From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: mail.toke.dk; spf=pass smtp.mailfrom=; dkim=pass header.d=gmx.de header.i=moeller0@gmx.de; arc=none (Message is not ARC signed); dmarc=pass (Used From Domain Record) header.from=gmx.de policy.dmarc=quarantine Received: from mout.gmx.net (mout.gmx.net [212.227.15.15]) by mail.toke.dk (Postfix) with ESMTPS id CABCB115A088; Mon, 25 May 2026 08:58:53 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmx.de; s=s31663417; t=1779692297; x=1780297097; i=moeller0@gmx.de; bh=cmMnzprEN44Zooy1ahKvjDxwfoqsMbJI3w9utXu8/gI=; h=X-UI-Sender-Class:Date:From:To:CC:Subject:In-Reply-To:References: Message-ID:MIME-Version:Content-Type:Content-Transfer-Encoding:cc: content-transfer-encoding:content-type:date:from:message-id: mime-version:reply-to:subject:to; b=VQBbmcIfRBvMa1ukjvLhfnwi1vBWBEeNYaFUgmkz4v9WthqjUhHgudqdtw9OjJzi fhfZ/b2NXqsowglYFfX1lopsvkoH6Xj7rgbM8GiGIKA3hv++WONf4vZQMNMm/cNUx mfvE1eLcQShMBF8yRLrSZWLO7Ja50MliRQQRlRHcVjHBYXNUOznKDDigZ43Y5cexC yxtwP+U2Mbc6NlVXiiqOQx3AuuKTM1EO2yazbwvopwmUGYKbo5SWxgKeg6vAjIulE RgN7cdU1YOetJsjN43wOwh64pHtQr/0yCyK04zswcOJu7fhtNkldKwubfg+etwz5/ SVx3NC/X0peZfM3FUA== X-UI-Sender-Class: 724b4f7f-cbec-4199-ad4e-598c01a50d3a Received: from client.hidden.invalid by mail.gmx.net (mrgmx004 [212.227.17.190]) with ESMTPSA (Nemesis) id 1MMXUD-1wjDGY1xtH-00MwcA; Mon, 25 May 2026 08:58:17 +0200 Date: Mon, 25 May 2026 08:58:12 +0200 From: Sebastian Moeller To: codel@lists.bufferbloat.net, Frantisek Borsik , bob.mcmahon@umbernetworks.com CC: dan , Robert McMahon , David Lang , "Livingood, Jason" , Cake List , Make-Wifi-fast , bloat , Jeremy Austin via Rpm , "Dave.seddon Ca" , William Fisher , Igor Aleinikov , Jim , Jiml , Douglas Fairbairn , Thomas , Tim Odriscoll , Morten , Sebastian Moeller , Mt Denicolo , Mmcmahon01 , Santanu Sinha , Matthew , Koen DS , Shotaro Saito , Robin Jarry , Ehf , G White , Chunyuhu07 , Matthew Fischer User-Agent: K-9 Mail for Android In-Reply-To: References: <0oq1n88q-36qn-p6s7-699s-p4nr0440p950@ynat.uz> <8e14c6935753c6263351ad00ec59b9cb@umbernetworks.com> <055e42685cddfa4c1a4ff4da089996eb@umbernetworks.com> Message-ID: <7455E3B4-7FB4-4D40-A900-B31151D12F6F@gmx.de> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable X-Provags-ID: V03:K1:n51q3f7x/G70xSZwmuHykp54NBhdMyocEn4duj2HJeBSyMNyVtr uWWXmBFEVk2tNkvwKjhahyH8GYEAMuEnLGO4NLSpuy4M7UW/eYpnsjzyesNRcP9xyuA651J 3CtkQ0BD5TVVulMSEwaxr8Mze99c7WM1moKit5cAX7RmmM+fc8SX5XS+nP6kH7HhUKnJ2DF /p2m/VFtaVT3eBnJw73gA== X-Spam-Flag: