples. Else loop back
             * and do it all again.
             */
            page = BufferGetPage(so->currPos.buf);
            opaque = BTPageGetOpaque(page);
            if (!P_IGNORE(opaque))
            {
                PredicateLockPage(rel, BufferGetBlockNumber(so->currPos.buf), scan->xs_snapshot);
                /* see if there are any matches on this page */
                /* note that this will clear moreLeft if we can stop */
                if (_bt_readpage(scan, dir, PageGetMaxOffsetNumber(page), false))
                    break;
            }
            else if (scan->parallel_scan != NULL)
            {
                /* allow next page be processed by parallel worker */
                _bt_parallel_release(scan, BufferGetBlockNumber(so->currPos.buf));
            }
 
            /*
             * For parallel scans, get the last page scanned as it is quite
             * possible that by the time we try to seize the scan, some other
             * worker has already advanced the scan to a different page.  We
             * must continue based on the latest page scanned by any worker.
             */
            if (scan->parallel_scan != NULL)
            {
                _bt_relbuf(rel, so->currPos.buf);
                status = _bt_parallel_seize(scan, &blkno, false);
                if (!status)
                {
                    BTScanPosInvalidate(so->currPos);
                    return false;
                }
                so->currPos.buf = _bt_getbuf(rel, blkno, BT_READ);
            }
        }
    }
 
    return true;
}

References _bt_getbuf(), _bt_lockbuf(), _bt_parallel_done(), _bt_parallel_release(), _bt_parallel_seize(), _bt_readpage(), _bt_relbuf(), _bt_walk_left(), BT_READ, BTPageGetOpaque, BTScanPosInvalidate, BTScanPosIsPinned, BTScanPosUnpinIfPinned, BTScanPosData::buf, BufferGetBlockNumber(), BufferGetPage(), CHECK_FOR_INTERRUPTS, BTScanPosData::currPage, BTScanOpaqueData::currPos, if(), IndexScanDescData::indexRelation, InvalidBuffer, BTScanPosData::moreLeft, BTScanPosData::moreRight, IndexScanDescData::opaque, P_FIRSTDATAKEY, P_IGNORE, P_NONE, PageGetMaxOffsetNumber(), IndexScanDescData::parallel_scan, PredicateLockPage(), ScanDirectionIsForward, and IndexScanDescData::xs_snapshot.

Referenced by _bt_parallel_readpage(), and _bt_steppage().

_bt_readpage()

static bool _bt_readpage ( IndexScanDesc  scan, ScanDirection  dir, OffsetNumber  offnum, bool  firstPage  )

static

Definition at line 1556 of file nbtsearch.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    Page        page;
    BTPageOpaque opaque;
    OffsetNumber minoff;
    OffsetNumber maxoff;
    BTReadPageState pstate;
    bool        arrayKeys;
    int         itemIndex,
                indnatts;
 
    /*
     * We must have the buffer pinned and locked, but the usual macro can't be
     * used here; this function is what makes it good for currPos.
     */
    Assert(BufferIsValid(so->currPos.buf));
 
    page = BufferGetPage(so->currPos.buf);
    opaque = BTPageGetOpaque(page);
 
    /* allow next page be processed by parallel worker */
    if (scan->parallel_scan)
    {
        if (ScanDirectionIsForward(dir))
            pstate.prev_scan_page = opaque->btpo_next;
        else
            pstate.prev_scan_page = BufferGetBlockNumber(so->currPos.buf);
 
        _bt_parallel_release(scan, pstate.prev_scan_page);
    }
 
    indnatts = IndexRelationGetNumberOfAttributes(scan->indexRelation);
    arrayKeys = so->numArrayKeys != 0;
    minoff = P_FIRSTDATAKEY(opaque);
    maxoff = PageGetMaxOffsetNumber(page);
 
    /* initialize page-level state that we'll pass to _bt_checkkeys */
    pstate.dir = dir;
    pstate.minoff = minoff;
    pstate.maxoff = maxoff;
    pstate.finaltup = NULL;
    pstate.page = page;
    pstate.offnum = InvalidOffsetNumber;
    pstate.skip = InvalidOffsetNumber;
    pstate.continuescan = true; /* default assumption */
    pstate.prechecked = false;
    pstate.firstmatch = false;
    pstate.rechecks = 0;
    pstate.targetdistance = 0;
 
