Subject: Re: FreeBSD Bus DMA
To: None <>
From: Ted Lemon <>
List: tech-kern
Date: 06/11/1998 20:10:58
> > So you're willing to make claims about FreeBSD's performance, but
> > you're not willing to back them up with numbers?   Am I the only
> > person to whom this seems more than a little bit disingenuous?
> > 
> If I don't do all your work for you to improve your OS, it isn't
> my fault. You should take it as a challenge to improve the results
> of your project, just as I do mine.

John, you're saying that NetBSD performs in an inferior manner to
FreeBSD.   I haven't seen any evidence of that.   This is not
something that I'm hearing from other people.   I suspect that it's a
prejudice, and not a fact.   This is why I'm asking you about
benchmarks.   If you haven't run benchmarks, how do you know?   The
answer is that you don't.   That is what I am trying to point out.

> What VM fix are you talking about????  If you are talking about the
> FreeBSD code, there is really no fix, but a rework.  If you are talking
> about that silly 1second bug in the NetBSD VM code eons ago that
> I helped you guys with, that wasn't even a fix.  The VM code at that
> time was so far gone as to be not worth fixing, and you guys are
> moving to follow that route that I knew long ago was the only real
> solution.

I'm talking about the complete rewrite of NetBSD's VM code, which
happens to correct the problem that you were talking about when you
brought up NetBSD's poor performance under paging at the FreeBSD BOF
in New Orleans (or was it San Diego?).

> I chose to fix the VM code, by making it work as advertised, and
> you guys ended up rewriting alot of it from scratch.  So what?

I don't know so what.   That's what I'm asking you.