Date: Mon, 05 Jul 1999 13:53:02 -0700 From: David Greenman <dg@root.com> To: Dann Lunsford <dann@greycat.com> Cc: Net@FreeBSD.ORG Subject: Re: mbuf-less IP? Message-ID: <199907052053.NAA05826@implode.root.com> In-Reply-To: Your message of "Mon, 05 Jul 1999 09:33:56 PDT." <3780DE74.2DD4F526@greycat.com>
next in thread | previous in thread | raw e-mail | index | archive | help
>Just a question out of pure curiosity. I've been studying the Stevens
>set ("TCP/IP Illustrated", all three vols) and came across a comment
>that Van Jacobson had an experimental IP stack that didn't use the mbuf
>structures. The reasoning was that the current implementation was
>designed when memory was much more constrained, CPU speed was lower, and
>networks weren't as fast or fat. Reportedly, Jacobson found
>siginificant performance improvements and better resource utilization
>over current, mbuf based, implementations.
>
>So... Has anybody looked into this idea? I realize it would entail
>*MAJOR* rewrites and redesigns, and would not be undertaken lightly, but
>perhaps it would be worth considering for the future. The current
>design smacks of "It's always been done that way"; whenever I hear that
>phrase, a chill goes up my spine :-).
>
>Anyway, that's it. Just tossing it into the ring; please don't throw
>knives back :-).
We've made substantial improvements in FreeBSD to the way that mbufs are
allocated and used which have mitigated much of the old problems. It could
still be a lot better, however. It's really the socket layer that needs the
rewrite; I don't think the TCP/IP stack itself would be that difficult.
-DG
David Greenman
Co-founder/Principal Architect, The FreeBSD Project - http://www.freebsd.org
Creator of high-performance Internet servers - http://www.terasolutions.com
To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-net" in the body of the message
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199907052053.NAA05826>