February 14

Attending:  Eric Hiroshi Patrick Mike Lisa Iwona Larry

Utilization:  Cluster has not been completely full due to ALICE not running much.  There will be an ALICE troubleshooting session later in the week.

Outages:  eliza1 has recovered - Dell rewrote headers on all 45 drives.  eliza2 firmware was upgraded as well.  eliza8 was fixed yesterday.

Upcoming downtimes:  Bestman to be restarted 2/21/12 at 9am.

Procurements:  ALICE is buying more compute power.  Groups can test using /project for storage and consider buying storage to put there instead of on PDSF.

SL4:  We still hope to retire it 3/1.

SL6:  Will need to reboot rack 9 and will have to coordinate that w/STAR.  We should be able to roll out SL6 on the whole cluster pretty soon.

Priorities:  Patrick mentioned a colleague having problems getting jobs to run.  A discussion of how SGE schedules within a project followed.  It looks like this user is specifying 6 elizaio's and that is probably what it hurting his throughput.