Reprocessing: Meeting of 25-July-2005: 9:30-10:30CDT ESNet video conference
Our meeting number on the ESNet is 823073776 (82d0repro).
Instructions to dial into a video conference via phone.
Agenda
- News
- Status of new JIM release cut
- Status of remote site Certification
- Status of production
- JIM Deployment and Remote Setup of remaining sites.
- AOB.
Minutes
Participants
Joel Snow (Oklahoma),
Patrice Lebrun, Tibor Kurca (Lyon), Frederic Villeneuve-Seguier (London),
Jae Yu (FNAL, Outback),
Andrew Baranovski, Gabriele Garzoglio, Parag Mhashilkar, Vlastislav Hynek,
Mike Diesburg, Daniel Wicke (FNAL, WH7X)
Topics
- News
- Joe Steele is taking several weeks of paternity leave. He will be in email contact and continue to run certificaton.
- Status page per project is outdated. The programm to collect the infromation has to be rewritten.
- Status of new JIM release cut
- Cut delayed by one week due to various reasons.
- Status of production
- WestGrid: --
- Lyon: Observing up to 20 parallel gridftp transorting files *to* FNAL.
Suggested solution is to limit the number of concurrent transfers for FSS.
- SAR-Oscer: Low rate du to high competition for CPUs.
- CMS-Farm: Problems with the sam-station and with job resubmission.
The latter one should be fixed in the "sam_condor_handler". Parameters to avoid resubmission can be added in there.
- Wisconsin: Problems in Wisconsin fixed (durable location wasn't cleaned)
- SAR-UTA: Performing better than expected due to extra available CPUs. New datasets needed (Mike will assign new ones today)
- Prague: Problems with merging. Producion and merging can't be run at the same time (is very inefficient).
The limit seems to be the transfer through the head node. Suggestion is to use sam_fcp instead of plain sam_gridftp.
It might also help to reduce the number of concurrent merge jobs. The new release cut will allow to configure a separate queues
(for transport as well as for jobs) for merging.
- Imperial College: Still problems with disk space management.
- Manchester: --
- GridKa: --
- Status of remote site Certification
- Status of production certification.
- Status of Merge Certification of Sites
- DØFarm: done.
- WestGrid: done.
- Lyon: done.
- SAR: UTA: done
- SAR: Oscer: done
- GridKa: done.
- Wisconsin: done.
- Prague: done.
- GridKa: done. But expected to run remaining two dataset.
- SAR-SPRACE: Ongoing. Unmerged files available to be produced with RecoCert.
- JIM Deployment and Remote Setup of remaining sites.
- RAL: Gatekeeper installed. Frederic is working on the configuration.
- Lancs: --
- AOB:
Action Items:
Next Meeting
1-Aug-2005(?)
Mike Diesburg, Daniel Wicke, 22-July-2005. Last Change 25-July-2005.
Diesburg@fnal.gov,
Wicke@fnal.gov