Reprocessing: Meeting of 18-July-2005: 9:30-10:30CDT ESNet video conference

Agenda

1. News
2. Features for new JIM release cut (Andrew Baranovski)
3. Status of remote site Certification
4. Status of production
5. JIM Deployment and Remote Setup of remaining sites.
6. AOB.

Minutes

Participants

Topics

1. News
   
   • Marco Verzocchi found 32 files that have a wrong event count. In many cases we still have the log files and understood what happened. The new release cut of JIM will include a fix that verifies the number of events before storing a merged file.
   • 8 additional file were corrupted, can't be read.
   • Recovery will be done with p17.05.xx probably at the d0farm.

2. Status of new JIM release cut (Andrew Baranovski)
   
   • All code is in CVS and realease (since Friday).
   • SamGrid team is testing new features on the SAMGrid-farm (from today).
   • Deployment to d0farm expected on Wednesday. Additional testing of new features from Friday or Monday Lyon.

3. Status of production
   • WestGrid: Home partition got filled. Recovery ongoing. No special problems. Prestageing: New prestaged files are no longer pinned, which makes downloads way faster and removed interference with production. Unpinning files with sam uncache file.
   • Lyon: No (new) problems. New datasets required (within the next week).
   • SAR-UTA: Limitation to 5 merge jobs resolved (though not understood). New datasets required (within the next week).
   • SAR-Oscer: ??
   • CMS-Farm: ??
   • Wisconsin: ??
   • Prague: ??
   • Manchester: ??
   • Imperial College: Extended size of durable location. Now starting to run with new setup.
   • GridKa: ??

4. Status of remote site Certification
   • Status of production certification.
     
     • SAR-SPRACE: available.

   • 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

5. JIM Deployment and Remote Setup of remaining sites.
   • RAL: Admins could be convinced to install dedicated gatekeeper, which is now being installed.
   • Lancs: Site installed, now testing setup.

6. AOB:
   
   • Joe will produce a comparision of the various versions of recocert we used and put the comparision to rou web page.

Action Items:

Next Meeting