[45336] in North American Network Operators' Group
Re: representativeness of flow data based on samples
daemon@ATHENA.MIT.EDU (Jennifer Rexford)
Thu Jan 31 13:28:30 2002
Date: Thu, 31 Jan 2002 13:26:47 -0500 (EST)
Message-Id: <200201311826.NAA79369@chips.research.att.com>
From: Jennifer Rexford <jrex@research.att.com>
To: jabley@automagic.org
Cc: nanog@merit.edu
Errors-To: owner-nanog-outgoing@merit.edu
> There are a few vendors who now provide traffic export from high-speed
> interfaces by sampling those interfaces at a particular rate, and
> using the sampled packets to populate the per-flow counters, rather
> than looking at every packet.
Folks might be interested in the Internet Draft on "A framework for
passive packet measurement" that focuses on packet sampling. See
http://www.ietf.org/internet-drafts/draft-duffield-framework-papame-00.txt
There's a public mailing list at
listname : psamp@ops.ietf.org
subscribe: psamp-request@ops.ietf.org (with "subscribe" as the message)
archive : https://ops.ietf.org/lists/psamp/
The goal is to define a minimal set of requirements that need to be
supported in routers (or line cards) to meet the needs of folks that
operate networks. Feedback more than welcome!
-- Jen
