Job array is working like magic for me.
Thank you very much for the hint!
> 27 июня 2021 г., в 17:40, Brian Andrus написал(а):
>
> I suspect you are misunderstanding how the flow works.
>
> You request X nodes to do some work.
> You start a job that uses all the nodes.
> Job runs until everythi
I suspect you are misunderstanding how the flow works.
1. You request X nodes to do some work.
2. You start a job that uses all the nodes.
3. Job runs until everything is done.
4. Resources are released back to be used again.
If your job allows it, you probably want an array job, which will be
Hello!
Recently I've started using MPI on our HPC-cluster.
It has 40 nodes.
It runs SLURM.
I'm new to MPI and SLURM but so far everything works fine except one thing.
In short: nodes that finished calculation do not become idle.
Only after all the nodes finished calculations they all become idle.
