March 15
Attending: Jay and Eric from NERSC; users Craig and Andrei
Cluster Status: Still running at full capacity
Recent Outages: SWO Sunday. Problem was corruption on /common which was restricted to dayabay files. Did rsync of ~25% of /home also.
Upcoming downtimes: Nothing for PDSF but NGF downtime 3/30-3/31. Dayabay discussed their need for webhosting and how this will impact their work.
Procurements: Small procurement of local disks for STAR; dayabay might want 20 or 40 TB in the near future.
Interactive Node abuse: Memory limits are in place; users running too many jobs, too long jobs; we don't want to auto-kill as it is more difficult with NX being used a lot
Grid issues: ATLAS needs permissions changed; server doesn't seem to be working right...
NXproxy: Yushu is looking into how to provide this or an equivalent