[Top] [All Lists]

Re: Interesting possible XFS crash condition

To: Shawn Usry <shawn@xxxxxxxxxxxxxxxx>
Subject: Re: Interesting possible XFS crash condition
From: Dave Chinner <david@xxxxxxxxxxxxx>
Date: Thu, 21 Oct 2010 17:06:05 +1100
Cc: xfs@xxxxxxxxxxx
In-reply-to: <4CBFC54F.8030403@xxxxxxxxxxxxxxxx>
References: <4CBE887F.6020506@xxxxxxxxxxxxxxxx> <201010201012.39778@xxxxxx> <4CBF3C6C.2020803@xxxxxxxxxxxxxxxx> <20101020232758.51ac507a@xxxxxxxxxxxxxx> <4CBFC54F.8030403@xxxxxxxxxxxxxxxx>
User-agent: Mutt/1.5.20 (2009-06-14)
On Wed, Oct 20, 2010 at 11:45:03PM -0500, Shawn Usry wrote:
> On 10/20/2010 4:27 PM, Emmanuel Florac wrote:
> >Le Wed, 20 Oct 2010 14:01:00 -0500 vous écriviez:
> >
> >>2.  I did upgrade the firmware on the controller to a newer version
> >>AFTER the issue appeared, hoping this would resolve it.  Same results.
> >>
> >>At this point I'm leaning toward faulty hardware somewhere.
> >Another possibility is a memory problem, possibly making the machine
> >crash under heavy load; if most RAM is used as filesystem caching, this
> >maybe may lead to apparently xfs related errors. You could try running
> >memtest86+ on the system for a couple of hours.
> >
> Great minds think alike :)  Actually I have indeed already run a
> memtest86+ on the system which completed without a problem.
> Loading up read/writes on other single disks on the system also
> doesn't produce a problem.  Just this one filesystem ;)     It's a
> stumper!

Having some idea of the log messages generated by the crash - even
if it is screen shorts via hand-held camera - might help us narrow
down the cause.


Dave Chinner

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