Deployment team

Tuesday 8 Apr 2008, 11:00 → 12:15 Europe/Zurich

EVO - GridPP Deployment team meeting

Jeremy Coles

- This is the weekly DTEAM meeting - The intention is to run the meeting in EVO: http://evo.caltech.edu/evoGate/. Join the meeting in the GridPP Community area

Minutes dteam-minutes-2008-04-06.txt

11:00 → 11:20 Experiment problems/issues

Review of weekly issues by experiment/VO - LHCb - CMS - ATLAS - Other

11:20 → 11:35 ROC update

ROC manager update ************************* ops meeting update ********************** - There was a reminder about publishing OS tags: http://goc.grid.sinica.edu.tw/gocwiki/How_to_publish_the_OS_name - gLite3.0.2 PPS Update47 released to PPS yesterday. The update contains, FTS update (PATCH:1740). gridFTP session handling was changed: now copy and getFileSize are done in the same session: fix for BUG:33528 - gLite3.1.0 PPS Update23 is in preparation: The release will introduce the WMS and LB services for SL4 - Complaint from French ROC on behalf of site-admins whose email addresses were added to a new list without their agreement - project spam - gLite 3.1 Update18, announced for last week, was? released to production yesterday. The update contains: * NEW: glite-MON for SL4 * DPM 1.6.7-4 o fix for bug #33769: incorrect pool free space after dpm-drain o improved ACL management for srmMkdir command * UI/WN/VOBOX o lcg-tags non longer produces Globus warnings suppressed o voms-admin client 2.0.6-1 providing ACL support on command line * vdt_globus_essentials (affecting several services and notably the CE) o bug fix to prevent globus-job-manager processes to pile-up on a CE (bug observed at CERN after SAM WMS/RB tests were enabled ) * voms-admin server (VOMS) o Refactored voms-admin-ping script o ACL management web service (compatible with client >= 2.0.6-1) o Registration web service. o many bug fixes CCRC related: " There will be a test of the Tier0 to Tier1 Optical Private Networks backup links from 15.00 to 19.00 CEST (13.00 to 17.00 UTC) on Wednesday 9 April. The plan of the test is here: https://twiki.cern.ch/twiki/bin/view/LHCOPN/BackupTest RAL will be unreachable for 15-20 minutes between 16:45 and 17:15 CEST PIC will be unreachable for 15-20 minutes between 17:15 and 17:45 CEST The goal of the maintenance is to verify that all the backup solutions work as expected. The T1s with a backup link should be up all the time, but at the moment we cannot guarantee that it will be the case and there may be outages at any time for any Tier1. It would be appreciated if experiments could particularly exercise their links as much as possible during the test period." Ticket status *************** See attachment - we've nearly closed all the T2 relates footprints tickets.

more information report_file8008.html

11:35 → 11:45 GDB/CCRC topics

- Last Tuesday there was a pre-GDB meeting (http://indico.cern.ch/conferenceDisplay.py?confId=30246) looking again at CCRC'08 with a focus on what is needed for the May challenge. For a summary see http://indico.cern.ch/materialDisplay.py?sessionId=4&materialId=4&confId =20228. CCRC'08 part 2 runs from Monday 5th May to Friday 30th and is intended to test all aspects of the experiment production chains. Part 1 was generally considered a success - things came together just in time and lessons were learned from communication issues to bugs in the software. A 2-day post-mortem workshop is planned 12th-13th June at CERN. One remaining issue is whether SRMv1 should continue to be supported in May. Some components are not likely to be fully deployed - SL4 WMS and CREAM CE for example. - There was a GDB last week (http://indico.cern.ch/conferenceDisplay.py?confId=20228) covering: Ways of improving grid service monitoring at sites; How the experiments negotiate with sites (a communication topic left over from the pre-GDB meeting); CPU benchmarking (there are trends starting to appear with different suites vs hardware and experiment code performance but no answer yet as to what to use in forthcoming tenders); an update on the OPN (most countries rejected the DANTE proposal); pilot job progress (testing continues but a working group is in place to look at the experiment frameworks); tape efficiencies (small files have been a problem) and preparation for the WLCG workshop 21st-25th April. - Any team comments/observations for discussion??

11:45 → 11:55 Team updates

- Summary of current work and priorities of each team member - Any progress on the GridMon checks and T1-site rates? (raised last week by Andrew Sansum) - From the blogs: -- Use of perfsonar at the T1 -- Use of maui tools for looking at job efficiency (GridIreland) -- ECDF running for ATLAS -- T1 tape migration -- Southgrid changes -- New pakiti release

11:55 → 12:05 Actions review

12:05 → 12:10 AOB

- Please review the WLCG collaboration workshop agenda and give feedback: http://indico.cern.ch/conferenceTimeTable.py?confId=6552. (T2Cs please check that your site admins have registered). - T2 quarterly reports (Q108) are due next week. (T2Cs Please let Jeremy know if it is going to be late!)