Week of 170724

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: Kate (WLCG, chair, DB), Maarten (ALICE, WLCG), Vincent (security), Ken (CMS), Julia (WLCG), Marian B (network)
  • remote: Chi-Hsun (ASGC), Di Qing (TRIUMF), Jens (NDGF), John K (RAL), Onno (NL-T1), David B (IN2P3), Nurcan (ATLAS), Sang Un (KISTI), Elena (CNAF), David M (FNAL), Vincenzo (EGI), Xin Zhao (BNL), Kyle (OSG)

Experiments round table:

  • ATLAS reports ( raw view) -
    • Activities:
      • Grid is occupied with Monte-Carlo production mostly, ~300k slots of running jobs, with spikes at 700k when the HPCs (NERSC_Edison_2) run.
        • Maarten asked if NERSC is permanent. A: for the moment only spikes are expected.
    • Issues
      • No major issues. Taiwan network outage last week due to ipv6 dns resolution issue (GGUS:129603).

  • CMS reports ( raw view) -
    • A pretty quiet week as far as I could tell
    • Spiky usage of global pool waiting for start of large campaign (that was written last week, still true)
    • cmsd process at CERN T2 apparently got stuck, GGUS:129683. Happened on Saturday, didn't get addressed until Monday. Yes, not a critical service, shouldn't be treated as an emergency, but still annoying (at least to me) as CERN is an important site for many users. cmsd is run by EOS team.
    • Usual low-level issues, but not many tickets generated during the week.

  • ALICE -
    • Very high activity
    • CERN: ce505 and ce506 crashed on Sunday, ~18k jobs were lost

Sites / Services round table:

  • ASGC: Network issue is almost resolved, investigation is ongoing.
  • BNL: NTR
  • CNAF: NTR
  • EGI: NTR
  • FNAL: NTR
  • IN2P3: NTR
  • JINR: NTR
  • KISTI: NTR
  • KIT: nc
  • NDGF: There will probably be a Java/kernel upgrade this week for dCache head nodes and pools. Should be mostly invisible for the experiments (except for the pools restarts).
  • NL-T1:
    • After last Tuesday's network maintenance, we had three issues causing transfer failures:
      • We had an error in the routing table on a few dCache nodes;
      • Cumulus was installed on many routers. We ran into a Cumulus bug: one of our IPv4 subnets is a /16, and Cumulus was trying to create ARP table entries for this entire subnet, even though this subnet does not contain any active addresses. The ARP table rapidly filled up, blocking new entries. The switches then started putting traffic through CPU instead of ASIC, causing packet loss. Our workaround is to disable this subnet because we don't use it yet. Cumulus has recognised this bug and will fix it.
      • A routing configuration error caused some IPv6 traffic to fail.
    • IPv4 traffic was stable from Thursday around 17:00 CEST; although LHCb reports still 2% failures in GGUS:129622.
    • IPv6 traffic was stable from Friday around 14:30 CEST.
    • We hope this operation ends a lot of networking misery caused by the badly supported Qfabric platform.
  • NRC-KI: nc
  • OSG: The issue of downtimes not being propagated to AGIS is still being tracked
  • PIC: NC
  • RAL: Downtime of CASTOR tomorrow morning.
  • TRIUMF: NTR

  • CERN computing services: nc
  • CERN storage services: nc
  • CERN databases:
    • PGA memory leak bug affecting ALICE and LHCb online databases, causing WinCC session failures. Oracle Support quickly provided a patch. The patch was applied to ALICE online DB on Tuesday 18th July, and to LHCb online DB today, Monday 24th July. This resolved the issue.
  • GGUS:
    • On Wed this week a new GGUS release will be deployed
    • A downtime has been declared for 06:00-09:00 UTC
    • The usual alarm tests will be done after the intervention
  • Monitoring:
    • NTR
  • MW Officer:
  • Networks:
    • JINR network performance issue (GGUS:129544) - visible improvement seen since 18th of June (starting around 10am) right after the link went from backup to primary. In case the performance issues come back, a concrete plan of testing can be proposed and performed in collaboration with JINR.
  • Security: NTR

AOB:

Edit | Attach | Watch | Print version | History: r16 < r15 < r14 < r13 < r12 | Backlinks | Raw View | WYSIWYG | More topic actions
Topic revision: r16 - 2017-07-24 - 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