Week of 170320

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




  • local: Luca (SCOD+Storage), Andrew (LHCb), Kate (DB+CMS), Andrei (DB), Gavin (Computing), Alberto (Monitoring)
  • remote: Stephan (CMS), Xin (BNL), Luca (CNAF), David (FNAL), Vincenzo (EGI), David (IN2P3), Victor (JINR), Dimitri (KIT), Dmytro (NDGF), Onno (NLT1), Kyle (OSG), Pepe (PIC), Gareth (RAL)

Experiments round table:

  • ATLAS reports ( raw view) -
    • ATLAS Software&Computing week last week. A parallel session on Docker Containers and Singularity with good interest.
    • Reprocessing jobs put heavy load on the Frontier/squid from merge jobs last week, one issue identified, condition data folders with missing cache tag, one folder was fixed and tested, lowered the load at some level, other folders with the missing cache tag need to be scanned.
    • Load on the Tier-0 Frontier on Friday and during the weekend when reprocessing of ~10 cosmics runs submitted with ~4500 parallel running jobs, under investigation.

  • CMS reports ( raw view) -
    • no major issues
    • Mid Week Global Run #3 last week
    • Phase 1 upgrade Monte Carlo generations in progress
    • Argus server outage at CERN Saturday 9:00 to 20:00 wasn't caught late on CMS side.

  • ALICE -
    • CERN: alarm ticket GGUS:127202 on Sat
      • Job submissions stopped due to Argus not working
    • CERN: CASTOR overloaded by reco jobs at CERN and T1 sites (GGUS:127203)
      • Cured by limiting the number of parallel transfers + request queuing

  • LHCb reports ( raw view) -
    • Activity
      • MC Simulation, Stripping
      • Database backup locking and long queries from us on Friday caused severe distribution to LHCb production management system over weekend and into today, both for data and MC. A lot of manual work has been done to resolve inconsistencies.
    • Site Issues
      • T0:
        • ALARM ticket GGUS:126874 about users running out of AUP signature validity. User AUP validity overwritten with admin rights. No update since 9th March.
        • GGUS:127148 has jobs being killed (rather than just limited by cgroups) when using more than 2GB of physical memory when there is contention. LHCb VO ID card requests 4GB of virtual memory and jobs typically work with significantly less than 2GB RSS for almost all of their duration.
      • T1:
        • FZK: Some ongoing issues with submission timeouts to the new ARC CEs with arc-2-kit not working at all (GGUS:127075). Also GGUS:127122 with transfer timeouts causing lots of queued transfers in our production system.
        • CNAF: GGUS:127129 had a number of file transfer failures but this problem seems to be ok now. We have also had files which appear to have been transferred successfully but aren't there in reality, but this appears to be a consequence of the database problems we had on Friday rather than due to CNAF.

Sites / Services round table:

  • BNL: reminder of the dCache upgrade on this Wed/Thu, more details are in the downtime announcement.
  • CNAF: IPV6 Readiness: we are booting a dual stack test CE for internal use only after that we'll boot also a SE, if this works we need to agree on some date to expose these services and on which jobs might fail constantly.
  • EGI: NTR
  • FNAL: issue with upgrade of xrootd (4.6.0), clients not able to talk with dCache 2.13. Rolled back to 4.5.7
  • IN2P3: Scheduled maintenance tomorrow March 21st: site disconnected from 6:00 to 7:00 UTC to change external router; services (CEs, SEs) in downtime for the whole day
  • KISTI:
  • KIT: network problem (~1h) on Friday
  • NL-T1: NTR
  • NRC-KI:
  • OSG:
    • following up on ticket exchange issue (looping)
    • OSG BDII will be decommissioned on the 4th April
  • PIC:
    • 10% of the worker nodes running HTCondor
    • scheduled update of dCache doors due to a vulnerability
  • RAL: Planning to update Castor SRMs for LHCb on Thursday of this week (23rd March).

  • CERN computing services:
    • ARGUS certificate expired OTG:0036538 (email was lost in deluge) - automated renewal for Grid certs on the configuration service todo list.
    • Instabilities in CREAM CEs.
  • CERN storage services:
    • CASTORCMS affected by DB issue
    • CASTORALICE overloaded GGUS:127203
  • CERN databases:
    • LCGR database migration to new hardware OTG:0036148
    • ATLR database migration to new hardware OTG:0036429
    • CMSR database migration to new hardware OTG:0036368
    • CMSONR database migration to P5 hardware postponed until the 1st week of April OTG:0036369
    • ALICE Online database (ALIONR) was powered off from Wednesday evening to Friday midday in a scheduled intervention due to the planned power instability in the ALICE pit
    • Castor CMS stager DB not accessible from 23:46 on Sunday for approx 45 minutes. OTG:0036537
  • Monitoring:
    • Final reports for the February 2017 availability sent around
    • Full downtime for 2 hours on 15th of March due to a scheduled hardware upgrade of the LCGR database cluster. OTG:0036400
  • MW Officer:
  • Networks: LHCOPN/ONE routers update to fix vulnerability OTG:0036544
  • Security: NTR


This topic: LCG > WebHome > WLCGCommonComputingReadinessChallenges > WLCGOperationsMeetings > WLCGOpsMeetingWeek170320
Topic revision: r26 - 2017-03-20 - LucaMascetti
This site is powered by the TWiki collaboration platform Powered by PerlCopyright & 2008-2021 by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
or Ideas, requests, problems regarding TWiki? use Discourse or Send feedback