The change to APEL is an easy one but it is queued behind an earlier
patch which has been queuing for months in certification.
Stephen is right, the recommendation is to hold off this change for now
as it is more important to get accounting right than installed capacity.
I think Steve Traylen said at the GDB this week that there were only a
few sites affected.
John
> -----Original Message-----
> From: LHC Computer Grid - Rollout [mailto:[log in to unmask]]
> On Behalf Of Burke, S (Stephen)
> Sent: 10 July 2009 10:52
> To: [log in to unmask]
> Subject: Re: [LCG-ROLLOUT] New CE info publication
>
> LHC Computer Grid - Rollout
> > [mailto:[log in to unmask]] On Behalf Of Rob Fay said:
> > But if APEL hasn't been changed to use this new CECapability
> > value yet, won't
> > putting an average in GlueHostBenchmarkSI00 now give
> > incorrect accounting
> > figures until it has? Shouldn't we hold off making this
> > change until APEL is actually using CPUScalingReferenceSI00?
>
> John Gordon may want to give an official answer but I would think
> that's
> right, i.e. the GlueHostBenchmarkSI00 shouldn't change yet. The
> relevant
> bug for APEL is here:
>
> https://savannah.cern.ch/bugs/index.php?51176
>
> Stephen
> --
> Scanned by iCritical.
--
Scanned by iCritical.
|