nodeAgg.h File Reference

#include "nodes/execnodes.h"

Include dependency graph for nodeAgg.h:

This graph shows which files directly or indirectly include this file:

Go to the source code of this file.

Functions
AggState *	ExecInitAgg (Agg *node, EState *estate, int eflags)
void	ExecEndAgg (AggState *node)
void	ExecReScanAgg (AggState *node)
Size	hash_agg_entry_size (int numAggs)
Datum	aggregate_dummy (PG_FUNCTION_ARGS)

Function Documentation

Datum aggregate_dummy

(

PG_FUNCTION_ARGS

)

Definition at line 4148 of file nodeAgg.c.

References elog, and ERROR.

{
    elog(ERROR, "aggregate function %u called as normal function",
         fcinfo->flinfo->fn_oid);
    return (Datum) 0;           /* keep compiler quiet */
}

void ExecEndAgg

(

AggState *

node

)

Definition at line 3850 of file nodeAgg.c.

References AggState::aggcontexts, ExecClearTuple(), ExecEndNode(), ExecFreeExprContext(), AggState::hashcontext, Max, AggState::maxsets, AggState::numtrans, outerPlan, outerPlanState, AggState::pertrans, ScanState::ps, ReScanExprContext(), AggState::sort_in, AggState::sort_out, AggStatePerTransData::sortstates, AggState::ss, ScanState::ss_ScanTupleSlot, and tuplesort_end().

Referenced by ExecEndNode().

{
    PlanState  *outerPlan;
    int         transno;
    int         numGroupingSets = Max(node->maxsets, 1);
    int         setno;

    /* Make sure we have closed any open tuplesorts */

    if (node->sort_in)
        tuplesort_end(node->sort_in);
    if (node->sort_out)
        tuplesort_end(node->sort_out);

    for (transno = 0; transno < node->numtrans; transno++)
    {
        AggStatePerTrans pertrans = &node->pertrans[transno];

        for (setno = 0; setno < numGroupingSets; setno++)
        {
            if (pertrans->sortstates[setno])
                tuplesort_end(pertrans->sortstates[setno]);
        }
    }

    /* And ensure any agg shutdown callbacks have been called */
    for (setno = 0; setno < numGroupingSets; setno++)
        ReScanExprContext(node->aggcontexts[setno]);
    if (node->hashcontext)
        ReScanExprContext(node->hashcontext);

    /*
     * We don't actually free any ExprContexts here (see comment in
     * ExecFreeExprContext), just unlinking the output one from the plan node
     * suffices.
     */
    ExecFreeExprContext(&node->ss.ps);

    /* clean up tuple table */
    ExecClearTuple(node->ss.ss_ScanTupleSlot);

    outerPlan = outerPlanState(node);
    ExecEndNode(outerPlan);
}

AggState* ExecInitAgg	(	Agg *	node,
		EState *	estate,
		int	eflags
	)

Definition at line 2670 of file nodeAgg.c.

