Re: Excessive (and slow) fsync() within single transaction

Поиск
Список
Период
Сортировка
От Scott Marlowe
Тема Re: Excessive (and slow) fsync() within single transaction
Дата
Msg-id dcc563d10912091302r44a7ee52jb2b9ff2ee93f0c99@mail.gmail.com
обсуждение исходный текст
Ответ на Re: Excessive (and slow) fsync() within single transaction  (Stephen Tyler <stephen@stephen-tyler.com>)
Ответы Re: Excessive (and slow) fsync() within single transaction  (Ron Mayer <rm_pg@cheapcomplexdevices.com>)
Список pgsql-general
On Wed, Dec 9, 2009 at 5:11 AM, Stephen Tyler <stephen@stephen-tyler.com> wrote:
> The times are apparently in milliseconds.  But that doesn't make any sense
> for the 7200rpm SATA HDD, given it has an 8.3ms rotation time.  And the
> numbers for the SSD are basically identical to the HDD, apart from the bare
> write timing.
>
> Do I conclude that the sync timings are all faked by the OS?

Actually, it's usually the drives that lie about fsync, especially
consumer grade (and some server grade) SATA / PATA drives are known
for this.

В списке pgsql-general по дате отправления:

Предыдущее
От: Stephen Tyler
Дата:
Сообщение: Re: Excessive (and slow) fsync() within single transaction
Следующее
От: Ron Mayer
Дата:
Сообщение: Re: Excessive (and slow) fsync() within single transaction