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-e3d7317c3...@gmail.com Discussion: https://postgr.es/m/2892135.1668976...@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(-)
