linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Wu Fengguang <fengguang.wu@intel.com>
To: Jan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@infradead.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Mel Gorman <mel@linux.vnet.ibm.com>,
	Dave Chinner <david@fromorbit.com>,
	Trond Myklebust <Trond.Myklebust@netapp.com>,
	Itaru Kitayama <kitayama@cl.bb4u.ne.jp>,
	Minchan Kim <minchan.kim@gmail.com>,
	LKML <linux-kernel@vger.kernel.org>,
	"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
	Linux Memory Management List <linux-mm@kvack.org>
Subject: Re: [PATCH 5/6] writeback: try more writeback as long as something was written
Date: Fri, 22 Apr 2011 10:32:26 +0800	[thread overview]
Message-ID: <20110422023226.GB6199@localhost> (raw)
In-Reply-To: <20110421164154.GC4476@quack.suse.cz>

On Fri, Apr 22, 2011 at 12:41:54AM +0800, Jan Kara wrote:
> On Thu 21-04-11 14:05:56, Wu Fengguang wrote:
> > On Thu, Apr 21, 2011 at 12:39:40PM +0800, Christoph Hellwig wrote:
> > > On Thu, Apr 21, 2011 at 11:33:25AM +0800, Wu Fengguang wrote:
> > > > I collected the writeback_single_inode() traces (patch attached for
> > > > your reference) each for several test runs, and find much more
> > > > I_DIRTY_PAGES after patchset. Dave, do you know why there are so many
> > > > I_DIRTY_PAGES (or radix tag) remained after the XFS ->writepages() call,
> > > > even for small files?
> > > 
> > > What is your defintion of a small file?  As soon as it has multiple
> > > extents or holes there's absolutely no way to clean it with a single
> > > writepage call.
> > 
> > It's writing a kernel source tree to XFS. You can find in the below
> > trace that it often leaves more dirty pages behind (indicated by the
> > I_DIRTY_PAGES flag) after writing as less as 1 page (indicated by the
> > wrote=1 field).
>   As Dave said, it's probably just a race since XFS redirties the inode on
> IO completion. So I think the inodes are just small so they have only a few
> dirty pages so you don't have much to write and they are written and
> redirtied before you check the I_DIRTY flags. You could use radix tree
> dirty tag to verify whether there are really dirty pages or not...

Yeah, Dave and Christoph root caused it in the other email -- XFS sets
I_DIRTY which accidentally sets I_DIRTY_PAGES. We can safely bet there
are no real dirty pages -- otherwise it would have turned up as
performance regressions.

>   BTW a quick check of kernel tree shows the following distribution of
> sizes (in KB):
>   Count KB  Cumulative Percent
>     257 0   0.9%
>   13309 4   45%
>    5553 8   63%
>    2997 12  73%
>    1879 16  80%
>    1275 20  83%
>     987 24  87%
>     685 28  89%
>     540 32  91%
>     387 36  ...
>     309 40
>     264 44
>     249 48
>     170 52
>     143 56
>     144 60
>     132 64
>     100 68
>     ...
> Total 30155
> 
> And the distribution of your 'wrote=xxx' roughly corresponds to this...

Nice numbers! How do you manage to account them? :)

Thanks,
Fengguang

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  reply	other threads:[~2011-04-22  2:32 UTC|newest]

