Mime-Version: 1.0 (Apple Message framework v1283)
Content-Type: text/plain; charset=us-ascii
From: Michael Welzl <michawe@ifi.uio.no>
In-Reply-To: <20140423163717.GG86778@verdi>
Date: Thu, 24 Apr 2014 13:04:27 +0200
Content-Transfer-Encoding: quoted-printable
Message-Id: <0E4B3960-4AA1-4F20-A46F-913E143AA18A@ifi.uio.no>
References: <5357B281.1030900@alvestrand.no>
 <CAA93jw6paiARfbd_S8_OzBLy9pxavxe9wVM_Yqte_oUaPBHxiw@mail.gmail.com>
 <20140423163717.GG86778@verdi>
To: John Leslie <john@jlc.net>
Archived-At: http://mailarchive.ietf.org/arch/msg/rtcweb/gTfbznJdlCYiPsB0tk3275Yhv2c
Cc: "rtcweb@ietf.org" <rtcweb@ietf.org>
Subject: Re: [rtcweb] Pictures of congestion control on the Internet - which
 is more realistic?
Precedence: list

On 23. apr. 2014, at 18:37, John Leslie wrote:

> Dave Taht <dave.taht@gmail.com> wrote:
>>=20
>> I'm not sure if we have a shared definition of "congestion".  Mine is
>> network delays exceeding that of what human factors research notes
>> as "perceptible" with about 20ms as the outer bound.
>=20
>   I, OTOH, am quite sure we don't have a shared definition of =
congestion.
>=20
>   My preferred definition is rate-of-arrival exceeding =
rate-of-forwarding.

FWIW, there's RFC 6077, which discusses definitions of congestion and =
congestion control in its introduction. It says:

" Congestion can be defined as a state or condition that occurs when
   network resources are overloaded, resulting in impairments for
   network users as objectively measured by the probability of loss
   and/or delay.  The overload results in the reduction of utility in
   networks that support both spatial and temporal multiplexing, but no
   reservation"

which is based on a presentation by Keshav in 2007, which, in turn, is =
based on the long and boring discussion about this definition that =
happened when ICCRG was born. Been there, done that, let's not repeat =
please.

Buuuuuut this seems off topic for the context here anyway... if you =
really want to discuss this definition, I suggest to take it to ICCRG. =
There, we will tell you to read the mailing list archives  :-)

Cheers,
Michael