ATLAS UK Cloud Support

Thursday 5 Aug 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)

● Status

• 153405 TEAM atlas UKI-LT2-QMUL less urgent NGI_UK assigned 2021-08-04 21:38:00 UKI-LT2-QMUL squid degraded WLCG

  • • Rebooted; may need new disks if issue reappears
    • Ticket now solved

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

    • Tracking ticket for Tape tests

  • 153295 USER atlas RAL-LCG2 less urgent NGI_UK in progress 2021-08-02 09:37:00 stuck staging requests from RAL MCTAPE WLCG

    • 14 files declared as lost; unclear now whether they were never correctly transfered/staged, or otherwise lost.

  • 153277 TEAM atlas UKI-SCOTGRID-GLASGOW less urgent NGI_UK in progress 2021-07-28 13:14:00 UKI-SCOTGRID-GLASGOW_CEPH job stage-in failures WLCG

    • All should be back to normal now; Cric wan/lan settings quite complex.

 

---

● CPU

• RAL

  • 2021 pledge values now applied; awaiting some steady state to assess fairshares

• Northgrid

  • LANCS in downtime for updates

• London

  • QMUL - More nodes onlines; user namespace for singularity needed some rebooting

• SouthGrid

  • OX - Problems with Xcache over weekend; Went back to a previous configuration
  • BHAM; no jobs running for last couple of days

• Scotgrid

  • Aiming for internal switch monitoring improvements
  • Recovering after the (above) GGUS issues

---

● Other new issues / tasks

• • Major Downtime for RAL + T1 on 14/15th August

 

 

---

● Ongoing Items

• CentOS7 - Sussex

  • NTR

• TPC with http

  • Both RAL and Glasgow looking ok when Src site; more problems when acting as destination

• Storageless Site test (Oxford)

  • Following from Storage Mtg. discussions; would be interesting to get accurate / latest numbers for atlas throughputs at sites, and for particular acitvities

---

● News round-table

• Dan

  • NTR

• Gerard

  • NTR

• Matt

  • NTR;

• Sam

  • NTR

---

● AOB

• Expect to keep this mtg weekly for the Summer


 

10:00 → 10:20 Status

• 153405 TEAM atlas UKI-LT2-QMUL less urgent NGI_UK assigned 2021-08-04 21:38:00 UKI-LT2-QMUL squid degraded WLCG

  • • Rebooted; may need new disks if issue reappears
    • Ticket now solved

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

    • Tracking ticket for Tape tests

  • 153295 USER atlas RAL-LCG2 less urgent NGI_UK in progress 2021-08-02 09:37:00 stuck staging requests from RAL MCTAPE WLCG

    • 14 files declared as lost; unclear now whether they were never correctly transfered/staged, or otherwise lost.

  • 153277 TEAM atlas UKI-SCOTGRID-GLASGOW less urgent NGI_UK in progress 2021-07-28 13:14:00 UKI-SCOTGRID-GLASGOW_CEPH job stage-in failures WLCG

    • All should be back to normal now; Cric wan/lan settings quite complex.

 

10:20 → 10:40 Ongoing Items

• CentOS7 - Sussex

  • NTR

• TPC with http

  • Both RAL and Glasgow looking ok when Src site; more problems when acting as destination

• Storageless Site test (Oxford)

  • Following from Storage Mtg. discussions; would be interesting to get accurate / latest numbers for atlas throughputs at sites, and for particular acitvities

10:40 → 10:50 News round-table

• Dan

  • NTR

• Gerard

  • NTR

• Matt

  • NTR;

• Sam

  • NTR

10:50 → 11:00 AOB

ATLAS Monitoring (UK Cloud)

• Expect to keep this mtg weekly for the Summer