NO UI-OutboundReport: notjunk:1;M01:P0:nYmpl7O0cq4=;/cf9CPow5K23mU8UNwpSGU6dDS7 jli4/B2oRvsSp5ND8smIm6MDSm0zyYQwg9dMD2NPs0EM3rb77Su22prh73VSyRwV4mCLLTH2o 7jDlP3ebnLuMPgGXXnEnxDAt9eiMIquTH07iWkmaGaYC/3zlS+gr6g9PVpGqG6VLRJgqnNY5f pi11OdrH21zBK27DteJw87oUa7tFvQLzThE9uqcrOOxJLSXkJ0vJlamecWU4F06If2rcdqg61 H/86+UUTAQgofGj/Hc0C98z7ymNbqlFPW2TGqJU2ykxMTFIHOYLCKpcMWlnDNYZHcaxtbfhXe 9bHMWtNObQf3Z/7HnGqtnxPC9aOijJW7pBorIbI4p/ZeTg2J523+T1UroNltTOr/60qjdrqb3 WFU35mP+x5UPy6JZRrzIn4zAWULXWLMum02H8/l+71h67l51XA13LF7Pj0CsXknQJOwaYTmk7 OwSbJTJQhUEIHsmI3vZfYa+Je/8u8KAzbzH4g1gygNV2pvMaf57mAgk4aS94N2eJ9sXIzpjHE goAVvjvbPZZV+iOua4i9fR2ewubJVs4Itllb2w97w/16mOh7q3ZhjW3kmIksNqrwn86BoKcnE cii8bqEUPzUYu3uBS6fTUA70DHsZCg6i5jeSwqvfyfOyIP4qC8bVbFCPpjMISgVEXoIX+3JlH JUoQBt/ETOlG+PLggJ5YMe40yTitEP7OUGojhtdQnOtODPzTTgAWPKN04V4vryhDWt4gdk4rX eSbEKlfiolDBi2LWyI+84wFZ8meRzurh7QiwSKq+mvGwMnpIe6kwL750KvQSej07lNjT8E5+Z 31FSTuDB/j/RTy9QAxZDA3qYX+w95LNoNTsGyuAgVOpduLHpo0QssAwrGtsIcJX0Is0SilgJg fVrwaNSvSOgiwKFI+2m9RcQyXOsgLpR6jmccyBcjML8CwuC1mLFbwVgeA2FVWcOCirFo4El4I s4HkoaF6VUQZJ1QOuPEQ51xYKAHVSajReS0peBvG/YCKxWp9Ne72ssETe3ig1cVMzysTQS28R NNL3KfPtrOMC9g2c/ci3v4xjDYY1OdkCrBJYOpbfv2Dg3WKlHQUKKTZVsUxJ2HVI51iSyGKzL /Ti64L0ALeJ24QUb1VNq+MZId7aYLvfHQVDpLBpCZuzYyQ9HOg8ImQ2gjrYkB37PSZvg8drAP xToHSn7sjsvL5oQEVKatJhqoxvmJxtCnOjHlU9Io+C+YBI0aodWc4R/Nf05H7Dc7lQ7h+nbfQ /PnD+uFi8h3nJUiUHpfkmD83qInjtf1bFlUYxVK4B4+gQmSUUS1RwLFLUb+Ws7fjQOFb/EN/Q HaFhYKSDftgLc1L1vMu5zDp9OvffcdYcvk4dNrxH0iZQYZ1IWr14f9e7JBtB5IhvEiVy01XPH sIhtJZMlkaGNBmsnu/qpRZUYXKzIGJfXweZ3qt5FFn8IFn+1VcdymDWk2COvF9vTVfWCd9iev ea+IWuKvhnY4eRmQ996wBtUeIAP92v59OjYWmUP2jQf7Jjrs4oo+HuZzHKt6cmv9T7E0co13H lfpSLhWD1kUginYdGAXpRyxfm6xM24QU2/v45emrui94N9neQbNOfHX8z4xdlifugLRNhe7Rf PC/ibEbkwKRKYXG2Anlv7mNoogU+ONGbcvGiP6gaqtEtsvXO/9ncJK+bxxu5WDOplQSFCk+X7 iUTjitfy558R36PFT61S7hlAgLKJ9ks+yZpAoYxK3f0C4dZp9LtV3qHA/mly9g27EehXsY7XG DtEI3UBLtC6BF3YykYZkum3kP4IToGTemvThQjxXHKXi7ImOgXMnwFNGXD2pSDp1BFl8ZiwLG F3uQJ9rlo4P8IWZFzZhlsQEW6jpdE8t1ssjidd63mCoD8OdErWWlNQlfRLXA9+Q5wK4aueCtj 5VGn8jBG+qrDvi9xd0Yv4oHLdDF89ybm7eXgK9f8hGJJDN/5wO15mLNmbCnF4UgWa7vYNKXLT ME94fVDWNMtxAvlgRD0iOfFxHLY6PxIY+a18F0DRcN3GyunEdCXa3MHXz826pfHvB8DvYFXxt bW7jeXMGZeSn37M9JkxdJlCeBHS0JvNsOD3flkxdYt7QckgAe1Wsvw0O2ljiqahfTAWuPKe+c w9H1WLmRfzZx2Wh/dUEkZXxFWuW4aq3TjXnckiA2DRrUivMxKbdcNuJtuXd+ALGhz9tW49ZGD G+bfKpG0i6o/q0HYwn8tc9M3KAktWuWpA35cKwu07JSlSdT09Bs1oWQo7kEY7Q/ddy7JVnRSb 9bxV7OXh7hzg8kHsUsGhJliI9eclOKvbw/tk5HbwgKT045SDJ/7GrK8ghKWFwbaT6SdLwTLKp 1LnqDWq2DXJFObjMUaT1Y4laUAe/oa67nADTdTaoXKOb+QGapMVxrr4SgEfhGvSBRHaxOp/k3 