NGI DE CH Operations Center:Operations Meeting:21102011

From EGIWiki
Jump to: navigation, search

Operations Meeting Main

Introduction

  • Minutes of last meeting
  • SGE Support for cream starts from EMI Update 9 in November

Announcements

  • Meetings/conferences
  • Availability/reliability statistics
The Availability/Reliability League statistics for September 2011 have been added to:
https://wiki.egi.eu/wiki/Availability_and_reliability_monthly_statistics
UNI-Karlsruhe did not hit the targets and they were requested by Dimitri via email to update the corresponding ticket
  • Monitoring
Email from Dimitri on Monday, 17. October 2011 14:17:
Dear NGI-DE/NGI-CH sites manager,
as you know, nagios SAM tests where using Wen Mei proxy certificates with OPS VO extension to submit SAM tests.
This weekend Wen Mei's membershift in OPS VO expired, even her certificate is still vallid. This was cause of weekend failures 
for nagios SAM tests. Now tests are running under Foued Jrad certificate with OPS VO extension. But still some sites have failed 
tests. This looks like a mapping problem. So please check the mapping for Foued Jrad.
In next days we would exchange this certificate with a robot certificate for SAM nagios tests. Next week the robot certificate will 
be in production.
  • Staged rollout/updates
  • Quater report August-October
Email from Jie Tao on Tuesday, 18. October 2011 12:36:
Jie is collecting information for the coming quarter report (QR 6) covering August, September and October. She is expecting your  
contribution by October 31. Please send her (email: jie.tao@kit.edu) the report of your site directly. As the last QR, I need 
infos about:
Main achievements 
Issues and mitigations
conference/workshop organized  (date, location, title, participants, short report)
other conferences attended (date, location, title, participants, short report)
Publications (title, journal/conference, volume No., page No., authors)
ITWM, LRZ-LMU, JUERLICH: how many staged rollout components do you have for the reported quarter? (i.e. number of patches tested)
Thank you in advance.

Round the sites

NGI-DE
  • BMRZ-FRANKFURT (Uni Frankfurt)
  • DESY-HH (Dmitri Ozerov)
- during September we increased the number of CPUs
- end of October we are switching of the LCG-CEs
- 5000 jobs in the queue-> every few days: MAUI gets unresponsive and stops submitting jobs to the batch
- increased storage, now we have 3.5 PB for the Grid
- half of the services migrated to the EMI releases (top BDII, sBDII, VOMS, WMS), not using UMD, not happy with the quality of the 
software, EMI people/support react very fast
  • DESY-ZN
  • FZJuelich
  • Goegrid
  • GSI
  • ITWM (Martin Braun)
 - Staged rollout for glite-TORQUE_client (Patch #5060)
  • KIT (GridKa, FZK-LCG2) (Dimitri Nilsen, Tobias Koenig)
FTS Connection problems for Oracle back end 
dCache OPS failing up to time
  • KIT (Uni Karlsruhe)
  • LRZ
  • MPI-K
  • MPPMU (Cesare Delle Fratte)
 - SAM test mapping issue solved
 - upgrading to glite-CREAM > 3.2.13-1
 - Down Time next week  
  • RWTH Aachen
  • SCAI
  • Uni Bonn
  • Uni Dortmund
  • Uni Dresden
  • Uni Freiburg
  • Uni Mainz-Maigrid
  • Uni Siegen
  • Uni Wuppertal
SwiNG
  • CSCS (Miguel Gila)
- ntr
  • PSI
  • Switch

Note: please update your entry at https://wiki.egi.eu/wiki/NGI_DE:Sites if needed.

Status ROD

  • Any problematic tickets?
Ticket for Maigrid opened this week https://helpdesk.ngi-de.eu/index.php?mode=ticket_info&ticket_id=1635 . No reaction until now.  
There was also a correlated problem with the dashboard/GGUS. Ticket opened by ROD https://train.ggus.eu/ws/ticket_info.php?ticket=48713
  • Handover of the ROD shift
42 17.10 23.10	Team3, KIT 	
43 24.10 30.10	Team4, JUELICH 	
44 31.10 06.11	Team5, BADW-LRZ	
45 07.11 13.11	Team6, CSCS/NGI_CH 
We will ask LRZ 'How to continue with the ROD shifts?'	

AOB

If you have additional topics to be discussed during the meeting, please submit them in advance via our email list email list.