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

Re: [Condor-users] Backup Scheduler



Hermann,


You could try the High Availability Daemons [ http://research.cs.wisc.edu/condor/manual/v7.0/3_10High_Availability.html ]. Section 3.10.1, High Availability of the Job Queue, is what you're looking for. Afair, Condor is using a hot spares and a fail-over mechanism.

Regards,
Alexandru

-- 
Dr. Alexandru Iosup
Parallel and Distributed Systems Group
Delft University of Technology, The Netherlands
w http://www.pds.ewi.tudelft.nl/~iosup/ 
l http://www.linkedin.com/pub/dir/alexandru/iosup
 

> -----Original Message-----
> From: condor-users-bounces@xxxxxxxxxxx 
> [mailto:condor-users-bounces@xxxxxxxxxxx] On Behalf Of Hermann Fuchs
> Sent: woensdag 21 maart 2012 10:01
> To: condor-users
> Subject: [Condor-users] Backup Scheduler
> 
> Hi
> 
> As far as I understood the scheduler (e.g. the submit 
> machine) is a critical part in the condor set up. If this 
> machine fails, all jobs which are controlled and have been 
> started already will stop and only continue after the 
> scheduler is back online.
> 
> Is there a way to build a back-up scheduler?
> 
> We have a cluster with one dedicated submit machine. Mainly 
> due to security and hardware reasons we want to have only one 
> machine where to user can log in and start jobs.
> While this machine is usually running, reboots e.g. due to 
> updates cause all jobs within the cluster to stop and restart 
> when it comes back on.
> We would like to avoid that, as most of our jobs are within 
> the vanilla universe.
> 
> Is there a way to do so?
> 
> Greetings from Austria,
> Hermann
> --
> -------------
> DI Hermann Fuchs
> Christian Doppler Laboratory for Medical Radiation Research 
> for Radiation Oncology Department of Radiation Oncology 
> Medical University Vienna Währinger Gürtel 18-20 A-1090 Wien
> 
> Tel.  + 43 / 1 / 40 400 7271
> Mail. hermann.fuchs@xxxxxxxxxxxxxxxx
> 
> _______________________________________________
> 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/
>