[prev in list] [next in list] [prev in thread] [next in thread] 

List:       grid-engine-users
Subject:    Re: [GE users] No free slots for interactive job # !
From:       Andy Schwierskott <andy.schwierskott () sun ! com>
Date:       2003-01-22 15:14:45
Message-ID: Pine.GSO.4.44.0301221611290.15911-100000 () sr-ergb01-01
[Download RAW message or body]

Mark,

> My cluster was working fine last week.  Today I get this error
> message a few moments after I submit a job that never runs.  All my
> jobs go into "pending" for some reason now.  I was playing around
> with the PE and have Queues set to all, could this be a problem.
> The machine will mostly run parallel jobs so I allocated all the
> queues for this.  I also want GE to run like it did when I first
> installed it, submitting jobs across the queues.  What am I doing
> wrong?
>
> I'm running RH Linux 8.0 with 6 execution hosts.

Can you add to you command line the switch "-w v "? What (error) message do
you get about scheduleability of your job?

Are your queues still set to TPYE "interactive"?

When the job arepending what is the reason you get with


   qstat -j <jobid>

(assuming the schedd_job_info is set to "true" in the scheduler config)

Andy


[prev in list] [next in list] [prev in thread] [next in thread]