[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Condor-users] Jobs are Executed Only on the Central Manager



One machine is the central manager configured to be submit and execute
machine as well and the other 3 machines are configured as submit and
execute nodes. On the central manager all the 5 necessary daemons run,
(master, schedd, startd, negotiator,and collector) while on the other
nodes, only the 3 daemons run (master, schedd and startd).

When i fire condor_q after firing a condor_submit command with the
following submit file:

##################################
Universe   = vanilla
Executable = simple
Arguments  = 4 10
Log        = simple.log
Output     = simple.out
Error      = simple.error

should_transfer_file = YES
when_to_transfer_file = ON_EXIT

Queue 25
#################################

...i got

003.000:  Request is being serviced

---
003.001:  Run analysis summary.  Of 4 machines,
      0 are rejected by your job's requirements
      3 reject your job because of their own requirements
      1 match but are serving users with a better priority in the pool
      0 match but reject the job for unknown reasons
      0 match but will not currently preempt their existing job
      0 are available to run your job
        No successful match recorded.
        Last failed match: Sat Sep 16 19:32:44 2006
        Reason for last match failure: no match found

25 jobs; 24 idle, 1 running, 0 held

I see now, what does it meant by "...their own requirements"?

Thanks for your time reading my message.

Leo

> I'm a rank newbie myself but if nobody else is answering I'll take a
> stab...
>
> How do you know that all your machines are execute nodes?  What's in
> your deamon list?
>
> With one or more jobs in the queue, what does condor_q -analyze tell
> you?



> On Sun, Sep 17, 2006 at 02:10:54AM +0800, leo@xxxxxxxxxxxxxxxxxxxxx wrote:
>>
>> just a quick question, I want to submit either vanilla or standard jobs
>> which can be be run distributively on all idle machines....because what
>> happens in my condor pool is that all the jobs I submitted were all
>> queued
>> up and run on the CENTRAL MANAGER ONLY even though the other execute
>> machines are idle. I have 4 machines in my pool, all are both submit and
>> execute machines. I have submitted jobs from all machines but still they
>> were executed ONLY on the CENTRAL MANAGER.
>