Tier1 and Tier-2 Weekly Report 2012-03-20
General News
- ADC and ATLAS Computing News [20120320]
- ADC Weekly meeting
- LHC ramped up to 4TeV Friday last week
- 900 GeV collisions expected Wednesday
- Full data taking at 8TeV in earnest expected to begin April 1
- Comp@P1 - most shifts covered (56 shifters)
- Harder time filling AMOD/ADCOS shifts (14/12 shifters currently, training 4/3 more)
- Hammercloud machine moved to better hardware (4 core, 16GB RAM) and mysql updated. Did not affect sites.
- One hour intervention in production next week. Put Panda on hold. New naming convention for task.
- LFC migration in the French cloud (20 Mar)
- Fast Tracker (FTK)
- Aim: Reconstructs tracks in hardware after L1 trigger in < 100us and propagate to L2
- https://twiki.cern.ch/twiki/bin/viewauth/Atlas/FastTracKer
- Need to produce lots of studies this year for LOI for upgrade - in production by Fall
- Use prodsys mechanisms to split up the large jobs for processing on the grid
- Generate FTK input files from RDO
- Simulate the FTK response
- Need to slice detector into segments for job scaling (~128)
- Each segment needs merging at the end
- Reconstruct events, using FTK simulation inputs
-
- ATLAS Cloud Status Monitoring in the ATLAS Site Status Board
* CA Cloud Squad Actions [20120228]
-
- User DaTRI requests approved / processed (last week)
- Declared Downtimes
- TRIUMF-LCG2 SCHEDULED downtime (OUTAGE) [19-03-2012 17:30 to 19-03-2012 19:30 UTC ] - Upgrade FTS to 2.2.8
- CA-VICTORIA-WESTGRID-T2 SCHEDULED downtime (OUTAGE) [21-03-2012 14:00 to 21-03-2012 23:59 UTC ] - cluster maintenance in preparation for upgrades
- SFU-LCG2/ SCHEDULED downtime (OUTAGE) [19-02-2012 09:00 to 22-02-2012 03:00 UTC] - The main power cable to the whole building will be replaced.
- CA-MCGILL-CLUMEQ-T2 SCHEDULED downtime (OUTAGE) [30-03-2012 09:00 to 02-04-2012 18:00 UTC ]
- HammerCloud autoexclusions * ANALY_SCINET reset online at Sat Feb 25 03:00:09 2012 CET
- other cloud squad related savannah and / or ROC ggus tickets [20110705]
- panda monitor for PD2P activity within clouds (default view (last 7 days) units = datasets)
- Open Issues and Ongoing Discussions
- Sites should be providing the April 2011 storage pledge. [see 20110315 report.
- HammerCloud [20120214]
- Security News [20120207]
- gLite News [20120320]
- ROC_Canada News [20120214]
- WLCG and General Computing News [20120221]
SSB Results
- Critical tests for each site in the Site Status dashBoard are available at the links below
SSB PanDA Test Queue Availability (month)
- this metric, measured for the analysis queues, defines the site status for data preplacement as alpha (
T2D and avail > 90%), bravo (T2 and avail > 90%) or charlie (< 90%).
SAM Results
- site service status via Gridview
- Please check your site
- March 2012 Detailed Site Information (valid until 20120331):
- TRIUMF-LCG2
- Australia-ATLAS
- CA-ALBERTA-WESTGRID-T2
- CA-SCINET-T2
- CA-VICTORIA-WESTGRID-T2
- SFU-LCG2
APEL Accounting
- ACTION ITEM FOR SITES: Sites please regularly check and confirm that your historical APEL data has been published and looks correct when comparing with batch system utilization
APEL Publishing Status
APEL Accounting Results
APEL Synchronization Test Links
Site Reports
Alberta
Recent Issues
- summary of this weeks Savannah bugs and GGUS tickets for site:
Outstanding Issues
Recent Issues
- summary of this weeks Savannah bugs and GGUS tickets for site:
Outstanding Issues
Victoria
Recent Issues
- summary of this weeks Savannah bugs and GGUS tickets for site:
Outstanding Issues
Toronto
Recent Issues
- summary of this weeks Savannah bugs and GGUS tickets for site:
Outstanding Issues
McGill
Recent Issues
- summary of this weeks Savannah bugs and GGUS tickets for site:
Outstanding Issues
Recent Issues
- summary of this weeks Savannah bugs and GGUS tickets for site:
Outstanding Issues
Australia-ATLAS
Recent Issues
- summary of this weeks Savannah bugs and GGUS tickets for site:
Outstanding Issues
Production
Summary
- NOTE: ARDA ProdSys Dashboard has stopped being used by ADCoS team due to information updating issues with the interface. The historical job usage information is to appear separately within ARDA and is being validated. This will be used in the future for information presented here.
