For a while, the Alpha project was running their own scheduler on the machines. CERN central grid people thought Alpha was using lots of CPU time, but really they were just block booking it for when they needed it. Why? Central scheduler was too unresponsive, and as they weren't being billed for CPU time, why not block book the cores?

You mean like this?

http://lhcathome.cern.ch/

...oh.

"CERN's Alpine headquarters"

If anything, it's CERN's Jura headquarters, given that the tunnel is under the foothills of the Jura. The Alps are on the other side of Geneva.

Still, nice article. And Lewis is at CERN, too, presumably trying to find that secret X-plane the boffins have. ;-)

"We are the only ones [here at CERN] who have profited from the delays [to the LHC]," he jokes.

Not even remotely true. I know (admittedly second-handedly) that more than one group has spent the last year on fine-honing their machines.

[nitpicking]

While CERN is fairly close to the Alps, it's even closer to the Jura, so it's more accurately described as being 'Jurassic' rather than Alpine.

[/nitpicking]

will it run vista?

Are they using any DC clients on this? If not, why not?

possibly their reasoning for not doing so was along the line:

possibility that something goes wrong enough to destroy the computer center 1km away: 1e-3*

possibility that something goes just wrong enough to destroy the computer center 1km away but not the computer center 6000km away (through the earth): 1e-30*

cost of additional compter center: factor 2

(cost of transmission line able to transmit all experiment data ahead of the wave of destruction: huge?)

summary: nope

*numbers are obviously made up

Errm, that's what Grid computing does. The compute resource at CERN is only a small fraction of what we use:

http://lcg.web.cern.ch/LCG/