From efe7d48a2944660a90975936d12596e6d7dbbc58 Mon Sep 17 00:00:00 2001 From: Thomas Munro Date: Wed, 6 Dec 2017 09:59:48 +1300 Subject: [PATCH] Add a regression test for parallel hash join rescans. *FOR DEMONSTRATION ONLY, NOT FOR COMMIT YET* --- src/test/regress/expected/join.out | 106 +++++++++++++++++++++++++++++++++++++ src/test/regress/sql/join.sql | 60 +++++++++++++++++++++ 2 files changed, 166 insertions(+) diff --git a/src/test/regress/expected/join.out b/src/test/regress/expected/join.out index 001d96dc2d8..9d3abf0ed05 100644 --- a/src/test/regress/expected/join.out +++ b/src/test/regress/expected/join.out @@ -6187,6 +6187,112 @@ $$); 1 | 1 (1 row) +rollback to settings; +-- Exercise rescans. We'll turn off parallel_leader_participation so +-- that we can check that instrumentation comes back correctly. +create table foo as select generate_series(1, 3) as id, 'xxxxx'::text as t; +alter table foo set (parallel_workers = 0); +create table bar as select generate_series(1, 5000) as id, 'xxxxx'::text as t; +alter table bar set (parallel_workers = 2); +-- multi-batch with rescan, parallel-oblivious +savepoint settings; +set parallel_leader_participation = off; +set min_parallel_table_scan_size = 0; +set parallel_setup_cost = 0; +set parallel_tuple_cost = 0; +set max_parallel_workers_per_gather = 2; +set enable_material = off; +set enable_mergejoin = off; +set work_mem = '64kB'; +explain (costs off) + select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; + QUERY PLAN +-------------------------------------------------------------------------- + Aggregate + -> Nested Loop Left Join + Join Filter: ((foo.id < (b1.id + 1)) AND (foo.id > (b1.id - 1))) + -> Seq Scan on foo + -> Gather + Workers Planned: 2 + -> Hash Join + Hash Cond: (b1.id = b2.id) + -> Parallel Seq Scan on bar b1 + -> Hash + -> Seq Scan on bar b2 +(11 rows) + +select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; + count +------- + 3 +(1 row) + +select final > 1 as multibatch + from hash_join_batches( +$$ + select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; +$$); + multibatch +------------ + t +(1 row) + +rollback to settings; +-- single-batch with rescan, parallel-oblivious +savepoint settings; +set parallel_leader_participation = off; +set min_parallel_table_scan_size = 0; +set parallel_setup_cost = 0; +set parallel_tuple_cost = 0; +set max_parallel_workers_per_gather = 2; +set enable_material = off; +set enable_mergejoin = off; +set work_mem = '4MB'; +explain (costs off) + select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; + QUERY PLAN +-------------------------------------------------------------------------- + Aggregate + -> Nested Loop Left Join + Join Filter: ((foo.id < (b1.id + 1)) AND (foo.id > (b1.id - 1))) + -> Seq Scan on foo + -> Gather + Workers Planned: 2 + -> Hash Join + Hash Cond: (b1.id = b2.id) + -> Parallel Seq Scan on bar b1 + -> Hash + -> Seq Scan on bar b2 +(11 rows) + +select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; + count +------- + 3 +(1 row) + +select final > 1 as multibatch + from hash_join_batches( +$$ + select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; +$$); + multibatch +------------ + f +(1 row) + rollback to settings; -- A full outer join where every record is matched. -- non-parallel diff --git a/src/test/regress/sql/join.sql b/src/test/regress/sql/join.sql index 882601b3388..0e933e00d54 100644 --- a/src/test/regress/sql/join.sql +++ b/src/test/regress/sql/join.sql @@ -2170,6 +2170,66 @@ $$ $$); rollback to settings; +-- Exercise rescans. We'll turn off parallel_leader_participation so +-- that we can check that instrumentation comes back correctly. + +create table foo as select generate_series(1, 3) as id, 'xxxxx'::text as t; +alter table foo set (parallel_workers = 0); +create table bar as select generate_series(1, 5000) as id, 'xxxxx'::text as t; +alter table bar set (parallel_workers = 2); + +-- multi-batch with rescan, parallel-oblivious +savepoint settings; +set parallel_leader_participation = off; +set min_parallel_table_scan_size = 0; +set parallel_setup_cost = 0; +set parallel_tuple_cost = 0; +set max_parallel_workers_per_gather = 2; +set enable_material = off; +set enable_mergejoin = off; +set work_mem = '64kB'; +explain (costs off) + select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; +select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; +select final > 1 as multibatch + from hash_join_batches( +$$ + select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; +$$); +rollback to settings; + +-- single-batch with rescan, parallel-oblivious +savepoint settings; +set parallel_leader_participation = off; +set min_parallel_table_scan_size = 0; +set parallel_setup_cost = 0; +set parallel_tuple_cost = 0; +set max_parallel_workers_per_gather = 2; +set enable_material = off; +set enable_mergejoin = off; +set work_mem = '4MB'; +explain (costs off) + select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; +select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; +select final > 1 as multibatch + from hash_join_batches( +$$ + select count(*) from foo + left join (select b1.id, b1.t from bar b1 join bar b2 using (id)) ss + on foo.id < ss.id + 1 and foo.id > ss.id - 1; +$$); +rollback to settings; + -- A full outer join where every record is matched. -- non-parallel -- 2.15.0