[34725] in North American Network Operators' Group
Re: T3 Latency
daemon@ATHENA.MIT.EDU (Steven M. Bellovin)
Sat Feb 17 11:24:12 2001
From: "Steven M. Bellovin" <smb@research.att.com>
To: Paul Bradford <pbradford@adelphia.net>
Cc: Charles Scott <cscott@gaslightmedia.com>,
Chris Cappuccio <chris@dqc.org>,
Jeffrey Burgan <burgan@corp.home.net>,
Brian Guinan <doctor@dman.com>, Jonathan Cohn <mail57543@pop.net>,
nanog@merit.edu
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Date: Sat, 17 Feb 2001 11:19:09 -0500
Message-Id: <20010217161910.C594635C42@berkshire.research.att.com>
Errors-To: owner-nanog-outgoing@merit.edu
In message <Pine.LNX.4.10.10102171056510.4084-100000@merlin.noc.adelphia.net>,
Paul Bradford writes:
>
>Charles,
> One thing I have a hard time explaining to some customers is that
>latency is one thing.... what does it tell me... it tells me that from
>one hop to another things are a bit slow.... the real important thing is
>how are you're throughput speeds... I started a thread a while back asking
>a similar question... is ping/traceroute a good measurement of throughput
>on the link? the unanimous response was use pathchar or mtr or ttcp which
>all give you a better guestimate of how your link is doing performance
>wise..
Latency and packet loss both put an upper bound on throughput. See,
for example, http://www.acm.org/sigcomm/sigcomm98/tp/abs_25.html
or draft-ietf-pilc-error-06.txt
--Steve Bellovin, http://www.research.att.com/~smb