    /*
     * We note the buffer's block number so that we can release the pin later.
     * This allows us to re-read the buffer if it is needed again for hinting.
     */
    so->currPos.currPage = BufferGetBlockNumber(so->currPos.buf);
 
    /*
     * We save the LSN of the page as we read it, so that we know whether it
     * safe to apply LP_DEAD hints to the page later.  This allows us to drop
     * the pin for MVCC scans, which allows vacuum to avoid blocking.
     */
    so->currPos.lsn = BufferGetLSNAtomic(so->currPos.buf);
 
    /*
     * we must save the page's right-link while scanning it; this tells us
     * where to step right to after we're done with these items.  There is no
     * corresponding need for the left-link, since splits always go right.
     */
    so->currPos.nextPage = opaque->btpo_next;
 
    /* initialize tuple workspace to empty */
    so->currPos.nextTupleOffset = 0;
 
    /*
     * Now that the current page has been made consistent, the macro should be
     * good.
     */
    Assert(BTScanPosIsPinned(so->currPos));
 
    /*
     * Prechecking the value of the continuescan flag for the last item on the
     * page (for backwards scan it will be the first item on a page).  If we
     * observe it to be true, then it should be true for all other items. This
     * allows us to do significant optimizations in the _bt_checkkeys()
     * function for all the items on the page.
     *
     * With the forward scan, we do this check for the last item on the page
     * instead of the high key.  It's relatively likely that the most
     * significant column in the high key will be different from the
     * corresponding value from the last item on the page.  So checking with
     * the last item on the page would give a more precise answer.
     *
     * We skip this for the first page read by each (primitive) scan, to avoid
     * slowing down point queries.  They typically don't stand to gain much
     * when the optimization can be applied, and are more likely to notice the
     * overhead of the precheck.
     *
     * The optimization is unsafe and must be avoided whenever _bt_checkkeys
     * just set a low-order required array's key to the best available match
     * for a truncated -inf attribute value from the prior page's high key
     * (array element 0 is always the best available match in this scenario).
     * It's quite likely that matches for array element 0 begin on this page,
     * but the start of matches won't necessarily align with page boundaries.
     * When the start of matches is somewhere in the middle of this page, it
     * would be wrong to treat page's final non-pivot tuple as representative.
     * Doing so might lead us to treat some of the page's earlier tuples as
     * being part of a group of tuples thought to satisfy the required keys.
     *
     * Note: Conversely, in the case where the scan's arrays just advanced
     * using the prior page's HIKEY _without_ advancement setting scanBehind,
     * the start of matches must be aligned with page boundaries, which makes
     * it safe to attempt the optimization here now.  It's also safe when the
     * prior page's HIKEY simply didn't need to advance any required array. In
     * both cases we can safely assume that the _first_ tuple from this page
     * must be >= the current set of array keys/equality constraints. And so
     * if the final tuple is == those same keys (and also satisfies any
     * required < or <= strategy scan keys) during the precheck, we can safely
     * assume that this must also be true of all earlier tuples from the page.
     */
    if (!firstPage && !so->scanBehind && minoff < maxoff)
    {
        ItemId      iid;
        IndexTuple  itup;
 
        iid = PageGetItemId(page, ScanDirectionIsForward(dir) ? maxoff : minoff);
        itup = (IndexTuple) PageGetItem(page, iid);
 
        /* Call with arrayKeys=false to avoid undesirable side-effects */
        _bt_checkkeys(scan, &pstate, false, itup, indnatts);
        pstate.prechecked = pstate.continuescan;
        pstate.continuescan = true; /* reset */
    }
 
    if (ScanDirectionIsForward(dir))
    {
        /* SK_SEARCHARRAY forward scans must provide high key up front */
        if (arrayKeys && !P_RIGHTMOST(opaque))
        {
            ItemId      iid = PageGetItemId(page, P_HIKEY);
 
            pstate.finaltup = (IndexTuple) PageGetItem(page, iid);
        }
 
        /* load items[] in ascending order */
        itemIndex = 0;
 
        offnum = Max(offnum, minoff);
 
        while (offnum <= maxoff)
        {
            ItemId      iid = PageGetItemId(page, offnum);
            IndexTuple  itup;
            bool        passes_quals;
 
