[torquedev] Zombie Torque jobs

[Chris Samuel]

On Sat, 23 Jun 2007, Peter Enstrom wrote:

> The biggest issue is that the job is unkillable.

I don't know if this would help your problem, but in the past when I've seen 
similar I've done:

qsig -s0 $JOBID

That tells the pbs_mom to send signal 0 to the lead process.  That doesn't 
actually do anything except raise an error if that process no longer exists, 
and the pbs_mom then realises that the job has died.

Not had to do that for a long time though!

cheers,
Chris
-- 
 Christopher Samuel - (03)9925 4751 - VPAC Deputy Systems Manager
 Victorian Partnership for Advanced Computing http://www.vpac.org/
 Bldg 91, 110 Victoria Street, Carlton South, VIC 3053, Australia

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part.
Url : http://www.supercluster.org/pipermail/torquedev/attachments/20070702/a9ce6527/attachment.bin