References ACL_EXECUTE, ACL_KIND_PROC, aclcheck_error(), ACLCHECK_OK, AggState::agg_done, AGG_HASHED, AGG_MIXED, AGG_SORTED, AggState::aggcontexts, Aggref::aggdirectargs, AGGFNOID, Aggref::aggfnoid, Aggref::agglevelsup, AggrefExprState::aggno, AggStatePerPhaseData::aggnode, AggStatePerHashData::aggnode, AggStatePerTransData::aggref, AggStatePerAggData::aggref, AggrefExprState::aggref, AggState::aggs, Aggref::aggsplit, Agg::aggsplit, AggState::aggsplit, AggStatePerPhaseData::aggstrategy, Agg::aggstrategy, AggState::aggstrategy, Aggref::aggtranstype, Aggref::aggtype, AggState::all_grouped_cols, Anum_pg_aggregate_agginitval, arg, Aggref::args, Assert, bms_add_member(), bms_add_members(), bms_next_member(), build_aggregate_finalfn_expr(), build_hash_table(), build_pertrans_for_aggref(), castNode, Agg::chain, AggState::curpertrans, AggState::current_phase, AggState::current_set, DO_AGGSPLIT_COMBINE, DO_AGGSPLIT_DESERIALIZE, DO_AGGSPLIT_SERIALIZE, DO_AGGSPLIT_SKIPFINAL, ExprContext::ecxt_aggnulls, ExprContext::ecxt_aggvalues, elog, AggStatePerPhaseData::eqfunctions, AggStatePerHashData::eqfunctions, ERROR, AggState::evaldesc, AggState::evalproj, AggState::evalslot, EXEC_FLAG_BACKWARD, EXEC_FLAG_MARK, EXEC_FLAG_REWIND, ExecAgg(), ExecAssignExprContext(), ExecAssignProjectionInfo(), ExecAssignResultTypeFromTL(), ExecAssignScanTypeFromOuterPlan(), ExecBuildProjectionInfo(), ExecInitExtraTupleSlot(), ExecInitNode(), ExecInitQual(), ExecInitResultTupleSlot(), ExecInitScanTupleSlot(), PlanState::ExecProcNode, ExecSetSlotDescriptor(), execTuplesHashPrepare(), execTuplesMatchPrepare(), ExecTypeFromTL(), AggStatePerAggData::finalfn, AggStatePerAggData::finalfn_oid, find_compatible_peragg(), find_compatible_pertrans(), find_hash_columns(), flatCopyTargetEntry(), fmgr_info(), fmgr_info_set_expr, FUNC_MAX_ARGS, get_aggregate_argtypes(), get_func_name(), get_typlenbyval(), GetAggInitVal(), GETSTRUCT, GetUserId(), AggStatePerPhaseData::grouped_cols, Agg::groupingSets, AggState::grp_firstTuple, Agg::grpColIdx, Agg::grpOperators, AggStatePerPhaseData::gset_lengths, AggState::hash_pergroup, AggState::hashcontext, AggStatePerHashData::hashfunctions, AggStatePerHashData::hashslot, HeapTupleIsValid, i, initialize_phase(), initValue(), AggState::input_done, Aggref::inputcollid, AggStatePerTransData::inputoff, INTERNALOID, InvalidOid, InvokeFunctionExecuteHook, lappend(), lcons_int(), Plan::lefttree, lfirst, lfirst_node, list_length(), list_nth_node, makeNode, Max, AggState::maxsets, NIL, NULL, AggState::num_hashes, AggState::numaggs, AggStatePerHashData::numCols, Agg::numCols, AggStatePerAggData::numFinalArgs, AggState::numphases, AggStatePerPhaseData::numsets, AggState::numtrans, ObjectIdGetDatum, OidIsValid, outerPlan, outerPlanState, palloc(), palloc0(), AggState::peragg, AggState::pergroup, AggState::perhash, AggState::pertrans, pg_proc_aclcheck(), AggState::phases, Agg::plan, PlanState::plan, PROCOID, AggState::projected_set, ScanState::ps, PlanState::ps_ExprContext, Plan::qual, PlanState::qual, ReleaseSysCache(), TargetEntry::resno, AggStatePerAggData::resulttypeByVal, AggStatePerAggData::resulttypeLen, SearchSysCache1, select_current_set(), AggState::sort_in, AggState::sort_out, AggState::sort_slot, AggStatePerPhaseData::sortnode, AggState::ss, ScanState::ss_ScanTupleSlot, PlanState::state, SysCacheGetAttr(), AggState::table_filled, AggState::tmpcontext, AggStatePerAggData::transno, and TupleTableSlot::tts_tupleDescriptor.

Referenced by ExecInitNode().

{
    AggState   *aggstate;
    AggStatePerAgg peraggs;
    AggStatePerTrans pertransstates;
    Plan       *outerPlan;
    ExprContext *econtext;
    int         numaggs,
                transno,
                aggno;
    int         phase;
    int         phaseidx;
    List       *combined_inputeval;
    ListCell   *l;
    Bitmapset  *all_grouped_cols = NULL;
    int         numGroupingSets = 1;
    int         numPhases;
    int         numHashes;
    int         column_offset;
    int         i = 0;
    int         j = 0;
    bool        use_hashing = (node->aggstrategy == AGG_HASHED ||
                               node->aggstrategy == AGG_MIXED);

    /* check for unsupported flags */
    Assert(!(eflags & (EXEC_FLAG_BACKWARD | EXEC_FLAG_MARK)));

    /*
     * create state structure
     */
    aggstate = makeNode(AggState);
    aggstate->ss.ps.plan = (Plan *) node;
    aggstate->ss.ps.state = estate;
    aggstate->ss.ps.ExecProcNode = ExecAgg;

    aggstate->aggs = NIL;
    aggstate->numaggs = 0;
    aggstate->numtrans = 0;
    aggstate->aggstrategy = node->aggstrategy;
    aggstate->aggsplit = node->aggsplit;
    aggstate->maxsets = 0;
    aggstate->projected_set = -1;
    aggstate->current_set = 0;
    aggstate->peragg = NULL;
    aggstate->pertrans = NULL;
    aggstate->curpertrans = NULL;
    aggstate->input_done = false;
    aggstate->agg_done = false;
    aggstate->pergroup = NULL;
    aggstate->grp_firstTuple = NULL;
    aggstate->sort_in = NULL;
    aggstate->sort_out = NULL;

    /*
     * phases[0] always exists, but is dummy in sorted/plain mode
     */
    numPhases = (use_hashing ? 1 : 2);
    numHashes = (use_hashing ? 1 : 0);