            /*
             * If the scan specifies not to return killed tuples, then we
             * treat a killed tuple as not passing the qual
             */
            if (scan->ignore_killed_tuples && ItemIdIsDead(iid))
            {
                offnum = OffsetNumberNext(offnum);
                continue;
            }
 
            itup = (IndexTuple) PageGetItem(page, iid);
            Assert(!BTreeTupleIsPivot(itup));
 
            pstate.offnum = offnum;
            passes_quals = _bt_checkkeys(scan, &pstate, arrayKeys,
                                         itup, indnatts);
 
            /*
             * Check if we need to skip ahead to a later tuple (only possible
             * when the scan uses array keys)
             */
            if (arrayKeys && OffsetNumberIsValid(pstate.skip))
            {
                Assert(!passes_quals && pstate.continuescan);
                Assert(offnum < pstate.skip);
 
                offnum = pstate.skip;
                pstate.skip = InvalidOffsetNumber;
                continue;
            }
 
            if (passes_quals)
            {
                /* tuple passes all scan key conditions */
                pstate.firstmatch = true;
                if (!BTreeTupleIsPosting(itup))
                {
                    /* Remember it */
                    _bt_saveitem(so, itemIndex, offnum, itup);
                    itemIndex++;
                }
                else
                {
                    int         tupleOffset;
 
                    /*
                     * Set up state to return posting list, and remember first
                     * TID
                     */
                    tupleOffset =
                        _bt_setuppostingitems(so, itemIndex, offnum,
                                              BTreeTupleGetPostingN(itup, 0),
                                              itup);
                    itemIndex++;
                    /* Remember additional TIDs */
                    for (int i = 1; i < BTreeTupleGetNPosting(itup); i++)
                    {
                        _bt_savepostingitem(so, itemIndex, offnum,
                                            BTreeTupleGetPostingN(itup, i),
                                            tupleOffset);
                        itemIndex++;
                    }
                }
            }
            /* When !continuescan, there can't be any more matches, so stop */
            if (!pstate.continuescan)
                break;
 
            offnum = OffsetNumberNext(offnum);
        }
 
        /*
         * We don't need to visit page to the right when the high key
         * indicates that no more matches will be found there.
         *
         * Checking the high key like this works out more often than you might
         * think.  Leaf page splits pick a split point between the two most
         * dissimilar tuples (this is weighed against the need to evenly share
         * free space).  Leaf pages with high key attribute values that can
         * only appear on non-pivot tuples on the right sibling page are
         * common.
         */
        if (pstate.continuescan && !P_RIGHTMOST(opaque))
        {
            ItemId      iid = PageGetItemId(page, P_HIKEY);
            IndexTuple  itup = (IndexTuple) PageGetItem(page, iid);
            int         truncatt;
 
            truncatt = BTreeTupleGetNAtts(itup, scan->indexRelation);
            pstate.prechecked = false;  /* precheck didn't cover HIKEY */
            _bt_checkkeys(scan, &pstate, arrayKeys, itup, truncatt);
        }
 
        if (!pstate.continuescan)
            so->currPos.moreRight = false;
 
        Assert(itemIndex <= MaxTIDsPerBTreePage);
        so->currPos.firstItem = 0;
        so->currPos.lastItem = itemIndex - 1;
        so->currPos.itemIndex = 0;
    }
    else
    {
        /* SK_SEARCHARRAY backward scans must provide final tuple up front */
        if (arrayKeys && minoff <= maxoff && !P_LEFTMOST(opaque))
        {
            ItemId      iid = PageGetItemId(page, minoff);
 
            pstate.finaltup = (IndexTuple) PageGetItem(page, iid);
        }
 
        /* load items[] in descending order */
        itemIndex = MaxTIDsPerBTreePage;
 
        offnum = Min(offnum, maxoff);
 
        while (offnum >= minoff)
        {
            ItemId      iid = PageGetItemId(page, offnum);
            IndexTuple  itup;
            bool        tuple_alive;
            bool        passes_quals;
 
