On Mon, Aug 21, 2006 at 01:57:22PM -0400, Charles M. Hannum wrote:
> 
> Given the simplistic "block rotor" used for block allocation, reducing
> the number of CGs can *only* make the problem worse.

I don't think that's necessarily the case: consider the extreme case
where there's only one CG.  Clearly, the problem is not worse.  For a
disk of the same size, less CGs means less likelihood that any given
CG is full; obviously, there's a balance against the longer seek to the
next CG that a larger CG yields, but I don't think the result is as
blindingly obvious as you do.

The other possibility, of course, is that I'm mistaken or stupid; it
would hardly be the first time.

-- 
  Thor Lancelot Simon	                                     tls@rek.tjls.com

  "We cannot usually in social life pursue a single value or a single moral
   aim, untroubled by the need to compromise with others."      - H.L.A. Hart