#include "postgres.h"
#include <time.h>
#include "access/nbtree.h"
#include "access/reloptions.h"
#include "commands/progress.h"
#include "miscadmin.h"
#include "utils/datum.h"
#include "utils/lsyscache.h"

Include dependency graph for nbtutils.c:

Data Structures
struct	BTOneVacInfo

struct	BTVacInfo

Macros
#define	LOOK_AHEAD_REQUIRED_RECHECKS 3

#define	LOOK_AHEAD_DEFAULT_DISTANCE 5

Typedefs
typedef struct BTOneVacInfo	BTOneVacInfo

typedef struct BTVacInfo	BTVacInfo

Functions
static int32	_bt_compare_array_skey (FmgrInfo *orderproc, Datum tupdatum, bool tupnull, Datum arrdatum, ScanKey cur)

static bool	_bt_advance_array_keys_increment (IndexScanDesc scan, ScanDirection dir)

static void	_bt_rewind_nonrequired_arrays (IndexScanDesc scan, ScanDirection dir)

static bool	_bt_tuple_before_array_skeys (IndexScanDesc scan, ScanDirection dir, IndexTuple tuple, TupleDesc tupdesc, int tupnatts, bool readpagetup, int sktrig, bool *scanBehind)

static bool	_bt_advance_array_keys (IndexScanDesc scan, BTReadPageState *pstate, IndexTuple tuple, int tupnatts, TupleDesc tupdesc, int sktrig, bool sktrig_required)

static bool	_bt_check_compare (IndexScanDesc scan, ScanDirection dir, IndexTuple tuple, int tupnatts, TupleDesc tupdesc, bool advancenonrequired, bool prechecked, bool firstmatch, bool continuescan, int ikey)

static bool	_bt_check_rowcompare (ScanKey skey, IndexTuple tuple, int tupnatts, TupleDesc tupdesc, ScanDirection dir, bool *continuescan)

static void	_bt_checkkeys_look_ahead (IndexScanDesc scan, BTReadPageState *pstate, int tupnatts, TupleDesc tupdesc)

static int	_bt_keep_natts (Relation rel, IndexTuple lastleft, IndexTuple firstright, BTScanInsert itup_key)

BTScanInsert	_bt_mkscankey (Relation rel, IndexTuple itup)

void	_bt_freestack (BTStack stack)

int	_bt_binsrch_array_skey (FmgrInfo orderproc, bool cur_elem_trig, ScanDirection dir, Datum tupdatum, bool tupnull, BTArrayKeyInfo array, ScanKey cur, int32 *set_elem_result)

void	_bt_start_array_keys (IndexScanDesc scan, ScanDirection dir)

bool	_bt_start_prim_scan (IndexScanDesc scan, ScanDirection dir)

bool	_bt_checkkeys (IndexScanDesc scan, BTReadPageState *pstate, bool arrayKeys, IndexTuple tuple, int tupnatts)

bool	_bt_oppodir_checkkeys (IndexScanDesc scan, ScanDirection dir, IndexTuple finaltup)

void	_bt_killitems (IndexScanDesc scan)

BTCycleId	_bt_vacuum_cycleid (Relation rel)

BTCycleId	_bt_start_vacuum (Relation rel)

void	_bt_end_vacuum (Relation rel)

void	_bt_end_vacuum_callback (int code, Datum arg)

Size	BTreeShmemSize (void)

void	BTreeShmemInit (void)

bytea *	btoptions (Datum reloptions, bool validate)

bool	btproperty (Oid index_oid, int attno, IndexAMProperty prop, const char propname, bool res, bool *isnull)

char *	btbuildphasename (int64 phasenum)

IndexTuple	_bt_truncate (Relation rel, IndexTuple lastleft, IndexTuple firstright, BTScanInsert itup_key)

int	_bt_keep_natts_fast (Relation rel, IndexTuple lastleft, IndexTuple firstright)

bool	_bt_check_natts (Relation rel, bool heapkeyspace, Page page, OffsetNumber offnum)

void	_bt_check_third_page (Relation rel, Relation heap, bool needheaptidspace, Page page, IndexTuple newtup)

bool	_bt_allequalimage (Relation rel, bool debugmessage)

Variables
static BTVacInfo *	btvacinfo

Macro Definition Documentation

◆ LOOK_AHEAD_DEFAULT_DISTANCE

#define LOOK_AHEAD_DEFAULT_DISTANCE 5

Definition at line 28 of file nbtutils.c.

◆ LOOK_AHEAD_REQUIRED_RECHECKS

#define LOOK_AHEAD_REQUIRED_RECHECKS 3

Definition at line 27 of file nbtutils.c.

Typedef Documentation

◆ BTOneVacInfo

typedef struct BTOneVacInfo BTOneVacInfo

◆ BTVacInfo

typedef struct BTVacInfo BTVacInfo

Function Documentation

◆ _bt_advance_array_keys()

static bool _bt_advance_array_keys	(	IndexScanDesc	scan,
		BTReadPageState *	pstate,
		IndexTuple	tuple,
		int	tupnatts,
		TupleDesc	tupdesc,
		int	sktrig,
		bool	sktrig_required
	)

static

Definition at line 863 of file nbtutils.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    Relation    rel = scan->indexRelation;
    ScanDirection dir = so->currPos.dir;
    int         arrayidx = 0;
    bool        beyond_end_advance = false,
                has_required_opposite_direction_only = false,
                oppodir_inequality_sktrig = false,
                all_required_satisfied = true,
                all_satisfied = true;
 
    /*
     * Unset so->scanBehind (and so->oppositeDirCheck) in case they're still
     * set from back when we dealt with the previous page's high key/finaltup
     */
    so->scanBehind = so->oppositeDirCheck = false;
 
    if (sktrig_required)
    {
        /*
         * Precondition array state assertion
         */
        Assert(!_bt_tuple_before_array_skeys(scan, dir, tuple, tupdesc,
                                             tupnatts, false, 0, NULL));
 
        /*
         * Required scan key wasn't satisfied, so required arrays will have to
         * advance.  Invalidate page-level state that tracks whether the
         * scan's required-in-opposite-direction-only keys are known to be
         * satisfied by page's remaining tuples.
         */
        pstate->firstmatch = false;
 
        /* Shouldn't have to invalidate 'prechecked', though */
        Assert(!pstate->prechecked);
 
        /*
         * Once we return we'll have a new set of required array keys, so
         * reset state used by "look ahead" optimization
         */
        pstate->rechecks = 0;
        pstate->targetdistance = 0;
    }
 
    Assert(_bt_verify_keys_with_arraykeys(scan));
 
    for (int ikey = 0; ikey < so->numberOfKeys; ikey++)
    {
        ScanKey     cur = so->keyData + ikey;
        BTArrayKeyInfo *array = NULL;
        Datum       tupdatum;
        bool        required = false,
                    required_opposite_direction_only = false,
                    tupnull;
        int32       result;
        int         set_elem = 0;
 
        if (cur->sk_strategy == BTEqualStrategyNumber)
        {
            /* Manage array state */
            if (cur->sk_flags & SK_SEARCHARRAY)
            {
                array = &so->arrayKeys[arrayidx++];
                Assert(array->scan_key == ikey);
            }
        }
        else
        {
            /*
             * Are any inequalities required in the opposite direction only
             * present here?
             */
            if (((ScanDirectionIsForward(dir) &&
                  (cur->sk_flags & (SK_BT_REQBKWD))) ||
                 (ScanDirectionIsBackward(dir) &&
                  (cur->sk_flags & (SK_BT_REQFWD)))))
                has_required_opposite_direction_only =
                    required_opposite_direction_only = true;
        }
 
        /* Optimization: skip over known-satisfied scan keys */
        if (ikey < sktrig)
            continue;
 
        if (cur->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD))
        {
            Assert(sktrig_required);
 
            required = true;
 
            if (cur->sk_attno > tupnatts)
            {
                /* Set this just like _bt_tuple_before_array_skeys */
                Assert(sktrig < ikey);
                so->scanBehind = true;
            }
        }
 
        /*
         * Handle a required non-array scan key that the initial call to
         * _bt_check_compare indicated triggered array advancement, if any.
         *
         * The non-array scan key's strategy will be <, <=, or = during a
         * forwards scan (or any one of =, >=, or > during a backwards scan).
         * It follows that the corresponding tuple attribute's value must now
         * be either > or >= the scan key value (for backwards scans it must
         * be either < or <= that value).
         *
         * If this is a required equality strategy scan key, this is just an
         * optimization; _bt_tuple_before_array_skeys already confirmed that
         * this scan key places us ahead of caller's tuple.  There's no need
         * to repeat that work now.  (The same underlying principle also gets
         * applied by the cur_elem_trig optimization used to speed up searches
         * for the next array element.)
         *
         * If this is a required inequality strategy scan key, we _must_ rely
         * on _bt_check_compare like this; we aren't capable of directly
         * evaluating required inequality strategy scan keys here, on our own.
         */
        if (ikey == sktrig && !array)
        {
            Assert(sktrig_required && required && all_required_satisfied);
 
            /* Use "beyond end" advancement.  See below for an explanation. */
            beyond_end_advance = true;
            all_satisfied = all_required_satisfied = false;
 
            /*
             * Set a flag that remembers that this was an inequality required
             * in the opposite scan direction only, that nevertheless
             * triggered the call here.
             *
             * This only happens when an inequality operator (which must be
             * strict) encounters a group of NULLs that indicate the end of
             * non-NULL values for tuples in the current scan direction.
             */
            if (unlikely(required_opposite_direction_only))
                oppodir_inequality_sktrig = true;
 
            continue;
        }
 
        /*
         * Nothing more for us to do with an inequality strategy scan key that
         * wasn't the one that _bt_check_compare stopped on, though.
         *
         * Note: if our later call to _bt_check_compare (to recheck caller's
         * tuple) sets continuescan=false due to finding this same inequality
         * unsatisfied (possible when it's required in the scan direction),
         * we'll deal with it via a recursive "second pass" call.
         */
        else if (cur->sk_strategy != BTEqualStrategyNumber)
            continue;
 
        /*
         * Nothing for us to do with an equality strategy scan key that isn't
         * marked required, either -- unless it's a non-required array
         */
        else if (!required && !array)
            continue;
 
        /*
         * Here we perform steps for all array scan keys after a required
         * array scan key whose binary search triggered "beyond end of array
         * element" array advancement due to encountering a tuple attribute
         * value > the closest matching array key (or < for backwards scans).
         */
        if (beyond_end_advance)
        {
            int         final_elem_dir;
 
            if (ScanDirectionIsBackward(dir) || !array)
                final_elem_dir = 0;
            else
                final_elem_dir = array->num_elems - 1;
 
            if (array && array->cur_elem != final_elem_dir)
            {
                array->cur_elem = final_elem_dir;
                cur->sk_argument = array->elem_values[final_elem_dir];
            }
 
            continue;
        }
 
        /*
         * Here we perform steps for all array scan keys after a required
         * array scan key whose tuple attribute was < the closest matching
         * array key when we dealt with it (or > for backwards scans).
         *
         * This earlier required array key already puts us ahead of caller's
         * tuple in the key space (for the current scan direction).  We must
         * make sure that subsequent lower-order array keys do not put us too
         * far ahead (ahead of tuples that have yet to be seen by our caller).
         * For example, when a tuple "(a, b) = (42, 5)" advances the array
         * keys on "a" from 40 to 45, we must also set "b" to whatever the
         * first array element for "b" is.  It would be wrong to allow "b" to
         * be set based on the tuple value.
         *
         * Perform the same steps with truncated high key attributes.  You can
         * think of this as a "binary search" for the element closest to the
         * value -inf.  Again, the arrays must never get ahead of the scan.
         */
        if (!all_required_satisfied || cur->sk_attno > tupnatts)
        {
            int         first_elem_dir;
 
            if (ScanDirectionIsForward(dir) || !array)
                first_elem_dir = 0;
            else
                first_elem_dir = array->num_elems - 1;
 
            if (array && array->cur_elem != first_elem_dir)
            {
                array->cur_elem = first_elem_dir;
                cur->sk_argument = array->elem_values[first_elem_dir];
            }
 
            continue;
        }
 
        /*
         * Search in scankey's array for the corresponding tuple attribute
         * value from caller's tuple
         */
        tupdatum = index_getattr(tuple, cur->sk_attno, tupdesc, &tupnull);
 
        if (array)
        {
            bool        cur_elem_trig = (sktrig_required && ikey == sktrig);
 
            /*
             * Binary search for closest match that's available from the array
             */
            set_elem = _bt_binsrch_array_skey(&so->orderProcs[ikey],
                                              cur_elem_trig, dir,
                                              tupdatum, tupnull, array, cur,
                                              &result);
 
            Assert(set_elem >= 0 && set_elem < array->num_elems);
        }
        else
        {
            Assert(sktrig_required && required);
 
            /*
             * This is a required non-array equality strategy scan key, which
             * we'll treat as a degenerate single element array.
             *
             * This scan key's imaginary "array" can't really advance, but it
             * can still roll over like any other array.  (Actually, this is
             * no different to real single value arrays, which never advance
             * without rolling over -- they can never truly advance, either.)
             */
            result = _bt_compare_array_skey(&so->orderProcs[ikey],
                                            tupdatum, tupnull,
                                            cur->sk_argument, cur);
        }
 
        /*
         * Consider "beyond end of array element" array advancement.
         *
         * When the tuple attribute value is > the closest matching array key
         * (or < in the backwards scan case), we need to ratchet this array
         * forward (backward) by one increment, so that caller's tuple ends up
         * being < final array value instead (or > final array value instead).
         * This process has to work for all of the arrays, not just this one:
         * it must "carry" to higher-order arrays when the set_elem that we
         * just found happens to be the final one for the scan's direction.
         * Incrementing (decrementing) set_elem itself isn't good enough.
         *
         * Our approach is to provisionally use set_elem as if it was an exact
         * match now, then set each later/less significant array to whatever
         * its final element is.  Once outside the loop we'll then "increment
         * this array's set_elem" by calling _bt_advance_array_keys_increment.
         * That way the process rolls over to higher order arrays as needed.
         *
         * Under this scheme any required arrays only ever ratchet forwards
         * (or backwards), and always do so to the maximum possible extent
         * that we can know will be safe without seeing the scan's next tuple.
         * We don't need any special handling for required scan keys that lack
         * a real array to advance, nor for redundant scan keys that couldn't
         * be eliminated by _bt_preprocess_keys.  It won't matter if some of
         * our "true" array scan keys (or even all of them) are non-required.
         */
        if (required &&
            ((ScanDirectionIsForward(dir) && result > 0) ||
             (ScanDirectionIsBackward(dir) && result < 0)))
            beyond_end_advance = true;
 
