Swiss WLCG Operations Meeting on 2012-07-05

• Date and time: First Thursday of the month, at 14:00
• Place: EVO, password: chipp
• External link / EVO: http://evo.caltech.edu/evoNext/koala.jnlp?meeting=MaMDMt2a28DIDe9D9sDI9a

Agenda

Status

• CSCS (reports Pablo):
  • Last maintenance status:
    • Thor kernel/os upgrade
    • Bios/Ilom FW upgrade on GPFS
    • Torque upgrade to 2.4.17
    • New CreamCE service: cream03
    • CVMFS enabled for Atlas
• PSI (reports Fabio):
  • dCache: Created a working testbed SL6 dCache 1.9.5-29 + BDII, RPMs from EGI.
  • dCache: Our production SL6 pools were affected by Leap second problem affects dCache on SL6 nodes!
  • dCache: A 'migration cache' job can be transformed in a 'migration copy' job without to transfer again the same files. This saves time.
  • Disks FW: Properly updated the FW on ~40 Seagate disks inside a Sun Fire X4540, used Oracle patch 141468-07.
  • WNs: Firmware Update on the new DALCO Nodes, to be done without downtimes during July.
• UNIBE (reports Gianfranco):
  • Stable operations
  • Status of PhaseC nodes at UniBE
• UNIGE (reports Szymon):
  • Operations
    • Space management picks up again, even with 310 TB in the SE and 100 TB in NFS.
    • Otherwise stable.
  • Upgrade
    • IBM still the best deal
    • Hesitating to get 64 cores/box in 2U machines we will rather get 1U machines with 32 cores.
    • More cores with AMD, so go for that. We don't believe in the outstanding Intel specs.
    • One machine to test first (IBM x3755 M3) planning 10.
  • CVMFS
    • Not yet here, 20 GB cache on disk would be a problem on some machines
    • Will try CVMFS on an NFS server.
      • Suggested by Andrej Filipcic.
      • Interesting for more sites.

• ATLAS @ CSCS news:
  • Availability for analysis (site classification)
  • CVMFS
  • Storage pledges
• Topic2

AOB

Attendants

• CSCS: Pablo
• CMS: Derek, Fabio, Leo
• ATLAS: Gianfranc, Szymon
• LHCb:
• EGI:

Action items

• Item1