nodeIndexonlyscan.c File Reference

#include "postgres.h"
#include "access/genam.h"
#include "access/htup_details.h"
#include "access/relscan.h"
#include "access/tableam.h"
#include "access/tupdesc.h"
#include "access/visibilitymap.h"
#include "catalog/pg_type.h"
#include "executor/executor.h"
#include "executor/instrument.h"
#include "executor/nodeIndexonlyscan.h"
#include "executor/nodeIndexscan.h"
#include "miscadmin.h"
#include "storage/bufmgr.h"
#include "storage/predicate.h"
#include "utils/builtins.h"
#include "utils/rel.h"

Include dependency graph for nodeIndexonlyscan.c:

Go to the source code of this file.

Functions
static TupleTableSlot *	IndexOnlyNext (IndexOnlyScanState *node)
static void	StoreIndexTuple (IndexOnlyScanState *node, TupleTableSlot *slot, IndexScanDesc scandesc)
static bool	IndexOnlyRecheck (IndexOnlyScanState *node, TupleTableSlot *slot)
static TupleTableSlot *	ExecIndexOnlyScan (PlanState *pstate)
void	ExecReScanIndexOnlyScan (IndexOnlyScanState *node)
void	ExecEndIndexOnlyScan (IndexOnlyScanState *node)
void	ExecIndexOnlyMarkPos (IndexOnlyScanState *node)
void	ExecIndexOnlyRestrPos (IndexOnlyScanState *node)
IndexOnlyScanState *	ExecInitIndexOnlyScan (IndexOnlyScan *node, EState *estate, int eflags)
void	ExecIndexOnlyScanEstimate (IndexOnlyScanState *node, ParallelContext *pcxt)
void	ExecIndexOnlyScanInitializeDSM (IndexOnlyScanState *node, ParallelContext *pcxt)
void	ExecIndexOnlyScanReInitializeDSM (IndexOnlyScanState *node, ParallelContext *pcxt)
void	ExecIndexOnlyScanInitializeWorker (IndexOnlyScanState *node, ParallelWorkerContext *pwcxt)
void	ExecIndexOnlyScanInstrumentEstimate (IndexOnlyScanState *node, ParallelContext *pcxt)
void	ExecIndexOnlyScanInstrumentInitDSM (IndexOnlyScanState *node, ParallelContext *pcxt)
void	ExecIndexOnlyScanInstrumentInitWorker (IndexOnlyScanState *node, ParallelWorkerContext *pwcxt)
void	ExecIndexOnlyScanRetrieveInstrumentation (IndexOnlyScanState *node)

Function Documentation

ExecEndIndexOnlyScan()

void ExecEndIndexOnlyScan

(

IndexOnlyScanState *

node

)

Definition at line 407 of file nodeIndexonlyscan.c.

{
    Relation    indexRelationDesc;
    IndexScanDesc indexScanDesc;
 
    /*
     * extract information from the node
     */
    indexRelationDesc = node->ioss_RelationDesc;
    indexScanDesc = node->ioss_ScanDesc;
 
    /* Release VM buffer pin, if any. */
    if (node->ioss_VMBuffer != InvalidBuffer)
    {
        ReleaseBuffer(node->ioss_VMBuffer);
        node->ioss_VMBuffer = InvalidBuffer;
    }
 
    /*
     * When ending a parallel worker, copy the statistics gathered by the
     * worker back into shared memory so that it can be picked up by the main
     * process to report in EXPLAIN ANALYZE
     */
    if (node->ioss_SharedInfo != NULL && IsParallelWorker())
    {
        IndexScanInstrumentation *winstrument;
 
        Assert(ParallelWorkerNumber < node->ioss_SharedInfo->num_workers);
        winstrument = &node->ioss_SharedInfo->winstrument[ParallelWorkerNumber];
 
        /*
         * We have to accumulate the stats rather than performing a memcpy.
         * When a Gather/GatherMerge node finishes it will perform planner
         * shutdown on the workers.  On rescan it will spin up new workers
         * which will have a new IndexOnlyScanState and zeroed stats.
         */
        winstrument->nsearches += node->ioss_Instrument->nsearches;
    }
 
    /*
     * close the index relation (no-op if we didn't open it)
     */
    if (indexScanDesc)
        index_endscan(indexScanDesc);
    if (indexRelationDesc)
        index_close(indexRelationDesc, NoLock);
}

References Assert, fb(), index_close(), index_endscan(), InvalidBuffer, IndexOnlyScanState::ioss_Instrument, IndexOnlyScanState::ioss_RelationDesc, IndexOnlyScanState::ioss_ScanDesc, IndexOnlyScanState::ioss_SharedInfo, IndexOnlyScanState::ioss_VMBuffer, IsParallelWorker, NoLock, IndexScanInstrumentation::nsearches, ParallelWorkerNumber, ReleaseBuffer(), and SharedIndexScanInstrumentation::winstrument.

Referenced by ExecEndNode().

ExecIndexOnlyMarkPos()

void ExecIndexOnlyMarkPos

(

IndexOnlyScanState *

node

)

Definition at line 463 of file nodeIndexonlyscan.c.

