hcq/postgresql
1
0
Fork 0
mirror of https://git.postgresql.org/git/postgresql.git synced 2026-02-20 05:17:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Use multi-variate MCV lists to estimate ScalarArrayOpExpr

Browse Source 
Commit 8f321bd16c added support for estimating ScalarArrayOpExpr clauses
(IN/ANY) clauses using functional dependencies. There's no good reason
not to support estimation of these clauses using multi-variate MCV lists
too, so this commits implements that. That makes the behavior consistent
and MCV lists can estimate all variants (ANY/ALL, inequalities, ...).

Author: Tomas Vondra
Review: Dean Rasheed
Discussion: https://www.postgresql.org/message-id/flat/13902317.Eha0YfKkKy%40pierred-pdoc
This commit is contained in:
Tomas Vondra
2020-03-14 14:56:37 +01:00
parent 8f321bd16c
commit e83daa7e33
5 changed files with 252 additions and 9 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
src/test/regress/expected/stats_ext.out
View File

@ -827,6 +827,36 @@ SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = '
343 | 200
(1 row)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IN (1, 2, 51, 52) AND b IN ( ''1'', ''2'')');
estimated | actual
-----------+--------
8 | 200
(1 row)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = ANY (ARRAY[1, 2, 51, 52]) AND b = ANY (ARRAY[''1'', ''2''])');
estimated | actual
-----------+--------
8 | 200
(1 row)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= ANY (ARRAY[1, 2, 3]) AND b IN (''1'', ''2'', ''3'')');
estimated | actual
-----------+--------
26 | 150
(1 row)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND c > ANY (ARRAY[1, 2, 3])');
estimated | actual
-----------+--------
10 | 100
(1 row)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND b IN (''1'', ''2'', ''3'') AND c > ANY (ARRAY[1, 2, 3])');
estimated | actual
-----------+--------
1 | 100
(1 row)
-- create statistics
CREATE STATISTICS mcv_lists_stats (mcv) ON a, b, c FROM mcv_lists;
ANALYZE mcv_lists;
@ -872,6 +902,36 @@ SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = '
200 | 200
(1 row)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IN (1, 2, 51, 52) AND b IN ( ''1'', ''2'')');
estimated | actual
-----------+--------
200 | 200
(1 row)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = ANY (ARRAY[1, 2, 51, 52]) AND b = ANY (ARRAY[''1'', ''2''])');
estimated | actual
-----------+--------
200 | 200
(1 row)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= ANY (ARRAY[1, 2, 3]) AND b IN (''1'', ''2'', ''3'')');
estimated | actual
-----------+--------
150 | 150
(1 row)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND c > ANY (ARRAY[1, 2, 3])');
estimated | actual
-----------+--------
100 | 100
(1 row)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND b IN (''1'', ''2'', ''3'') AND c > ANY (ARRAY[1, 2, 3])');
estimated | actual
-----------+--------
100 | 100
(1 row)
-- we can't use the statistic for OR clauses that are not fully covered (missing 'd' attribute)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = ''1'' OR c = 1 OR d IS NOT NULL');
estimated | actual

20
src/test/regress/sql/stats_ext.sql
View File

@ -461,6 +461,16 @@ SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = '
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = ''1'' OR c = 1 OR d IS NOT NULL');
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IN (1, 2, 51, 52) AND b IN ( ''1'', ''2'')');
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = ANY (ARRAY[1, 2, 51, 52]) AND b = ANY (ARRAY[''1'', ''2''])');
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= ANY (ARRAY[1, 2, 3]) AND b IN (''1'', ''2'', ''3'')');
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND c > ANY (ARRAY[1, 2, 3])');
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND b IN (''1'', ''2'', ''3'') AND c > ANY (ARRAY[1, 2, 3])');
-- create statistics
CREATE STATISTICS mcv_lists_stats (mcv) ON a, b, c FROM mcv_lists;
@ -480,6 +490,16 @@ SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= 4 AND b <
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = ''1'' OR c = 1');
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a IN (1, 2, 51, 52) AND b IN ( ''1'', ''2'')');
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = ANY (ARRAY[1, 2, 51, 52]) AND b = ANY (ARRAY[''1'', ''2''])');
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a <= ANY (ARRAY[1, 2, 3]) AND b IN (''1'', ''2'', ''3'')');
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND c > ANY (ARRAY[1, 2, 3])');
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a < ALL (ARRAY[4, 5]) AND b IN (''1'', ''2'', ''3'') AND c > ANY (ARRAY[1, 2, 3])');
-- we can't use the statistic for OR clauses that are not fully covered (missing 'd' attribute)
SELECT * FROM check_estimated_rows('SELECT * FROM mcv_lists WHERE a = 1 OR b = ''1'' OR c = 1 OR d IS NOT NULL');