            /*
             * If the scan specifies not to return killed tuples, then we
             * treat a killed tuple as not passing the qual.  Most of the
             * time, it's a win to not bother examining the tuple's index
             * keys, but just skip to the next tuple (previous, actually,
             * since we're scanning backwards).  However, if this is the first
             * tuple on the page, we do check the index keys, to prevent
             * uselessly advancing to the page to the left.  This is similar
             * to the high key optimization used by forward scans.
             */
            if (scan->ignore_killed_tuples && ItemIdIsDead(iid))
            {
                Assert(offnum >= P_FIRSTDATAKEY(opaque));
                if (offnum > P_FIRSTDATAKEY(opaque))
                {
                    offnum = OffsetNumberPrev(offnum);
                    continue;
                }
 
                tuple_alive = false;
            }
            else
                tuple_alive = true;
 
            itup = (IndexTuple) PageGetItem(page, iid);
            Assert(!BTreeTupleIsPivot(itup));
 
            pstate.offnum = offnum;
            passes_quals = _bt_checkkeys(scan, &pstate, arrayKeys,
                                         itup, indnatts);
 
            /*
             * Check if we need to skip ahead to a later tuple (only possible
             * when the scan uses array keys)
             */
            if (arrayKeys && OffsetNumberIsValid(pstate.skip))
            {
                Assert(!passes_quals && pstate.continuescan);
                Assert(offnum > pstate.skip);
 
                offnum = pstate.skip;
                pstate.skip = InvalidOffsetNumber;
                continue;
            }
 
            if (passes_quals && tuple_alive)
            {
                /* tuple passes all scan key conditions */
                pstate.firstmatch = true;
                if (!BTreeTupleIsPosting(itup))
                {
                    /* Remember it */
                    itemIndex--;
                    _bt_saveitem(so, itemIndex, offnum, itup);
                }
                else
                {
                    int         tupleOffset;
 
                    /*
                     * Set up state to return posting list, and remember first
                     * TID.
                     *
                     * Note that we deliberately save/return items from
                     * posting lists in ascending heap TID order for backwards
                     * scans.  This allows _bt_killitems() to make a
                     * consistent assumption about the order of items
                     * associated with the same posting list tuple.
                     */
                    itemIndex--;
                    tupleOffset =
                        _bt_setuppostingitems(so, itemIndex, offnum,
                                              BTreeTupleGetPostingN(itup, 0),
                                              itup);
                    /* Remember additional TIDs */
                    for (int i = 1; i < BTreeTupleGetNPosting(itup); i++)
                    {
                        itemIndex--;
                        _bt_savepostingitem(so, itemIndex, offnum,
                                            BTreeTupleGetPostingN(itup, i),
                                            tupleOffset);
                    }
                }
            }
            if (!pstate.continuescan)
            {
                /* there can't be any more matches, so stop */
                so->currPos.moreLeft = false;
                break;
            }
 
            offnum = OffsetNumberPrev(offnum);
        }
 
        Assert(itemIndex >= 0);
        so->currPos.firstItem = itemIndex;
        so->currPos.lastItem = MaxTIDsPerBTreePage - 1;
        so->currPos.itemIndex = MaxTIDsPerBTreePage - 1;
    }
 
    return (so->currPos.firstItem <= so->currPos.lastItem);
}

References _bt_checkkeys(), _bt_parallel_release(), _bt_saveitem(), _bt_savepostingitem(), _bt_setuppostingitems(), Assert, BTPageGetOpaque, BTreeTupleGetNAtts, BTreeTupleGetNPosting(), BTreeTupleGetPostingN(), BTreeTupleIsPivot(), BTreeTupleIsPosting(), BTScanPosIsPinned, BTScanPosData::buf, BufferGetBlockNumber(), BufferGetLSNAtomic(), BufferGetPage(), BufferIsValid(), BTScanPosData::currPage, BTScanOpaqueData::currPos, BTScanPosData::firstItem, i, IndexScanDescData::ignore_killed_tuples, IndexScanDescData::indexRelation, IndexRelationGetNumberOfAttributes, InvalidOffsetNumber, ItemIdIsDead, BTScanPosData::itemIndex, BTScanPosData::lastItem, BTScanPosData::lsn, Max, MaxTIDsPerBTreePage, Min, BTScanPosData::moreLeft, BTScanPosData::moreRight, BTScanPosData::nextPage, BTScanPosData::nextTupleOffset, BTScanOpaqueData::numArrayKeys, OffsetNumberIsValid, OffsetNumberNext, OffsetNumberPrev, IndexScanDescData::opaque, P_FIRSTDATAKEY, P_HIKEY, P_LEFTMOST, P_RIGHTMOST, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), IndexScanDescData::parallel_scan, BTScanOpaqueData::scanBehind, and ScanDirectionIsForward.

