xfs
[Top] [All Lists]

Re: INFO: task mount:11202 blocked for more than 120 seconds

To: David Chinner <dgc@xxxxxxx>
Subject: Re: INFO: task mount:11202 blocked for more than 120 seconds
From: Christian Kujau <lists@xxxxxxxxxxxxxxx>
Date: Mon, 10 Mar 2008 02:46:38 +0100 (CET)
Cc: LKML <linux-kernel@xxxxxxxxxxxxxxx>, xfs@xxxxxxxxxxx, dm-devel@xxxxxxxxxx
In-reply-to: <20080309213441.GQ155407@xxxxxxx>
References: <alpine.DEB.1.00.0803072116420.7723@xxxxxxxxxxxxxxxxxx> <20080307224040.GV155259@xxxxxxx> <alpine.DEB.1.00.0803080032020.7723@xxxxxxxxxxxxxxxxxx> <20080309213441.GQ155407@xxxxxxx>
Sender: xfs-bounce@xxxxxxxxxxx
User-agent: Alpine 1.00 (DEB 882 2007-12-20)
On Mon, 10 Mar 2008, David Chinner wrote:
Oh, dm-crypt. Well, I'd definitely start looking there. XFS has a
history of exposing dm-crypt bugs, and these hangs appear to be I/O
congestion/scheduling related and not XFS.

Yeah, I noticed that too, thanks for verifying this: during the 2nd bisect run, the box locked up hard when I accessed the device-mapper. I'm using a wrapper script to set up my luks/dm-crypt devices and still have to find out which command exactly triggers the lockup. So, maybe the hard lockup and the hangs are not so unrelated after all...oh well.

Also, we haven't changed
anything related to plug/unplug of block devices in XFS recently, so
that also points to some other change as well...

Thanks for your assistance, David, I really appreciate it. I'll try to find out more about this dm-crypt thingy....

Christian.
--
BOFH excuse #396:

Mail server hit by UniSpammer.


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