Week of 150427

WLCG Operations Call details

  • At CERN the meeting room is 513 R-068.

  • For remote participation we use the Vidyo system. Instructions can be found here.

General Information

  • The purpose of the meeting is:
    • to report significant operational issues (i.e. issues which can or did degrade experiment or site operations) which are ongoing or were resolved after the previous meeting;
    • to announce or schedule interventions at Tier-1 sites;
    • to inform about recent or upcoming changes in the experiment activities or systems having a visible impact on sites;
    • to provide important news about the middleware;
    • to communicate any other information considered interesting for WLCG operations.
  • The meeting should run from 15:00 until 15:20, exceptionally to 15:30.
  • The SCOD rota for the next few weeks is at ScodRota
  • General information about the WLCG Service can be accessed from the Operations Web
  • Whenever a particular topic needs to be discussed at the daily meeting requiring information from site or experiments, it is highly recommended to announce it by email to wlcg-operations@cernSPAMNOTNOSPAMPLEASE.ch to make sure that the relevant parties have the time to collect the required information or invite the right people at the meeting.

Monday

Attendance:

  • local: Luca (SCOD+Storage), Ulrich (Batch), Maarten (ALICE), Stefan (LHCb), Alessandro (ATLAS)
  • remote: Lisa (FNAL), Michael (BNL), Rob (OSG), Rolf (IN2P3), Gareth (RAL), Dimitri (KIT), Di Qing (Triumf), Matteo (CNAF), Christian (NDGF)

Experiments round table:

  • ATLAS reports (raw view) -
    • Central services and general ATLAS points
      • mc15 digi+reco was launched on Thursday/Friday. Few tasks up to now (20M events). Observed not so high CPU/WALLCLOCK efficiency, under investigation how to improve it (more events per job being the first measure)
      • Muon Reprocessing finished, Repro coordination happy about the speed.
      • nothing specific to sites to report.

  • CMS reports (raw view) -
    • Nobody available to attend the call - sorry
    • 670 files lost at FNAL due to disk server failure
      • 281 could be recovered from other locations
      • 389 got lost and needed to be invalidated globally

  • ALICE -
    • high activity
    • intermittent proxy renewal failures for NIKHEF (GGUS:113240)
      • looks like a CRL issue on myproxy.cern.ch

  • LHCb reports (raw view) -
    • Operations dominated by MC jobs and user analysis
    • T0:
      • Problem with SRM for pit file export (GGUS:113316)
      • Discussing old VOMS servers retirements, previously planned for Wed, might happen on Tue now

Sites / Services round table:

  • ASGC:
  • BNL: NTR
  • CNAF: NTR
  • FNAL: short downtime on Wed starting at 10:00 CST. EOS@FNAL will be initially unavailable for 1 hour and then degraded for 4 hours.
  • GridPP:
  • IN2P3: Schedule downtime Wed morning. Batch queues will start draining on Tue around 22:00 CEST.
  • JINR:
  • KISTI: 10Gb link enabled last Friday, all link tests successfully done during the last weekend (thanks to Edoardo Martelli, Latchezar Betev and Costin Grigoras). For the moment ALICE raw replication to KISTI's tape is on-going (~210TB) and they are observing a good performance of the link from KISTI and CERN (transfer rate up to 8Gbps).
  • KIT: NTR
  • NDGF: NTR
  • NL-T1:
  • NRC-KI:
  • OSG: waiting GGUS:112737 (now closed)
  • PIC:
  • RAL: NTR
  • RRC-KI:
  • TRIUMF: NTR

  • CERN batch and grid services: Problem with CE405, was removed from production. Apparently the issue was fixed after a reboot.
  • CERN storage services: EOSCMS namespace restart at 9:00 CEST (5min intervention)
  • Databases:
  • GGUS:
  • Grid Monitoring:
  • MW Officer: Last week a major upgrade of torque arrived in EPEL (from torque-2.5.7 to torque-4.2.10) . The new torque version is not compatible with the standard EMI torque installation. Therefore sites are advised to not update for the time being otherwise the installation will break (some sites already reported this problem i.e. GGUS:113279) . For sites that have already upgraded, the previous version of torque has been pushed to the EMI third-party repo in order to downgrade and will be also pushed soon to UMD third-party

AOB:

Thursday

Attendance:

  • local: Luca (SCOD+Storage), Ulrich (Batch), Maarten (ALICE), Stefan (LHCb)
  • remote: David (ATLAS), Christoph (CMS), Lisa (FNAL), Michael (BNL), Rolf (IN2P3), Pavel (KIT), Rob (OSG), Tiju (RAL), Sang-Un (KISTI), Di Qing (Triumf)

Experiments round table:

  • ATLAS reports (raw view) -
    • mc15 digi+reco ongoing, working on increasing number of events in each job to improve efficiency
    • Network issue at RAL affecting FTS transfers

  • CMS reports (raw view) -
    • Utilizing mainly all Grid CPU resources available for CMS (~100k-110k cores)
    • No major issues

  • ALICE -
    • NTR

  • LHCb reports (raw view) -
    • Operations dominated by MC jobs and user analysis
    • T0:
      • VOMS server retirement on Tuesday, all ok
    • T1:

Sites / Services round table:

  • ASGC:
  • BNL: NTR
  • CNAF:
  • FNAL: NTR, FNAL will provide a SIR about the CMS file loss reported on Monday.
  • GridPP:
  • IN2P3: Downtime for batch system finished.
  • JINR:
  • KISTI: Scheduled downtime on the link to CERN. Occasional disconnections that affected KISTI services. The Link will be effective from the 1st of May.
  • KIT: NTR
  • NDGF:
  • NL-T1: NTR
  • OSG: NTR
  • PIC: Two new firewalls were put in production last Tuesday. Also, we upgraded dcache from 2.10.20 to 2.10.25. Everything went fine. We do expect another downtime in about 3 weeks to finish the new routing configuration in PIC. This will allow us to cope with future network work, such as enabling IPv6 dual-stack on disk pools.
  • RAL: Patching of the ATLAS Frontier DB next Tue from 9:00 to 13:00 localtime. Next Monday RAL people won't be able to join this meeting since in UK is public holiday.
  • TRIUMF: NTR

  • CERN batch and grid services:
  • CERN storage services:
  • Databases:
  • GGUS:
    • As announced last week, new release deployed yesterday. All the test alarms have been acknowledged
  • Grid Monitoring:
  • MW Officer:

AOB:

  • edg-mkgridmap bug affecting services that support the dzero VO
    • the dzero VOMS server has had an empty entry since Apr 1st (GGUS:113371)
    • such an entry will cause edg-mkgridmap < 4.0.2 to crash and thereby prevent updates of the grid-mapfile
    • at the time of writing, the VOMS service manager did not yet manage to remove the bad entry
    • the bug is fixed in edg-mkgridmap-4.0.2 currently available in these repositories:
    • EPEL and UMD will be updated later

-- AndreaSciaba - 2015-02-27

Edit | Attach | Watch | Print version | History: r15 < r14 < r13 < r12 < r11 | Backlinks | Raw View | WYSIWYG | More topic actions
Topic revision: r15 - 2015-04-30 - MaartenLitmaath
 
    • Cern Search Icon Cern Search
    • TWiki Search Icon TWiki Search
    • Google Search Icon Google Search

    LCG All webs login

This site is powered by the TWiki collaboration platform Powered by PerlCopyright & 2008-2019 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding TWiki? Send feedback