Re: Two identical systems, radically different performance

Поиск
Список
Период
Сортировка
От Craig James
Тема Re: Two identical systems, radically different performance
Дата
Msg-id CAFwQ8rdmzO046cXO-mqcsZKsj9Ch_W-mfiJpeQnOx8xob-SMVw@mail.gmail.com
обсуждение исходный текст
Ответ на Re: Two identical systems, radically different performance  (Claudio Freire <klaussfreire@gmail.com>)
Ответы Re: Two identical systems, radically different performance  (Claudio Freire <klaussfreire@gmail.com>)
Re: Two identical systems, radically different performance  (Mark Kirkwood <mark.kirkwood@catalyst.net.nz>)
Список pgsql-performance
Дерево обсуждения


On Mon, Oct 8, 2012 at 3:44 PM, Claudio Freire <klaussfreire@gmail.com> wrote:
On Mon, Oct 8, 2012 at 7:25 PM, Craig James <cjames@emolecules.com> wrote:
>> > But why? What have I overlooked?
>>
>> Do you have readahead properly set up on the new one?
>
>
>  # blockdev --getra /dev/sdb1
> 256


It's probably this. 256 is way too low to saturate your I/O system.
Pump it up. I've found 8192 works nice for a system I have, 32000 I
guess could work too.

But again ... the two systems are identical.  This can't explain it.

Thanks,
Craig

В списке pgsql-performance по дате отправления:

Предыдущее
От: Evgeny Shishkin
Дата:
Сообщение: Re: Two identical systems, radically different performance
Следующее
От: Claudio Freire
Дата:
Сообщение: Re: Two identical systems, radically different performance