From owner-freebsd-hackers  Sun Jun 25 11:40:38 1995
Return-Path: hackers-owner
Received: (from majordom@localhost)
          by freefall.cdrom.com (8.6.10/8.6.6) id LAA01365
          for hackers-outgoing; Sun, 25 Jun 1995 11:40:38 -0700
Received: from gndrsh.aac.dev.com (gndrsh.aac.dev.com [198.145.92.241])
          by freefall.cdrom.com (8.6.10/8.6.6) with ESMTP id LAA01359
          ; Sun, 25 Jun 1995 11:40:35 -0700
Received: (from rgrimes@localhost) by gndrsh.aac.dev.com (8.6.11/8.6.9) id LAA01851; Sun, 25 Jun 1995 11:40:50 -0700
From: "Rodney W. Grimes" <rgrimes@gndrsh.aac.dev.com>
Message-Id: <199506251840.LAA01851@gndrsh.aac.dev.com>
Subject: Re: FreeBSD as a router
To: dennis@et.htp.com (dennis)
Date: Sun, 25 Jun 1995 11:40:50 -0700 (PDT)
Cc: phk@freefall.cdrom.com, freebsd-hackers@freebsd.org
In-Reply-To: <199506251650.MAA26983@mail.htp.com> from "dennis" at Jun 25, 95 12:50:53 pm
X-Mailer: ELM [version 2.4 PL24]
MIME-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Content-Length: 1483      
Sender: hackers-owner@freebsd.org
Precedence: bulk

> 
> >> >Here is the funny shaped conical hat, please go think about what you
> >> >said for a while <:-).
> >> >
> >> I love this "I can demonstrate" stuff. Try the hat on yourself. To get from
> >> a to b to c requires 2 transmission times at 10mbs (because you have to wait
> >> for the full frame to arrive, which was what we were talking about) , which
> >> means that net throughput cannot be greater than 50% of 10mbs.
> >> 
> >
> >Why shouldn't I be able to receive the next frame while transmitting the 
> >first one ?
> >
> >Recv Frame 1  Recv Frame 2  Recv Frame 3
> >------------> ------------> ------------>
> >	      Send Frame 1  Send Frame 2 ...
> >
> 
> It has nothing to do with receiving while transmitting, it has to do with
> physical science.
> 
> Box A ----> Box B (the Ethernet Router) -----> Box C
> 
> I transmit a frame from Box A to Box B. For simplicity say it takes 100
> microseconds to get  to point B at 10mbs. I now need to re-transmit the
...

Your are seriously confusing latency with throughput.  I agree that we
will see a 200uS latency for your sensario, but that does not necessarily
make the throughput 1/200uS*packetsize.  Latency does not effect throughput
for non acked data streams and may not effect it for acked data streams
if the window size is such that the pipe is kept full.


-- 
Rod Grimes                                      rgrimes@gndrsh.aac.dev.com
Accurate Automation Company                 Reliable computers for FreeBSD