From: NeilBrown <neilb@suse.de>
To: Marco Schindler <marco.schindler@gmail.com>
Cc: linux-raid@vger.kernel.org
Subject: Re: frequent disk activity with mdadm-3.3
Date: Mon, 15 Sep 2014 10:18:30 +1000 [thread overview]
Message-ID: <20140915101830.3c85d423@notabene.brown> (raw)
In-Reply-To: <BDDC2624-8578-4720-A526-56EFDFBE26C4@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 2252 bytes --]
On Fri, 12 Sep 2014 14:15:35 +0200 Marco Schindler
<marco.schindler@gmail.com> wrote:
> ok, that’s interesting.
> the process id is _not_ mdadm daemon and it looks like the spindown itself is triggering the process.
>
> ps ax | grep mdadm
> 28956 ? Ss 0:00 mdadm --monitor --scan --daemonise --pid-file /var/run/mdadm.pid --syslog
>
> grep sda /var/log/messages
> Sep 12 13:55:04 alina spindown: sda is now inactive.
> Sep 12 13:55:09 alina kernel: mdadm(29737): READ block 3907028992 on sda (8 sectors)
> Sep 12 13:55:17 alina kernel: mdadm(29737): READ block 3907029152 on sda (8 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 0 on sda (8 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 8 on sda (8 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 8 on sda (8 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 3907029167 on sda (1 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 3907029166 on sda (1 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 0 on sda (1 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 0 on sda (1 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 3907029152 on sda (8 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 0 on sda (8 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 8 on sda (8 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 8 on sda (8 sectors)
> Sep 12 13:55:26 alina kernel: mdadm(29737): READ block 8 on sda (8 sectors)
> Sep 12 13:56:12 alina spindown: sda is now active.
It would help to get "udevadm monitor" info to correlate with this.
Presumably some uevent is generated when the spindown happens. udev might
respond to this by reading from the device, which defeats the purpose...
>
> here’s the output of blktrace -d /dev/sda during that time.
> https://dl.dropboxusercontent.com/u/3464720/blktrace.tar.bz2
That suggest that something is reading the metadata from the device almost
constantly. Mostly a 'kworker' thread. I don't know what would cause that.
Let's look at the 'udevadm monitor' trace first and see what that shows.
NeilBrown
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 828 bytes --]
next prev parent reply other threads:[~2014-09-15 0:18 UTC|newest]
Thread overview: 10+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-09-11 22:05 frequent disk activity with mdadm-3.3 Marco Schindler
2014-09-11 22:24 ` NeilBrown
2014-09-11 22:45 ` Marco Schindler
2014-09-12 12:15 ` Marco Schindler
2014-09-15 0:18 ` NeilBrown [this message]
2014-09-15 10:52 ` Marco Schindler
2014-09-18 10:03 ` NeilBrown
2014-09-18 10:38 ` Marco Schindler
2014-09-18 11:09 ` NeilBrown
2014-09-18 11:22 ` Marco Schindler
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=20140915101830.3c85d423@notabene.brown \
--to=neilb@suse.de \
--cc=linux-raid@vger.kernel.org \
--cc=marco.schindler@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).