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

_bt_saveitem()

static void _bt_saveitem ( BTScanOpaque  so, int  itemIndex, OffsetNumber  offnum, IndexTuple  itup  )

static

Definition at line 1940 of file nbtsearch.c.

{
    BTScanPosItem *currItem = &so->currPos.items[itemIndex];
 
    Assert(!BTreeTupleIsPivot(itup) && !BTreeTupleIsPosting(itup));
 
    currItem->heapTid = itup->t_tid;
    currItem->indexOffset = offnum;
    if (so->currTuples)
    {
        Size        itupsz = IndexTupleSize(itup);
 
        currItem->tupleOffset = so->currPos.nextTupleOffset;
        memcpy(so->currTuples + so->currPos.nextTupleOffset, itup, itupsz);
        so->currPos.nextTupleOffset += MAXALIGN(itupsz);
    }
}

References Assert, BTreeTupleIsPivot(), BTreeTupleIsPosting(), BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, BTScanPosItem::heapTid, BTScanPosItem::indexOffset, IndexTupleSize, BTScanPosData::items, MAXALIGN, BTScanPosData::nextTupleOffset, IndexTupleData::t_tid, and BTScanPosItem::tupleOffset.

Referenced by _bt_readpage().

_bt_savepostingitem()

static void _bt_savepostingitem ( BTScanOpaque  so, int  itemIndex, OffsetNumber  offnum, ItemPointer  heapTid, int  tupleOffset  )

inlinestatic

Definition at line 2008 of file nbtsearch.c.

{
    BTScanPosItem *currItem = &so->currPos.items[itemIndex];
 
    currItem->heapTid = *heapTid;
    currItem->indexOffset = offnum;
 
    /*
     * Have index-only scans return the same base IndexTuple for every TID
     * that originates from the same posting list
     */
    if (so->currTuples)
        currItem->tupleOffset = tupleOffset;
}

References BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, BTScanPosItem::heapTid, BTScanPosItem::indexOffset, BTScanPosData::items, and BTScanPosItem::tupleOffset.

Referenced by _bt_readpage().

_bt_search()

BTStack _bt_search	(	Relation	rel,
		Relation	heaprel,
		BTScanInsert	key,
		Buffer *	bufP,
		int	access
	)

Definition at line 96 of file nbtsearch.c.

{
    BTStack     stack_in = NULL;
    int         page_access = BT_READ;
 
    /* heaprel must be set whenever _bt_allocbuf is reachable */
    Assert(access == BT_READ || access == BT_WRITE);
    Assert(access == BT_READ || heaprel != NULL);
 
    /* Get the root page to start with */
    *bufP = _bt_getroot(rel, heaprel, access);
 
    /* If index is empty and access = BT_READ, no root page is created. */
    if (!BufferIsValid(*bufP))
        return (BTStack) NULL;
 
    /* Loop iterates once per level descended in the tree */
    for (;;)
    {
        Page        page;
        BTPageOpaque opaque;
        OffsetNumber offnum;
        ItemId      itemid;
        IndexTuple  itup;
        BlockNumber child;
        BTStack     new_stack;
 
        /*
         * Race -- the page we just grabbed may have split since we read its
         * downlink in its parent page (or the metapage).  If it has, we may
         * need to move right to its new sibling.  Do that.
         *
         * In write-mode, allow _bt_moveright to finish any incomplete splits
         * along the way.  Strictly speaking, we'd only need to finish an
         * incomplete split on the leaf page we're about to insert to, not on
         * any of the upper levels (internal pages with incomplete splits are
         * also taken care of in _bt_getstackbuf).  But this is a good
         * opportunity to finish splits of internal pages too.
         */
        *bufP = _bt_moveright(rel, heaprel, key, *bufP, (access == BT_WRITE),
                              stack_in, page_access);
 
        /* if this is a leaf page, we're done */
        page = BufferGetPage(*bufP);
        opaque = BTPageGetOpaque(page);
        if (P_ISLEAF(opaque))
            break;
 
        /*
         * Find the appropriate pivot tuple on this page.  Its downlink points
         * to the child page that we're about to descend to.
         */
        offnum = _bt_binsrch(rel, key, *bufP);
        itemid = PageGetItemId(page, offnum);
        itup = (IndexTuple) PageGetItem(page, itemid);
        Assert(BTreeTupleIsPivot(itup) || !key->heapkeyspace);
        child = BTreeTupleGetDownLink(itup);
 
