Re: checkpointer continuous flushing

Поиск
Список
Период
Сортировка
От Amit Kapila
Тема Re: checkpointer continuous flushing
Дата
Msg-id CAA4eK1J__4RCgbPfTA9jOxW3Nq5GkuBu1jt_-1AhH4E8YM6XMQ@mail.gmail.com
обсуждение исходный текст
Ответ на Re: checkpointer continuous flushing  (Andres Freund <andres@anarazel.de>)
Список pgsql-hackers
On Mon, Oct 19, 2015 at 4:06 AM, Andres Freund <andres@anarazel.de> wrote:
>
>
> I wonder if mmap() && msync(MS_ASYNC) isn't a better replacement for
> sync_file_range(SYNC_FILE_RANGE_WRITE) than posix_fadvise(DONTNEED). It
> might even be possible to later approximate that on windows using
> FlushViewOfFile().
>

I think this idea is worth exploring especially because we can have
Windows equivalent for this optimisation.  Will this option by any
chance can lead to increase in memory usage as mmap has to
map the file/'s?


With Regards,
Amit Kapila.

В списке pgsql-hackers по дате отправления:

Предыдущее
От: Michael Paquier
Дата:
Сообщение: Re: [RFC] overflow checks optimized away
Следующее
От: Amit Kapila
Дата:
Сообщение: Re: Checkpoint throttling issues