EGI-InSPIRE:Czech Rep-QR8

From EGIWiki
Jump to: navigation, search
EGI Inspire Main page


Inspire reports menu: Home SA1 weekly Reports SA1 Task QR Reports NGI QR Reports NGI QR User support Reports


Contents


Quarterly Report Number NGI Name Partner Name Author
8 NGI_CZ CESNET Miroslav Ruda


1. MEETINGS AND DISSEMINATION

1.1. CONFERENCES/WORKSHOPS ORGANISED

Date Location Title Participants Outcome (Short report & Indico URL)
23.-27. April Prague, Czech Republic Hepix 85 https://indico.cern.ch/conferenceDisplay.py?ovw=True&confId=160737

1.2. OTHER CONFERENCES/WORKSHOPS ATTENDED

Date Location Title Participants Outcome (Short report & Indico URL)
26. March Munich, Germany Belle Grid Sites Meeting 1 http://kds.kek.jp/conferenceDisplay.py?confId=9080
26.-30. March 2012 Munich, Germany EGI Community Forum 10 http://cf2012.egi.eu/
April 2012 CNAF, Bologna, Italy EGI CSIRT face-to-face meeting 1 https://wiki.egi.eu/csirt/index.php/EGI_CSIRT_Face_2_Face_meeting (access only for closed group)
23.-27. April Prague, Czech Republic Hepix 4 https://indico.cern.ch/conferenceDisplay.py?ovw=True&confId=160737
28 February – 2 March 2012 Taipei, Taiwan ISGC 2012 1 presentation of EGI Security Monitoring http://indico3.twgrid.org/indico/contributionDisplay.py?contribId=28&sessionId=38&confId=44


1.3. PUBLICATIONS

Publication title Journal / Proceedings title Journal references
Volume number
Issue

Pages from - to
Authors
1.
2.
3.
Et al?

2. ACTIVITY REPORT

2.1. Progress Summary

National Nagios, Dashboard and Top BDII were maintained and regularly upgraded. Maintenance of WMS+LB, DPM, MyProxy, VOMS and UI provided for Auger and VOCE. MPI-VO established - registration form, UI, VOMS provided.

We performed regular activities of the EGI CSIRT team, including participation to weekly and monhtly conferences. We carried on with coordination of the security monitoring activity, mainly focusing on putting the security dashboard to the production, which has been accomplished during this period.

2.2. Main Achievements

New subcluster rubus in production, 23 nodes, 736 jobslots, 5340 HEPSPEC06. Investigation of low cpu/wall time ratio of ALICE jobs. Ratio improved when we limited the number of ALICE concurrent jobs, from 45% to 67%. If it is due to network limits, it can be at the source location, the monitored part of the network connection of praguelcg2 is not saturated.

Continuous running of production and analysis jobs of supported VOs. The data flow to praguelcg2 reaches 40 TB/day.

2.3. Issues and mitigation

Issue Description Mitigation Description
Low availability for NGI_CZ sites due to problems with top level BDDI (GGUS ticket #33713 and #80202) Both instances upgraded, precise explanation unknown
Lower (98.8%) than targetted availability of the top level BDII due to wrongly

announced scheduled downtime (GGUS ticket #80939)

Improved policy
Personal tools
Namespaces
Variants
Actions
Navigation
Toolbox
Print/export