{
    EState     *estate = node->ss.ps.state;
    EPQState   *epqstate = estate->es_epq_active;
 
    if (epqstate != NULL)
    {
        /*
         * We are inside an EvalPlanQual recheck.  If a test tuple exists for
         * this relation, then we shouldn't access the index at all.  We would
         * instead need to save, and later restore, the state of the
         * relsubs_done flag, so that re-fetching the test tuple is possible.
         * However, given the assumption that no caller sets a mark at the
         * start of the scan, we can only get here with relsubs_done[i]
         * already set, and so no state need be saved.
         */
        Index       scanrelid = ((Scan *) node->ss.ps.plan)->scanrelid;
 
        Assert(scanrelid > 0);
        if (epqstate->relsubs_slot[scanrelid - 1] != NULL ||
            epqstate->relsubs_rowmark[scanrelid - 1] != NULL)
        {
            /* Verify the claim above */
            if (!epqstate->relsubs_done[scanrelid - 1])
                elog(ERROR, "unexpected ExecIndexOnlyMarkPos call in EPQ recheck");
            return;
        }
    }
 
    index_markpos(node->ioss_ScanDesc);
}

References Assert, elog, ERROR, EState::es_epq_active, fb(), index_markpos(), IndexOnlyScanState::ioss_ScanDesc, PlanState::plan, ScanState::ps, EPQState::relsubs_done, EPQState::relsubs_rowmark, EPQState::relsubs_slot, IndexOnlyScanState::ss, and PlanState::state.

Referenced by ExecMarkPos().

ExecIndexOnlyRestrPos()

void ExecIndexOnlyRestrPos

(

IndexOnlyScanState *

node

)

Definition at line 500 of file nodeIndexonlyscan.c.

{
    EState     *estate = node->ss.ps.state;
    EPQState   *epqstate = estate->es_epq_active;
 
    if (estate->es_epq_active != NULL)
    {
        /* See comments in ExecIndexMarkPos */
        Index       scanrelid = ((Scan *) node->ss.ps.plan)->scanrelid;
 
        Assert(scanrelid > 0);
        if (epqstate->relsubs_slot[scanrelid - 1] != NULL ||
            epqstate->relsubs_rowmark[scanrelid - 1] != NULL)
        {
            /* Verify the claim above */
            if (!epqstate->relsubs_done[scanrelid - 1])
                elog(ERROR, "unexpected ExecIndexOnlyRestrPos call in EPQ recheck");
            return;
        }
    }
 
    index_restrpos(node->ioss_ScanDesc);
}

References Assert, elog, ERROR, EState::es_epq_active, fb(), index_restrpos(), IndexOnlyScanState::ioss_ScanDesc, PlanState::plan, ScanState::ps, EPQState::relsubs_done, EPQState::relsubs_rowmark, EPQState::relsubs_slot, IndexOnlyScanState::ss, and PlanState::state.

Referenced by ExecRestrPos().

ExecIndexOnlyScan()

static TupleTableSlot * ExecIndexOnlyScan ( PlanState *  pstate )

static

Definition at line 345 of file nodeIndexonlyscan.c.

{
    IndexOnlyScanState *node = castNode(IndexOnlyScanState, pstate);
 
    /*
     * If we have runtime keys and they've not already been set up, do it now.
     */
    if (node->ioss_NumRuntimeKeys != 0 && !node->ioss_RuntimeKeysReady)
        ExecReScan((PlanState *) node);
 
    return ExecScan(&node->ss,
                    (ExecScanAccessMtd) IndexOnlyNext,
                    (ExecScanRecheckMtd) IndexOnlyRecheck);
}

References castNode, ExecReScan(), ExecScan(), IndexOnlyNext(), IndexOnlyRecheck(), IndexOnlyScanState::ioss_NumRuntimeKeys, IndexOnlyScanState::ioss_RuntimeKeysReady, and IndexOnlyScanState::ss.

Referenced by ExecInitIndexOnlyScan().

ExecIndexOnlyScanEstimate()

void ExecIndexOnlyScanEstimate	(	IndexOnlyScanState *	node,
		ParallelContext *	pcxt
	)

Definition at line 740 of file nodeIndexonlyscan.c.

{
    EState     *estate = node->ss.ps.state;
 
    node->ioss_PscanLen = index_parallelscan_estimate(node->ioss_RelationDesc,
                                                      node->ioss_NumScanKeys,
                                                      node->ioss_NumOrderByKeys,
                                                      estate->es_snapshot);
    shm_toc_estimate_chunk(&pcxt->estimator, node->ioss_PscanLen);
    shm_toc_estimate_keys(&pcxt->estimator, 1);
}

References EState::es_snapshot, ParallelContext::estimator, index_parallelscan_estimate(), IndexOnlyScanState::ioss_NumOrderByKeys, IndexOnlyScanState::ioss_NumScanKeys, IndexOnlyScanState::ioss_PscanLen, IndexOnlyScanState::ioss_RelationDesc, ScanState::ps, shm_toc_estimate_chunk, shm_toc_estimate_keys, IndexOnlyScanState::ss, and PlanState::state.

Referenced by ExecParallelEstimate().

ExecIndexOnlyScanInitializeDSM()

void ExecIndexOnlyScanInitializeDSM	(	IndexOnlyScanState *	node,
		ParallelContext *	pcxt
	)

Definition at line 760 of file nodeIndexonlyscan.c.

