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

Re: [Condor-users] Checkpoint and Migration



Ok... sorry for my fault... now I need to compile all binaries with condor_compile to it works right? But for now, how can I say to condor "dont stop my jobs when the owner machines becomes"? If the owner machine will work slowly, it dont mather...

Thanks very much!!!

On 7/25/07, Si Hammond < simon.hammond@xxxxxxxxx> wrote:

Checkpointing is only available in the standard Universe (it says
Vanilla below).



On 25 Jul 2007, at 20:22, Ary Junior wrote:

> Hi, when I submit a job to the condor pool it go to be executed in
> the machine A, because it state is Unclaimed  and activity is
> Idle... if the machine A user becomes and change it state to Owner,
> the condor pool stop the job and migrate it to the machine B...
> however the job is restarted on machine B instead to continue....
> my submit file contents is:
>
> universe        = vanilla
> executable      = zr2o4ti2o4.sh
> output          = zr2o4ti2o4.sh.out
> error           = zr2o4ti2o4.sh.err
> log             = zr2o4ti2o4.sh.log
> should_transfer_files = IF_NEEDED
> when_to_transfer_output = ON_EXIT
> queue
>
> How can I configure it to checkpoint works?
>
> Thanks very much!!!
> _______________________________________________
> 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/

_______________________________________________
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/