Re: [HTCondor-users] Job Submission in Parallel Universe

[Todd Tannenbaum <tannenba@xxxxxxxxxxx>]

On 4/8/2013 2:53 AM, Muak rules wrote:
> I'm submitting my first parallel universe job. which is basically a
> simple hello world problem.
> I'm using CentOs 6.3 and had installed HTCondor using "yum install condor".
> I'm not sure about about version of HTCondor.

Just enter  "condor_version" to find out.

> When I submit it the job
> goes on idle state.
> Please help me out through this......Following is my submit description
> file.
>
>
> universe=parallel
> executable=mpi_hello_world
> machine_count=1
> log=hello.log
> out=hello.out
> queue

See the section on parallel applications in the HTCondor Manual at

http://research.cs.wisc.edu/htcondor/manual/v7.8/2_9Parallel_Applications.html

For starters, I would expect your submit file to look like

  universe=parallel
  executable=openmpiscript
  arguments=mpi_hello_world
  machine_count=1
  log=hello.log
  out=hello.out
  queue

where executable is a startup-script (that ships with HTCondor) that 
lauches jobs using the MPI of your choice (openmpi, or mpich, or lam).

I would also suspect that your schedd is not configured as a dedicated 
scheduler.

At any rate, the section of the Manual I referenced above covers all this.

Hope this helps,
Todd