From f2c7871c6de5e27be0f484c119855ca22ba149d1 Mon Sep 17 00:00:00 2001 From: Tomas Vondra Date: Mon, 27 Jul 2026 19:08:39 +0200 Subject: [PATCH v8 19/20] Test a starjoin with multi-column FK join clauses --- .../regress/expected/hashjoin_bloom_star.out | 343 +++++++++++++++++- src/test/regress/sql/hashjoin_bloom_star.sql | 135 ++++++- 2 files changed, 476 insertions(+), 2 deletions(-) diff --git a/src/test/regress/expected/hashjoin_bloom_star.out b/src/test/regress/expected/hashjoin_bloom_star.out index 7e6a60d3266..94635408206 100644 --- a/src/test/regress/expected/hashjoin_bloom_star.out +++ b/src/test/regress/expected/hashjoin_bloom_star.out @@ -397,7 +397,6 @@ WHERE d1.r < 0.3 AND d2.r < 0.35 AND d3.r < 0.4 AND d4.r < 0.45 AND d5.r < 0.5 A (50 rows) RESET bloom_filter_pushdown_max; -RESET join_collapse_limit; DROP TABLE bloom_star_dim_1; DROP TABLE bloom_star_dim_2; DROP TABLE bloom_star_dim_3; @@ -406,3 +405,345 @@ DROP TABLE bloom_star_dim_5; DROP TABLE bloom_star_dim_6; DROP TABLE bloom_star_dim_7; DROP TABLE bloom_star_fact; +-- schema with multi-column FK joins +CREATE TABLE bloom_star_multi_dim_1 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_2 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_3 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_4 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_5 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_6 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_7 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_fact ( + id1a int, id1b int, + id2a int, id2b int, + id3a int, id3b int, + id4a int, id4b int, + id5a int, id5b int, + id6a int, id6b int, + id7a int, id7b int, + FOREIGN KEY (id1a, id1b) REFERENCES bloom_star_multi_dim_1 (a, b), + FOREIGN KEY (id2a, id2b) REFERENCES bloom_star_multi_dim_2 (a, b), + FOREIGN KEY (id3a, id3b) REFERENCES bloom_star_multi_dim_3 (a, b), + FOREIGN KEY (id4a, id4b) REFERENCES bloom_star_multi_dim_4 (a, b), + FOREIGN KEY (id5a, id5b) REFERENCES bloom_star_multi_dim_5 (a, b), + FOREIGN KEY (id6a, id6b) REFERENCES bloom_star_multi_dim_6 (a, b), + FOREIGN KEY (id7a, id7b) REFERENCES bloom_star_multi_dim_7 (a, b), + padding text); +SELECT setseed(1); + setseed +--------- + +(1 row) + +INSERT INTO bloom_star_multi_dim_1 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_2 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_3 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_4 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_5 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_6 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_7 SELECT i, i, random() FROM generate_series(1,1000) s(i); +WITH d AS ( + SELECT + 1 + mod((100000 * random())::int, 1000) AS id1, + 1 + mod((100000 * random())::int, 1000) AS id2, + 1 + mod((100000 * random())::int, 1000) AS id3, + 1 + mod((100000 * random())::int, 1000) AS id4, + 1 + mod((100000 * random())::int, 1000) AS id5, + 1 + mod((100000 * random())::int, 1000) AS id6, + 1 + mod((100000 * random())::int, 1000) AS id7, + md5(i::text) AS p + FROM generate_series(1,100000) s(i) +) +INSERT INTO bloom_star_multi_fact +SELECT + id1, id1, + id2, id2, + id3, id3, + id4, id4, + id5, id5, + id6, id6, + id7, id7, + p +FROM