Tier1 and Tier-2 Weekly Report 2009-03-17

SAM Results

• Source URL: http://lcg-sam.cern.ch:8080/reports/t2/site_avail.xsql

• availability-ops-20090317.png:
  

• reliability-ops-20090317.png:
  

• availability-atlas-20090317.png:
  

• reliability-atlas-20090317.png:
  

APEL Accounting Publishing Status

• apel-gantt-20090317.png:
  

APEL Accounting Results

• apel-stats-20090317.png:
  

General News

Site Reports

Alberta

Recent Issues

Outstanding Issues

• few WNs to be debugged with respect to missing stderr/stdout
• still need to add 2nd GigE? nics to dCache pools for internal network access from WNs to avoid NAT

SFU

Recent Issues

Outstanding Issues

Victoria

Recent Issues

Outstanding Issues

Toronto

Recent Issues

Outstanding Issues

TRIUMF

Recent Issues

Outstanding Issues

Production

Summary

site	success	failure	success (walltime)	failure (walltime)	efficiency	efficiency (walltime)
TRIUMF-LCG2	12257	4331	172294321	137879348	73.9%	55.5%
SFU-LCG2	4791	459	114040387	10683682	91.3%	91.4%
VICTORIA-LCG2	2224	85	110765602	636996	96.3%	99.4%
ALBERTA-LCG2	981	48	27992511	902552	95.3%	96.9%
total	20253	4923	425092821	150102578	80.4%	73.9%

dashboardSummary.pdf

Failed Jobs

Panda Monitoring looks incomplete for searching the 7 day archive. They are migrating to Oracle and are already aware of issues to be resolved.

For TRIUMF, these are the reasons from the dashboard ... looks like the majority are Transform exceptions:

name,rank,value
TRF_EXC,1,3181
EXEPANDA_JOBKILL_BYPILOT,2,632
TRF_SEGFAULT,3,172
EXEPANDA_JOBEXPIRED_SIXDAYS,4,109
EXEPANDA_JOBKILL_SIGTERM,5,51
TRF_UNKNOWN,6,38
EXEPANDA_JOBDISPATCHER_HEARTBEAT,7,32
TRF_OUTFILE,8,30
EXEPANDA_GET_SIZEMISMATCH,9,22
EXEPANDA_GET_ADLER32MISMATCH,10,15
TRF_PYT_SYNTAX,11,12
EXEPANDA_DQ2PUT_FILECOPYTIMEOUT,12,4
EXEPANDA_DQ2_STAGEIN,13,2
EXEPANDA_DQ2_SERVERERROR,14,2
EXEPANDA_GET_FAILEDTOGETLFCREPLICA,15,1
EXEPANDA_PILOTEXCEPTION,16,1

Notes

-- AsokaDeSilva - 17 Mar 2009