[torqueusers] qdel return code 153

[Dr. Henrik Schulz]

Dear all,

I run into the problem that qdel (torque 4.2.7) returns the exit code 153 when being executed on a pbs_mom node and does not delete the job. Other commands like qsub or qstat work fine on that node. Is this a configuration problem?

Thanks in advance for any kind of hints.

Best regards,
Henrik

[Bidwell, Matt]

Are all the nodes in the job up? Have you tried qdel -p? qdel without any options requires the nodes to be responsive I order for the job to be deleted.

-----Original Message-----
From: torqueusers-***@supercluster.org [mailto:torqueusers-***@supercluster.org] On Behalf Of Dr. Henrik Schulz
Sent: Tuesday, February 20, 2018 1:41 AM
To: Torque Users Mailing List <***@supercluster.org>
Subject: [torqueusers] qdel return code 153

Dear all,

I run into the problem that qdel (torque 4.2.7) returns the exit code 153 when being executed on a pbs_mom node and does not delete the job. Other commands like qsub or qstat work fine on that node. Is this a configuration problem?

Thanks in advance for any kind of hints.

Best regards,
Henrik

[Dr. Henrik Schulz]

Dear Matt,

thanks for the suggestions!

The situation is like this:

- pbs_server runs on HEADNODE
- pbs_mom with job 1 runs on NODE1
- qdel is executed on NODE2 where pbs_mom is also running
- all nodes are up and reachable
- qdel 1 on NODE2 returns 153
- qdel -p 1 on NODE2 also returns 153
- job 1 on NODE1 is an interactive job. After qdel on NODE2 nothing happens to the job.
- qdel 1 on NODE1 (using the shell of the interactive job) also returns 153
- the same happens when the job is non-interactíve

Question: what does the return code 153 mean?

Thanks!
Henrik

Post by Bidwell, Matt
Are all the nodes in the job up? Have you tried qdel -p? qdel without any options requires the nodes to be responsive I order for the job to be deleted.
-----Original Message-----
Sent: Tuesday, February 20, 2018 1:41 AM
Subject: [torqueusers] qdel return code 153
Dear all,
I run into the problem that qdel (torque 4.2.7) returns the exit code 153 when being executed on a pbs_mom node and does not delete the job. Other commands like qsub or qstat work fine on that node. Is this a configuration problem?
Thanks in advance for any kind of hints.
Best regards,
Henrik
_______________________________________________
torqueusers mailing list
http://www.supercluster.org/mailman/listinfo/torqueusers