NT1 bi-weekly meeting

Wednesday 31 Mar 2021, 14:00 → 15:05 Europe/Copenhagen

Meeting slot for discussions, report on some cool technologies, coming changes , follow-up on activities, etc.

 Zoom link

Present: Erik, Mattias, Oxana, Jens, Darren, Krishnaveni, Christian, Petter, Vincent
Absent: Norway aka Maiken ;), Ville

Next All hands meeting: 1st week of May. Monday -  Wed: 3rd-5th May

NT1 evaluation:

• Need input from each site for resource location and description. Please check/Fill the table.
• Ask input to NLCG and site management for funding, budget and operational costs

About Reliability & Availability measured by WLCG:

• For now, OoD should proactively check the page https://monit-grafana.cern.ch/d/000000619/wlcg-sitemon-historical-profiles?orgId=20&from=now-7d&to=now&var-vo=atlas&var-profile=ATLAS_CRITICAL&var-dst_tier=1&var-dst_country=All&var-dst_federation=All&var-dst_experiment_site=NDGF-T1&var-service_flavour=All&var-dst_hostname=All&var-recomputation=status
• For medium term, Investigate if the information can be programmatically extracted from Grafana
• About the mitigation issue wrt dCache pool, Jens will check if the same local pool tests done at snic can be done on NT1

Next meeting: CI/CD for ARC (Maiken): April 14th

• Clash with GDB. Check maybe for another date.

AOB:

• New protocol (AMS) enabled and enforced in APEL to post accounting report before it was STOMP (Oxana). Erik confirmed that SGAS used it since few months. The probe checking the consistency between APEL and SGAS  is fine(sure ?).

1st FitSM discussion:

• We have extended our knowledge with plenty of new acronyms  
• Having NT1 FitSM certified is not requested by WLCG. New communities might request it 
• Some part of FitSM are relevant for NT1:
  • Service catalog, portofolio SLAs and support channel for possible new communities
  • Some procedures like Incident management
• Need to streamline the current incident procedure for ALL NT1 components

To be followed up..

14:00 → 14:05 News

Speaker: Vincent Garonne (University of Oslo (NO))

• NeIC Survey:
  • "Post-pandemic challenges and how to tackle them": https://forms.gle/huEBUE1EVmJoSvre9
• Spring All hands meeting:
  • Tentative Slots:
    • 1st week of May. Monday -  Wed: 3rd-5th May
• NT1 evaluation still ongoing:
  • https://drive.google.com/drive/u/0/folders/18tN7K6033Gnne77S7K8OCF3unZTdkls_
  • Need input from each site for resource location, purchase, funding, personnel, electricity, etc.
  • See table at the end: https://docs.google.com/document/d/1q4O5bwKPZVHF6QRQLWBA4ZG14zVLzAJ-JDymqT1iGDQ/edit#

Highlights:

• SRR has been enabled in dcache@prod/preprod
  • Details: https://source.coderefinery.org/NT1/Operations/-/issues/91
  • GGUS Red ticket should be updated:
    • https://ggus.eu/index.php?mode=ticket_info&ticket_id=144516
    • ATLAS has already confirmed the contents of SRR

• 87.90% of Reliability & Availability for February v.s.  >99% by SLA

  • Grafana link
  • Reason: SAM tests ended up on ceph-osd10.grid.uio.no with the wrong port opened
  • Mitigation ticket: https://source.coderefinery.org/NT1/Operations/-/issues/136 
  • OoD should check the link above from time to time
    • Last 7 days report

Next meeting:

• CI/CD for ARC Maiken: April 14th

AOB:

14:05 → 14:25 Post FitSM training discussion

• What did we learn ?
• How to implement it ?
• Tools ?
• Re-make operational procedures page ?
  ** https://source.coderefinery.org/NT1/management/-/issues/6

Speaker: Mattias Wadenstein (NeIC)