Path: utzoo!attcan!uunet!husc6!rice!titan!retrac
From: retrac@titan.rice.edu (John Carter)
Newsgroups: comp.dcom.lans
Subject: Re: Re: Ethermet Utilisation
Keywords: ugh.
Message-ID: <668@thalia.rice.edu>
Date: 5 May 88 03:23:53 GMT
References: <48@xenon.UUCP>
Sender: usenet@rice.edu
Reply-To: retrac@rice.edu (John Carter)
Organization: Rice University, Houston
Lines: 22

In article <48@xenon.UUCP> goodloe@xenon.UUCP (Tony Goodloe) writes:
...
>I was looking for more
>info like this, or real live experience.  Our net gets up to about 35%
>and we do have individual nodes capable of more. What I am curious about
>is what people have seen or caculated (using statistical means (no pun
>intended)) on other nets with lots of these beasts on them.

Willy Zwaenepoel and myself have implemented a bulk data transfer protocol
under the V System (*not* System V) which can sustain about 92% of the
theoretical ethernet bandwidth (8.4 Mbps user memory-to-user memory plus
protocol overhead of 90 bytes per 1024 byte data packet).  This is on
a very busy interdepartmental ethernet (so busy that when we monitored
it over a period of a few days we never saw the network load drop
below 8%, even in the wee hours of the night - too many fileservers
and gateways I guess :-).  Yet more proof that you can usefully use all
the bandwidth that the ethernet provides...

John Carter               Internet: retrac@rice.edu
Dept of Computer Science  CSNET:    retrac@rice.edu
Rice University           UUCP:     {internet node or backbone}!rice!retrac
Houston, TX