Week of 160919

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.

Tier-1 downtimes

Experiments may experience problems if two or more of their Tier-1 sites are inaccessible at the same time. Therefore Tier-1 sites should do their best to avoid scheduling a downtime classified as "outage" in a time slot overlapping with an "outage" downtime already declared by another Tier-1 site supporting the same VO(s). The following procedure is recommended:
  1. A Tier-1 should check the downtimes calendar to see if another Tier-1 has already an "outage" downtime in the desired time slot.
  2. If there is a conflict, another time slot should be chosen.
  3. In case stronger constraints cannot allow to choose another time slot, the Tier-1 will point out the existence of the conflict to the SCOD mailing list and at the next WLCG operations call, to discuss it with the representatives of the experiments involved and the other Tier-1.

As an additional precaution, the SCOD will check the downtimes calendar for Tier-1 "outage" downtime conflicts at least once during his/her shift, for the current and the following two weeks; in case a conflict is found, it will be discussed at the next operations call, or offline if at least one relevant experiment or site contact is absent.

Links to Tier-1 downtimes

ALICE ATLAS CMS LHCB
  BNL FNAL  

Monday

Attendance:

  • local: Maria A (chair and minutes), Julia Andreeva (WLCG), Oliver Gutsche (CMS), Mark Slater (LHCb), Maarten Litmaath (ALICE), Andrea Manzi (MW Officer), Eddie Karavakis (Monitoring), Maria Dimou (GGUS), Andrei Dumitru (DB), Iain Steers (Computing), Vincent Brillault (Security)
  • remote: Fahui (ASGC), Eric Lancon (BNL), Vincenzo Spinoso (EGI), Dave Mason (FNAL), Rolf Rumler (IN2P3), Victor Zhiltsov (JINR), Sang-Un Ahn (KISTI), Dimitri (KIT), Jens (NDGF), Onno Zweers (NL-T1), Kyle Gross (OSG), Jose Flix (pic), Tiju Idiculla (RAL).

Experiments round table:

  • CMS reports (raw view) -
    • data taking overview:
      • September 12-16: Technical Stop
      • September 17-18: restart with several problems:
        • Lost 66 kV power in IP2 with loss of cryo S12, S23. Trip of S12, S23 and S34, experimental magnets ALICE/LHCb down and MKI IP2 in fault.
      • Plans for week September 19-25
        • 2.5km beta* setup and physics for the next 4 days
        • then physics
    • production activity
      • low activity, expecting ramp-up soon
        • data rereco campaign to start this week
        • PileUp pre-mix library production
    • issues
      • FNAL downtime declared in MyOSG but did not propagate to GOCDB, informed CMS manually
        • ticket: GGUS:123876
        • Question: Shouldn’t MyOSG propagate downtimes to GOCDB automatically?
      • T2_IT_Rome GOCDB manager lost access to GOCDB after grid certificate change
      • Problems with Kibana and ES storage
      • CouchDB problems
        • Friday later afternoon our CouchDB instance on cmsweb.cern.ch started to crash, after restart keeps crashing
        • Problem is not identified yet, experts are working for it
        • Thanks to the piquet(s) for their patience
      • VM with transfer system from P5 to Meyrin was rebooted on Friday night
        • INC:1134167
        • Hypervisor hosting these VMs rebooted Friday evening. Just like 5 months ago, no obvious reason for this. Note this hypervisor will be retired in the coming two months, VMs will be migrated to newer hardware
      • Intermittent connectivity problems to outside CERN
        • OTG:0033002
        • xrootd redirectors seem to be affected
        • Any updates?

Julia asks whether the Kibana issues have been solved and Oliver confirms so.