- Within the CA Cloud and Worldwide (Panglia
View):
World-wide weekly ATLAS ADCoS summary (Mar.13-19,2012)
________________________________________________________________________
I. General summary:
---------------
A) During the past week (Mar.13-19,2012) Panda production service
- completed 1,322,660 managed group, MC production, validation and reprocessing jobs
- average ~188,951 jobs per day
- failed 53,152 jobs
- average efficiency:
-- jobs ~96.1%
- active tasks: 388
-- distribution by cloud: CA:11 CERN:26 DE:89 ES:17 FR:57 IT:6 ND:38 NL:22 TW:5 UK:62 US:55
B) - DE/FZK-LCG2 DT (LFC,SE,SRM,CE,BDII OUTAGE:maintenance), Mar.12-15.
- UK/RAL-LCG2 DT (FTS OUTAGE:problems with b/e DB ~3.5h), Mar.14.
- UK/RAL-LCG2 DT (LFC,SE,SRM OUTAGE:network problems), Mar.16.
- FR/IN2P3 DT (LFC OUTAGE:LFC migration), Mar.20-21.
- New DB Release 18.7.1 subscribed to sites, Mar.17.
- New pilot version v52a announced and released, Mar.16,19.
- HammerCloud intervention for DB uptate (~2h.), Mar.20.
II. Site and FT/DDM related interruptions/issues/news (+fixed, -not yet)
-------------------------------------------------------------------
4) Fri Mar.16
-> Cloud/site PROD efficiency ever<50% : -
-> Cloud/site DDM efficiency <50% : DE,CERN
............................................
+ CERN/SLS ATLAS-Frontier availability 86% due to ATLAS-KIT-Frontier not
available.Savannah 92676:Oracle DB at FZK fixed,FTS+Frontier are back.
Availability is back to 100% as of Mar.16,the ticket can be closed.
- DE/FZK-LCG2_DATADISK low(25%) success for FT/SOURCE:GENERAL_FAILURE:
RQueued.Elog 34396.Related to FTS DB issue at FZK?See Savannah 92676.
6) Sun Mar.18
-> Cloud/site PROD efficiency ever<50% : -
-> Cloud/site DDM efficiency < 50%: DE
........................................
+ CERN/ATONR,ATLR DB monitor yellow/blocking+waiting session.Elog.34424,41
Recovered.
+ CERN/AGIS error 503,service temp.unavailable 4:00-5:54.Restarted,fixed.
Elog 34416,18-19.
III. ATLAS Validation,Repro,DDM,ADC Operation Savannah bug-reports
(++ bug understood/fixed, -+ fixed in part, -- not fixed yet)
----------------------------------------------------------------------
++ 17.1.4.6 valid1 DigiMReco task 736292 crashes: TRF_SEGFAULT | "Caught
signal 11(Segmentation fault).Savannah 92526:SampleT production - r3373.
All jobs crashed up to 6-7 attempts in a row each at various sites in CA
cloud due to the reproducible error on the same event (RAWtoESD step).
Task ABORTED.Should be fixed for release 17.1.4.7(or 17.2.0.1).
++ 17.0.6.4.5 mc11_7TeV Reco merge tasks 741421 failures:Too many/too
large input files.Group production TRIGGER L1CALO.Othe affected tasks:
741406-14,16,18,19,21,43,47,449,549,571,575,577.All jobs failed multiple
attempts in various clouds.Elog.31411-3.Understood:wrong task definition,
tasks ABORTED,to be redefined.
--
LeslieGroer - 2012-03-19