Re: new scheduler

[Tim Hockin <tphocki@www.orl.ilstu.edu>]

> - better throughput (on SMP systems) by less memory contention
>   and less unneeded context switches
> - better interactive response under load

these are the two that strike ME as most important.  I am finishing up a 
complete re-write of my pset implementation, which has a minor chnage in
schedule().  I have the kernel portion 95% done (still not completely tested
and the user space stuff is not done) if you want to look at what I did.  I 
have a few questions inside this section that perhaps you can answer in the 
course of redesigning the whole thing.

Tim
-
Linux-future: thinking about the future of the Linux kernel
Archive:      http://humbolt.nl.linux.org/lists/
Wish list:    http://users.ox.ac.uk/~mert0236/linux-future.html