That's good. WE may have exposed a problem with the way gstat collects data but your pragmatic solution gets round that.
Thanks,
John
> -----Original Message-----
> From: Testbed Support for GridPP member institutes [mailto:TB-
> [log in to unmask]] On Behalf Of Chris Curtis
> Sent: 01 March 2011 12:20
> To: [log in to unmask]
> Subject: Re: Dteam & sites meeting at 11am
>
> Hmmmm, problem fixed.
>
> We have two clusters, which two different polices:
> Local cluster: Share=atlas:40 Share=alice:40 Share=others:20
> Shared cluster: Share=atlas:40 Share=lhcb:40 Share=others:20
>
> As atlas, alice and lhcb are supported on both clusters, I'll publish
> 30%
> per VO on all CEs.
>
> Chris
>
> On Tue, 1 Mar 2011, Chris Curtis wrote:
>
> >
> > Hi -
> >
> > Regarding Birmingham, we have used the yaim variable:
> >
> > CE_CAPABILITY="CPUScalingReferenceSI00=2404 Share=atlas:40
> Share=alice:40
> > Share=others:20"
> >
> > with no explicit mention of LHCb. I can add LHCb manually to fix the
> > problem?
> >
> > Cheers,
> >
> > Chris
> >
> >
> > On Tue, 1 Mar 2011, John Gordon wrote:
> >
> >> I've had a preview of a gstat view of publishing SHAREs. As it
> hasn't been
> >> released I probably shouldn't send it round but I can say that it
> looks
> >> good except for
> >>
> >> a) Durham, EFDA-JET and UCL-HEP not publishing any shares
> >> b) Birmingham publishing 40% each for Alice, ATLAS, and LHCB.
> >>
> >> John
> >>
> >> -----Original Message-----
> >> From: Testbed Support for GridPP member institutes
> >> [mailto:[log in to unmask]] On Behalf Of J Coles
> >> Sent: 01 March 2011 10:01
> >> To: [log in to unmask]
> >> Subject: Dteam & sites meeting at 11am
> >>
> >> Dear All
> >>
> >> The agenda for today's sites meeting is here:
> >> http://indico.cern.ch/conferenceDisplay.py?confId=113885. In
> addition to
> >> the regular updates the main extra topic this week is discussion of
> the
> >> sonar network testing results. If you have other topics that you
> would like
> >> discussed please let me know. I have a slot down for looking at
> progress
> >> and problems in deployment of new nodes such as ARGUS. The status of
> CREAM
> >> will be reviewed at next week's GDB so we will also cover the status
> in the
> >> UK today.
> >>
> >> For minutes today: Kashif -> Alessandra -> Daniela -> Duncan->
> Graeme->
> >> Mark-> Sam-> Wahid-> Stuart
> >>
> >> regards,
> >> Jeremy
> >>
> >
> >
>
> --
> West 326
> Physics and Astronomy
> University of Birmingham
> Edgbaston
> Birmingham
> B15 2TT
>
> (Office) 0121 414 4700
> (Mobile) 0798 666 1959
|