        Assert(all_required_satisfied && all_satisfied);
        if (result != 0)
        {
            /*
             * Track whether caller's tuple satisfies our new post-advancement
             * qual, for required scan keys, as well as for the entire set of
             * interesting scan keys (all required scan keys plus non-required
             * array scan keys are considered interesting.)
             */
            all_satisfied = false;
            if (required)
                all_required_satisfied = false;
            else
            {
                /*
                 * There's no need to advance the arrays using the best
                 * available match for a non-required array.  Give up now.
                 * (Though note that sktrig_required calls still have to do
                 * all the usual post-advancement steps, including the recheck
                 * call to _bt_check_compare.)
                 */
                break;
            }
        }
 
        /* Advance array keys, even when set_elem isn't an exact match */
        if (array && array->cur_elem != set_elem)
        {
            array->cur_elem = set_elem;
            cur->sk_argument = array->elem_values[set_elem];
        }
    }
 
    /*
     * Advance the array keys incrementally whenever "beyond end of array
     * element" array advancement happens, so that advancement will carry to
     * higher-order arrays (might exhaust all the scan's arrays instead, which
     * ends the top-level scan).
     */
    if (beyond_end_advance && !_bt_advance_array_keys_increment(scan, dir))
        goto end_toplevel_scan;
 
    Assert(_bt_verify_keys_with_arraykeys(scan));
 
    /*
     * Does tuple now satisfy our new qual?  Recheck with _bt_check_compare.
     *
     * Calls triggered by an unsatisfied required scan key, whose tuple now
     * satisfies all required scan keys, but not all nonrequired array keys,
     * will still require a recheck call to _bt_check_compare.  They'll still
     * need its "second pass" handling of required inequality scan keys.
     * (Might have missed a still-unsatisfied required inequality scan key
     * that caller didn't detect as the sktrig scan key during its initial
     * _bt_check_compare call that used the old/original qual.)
     *
     * Calls triggered by an unsatisfied nonrequired array scan key never need
     * "second pass" handling of required inequalities (nor any other handling
     * of any required scan key).  All that matters is whether caller's tuple
     * satisfies the new qual, so it's safe to just skip the _bt_check_compare
     * recheck when we've already determined that it can only return 'false'.
     */
    if ((sktrig_required && all_required_satisfied) ||
        (!sktrig_required && all_satisfied))
    {
        int         nsktrig = sktrig + 1;
        bool        continuescan;
 
        Assert(all_required_satisfied);
 
        /* Recheck _bt_check_compare on behalf of caller */
        if (_bt_check_compare(scan, dir, tuple, tupnatts, tupdesc,
                              false, false, false,
                              &continuescan, &nsktrig) &&
            !so->scanBehind)
        {
            /* This tuple satisfies the new qual */
            Assert(all_satisfied && continuescan);
 
            if (pstate)
                pstate->continuescan = true;
 
            return true;
        }
 
        /*
         * Consider "second pass" handling of required inequalities.
         *
         * It's possible that our _bt_check_compare call indicated that the
         * scan should end due to some unsatisfied inequality that wasn't
         * initially recognized as such by us.  Handle this by calling
         * ourselves recursively, this time indicating that the trigger is the
         * inequality that we missed first time around (and using a set of
         * required array/equality keys that are now exact matches for tuple).
         *
         * We make a strong, general guarantee that every _bt_checkkeys call
         * here will advance the array keys to the maximum possible extent
         * that we can know to be safe based on caller's tuple alone.  If we
         * didn't perform this step, then that guarantee wouldn't quite hold.
         */
        if (unlikely(!continuescan))
        {
            bool        satisfied PG_USED_FOR_ASSERTS_ONLY;
 
            Assert(sktrig_required);
            Assert(so->keyData[nsktrig].sk_strategy != BTEqualStrategyNumber);
 
            /*
             * The tuple must use "beyond end" advancement during the
             * recursive call, so we cannot possibly end up back here when
             * recursing.  We'll consume a small, fixed amount of stack space.
             */
            Assert(!beyond_end_advance);
 
            /* Advance the array keys a second time using same tuple */
            satisfied = _bt_advance_array_keys(scan, pstate, tuple, tupnatts,
                                               tupdesc, nsktrig, true);
 
            /* This tuple doesn't satisfy the inequality */
            Assert(!satisfied);
            return false;
        }
 
        /*
         * Some non-required scan key (from new qual) still not satisfied.
         *
         * All scan keys required in the current scan direction must still be
         * satisfied, though, so we can trust all_required_satisfied below.
         */
    }
 
    /*
     * When we were called just to deal with "advancing" non-required arrays,
     * this is as far as we can go (cannot stop the scan for these callers)
     */
    if (!sktrig_required)
    {
        /* Caller's tuple doesn't match any qual */
        return false;
    }
 
    /*
     * Postcondition array state assertion (for still-unsatisfied tuples).
     *
     * By here we have established that the scan's required arrays (scan must
     * have at least one required array) advanced, without becoming exhausted.
     *
     * Caller's tuple is now < the newly advanced array keys (or > when this
     * is a backwards scan), except in the case where we only got this far due
     * to an unsatisfied non-required scan key.  Verify that with an assert.
     *
     * Note: we don't just quit at this point when all required scan keys were
     * found to be satisfied because we need to consider edge-cases involving
     * scan keys required in the opposite direction only; those aren't tracked
     * by all_required_satisfied. (Actually, oppodir_inequality_sktrig trigger
     * scan keys are tracked by all_required_satisfied, since it's convenient
     * for _bt_check_compare to behave as if they are required in the current
     * scan direction to deal with NULLs.  We'll account for that separately.)
     */
    Assert(_bt_tuple_before_array_skeys(scan, dir, tuple, tupdesc, tupnatts,
                                        false, 0, NULL) ==
           !all_required_satisfied);
 
    /*
     * We generally permit primitive index scans to continue onto the next
     * sibling page when the page's finaltup satisfies all required scan keys
     * at the point where we're between pages.
     *
     * If caller's tuple is also the page's finaltup, and we see that required
     * scan keys still aren't satisfied, start a new primitive index scan.
     */
    if (!all_required_satisfied && pstate->finaltup == tuple)
        goto new_prim_scan;
 
    /*
     * Proactively check finaltup (don't wait until finaltup is reached by the
     * scan) when it might well turn out to not be satisfied later on.
     *
     * Note: if so->scanBehind hasn't already been set for finaltup by us,
     * it'll be set during this call to _bt_tuple_before_array_skeys.  Either
     * way, it'll be set correctly (for the whole page) after this point.
     */
    if (!all_required_satisfied && pstate->finaltup &&
        _bt_tuple_before_array_skeys(scan, dir, pstate->finaltup, tupdesc,
                                     BTreeTupleGetNAtts(pstate->finaltup, rel),
                                     false, 0, &so->scanBehind))
        goto new_prim_scan;
 
    /*
     * When we encounter a truncated finaltup high key attribute, we're
     * optimistic about the chances of its corresponding required scan key
     * being satisfied when we go on to check it against tuples from this
     * page's right sibling leaf page.  We consider truncated attributes to be
     * satisfied by required scan keys, which allows the primitive index scan
     * to continue to the next leaf page.  We must set so->scanBehind to true
     * to remember that the last page's finaltup had "satisfied" required scan
     * keys for one or more truncated attribute values (scan keys required in
     * _either_ scan direction).
     *
     * There is a chance that _bt_checkkeys (which checks so->scanBehind) will
     * find that even the sibling leaf page's finaltup is < the new array
     * keys.  When that happens, our optimistic policy will have incurred a
     * single extra leaf page access that could have been avoided.
     *
     * A pessimistic policy would give backward scans a gratuitous advantage
     * over forward scans.  We'd punish forward scans for applying more
     * accurate information from the high key, rather than just using the
     * final non-pivot tuple as finaltup, in the style of backward scans.
     * Being pessimistic would also give some scans with non-required arrays a
     * perverse advantage over similar scans that use required arrays instead.
     *
     * You can think of this as a speculative bet on what the scan is likely
     * to find on the next page.  It's not much of a gamble, though, since the
     * untruncated prefix of attributes must strictly satisfy the new qual
     * (though it's okay if any non-required scan keys fail to be satisfied).
     */
    if (so->scanBehind && has_required_opposite_direction_only)
    {
        /*
         * However, we need to work harder whenever the scan involves a scan
         * key required in the opposite direction to the scan only, along with
         * a finaltup with at least one truncated attribute that's associated
         * with a scan key marked required (required in either direction).
         *
         * _bt_check_compare simply won't stop the scan for a scan key that's
         * marked required in the opposite scan direction only.  That leaves
         * us without an automatic way of reconsidering any opposite-direction
         * inequalities if it turns out that starting a new primitive index
         * scan will allow _bt_first to skip ahead by a great many leaf pages.
         *
         * We deal with this by explicitly scheduling a finaltup recheck on
         * the right sibling page.  _bt_readpage calls _bt_oppodir_checkkeys
         * for next page's finaltup (and we skip it for this page's finaltup).
         */
        so->oppositeDirCheck = true;    /* recheck next page's high key */
    }
 
    /*
     * Handle inequalities marked required in the opposite scan direction.
     * They can also signal that we should start a new primitive index scan.
     *
     * It's possible that the scan is now positioned where "matching" tuples
     * begin, and that caller's tuple satisfies all scan keys required in the
     * current scan direction.  But if caller's tuple still doesn't satisfy
     * other scan keys that are required in the opposite scan direction only
     * (e.g., a required >= strategy scan key when scan direction is forward),
     * it's still possible that there are many leaf pages before the page that
     * _bt_first could skip straight to.  Groveling through all those pages
     * will always give correct answers, but it can be very inefficient.  We
     * must avoid needlessly scanning extra pages.
     *
     * Separately, it's possible that _bt_check_compare set continuescan=false
     * for a scan key that's required in the opposite direction only.  This is
     * a special case, that happens only when _bt_check_compare sees that the
     * inequality encountered a NULL value.  This signals the end of non-NULL
     * values in the current scan direction, which is reason enough to end the
     * (primitive) scan.  If this happens at the start of a large group of
     * NULL values, then we shouldn't expect to be called again until after
     * the scan has already read indefinitely-many leaf pages full of tuples
     * with NULL suffix values.  We need a separate test for this case so that
     * we don't miss our only opportunity to skip over such a group of pages.
     * (_bt_first is expected to skip over the group of NULLs by applying a
     * similar "deduce NOT NULL" rule, where it finishes its insertion scan
     * key by consing up an explicit SK_SEARCHNOTNULL key.)
     *
     * Apply a test against finaltup to detect and recover from the problem:
     * if even finaltup doesn't satisfy such an inequality, we just skip by
     * starting a new primitive index scan.  When we skip, we know for sure
     * that all of the tuples on the current page following caller's tuple are
     * also before the _bt_first-wise start of tuples for our new qual.  That
     * at least suggests many more skippable pages beyond the current page.
     * (when so->oppositeDirCheck was set, this'll happen on the next page.)
     */
    else if (has_required_opposite_direction_only && pstate->finaltup &&
             (all_required_satisfied || oppodir_inequality_sktrig) &&
             unlikely(!_bt_oppodir_checkkeys(scan, dir, pstate->finaltup)))
    {
        /*
         * Make sure that any non-required arrays are set to the first array
         * element for the current scan direction
         */
        _bt_rewind_nonrequired_arrays(scan, dir);
        goto new_prim_scan;
    }
 
    /*
     * Stick with the ongoing primitive index scan for now.
     *
     * It's possible that later tuples will also turn out to have values that
     * are still < the now-current array keys (or > the current array keys).
     * Our caller will handle this by performing what amounts to a linear
     * search of the page, implemented by calling _bt_check_compare and then
     * _bt_tuple_before_array_skeys for each tuple.
     *
     * This approach has various advantages over a binary search of the page.
     * Repeated binary searches of the page (one binary search for every array
     * advancement) won't outperform a continuous linear search.  While there
     * are workloads that a naive linear search won't handle well, our caller
     * has a "look ahead" fallback mechanism to deal with that problem.
     */
    pstate->continuescan = true;    /* Override _bt_check_compare */
    so->needPrimScan = false;   /* _bt_readpage has more tuples to check */
 
    if (so->scanBehind)
    {
        /* Optimization: skip by setting "look ahead" mechanism's offnum */
        Assert(ScanDirectionIsForward(dir));
        pstate->skip = pstate->maxoff + 1;
    }
 
    /* Caller's tuple doesn't match the new qual */
    return false;
 
new_prim_scan:
 
    Assert(pstate->finaltup);   /* not on rightmost/leftmost page */
 
    /*
     * End this primitive index scan, but schedule another.
     *
     * Note: We make a soft assumption that the current scan direction will
     * also be used within _bt_next, when it is asked to step off this page.
     * It is up to _bt_next to cancel this scheduled primitive index scan
     * whenever it steps to a page in the direction opposite currPos.dir.
     */
    pstate->continuescan = false;   /* Tell _bt_readpage we're done... */
    so->needPrimScan = true;    /* ...but call _bt_first again */
 
    if (scan->parallel_scan)
        _bt_parallel_primscan_schedule(scan, so->currPos.currPage);
 
    /* Caller's tuple doesn't match the new qual */
    return false;
 
end_toplevel_scan:
 
    /*
     * End the current primitive index scan, but don't schedule another.
     *
     * This ends the entire top-level scan in the current scan direction.
     *
     * Note: The scan's arrays (including any non-required arrays) are now in
     * their final positions for the current scan direction.  If the scan
     * direction happens to change, then the arrays will already be in their
     * first positions for what will then be the current scan direction.
     */
    pstate->continuescan = false;   /* Tell _bt_readpage we're done... */
    so->needPrimScan = false;   /* ...don't call _bt_first again, though */
 
    /* Caller's tuple doesn't match any qual */
    return false;
}

Referenced by _bt_advance_array_keys(), _bt_check_compare(), and _bt_checkkeys().

