1 / 14

Accounting Reporting Update

Accounting Reporting Update. John Gordon, CCLRC LCG Grid Deployment Board 5 th April 2006. Tier1 Reporting. Background. On 22 nd February I sent a list of sites who were not publishing accounting to:- MB GDB EGEE ROC Managers I asked them to:-

samuru
Download Presentation

Accounting Reporting 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. Accounting Reporting Update John Gordon, CCLRC LCG Grid Deployment Board 5th April 2006

  2. Tier1 Reporting

  3. Background • On 22nd February I sent a list of sites who were not publishing accounting to:- • MB • GDB • EGEE ROC Managers • I asked them to:- a) check the list for sites in your country or supported by your Tier1/ROC.  I think these should be obvious but if anyone has problems, let me know.  b) approach these sites and ask why they are not publishing and report the reason back to me. I will collate the replies. If you consider that they will not be contributing to LHC computing then that is a valid reason for the MB but they may be hearing from EGEE.  c) make them aware of the LCG policy agreed by the last MB that everyone should publish regular accounts for their LHC VOs by some method (as discussed during my MB Accounting talk) d) if there are legal or security arguments why they cannot publish, please highlight this so that we can get a working group investigating the implications.   e) get an estimate from them of when they can start publishing. • Very few replies (none on policies or legal issues) • ~72 sites not publishing in last 3 months cf ~150 who have published at all

  4. 21 February 2006

  5. Actions from February MB • Countries to give feedback on legal issues with LCG-wide accounting (By April) Finland only • APEL to understand gLite implications (previous talk) • Tier1s to help ‘their’ associated sites to deploy and configure APEL. (More Green sites) • or to use their own accounting system to publish to LCG Repository • Sites to check their APEL logs for errors • give feedback to increase reliability and robustness • Sites to compare with other sources as reality check • eg if Ganglia shows 90% average utilisation over a month then APEL numbers should agree. • Work with OSG to push/pull their LCG accounting data • (Previous talk)

  6. 05 March 2006

  7. 05 April 2006 (incomplete)

  8. Comments • We have observed that the list of sites not publishing has a few false positives. • Some non-publishing sites may be publishing under another name (mainly sorted) • Some flagged sites were not yet in production. • No way of flagging old that should no longer be publishing. Type=Closed proposed • NIKHEF publish from their own database and are seeing an R-GMA problem. (??)

  9. Reporting to CRRB • The OB wants the CRRB to receive monthly figures for LHC use at Tier1 Centres • to start with • We have sufficient CPU reporting in APEL for T1s • but only report Grid work • How many T1s run significant non-Grid LHC work? • Not ready with tape and disk reporting yet • So what do we do? • How about manual reporting? • Example courtesy of Manuel Delfino

  10. Which Numbers? • What numbers are to be input? • CPU easy, use APEL or your local system • Normailise to SI2K kilohours as in APEL • Disk and tape are not so easy • TBdays integrated over the month? • months have different numbers of days • Average TB/day ? • A snapshot on the 1st (or last) day of the month? • all per LHC VO • allocated or used space?

  11. Can we do better? • A simple tool could take the manually produced disk and tape numbers and publish them to the central APEL respository • The change to automatic measurement and submission would then be controlled and easily phased in.

More Related