[torqueusers] Torque 3.0.2: Pb with "Bad UID for job execution MSG=ruserok" on node (rsh/ssh questions)

giggzounet giggzounet at gmail.com
Wed Mar 28 07:13:12 MDT 2012


Hi,

We have a cluster with torque 3.0.2 (and maui). We would like to be able
to start job on nodes too. But a qsub on the node gives:
Bad UID for job execution MSG=ruserok failed validating...

We have no problem when we start a job from the frontend.

The configuration is a classical one:
- frontend: pbs_server (allow_node_submit = True) + maui are running
- nodes: pbs_mom is running
- we have a /etc/ssh/shosts.equiv file with all the nodes and frontend
names.

If I copy /etc/ssh/shosts.equiv to /etc/hosts.equiv the "bad uid"
problem disappears. But I don't want rsh...

The torque package was configured and installed by the firm which built
the cluster. A few questions:

- How can I know if torque is using rsh or ssh ?

- Is there a solution to know the configure options used for our torque
? I mean for example "scp". I don't want rsh.

- Is there a way to force torque to use ssh instead of rsh ?

- If torque is using ssh, why it works with the /etc/hosts.equiv and not
with /etc/ssh/shosts.equiv ?

Thx a lot,

best regards,
Guillaume




More information about the torqueusers mailing list