◆ _bt_advance_array_keys_increment()

static bool _bt_advance_array_keys_increment	(	IndexScanDesc	scan,
		ScanDirection	dir
	)

static

Definition at line 451 of file nbtutils.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
 
    /*
     * We must advance the last array key most quickly, since it will
     * correspond to the lowest-order index column among the available
     * qualifications
     */
    for (int i = so->numArrayKeys - 1; i >= 0; i--)
    {
        BTArrayKeyInfo *curArrayKey = &so->arrayKeys[i];
        ScanKey     skey = &so->keyData[curArrayKey->scan_key];
        int         cur_elem = curArrayKey->cur_elem;
        int         num_elems = curArrayKey->num_elems;
        bool        rolled = false;
 
        if (ScanDirectionIsForward(dir) && ++cur_elem >= num_elems)
        {
            cur_elem = 0;
            rolled = true;
        }
        else if (ScanDirectionIsBackward(dir) && --cur_elem < 0)
        {
            cur_elem = num_elems - 1;
            rolled = true;
        }
 
        curArrayKey->cur_elem = cur_elem;
        skey->sk_argument = curArrayKey->elem_values[cur_elem];
        if (!rolled)
            return true;
 
        /* Need to advance next array key, if any */
    }
 
    /*
     * The array keys are now exhausted.
     *
     * Restore the array keys to the state they were in immediately before we
     * were called.  This ensures that the arrays only ever ratchet in the
     * current scan direction.
     *
     * Without this, scans could overlook matching tuples when the scan
     * direction gets reversed just before btgettuple runs out of items to
     * return, but just after _bt_readpage prepares all the items from the
     * scan's final page in so->currPos.  When we're on the final page it is
     * typical for so->currPos to get invalidated once btgettuple finally
     * returns false, which'll effectively invalidate the scan's array keys.
     * That hasn't happened yet, though -- and in general it may never happen.
     */
    _bt_start_array_keys(scan, -dir);
 
    return false;
}

References _bt_start_array_keys(), BTScanOpaqueData::arrayKeys, BTArrayKeyInfo::cur_elem, BTArrayKeyInfo::elem_values, for(), i, BTScanOpaqueData::keyData, BTArrayKeyInfo::num_elems, BTScanOpaqueData::numArrayKeys, IndexScanDescData::opaque, BTArrayKeyInfo::scan_key, ScanDirectionIsBackward, ScanDirectionIsForward, and ScanKeyData::sk_argument.

Referenced by _bt_advance_array_keys().

◆ _bt_allequalimage()

bool _bt_allequalimage	(	Relation	rel,
		bool	debugmessage
	)

Definition at line 3297 of file nbtutils.c.

{
    bool        allequalimage = true;
 
    /* INCLUDE indexes can never support deduplication */
    if (IndexRelationGetNumberOfAttributes(rel) !=
        IndexRelationGetNumberOfKeyAttributes(rel))
        return false;
 
    for (int i = 0; i < IndexRelationGetNumberOfKeyAttributes(rel); i++)
    {
        Oid         opfamily = rel->rd_opfamily[i];
        Oid         opcintype = rel->rd_opcintype[i];
        Oid         collation = rel->rd_indcollation[i];
        Oid         equalimageproc;
 
        equalimageproc = get_opfamily_proc(opfamily, opcintype, opcintype,
                                           BTEQUALIMAGE_PROC);
 
        /*
         * If there is no BTEQUALIMAGE_PROC then deduplication is assumed to
         * be unsafe.  Otherwise, actually call proc and see what it says.
         */
        if (!OidIsValid(equalimageproc) ||
            !DatumGetBool(OidFunctionCall1Coll(equalimageproc, collation,
                                               ObjectIdGetDatum(opcintype))))
        {
            allequalimage = false;
            break;
        }
    }
 
    if (debugmessage)
    {
        if (allequalimage)
            elog(DEBUG1, "index \"%s\" can safely use deduplication",
                 RelationGetRelationName(rel));
        else
            elog(DEBUG1, "index \"%s\" cannot use deduplication",
                 RelationGetRelationName(rel));
    }
 
    return allequalimage;
}

References BTEQUALIMAGE_PROC, DatumGetBool(), DEBUG1, elog, get_opfamily_proc(), i, IndexRelationGetNumberOfAttributes, IndexRelationGetNumberOfKeyAttributes, ObjectIdGetDatum(), OidFunctionCall1Coll(), OidIsValid, RelationData::rd_indcollation, RelationData::rd_opcintype, RelationData::rd_opfamily, and RelationGetRelationName.

Referenced by _bt_leafbuild(), bt_index_check_internal(), and btbuildempty().

◆ _bt_binsrch_array_skey()

int _bt_binsrch_array_skey	(	FmgrInfo *	orderproc,
		bool	cur_elem_trig,
		ScanDirection	dir,
		Datum	tupdatum,
		bool	tupnull,
		BTArrayKeyInfo *	array,
		ScanKey	cur,
		int32 *	set_elem_result
	)

Definition at line 271 of file nbtutils.c.

{
    int         low_elem = 0,
                mid_elem = -1,
                high_elem = array->num_elems - 1,
                result = 0;
    Datum       arrdatum;
 
    Assert(cur->sk_flags & SK_SEARCHARRAY);
    Assert(cur->sk_strategy == BTEqualStrategyNumber);
 
    if (cur_elem_trig)
    {
        Assert(!ScanDirectionIsNoMovement(dir));
        Assert(cur->sk_flags & SK_BT_REQFWD);
 
        /*
         * When the scan key that triggered array advancement is a required
         * array scan key, it is now certain that the current array element
         * (plus all prior elements relative to the current scan direction)
         * cannot possibly be at or ahead of the corresponding tuple value.
         * (_bt_checkkeys must have called _bt_tuple_before_array_skeys, which
         * makes sure this is true as a condition of advancing the arrays.)
         *
         * This makes it safe to exclude array elements up to and including
         * the former-current array element from our search.
         *
         * Separately, when array advancement was triggered by a required scan
         * key, the array element immediately after the former-current element
         * is often either an exact tupdatum match, or a "close by" near-match
         * (a near-match tupdatum is one whose key space falls _between_ the
         * former-current and new-current array elements).  We'll detect both
         * cases via an optimistic comparison of the new search lower bound
         * (or new search upper bound in the case of backwards scans).
         */
        if (ScanDirectionIsForward(dir))
        {
            low_elem = array->cur_elem + 1; /* old cur_elem exhausted */
 
            /* Compare prospective new cur_elem (also the new lower bound) */
            if (high_elem >= low_elem)
            {
                arrdatum = array->elem_values[low_elem];
                result = _bt_compare_array_skey(orderproc, tupdatum, tupnull,
                                                arrdatum, cur);
 
                if (result <= 0)
                {
                    /* Optimistic comparison optimization worked out */
                    *set_elem_result = result;
                    return low_elem;
                }
                mid_elem = low_elem;
                low_elem++;     /* this cur_elem exhausted, too */
            }
 
            if (high_elem < low_elem)
            {
                /* Caller needs to perform "beyond end" array advancement */
                *set_elem_result = 1;
                return high_elem;
            }
        }
        else
        {
            high_elem = array->cur_elem - 1;    /* old cur_elem exhausted */
 
            /* Compare prospective new cur_elem (also the new upper bound) */
            if (high_elem >= low_elem)
            {
                arrdatum = array->elem_values[high_elem];
                result = _bt_compare_array_skey(orderproc, tupdatum, tupnull,
                                                arrdatum, cur);
 
                if (result >= 0)
                {
                    /* Optimistic comparison optimization worked out */
                    *set_elem_result = result;
                    return high_elem;
                }
                mid_elem = high_elem;
                high_elem--;    /* this cur_elem exhausted, too */
            }
 
            if (high_elem < low_elem)
            {
                /* Caller needs to perform "beyond end" array advancement */
                *set_elem_result = -1;
                return low_elem;
            }
        }
    }
 
    while (high_elem > low_elem)
    {
        mid_elem = low_elem + ((high_elem - low_elem) / 2);
        arrdatum = array->elem_values[mid_elem];
 
        result = _bt_compare_array_skey(orderproc, tupdatum, tupnull,
                                        arrdatum, cur);
 
        if (result == 0)
        {
            /*
             * It's safe to quit as soon as we see an equal array element.
             * This often saves an extra comparison or two...
             */
            low_elem = mid_elem;
            break;
        }
 
        if (result > 0)
            low_elem = mid_elem + 1;
        else
            high_elem = mid_elem;
    }
 
    /*
     * ...but our caller also cares about how its searched-for tuple datum
     * compares to the low_elem datum.  Must always set *set_elem_result with
     * the result of that comparison specifically.
     */
    if (low_elem != mid_elem)
        result = _bt_compare_array_skey(orderproc, tupdatum, tupnull,
                                        array->elem_values[low_elem], cur);
 
    *set_elem_result = result;
 
    return low_elem;
}

References _bt_compare_array_skey(), Assert, BTEqualStrategyNumber, cur, BTArrayKeyInfo::cur_elem, BTArrayKeyInfo::elem_values, BTArrayKeyInfo::num_elems, ScanDirectionIsForward, ScanDirectionIsNoMovement, SK_BT_REQFWD, and SK_SEARCHARRAY.

Referenced by _bt_advance_array_keys(), and _bt_compare_array_scankey_args().

◆ _bt_check_compare()

static bool _bt_check_compare	(	IndexScanDesc	scan,
		ScanDirection	dir,
		IndexTuple	tuple,
		int	tupnatts,
		TupleDesc	tupdesc,
		bool	advancenonrequired,
		bool	prechecked,
		bool	firstmatch,
		bool *	continuescan,
		int *	ikey
	)

static

Definition at line 1843 of file nbtutils.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
 
    *continuescan = true;       /* default assumption */
 
    for (; *ikey < so->numberOfKeys; (*ikey)++)
    {
        ScanKey     key = so->keyData + *ikey;
        Datum       datum;
        bool        isNull;
        bool        requiredSameDir = false,
                    requiredOppositeDirOnly = false;
 
        /*
         * Check if the key is required in the current scan direction, in the
         * opposite scan direction _only_, or in neither direction
         */
        if (((key->sk_flags & SK_BT_REQFWD) && ScanDirectionIsForward(dir)) ||
            ((key->sk_flags & SK_BT_REQBKWD) && ScanDirectionIsBackward(dir)))
            requiredSameDir = true;
        else if (((key->sk_flags & SK_BT_REQFWD) && ScanDirectionIsBackward(dir)) ||
                 ((key->sk_flags & SK_BT_REQBKWD) && ScanDirectionIsForward(dir)))
            requiredOppositeDirOnly = true;
 
        /*
         * If the caller told us the *continuescan flag is known to be true
         * for the last item on the page, then we know the keys required for
         * the current direction scan should be matched.  Otherwise, the
         * *continuescan flag would be set for the current item and
         * subsequently the last item on the page accordingly.
         *
         * If the key is required for the opposite direction scan, we can skip
         * the check if the caller tells us there was already at least one
         * matching item on the page. Also, we require the *continuescan flag
         * to be true for the last item on the page to know there are no
         * NULLs.
         *
         * Both cases above work except for the row keys, where NULLs could be
         * found in the middle of matching values.
         */
        if (prechecked &&
            (requiredSameDir || (requiredOppositeDirOnly && firstmatch)) &&
            !(key->sk_flags & SK_ROW_HEADER))
            continue;
 
        if (key->sk_attno > tupnatts)
        {
            /*
             * This attribute is truncated (must be high key).  The value for
             * this attribute in the first non-pivot tuple on the page to the
             * right could be any possible value.  Assume that truncated
             * attribute passes the qual.
             */
            Assert(BTreeTupleIsPivot(tuple));
            continue;
        }
 
        /* row-comparison keys need special processing */
        if (key->sk_flags & SK_ROW_HEADER)
        {
            if (_bt_check_rowcompare(key, tuple, tupnatts, tupdesc, dir,
                                     continuescan))
                continue;
            return false;
        }
 
        datum = index_getattr(tuple,
                              key->sk_attno,
                              tupdesc,
                              &isNull);
 
        if (key->sk_flags & SK_ISNULL)
        {
            /* Handle IS NULL/NOT NULL tests */
            if (key->sk_flags & SK_SEARCHNULL)
            {
                if (isNull)
                    continue;   /* tuple satisfies this qual */
            }
            else
            {
                Assert(key->sk_flags & SK_SEARCHNOTNULL);
                if (!isNull)
                    continue;   /* tuple satisfies this qual */
            }
 
            /*
             * Tuple fails this qual.  If it's a required qual for the current
             * scan direction, then we can conclude no further tuples will
             * pass, either.
             */
            if (requiredSameDir)
                *continuescan = false;
 
            /*
             * In any case, this indextuple doesn't match the qual.
             */
            return false;
        }
 
        if (isNull)
        {
            if (key->sk_flags & SK_BT_NULLS_FIRST)
            {
                /*
                 * Since NULLs are sorted before non-NULLs, we know we have
                 * reached the lower limit of the range of values for this
                 * index attr.  On a backward scan, we can stop if this qual
                 * is one of the "must match" subset.  We can stop regardless
                 * of whether the qual is > or <, so long as it's required,
                 * because it's not possible for any future tuples to pass. On
                 * a forward scan, however, we must keep going, because we may
                 * have initially positioned to the start of the index.
                 * (_bt_advance_array_keys also relies on this behavior during
                 * forward scans.)
                 */
                if ((key->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)) &&
                    ScanDirectionIsBackward(dir))
                    *continuescan = false;
            }
            else
            {
                /*
                 * Since NULLs are sorted after non-NULLs, we know we have
                 * reached the upper limit of the range of values for this
                 * index attr.  On a forward scan, we can stop if this qual is
                 * one of the "must match" subset.  We can stop regardless of
                 * whether the qual is > or <, so long as it's required,
                 * because it's not possible for any future tuples to pass. On
                 * a backward scan, however, we must keep going, because we
                 * may have initially positioned to the end of the index.
                 * (_bt_advance_array_keys also relies on this behavior during
                 * backward scans.)
                 */
                if ((key->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)) &&
                    ScanDirectionIsForward(dir))
                    *continuescan = false;
            }
 
            /*
             * In any case, this indextuple doesn't match the qual.
             */
            return false;
        }
 
        /*
         * Apply the key-checking function, though only if we must.
         *
         * When a key is required in the opposite-of-scan direction _only_,
         * then it must already be satisfied if firstmatch=true indicates that
         * an earlier tuple from this same page satisfied it earlier on.
         */
        if (!(requiredOppositeDirOnly && firstmatch) &&
            !DatumGetBool(FunctionCall2Coll(&key->sk_func, key->sk_collation,
                                            datum, key->sk_argument)))
        {
            /*
             * Tuple fails this qual.  If it's a required qual for the current
             * scan direction, then we can conclude no further tuples will
             * pass, either.
             *
             * Note: because we stop the scan as soon as any required equality
             * qual fails, it is critical that equality quals be used for the
             * initial positioning in _bt_first() when they are available. See
             * comments in _bt_first().
             */
            if (requiredSameDir)
                *continuescan = false;
 
            /*
             * If this is a non-required equality-type array key, the tuple
             * needs to be checked against every possible array key.  Handle
             * this by "advancing" the scan key's array to a matching value
             * (if we're successful then the tuple might match the qual).
             */
            else if (advancenonrequired &&
                     key->sk_strategy == BTEqualStrategyNumber &&
                     (key->sk_flags & SK_SEARCHARRAY))
                return _bt_advance_array_keys(scan, NULL, tuple, tupnatts,
                                              tupdesc, *ikey, false);
 
            /*
             * This indextuple doesn't match the qual.
             */
            return false;
        }
    }
 
    /* If we get here, the tuple passes all index quals. */
    return true;
}

References _bt_advance_array_keys(), _bt_check_rowcompare(), Assert, BTEqualStrategyNumber, BTreeTupleIsPivot(), DatumGetBool(), for(), FunctionCall2Coll(), index_getattr(), sort-test::key, BTScanOpaqueData::keyData, BTScanOpaqueData::numberOfKeys, IndexScanDescData::opaque, ScanDirectionIsBackward, ScanDirectionIsForward, SK_BT_NULLS_FIRST, SK_BT_REQBKWD, SK_BT_REQFWD, SK_ISNULL, SK_ROW_HEADER, SK_SEARCHARRAY, SK_SEARCHNOTNULL, and SK_SEARCHNULL.

