Hi, We use Slurm on our cluster and set a max number of all jobs. But we would want to implement this: N concurrent individual jobs and M concurrent jobs in all job arrays (e.g. m job arrays with n jobs in each and M=n*m), and M is much larger than N. I have read the Slurm documentation, but cannot find a way to separate the individual jobs and jobs in arrays. Does anyone know how to do that?
Thank you. Shaohao
