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

Re: [Condor-users] idling jobs



Thanks, Nick, for your reply.

I've run 'condor_q -better' on the farm as you suggested. I'm attaching
the output. I'm not an expert enough to understand it though. Can you
glean something from it?

Thanks in advance,
Daniel


-----Original Message-----
From: condor-users-bounces@xxxxxxxxxxx on behalf of Nick LeRoy
Sent: Mon 4/9/2007 10:47 PM
To: Condor-Users Mail List
Subject: Re: [Condor-users] idling jobs
 
On Wed April 4 2007 11:19 am, Daniel Goldin wrote:
> Hi,
Hello,

> I have submitted 30 jobs to run on a farm with 30 nodes. The "submit"
> file looks like this:

<snip>
>
> I am the only user on the farm, but what I see is only 5-6 jobs are
> running simultaneously and the rest are idling. Can I reconfigure
> something so that all the jobs run simultaneously? Could it be a
> priority issue? (If it can be done, I'd like to do it non-intrusively,
> i.e. keep the running jobs running...)

There's not a lot of information here, and there could be quite a lot of 
things going wrong.

First, have you waited at least one negotiation cycle (typically 5 minutes)?  
I'm assuming that these are all long running jobs (from your description 
above).  Condor doesn't do particularly well when users submit a lot of short 
running jobs.  If that's not the case, then let's try a couple debugging 
exercises:

1. Have you looked at the output of 'condor_status' to verify that all of the 
execute machines are reporting to the pool correctly, and that they're all in 
the unclaimed / idle state?

2. Have you tried running 'condor_queue -analyze' or (even 
better) 'condor_queue -better' (better analyze) and looked through it's 
output?

I'd start with the above two exercises...   If they don't help, give us a 
little more information to go on (like the output of condor_status and 
condor_q or 'condor_q -ana').

Hope this helps

-Nick

-- 
           <<< Follow the white rabbit. >>>
 /`-_    Nicholas R. LeRoy               The Condor Project
{     }/ http://www.cs.wisc.edu/~nleroy  http://www.cs.wisc.edu/condor
 \    /  nleroy@xxxxxxxxxxx              The University of Wisconsin
 |_*_|   608-265-5761                    Department of Computer Sciences
_______________________________________________
Condor-users mailing list
To unsubscribe, send a message to condor-users-request@xxxxxxxxxxx with a
subject: Unsubscribe
You can also unsubscribe by visiting
https://lists.cs.wisc.edu/mailman/listinfo/condor-users

The archives can be found at either
https://lists.cs.wisc.edu/archive/condor-users/
http://www.opencondor.org/spaces/viewmailarchive.action?key=CONDOR


<<winmail.dat>>