Referenced by _bt_advance_array_keys(), _bt_checkkeys(), and _bt_oppodir_checkkeys().

◆ _bt_check_natts()

bool _bt_check_natts	(	Relation	rel,
		bool	heapkeyspace,
		Page	page,
		OffsetNumber	offnum
	)

Definition at line 3079 of file nbtutils.c.

{
    int16       natts = IndexRelationGetNumberOfAttributes(rel);
    int16       nkeyatts = IndexRelationGetNumberOfKeyAttributes(rel);
    BTPageOpaque opaque = BTPageGetOpaque(page);
    IndexTuple  itup;
    int         tupnatts;
 
    /*
     * We cannot reliably test a deleted or half-dead page, since they have
     * dummy high keys
     */
    if (P_IGNORE(opaque))
        return true;
 
    Assert(offnum >= FirstOffsetNumber &&
           offnum <= PageGetMaxOffsetNumber(page));
 
    itup = (IndexTuple) PageGetItem(page, PageGetItemId(page, offnum));
    tupnatts = BTreeTupleGetNAtts(itup, rel);
 
    /* !heapkeyspace indexes do not support deduplication */
    if (!heapkeyspace && BTreeTupleIsPosting(itup))
        return false;
 
    /* Posting list tuples should never have "pivot heap TID" bit set */
    if (BTreeTupleIsPosting(itup) &&
        (ItemPointerGetOffsetNumberNoCheck(&itup->t_tid) &
         BT_PIVOT_HEAP_TID_ATTR) != 0)
        return false;
 
    /* INCLUDE indexes do not support deduplication */
    if (natts != nkeyatts && BTreeTupleIsPosting(itup))
        return false;
 
    if (P_ISLEAF(opaque))
    {
        if (offnum >= P_FIRSTDATAKEY(opaque))
        {
            /*
             * Non-pivot tuple should never be explicitly marked as a pivot
             * tuple
             */
            if (BTreeTupleIsPivot(itup))
                return false;
 
            /*
             * Leaf tuples that are not the page high key (non-pivot tuples)
             * should never be truncated.  (Note that tupnatts must have been
             * inferred, even with a posting list tuple, because only pivot
             * tuples store tupnatts directly.)
             */
            return tupnatts == natts;
        }
        else
        {
            /*
             * Rightmost page doesn't contain a page high key, so tuple was
             * checked above as ordinary leaf tuple
             */
            Assert(!P_RIGHTMOST(opaque));
 
            /*
             * !heapkeyspace high key tuple contains only key attributes. Note
             * that tupnatts will only have been explicitly represented in
             * !heapkeyspace indexes that happen to have non-key attributes.
             */
            if (!heapkeyspace)
                return tupnatts == nkeyatts;
 
            /* Use generic heapkeyspace pivot tuple handling */
        }
    }
    else                        /* !P_ISLEAF(opaque) */
    {
        if (offnum == P_FIRSTDATAKEY(opaque))
        {
            /*
             * The first tuple on any internal page (possibly the first after
             * its high key) is its negative infinity tuple.  Negative
             * infinity tuples are always truncated to zero attributes.  They
             * are a particular kind of pivot tuple.
             */
            if (heapkeyspace)
                return tupnatts == 0;
 
            /*
             * The number of attributes won't be explicitly represented if the
             * negative infinity tuple was generated during a page split that
             * occurred with a version of Postgres before v11.  There must be
             * a problem when there is an explicit representation that is
             * non-zero, or when there is no explicit representation and the
             * tuple is evidently not a pre-pg_upgrade tuple.
             *
             * Prior to v11, downlinks always had P_HIKEY as their offset.
             * Accept that as an alternative indication of a valid
             * !heapkeyspace negative infinity tuple.
             */
            return tupnatts == 0 ||
                ItemPointerGetOffsetNumber(&(itup->t_tid)) == P_HIKEY;
        }
        else
        {
            /*
             * !heapkeyspace downlink tuple with separator key contains only
             * key attributes.  Note that tupnatts will only have been
             * explicitly represented in !heapkeyspace indexes that happen to
             * have non-key attributes.
             */
            if (!heapkeyspace)
                return tupnatts == nkeyatts;
 
            /* Use generic heapkeyspace pivot tuple handling */
        }
    }
 
    /* Handle heapkeyspace pivot tuples (excluding minus infinity items) */
    Assert(heapkeyspace);
 
    /*
     * Explicit representation of the number of attributes is mandatory with
     * heapkeyspace index pivot tuples, regardless of whether or not there are
     * non-key attributes.
     */
    if (!BTreeTupleIsPivot(itup))
        return false;
 
    /* Pivot tuple should not use posting list representation (redundant) */
    if (BTreeTupleIsPosting(itup))
        return false;
 
    /*
     * Heap TID is a tiebreaker key attribute, so it cannot be untruncated
     * when any other key attribute is truncated
     */
    if (BTreeTupleGetHeapTID(itup) != NULL && tupnatts != nkeyatts)
        return false;
 
    /*
     * Pivot tuple must have at least one untruncated key attribute (minus
     * infinity pivot tuples are the only exception).  Pivot tuples can never
     * represent that there is a value present for a key attribute that
     * exceeds pg_index.indnkeyatts for the index.
     */
    return tupnatts > 0 && tupnatts <= nkeyatts;
}

References Assert, BT_PIVOT_HEAP_TID_ATTR, BTPageGetOpaque, BTreeTupleGetHeapTID(), BTreeTupleGetNAtts, BTreeTupleIsPivot(), BTreeTupleIsPosting(), FirstOffsetNumber, IndexRelationGetNumberOfAttributes, IndexRelationGetNumberOfKeyAttributes, ItemPointerGetOffsetNumber(), ItemPointerGetOffsetNumberNoCheck(), P_FIRSTDATAKEY, P_HIKEY, P_IGNORE, P_ISLEAF, P_RIGHTMOST, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), and IndexTupleData::t_tid.

Referenced by _bt_compare(), and bt_target_page_check().

◆ _bt_check_rowcompare()

static bool _bt_check_rowcompare	(	ScanKey	skey,
		IndexTuple	tuple,
		int	tupnatts,
		TupleDesc	tupdesc,
		ScanDirection	dir,
		bool *	continuescan
	)

static

Definition at line 2049 of file nbtutils.c.

{
    ScanKey     subkey = (ScanKey) DatumGetPointer(skey->sk_argument);
    int32       cmpresult = 0;
    bool        result;
 
    /* First subkey should be same as the header says */
    Assert(subkey->sk_attno == skey->sk_attno);
 
    /* Loop over columns of the row condition */
    for (;;)
    {
        Datum       datum;
        bool        isNull;
 
        Assert(subkey->sk_flags & SK_ROW_MEMBER);
 
        if (subkey->sk_attno > tupnatts)
        {
            /*
             * This attribute is truncated (must be high key).  The value for
             * this attribute in the first non-pivot tuple on the page to the
             * right could be any possible value.  Assume that truncated
             * attribute passes the qual.
             */
            Assert(BTreeTupleIsPivot(tuple));
            cmpresult = 0;
            if (subkey->sk_flags & SK_ROW_END)
                break;
            subkey++;
            continue;
        }
 
        datum = index_getattr(tuple,
                              subkey->sk_attno,
                              tupdesc,
                              &isNull);
 
        if (isNull)
        {
            if (subkey->sk_flags & SK_BT_NULLS_FIRST)
            {
                /*
                 * Since NULLs are sorted before non-NULLs, we know we have
                 * reached the lower limit of the range of values for this
                 * index attr.  On a backward scan, we can stop if this qual
                 * is one of the "must match" subset.  We can stop regardless
                 * of whether the qual is > or <, so long as it's required,
                 * because it's not possible for any future tuples to pass. On
                 * a forward scan, however, we must keep going, because we may
                 * have initially positioned to the start of the index.
                 * (_bt_advance_array_keys also relies on this behavior during
                 * forward scans.)
                 */
                if ((subkey->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)) &&
                    ScanDirectionIsBackward(dir))
                    *continuescan = false;
            }
            else
            {
                /*
                 * Since NULLs are sorted after non-NULLs, we know we have
                 * reached the upper limit of the range of values for this
                 * index attr.  On a forward scan, we can stop if this qual is
                 * one of the "must match" subset.  We can stop regardless of
                 * whether the qual is > or <, so long as it's required,
                 * because it's not possible for any future tuples to pass. On
                 * a backward scan, however, we must keep going, because we
                 * may have initially positioned to the end of the index.
                 * (_bt_advance_array_keys also relies on this behavior during
                 * backward scans.)
                 */
                if ((subkey->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)) &&
                    ScanDirectionIsForward(dir))
                    *continuescan = false;
            }
 
            /*
             * In any case, this indextuple doesn't match the qual.
             */
            return false;
        }
 
        if (subkey->sk_flags & SK_ISNULL)
        {
            /*
             * Unlike the simple-scankey case, this isn't a disallowed case
             * (except when it's the first row element that has the NULL arg).
             * But it can never match.  If all the earlier row comparison
             * columns are required for the scan direction, we can stop the
             * scan, because there can't be another tuple that will succeed.
             */
            Assert(subkey != (ScanKey) DatumGetPointer(skey->sk_argument));
            subkey--;
            if ((subkey->sk_flags & SK_BT_REQFWD) &&
                ScanDirectionIsForward(dir))
                *continuescan = false;
            else if ((subkey->sk_flags & SK_BT_REQBKWD) &&
                     ScanDirectionIsBackward(dir))
                *continuescan = false;
            return false;
        }
 
        /* Perform the test --- three-way comparison not bool operator */
        cmpresult = DatumGetInt32(FunctionCall2Coll(&subkey->sk_func,
                                                    subkey->sk_collation,
                                                    datum,
                                                    subkey->sk_argument));
 
        if (subkey->sk_flags & SK_BT_DESC)
            INVERT_COMPARE_RESULT(cmpresult);
 
        /* Done comparing if unequal, else advance to next column */
        if (cmpresult != 0)
            break;
 
        if (subkey->sk_flags & SK_ROW_END)
            break;
        subkey++;
    }
 
    /*
     * At this point cmpresult indicates the overall result of the row
     * comparison, and subkey points to the deciding column (or the last
     * column if the result is "=").
     */
    switch (subkey->sk_strategy)
    {
            /* EQ and NE cases aren't allowed here */
        case BTLessStrategyNumber:
            result = (cmpresult < 0);
            break;
        case BTLessEqualStrategyNumber:
            result = (cmpresult <= 0);
            break;
        case BTGreaterEqualStrategyNumber:
            result = (cmpresult >= 0);
            break;
        case BTGreaterStrategyNumber:
            result = (cmpresult > 0);
            break;
        default:
            elog(ERROR, "unexpected strategy number %d", subkey->sk_strategy);
            result = 0;         /* keep compiler quiet */
            break;
    }
 
    if (!result)
    {
        /*
         * Tuple fails this qual.  If it's a required qual for the current
         * scan direction, then we can conclude no further tuples will pass,
         * either.  Note we have to look at the deciding column, not
         * necessarily the first or last column of the row condition.
         */
        if ((subkey->sk_flags & SK_BT_REQFWD) &&
            ScanDirectionIsForward(dir))
            *continuescan = false;
        else if ((subkey->sk_flags & SK_BT_REQBKWD) &&
                 ScanDirectionIsBackward(dir))
            *continuescan = false;
    }
 
    return result;
}

References Assert, BTGreaterEqualStrategyNumber, BTGreaterStrategyNumber, BTLessEqualStrategyNumber, BTLessStrategyNumber, BTreeTupleIsPivot(), DatumGetInt32(), DatumGetPointer(), elog, ERROR, FunctionCall2Coll(), index_getattr(), INVERT_COMPARE_RESULT, ScanDirectionIsBackward, ScanDirectionIsForward, ScanKeyData::sk_argument, ScanKeyData::sk_attno, SK_BT_DESC, SK_BT_NULLS_FIRST, SK_BT_REQBKWD, SK_BT_REQFWD, ScanKeyData::sk_collation, ScanKeyData::sk_flags, ScanKeyData::sk_func, SK_ISNULL, SK_ROW_END, SK_ROW_MEMBER, and ScanKeyData::sk_strategy.

Referenced by _bt_check_compare().

◆ _bt_check_third_page()

void _bt_check_third_page	(	Relation	rel,
		Relation	heap,
		bool	needheaptidspace,
		Page	page,
		IndexTuple	newtup
	)

Definition at line 3239 of file nbtutils.c.

