pgsql: Teach UNION planner to remove dummy inputs - Mailing list pgsql-committers

From David Rowley
Subject pgsql: Teach UNION planner to remove dummy inputs
Date
Msg-id E1v4r6m-001Lgx-1h@gemulon.postgresql.org
Whole thread Raw
List pgsql-committers
Teach UNION planner to remove dummy inputs

This adjusts UNION planning so that the planner produces more optimal
plans when one or more of the UNION's subqueries have been proven to be
empty (a dummy rel).

If any of the inputs are empty, then that input can be removed from the
Append / MergeAppend.  Previously, a const-false "Result" node would
appear to represent this.  Removing empty inputs has a few extra
benefits when only 1 union child remains as it means the Append or
MergeAppend can be removed in setrefs.c, making the plan slightly faster
to execute.  Also, we can provide better n_distinct estimates by looking
at the sole remaining input rel's statistics.

Author: David Rowley <dgrowleyml@gmail.com>
Reviewed-by: Tom Lane <tgl@sss.pgh.pa.us>
Discussion: https://postgr.es/m/CAApHDvri53PPF76c3M94_QNWbJfXjyCnjXuj_2=LYM-0m8WZtw@mail.gmail.com

Branch
------
master

Details
-------
https://git.postgresql.org/pg/commitdiff/03d40e4b523b2075c198aa89d9445ea8297f8eca

Modified Files
--------------
src/backend/optimizer/prep/prepunion.c | 56 ++++++++++++++++++++++++++++------
src/test/regress/expected/union.out    | 51 +++++++++++++++++++++++++++++++
src/test/regress/sql/union.sql         | 27 ++++++++++++++++
3 files changed, 125 insertions(+), 9 deletions(-)


pgsql-committers by date:

Previous
From: David Rowley
Date:
Subject: pgsql: Use bms_add_members() instead of bms_union() when possible
Next
From: Álvaro Herrera
Date:
Subject: pgsql: Don't include execnodes.h in brin.h or gin.h