LHCONE R&D and RNT-WG call

Europe/Zurich
Edoardo Martelli (CERN), Joe Mambretti (International Center for Advanced Internet Research Northwestern University), Marian Babik (CERN), Shawn Mc Kee (University of Michigan (US))
Videoconference
Zoom Meeting ID
97610360540
Host
Edoardo Martelli
Useful links
Join via phone
Zoom URL
    • 5:00 PM 5:20 PM
      LHCONE 20m

      Jumbo Frame survey
      Agenda for meeting in Catania

      Presents: Edoardo Martelli, Carmen, Misa, Tim Chown, Justas Balcas , Bill Johnston. Richard HughesJones,, Laurent Duflot, Dale Carder, Yatish Kumar, Doug Southwotth, Tom Lehman, Phil Demar, Tristan Sullivan, Marian Babik, Jim Chen, Joe Mambretti, Harvey Newman

      DC24
      - DC24 has started. Traffic rates are not as high as the ones seen during the CMS pre-dc24 test.
      - RAL links still down for a sea cable cut, but should get fixed today 

      Jumbo Frame survey
      - Jumbo frame survey going well
      - 50 votes received. Survey will stay open for two more weeks


      Next meeting:
      - 27th of February 

    • 5:20 PM 5:50 PM
      RNTWG 30m

      Packet marking
      - CMS enabled scitags in Rucio production !
      - FTS enabled scitags for all experiments in production !
         - We were able to confirm that all this works, i.e. scitags are propagated all the way to the storages (Rucio -> FTS -> http-tpc -> Xrootd) works fine
      - EOS enabled scitags in production for almost the entire CMS cluster (80%) - this works fine !
          - Since xrootd is unable to filter local subnets/prefix, we had to setup a middle-service (collector) to catch the fireflies and forward them to ESnet (this also worked fine, but not on the first attempt)
          - The additional benefit of this is that we're able to see/compare fireflies sent/received (and for EOS it matches)
      - ESnet collector demonstrated capability to handle 15M fireflies/hour (during DC the rate from EOS CMS had peaks of ~ 100k/hour) !
      - Firefly dashboard shows fireflies from UNL and CERN at
           - https://public.stardust.es.net/d/b8dddac0-5b24-4739-9c8d-e88a05c1344f/scientific-network-tags3a-rande-dashboard?orgId=1&from=now-12h&to=now
           - Dashboard will be updated to allow filtering per src_site (update sent to Andy, waiting for it to be deployed)
           - Andy added median/max duration flow - looks very interesting - no "fat" flows from EOS CMS during DC !
           - Cross-validation with other dashboards to be done
      - Issues:
         - We hit an issue at UNL with XRootd that causes it to crash while parsing http-tpc, this is fixed in XRootd 5.6.7 
         - We notified sites (mostly in UK) to disable fireflies until they're able to upgrade to XRootd 5.6.7.
         - Unfortunatly this had a negative impact on firefly collection for UK sites during DC, but keeping transfers operational during DC has higher priority.
         - We have also postponed ATLAS Rucio scitags production, but it's up from today.
         - UNL is back in production running on 5.6.7 but reported an issue with some thread getting stuck in a loop    

       

    • 5:50 PM 5:55 PM
      AOB 5m
    • 5:55 PM 6:00 PM
      Next meeting 5m