Re: more anti-postgresql FUD

Поиск
Список
Период
Сортировка
От Andrew - Supernews
Тема Re: more anti-postgresql FUD
Дата
Msg-id slrneivci9.27so.andrew+nonews@atlantis.supernews.net
обсуждение исходный текст
Ответ на more anti-postgresql FUD  ("Merlin Moncure" <mmoncure@gmail.com>)
Ответы Re: more anti-postgresql FUD  (Alexander Staubo <alex@purefiction.net>)
Re: more anti-postgresql FUD  (Martijn van Oosterhout <kleptog@svana.org>)
Список pgsql-general
On 2006-10-13, Alexander Staubo <alex@purefiction.net> wrote:
> On Oct 13, 2006, at 17:13 , Andrew - Supernews wrote:
>> Your disk probably has write caching enabled. A 10krpm disk should be
>> limiting you to under 170 transactions/sec with a single connection
>> and fsync enabled.
>
> What formula did you use to get to that number?

It's just the number of disk revolutions per second. Without caching, each
WAL flush tends to require a whole revolution unless the on-disk layout of
the filesystem is _very_ strange. You can get multiple commits per WAL
flush if you have many concurrent connections, but with a single connection
that doesn't apply.

> Is there a generic
> way on Linux to turn off (controller-based?) write caching?

I don't use Linux, sorry. Modern SCSI disks seem to ship with WCE=1 on
mode page 8 on the disk, thus enabling evil write caching by default.

--
Andrew, Supernews
http://www.supernews.com - individual and corporate NNTP services

В списке pgsql-general по дате отправления:

Предыдущее
От: "Merlin Moncure"
Дата:
Сообщение: Re: more anti-postgresql FUD
Следующее
От: "Tomi NA"
Дата:
Сообщение: Re: UTF-8