[37163] in North American Network Operators' Group
Re: Traffic per Prefix Length
daemon@ATHENA.MIT.EDU (Paul G. Donner)
Fri May 4 13:54:31 2001
Message-Id: <5.0.2.1.0.20010504080700.02945c10@lint.cisco.com>
Date: Fri, 04 May 2001 13:52:51 -0600
To: arnold@nipper.de, nanog@merit.edu
From: "Paul G. Donner" <pdonner@cisco.com>
In-Reply-To: <20010504015557.A8510@gateway.nipper.de>
Mime-Version: 1.0
Content-Type: text/plain; charset="us-ascii"; format=flowed
Errors-To: owner-nanog-outgoing@merit.edu
There are many interesting pieces of data and there is plenty of data
in the Internet to collect. ;-)
might show how much work routers have to do in particular areas of the
table (which, granted, varies from location to location) when doing
longest-prefix match. what areas of the table are hit more than others.
"sh ip cef traffic prefix"
At 01:55 AM 5/4/2001 +0200, Arnold Nipper wrote:
>On Thu, May 03, 2001 at 07:09:24PM -0600, Paul G. Donner wrote:
> >
> > does anyone collect stats that would facilitate the derivation of
> > the number of packets forwarded per prefix length (per unit time)
> > in the routing table or per prefix length range? percentages would
> > work too.
> >
>
>Interesting ... Do you think that this will give you any useful information?
>I would be more interested in how far packets go. Not in networks terms but
>in real distance. Next would be to go further up the stack and see if there
>is a difference in protocols (i.e www compared to dns).
>
>-- Arnold
