Operations team & Sites

Europe/London
EVO - GridPP Operations team meeting

EVO - GridPP Operations team meeting

Description
- This is the biweekly ops & sites meeting - The intention is to run the meeting in EVO: http://evo.caltech.edu/evoGate/. Join the meeting in the GridPP Community area. - The phone bridge number is +44 (0)161 306 6802 (CERN number +41 22 76 71400). The phone bridge ID is 14 0782 with code: 4880. Apologies: Pete, Jeremy, Elena
Minutes
    • 11:00 11:20
      Experiment problems/issues 20m
      Review of weekly issues by experiment/VO - LHCb - CMS - ATLAS - Other
    • 11:20 11:40
      Meetings & updates 20m
      With reference to: http://www.gridpp.ac.uk/wiki/Operations_Bulletin_Latest - Tier-1 status - Accounting - Documentation - Interoperation - Monitoring - On-duty - Rollout - Security - Services - Tickets - Tools - VOs - SIte updates
    • 11:40 12:00
      Discussion 20m
      - Status of EMI updates (http://www.hep.ph.ic.ac.uk/~dbauer/grid/state_of_the_nation.html) and plans going forward. REMINDER of TIMELINE 1a) gLite 3.2 CEs are no longer supported and EGI expected sites to have them replaced with EMI CEs by the end of September (also true of most other gLite 3.2 products such as the BDII and SEs). 1b) EGI CSIRT have implemented tests to check site middleware versions and ticket a site that still has services (except UI/WN) on gLite 3.2. Sites are expected to acknowledge the tickets and indicate their upgrade plans or link to a GGUS ticket outlining the technical problem preventing immediate action. Failure to do this will make the site more likely to be suspended from the beginning of November. 1c) From the beginning of November the level of scrutiny will increase. For the UK we would still like to aim for upgrades to happen during October, but for those sites requiring a coupled CE-Torque-WN upgrade it is understood that there may be a delay (the 22nd October EMI release has not yet appeared). 2a) gLite 3.2 WN support/patching was extended until the end of November. Much testing has happened. DPM and dCache sites now have tested successfully with EMI-2 SL5 WNs and the VOs are supportive of the migration. Cross-check the status for WN-expt testing here: https://twiki.cern.ch/twiki/bin/view/LCG/WorkerNodeTesting#Result_tables_match_your_site_he. 2b) It is understood that 4 sites have a dependency on the availability of the tarball WN. (Matt may be able to give an update today). We (GridPP ops) will work to make future production of the tarball quicker. STATUS of UPDATES For the upcoming release we were informed of this timeline (status as at 8th October): https://twiki.cern.ch/twiki/bin/view/EMI/EmiEgiGOM#Status_08_10_2012. The EGI ops meeting yesterday gave the following update(s): https://wiki.egi.eu/wiki/Agenda-22-10-2012. SITE PLANS - Alessandra created this useful page https://www.gridpp.ac.uk/wiki/UK_EMI2_Deployment to record the plans across sites. We need more information for Bristol, Durham and UCL. Sheffield is not yet updated in the table but Elena reports for this meeting: "We have EMI1 cream ce in Sheffield. It passes nagios tests for a week. I'll set up atlas queue for it on Wednesday and glite ce will be retired next week (by Oct 31). We already have bdii, apel and argus at EMI1. WN's and DPM will be done in November." RAL Tier-1 has downtime scheduled for CE upgrades today.
    • 12:00 12:05
      Actions 5m
      To be completed: https://www.gridpp.ac.uk/wiki/Operations_Team_Action_items Completed: https://www.gridpp.ac.uk/wiki/Operations_Team_Completed_Actions
    • 12:05 12:06
      AOB 1m
      - At next week's meeting we will have a special presentation from Alastair Dewhurst on the Tier-1 findings and decisions regarding use of hyper-threading. - Please register for the HEPSYSMAN meeting: http://hepwww.rl.ac.uk/sysman/Nov2012/main.html. - Please help your Tier-2 technical reps finalise your Q3 T2 reports this week! Thank you.