SA1 coordination meeting

→ Europe/Zurich
28-R-06 (CERN)

28-R-06

CERN

Description

Minutes, https://edms.cern.ch/document/923879

Actions, https://twiki.cern.ch/twiki/bin/view/EGEE/SA1_CoordinationTasks

This meeting is 10:00 to 11:30 UTC+1
Phone number is: +41 22 767 6000
Access code is: 0191881
Or click here: https://audioconf.cern.ch/call/0191881

The conference call opens 15 minutes before the meeting starts.
    • 10:00 → 10:10
      Admin matters
      1. DSA1.3: Report on the status of the Regional Operations Centres (ROCs) and national/regional grid integration
    • 10:10 → 10:20
      Installed capacity: storage

      Current Status

      1. Detailed information in the installed capacity document: WLCG_GlueSchemaUsage-1.8.pdf.
      2. gstat2 web interface providing counts of installed capacity: https://gstat-dev.cern.ch/gstat/summary/country/. Mouse over occupancy bars for actual values.
      3. DPM, Storm, dCache and castor information providers have been available and deployed for quite some time now. DPM in particular is well deployed.
      4. gstat2 probes: There is a list of site BDIIs and for each there is a check-se probe. e.g Results are available site-bdii.cern.ch. These show all the the errors and warnings for what is being published. We will happily accept bug reports for these where you think they are wrong from reality or unfair.

        Sites are encouraged to check these now.

        We must get these probes into the site and ROC nagios that are/have been deployed.

      5. Pledges are available in http://gridops.cern.ch/mou
      6. OSG are publishing values via there XML interface to OMI (osg gocdb)

      Next Steps

      1. Arrange for gstat2 to create historical data of if its capacity measurements. This has been agreed verbally. They just need some detailed requirements.
      2. Create an iReport to merge OMI, gstat2 historical data and MOU data above. A comparison between installed and mou pledge is the target arranged by WLCG tier2 federation.
    • 10:20 → 10:40
      Guidelines on un/scheduled downtime and site suspension
    • Change request to gridview so only scheduled/unscheduled downtimes are differentiated (to be discussed with WLCG). John, could you please follow up this one?
    • Changes to Site downtime scheduling (some steps are not required any more, and do not scale with our present structure, like the reporting at the weekly operations meeting, which is a WLCG requirement and that we don’t follow any more; redefinition of core services).
    • Procedure on what to do with extended downtimes (longer than 1 month?), proposal to move those sites to uncertified?
document
link to OPS manual
more information
  • 10:40 → 10:50
  • Proposal to automate these reports, using the CIC site reports
  • 10:50 → 11:10
    Staged roll-out: proposal for the SA1 transition
    Detailed plan (heavy)
    more information
    slides
  • 11:10 → 11:30
    EU review recommendations
    document
  • 11:30 → 11:40
    AOB
    1. Sites running legacy gLite releases
    2. Call to upgrade WNs
    3. Remember deadline for QR5 contributions: next Monday 3rd of August!
    4. next meetings: 11th August, 1st September