#include "executor/executor.h"
#include "executor/nodeAgg.h"
#include "miscadmin.h"
+#include "nodes/makefuncs.h"
#include "nodes/nodeFuncs.h"
#include "optimizer/clauses.h"
#include "optimizer/tlist.h"
*/
int numInputs;
+ /* offset of input columns in AggState->evalslot */
+ int inputoff;
+
/*
* Number of aggregated input columns to pass to the transfn. This
* includes the ORDER BY columns for ordered-set aggs, but not for plain
/* ExprStates of the FILTER and argument expressions. */
ExprState *aggfilter; /* state of FILTER expression, if any */
- List *args; /* states of aggregated-argument expressions */
List *aggdirectargs; /* states of direct-argument expressions */
/*
transtypeByVal;
/*
- * Stuff for evaluation of inputs. We used to just use ExecEvalExpr, but
- * with the addition of ORDER BY we now need at least a slot for passing
- * data to the sort object, which requires a tupledesc, so we might as
- * well go whole hog and use ExecProject too.
+ * Stuff for evaluation of aggregate inputs in cases where the aggregate
+ * requires sorted input. The arguments themselves will be evaluated via
+ * AggState->evalslot/evalproj for all aggregates at once, but we only
+ * want to sort the relevant columns for individual aggregates.
*/
- TupleDesc evaldesc; /* descriptor of input tuples */
- ProjectionInfo *evalproj; /* projection machinery */
+ TupleDesc sortdesc; /* descriptor of input tuples */
/*
* Slots for holding the evaluated input arguments. These are set up
- * during ExecInitAgg() and then used for each input row.
+ * during ExecInitAgg() and then used for each input row requiring
+ * procesessing besides what's done in AggState->evalproj.
*/
- TupleTableSlot *evalslot; /* current input tuple */
+ TupleTableSlot *sortslot; /* current input tuple */
TupleTableSlot *uniqslot; /* used for multi-column DISTINCT */
/*
*/
if (pertrans->numInputs == 1)
pertrans->sortstates[aggstate->current_set] =
- tuplesort_begin_datum(pertrans->evaldesc->attrs[0]->atttypid,
+ tuplesort_begin_datum(pertrans->sortdesc->attrs[0]->atttypid,
pertrans->sortOperators[0],
pertrans->sortCollations[0],
pertrans->sortNullsFirst[0],
work_mem, false);
else
pertrans->sortstates[aggstate->current_set] =
- tuplesort_begin_heap(pertrans->evaldesc,
+ tuplesort_begin_heap(pertrans->sortdesc,
pertrans->numSortCols,
pertrans->sortColIdx,
pertrans->sortOperators,
int setno = 0;
int numGroupingSets = Max(aggstate->phase->numsets, 1);
int numTrans = aggstate->numtrans;
+ TupleTableSlot *slot = aggstate->evalslot;
+
+ /* compute input for all aggregates */
+ if (aggstate->evalproj)
+ aggstate->evalslot = ExecProject(aggstate->evalproj, NULL);
for (transno = 0; transno < numTrans; transno++)
{
ExprState *filter = pertrans->aggfilter;
int numTransInputs = pertrans->numTransInputs;
int i;
- TupleTableSlot *slot;
+ int inputoff = pertrans->inputoff;
/* Skip anything FILTERed out */
if (filter)
continue;
}
- /* Evaluate the current input expressions for this aggregate */
- slot = ExecProject(pertrans->evalproj, NULL);
-
if (pertrans->numSortCols > 0)
{
/* DISTINCT and/or ORDER BY case */
- Assert(slot->tts_nvalid == pertrans->numInputs);
+ Assert(slot->tts_nvalid >= (pertrans->numInputs + inputoff));
/*
* If the transfn is strict, we want to check for nullity before
{
for (i = 0; i < numTransInputs; i++)
{
- if (slot->tts_isnull[i])
+ if (slot->tts_isnull[i + inputoff])
break;
}
if (i < numTransInputs)
/* OK, put the tuple into the tuplesort object */
if (pertrans->numInputs == 1)
tuplesort_putdatum(pertrans->sortstates[setno],
- slot->tts_values[0],
- slot->tts_isnull[0]);
+ slot->tts_values[inputoff],
+ slot->tts_isnull[inputoff]);
else
- tuplesort_puttupleslot(pertrans->sortstates[setno], slot);
+ {
+ /*
+ * Copy slot contents, starting from inputoff, into sort
+ * slot.
