Skip to content

P
Postgres FD Implementation
Commit 69c8fbac authored by Tom Lane's avatar Tom Lane
Browse files
Options

Improve performance of numeric sum(), avg(), stddev(), variance(), etc. 

This patch improves performance of most built-in aggregates that formerly
used a NUMERIC or NUMERIC array as their transition type; this includes
not only aggregates on numeric inputs, but some aggregates on integer
inputs where overflow of an int8 value is a possibility.  The code now
uses a special-purpose data structure to avoid array construction and
deconstruction overhead, as well as packing and unpacking overhead for
numeric values.

These aggregates' transition type is now declared as INTERNAL, since
it doesn't correspond to any SQL data type.  To keep the planner from
thinking that that means a lot of storage will be used, we make use
of the just-added pg_aggregate.aggtransspace feature.  The space estimate
is set to 128 bytes, which is at least in the right ballpark.

Hadi Moshayedi, reviewed by Pavel Stehule and Tomas Vondra
parent 6cb86143
Expand all Show whitespace changes
Inline Side-by-side
Showing with 362 additions and 186 deletions
src/backend/utils/adt/numeric.c
View file @ 69c8fbac
This diff is collapsed.
src/include/catalog/catversion.h
View file @ 69c8fbac
......@@ -53,6 +53,6 @@
*/
/* yyyymmddN */
#define CATALOG_VERSION_NO 201311161
#define CATALOG_VERSION_NO 201311162
#endif
src/include/catalog/pg_aggregate.h
View file @ 69c8fbac
......@@ -80,23 +80,23 @@ typedef FormData_pg_aggregate *Form_pg_aggregate;
*/
/* avg */
DATA(insert ( 2100 int8_avg_accum numeric_avg 0 1231 0 "{0,0}" ));
DATA(insert ( 2100 int8_avg_accum numeric_avg 0 2281 128 _null_ ));
DATA(insert ( 2101 int4_avg_accum int8_avg 0 1016 0 "{0,0}" ));
DATA(insert ( 2102 int2_avg_accum int8_avg 0 1016 0 "{0,0}" ));
DATA(insert ( 2103 numeric_avg_accum numeric_avg 0 1231 0 "{0,0}" ));
DATA(insert ( 2103 numeric_avg_accum numeric_avg 0 2281 128 _null_ ));
DATA(insert ( 2104 float4_accum float8_avg 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2105 float8_accum float8_avg 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2106 interval_accum interval_avg 0 1187 0 "{0 second,0 second}" ));
/* sum */
DATA(insert ( 2107 int8_sum - 0 1700 0 _null_ ));
DATA(insert ( 2107 int8_avg_accum numeric_sum 0 2281 128 _null_ ));
DATA(insert ( 2108 int4_sum - 0 20 0 _null_ ));
DATA(insert ( 2109 int2_sum - 0 20 0 _null_ ));
DATA(insert ( 2110 float4pl - 0 700 0 _null_ ));
DATA(insert ( 2111 float8pl - 0 701 0 _null_ ));
DATA(insert ( 2112 cash_pl - 0 790 0 _null_ ));
DATA(insert ( 2113 interval_pl - 0 1186 0 _null_ ));
DATA(insert ( 2114 numeric_add - 0 1700 0 _null_ ));
DATA(insert ( 2114 numeric_avg_accum numeric_sum 0 2281 128 _null_ ));
/* max */
DATA(insert ( 2115 int8larger - 413 20 0 _null_ ));
......@@ -147,52 +147,52 @@ DATA(insert ( 2147 int8inc_any - 0 20 0 "0" ));
DATA(insert ( 2803 int8inc - 0 20 0 "0" ));
/* var_pop */
DATA(insert ( 2718 int8_accum numeric_var_pop 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2719 int4_accum numeric_var_pop 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2720 int2_accum numeric_var_pop 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2718 int8_accum numeric_var_pop 0 2281 128 _null_ ));
DATA(insert ( 2719 int4_accum numeric_var_pop 0 2281 128 _null_ ));
DATA(insert ( 2720 int2_accum numeric_var_pop 0 2281 128 _null_ ));
DATA(insert ( 2721 float4_accum float8_var_pop 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2722 float8_accum float8_var_pop 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2723 numeric_accum numeric_var_pop 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2723 numeric_accum numeric_var_pop 0 2281 128 _null_ ));
/* var_samp */
DATA(insert ( 2641 int8_accum numeric_var_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2642 int4_accum numeric_var_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2643 int2_accum numeric_var_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2641 int8_accum numeric_var_samp 0 2281 128 _null_ ));
