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

Agenda

1. News
2. Status of production
3. Status of remote site Certification
4. JIM Deployment and Remote Setup of remaining sites.
5. AOB.

Minutes

Participants

Topics

1. News
   
   • New release cut with reduced load du to polling tested. To be release by Friday.
     When upgrading there is a risk that jobs get held.
   • Joe remerged the p17.02.00 root tuples with p17.04.00 MergeRecoCert. And produced new overlay plots. Plots representing rates get fixed.

2. Status of production
   • WestGrid: Yann crashed his machine with around 400 batch jobs. Yann believes that this is more related to the number of jobs run before. Do we have a memory leak? GG: will check for know bugs in globus. Yann says 500 to 600 production jobs and 4-5 merge jobs were sufficient to crash the system.

   • Lyon: machine crashes occur at around 1000 batch jobs in the queue. Now messages in /var/log/messages .

   In order to reduce the number of batch jobs in execution sites Gabriele will look into adding some logic to the broker.

3. Status of remote site Certification
   • Status of production certification.
     

   • We have certification plots for SAR-UTA, Wisconsin and Prague.
   • Prague seems to run a different version of the proxy server (according to SAM at a Glance).
     UTA proxy server isn't mentioned here. Did you UTA use its proxy servers?
     Prague and UTA should wait until their proxy setup is confirmed.
   • Status of Merge Certification of Sites
     
     • DØFarm: done.
     • WestGrid: done.
     • Lyon: done.
     • SAR: UTA: done
     • GridKa: done.
     • Wisconsin: done.

4. JIM Deployment and Remote Setup of remaining sites.
   • GridKa:
   • Prague:
   • UK:
     • IC:
     • Manchester:
     • RAL:
     • Lancs:
   • CMS Farm:

5. AOB:
   

Action Items:

Next Meeting