RgJhIaD95o1lyeZDCS9Dk9lRE/X7WYuKY5O24+aM1D5U+7W3fIpa8si6Kia546PT2yLePojEr NhvYue+kx/dOaJiCRbSNvzaxGSMlFzbST54mR65QrvvjAXdGz73CXp2G1fgIwfBZQSqTCcdRK CAQZBQ15TNUq1z4DT+ueGtbAM9NNyHZ6ospwEMe+j5cNc+VIHw4wZUqc2SpzFmDElBxSTe+lR beMstoUxMTYo/LW6raPn9NSD1BpB8tverVj76XpdJN5hkKo36OdCo1wHDx48G2uvgt7/+LJMn CRnCdrCpvKGDYNmr4LXa099dIJz3HKtosgQS3MJfI9damr9bZBwgBiBXfl84gv06KqZYVDF36 vkXDJkXiFiMjxRNqzVfssFfa4DY7qgDG5DB28jHMWGdkFy2CgorGUfShyH7qh8nHz2qTR2uzd 5P/lQ0r2OO1AG85jZiXs5mFotcOElpTrtDkcSFMHJnBw2vjClV5xLtlCvYRIhBJsrcpJcaOr4 KjRx1uscRWjItEA43pKdVHaODH9W2GWRIHXVFVidgRpkgfZulCAcy6qu4kG3jAfhlHmsxs3K2 BOjuv50B7DFLSDotttI65OFLBC0BbbQem6D1YavRJV7cmNMoNsDvYFD2HXecX5FeLXVflUV2M QZPWQ8GdR7up1LImIfxxZSBkJTMoABLvcUtDyf/zTQ1RtJzgKRX8/WEBZRNWLfxW1YJrnfYqm 7aTiFHjVYoFfVbrYHjYet4GY821tY5OM0z4e3bC2GqH8Pb6BfLBzcFWIXsp7BWWkQBWwHLAGM C6BBRtEabuwyz6PQbB+ybJwDFaeL/GKfV7oig4kHMluTTcP6gu1JOoX7e/qqN5V0trAFhak1o 8jOaGVXL6E+pQTpzziIm0YCJ5VarQ/LhPHGbpFwQ33wCw9Oo/CeL2gNhHAKAh0DTpiBETxv0R 2hCfGg8AvG2czRWTSKoIn5fyiiVLyuBd+yeX7XG4XxmlQpp/uMRqxGz+ibTVB3lIbmaCZ0QpR wmaUM6YU9uu9+VR3mPSM52u78oDWyK9yH+UX2877q6wQ27SZOQJpSgr7xW8qnH3fSj5+VmSUM gPvKsA3Z45zo2s775B+oM8N8H4oeJqjirr9ClHqBZaZbKd7MFJstHnZnuEOO1d8aSsG7LnX5W 2Dghwm6OOc/CVfprOkyCA0gXOgQOyO+jY92qtoHYdZQDXiuD0X87xXYCB2aZIurdsXEthPGso uFFlsfLc/1HKDVxUednHWnkAYxbHWg1YSRDgBfD3lv19Wr81OrcZ61QSPEZnp4lA3P5qOVQUn O5Z7oq08h+y1dxvolG2NlVKrNTtkAIwqNqc9vkEoZO49kycZGHWbozZDVMVhvdizcAWTTThXf eeGobgmoHt2w6YekX84ZCn09w4LC64L0MfA2va1EPP4WXVKTLsGFghweDt0/8hYTGYfZmI/mL 6vGFBWEgi68vbJbR8TN7b0xnLEOiPQfiJC5xEdCdgiALLd9C5lfvGXDGOFJ+x6An2QlwmCXTC 8+JS6GZd9GmggaWDhUuZHC2y1JOsbK3Ta34/sLrmNhBYq/qhn2MzK+5q4BOxu96onDVSQ3Uug bto7ncU9XBhvfXBCYSLQxgSZHYMfgcwikd6Vxz4N7Beg0WkD8yO12qpHnu8CkZtvtHoIN6Iqz YudrXU9ccBlvlJKSZ8o8qS/vq8L+sz/WA0nmUuLbQCR8JBjfYehPCtvZY/RSKL4zTod1eIW9z L28eXZLOxnsGEkoDukPCY1v5E0JlHneWK6njCZpqav/qRGDt0iKEjP7kqAYa0hr18QQnYFn2U XW1HIrer+Iq7YOAWBFF8LvmHWPeUcpT5IYeUHz/V82C6Vn0YFDwptBPAb1UCYT042PApbncee t5oJ0E8lkDsLRNWwVmt+ZZ2ZqY5l/WxcP+QJfvQ4bi2Mw8tmW16LZjiHvI9byGQ1c3n0M6dlw azvYa8DA5tKHfOvrDzU+TrzCLImOexaJB2tN3IBNmy9Ob+4O6WIOldWpDMy+ExWXmN2eBrFg8 gV6BMpwOeX3vcPYY3mSkFNxBTdhEiWgux4RWWPoFdCMG4ZEn3O3Z12hT5M2DlaI2JbEq6Vd7O f4GMMK91J2iM/I+tbEtB5BUTluJIgFbDO37EUj4C3T2vY3bS6OjwZapQ/StLKs2IrSHqt1BfR SFeD1zvY1Awufg69kq/1+iFT/wBsvGkKkPJLUFNQO7xg5yr4FB5sDkvICd8Lw2ByBx3muu3s0 9hl2c9HrDsCtgZLxi/GfGRWQP1Cpw8fV4s9LIWCHBsTUz7RyZoGFCCTcwNNxKNTHdIOW0NXkc 7zm7XQKrpp5yQJE8r84wUbFrR9j4gfb0iaZFqS0NAy8zxHS6JCqxUkkuOTMqXFqSalg6n5sTX