linux-ext4.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: bugzilla-daemon@bugzilla.kernel.org
To: linux-ext4@vger.kernel.org
Subject: [Bug 15906] New: serious performance regression in "umount" on ext4 over LVM
Date: Tue, 4 May 2010 20:36:59 GMT	[thread overview]
Message-ID: <bug-15906-13602@https.bugzilla.kernel.org/> (raw)

https://bugzilla.kernel.org/show_bug.cgi?id=15906

           Summary: serious performance regression in "umount" on ext4
                    over LVM
           Product: File System
           Version: 2.5
    Kernel Version: 2.6.33
          Platform: All
        OS/Version: Linux
              Tree: Mainline
            Status: NEW
          Severity: normal
          Priority: P1
         Component: ext4
        AssignedTo: fs_ext4@kernel-bugs.osdl.org
        ReportedBy: kees@outflux.net
        Regression: Yes


As root, if /tmp is on an LV (or possibly even without this):

cd /tmp
dd if=/dev/zero of=test.ext4 bs=1 count=1 seek=1G
mkfs.ext4 -F test.ext4
mkdir -p /mnt/test
mount -o loop test.ext4 /mnt/test
echo $(seq 65536) | (cd /mnt/test; xargs touch)
time umount /mnt/test

Prior to 2.6.32, this took a second or so.  Now it takes over a minute.

Reproduced in both Ubuntu 10.04 (2.6.32) and Fedora 12 (2.6.33).
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/543617

The current Ubuntu work-around is only useful on an otherwise idle system.

-- 
Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are watching the assignee of the bug.

             reply	other threads:[~2010-05-04 20:37 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-05-04 20:36 bugzilla-daemon [this message]
2010-05-04 20:37 ` [Bug 15906] serious performance regression in "umount" on ext4 over LVM bugzilla-daemon
2010-05-04 20:41 ` bugzilla-daemon
2010-05-04 20:52 ` bugzilla-daemon
2010-05-04 21:05 ` bugzilla-daemon
2010-05-04 21:11 ` bugzilla-daemon
2010-05-04 21:12 ` bugzilla-daemon
2010-05-04 21:34 ` bugzilla-daemon
2010-05-04 21:48 ` bugzilla-daemon
2010-05-05  0:28 ` bugzilla-daemon
2010-05-05  3:18 ` bugzilla-daemon
2010-05-05  4:00 ` bugzilla-daemon
2010-05-05  4:46 ` bugzilla-daemon
2010-05-05  7:28 ` bugzilla-daemon
2010-05-05  8:27   ` Dmitry Monakhov
2010-05-05  8:40     ` Jens Axboe
2010-05-05  9:06       ` Dmitry Monakhov
2010-05-05  7:30 ` bugzilla-daemon
2010-05-05 19:44 ` bugzilla-daemon
2010-05-05 20:34 ` [Bug 15906] performance regression in "umount" of filesystems using barriers bugzilla-daemon
2010-05-05 21:36   ` Greg Freemyer
2010-05-05 20:34 ` bugzilla-daemon
2010-05-05 21:36 ` bugzilla-daemon
2010-05-05 21:55   ` Greg Freemyer
2010-05-06  3:49 ` bugzilla-daemon
2010-05-06  7:09 ` bugzilla-daemon
2010-05-06  7:10 ` bugzilla-daemon
2010-05-07  9:47 ` bugzilla-daemon
2010-05-08 14:30 ` bugzilla-daemon
2010-05-17  3:28 ` bugzilla-daemon
2010-05-17  3:44 ` bugzilla-daemon
2010-05-17 10:52 ` bugzilla-daemon
2010-05-19 18:57 ` bugzilla-daemon
2010-05-19 19:12 ` bugzilla-daemon
2010-05-21  1:05 ` bugzilla-daemon
2010-05-21  2:07 ` bugzilla-daemon
2010-05-21  6:08 ` bugzilla-daemon
2010-05-22  4:38 ` bugzilla-daemon
2010-05-26 16:44 ` bugzilla-daemon

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=bug-15906-13602@https.bugzilla.kernel.org/ \
    --to=bugzilla-daemon@bugzilla.kernel.org \
    --cc=linux-ext4@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).