From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from homiemail-a102.g.dreamhost.com (sub4.mail.dreamhost.com [69.163.253.135]) by huchra.bufferbloat.net (Postfix) with ESMTP id 213E9201240; Thu, 16 Apr 2015 07:47:44 -0700 (PDT) Received: from homiemail-a102.g.dreamhost.com (localhost [127.0.0.1]) by homiemail-a102.g.dreamhost.com (Postfix) with ESMTP id 03FF820047B8C; Thu, 16 Apr 2015 07:47:44 -0700 (PDT) Received: from kmnimac.local (c-50-156-111-45.hsd1.ca.comcast.net [50.156.111.45]) (using TLSv1 with cipher ECDHE-RSA-AES128-SHA (128/128 bits)) (No client certificate requested) (Authenticated sender: nichols@pollere.net) by homiemail-a102.g.dreamhost.com (Postfix) with ESMTPSA id 59EC920047B8A; Thu, 16 Apr 2015 07:47:43 -0700 (PDT) Message-ID: <552FCB8D.9070504@pollere.com> Date: Thu, 16 Apr 2015 07:47:41 -0700 From: Kathleen Nichols User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.10; rv:31.0) Gecko/20100101 Thunderbird/31.6.0 MIME-Version: 1.0 To: codel@lists.bufferbloat.net References: <87twwg5m1u.fsf@toke.dk> <91CCD5F5-5F5D-435D-9FD1-77BBEEC1E84E@gmail.com> In-Reply-To: <91CCD5F5-5F5D-435D-9FD1-77BBEEC1E84E@gmail.com> Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Cc: cake@lists.bufferbloat.net Subject: Re: [Codel] [Cake] hard limit codel X-BeenThere: codel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: CoDel AQM discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 16 Apr 2015 14:48:15 -0000 You are taking this much too seriously. This was written in order to write a paper. There is no study of the "problem" just a presentation of the "solution". They probably even submitted a patent. On 4/16/15 5:00 AM, Jonathan Morton wrote: >=20 >> On 16 Apr, 2015, at 14:50, Toke H=C3=B8iland-J=C3=B8rgensen >> wrote: >>=20 >> I'll add, though, that I have seen the sentiment expressed here >> ("we need to limit the max delay of CoDel") in other contexts. And, >> well, delay spikes *is* a problem! >=20 > Yes, they are. >=20 > But in general AQM can=E2=80=99t be used to solve that problem without = also > suffering poor throughput; combining AQM with FQ *does* solve it. > Just like FQ is unfair to single flows competing against a swarm, but > classifying the swarm traffic into a separate traffic class fixes > that problem too. >=20 > Which of course is why cake uses AQM, FQ *and* Diffserv, all at > once. >=20 > The linked paper didn=E2=80=99t measure HLC against fq_codel, even thou= gh > they mention fq_codel. That=E2=80=99s a major shortcoming. >=20 > - Jonathan Morton >=20 > _______________________________________________ Codel mailing list=20 > Codel@lists.bufferbloat.net=20 > https://lists.bufferbloat.net/listinfo/codel >=20