DATA(insert ( 2642 int4_accum numeric_var_samp 0 2281 128 _null_ ));
DATA(insert ( 2643 int2_accum numeric_var_samp 0 2281 128 _null_ ));
DATA(insert ( 2644 float4_accum float8_var_samp 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2645 float8_accum float8_var_samp 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2646 numeric_accum numeric_var_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2646 numeric_accum numeric_var_samp 0 2281 128 _null_ ));
/* variance: historical Postgres syntax for var_samp */
DATA(insert ( 2148 int8_accum numeric_var_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2149 int4_accum numeric_var_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2150 int2_accum numeric_var_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2148 int8_accum numeric_var_samp 0 2281 128 _null_ ));
DATA(insert ( 2149 int4_accum numeric_var_samp 0 2281 128 _null_ ));
DATA(insert ( 2150 int2_accum numeric_var_samp 0 2281 128 _null_ ));
DATA(insert ( 2151 float4_accum float8_var_samp 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2152 float8_accum float8_var_samp 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2153 numeric_accum numeric_var_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2153 numeric_accum numeric_var_samp 0 2281 128 _null_ ));
/* stddev_pop */
DATA(insert ( 2724 int8_accum numeric_stddev_pop 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2725 int4_accum numeric_stddev_pop 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2726 int2_accum numeric_stddev_pop 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2724 int8_accum numeric_stddev_pop 0 2281 128 _null_ ));
DATA(insert ( 2725 int4_accum numeric_stddev_pop 0 2281 128 _null_ ));
DATA(insert ( 2726 int2_accum numeric_stddev_pop 0 2281 128 _null_ ));
DATA(insert ( 2727 float4_accum float8_stddev_pop 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2728 float8_accum float8_stddev_pop 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2729 numeric_accum numeric_stddev_pop 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2729 numeric_accum numeric_stddev_pop 0 2281 128 _null_ ));
/* stddev_samp */
DATA(insert ( 2712 int8_accum numeric_stddev_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2713 int4_accum numeric_stddev_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2714 int2_accum numeric_stddev_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2712 int8_accum numeric_stddev_samp 0 2281 128 _null_ ));
DATA(insert ( 2713 int4_accum numeric_stddev_samp 0 2281 128 _null_ ));
DATA(insert ( 2714 int2_accum numeric_stddev_samp 0 2281 128 _null_ ));
DATA(insert ( 2715 float4_accum float8_stddev_samp 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2716 float8_accum float8_stddev_samp 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2717 numeric_accum numeric_stddev_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2717 numeric_accum numeric_stddev_samp 0 2281 128 _null_ ));
/* stddev: historical Postgres syntax for stddev_samp */
DATA(insert ( 2154 int8_accum numeric_stddev_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2155 int4_accum numeric_stddev_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2156 int2_accum numeric_stddev_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2154 int8_accum numeric_stddev_samp 0 2281 128 _null_ ));
DATA(insert ( 2155 int4_accum numeric_stddev_samp 0 2281 128 _null_ ));
DATA(insert ( 2156 int2_accum numeric_stddev_samp 0 2281 128 _null_ ));
DATA(insert ( 2157 float4_accum float8_stddev_samp 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2158 float8_accum float8_stddev_samp 0 1022 0 "{0,0,0}" ));
DATA(insert ( 2159 numeric_accum numeric_stddev_samp 0 1231 0 "{0,0,0}" ));
DATA(insert ( 2159 numeric_accum numeric_stddev_samp 0 2281 128 _null_ ));
/* SQL2003 binary regression aggregates */
DATA(insert ( 2818 int8inc_float8_float8 - 0 20 0 "0" ));
......
