From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail.taht.net (mail.taht.net [IPv6:2a01:7e00::f03c:91ff:feae:7028]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 5AC213B2A4 for ; Sun, 3 Dec 2017 22:29:14 -0500 (EST) Received: from nemesis.taht.net (unknown [IPv6:2603:3024:1536:86f0:2e0:4cff:fec1:1206]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by mail.taht.net (Postfix) with ESMTPSA id 8C14B213CA; Mon, 4 Dec 2017 03:29:12 +0000 (UTC) From: Dave Taht To: Pete Heist Cc: Cake List References: <7855AA2C-BF69-4B9E-8794-A7D15DE44C4F@gmail.com> Date: Sun, 03 Dec 2017 19:29:11 -0800 In-Reply-To: <7855AA2C-BF69-4B9E-8794-A7D15DE44C4F@gmail.com> (Pete Heist's message of "Sat, 2 Dec 2017 21:13:51 +0100") Message-ID: <87k1y3f9x4.fsf@nemesis.taht.net> User-Agent: Gnus/5.13 (Gnus v5.13) Emacs/24.5 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable Subject: Re: [Cake] cake flenter results round 4 X-BeenThere: cake@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Cake - FQ_codel the next generation List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Mon, 04 Dec 2017 03:29:14 -0000 Pete Heist writes: > http://www.drhleny.cz/bufferbloat/cake/round4/ > > Round 4 Tarball: http://www.drhleny.cz/bufferbloat/cake/round4.tgz > > *** Notes/Analysis *** > > * I took the average satellite Internet latency of 638ms > (https://en.wikipedia.org/wiki/Satellite_Internet_access) and tried 20/20= mbit > 320ms delay each direction. So here we have 20mbit symmetric Internet wit= h Cake > running on both the CPE and satellite- common config! I=E2=80=99m sorry w= e don=E2=80=99t have > Tooway 6/22mbit anymore for a real test, which was also here in desperati= on at > the house at some point. > > * Since I left the default rtt setting for most tests, these tests are an > exploration of what problems that can cause. I enjoy failed experiments t= hough > (I=E2=80=99m looking at you penicillin). Here we can see that as we incre= ase Cake=E2=80=99s rtt > setting, total bandwidth improves, generally: > > http://www.drhleny.cz/bufferbloat/cake/round4/cake_rtt_200ms_rrulbe_eg_ca= ke_18.0mbit/index.html (22.77mbit) > http://www.drhleny.cz/bufferbloat/cake/round4/cake_rtt_400ms_rrulbe_eg_ca= ke_18.0mbit/index.html (26.17mbit) > http://www.drhleny.cz/bufferbloat/cake/round4/cake_rtt_600ms_rrulbe_eg_ca= ke_18.0mbit/index.html (25.99mbit) > http://www.drhleny.cz/bufferbloat/cake/round4/cake_rtt_800ms_rrulbe_eg_ca= ke_18.0mbit/index.html (25.96mbit) > http://www.drhleny.cz/bufferbloat/cake/round4/cake_rtt_1000ms_rrulbe_eg_c= ake_18.0mbit/index.html (29.04mbit) > > * Cool. In this case, increasing rtt actually _improves_ host fairness, as > opposed to what we see with Ethernet around rtt 1ms, although TCP RTT suf= fers: Hmm. > > http://www.drhleny.cz/bufferbloat/cake/round4/hostiso_cake_200ms_eg_cake_= src_cake_dst_18.0mbit/index.html (1.83) > http://www.drhleny.cz/bufferbloat/cake/round4/hostiso_cake_400ms_eg_cake_= src_cake_dst_18.0mbit/index.html (1.64) > http://www.drhleny.cz/bufferbloat/cake/round4/hostiso_cake_600ms_eg_cake_= src_cake_dst_18.0mbit/index.html (1.57) > http://www.drhleny.cz/bufferbloat/cake/round4/hostiso_cake_800ms_eg_cake_= src_cake_dst_18.0mbit/index.html (1.45) > http://www.drhleny.cz/bufferbloat/cake/round4/hostiso_cake_1000ms_eg_cake= _src_cake_dst_18.0mbit/index.html (1.06) > > * Sorry for the delay and not testing much in the last few days. R.I.P. o= ur 16yo > European housecat who left us yesterday. I really liked that cat. I=E2=80= =99ve enjoyed > looking at some of George=E2=80=99s results meanwhile... :( I used to have a cat, 'cindi clawford'. Been travelling too much to ever settle down again, it seems. > > *** Round 5 Plans > > * If I do another high RTT test, make rtt 1000ms default and try even hig= her > > * From Dave: tcp bbr, cdg, reno? dctcp would be weirdly interesting. > > * From Dave: slot 4ms 4ms bytes 10k 16 > > * If I get time I could change flenter to do asymmetric bandwidth tests a= nd go > back to Dave=E2=80=99s four box config with ingress cake, which would pro= bably be a more > common config. All depends on time available=E2=80=A6 Well, let's see what happens on netdev. I took a few steps towards ripping out blue for comparison the other day. > > > _______________________________________________ > Cake mailing list > Cake@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/cake