{
    EState     *estate = node->ss.ps.state;
    ParallelIndexScanDesc piscan;
 
    piscan = shm_toc_allocate(pcxt->toc, node->ioss_PscanLen);
    index_parallelscan_initialize(node->ss.ss_currentRelation,
                                  node->ioss_RelationDesc,
                                  estate->es_snapshot,
                                  piscan);
    shm_toc_insert(pcxt->toc, node->ss.ps.plan->plan_node_id, piscan);
 
    node->ioss_ScanDesc =
        index_beginscan_parallel(node->ss.ss_currentRelation,
                                 node->ioss_RelationDesc,
                                 node->ioss_Instrument,
                                 node->ioss_NumScanKeys,
                                 node->ioss_NumOrderByKeys,
                                 piscan,
                                 ScanRelIsReadOnly(&node->ss) ?
                                 SO_HINT_REL_READ_ONLY : SO_NONE);
    node->ioss_ScanDesc->xs_want_itup = true;
    node->ioss_VMBuffer = InvalidBuffer;
 
    /*
     * If no run-time keys to calculate or they are ready, go ahead and pass
     * the scankeys to the index AM.
     */
    if (node->ioss_NumRuntimeKeys == 0 || node->ioss_RuntimeKeysReady)
        index_rescan(node->ioss_ScanDesc,
                     node->ioss_ScanKeys, node->ioss_NumScanKeys,
                     node->ioss_OrderByKeys, node->ioss_NumOrderByKeys);
}

References EState::es_snapshot, fb(), index_beginscan_parallel(), index_parallelscan_initialize(), index_rescan(), InvalidBuffer, IndexOnlyScanState::ioss_Instrument, IndexOnlyScanState::ioss_NumOrderByKeys, IndexOnlyScanState::ioss_NumRuntimeKeys, IndexOnlyScanState::ioss_NumScanKeys, IndexOnlyScanState::ioss_OrderByKeys, IndexOnlyScanState::ioss_PscanLen, IndexOnlyScanState::ioss_RelationDesc, IndexOnlyScanState::ioss_RuntimeKeysReady, IndexOnlyScanState::ioss_ScanDesc, IndexOnlyScanState::ioss_ScanKeys, IndexOnlyScanState::ioss_VMBuffer, PlanState::plan, Plan::plan_node_id, ScanState::ps, ScanRelIsReadOnly(), shm_toc_allocate(), shm_toc_insert(), SO_HINT_REL_READ_ONLY, SO_NONE, IndexOnlyScanState::ss, ScanState::ss_currentRelation, PlanState::state, ParallelContext::toc, and IndexScanDescData::xs_want_itup.

Referenced by ExecParallelInitializeDSM().

ExecIndexOnlyScanInitializeWorker()

void ExecIndexOnlyScanInitializeWorker	(	IndexOnlyScanState *	node,
		ParallelWorkerContext *	pwcxt
	)

Definition at line 816 of file nodeIndexonlyscan.c.

{
    ParallelIndexScanDesc piscan;
 
    piscan = shm_toc_lookup(pwcxt->toc, node->ss.ps.plan->plan_node_id, false);
 
    node->ioss_ScanDesc =
        index_beginscan_parallel(node->ss.ss_currentRelation,
                                 node->ioss_RelationDesc,
                                 node->ioss_Instrument,
                                 node->ioss_NumScanKeys,
                                 node->ioss_NumOrderByKeys,
                                 piscan,
                                 ScanRelIsReadOnly(&node->ss) ?
                                 SO_HINT_REL_READ_ONLY : SO_NONE);
    node->ioss_ScanDesc->xs_want_itup = true;
 
    /*
     * If no run-time keys to calculate or they are ready, go ahead and pass
     * the scankeys to the index AM.
     */
    if (node->ioss_NumRuntimeKeys == 0 || node->ioss_RuntimeKeysReady)
        index_rescan(node->ioss_ScanDesc,
                     node->ioss_ScanKeys, node->ioss_NumScanKeys,
                     node->ioss_OrderByKeys, node->ioss_NumOrderByKeys);
}

References fb(), index_beginscan_parallel(), index_rescan(), IndexOnlyScanState::ioss_Instrument, IndexOnlyScanState::ioss_NumOrderByKeys, IndexOnlyScanState::ioss_NumRuntimeKeys, IndexOnlyScanState::ioss_NumScanKeys, IndexOnlyScanState::ioss_OrderByKeys, IndexOnlyScanState::ioss_RelationDesc, IndexOnlyScanState::ioss_RuntimeKeysReady, IndexOnlyScanState::ioss_ScanDesc, IndexOnlyScanState::ioss_ScanKeys, PlanState::plan, Plan::plan_node_id, ScanState::ps, ScanRelIsReadOnly(), shm_toc_lookup(), SO_HINT_REL_READ_ONLY, SO_NONE, IndexOnlyScanState::ss, ScanState::ss_currentRelation, and IndexScanDescData::xs_want_itup.

Referenced by ExecParallelInitializeWorker().

ExecIndexOnlyScanInstrumentEstimate()

void ExecIndexOnlyScanInstrumentEstimate	(	IndexOnlyScanState *	node,
		ParallelContext *	pcxt
	)

Definition at line 849 of file nodeIndexonlyscan.c.

{
    Size        size;
 
    if (!node->ss.ps.instrument || pcxt->nworkers == 0)
        return;
 
    /*
     * This size calculation is trivial enough that we don't bother saving it
     * in the IndexOnlyScanState. We'll recalculate the needed size in
     * ExecIndexOnlyScanInstrumentInitDSM().
     */
    size = add_size(offsetof(SharedIndexScanInstrumentation, winstrument),
                    mul_size(pcxt->nworkers, sizeof(IndexScanInstrumentation)));
    shm_toc_estimate_chunk(&pcxt->estimator, size);
    shm_toc_estimate_keys(&pcxt->estimator, 1);
}

References add_size(), ParallelContext::estimator, fb(), PlanState::instrument, mul_size(), ParallelContext::nworkers, ScanState::ps, shm_toc_estimate_chunk, shm_toc_estimate_keys, and IndexOnlyScanState::ss.

