Lockless algorithms [was Re: splxxx replacements?]

[Bill Huey (hui)]

On Thu, Nov 16, 2006 at 10:35:31AM -0800, Matthew Dillon wrote:
>     * A multi-layer abstraction (where one interrupt can interrupt another
>       interrupt)... also known as preemption in FreeBSDland, is a bad idea
>       that can lead to all sorts of unexpected side effects.  I just don't
>       want to have to deal with it.

Matt,

What's going on with DragonFly ? It might be a good thing to have some
technical discusssion on commit be summarized here as well. Apparently
you folks decided to move away from tokens in favor of straight
spinlocks since they were a pain in the ass to use and there was no public
mention about this.

Another thing I've heard is that your route table stuff went lockless,
which is a significant change and worth noting as well as discussing. And
fron IRC discussions, RCU is starting to be pushed by various people,
correct ?

What's going on with you folks and lockless algorithms ?

bill