    /*
     * Calculate the maximum number of grouping sets in any phase; this
     * determines the size of some allocations.  Also calculate the number of
     * phases, since all hashed/mixed nodes contribute to only a single phase.
     */
    if (node->groupingSets)
    {
        numGroupingSets = list_length(node->groupingSets);

        foreach(l, node->chain)
        {
            Agg        *agg = lfirst(l);

            numGroupingSets = Max(numGroupingSets,
                                  list_length(agg->groupingSets));

            /*
             * additional AGG_HASHED aggs become part of phase 0, but all
             * others add an extra phase.
             */
            if (agg->aggstrategy != AGG_HASHED)
                ++numPhases;
            else
                ++numHashes;
        }
    }

    aggstate->maxsets = numGroupingSets;
    aggstate->numphases = numPhases;

    aggstate->aggcontexts = (ExprContext **)
        palloc0(sizeof(ExprContext *) * numGroupingSets);

    /*
     * Create expression contexts.  We need three or more, one for
     * per-input-tuple processing, one for per-output-tuple processing, one
     * for all the hashtables, and one for each grouping set.  The per-tuple
     * memory context of the per-grouping-set ExprContexts (aggcontexts)
     * replaces the standalone memory context formerly used to hold transition
     * values.  We cheat a little by using ExecAssignExprContext() to build
     * all of them.
     *
     * NOTE: the details of what is stored in aggcontexts and what is stored
     * in the regular per-query memory context are driven by a simple
     * decision: we want to reset the aggcontext at group boundaries (if not
     * hashing) and in ExecReScanAgg to recover no-longer-wanted space.
     */
    ExecAssignExprContext(estate, &aggstate->ss.ps);
    aggstate->tmpcontext = aggstate->ss.ps.ps_ExprContext;

    for (i = 0; i < numGroupingSets; ++i)
    {
        ExecAssignExprContext(estate, &aggstate->ss.ps);
        aggstate->aggcontexts[i] = aggstate->ss.ps.ps_ExprContext;
    }

    if (use_hashing)
    {
        ExecAssignExprContext(estate, &aggstate->ss.ps);
        aggstate->hashcontext = aggstate->ss.ps.ps_ExprContext;
    }

    ExecAssignExprContext(estate, &aggstate->ss.ps);

    /*
     * tuple table initialization.
     *
     * For hashtables, we create some additional slots below.
     */
    ExecInitScanTupleSlot(estate, &aggstate->ss);
    ExecInitResultTupleSlot(estate, &aggstate->ss.ps);
    aggstate->sort_slot = ExecInitExtraTupleSlot(estate);

    /*
     * initialize child expressions
     *
     * We rely on the parser to have checked that no aggs contain other agg
     * calls in their arguments.  This would make no sense under SQL semantics
     * (and it's forbidden by the spec).  Because it is true, we don't need to
     * worry about evaluating the aggs in any particular order.
     *
     * Note: execExpr.c finds Aggrefs for us, and adds their AggrefExprState
     * nodes to aggstate->aggs.  Aggrefs in the qual are found here; Aggrefs
     * in the targetlist are found during ExecAssignProjectionInfo, below.
     */
    aggstate->ss.ps.qual =
        ExecInitQual(node->plan.qual, (PlanState *) aggstate);

    /*
     * Initialize child nodes.
     *
     * If we are doing a hashed aggregation then the child plan does not need
     * to handle REWIND efficiently; see ExecReScanAgg.
     */
    if (node->aggstrategy == AGG_HASHED)
        eflags &= ~EXEC_FLAG_REWIND;
    outerPlan = outerPlan(node);
    outerPlanState(aggstate) = ExecInitNode(outerPlan, estate, eflags);

    /*
     * initialize source tuple type.
     */
    ExecAssignScanTypeFromOuterPlan(&aggstate->ss);
    if (node->chain)
        ExecSetSlotDescriptor(aggstate->sort_slot,
                              aggstate->ss.ss_ScanTupleSlot->tts_tupleDescriptor);

    /*
     * Initialize result tuple type and projection info.
     */
    ExecAssignResultTypeFromTL(&aggstate->ss.ps);
    ExecAssignProjectionInfo(&aggstate->ss.ps, NULL);

    /*
     * We should now have found all Aggrefs in the targetlist and quals.
     */
    numaggs = aggstate->numaggs;
    Assert(numaggs == list_length(aggstate->aggs));
    if (numaggs <= 0)
    {
        /*
         * This is not an error condition: we might be using the Agg node just
         * to do hash-based grouping.  Even in the regular case,
         * constant-expression simplification could optimize away all of the
         * Aggrefs in the targetlist and qual.  So keep going, but force local
         * copy of numaggs positive so that palloc()s below don't choke.
         */
        numaggs = 1;
    }