Referenced by ExecParallelEstimate().

ExecIndexOnlyScanInstrumentInitDSM()

void ExecIndexOnlyScanInstrumentInitDSM	(	IndexOnlyScanState *	node,
		ParallelContext *	pcxt
	)

Definition at line 872 of file nodeIndexonlyscan.c.

{
    Size        size;
 
    if (!node->ss.ps.instrument || pcxt->nworkers == 0)
        return;
 
    size = add_size(offsetof(SharedIndexScanInstrumentation, winstrument),
                    mul_size(pcxt->nworkers, sizeof(IndexScanInstrumentation)));
    node->ioss_SharedInfo =
        (SharedIndexScanInstrumentation *) shm_toc_allocate(pcxt->toc, size);
 
    /* Each per-worker area must start out as zeroes */
    memset(node->ioss_SharedInfo, 0, size);
    node->ioss_SharedInfo->num_workers = pcxt->nworkers;
    shm_toc_insert(pcxt->toc,
                   node->ss.ps.plan->plan_node_id +
                   PARALLEL_KEY_SCAN_INSTRUMENT_OFFSET,
                   node->ioss_SharedInfo);
}

References add_size(), fb(), PlanState::instrument, IndexOnlyScanState::ioss_SharedInfo, mul_size(), SharedIndexScanInstrumentation::num_workers, ParallelContext::nworkers, PARALLEL_KEY_SCAN_INSTRUMENT_OFFSET, PlanState::plan, Plan::plan_node_id, ScanState::ps, shm_toc_allocate(), shm_toc_insert(), IndexOnlyScanState::ss, and ParallelContext::toc.

Referenced by ExecParallelInitializeDSM().

ExecIndexOnlyScanInstrumentInitWorker()

void ExecIndexOnlyScanInstrumentInitWorker	(	IndexOnlyScanState *	node,
		ParallelWorkerContext *	pwcxt
	)

Definition at line 898 of file nodeIndexonlyscan.c.

{
    if (!node->ss.ps.instrument)
        return;
 
    node->ioss_SharedInfo = (SharedIndexScanInstrumentation *)
        shm_toc_lookup(pwcxt->toc,
                       node->ss.ps.plan->plan_node_id +
                       PARALLEL_KEY_SCAN_INSTRUMENT_OFFSET,
                       false);
}

References fb(), PlanState::instrument, IndexOnlyScanState::ioss_SharedInfo, PARALLEL_KEY_SCAN_INSTRUMENT_OFFSET, PlanState::plan, Plan::plan_node_id, ScanState::ps, shm_toc_lookup(), and IndexOnlyScanState::ss.

Referenced by ExecParallelInitializeWorker().

ExecIndexOnlyScanReInitializeDSM()

void ExecIndexOnlyScanReInitializeDSM	(	IndexOnlyScanState *	node,
		ParallelContext *	pcxt
	)

Definition at line 802 of file nodeIndexonlyscan.c.

{
    Assert(node->ss.ps.plan->parallel_aware);
    index_parallelrescan(node->ioss_ScanDesc);
}

References Assert, index_parallelrescan(), IndexOnlyScanState::ioss_ScanDesc, Plan::parallel_aware, PlanState::plan, ScanState::ps, and IndexOnlyScanState::ss.

Referenced by ExecParallelReInitializeDSM().

ExecIndexOnlyScanRetrieveInstrumentation()

void ExecIndexOnlyScanRetrieveInstrumentation

(

IndexOnlyScanState *

node

)

Definition at line 918 of file nodeIndexonlyscan.c.

{
    SharedIndexScanInstrumentation *SharedInfo = node->ioss_SharedInfo;
    size_t      size;
 
    if (SharedInfo == NULL)
        return;
 
    /* Create a copy of SharedInfo in backend-local memory */
    size = offsetof(SharedIndexScanInstrumentation, winstrument) +
        SharedInfo->num_workers * sizeof(IndexScanInstrumentation);
    node->ioss_SharedInfo = palloc(size);
    memcpy(node->ioss_SharedInfo, SharedInfo, size);
}

References fb(), IndexOnlyScanState::ioss_SharedInfo, memcpy(), SharedIndexScanInstrumentation::num_workers, and palloc().

Referenced by ExecParallelRetrieveInstrumentation().

ExecInitIndexOnlyScan()

IndexOnlyScanState * ExecInitIndexOnlyScan	(	IndexOnlyScan *	node,
		EState *	estate,
		int	eflags
	)

Definition at line 536 of file nodeIndexonlyscan.c.

