Date: Mon, 29 Mar 1999 17:14:28 -0500 (EST) From: Garrett Wollman <wollman@khavrinen.lcs.mit.edu> To: alk@pobox.com Cc: freebsd-net@FreeBSD.ORG Subject: Re: FreeBSD as a router Message-ID: <199903292214.RAA14019@khavrinen.lcs.mit.edu> In-Reply-To: <14079.61724.162248.667212@avalon.east> References: <4.1.19990329115145.00a62ab0@mail.dnai.com> <199903292051.UAA10838@inner.net> <14079.61724.162248.667212@avalon.east>
next in thread | previous in thread | raw e-mail | index | archive | help
<<On Mon, 29 Mar 1999 15:34:58 -0600 (CST), Anthony Kimball <alk@pobox.com> said:
> in determining maximum routing throughput: The box has to do a lot
> more routing for 512B packets than it does for 1024B packets at the
> same bandwidth.
Very true. Just some quick statistics for one real-world network:
Port Link Packet Sizes
Num Status 0-64 65-127 128-255 256-511 512-1023 1024-1518
===============================================================================
26 ACTIVE 1235904191 407413622 49843785 46400345 68324479 340953031
...in percentage terms, that's:
57.5% 19.0% 2.3% 2.2% 3.2% 15.9%
These numbers include all of the external network traffic of a
medium-sized (500 people/1200 machines) nationally-reknowned research
laboratory over the course of 13 days. As you can see, more than half
of all packets are relatively tiny, and consist of things such as
ICMPs, small TCP segments from interactive sessions, and DNS queries.
(One of these days I'll set up port mirroring so that I can see just
what all that traffic is.)
-GAWollman
--
Garrett A. Wollman | O Siem / We are all family / O Siem / We're all the same
wollman@lcs.mit.edu | O Siem / The fires of freedom
Opinions not those of| Dance in the burning flame
MIT, LCS, CRS, or NSA| - Susan Aglukark and Chad Irschick
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?199903292214.RAA14019>