Hi,
Thanks all who answered. The problem was indeed in the max. locked
memory limitation.
Though, changing it in /default/common/settings.sh was not enough.
I also had to add ". /default/common/settings.sh" to
/default/common/sgeexecd (and to /etc/init.d/sgeexecd on the
compute nodes) as when
I suspect that your SGE daemons are not starting with the proper
locked memory limits (and therefore jobs started under SGE get
severely limited locked memory limits).
See these FAQ entries -- the issues described for SLURM are
applicable to all resource managers (to include SGE):
http://
On Wed, Aug 22, 2007 at 03:31:20PM +0300, Noam Meltzer wrote:
> Hi,
>
> I am running openmpi-1.2.3 compiled for 64bit on RHEL4u4.
> I also have a Voltaire InfiniBand interconnect.
> When I manually run jobs using the following command:
>
> /opt/local/openmpi-1.2.3-gcc4/bin/orterun -np 8 -hostfile
Hi,
I am running openmpi-1.2.3 compiled for 64bit on RHEL4u4.
I also have a Voltaire InfiniBand interconnect.
When I manually run jobs using the following command:
/opt/local/openmpi-1.2.3-gcc4/bin/orterun -np 8 -hostfile ~/myHostList
-mca btl self,openib /tcc/eandm/performance/igor/main.exe.op
