From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mout.gmx.net (mout.gmx.net [212.227.17.22]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 670B53B29E; Tue, 18 Oct 2022 14:07:55 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=gmx.net; s=badeba3b8450; t=1666116461; bh=taqeBvt73pRYOXtTqZBFxS8s/fZssAY3W4XBy4+71+c=; h=X-UI-Sender-Class:Date:From:To:CC:Subject:In-Reply-To:References; b=KwgIIBaPZr06QhuWKO7gnkgCdOb6CGMiFwXVKR7SMKsBWCrr6UMgPRr4L7kmIEyzv PPq7+rWIHaMTloxHzbHtC602IYswqHozE3XlSQGWXzMDmf2vqBFxUKgDvNDLh5439p uMVGMB1L9REZvHUdcfH5ISi5q14diYClpWEwymvM= X-UI-Sender-Class: 01bb95c1-4bf8-414a-932a-4f6e2808ef9c Received: from [127.0.0.1] ([79.234.22.28]) by mail.gmx.net (mrgmx104 [212.227.17.168]) with ESMTPSA (Nemesis) id 1M89L1-1oozap1MaB-005I3i; Tue, 18 Oct 2022 20:07:41 +0200 Date: Tue, 18 Oct 2022 20:07:19 +0200 From: Sebastian Moeller To: Stuart Cheshire , Stuart Cheshire via Bloat , =?ISO-8859-1?Q?Dave_T=E4ht?= CC: Rpm , Make-Wifi-fast , Cake List , bloat User-Agent: K-9 Mail for Android In-Reply-To: <938D9D45-DADA-4291-BD8A-84E4257CEE49@apple.com> References: <938D9D45-DADA-4291-BD8A-84E4257CEE49@apple.com> Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-Provags-ID: V03:K1:SoiUufa/1xz5KVi1yovAgJtv/qIeGQd02QwpnqsibOvaUnLQQXt 8AbXor/8jfN+jZ+9CRGOMzzcCQ+EgbUdjPj8L1K3NEZDi/3cB3de3Nox6jxy0d/jQEneF3I y15L3gx0efRmF15zuiNzvUyQF5ojwdk8AV1Bs2pxDYqiYreQkF7bKuqXxGuiAsx0AzPyyJw T3LkI1CWwdJTgstUHJ5wA== X-Spam-Flag: NO X-UI-Out-Filterresults: notjunk:1;V03:K0:1T3AmEx6hW8=:P9spaqK2cmj4EbxUbdeccM JIy52ohLmWCCJZCAn7OqLTPOEWQDa8CdQAi3ytAd/MVykYaWqS2kZT8lEhlNhklIm1onojCw0 lAWJJTdI2XmDR2Mka+Qcn5GTdbxU5A64fcfREc52Ii5VXmovYFsQrvkFQ1iibWZSoQRuF0NPW 43p5wEYTXX8lu/ARvypgPc7f7I5lLfRb8p3J/UHgkItmH6hnZMwAP+QjnxsLqiX7quzLenI5x lm07EUWgYZ+IGTCwiJZlp+nWRMY77FpQ1l0k44JmxX26SAKqrsNYOIJ1U+Tfh3vrtJv3LJh9H D1XZp9wzTWs4XbY7i7JJbh1c9jlzZEh4KAjSCiKyirjvSy9rVydpLo4VLY6Ircnj5pRg/G1Ms D030Wz+IVSFVN9zBfDVZ3DemxVGKPfievX+18W+H/+4Pv7Ux5Eqzcxj5BOzRpDfw0QDI7Hy94 zDV7okKJFH4W0xo4me9b/qk5yHp8ERtHCBu45JNVZqZIIvkqZNDTqcxVjri3jHTzfPx8RzoQ4 HpT/Xt/jog48G7KsOmSdXU3rYwayX8auERT3ivPWS1EexQZiRGVB24fN1oJkvKRLbEGAerLjq Lp87mbVLRqfJhlMjXzq8bJrCugb36dzkASF34gA/jvJcC/Uj41aDBVYSXZjmFJh9e/Xh2HR4O rELw5AjA4anWbE+XkBPq716jnP5DzRDiqPt7zPvW52L7kCYejvWEqNHLGb1dNkm/2+KLVGq63 OUuTLqiCa67V1RSfQAKVnQuj+uHHyAn/JnmNiL2pEATclxLQs6L4v5AoUsl3I4XyEivdb6HcK qxRMBOOnuqSSr1CXbjconDnmqcZaWeyuV1xnkgd5TitgOTPZkhpkoAWgeF3er0nEtTtZqtoie 2pWvW/p49Mdbz8BX8ebXcJbYOtT/CliOf1cJJREDJhWufUq16GqTo+emzumzILzDZiM2/VkNW Snb8R+2BSsxeA09vG7JWXJEnTLtzJEJMMFhMpxpPFR6aD4TT5ewe9l3lEbHbL6iJhnnZR53wb SuG8O4+H/vH2YLv/N+uCUU6JK9GEWRGJAkAzlQq7XseXxLEQCzYOo7ktAiG1cgtIe9GWFGZVO 7lj6OYIv22xNwH/JV75JIuNVF0rfVE+vmMQjToqd0bk5bYEQKjZdgGP+ctcVDk8q6JbOo+TC8 YIeH/aPbh+lzU2lIKwQFK/kCnOYtXnqHOcGo14CpdYHV//87BCerUwajx/kFCQnS4NbRxJ9ZS L/Rrz5tpmPJxR8gc+PhqAK0aVne681ssb6jdbNnu2N4YYzqy6GofBLb13eo7PktfEwJZ0JctX NPf8kNlWY7oK3/fsWgHvwcWVhE1TzHFnSCkDPckrzeHyfy/bQIhmmZRcfeHtIvzc8EFrsnSv+ 7CichxD6X1qfc7+xENHT9ZirsZB+ZE/QnOXcBqw29Pv+AYcLBeggg3g52nr/ie9/4VJkjFiYM OgnSHmMxVFvp2QqL1SjYmyJetymqSdzk2arIFd/dOitqXiwYBLAwCIMbVBgGTIf046GmO+KMr EYb7X2njJQzWAZqEIAHmR6My1mI7cRL8KDEescFvXCGLV Subject: Re: [Make-wifi-fast] [Bloat] The most wonderful video ever about bufferbloat X-BeenThere: make-wifi-fast@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 18 Oct 2022 18:07:55 -0000 Hi Stuart, On 18 October 2022 02:02:01 CEST, Stuart Cheshire via Bloat wrote: >On 9 Oct 2022, at 06:14, Dave Taht via Make-wifi-fast wrote: > >> This was so massively well done, I cried=2E Does anyone know how to get= in touch with the ifxit folk? >>=20 >> https://www=2Eyoutube=2Ecom/watch?v=3DUICh3ScfNWI > >I=E2=80=99m surprised that you liked this video=2E It