On Tue, Jan 07, 2014 at 03:19:23PM -0800, Joshua Baker-LePain wrote: > On Tue, 7 Jan 2014 at 3:09pm, Skylar Thompson wrote > > > Quick question - are you limiting memory usage for the job (i.e. h_vmem)? > > No. We have mem_free set to consumable (and the jobs include a request), > but (obviously) that's not a hard limit.
The reason I ask is we ran into a problem where the probability a job would run out of memory scaled with the number of nodes it ran on, due to one GE process per node needed on the OpenMPI master node. Quick fix for us was to use $fill_up rather than $round_robin allocation in the PE. Sounds like you wouldn't be running into it, but it might be something ot look at. -- -- Skylar Thompson ([email protected]) -- Genome Sciences Department, System Administrator -- Foege Building S046, (206)-685-7354 -- University of Washington School of Medicine _______________________________________________ users mailing list [email protected] https://gridengine.org/mailman/listinfo/users
