pgsql: Improve BRIN minmax-multi opclass test coverage

Поиск
Список
Период
Сортировка
От Tomas Vondra
Тема pgsql: Improve BRIN minmax-multi opclass test coverage
Дата
Msg-id E1qFsXm-001Uqd-Tv@gemulon.postgresql.org
обсуждение исходный текст
Ответы Re: pgsql: Improve BRIN minmax-multi opclass test coverage  (Peter Eisentraut <peter@eisentraut.org>)
Список 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(+)


В списке pgsql-committers по дате отправления:

Предыдущее
От: Tomas Vondra
Дата:
Сообщение: pgsql: Introduce bloom_filter_size for BRIN bloom opclass
Следующее
От: Tomas Vondra
Дата:
Сообщение: pgsql: Fix memory leak in Incremental Sort rescans