1 / 26

Metrics and deployment update

Metrics and deployment update. GridPP13. 4 th July 2005. Jeremy Coles J.Coles@rl.ac.uk. Overview. Deployment planning . General metrics – status within EGEE. GridPP performance. Deployment issues. Service challenges. Summary. Deployment plans (process). Deployment plans (issues).

paley
Download Presentation

Metrics and deployment update

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Metrics and deployment update GridPP13 4th July 2005 Jeremy Coles J.Coles@rl.ac.uk

  2. Overview Deployment planning General metrics – status within EGEE GridPP performance Deployment issues Service challenges Summary

  3. Deployment plans (process)

  4. Deployment plans (issues) • GridPP security challenges • UK network tests • Pre-production commitments • UKQCD (need to move to dCache servers) • Tier-2s delivering to MoUs • Non-HEP commitments • Update to deployment web-pages • Review of available documentation • Sysadmin training course II

  5. UK job slots

  6. Growth of EGEE job slots

  7. GridPP job slots as a percentage of the EGEE total

  8. Percentage of running jobs that are at GridPP sites

  9. Percentage of job slots used

  10. Gstat storage data

  11. Unique users of resources

  12. SFT results by quarter

  13. The story with accounting

  14. EGEE- take up of releases

  15. UKI - upgrades

  16. The “gstat metric” Gstat metric = ((#ok sites)*10+(#info sites)*20+(#note sites)*30+(#warn sites)*40+(#error sites)*50+(#crit sites)*60) / (#sites – (#maint+#off))

  17. Gstat metric vs EGEE

  18. Job success rate as measured by JRA2

  19. Metrics – summary 1 • Average number of published job slots for the last quarter (2477) 2: Average number of job slots used for the last quarter (481) 3: Published storage at the end of the last quarter (64TB) 4: Average gstat service metric for the last quarter (19.8) 5: KSI2K nominally available to LCG at the end of the last quarter (1846 KSI2K) 6: Integrated KSI2K hours available to LCG in the last quarter 7: Disk storage space nominally available to LCG at the end of the last quarter (240 TB) 8: Tape storage space nominally available at the end of the last quarter (239 TB) 9: Disk storage usage by LCG at the end of the last quarter (16 TB) 10: Number of sites publishing accounting data at the end of the last quarter (13) 11: KSI2K hours of CPU processing delivered (per VO) over the last quarter 12: Storage used (per VO) over the last quarter

  20. Metrics – summary 2 13: Number of supported VOs (10) 14: Number of users in supported VOs (other than dteam) at the end of the last quarter (812) 15: Average number of active users (of Tier-1) in supported VOs at the end of the last quarter (46) 16: Percentage of Site Functional Tests results that were passes “OK” over the last quarter (38%) 17: Number of trouble tickets raised against GridPP sites over the last quarter (TBC) 18: Number of sites upgrading in requested time period for last release (16) 19: Accumulated days of scheduled downtime for last quarter (418) 20: Average number of sites per quarter available in VO selections 21: Number of GridPP (site) system security incidents in the last quarter (3) 22: Number of EGEE Grid security incidents in the last quarter (0) 23: Average job success rate over the last quarter for LHC experiments (N/a) 24: GridPP contribution to experiment’s overall running for the last quarter (ALICE:ATLAS:CMS:LHCb; x1: x2%: x3%: x4%)

  21. Current deployment issues Main GridPP concerns: • gLite migration • Fabric management & future of YAIM • SRMs and data migration – dCache/DPM • Security (improving practices and dealing with vulnerabilities) • Ganglia deployment (to provide an overall view of GridPP resources) • Use of ticketing system (support services) • Use of UK testzone • Increase usage of resources • Hold training course (advance on Sysadmin training in Oxford) General • Job success rates at sites – (nb. Freedom of Choice is coming!) • Support more EGEE VOs • GOCDB2

  22. GOCDB2

  23. Freedom of choice - VO Page

  24. gLite and LCG2 components VOMS Catalogue and access control LFC RB gLite WLM FIREMAN myProxy BD-II BD-II APEL dgas Independent IS R-GMA R-GMA R-GMAs can be merged (security ON) UIs gLite-IO LCG gLite LCG CE SITE CEs use same batch system WNs gLite-CE FTS for LCG uses user proxy, gLite uses service cert FTS FTS shared LCG SRM-SE Data from LCG is owned by VO and role, gLite-IO service owns gLite data gLite

  25. GridPP status for SC3

  26. Summary Planning – some areas of concern Available data is improving allowing better monitoring of performance Resources at Tier-2s behind schedule but utilisation is not high Deployment process appears to be improving. 2-6-0 out soon Freedom of Choice & gLite migration starting Service Challenge 3 next week. Good progress. Testing setups now

More Related