{
    IndexOnlyScanState *indexstate;
    Relation    currentRelation;
    Relation    indexRelation;
    LOCKMODE    lockmode;
    TupleDesc   tupDesc;
    int         indnkeyatts;
    int         namecount;
 
    /*
     * create state structure
     */
    indexstate = makeNode(IndexOnlyScanState);
    indexstate->ss.ps.plan = (Plan *) node;
    indexstate->ss.ps.state = estate;
    indexstate->ss.ps.ExecProcNode = ExecIndexOnlyScan;
 
    /*
     * Miscellaneous initialization
     *
     * create expression context for node
     */
    ExecAssignExprContext(estate, &indexstate->ss.ps);
 
    /*
     * open the scan relation
     */
    currentRelation = ExecOpenScanRelation(estate, node->scan.scanrelid, eflags);
 
    indexstate->ss.ss_currentRelation = currentRelation;
    indexstate->ss.ss_currentScanDesc = NULL;   /* no heap scan here */
 
    /*
     * Build the scan tuple type using the indextlist generated by the
     * planner.  We use this, rather than the index's physical tuple
     * descriptor, because the latter contains storage column types not the
     * types of the original datums.  (It's the AM's responsibility to return
     * suitable data anyway.)
     */
    tupDesc = ExecTypeFromTL(node->indextlist);
    ExecInitScanTupleSlot(estate, &indexstate->ss, tupDesc,
                          &TTSOpsVirtual,
                          0);
 
    /*
     * We need another slot, in a format that's suitable for the table AM, for
     * when we need to fetch a tuple from the table for rechecking visibility.
     */
    indexstate->ioss_TableSlot =
        ExecAllocTableSlot(&estate->es_tupleTable,
                           RelationGetDescr(currentRelation),
                           table_slot_callbacks(currentRelation), 0);
 
    /*
     * Initialize result type and projection info.  The node's targetlist will
     * contain Vars with varno = INDEX_VAR, referencing the scan tuple.
     */
    ExecInitResultTypeTL(&indexstate->ss.ps);
    ExecAssignScanProjectionInfoWithVarno(&indexstate->ss, INDEX_VAR);
 
    /*
     * initialize child expressions
     *
     * Note: we don't initialize all of the indexorderby expression, only the
     * sub-parts corresponding to runtime keys (see below).
     */
    indexstate->ss.ps.qual =
        ExecInitQual(node->scan.plan.qual, (PlanState *) indexstate);
    indexstate->recheckqual =
        ExecInitQual(node->recheckqual, (PlanState *) indexstate);
 
    /*
     * If we are just doing EXPLAIN (ie, aren't going to run the plan), stop
     * here.  This allows an index-advisor plugin to EXPLAIN a plan containing
     * references to nonexistent indexes.
     */
    if (eflags & EXEC_FLAG_EXPLAIN_ONLY)
        return indexstate;
 
    /* Set up instrumentation of index-only scans if requested */
    if (estate->es_instrument)
        indexstate->ioss_Instrument = palloc0_object(IndexScanInstrumentation);
 
    /* Open the index relation. */
    lockmode = exec_rt_fetch(node->scan.scanrelid, estate)->rellockmode;
    indexRelation = index_open(node->indexid, lockmode);
    indexstate->ioss_RelationDesc = indexRelation;
 
    /*
     * Initialize index-specific scan state
     */
    indexstate->ioss_RuntimeKeysReady = false;
    indexstate->ioss_RuntimeKeys = NULL;
    indexstate->ioss_NumRuntimeKeys = 0;
 
    /*
     * build the index scan keys from the index qualification
     */
    ExecIndexBuildScanKeys((PlanState *) indexstate,
                           indexRelation,
                           node->indexqual,
                           false,
                           &indexstate->ioss_ScanKeys,
                           &indexstate->ioss_NumScanKeys,
                           &indexstate->ioss_RuntimeKeys,
                           &indexstate->ioss_NumRuntimeKeys,
                           NULL,    /* no ArrayKeys */
                           NULL);
 
    /*
     * any ORDER BY exprs have to be turned into scankeys in the same way
     */
    ExecIndexBuildScanKeys((PlanState *) indexstate,
                           indexRelation,
                           node->indexorderby,
                           true,
                           &indexstate->ioss_OrderByKeys,
                           &indexstate->ioss_NumOrderByKeys,
                           &indexstate->ioss_RuntimeKeys,
                           &indexstate->ioss_NumRuntimeKeys,
                           NULL,    /* no ArrayKeys */
                           NULL);
 
    /*
     * If we have runtime keys, we need an ExprContext to evaluate them. The
     * node's standard context won't do because we want to reset that context
     * for every tuple.  So, build another context just like the other one...
     * -tgl 7/11/00
     */
    if (indexstate->ioss_NumRuntimeKeys != 0)
    {
        ExprContext *stdecontext = indexstate->ss.ps.ps_ExprContext;
 
        ExecAssignExprContext(estate, &indexstate->ss.ps);
        indexstate->ioss_RuntimeContext = indexstate->ss.ps.ps_ExprContext;
        indexstate->ss.ps.ps_ExprContext = stdecontext;
    }
    else
    {
        indexstate->ioss_RuntimeContext = NULL;
    }
 
    indexstate->ioss_NameCStringAttNums = NULL;
    indnkeyatts = indexRelation->rd_index->indnkeyatts;
    namecount = 0;
 
    /*
     * The "name" type for btree uses text_ops which results in storing
     * cstrings in the indexed keys rather than names.  Here we detect that in
     * a generic way in case other index AMs want to do the same optimization.
     * Check for opclasses with an opcintype of NAMEOID and an index tuple
     * descriptor with CSTRINGOID.  If any of these are found, create an array
     * marking the index attribute number of each of them.  StoreIndexTuple()
     * handles copying the name Datums into a NAMEDATALEN-byte allocation.
     */
 
    /* First, count the number of such index keys */
    for (int attnum = 0; attnum < indnkeyatts; attnum++)
    {
        if (TupleDescAttr(indexRelation->rd_att, attnum)->atttypid == CSTRINGOID &&
            indexRelation->rd_opcintype[attnum] == NAMEOID)
            namecount++;
    }
 
    if (namecount > 0)
    {
        int         idx = 0;
 
