From: Wu Fengguang <fengguang.wu@intel.com>
To: Jan Kara <jack@suse.cz>
Cc: "linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
Dave Chinner <david@fromorbit.com>,
Christoph Hellwig <hch@infradead.org>,
Andrew Morton <akpm@linux-foundation.org>,
LKML <linux-kernel@vger.kernel.org>,
"Tang, Feng" <feng.tang@intel.com>
Subject: Re: [PATCH 0/7] writeback: avoid touching dirtied_when on blocked inodes
Date: Sat, 22 Oct 2011 14:59:26 +0800 [thread overview]
Message-ID: <20111022065926.GA31074@localhost> (raw)
In-Reply-To: <20111022053851.GA23033@localhost>
[-- Attachment #1: Type: text/plain, Size: 551 bytes --]
> In general it looks better we first root case the "decreasing wrote
> pages by writeback_single_inode() over time" problem before looking
> into further steps..
The problem shows up in many of the regression cases. For example,
the thresh=1G/ext4-100dd case with patches 1-4 applied will not only
see nr_writeback occasionally dropped low (bdi_dirty_state-8:0.png),
but also see repeated pattern of nr_wrote by writeback_single_inode()
slowly decreasing to 0 during some period of dozens of seconds
(writeback_single_inode.png).
Thanks,
Fengguang
[-- Attachment #2: bdi_dirty_state-8:0.png --]
[-- Type: image/png, Size: 42728 bytes --]
[-- Attachment #3: balance_dirty_pages-pages.png --]
[-- Type: image/png, Size: 85151 bytes --]
[-- Attachment #4: writeback_single_inode.png --]
[-- Type: image/png, Size: 52548 bytes --]
[-- Attachment #5: iostat-misc.png --]
[-- Type: image/png, Size: 102612 bytes --]
next prev parent reply other threads:[~2011-10-22 6:59 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-10-20 15:22 [PATCH 0/7] writeback: avoid touching dirtied_when on blocked inodes Wu Fengguang
2011-10-20 15:22 ` [PATCH 1/7] writeback: introduce queue b_more_io_wait Wu Fengguang
2011-10-20 23:23 ` Jan Kara
2011-10-20 15:22 ` [PATCH 2/7] writeback: avoid redirtying when ->write_inode failed to clear I_DIRTY Wu Fengguang
2011-10-20 23:24 ` Jan Kara
2011-10-20 15:22 ` [PATCH 3/7] writeback: update wb->last_active on written pages/inodes Wu Fengguang
2011-10-20 15:22 ` [PATCH 4/7] writeback: Retry kupdate work early if we need to retry some inode writeback Wu Fengguang
2011-10-20 15:22 ` [PATCH 5/7] writeback: requeue_io_wait() on pages_skipped inode Wu Fengguang
2011-10-20 23:25 ` Jan Kara
2011-10-20 15:22 ` [PATCH 6/7] writeback: requeue_io_wait() on blocked inode Wu Fengguang
2011-10-20 23:31 ` Jan Kara
2011-10-20 15:22 ` [PATCH 7/7] writeback: requeue_io_wait() when failed to grab superblock Wu Fengguang
2011-10-20 23:25 ` Jan Kara
2011-10-20 23:21 ` [PATCH 0/7] writeback: avoid touching dirtied_when on blocked inodes Jan Kara
2011-10-21 10:40 ` Wu Fengguang
2011-10-21 19:54 ` Jan Kara
2011-10-22 3:11 ` Wu Fengguang
2011-10-22 5:38 ` Wu Fengguang
2011-10-22 6:59 ` Wu Fengguang [this message]
2011-10-22 7:07 ` Wu Fengguang
2011-10-22 7:46 ` Wu Fengguang
2011-10-22 4:46 ` 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=20111022065926.GA31074@localhost \
--to=fengguang.wu@intel.com \
--cc=akpm@linux-foundation.org \
--cc=david@fromorbit.com \
--cc=feng.tang@intel.com \
--cc=hch@infradead.org \
--cc=jack@suse.cz \
--cc=linux-fsdevel@vger.kernel.org \
--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 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).