[GE users] Jobs stuck in delete status

seandavi seandavi at gmail.com
Tue Jun 9 17:39:50 BST 2009


    [ The following text is in the "utf-8" character set. ]
    [ Your display is set for the "ISO-8859-10" character set.  ]
    [ Some characters may be displayed incorrectly. ]

On Tue, Jun 9, 2009 at 12:33 PM, rayson <rayrayson at gmail.com> wrote:
> As the cluster admin user, issue:
>
> % qdel -f <job id>

Yep.  That did it.

Thanks again, Rayson.

San

>
> On 6/9/09, seandavi <seandavi at gmail.com> wrote:
>> I'm using 6.2 and have managed to get a couple of jobs stuck in "dr"
>> status.  Both were parallel jobs running across multiple machines, but
>> both appear to have the "master" task running on the same machine.  I
>> have restarted the qmaster and the execd on the machine on which the
>> jobs appear to have had the "master" task.  Here is what I have in the
>> execd messages file:
>>
>> 06/09/2009 12:18:46|  main|pressa|I|controlled shutdown 6.2
>> 06/09/2009 12:18:53|  main|pressa|I|starting up SGE 6.2 (lx24-amd64)
>> 06/09/2009 12:18:53|  main|pressa|W|reaping job "28147" ptf complains:
>> Job does not exist
>>
>> Any ideas as to what is going on or how to go further with diagnosing
>> the problem.  The cluster has been up and running for months without
>> problems.  The only new addition is openmpi integration; it turns out
>> that one of the jobs stuck in "dr" status is an mpirun job.
>>
>> Thanks,
>> Sean
>>
>> ------------------------------------------------------
>> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=201328
>>
>> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].
>>
>
> ------------------------------------------------------
> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=201329
>
> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].
>

------------------------------------------------------
http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=201331

To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].



More information about the gridengine-users mailing list