    /*
     * For each phase, prepare grouping set data and fmgr lookup data for
     * compare functions.  Accumulate all_grouped_cols in passing.
     */
    aggstate->phases = palloc0(numPhases * sizeof(AggStatePerPhaseData));

    aggstate->num_hashes = numHashes;
    if (numHashes)
    {
        aggstate->perhash = palloc0(sizeof(AggStatePerHashData) * numHashes);
        aggstate->phases[0].numsets = 0;
        aggstate->phases[0].gset_lengths = palloc(numHashes * sizeof(int));
        aggstate->phases[0].grouped_cols = palloc(numHashes * sizeof(Bitmapset *));
    }

    phase = 0;
    for (phaseidx = 0; phaseidx <= list_length(node->chain); ++phaseidx)
    {
        Agg        *aggnode;
        Sort       *sortnode;

        if (phaseidx > 0)
        {
            aggnode = list_nth_node(Agg, node->chain, phaseidx - 1);
            sortnode = castNode(Sort, aggnode->plan.lefttree);
        }
        else
        {
            aggnode = node;
            sortnode = NULL;
        }

        Assert(phase <= 1 || sortnode);

        if (aggnode->aggstrategy == AGG_HASHED
            || aggnode->aggstrategy == AGG_MIXED)
        {
            AggStatePerPhase phasedata = &aggstate->phases[0];
            AggStatePerHash perhash;
            Bitmapset  *cols = NULL;

            Assert(phase == 0);
            i = phasedata->numsets++;
            perhash = &aggstate->perhash[i];

            /* phase 0 always points to the "real" Agg in the hash case */
            phasedata->aggnode = node;
            phasedata->aggstrategy = node->aggstrategy;

            /* but the actual Agg node representing this hash is saved here */
            perhash->aggnode = aggnode;

            phasedata->gset_lengths[i] = perhash->numCols = aggnode->numCols;

            for (j = 0; j < aggnode->numCols; ++j)
                cols = bms_add_member(cols, aggnode->grpColIdx[j]);

            phasedata->grouped_cols[i] = cols;

            all_grouped_cols = bms_add_members(all_grouped_cols, cols);
            continue;
        }
        else
        {
            AggStatePerPhase phasedata = &aggstate->phases[++phase];
            int         num_sets;

            phasedata->numsets = num_sets = list_length(aggnode->groupingSets);

            if (num_sets)
            {
                phasedata->gset_lengths = palloc(num_sets * sizeof(int));
                phasedata->grouped_cols = palloc(num_sets * sizeof(Bitmapset *));

                i = 0;
                foreach(l, aggnode->groupingSets)
                {
                    int         current_length = list_length(lfirst(l));
                    Bitmapset  *cols = NULL;

                    /* planner forces this to be correct */
                    for (j = 0; j < current_length; ++j)
                        cols = bms_add_member(cols, aggnode->grpColIdx[j]);

                    phasedata->grouped_cols[i] = cols;
                    phasedata->gset_lengths[i] = current_length;

                    ++i;
                }

                all_grouped_cols = bms_add_members(all_grouped_cols,
                                                   phasedata->grouped_cols[0]);
            }
            else
            {
                Assert(phaseidx == 0);

                phasedata->gset_lengths = NULL;
                phasedata->grouped_cols = NULL;
            }

            /*
             * If we are grouping, precompute fmgr lookup data for inner loop.
             */
            if (aggnode->aggstrategy == AGG_SORTED)
            {
                Assert(aggnode->numCols > 0);

                phasedata->eqfunctions =
                    execTuplesMatchPrepare(aggnode->numCols,
                                           aggnode->grpOperators);
            }

            phasedata->aggnode = aggnode;
            phasedata->aggstrategy = aggnode->aggstrategy;
            phasedata->sortnode = sortnode;
        }
    }

    /*
     * Convert all_grouped_cols to a descending-order list.
     */
    i = -1;
    while ((i = bms_next_member(all_grouped_cols, i)) >= 0)
        aggstate->all_grouped_cols = lcons_int(i, aggstate->all_grouped_cols);

    /*
     * Set up aggregate-result storage in the output expr context, and also
     * allocate my private per-agg working storage
     */
    econtext = aggstate->ss.ps.ps_ExprContext;
    econtext->ecxt_aggvalues = (Datum *) palloc0(sizeof(Datum) * numaggs);
    econtext->ecxt_aggnulls = (bool *) palloc0(sizeof(bool) * numaggs);

    peraggs = (AggStatePerAgg) palloc0(sizeof(AggStatePerAggData) * numaggs);
    pertransstates = (AggStatePerTrans) palloc0(sizeof(AggStatePerTransData) * numaggs);

    aggstate->peragg = peraggs;
    aggstate->pertrans = pertransstates;

    /*
     * Hashing can only appear in the initial phase.
     */
    if (use_hashing)
    {
        for (i = 0; i < numHashes; ++i)
        {
            aggstate->perhash[i].hashslot = ExecInitExtraTupleSlot(estate);

            execTuplesHashPrepare(aggstate->perhash[i].numCols,
                                  aggstate->perhash[i].aggnode->grpOperators,
                                  &aggstate->perhash[i].eqfunctions,
                                  &aggstate->perhash[i].hashfunctions);
        }

