NERSCPowering Scientific Discovery Since 1974

July 19

Attending:  Jay and Eric, JeffA and JeffP

Utilization:  Full again after last week's maintenance and problems, mostly STAR and ALICE jobs.

Outages/Incidents:  The 7/13 maintenance ended up taking longer than scheduled due to some server issues.  The power upgrade took longer than expected so there wasn't time for the /common migration but the power upgrade was successful - we have enough power now for the recently purchased hardware as well as the next procurement. On 7/14 there was a problem with the connection between a 10G switch and the PDSF core router - this caused problems for eliza[16-18] as well as /home.  There was more trouble with it 7/15 but it was fixed at the end of the day on 7/15.

Upcoming Downtimes:  Next month there will be another all day downtime to finish /common migration and do some networking maintenance but it has not been scheduled yet.

Procurements/New Hardware:  Jay is still figuring out costs - will send email to PI's soon.

Grid Issues:  The ATLAS grid services was blacklisted for the outage last week and then put back into service.  This causes a lot of errors at first but it settles down after about 24 hours.

Torque:  The site license talks are proceeding, will hopefully be resolved in about a month's time.  Maui would be hard to use because of all the workarounds that would be necessary but it is still probably preferable to SGE.

Topics from Users:  Discussed unix groups and ACLs.  JeffP to file a ticket to see if it would be possible to remove (secondary) unix groups in NIM.