From: David Chinner <dgc@sgi.com>
To: Fengguang Wu <wfg@mail.ustc.edu.cn>
Cc: Andrew Morton <akpm@osdl.org>,
linux-kernel@vger.kernel.org, David Chinner <dgc@sgi.com>,
Ken Chen <kenchen@google.com>,
Andrew Morton <akpm@linux-foundation.org>,
Michael Rubin <mrubin@google.com>
Subject: Re: [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io
Date: Wed, 3 Oct 2007 07:47:45 +1000 [thread overview]
Message-ID: <20071002214736.GJ995458@sgi.com> (raw)
In-Reply-To: <20071002090254.987182999@mail.ustc.edu.cn>
On Tue, Oct 02, 2007 at 04:41:48PM +0800, Fengguang Wu wrote:
> wbc.pages_skipped = 0;
> @@ -560,8 +561,9 @@ static void background_writeout(unsigned
> min_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
> if (wbc.nr_to_write > 0 || wbc.pages_skipped > 0) {
> /* Wrote less than expected */
> - congestion_wait(WRITE, HZ/10);
> - if (!wbc.encountered_congestion)
> + if (wbc.encountered_congestion || wbc.more_io)
> + congestion_wait(WRITE, HZ/10);
> + else
> break;
> }
Why do you call congestion_wait() if there is more I/O to issue? If
we have a fast filesystem, this might cause the device queues to
fill, then drain on congestion_wait(), then fill again, etc. i.e. we
will have trouble keeping the queues full, right?
Cheers,
Dave.
--
Dave Chinner
Principal Engineer
SGI Australian Software Group
next prev parent reply other threads:[~2007-10-02 21:48 UTC|newest]
Thread overview: 19+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20071002084143.110486039@mail.ustc.edu.cn>
2007-10-02 8:41 ` [PATCH 0/5] sluggish writeback fixes Fengguang Wu
2007-10-03 11:04 ` Martin Knoblauch
[not found] ` <20071002090254.489150786@mail.ustc.edu.cn>
2007-10-02 8:41 ` [PATCH 1/5] revert check_dirty_inode_list.patch Fengguang Wu
[not found] ` <20071002090254.596842343@mail.ustc.edu.cn>
2007-10-02 8:41 ` [PATCH 2/5] writeback: fix time ordering of the per superblock inode lists 8 Fengguang Wu
[not found] ` <20071002090254.728493507@mail.ustc.edu.cn>
2007-10-02 8:41 ` [PATCH 3/5] writeback: fix ntfs with sb_has_dirty_inodes() Fengguang Wu
[not found] ` <20071002090254.987182999@mail.ustc.edu.cn>
2007-10-02 8:41 ` [PATCH 5/5] writeback: introduce writeback_control.more_io to indicate more io Fengguang Wu
2007-10-02 21:47 ` David Chinner [this message]
[not found] ` <20071003013439.GA6501@mail.ustc.edu.cn>
2007-10-03 1:34 ` Fengguang Wu
2007-10-03 2:41 ` David Chinner
[not found] ` <20071004022133.GA6244@mail.ustc.edu.cn>
2007-10-04 2:21 ` Fengguang Wu
2007-10-04 5:03 ` David Chinner
[not found] ` <20071005033652.GA6448@mail.ustc.edu.cn>
2007-10-05 3:36 ` Fengguang Wu
2007-10-05 7:41 ` David Chinner
[not found] ` <20071005115508.GA9998@mail.ustc.edu.cn>
2007-10-05 11:55 ` Fengguang Wu
[not found] ` <20071002090254.873023041@mail.ustc.edu.cn>
2007-10-02 8:41 ` [PATCH 4/5] writeback: remove pages_skipped accounting in __block_write_full_page() Fengguang Wu
2007-10-04 21:26 ` Andrew Morton
2007-10-02 21:55 ` David Chinner
[not found] ` <20071003014333.GB6501@mail.ustc.edu.cn>
2007-10-03 1:43 ` Fengguang Wu
2007-10-03 2:22 ` David Chinner
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=20071002214736.GJ995458@sgi.com \
--to=dgc@sgi.com \
--cc=akpm@linux-foundation.org \
--cc=akpm@osdl.org \
--cc=kenchen@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mrubin@google.com \
--cc=wfg@mail.ustc.edu.cn \
/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