RAL Tier1 Experiments Liaison Meeting

Wednesday 25 Jan 2023, 12:30 → 14:30 Europe/London

Access Grid (RAL R89)

13:00 → 13:01 Major Incidents Changes

13:01 → 13:02 Summary of Operational Status and Issues

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

Weekly Report 25 January 2023 (1).docx

Weekly Report 25 January 2023 (1).pdf

13:02 → 13:03 GGUS /RT Tickets

https://tinyurl.com/T1-GGUS-Open
https://tinyurl.com/T1-GGUS-Closed

13:04 → 13:05 Site Availability

https://lcgwww.gridpp.rl.ac.uk/utils/availchart/

https://cms-site-readiness.web.cern.ch/cms-site-readiness/SiteReadiness/HTML/SiteReadinessReport.html#T1_UK_RAL

http://hammercloud.cern.ch/hc/app/atlas/siteoverview/?site=RAL-LCG2&startTime=2020-01-29&endTime=2020-02-06&templateType=isGolden

13:05 → 13:06 Experiment Operational Issues

13:15 → 13:16 VO Liaison CMS

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

Katy planning to remove gsiftp tests from contribution to SAM status. 

 

CMS saw spikes in failures on writes to Echo on the 18th and 23rd during the DNS issues. Also SAM status failed on those days due to storage tests (gsiftp and webdav).

 

Large numbers of (Processing type) jobs failing, but this is reflected at other sites.

13:16 → 13:17 VO-Liaison ATLAS

Speakers: James William Walder (Science and Technology Facilities Council STFC (GB)), Jyoti Prakash Biswal (Rutherford Appleton Laboratory)

GGUS: 160156 

The last DNS outage 'reset' most transfers. As of this morning, 33k submitted transfers to write into Echo, + 12k files being recalled from Antares (via Echo). 

Very few failures (O(100)) in the last 24hrs where the source file had been evicted prior to transfer; We can (hopefully) resolve the ticket this afternoon if no further issues arise. 

 

DNS Failed name resolution from external hosts:

                           Last Wednesday, AM, and Monday evening.  ~ 220k transfers failed (not started). 

                           GOCDB was also affected (any other ancillary services?).

 

 

13:20 → 13:21 VO Liaison LHCb

Speaker: Alexander Rogovskiy (Rutherford Appleton Laboratory)

dc_review.pdf

1. Reading part of the tape challenge finished last week. Results look promising -- expected throughput was 1.93GB/s, we achieved ~ 1GB/s more than this.
2. There was a major LHCb Dirac update on Monday, which introduced some issues. Recovered within several hours. There were lot of failed jobs due to this.
3. Low number of running LHCb jobs due to insufficient number of production requests.
4. Consistency check identified some dark and lost data. Dark data was removed, lost files were re-replicated by (all data operations were done by the LHCb Computing team).

 

Tickets:

1. Slow checksums (stats):
   • Still waiting
2. Deletion problems
   • Solved
3. Problems with simultaneous access to the same file on ECHO
   • On hold, tests are ongoing at Glasgow
4. Vector read.
   • One more test: what happens with the LHCb applications is vector read requests returns "wrong" (i.e. not the one that was requested) data. This was tested (the same patch, but once in a 1000 vector reads it shifts one of the requested chunks by 1 byte), and it seems like the application crashes.
   • Dedicated patched WN for production LHCb jobs is being prepared.

13:25 → 13:28 VO Liaison LSST

Speaker: Timothy John Noble (Science and Technology Facilities Council STFC (GB))

13:30 → 13:31 VO Liaison Others

13:31 → 13:32 AOB

13:32 → 13:33 Any other Business

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