Hi, cgroups have been on my radar since about two weeks after I started looking into SLURM and I'm just getting around to looking at them now.
I note that the ProcTrackType docs say > This plugin writes to disk often and can impact performance. If you are running lots of > short running jobs (less than a couple of seconds) this plugin slows down performance > dramatically. It should probably be avoided in an HTC environment. http://slurm.schedmd.com/slurm.conf.html#OPT_ProctrackType Despite this, I feel like I've seen a number of people on this list that use it. Does this mean that it's now considered acceptable to run cgroups for ProcTrackType? Also, when it status "writes to disk often....slows down performance" is this a reference to per-compute-node or per-head-node? Cheers L. ------ The most dangerous phrase in the language is, "We've always done it this way." - Grace Hopper