        /* this is an array of pointers, not structures */
        aggstate->hash_pergroup = palloc0(sizeof(AggStatePerGroup) * numHashes);

        find_hash_columns(aggstate);
        build_hash_table(aggstate);
        aggstate->table_filled = false;
    }

    if (node->aggstrategy != AGG_HASHED)
    {
        AggStatePerGroup pergroup;

        pergroup = (AggStatePerGroup) palloc0(sizeof(AggStatePerGroupData)
                                              * numaggs
                                              * numGroupingSets);

        aggstate->pergroup = pergroup;
    }

    /*
     * Initialize current phase-dependent values to initial phase. The initial
     * phase is 1 (first sort pass) for all strategies that use sorting (if
     * hashing is being done too, then phase 0 is processed last); but if only
     * hashing is being done, then phase 0 is all there is.
     */
    if (node->aggstrategy == AGG_HASHED)
    {
        aggstate->current_phase = 0;
        initialize_phase(aggstate, 0);
        select_current_set(aggstate, 0, true);
    }
    else
    {
        aggstate->current_phase = 1;
        initialize_phase(aggstate, 1);
        select_current_set(aggstate, 0, false);
    }

    /* -----------------
     * Perform lookups of aggregate function info, and initialize the
     * unchanging fields of the per-agg and per-trans data.
     *
     * We try to optimize by detecting duplicate aggregate functions so that
     * their state and final values are re-used, rather than needlessly being
     * re-calculated independently. We also detect aggregates that are not
     * the same, but which can share the same transition state.
     *
     * Scenarios:
     *
     * 1. An aggregate function appears more than once in query:
     *
     *    SELECT SUM(x) FROM ... HAVING SUM(x) > 0
     *
     *    Since the aggregates are the identical, we only need to calculate
     *    the calculate it once. Both aggregates will share the same 'aggno'
     *    value.
     *
     * 2. Two different aggregate functions appear in the query, but the
     *    aggregates have the same transition function and initial value, but
     *    different final function:
     *
     *    SELECT SUM(x), AVG(x) FROM ...
     *
     *    In this case we must create a new peragg for the varying aggregate,
     *    and need to call the final functions separately, but can share the
     *    same transition state.
     *
     * For either of these optimizations to be valid, the aggregate's
     * arguments must be the same, including any modifiers such as ORDER BY,
     * DISTINCT and FILTER, and they mustn't contain any volatile functions.
     * -----------------
     */
    aggno = -1;
    transno = -1;
    foreach(l, aggstate->aggs)
    {
        AggrefExprState *aggrefstate = (AggrefExprState *) lfirst(l);
        Aggref     *aggref = aggrefstate->aggref;
        AggStatePerAgg peragg;
        AggStatePerTrans pertrans;
        int         existing_aggno;
        int         existing_transno;
        List       *same_input_transnos;
        Oid         inputTypes[FUNC_MAX_ARGS];
        int         numArguments;
        int         numDirectArgs;
        HeapTuple   aggTuple;
        Form_pg_aggregate aggform;
        AclResult   aclresult;
        Oid         transfn_oid,
                    finalfn_oid;
        Oid         serialfn_oid,
                    deserialfn_oid;
        Expr       *finalfnexpr;
        Oid         aggtranstype;
        Datum       textInitVal;
        Datum       initValue;
        bool        initValueIsNull;

        /* Planner should have assigned aggregate to correct level */
        Assert(aggref->agglevelsup == 0);
        /* ... and the split mode should match */
        Assert(aggref->aggsplit == aggstate->aggsplit);

        /* 1. Check for already processed aggs which can be re-used */
        existing_aggno = find_compatible_peragg(aggref, aggstate, aggno,
                                                &same_input_transnos);
        if (existing_aggno != -1)
        {
            /*
             * Existing compatible agg found. so just point the Aggref to the
             * same per-agg struct.
             */
            aggrefstate->aggno = existing_aggno;
            continue;
        }

        /* Mark Aggref state node with assigned index in the result array */
        peragg = &peraggs[++aggno];
        peragg->aggref = aggref;
        aggrefstate->aggno = aggno;

        /* Fetch the pg_aggregate row */
        aggTuple = SearchSysCache1(AGGFNOID,
                                   ObjectIdGetDatum(aggref->aggfnoid));
        if (!HeapTupleIsValid(aggTuple))
            elog(ERROR, "cache lookup failed for aggregate %u",
                 aggref->aggfnoid);
        aggform = (Form_pg_aggregate) GETSTRUCT(aggTuple);

        /* Check permission to call aggregate function */
        aclresult = pg_proc_aclcheck(aggref->aggfnoid, GetUserId(),
                                     ACL_EXECUTE);
        if (aclresult != ACLCHECK_OK)
            aclcheck_error(aclresult, ACL_KIND_PROC,
                           get_func_name(aggref->aggfnoid));
        InvokeFunctionExecuteHook(aggref->aggfnoid);

