Il 19/08/2016 02:23, Christopher Samuel ha scritto: >> scontrol reconfigure > "scontrol reconfigure" will do most, but not all parameters. For > instance adding/removing nodes requires daemon restarts. What's the risk doing a service slurmd restart when there are running jobs?
Is it a problem only if a job terminates while slurmd is stopped or could it have other effects? Yesterday I did it at least 3 times (using clusterssh) in parallel on all nodes, including frontend (where I restarted slurmctld instead of slurmd). Maybe I've only been very lucky? -- Diego Zuccato Servizi Informatici Dip. di Fisica e Astronomia (DIFA) - Università di Bologna V.le Berti-Pichat 6/2 - 40127 Bologna - Italy tel.: +39 051 20 95786 mail: [email protected]
