On Thu, Mar 23, 2000 at 04:00:27PM +0000, Martin J. Laubach wrote:

 >   Just out of sheer curiosity, do you have any before/after
 > benchmark, or is the improvement here to slight to notice?

Unfortunately, both timeout and callout_* are noise in a general kernel
profile.  However, one of the reasons that timeout/untimeout isn't used
in all the places that actually use timers is because they're known to
not scale well.

Now that we *have* a better timer facility, we can use it in a lot more
places.  One of these places is going to be TCP timers.  The current scheme
for TCP timers does not scale well at all.  Route timers are another good
candidate.

-- 
        -- Jason R. Thorpe <thorpej@zembu.com>