Date: Thu, 26 Dec 1996 10:47:15 -0500 From: dennis <dennis@etinc.com> To: Luigi Rizzo <luigi@labinfo.iet.unipi.it> Cc: isp@freebsd.org, hackers@freebsd.org Subject: Re: ipretard.c selective tcp/ip queues and throughput limiters Message-ID: <3.0.32.19961226104713.00ae68a0@etinc.com>
next in thread | raw e-mail | index | archive | help
At 09:24 PM 12/23/96 +0100, you wrote: >> Luigi Rizzo wrote: > >> > very useful. The only drawback is the overhead that this (and basically >> > everything using the divert socket) has: packets move to user space and >> > back, something you don't want to do on high-speed traffic. >. >> but as Kieth sklower at CSRG told me.. >> There's got to be a way to make it possible for essoteric or unusual >> modules to be implimented OUT OF THE KERNEL, or >> they are >> (1) hard to prototype >> (2) increasing the complexity of what IS in the kernel beyond the >> point of debuggability :) > >which is why I like very much the idea of divert sockets, tun devices >and similar things, but only when used in the proper way (e.g. >prototyping and/or slow speeds). Our "soon-to-be-released" version 2.0 of ET/BWMGR does this inline, and will provide for precise, bidirectional bandwidth allocation and control by data type (ie, http, ftp, IP address, etc) and is specifically designed for high speed systems With a few rules there is no noticable overhead. It will allow ISPs and corporate administrators to control the traffic of individual workstations, networks or the entire intranet without adversly affecting the routers performance or other traffic. So you could, for example, limit ftp downloads to 512k on a T1, guarantee a specific bandwidth for outgoing http traffic or limit video traffic to 56k to guarantee bandwidth availability for other critical services. Dennis Emerging Technologies, Inc. Router cards for BSD/OS, FreeBSD and Linux Standalone Routers Bandwidth Manager http://www.etinc.com sales@etinc.com (516) 271-4525
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?3.0.32.19961226104713.00ae68a0>