d; +SET default_statistics_target = 1000; +VACUUM ANALYZE; +-- first join is 50% selective (good enough for a filter push down) +-- the join will be executed done last +EXPLAIN (ANALYZE, TIMING OFF, SUMMARY OFF, BUFFERS OFF) +SELECT * +FROM bloom_star_multi_fact f +JOIN bloom_star_multi_dim_1 d1 ON (f.id1a = d1.a AND f.id1b = d1.b) +JOIN bloom_star_multi_dim_2 d2 ON (f.id2a = d2.a AND f.id2b = d2.b) +JOIN bloom_star_multi_dim_3 d3 ON (f.id3a = d3.a AND f.id3b = d3.b) +JOIN bloom_star_multi_dim_4 d4 ON (f.id4a = d4.a AND f.id4b = d4.b) +JOIN bloom_star_multi_dim_5 d5 ON (f.id5a = d5.a AND f.id5b = d5.b) +JOIN bloom_star_multi_dim_6 d6 ON (f.id6a = d6.a AND f.id6b = d6.b) +JOIN bloom_star_multi_dim_7 d7 ON (f.id7a = d7.a AND f.id7b = d7.b) +WHERE d1.r < 0.5; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------------------------------------------------- + Hash Join (cost=211.53..4474.11 rows=46900 width=173) (actual rows=46848.00 loops=1) + Hash Cond: ((f.id7a = d7.a) AND (f.id7b = d7.b)) + -> Hash Join (cost=180.53..4196.88 rows=46900 width=161) (actual rows=46848.00 loops=1) + Hash Cond: ((f.id6a = d6.a) AND (f.id6b = d6.b)) + -> Hash Join (cost=149.53..3919.66 rows=46900 width=149) (actual rows=46848.00 loops=1) + Hash Cond: ((f.id5a = d5.a) AND (f.id5b = d5.b)) + -> Hash Join (cost=118.53..3642.43 rows=46900 width=137) (actual rows=46848.00 loops=1) + Hash Cond: ((f.id4a = d4.a) AND (f.id4b = d4.b)) + -> Hash Join (cost=87.53..3365.21 rows=46900 width=125) (actual rows=46848.00 loops=1) + Hash Cond: ((f.id3a = d3.a) AND (f.id3b = d3.b)) + -> Hash Join (cost=56.53..3087.98 rows=46900 width=113) (actual rows=46848.00 loops=1) + Hash Cond: ((f.id2a = d2.a) AND (f.id2b = d2.b)) + -> Hash Join (cost=25.54..2810.76 rows=46900 width=101) (actual rows=46848.00 loops=1) + Hash Cond: ((f.id1a = d1.a) AND (f.id1b = d1.b)) + -> Seq Scan on bloom_star_multi_fact f (cost=0.00..2539.00 rows=46900 width=89) (actual rows=46848.00 loops=1) + Bloom Filter 1: keys=(id1a, id1b) expected=46.9% checked=99999 rejected=53152 (53.2%) + -> Hash (cost=18.50..18.50 rows=469 width=12) (actual rows=470.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 29kB + Bloom Filter 1: bits=8388608 hashes=10 memory=1024kB checked=99999 rejected=53152 + -> Seq Scan on bloom_star_multi_dim_1 d1 (cost=0.00..18.50 rows=469 width=12) (actual rows=470.00 loops=1) + Filter: (r < '0.5'::double precision) + Rows Removed by Filter: 530 + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_2 d2 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_3 d3 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_4 d4 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_5 d5 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_6 d6 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_7 d7 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) +(40 rows) + +-- two joins 50% selective +EXPLAIN (ANALYZE, TIMING OFF, SUMMARY OFF, BUFFERS OFF) +SELECT * +FROM bloom_star_multi_fact f +JOIN bloom_star_multi_dim_1 d1 ON (f.id1a = d1.a AND f.id1b = d1.b) +JOIN bloom_star_multi_dim_2 d2 ON (f.id2a = d2.a AND f.id2b = d2.b) +JOIN bloom_star_multi_dim_3 d3 ON (f.id3a = d3.a AND f.id3b = d3.b) +JOIN bloom_star_multi_dim_4 d4 ON (f.id4a = d4.a AND f.id4b = d4.b) +JOIN bloom_star_multi_dim_5 d5 ON (f.id5a = d5.a AND f.id5b = d5.b) +JOIN bloom_star_multi_dim_6 d6 ON (f.id6a = d6.a AND f.id6b = d6.b) +JOIN bloom_star_multi_dim_7 d7 ON (f.id7a = d7.a AND f.id7b = d7.b) +WHERE d1.r < 0.4 AND d7.r < 0.5; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------------------------------------------------- + Hash Join (cost=204.78..3401.16 rows=17888 width=173) (actual rows=17864.00 loops=1) + Hash Cond: ((f.id7a = d7.a) AND (f.id7b = d7.b)) + -> Hash Join (cost=179.12..3281.60 rows=17888 width=161) (actual rows=17864.00 loops=1) + Hash Cond: ((f.id6a = d6.a) AND (f.id6b = d6.b)) + -> Hash Join (cost=148.12..3156.69 rows=17888 width=149) (actual rows=17864.00 loops=1) + Hash Cond: ((f.id5a = d5.a) AND (f.id5b = d5.b)) + -> Hash Join (cost=117.12..3031.77 rows=17888 width=137) (actual rows=17864.00 loops=1) + Hash Cond: ((f.id4a = d4.a) AND (f.id4b = d4.b)) + -> Hash Join (cost=86.12..2906.86 rows=17888 width=125) (actual rows=17864.00 loops=1) + Hash Cond: ((f.id3a = d3.a) AND (f.id3b = d3.b)) + -> Hash Join (cost=55.12..2781.95 rows=17888 width=113) (actual rows=17864.00 loops=1) + Hash Cond: ((f.id2a = d2.a) AND (f.id2b = d2.b)) + -> Hash Join (cost=24.12..2657.04 rows=17888 width=101) (actual rows=17864.00 loops=1) + Hash Cond: ((f.id1a = d1.a) AND (f.id1b = d1.b)) + -> Seq Scan on bloom_star_multi_fact f (cost=0.00..2539.00 rows=17888 width=89) (actual rows=17864.00 loops=1) + Bloom Filter 1: keys=(id1a, id1b) expected=37.5% checked=99999 rejected=62610 (62.6%) + Bloom Filter 2: keys=(id7a, id7b) expected=47.7% checked=37390 rejected=19526 (52.2%) + -> Hash (cost=18.50..18.50 rows=375 width=12) (actual rows=376.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 25kB + Bloom Filter 1: bits=8388608 hashes=10 memory=1024kB checked=99999 rejected=62610 + -> Seq Scan on bloom_star_multi_dim_1 d1 (cost=0.00..18.50 rows=375 width=12) (actual rows=376.00 loops=1) + Filter: (r < '0.4'::double precision) + Rows Removed by Filter: 624 + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_2 d2 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_3 d3 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_4 d4 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_5 d5 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + -> Hash (cost=16.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 51kB + -> Seq Scan on bloom_star_multi_dim_6 d6 (cost=0.00..16.00 rows=1000 width=12) (actual rows=1000.00 loops=1) + -> Hash (cost=18.50..18.50 rows=477 width=12) (actual rows=478.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 29kB + Bloom Filter 2: bits=8388608 hashes=10 memory=1024kB checked=37390 rejected=19526 + -> Seq Scan on bloom_star_multi_dim_7 d7 (cost=0.00..18.50 rows=477 width=12) (actual rows=478.00 loops=1) + Filter: (r < '0.5'::double precision) + Rows Removed by Filter: 522 +(44 rows) + +-- all joins selective for a filter (more than how many we allow) +EXPLAIN (ANALYZE, TIMING OFF, SUMMARY OFF, BUFFERS OFF) +SELECT * +FROM bloom_star_multi_fact f +JOIN bloom_star_multi_dim_1 d1 ON (f.id1a = d1.a AND f.id1b = d1.b) +JOIN bloom_star_multi_dim_2 d2 ON (f.id2a = d2.a AND f.id2b = d2.b) +JOIN bloom_star_multi_dim_3 