freebsd router

[Danial Thom]

--- "Matthew D. Fuller"
<fullermd at over-yonder.net> wrote:

> On Wed, Jan 11, 2006 at 07:22:15AM -0800 I
> heard the voice of
> Danial Thom, and lo! it spake thus:
> >
> > You're basically limited in an MP environment
> to sucking the packet
> > out of the ring and throwing it into a queue.
> 
> I can only presume you're being willfully
> silly.  An MP environment is
> quite capable of grabbing the packet from an
> interface, and then
> CONTINUING TO PROCESS IT while the other CPU
> grabs the next packet and
> starts processing it.  You can process through
> to completion JUST as
> easily on a MP system as you can on a UP
> system, except that you're
> not blocking the next packet while you do it. 
> Furthermore, you've got
> another CPU to do things like update the
> routing table and deal with
> OTHER interrupts and kernel tasks at the same
> time.


That all sounds good but it doesn't work all that
peachily in practice. Your concept of this
ultra-efficient scheduler that can do all this
stuff with no overhead is just plain fantasy.

> 
> 
> > I can pass a million pps on freebsd 4.x, so
> perhaps your *hardware
> > limit* has more to do with you or them not
> understanding the test?
> 
> I'll leave you to argue with the people writing
> the network subsystem
> about their understanding of it.
> 
> 
> > Funny that they don't mention packet loss,
> maybe they forgot to
> > look?
> 
> Why, yes, in point of fact, they did (rather,
> the total lack of it),
> which you'd know if you were following the
> discussions on the lists
> specifically set up to talk about these things,
> rather than simply
> puffing yourself up on an unrelated list.


You know, I just read the thread on the snippet
you posted, and its frightening to me that they
are committing this hacked code to the source
after 1 rather uncontrolled test from a known
BSer like Andre Oppermann. I think it just goes
to show how utterly disorganized and desparate
the FreeBSD "team" has become. There used to be a
controlled method to commiting code; thoughtful
discussion between several people with strong
knowledge of all aspects of the affected
subsystems. Now some "dude" does some test with
FASTFORWARDING enabled (which uses a different
path than any real router would use)and bam, lets
commit the code!

Our buddy Andre has been making bogus claims for
years now, so be careful who you snuggle up with.
Here's a paper he wrote on 5.3, when he claimed
FreeBSD 5.3 could route 1 million pps with the
"new" fastforwarding code:

http://people.freebsd.org/~andre/FreeBSD-5.3-Networking.pdf

page 11 is the reference. Of course now he says
that his "new" code can do 750Kpps and that more
than 800K is impossible? lol. Please believe me
when I tell you that you are being lied to and
bamboozled. I really do know what I'm talking
about. The freebsd "team" no longer has the
talent to get this project done.

Its really quite frightening what FreeBSD has
become. I truly wonder if it will ever be a
trustworthy O/S again. It reminds me of the early
days of LINUX.  A big mess run by a bunch of
college kids.

DT

__________________________________________________
Do You Yahoo!?
Tired of spam?  Yahoo! Mail has the best spam protection around 
http://mail.yahoo.com