Re: Testing Sandforce SSD

От: Andres Freund
Тема: Re: Testing Sandforce SSD
Дата: ,
Msg-id: 20100726222804.GA3054@anarazel.de
(см: обсуждение, исходный текст)
Ответ на: Re: Testing Sandforce SSD  (Greg Spiegelberg)
Список: pgsql-performance

Скрыть дерево обсуждения

Testing Sandforce SSD  (Yeb Havinga, )
 Re: Testing Sandforce SSD  (David Boreham, )
  Re: Testing Sandforce SSD  (, )
 Re: Testing Sandforce SSD  (Ben Chobot, )
 Re: Testing Sandforce SSD  (Greg Smith, )
  Re: Testing Sandforce SSD  (Yeb Havinga, )
   Re: Testing Sandforce SSD  (Yeb Havinga, )
    Re: Testing Sandforce SSD  (Yeb Havinga, )
     Re: Testing Sandforce SSD  (Greg Smith, )
  Re: Testing Sandforce SSD  (Greg Smith, )
   Re: Testing Sandforce SSD  ("Joshua D. Drake", )
    Re: Testing Sandforce SSD  (Greg Smith, )
   Re: Testing Sandforce SSD  (Yeb Havinga, )
    Re: Testing Sandforce SSD  (Karl Denninger, )
    Re: Testing Sandforce SSD  (Merlin Moncure, )
     Re: Testing Sandforce SSD  (Yeb Havinga, )
      Re: Testing Sandforce SSD  (Josh Berkus, )
       Re: Testing Sandforce SSD  (Greg Smith, )
        Re: Testing Sandforce SSD  (Scott Marlowe, )
         Re: Testing Sandforce SSD  (Yeb Havinga, )
          Re: Testing Sandforce SSD  (Greg Smith, )
          Re: Testing Sandforce SSD  (Hannu Krosing, )
     Re: Testing Sandforce SSD  (Scott Carey, )
      Re: Testing Sandforce SSD  (Brad Nicholson, )
   Re: Testing Sandforce SSD  ("Joshua D. Drake", )
  Re: Testing Sandforce SSD  (Yeb Havinga, )
   Re: Testing Sandforce SSD  (Yeb Havinga, )
    Re: Testing Sandforce SSD  (Matthew Wakeling, )
     Re: Testing Sandforce SSD  (Yeb Havinga, )
      Re: Testing Sandforce SSD  (Greg Smith, )
       Re: Testing Sandforce SSD  (Yeb Havinga, )
        Re: Testing Sandforce SSD  (Yeb Havinga, )
        Re: Testing Sandforce SSD  (Greg Smith, )
         Re: Testing Sandforce SSD  (Greg Spiegelberg, )
          Re: Testing Sandforce SSD  (Andres Freund, )
          Re: Testing Sandforce SSD  (Greg Smith, )
          Re: Testing Sandforce SSD  (Michael Stone, )
           Re: Testing Sandforce SSD  (Yeb Havinga, )
            Re: Testing Sandforce SSD  (Yeb Havinga, )
             Re: Testing Sandforce SSD  (Greg Spiegelberg, )
            Re: Testing Sandforce SSD  (Michael Stone, )
         Re: Testing Sandforce SSD  (Scott Carey, )
     Re: Testing Sandforce SSD  (Greg Smith, )
      Re: Testing Sandforce SSD  (Matthew Wakeling, )
       Re: Testing Sandforce SSD  (Yeb Havinga, )
        Re: Testing Sandforce SSD  (Greg Spiegelberg, )
         Re: Testing Sandforce SSD  (Greg Smith, )
          Re: Testing Sandforce SSD  (Scott Marlowe, )
           Re: Testing Sandforce SSD  (Michael Stone, )
       Re: Testing Sandforce SSD  (Greg Smith, )
        Re: Testing Sandforce SSD  ("Kevin Grittner", )
        Re: Testing Sandforce SSD  (Hannu Krosing, )
   Re: Testing Sandforce SSD  (Yeb Havinga, )
  Re: Testing Sandforce SSD  (Bruce Momjian, )
 Re: Testing Sandforce SSD  (Merlin Moncure, )
 Re: Testing Sandforce SSD  (Yeb Havinga, )
  Re: Testing Sandforce SSD  (Yeb Havinga, )
   Re: Testing Sandforce SSD  (Merlin Moncure, )
    Re: Testing Sandforce SSD  (Scott Carey, )
 Re: Testing Sandforce SSD  (Chris Browne, )
 Re: Testing Sandforce SSD  (Chris Browne, )

On Mon, Jul 26, 2010 at 03:23:20PM -0600, Greg Spiegelberg wrote:
> On Mon, Jul 26, 2010 at 1:45 PM, Greg Smith <> wrote:
> > Yeb Havinga wrote:
> >> I did some ext3,ext4,xfs,jfs and also ext2 tests on the just-in-memory
> >> read/write test. (scale 300) No real winners or losers, though ext2 isn't
> >> really faster and the manual need for fix (y) during boot makes it
> >> impractical in its standard configuration.
> >>
> >
> > That's what happens every time I try it too.  The theoretical benefits of
> > ext2 for hosting PostgreSQL just don't translate into significant
> > performance increases on database oriented tests, certainly not ones that
> > would justify the downside of having fsck issues come back again.  Glad to
> > see that holds true on this hardware too.
> I know I'm talking development now but is there a case for a pg_xlog block
> device to remove the file system overhead and guaranteeing your data is
> written sequentially every time?
For one I doubt that its a relevant enough efficiency loss in
comparison with a significantly significantly complex implementation
(for one you cant grow/shrink, for another you have to do more
complex, hw-dependent things like rounding to hardware boundaries,
page size etc to stay efficient) for another my experience is that at
a relatively low point XlogInsert gets to be the bottleneck - so I
don't see much point in improving at that low level (yet at least).

Where I would like to do some hw dependent measuring (because I see
significant improvements there) would be prefetching for seqscan,
indexscans et al. using blktrace... But I currently dont have the
time. And its another topic ;-)

Andres


В списке pgsql-performance по дате сообщения:

От: Tom Lane
Дата:
Сообщение: Re: Big difference in time returned by EXPLAIN ANALYZE SELECT ... AND SELECT ...
От: Mark Kirkwood
Дата:
Сообщение: Linux Filesystems again - Ubuntu this time