PDSF users meeting 1/4/11
Attending: Eric, Katie and Jay from NERSC and users Jeff P., Thomas, Art and possibly an an unknown person on the phone (?).
Cluster Status/Utilization: Quite full over the break and stable. Only issue was that at one point there were 26k jobs running or pending but that didn't cause any major problems.
Upcoming downtimes: Need to do some work on rack 22 - clean up and rearrange some things. This will affect STAR db and will take ~5 hours. eliza16/17/18 will also get worked on. HPSS downtime 1/12. Also will need to restart SGE at some point.
Procurements/New Hardware: eliza5 additional storage is being worked on - had to check with vendor to be sure the new hardware would work with the existing hardware. Requisition will go out soon.
sl302 retirement: still waiting for a downtime when the interactives can be rebooted.
Topics from users:
- Some discussion about chos documentation
- Discussed a bit about how to manage SRM.
The rest of the meeting was a demo of the new website by Eric.