Hi folks, We're at the tail end of a planned outage for a bunch of work, and we have a reservation on all our compute nodes on all our clusters.
I thought I would do an "scontrol reboot" to reboot our compute nodes into a new xCAT osimage and then noticed that nothing happened. All the nodes had a reservation that was created with: scontrol create reservation starttime=2016-02-23T14:00 duration=7-0 \ accounts=ibm,vlsci flags=maint,overlap nodes=ALL \ reservationName=GPFS_RT19363 So it had the MAINT flag on it, and given that scontrol reboot marked all nodes as a state of MAINT anyway I'm bemused that it didn't then reboot the nodes. Anyone seen this before? We're on Slurm 15.08.8. All the best, Chris -- Christopher Samuel Senior Systems Administrator VLSCI - Victorian Life Sciences Computation Initiative Email: [email protected] Phone: +61 (0)3 903 55545 http://www.vlsci.org.au/ http://twitter.com/vlsci
