Ian,
Have you run "condor_q -better-analyze [job_id]" on one of the idle jobs
to see if Condor can tell you why it's not running? Are other users
able to start jobs on all of the other machines? Does condor_status
list those machines as Unclaimed and Idle?
- dave
Ian Cottam wrote:
I sometimes see 1000 jobs in the queue from a single user. Our pool has,
say, 50 processors free that match, but has allocated just two (he runs
jobs more or less constantly). Now, I know about the "freedom of the
commons" scheduling, but is that what is going on?
Why cannot this user get a large share and then get thrown off some of
the processors should a second user come along?
Apologies if this is all obvious.
-Ian
_______________________________________________
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:
https://lists.cs.wisc.edu/archive/condor-users/