From: Jan Stilow <jstilow@mobileobjects.de>
To: linux-btrfs@vger.kernel.org
Subject: Re: Applications using fsync cause hangs for several seconds every few minutes
Date: Tue, 21 Jun 2011 13:15:30 +0200 [thread overview]
Message-ID: <4E007D52.4000509@mobileobjects.de> (raw)
Hello,
Nirbheek Chauhan <nirbheek <at> gentoo.org> writes:
> However, recently, perhaps with 2.6.39, or after I quickly started
> filling up my disk again, it has become impossible for me to work for
> long periods on my machine.
>
> Every few minutes, (I guess) when applications do fsync (firefox,
> xchat, vim, etc), all applications that use fsync() hang for several
> seconds, and applications that use general IO suffer extreme
> slowdowns. iotop shows various combinations of the processes listed
> below doing writes, and the total write as 2-3MB/s.
>
> [btrfs-dealloc-]
> [btrfs-submit-0]
> [btrfs-transacti]
> [btrfs-endio-wri]
> [flush-btrfs-1]
I'm using btrfs under a 2.6.39-ARCH kernel and run into the same issue.
In my case the [btrfs-submit-0] and [btrfs-transacti] shows up in iotop
and produce 99% of IO at the time a application is frozen. For something
like 10 to 30 seconds.
After a fresh boot everything runs quiet acceptable and goes worse over
the day. If I reboot the unmount process takes a lot of time something
up to 8 minutes. After the reboot everything is back to normal. At least
for a while.
I use snapshots on a daily base and have 20 active snapshots all the
time. Maybe this is the reason for the performance impact?
> What can I do to debug this issue? What other information should I
> supply? Could someone guide me on how to figure out why my machine is
> unusable now?
I have no solution for this problem. In fact a reboot helps me even if
only temporary. I also changed the IO scheduler, switched to laptop mode
and remounted the device. Neither of these helped.
Maybe someone else has any suggestion?
Thanks.
Jan Stilow
next reply other threads:[~2011-06-21 11:15 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2011-06-21 11:15 Jan Stilow [this message]
-- strict thread matches above, loose matches on Subject: below --
2011-08-09 21:29 Applications using fsync cause hangs for several seconds every few minutes Andrew Guertin
2011-08-12 1:13 ` Andrew Guertin
2011-08-18 14:38 ` Chris Mason
2011-08-20 17:18 ` Andrew Guertin
2011-08-17 14:24 ` Andrew Guertin
2011-08-17 14:29 ` Michael Cronenworth
2011-08-17 14:38 ` Andrew Guertin
2011-08-17 14:55 ` Dave
2011-08-18 2:41 ` Anand Jain
2011-08-18 6:44 ` youagree
2011-08-18 7:29 ` Andrew Guertin
2011-08-18 7:55 ` youagree
2011-08-18 11:45 ` Andrew Guertin
2011-08-19 9:58 ` Anand Jain
2011-08-18 7:41 ` Andrew Guertin
2011-08-18 6:47 ` Chris Samuel
2011-08-18 6:58 ` youagree
2011-08-19 7:34 ` Chris Samuel
2011-06-06 22:58 Nirbheek Chauhan
2011-07-18 17:37 ` Mck
2011-07-18 18:17 ` Josef Bacik
2011-07-20 20:59 ` Nirbheek Chauhan
2011-08-03 15:50 ` mck
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=4E007D52.4000509@mobileobjects.de \
--to=jstilow@mobileobjects.de \
--cc=linux-btrfs@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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.