d3 ON (f.id3a = d3.a AND f.id3b = d3.b) +JOIN bloom_star_multi_dim_4 d4 ON (f.id4a = d4.a AND f.id4b = d4.b) +JOIN bloom_star_multi_dim_5 d5 ON (f.id5a = d5.a AND f.id5b = d5.b) +JOIN bloom_star_multi_dim_6 d6 ON (f.id6a = d6.a AND f.id6b = d6.b) +JOIN bloom_star_multi_dim_7 d7 ON (f.id7a = d7.a AND f.id7b = d7.b) +WHERE d1.r < 0.3 AND d2.r < 0.35 AND d3.r < 0.4 AND d4.r < 0.45 AND d5.r < 0.5 AND d6.r < 0.55 AND d7.r < 0.6; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------------------------------------------------- + Hash Join (cost=176.01..2816.72 rows=283 width=173) (actual rows=292.00 loops=1) + Hash Cond: ((f.id7a = d7.a) AND (f.id7b = d7.b)) + -> Hash Join (cost=149.07..2787.14 rows=503 width=161) (actual rows=526.00 loops=1) + Hash Cond: ((f.id6a = d6.a) AND (f.id6b = d6.b)) + -> Hash Join (cost=122.51..2755.67 rows=936 width=149) (actual rows=923.00 loops=1) + Hash Cond: ((f.id5a = d5.a) AND (f.id5b = d5.b)) + -> Hash Join (cost=96.24..2719.92 rows=1806 width=137) (actual rows=1774.00 loops=1) + Hash Cond: ((f.id4a = d4.a) AND (f.id4b = d4.b)) + -> Hash Join (cost=71.02..2673.53 rows=4032 width=125) (actual rows=3997.00 loops=1) + Hash Cond: ((f.id3a = d3.a) AND (f.id3b = d3.b)) + -> Hash Join (cost=46.69..2628.03 rows=4032 width=113) (actual rows=3997.00 loops=1) + Hash Cond: ((f.id2a = d2.a) AND (f.id2b = d2.b)) + -> Hash Join (cost=22.95..2583.12 rows=4032 width=101) (actual rows=3997.00 loops=1) + Hash Cond: ((f.id1a = d1.a) AND (f.id1b = d1.b)) + -> Seq Scan on bloom_star_multi_fact f (cost=0.00..2539.00 rows=4032 width=89) (actual rows=3997.00 loops=1) + Bloom Filter 1: keys=(id1a, id1b) expected=29.7% checked=99991 rejected=70413 (70.4%) + Bloom Filter 2: keys=(id2a, id2b) expected=34.9% checked=29587 rejected=19399 (65.6%) + Bloom Filter 3: keys=(id3a, id3b) expected=38.9% checked=10188 rejected=6191 (60.8%) + -> Hash (cost=18.50..18.50 rows=297 width=12) (actual rows=298.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 21kB + Bloom Filter 1: bits=8388608 hashes=10 memory=1024kB checked=99991 rejected=70413 + -> Seq Scan on bloom_star_multi_dim_1 d1 (cost=0.00..18.50 rows=297 width=12) (actual rows=298.00 loops=1) + Filter: (r < '0.3'::double precision) + Rows Removed by Filter: 702 + -> Hash (cost=18.50..18.50 rows=349 width=12) (actual rows=350.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 24kB + Bloom Filter 2: bits=8388608 hashes=10 memory=1024kB checked=29587 rejected=19399 + -> Seq Scan on bloom_star_multi_dim_2 d2 (cost=0.00..18.50 rows=349 width=12) (actual rows=350.00 loops=1) + Filter: (r < '0.35'::double precision) + Rows Removed by Filter: 650 + -> Hash (cost=18.50..18.50 rows=389 width=12) (actual rows=391.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 25kB + Bloom Filter 3: bits=8388608 hashes=10 memory=1024kB checked=10188 rejected=6191 + -> Seq Scan on bloom_star_multi_dim_3 d3 (cost=0.00..18.50 rows=389 width=12) (actual rows=391.00 loops=1) + Filter: (r < '0.4'::double precision) + Rows Removed by Filter: 609 + -> Hash (cost=18.50..18.50 rows=448 width=12) (actual rows=449.