Horton

v12-0001-Add-tests-for-group-by-optimization.patch

application/octet-stream

Download
Filename: v12-0001-Add-tests-for-group-by-optimization.patch
Type: application/octet-stream
Part: 0
Message: Re: POC: GROUP BY optimization

Patch

Same data as JSON: GET /api/v1/attachments/:id/patch the parsed metadata as JSON — format, series position, per-file stats; never the diff bytes. API reference →
Format: format-patch
Series: patch v12-0001
Subject: Add tests for group by optimization
File+−
src/test/regress/expected/aggregates.out 232 0
src/test/regress/sql/aggregates.sql 96 0 
From 35f3227677f715b0ec76b583c109e62d262d1f42 Mon Sep 17 00:00:00 2001
From: erthalion <9erthalion6@gmail.com>
Date: Tue, 2 Apr 2019 17:49:18 +0200
Subject: [PATCH v12 1/3] Add tests for group by optimization

---
 src/test/regress/expected/aggregates.out | 232 +++++++++++++++++++++++++++++++
 src/test/regress/sql/aggregates.sql      |  96 +++++++++++++
 2 files changed, 328 insertions(+)

diff --git a/src/test/regress/expected/aggregates.out b/src/test/regress/expected/aggregates.out
index 129c1e5075..a20c69469f 100644
--- a/src/test/regress/expected/aggregates.out
+++ b/src/test/regress/expected/aggregates.out
@@ -2195,6 +2195,238 @@ SELECT balk(hundred) FROM tenk1;
 (1 row)
 
 ROLLBACK;
+-- GROUP BY optimization by reorder columns
+SELECT
+	i AS id,
+	i/2 AS p,
+	format('%60s', i%2) AS v,
+	i/4 AS c,
+	i/8 AS d,
+	(random() * (10000/8))::int as e --the same as d but no correlation with p
+	INTO btg
+FROM
+	generate_series(1, 10000) i;
+VACUUM btg;
+ANALYZE btg;
+-- GROUP BY optimization by reorder columns by frequency
+SET enable_hashagg=off;
+SET max_parallel_workers= 0;
+SET max_parallel_workers_per_gather = 0;
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, v;
+         QUERY PLAN          
+-----------------------------
+ GroupAggregate
+   Group Key: p, v
+   ->  Sort
+         Sort Key: p, v
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p;
+         QUERY PLAN          
+-----------------------------
+ GroupAggregate
+   Group Key: v, p
+   ->  Sort
+         Sort Key: v, p
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, c;
+         QUERY PLAN          
+-----------------------------
+ GroupAggregate
+   Group Key: v, p, c
+   ->  Sort
+         Sort Key: v, p, c
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, c ORDER BY v, p, c;
+         QUERY PLAN          
+-----------------------------
+ GroupAggregate
+   Group Key: v, p, c
+   ->  Sort
+         Sort Key: v, p, c
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, d, c;
+          QUERY PLAN          
+------------------------------
+ GroupAggregate
+   Group Key: v, p, d, c
+   ->  Sort
+         Sort Key: v, p, d, c
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, d, c ORDER BY v, p, d ,c;
+          QUERY PLAN          
+------------------------------
+ GroupAggregate
+   Group Key: v, p, d, c
+   ->  Sort
+         Sort Key: v, p, d, c
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, d, c ORDER BY p, v, d ,c;
+          QUERY PLAN          
+------------------------------
+ GroupAggregate
+   Group Key: p, v, d, c
+   ->  Sort
+         Sort Key: p, v, d, c
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, d, e;
+         QUERY PLAN          
+-----------------------------
+ GroupAggregate
+   Group Key: p, d, e
+   ->  Sort
+         Sort Key: p, d, e
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, e, d;
+         QUERY PLAN          
+-----------------------------
+ GroupAggregate
+   Group Key: p, e, d
+   ->  Sort
+         Sort Key: p, e, d
+         ->  Seq Scan on btg
+(5 rows)
+
+CREATE STATISTICS btg_dep ON d, e, p FROM btg;
+ANALYZE btg;
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, d, e;
+         QUERY PLAN          
+-----------------------------
+ GroupAggregate
+   Group Key: p, d, e
+   ->  Sort
+         Sort Key: p, d, e
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, e, d;
+         QUERY PLAN          
+-----------------------------
+ GroupAggregate
+   Group Key: p, e, d
+   ->  Sort
+         Sort Key: p, e, d
+         ->  Seq Scan on btg
+(5 rows)
+
+-- GROUP BY optimization by reorder columns by index scan
+CREATE INDEX ON btg(p, v);
+SET enable_seqscan=off;
+SET enable_bitmapscan=off;
+VACUUM btg;
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, v;
+                   QUERY PLAN                   
+------------------------------------------------
+ GroupAggregate
+   Group Key: p, v
+   ->  Index Only Scan using btg_p_v_idx on btg
+(3 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, v ORDER BY p, v;
+                   QUERY PLAN                   
+------------------------------------------------
+ GroupAggregate
+   Group Key: p, v
+   ->  Index Only Scan using btg_p_v_idx on btg
+(3 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p;
+                      QUERY PLAN                      
+------------------------------------------------------
+ GroupAggregate
+   Group Key: v, p
+   ->  Sort
+         Sort Key: v, p
+         ->  Index Only Scan using btg_p_v_idx on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p ORDER BY p, v;
+                   QUERY PLAN                   
+------------------------------------------------
+ GroupAggregate
+   Group Key: p, v
+   ->  Index Only Scan using btg_p_v_idx on btg
+(3 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, c;
+         QUERY PLAN          
+-----------------------------
+ GroupAggregate
+   Group Key: v, p, c
+   ->  Sort
+         Sort Key: v, p, c
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, c ORDER BY p, v;
+         QUERY PLAN          
+-----------------------------
+ GroupAggregate
+   Group Key: p, v, c
+   ->  Sort
+         Sort Key: p, v, c
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, c, p, d;
+          QUERY PLAN          
+------------------------------
+ GroupAggregate
+   Group Key: v, c, p, d
+   ->  Sort
+         Sort Key: v, c, p, d
+         ->  Seq Scan on btg
+(5 rows)
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, c, p, d ORDER BY p, v;
+          QUERY PLAN          
+------------------------------
+ GroupAggregate
+   Group Key: p, v, c, d
+   ->  Sort
+         Sort Key: p, v, c, d
+         ->  Seq Scan on btg
+(5 rows)
+
+RESET enable_hashagg;
+RESET max_parallel_workers;
+RESET max_parallel_workers_per_gather;
+RESET enable_seqscan;
+RESET enable_bitmapscan;
 -- test coverage for aggregate combine/serial/deserial functions
 BEGIN ISOLATION LEVEL REPEATABLE READ;
 SET parallel_setup_cost = 0;
diff --git a/src/test/regress/sql/aggregates.sql b/src/test/regress/sql/aggregates.sql
index d4fd657188..ad73254f88 100644
--- a/src/test/regress/sql/aggregates.sql
+++ b/src/test/regress/sql/aggregates.sql
@@ -952,6 +952,102 @@ SELECT balk(hundred) FROM tenk1;
 
