Re: checkpoints/bgwriter tuning verification

Поиск
Список
Период
Сортировка
От Steve Clark
Тема Re: checkpoints/bgwriter tuning verification
Дата
Msg-id 4AEACAE3.2000701@netwolves.com
обсуждение исходный текст
Ответ на Re: checkpoints/bgwriter tuning verification  (Scott Marlowe <scott.marlowe@gmail.com>)
Ответы Re: checkpoints/bgwriter tuning verification  (Brad Nicholson <bnichols@ca.afilias.info>)
Список pgsql-general
On 10/29/2009 04:42 PM, Scott Marlowe wrote:
> On Thu, Oct 29, 2009 at 12:46 PM, Vick Khera<vivek@khera.org>  wrote:
>> On my primary DB I'm observing random slowness which just doesn't make
>> sense to me.  The I/O system can easily do 40MB/sec writes, but I'm
>> only seeing a sustained 5MB/sec, even as the application is stalling
>> waiting on the DB.
>
> Just one point on top of everything else you'll hear.  40 MB/sec
> sequential throughput does not equal 40MB/sec random PLUS checkpoint
> throughput.  Random access is gonna lower that 40MB/sec way down real
> fast.
>
> First step to speed things up is putting pg_xlog on its own disk(s).
Hi Scott,

How exactly do you do this? By creating a link to the new location or
is there a config option somewhere that says where the pg_xlog resides?

Thanks,
Steve

> Since pg_xlog is mostly sequentially access, it's much faster when
> it's not competing with the rest of the db.  THEN if you need faster
> disks you can buy them and throw them at path/data/base/.  However,
> often just splitting things out like this will make a world of
> difference on a write heavy database.
>


В списке pgsql-general по дате отправления:

Предыдущее
От: Thom Brown
Дата:
Сообщение: Re: Forms generator ?
Следующее
От: Sam Mason
Дата:
Сообщение: Re: Absolute value of intervals