{
    Size        itemsz;
    BTPageOpaque opaque;
 
    itemsz = MAXALIGN(IndexTupleSize(newtup));
 
    /* Double check item size against limit */
    if (itemsz <= BTMaxItemSize(page))
        return;
 
    /*
     * Tuple is probably too large to fit on page, but it's possible that the
     * index uses version 2 or version 3, or that page is an internal page, in
     * which case a slightly higher limit applies.
     */
    if (!needheaptidspace && itemsz <= BTMaxItemSizeNoHeapTid(page))
        return;
 
    /*
     * Internal page insertions cannot fail here, because that would mean that
     * an earlier leaf level insertion that should have failed didn't
     */
    opaque = BTPageGetOpaque(page);
    if (!P_ISLEAF(opaque))
        elog(ERROR, "cannot insert oversized tuple of size %zu on internal page of index \"%s\"",
             itemsz, RelationGetRelationName(rel));
 
    ereport(ERROR,
            (errcode(ERRCODE_PROGRAM_LIMIT_EXCEEDED),
             errmsg("index row size %zu exceeds btree version %u maximum %zu for index \"%s\"",
                    itemsz,
                    needheaptidspace ? BTREE_VERSION : BTREE_NOVAC_VERSION,
                    needheaptidspace ? BTMaxItemSize(page) :
                    BTMaxItemSizeNoHeapTid(page),
                    RelationGetRelationName(rel)),
             errdetail("Index row references tuple (%u,%u) in relation \"%s\".",
                       ItemPointerGetBlockNumber(BTreeTupleGetHeapTID(newtup)),
                       ItemPointerGetOffsetNumber(BTreeTupleGetHeapTID(newtup)),
                       RelationGetRelationName(heap)),
             errhint("Values larger than 1/3 of a buffer page cannot be indexed.\n"
                     "Consider a function index of an MD5 hash of the value, "
                     "or use full text indexing."),
             errtableconstraint(heap, RelationGetRelationName(rel))));
}

References BTMaxItemSize, BTMaxItemSizeNoHeapTid, BTPageGetOpaque, BTREE_NOVAC_VERSION, BTREE_VERSION, BTreeTupleGetHeapTID(), elog, ereport, errcode(), errdetail(), errhint(), errmsg(), ERROR, errtableconstraint(), IndexTupleSize, ItemPointerGetBlockNumber(), ItemPointerGetOffsetNumber(), MAXALIGN, P_ISLEAF, and RelationGetRelationName.

Referenced by _bt_buildadd(), and _bt_findinsertloc().

◆ _bt_checkkeys()

bool _bt_checkkeys	(	IndexScanDesc	scan,
		BTReadPageState *	pstate,
		bool	arrayKeys,
		IndexTuple	tuple,
		int	tupnatts
	)

Definition at line 1627 of file nbtutils.c.

{
    TupleDesc   tupdesc = RelationGetDescr(scan->indexRelation);
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    ScanDirection dir = so->currPos.dir;
    int         ikey = 0;
    bool        res;
 
    Assert(BTreeTupleGetNAtts(tuple, scan->indexRelation) == tupnatts);
 
    res = _bt_check_compare(scan, dir, tuple, tupnatts, tupdesc,
                            arrayKeys, pstate->prechecked, pstate->firstmatch,
                            &pstate->continuescan, &ikey);
 
#ifdef USE_ASSERT_CHECKING
    if (!arrayKeys && so->numArrayKeys)
    {
        /*
         * This is a continuescan precheck call for a scan with array keys.
         *
         * Assert that the scan isn't in danger of becoming confused.
         */
        Assert(!so->scanBehind && !so->oppositeDirCheck);
        Assert(!pstate->prechecked && !pstate->firstmatch);
        Assert(!_bt_tuple_before_array_skeys(scan, dir, tuple, tupdesc,
                                             tupnatts, false, 0, NULL));
    }
    if (pstate->prechecked || pstate->firstmatch)
    {
        bool        dcontinuescan;
        int         dikey = 0;
 
        /*
         * Call relied on continuescan/firstmatch prechecks -- assert that we
         * get the same answer without those optimizations
         */
        Assert(res == _bt_check_compare(scan, dir, tuple, tupnatts, tupdesc,
                                        false, false, false,
                                        &dcontinuescan, &dikey));
        Assert(pstate->continuescan == dcontinuescan);
    }
#endif
 
    /*
     * Only one _bt_check_compare call is required in the common case where
     * there are no equality strategy array scan keys.  Otherwise we can only
     * accept _bt_check_compare's answer unreservedly when it didn't set
     * pstate.continuescan=false.
     */
    if (!arrayKeys || pstate->continuescan)
        return res;
 
    /*
     * _bt_check_compare call set continuescan=false in the presence of
     * equality type array keys.  This could mean that the tuple is just past
     * the end of matches for the current array keys.
     *
     * It's also possible that the scan is still _before_ the _start_ of
     * tuples matching the current set of array keys.  Check for that first.
     */
    if (_bt_tuple_before_array_skeys(scan, dir, tuple, tupdesc, tupnatts, true,
                                     ikey, NULL))
    {
        /*
         * Tuple is still before the start of matches according to the scan's
         * required array keys (according to _all_ of its required equality
         * strategy keys, actually).
         *
         * _bt_advance_array_keys occasionally sets so->scanBehind to signal
         * that the scan's current position/tuples might be significantly
         * behind (multiple pages behind) its current array keys.  When this
         * happens, we need to be prepared to recover by starting a new
         * primitive index scan here, on our own.
         */
        Assert(!so->scanBehind ||
               so->keyData[ikey].sk_strategy == BTEqualStrategyNumber);
        if (unlikely(so->scanBehind) && pstate->finaltup &&
            _bt_tuple_before_array_skeys(scan, dir, pstate->finaltup, tupdesc,
                                         BTreeTupleGetNAtts(pstate->finaltup,
                                                            scan->indexRelation),
                                         false, 0, NULL))
        {
            /* Cut our losses -- start a new primitive index scan now */
            pstate->continuescan = false;
            so->needPrimScan = true;
        }
        else
        {
            /* Override _bt_check_compare, continue primitive scan */
            pstate->continuescan = true;
 
            /*
             * We will end up here repeatedly given a group of tuples > the
             * previous array keys and < the now-current keys (for a backwards
             * scan it's just the same, though the operators swap positions).
             *
             * We must avoid allowing this linear search process to scan very
             * many tuples from well before the start of tuples matching the
             * current array keys (or from well before the point where we'll
             * once again have to advance the scan's array keys).
             *
             * We keep the overhead under control by speculatively "looking
             * ahead" to later still-unscanned items from this same leaf page.
             * We'll only attempt this once the number of tuples that the
             * linear search process has examined starts to get out of hand.
             */
            pstate->rechecks++;
            if (pstate->rechecks >= LOOK_AHEAD_REQUIRED_RECHECKS)
            {
                /* See if we should skip ahead within the current leaf page */
                _bt_checkkeys_look_ahead(scan, pstate, tupnatts, tupdesc);
 
                /*
                 * Might have set pstate.skip to a later page offset.  When
                 * that happens then _bt_readpage caller will inexpensively
                 * skip ahead to a later tuple from the same page (the one
                 * just after the tuple we successfully "looked ahead" to).
                 */
            }
        }
 
        /* This indextuple doesn't match the current qual, in any case */
        return false;
    }
 
    /*
     * Caller's tuple is >= the current set of array keys and other equality
     * constraint scan keys (or <= if this is a backwards scan).  It's now
     * clear that we _must_ advance any required array keys in lockstep with
     * the scan.
     */
    return _bt_advance_array_keys(scan, pstate, tuple, tupnatts, tupdesc,
                                  ikey, true);
}

References _bt_advance_array_keys(), _bt_check_compare(), _bt_checkkeys_look_ahead(), _bt_tuple_before_array_skeys(), Assert, BTEqualStrategyNumber, BTreeTupleGetNAtts, BTReadPageState::continuescan, BTScanOpaqueData::currPos, BTScanPosData::dir, BTReadPageState::finaltup, BTReadPageState::firstmatch, IndexScanDescData::indexRelation, BTScanOpaqueData::keyData, LOOK_AHEAD_REQUIRED_RECHECKS, BTScanOpaqueData::needPrimScan, BTScanOpaqueData::numArrayKeys, IndexScanDescData::opaque, BTScanOpaqueData::oppositeDirCheck, BTReadPageState::prechecked, BTReadPageState::rechecks, RelationGetDescr, res, BTScanOpaqueData::scanBehind, ScanKeyData::sk_strategy, and unlikely.

Referenced by _bt_readpage().

◆ _bt_checkkeys_look_ahead()

static void _bt_checkkeys_look_ahead	(	IndexScanDesc	scan,
		BTReadPageState *	pstate,
		int	tupnatts,
		TupleDesc	tupdesc
	)

static

Definition at line 2233 of file nbtutils.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    ScanDirection dir = so->currPos.dir;
    OffsetNumber aheadoffnum;
    IndexTuple  ahead;
 
    /* Avoid looking ahead when comparing the page high key */
    if (pstate->offnum < pstate->minoff)
        return;
 
    /*
     * Don't look ahead when there aren't enough tuples remaining on the page
     * (in the current scan direction) for it to be worth our while
     */
    if (ScanDirectionIsForward(dir) &&
        pstate->offnum >= pstate->maxoff - LOOK_AHEAD_DEFAULT_DISTANCE)
        return;
    else if (ScanDirectionIsBackward(dir) &&
             pstate->offnum <= pstate->minoff + LOOK_AHEAD_DEFAULT_DISTANCE)
        return;
 
    /*
     * The look ahead distance starts small, and ramps up as each call here
     * allows _bt_readpage to skip over more tuples
     */
    if (!pstate->targetdistance)
        pstate->targetdistance = LOOK_AHEAD_DEFAULT_DISTANCE;
    else if (pstate->targetdistance < MaxIndexTuplesPerPage / 2)
        pstate->targetdistance *= 2;
 
    /* Don't read past the end (or before the start) of the page, though */
    if (ScanDirectionIsForward(dir))
        aheadoffnum = Min((int) pstate->maxoff,
                          (int) pstate->offnum + pstate->targetdistance);
    else
        aheadoffnum = Max((int) pstate->minoff,
                          (int) pstate->offnum - pstate->targetdistance);
 
    ahead = (IndexTuple) PageGetItem(pstate->page,
                                     PageGetItemId(pstate->page, aheadoffnum));
    if (_bt_tuple_before_array_skeys(scan, dir, ahead, tupdesc, tupnatts,
                                     false, 0, NULL))
    {
        /*
         * Success -- instruct _bt_readpage to skip ahead to very next tuple
         * after the one we determined was still before the current array keys
         */
        if (ScanDirectionIsForward(dir))
            pstate->skip = aheadoffnum + 1;
        else
            pstate->skip = aheadoffnum - 1;
    }
    else
    {
        /*
         * Failure -- "ahead" tuple is too far ahead (we were too aggressive).
         *
         * Reset the number of rechecks, and aggressively reduce the target
         * distance (we're much more aggressive here than we were when the
         * distance was initially ramped up).
         */
        pstate->rechecks = 0;
        pstate->targetdistance = Max(pstate->targetdistance / 8, 1);
    }
}

References _bt_tuple_before_array_skeys(), BTScanOpaqueData::currPos, BTScanPosData::dir, if(), LOOK_AHEAD_DEFAULT_DISTANCE, Max, MaxIndexTuplesPerPage, BTReadPageState::maxoff, Min, BTReadPageState::minoff, BTReadPageState::offnum, IndexScanDescData::opaque, BTReadPageState::page, PageGetItem(), PageGetItemId(), BTReadPageState::rechecks, ScanDirectionIsBackward, ScanDirectionIsForward, BTReadPageState::skip, and BTReadPageState::targetdistance.

Referenced by _bt_checkkeys().

◆ _bt_compare_array_skey()

static int32 _bt_compare_array_skey	(	FmgrInfo *	orderproc,
		Datum	tupdatum,
		bool	tupnull,
		Datum	arrdatum,
		ScanKey	cur
	)

inlinestatic

Definition at line 201 of file nbtutils.c.

{
    int32       result = 0;
 
    Assert(cur->sk_strategy == BTEqualStrategyNumber);
 
    if (tupnull)                /* NULL tupdatum */
    {
        if (cur->sk_flags & SK_ISNULL)
            result = 0;         /* NULL "=" NULL */
        else if (cur->sk_flags & SK_BT_NULLS_FIRST)
            result = -1;        /* NULL "<" NOT_NULL */
        else
            result = 1;         /* NULL ">" NOT_NULL */
    }
    else if (cur->sk_flags & SK_ISNULL) /* NOT_NULL tupdatum, NULL arrdatum */
    {
        if (cur->sk_flags & SK_BT_NULLS_FIRST)
            result = 1;         /* NOT_NULL ">" NULL */
        else
            result = -1;        /* NOT_NULL "<" NULL */
    }
    else
    {
        /*
         * Like _bt_compare, we need to be careful of cross-type comparisons,
         * so the left value has to be the value that came from an index tuple
         */
        result = DatumGetInt32(FunctionCall2Coll(orderproc, cur->sk_collation,
                                                 tupdatum, arrdatum));
 
        /*
         * We flip the sign by following the obvious rule: flip whenever the
         * column is a DESC column.
         *
         * _bt_compare does it the wrong way around (flip when *ASC*) in order
         * to compensate for passing its orderproc arguments backwards.  We
         * don't need to play these games because we find it natural to pass
         * tupdatum as the left value (and arrdatum as the right value).
         */
        if (cur->sk_flags & SK_BT_DESC)
            INVERT_COMPARE_RESULT(result);
    }
 
    return result;
}

References Assert, BTEqualStrategyNumber, cur, DatumGetInt32(), FunctionCall2Coll(), INVERT_COMPARE_RESULT, SK_BT_DESC, SK_BT_NULLS_FIRST, and SK_ISNULL.

Referenced by _bt_advance_array_keys(), _bt_binsrch_array_skey(), and _bt_tuple_before_array_skeys().

◆ _bt_end_vacuum()

void _bt_end_vacuum ( Relation rel )

Definition at line 2641 of file nbtutils.c.

{
    int         i;
 
    LWLockAcquire(BtreeVacuumLock, LW_EXCLUSIVE);
 
    /* Find the array entry */
    for (i = 0; i < btvacinfo->num_vacuums; i++)
    {
        BTOneVacInfo *vac = &btvacinfo->vacuums[i];
 
        if (vac->relid.relId == rel->rd_lockInfo.lockRelId.relId &&
            vac->relid.dbId == rel->rd_lockInfo.lockRelId.dbId)
        {
            /* Remove it by shifting down the last entry */
            *vac = btvacinfo->vacuums[btvacinfo->num_vacuums - 1];
            btvacinfo->num_vacuums--;
            break;
        }
    }
 
    LWLockRelease(BtreeVacuumLock);
}

References btvacinfo, LockRelId::dbId, i, LockInfoData::lockRelId, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), BTVacInfo::num_vacuums, RelationData::rd_lockInfo, BTOneVacInfo::relid, LockRelId::relId, and BTVacInfo::vacuums.

