Re: scalablility problem

От: Michael Stone
Тема: Re: scalablility problem
Дата: ,
Msg-id: 20070331114104.GD11402@mathom.us
(см: обсуждение, исходный текст)
Ответ на: Re: scalablility problem  (Guido Neitzer)
Ответы: Re: scalablility problem  (Xiaoning Ding <-state.edu>)
Список: pgsql-performance

Скрыть дерево обсуждения

scalablility problem  (Xiaoning Ding <-state.edu>, )
 Re: scalablility problem  ("Dave Dutcher", )
 Re: scalablility problem  (Tom Lane, )
  Re: scalablility problem  (Xiaoning Ding <-state.edu>, )
   Re: scalablility problem  (Scott Marlowe, )
   Re: scalablility problem  (Ron Mayer, )
    Re: scalablility problem  (Xiaoning Ding <-state.edu>, )
     Re: scalablility problem  (Dave Cramer, )
 Re: scalablility problem  (Scott Marlowe, )
  Re: scalablility problem  (Xiaoning Ding <-state.edu>, )
   Re: scalablility problem  ("Joshua D. Drake", )
    Re: scalablility problem  (Tom Lane, )
     Re: scalablility problem  (Xiaoning Ding <-state.edu>, )
 Re: scalablility problem  (Christopher Browne, )
  Re: scalablility problem  (Guido Neitzer, )
   Re: scalablility problem  (Michael Stone, )
    Re: scalablility problem  (Xiaoning Ding <-state.edu>, )
  Re: scalablility problem  (Xiaoning Ding <-state.edu>, )

On Fri, Mar 30, 2007 at 10:00:30PM -0600, Guido Neitzer wrote:
>On 30.03.2007, at 19:18, Christopher Browne wrote:
>>2.  There are known issues with the combination of Xeon processors and
>>PAE memory addressing; that sort of hardware tends to be *way* less
>>speedy than the specs would suggest.
>
>That is not true as the current series of processors (Woodcrest and
>the like) are also called Xeon. You probably mean the Pentium IV era
>Xeons.

Well, the newer ones can address large amounts of memory directly,
without using PAE, but the original comment was correct--PAE is slow
regardless of what processor implements it.

Mike Stone


В списке pgsql-performance по дате сообщения:

От: Xiaoning Ding
Дата:
Сообщение: Re: scalablility problem
От: Andrew - Supernews
Дата:
Сообщение: Re: Scaling SELECT:s with the number of disks on a stripe