        /*
         * Now create an array to mark the attribute numbers of the keys that
         * need to be converted from cstring to name.
         */
        indexstate->ioss_NameCStringAttNums = palloc_array(AttrNumber, namecount);
 
        for (int attnum = 0; attnum < indnkeyatts; attnum++)
        {
            if (TupleDescAttr(indexRelation->rd_att, attnum)->atttypid == CSTRINGOID &&
                indexRelation->rd_opcintype[attnum] == NAMEOID)
                indexstate->ioss_NameCStringAttNums[idx++] = (AttrNumber) attnum;
        }
    }
 
    indexstate->ioss_NameCStringCount = namecount;
 
    /*
     * all done.
     */
    return indexstate;
}

References attnum, EState::es_instrument, EState::es_tupleTable, EXEC_FLAG_EXPLAIN_ONLY, exec_rt_fetch(), ExecAllocTableSlot(), ExecAssignExprContext(), ExecAssignScanProjectionInfoWithVarno(), ExecIndexBuildScanKeys(), ExecIndexOnlyScan(), ExecInitQual(), ExecInitResultTypeTL(), ExecInitScanTupleSlot(), ExecOpenScanRelation(), ExecTypeFromTL(), fb(), idx(), index_open(), INDEX_VAR, IndexOnlyScan::indexid, IndexOnlyScan::indexorderby, IndexOnlyScan::indexqual, IndexOnlyScan::indextlist, makeNode, palloc0_object, palloc_array, RelationData::rd_att, RelationData::rd_index, RelationData::rd_opcintype, IndexOnlyScan::recheckqual, RelationGetDescr, IndexOnlyScan::scan, Scan::scanrelid, table_slot_callbacks(), TTSOpsVirtual, and TupleDescAttr().

Referenced by ExecInitNode().

ExecReScanIndexOnlyScan()

void ExecReScanIndexOnlyScan

(

IndexOnlyScanState *

node

)

Definition at line 372 of file nodeIndexonlyscan.c.

{
    /*
     * If we are doing runtime key calculations (ie, any of the index key
     * values weren't simple Consts), compute the new key values.  But first,
     * reset the context so we don't leak memory as each outer tuple is
     * scanned.  Note this assumes that we will recalculate *all* runtime keys
     * on each call.
     */
    if (node->ioss_NumRuntimeKeys != 0)
    {
        ExprContext *econtext = node->ioss_RuntimeContext;
 
        ResetExprContext(econtext);
        ExecIndexEvalRuntimeKeys(econtext,
                                 node->ioss_RuntimeKeys,
                                 node->ioss_NumRuntimeKeys);
    }
    node->ioss_RuntimeKeysReady = true;
 
    /* reset index scan */
    if (node->ioss_ScanDesc)
        index_rescan(node->ioss_ScanDesc,
                     node->ioss_ScanKeys, node->ioss_NumScanKeys,
                     node->ioss_OrderByKeys, node->ioss_NumOrderByKeys);
 
    ExecScanReScan(&node->ss);
}

References ExecIndexEvalRuntimeKeys(), ExecScanReScan(), index_rescan(), IndexOnlyScanState::ioss_NumOrderByKeys, IndexOnlyScanState::ioss_NumRuntimeKeys, IndexOnlyScanState::ioss_NumScanKeys, IndexOnlyScanState::ioss_OrderByKeys, IndexOnlyScanState::ioss_RuntimeContext, IndexOnlyScanState::ioss_RuntimeKeys, IndexOnlyScanState::ioss_RuntimeKeysReady, IndexOnlyScanState::ioss_ScanDesc, IndexOnlyScanState::ioss_ScanKeys, ResetExprContext, and IndexOnlyScanState::ss.

Referenced by ExecReScan().

IndexOnlyNext()

static TupleTableSlot * IndexOnlyNext ( IndexOnlyScanState *  node )

static

Definition at line 63 of file nodeIndexonlyscan.c.

{
    EState     *estate;
    ExprContext *econtext;
    ScanDirection direction;
    IndexScanDesc scandesc;
    TupleTableSlot *slot;
    ItemPointer tid;
 
    /*
     * extract necessary information from index scan node
     */
    estate = node->ss.ps.state;
 
    /*
     * Determine which direction to scan the index in based on the plan's scan
     * direction and the current direction of execution.
     */
    direction = ScanDirectionCombine(estate->es_direction,
                                     ((IndexOnlyScan *) node->ss.ps.plan)->indexorderdir);
    scandesc = node->ioss_ScanDesc;
    econtext = node->ss.ps.ps_ExprContext;
    slot = node->ss.ss_ScanTupleSlot;
 
    if (scandesc == NULL)
    {
        /*
         * We reach here if the index only scan is not parallel, or if we're
         * serially executing an index only scan that was planned to be
         * parallel.
         */
        scandesc = index_beginscan(node->ss.ss_currentRelation,
                                   node->ioss_RelationDesc,
                                   estate->es_snapshot,
                                   node->ioss_Instrument,
                                   node->ioss_NumScanKeys,
                                   node->ioss_NumOrderByKeys,
                                   ScanRelIsReadOnly(&node->ss) ?
                                   SO_HINT_REL_READ_ONLY : SO_NONE);
 
        node->ioss_ScanDesc = scandesc;
 
