I just published a set of scripts, programs, config file examples, etc that I wrote for use at BYU but should be useful to other HPC sites. I couldn't think of a better name for it, so I called it the User Fencing Tools (UFT). It is available in our github repo at https://github.com/BYUHPC/uft.
The tools are used to control users on HPC login nodes and compute nodes in various ways. The tools make use of cgroups, namespaces, and cputime limits to ensure that users don't negatively affect each others' work. We limit memory, CPU, disk, and cputime for users.
UFT also has examples for how to control ssh-launched processes
on compute nodes. You can account for those with Torque but can't
control them (just like normal). SLURM will have accounting and
resource enforcement for these in 13.12 (Dec. 2013).
I still need to add quotas to the mix of published tools but I'll get around to it some day. It's really not that hard but our script for doing so is integrated with something site-specific.
Everything is under the MIT license so have fun with it. I need to do some more code cleanup, as always, but it Works For Us!
No comments:
Post a Comment
Please leave any comments, questions, or suggestions below. If you find a better approach than what I have documented in my posts, please list that as well. I also enjoy hearing when my posts are beneficial to others.