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

Re: [Condor-users] Condor and shared file systems


do you know of a way to have the jobs keep running and still have the
output goto a local filesystem and without the jobs restarting?

On Mon, Jun 13, 2011 at 10:51 AM, Matthew Farrellee <matt@xxxxxxxxxx> wrote:
> On 06/13/2011 08:26 AM, jhowes@xxxxxxxxxxxxxxxx wrote:
>> This is kind of a follow-up question to the recent discussion on Condor
>> and NFS.
>> If a submit node is using a public share for all of the job related
>> files, does the submit node need to be on-line after the initial job
>> submission i.e., could the submit node be a laptop that comes and goes
>> from the pool and is only online when submitting jobs? But output is
>> returned either at job end or streamed to the file share?
>> John L. (Jack) Howes
>> HPT Computing
> The submit node needs to be present to keep running jobs running - keep the
> claim on the remote resource alive. You can make the lease very long, such
> that the laptop is likely to come back, or more reliably you could do a
> -remote submit to an infrastructure schedd. You'd then use
> condor_transfer_data when the job is done.
> Best,
> matt
> _______________________________________________
> 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/