CHIPP-CSCS Face to Face Meeting on 2019-01-21
- Date and time: Monday 21st of January at 10:15
- Place: CSCS
- External link / EVO: Yes, Scopia. Win/Mac: https://vcmeeting.ethz.ch/ (Room: 6708238) | Linux(vidyo): sip:6708238@vc.ethz.ch | Phone gate: +41 43 244 8930 (ext 6708238 #)
Agenda
- 10:15 - Welcome, coffee and agenda
- 10:30 - VO Status report (~last 6 months + changes since last F2F, for both Phoenix and CRAY)
- LHCb (20' - Roland)
- ATLAS (20' - Gianfranco)
- CMS (20' - Thomas)
- 11:30 - Tier-2 status, plans & pledges
- CSCS (45' - Various people, for both Phoenix and CRAY)
- Discussion (30')
- 13:00 - Lunch
- 14:15 - Tier-2 status, plans & pledges
- UNIBE-LHEP (30' - Gianfranco)
- 14:45 - Tier-3 status and plans
- PSI (15' - Nina)
- UNIBE-ID (15' - Gianfranco)
- UNIGE (15' - Gianfranco)
- 15:30 - Coffee break
- 15:45 - NGI_CH (20' - Gianfranco)
- 16:05 - Tier-0 activities (10' - Pablo & Gianfranco)
- 16:15 - End of meeting
Attendants
- CSCS: Dario, Dino, Marco, Stefano, Pablo
- CMS: Christoph Grab
- ATLAS: Gianfranco Sciacca
- LHCb: Roland Bernet
Minutes
LHCb
- Higher failure rates in Daint, mostly solved
- Monitoring in the dashboard is great, more than sufficient
- [Action Roland] Data efficiency is slower on Daint, Roland will follow up on this
ATLAS
- Higher failure rates in Phoenix
- Good jobs have very good performance, mostly thanks to the new scratch
- ATLAS takes too much time to recover after downtimes, as CMS does not seem to stop submission, which is a problem
- Fair-share is completely off in Phoenix
- [Action CSCS] Wish-list for the monitoring dashboard:
- ARC ganglia charts, and
- Green/red lights from VO tests
- [Action Gianfranco] send info/links to follow up on new ATLAS storage models. CSCS can't really focus on that until after mid'19
CSCS
- [Action Roland] ask LHCb for tech contact to better address issues (aid Vladimir)
- [Action CSCS] ARGUS is probably not needed by anyone, but is almost impossible to confirm; it should be removed from GOCDB first to see what happens.
- The fair-share issue should be discussed in mid-February when all data is gathered
- [Action CSCS] The container service (Shifter/Sarus) should be added to the Phoenix's service diagram * It was agreed to keep the 40/40/20 shares for both compute and storage resources until further notice
- [Action CMS and LHCb] We need a written statement from all VOs saying if they want any leftover HW from Phoenix or not
- [Action CSCS] CSCS should provide a list of HW that's available, including cables and switches
- [Action Pablo] Answer Sigve's email to see if the EGI fee is covered in the P5 project
- [Action Gianfranco] Investigate alternatives to the CA before March and, if not, advice everyone to get a cert renoval in time
- [Action Pablo] Add wiki page about outreach and publications
- [Action Pablo] Call a Doodle for the next F2F on the 2-6th of September in Zurich
Other Action items
Attachments
This topic: LCGTier2
> WebHome >
MeetingsBoard > MeetingCHIPPCSCSFaceToFace20190121
Topic revision: r13 - 2019-01-29 - PabloFernandez