Re: Dual Xeon + HW RAID question

От: Jord Tanner
Тема: Re: Dual Xeon + HW RAID question
Дата: ,
Msg-id: 1058901531.4339.57.camel@gecko
(см: обсуждение, исходный текст)
Ответ на: Re: Dual Xeon + HW RAID question  (Bruce Momjian)
Список: pgsql-performance

Скрыть дерево обсуждения

Dual Xeon + HW RAID question  ("alexandre arruda paes :: aldeia digital", )
 Re: Dual Xeon + HW RAID question  (Rod Taylor, )
 Re: Dual Xeon + HW RAID question  ("Nikolaus Dilger", )
  [OT] Such incredible h/w (was Re: Dual Xeon + HW RAID question)  (Ron Johnson, )
  Re: Dual Xeon + HW RAID question  (Andrew Sullivan, )
  Re: Dual Xeon + HW RAID question  (SZUCS Gábor, )
   Re: Dual Xeon + HW RAID question  ("alexandre paes :: aldeia digital", )
   Re: Dual Xeon + HW RAID question  (Bruce Momjian, )
    Re: Dual Xeon + HW RAID question  ("Mindaugas Riauba", )
     Re: Dual Xeon + HW RAID question  (Bruce Momjian, )
      Re: Dual Xeon + HW RAID question  (SZUCS Gábor, )
       Re: Dual Xeon + HW RAID question  (Jord Tanner, )
        Re: Dual Xeon + HW RAID question  (Bruce Momjian, )
         Re: Dual Xeon + HW RAID question  (Jord Tanner, )
          Re: Dual Xeon + HW RAID question  (Bruce Momjian, )
           Re: Dual Xeon + HW RAID question  (Jord Tanner, )
       Re: Dual Xeon + HW RAID question  (Bruce Momjian, )

On Tue, 2003-07-22 at 11:50, Bruce Momjian wrote:
> Jord Tanner wrote:
> > On Tue, 2003-07-22 at 10:39, Bruce Momjian wrote:
> > > But CPU affinity isn't realated to hyperthreading, as far as I know.
> > > CPU affinity tries to keep processes on the same cpu in case there is
> > > still valuable info in the cpu cache.
> > >
> >
> > It is true that CPU affinity is designed to prevent the dump of valuable
> > CPU cache. My thought is that if you are trying to prevent CPU
> > contention, you could use CPU affinity to prevent 2 postmaster processes
> > from running simultaneously on the same die. Am I out to lunch here?
> > I've not worked with CPU affinity before, so I'm not familiar with the
> > intimate details.
>
> I guess you could but it is the backends that use the cpu.  I don't
> think manually specifying affinity will work for most applications.

This is beating a dead horse, but I'll take one more kick at it.

CPU affinity is defined by a bit mask, so multiple processors can be
selected. It is also inherited by child processes, so assigning CPU 0
and CPU 2 (which I assume would be on different dies in a dual processor
hyper-threading system) to the parent postmaster should prevent CPU
contention with respect to the postgres backend.

I would be very interested to see if any advantage could be gained by a
combination of multiple HT processors and cpu affinity over multiple
non-HT processors. Yet Another Performance Testing To Do (YAPTTD)!

--
Jord Tanner <>



В списке pgsql-performance по дате сообщения:

От: Joe Conway
Дата:
Сообщение: Re: One table or many tables for data set
От: "Castle, Lindsay"
Дата:
Сообщение: Re: One table or many tables for data set