From: Wu Fengguang <fengguang.wu@intel.com>
To: Richard Kennedy <richard@rsk.demon.co.uk>
Cc: Dave Chinner <david@fromorbit.com>, Jan Kara <jack@suse.cz>,
Andrew Morton <akpm@linux-foundation.org>,
Peter Zijlstra <a.p.zijlstra@chello.nl>,
Hugh Dickins <hughd@google.com>, Rik van Riel <riel@redhat.com>,
LKML <linux-kernel@vger.kernel.org>,
Linux Memory Management List <linux-mm@kvack.org>,
"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>
Subject: Re: [PATCH 4/4] writeback: reduce per-bdi dirty threshold ramp up time
Date: Thu, 14 Apr 2011 22:08:17 +0800 [thread overview]
Message-ID: <20110414140817.GA29926@localhost> (raw)
In-Reply-To: <20110414134940.GA19392@localhost>
[-- Attachment #1: Type: text/plain, Size: 930 bytes --]
> > I'm only testing on a desktop with 2 drives. I use a simple test to
> > write 2gb to sda then 2gb to sdb while recording the threshold values.
> > On 2.6.39-rc3, after the 2nd write starts it take approx 90 seconds for
> > sda's threshold value to drop from its maximum to minimum and sdb's to
> > rise from min to max. So this seems much too slow for normal desktop
> > workloads.
>
> Yes.
>
> > I haven't tested with this patch on 2.6.39-rc3 yet, but I'm just about
> > to set that up.
>
> It will sure help, but the problem is now the low-memory NAS servers..
>
> Fortunately my patchset could make the dirty pages ramp up much more
> fast than the ramp up speed of the per-bdi threshold, and is also less
> sensitive to the fluctuations of per-bdi thresholds in JBOD setup.
Look at the attached graph. You cannot notice an obvious "rampup"
stage in the number of dirty pages (red line) at all :)
Thanks,
Fengguang
[-- Attachment #2: balance_dirty_pages-pages.png --]
[-- Type: image/png, Size: 81675 bytes --]
next prev parent reply other threads:[~2011-04-14 14:08 UTC|newest]
Thread overview: 62+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-04-13 8:59 [PATCH 0/4] trivial writeback fixes Wu Fengguang
2011-04-13 8:59 ` Wu Fengguang
2011-04-13 8:59 ` [PATCH 1/4] writeback: add bdi_dirty_limit() kernel-doc Wu Fengguang
2011-04-13 8:59 ` Wu Fengguang
2011-04-13 8:59 ` Wu Fengguang
2011-04-13 21:47 ` Jan Kara
2011-04-13 21:47 ` Jan Kara
2011-04-13 8:59 ` [PATCH 2/4] writeback: avoid duplicate balance_dirty_pages_ratelimited() calls Wu Fengguang
2011-04-13 8:59 ` Wu Fengguang
2011-04-13 8:59 ` Wu Fengguang
2011-04-13 21:53 ` Jan Kara
2011-04-13 21:53 ` Jan Kara
2011-04-14 0:30 ` Wu Fengguang
2011-04-14 0:30 ` Wu Fengguang
2011-04-14 10:20 ` Jan Kara
2011-04-14 10:20 ` Jan Kara
2011-04-13 8:59 ` [PATCH 3/4] writeback: skip balance_dirty_pages() for in-memory fs Wu Fengguang
2011-04-13 8:59 ` Wu Fengguang
2011-04-13 8:59 ` Wu Fengguang
2011-04-13 21:54 ` Jan Kara
2011-04-13 21:54 ` Jan Kara
2011-04-13 8:59 ` [PATCH 4/4] writeback: reduce per-bdi dirty threshold ramp up time Wu Fengguang
2011-04-13 8:59 ` Wu Fengguang
2011-04-13 8:59 ` Wu Fengguang
2011-04-13 22:04 ` Jan Kara
2011-04-13 22:04 ` Jan Kara
2011-04-13 23:31 ` Wu Fengguang
2011-04-13 23:31 ` Wu Fengguang
2011-04-13 23:52 ` Dave Chinner
2011-04-13 23:52 ` Dave Chinner
2011-04-14 0:23 ` Wu Fengguang
2011-04-14 0:23 ` Wu Fengguang
2011-04-14 10:36 ` Richard Kennedy
2011-04-14 10:36 ` Richard Kennedy
2011-04-14 13:49 ` Wu Fengguang
2011-04-14 13:49 ` Wu Fengguang
2011-04-14 14:08 ` Wu Fengguang [this message]
2011-04-14 15:14 ` Wu Fengguang
2011-04-14 15:56 ` Wu Fengguang
2011-04-14 18:16 ` Jan Kara
2011-04-14 18:16 ` Jan Kara
2011-04-15 3:43 ` Wu Fengguang
2011-04-15 14:37 ` Wu Fengguang
2011-04-15 22:13 ` Jan Kara
2011-04-15 22:13 ` Jan Kara
2011-04-16 6:05 ` Wu Fengguang
2011-04-16 6:05 ` Wu Fengguang
2011-04-16 8:33 ` Peter Zijlstra
2011-04-16 8:33 ` Peter Zijlstra
2011-04-16 14:21 ` Wu Fengguang
2011-04-17 2:11 ` Wu Fengguang
2011-04-17 2:11 ` Wu Fengguang
2011-04-18 14:59 ` Jan Kara
2011-04-18 14:59 ` Jan Kara
2011-05-24 12:24 ` Peter Zijlstra
2011-05-24 12:24 ` Peter Zijlstra
2011-05-24 12:41 ` Peter Zijlstra
2011-05-24 12:41 ` Peter Zijlstra
2011-06-09 23:58 ` Jan Kara
2011-06-09 23:58 ` Jan Kara
2011-04-13 10:15 ` [PATCH 0/4] trivial writeback fixes Peter Zijlstra
2011-04-13 10:15 ` Peter Zijlstra
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=20110414140817.GA29926@localhost \
--to=fengguang.wu@intel.com \
--cc=a.p.zijlstra@chello.nl \
--cc=akpm@linux-foundation.org \
--cc=david@fromorbit.com \
--cc=hughd@google.com \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=richard@rsk.demon.co.uk \
--cc=riel@redhat.com \
/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.