[Beowulf] Good upgrade intervals (Was: Oldest functioning clusters)

[Roger L. Smith]

On Tue, 23 Nov 2004, Josip Loncaric wrote:

> Robert G. Brown wrote:
> >
> > [...]  -- Moore's Law is brutal.  So
> > production clusters older than five (really three, but certainly five)
> > are a net loss and make negative sense.  [...]
>
> Here is a simple argument which I derived back in 1998 to justify
> upgrades whenever the same money can buy approximately 5 times the old
> system's performance.  This works out to about 3-4 year upgrade
> intervals, given nominal assumptions.

We use a 3-4 year cycle, but we don't necessarily decommission our old
stuff when we purchase new stuff.  As long as our users are still heavily
using the old systems, we keep them running.