gZfFDP2V5Q22FwVqSz+rZmy+I2xGV7qtcHVeMhKmE4oFIPLMbQuRsWjmFJdzs71ndLjkMLhvz FPzmvhISci2oIywNXquKpC4TQhO8wnxuDrAShb+n1nT/nuY4WI/z7Ew3yXvpk1l4eP9C0rKRm QQHMBZVCB4XbsGpBjJ8WiMXER+t6vbwwlQMwEXHF0n5pSPansYGShbTVx1IEZF1CyL+2Zhttg himBA9+cCpZPC3ojyRPbknnbffdZXAgFvI3NSL5hMLcGRYinPP3gCCJbKR7wIe8AyBrrSPbY0 5Tx7pwi+2f+xXAW/Jz/1D47La52F+35m9UETSu+OTR/NU+6zFptVwNr5CeEgLIcXAANqV4fZX ZmipYDIyPYACyHS778jSe/Ru0NrC/Hh7panYWDj7fs+eZPYgZ90Q6nqrrlTTRQCz5jhqJg8g0 6LBl9D2j0mkvWXOp8wG/6yIZ905pm3p5d9DTgUrhJ2QjSCXd6gg/Wz8oqx7kbNR5LKLPLzAXO 4Gvb5E3lKhF8PiveZ9Pq/ArDcH+9jq34L0FQiUHseMe1/9gAvvkhLm3mUoMrCCGDStWZCGBFB FDps4Em4hRi+wUV/NeofyPiMWfCKZMKL3Vz3DdkZ11fGp8oxRAC2/zjjc5nXatHervIRpT3Pm p1pmUOMOwqEKnZbHEmbiqv1hke1WQ+cUv1RzhHptE/t9h9R5tioQu6AWd8BAGQ+sLfYBYYcR9 J552Jlyr45q4LSmhMvUw1mUgjlb99kfmLjxnCkDXynqydeCl6XBsHtdKITG/f0tasOJo3Qfsa LXuDZc0oKbBaTP+cEDplgiAxD/U2e0rnPWkJ4jmxDYdXuK5La9kN22IFz8guiheFbNjwhI0RQ JNeTygtgzEgvjnW5hErln/bsnWg2a+06SDD75vKMHctgodHqb/0NzMNrsNn0X9vlAf/9k8+LO avLoEmTNgE0yVwEb56u8wY8dUJC4A6H/vgIysAm1WElkTZ/HvV/6P3zuV+ui5p3so+nfcsool CdMOXscnpJPsL9ekzaqCx Message-ID-Hash: X374XKO3EMOLPQBAL5HX5PTSMT5SNC3K X-Message-ID-Hash: X374XKO3EMOLPQBAL5HX5PTSMT5SNC3K X-MailFrom: moeller0@gmx.de X-Mailman-Rule-Misses: dmarc-mitigation; no-senders; approved; loop; banned-address; emergency; member-moderation; nonmember-moderation; administrivia; implicit-dest; max-recipients; max-size; news-moderation; no-subject; digests; suspicious-header X-Mailman-Version: 3.3.10 Precedence: list Subject: [Cake] Re: [Codel] Re: [Rpm] Re: [Bloat] Re: "Fi-Wi is a new forwarding plane for wireless" - Bob McMahon List-Id: Cake - FQ_codel the next generation Archived-At: List-Archive: List-Help: List-Owner: List-Post: List-Subscribe: List-Unsubscribe: On May 25, 2026 7:43:01 AM GMT+02:00, Frantisek Borsik wrote: >Hey Bob, > >This is all nice and all, but it really doesn't matter=2E The only measur= able >term IMO we really need is this - is the setup we are using good enough a= nd >delivering all we need? And the answer for ISP like Dan and many that wil= l >come "to Jesus" is sounding YES=2E It's here, it's cheap, it's getting be= tter=2E Not sure I fully buy this, if I understand correctly, Dan uses traffic sha= ping to "neuter" WiFi from its worst self congestion tendencies=2E=2E=2E th= at is a clever way to work around clear short comings in modern WiFi not ev= idence that modern WiFi has no issues=2E=2E=2E > >You will get your evidence and then what? When (and big iF) Fi-Wi will >materialize, we will have Wi-Fi 