[torqueusers] Torque is not handling jobs to nodes

Zhiliang Hu zhu at iastate.edu
Fri Sep 26 14:57:40 MDT 2008


I have a situation:

> qsub -l nodes=6:ppn=2 /path/to/mpi_program

where "mpi_program" is:

/path/to/mpirun -np 12 /path/to/my_program

-- Everything went to run on head node (one time on the first compute node).  Jobs can be done anyway.

While the mpirun can run on its own by specifying a "-machinefile", it is pointed out by Glen, and also on this web site http://wiki.hpc.ufl.edu/index.php/Common_Problems that it's not a good idea to provide machinefile since it's "already handled by OpenMPI and Torque".

But in my case why the OpenMPI and Torque is not handling the jobs to nodes?

Zhiliang



More information about the torqueusers mailing list