Subject: Re: FreeBSD Bus DMA
To: None <>
From: John S. Dyson <>
List: tech-kern
Date: 06/11/1998 15:47:01
Perry E. Metzger said:
> "John S. Dyson" writes:
> > Perry E. Metzger said:
> > > FreeBSD has ONE architecture up and fully supported. You have the
> > > i386, period. You've never finished a single port to another
> > > architecture.
> >
> > FreeBSD or me?  The very interesting thing is that whether or
> > not someone works on FreeBSD, has little to do with previous
> > experience.
> Fine. I'll accept that you have experience. Can you tell me, then, on
> which architectures other than Wintel boxes you have tried this new
> bus_dma design on, and what the results have been?
My experience is not tehnology based, but engineering.  And, of course,
I have done U**X and non U**X based OS work for approx 20yrs now.

> "Projecting personal experience?"
> I've been hacking on BSD since 4.2 on Vaxes. My memory stretches back
> to the PDP-8.
It must be *extreme* arrogance on your part then.

> > Please don't associate choosing FreeBSD as a platform with
> > a lack of experience, because that alienates people who
> > have had to choose it, due to it being the only alternative
> > that really works for them.
> Frankly, for most end users on a wintel platform, NetBSD and FreeBSD
> are going to be equally usable once installed, but that is a
> canard. You are distracting from my point, which is utterly
> unrelated. I never said anything about being stupid or
> lacking experience in general.
Funny, that is why our build times are 3X faster on FreeBSD, for NetBSD
based products than on NetBSD, right?  We even have a development
team avoiding *BSD all together because of NetBSD/X86 performance
problems.  Of course all of the platforms have many of the same,
architectural performance glitches.  Gessh, even Linux outperforms
NetBSD on many platforms, and that is embarassing (even to me.)

Things like a simple switch-out of VM code doesn't fix the problems,

> I made a specific claim, to whit, that the FreeBSD development team
> does not have anywhere near the experience with multi-platform
> portability that the NetBSD team has, and thus doesn't have any place
> making claims about portable architecture UNTIL it has managed to port
> its system to at least *one* other architecture other than
> Wintel. Hell, you don't even have the experience that the Linux people
> have at this point.
Who do you mean when you say "you."  Neither Linux nor NetBSD "know"
anything, it is the team members who posses "knowledge", and we
do have very competent people, and you have absolutely no monopoly on that.
(We have had Linux, QNX and other people working with us from
time to time -- it is really weird to somehow say that we are

> If you are going to claim that you have a better architectural design
> than us for multi-platform portability, you'd better be able to back
> that up with at least one non-Wintel box that your design is running
> on.
FreeBSD isn't perfect, but also claiming somehow that only you have
magical and more correct solutions seems to show that working with
you isn't going to happen.  We certainly don't want to be constrained
by the limitations of an OS that has lots of ports...  sort of...

This is a quality vs. quantity argument.  I suggest that there
is a difference between "working" and "WORKING."   I am very
concerned about some peoples generalization of NetBSD behavior
to FreeBSD.

We all have lots to learn, but being engineers, and not just technologists,
we have the tools to move forward.  Assuming ignorance in other parties
becomes quickly a very bad mistake (or at least an embarassment.)

John                  | Never try to teach a pig to sing,     | it just makes you look stupid,         | and it irritates the pig.