xfs
[Top] [All Lists]

Re: XFS blocked task in xlog_cil_force_lsn

To: Stefan Priebe - Profihost AG <s.priebe@xxxxxxxxxxxx>
Subject: Re: XFS blocked task in xlog_cil_force_lsn
From: Dave Chinner <david@xxxxxxxxxxxxx>
Date: Tue, 17 Apr 2012 09:56:47 +1000
Cc: stable@xxxxxxxxxxxxxxx, Greg KH <gregkh@xxxxxxxxxxxxxxxxxxx>, Christoph Hellwig <hch@xxxxxxxxxxxxx>, "xfs@xxxxxxxxxxx" <xfs@xxxxxxxxxxx>, Philipp Herz - Profihost AG <p.herz@xxxxxxxxxxxx>
In-reply-to: <4F8BC0B9.90604@xxxxxxxxxxxx>
References: <4F8BC0B9.90604@xxxxxxxxxxxx>
User-agent: Mutt/1.5.21 (2010-09-15)
On Mon, Apr 16, 2012 at 08:48:25AM +0200, Stefan Priebe - Profihost AG wrote:
> Hi,
> 
> today i've seen this call trace / block in XFS while running 3.0.27.
> 
> INFO: task xfsaild/sdc3:1818 blocked for more than 120 seconds.
> "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
> xfsaild/sdc3    D ffff88041f374dc8     0  1818      2 0x00000000
> ffff88041edd3d30 0000000000000046 ffff8803ecaa8dc0 ffff88041f23fe28
> ffff88041f374860 0000000000010800 ffff88041edd3fd8 ffff88041edd2010
> ffff88041edd3fd8 0000000000010800 ffff88041f15c860 ffff88041f374860
> Call Trace:
>  [<ffffffff8159c94a>] schedule+0x3a/0x60
>  [<ffffffff812763a9>] xlog_cil_force_lsn+0xe9/0x110
>  [<ffffffff8104caf0>] ? try_to_wake_up+0x2a0/0x2a0
>  [<ffffffff81273922>] _xfs_log_force+0x62/0x250
>  [<ffffffff81273d23>] xfs_log_force+0x13/0x40
>  [<ffffffff81281ac7>] ? xfs_trans_ail_cursor_next+0x27/0x30
>  [<ffffffff81282237>] xfsaild+0x447/0x460
>  [<ffffffff81281df0>] ? xfs_trans_ail_init+0xb0/0xb0
>  [<ffffffff8106f646>] kthread+0x96/0xa0
>  [<ffffffff815a0214>] kernel_thread_helper+0x4/0x10
>  [<ffffffff8106f5b0>] ? kthread_worker_fn+0x130/0x130
>  [<ffffffff815a0210>] ? gs_change+0xb/0xb
> 
> Is there a known fix / patch available?

Your first question should be: is this a known problem?

And the answer to that is: I don't think so.

So, is the system actually hung? Were there IO errors around this
time? did the system recover and continue to work normally? What's
your storage hardware, application, workload, etc?

Cheers,

Dave.
-- 
Dave Chinner
david@xxxxxxxxxxxxx

<Prev in Thread] Current Thread [Next in Thread>