Tier1 and Tier-2 Weekly Report 2017-10-24

Tier1 and Tier-2 Weekly Report 2017-10-24

General News

ADC Technical Coordination Meeting [20171023]
- Direct I/O tests - root, https, fax, rucio; local and remote
- Overview of various TCB projects (e.g. DDM, WFMS)
ADC Weekly Meeting [20171024]
- MC Production
  - Usual ~250k+ slots being used all week, about half simul
  - Most MC16a+c samples done
  - Finally submitted 200/650M of the large BPHY sample for MC16a simul/reco. Simul is AF2 running mcore
  - First large MC16e evgen submitted, ~84M so far (about 15%)
- Group Derivation Production
  - Starting deletion of obsoleted data 1.4PB
  - Built AthDerivation 21.2.4.0
    - Will prepare a test DAOD production
  - Regrouped trains according to format size and fraction to optimiz inputs per job - 96 formats, 18 trains
  - Will use a similar config for the MC production
  - Running up to ~60k job slots
- Reprocessing
  - Done reprocessing 2017 toroid-ff runs with new 1-lines
  - No progress on missing trigger info runs in physics_Background
  - Prepping for fast reprocessing of data17
    - Running test slices
      - maybe use 2 files per job, no merge steps in slices
- CRC/ADCoS Report
  - Quiet week
  - TRIUMF-LCG2 tape endpoints: transfers failing with timeout errors, still under investigation (GGUS:131004, open)
  - Issue identified in GGUS tickets where a link ending in parenthesis causes a broken link
- RFC Proxy and PaloAlto IPS Block (Asoka)
  - Summarize long thread in Tier3 eGroup: http://cern.ch/go/6slf affecting Stonybrook, UT Dallas, SMU and UVic
  - Rucio failures if using RFC proxy but works with legacy proxy
  - Traced to traffic being blocked by PaloAlto devices sitting on campus ITs due to work around for a GnuTLS library exploit
  - No real security issue - likely caused by devices doing packet inspection. Fixed by Palo Alto content release 744 30454
CA Cloud Squad Actions
- User DaTRI requests approved / processed (last week)
Open Issues and Ongoing Discussions
- Availability & Reliability Reports [20170328]
  - 2017 Reports - click down to find reports of format WLCG_All_Sites_ATLAS_MMMYYYY.(html|pdf)
- Sites should be providing the 2016 storage pledge.
  - REBUS Site Capacities
  - REBUS Federation Resource Pledges
- ATLAS Canada HammerCloud Tests
WLCG and General Computing News
- Security News
- gLite/EMI News
ROC_Canada News
- Current shift