From: Dave Chinner <david@fromorbit.com>
To: Eric Sandeen <sandeen@sandeen.net>
Cc: Martin Steigerwald <Martin@lichtvoll.de>,
linux-xfs@oss.sgi.com, linux-raid@vger.kernel.org,
Alan Piszcz <ap@solarrain.com>xfs@oss.sgi.com
Subject: Re: 12x performance drop on md/linux+sw raid1 due to barriers [xfs]
Date: Mon, 15 Dec 2008 10:36:17 +1100 [thread overview]
Message-ID: <20081214233617.GD32301@disturbed> (raw)
In-Reply-To: <4943F37B.8080405@sandeen.net>
On Sat, Dec 13, 2008 at 11:40:11AM -0600, Eric Sandeen wrote:
> Martin Steigerwald wrote:
>
> > At the moment it appears to me that disabling write cache may often give
> > more performance than using barriers. And this doesn't match my
> > expectation of write barriers as a feature that enhances performance.
>
> Why do you have that expectation? I've never seen barriers advertised
> as enhancing performance. :)
>
> I do wonder why barriers on, write cache off is so slow; I'd have
> thought the barriers were a no-op. Maybe I'm missing something.
Barriers still enforce ordering in this case, so it affects the
elevator algorithm....
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
WARNING: multiple messages have this Message-ID (diff)
From: Dave Chinner <david@fromorbit.com>
To: Eric Sandeen <sandeen@sandeen.net>
Cc: linux-xfs@oss.sgi.com, Alan Piszcz <ap@solarrain.com>,
linux-raid@vger.kernel.orgxfs@oss.sgi.com
Subject: Re: 12x performance drop on md/linux+sw raid1 due to barriers [xfs]
Date: Mon, 15 Dec 2008 10:36:17 +1100 [thread overview]
Message-ID: <20081214233617.GD32301@disturbed> (raw)
In-Reply-To: <4943F37B.8080405@sandeen.net>
On Sat, Dec 13, 2008 at 11:40:11AM -0600, Eric Sandeen wrote:
> Martin Steigerwald wrote:
>
> > At the moment it appears to me that disabling write cache may often give
> > more performance than using barriers. And this doesn't match my
> > expectation of write barriers as a feature that enhances performance.
>
> Why do you have that expectation? I've never seen barriers advertised
> as enhancing performance. :)
>
> I do wonder why barriers on, write cache off is so slow; I'd have
> thought the barriers were a no-op. Maybe I'm missing something.
Barriers still enforce ordering in this case, so it affects the
elevator algorithm....
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs
next prev parent reply other threads:[~2008-12-14 23:36 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-12-06 14:28 12x performance drop on md/linux+sw raid1 due to barriers [xfs] Justin Piszcz
2008-12-06 14:28 ` Justin Piszcz
2008-12-06 15:36 ` Eric Sandeen
2008-12-06 20:35 ` Redeeman
2008-12-06 20:35 ` Redeeman
2008-12-13 12:54 ` Justin Piszcz
2008-12-13 12:54 ` Justin Piszcz
2008-12-13 17:26 ` Martin Steigerwald
2008-12-13 17:26 ` Martin Steigerwald
2008-12-13 17:40 ` Eric Sandeen
2008-12-13 17:40 ` Eric Sandeen
2008-12-14 3:31 ` Redeeman
2008-12-14 3:31 ` Redeeman
2008-12-14 14:02 ` Peter Grandi
2008-12-14 14:02 ` Peter Grandi
2008-12-14 18:12 ` Martin Steigerwald
2008-12-14 18:12 ` Martin Steigerwald
2008-12-14 22:02 ` Peter Grandi
2008-12-14 22:02 ` Peter Grandi
2008-12-15 18:48 ` Martin Steigerwald
2008-12-15 22:50 ` Peter Grandi
2009-02-18 22:14 ` Leon Woestenberg
2009-02-18 22:24 ` Eric Sandeen
2009-02-18 23:09 ` Ralf Liebenow
2009-02-18 23:19 ` Eric Sandeen
2009-02-20 19:19 ` Peter Grandi
2008-12-15 22:38 ` Dave Chinner
2008-12-15 22:38 ` Dave Chinner
2008-12-16 9:39 ` Martin Steigerwald
2008-12-16 9:39 ` Martin Steigerwald
2008-12-16 20:57 ` Peter Grandi
2008-12-16 23:14 ` Dave Chinner
2008-12-16 23:14 ` Dave Chinner
2008-12-17 21:40 ` Bill Davidsen
2008-12-17 21:40 ` Bill Davidsen
2008-12-18 8:20 ` Leon Woestenberg
2008-12-18 23:33 ` Bill Davidsen
2008-12-21 19:16 ` Peter Grandi
2008-12-22 13:19 ` Leon Woestenberg
2008-12-22 13:19 ` Leon Woestenberg
2008-12-18 22:26 ` Dave Chinner
2008-12-18 22:26 ` Dave Chinner
2008-12-20 14:06 ` Peter Grandi
2008-12-14 18:35 ` Martin Steigerwald
2008-12-14 18:35 ` Martin Steigerwald
2008-12-14 17:49 ` Martin Steigerwald
2008-12-14 17:49 ` Martin Steigerwald
2008-12-14 23:36 ` Dave Chinner [this message]
2008-12-14 23:36 ` Dave Chinner
2008-12-14 23:55 ` Eric Sandeen
2008-12-13 18:01 ` David Lethe
2008-12-13 18:01 ` David Lethe
2008-12-06 18:42 ` Peter Grandi
2008-12-11 0:20 ` Bill Davidsen
2008-12-11 0:20 ` Bill Davidsen
2008-12-11 9:18 ` Justin Piszcz
2008-12-11 9:18 ` Justin Piszcz
2008-12-11 9:24 ` Justin Piszcz
2008-12-11 9:24 ` Justin Piszcz
-- strict thread matches above, loose matches on Subject: below --
2008-12-14 18:33 Martin Steigerwald
2008-12-14 18:33 ` Martin Steigerwald
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20081214233617.GD32301@disturbed \
--to=david@fromorbit.com \
--cc=Martin@lichtvoll.de \
--cc=ap@solarrain.com \
--cc=linux-raid@vger.kernel.org \
--cc=linux-xfs@oss.sgi.com \
--cc=sandeen@sandeen.net \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.