[GE users] qresub as other user

Sebastian Stark stark at tuebingen.mpg.de
Wed Nov 16 15:34:31 GMT 2005


    [ The following text is in the "iso-8859-1" character set. ]
    [ Your display is set for the "ISO-8859-10" character set.  ]
    [ Some special characters may be displayed incorrectly. ]

On Wednesday 16 November 2005 16:23, Andreas Haas wrote:
> > I would expect qresub (as an admin) to do the same as the rerun mechanism
> > does. If I want to relocate a users job from one machine to some other
> > machine I can simply reboot it and it will start somewhere else, given
> > that the rerun flag is set.
> >
> > But of course I don't know the implementation details so I cannot really
> > argue with that...
>
> For that case qmod -r <jobid> exists.

Thanks. If I had been aware of this I would not have asked silly questions at 
first.

> > Another case where I think qresub as an admin can be useful is the
> > following:
> >
> >   - User submits job
> >   - Job runs, errors out because of some problem
> >   - Admin fixes problem
> >   - Admin qresubs other users jobs
>
> There is a job error and a queue error for error conditions. Job
> error is for cases when the end user made a failure that must be
> fixed before rerun is possible. The queue error is for problem with
> set-up problems which can be fixed by admins only.

99% of the errors in our cluster are like this:

  failed changing into working directory:11/15/2005 17:48:30 [1792:20744]:   
  error: can't chdir to /agbs/cluster/chrisd: No such file or direct

(of course people notice right *after* submitting thousands of jobs...)

In case of a not accessible NFS mount a user error occures that can not be 
fixed by the user.

> > The current behavior of qresub is, at least for me, the most unexpected
> > one.
>
> Well, the reason to introduce qresub was to have a means to submit a job
> which is absolutely identical with an already existing job. IIRC we didn't
> have the exit 99 reschedule at that point in time.

Yes, now that I know qmod -r I do not see any reason for qresub any more.


Thanks again for the help,
Sebastian

-- 
Sebastian Stark -- http://www.kyb.tuebingen.mpg.de/~stark
Max Planck Institute for Biological Cybernetics

---------------------------------------------------------------------
To unsubscribe, e-mail: users-unsubscribe at gridengine.sunsource.net
For additional commands, e-mail: users-help at gridengine.sunsource.net




More information about the gridengine-users mailing list