pgsql: Improve BRIN minmax-multi opclass test coverage - Mailing list pgsql-committers

From Tomas Vondra
Subject pgsql: Improve BRIN minmax-multi opclass test coverage
Date
Msg-id E1qFsXm-001Uqd-Tv@gemulon.postgresql.org
Whole thread Raw
Responses Re: pgsql: Improve BRIN minmax-multi opclass test coverage
List pgsql-committers
Improve BRIN minmax-multi opclass test coverage

Per the code coverage report, the existing regression tests did not
exercice some a couple important BRIN minmax-multi code paths.

- The tests focused on testing planning with a range of scan key
  strategies, but not the execution. Fixed by adding queries that
  actually test query execution for both equality and inequality.

- All tests created indexes after inserting data, but this only
  exercises the CREATE INDEX strategy that sees all values at once, not
  incremental summary updates. The new tests flip the order and create
  the index before adding data.

- The assert check(s) validating correctness of expanded ranges were
  present only in the "union" code path, which is not covered by
  regression tests at all (as it requires concurrency etc.). Fixed by
  adding the asserts to a couple more places.

Reviewed-by: Heikki Linnakangas
Discussion: https://postgr.es/m/57020b2e-d9c9-9bc7-4892-b36d9bb07563%40enterprisedb.com

Branch
------
master

Details
-------
https://git.postgresql.org/pg/commitdiff/0457109344b46f481f9bf09b85674695ba57c8e4

Modified Files
--------------
src/backend/access/brin/brin_minmax_multi.c |   9 +
src/test/regress/expected/brin_multi.out    | 357 ++++++++++++++++++++++++++++
src/test/regress/sql/brin_multi.sql         | 165 +++++++++++++
3 files changed, 531 insertions(+)


pgsql-committers by date:

Previous
From: Tomas Vondra
Date:
Subject: pgsql: Introduce bloom_filter_size for BRIN bloom opclass
Next
From: Tomas Vondra
Date:
Subject: pgsql: Fix memory leak in Incremental Sort rescans