That's true. All this is in raw job data but the portal only has it summarized by UserDN (for the top ten) and FQAN (I think the same). Summarising by a combination would need work. John > -----Original Message----- > From: Testbed Support for GridPP member institutes [mailto:TB- > [log in to unmask]] On Behalf Of Stephen Burke > Sent: 04 April 2011 14:24 > To: [log in to unmask] > Subject: Re: HEPSPEC06 numbers for GridPP metrics > > Testbed Support for GridPP member institutes [mailto:TB- > > [log in to unmask]] On Behalf Of John Gordon said: > > The main problem is that APEL accounting which can normalise cpu > using > > a site average doesn't know which are production and which analysis > > jobs. > > Doesn't it store the DN and FQAN the job was run under? > > > The site average HEPSPEC06 is already published in the BDII though. > > The subcluster average in fact - so if sites create a subcluster per > hepspec category it's accurate, but of course not everyone does. > > Stephen