        /*
         * We need to save the location of the pivot tuple we chose in a new
         * stack entry for this page/level.  If caller ends up splitting a
         * page one level down, it usually ends up inserting a new pivot
         * tuple/downlink immediately after the location recorded here.
         */
        new_stack = (BTStack) palloc(sizeof(BTStackData));
        new_stack->bts_blkno = BufferGetBlockNumber(*bufP);
        new_stack->bts_offset = offnum;
        new_stack->bts_parent = stack_in;
 
        /*
         * Page level 1 is lowest non-leaf page level prior to leaves.  So, if
         * we're on the level 1 and asked to lock leaf page in write mode,
         * then lock next page in write mode, because it must be a leaf.
         */
        if (opaque->btpo_level == 1 && access == BT_WRITE)
            page_access = BT_WRITE;
 
        /* drop the read lock on the page, then acquire one on its child */
        *bufP = _bt_relandgetbuf(rel, *bufP, child, page_access);
 
        /* okay, all set to move down a level */
        stack_in = new_stack;
    }
 
    /*
     * If we're asked to lock leaf in write mode, but didn't manage to, then
     * relock.  This should only happen when the root page is a leaf page (and
     * the only page in the index other than the metapage).
     */
    if (access == BT_WRITE && page_access == BT_READ)
    {
        /* trade in our read lock for a write lock */
        _bt_unlockbuf(rel, *bufP);
        _bt_lockbuf(rel, *bufP, BT_WRITE);
 
        /*
         * Race -- the leaf page may have split after we dropped the read lock
         * but before we acquired a write lock.  If it has, we may need to
         * move right to its new sibling.  Do that.
         */
        *bufP = _bt_moveright(rel, heaprel, key, *bufP, true, stack_in, BT_WRITE);
    }
 
    return stack_in;
}

References _bt_binsrch(), _bt_getroot(), _bt_lockbuf(), _bt_moveright(), _bt_relandgetbuf(), _bt_unlockbuf(), Assert, BT_READ, BT_WRITE, BTPageGetOpaque, BTPageOpaqueData::btpo_level, BTreeTupleGetDownLink(), BTreeTupleIsPivot(), BTStackData::bts_blkno, BTStackData::bts_offset, BTStackData::bts_parent, BufferGetBlockNumber(), BufferGetPage(), BufferIsValid(), sort-test::key, P_ISLEAF, PageGetItem(), PageGetItemId(), and palloc().

Referenced by _bt_first(), _bt_pagedel(), _bt_search_insert(), and bt_rootdescend().

_bt_setuppostingitems()

static int _bt_setuppostingitems ( BTScanOpaque  so, int  itemIndex, OffsetNumber  offnum, ItemPointer  heapTid, IndexTuple  itup  )

static

Definition at line 1970 of file nbtsearch.c.

{
    BTScanPosItem *currItem = &so->currPos.items[itemIndex];
 
    Assert(BTreeTupleIsPosting(itup));
 
    currItem->heapTid = *heapTid;
    currItem->indexOffset = offnum;
    if (so->currTuples)
    {
        /* Save base IndexTuple (truncate posting list) */
        IndexTuple  base;
        Size        itupsz = BTreeTupleGetPostingOffset(itup);
 
        itupsz = MAXALIGN(itupsz);
        currItem->tupleOffset = so->currPos.nextTupleOffset;
        base = (IndexTuple) (so->currTuples + so->currPos.nextTupleOffset);
        memcpy(base, itup, itupsz);
        /* Defensively reduce work area index tuple header size */
        base->t_info &= ~INDEX_SIZE_MASK;
        base->t_info |= itupsz;
        so->currPos.nextTupleOffset += itupsz;
 
        return currItem->tupleOffset;
    }
 
    return 0;
}

References Assert, BTreeTupleGetPostingOffset(), BTreeTupleIsPosting(), BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, BTScanPosItem::heapTid, INDEX_SIZE_MASK, BTScanPosItem::indexOffset, BTScanPosData::items, MAXALIGN, BTScanPosData::nextTupleOffset, IndexTupleData::t_info, and BTScanPosItem::tupleOffset.

Referenced by _bt_readpage().

