NGI DE CH Operations Center:Operations Meeting:02122011

Operations Meeting Main

Introduction

• Minutes of last meeting

Announcements

• Meetings/conferences

NGI-DE/NGI-CH/D-Grid Workshop in April
Note: There is also a dCache Workshop in April. Date should be chosen carefully.

The EGI Community Forum (http://go.egi.eu/cf12) will be in Munich 26-30th March 2012 and held in conjunction with the 2nd EMI 
Technical Conference. Abstract submission was open until 2/12/11.

• Availability/reliability statistics

Last:
https://documents.egi.eu/public/ShowDocument?docid=959

recomputation done
https://helpdesk.ngi-de.eu/index.php?mode=ticket_info&ticket_id=1720

• Monitoring

https://tomtools.cern.ch/confluence/display/SAMDOC/Update-15

• Staged rollout/updates

UMD

https://wiki.egi.eu/wiki/UMD-1:UMD-1.5.0

EMI

http://www.eu-emi.eu/emi-1-kebnekaise-updates

gLite3.1

http://glite.web.cern.ch/glite/packages/R3.1/updates.asp

gLite3.2

http://glite.web.cern.ch/glite/packages/R3.2/sl5_x86_64/updates.asp

other topics

EMI release / possible infosys errors (UNI-SIEGEN)
https://helpdesk.ngi-de.eu/?mode=ticket_info&ticket_id=1722

Gstat
https://helpdesk.ngi-de.eu/?mode=ticket_info&ticket_id=1930

Gstat
Sites with CRYTICAL gstat status: wuppertalprod Uni-Bonn DESY-HH SCAI MaiGRID LRZ-LMU

Round the sites

NGI-DE

• BMRZ-FRANKFURT (Uni Frankfurt)
• DESY-HH

we updated all our wn's to torque 2.5.7-2 (glite-WN-version-3.2.12-1) and this works fine with the old torque server (2.3.13-1).  
Server we didn't update because of the problem with memory in new version.
This week update of dcache-cms instance to 1.9.12-13 was done

• DESY-ZN
• FZJuelich
• Goegrid
• GSI
• ITWM (Martin Braun)

ntr

• KIT (GridKa, FZK-LCG2, Dimitri Nilsen, Tobias Koenig)

gLexec updated at WNs
roled based mapping for glexec was requested by atlas
WMS disk full: Problems with ngi-de-nagios portal

• KIT (Uni Karlsruhe)
• LRZ
• MPI-K
• MPPMU (Cesare Delle Fratte)

   - DOWNTIME 29/11 01/12 dcache upgrade from 1.9.5-28 to 1.9.12-13
   - problems with gridftp doors (solved by Java jdk update to latest packages)
   - dCache: number of movers was increased
   - updated one of the two CREAM
   - installed security fix on Apel box
   - strange lfc failures caused by gpfs partition problems

• RWTH Aachen
• SCAI
• Uni Bonn

services online

• Uni Dortmund
• Uni Dresden (Ralph Mueller-Pfefferkorn)

- since about two months problem with our file system, especially with the central nfs file system. The nfs system becomes 
  overloaded. 100s of jobs with 100s of files.
  Paolo/CSCS: We had the same problems. It was fixed by changing the CREAM grubber and we went from Lustre to gpfs and SSD disks 
  for the metadata and for the inode's table.

• Uni Freiburg (Anton Gamel)

- problems with gsi ssh -> increased movers
- installed additional dCache servers

• Uni Mainz-Maigrid
• Uni Siegen
• Uni Wuppertal

SwiNG

• CSCS (Paolo)

- maintenance two days ago: firmware update of the disks, lost 4 disks/CMS pool (in contact with CMS)
- test CERNVMFS in preproduction

• PSI
• Switch

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

Status ROD

• Any problematic tickets?
• Handover of the ROD shift
• ROD shift schedule https://wiki.egi.eu/wiki/NGI_DE_CH_Operations_Center:Operations_Teams#Shifts_rotation_table

LRZ from 02.2012. 2*2 Shifts

ROD Newsletter Nov. 2011
https://documents.egi.eu/secure/RetrieveFile?docid=298&version=1&filename=ROD%20newsletter%2011-2011.pdf

tickets were not mentioned within 10 days. Be aware of the ROD statistics.
Please pay attention to the Escalation Procedures
https://wiki.egi.eu/wiki/Operations:COD_Escalation_Procedure#Escalation_for_operational_problem_at_site

AOB

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