[Lustre-discuss] Lustre client kernel panic

[Nick Jennings]

On Sat, 2009-09-26 at 04:11 -0400, Oleg Drokin wrote:
> Hello!
> 
> On Sep 26, 2009, at 1:57 AM, Nick Jennings wrote:
> 
> >  About an hour ago the client completely hung. Hosting co. says it was
> > a kernel panic. I got not useful feedback in /var/log/messages from  
> > the
> > client or the MDS. However from the OST I got several complaints.
> > (below).
> > Does anyone have any insight into the problem? All help as to how I  
> > can
> > fix this, or avoid the problem, greatly appreciated.
> 
> The traces you see is a known bug (19557), it happens when client is  
> evicted
> that had too many locks cached.
> Unfortunately that provides us with zero insight into what happened to  
> the client
> and MDS.

 Hi Oleg! How ya doing? :)

 Unfortunately that was the only info I could get. The client had no
information in the logs about what happened. The MDS only had the
following entry near the time:

Sep 25 22:28:43 dbn1 kernel: Lustre: MGS: haven't heard from client
ab5e5f08-e39d-385d-f7e3-fbd1addb0fac (at 10.0.0.21 at tcp1) in 248 seconds.
I think it's dead, and I am evicting it.

 Is there any other info I should be gathering when something like this
happens? (Sorry, it's been a while since I've done any lustre bug
reporting) :)

Cheers,
-Nick

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 197 bytes
Desc: This is a digitally signed message part
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20090926/d52caa22/attachment.pgp>