[3375] in linux-net channel archive
No subject found in mail header
daemon@ATHENA.MIT.EDU (Olaf Titz)
Fri Jun 21 05:11:31 1996
Date: Fri, 21 Jun 96 01:08 +0200
From: olaf@bigred.inka.de (Olaf Titz)
To: submit-linux-dev-net@ratatosk.yggdrasil.com
Newsgroups: linux.dev.net
Path: not-for-mail
From: Olaf Titz <olaf@bigred.inka.de>
Subject: Re: Traffic shaper
Message-ID: <dtbmxg.a6@bigred.inka.de>
Date: 21 Jun 1996 01:08:01 +0200
References: <199606200832.JAA19103@snowcrash.cymru.net>
<96Jun20.052211edt.106196-7187+6418@vger.rutgers.edu>
Organization: private Linux site, southern Germany
Lines: 25
Mike Kilburn <mike@lserv.conexio.co.za> wrote:
> I see. Well I would not drop any frames so I guess what I am talking about
> is not a traffic shaper but a "slow link simulator". The amount of buffer
> space required to hold the receive data could get quite large if you were
> trying to take a T1 down to a 14400kbs but it is quantifiable. The data
IMHO that would only need as much buffer space as would actually fit
in the outgoing data rate. I.e. the (worst possible) maximum lifetime
of an IP packet is 255 seconds, after that it gets killed anyway; at
14.4kpbs you can (nominally) transfer 459000 bytes in this time.
Down to the common TTL of 64 it's only 115200 bytes.
If you ever get to buffer more than this, you _must_ throw away some
packets, or the outgoing link will not be able to catch up with the
incoming data (whether it's T1 or 64kbps doesn't matter). I _guess_
this is what already is done in the kernel for a real slow link.
Or what is done when you stuff a PPP link from the ethernet?
olaf
--
___ Olaf.Titz@inka.de or @{stud,informatik}.uni-karlsruhe.de ____
__ o <URL:http://www.inka.de/~bigred/> <IRC:praetorius>
__/<_ >> Just as long as the wheels keep on turning round
_)>(_)______________ I will live for the groove 'til the sun goes down << ____
