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
This commit is contained in:
parent
03107b4eda
commit
4d916dd876
@ -109,7 +109,7 @@ SELECT (COUNT(*) = (SELECT relpages FROM pg_class WHERE relname = 'test2')) AS r
|
||||
DROP TABLE test1;
|
||||
DROP TABLE test2;
|
||||
-- Test that parallel index build produces the same BRIN index as serial build.
|
||||
CREATE TABLE brin_parallel_test (a int, b text, c bigint) WITH (fillfactor=40);
|
||||
CREATE TEMPORARY TABLE brin_parallel_test (a int, b text, c bigint) WITH (fillfactor=40);
|
||||
-- Generate a table with a mix of NULLs and non-NULL values (and data suitable
|
||||
-- for the different opclasses we build later).
|
||||
INSERT INTO brin_parallel_test
|
||||
|
@ -56,7 +56,7 @@ DROP TABLE test1;
|
||||
DROP TABLE test2;
|
||||
|
||||
-- Test that parallel index build produces the same BRIN index as serial build.
|
||||
CREATE TABLE brin_parallel_test (a int, b text, c bigint) WITH (fillfactor=40);
|
||||
CREATE TEMPORARY TABLE brin_parallel_test (a int, b text, c bigint) WITH (fillfactor=40);
|
||||
|
||||
-- Generate a table with a mix of NULLs and non-NULL values (and data suitable
|
||||
-- for the different opclasses we build later).
|
||||
|
Loading…
x
Reference in New Issue
Block a user