+ */
+ ExecClearTuple(pertrans->sortslot);
+ memcpy(pertrans->sortslot->tts_values,
+ &slot->tts_values[inputoff],
+ pertrans->numInputs * sizeof(Datum));
+ memcpy(pertrans->sortslot->tts_isnull,
+ &slot->tts_isnull[inputoff],
+ pertrans->numInputs * sizeof(bool));
+ pertrans->sortslot->tts_nvalid = pertrans->numInputs;
+ ExecStoreVirtualTuple(pertrans->sortslot);
+ tuplesort_puttupleslot(pertrans->sortstates[setno], pertrans->sortslot);
+ }
}
}
else
Assert(slot->tts_nvalid >= numTransInputs);
for (i = 0; i < numTransInputs; i++)
{
- fcinfo->arg[i + 1] = slot->tts_values[i];
- fcinfo->argnull[i + 1] = slot->tts_isnull[i];
+ fcinfo->arg[i + 1] = slot->tts_values[i + inputoff];
+ fcinfo->argnull[i + 1] = slot->tts_isnull[i + inputoff];
}
for (setno = 0; setno < numGroupingSets; setno++)
{
int transno;
int numTrans = aggstate->numtrans;
+ TupleTableSlot *slot = NULL;
/* combine not supported with grouping sets */
Assert(aggstate->phase->numsets == 0);
+ /* compute input for all aggregates */
+ if (aggstate->evalproj)
+ slot = ExecProject(aggstate->evalproj, NULL);
+
for (transno = 0; transno < numTrans; transno++)
{
AggStatePerTrans pertrans = &aggstate->pertrans[transno];
AggStatePerGroup pergroupstate = &pergroup[transno];
- TupleTableSlot *slot;
FunctionCallInfo fcinfo = &pertrans->transfn_fcinfo;
+ int inputoff = pertrans->inputoff;
- /* Evaluate the current input expressions for this aggregate */
- slot = ExecProject(pertrans->evalproj, NULL);
Assert(slot->tts_nvalid >= 1);
+ Assert(slot->tts_nvalid + inputoff >= 1);
/*
* deserialfn_oid will be set if we must deserialize the input state
if (OidIsValid(pertrans->deserialfn_oid))
{
/* Don't call a strict deserialization function with NULL input */
- if (pertrans->deserialfn.fn_strict && slot->tts_isnull[0])
+ if (pertrans->deserialfn.fn_strict && slot->tts_isnull[inputoff])
{
- fcinfo->arg[1] = slot->tts_values[0];
- fcinfo->argnull[1] = slot->tts_isnull[0];
+ fcinfo->arg[1] = slot->tts_values[inputoff];
+ fcinfo->argnull[1] = slot->tts_isnull[inputoff];
}
else
{
FunctionCallInfo dsinfo = &pertrans->deserialfn_fcinfo;
MemoryContext oldContext;
- dsinfo->arg[0] = slot->tts_values[0];
- dsinfo->argnull[0] = slot->tts_isnull[0];
+ dsinfo->arg[0] = slot->tts_values[inputoff];
+ dsinfo->argnull[0] = slot->tts_isnull[inputoff];
/* Dummy second argument for type-safety reasons */
dsinfo->arg[1] = PointerGetDatum(NULL);
dsinfo->argnull[1] = false;
}
else
{
- fcinfo->arg[1] = slot->tts_values[0];
- fcinfo->argnull[1] = slot->tts_isnull[0];
+ fcinfo->arg[1] = slot->tts_values[inputoff];
+ fcinfo->argnull[1] = slot->tts_isnull[inputoff];
}
advance_combine_function(aggstate, pertrans, pergroupstate);
{
MemoryContext workcontext = aggstate->tmpcontext->ecxt_per_tuple_memory;
FunctionCallInfo fcinfo = &pertrans->transfn_fcinfo;
