From: Dave Chinner <david@fromorbit.com>
To: Wu Fengguang <fengguang.wu@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Jan Kara <jack@suse.cz>, Mel Gorman <mel@csn.ul.ie>,
Christoph Hellwig <hch@infradead.org>,
"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
LKML <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 03/17] writeback: introduce writeback_control.inodes_cleaned
Date: Mon, 16 May 2011 09:50:21 +1000 [thread overview]
Message-ID: <20110515235021.GP19446@dastard> (raw)
In-Reply-To: <20110513033605.GC8016@localhost>
On Fri, May 13, 2011 at 11:36:05AM +0800, Wu Fengguang wrote:
> On Fri, May 13, 2011 at 06:44:20AM +0800, Dave Chinner wrote:
> > On Thu, May 12, 2011 at 09:57:09PM +0800, Wu Fengguang wrote:
> > > The flusher works on dirty inodes in batches, and may quit prematurely
> > > if the batch of inodes happen to be metadata-only dirtied: in this case
> > > wbc->nr_to_write won't be decreased at all, which stands for "no pages
> > > written" but also mis-interpreted as "no progress".
> > >
> > > So introduce writeback_control.inodes_cleaned to count the inodes get
> > > cleaned. A non-zero value means there are some progress on writeback,
> > > in which case more writeback can be tried.
> >
> > Why introduce a new field for this?
>
> Yeah sorry, but this is an intermediate field that will be removed in
> patch 14.
>
> > Just decrement nr_to_write for every write_inode() call made in
> > writeback_single_inode()....
>
> There are two problems
>
> - nr_to_write has always been "# of pages written" and writeback_sb_inodes()
> is actually making use of it to do page accounting in work->nr_pages.
Do we really care whether it's inodes or pages that are written? As
far as i can tell it doesn't, because writing inodes generally
requires more IO and so needs to be limited anyway.
You are already changing the definition of wbc->nr_to_write is per
writeback_single_inode() call anyway, so changing it to account for
indoe writeback as well is mostly irrelevant to the accounting.
> - write_inode() does not always succeed, and its return value is not
> reliable on every filesystem.. (I actually tried this approach in v1
> and found sync(1) hang on NFS)
So put the accounting in the post-write code in
writeback_single_inode() where we already check if the inode is
still dirty or not. Splitting per-inode post-write processing
between writeback_single_inode and the higher level code is cludgy -
I'd much prefer it done in only one place.
Cheers,
Dave.
--
Dave Chinner
david@fromorbit.com
next prev parent reply other threads:[~2011-05-15 23:50 UTC|newest]
Thread overview: 56+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-05-12 13:57 [PATCH 00/17] writeback fixes and cleanups for 2.6.40 (v2) Wu Fengguang
2011-05-12 13:57 ` [PATCH 01/17] writeback: introduce .tagged_sync for the WB_SYNC_NONE sync stage Wu Fengguang
2011-05-12 22:40 ` Dave Chinner
2011-05-13 2:56 ` Wu Fengguang
2011-05-13 10:17 ` Christoph Hellwig
2011-05-15 23:43 ` Dave Chinner
2011-05-16 5:39 ` Wu Fengguang
2011-05-19 21:17 ` Wu Fengguang
2011-05-12 13:57 ` [PATCH 02/17] writeback: update dirtied_when for synced inode to prevent livelock Wu Fengguang
2011-05-12 22:42 ` Dave Chinner
2011-05-13 3:08 ` Wu Fengguang
2011-05-19 21:31 ` Wu Fengguang
2011-05-23 13:14 ` Jan Kara
2011-05-24 3:03 ` Wu Fengguang
2011-05-12 13:57 ` [PATCH 03/17] writeback: introduce writeback_control.inodes_cleaned Wu Fengguang
2011-05-12 22:44 ` Dave Chinner
2011-05-13 3:36 ` Wu Fengguang
2011-05-15 23:50 ` Dave Chinner [this message]
2011-05-16 10:40 ` Christoph Hellwig
2011-05-16 11:14 ` Wu Fengguang
2011-05-12 13:57 ` [PATCH 04/17] writeback: try more writeback as long as something was written Wu Fengguang
2011-05-12 13:57 ` [PATCH 05/17] writeback: the kupdate expire timestamp should be a moving target Wu Fengguang
2011-05-12 13:57 ` [PATCH 06/17] writeback: sync expired inodes first in background writeback Wu Fengguang
2011-05-12 22:55 ` Dave Chinner
2011-05-16 13:00 ` Wu Fengguang
2011-05-12 13:57 ` [PATCH 07/17] writeback: refill b_io iff empty Wu Fengguang
2011-05-12 13:57 ` [PATCH 08/17] writeback: split inode_wb_list_lock into bdi_writeback.list_lock Wu Fengguang
2011-05-12 13:57 ` [PATCH 09/17] writeback: elevate queue_io() into wb_writeback() Wu Fengguang
2011-05-12 13:57 ` [PATCH 10/17] writeback: avoid extra sync work at enqueue time Wu Fengguang
2011-05-12 13:57 ` [PATCH 11/17] writeback: add bdi_dirty_limit() kernel-doc Wu Fengguang
2011-05-12 13:57 ` [PATCH 12/17] writeback: skip balance_dirty_pages() for in-memory fs Wu Fengguang
2011-05-16 10:43 ` Christoph Hellwig
2011-05-16 10:49 ` Wu Fengguang
2011-05-12 13:57 ` [PATCH 13/17] writeback: remove writeback_control.more_io Wu Fengguang
2011-05-12 14:25 ` Minchan Kim
2011-05-12 23:04 ` Dave Chinner
2011-05-13 5:03 ` Wu Fengguang
2011-05-15 23:54 ` Dave Chinner
2011-05-12 13:57 ` [PATCH 14/17] writeback: make writeback_control.nr_to_write straight Wu Fengguang
2011-05-12 14:56 ` Jan Kara
2011-05-12 23:18 ` Dave Chinner
2011-05-13 5:28 ` Wu Fengguang
2011-05-16 0:12 ` Dave Chinner
2011-05-16 12:05 ` Wu Fengguang
2011-05-12 13:57 ` [PATCH 15/17] writeback: remove .nonblocking and .encountered_congestion Wu Fengguang
2011-05-12 13:57 ` [PATCH 16/17] writeback: trace event writeback_single_inode Wu Fengguang
2011-05-12 23:20 ` Dave Chinner
2011-05-13 5:37 ` Wu Fengguang
2011-05-16 0:14 ` Dave Chinner
2011-05-16 12:21 ` Wu Fengguang
2011-05-12 13:57 ` [PATCH 17/17] writeback: trace event writeback_queue_io Wu Fengguang
-- strict thread matches above, loose matches on Subject: below --
2011-05-06 3:08 [PATCH 00/17] writeback fixes and cleanups for 2.6.40 Wu Fengguang
2011-05-06 3:08 ` [PATCH 03/17] writeback: introduce writeback_control.inodes_cleaned Wu Fengguang
2011-05-06 14:36 ` Jan Kara
2011-05-10 2:23 ` Wu Fengguang
2011-05-10 13:52 ` Jan Kara
2011-05-10 15:00 ` 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=20110515235021.GP19446@dastard \
--to=david@fromorbit.com \
--cc=akpm@linux-foundation.org \
--cc=fengguang.wu@intel.com \
--cc=hch@infradead.org \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mel@csn.ul.ie \
/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).