pgsql: Stabilize test of BRIN parallel create - Mailing list pgsql-committers

From Tomas Vondra
Subject pgsql: Stabilize test of BRIN parallel create
Date
Msg-id E1rwkrg-002MJY-Nv@gemulon.postgresql.org
Whole thread Raw
List pgsql-committers
Stabilize test of BRIN parallel create

The test for parallel create of BRIN indexes added by commit 8225c2fd40
happens to be unstable - a background transaction (e.g. auto-analyze)
may hold back global xmin for the initial VACUUM / CREATE INDEX. If the
cleanup happens before the next CREATE INDEX, the indexes will not be
exactly the same.

This is the same issue as e2933a6e11, so fix it the same way by making
the table TEMPORARY, which uses an up-to-date cutoff xmin that is not
held back by other processes.

Reported by Alexander Lakhin, who also suggested the fix.

Author: Alexander Lakhin
Discussion: https://postgr.es/m/b58901cd-a7cc-29c6-e2b1-e3d7317c3c69@gmail.com
Discussion: https://postgr.es/m/2892135.1668976646@sss.pgh.pa.us

Branch
------
master

Details
-------
https://git.postgresql.org/pg/commitdiff/4d916dd876c3d9a4ceff5a0c54c5c58a0d1052e3

Modified Files
--------------
contrib/pageinspect/expected/brin.out | 2 +-
contrib/pageinspect/sql/brin.sql      | 2 +-
2 files changed, 2 insertions(+), 2 deletions(-)


pgsql-committers by date:

Previous
From: Tom Lane
Date:
Subject: pgsql: Fix generation of EC join conditions at the wrong plan level.
Next
From: Tom Lane
Date:
Subject: pgsql: Undo incorrect typedefs.list change.