Referenced by _bt_end_vacuum_callback(), and btbulkdelete().

◆ _bt_end_vacuum_callback()

void _bt_end_vacuum_callback	(	int	code,
		Datum	arg
	)

Definition at line 2669 of file nbtutils.c.

{
    _bt_end_vacuum((Relation) DatumGetPointer(arg));
}

References _bt_end_vacuum(), arg, and DatumGetPointer().

Referenced by btbulkdelete().

◆ _bt_freestack()

void _bt_freestack ( BTStack stack )

Definition at line 172 of file nbtutils.c.

{
    BTStack     ostack;
 
    while (stack != NULL)
    {
        ostack = stack;
        stack = stack->bts_parent;
        pfree(ostack);
    }
}

References BTStackData::bts_parent, and pfree().

Referenced by _bt_doinsert(), _bt_first(), and bt_rootdescend().

◆ _bt_keep_natts()

static int _bt_keep_natts	(	Relation	rel,
		IndexTuple	lastleft,
		IndexTuple	firstright,
		BTScanInsert	itup_key
	)

static

Definition at line 2958 of file nbtutils.c.

{
    int         nkeyatts = IndexRelationGetNumberOfKeyAttributes(rel);
    TupleDesc   itupdesc = RelationGetDescr(rel);
    int         keepnatts;
    ScanKey     scankey;
 
    /*
     * _bt_compare() treats truncated key attributes as having the value minus
     * infinity, which would break searches within !heapkeyspace indexes.  We
     * must still truncate away non-key attribute values, though.
     */
    if (!itup_key->heapkeyspace)
        return nkeyatts;
 
    scankey = itup_key->scankeys;
    keepnatts = 1;
    for (int attnum = 1; attnum <= nkeyatts; attnum++, scankey++)
    {
        Datum       datum1,
                    datum2;
        bool        isNull1,
                    isNull2;
 
        datum1 = index_getattr(lastleft, attnum, itupdesc, &isNull1);
        datum2 = index_getattr(firstright, attnum, itupdesc, &isNull2);
 
        if (isNull1 != isNull2)
            break;
 
        if (!isNull1 &&
            DatumGetInt32(FunctionCall2Coll(&scankey->sk_func,
                                            scankey->sk_collation,
                                            datum1,
                                            datum2)) != 0)
            break;
 
        keepnatts++;
    }
 
    /*
     * Assert that _bt_keep_natts_fast() agrees with us in passing.  This is
     * expected in an allequalimage index.
     */
    Assert(!itup_key->allequalimage ||
           keepnatts == _bt_keep_natts_fast(rel, lastleft, firstright));
 
    return keepnatts;
}

References _bt_keep_natts_fast(), BTScanInsertData::allequalimage, Assert, attnum, DatumGetInt32(), FunctionCall2Coll(), BTScanInsertData::heapkeyspace, index_getattr(), IndexRelationGetNumberOfKeyAttributes, RelationGetDescr, BTScanInsertData::scankeys, ScanKeyData::sk_collation, and ScanKeyData::sk_func.

Referenced by _bt_truncate().

◆ _bt_keep_natts_fast()

int _bt_keep_natts_fast	(	Relation	rel,
		IndexTuple	lastleft,
		IndexTuple	firstright
	)

Definition at line 3032 of file nbtutils.c.

{
    TupleDesc   itupdesc = RelationGetDescr(rel);
    int         keysz = IndexRelationGetNumberOfKeyAttributes(rel);
    int         keepnatts;
 
    keepnatts = 1;
    for (int attnum = 1; attnum <= keysz; attnum++)
    {
        Datum       datum1,
                    datum2;
        bool        isNull1,
                    isNull2;
        CompactAttribute *att;
 
        datum1 = index_getattr(lastleft, attnum, itupdesc, &isNull1);
        datum2 = index_getattr(firstright, attnum, itupdesc, &isNull2);
        att = TupleDescCompactAttr(itupdesc, attnum - 1);
 
        if (isNull1 != isNull2)
            break;
 
        if (!isNull1 &&
            !datum_image_eq(datum1, datum2, att->attbyval, att->attlen))
            break;
 
        keepnatts++;
    }
 
    return keepnatts;
}

References CompactAttribute::attbyval, CompactAttribute::attlen, attnum, datum_image_eq(), index_getattr(), IndexRelationGetNumberOfKeyAttributes, RelationGetDescr, and TupleDescCompactAttr().

Referenced by _bt_afternewitemoff(), _bt_bottomupdel_pass(), _bt_dedup_pass(), _bt_do_singleval(), _bt_keep_natts(), _bt_load(), _bt_split_penalty(), and _bt_strategy().

◆ _bt_killitems()

void _bt_killitems ( IndexScanDesc scan )

Definition at line 2333 of file nbtutils.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    Page        page;
    BTPageOpaque opaque;
    OffsetNumber minoff;
    OffsetNumber maxoff;
    int         i;
    int         numKilled = so->numKilled;
    bool        killedsomething = false;
    bool        droppedpin PG_USED_FOR_ASSERTS_ONLY;
 
    Assert(BTScanPosIsValid(so->currPos));
 
    /*
     * Always reset the scan state, so we don't look for same items on other
     * pages.
     */
    so->numKilled = 0;
 
    if (BTScanPosIsPinned(so->currPos))
    {
        /*
         * We have held the pin on this page since we read the index tuples,
         * so all we need to do is lock it.  The pin will have prevented
         * re-use of any TID on the page, so there is no need to check the
         * LSN.
         */
        droppedpin = false;
        _bt_lockbuf(scan->indexRelation, so->currPos.buf, BT_READ);
 
        page = BufferGetPage(so->currPos.buf);
    }
    else
    {
        Buffer      buf;
 
        droppedpin = true;
        /* Attempt to re-read the buffer, getting pin and lock. */
        buf = _bt_getbuf(scan->indexRelation, so->currPos.currPage, BT_READ);
 
        page = BufferGetPage(buf);
        if (BufferGetLSNAtomic(buf) == so->currPos.lsn)
            so->currPos.buf = buf;
        else
        {
            /* Modified while not pinned means hinting is not safe. */
            _bt_relbuf(scan->indexRelation, buf);
            return;
        }
    }
 
    opaque = BTPageGetOpaque(page);
    minoff = P_FIRSTDATAKEY(opaque);
    maxoff = PageGetMaxOffsetNumber(page);
 
    for (i = 0; i < numKilled; i++)
    {
        int         itemIndex = so->killedItems[i];
        BTScanPosItem *kitem = &so->currPos.items[itemIndex];
        OffsetNumber offnum = kitem->indexOffset;
 
        Assert(itemIndex >= so->currPos.firstItem &&
               itemIndex <= so->currPos.lastItem);
        if (offnum < minoff)
            continue;           /* pure paranoia */
        while (offnum <= maxoff)
        {
            ItemId      iid = PageGetItemId(page, offnum);
            IndexTuple  ituple = (IndexTuple) PageGetItem(page, iid);
            bool        killtuple = false;
 
            if (BTreeTupleIsPosting(ituple))
            {
                int         pi = i + 1;
                int         nposting = BTreeTupleGetNPosting(ituple);
                int         j;
 
                /*
                 * We rely on the convention that heap TIDs in the scanpos
                 * items array are stored in ascending heap TID order for a
                 * group of TIDs that originally came from a posting list
                 * tuple.  This convention even applies during backwards
                 * scans, where returning the TIDs in descending order might
                 * seem more natural.  This is about effectiveness, not
                 * correctness.
                 *
                 * Note that the page may have been modified in almost any way
                 * since we first read it (in the !droppedpin case), so it's
                 * possible that this posting list tuple wasn't a posting list
                 * tuple when we first encountered its heap TIDs.
                 */
                for (j = 0; j < nposting; j++)
                {
                    ItemPointer item = BTreeTupleGetPostingN(ituple, j);
 
                    if (!ItemPointerEquals(item, &kitem->heapTid))
                        break;  /* out of posting list loop */
 
                    /*
                     * kitem must have matching offnum when heap TIDs match,
                     * though only in the common case where the page can't
                     * have been concurrently modified
                     */
                    Assert(kitem->indexOffset == offnum || !droppedpin);
 
                    /*
                     * Read-ahead to later kitems here.
                     *
                     * We rely on the assumption that not advancing kitem here
                     * will prevent us from considering the posting list tuple
                     * fully dead by not matching its next heap TID in next
                     * loop iteration.
                     *
                     * If, on the other hand, this is the final heap TID in
                     * the posting list tuple, then tuple gets killed
                     * regardless (i.e. we handle the case where the last
                     * kitem is also the last heap TID in the last index tuple
                     * correctly -- posting tuple still gets killed).
                     */
                    if (pi < numKilled)
                        kitem = &so->currPos.items[so->killedItems[pi++]];
                }
 
                /*
                 * Don't bother advancing the outermost loop's int iterator to
                 * avoid processing killed items that relate to the same
                 * offnum/posting list tuple.  This micro-optimization hardly
                 * seems worth it.  (Further iterations of the outermost loop
                 * will fail to match on this same posting list's first heap
                 * TID instead, so we'll advance to the next offnum/index
                 * tuple pretty quickly.)
                 */
                if (j == nposting)
                    killtuple = true;
            }
            else if (ItemPointerEquals(&ituple->t_tid, &kitem->heapTid))
                killtuple = true;
 
            /*
             * Mark index item as dead, if it isn't already.  Since this
             * happens while holding a buffer lock possibly in shared mode,
             * it's possible that multiple processes attempt to do this
             * simultaneously, leading to multiple full-page images being sent
             * to WAL (if wal_log_hints or data checksums are enabled), which
             * is undesirable.
             */
            if (killtuple && !ItemIdIsDead(iid))
            {
                /* found the item/all posting list items */
                ItemIdMarkDead(iid);
                killedsomething = true;
                break;          /* out of inner search loop */
            }
            offnum = OffsetNumberNext(offnum);
        }
    }
 
    /*
     * Since this can be redone later if needed, mark as dirty hint.
     *
     * Whenever we mark anything LP_DEAD, we also set the page's
     * BTP_HAS_GARBAGE flag, which is likewise just a hint.  (Note that we
     * only rely on the page-level flag in !heapkeyspace indexes.)
     */
    if (killedsomething)
    {
        opaque->btpo_flags |= BTP_HAS_GARBAGE;
        MarkBufferDirtyHint(so->currPos.buf, true);
    }
 
    _bt_unlockbuf(scan->indexRelation, so->currPos.buf);
}

References _bt_getbuf(), _bt_lockbuf(), _bt_relbuf(), _bt_unlockbuf(), Assert, BT_READ, BTP_HAS_GARBAGE, BTPageGetOpaque, BTreeTupleGetNPosting(), BTreeTupleGetPostingN(), BTreeTupleIsPosting(), BTScanPosIsPinned, BTScanPosIsValid, buf, BTScanPosData::buf, BufferGetLSNAtomic(), BufferGetPage(), BTScanPosData::currPage, BTScanOpaqueData::currPos, BTScanPosData::firstItem, BTScanPosItem::heapTid, i, BTScanPosItem::indexOffset, IndexScanDescData::indexRelation, ItemIdIsDead, ItemIdMarkDead, ItemPointerEquals(), BTScanPosData::items, j, BTScanOpaqueData::killedItems, BTScanPosData::lsn, MarkBufferDirtyHint(), BTScanOpaqueData::numKilled, OffsetNumberNext, IndexScanDescData::opaque, P_FIRSTDATAKEY, PageGetItem(), PageGetItemId(), PageGetMaxOffsetNumber(), PG_USED_FOR_ASSERTS_ONLY, and IndexTupleData::t_tid.

Referenced by _bt_steppage(), btendscan(), btrescan(), and btrestrpos().

◆ _bt_mkscankey()

BTScanInsert _bt_mkscankey	(	Relation	rel,
		IndexTuple	itup
	)

Definition at line 80 of file nbtutils.c.

{
    BTScanInsert key;
    ScanKey     skey;
    TupleDesc   itupdesc;
    int         indnkeyatts;
    int16      *indoption;
    int         tupnatts;
    int         i;
 
    itupdesc = RelationGetDescr(rel);
    indnkeyatts = IndexRelationGetNumberOfKeyAttributes(rel);
    indoption = rel->rd_indoption;
    tupnatts = itup ? BTreeTupleGetNAtts(itup, rel) : 0;
 
    Assert(tupnatts <= IndexRelationGetNumberOfAttributes(rel));
 
    /*
     * We'll execute search using scan key constructed on key columns.
     * Truncated attributes and non-key attributes are omitted from the final
     * scan key.
     */
    key = palloc(offsetof(BTScanInsertData, scankeys) +
                 sizeof(ScanKeyData) * indnkeyatts);
    if (itup)
        _bt_metaversion(rel, &key->heapkeyspace, &key->allequalimage);
    else
    {
        /* Utility statement callers can set these fields themselves */
        key->heapkeyspace = true;
        key->allequalimage = false;
    }
    key->anynullkeys = false;   /* initial assumption */
    key->nextkey = false;       /* usual case, required by btinsert */
    key->backward = false;      /* usual case, required by btinsert */
    key->keysz = Min(indnkeyatts, tupnatts);
    key->scantid = key->heapkeyspace && itup ?
        BTreeTupleGetHeapTID(itup) : NULL;
    skey = key->scankeys;
    for (i = 0; i < indnkeyatts; i++)
    {
        FmgrInfo   *procinfo;
        Datum       arg;
        bool        null;
        int         flags;
 
        /*
         * We can use the cached (default) support procs since no cross-type
         * comparison can be needed.
         */
        procinfo = index_getprocinfo(rel, i + 1, BTORDER_PROC);
 
        /*
         * Key arguments built from truncated attributes (or when caller
         * provides no tuple) are defensively represented as NULL values. They
         * should never be used.
         */
        if (i < tupnatts)
            arg = index_getattr(itup, i + 1, itupdesc, &null);
        else
        {
            arg = (Datum) 0;
            null = true;
        }
        flags = (null ? SK_ISNULL : 0) | (indoption[i] << SK_BT_INDOPTION_SHIFT);
        ScanKeyEntryInitializeWithInfo(&skey[i],
                                       flags,
                                       (AttrNumber) (i + 1),
                                       InvalidStrategy,
                                       InvalidOid,
                                       rel->rd_indcollation[i],
                                       procinfo,
                                       arg);
        /* Record if any key attribute is NULL (or truncated) */
        if (null)
            key->anynullkeys = true;
    }
 
    /*
     * In NULLS NOT DISTINCT mode, we pretend that there are no null keys, so
     * that full uniqueness check is done.
     */
    if (rel->rd_index->indnullsnotdistinct)
        key->anynullkeys = false;
 
    return key;
}

References _bt_metaversion(), arg, Assert, BTORDER_PROC, BTreeTupleGetHeapTID(), BTreeTupleGetNAtts, i, index_getattr(), index_getprocinfo(), IndexRelationGetNumberOfAttributes, IndexRelationGetNumberOfKeyAttributes, InvalidOid, InvalidStrategy, sort-test::key, Min, palloc(), RelationData::rd_indcollation, RelationData::rd_index, RelationData::rd_indoption, RelationGetDescr, ScanKeyEntryInitializeWithInfo(), SK_BT_INDOPTION_SHIFT, and SK_ISNULL.

