From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755022Ab0CCASA (ORCPT ); Tue, 2 Mar 2010 19:18:00 -0500 Received: from smtp1.linux-foundation.org ([140.211.169.13]:54569 "EHLO smtp1.linux-foundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751884Ab0CCAR6 (ORCPT ); Tue, 2 Mar 2010 19:17:58 -0500 Date: Tue, 2 Mar 2010 16:16:27 -0800 From: Andrew Morton To: john@calva.com Cc: bugzilla-daemon@bugzilla.kernel.org, bugme-daemon@bugzilla.kernel.org, linux-kernel@vger.kernel.org, Jens Axboe Subject: Re: [Bugme-new] [Bug 15426] New: Running many copies of bonnie++ on different filesystems seems to deadlock in sync Message-Id: <20100302161627.bf02d0a2.akpm@linux-foundation.org> In-Reply-To: References: X-Mailer: Sylpheed 2.4.8 (GTK+ 2.12.9; x86_64-pc-linux-gnu) Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org (switched to email. Please respond via emailed reply-to-all, not via the bugzilla web interface). On Tue, 2 Mar 2010 16:31:03 GMT bugzilla-daemon@bugzilla.kernel.org wrote: > http://bugzilla.kernel.org/show_bug.cgi?id=15426 > > Summary: Running many copies of bonnie++ on different > filesystems seems to deadlock in sync > Product: File System > Version: 2.5 > Kernel Version: 2.6.32 > Platform: All > OS/Version: Linux > Tree: Mainline > Status: NEW > Severity: normal > Priority: P1 > Component: VFS > AssignedTo: fs_vfs@kernel-bugs.osdl.org > ReportedBy: john@calva.com > Regression: No > > > I create 8 ext3 filesystems on 8 disks and run a copy of bonnie++ on each > filesystem. All but two or three of the Bonnie++ processes seem to hang in > sync and I get log messages like: > > [ 1557.377626] INFO: task bonnie:2503 blocked for more than 120 seconds. > [ 1557.377693] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this > message. > [ 1557.377775] bonnie D 0000000000000000 0 2503 2489 0x00000000 > [ 1557.377778] ffffffff8144b1f0 0000000000000082 0000000000000000 > ffff88034ac155c0 > [ 1557.377780] ffff88033c079880 ffffffff81047f43 000000000000f8a0 > ffff88063b1e9fd8 > [ 1557.377783] 00000000000155c0 00000000000155c0 ffff88063bbe3f90 > ffff88063bbe4288 > [ 1557.377785] Call Trace: > [ 1557.377787] [] ? finish_task_switch+0x3a/0xa7 > [ 1557.377790] [] ? __mutex_lock_common+0x10b/0x17b > [ 1557.377792] [] ? mutex_lock+0x1a/0x31 > [ 1557.377794] [] ? sync_filesystems+0x13/0xe3 > [ 1557.377796] [] ? sys_sync+0x12/0x2e > [ 1557.377799] [] ? system_call_fastpath+0x16/0x1b > When the system is stuck, please run echo w > /proc/sysrq-trigger or, equivalently, hit `alt-sysrq-w'. This will emit huge amounts of stack traces into the system logs and onto the console. There's no need to send all of them - please identify typical-looking ones and then send them in reply to this email. Email clients like to wordwrap these traces - please try to prevent that. Thanks.