src/include/catalog/pg_proc.h
View file @ 69c8fbac
......@@ -2390,27 +2390,29 @@ DATA(insert OID = 2513 ( float8_stddev_pop PGNSP PGUID 12 1 0 0 0 f f f f t f i
DESCR("aggregate final function");
DATA(insert OID = 1832 ( float8_stddev_samp PGNSP PGUID 12 1 0 0 0 f f f f t f i 1 0 701 "1022" _null_ _null_ _null_ _null_ float8_stddev_samp _null_ _null_ _null_ ));
DESCR("aggregate final function");
DATA(insert OID = 1833 ( numeric_accum PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 1231 "1231 1700" _null_ _null_ _null_ _null_ numeric_accum _null_ _null_ _null_ ));
DATA(insert OID = 1833 ( numeric_accum PGNSP PGUID 12 1 0 0 0 f f f f f f i 2 0 2281 "2281 1700" _null_ _null_ _null_ _null_ numeric_accum _null_ _null_ _null_ ));
DESCR("aggregate transition function");
DATA(insert OID = 2858 ( numeric_avg_accum PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 1231 "1231 1700" _null_ _null_ _null_ _null_ numeric_avg_accum _null_ _null_ _null_ ));
DATA(insert OID = 2858 ( numeric_avg_accum PGNSP PGUID 12 1 0 0 0 f f f f f f i 2 0 2281 "2281 1700" _null_ _null_ _null_ _null_ numeric_avg_accum _null_ _null_ _null_ ));
DESCR("aggregate transition function");
DATA(insert OID = 1834 ( int2_accum PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 1231 "1231 21" _null_ _null_ _null_ _null_ int2_accum _null_ _null_ _null_ ));
DATA(insert OID = 1834 ( int2_accum PGNSP PGUID 12 1 0 0 0 f f f f f f i 2 0 2281 "2281 21" _null_ _null_ _null_ _null_ int2_accum _null_ _null_ _null_ ));
DESCR("aggregate transition function");
DATA(insert OID = 1835 ( int4_accum PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 1231 "1231 23" _null_ _null_ _null_ _null_ int4_accum _null_ _null_ _null_ ));
DATA(insert OID = 1835 ( int4_accum PGNSP PGUID 12 1 0 0 0 f f f f f f i 2 0 2281 "2281 23" _null_ _null_ _null_ _null_ int4_accum _null_ _null_ _null_ ));
DESCR("aggregate transition function");
DATA(insert OID = 1836 ( int8_accum PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 1231 "1231 20" _null_ _null_ _null_ _null_ int8_accum _null_ _null_ _null_ ));
DATA(insert OID = 1836 ( int8_accum PGNSP PGUID 12 1 0 0 0 f f f f f f i 2 0 2281 "2281 20" _null_ _null_ _null_ _null_ int8_accum _null_ _null_ _null_ ));
DESCR("aggregate transition function");
DATA(insert OID = 2746 ( int8_avg_accum PGNSP PGUID 12 1 0 0 0 f f f f t f i 2 0 1231 "1231 20" _null_ _null_ _null_ _null_ int8_avg_accum _null_ _null_ _null_ ));
DATA(insert OID = 2746 ( int8_avg_accum PGNSP PGUID 12 1 0 0 0 f f f f f f i 2 0 2281 "2281 20" _null_ _null_ _null_ _null_ int8_avg_accum _null_ _null_ _null_ ));
DESCR("aggregate transition function");
DATA(insert OID = 1837 ( numeric_avg PGNSP PGUID 12 1 0 0 0 f f f f t f i 1 0 1700 "1231" _null_ _null_ _null_ _null_ numeric_avg _null_ _null_ _null_ ));
DATA(insert OID = 3178 ( numeric_sum PGNSP PGUID 12 1 0 0 0 f f f f f f i 1 0 1700 "2281" _null_ _null_ _null_ _null_ numeric_sum _null_ _null_ _null_ ));
DESCR("aggregate final function");
DATA(insert OID = 2514 ( numeric_var_pop PGNSP PGUID 12 1 0 0 0 f f f f t f i 1 0 1700 "1231" _null_ _null_ _null_ _null_ numeric_var_pop _null_ _null_ _null_ ));
DATA(insert OID = 1837 ( numeric_avg PGNSP PGUID 12 1 0 0 0 f f f f f f i 1 0 1700 "2281" _null_ _null_ _null_ _null_ numeric_avg _null_ _null_ _null_ ));
DESCR("aggregate final function");
DATA(insert OID = 1838 ( numeric_var_samp PGNSP PGUID 12 1 0 0 0 f f f f t f i 1 0 1700 "1231" _null_ _null_ _null_ _null_ numeric_var_samp _null_ _null_ _null_ ));
DATA(insert OID = 2514 ( numeric_var_pop PGNSP PGUID 12 1 0 0 0 f f f f f f i 1 0 1700 "2281" _null_ _null_ _null_ _null_ numeric_var_pop _null_ _null_ _null_ ));
