Interesting analysis of linux kernel threading by IBM

[michael_schulz en public.uni-hamburg.de]

Horst von Brand:
> Say which hard facts?
Simple. Let's play the game of optimizing.

The IBM  guy looked at sched.c  and did some tweaking  which seemed an
obvious improvement  for him  (don't always  compute goodness  for all
running  processes.) Actualy there  are a  couple of  guys looking  at
sched.c and  try to change  O(n) to  O(log(n)). If you find  any place
where you thingk you might introduce such a change then go for it.

Keep in mind that the absolut  numbers of an O(log(n)) algorithm might
be  worse than  for O(n)  in  the average  case. Then say  good by  to
averaging and do resource adaptive algorithms and mind the overhead.

More or less this is the game called optimizing.  
Let's play it.  We will see...

	Micha.

-- 
-- Michael Schulz, Uni Hamburg

-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo en vger.rutgers.edu
Please read the FAQ at http://www.tux.org/lkml/