Re: The shared buffers challenge

Поиск
Список
Период
Сортировка
От Jeff Davis
Тема Re: The shared buffers challenge
Дата
Msg-id 1306541941.32559.119.camel@jdavis-ux.asterdata.local
обсуждение исходный текст
Ответ на The shared buffers challenge  (Merlin Moncure <mmoncure@gmail.com>)
Ответы Re: The shared buffers challenge
Список pgsql-performance
On Thu, 2011-05-26 at 09:31 -0500, Merlin Moncure wrote:
> Where they are most helpful is for masking of i/o if
> a page gets dirtied >1 times before it's written out to the heap

Another possible benefit of higher shared_buffers is that it may reduce
WAL flushes. A page cannot be evicted from shared_buffers until the WAL
has been flushed up to the page's LSN ("WAL before data"); so if there
is memory pressure to evict dirty buffers, it may cause extra WAL
flushes.

I'm not sure what the practical effects of this are, however, but it
might be an interesting thing to test.

Regards,
    Jeff Davis


В списке pgsql-performance по дате отправления:

Предыдущее
От: Mark Kirkwood
Дата:
Сообщение: Re: The shared buffers challenge
Следующее
От: Grzegorz Jaśkiewicz
Дата:
Сообщение: Re: serveRAID M5014 SAS