        /* planner recorded transition state type in the Aggref itself */
        aggtranstype = aggref->aggtranstype;
        Assert(OidIsValid(aggtranstype));

        /*
         * If this aggregation is performing state combines, then instead of
         * using the transition function, we'll use the combine function
         */
        if (DO_AGGSPLIT_COMBINE(aggstate->aggsplit))
        {
            transfn_oid = aggform->aggcombinefn;

            /* If not set then the planner messed up */
            if (!OidIsValid(transfn_oid))
                elog(ERROR, "combinefn not set for aggregate function");
        }
        else
            transfn_oid = aggform->aggtransfn;

        /* Final function only required if we're finalizing the aggregates */
        if (DO_AGGSPLIT_SKIPFINAL(aggstate->aggsplit))
            peragg->finalfn_oid = finalfn_oid = InvalidOid;
        else
            peragg->finalfn_oid = finalfn_oid = aggform->aggfinalfn;

        serialfn_oid = InvalidOid;
        deserialfn_oid = InvalidOid;

        /*
         * Check if serialization/deserialization is required.  We only do it
         * for aggregates that have transtype INTERNAL.
         */
        if (aggtranstype == INTERNALOID)
        {
            /*
             * The planner should only have generated a serialize agg node if
             * every aggregate with an INTERNAL state has a serialization
             * function.  Verify that.
             */
            if (DO_AGGSPLIT_SERIALIZE(aggstate->aggsplit))
            {
                /* serialization only valid when not running finalfn */
                Assert(DO_AGGSPLIT_SKIPFINAL(aggstate->aggsplit));

                if (!OidIsValid(aggform->aggserialfn))
                    elog(ERROR, "serialfunc not provided for serialization aggregation");
                serialfn_oid = aggform->aggserialfn;
            }

            /* Likewise for deserialization functions */
            if (DO_AGGSPLIT_DESERIALIZE(aggstate->aggsplit))
            {
                /* deserialization only valid when combining states */
                Assert(DO_AGGSPLIT_COMBINE(aggstate->aggsplit));

                if (!OidIsValid(aggform->aggdeserialfn))
                    elog(ERROR, "deserialfunc not provided for deserialization aggregation");
                deserialfn_oid = aggform->aggdeserialfn;
            }
        }

        /* Check that aggregate owner has permission to call component fns */
        {
            HeapTuple   procTuple;
            Oid         aggOwner;

            procTuple = SearchSysCache1(PROCOID,
                                        ObjectIdGetDatum(aggref->aggfnoid));
            if (!HeapTupleIsValid(procTuple))
                elog(ERROR, "cache lookup failed for function %u",
                     aggref->aggfnoid);
            aggOwner = ((Form_pg_proc) GETSTRUCT(procTuple))->proowner;
            ReleaseSysCache(procTuple);

            aclresult = pg_proc_aclcheck(transfn_oid, aggOwner,
                                         ACL_EXECUTE);
            if (aclresult != ACLCHECK_OK)
                aclcheck_error(aclresult, ACL_KIND_PROC,
                               get_func_name(transfn_oid));
            InvokeFunctionExecuteHook(transfn_oid);
            if (OidIsValid(finalfn_oid))
            {
                aclresult = pg_proc_aclcheck(finalfn_oid, aggOwner,
                                             ACL_EXECUTE);
                if (aclresult != ACLCHECK_OK)
                    aclcheck_error(aclresult, ACL_KIND_PROC,
                                   get_func_name(finalfn_oid));
                InvokeFunctionExecuteHook(finalfn_oid);
            }
            if (OidIsValid(serialfn_oid))
            {
                aclresult = pg_proc_aclcheck(serialfn_oid, aggOwner,
                                             ACL_EXECUTE);
                if (aclresult != ACLCHECK_OK)
                    aclcheck_error(aclresult, ACL_KIND_PROC,
                                   get_func_name(serialfn_oid));
                InvokeFunctionExecuteHook(serialfn_oid);
            }
            if (OidIsValid(deserialfn_oid))
            {
                aclresult = pg_proc_aclcheck(deserialfn_oid, aggOwner,
                                             ACL_EXECUTE);
                if (aclresult != ACLCHECK_OK)
                    aclcheck_error(aclresult, ACL_KIND_PROC,
                                   get_func_name(deserialfn_oid));
                InvokeFunctionExecuteHook(deserialfn_oid);
            }
        }

        /*
         * Get actual datatypes of the (nominal) aggregate inputs.  These
         * could be different from the agg's declared input types, when the
         * agg accepts ANY or a polymorphic type.
         */
        numArguments = get_aggregate_argtypes(aggref, inputTypes);

