From 7e0ade0ffe0a76b1926a4af39ecdf799c96ef1ba Mon Sep 17 00:00:00 2001 From: David Rowley Date: Sat, 3 Feb 2024 00:20:18 +1300 Subject: [PATCH] Allow Gather Merge in more cases for parallel DISTINCT Here we adjust the partial path generation for parallel DISTINCT queries to add Sort nodes on top of any unsorted partial distinct paths. This increases the likelihood of the planner pushing a Sort below a Gather Merge which enables the final phase of the parallel distinct to be implemented using a Unique node in more cases. Sorting the partial distinct paths is particularly useful when the DISTINCT query has an ORDER BY and LIMIT clause as this can allow cheaper plans by having the workers Hash Aggregate then Sort before feeding the results into the Gather Merge. The non-parallel portion of the plan then becomes very cheap as it leaves only Unique and Limit to do in the leader process. Author: Richard Guo Reviewed-by: David Rowley Discussion: https://postgr.es/m/CAMbWs48u9VoVOouJsys1qOaC9WVGVmBa+wT1dx8KvxF5GPzezA@mail.gmail.com --- src/backend/optimizer/plan/planner.c | 2 +- src/test/regress/expected/select_distinct.out | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/src/backend/optimizer/plan/planner.c b/src/backend/optimizer/plan/planner.c index 342f5ad8d0a..acc324122fd 100644 --- a/src/backend/optimizer/plan/planner.c +++ b/src/backend/optimizer/plan/planner.c @@ -4819,7 +4819,7 @@ create_partial_distinct_paths(PlannerInfo *root, RelOptInfo *input_rel, if (partial_distinct_rel->partial_pathlist != NIL) { - generate_gather_paths(root, partial_distinct_rel, true); + generate_useful_gather_paths(root, partial_distinct_rel, true); set_cheapest(partial_distinct_rel); /* diff --git a/src/test/regress/expected/select_distinct.out b/src/test/regress/expected/select_distinct.out index 1f72756ccb4..82b8e54f5f1 100644 --- a/src/test/regress/expected/select_distinct.out +++ b/src/test/regress/expected/select_distinct.out @@ -235,10 +235,10 @@ SELECT DISTINCT four FROM tenk1; QUERY PLAN ---------------------------------------------------- Unique - -> Sort - Sort Key: four - -> Gather - Workers Planned: 2 + -> Gather Merge + Workers Planned: 2 + -> Sort + Sort Key: four -> HashAggregate Group Key: four -> Parallel Seq Scan on tenk1