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 28kB + -> Seq Scan on bloom_star_multi_dim_4 d4 (cost=0.00..18.50 rows=448 width=12) (actual rows=449.00 loops=1) + Filter: (r < '0.45'::double precision) + Rows Removed by Filter: 551 + -> Hash (cost=18.50..18.50 rows=518 width=12) (actual rows=519.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 31kB + -> Seq Scan on bloom_star_multi_dim_5 d5 (cost=0.00..18.50 rows=518 width=12) (actual rows=519.00 loops=1) + Filter: (r < '0.5'::double precision) + Rows Removed by Filter: 481 + -> Hash (cost=18.50..18.50 rows=537 width=12) (actual rows=538.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 32kB + -> Seq Scan on bloom_star_multi_dim_6 d6 (cost=0.00..18.50 rows=537 width=12) (actual rows=538.00 loops=1) + Filter: (r < '0.55'::double precision) + Rows Removed by Filter: 462 + -> Hash (cost=18.50..18.50 rows=563 width=12) (actual rows=564.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 33kB + -> Seq Scan on bloom_star_multi_dim_7 d7 (cost=0.00..18.50 rows=563 width=12) (actual rows=564.00 loops=1) + Filter: (r < '0.6'::double precision) + Rows Removed by Filter: 436 +(56 rows) + +SET bloom_filter_pushdown_max = 10; +-- all joins selective for a filter +EXPLAIN (ANALYZE, TIMING OFF, SUMMARY OFF, BUFFERS OFF) +SELECT * +FROM bloom_star_multi_fact f +JOIN bloom_star_multi_dim_1 d1 ON (f.id1a = d1.a AND f.id1b = d1.b) +JOIN bloom_star_multi_dim_2 d2 ON (f.id2a = d2.a AND f.id2b = d2.b) +JOIN bloom_star_multi_dim_3 d3 ON (f.id3a = d3.a AND f.id3b = d3.b) +JOIN bloom_star_multi_dim_4 d4 ON (f.id4a = d4.a AND f.id4b = d4.b) +JOIN bloom_star_multi_dim_5 d5 ON (f.id5a = d5.a AND f.id5b = d5.b) +JOIN bloom_star_multi_dim_6 d6 ON (f.id6a = d6.a AND f.id6b = d6.b) +JOIN bloom_star_multi_dim_7 d7 ON (f.id7a = d7.a AND f.id7b = d7.b) +WHERE d1.r < 0.3 AND d2.r < 0.35 AND d3.r < 0.4 AND d4.r < 0.45 AND d5.r < 0.5 AND d6.r < 0.55 AND d7.r < 0.6; + QUERY PLAN +---------------------------------------------------------------------------------------------------------------------------------------------------------- + Hash Join (cost=176.01..2725.42 rows=283 width=173) (actual rows=292.00 loops=1) + Hash Cond: ((f.id7a = d7.a) AND (f.id7b = d7.b)) + -> Hash Join (cost=149.07..2696.98 rows=283 width=161) (actual rows=292.00 loops=1) + Hash Cond: ((f.id6a = d6.a) AND (f.id6b = d6.b)) + -> Hash Join (cost=122.51..2668.94 rows=283 width=149) (actual rows=292.00 loops=1) + Hash Cond: ((f.id5a = d5.a) AND (f.id5b = d5.b)) + -> Hash Join (cost=96.24..2641.19 rows=283 width=137) (actual rows=292.00 loops=1) + Hash Cond: ((f.id4a = d4.a) AND (f.id4b = d4.b)) + -> Hash Join (cost=71.02..2614.48 rows=283 width=125) (actual rows=292.00 loops=1) + Hash Cond: ((f.id3a = d3.a) AND (f.id3b = d3.b)) + -> Hash Join (cost=46.69..2588.66 rows=283 width=113) (actual rows=292.00 loops=1) + Hash Cond: ((f.id2a = d2.a) AND (f.id2b = d2.b)) + -> Hash Join (cost=22.95..2563.44 rows=283 width=101) (actual rows=292.00 loops=1) + Hash Cond: ((f.id1a = d1.a) AND (f.id1b = d1.b)) + -> Seq Scan on bloom_star_multi_fact f (cost=0.00..2539.00 rows=283 width=89) (actual rows=292.00 loops=1) + Bloom Filter 1: keys=(id1a, id1b) expected=29.7% checked=99991 rejected=70413 (70.4%) + Bloom Filter 2: keys=(id2a, id2b) expected=34.9% checked=29587 rejected=19399 (65.6%) + Bloom Filter 3: keys=(id3a, id3b) expected=38.9% checked=10188 rejected=6191 (60.8%) + Bloom Filter 4: keys=(id4a, id4b) expected=44.8% checked=3997 rejected=2223 (55.6%) + Bloom Filter 5: keys=(id5a, id5b) expected=51.8% checked=1774 rejected=851 (48.0%) + Bloom Filter 6: keys=(id6a, id6b) expected=53.7% checked=923 rejected=397 (43.0%) + Bloom Filter 7: keys=(id7a, id7b) expected=56.3% checked=526 rejected=234 (44.5%) + -> Hash (cost=18.50..18.50 rows=297 width=12) (actual rows=298.