seems to me that it= repeats all the standard misinformation=2E The analogy they use is the sta= ndard terrible example of waiting in a long line at a grocery store, and th= e =E2=80=9Csolution=E2=80=9D is letting certain traffic =E2=80=9Cjump the l= ine, angering everyone behind them=E2=80=9D=2E > >Some quotes from the video: > >> it would be so much more efficient for them to let you skip the line an= d just check out, especially since you=E2=80=99re in a hurry, but they=E2= =80=99re rudely refusing > >> to go back to our grocery store analogy this would be like if a worker = saw you standing at the back =2E=2E=2E and either let you skip to the front= of the line or opens up an express lane just for you > >The video describes the problem of bufferbloat, and then describes the sa= me failed solution that hasn=E2=80=99t worked for the last three decades=2E= Describing the obvious simple-minded (wrong) solution that any normal pers= on would think of based on their personal human experience waiting in groce= ry stores and airports, is not describing the solution to bufferbloat=2E Th= e solution to bufferbloat is not that if you are privileged then you get to= =E2=80=9Cskip to the front of the line=E2=80=9D=2E The solution to bufferb= loat is that there is no line! [SM] Short of an oracle at all endpoints that seems as worthy a goal as im= possible to achieve=2E IMHO the engineering should focus more on the 'faste= st possible without any congestion' to acceptable performance (throughput a= nd latency) in full and near saturation conditions=2E That is assume that, = in spite of best efforts to avoid a line building, you need robust and reli= able means to deal with lines that will sooner or later appear=2E=20 > >With grocery stores and airports people=E2=80=99s arrivals are independen= t and not controlled=2E There is no way for a grocery store or airport to g= enerate backpressure to tell people to wait at home when a queue begins to = form=2E The key to solving bufferbloat is generating timely backpressure to= prevent the queue forming in the first place,=20 [SM] Seems somewhat hard for my router on the bottleneck to transmit backp= ressure to the sending applications in less than 1/2 RTT at best, during th= at time sending rate and acceptable capacity share will not be matched=2E= =2E=2E=2E L4S type signalling will only really help if the bottleneck's rat= e fluctuation is on a slower timeframe than the signaling delay=2E In short= aiming for no/low queue is fine, but better carry a big stick as well for = when the queue builds up=2E not accepting a huge queue and then deciding who deserves special treatmen= t to get better service than all the other peons who still have to wait in = a long queue, just like before=2E [SM] This is where a flow scheduler in practise helps a ton=2E=2E=2E as it a) avoids starving individual flows as well as possible with minimal infor= mation b) it tends to restrict the fall-out of under-responsive flows to those fl= ows themselves (or to their hash bins)=2E In a sense this is the opposite of special treatment as all flows are trea= ted with the same goal in mind=2E=2E=2E=2E I am not really jousting for the video here, but I want to highlight that = any short summary of a complex problem will have to gloss over some complex= ity (I expect you fully understood the points I make above, but omitted dis= cussing them for brevity)=2E Regards Sebastian > >Stuart Cheshire > >_______________________________________________ >Bloat mailing list >Bloat@lists=2Ebufferbloat=2Enet >https://lists=2Ebufferbloat=2Enet/listinfo/bloat --=20 Sent from my Android device with K-9 Mail=2E Please excuse my brevity=2E