Re: VM and classzone

From: Craig Kulesa (ckulesa@loke.as.arizona.edu)
Date: Sat May 20 2000 - 13:58:39 EST


On Sat, 20 May 2000 Carlo Wood wrote:

> In order to come to a solution, I'd like to suggest the
> following:
>
> - - Linus makes a short list of what he thinks are the
> pros and cons of Andreas design, so it is more clear

Classzone was presented and discussed extensively on the linux-mm list at
the end of April. Start here, follow the thread onwards:

        http://mail.nl.linux.org/linux-mm/2000-04/msg00172.html

> of benchmark tests if proposed by all parties that will
> produce *numbers* - so we will be able to actually see
> the impact of Andreas patch (with and without).

I remember seeing a post or two like that here. But it seems that the
_real_ issues w/ classzone are the basic tenets of its fundamental
design. I actually see nice performance with classzone on generic PC's,
but there are clearly several ways to reach that goal. Additionally, the
aim is to have a _flexible_ VM system that will handle a wide variety of
memory topologies (NUMA, etc...).

Craig Kulesa

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



This archive was generated by hypermail 2b29 : Tue May 23 2000 - 21:00:19 EST