Re: [RFC][PATCH] linux-2.5.59_getcycles_A0

["Martin J. Bligh" <mbligh@aracnet.com>]

>> However this doesn't work on systems w/o a synced TSC, so by simply
> 
> Why not? This shouldn't be performance critical and you can make 
> it monotonous with an additional variable + lock if backwards jumps
> should be a problem.
> 
> Also the variations between non synced TSCs should be far below 
> any watchdog's radar screen.

Not true. They'll drift further and further apart over time.
Even a 0.01% crystal difference will eventually kill you.

And if that isn't bad enough think about what happens when I run 180 MHz
processors in one node, and 900MHz in another.

You really can't make any assumptions about TSC sync on boxes where
they're not synced.

M.