Go to the Indico Home Page Oldest event Older event Up to category Newer event Newest event Printable version
  • Compact style
  • Indico style
  • Indico style - inline minutes
  • Indico style - numbered
  • Indico style - numbered + minutes
  • Indico Weeks View
    • Switch to the management area of this event
    Login

    LCG Service Coordination Meeting

    → Europe/Zurich
    28/S-029 (CERN)

    28/S-029

    CERN

    35
    Show room on map
    Jamie Shiers
    Description
    LCGSCM

    Internal meeting for host laboratory LCG service providers focussing on issues on a timescale of ~1 week to ~1 month.

    Mailing list: lcg-service-coordination-meeting@cern.ch

    Minutes
      • 10:00 → 10:20
        Outstanding Issues & Actions 20m
        • WLCG Service Targets for Full Dress Rehearsal Preparations
          Target date is April 1st for required services to be deployed at sites so that experiments can begin preparations / testing for the Full Dress Rehearsals (from 1st July on)
          • SC3 target was to have services 2 months in advance
          • CMS CSA06: June - September was used to extensively debug and prepare for the full exercise - i.e. 4 months
          • 3 months is probably acceptable in this case as the DRs are not foreseen to be 'big bang', but repeated ~monthly with eventually new releases of experiment s/w and other fixes
          FDR services
          WMS 3.1
        • Distributed DB Services - Schedule
          Upcoming dates are 1st March (tomorrow - ATLAS conditions at 7 sites) and 1st April (all sites for ATLAS and LHCb conditions, LHCb LFC) - see attached slide for details by VO, by application and by site. 26 Feb - ATLAS deployed delayed by 1 month so now start date is 1st April for all sites

          Downstream capture boxes for ATLAS and LHCb in production (see C5 minutes of 9 Feb)

          Revised Schedule
          Schedule
        • FTS 2.0 rollout schedule & plans
        • FTS server split - status
        • Reinstallation of service nodes - target end 2006
        • CMS servers / services: status
          See CMS task force of Sep 20
        • prod-lfc-atlas-central.cern.ch - status and plans
          The so called "central" lfc is prod-lfc-atlas-central.cern.ch. It is not used by the ATLAS DDM but unfortunately has a legacy role for the users.

          Q: when can we shut it down? 31st April 2007?

        • CASTOR interventions - update on scope & schedule
        • Oracle Critical Patch Update <a href="http://www.oracle.com/technology/deploy/security/alerts.htm">Release Schedule</a>
          Critical Patch Updates

          Starting 2005, Critical Patch Updates are the primary means of releasing security fixes for Oracle products. They are released on the Tuesday closest to the 15th day of January, April, July and October. The next four dates are:

          • 17 April 2007
          • 17 July 2007
          • 16 October 2007
          • 15 January 2008
        • Other changes in the pipeline
          text
        • Changing SE names in the LFC and other such manipulations
          What should the proposed policy be?
          • Agree procedure with experiments on:
            • Channel through which such requests should come e.g.
              • from named / known contacts in experiments' operations team
              • through weekly operations meeting - confirmed by experiment representative at meeting
            • Scheduling and execution of changes
          • go mode - just execute blindly any request
          • Discuss each case at next convenient IT-experiment meeting
          Any of above is 'fine' but it should be clear on both sides what the procedure is...
        • Scheduling of Service Interventions - Lessons Learnt and Proposals
          Request to take this item at the end of the meeting after AOB

          The current procedure was proposed to the WLCG Management Board in May 2005, prior to the service phase of SC4.

          Since then we have had numerous interventions of varying degrees of complexity and length and now would be a good time to review the procedure and propose possible changes (prior to the experiments' Dress Rehearsals).

          Another potentially useful distinction, proposed by Stefano Belforte, was between 'short' / transparent interventions, for which the middleware and / or client s/w should retry, versus 'long' interventions for which this was not possible / (implemented?)

          Or should the deployment goal be such that this is 'always' possible?

          Proposals and discussion.

          Slides
          Template
          text
      • 10:20 → 10:40
        LCG Service Review 20m
        • <a href="https://twiki.cern.ch/twiki/bin/view/LCG/LcgScmStatusDeploy">Certification / Pre-production</a>
          Speakers: Nick Thackray, Oliver Keeble
        • <a href="https://twiki.cern.ch/twiki/bin/view/LCG/LcgScmStatusMLR">Monitoring, Logging & Reporting</a>
          Speakers: Ian Neilson, James Casey
        • Core Grid Services
          Speakers: Gavin McCance, Jan van Eldik, Thorsten Kleinwort, Ulrich Schwickerath
        • Fabric & Infrastructure Services
          Speakers: Maria Dimou, Maria Girone, Remi Mollon
        • <a href="https://twiki.cern.ch/twiki/bin/view/LCG/LcgScmStatusExp">Experiment Issues</a>
          Speaker: EIS Team
      • 10:40 → 10:45
        Any Other Business 5m