Re: lockup in parallel hash join on dikkop (freebsd 14.0-current)

Поиск
Список
Период
Сортировка
От Robert Haas
Тема Re: lockup in parallel hash join on dikkop (freebsd 14.0-current)
Дата
Msg-id CA+TgmoY61uExKGTxA_gRFAr-yiXfWd=1u7_SB0t2eZ9oa8QRxQ@mail.gmail.com
обсуждение исходный текст
Ответ на Re: lockup in parallel hash join on dikkop (freebsd 14.0-current)  (Alexander Lakhin <exclusion@gmail.com>)
Ответы Re: lockup in parallel hash join on dikkop (freebsd 14.0-current)  (Alexander Lakhin <exclusion@gmail.com>)
Список pgsql-hackers
On Fri, Sep 1, 2023 at 6:13 AM Alexander Lakhin <exclusion@gmail.com> wrote:
> (Placing "pg_compiler_barrier();" just after "waiting = true;" fixed the
> issue for us.)

Maybe it'd be worth trying something stronger, like
pg_memory_barrier(). A compiler barrier doesn't prevent the CPU from
reordering loads and stores as it goes, and ARM64 has weak memory
ordering.

--
Robert Haas
EDB: http://www.enterprisedb.com



В списке pgsql-hackers по дате отправления:

Предыдущее
От: Robert Haas
Дата:
Сообщение: Re: Avoid a possible null pointer (src/backend/utils/adt/pg_locale.c)
Следующее
От: Peter Eisentraut
Дата:
Сообщение: Re: Transaction timeout