        /* Count the "direct" arguments, if any */
        numDirectArgs = list_length(aggref->aggdirectargs);

        /* Detect how many arguments to pass to the finalfn */
        if (aggform->aggfinalextra)
            peragg->numFinalArgs = numArguments + 1;
        else
            peragg->numFinalArgs = numDirectArgs + 1;

        /*
         * build expression trees using actual argument & result types for the
         * finalfn, if it exists and is required.
         */
        if (OidIsValid(finalfn_oid))
        {
            build_aggregate_finalfn_expr(inputTypes,
                                         peragg->numFinalArgs,
                                         aggtranstype,
                                         aggref->aggtype,
                                         aggref->inputcollid,
                                         finalfn_oid,
                                         &finalfnexpr);
            fmgr_info(finalfn_oid, &peragg->finalfn);
            fmgr_info_set_expr((Node *) finalfnexpr, &peragg->finalfn);
        }

        /* get info about the output value's datatype */
        get_typlenbyval(aggref->aggtype,
                        &peragg->resulttypeLen,
                        &peragg->resulttypeByVal);

        /*
         * initval is potentially null, so don't try to access it as a struct
         * field. Must do it the hard way with SysCacheGetAttr.
         */
        textInitVal = SysCacheGetAttr(AGGFNOID, aggTuple,
                                      Anum_pg_aggregate_agginitval,
                                      &initValueIsNull);
        if (initValueIsNull)
            initValue = (Datum) 0;
        else
            initValue = GetAggInitVal(textInitVal, aggtranstype);

        /*
         * 2. Build working state for invoking the transition function, or
         * look up previously initialized working state, if we can share it.
         *
         * find_compatible_peragg() already collected a list of per-Trans's
         * with the same inputs. Check if any of them have the same transition
         * function and initial value.
         */
        existing_transno = find_compatible_pertrans(aggstate, aggref,
                                                    transfn_oid, aggtranstype,
                                                    serialfn_oid, deserialfn_oid,
                                                    initValue, initValueIsNull,
                                                    same_input_transnos);
        if (existing_transno != -1)
        {
            /*
             * Existing compatible trans found, so just point the 'peragg' to
             * the same per-trans struct.
             */
            pertrans = &pertransstates[existing_transno];
            peragg->transno = existing_transno;
        }
        else
        {
            pertrans = &pertransstates[++transno];
            build_pertrans_for_aggref(pertrans, aggstate, estate,
                                      aggref, transfn_oid, aggtranstype,
                                      serialfn_oid, deserialfn_oid,
                                      initValue, initValueIsNull,
                                      inputTypes, numArguments);
            peragg->transno = transno;
        }
        ReleaseSysCache(aggTuple);
    }

    /*
     * Update numaggs to match the number of unique aggregates found. Also set
     * numstates to the number of unique aggregate states found.
     */
    aggstate->numaggs = aggno + 1;
    aggstate->numtrans = transno + 1;

    /*
     * Build a single projection computing the aggregate arguments for all
     * aggregates at once, that's considerably faster than doing it separately
     * for each.
     *
     * First create a targetlist combining the targetlist of all the
     * transitions.
     */
    combined_inputeval = NIL;
    column_offset = 0;
    for (transno = 0; transno < aggstate->numtrans; transno++)
    {
        AggStatePerTrans pertrans = &pertransstates[transno];
        ListCell   *arg;

        pertrans->inputoff = column_offset;

        /*
         * Adjust resno in a copied target entries, to point into the combined
         * slot.
         */
        foreach(arg, pertrans->aggref->args)
        {
            TargetEntry *source_tle = lfirst_node(TargetEntry, arg);
            TargetEntry *tle;

            tle = flatCopyTargetEntry(source_tle);
            tle->resno += column_offset;

            combined_inputeval = lappend(combined_inputeval, tle);
        }

        column_offset += list_length(pertrans->aggref->args);
    }

    /* and then create a projection for that targetlist */
    aggstate->evaldesc = ExecTypeFromTL(combined_inputeval, false);
    aggstate->evalslot = ExecInitExtraTupleSlot(estate);
    aggstate->evalproj = ExecBuildProjectionInfo(combined_inputeval,
                                                 aggstate->tmpcontext,
                                                 aggstate->evalslot,
                                                 &aggstate->ss.ps,
                                                 NULL);
    ExecSetSlotDescriptor(aggstate->evalslot, aggstate->evaldesc);

    return aggstate;
}

void ExecReScanAgg

(

AggState *

node

)

Definition at line 3896 of file nodeAgg.c.

