RAL Tier1 Experiments Liaison Meeting
Access Grid
RAL R89
-
-
13:30
→
13:34
Site Operations 4m
-
13:34
→
13:35
Experiment Operational Issues 1m
-
13:35
→
13:40
ATLAS Operations Report 5mSpeakers: Brij Kishor Jashal (Rutherford Appleton Laboratory), Jyoti Prakash Biswal (Rutherford Appleton Laboratory)
-
13:40
→
13:45
CMS Operations Report 5mSpeaker: Katy Ellis (Science and Technology Facilities Council STFC (GB))
Apologies one more time, Katy is in Naples for LHCONE meeting and will not join the meeting.
From last week: On the intermittent failures on the (token version of the) CVMFS test, see https://cmssst.web.cern.ch/siteStatus/detail.html?site=T1_UK_RAL :
Alex checked it and says we are frequently contacting the Stratum-1 in Brazil. I question how often we should be contacting that host - possible issue #1. It seems that there are many retries. Asking CMS experts, they are not even aware of a Stratum-1 in Brazil. The reply from the Brazilian site shows they are a Stratum-1 for ALICE. Not many other CMS sites are seeing an error on the same test - those that are could have a different cause. Alex wondered whether there could be some issue with the network path between RAL T1 and the Brazilian site - possible issue #2. Thanks Alex for investigating. I wonder if ALCE jobs at RAL try to contact this Brazilian host? Possible solutions - fix whatever is stopping this connection with Brazil (São Paulo) or somehow stop the test trying to access it.
Job appear to be running fine.
Note that this afternoon the WLCG VOs will present their DC27 targets at the DOMA-General.
-
13:45
→
13:50
LHCb Operations Report 5mSpeaker: Alexander Rogovskiy (Rutherford Appleton Laboratory)
- 13:50 → 13:55
-
13:55
→
14:00
LSST Operations Report 5mSpeakers: Thomas Birkett, Timothy Noble (Science and Technology Facilities Council STFC (GB))
- Data access optimisations have been ongoing over the last few weeks - with pulling in the quantum graphs (job task information) and butler.yaml files that provide information on how to access the butler database
-
- Additional optimisations were implemented and tested thanks to the XrootD monitoring from Martina, helping me identify file access counts, and timeframes highlighting highly re-used files that could be cached in the job scratch space
- Upside more efficient jobs and Jyothish / Martina may not hunt me down as quickly when LSST run jobs
This has led to marked inprovement in step4c of the pipelines:
-
- Changes to where and how the butler.yaml files caused some issues, that are now resolved.
- RAL continues to run jobs well for LSST - the ~100% efficiency spike is 'legacy' dc2 testing (as its run with single core jobs submitted by Panda) where all multicore jobs are now submitted by HTCondor

- No data move to RAL over the last 2 weeks - I will follow this up after the meeting to ensure this is correct behaviour
- VOMS change for SLAC LSST Voms server, Tom is working on the change
- Data access optimisations have been ongoing over the last few weeks - with pulling in the quantum graphs (job task information) and butler.yaml files that provide information on how to access the butler database
-
14:00
→
14:01
Tier-1 Projects 1m
-
14:05
→
14:10
XRootD Development 5mSpeakers: Alexander Rogovskiy (Rutherford Appleton Laboratory), Jyothish Thomas (STFC)
-
14:15
→
14:20
Utilizing GPUs 5mSpeakers: Dr Brij Kishor Jashal (Rutherford Appleton Laboratory), Thomas Birkett
-
14:25
→
14:45
Hardware deployment 20m
Echo SN
WN
GPUSpeaker: Jacob Ward -
14:45
→
14:46
DC 27 1m
-
14:50
→
14:59
Summary of Operational Status and Issues 9mSpeakers: Brian Davies (Science and Technology Facilities Council STFC (GB)), Darren Moore, Thomas Birkett
-
15:00
→
15:05
Any other Business 5mSpeakers: Brian Davies (Science and Technology Facilities Council STFC (GB)), Darren Moore
-
15:15
→
15:16
AOB 1m
-
13:30
→
13:34