EGI-InSPIRE:Ireland-QR3

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



Quarterly Report Number NGI Name Partner Name Author
QR3 NGI-IE Ireland John Walsh


1. MEETINGS AND DISSEMINATION

1.1. CONFERENCES/WORKSHOPS ORGANISED

Date Location Title Participants Outcome (Short report & Indico URL)

1.2. OTHER CONFERENCES/WORKSHOPS ATTENDED

Date Location Title Participants Outcome (Short report & Indico URL)
9/Nov/2010 Dublin, Ireland e-INIS all-hands 3 Presentations about Grid-Ireland status and plans
12/Jan/2011-13/Jan/2011 Amsterdam, Netherlands EGI Security Policy Group 1 http://www.nikhef.nl/grid/meetings/spg2011/
24/Jan/2011-25/Jan/2011 Amsterdam, Netherlands OMB face to face 1 https://www.egi.eu/indico/conferenceDisplay.py?confId=153
25/Jan/2011 Amsterdam, Netherlands OTAG 1 https://www.egi.eu/indico/conferenceDisplay.py?confId=245


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

  • Fully commissioned a redundant 10Gb link (with failover) from OpsCentre to Main Campus to NREN.
  • Grid-Ireland started the process of creating the operational structure NGI_IE.
  • Deployment of National UI (gLite 3.2)

2.2. Main Achievements

  • Record number of CPU hours recorded on during all three months at csTCDie, csUCCie and scgNUIGie.
  • Support more international VOs at csUCCie (biomed) and NUIG (astro).
  • Availability and Reliability statistics for November, December and January were excellent (despite miscellaneous security updates and subsequent deployment).
  • CA self-audit report and feedback from EU Grid PMA reviewers
  • Migration to glite-APEL

2.3. Issues and mitigation

Issue Description Mitigation Description
gLite 3.1 to gLite 3.2 migration making slow progress Migration handled by Quattor, some services not available
Power issues (overloading of UPS) at scgNUIGie in January required shutdown of 12 dual-core nodes Have deployed an additional 24-core SMP unit
NFS issues at csTCDie (vendor supplied solution related) resulted in long running jobs failing at last stage of job management split load over 4 servers, increased default timeouts and retries, forced restart of lower level services
Weaknessess in globus cleanup script (over NFS) Writing script to clean old files
csTCDie is still waiting on production ready glite-CLUSTER node type to integrate Ubuntu and PS3 nodes
VO dashboard information is sometimes not updated. Quattor sites depend on up-to-date information, thus recent issues seen with move of DTEAM to NGI-GR
Detected problem with Nagios MPI sensor at csUCCie Problem fixed by EGI Nagios tools group