[GE users] Re: [HPC] Running Array job only one per node

rkrug R.M.Krug at gmail.com
Fri Mar 13 08:42:24 GMT 2009


I want to submit an array job which should run 25 times, but only
one instance at each node at the same time. When I submit the script as
below, it starts all instances at the same time and up to 8 per node
(one per core). Is it possible to state that only one instance should
run at the same time on one node? This has to do with resources use and
disk access.



#$ -t 1-25
#$ -cwd -j y

export MPIEXEC_RSH=ssh
export LD_LIBRARY_PATH=$HOME/lib:/usr/local/openmpi_gnu/lib:$LD_LIBRARY_PATH
export PATH=$HOME/bin:/usr/local/openmpi_gnu/bin:$PATH

Rainer M. Krug, PhD (Conservation Ecology, SUN), MSc (Conservation
Biology, UCT), Dipl. Phys. (Germany)

Centre of Excellence for Invasion Biology
Natural Sciences Building
Office Suite 2039
Stellenbosch University
Main Campus, Merriman Avenue
South Africa

Cell:		+27 - (0)83 9479 042
Fax:		+27 - (0)86 516 2782
Fax:		+49 - (0)721 151 334 888
email:		Rainer at krugs.de

Skype:		RMkrug
Google:		R.M.Krug at gmail.com


To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].

More information about the gridengine-users mailing list