Referenced by _bt_doinsert(), _bt_leafbuild(), _bt_pagedel(), bt_mkscankey_pivotsearch(), bt_rootdescend(), tuplesort_begin_cluster(), and tuplesort_begin_index_btree().

◆ _bt_oppodir_checkkeys()

bool _bt_oppodir_checkkeys	(	IndexScanDesc	scan,
		ScanDirection	dir,
		IndexTuple	finaltup
	)

Definition at line 1782 of file nbtutils.c.

{
    Relation    rel = scan->indexRelation;
    TupleDesc   tupdesc = RelationGetDescr(rel);
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    int         nfinaltupatts = BTreeTupleGetNAtts(finaltup, rel);
    bool        continuescan;
    ScanDirection flipped = -dir;
    int         ikey = 0;
 
    Assert(so->numArrayKeys);
 
    _bt_check_compare(scan, flipped, finaltup, nfinaltupatts, tupdesc,
                      false, false, false, &continuescan, &ikey);
 
    if (!continuescan && so->keyData[ikey].sk_strategy != BTEqualStrategyNumber)
        return false;
 
    return true;
}

References _bt_check_compare(), Assert, BTEqualStrategyNumber, BTreeTupleGetNAtts, IndexScanDescData::indexRelation, BTScanOpaqueData::keyData, BTScanOpaqueData::numArrayKeys, IndexScanDescData::opaque, RelationGetDescr, and ScanKeyData::sk_strategy.

Referenced by _bt_advance_array_keys(), and _bt_readpage().

◆ _bt_rewind_nonrequired_arrays()

static void _bt_rewind_nonrequired_arrays	(	IndexScanDesc	scan,
		ScanDirection	dir
	)

static

Definition at line 542 of file nbtutils.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    int         arrayidx = 0;
 
    for (int ikey = 0; ikey < so->numberOfKeys; ikey++)
    {
        ScanKey     cur = so->keyData + ikey;
        BTArrayKeyInfo *array = NULL;
        int         first_elem_dir;
 
        if (!(cur->sk_flags & SK_SEARCHARRAY) ||
            cur->sk_strategy != BTEqualStrategyNumber)
            continue;
 
        array = &so->arrayKeys[arrayidx++];
        Assert(array->scan_key == ikey);
 
        if ((cur->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)))
            continue;
 
        if (ScanDirectionIsForward(dir))
            first_elem_dir = 0;
        else
            first_elem_dir = array->num_elems - 1;
 
        if (array->cur_elem != first_elem_dir)
        {
            array->cur_elem = first_elem_dir;
            cur->sk_argument = array->elem_values[first_elem_dir];
        }
    }
}

References BTScanOpaqueData::arrayKeys, Assert, BTEqualStrategyNumber, cur, BTArrayKeyInfo::cur_elem, BTArrayKeyInfo::elem_values, for(), BTScanOpaqueData::keyData, BTArrayKeyInfo::num_elems, BTScanOpaqueData::numberOfKeys, IndexScanDescData::opaque, BTArrayKeyInfo::scan_key, ScanDirectionIsForward, SK_BT_REQBKWD, SK_BT_REQFWD, and SK_SEARCHARRAY.

Referenced by _bt_advance_array_keys().

◆ _bt_start_array_keys()

void _bt_start_array_keys	(	IndexScanDesc	scan,
		ScanDirection	dir
	)

Definition at line 413 of file nbtutils.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
    int         i;
 
    Assert(so->numArrayKeys);
    Assert(so->qual_ok);
 
    for (i = 0; i < so->numArrayKeys; i++)
    {
        BTArrayKeyInfo *curArrayKey = &so->arrayKeys[i];
        ScanKey     skey = &so->keyData[curArrayKey->scan_key];
 
        Assert(curArrayKey->num_elems > 0);
        Assert(skey->sk_flags & SK_SEARCHARRAY);
 
        if (ScanDirectionIsBackward(dir))
            curArrayKey->cur_elem = curArrayKey->num_elems - 1;
        else
            curArrayKey->cur_elem = 0;
        skey->sk_argument = curArrayKey->elem_values[curArrayKey->cur_elem];
    }
    so->scanBehind = so->oppositeDirCheck = false;  /* reset */
}

References BTScanOpaqueData::arrayKeys, Assert, BTArrayKeyInfo::cur_elem, BTArrayKeyInfo::elem_values, i, BTScanOpaqueData::keyData, BTArrayKeyInfo::num_elems, BTScanOpaqueData::numArrayKeys, IndexScanDescData::opaque, BTScanOpaqueData::oppositeDirCheck, BTScanOpaqueData::qual_ok, BTArrayKeyInfo::scan_key, BTScanOpaqueData::scanBehind, ScanDirectionIsBackward, ScanKeyData::sk_argument, ScanKeyData::sk_flags, and SK_SEARCHARRAY.

Referenced by _bt_advance_array_keys_increment(), _bt_first(), and btrestrpos().

◆ _bt_start_prim_scan()

bool _bt_start_prim_scan	(	IndexScanDesc	scan,
		ScanDirection	dir
	)

Definition at line 743 of file nbtutils.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
 
    Assert(so->numArrayKeys);
 
    so->scanBehind = so->oppositeDirCheck = false;  /* reset */
 
    /*
     * Array keys are advanced within _bt_checkkeys when the scan reaches the
     * leaf level (more precisely, they're advanced when the scan reaches the
     * end of each distinct set of array elements).  This process avoids
     * repeat access to leaf pages (across multiple primitive index scans) by
     * advancing the scan's array keys when it allows the primitive index scan
     * to find nearby matching tuples (or when it eliminates ranges of array
     * key space that can't possibly be satisfied by any index tuple).
     *
     * _bt_checkkeys sets a simple flag variable to schedule another primitive
     * index scan.  The flag tells us what to do.
     *
     * We cannot rely on _bt_first always reaching _bt_checkkeys.  There are
     * various cases where that won't happen.  For example, if the index is
     * completely empty, then _bt_first won't call _bt_readpage/_bt_checkkeys.
     * We also don't expect a call to _bt_checkkeys during searches for a
     * non-existent value that happens to be lower/higher than any existing
     * value in the index.
     *
     * We don't require special handling for these cases -- we don't need to
     * be explicitly instructed to _not_ perform another primitive index scan.
     * It's up to code under the control of _bt_first to always set the flag
     * when another primitive index scan will be required.
     *
     * This works correctly, even with the tricky cases listed above, which
     * all involve access to leaf pages "near the boundaries of the key space"
     * (whether it's from a leftmost/rightmost page, or an imaginary empty
     * leaf root page).  If _bt_checkkeys cannot be reached by a primitive
     * index scan for one set of array keys, then it also won't be reached for
     * any later set ("later" in terms of the direction that we scan the index
     * and advance the arrays).  The array keys won't have advanced in these
     * cases, but that's the correct behavior (even _bt_advance_array_keys
     * won't always advance the arrays at the point they become "exhausted").
     */
    if (so->needPrimScan)
    {
        Assert(_bt_verify_arrays_bt_first(scan, dir));
 
        /*
         * Flag was set -- must call _bt_first again, which will reset the
         * scan's needPrimScan flag
         */
        return true;
    }
 
    /* The top-level index scan ran out of tuples in this scan direction */
    if (scan->parallel_scan != NULL)
        _bt_parallel_done(scan);
 
    return false;
}

References _bt_parallel_done(), Assert, BTScanOpaqueData::needPrimScan, BTScanOpaqueData::numArrayKeys, IndexScanDescData::opaque, BTScanOpaqueData::oppositeDirCheck, IndexScanDescData::parallel_scan, and BTScanOpaqueData::scanBehind.

◆ _bt_start_vacuum()

BTCycleId _bt_start_vacuum ( Relation rel )

Definition at line 2584 of file nbtutils.c.

{
    BTCycleId   result;
    int         i;
    BTOneVacInfo *vac;
 
    LWLockAcquire(BtreeVacuumLock, LW_EXCLUSIVE);
 
    /*
     * Assign the next cycle ID, being careful to avoid zero as well as the
     * reserved high values.
     */
    result = ++(btvacinfo->cycle_ctr);
    if (result == 0 || result > MAX_BT_CYCLE_ID)
        result = btvacinfo->cycle_ctr = 1;
 
    /* Let's just make sure there's no entry already for this index */
    for (i = 0; i < btvacinfo->num_vacuums; i++)
    {
        vac = &btvacinfo->vacuums[i];
        if (vac->relid.relId == rel->rd_lockInfo.lockRelId.relId &&
            vac->relid.dbId == rel->rd_lockInfo.lockRelId.dbId)
        {
            /*
             * Unlike most places in the backend, we have to explicitly
             * release our LWLock before throwing an error.  This is because
             * we expect _bt_end_vacuum() to be called before transaction
             * abort cleanup can run to release LWLocks.
             */
            LWLockRelease(BtreeVacuumLock);
            elog(ERROR, "multiple active vacuums for index \"%s\"",
                 RelationGetRelationName(rel));
        }
    }
 
    /* OK, add an entry */
    if (btvacinfo->num_vacuums >= btvacinfo->max_vacuums)
    {
        LWLockRelease(BtreeVacuumLock);
        elog(ERROR, "out of btvacinfo slots");
    }
    vac = &btvacinfo->vacuums[btvacinfo->num_vacuums];
    vac->relid = rel->rd_lockInfo.lockRelId;
    vac->cycleid = result;
    btvacinfo->num_vacuums++;
 
    LWLockRelease(BtreeVacuumLock);
    return result;
}

References btvacinfo, BTVacInfo::cycle_ctr, BTOneVacInfo::cycleid, LockRelId::dbId, elog, ERROR, i, LockInfoData::lockRelId, LW_EXCLUSIVE, LWLockAcquire(), LWLockRelease(), MAX_BT_CYCLE_ID, BTVacInfo::max_vacuums, BTVacInfo::num_vacuums, RelationData::rd_lockInfo, RelationGetRelationName, BTOneVacInfo::relid, LockRelId::relId, and BTVacInfo::vacuums.

Referenced by btbulkdelete().

◆ _bt_truncate()

IndexTuple _bt_truncate	(	Relation	rel,
		IndexTuple	lastleft,
		IndexTuple	firstright,
		BTScanInsert	itup_key
	)

Definition at line 2813 of file nbtutils.c.

{
    TupleDesc   itupdesc = RelationGetDescr(rel);
    int16       nkeyatts = IndexRelationGetNumberOfKeyAttributes(rel);
    int         keepnatts;
    IndexTuple  pivot;
    IndexTuple  tidpivot;
    ItemPointer pivotheaptid;
    Size        newsize;
 
    /*
     * We should only ever truncate non-pivot tuples from leaf pages.  It's
     * never okay to truncate when splitting an internal page.
     */
    Assert(!BTreeTupleIsPivot(lastleft) && !BTreeTupleIsPivot(firstright));
 
    /* Determine how many attributes must be kept in truncated tuple */
    keepnatts = _bt_keep_natts(rel, lastleft, firstright, itup_key);
 
#ifdef DEBUG_NO_TRUNCATE
    /* Force truncation to be ineffective for testing purposes */
    keepnatts = nkeyatts + 1;
#endif
 
    pivot = index_truncate_tuple(itupdesc, firstright,
                                 Min(keepnatts, nkeyatts));
 
    if (BTreeTupleIsPosting(pivot))
    {
        /*
         * index_truncate_tuple() just returns a straight copy of firstright
         * when it has no attributes to truncate.  When that happens, we may
         * need to truncate away a posting list here instead.
         */
        Assert(keepnatts == nkeyatts || keepnatts == nkeyatts + 1);
        Assert(IndexRelationGetNumberOfAttributes(rel) == nkeyatts);
        pivot->t_info &= ~INDEX_SIZE_MASK;
        pivot->t_info |= MAXALIGN(BTreeTupleGetPostingOffset(firstright));
    }
 
    /*
     * If there is a distinguishing key attribute within pivot tuple, we're
     * done
     */
    if (keepnatts <= nkeyatts)
    {
        BTreeTupleSetNAtts(pivot, keepnatts, false);
        return pivot;
    }
 
    /*
     * We have to store a heap TID in the new pivot tuple, since no non-TID
     * key attribute value in firstright distinguishes the right side of the
     * split from the left side.  nbtree conceptualizes this case as an
     * inability to truncate away any key attributes, since heap TID is
     * treated as just another key attribute (despite lacking a pg_attribute
     * entry).
     *
     * Use enlarged space that holds a copy of pivot.  We need the extra space
     * to store a heap TID at the end (using the special pivot tuple
     * representation).  Note that the original pivot already has firstright's
     * possible posting list/non-key attribute values removed at this point.
     */
    newsize = MAXALIGN(IndexTupleSize(pivot)) + MAXALIGN(sizeof(ItemPointerData));
    tidpivot = palloc0(newsize);
    memcpy(tidpivot, pivot, MAXALIGN(IndexTupleSize(pivot)));
    /* Cannot leak memory here */
    pfree(pivot);
 
    /*
     * Store all of firstright's key attribute values plus a tiebreaker heap
     * TID value in enlarged pivot tuple
     */
    tidpivot->t_info &= ~INDEX_SIZE_MASK;
    tidpivot->t_info |= newsize;
    BTreeTupleSetNAtts(tidpivot, nkeyatts, true);
    pivotheaptid = BTreeTupleGetHeapTID(tidpivot);
 