  • ALICE -
    • central services were unavailable from Wed evening to Thu afternoon
      • a big network intervention made them unreachable for many hours
      • all grid and user activity for ALICE was stopped for that period
      • in parallel the File Catalog was moved to a more powerful new machine
    • CERN: team ticket GGUS:123929 opened Thu late afternoon
      • CREAM / LSF was not working for ALICE
      • fall-out from OTG:0032902
      • converted to ALARM Fri afternoon
      • LSF info provider issue got fixed
      • job submissions resumed late afternoon
    • KISTI: the CRL of the KISTI CA expired on Fri morning CEST
      • no new jobs could be submitted and the site gradually drained
      • the CA was contacted and the CRL got fixed on Sat

Maarten adds that the LSF information providers stopped working due to the LSF outage and this has a big impact on ALICE operations since ALICE relies on the values being published by the CREAM CEs in the BDII.

  • LHCb reports (raw view) -
    • Activity
      • Monte Carlo simulation, data reconstruction/stripping and user jobs on the Grid
    • Site Issues
      • T0:
        • EOS timeout problem over the weekend that looks like it was to do with a mass recursive deletion by a user (GGUS:123957)
        • Serious problems with LSF at the end of last week. LSF CEs were down for ~30+ hours from Thursday morning. Will there be a formal incident report? (GGUS:123937)
      • T1:
        • NTR

On a question by Mark, Iain confirms that a SIR will be provided by CERN describing the issue with the LSF master.

Sites / Services round table:

  • ASGC: Power cut last Wednesday affected many services. All recovered now.
  • BNL: NTR
  • CNAF: NA
  • EGI: Vincenzo agrees to follow up on GOCDB issues reported by CMS.
  • FNAL:
    • Tape dCache was upgraded to v. 2.13 this past Tuesday. Disk instance was upgraded in April, so now all using 2.13
    • Computing center power off scheduled over the weekend was successful and all services are now back in operations.
  • GridPP: NA
  • IN2P3: A reminder, site will be in downtime tomorrow, batch draining already tonight; see downtime declarations for details.
  • JINR: NTR
  • KISTI: NTR
  • KIT: NTR
  • NDGF:
    • Outage of storage pool containing ALICE data still on going. Moving data out of it. Some files unavailable in the next 24h.
    • dCache upgraded to v. 3.0.
  • NL-T1:
    • Reminder: SARA grid facilities will be moved to the new datacenter during the first two weeks of October.
    • We may not be able to dial in due to preparations for the datacenter move.
  • NRC-KI: NA
  • OSG: perfSONAR data store mow working normal since earlier last week.
  • PIC: NTR
  • RAL: NTR
  • TRIUMF: NA

  • CERN computing services:
    • Batch service (LSF) outage on Thursday: the service did not come back after the morning reconfig (~06.00) - the service was brought back around 10.00.
    • Corruption in the queues was found, which caused some capacity issues - this was corrected later in the afternoon. We'll followup on the configuration of LSF.
    • The CREAM CEs were affected (affecting LHCb) and the reporting to the BDII of the CREAM CEs did not recover (affecting ALICE, Alarm ticket) - the CREAM CEs were corrected on the Friday afternoon after a reboot.
    • The HTCondor batch service was unaffected.
  • CERN storage services:
    • FTS service will be upgraded next week to v 3.5.3 and moved to CentOS 7. Exact date will be discussed tomorrow with the experiments during the FTS steering meeting.
  • CERN databases:
  • GGUS: Release on 28/9 with test ALARMs as usual. Maria D. will be travelling. Please contact ggus-info at cern dot ch in case of any trouble.
  • Monitoring:
  • MW Officer: NTR
  • Networks:
  • Security: NTR

AOB:

Topic attachments
I Attachment History Action Size Date Who Comment
Unknown file formatpptx GGUS-for-MB-Sep-16.pptx r1 manage 2848.7 K 2016-09-19 - 11:26 MariaDimou GGUS slide for the 20/9 MB
Edit | Attach | Watch | Print version | History: r19 < r18 < r17 < r16 < r15 | Backlinks | Raw View | WYSIWYG | More topic actions
Topic revision: r19 - 2016-09-19 - DavidMason
 
    • 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