Thread overview: 63+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-04-19  3:00 [PATCH 0/6] writeback: moving expire targets for background/kupdate works Wu Fengguang
2011-04-19  3:00 ` [PATCH 1/6] writeback: pass writeback_control down to move_expired_inodes() Wu Fengguang
2011-04-19  3:00 ` [PATCH 2/6] writeback: the kupdate expire timestamp should be a moving target Wu Fengguang
2011-04-19  7:02   ` Dave Chinner
2011-04-19  7:20     ` Wu Fengguang
2011-04-19  9:31       ` Jan Kara
2011-04-19  3:00 ` [PATCH 3/6] writeback: sync expired inodes first in background writeback Wu Fengguang
2011-04-19  7:35   ` Dave Chinner
2011-04-19  9:57     ` Jan Kara
2011-04-19 12:56       ` Wu Fengguang
2011-04-19 13:46         ` Wu Fengguang
2011-04-20  1:21         ` Dave Chinner
2011-04-20  2:53           ` Wu Fengguang
2011-04-21  0:45             ` Dave Chinner
2011-04-21  2:06               ` Wu Fengguang
2011-04-21  3:01                 ` Dave Chinner
2011-04-21  3:59                   ` Wu Fengguang
2011-04-21  4:10                     ` Wu Fengguang
2011-04-21  4:36                       ` Christoph Hellwig
2011-04-21  6:36                       ` Dave Chinner
2011-04-21 16:04                       ` Jan Kara
2011-04-22  2:24                         ` Wu Fengguang
2011-04-22 21:12                           ` Jan Kara
2011-04-26  5:37                             ` Wu Fengguang
2011-04-26 14:30                               ` Jan Kara
2011-04-20  7:38           ` Wu Fengguang
2011-04-21  1:01             ` Dave Chinner
2011-04-21  1:47               ` Wu Fengguang
2011-04-19  3:00 ` [PATCH 4/6] writeback: introduce writeback_control.inodes_cleaned Wu Fengguang
2011-04-19  9:47   ` Jan Kara
2011-04-19  3:00 ` [PATCH 5/6] writeback: try more writeback as long as something was written Wu Fengguang
2011-04-19 10:20   ` Jan Kara
2011-04-19 11:16     ` Wu Fengguang
2011-04-19 21:10       ` Jan Kara
2011-04-20  7:50         ` Wu Fengguang
2011-04-20 15:22           ` Jan Kara
2011-04-21  3:33             ` Wu Fengguang
2011-04-21  4:39               ` Christoph Hellwig
2011-04-21  6:05                 ` Wu Fengguang
2011-04-21 16:41                   ` Jan Kara
2011-04-22  2:32                     ` Wu Fengguang [this message]
2011-04-22 21:23                       ` Jan Kara
2011-04-21  7:09               ` Dave Chinner
2011-04-21  7:14                 ` Christoph Hellwig
2011-04-21  7:52                   ` Dave Chinner
2011-04-21  8:00                     ` Christoph Hellwig
2011-04-19  3:00 ` [PATCH 6/6] NFS: return -EAGAIN when skipped commit in nfs_commit_unstable_pages() Wu Fengguang
2011-04-19  3:29   ` Trond Myklebust
2011-04-19  3:55     ` Wu Fengguang
2011-04-21  4:40   ` Christoph Hellwig
2011-04-19  6:38 ` [PATCH 0/6] writeback: moving expire targets for background/kupdate works Dave Chinner
2011-04-19  8:02   ` Wu Fengguang
2011-04-21  4:34 ` Christoph Hellwig
2011-04-21  5:50   ` Wu Fengguang
2011-04-21  5:56     ` Christoph Hellwig
2011-04-21  6:07       ` Wu Fengguang
2011-04-21  7:17         ` Christoph Hellwig
2011-04-21 10:15           ` Wu Fengguang
  -- strict thread matches above, loose matches on Subject: below --
2010-07-22  5:09 [PATCH 0/6] [RFC] writeback: try to write older pages first Wu Fengguang
2010-07-22  5:09 ` [PATCH 5/6] writeback: try more writeback as long as something was written Wu Fengguang
2010-07-23 17:39   ` Jan Kara
2010-07-26 12:39     ` Wu Fengguang
2010-07-26 11:01   ` Mel Gorman
2010-07-26 11:39     ` Wu Fengguang

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=20110422023226.GB6199@localhost \
    --to=fengguang.wu@intel.com \
    --cc=Trond.Myklebust@netapp.com \
    --cc=akpm@linux-foundation.org \
    --cc=david@fromorbit.com \
    --cc=hch@infradead.org \
    --cc=jack@suse.cz \
    --cc=kitayama@cl.bb4u.ne.jp \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mel@linux.vnet.ibm.com \
    --cc=minchan.kim@gmail.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).