From mboxrd@z Thu Jan 1 00:00:00 1970 From: bugzilla-daemon@bugzilla.kernel.org Subject: [Bug 42895] jbd2 makes all system unresponsive Date: Tue, 15 May 2012 14:40:06 +0000 (UTC) Message-ID: <20120515144006.400F011FCF2@bugzilla.kernel.org> References: Mime-Version: 1.0 Content-Type: text/plain; charset="UTF-8" To: linux-ext4@vger.kernel.org Return-path: Received: from mail.kernel.org ([198.145.19.201]:53002 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1758305Ab2EOOkN (ORCPT ); Tue, 15 May 2012 10:40:13 -0400 Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id CDD6B2054E for ; Tue, 15 May 2012 14:40:07 +0000 (UTC) Received: from bugzilla.kernel.org (bugzilla.kernel.org [198.145.19.204]) by mail.kernel.org (Postfix) with ESMTP id 459D920548 for ; Tue, 15 May 2012 14:40:06 +0000 (UTC) In-Reply-To: Sender: linux-ext4-owner@vger.kernel.org List-ID: https://bugzilla.kernel.org/show_bug.cgi?id=42895 Eugene changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |ivanovstm2@zmail.ru --- Comment #11 from Eugene 2012-05-15 14:40:05 --- Thanks for the answers guys. to Hugues Tranli: >maybe it's related to a daemon/software running in the background. Well, that's pretty much what everybody want to find out. But seems it's not that easy. I'm on Xubuntu 11.10 on 3.0.0-17-generic #30-Ubuntu SMP Thu Mar 8 20:45:39 UTC 2012 x86_64 x86_64 x86_64 GNU/Linux on AMD CPU. cat /etc/fstab and cat /proc/mounts give me usual default settings: / ext4 rw,noatime,errors=remount-ro,user_xattr,barrier=1,data=ordered Except that I changed relatime to noatime. Though it's almost the same and on desktop it doesn't give noticeable change in disk usage. Block_dump: See message 73 in https://bugs.launchpad.net/ubuntu/+source/linux/+bug/607560 but overall it's like this: echo 1 > /proc/sys/vm/block_dump Watch results in syslog (note that syslog will frequently write to disk) or by periodically running dmesg. To get more "clean" results - disable kernel logging in syslog, enable block_dump, wait some time or do something in the system, then reenable kernel logging - results of block_dump should appear in syslog. I'm not aware of convenient way to watch it in realtime. to Jan Kara: Enabling ext4_mark_inode_dirty gives me constant flood of events where xfce4-terminal dirties mostly two same inodes: http://paste.ubuntu.com/988896/ Is it expected behavior? This is default terminal in Xubuntu. -- Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are watching the assignee of the bug.