Re: Should we cacheline align PGXACT?

Поиск
Список
Период
Сортировка
От Tom Lane
Тема Re: Should we cacheline align PGXACT?
Дата
Msg-id 31991.1471614372@sss.pgh.pa.us
обсуждение исходный текст
Ответ на Should we cacheline align PGXACT?  (Alexander Korotkov <a.korotkov@postgrespro.ru>)
Ответы Re: Should we cacheline align PGXACT?  (Alexander Korotkov <a.korotkov@postgrespro.ru>)
Re: Should we cacheline align PGXACT?  (Andres Freund <andres@anarazel.de>)
Список pgsql-hackers
Alexander Korotkov <a.korotkov@postgrespro.ru> writes:
> originally this idea was proposed by Andres Freund while experimenting with
> lockfree Pin/UnpinBuffer [1].
> The patch is attached as well as results of pgbench -S on 72-cores
> machine.  As before it shows huge benefit in this case.

That's one mighty ugly patch.  Can't you do it without needing to
introduce the additional layer of struct nesting?
        regards, tom lane



В списке pgsql-hackers по дате отправления:

Предыдущее
От: Tom Lane
Дата:
Сообщение: Re: Exporting more function in libpq
Следующее
От: Adrien Nayrat
Дата:
Сообщение: Re: LSN as a recovery target