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 21kB + Bloom Filter 1: bits=8388608 hashes=10 memory=1024kB checked=99991 rejected=70413 + -> Seq Scan on bloom_star_multi_dim_1 d1 (cost=0.00..18.50 rows=297 width=12) (actual rows=298.00 loops=1) + Filter: (r < '0.3'::double precision) + Rows Removed by Filter: 702 + -> Hash (cost=18.50..18.50 rows=349 width=12) (actual rows=350.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 24kB + Bloom Filter 2: bits=8388608 hashes=10 memory=1024kB checked=29587 rejected=19399 + -> Seq Scan on bloom_star_multi_dim_2 d2 (cost=0.00..18.50 rows=349 width=12) (actual rows=350.00 loops=1) + Filter: (r < '0.35'::double precision) + Rows Removed by Filter: 650 + -> Hash (cost=18.50..18.50 rows=389 width=12) (actual rows=391.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 25kB + Bloom Filter 3: bits=8388608 hashes=10 memory=1024kB checked=10188 rejected=6191 + -> Seq Scan on bloom_star_multi_dim_3 d3 (cost=0.00..18.50 rows=389 width=12) (actual rows=391.00 loops=1) + Filter: (r < '0.4'::double precision) + Rows Removed by Filter: 609 + -> Hash (cost=18.50..18.50 rows=448 width=12) (actual rows=449.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 28kB + Bloom Filter 4: bits=8388608 hashes=10 memory=1024kB checked=3997 rejected=2223 + -> Seq Scan on bloom_star_multi_dim_4 d4 (cost=0.00..18.50 rows=448 width=12) (actual rows=449.00 loops=1) + Filter: (r < '0.45'::double precision) + Rows Removed by Filter: 551 + -> Hash (cost=18.50..18.50 rows=518 width=12) (actual rows=519.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 31kB + Bloom Filter 5: bits=8388608 hashes=10 memory=1024kB checked=1774 rejected=851 + -> Seq Scan on bloom_star_multi_dim_5 d5 (cost=0.00..18.50 rows=518 width=12) (actual rows=519.00 loops=1) + Filter: (r < '0.5'::double precision) + Rows Removed by Filter: 481 + -> Hash (cost=18.50..18.50 rows=537 width=12) (actual rows=538.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 32kB + Bloom Filter 6: bits=8388608 hashes=10 memory=1024kB checked=923 rejected=397 + -> Seq Scan on bloom_star_multi_dim_6 d6 (cost=0.00..18.50 rows=537 width=12) (actual rows=538.00 loops=1) + Filter: (r < '0.55'::double precision) + Rows Removed by Filter: 462 + -> Hash (cost=18.50..18.50 rows=563 width=12) (actual rows=564.00 loops=1) + Buckets: 1024 Batches: 1 Memory Usage: 33kB + Bloom Filter 7: bits=8388608 hashes=10 memory=1024kB checked=526 rejected=234 + -> Seq Scan on bloom_star_multi_dim_7 d7 (cost=0.00..18.50 rows=563 width=12) (actual rows=564.00 loops=1) + Filter: (r < '0.6'::double precision) + Rows Removed by Filter: 436 +(64 rows) + +RESET bloom_filter_pushdown_max; +RESET join_collapse_limit; +DROP TABLE bloom_star_multi_fact; +DROP TABLE