DESCR("aggregate final function");
DATA(insert OID = 2596 ( numeric_stddev_pop PGNSP PGUID 12 1 0 0 0 f f f f t f i 1 0 1700 "1231" _null_ _null_ _null_ _null_ numeric_stddev_pop _null_ _null_ _null_ ));
DATA(insert OID = 1838 ( numeric_var_samp PGNSP PGUID 12 1 0 0 0 f f f f f f i 1 0 1700 "2281" _null_ _null_ _null_ _null_ numeric_var_samp _null_ _null_ _null_ ));
DESCR("aggregate final function");
DATA(insert OID = 1839 ( numeric_stddev_samp PGNSP PGUID 12 1 0 0 0 f f f f t f i 1 0 1700 "1231" _null_ _null_ _null_ _null_ numeric_stddev_samp _null_ _null_ _null_ ));
DATA(insert OID = 2596 ( numeric_stddev_pop PGNSP PGUID 12 1 0 0 0 f f f f f f i 1 0 1700 "2281" _null_ _null_ _null_ _null_ numeric_stddev_pop _null_ _null_ _null_ ));
DESCR("aggregate final function");
DATA(insert OID = 1839 ( numeric_stddev_samp PGNSP PGUID 12 1 0 0 0 f f f f f f i 1 0 1700 "2281" _null_ _null_ _null_ _null_ numeric_stddev_samp _null_ _null_ _null_ ));
DESCR("aggregate final function");
DATA(insert OID = 1840 ( int2_sum PGNSP PGUID 12 1 0 0 0 f f f f f f i 2 0 20 "20 21" _null_ _null_ _null_ _null_ int2_sum _null_ _null_ _null_ ));
DESCR("aggregate transition function");
......
src/include/utils/builtins.h
View file @ 69c8fbac
......@@ -989,6 +989,7 @@ extern Datum int4_accum(PG_FUNCTION_ARGS);
extern Datum int8_accum(PG_FUNCTION_ARGS);
extern Datum int8_avg_accum(PG_FUNCTION_ARGS);
extern Datum numeric_avg(PG_FUNCTION_ARGS);
extern Datum numeric_sum(PG_FUNCTION_ARGS);
extern Datum numeric_var_pop(PG_FUNCTION_ARGS);
extern Datum numeric_var_samp(PG_FUNCTION_ARGS);
extern Datum numeric_stddev_pop(PG_FUNCTION_ARGS);
......
src/test/regress/expected/aggregates.out
View file @ 69c8fbac
......@@ -137,6 +137,67 @@ SELECT stddev_pop(3.0::numeric), stddev_samp(4.0::numeric);
0 |
(1 row)
-- verify correct results for null and NaN inputs
select sum(null::int4) from generate_series(1,3);
sum
-----
(1 row)
select sum(null::int8) from generate_series(1,3);
sum
-----
(1 row)
select sum(null::numeric) from generate_series(1,3);
sum
-----
(1 row)
select sum(null::float8) from generate_series(1,3);
sum
-----
(1 row)
select avg(null::int4) from generate_series(1,3);
avg
-----
(1 row)
select avg(null::int8) from generate_series(1,3);
avg
-----
(1 row)
select avg(null::numeric) from generate_series(1,3);
avg
-----
(1 row)
select avg(null::float8) from generate_series(1,3);
avg
-----
(1 row)
select sum('NaN'::numeric) from generate_series(1,3);
sum
-----
NaN
(1 row)
select avg('NaN'::numeric) from generate_series(1,3);
avg
-----
NaN
(1 row)
-- SQL2003 binary aggregates
SELECT regr_count(b, a) FROM aggtest;
regr_count
......
src/test/regress/sql/aggregates.sql
View file @ 69c8fbac
......@@ -39,6 +39,18 @@ SELECT var_samp(b::numeric) FROM aggtest;
SELECT var_pop(1.0), var_samp(2.0);
SELECT stddev_pop(3.0::numeric), stddev_samp(4.0::numeric);
-- verify correct results for null and NaN inputs
select sum(null::int4) from generate_series(1,3);
select sum(null::int8) from generate_series(1,3);
select sum(null::numeric) from generate_series(1,3);
select sum(null::float8) from generate_series(1,3);
select avg(null::int4) from generate_series(1,3);
select avg(null::int8) from generate_series(1,3);
select avg(null::numeric) from generate_series(1,3);
select avg(null::float8) from generate_series(1,3);
select sum('NaN'::numeric) from generate_series(1,3);
select avg('NaN'::numeric) from generate_series(1,3);
-- SQL2003 binary aggregates
SELECT regr_count(b, a) FROM aggtest;
SELECT regr_sxx(b, a) FROM aggtest;
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment