[torqueusers] Newbie question: jobs queued, but only some run

[David Chin]

I have a setup described here:
        http://www.clusterresources.com/pipermail/torqueusers/2006-December/004848.html

And now... I just checked and the behavior seems to have changed from
what I initially intended to ask about. D'oh!  (I thought that it
would execute jobs on one queue, but not the others.)

Anyway, I have pbs_server and pbs_sched running on the head node as
root, pbs_mom running on all the cluster nodes as root. I've
configured 3 queues (short, medium, long), each with its own priority
(high, medium, low). I followed the quick start instructions at

    http://www.clusterresources.com/wiki/doku.php?id=torque:appendix:l_torque_quickstart_guide

Whenever I submit a job, it is queued, but not executed. I have to
manually do a qrun and specify a node. This is true no matter if I am
operator, manager, both, or neither.

When I do a "pbsnodes -a", all nodes report

     state = free
     np = 1
     ntype = cluster

I tried tweaking strict_fifo in sched_config, but neither "true" nor
"false" seem to change the behavior above.

Thanks in advance again for any advice.

Cheers,
    Dave

-- 
Email: david.w.h.chin at gmail.com  dwchin at lroc.harvard.edu
Public key: http://gallatin.physics.lsa.umich.edu/~dwchin/crypto.html
      pub   1024D/1C557DDF 2006-07-21 [expires: 2007-07-21]
      Key fingerprint = 4EEB A409 5010 3679 4EA7  D420 4E52 202A 1C55 7DDF