I recently did something very similar, albeit for a serial application - here
is what
worked for me:
#!/bin/bash
#SBATCH --tasks=64
# other generic SBATCH requests suppressed for brevity ...
for ((i=0;i<SLURM_NTASKS;i++)); do
echo "Task $i"
srun --cpus-per-task=1 --exclusive --nodes=1 --ntasks=1 ./rp p11_4.$i >
out.$i &
done
wait
Your mileage may vary, as well as the usual warnings about load balancing, etc.
...
Matt
On 7/31/13 11:59 AM, Kasra Hosseini wrote:
> Thanks for your response...and how should I implement it into my BATCH
> script, because:
> srun --exclusive ./submit.sh my_job_1 24 &
> srun --exclusive ./submit.sh my_job_2 24 &
>
> did not work!
>
>
> On Wed, Jul 31, 2013 at 5:39 PM, Moe Jette <[email protected]
> <mailto:[email protected]>> wrote:
>
>
> srun has a multitude of options to control where the job steps run.
> Perhaps you just want "srun --exclusive ...".
>
> Quoting Kasra Hosseini <[email protected]
> <mailto:[email protected]>>:
>
> > Dear SLURMers!
> >
> > I want to run a program with the following configuration:
> > - One Batch script which runs two or more embarrassingly parallel
> workloads
> > - Each of these embarrassingly parallel workloads needs one node (24
> CPUs)
> > - Therefore, I need two or more nodes, each node takes care of one
> > embarrassingly parallel workload
> >
> > Problem:
> > - All tasks will be distributed on just one node! (the first one)
> >
> > Here is my BATCH script: (Each node in our cluster has 24 CPUs. Since I
> > want to run two jobs, I requested 2 nodes and for each node, 24 tasks)
> >
> > #!/bin/bash
> > #SBATCH --partition=....
> > #SBATCH --output=...
> > #SBATCH --workdir=...
> > #SBATCH --job-name="testing"
> > #SBATCH --tasks-per-node=24
> > #SBATCH --nodes=2
> > #SBATCH --mail-type=all
> > #SBATCH --time=71:59:59
> >
> > # run compute job
> > source ..../.bashrc
> > ./submit.sh my_job_1 24 &
> > ./submit.sh my_job_2 24 &
> >
> > wait
> >
> > Result:
> > - 48 tasks on the first node, nothing on the second one!
> >
> > Any idea?
> >
> > Thank you very much in advance for your time and kind attention to my
> > request.
> >
> > Best,
> > Kasra
> >
>
>
>
>
> --
> *********************************************************************
> Seyed Kasra Hosseini zad
> M.Sc. in Applied Mechanics
> Department of Mechanical Engineering
> Amirkabir University of Technology
> Tehran, Iran
>
> http://imechanica.org/user/17362
> *********************************************************************
