Week of 150629

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: Asa (ASGC), Belinda (storage), Ken (CMS), Kuo-Hao (ASGC), Maarten (SCOD + ALICE)
  • remote: Di (TRIUMF), Kyle (OSG), Lisa (FNAL), Onno (NLT1), Pavel (KIT), Pepe (PIC), Rolf (IN2P3), Tiju (RAL), Vladimir (LHCb)

Experiments round table:

  • ATLAS reports (raw view) -
    • excused because of ongoing SW and Computing Week
    • no major issues were reported

  • CMS reports (raw view) -
    • I think that there is nothing of note today. No new GGUS tickets to T0 or T1. I hope I'm not missing anything.

  • ALICE -
    • CERN: network incident Fri evening caused all CERN VOBOXes to become unreachable and the site to go empty the whole weekend
      • fortunately no urgent work needed to run at CERN
      • the issue revealed a bug in the AliEn ARC client, which kept submitting a huge amount of jobs
      • team ticket GGUS:114671 solved Mon morning
      • jobs ramping up again since 13:00 CEST
    • Onno: since Fri there have been tens of thousands of dCache movers concurrently active for ALICE - that does not look right
    • Maarten: NDGF have just alerted ALICE about a similar problem; this will be followed up after the meeting
      • the issues at both sites were caused by a large number of faulty jobs
      • the jobs were killed, so the mover load should be going down again
      • the owner of the jobs will debug his code

  • LHCb reports (raw view) -
    • Validating Data Processing workflows. User and MC jobs on the grid.
    • T0
    • T1
      • LHCb VO-box at GridKa upgrade to sl6 request (GGUS:114360)
        • Pavel: there is a plan to do the upgrade; will ping my colleagues
      • Problem at worker nodes at RAL (GGUS:114659)
        • see RAL report below
      • RRCKI does not accept proxies generated by DIRAC (GGUS:114684)
        • Vladimir: they need to upgrade the host from SL5
        • Maarten: we may start seeing other such issues, due to incompatibility with more recent openssl versions on SL6 and now even CentOS7 (myproxy.cern.ch)

Sites / Services round table:

  • ASGC: ntr
  • BNL:
  • CNAF:
  • FNAL: ntr
  • GridPP:
  • IN2P3: ntr
  • JINR:
  • KISTI:
  • KIT: ntr
  • NDGF:
  • NL-T1:
    • downtime on Thu for dCache updates
  • NRC-KI:
  • OSG: ntr
  • PIC: ntr
  • RAL:
    • We are working on a problem on one set of worker nodes that is affecting LHCb jobs. GGUS:114659
  • TRIUMF: ntr

  • CERN batch and grid services:
  • CERN storage services:
    • transparent CASTOR upgrades are foreseen next week; more details to come
  • Databases:
  • GGUS:
  • Grid Monitoring:
  • MW Officer:

AOB:

Thursday

Attendance:

  • local: Alessandro F (storage), Andrea (MW Officer), Belinda (storage), Ken (CMS), Maarten (SCOD + ALICE), Steve (batch and grid), Thomas (KIT)
  • remote: Doug (ATLAS), Jeff (NLT1), John (RAL), Lisa (FNAL), Rolf (IN2P3), Vladimir (LHCb)

Experiments round table:

  • ATLAS reports (raw view) -
    • ATLAS is seeing lost files (all derived data which can be re-recreated, but still not good) and is actively debugging. This is due to interaction between Rucio/FTS, something in Rucio, something in FTS: observed wrong duplicated messages from FTS, but also Rucio has something not perfect on which people are working.
    • SARA-MATRIX GGUS:114787
      • tape failures understood: SARA is in a scheduled downtime
      • Doug: it appears the downtime was not caught by our transfer system; to be understood

  • CMS reports (raw view) -
    • More work is coming into the system!
    • GGUS:114712 -- more fun with the xrootd global redirector. Number of threads for the cmsd process have been increased, hopefully that will solve it. But it was noticed by the wrong person...we will have to work on this.
    • GGUS:114777 -- transfer problems from FNAL. Believed to be a problematic dCache pool; investigating.
      • Lisa: so far we do not know what is going on, but transfers are slow; the network configuration was checked
    • Transfers to various sites failing due to expired Spanish CA root certificate. Affected sites, including CERN, were ticketed.
    • There is a good chance I won't be able to attend this meeting next week, but I will write a report here.

  • ALICE -
    • CERN
      • IT-DSS have set up a few gateway hosts for the raw data export from CASTOR
        • thanks in particular to Andreas Peters!
      • needed for transfers to sites with Xrootd < 3.3.6
        • all sites are asked to upgrade, particularly the T1
        • Xrootd >= 4.1 also brings IPv6 support that will become important
      • using 500 parallel transfers the gateways allowed 50 TB to be transferred to KISTI in ~1 day at an average rate of 616 MB/s!

Sites / Services round table:

  • ASGC:
  • BNL:
  • CNAF:
  • FNAL: nta
  • GridPP:
  • IN2P3: ntr
  • JINR:
  • KISTI:
  • KIT:
    • today during the night about 1/4 of the WN lost connectivity to outside; the issue has been fixed
  • NDGF:
  • NL-T1:
    • The dCache downtime at SURFsara progresses according to plan. The RC4 cipher has been turned off, clients that still depend on this might experience failed transfers.
  • NRC-KI:
  • OSG:
  • PIC:
  • RAL:
    • we think the CVMFS issue for LHCb has been fixed earlier today; to be confirmed
  • TRIUMF:

  • CERN batch and grid services:
    • the Stratum-0 server for CMS has been upgraded so that its catalog could be defragmented
    • the issue with the expired Spanish CA was due to a change in the tree structure of the IGTF rpm repository that was not caught by the mirroring to our repository
  • CERN storage services: ntr
  • Databases:
  • GGUS:
  • Grid Monitoring:
  • MW Officer: ntr

AOB:

Edit | Attach | Watch | Print version | History: r5 < r4 < r3 < r2 < r1 | Backlinks | Raw View | WYSIWYG | More topic actions
Topic revision: r5 - 2015-07-02 - 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