Re: mosbench revisited

Поиск
Список
Период
Сортировка
От Robert Haas
Тема Re: mosbench revisited
Дата
Msg-id CA+TgmoYYzv1xxCfhtWYcuuMLitmVRZ58-Zhy0NtrcEY0k+oq+A@mail.gmail.com
обсуждение исходный текст
Ответ на Re: mosbench revisited  (Aidan Van Dyk <aidan@highrise.ca>)
Список pgsql-hackers
On Thu, Aug 4, 2011 at 5:09 PM, Aidan Van Dyk <aidan@highrise.ca> wrote:
> On Wed, Aug 3, 2011 at 5:04 PM, Robert Haas <robertmhaas@gmail.com> wrote:
>
>>      And hoping that the Linux guys decide to do something about it.
>>  This isn't really our bug - lseek is quite cheap in the uncontended
>> case.
>
> Has anyone tried this on a recent kernel (i.e. 2.6.39 or later), where
> they've finally remove the BKL out of VFS/inode?
>
> I mean, complaining about scalability in linux 2.6.18 is like
> complaining about scalability in postgresql 8.2 ;-)

Hmm.  This machine is running 2.6.32-131.6.1.el6.x86_64, not 2.6.18.
Not sure how much the code has changed since then, but the spinlock is
there in the master branch of Linus's repository.

--
Robert Haas
EnterpriseDB: http://www.enterprisedb.com
The Enterprise PostgreSQL Company


В списке pgsql-hackers по дате отправления:

Предыдущее
От: Alex Hunsaker
Дата:
Сообщение: Re: plperl crash with Debian 6 (64 bit), pl/perlu, libwww and https
Следующее
От: Jeff Davis
Дата:
Сообщение: Re: Transient plans versus the SPI API