Closed sjpb closed 3 years ago
Ok turns out this is expected. From configless slurm docs:
This slurmctld can be identified by either an explicit option, or — preferably — through DNS SRV records defined within the cluster itself. If you have a login node you will be running client commands from, those client commands will have to use the DNS record to get the configuration information from the controller when they run. If you expect to have a lot of traffic from a login node, this can generate a lot of requests for the configuration files. In cases like this, you may want to consider running slurmd on the machine so it can manage the configuration files, but not allowing it to run jobs.
Currently we only use the "explicit option", i.e. setting SLURMD_OPTIONS in /etc/sysconfig/slurmd
.
Note
sinfo
on control node works ok.