[torqueusers] stuck "e" state
Jens Home For Wayward Cats
aquarijen at gmail.com
Tue Feb 5 10:32:17 MST 2008
You'll want to check the nodes that the job was running on to make
sure there isn't anything left over in /var/spool/pbs/mom_priv/jobs -
the -p means purge and it will take the job out of the queue but will
do no cleanup and will not run any epilog scripts (if you have them).
On Feb 5, 2008 11:47 AM, Adams, Samuel D AFRL/RHDR
<Samuel.Adams at brooks.af.mil> wrote:
> Thanks that worked.
> I tried qdel before but not with the -p option. The -p did the trick.
> Sam Adams
> General Dynamics Information Technology
> Phone: 210.536.5945
> -----Original Message-----
> From: Miles O'Neal [mailto:meo at intrinsity.com]
> Sent: Tuesday, February 05, 2008 10:44 AM
> To: Adams, Samuel D AFRL/RHDR
> Cc: torqueusers at supercluster.org
> Subject: Re: [torqueusers] stuck "e" state
> Adams, Samuel D AFRL/RHDR said...
> |We had a power failure a while back and some jobs were running at the
> |time. Some of the job could be restarted just fine, but I have a few
> |that are perpetually stuck in an "e" (exiting I think) state. I can't
> |restart or delete them. How can I get them out of the queue?
> |Job id Name User Time Use S Queue
> |------------------- ---------------- --------------- -------- - -----
> |1934.prodnode1 mie_comp-freq=3D30 sam 0 E
> Did you try "qdel -p $JOBID"?
> torqueusers mailing list
> torqueusers at supercluster.org
More information about the torqueusers