This patch changes int2_avg_accum() and int4_avg_accum() use the nodeAgg

performance hack Tom introduced recently. This means we can avoid
copying the transition array for each input tuple if these functions
are invoked as aggregate transition functions.

To test the performance improvement, I created a 1 million row table
with a single int4 column. Without the patch, SELECT avg(col) FROM
table took about 4.2 seconds (after the data was cached); with the
patch, it took about 3.2 seconds. Naturally, the performance
improvement for a less trivial query (or a table with wider rows)
would be relatively smaller.

diff --git a/src/backend/utils/adt/numeric.c b/src/backend/utils/adt/numeric.c
index 411891e269b1d0225534e6512346ae6046c9915a..a459ca2d6e42975699e52b26c6bc16e0ea8d25bb 100644 (file)
--- a/src/backend/utils/adt/numeric.c
+++ b/src/backend/utils/adt/numeric.c
@@ -14,7 +14,7 @@
  * Copyright (c) 1998-2005, PostgreSQL Global Development Group
  *
  * IDENTIFICATION
- *       $PostgreSQL: pgsql/src/backend/utils/adt/numeric.c,v 1.81 2005/01/01 05:43:07 momjian Exp $
+ *       $PostgreSQL: pgsql/src/backend/utils/adt/numeric.c,v 1.82 2005/04/04 23:50:27 neilc Exp $
  *
  *-------------------------------------------------------------------------
  */
@@ -2462,17 +2462,24 @@ typedef struct Int8TransTypeData
 Datum
 int2_avg_accum(PG_FUNCTION_ARGS)
 {
-       ArrayType  *transarray = PG_GETARG_ARRAYTYPE_P_COPY(0);
+       ArrayType  *transarray;
        int16           newval = PG_GETARG_INT16(1);
        Int8TransTypeData *transdata;
 
        /*
-        * We copied the input array, so it's okay to scribble on it directly.
+        * If we're invoked by nodeAgg, we can cheat and modify our first
+        * parameter in-place to reduce palloc overhead. Otherwise we need
+        * to make a copy of it before scribbling on it.
         */
+       if (fcinfo->context && IsA(fcinfo->context, AggState))
+               transarray = PG_GETARG_ARRAYTYPE_P(0);
+       else
+               transarray = PG_GETARG_ARRAYTYPE_P_COPY(0);
+
        if (ARR_SIZE(transarray) != ARR_OVERHEAD(1) + sizeof(Int8TransTypeData))
                elog(ERROR, "expected 2-element int8 array");
-       transdata = (Int8TransTypeData *) ARR_DATA_PTR(transarray);
 
+       transdata = (Int8TransTypeData *) ARR_DATA_PTR(transarray);
        transdata->count++;
        transdata->sum += newval;
 
@@ -2482,17 +2489,24 @@ int2_avg_accum(PG_FUNCTION_ARGS)
 Datum
 int4_avg_accum(PG_FUNCTION_ARGS)
 {
-       ArrayType  *transarray = PG_GETARG_ARRAYTYPE_P_COPY(0);
+       ArrayType  *transarray;
        int32           newval = PG_GETARG_INT32(1);
        Int8TransTypeData *transdata;
 
        /*
-        * We copied the input array, so it's okay to scribble on it directly.
+        * If we're invoked by nodeAgg, we can cheat and modify our first
+        * parameter in-place to reduce palloc overhead. Otherwise we need
+        * to make a copy of it before scribbling on it.
         */
+       if (fcinfo->context && IsA(fcinfo->context, AggState))
+               transarray = PG_GETARG_ARRAYTYPE_P(0);
+       else
+               transarray = PG_GETARG_ARRAYTYPE_P_COPY(0);
+
        if (ARR_SIZE(transarray) != ARR_OVERHEAD(1) + sizeof(Int8TransTypeData))
                elog(ERROR, "expected 2-element int8 array");
-       transdata = (Int8TransTypeData *) ARR_DATA_PTR(transarray);
 
+       transdata = (Int8TransTypeData *) ARR_DATA_PTR(transarray);
        transdata->count++;
        transdata->sum += newval;