AW: [torqueusers] non-existing job

[Schulz, Henrik]

Thanks Garrick,

but unfortunately it does not work. The messages still appear...

Henrik

-----Ursprüngliche Nachricht-----
Von: torqueusers-bounces at supercluster.org [mailto:torqueusers-bounces at supercluster.org] Im Auftrag von Garrick Staples
Gesendet: Mittwoch, 23. Januar 2008 20:36
An: torqueusers at supercluster.org
Betreff: Re: [torqueusers] non-existing job

On Wed, Jan 23, 2008 at 02:39:35PM +0100, Schulz, Henrik alleged:
> Dear all,
> 
> I am running TORQUE 2.1.2 together with MAUI 3.2.6p16. On a couple of nodes I have such a line every 45 seconds in my mom_logs:
> 
> 01/23/2008 00:00:27;0008;   pbs_mom;Job;34422.master;job was terminated
> 
> On other nodes job 34422 produces this line:
> 
> 01/23/2008 14:33:17;0008;   pbs_mom;Job;34422.master;ERROR:    received request 'KILL_JOB' from 10.0.0.91:1023 for job '34422.master' (job does not exist locally)
> 
> The job with number 34422 really existed, but this was about 4 months ago. Maybe there was a problem with this job concerning MPI communication.
> 
> Is there any chance to suppress these messages?

momctl -c 34422 -h <momhostname>