_bt_steppage()

static bool _bt_steppage ( IndexScanDesc  scan, ScanDirection  dir  )

static

Definition at line 2036 of file nbtsearch.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    BlockNumber blkno = InvalidBlockNumber;
    bool        status;
 
    Assert(BTScanPosIsValid(so->currPos));
 
    /* Before leaving current page, deal with any killed items */
    if (so->numKilled > 0)
        _bt_killitems(scan);
 
    /*
     * Before we modify currPos, make a copy of the page data if there was a
     * mark position that needs it.
     */
    if (so->markItemIndex >= 0)
    {
        /* bump pin on current buffer for assignment to mark buffer */
        if (BTScanPosIsPinned(so->currPos))
            IncrBufferRefCount(so->currPos.buf);
        memcpy(&so->markPos, &so->currPos,
               offsetof(BTScanPosData, items[1]) +
               so->currPos.lastItem * sizeof(BTScanPosItem));
        if (so->markTuples)
            memcpy(so->markTuples, so->currTuples,
                   so->currPos.nextTupleOffset);
        so->markPos.itemIndex = so->markItemIndex;
        so->markItemIndex = -1;
 
        /*
         * If we're just about to start the next primitive index scan
         * (possible with a scan that has arrays keys, and needs to skip to
         * continue in the current scan direction), moreLeft/moreRight only
         * indicate the end of the current primitive index scan.  They must
         * never be taken to indicate that the top-level index scan has ended
         * (that would be wrong).
         *
         * We could handle this case by treating the current array keys as
         * markPos state.  But depending on the current array state like this
         * would add complexity.  Instead, we just unset markPos's copy of
         * moreRight or moreLeft (whichever might be affected), while making
         * btrestpos reset the scan's arrays to their initial scan positions.
         * In effect, btrestpos leaves advancing the arrays up to the first
         * _bt_readpage call (that takes place after it has restored markPos).
         */
        Assert(so->markPos.dir == dir);
        if (so->needPrimScan)
        {
            if (ScanDirectionIsForward(dir))
                so->markPos.moreRight = true;
            else
                so->markPos.moreLeft = true;
        }
    }
 
    if (ScanDirectionIsForward(dir))
    {
        /* Walk right to the next page with data */
        if (scan->parallel_scan != NULL)
        {
            /*
             * Seize the scan to get the next block number; if the scan has
             * ended already, bail out.
             */
            status = _bt_parallel_seize(scan, &blkno, false);
            if (!status)
            {
                /* release the previous buffer, if pinned */
                BTScanPosUnpinIfPinned(so->currPos);
                BTScanPosInvalidate(so->currPos);
                return false;
            }
        }
        else
        {
            /* Not parallel, so use the previously-saved nextPage link. */
            blkno = so->currPos.nextPage;
        }
 
        /* Remember we left a page with data */
        so->currPos.moreLeft = true;
 
        /* release the previous buffer, if pinned */
        BTScanPosUnpinIfPinned(so->currPos);
    }
    else
    {
        /* Remember we left a page with data */
        so->currPos.moreRight = true;
 
        if (scan->parallel_scan != NULL)
        {
            /*
             * Seize the scan to get the current block number; if the scan has
             * ended already, bail out.
             */
            status = _bt_parallel_seize(scan, &blkno, false);
            BTScanPosUnpinIfPinned(so->currPos);
            if (!status)
            {
                BTScanPosInvalidate(so->currPos);
                return false;
            }
        }
        else
        {
            /* Not parallel, so just use our own notion of the current page */
            blkno = so->currPos.currPage;
        }
    }
 
    if (!_bt_readnextpage(scan, blkno, dir))
        return false;
 
    /* We have at least one item to return as scan's next item */
    _bt_drop_lock_and_maybe_pin(scan, &so->currPos);
 
    return true;
}

References _bt_drop_lock_and_maybe_pin(), _bt_killitems(), _bt_parallel_seize(), _bt_readnextpage(), Assert, BTScanPosInvalidate, BTScanPosIsPinned, BTScanPosIsValid, BTScanPosUnpinIfPinned, BTScanPosData::buf, BTScanPosData::currPage, BTScanOpaqueData::currPos, BTScanOpaqueData::currTuples, BTScanPosData::dir, IncrBufferRefCount(), InvalidBlockNumber, BTScanPosData::itemIndex, items, BTScanPosData::lastItem, BTScanOpaqueData::markItemIndex, BTScanOpaqueData::markPos, BTScanOpaqueData::markTuples, BTScanPosData::moreLeft, BTScanPosData::moreRight, BTScanOpaqueData::needPrimScan, BTScanPosData::nextPage, BTScanPosData::nextTupleOffset, BTScanOpaqueData::numKilled, IndexScanDescData::opaque, IndexScanDescData::parallel_scan, and ScanDirectionIsForward.