bloom_star_multi_dim_1; +DROP TABLE bloom_star_multi_dim_2; +DROP TABLE bloom_star_multi_dim_3; +DROP TABLE bloom_star_multi_dim_4; +DROP TABLE bloom_star_multi_dim_5; +DROP TABLE bloom_star_multi_dim_6; +DROP TABLE bloom_star_multi_dim_7; diff --git a/src/test/regress/sql/hashjoin_bloom_star.sql b/src/test/regress/sql/hashjoin_bloom_star.sql index 7ee3069ccd6..07ed67ee90e 100644 --- a/src/test/regress/sql/hashjoin_bloom_star.sql +++ b/src/test/regress/sql/hashjoin_bloom_star.sql @@ -135,7 +135,6 @@ JOIN bloom_star_dim_7 d7 ON (f.id7 = d7.id) WHERE d1.r < 0.3 AND d2.r < 0.35 AND d3.r < 0.4 AND d4.r < 0.45 AND d5.r < 0.5 AND d6.r < 0.55 AND d7.r < 0.6; RESET bloom_filter_pushdown_max; -RESET join_collapse_limit; DROP TABLE bloom_star_dim_1; DROP TABLE bloom_star_dim_2; @@ -145,3 +144,137 @@ DROP TABLE bloom_star_dim_5; DROP TABLE bloom_star_dim_6; DROP TABLE bloom_star_dim_7; DROP TABLE bloom_star_fact; + + +-- schema with multi-column FK joins + +CREATE TABLE bloom_star_multi_dim_1 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_2 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_3 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_4 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_5 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_6 (a int, b int, r real, primary key (a, b)); +CREATE TABLE bloom_star_multi_dim_7 (a int, b int, r real, primary key (a, b)); + +CREATE TABLE bloom_star_multi_fact ( + id1a int, id1b int, + id2a int, id2b int, + id3a int, id3b int, + id4a int, id4b int, + id5a int, id5b int, + id6a int, id6b int, + id7a int, id7b int, + FOREIGN KEY (id1a, id1b) REFERENCES bloom_star_multi_dim_1 (a, b), + FOREIGN KEY (id2a, id2b) REFERENCES bloom_star_multi_dim_2 (a, b), + FOREIGN KEY (id3a, id3b) REFERENCES bloom_star_multi_dim_3 (a, b), + FOREIGN KEY (id4a, id4b) REFERENCES bloom_star_multi_dim_4 (a, b), + FOREIGN KEY (id5a, id5b) REFERENCES bloom_star_multi_dim_5 (a, b), + FOREIGN KEY (id6a, id6b) REFERENCES bloom_star_multi_dim_6 (a, b), + FOREIGN KEY (id7a, id7b) REFERENCES bloom_star_multi_dim_7 (a, b), + padding text); + +SELECT setseed(1); + +INSERT INTO bloom_star_multi_dim_1 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_2 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_3 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_4 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_5 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_6 SELECT i, i, random() FROM generate_series(1,1000) s(i); +INSERT INTO bloom_star_multi_dim_7 SELECT i, i, random() FROM generate_series(1,1000) s(i); + +WITH d AS ( + SELECT + 1 + mod((100000 * random())::int, 1000) AS id1, + 1 + mod((100000 * random())::int, 1000) AS id2, + 1 + mod((100000 * random())::int, 1000) AS id3, + 1 + mod((100000 * random())::int, 1000) AS id4, + 1 + mod((100000 * random())::int, 1000) AS id5, + 1 + mod((100000 * random())::int, 1000) AS id6, + 1 + mod((100000 * random())::int, 1000) AS id7, + md5(i::text) AS p + FROM generate_series(1,100000) s(i) +) +INSERT INTO bloom_star_multi_fact +SELECT + id1, id1, + id2, id2, + id3, id3, + id4, id4, + id5, id5, + id6, id6, + id7, id7, + p +FROM d; + +SET default_statistics_target = 1000; + +VACUUM ANALYZE; + +-- first join is 