From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qk0-x232.google.com (mail-qk0-x232.google.com [IPv6:2607:f8b0:400d:c09::232]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 530F73B2A4 for ; Mon, 27 Nov 2017 21:08:05 -0500 (EST) Received: by mail-qk0-x232.google.com with SMTP id a142so35187508qkb.5 for ; Mon, 27 Nov 2017 18:08:05 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc; bh=J7gPgC4b1hdWk3qd+sEJJQaJreAYbppa54UTaCOyza0=; b=CByqULhUp5EbqClUIydC+fF2gpXby1LLmpNfir5vnhf/Jfg94dcNfR5eA+LJzI3g/Z 7FzL8O150hZuLyiFSspoM7gN4GlO1metP8OpLQ4HHeJ00roHCB50zoWstk9RMRCNyanB 7VndZ3RTm8g6AnkgK4hQOtQQL81Zzs/NWgnjR6g1ajP7WmHk9y6Z89mnw9JeGjyaPqVC VsMIvOtah+DcDiYZHmWtf7NUZxuVfUgzQ7Ooq/Zda38BjU0WrVCxR94XyGDnmIAam1z6 DhbaXsNctRZWHWViNs9lClojP/O2hzPjJyU1jPUYRwPe5gII7wjHgghBvR8o8gzh11lz zX7A== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc; bh=J7gPgC4b1hdWk3qd+sEJJQaJreAYbppa54UTaCOyza0=; b=Xs50psqKu+aCMp5MtnQQMy3aKh5CxzQnkeJ7edf/zoY0EQGmCofRjNJSVFI+MPtfLt yBP8rd3Gaj2GcRL7vnX8X4n60NJDnOODFRtE/Jl50TUfHsTEl7dTl6dSe+Tb6Ev3pxHD pqQdY24dGZN7j4OkEK8qvCrv2NGGpwBuNS87u76o7Qaro5jDrPW7kZDNeqbRtiNBkZ9X R4ro/7nq97/r6Syx/b5A2kcKTgPjsYHni3MWB8gq2vXw2T1/5cdXOb2lQp3lq/6Fd/e9 Bo3o87DodYe3wLcLvv3/XL8q4KrGtk4HxdRhnhzkUQN8fau3+wYpuKTsR09ap+7dLBKC JIng== X-Gm-Message-State: AJaThX6z/oRkLOs4D5p9gQ+h8k/4K9/UeDylhT9MUcupKw/Bzvy33Rrs Vu/4ldBZuna+ccoqO7JrlI5gueysKl3pJlm0338= X-Google-Smtp-Source: AGs4zMbVBbuQeuYORmSbIyI18jK48LqUH2LdI5FoTfyAe5zjR7SBIQumOeDmtHTtPOSoQZjrlCSZIa7jslcHad6FmUg= X-Received: by 10.55.179.135 with SMTP id c129mr57704663qkf.254.1511834884715; Mon, 27 Nov 2017 18:08:04 -0800 (PST) MIME-Version: 1.0 References: <87shd18c51.fsf@toke.dk> In-Reply-To: From: Aaron Wood Date: Tue, 28 Nov 2017 02:07:53 +0000 Message-ID: To: Dave Taht , Martin Geddes Cc: bloat Content-Type: multipart/alternative; boundary="94eb2c06fabe433b5a055f017d55" Subject: Re: [Bloat] Bufferbloat in high resolution + non-stationarity X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 28 Nov 2017 02:08:05 -0000 --94eb2c06fabe433b5a055f017d55 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable For the graphs, it would be great for f they were using a normalize output that allows for easy comparisons between runs. Especially the y axis for the =E2=80=9Call=E2=80=9D graph. On Mon, Nov 27, 2017 at 15:55 Dave Taht wrote: > On Mon, Nov 27, 2017 at 3:16 PM, Martin Geddes > wrote: > > Hi Toke, > > > > The two critical references are this paper and this PhD thesis. The > former > > describes "cherish-urgency" multiplexing. The "cherish" is what is > different > > to today's scheduling. It is used to create a new class of algorithm > whose > > goal is global optimisation, not local optimisation (and global > > pessimisation). > > > > The latter describes a paradigm change from "build it and then reason > about > > emergent performance" to "reason about engineered performance and then > build > > it". It works in practise, so whether it works in theory is left as an > > exercise to the reader. > > > > The first step is to get the measurement right. I'm running a public > > workshop in London on 8th Dec, and I am happy to accommodate anyone fro= m > > this list at our internal cost. > > > > Everyone working on AQM has done the best possible within the paradigm > they > > are operating. There is a bigger box of possibilities available, but it > > needs you to engage with a paradigm change. > > We are currently benchmarking the known alternatives vs everything > else via a dozen methods we understand. > > fq_codel v "cake": > > > http://www.drhleny.cz/bufferbloat/cake/round1/eg_csrt_rrulbe_eg_fq_codel_= 200mbit/index.html > > > http://www.drhleny.cz/bufferbloat/cake/round1/eg_csrt_rrulbe_eg_cakeeth_2= 00mbit/index.html > > > Martin > > > > About me Free newsletter Company website Twitter Zoom My new start-up N= ot > > LinkedIn Martin Geddes Consulting Ltd, Incorporated in Scotland, number > > SC275827 VAT Number: 859 5634 72 Registered office: 17-1 > 9 > East London > > Street, Edinburgh, EH7 4BN > > > > On 26 November 2017 at 12:20, Toke H=C3=B8iland-J=C3=B8rgensen > wrote: > >> > >> Martin Geddes writes: > >> > >> > It doesn't matter what scheduling algorithm you build if it creates > >> > arbitrage or denial-of-service attacks that can arm a systemic > >> > collapse hazard. The good news is we have a new class of scheduling > >> > technology (that works on a different paradigm) that can fully addre= ss > >> > all of the requirements. We are currently deploying it to enable the > >> > world's first commercial quality-assured broadband service. > >> > >> Could you point to any research papers describing this technology? Wou= ld > >> be interesting to read up on... > >> > >> -Toke > > > > > > > > _______________________________________________ > > Bloat mailing list > > Bloat@lists.bufferbloat.net > > https://lists.bufferbloat.net/listinfo/bloat > > > > > > -- > > Dave T=C3=A4ht > CEO, TekLibre, LLC > http://www.teklibre.com > Tel: 1-669-226-2619 > _______________________________________________ > Bloat mailing list > Bloat@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/bloat > --94eb2c06fabe433b5a055f017d55 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable For the graphs, it would be great for f they were using a normalize output = that allows for easy comparisons between runs. Especially the y axis for t= he =E2=80=9Call=E2=80=9D graph.
On Mon, Nov 27, 2017 at 15:55 Dave Taht <dave.taht@gmail.com> wrote:
On Mon, Nov 27, 2017 at 3:16 PM, Martin Geddes <mail@martingeddes.com&= gt; wrote:
> Hi Toke,
>
> The two critical references are this paper and this PhD thesis. The fo= rmer
> describes "cherish-urgency" multiplexing. The "cherish&= quot; is what is different
> to today's scheduling. It is used to create a new class of algorit= hm whose
> goal is global optimisation, not local optimisation (and global
> pessimisation).
>
> The latter describes a paradigm change from "build it and then re= ason about
> emergent performance" to "reason about engineered performanc= e and then build
> it". It works in practise, so whether it works in theory is left = as an
> exercise to the reader.
>
> The first step is to get the measurement right. I'm running a publ= ic
> workshop in London on 8th Dec, and I am happy to accommodate anyone fr= om
> this list at our internal cost.
>
> Everyone working on AQM has done the best possible within the paradigm= they
> are operating. There is a bigger box of possibilities available, but i= t
> needs you to engage with a paradigm change.