- TupleTableSlot *slot1 = pertrans->evalslot;
+ TupleTableSlot *slot1 = pertrans->sortslot;
TupleTableSlot *slot2 = pertrans->uniqslot;
int numTransInputs = pertrans->numTransInputs;
int numDistinctCols = pertrans->numDistinctCols;
transno,
aggno;
int phase;
+ List *combined_inputeval;
ListCell *l;
Bitmapset *all_grouped_cols = NULL;
int numGroupingSets = 1;
int numPhases;
+ int column_offset;
int i = 0;
int j = 0;
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 = (TargetEntry *) lfirst(arg);
+ TargetEntry *tle;
+
+ Assert(IsA(source_tle, TargetEntry));
+ 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);
+ combined_inputeval = (List *) ExecInitExpr((Expr *) combined_inputeval,
+ (PlanState *) aggstate);
+ aggstate->evalproj = ExecBuildProjectionInfo(combined_inputeval,
+ aggstate->tmpcontext,
+ aggstate->evalslot,
+ NULL);
+ ExecSetSlotDescriptor(aggstate->evalslot, aggstate->evaldesc);
+
return aggstate;
}
}
- /*
- * Get a tupledesc corresponding to the aggregated inputs (including sort
- * expressions) of the agg.
- */
- pertrans->evaldesc = ExecTypeFromTL(aggref->args, false);
-
- /* Create slot we're going to do argument evaluation in */
- pertrans->evalslot = ExecInitExtraTupleSlot(estate);
- ExecSetSlotDescriptor(pertrans->evalslot, pertrans->evaldesc);
-
/* Initialize the input and FILTER expressions */
naggs = aggstate->numaggs;
pertrans->aggfilter = ExecInitExpr(aggref->aggfilter,
(PlanState *) aggstate);
pertrans->aggdirectargs = (List *) ExecInitExpr((Expr *) aggref->aggdirectargs,
(PlanState *) aggstate);
- pertrans->args = (List *) ExecInitExpr((Expr *) aggref->args,
- (PlanState *) aggstate);
/*
* Complain if the aggregate's arguments contain any aggregates; nested
(errcode(ERRCODE_GROUPING_ERROR),
errmsg("aggregate function calls cannot be nested")));
- /* Set up projection info for evaluation */
- pertrans->evalproj = ExecBuildProjectionInfo(pertrans->args,
- aggstate->tmpcontext,
- pertrans->evalslot,
- NULL);
-
/*
* If we're doing either DISTINCT or ORDER BY for a plain agg, then we
* have a list of SortGroupClause nodes; fish out the data in them and
if (numSortCols > 0)
{
+ /*
+ * Get a tupledesc and slot corresponding to the aggregated inputs
+ * (including sort expressions) of the agg.
+ */
+ pertrans->sortdesc = ExecTypeFromTL(aggref->args, false);
+ pertrans->sortslot = ExecInitExtraTupleSlot(estate);
+ ExecSetSlotDescriptor(pertrans->sortslot, pertrans->sortdesc);
+
/*
* We don't implement DISTINCT or ORDER BY aggs in the HASHED case
* (yet)
/* we will need an extra slot to store prior values */
pertrans->uniqslot = ExecInitExtraTupleSlot(estate);
ExecSetSlotDescriptor(pertrans->uniqslot,
- pertrans->evaldesc);
+ pertrans->sortdesc);
}
/* Extract the sort information for use later */