>>>>> Jeremy Coles writes:
> Yes - I had in mind two efficiency figures. The one from the RB
> would be based on the successful vs unsuccessful CPU time (as
> defined in your RB data) while Matt's analysis effectively looks at
> useful vs idle job time. Matt's script works with the APEL data so
> we could provide something centrally but I would like a few sites
> to check it first. The Tier-1 implementation uses data directly
> from a PBS database (which is checked against APEL and mostly found
> to agree).
I just ran the script accessing the APEL data for RAL jobs (only for
the LHC experiments), and it still seems to work OK:
http://www.gridpp.rl.ac.uk/stats/eff/APEL-tunnel/Grid/archive/summary.html
Jeremy's suggestion is, I think, to try and get the script working at
perhaps one nominated site to start with. I've only run it at RAL, so
there may be various issues arising when running it elsewhere, and I
am willing to help resolve them.
Matt
|