Attending: Eric Iwona Larry Evan JeffP Lisa Tom Mike Gene
Utilization: Cluster is not so full due primarily to STAR problems w/eliza17
Outages: On 4/2 eliza17 had problems which ended up bringing down the entire cluster. eliza17 was taken offline and the cluster was brought back up. Problems are related to a bad controller and a bad card in one server. Not clear yet when eliza17 will be put back into service. On the same day as the eliza17 outage GPFS quotas were turned off and are now enforced manually. Users are notified when they go over quota.
Upcoming downtimes: eliza18 will need 1/2 day downtime for firmware upgrade. Also, the pdsfdtn's need to be rearranged and we will schedule this for 4/18. The result will be that ATLAS and STAR will be independent. There are rolling SL6 upgrades underway on the batch nodes.
Procurements: RFP is out - deadline 4/30 for proposals.
Grid Issues: ATLAS had some problems with out of date CRLs and we haven't heard back from them so the status is uncertain.
Topics from users: People have notice better performance without quotas. SL6: icecube hasn't had time to work on it.