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: Mon, 14 May 2012 21:43:40 +0000 (UTC) Message-ID: <20120514214340.5B64C11F973@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]:53856 "EHLO mail.kernel.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932258Ab2ENVnm (ORCPT ); Mon, 14 May 2012 17:43:42 -0400 Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 422D7204CE for ; Mon, 14 May 2012 21:43:41 +0000 (UTC) Received: from bugzilla.kernel.org (bugzilla.kernel.org [198.145.19.204]) by mail.kernel.org (Postfix) with ESMTP id 62EA120497 for ; Mon, 14 May 2012 21:43:40 +0000 (UTC) In-Reply-To: Sender: linux-ext4-owner@vger.kernel.org List-ID: https://bugzilla.kernel.org/show_bug.cgi?id=42895 Jan Kara changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |jack@suse.cz --- Comment #10 from Jan Kara 2012-05-14 21:43:40 --- (In reply to comment #8) > Is there a way to find a cause of flush and jbd2 writes? Like apllication name > or PID? > Preferably without need to patch/compile new kernel, so that as many people as > possible can use it. If you have tracepoints enabled in your kernel (they usually are) and you have relatively recent kernel, then you can enable tracepoint in ext4_mark_inode_dirty() by: echo 1 >/sys/kernel/debug/tracing/events/ext4/ext4_mark_inode_dirty/enable Then you can run: cat /sys/kernel/debug/tracing/trace_pipe and watch how inodes are dirtied. That should catch practically all cases where JBD2 eventually ends up doing some IO. -- Configure bugmail: https://bugzilla.kernel.org/userprefs.cgi?tab=email ------- You are receiving this mail because: ------- You are watching the assignee of the bug.