50% selective (good enough for a filter push down) +-- the join will be executed done last +EXPLAIN (ANALYZE, TIMING OFF, SUMMARY OFF, BUFFERS OFF) +SELECT * +FROM bloom_star_multi_fact f +JOIN bloom_star_multi_dim_1 d1 ON (f.id1a = d1.a AND f.id1b = d1.b) +JOIN bloom_star_multi_dim_2 d2 ON (f.id2a = d2.a AND f.id2b = d2.b) +JOIN bloom_star_multi_dim_3 d3 ON (f.id3a = d3.a AND f.id3b = d3.b) +JOIN bloom_star_multi_dim_4 d4 ON (f.id4a = d4.a AND f.id4b = d4.b) +JOIN bloom_star_multi_dim_5 d5 ON (f.id5a = d5.a AND f.id5b = d5.b) +JOIN bloom_star_multi_dim_6 d6 ON (f.id6a = d6.a AND f.id6b = d6.b) +JOIN bloom_star_multi_dim_7 d7 ON (f.id7a = d7.a AND f.id7b = d7.b) +WHERE d1.r < 0.5; + +-- two joins 50% selective +EXPLAIN (ANALYZE, TIMING OFF, SUMMARY OFF, BUFFERS OFF) +SELECT * +FROM bloom_star_multi_fact f +JOIN bloom_star_multi_dim_1 d1 ON (f.id1a = d1.a AND f.id1b = d1.b) +JOIN bloom_star_multi_dim_2 d2 ON (f.id2a = d2.a AND f.id2b = d2.b) +JOIN bloom_star_multi_dim_3 d3 ON (f.id3a = d3.a AND f.id3b = d3.b) +JOIN bloom_star_multi_dim_4 d4 ON (f.id4a = d4.a AND f.id4b = d4.b) +JOIN bloom_star_multi_dim_5 d5 ON (f.id5a = d5.a AND f.id5b = d5.b) +JOIN bloom_star_multi_dim_6 d6 ON (f.id6a = d6.a AND f.id6b = d6.b) +JOIN bloom_star_multi_dim_7 d7 ON (f.id7a = d7.a AND f.id7b = d7.b) +WHERE d1.r < 0.4 AND d7.r < 0.5; + +-- all joins selective for a filter (more than how many we allow) +EXPLAIN (ANALYZE, TIMING OFF, SUMMARY OFF, BUFFERS OFF) +SELECT * +FROM bloom_star_multi_fact f +JOIN bloom_star_multi_dim_1 d1 ON (f.id1a = d1.a AND f.id1b = d1.b) +JOIN bloom_star_multi_dim_2 d2 ON (f.id2a = d2.a AND f.id2b = d2.b) +JOIN bloom_star_multi_dim_3 d3 ON (f.id3a = d3.a AND f.id3b = d3.b) +JOIN bloom_star_multi_dim_4 d4 ON (f.id4a = d4.a AND f.id4b = d4.b) +JOIN bloom_star_multi_dim_5 d5 ON (f.id5a = d5.a AND f.id5b = d5.b) +JOIN bloom_star_multi_dim_6 d6 ON (f.id6a = d6.a AND f.id6b = d6.b) +JOIN bloom_star_multi_dim_7 d7 ON (f.id7a = d7.a AND f.id7b = d7.b) +WHERE d1.r < 0.3 AND d2.r < 0.35 AND d3.r < 0.4 AND d4.r < 0.45 AND d5.r < 0.5 AND d6.r < 0.55 AND d7.r < 0.6; + + +SET bloom_filter_pushdown_max = 10; + +-- all joins selective for a filter +EXPLAIN (ANALYZE, TIMING OFF, SUMMARY OFF, BUFFERS OFF) +SELECT * +FROM bloom_star_multi_fact f +JOIN bloom_star_multi_dim_1 d1 ON (f.id1a = d1.a AND f.id1b = d1.b) +JOIN bloom_star_multi_dim_2 d2 ON (f.id2a = d2.a AND f.id2b = d2.b) +JOIN bloom_star_multi_dim_3 d3 ON (f.id3a = d3.a AND f.id3b = d3.b) +JOIN bloom_star_multi_dim_4 d4 ON (f.id4a = d4.a AND f.id4b = d4.b) +JOIN bloom_star_multi_dim_5 d5 ON (f.id5a = d5.a AND f.id5b = d5.b) +JOIN bloom_star_multi_dim_6 d6 ON (f.id6a = d6.a AND f.id6b = d6.b) +JOIN bloom_star_multi_dim_7 d7 ON (f.id7a = d7.a AND f.id7b = d7.b) +WHERE d1.r < 0.3 AND d2.r < 0.35 AND d3.r < 0.4 AND d4.r < 0.45 AND d5.r < 0.5 AND d6.r < 0.55 AND d7.r < 0.6; + +RESET bloom_filter_pushdown_max; +RESET join_collapse_limit; + +DROP TABLE bloom_star_multi_fact; +DROP TABLE bloom_star_multi_dim_1; +DROP TABLE bloom_star_multi_dim_2; +DROP TABLE bloom_star_multi_dim_3; +DROP TABLE bloom_star_multi_dim_4; +DROP TABLE bloom_star_multi_dim_5; +DROP TABLE bloom_star_multi_dim_6; +DROP TABLE bloom_star_multi_dim_7; -- 2.55.0