From a16ef313f2c21225e89ddb9168f30601f21c7d07 Mon Sep 17 00:00:00 2001 From: Tom Lane Date: Fri, 20 Jun 2025 15:55:12 -0400 Subject: Remove planner's have_dangerous_phv() join-order restriction. Commit 85e5e222b, which added (a forerunner of) this logic, argued that Adding the necessary complexity to make this work doesn't seem like it would be repaid in significantly better plans, because in cases where such a PHV exists, there is probably a corresponding join order constraint that would allow a good plan to be found without using the star-schema exception. The flaw in this claim is that there may be other join-order restrictions that prevent us from finding a join order that doesn't involve a "dangerous" PHV. In particular we now recognize that small join_collapse_limit or from_collapse_limit could prevent it. Therefore, let's bite the bullet and make the case work. We don't have to extend the executor's support for nestloop parameters as I thought at the time, because we can instead push the evaluation of the placeholder's expression into the left-hand input of the NestLoop node. So there's not really a lot of downside to this solution, and giving the planner more join-order flexibility should have value beyond just avoiding failure. Having said that, there surely is a nonzero risk of introducing new bugs. Since this failure mode escaped detection for ten years, such cases don't seem common enough to justify a lot of risk. Therefore, let's put this fix into master but leave the back branches alone (for now anyway). Bug: #18953 Reported-by: Alexander Lakhin Diagnosed-by: Richard Guo Author: Tom Lane Discussion: https://postgr.es/m/18953-1c9883a9d4afeb30@postgresql.org --- src/test/regress/expected/join.out | 84 ++++++++++++++++++++++++++++++++++++++ src/test/regress/sql/join.sql | 29 +++++++++++++ 2 files changed, 113 insertions(+) (limited to 'src/test') diff --git a/src/test/regress/expected/join.out b/src/test/regress/expected/join.out index f35a0b18c37..c292f04fdba 100644 --- a/src/test/regress/expected/join.out +++ b/src/test/regress/expected/join.out @@ -3946,6 +3946,59 @@ where t1.unique2 < 42 and t1.stringu1 > t2.stringu2; (1 row) -- variant that isn't quite a star-schema case +explain (verbose, costs off) +select ss1.d1 from + tenk1 as t1 + inner join tenk1 as t2 + on t1.tenthous = t2.ten + inner join + int8_tbl as i8 + left join int4_tbl as i4 + inner join (select 64::information_schema.cardinal_number as d1 + from tenk1 t3, + lateral (select abs(t3.unique1) + random()) ss0(x) + where t3.fivethous < 0) as ss1 + on i4.f1 = ss1.d1 + on i8.q1 = i4.f1 + on t1.tenthous = ss1.d1 +where t1.unique1 < i4.f1; + QUERY PLAN +------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- + Nested Loop + Output: (64)::information_schema.cardinal_number + Join Filter: (t1.tenthous = ((64)::information_schema.cardinal_number)::integer) + -> Seq Scan on public.tenk1 t3 + Output: t3.unique1, t3.unique2, t3.two, t3.four, t3.ten, t3.twenty, t3.hundred, t3.thousand, t3.twothousand, t3.fivethous, t3.tenthous, t3.odd, t3.even, t3.stringu1, t3.stringu2, t3.string4 + Filter: (t3.fivethous < 0) + -> Nested Loop + Output: t1.tenthous, t2.ten + -> Nested Loop + Output: t1.tenthous, t2.ten, i4.f1 + Join Filter: (t1.unique1 < i4.f1) + -> Hash Join + Output: t1.tenthous, t1.unique1, t2.ten + Hash Cond: (t2.ten = t1.tenthous) + -> Seq Scan on public.tenk1 t2 + Output: t2.unique1, t2.unique2, t2.two, t2.four, t2.ten, t2.twenty, t2.hundred, t2.thousand, t2.twothousand, t2.fivethous, t2.tenthous, t2.odd, t2.even, t2.stringu1, t2.stringu2, t2.string4 + -> Hash + Output: t1.tenthous, t1.unique1 + -> Nested Loop + Output: t1.tenthous, t1.unique1 + -> Subquery Scan on ss0 + Output: ss0.x, (64)::information_schema.cardinal_number + -> Result + Output: ((abs(t3.unique1))::double precision + random()) + -> Index Scan using tenk1_thous_tenthous on public.tenk1 t1 + Output: t1.unique1, t1.unique2, t1.two, t1.four, t1.ten, t1.twenty, t1.hundred, t1.thousand, t1.twothousand, t1.fivethous, t1.tenthous, t1.odd, t1.even, t1.stringu1, t1.stringu2, t1.string4 + Index Cond: (t1.tenthous = (((64)::information_schema.cardinal_number))::integer) + -> Seq Scan on public.int4_tbl i4 + Output: i4.f1 + Filter: (i4.f1 = ((64)::information_schema.cardinal_number)::integer) + -> Seq Scan on public.int8_tbl i8 + Output: i8.q1, i8.q2 + Filter: (i8.q1 = ((64)::information_schema.cardinal_number)::integer) +(33 rows) + select ss1.d1 from tenk1 as t1 inner join tenk1 as t2 @@ -4035,6 +4088,37 @@ select * from 1 | 2 | 2 (1 row) +-- This example demonstrates the folly of our old "have_dangerous_phv" logic +begin; +set local from_collapse_limit to 2; +explain (verbose, costs off) +select * from int8_tbl t1 + left join + (select coalesce(t2.q1 + x, 0) from int8_tbl t2, + lateral (select t3.q1 as x from int8_tbl t3, + lateral (select t2.q1, t3.q1 offset 0) s)) + on true; + QUERY PLAN +------------------------------------------------------------------ + Nested Loop Left Join + Output: t1.q1, t1.q2, (COALESCE((t2.q1 + t3.q1), '0'::bigint)) + -> Seq Scan on public.int8_tbl t1 + Output: t1.q1, t1.q2 + -> Materialize + Output: (COALESCE((t2.q1 + t3.q1), '0'::bigint)) + -> Nested Loop + Output: COALESCE((t2.q1 + t3.q1), '0'::bigint) + -> Seq Scan on public.int8_tbl t2 + Output: t2.q1, t2.q2 + -> Nested Loop + Output: t3.q1 + -> Seq Scan on public.int8_tbl t3 + Output: t3.q1, t3.q2 + -> Result + Output: NULL::bigint, NULL::bigint +(16 rows) + +rollback; -- Test proper handling of appendrel PHVs during useless-RTE removal explain (costs off) select * from diff --git a/src/test/regress/sql/join.sql b/src/test/regress/sql/join.sql index cc5128add4d..88d2204e447 100644 --- a/src/test/regress/sql/join.sql +++ b/src/test/regress/sql/join.sql @@ -1277,6 +1277,23 @@ where t1.unique2 < 42 and t1.stringu1 > t2.stringu2; -- variant that isn't quite a star-schema case +explain (verbose, costs off) +select ss1.d1 from + tenk1 as t1 + inner join tenk1 as t2 + on t1.tenthous = t2.ten + inner join + int8_tbl as i8 + left join int4_tbl as i4 + inner join (select 64::information_schema.cardinal_number as d1 + from tenk1 t3, + lateral (select abs(t3.unique1) + random()) ss0(x) + where t3.fivethous < 0) as ss1 + on i4.f1 = ss1.d1 + on i8.q1 = i4.f1 + on t1.tenthous = ss1.d1 +where t1.unique1 < i4.f1; + select ss1.d1 from tenk1 as t1 inner join tenk1 as t2 @@ -1332,6 +1349,18 @@ select * from (select 1 as x) ss1 left join (select 2 as y) ss2 on (true), lateral (select ss2.y as z limit 1) ss3; +-- This example demonstrates the folly of our old "have_dangerous_phv" logic +begin; +set local from_collapse_limit to 2; +explain (verbose, costs off) +select * from int8_tbl t1 + left join + (select coalesce(t2.q1 + x, 0) from int8_tbl t2, + lateral (select t3.q1 as x from int8_tbl t3, + lateral (select t2.q1, t3.q1 offset 0) s)) + on true; +rollback; + -- Test proper handling of appendrel PHVs during useless-RTE removal explain (costs off) select * from -- cgit v1.2.3