 
        /* Set it up for index-only scan */
        node->ioss_ScanDesc->xs_want_itup = true;
        node->ioss_VMBuffer = InvalidBuffer;
 
        /*
         * If no run-time keys to calculate or they are ready, go ahead and
         * pass the scankeys to the index AM.
         */
        if (node->ioss_NumRuntimeKeys == 0 || node->ioss_RuntimeKeysReady)
            index_rescan(scandesc,
                         node->ioss_ScanKeys,
                         node->ioss_NumScanKeys,
                         node->ioss_OrderByKeys,
                         node->ioss_NumOrderByKeys);
    }
 
    /*
     * OK, now that we have what we need, fetch the next tuple.
     */
    while ((tid = index_getnext_tid(scandesc, direction)) != NULL)
    {
        bool        tuple_from_heap = false;
 
        CHECK_FOR_INTERRUPTS();
 
        /*
         * We can skip the heap fetch if the TID references a heap page on
         * which all tuples are known visible to everybody.  In any case,
         * we'll use the index tuple not the heap tuple as the data source.
         *
         * Note on Memory Ordering Effects: visibilitymap_get_status does not
         * lock the visibility map buffer, and therefore the result we read
         * here could be slightly stale.  However, it can't be stale enough to
         * matter.
         *
         * We need to detect clearing a VM bit due to an insert right away,
         * because the tuple is present in the index page but not visible. The
         * reading of the TID by this scan (using a shared lock on the index
         * buffer) is serialized with the insert of the TID into the index
         * (using an exclusive lock on the index buffer). Because the VM bit
         * is cleared before updating the index, and locking/unlocking of the
         * index page acts as a full memory barrier, we are sure to see the
         * cleared bit if we see a recently-inserted TID.
         *
         * Deletes do not update the index page (only VACUUM will clear out
         * the TID), so the clearing of the VM bit by a delete is not
         * serialized with this test below, and we may see a value that is
         * significantly stale. However, we don't care about the delete right
         * away, because the tuple is still visible until the deleting
         * transaction commits or the statement ends (if it's our
         * transaction). In either case, the lock on the VM buffer will have
         * been released (acting as a write barrier) after clearing the bit.
         * And for us to have a snapshot that includes the deleting
         * transaction (making the tuple invisible), we must have acquired
         * ProcArrayLock after that time, acting as a read barrier.
         *
         * It's worth going through this complexity to avoid needing to lock
         * the VM buffer, which could cause significant contention.
         */
        if (!VM_ALL_VISIBLE(scandesc->heapRelation,
                            ItemPointerGetBlockNumber(tid),
                            &node->ioss_VMBuffer))
        {
            /*
             * Rats, we have to visit the heap to check visibility.
             */
            InstrCountTuples2(node, 1);
            if (!index_fetch_heap(scandesc, node->ioss_TableSlot))
                continue;       /* no visible tuple, try next index entry */
 
            ExecClearTuple(node->ioss_TableSlot);
 
            /*
             * Only MVCC snapshots are supported here, so there should be no
             * need to keep following the HOT chain once a visible entry has
             * been found.  If we did want to allow that, we'd need to keep
             * more state to remember not to call index_getnext_tid next time.
             */
            if (scandesc->xs_heap_continue)
                elog(ERROR, "non-MVCC snapshots are not supported in index-only scans");
 
            /*
             * Note: at this point we are holding a pin on the heap page, as
             * recorded in scandesc->xs_cbuf.  We could release that pin now,
             * but it's not clear whether it's a win to do so.  The next index
             * entry might require a visit to the same heap page.
             */
 
            tuple_from_heap = true;
        }
 
        /* Fill the scan tuple slot with data from the index */
        StoreIndexTuple(node, slot, scandesc);
 
        /*
         * If the index was lossy, we have to recheck the index quals.
         */
        if (scandesc->xs_recheck)
        {
            econtext->ecxt_scantuple = slot;
            if (!ExecQualAndReset(node->recheckqual, econtext))
            {
                /* Fails recheck, so drop it and loop back for another */
                InstrCountFiltered2(node, 1);
                continue;
            }
        }
 
        /*
         * We don't currently support rechecking ORDER BY distances.  (In
         * principle, if the index can support retrieval of the originally
         * indexed value, it should be able to produce an exact distance
         * calculation too.  So it's not clear that adding code here for
         * recheck/re-sort would be worth the trouble.  But we should at least
         * throw an error if someone tries it.)
         */
        if (scandesc->numberOfOrderBys > 0 && scandesc->xs_recheckorderby)
            ereport(ERROR,
                    (errcode(ERRCODE_FEATURE_NOT_SUPPORTED),
                     errmsg("lossy distance functions are not supported in index-only scans")));
 
        /*
         * If we didn't access the heap, then we'll need to take a predicate
         * lock explicitly, as if we had.  For now we do that at page level.
         */
        if (!tuple_from_heap)
            PredicateLockPage(scandesc->heapRelation,
                              ItemPointerGetBlockNumber(tid),
                              estate->es_snapshot);
 
        return slot;
    }
 
    /*
     * if we get here it means the index scan failed so we are at the end of
     * the scan..
     */
    return ExecClearTuple(slot);
}