References AggState::agg_done, AGG_HASHED, AGG_MIXED, AggState::aggcontexts, Agg::aggParams, AggState::aggstrategy, bms_overlap(), build_hash_table(), PlanState::chgParam, ExprContext::ecxt_aggnulls, ExprContext::ecxt_aggvalues, ExecClearTuple(), ExecReScan(), AggState::grp_firstTuple, AggState::hashcontext, AggStatePerHashData::hashiter, AggStatePerHashData::hashtable, heap_freetuple(), initialize_phase(), AggState::input_done, Max, AggState::maxsets, MemSet, NULL, AggState::numaggs, AggState::numtrans, outerPlan, outerPlanState, AggState::pergroup, AggState::perhash, AggState::pertrans, PlanState::plan, AggState::projected_set, ScanState::ps, PlanState::ps_ExprContext, ReScanExprContext(), ResetTupleHashIterator, select_current_set(), AggStatePerTransData::sortstates, AggState::ss, ScanState::ss_ScanTupleSlot, AggState::table_filled, and tuplesort_end().

Referenced by ExecReScan().

{
    ExprContext *econtext = node->ss.ps.ps_ExprContext;
    PlanState  *outerPlan = outerPlanState(node);
    Agg        *aggnode = (Agg *) node->ss.ps.plan;
    int         transno;
    int         numGroupingSets = Max(node->maxsets, 1);
    int         setno;

    node->agg_done = false;

    if (node->aggstrategy == AGG_HASHED)
    {
        /*
         * In the hashed case, if we haven't yet built the hash table then we
         * can just return; nothing done yet, so nothing to undo. If subnode's
         * chgParam is not NULL then it will be re-scanned by ExecProcNode,
         * else no reason to re-scan it at all.
         */
        if (!node->table_filled)
            return;

        /*
         * If we do have the hash table, and the subplan does not have any
         * parameter changes, and none of our own parameter changes affect
         * input expressions of the aggregated functions, then we can just
         * rescan the existing hash table; no need to build it again.
         */
        if (outerPlan->chgParam == NULL &&
            !bms_overlap(node->ss.ps.chgParam, aggnode->aggParams))
        {
            ResetTupleHashIterator(node->perhash[0].hashtable,
                                   &node->perhash[0].hashiter);
            select_current_set(node, 0, true);
            return;
        }
    }

    /* Make sure we have closed any open tuplesorts */
    for (transno = 0; transno < node->numtrans; transno++)
    {
        for (setno = 0; setno < numGroupingSets; setno++)
        {
            AggStatePerTrans pertrans = &node->pertrans[transno];

            if (pertrans->sortstates[setno])
            {
                tuplesort_end(pertrans->sortstates[setno]);
                pertrans->sortstates[setno] = NULL;
            }
        }
    }

    /*
     * We don't need to ReScanExprContext the output tuple context here;
     * ExecReScan already did it. But we do need to reset our per-grouping-set
     * contexts, which may have transvalues stored in them. (We use rescan
     * rather than just reset because transfns may have registered callbacks
     * that need to be run now.) For the AGG_HASHED case, see below.
     */

    for (setno = 0; setno < numGroupingSets; setno++)
    {
        ReScanExprContext(node->aggcontexts[setno]);
    }

    /* Release first tuple of group, if we have made a copy */
    if (node->grp_firstTuple != NULL)
    {
        heap_freetuple(node->grp_firstTuple);
        node->grp_firstTuple = NULL;
    }
    ExecClearTuple(node->ss.ss_ScanTupleSlot);

    /* Forget current agg values */
    MemSet(econtext->ecxt_aggvalues, 0, sizeof(Datum) * node->numaggs);
    MemSet(econtext->ecxt_aggnulls, 0, sizeof(bool) * node->numaggs);

    /*
     * With AGG_HASHED/MIXED, the hash table is allocated in a sub-context of
     * the hashcontext. This used to be an issue, but now, resetting a context
     * automatically deletes sub-contexts too.
     */
    if (node->aggstrategy == AGG_HASHED || node->aggstrategy == AGG_MIXED)
    {
        ReScanExprContext(node->hashcontext);
        /* Rebuild an empty hash table */
        build_hash_table(node);
        node->table_filled = false;
        /* iterator will be reset when the table is filled */
    }

    if (node->aggstrategy != AGG_HASHED)
    {
        /*
         * Reset the per-group state (in particular, mark transvalues null)
         */
        MemSet(node->pergroup, 0,
               sizeof(AggStatePerGroupData) * node->numaggs * numGroupingSets);

        /* reset to phase 1 */
        initialize_phase(node, 1);

        node->input_done = false;
        node->projected_set = -1;
    }

    if (outerPlan->chgParam == NULL)
        ExecReScan(outerPlan);
}

Size hash_agg_entry_size

(

int

numAggs

)

Definition at line 2012 of file nodeAgg.c.

References MAXALIGN.

Referenced by create_distinct_paths(), and estimate_hashagg_tablesize().

{
    Size        entrysize;

    /* This must match build_hash_table */
    entrysize = sizeof(TupleHashEntryData) +
        numAggs * sizeof(AggStatePerGroupData);
    entrysize = MAXALIGN(entrysize);

    return entrysize;
}