On Mon, Dec 5, 2011 at 1:27 PM, Kunal Rao
<kunalgrao@xxxxxxxxx> wrote:
Hi,
I have setup condor pool with 2 dedicated resources (for MPI jobs), one of them with dedicated scheduler. I am running MPI jobs (MPICH2) with say 2 processes, I want these to go on 2 different machines (the one's which are configured as dedicated resources)
What I am seeing is that condor creates 2 processes and puts them on the same machine. How do I specify in the job submission script for it to start these 2 processes on different machines ?
My current job submission script is as follows :
---------
universe = parallel
executable = /var/spool/condor/etc/examples/mp2script
arguments = /home/kunal/condor/examples/hello_mpi
machine_count = 2
+WantIOProxy = True
Output = hello_mpi.out
error = hello_mpi.err
Log = hello_mpi.log
should_transfer_files = yes
when_to_transfer_output = on_exit
+ParallelShutdownPolicy = "WAIT_FOR_ALL"
transfer_input_files = /home/kunal/condor/examples/hello_mpi
queue
-------
I want to specify something like: start process 1 on machine1 and process 2 on machine2. How do I specify that ?
Thanks & Regards,
Kunal