RAL Tier1 Experiments Liaison Meeting
Access Grid
RAL R89
-
-
14:00
→
14:01
Major Incidents Changes 1m
-
14:05
→
14:06
Summary of Operational Status and Issues 1mSpeakers: Brian Davies (Lancaster University (GB)), Darren Moore, Kieran Howlett (STFC RAL)
-
14:10
→
14:11
Experiment Operational Issues 1m
-
14:15
→
14:16
VO Liaison CMS 1mSpeaker: Katy Ellis (Science and Technology Facilities Council STFC (GB))
Lazy-Download was removed to alleviate saturation of the OPN. As expected the amount of data read by the jobs on average fell drastically. This had the effect of pulling efficiency back up to ~T1 average, and also of fixing the large number of jobs that had been failing at a rate of 60% for the previous week. Performance has been good from the CMS point of view, with no issues reported from the Echo side. One small anomoly spotted was that some CMS jobs were reading from Echo via the external gateways rather than the WN gateways. This is due to the 'DNS poisoning' on the WNs not being applied to IPv6, so it seems CMS jobs that are using IPv6 are accessing data via this route.
On Jose's request, replaced the individual squids with a CMS alias. There was an error in the port number, hence the short periods of SAM test failures on Friday.
Also an issue with just one of the AAA gateways on Tues/Wed. Fixed by restart.
-
14:20
→
14:21
VO-Liaison ATLAS 1mSpeakers: Dr Brij Kishor Jashal (RAL, TIFR and IFIC), Jyoti Prakash Biswal (Rutherford Appleton Laboratory)
Unable to join due to ATLAS Away day (PPD), please find updates here
-
14:25
→
14:26
VO Liaison Others 1m
-
14:30
→
14:31
VO Liaison LHCb 1mSpeaker: Alexander Rogovskiy (Rutherford Appleton Laboratory)
LHCb:
- Suggest A&R Recalculation request for April -- tests were not working properly for all sites, this is not RAL's fault
- ETF test migration is scheduled for tomorrow!
- One WN (lcg2652) had problematic xrootd version, caused a lot of failed downloads
- A lot of LHCb pilots got stuck on the batch farm last week. But in LHCb pilot, triggered by voms (IAM) server issues.
- Xrootd bug follow up?
ALICE:
- ECHO's xrootd space reporting upddated last week
- Discussion on how to use Antares properly
-
14:35
→
14:38
VO Liaison LSST 3mSpeaker: Timothy John Noble (Science and Technology Facilities Council STFC (GB))
Jobs all green on LSST monitoring
Butler configured and running, but seems slow at times - Will look into resource provisioning for the VOBOX to ensure its not a bottleneck
US currently deploying and testing ingestDaemon, once configured and deployed correctly will deploy at the other DFs
Mat Sims is now also working on LSST so more LSST effort at RAL
-
14:40
→
14:41
VO Liaison APEL 1mSpeaker: Thomas Dack
-
14:45
→
14:46
AOB 1m
-
14:50
→
14:51
Any other Business 1mSpeakers: Brian Davies (Lancaster University (GB)), Darren Moore
-
14:00
→
14:01