Referenced by _bt_endpoint(), _bt_first(), and _bt_next().

_bt_walk_left()

static Buffer _bt_walk_left ( Relation  rel, Buffer  buf  )

static

Definition at line 2365 of file nbtsearch.c.

{
    Page        page;
    BTPageOpaque opaque;
 
    page = BufferGetPage(buf);
    opaque = BTPageGetOpaque(page);
 
    for (;;)
    {
        BlockNumber obknum;
        BlockNumber lblkno;
        BlockNumber blkno;
        int         tries;
 
        /* if we're at end of tree, release buf and return failure */
        if (P_LEFTMOST(opaque))
        {
            _bt_relbuf(rel, buf);
            break;
        }
        /* remember original page we are stepping left from */
        obknum = BufferGetBlockNumber(buf);
        /* step left */
        blkno = lblkno = opaque->btpo_prev;
        _bt_relbuf(rel, buf);
        /* check for interrupts while we're not holding any buffer lock */
        CHECK_FOR_INTERRUPTS();
        buf = _bt_getbuf(rel, blkno, BT_READ);
        page = BufferGetPage(buf);
        opaque = BTPageGetOpaque(page);
 
        /*
         * If this isn't the page we want, walk right till we find what we
         * want --- but go no more than four hops (an arbitrary limit). If we
         * don't find the correct page by then, the most likely bet is that
         * the original page got deleted and isn't in the sibling chain at all
         * anymore, not that its left sibling got split more than four times.
         *
         * Note that it is correct to test P_ISDELETED not P_IGNORE here,
         * because half-dead pages are still in the sibling chain.
         */
        tries = 0;
        for (;;)
        {
            if (!P_ISDELETED(opaque) && opaque->btpo_next == obknum)
            {
                /* Found desired page, return it */
                return buf;
            }
            if (P_RIGHTMOST(opaque) || ++tries > 4)
                break;
            blkno = opaque->btpo_next;
            buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
            page = BufferGetPage(buf);
            opaque = BTPageGetOpaque(page);
        }
 
        /* Return to the original page to see what's up */
        buf = _bt_relandgetbuf(rel, buf, obknum, BT_READ);
        page = BufferGetPage(buf);
        opaque = BTPageGetOpaque(page);
        if (P_ISDELETED(opaque))
        {
            /*
             * It was deleted.  Move right to first nondeleted page (there
             * must be one); that is the page that has acquired the deleted
             * one's keyspace, so stepping left from it will take us where we
             * want to be.
             */
            for (;;)
            {
                if (P_RIGHTMOST(opaque))
                    elog(ERROR, "fell off the end of index \"%s\"",
                         RelationGetRelationName(rel));
                blkno = opaque->btpo_next;
                buf = _bt_relandgetbuf(rel, buf, blkno, BT_READ);
                page = BufferGetPage(buf);
                opaque = BTPageGetOpaque(page);
                if (!P_ISDELETED(opaque))
                    break;
            }
 
            /*
             * Now return to top of loop, resetting obknum to point to this
             * nondeleted page, and try again.
             */
        }
        else
        {
            /*
             * It wasn't deleted; the explanation had better be that the page
             * to the left got split or deleted. Without this check, we'd go
             * into an infinite loop if there's anything wrong.
             */
            if (opaque->btpo_prev == lblkno)
                elog(ERROR, "could not find left sibling of block %u in index \"%s\"",
                     obknum, RelationGetRelationName(rel));
            /* Okay to try again with new lblkno value */
        }
    }
 
    return InvalidBuffer;
}

References _bt_getbuf(), _bt_relandgetbuf(), _bt_relbuf(), BT_READ, BTPageGetOpaque, BTPageOpaqueData::btpo_next, BTPageOpaqueData::btpo_prev, buf, BufferGetBlockNumber(), BufferGetPage(), CHECK_FOR_INTERRUPTS, elog, ERROR, InvalidBuffer, P_ISDELETED, P_LEFTMOST, P_RIGHTMOST, and RelationGetRelationName.

Referenced by _bt_readnextpage().