Hi,
I am working on a PhD on supercomputer scheduling and I am investigating if SLURM has the capabilities I am looking to use in a scheduler I want to develop and test. The main requirements are that the scheduler interface can suspend resume jobs, multiple jobs can be scheduled on a node (including mixing suspended and non-suspended nodes), and that the scheduler can access up to date stats such as memory use, CPU use etc. per job per node. Can you advise me if SLURM meets these requirements? Thanks, Leith Bade [email protected]
smime.p7s
Description: S/MIME cryptographic signature
