On 04/26/2011 06:04 PM, William Deegan wrote:
Greetings,
Is there a way to set the maximum rate at which new jobs will be
launched on a cluster (and/or a given machine)?
My client's worried about submitting a 100 jobs and having them all
start at the same time crushing the fileserver.
One possibility (other than re-architecting the storage infrastructure)
is to add a random delay to the beginning of the job script. E.g. bash
NUMBER=$[ ( $RANDOM % 1000 ) + 1 ]
sleep $NUMBER
That would likely distribute the startups of the jobs evenly over 1000
seconds, assuming SGE launches them all simultaneously.
Regards,
Alex
_______________________________________________
users mailing list
[email protected]
https://gridengine.org/mailman/listinfo/users
