From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mout.gmx.net (mout.gmx.net [212.227.17.20]) (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 DF2483BA8E for ; Tue, 5 Jun 2018 14:34:38 -0400 (EDT) Received: from hms-beagle2.lan ([79.192.244.98]) by mail.gmx.com (mrgmx103 [212.227.17.168]) with ESMTPSA (Nemesis) id 0MKHik-1fOc611H7O-001hEt; Tue, 05 Jun 2018 20:34:35 +0200 Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 11.4 \(3445.8.2\)) From: Sebastian Moeller In-Reply-To: <61E48C91-AEF9-4FF4-9F83-45EC7148EC54@jonathanfoulkes.com> Date: Tue, 5 Jun 2018 20:34:33 +0200 Cc: Jonathan Morton , bloat Content-Transfer-Encoding: quoted-printable Message-Id: <9675C88A-FCC0-43EB-9C71-CBEFD67408CB@gmx.de> References: <152717340941.28154.812883711295847116.malone@soybean.canonical.com> <4f67f9b3-05a1-8d15-0aee-dfe8ea730d7c@gmail.com> <73c25a21-0ace-b5ee-090e-d06fb3b8dc60@kit.edu> <3F65061F-4F05-4F3F-8A43-FFCC1D27F585@gmail.com> <61E48C91-AEF9-4FF4-9F83-45EC7148EC54@jonathanfoulkes.com> To: Jonathan Foulkes X-Mailer: Apple Mail (2.3445.8.2) X-Provags-ID: V03:K1:FSCVbLje6DgEV78nkvVxfQKDZXIgeG8vIDsJUQIUsyV+wKqgjVq dgREGj/bzTp/EjT825QzOHINFGGc0/jPTWXBzF96AwhCKjx/DHoSbmceVbAg/sIpCwZNoy4 B1EsppYE3Nhb/cI8IxOFNciH9GSYCZgo4yjILzb4YG95+U7yddbvUrMA5gMNESF38p/PrUl S89CHSOpY/67K0D+Qnolw== X-UI-Out-Filterresults: notjunk:1;V01:K0:Utc7Vre0WY4=:ZDzHI2Sw6HrlPM6G7Dzt9N l/1o8WUwGRumAXvGj5vPqSXnhiY/Yz/0CpasuIsHYVpF+Z2qxV9dV2L6SfZ9D4oVkR2VQwKYF S0nNJdGuz+O3Oz+zKvw074nGCKJbHRqbPnOGSRz/Dxqpw4b8K5vpWWECTSoxgnVuPCKC09dbt adZEcPrqP79kXxY/Cu/RwXWWsD9D1S5rivmIP6C8shLwmxx8w9I+G2YTxhfgy+S73PGIUtkZn tEMymC0CaG/7+NZ3ftwuEkW+BK/f4NxDe3poTBHysxiOZ1wcz3aFChugmtf8vXOFOdmAJsej2 SOy0MRYJRLAkW3z32JlLqK+tSbzLo/qZEmEGYlk91cDLfAsi0gRLkiBrE0jwLMUhlvlZLC0gm czM9l4CPdExYNpjPIvi5tmSi/S0+SDm2DrD8cCSX0g1b+Fworp77Ezz4bBCrcL2hnurX61unY Y+CXeJtQfKJMLrEiMLphwCPntVsuuq7WylySXHQZnL/XWXhBTX+6DMxtI105afAl8BbQvPe4+ /WetZFIm8bCxswYoutajVxOGod9V4HB9rklaUb7y7z0PyJTrDlVp+SXrThwq/YN4A3EDpKgbm eUD9maXhDfcJEb1KP7aZuRKPvQizVcqM4rUm4hiRe5zgkXdP94BwpnlBss2+dd1/NoL1w3JRN qxzyMURWSTUgds+anY348xdNxHuf4zESlE3VS3Uq4vv8LyHHt5j9aoF3CgT7mZHf4+kx4xYy/ bRzYxEMntIxsl6NruVTl2GViGWN0yyStlnW9KzyzDsFAzDePK2xOTgaVvGLEamuJyBzDBkDZv HzKJz/t Subject: Re: [Bloat] [Bug 1436945] Re: devel: consider fq_codel as the default qdisc for networking 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, 05 Jun 2018 18:34:39 -0000 Hi Jonathan, > On Jun 5, 2018, at 17:10, Jonathan Foulkes = wrote: >=20 > Jonathan, in the past the recommendation was for NOECN on egress if = capacity <4Mbps. Is that still the case in light of this? >=20 > Thanks, >=20 > Jonathan Foulkes >=20 >> On Jun 4, 2018, at 5:36 PM, Jonathan Morton = wrote: >>=20 >>> On 4 Jun, 2018, at 9:22 pm, Jonas M=C3=A5rtensson = wrote: >>>=20 >>> Speaking about systemd defaults, they just enabled ecn for outgoing = connections: >>=20 >> That is also good news. With Apple *and* Ubuntu using it by default, = we should finally get critical mass of ECN traffic and any remaining = blackholes fixed, making it easy for everyone else to justify turning it = on as well. The rationale for that decision still is valid, at low bandwidth = every opportunity to send a packet matters and every packet being = transferred will increase the queued packets delay by its serialization = delay. The question IMHO is more is 4 Mbps a reasonable threshold to = disable ECN or not. Here are the serialization delays for a few selected bandwidths: 1000*(1538*8)/(500*1000) =3D 24.61 ms 1000*(1538*8)/(1000*1000) =3D 12.30 ms 1000*(1538*8)/(2000*1000) =3D 6.15 ms 1000*(1538*8)/(4000*1000) =3D 3.08 ms 1000*(1538*8)/(8000*1000) =3D 1.54 ms 1000*(1538*8)/(10000*1000) =3D 1.23 ms 1000*(1538*8)/(12000*1000) =3D 1.03 ms Personally, I guess I sort of agree with the <=3D 4Mbps threshold, maybe = 2Mbps, but at <=3D1Mbps the serialization delay gets painful. =20 In sqm-scripts we currently unconditionally default to egress(ECN) off, = which might be to pessimistic about the usual egress bandwidths. Best Regards >>=20 >> - Jonathan Morton >>=20 >> _______________________________________________ >> Bloat mailing list >> Bloat@lists.bufferbloat.net >> https://lists.bufferbloat.net/listinfo/bloat >=20 > _______________________________________________ > Bloat mailing list > Bloat@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/bloat