Week of 170206

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: Luca (SCOD+Storage), Julia (WLCG), Maarten (ALICE), Andrew (LHCb), Vincent (Security), Fernando (Computing), Marian (Network)
  • remote: Tommaso (CMS), FaHui (ASGC), Xin (BNL), Elena (CNAF), David (FNAL), David (IN2P3), Victor (JINR), Sang-Un (KISTI), Max (KIT), Christian (NDGF), Andrew (NL-T1), Kyle (OSG), Jose (PIC), John (RAL), Di (TRIUMF)

Experiments round table:

  • CMS reports ( raw view) -
    • System running full speed (200k cores in use)
      • MC for: Moriond17, 2017 Run preparation, Phase II simulations for TDRs.
      • Data: Re-miniAOD from AOD submitted on Friday, should last ~ a week
      • Analysis at 60k cores, suffering a bit. Very high demand from Moriond17 analysis preparation.
      • All in all, system under stress but coping ...
    • At the start of the week a kibana problem, solved on Tuesday INC:1268853. As usual, this makes the Computing shifters blind to most of the situation.
    • Saturday: CERN/EOS crash, recovered in hours OTG:0035500 ...
    • ... but left the CERN/EOS outside the XrootD federation, up to Sunday morning (GGUS:126380)
    • Other problems:
      • CMSWEB frontends under pressure from the high activities ... frequent alarms and some operator restarts.
      • T1_RAL with storage problems (GGUS:126376) for the whole weekend
      • Some T2 + T3 transfer errors .... I would say usual business ....

  • ALICE -
    • High activity

  • LHCb reports ( raw view) -
    • Activity
      • MC Simulation and user analysis; reco jobs starting again
    • Site Issues
      • T0:
        • Major problems with SRM for LHCb use of EOS, unable to use it for most of the weekend (GGUS:126378). This led to loss of the results from 10,000s of jobs on HLT farm as it only connects to CERN. Appears to be resolved now: initial overloading led to avalanche of failures and retries, all increasing the load. Looking at ways to avoid this with IT and within LHCb.

Sites / Services round table:

  • ASGC: NTR
  • BNL: network migration went smoothly last Monday, no interruption to production. Tested what will happen to ATLAS jobs when cern AFS is cut, by mimicking CERN no afs day condition on several WNs, no obvious bad behavior were observed (https://its.cern.ch/jira/browse/NOAFS-463).
  • CNAF: NTR
  • EGI:
  • FNAL: NTR
  • GridPP:
  • IN2P3: NTR
  • JINR: CMS cleared out many files, which resulted in large free space on tapes. Input/output data stream lowered significantly. NTR on local HW/SW functionality.
  • KISTI: NTR
  • KIT: Uploaded SIR regarding files lost on tape (reported two weeks ago), see attachment below.
  • NDGF: Upgrade of dcache headnodes during the week. Should be invisible to experiments due to HA setup and automatic failover.
  • NL-T1: Problem with DNS and LDAP caused by an internal security test
  • NRC-KI:
  • OSG: NTR
  • PIC:
    • update of Enstore scheduled for the 21st Feb (marked as at risk)
    • update of dCache scheduled for the 3rd Mar (marked as downtime)
  • RAL: Scheduled a transparent reboot of the CASTOR nameservers headnode
  • TRIUMF: There was a site wide power outage caused by snow storm yesterday starting at 2:40pm (local time), the whole Tier1 center had been down about 6 hours.

  • CERN computing services:
    • Upstream thinks to have identified the bug that affected the HTCondor CEs and we have a workaround that we plan to test.
  • CERN storage services:
    • FTS: Pilot upgrade to 3.6.0 tomorrow at 10:00 CET (OTG:0035424). Due to db schema changes not compatible with the previous version, the service will be unavailable for 1 h.
      • We already contacted ATLAS and CMS to move their production transfers using the pilot to other FTS instances.
    • SRM issues on EOSLHCB during the weekend, ongoing discussion with LHCb computing team to improve the situation
    • EOSCMS crash on saturday took longer time to recover due to a corruption in the namespace (fixed).
  • CERN databases:
  • GGUS: NTR
  • Monitoring (sorry for the absence):
    • Updated reports for December 2016 availability distributed
    • Draft reports for the Jan 2017 availability distributed
  • MW Officer: Discussed with EGI about dCache 2.10 end of support. They sent a broadcast to sites and will open tickets soon to sites asking to upgrade to 2.13/2.16.
  • Networks:
    • BNL to ASGC network performance still ongoing (ESNET-20170123-005)
  • Security: NTR

AOB:

Topic attachments
I Attachment History Action Size Date Who Comment
PDFpdf KIT_SIR_Lost_files_after_TSM_DB_storage_crash.pdf r1 manage 111.7 K 2017-01-31 - 10:34 XavierMol SIR about files lost from tape archive, because of tape management software database crash.
Edit | Attach | Watch | Print version | History: r24 < r23 < r22 < r21 < r20 | Backlinks | Raw View | WYSIWYG | More topic actions
Topic revision: r24 - 2017-02-06 - 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