References CHECK_FOR_INTERRUPTS, ExprContext::ecxt_scantuple, elog, ereport, errcode(), errmsg, ERROR, EState::es_direction, EState::es_snapshot, ExecClearTuple(), ExecQualAndReset(), fb(), IndexScanDescData::heapRelation, index_beginscan(), index_fetch_heap(), index_getnext_tid(), index_rescan(), InstrCountFiltered2, InstrCountTuples2, InvalidBuffer, IndexOnlyScanState::ioss_Instrument, IndexOnlyScanState::ioss_NumOrderByKeys, IndexOnlyScanState::ioss_NumRuntimeKeys, IndexOnlyScanState::ioss_NumScanKeys, IndexOnlyScanState::ioss_OrderByKeys, IndexOnlyScanState::ioss_RelationDesc, IndexOnlyScanState::ioss_RuntimeKeysReady, IndexOnlyScanState::ioss_ScanDesc, IndexOnlyScanState::ioss_ScanKeys, IndexOnlyScanState::ioss_TableSlot, IndexOnlyScanState::ioss_VMBuffer, ItemPointerGetBlockNumber(), IndexScanDescData::numberOfOrderBys, PlanState::plan, PredicateLockPage(), ScanState::ps, PlanState::ps_ExprContext, IndexOnlyScanState::recheckqual, ScanDirectionCombine, ScanRelIsReadOnly(), SO_HINT_REL_READ_ONLY, SO_NONE, IndexOnlyScanState::ss, ScanState::ss_currentRelation, ScanState::ss_ScanTupleSlot, PlanState::state, StoreIndexTuple(), VM_ALL_VISIBLE, IndexScanDescData::xs_heap_continue, IndexScanDescData::xs_recheck, IndexScanDescData::xs_recheckorderby, and IndexScanDescData::xs_want_itup.

Referenced by ExecIndexOnlyScan().

IndexOnlyRecheck()

static bool IndexOnlyRecheck ( IndexOnlyScanState *  node, TupleTableSlot *  slot  )

static

Definition at line 334 of file nodeIndexonlyscan.c.

{
    elog(ERROR, "EvalPlanQual recheck is not supported in index-only scans");
    return false;               /* keep compiler quiet */
}

References elog, and ERROR.

Referenced by ExecIndexOnlyScan().

StoreIndexTuple()

static void StoreIndexTuple ( IndexOnlyScanState *  node, TupleTableSlot *  slot, IndexScanDesc  scandesc  )

static

Definition at line 259 of file nodeIndexonlyscan.c.

{
    ExecClearTuple(slot);
 
    /*
     * We must deform the tuple using the tupdesc the index AM formed it with
     * (xs_hitupdesc or xs_itupdesc), not the slot's tupdesc.  The datums
     * returned by the index AM must be binary compatible, but the descriptors
     * may align each column differently in certain rare cases. (Actually,
     * btree's "name" opclass stores cstring tuples that _aren't_ even binary
     * compatible, in the strictest sense.  We directly handle that here.)
     */
    if (scandesc->xs_hitup)
    {
        Assert(slot->tts_tupleDescriptor->natts == scandesc->xs_hitupdesc->natts);
 
        heap_deform_tuple(scandesc->xs_hitup, scandesc->xs_hitupdesc,
                          slot->tts_values, slot->tts_isnull);
    }
    else if (scandesc->xs_itup)
    {
        Assert(slot->tts_tupleDescriptor->natts == scandesc->xs_itupdesc->natts);
 
        index_deform_tuple(scandesc->xs_itup, scandesc->xs_itupdesc,
                           slot->tts_values, slot->tts_isnull);
 
        /*
         * Copy all name columns stored as cstrings back into a NAMEDATALEN
         * byte sized allocation.  We mark this branch as unlikely as
         * generally "name" is used only for the system catalogs and this
         * would have to be a user query running on those or some other user
         * table with an index on a name column.
         */
        if (unlikely(node->ioss_NameCStringAttNums != NULL))
        {
            int         attcount = node->ioss_NameCStringCount;
 
            for (int idx = 0; idx < attcount; idx++)
            {
                int         attnum = node->ioss_NameCStringAttNums[idx];
                Name        name;
 
                /* skip null Datums */
                if (slot->tts_isnull[attnum])
                    continue;
 
                /*
                 * allocate the NAMEDATALEN and copy the datum into that
                 * memory
                 */
                name = (Name) MemoryContextAlloc(node->ss.ps.ps_ExprContext->ecxt_per_tuple_memory,
                                                 NAMEDATALEN);
 
                /* use namestrcpy to zero-pad all trailing bytes */
                namestrcpy(name, DatumGetCString(slot->tts_values[attnum]));
                slot->tts_values[attnum] = NameGetDatum(name);
            }
        }
    }
    else
        elog(ERROR, "no data returned for index-only scan");
 
    ExecStoreVirtualTuple(slot);
}

References Assert, attnum, DatumGetCString(), ExprContext::ecxt_per_tuple_memory, elog, ERROR, ExecClearTuple(), ExecStoreVirtualTuple(), fb(), heap_deform_tuple(), idx(), index_deform_tuple(), IndexOnlyScanState::ioss_NameCStringAttNums, IndexOnlyScanState::ioss_NameCStringCount, MemoryContextAlloc(), name, NAMEDATALEN, NameGetDatum(), namestrcpy(), TupleDescData::natts, ScanState::ps, PlanState::ps_ExprContext, IndexOnlyScanState::ss, TupleTableSlot::tts_isnull, TupleTableSlot::tts_tupleDescriptor, TupleTableSlot::tts_values, unlikely, IndexScanDescData::xs_hitup, IndexScanDescData::xs_hitupdesc, IndexScanDescData::xs_itup, and IndexScanDescData::xs_itupdesc.

Referenced by IndexOnlyNext().