From: Theodore Ts'o <tytso@mit.edu>
To: Jan Kara <jack@suse.cz>
Cc: Eric Sandeen <sandeen@redhat.com>,
Sedat Dilek <sedat.dilek@gmail.com>,
Ext4 Developers List <linux-ext4@vger.kernel.org>,
mszeredi@suse.cz
Subject: Re: jbd2: don't wake kjournald unnecessarily
Date: Wed, 30 Jan 2013 00:26:58 -0500 [thread overview]
Message-ID: <20130130052658.GE25006@thunk.org> (raw)
In-Reply-To: <20130123192911.GB21112@quack.suse.cz>
On Wed, Jan 23, 2013 at 08:29:11PM +0100, Jan Kara wrote:
> > old JBD: AIM7 jobs/min 97624.39; got 78193 jbd wakeups
> > new JBD: AIM7 jobs/min 85929.43; got 6306999 jbd wakeups, 6264684 extra wakeups
> Yeah, that's a lot. My guess would be *a lot* of processes are hanging in
> start_this_handle() and waiting for transaction commit. Each of them calls
> __log_start_commit() and things add up. Thanks for getting these numbers.
Yeah, wow. That would imply that there are a huge number of processes
that get hung up in start_this_handle(), and they are waking up the
journal before the kjournald has a chance to set T_LOCKED (since then
they would get blocked earlier in start_this_handle).
Given that, I wonder if the following change would actually help or
hurt things. Eric, would you be willing to ask your perf team to try
testing out these patches?
- Ted
next prev parent reply other threads:[~2013-01-30 5:27 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-19 23:44 jbd2: don't wake kjournald unnecessarily Sedat Dilek
2013-01-20 0:06 ` Sedat Dilek
2013-01-20 0:35 ` Sedat Dilek
2013-01-20 0:55 ` Sedat Dilek
2013-01-21 10:47 ` Jan Kara
2013-01-21 11:40 ` Sedat Dilek
2013-01-21 12:30 ` Sedat Dilek
2013-01-21 14:07 ` Jan Kara
2013-01-21 14:28 ` Sedat Dilek
2013-01-21 17:39 ` Miklos Szeredi
2013-01-21 23:04 ` Sedat Dilek
2013-01-21 23:11 ` Theodore Ts'o
2013-01-21 23:29 ` Sedat Dilek
2013-01-22 23:50 ` Jan Kara
2013-01-23 1:37 ` Eric Sandeen
2013-01-23 9:44 ` Jan Kara
2013-01-23 15:20 ` Eric Sandeen
2013-01-23 19:29 ` Jan Kara
2013-01-30 5:26 ` Theodore Ts'o [this message]
2013-01-30 5:39 ` [PATCH 1/2] " Theodore Ts'o
2013-01-30 5:39 ` [PATCH 2/2] jbd2: commit as soon as possible after log_start_commit Theodore Ts'o
2013-02-02 19:33 ` Andreas Dilger
2013-01-30 10:07 ` jbd2: don't wake kjournald unnecessarily Jan Kara
2013-01-30 10:29 ` Sedat Dilek
2013-01-30 10:41 ` Jan Kara
2013-01-21 12:02 ` Carlos Maiolino
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=20130130052658.GE25006@thunk.org \
--to=tytso@mit.edu \
--cc=jack@suse.cz \
--cc=linux-ext4@vger.kernel.org \
--cc=mszeredi@suse.cz \
--cc=sandeen@redhat.com \
--cc=sedat.dilek@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).