Re: Performance problems on 4/8way Opteron (dualcore)

Поиск
Список
Период
Сортировка
Искать
От
William Yu
Тема
Re: Performance problems on 4/8way Opteron (dualcore)
Дата
Msg-id
dcjer1$16ov$1@news.hub.org
Ответ на
Список
Дерево обсуждения
Performance problems on 4/8way Opteron (dualcore) HP DL585 Dirk Lutzebäck <lutzeb@aeccom.com>
Re: Performance problems on 4/8way Opteron (dualcore) HP DL585 Josh Berkus <josh@agliodbs.com>
Re: Performance problems on 4/8way Opteron (dualcore) HP "Jeffrey W. Baker" <jwbaker@acm.org>
Re: Performance problems on 4/8way Opteron (dualcore) HP Dirk Lutzebäck <lutzeb@aeccom.com>
Re: Performance problems on 4/8way Opteron (dualcore) "J. Andrew Rogers" <jrogers@neopolitan.com>
Re: Performance problems on 4/8way Opteron (dualcore) HP Dirk Lutzebäck <lutzeb@aeccom.com>
Re: Performance problems on 4/8way Opteron (dualcore) William Yu <wyu@talisys.com>
Re: Performance problems on 4/8way Opteron (dualcore) "J. Andrew Rogers" <jrogers@neopolitan.com>
Re: Performance problems on 4/8way Opteron (dualcore) William Yu <wyu@talisys.com>
A 4xDC would be far more sensitive to poor NUMA code than 2xDC so I'm 
not surprised I don't see performance issues on our 2xDC w/ < 2.6.12.


J. Andrew Rogers wrote:
> On 7/30/05 12:57 AM, "William Yu"  wrote:
> 
>>I haven't investigated the 2.6.12+ kernel updates yet -- I probably will
>>do our development servers first to give it a test.
> 
> 
> 
> The kernel updates make the NUMA code dual-core aware, which apparently
> makes a big difference in some cases but not in others.  It makes some
> sense, since multi-processor multi-core machines will have two different
> types of non-locality instead of just one that need to be managed.  Prior to
> the v2.6.12 patches, a dual-core dual-proc machine was viewed as a quad-proc
> machine.
> 
> The closest thing to a supported v2.6.12 kernel that I know of is FC4, which
> is not really supported in the enterprise sense of course.
> 
> 
> J. Andrew Rogers
> 
> 
> 
> ---------------------------(end of broadcast)---------------------------
> TIP 2: Don't 'kill -9' the postmaster
> 
В списке pgsql-performance по дате отправления
От: Andreas Pflug
Дата:
От: Michael Parker
Дата:
FAQ