On 12-07-2021 20:17, Heitor wrote:
Hello,
I'm trying to find the minimum requirements (mainly CPU and RAM) for the
slurmctld, sulrmdbd, and slurmrestd daemons, but I did not find it in
the docs. Maybe I missed some page?
SchedMD recommends that the slurmctld server should have only a few, but
very fast CPU cores, in order to ensure the best responsiveness.
The file system for /var/spool/slurmctld/ should be mounted on the
fastest possible disks (SSD or NVMe if possible).
The database server should preferably run on a physical server.
I prefer to run slurmctld and slurmdbd on separate servers so that I can
upgrade the Slurm database independently and before the slurmctld server
upgrade. This allows me to test the slurmdbd upgrade without disturbing
slurmctld and the cluster operations (it's OK for slurmdbd to be
unavailable for many hours). See also my Slurm upgrade page
https://wiki.fysik.dtu.dk/niflheim/Slurm_installation#upgrading-slurm
It all depends on how large and busy your Slurm cluster is.
/Ole
