Name: WLCG-OSG-EGEE Operations meeting
Start: 2007-03-12T15:15:00+01:00
End: 2007-03-12T18:00:00+01:00
Location: CERN conferencing service (joining details below)

<big> gLite WMS/CE – LCG RB/CE deployment strategy</big>

Speaker: Dr Ian Bird (CERN)

<big>Upcoming WLCG Service Interventions (with dates / times where known) </big>

Link to CIC Portal (broadcasts/news), scheduled downtimes (GOCDB) and CERN IT Status Board

New endpoint SRM v1 for LHCb at INFN-T1.
The old endpoint will be active for LHCb for the time needed for the FTS and LFC changes.
CASTOR nameserver DBs will be migrated to new hardware on Monday 2nd April 2007. At the same time, 3 network switches affecting many Grid services at CERN will be replaced. The total intervention will start at 07:30 UTC (08:30 Geneva time) and last for about 2 hours. More details will be provided later (full list of services affected etc.)

Time at WLCG T0 and T1 sites.

<big>FTS service review</big>

Full weekly report

Main issues this week:

Transfer ranging from 90 to 420 Mb/s, averaging around 200MB/s per day.
Involving all major T1 sites.
FZK - very unstable SRM, problems expected until 16th March.
Mostly traffic from CMS and Atlas. Little activity from LHCb.
Significant service degradation due to Castor Atlas problem over the weekend.
12 tickets have been submitted to sites this week for a variety of problems, 7 problems have been solved.
FTS 2.0 pilot service available for testing by experiments.
Throughput plots

FTS report index - status by site and by VO
Transfer Operations Wiki

Speaker: Gavin McCance (CERN)

ATLAS service / challenge issues & Tier-1/Tier-2 reports

Speaker: Kors Bos (CERN / NIKHEF)

CMS service / challenge issues & Tier-1/Tier-2 reports

-- Job processing: CMS MC production activities are switching to a new production round, hence a ramp-down occurred last week.
-- Data transfers: last week was week-4 of the CMS LoadTest07 (see [*]) with focus on T0-T1 routes. All issues found in week-1/2 were addressed and fixed in week-3, and operations were quite smooth in week-4. Not all T1's participated though (ASGC just finished migration to Castor-2, RAL was down due to Castor-2), and not all participating T1's move data all at the same time, but a quite constant aggregate transfer rate out of CERN was seen in most days of the week (see Gridview). A stop on thursday noon time (CET) was seen, probably due to disturbances to some services after network interventions. Next week CMS will restart the LoadTest with T0-T1 transfers, in the multi-VO scenario, and will additionally test selected T1-T2 routes.
-- Other preparation activities: as from the planning, a first working prototype of the set of CMS-specific tests within the SAM infrastructure is in place.
[*] http://www.cnaf.infn.it/~dbonacorsi/LoadTest07.htm

Speaker: Mr Daniele Bonacorsi (CNAF-INFN BOLOGNA, ITALY)

ALICE service / challenge issues & Tier-1/Tier-2 reports

LHCb service / challenge issues & Tier-1/Tier-2 reports

LHCb want to bring the issue risen last week about the inconsistent behavior ofSRM on d-cache sites when lcg-gt command is issued. We'd like to understandfrom d-cache experts and involved site admins (RAL,GRIDKA,IN2P3 and SARA) whatit could be done in order to have staged in files at the tURL request.
For the time being the reprocessing activity in LHCb has been stopped for this problem because ROOT can open only file present on disk (or at least the gsidcap plug-inused by the applciation).
To tackle this problem thay have developed on their own a pre-stager service (very old idea in LHCb) that should coordinate all their reprocessing jobs allowing them to run only when all input files are staged on the pool. This special agent (under test now) relies on customized tools/scripts/commands that discriminate the SRM back-end storage and accordingly trigger stage-in operations.

Speaker: Dr roberto santinelli (CERN/IT/GD)

WLCG-OSG-EGEE Operations meeting

28-R-15

CERN conferencing service (joining details below)