WLCG Management Board #339

Europe/Zurich
513/R-068 (CERN)

513/R-068

CERN

19
Show room on map
Description

16:00 CERN/10:00 EDT/09:00 CDT

URL for the ZOOM call: https://cern.zoom.us/j/66011416092  (the passcode has been distributed by email)

To join by phone (see the dedicated support page):
1) dial your local ZOOM number (e.g. +41432107108) then enter the MB meeting ID  660 1141 6092 then #
2) mute your phone (there is no auto-mute facility)
Note: calls are charged to the caller (there is no callback facility)

Email Distribution List: worldwide-lcg-management-board@cern.ch
Email List Archive: worldwide-lcg-management-board (requires CERN authentication)
Minutes: Management Board Meeting Minutes
Action List: MbActionList
See also the: WLCG Document RepositoryWLCG Web Site

Zoom Meeting ID
66011416092
Host
Andrea Sciabà
Alternative hosts
Simone Campana, Maarten Litmaath
Useful links
Join via phone
Zoom URL
    • 16:00 16:05
      Minutes and Matters Arising 5m
      • C-RSG report [draft] has been distributed to the experiments on Mar 26th

        • ATLAS and LHCb untouched and happy with the outcome

        • CMS and ALICE had some exchanges with the committee, in view of some cuts (disk, mostly) – O(10 PB)

      • RRB on the week of Apr27th, with the WLCG session on the 28th

        • The WLCG-RRB doc has been promptly uploaded, thanks to the contributors and Cath

      • First handshake on the Jun LHCC sessions (first week of June)

        • No focus session expected

        • Standard Experiments’ talks + a review of HSF (under discussion)

        • Some specific questions to the experiments drafted + more to come

        • WLCG: we “promised” a report on the ongoing acquisitions (== resource prices). So it is vital to get info (even preliminary, under NDA, whatever …) from you → Andrea Sciaba’

      • Access to GPUs  (and heterogeneous resources in general) is a hot topic, in many meetings we are into and in many more we hear about. We are working on a proposal, and will start speaking with stakeholders asap.

      • On collecting PUE info from sites: I was reminded of a discussion on adding PUE as a (user editable) field in CRIC. This sits as an idea in the Sustainability Forum, and would need to be implemented by the CRIC team. The two groups should get in touch and report (a single line report is ok!) for the next MB.

      • Matters arising from Edoardo in the LHCONE AUP – he cannot attend since as many others is at the LHCONE meeting in Montreal

      • LHCOPN and LHCONE updates 1m
        Speaker: Edoardo Martelli (CERN)

        Edoardo apologise he cannot attend today's meeting because travelling to the LHCOPN/ONE meeting venue.

         

        LHCOPN IPv4 removal

        NDGF  removed IPv4 from its LHCOPN links to CERN on the 30th of March 2026.
        Soon after some problems were detected  ("..something is wrong with Sikt/Bergen and their compute jobs there stopped to be able to access data after this change."), so NDGF has restored its LHCOPN IPv4 connectivity on the 7th of April 2026

        PL-NCBJ has removed IPv4 from its LHCOPN link on the 13th of April.

         

        LHCONE AUP revision

        Few comments received, mainly about the definition of the entity that can connect to LHCONE: "Physics Lab" seems too be too restrictive, since it doesn't include HPC centres hired by a collaboration. 
        Other comments were about the collaborations which can join LHCONE, which "MUST be related to Particle Physics": Particle Physics may be too restrictive and could be changed to "Fundamental Research".
        And a clarification on flow data that can be shared among NRENs because it does not have personal information: t would be good to indicate that whatever element that is tolerated should remain compatible with the sharing flows principle.

        These points will be clarified at the LHCONE meeting in Montreal this week. 

         

    • 16:05 16:10
      Action List Review 5m
    • 16:10 16:20
      WLCG Service Report 10m
      Speaker: Maarten Litmaath (CERN)
    • 16:20 16:30
      TCB Report 10m
      Speakers: Alessandro Di Girolamo (CERN), James Letts (Univ. of California San Diego (US))

      OTF#9 (March 24-25, 2026)

      OTF#9 took place on March 24-25 at CERN [Indico] on the topics of the evolution of XRootD on Tuesday and WLCG accounting, information systems, and DC27 on Wednesday. There are comprehensive Live Notes attached to the Indico page. 

      XRootD: One of the main takeaways from the XRootD session was the need for a more regular stakeholder engagement process, though the experiments and ROOT developers expressed positive opinions of XRootD performance. The XRootD work plan was grouped into a short list of milestones (work in progress) including deploying the new monitoring before DC27, other performance challenges, etc. 

      WLCG Accounting: The second day focused on accounting evolution, where we heard from WLCG Operations on the evolution of the accounting system, which has been made all the more urgent by the end of life of the EGI accounting system at the end of June. The replacement consists of two components, AUDITOR and PEAR, which are the site probes and central accounting components, respectively. OSG uses GRAAC so the U.S. sites are not directly affected, though there is some development work needed on the OSG side to interface with the new system. 

      CRIC: Next we heard about the evolution plans of CRIC, the Computing Resource Information Catalogue. There is an ongoing migration to python3 that will continue during LS3. Much new information can be stored in CRIC, such as GPU resource information which will be able to be picked up by pilot submission systems. Power usage efficiency is now being recorded in CRIC (sustainability topic). There is also a proof of concept to put the FTS configuration in CRIC, but this will be done for FTS4 pending discussions with the developers. Finally, the careful use of AI agents is being explored.

      DC27: Lastly, we heard from DOMA on the scope and scheduling of the next WLCG Data Challenge, DC27. The proposed dates are February 23 - March 6, 2027. A final decision (depending on FTS4 being released) could be made at the November HSF-WLCG Workshop [Indico], which could also serve as the pre-challenge workshop meeting. The first thing to focus on now is the target transfer rate, noting that production traffic in recent months has reached the peak levels of DC24 already.

      OTF#10 (April 21, 2026)

      The TCB continues to prepare for OTF#10, which will be co-hosted with HEPiX at their Spring Workshop in Lisbon [Indico] focusing on the mid- to long-term evolution of sites. Agenda topics include operational effort at sites, tape evolution and performance (report from OTF#8 [Indico]), and storage capacity vs. throughput. There will also be a session with presentations of site evolution plans from U.S. CMS and IHEP (China), which combined with information from other sites shown in OTF#4 last year [Indico] can be used to form the basis of Chapter 2 of the WLCG Technical Roadmap on Facility Evolution. There will also be a panel discussion on deploying services with k8s.

      WLCG Technical Roadmap

      Significant progress has been made on most chapters of the Roadmap in anticipation of a plenary talk at CHEP26 in late May. There will be a practice talk at OTF#11 in mid-May.

    • 16:30 16:35
      AOB 5m
      • Next MB Meeting: Tuesday 19 May 2026 1m