    /*
     * Lehman & Yao use lastleft as the leaf high key in all cases, but don't
     * consider suffix truncation.  It seems like a good idea to follow that
     * example in cases where no truncation takes place -- use lastleft's heap
     * TID.  (This is also the closest value to negative infinity that's
     * legally usable.)
     */
    ItemPointerCopy(BTreeTupleGetMaxHeapTID(lastleft), pivotheaptid);
 
    /*
     * We're done.  Assert() that heap TID invariants hold before returning.
     *
     * Lehman and Yao require that the downlink to the right page, which is to
     * be inserted into the parent page in the second phase of a page split be
     * a strict lower bound on items on the right page, and a non-strict upper
     * bound for items on the left page.  Assert that heap TIDs follow these
     * invariants, since a heap TID value is apparently needed as a
     * tiebreaker.
     */
#ifndef DEBUG_NO_TRUNCATE
    Assert(ItemPointerCompare(BTreeTupleGetMaxHeapTID(lastleft),
                              BTreeTupleGetHeapTID(firstright)) < 0);
    Assert(ItemPointerCompare(pivotheaptid,
                              BTreeTupleGetHeapTID(lastleft)) >= 0);
    Assert(ItemPointerCompare(pivotheaptid,
                              BTreeTupleGetHeapTID(firstright)) < 0);
#else
 
    /*
     * Those invariants aren't guaranteed to hold for lastleft + firstright
     * heap TID attribute values when they're considered here only because
     * DEBUG_NO_TRUNCATE is defined (a heap TID is probably not actually
     * needed as a tiebreaker).  DEBUG_NO_TRUNCATE must therefore use a heap
     * TID value that always works as a strict lower bound for items to the
     * right.  In particular, it must avoid using firstright's leading key
     * attribute values along with lastleft's heap TID value when lastleft's
     * TID happens to be greater than firstright's TID.
     */
    ItemPointerCopy(BTreeTupleGetHeapTID(firstright), pivotheaptid);
 
    /*
     * Pivot heap TID should never be fully equal to firstright.  Note that
     * the pivot heap TID will still end up equal to lastleft's heap TID when
     * that's the only usable value.
     */
    ItemPointerSetOffsetNumber(pivotheaptid,
                               OffsetNumberPrev(ItemPointerGetOffsetNumber(pivotheaptid)));
    Assert(ItemPointerCompare(pivotheaptid,
                              BTreeTupleGetHeapTID(firstright)) < 0);
#endif
 
    return tidpivot;
}

References _bt_keep_natts(), Assert, BTreeTupleGetHeapTID(), BTreeTupleGetMaxHeapTID(), BTreeTupleGetPostingOffset(), BTreeTupleIsPivot(), BTreeTupleIsPosting(), BTreeTupleSetNAtts(), index_truncate_tuple(), IndexRelationGetNumberOfAttributes, IndexRelationGetNumberOfKeyAttributes, IndexTupleSize, ItemPointerCompare(), ItemPointerCopy(), ItemPointerGetOffsetNumber(), ItemPointerSetOffsetNumber(), MAXALIGN, Min, OffsetNumberPrev, palloc0(), pfree(), RelationGetDescr, and IndexTupleData::t_info.

Referenced by _bt_buildadd(), and _bt_split().

◆ _bt_tuple_before_array_skeys()

static bool _bt_tuple_before_array_skeys	(	IndexScanDesc	scan,
		ScanDirection	dir,
		IndexTuple	tuple,
		TupleDesc	tupdesc,
		int	tupnatts,
		bool	readpagetup,
		int	sktrig,
		bool *	scanBehind
	)

static

Definition at line 619 of file nbtutils.c.

{
    BTScanOpaque so = (BTScanOpaque) scan->opaque;
 
    Assert(so->numArrayKeys);
    Assert(so->numberOfKeys);
    Assert(sktrig == 0 || readpagetup);
    Assert(!readpagetup || scanBehind == NULL);
 
    if (scanBehind)
        *scanBehind = false;
 
    for (int ikey = sktrig; ikey < so->numberOfKeys; ikey++)
    {
        ScanKey     cur = so->keyData + ikey;
        Datum       tupdatum;
        bool        tupnull;
        int32       result;
 
        /* readpagetup calls require one ORDER proc comparison (at most) */
        Assert(!readpagetup || ikey == sktrig);
 
        /*
         * Once we reach a non-required scan key, we're completely done.
         *
         * Note: we deliberately don't consider the scan direction here.
         * _bt_advance_array_keys caller requires that we track *scanBehind
         * without concern for scan direction.
         */
        if ((cur->sk_flags & (SK_BT_REQFWD | SK_BT_REQBKWD)) == 0)
        {
            Assert(!readpagetup);
            Assert(ikey > sktrig || ikey == 0);
            return false;
        }
 
        if (cur->sk_attno > tupnatts)
        {
            Assert(!readpagetup);
 
            /*
             * When we reach a high key's truncated attribute, assume that the
             * tuple attribute's value is >= the scan's equality constraint
             * scan keys (but set *scanBehind to let interested callers know
             * that a truncated attribute might have affected our answer).
             */
            if (scanBehind)
                *scanBehind = true;
 
            return false;
        }
 
        /*
         * Deal with inequality strategy scan keys that _bt_check_compare set
         * continuescan=false for
         */
        if (cur->sk_strategy != BTEqualStrategyNumber)
        {
            /*
             * When _bt_check_compare indicated that a required inequality
             * scan key wasn't satisfied, there's no need to verify anything;
             * caller always calls _bt_advance_array_keys with this sktrig.
             */
            if (readpagetup)
                return false;
 
            /*
             * Otherwise we can't give up, since we must check all required
             * scan keys (required in either direction) in order to correctly
             * track *scanBehind for caller
             */
            continue;
        }
 
        tupdatum = index_getattr(tuple, cur->sk_attno, tupdesc, &tupnull);
 
        result = _bt_compare_array_skey(&so->orderProcs[ikey],
                                        tupdatum, tupnull,
                                        cur->sk_argument, cur);
 
        /*
         * Does this comparison indicate that caller must _not_ advance the
         * scan's arrays just yet?
         */
        if ((ScanDirectionIsForward(dir) && result < 0) ||
            (ScanDirectionIsBackward(dir) && result > 0))
            return true;
 
        /*
         * Does this comparison indicate that caller should now advance the
         * scan's arrays?  (Must be if we get here during a readpagetup call.)
         */
        if (readpagetup || result != 0)
        {
            Assert(result != 0);
            return false;
        }
 
        /*
         * Inconclusive -- need to check later scan keys, too.
         *
         * This must be a finaltup precheck, or a call made from an assertion.
         */
        Assert(result == 0);
    }
 
    Assert(!readpagetup);
 
    return false;
}

References _bt_compare_array_skey(), Assert, BTEqualStrategyNumber, cur, index_getattr(), BTScanOpaqueData::keyData, BTScanOpaqueData::numArrayKeys, BTScanOpaqueData::numberOfKeys, IndexScanDescData::opaque, BTScanOpaqueData::orderProcs, ScanDirectionIsBackward, ScanDirectionIsForward, SK_BT_REQBKWD, and SK_BT_REQFWD.

Referenced by _bt_advance_array_keys(), _bt_checkkeys(), and _bt_checkkeys_look_ahead().

◆ _bt_vacuum_cycleid()

BTCycleId _bt_vacuum_cycleid ( Relation rel )

Definition at line 2550 of file nbtutils.c.

{
    BTCycleId   result = 0;
    int         i;
 
    /* Share lock is enough since this is a read-only operation */
    LWLockAcquire(BtreeVacuumLock, LW_SHARED);
 
    for (i = 0; i < btvacinfo->num_vacuums; i++)
    {
        BTOneVacInfo *vac = &btvacinfo->vacuums[i];
 
        if (vac->relid.relId == rel->rd_lockInfo.lockRelId.relId &&
            vac->relid.dbId == rel->rd_lockInfo.lockRelId.dbId)
        {
            result = vac->cycleid;
            break;
        }
    }
 
    LWLockRelease(BtreeVacuumLock);
    return result;
}

References btvacinfo, BTOneVacInfo::cycleid, LockRelId::dbId, i, LockInfoData::lockRelId, LW_SHARED, LWLockAcquire(), LWLockRelease(), BTVacInfo::num_vacuums, RelationData::rd_lockInfo, BTOneVacInfo::relid, LockRelId::relId, and BTVacInfo::vacuums.

Referenced by _bt_split().

◆ btbuildphasename()

char * btbuildphasename ( int64 phasenum )

Definition at line 2765 of file nbtutils.c.

{
    switch (phasenum)
    {
        case PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE:
            return "initializing";
        case PROGRESS_BTREE_PHASE_INDEXBUILD_TABLESCAN:
            return "scanning table";
        case PROGRESS_BTREE_PHASE_PERFORMSORT_1:
            return "sorting live tuples";
        case PROGRESS_BTREE_PHASE_PERFORMSORT_2:
            return "sorting dead tuples";
        case PROGRESS_BTREE_PHASE_LEAF_LOAD:
            return "loading tuples in tree";
        default:
            return NULL;
    }
}

References PROGRESS_BTREE_PHASE_INDEXBUILD_TABLESCAN, PROGRESS_BTREE_PHASE_LEAF_LOAD, PROGRESS_BTREE_PHASE_PERFORMSORT_1, PROGRESS_BTREE_PHASE_PERFORMSORT_2, and PROGRESS_CREATEIDX_SUBPHASE_INITIALIZE.

Referenced by bthandler().

◆ btoptions()

bytea * btoptions	(	Datum	reloptions,
		bool	validate
	)

Definition at line 2719 of file nbtutils.c.

{
    static const relopt_parse_elt tab[] = {
        {"fillfactor", RELOPT_TYPE_INT, offsetof(BTOptions, fillfactor)},
        {"vacuum_cleanup_index_scale_factor", RELOPT_TYPE_REAL,
        offsetof(BTOptions, vacuum_cleanup_index_scale_factor)},
        {"deduplicate_items", RELOPT_TYPE_BOOL,
        offsetof(BTOptions, deduplicate_items)}
    };
 
    return (bytea *) build_reloptions(reloptions, validate,
                                      RELOPT_KIND_BTREE,
                                      sizeof(BTOptions),
                                      tab, lengthof(tab));
}

References build_reloptions(), fillfactor, lengthof, RELOPT_KIND_BTREE, RELOPT_TYPE_BOOL, RELOPT_TYPE_INT, and RELOPT_TYPE_REAL.

Referenced by bthandler().

◆ btproperty()

bool btproperty	(	Oid	index_oid,
		int	attno,
		IndexAMProperty	prop,
		const char *	propname,
		bool *	res,
		bool *	isnull
	)

Definition at line 2742 of file nbtutils.c.

{
    switch (prop)
    {
        case AMPROP_RETURNABLE:
            /* answer only for columns, not AM or whole index */
            if (attno == 0)
                return false;
            /* otherwise, btree can always return data */
            *res = true;
            return true;
 
        default:
            return false;       /* punt to generic code */
    }
}

References AMPROP_RETURNABLE, and res.

Referenced by bthandler().

◆ BTreeShmemInit()

void BTreeShmemInit ( void )

Definition at line 2691 of file nbtutils.c.

{
    bool        found;
 
    btvacinfo = (BTVacInfo *) ShmemInitStruct("BTree Vacuum State",
                                              BTreeShmemSize(),
                                              &found);
 
    if (!IsUnderPostmaster)
    {
        /* Initialize shared memory area */
        Assert(!found);
 
        /*
         * It doesn't really matter what the cycle counter starts at, but
         * having it always start the same doesn't seem good.  Seed with
         * low-order bits of time() instead.
         */
        btvacinfo->cycle_ctr = (BTCycleId) time(NULL);
 
        btvacinfo->num_vacuums = 0;
        btvacinfo->max_vacuums = MaxBackends;
    }
    else
        Assert(found);
}

References Assert, BTreeShmemSize(), btvacinfo, BTVacInfo::cycle_ctr, IsUnderPostmaster, BTVacInfo::max_vacuums, MaxBackends, BTVacInfo::num_vacuums, and ShmemInitStruct().

Referenced by CreateOrAttachShmemStructs().

◆ BTreeShmemSize()

Size BTreeShmemSize ( void )

Definition at line 2678 of file nbtutils.c.

{
    Size        size;
 
    size = offsetof(BTVacInfo, vacuums);
    size = add_size(size, mul_size(MaxBackends, sizeof(BTOneVacInfo)));
    return size;
}

References add_size(), MaxBackends, mul_size(), and size.

Referenced by BTreeShmemInit(), and CalculateShmemSize().

Variable Documentation

◆ btvacinfo

BTVacInfo* btvacinfo

static

Definition at line 2537 of file nbtutils.c.

Referenced by _bt_end_vacuum(), _bt_start_vacuum(), _bt_vacuum_cycleid(), and BTreeShmemInit().

Data Structures

Macros

Typedefs

Functions

Variables

Macro Definition Documentation

◆ LOOK_AHEAD_DEFAULT_DISTANCE

◆ LOOK_AHEAD_REQUIRED_RECHECKS

Typedef Documentation

◆ BTOneVacInfo

◆ BTVacInfo

Function Documentation

◆ _bt_advance_array_keys()

◆ _bt_advance_array_keys_increment()

◆ _bt_allequalimage()

◆ _bt_binsrch_array_skey()

◆ _bt_check_compare()

◆ _bt_check_natts()

◆ _bt_check_rowcompare()

◆ _bt_check_third_page()

◆ _bt_checkkeys()

◆ _bt_checkkeys_look_ahead()

◆ _bt_compare_array_skey()

◆ _bt_end_vacuum()

◆ _bt_end_vacuum_callback()

◆ _bt_freestack()

◆ _bt_keep_natts()

◆ _bt_keep_natts_fast()

◆ _bt_killitems()

◆ _bt_mkscankey()

◆ _bt_oppodir_checkkeys()

◆ _bt_rewind_nonrequired_arrays()

◆ _bt_start_array_keys()

◆ _bt_start_prim_scan()

◆ _bt_start_vacuum()

◆ _bt_truncate()

◆ _bt_tuple_before_array_skeys()

◆ _bt_vacuum_cycleid()

◆ btbuildphasename()

◆ btoptions()

◆ btproperty()

◆ BTreeShmemInit()

◆ BTreeShmemSize()

Variable Documentation

◆ btvacinfo