 ROLLBACK;
 
+-- GROUP BY optimization by reorder columns
+
+SELECT
+	i AS id,
+	i/2 AS p,
+	format('%60s', i%2) AS v,
+	i/4 AS c,
+	i/8 AS d,
+	(random() * (10000/8))::int as e --the same as d but no correlation with p
+	INTO btg
+FROM
+	generate_series(1, 10000) i;
+
+VACUUM btg;
+ANALYZE btg;
+
+-- GROUP BY optimization by reorder columns by frequency
+
+SET enable_hashagg=off;
+SET max_parallel_workers= 0;
+SET max_parallel_workers_per_gather = 0;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, v;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, c;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, c ORDER BY v, p, c;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, d, c;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, d, c ORDER BY v, p, d ,c;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, d, c ORDER BY p, v, d ,c;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, d, e;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, e, d;
+
+CREATE STATISTICS btg_dep ON d, e, p FROM btg;
+ANALYZE btg;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, d, e;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, e, d;
+
+
+-- GROUP BY optimization by reorder columns by index scan
+
+CREATE INDEX ON btg(p, v);
+SET enable_seqscan=off;
+SET enable_bitmapscan=off;
+VACUUM btg;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, v;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY p, v ORDER BY p, v;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p ORDER BY p, v;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, c;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, p, c ORDER BY p, v;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, c, p, d;
+
+EXPLAIN (COSTS off)
+SELECT count(*) FROM btg GROUP BY v, c, p, d ORDER BY p, v;
+
+RESET enable_hashagg;
+RESET max_parallel_workers;
+RESET max_parallel_workers_per_gather;
+RESET enable_seqscan;
+RESET enable_bitmapscan;
+
 -- test coverage for aggregate combine/serial/deserial functions
 BEGIN ISOLATION LEVEL REPEATABLE READ;
 
-- 
2.16.4