We are currently benchmarking the known alternatives vs everything
else via a dozen methods we understand.

fq_codel v "cake":

http://ww= w.drhleny.cz/bufferbloat/cake/round1/eg_csrt_rrulbe_eg_fq_codel_200mbit/ind= ex.html

http://www= .drhleny.cz/bufferbloat/cake/round1/eg_csrt_rrulbe_eg_cakeeth_200mbit/index= .html

> Martin
>
> About me Free newsletter Company website Twitter Zoom My new start-up = Not
> LinkedIn Martin Geddes Consulting Ltd, Incorporated in Scotland, numbe= r
> SC275827 VAT Number: 859 5634= 72 Registered office: 17-19 East London
> Street, Edinburgh, EH7 4BN
>
> On 26 November 2017 at 12:20, Toke H=C3=B8iland-J=C3=B8rgensen <toke@toke.dk> wrote:<= br> >>
>> Martin Geddes <mail@martingeddes.com> writes:
>>
>> > It doesn't matter what scheduling algorithm you build if = it creates
>> > arbitrage or denial-of-service attacks that can arm a systemi= c
>> > collapse hazard. The good news is we have a new class of sche= duling
>> > technology (that works on a different paradigm) that can full= y address
>> > all of the requirements. We are currently deploying it to ena= ble the
>> > world's first commercial quality-assured broadband servic= e.
>>
>> Could you point to any research papers describing this technology?= Would
>> be interesting to read up on...
>>
>> -Toke
>
>
>
> _______________________________________________
> Bloat mailing list
> Bloat= @lists.bufferbloat.net
> https://lists.bufferbloat.net/listinfo/bloat >



--

Dave T=C3=A4ht
CEO, TekLibre, LLC
ht= tp://www.teklibre.com
Tel: 1-669-226-2619
_______________________________________________
Bloat mailing list
Bloat@list= s.bufferbloat.net
https://lists.bufferbloat.net/listinfo/bloat
--94eb2c06fabe433b5a055f017d55--