All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <axboe@suse.de>
To: Lorenzo Allegrucci <l_allegrucci@despammed.com>
Cc: Andrew Morton <akpm@osdl.org>, linux-kernel@vger.kernel.org
Subject: Re: 2.6.6-mm5 oops mounting ext3 or reiserfs with -o barrier
Date: Sun, 23 May 2004 17:45:24 +0200	[thread overview]
Message-ID: <20040523154524.GR1952@suse.de> (raw)
In-Reply-To: <200405231732.15600.l_allegrucci@despammed.com>

On Sun, May 23 2004, Lorenzo Allegrucci wrote:
> On Sunday 23 May 2004 12:03, Jens Axboe wrote:
> 
> > Here's a rolled up updated version that tries to get async notification
> > of missing barrier support working as well. reiser currently doesn't
> > cope with that correctly (fails mount), ext3 seems to but gets stuck.
> > Andrew has that fixed already, I think :-)
> >
> > Lorenzo, can you test this on top of 2.6.6-mm5?
> 
> Problem fixed, but there is some performance regression
> 
> ext3 (default)
> untar		read		copy		remove
> 0m53.861s	0m24.942s	1m30.164s	0m20.664s
> 0m7.132s	0m1.191s	0m0.766s	0m0.076s
> 0m5.807s	0m3.345s	0m9.996s	0m1.719s
> 
> ext3 (-o barrier=1)
> untar		read		copy		remove
> 0m52.117s	0m28.502s	1m51.153s	0m25.561s
> 0m7.231s	0m1.209s	0m0.738s	0m0.071s
> 0m6.117s	0m3.191s	0m9.347s	0m1.635s

Not sure what you mean here, but yes of course -o barrier=1 is going to
be slower than default + write back caching. What you should compare is
without barrier support and hdparm -W0 /dev/hdX, if -o barrier=1 with
caching on is slower then that's a regression :-)

-- 
Jens Axboe


  reply	other threads:[~2004-05-23 15:45 UTC|newest]

Thread overview: 17+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2004-05-22 19:07 2.6.6-mm5 oops mounting ext3 or reiserfs with -o barrier Lorenzo Allegrucci
2004-05-22 19:21 ` Andrew Morton
2004-05-22 21:20   ` Jens Axboe
2004-05-22 21:30     ` Jens Axboe
2004-05-23  8:58       ` Lorenzo Allegrucci
2004-05-23  9:11         ` Jens Axboe
2004-05-23 10:03           ` Jens Axboe
2004-05-23 15:32             ` Lorenzo Allegrucci
2004-05-23 15:45               ` Jens Axboe [this message]
2004-05-23 16:43                 ` Lorenzo Allegrucci
2004-05-23 16:56                   ` Jens Axboe
2004-05-23 17:17                     ` Lorenzo Allegrucci
2004-05-23 17:31                       ` Jens Axboe
2004-05-23 20:41                         ` Lorenzo Allegrucci
2004-05-23  8:27 ` Jens Axboe
2004-05-23 10:37   ` Kurt Garloff
2004-05-23 10:56     ` Jens Axboe

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=20040523154524.GR1952@suse.de \
    --to=axboe@suse.de \
    --cc=akpm@osdl.org \
    --cc=l_allegrucci@despammed.com \
    --cc=linux-kernel@vger.kernel.org \
    /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.