RAL Tier1 Experiments Liaison Meeting

Wednesday 15 Jul 2026, 13:30 → 15:50 Europe/London

Access Grid (RAL R89)

1 Site Operations

13:34 Experiment Operational Issues

2 ATLAS Operations Report

Speakers: Brij Kishor Jashal (Rutherford Appleton Laboratory), Jyoti Prakash Biswal (Rutherford Appleton Laboratory)

Brij ATLAS liason meeting notes of the week

3 CMS Operations Report

Speaker: Katy Ellis (Science and Technology Facilities Council STFC (GB))

Katy sends apologies; on A/L yesterday and today. This report written on Monday.

Jobs have good efficiency and low failure rate.

(@Brian, the low failure rate to tape has now stopped after invalidation of those 4 files with incorrect checksum value on Echo) 

The new XCache machine (svc42) as AAA proxy which is in production for more than one week, seems to be doing well. 

Still to deal with /unmerged/

4 LHCb Operations Report

Speaker: Alexander Rogovskiy (Rutherford Appleton Laboratory)

jobs.png

transfers_from.png

transfers_to.png

Operational issues:

• Xrootd proxies started to crash yesterday afternoon GGUS:1003341
  • Looks like some atlas jobs are using very long (and very strange) filenames , which causes xrootd to crash
• Simulation job failure rate is still higher than usual at RAL (and other sites)
  • Some improvement is present -- some of the jobs get correct CPUTime estimation, but not all; investigation is in progress
• Transfers accounting is broken, no transfer data since ~yesterday

5 ALICE Operations Report

Speaker: Alexander Rogovskiy (Rutherford Appleton Laboratory)

NTR.

6 LSST Operations Report

Speakers: Thomas Birkett, Timothy Noble (Science and Technology Facilities Council STFC (GB))

• LSST jobs running well, 3k cores used over the last few days
  
  
• There were IO warnings on XrootD
  
• This corrolated with either LSST or LHCb works
  • Looking at the LSST jobs and transfers, this was one of two users that are deploying different tests
    
    • One user has redeployed the same job with slight code adjustments and has not produced the same results, so give the addition of a 9TB file writing out to Echo at the same time I believe this was the other user - I will contact them and find out what the job was and if it is expected to happen again
• Data transfer to RAL going well 9TB moved
  
• LSST automated ingestion services down with the T1 K8S Cluster - resolving that now, as got the cluster back up and expect them to be back up by the end of the week (probably sooner)

14:00 Tier-1 Projects

7 XRootD Development

Speakers: Alexander Rogovskiy (Rutherford Appleton Laboratory), Jyothish Thomas (STFC)

Proxy crashing bug being looked at - this was tracked down to an XrdCeph bug failing to reject long filenames
updating workernode gateways with the latest changes
1 100G gateway on xrootd 6

8 Utilizing GPUs

Speakers: Dr Brij Kishor Jashal (Rutherford Appleton Laboratory), Thomas Birkett

9 Hardware deployment

Echo SN
WN
GPU

Speaker: Jacob Ward

14:45 AOB

10 Summary of Operational Status and Issues

Speakers: Brian Davies (Science and Technology Facilities Council STFC (GB)), Darren Moore, Thomas Birkett

Weekly Report 15 July 2026.docx

Weekly Report 15 July 2026.pdf

11 Any other Business

Speakers: Brian Davies (Science and Technology Facilities Council STFC (GB)), Darren Moore