ATLAS UK Cloud Support

Thursday 9 Sept 2021, 10:00 → 11:00 Europe/London

Zoom

Tim Adye (Science and Technology Facilities Council STFC (GB)), James William Walder (Science and Technology Facilities Council STFC (GB))

https://cern.zoom.us/j/98434450232

Password protected (same as (new) OPs Mtg)

● Outstanding tickets

• • 153550 TEAM atlas UKI-SOUTHGRID-RALPP less urgent NGI_UK on hold 2021-09-01 15:56:00 Transfer failure at UKI-SOUTHGRID-RALPP with “Failed to select pool: All pools are full\n” error WLCG

    • On hold to collect stats / data

  • 153414 TEAM atlas UKI-SCOTGRID-ECDF less urgent NGI_UK in progress 2021-09-03 14:18:00 UKI-SCOTGRID-ECDF: Low transfer efficiency due to TRANSFER ERROR: Copy failed with mode 3rd pull, wi… WLCG

    • Closed

  • 153367 TEAM atlas RAL-LCG2 urgent NGI_UK in progress 2021-08-04 11:55:00 HTTPS on RAL CTA WLCG

    • Needs a comment

  • 153277 TEAM atlas UKI-SCOTGRID-GLASGOW less urgent NGI_UK in progress 2021-09-03 14:25:00 UKI-SCOTGRID-GLASGOW_CEPH job stage-in failures WLCG

    • Will close once Panda is back (hopefully)

---

● CPU

• • RAL

    • Variations in slots caused by (generally?) ATLAS submissions

  • Northgrid

    • LANCS running sim; but not enough slots
      • Attempting to change some of the Associated Params in CRIC to see if more work is possible
      • New SEs and networking being discussed
      • Currently using Rocky for test work

  • London

    • Black hole WN caused errors

  • SouthGrid

    • Oxford Xcache switching set site offline for a while; some power work on portion of nodes.
      • Running fine now

  • Scotgrid

    • A couple of dips, likely ATLAS related

• Other new issues / tasks

  • BHAM - ATLAS and BHAM working on improved setup for VAC communications

 

 

---

● Ongoing Items

• CentOS7 - Sussex

  • Post-Mtg ‘hackathon’ (see AOB)

• TPC with http

  • WebDav enabled on RAL and ATLAS running in passive mode
    • OK, but with low load

• Storageless Site test (Oxford)

  • Xcache disabled for ATLAS due to issue in xrootd 5.3

 

 

---

● News round-table

• Dan
  • NTR
• Gerard
  • NTR
• JW
  • NTR
• Matt
  • NTR
• Patrick
  • NTR
• Peter
  • Interested in the brokerage for jobs at LANCS
• Sam
  • NTR
• Vip
  • NTR

 

 

---

● AOB

AOB

• Some discussion on CERN’s status regarding future linux versions

SUSSEX Hackathon

• Reviewed and updated user namespace settings
  • re(?)-applied correct settings;
  • need to check that something else doesn’t clobber them again …
• Looked at the Parallel options: openmp might be the closest to matching correct setup.
• Awaiting to be set back online to review the progress

 

 

10:00 → 10:20 Status

10:20 → 10:40 Ongoing Items

• CentOS7 - Sussex

  • Post-Mtg ‘hackathon’ (see AOB)

• TPC with http

  • WebDav enabled on RAL and ATLAS running in passive mode
    • OK, but with low load

• Storageless Site test (Oxford)

  • Xcache disabled for ATLAS due to issue in xrootd 5.3

 

 

10:40 → 10:50 News round-table

• Dan
  • NTR
• Gerard
  • NTR
• JW
  • NTR
• Matt
  • NTR
• Patrick
  • NTR
• Peter
  • Interested in the brokerage for jobs at LANCS
• Sam
  • NTR
• Vip
  • NTR

 

 

10:50 → 11:00 AOB

ATLAS Monitoring (UK Cloud)

AOB

• Some discussion on CERN’s status regarding future linux versions

SUSSEX Hackathon

• Reviewed and updated user namespace settings
  • re(?)-applied correct settings;
  • need to check that something else doesn’t clobber them again …
• Looked at the Parallel options: openmp might be the closest to matching correct setup.
• Awaiting to be set back online to review the progress