RAL Tier1 Experiments Liaison Meeting

→ Europe/London
Access Grid (RAL R89)

Access Grid

RAL R89

Zoom Meeting ID
66811541532
Host
Alastair Dewhurst
Useful links
Join via phone
Zoom URL
    • 13:30 → 13:34
      Site Operations 4m
    • 13:34 → 13:35
      Experiment Operational Issues 1m
    • 13:35 → 13:40
      ATLAS Operations Report 5m
      Speakers: Brij Kishor Jashal (Rutherford Appleton Laboratory), Jyoti Prakash Biswal (Rutherford Appleton Laboratory)
    • 13:40 → 13:45
      CMS Operations Report 5m
      Speaker: Katy Ellis (Science and Technology Facilities Council STFC (GB))

      A quiet period over the holidays with not much to report. 

      Again seeing significant discrepancies between CMS monitoring and Vande regarding the number of running cores. This is consistent with particularly low 'job time ratios' measured by Vande (went as low as the 40-50% bracket). Reported this to CMS and they spotted a misconfigured workflow using 16 GB of RAM for single core job. This was corrected to 4 GB per core on Monday afternoon. I'm monitoring and the situation has improved slightly but not dramatically. Perhaps the correction is taking time to get through the system. There are some workflows that apparently do have large memory requirements but I think it's worth reporting this when spotted. 

      Performance in the last 7 days : job efficiency has been pulled down due to picking up analysis jobs during a few days. 

      Have started tape testing for CMS - started with RAL yesterday and things looked good on first analysis. 130 failures in 11k successful transfers. 

    • 13:45 → 13:50
      LHCb Operations Report 5m
      Speaker: Alexander Rogovskiy (Rutherford Appleton Laboratory)

      General news:

      • Relatively quite break
        • Issue with two DFC servers affected uploads and deletions from all sites on the 1st of January
        • A couple of buggy productions were submitted
      • Reprocessing campaign is ongoing
        • Final staging round started yesterday
      • LHCb is running ~40k jobs at RAL for the last couple of weeks!

       

      Issues:

      • Failed transfers from RAL to MIT
        • Expired certificate + old xrootd version @MIT (old xrootd version cannot handle token scopes properly), not our fault
    • 13:50 → 13:55
      ALICE Operations Report 5m
      Speaker: Alexander Rogovskiy (Rutherford Appleton Laboratory)

      Data distribution start is imminent.

    • 13:55 → 14:00
      LSST Operations Report 5m
      Speakers: Mathew Sims, Timothy Noble (Science and Technology Facilities Council STFC (GB))
      • IngestD (ingests data as it arrives at RAL into the MetaData database) was deleted before christmas by mistake from outside RAL interactions with the cloud
        • Running agian before christmas break, and running stable
      • No jobs to RAL or other sites unless they were orgainised by non-campaign management team
        • No data as far as I can tell either
        • Campaign management now back from break, and will be starting again soon
      • dp2_prep ingesting 10,000k zip files remaining to ingest (ingested 40k - each with 200 files inside), as well as 45K yaml files - nearing complete dataset
        • hoping in the future the ingestD will be used for this.
        •  
    • 14:00 → 14:01
      Tier-1 Projects 1m
    • 14:02 → 14:07
      Anatares Upgrade 5m
      Speakers: George Patargias, Thomas Byrne
    • 14:08 → 14:13
      XRootD Development 5m
      Speakers: Alexander Rogovskiy (Rutherford Appleton Laboratory), Jyothish Thomas (STFC)
    • 14:14 → 14:19
      Utilizing GPUs 5m
      Speakers: Jyoti Prakash Biswal (Rutherford Appleton Laboratory), Thomas Birkett
    • 14:20 → 14:25
      SSD Storage Evaluation 5m
    • 14:25 → 14:26
      AOB 1m
    • 14:27 → 14:36
      Summary of Operational Status and Issues 9m
      Speakers: Brian Davies (Science and Technology Facilities Council STFC (GB)), Darren Moore
    • 14:45 → 14:50
      Any other Business 5m
      Speakers: Brian Davies (Science and Technology Facilities Council STFC (GB)), Darren Moore