...
- upgrade testpost-master to RHEL7 so it can run Slurm
- upgrade nmpost-master to RHEL7 so it can run Slurm
- Look at upgrading to the latest version of Slurm
- Sort out the various memory settings (ConstrainRAMSpace, ConstrainSwapSpace, AllowedSwapSpace, etc)
Work
- Create a subset of testpost cluster that only runs Slurm for admins to test.
- Install Slurm on testpost-serv-1, testpost-master, and OS image
- install Slurm reaper on OS image
- Create a small subset of nmpost cluster that only runs Slurm for users to test.
- Install Slurm on nmpost-serv-1, nmpost-master, herapost-master, and OS image
- install Slurm reaper on OS image
- Need at least 4 nodes: batch, interactive, vlass/vlasstest, hera/hera-i
- Identify stake-holders (E.g. operations, DAs, sci-staff, SSA, HERA, observers) and give them the chance to test Slurm and provide opinions
- implement useful opinions
- Set a date to transition remaining cluster to Slurm. Possibly before we have to pay for Torque again around Jun. 2022.
- Do another pass on the documentation https://info.nrao.edu/computing/guide/cluster-processing
- Port nodeextendjob to Slurm
- Port nodesfree to Slurm
...