pg.ddx.io pgsql-performance@postgresql.org mailing list archive
help / color / mirror / Atom feedXFS vs Ext3, and schedulers, for WAL
4+ messages / 2 participants
[nested] [flat]
* XFS vs Ext3, and schedulers, for WAL
@ 2010-10-06 23:11 Josh Berkus <josh@agliodbs.com>
2010-10-11 17:50 ` Re: XFS vs Ext3, and schedulers, for WAL Josh Berkus <josh@agliodbs.com>
0 siblings, 1 reply; 4+ messages in thread
From: Josh Berkus @ 2010-10-06 23:11 UTC (permalink / raw)
To: pgsql-performance
All,
There's a number of blog tests floating around comparing XFS and Ext3,
and the various Linux schedulers, for PGDATA or for an all-in-one mount.
However, the WAL has a rather particular write pattern, and it's
reasonable to assume that it shouldn't be optimized the same way as
PGDATA. Has anyone done any head-to-heads for WAL drive configuration
changes?
--
-- Josh Berkus
PostgreSQL Experts Inc.
http://www.pgexperts.com
^ permalink raw reply [nested|flat] 4+ messages in thread
* Re: XFS vs Ext3, and schedulers, for WAL
2010-10-06 23:11 XFS vs Ext3, and schedulers, for WAL Josh Berkus <josh@agliodbs.com>
@ 2010-10-11 17:50 ` Josh Berkus <josh@agliodbs.com>
2010-10-11 18:06 ` Re: XFS vs Ext3, and schedulers, for WAL Joshua D. Drake <jd@commandprompt.com>
0 siblings, 1 reply; 4+ messages in thread
From: Josh Berkus @ 2010-10-11 17:50 UTC (permalink / raw)
To: pgsql-performance
> There's a number of blog tests floating around comparing XFS and Ext3,
> and the various Linux schedulers, for PGDATA or for an all-in-one mount.
>
> However, the WAL has a rather particular write pattern, and it's
> reasonable to assume that it shouldn't be optimized the same way as
> PGDATA. Has anyone done any head-to-heads for WAL drive configuration
> changes?
That would be a "no", then. Looks like I have my work cut out for me ...
--
-- Josh Berkus
PostgreSQL Experts Inc.
http://www.pgexperts.com
^ permalink raw reply [nested|flat] 4+ messages in thread
* Re: XFS vs Ext3, and schedulers, for WAL
2010-10-06 23:11 XFS vs Ext3, and schedulers, for WAL Josh Berkus <josh@agliodbs.com>
2010-10-11 17:50 ` Re: XFS vs Ext3, and schedulers, for WAL Josh Berkus <josh@agliodbs.com>
@ 2010-10-11 18:06 ` Joshua D. Drake <jd@commandprompt.com>
2010-10-11 18:59 ` Re: XFS vs Ext3, and schedulers, for WAL Josh Berkus <josh@agliodbs.com>
0 siblings, 1 reply; 4+ messages in thread
From: Joshua D. Drake @ 2010-10-11 18:06 UTC (permalink / raw)
To: Josh Berkus <josh@agliodbs.com>; +Cc: pgsql-performance
On Mon, 2010-10-11 at 10:50 -0700, Josh Berkus wrote:
> > There's a number of blog tests floating around comparing XFS and Ext3,
> > and the various Linux schedulers, for PGDATA or for an all-in-one mount.
> >
> > However, the WAL has a rather particular write pattern, and it's
> > reasonable to assume that it shouldn't be optimized the same way as
> > PGDATA. Has anyone done any head-to-heads for WAL drive configuration
> > changes?
>
> That would be a "no", then. Looks like I have my work cut out for me ...
The only thing I have done is:
http://www.commandprompt.com/blogs/joshua_drake/2008/04/is_that_performance_i_smell_ext2_vs_ext3_on_...
It doesn't cover XFS but it provides a decent and simple comparison on
ext2/ext3 etc...
Remember xlog is sequential so pushing it off is useful.
JD
>
> --
> -- Josh Berkus
> PostgreSQL Experts Inc.
> http://www.pgexperts.com
>
--
PostgreSQL.org Major Contributor
Command Prompt, Inc: http://www.commandprompt.com/ - 509.416.6579
Consulting, Training, Support, Custom Development, Engineering
http://twitter.com/cmdpromptinc | http://identi.ca/commandprompt
^ permalink raw reply [nested|flat] 4+ messages in thread
* Re: XFS vs Ext3, and schedulers, for WAL
2010-10-06 23:11 XFS vs Ext3, and schedulers, for WAL Josh Berkus <josh@agliodbs.com>
2010-10-11 17:50 ` Re: XFS vs Ext3, and schedulers, for WAL Josh Berkus <josh@agliodbs.com>
2010-10-11 18:06 ` Re: XFS vs Ext3, and schedulers, for WAL Joshua D. Drake <jd@commandprompt.com>
@ 2010-10-11 18:59 ` Josh Berkus <josh@agliodbs.com>
0 siblings, 0 replies; 4+ messages in thread
From: Josh Berkus @ 2010-10-11 18:59 UTC (permalink / raw)
To: Joshua D. Drake <jd@commandprompt.com>; +Cc: pgsql-performance
> http://www.commandprompt.com/blogs/joshua_drake/2008/04/is_that_performance_i_smell_ext2_vs_ext3_on_...
>
> It doesn't cover XFS but it provides a decent and simple comparison on
> ext2/ext3 etc...
Yeah, it doesn't test actual log writing, though. Nor specific settings
even for those two filesystems. So it's still a mystery ...
--
-- Josh Berkus
PostgreSQL Experts Inc.
http://www.pgexperts.com
^ permalink raw reply [nested|flat] 4+ messages in thread
end of thread, other threads:[~2010-10-11 18:59 UTC | newest]
Thread overview: 4+ messages (download: mbox mbox.gz follow: Atom feed)
-- links below jump to the message on this page --
2010-10-06 23:11 XFS vs Ext3, and schedulers, for WAL Josh Berkus <josh@agliodbs.com>
2010-10-11 17:50 ` Josh Berkus <josh@agliodbs.com>
2010-10-11 18:06 ` Joshua D. Drake <jd@commandprompt.com>
2010-10-11 18:59 ` Josh Berkus <josh@agliodbs.com>
This inbox is served by DDX for PostgreSQL; see mirroring instructions
for how to clone and mirror all data and code used for this inbox