Re: performance on new linux box

Поиск
Список
Период
Сортировка
От Ryan Wexler
Тема Re: performance on new linux box
Дата
Msg-id AANLkTino2ep4VyJDA9PVV6FObxHnBlLX3O9z8q19PzfN@mail.gmail.com
обсуждение исходный текст
Ответ на Re: performance on new linux box  ("Kevin Grittner" <Kevin.Grittner@wicourts.gov>)
Ответы Re: performance on new linux box  (David Boreham <david_list@boreham.org>)
Re: performance on new linux box  ("Kevin Grittner" <Kevin.Grittner@wicourts.gov>)
Re: performance on new linux box  (Craig James <craig_james@emolecules.com>)
Список pgsql-performance


On Thu, Jul 8, 2010 at 12:46 PM, Kevin Grittner <Kevin.Grittner@wicourts.gov> wrote:
Ryan Wexler <ryan@iridiumsuite.com> wrote:

> One thing I don't understand is why BBU will result in a huge
> performance gain.  I thought BBU was all about power failures?

Well, it makes it safe for the controller to consider the write
complete as soon as it hits the RAM cache, rather than waiting for
persistence to the disk itself.  It can then schedule the writes in
a manner which is efficient based on the physical medium.

Something like this was probably happening on your non-server
machines, but without BBU it was not actually safe.  Server class
machines tend to be more conservative about not losing your data,
but without a RAID controller with BBU cache, that slows writes down
to the speed of the rotating disks.

-Kevin
Thanks for the explanations that makes things clearer.  It still amazes me that it would account for a 5x change in IO.

В списке pgsql-performance по дате отправления:

Предыдущее
От: "Kevin Grittner"
Дата:
Сообщение: Re: performance on new linux box
Следующее
От: "Kevin Grittner"
Дата:
Сообщение: Re: [Slony1-general] WAL partition overloaded--by autovacuum?