[Info-vax] The Future of Server Hardware?

[JF Mezei]

On 12-10-01 15:21, David Froble wrote:

> Weren't racks of a "gazillion" DS10Ls a good solution for some problems? 
>   It seems that plenty of them were made and sold.


If a rackful of DS10Ls was the best solution, why then did people buy
Wildfire/Galaxy class machines ? How come the 1U version of the DS10
didn't survive in the transition to DS15 ?

In the case of Google or facebook, do they really need that much CPU
power, or is it IO bandwidth that they need ?

And if Google stopped using gratuitous HTTPS for public data such as
youtube etc, how much spare CPU would they suddently have in their data
centres ?

If at the end of the day, what you need is a metric tonne of 1gbps
ethernet interfaces to feed your internet links to the world with
youtube videos, would't there be a better way than to have 1 metric
tonne of 1U servers each with its 1gigE interface ?

In a mainframe class machine, how many gigE interfaces could the IO
backpane support ?