Operations team & Sites

Tuesday 30 Sept 2014, 11:00 → 14:00 Europe/London

EVO - GridPP Operations team meeting

- This is the weekly GridPP ops & sites meeting - The intention is to run the meeting in Vidyo: https://vidyoportal.cern.ch/flex.html?roomdirect.html&key=zXhsqAxVnaT6 -- The PIN is 1234. To join via phone see http://information-technology.web.cern.ch/services/fe/howto/users-join-vidyo-meeting-phone for dial in numbers. -- The London (UK) service is on +442030510622 -- The meeting extension is 9308582. Apologies: Chris W

Minutes Minutes_for_OPS_meeting_30_Sep2014.docx Minutes_for_OPS_meeting_30_Sep2014.pdf

11:00 → 11:15 Experiment problems/issues

Review of weekly issues by experiment/VO - LHCb - CMS The CMS site readiness table can be found here: https://cms-site-readiness.web.cern.ch/cms-site-readiness/SiteReadiness/HTML/SiteReadinessReport.html#T2_UK_London_Brunel Bristol's flakiness was noted in the CMS computing meeting, though it looks like they are on the up. Imperial's current problem stems from a dcache upgrade gone wrong yet again. Simon has been talking to the developers and it should be sorted out soon. - ATLAS - Other - DIRAC status -- http://www.gridpp.ac.uk/php/gridpp-dirac-sam.php?action=view .

Slides SandSweekSep2014.pdf

11:15 → 11:30 Meetings & updates

With reference to: http://www.gridpp.ac.uk/wiki/Operations_Bulletin_Latest - General updates - WLCG ops coordination - Tier-1 status - Storage and data management - Accounting - Documentation - Interoperation - Monitoring - On-duty - Rollout - Security - Services - Tickets - Tools - VOs - Site updates

11:30 → 11:40 Analysis of SHA2 site readiness campaign

- From Michel Jouvin - "the "postmortem analysis" of the SHA2 site readiness campaign, "just completed" 2 weeks ago. At the origin it was considered as a minor change for sites but the experience proved it took more times and more effort than anticipated to get this done. As part of the current effort to understand how we can improve our operation efforts (and costs), I think it is important to try to understand why this SHA2 campaign was harder than expected and what lessons we can learn from it for the future. This discussion is not intended to lead to definitive conclusion but rather to serve as one of the input to the ongoing discussion about operation efficiency, in conjunction with a site survey by the OpsCoord and a few other things. It would be very helpful if sites participating to the GDB could try to gather some information on what happened in their regions, the potential issues faced (technical and non technical)..." - Background: introduction of new servers; preprod testing; ticket follow-up; checking configurations... and at the start checking s/w compatibility and NGI migration.

11:40 → 11:50 Site updates/roundtable

11:50 → 12:00 Multi-core status and actions

- Configurations pages https://www.gridpp.ac.uk/wiki/Category:Multicore - Status table https://www.gridpp.ac.uk/wiki/Batch_system_status - Production: Oxford, Glasgow, RAL, Manchester, Liverpool, Lancaster and QMUL + IC, RALPP, Sussex. Cambridge? Still to hear: - ECDF, Sheffield.

12:00 → 12:01 AOB

* HEPSYSMAN dates * Almost the end of Q3... time for quarterly reports again!