8 > >for those interested in chasing marginal improvements and the latest thin= g=2E That is the 3GPP playbook, always overpromise for the coming generation N+= 1 and once that materilalizes and typically under-delivers roll-over the un= fulfilled promises simply into N+2, maybe add a few more claims=2E=2E=2E Su= re fitting for the latexstage capitalusm we find ourselves in, but let's no= t get fooled by marketing promises and judge WiFi8 once it exists by its me= rits/performance, please=2E >Jonathan Morton will deliver his improvement on CAKE, we might even get >into microsecond territory=2E Last time I researched his deltic approach it looked very much not going i= nto the microsecond territory, I remember 25ms as latency target somehow=2E= =2E=2E 25ms is certainly not bad, and not high-latency, but seems different= from ultra-low-latency approaches=2E So I might have missed some interesti= ng development, if you have a link you could share to get me up to speed ag= ain, I would be grateful=2E > There will be FQ-PIE, PURPLE CAKE, HTB-MQ (to >supplement CAKE-MQ)=2E=2E=2E > >Anyway, you will like this: >https://arstechnica=2Ecom/gadgets/2017/02/going-hands-on-and-behind-the-s= cenes-at-the-plume-wi-fi-hq/ > >Plume used to do this, you will have your Fi-Wi house test bed up and >running, soon=2E Let's have fun and do another round of the good ole >Wi-Fi/mesh router rumble: > >https://arstechnica=2Ecom/gadgets/2016/09/the-router-rumble-ars-diy-build= -faces-better-tests-tougher-competition/ >https://arstechnica=2Ecom/gadgets/2016/12/review-comparing-google-wifi-to= -other-mesh-networking-heavyweights/ > >Maybe Jim and Ars Technica would be interested in it=2E > > >All the best, > >Frank > >Frantisek (Frank) Borsik > > >*In loving memory of Dave T=C3=A4ht: *1965-2025 > >https://libreqos=2Eio/2025/04/01/in-loving-memory-of-dave/ > > >https://www=2Elinkedin=2Ecom/in/frantisekborsik > >Signal, Telegram, WhatsApp: +421919416714 > >iMessage, mobile: +420775230885 > >Skype: casioa5302ca > >frantisek=2Eborsik@gmail=2Ecom > > >On Sun, May 24, 2026 at 11:57=E2=80=AFPM wrote: > >> Hi Frank, >> >> The question needs to be framed in measurable terms=2E >> >> The systems you named operate at different layers than the 802=2E11 MAC= /PHY >> layer where TXOP allocation, retries, EDCA contention, AMPDU behavior, = and >> airtime utilization occur throughout the building=2E batman-adv routes >> between mesh nodes=2E CAKE and FQ-CoDel operate on IP-layer queues=2E Q= oE >> middle-boxes operate from the WAN/IP side=2E >> >> So the question is whether IP-layer AQMs or WAN-side QoE systems affect >> measurable 802=2E11 MAC/PHY behavior under load=2E >> >> If they do, the predicted MAC/PHY effects would include: >> >> - lower failed TXOP percentage >> - lower retransmission airtime fraction >> - improved AMPDU completion efficiency >> - higher payload delivered per TXOP >> - lower AMPDU truncation frequency >> - reduced EDCA wait distributions >> - improved airtime utilization >> - reduced service-time variance >> - changed MCS distributions across stations under realistic spatial >> topology, particularly at coverage edges and where multiple APs or R= RHs are >> candidates for node selection >> >> That is the measurement gap I am pointing at=2E The industry has extens= ive >> 802=2E11 feature lists and marketing claims, with comparatively little = open >> tooling to falsify what those actually do to building wide 802=2E11 MAC= /PHY >> behavior under real multi-client, multi-AP load=2E >> >> I developed and still maintain iperf2 because throughput alone has prov= en >> an insufficient measurement model for network behavior, e=2Eg=2E latenc= ies and >> responsiveness under load=2E Features added to iperf2 include: >> >> - trip-times >> - bounceback testing >> - one-way IP packet timing measurements >> - packet-level latency histograms >> - message-level (TCP write/read completion) latency histograms >> - responsiveness under load measurements >> - enhanced per-interval reporting >> - CWND reporting >> - RTT reporting >> - bytes/packets in-flight reporting >> - TCP retransmission reporting >> - TCP congestion-control selection (CUBIC, BBR, Prague, etc=2E) >> - udp-l4s including CE counters and durations >> - isochronous traffic generation >> - socket-layer pacing via SO_MAX_PACING_RATE >> - token-bucket write-rate control >> - Markov-chain packet-size generation >> - UDP latency/jitter analysis >> - multicast testing >> >> Those measurements operate above the 802=2E11 MAC/PHY=2E The missing la= yer >> remains open 802=2E11 MAC/PHY telemetry, which is what I'm building now= =2E >> >> This measurement standard should apply equally to any claim from any >> architecture, including Fi-Wi=2E >> >> The question becomes: does centralized MAC telemetry and coordinated >> airtime control affect measurable 802=2E11 MAC/PHY behavior under load >> relative to autonomous AP operation? >> >> Measure the same MAC/PHY metrics under equivalent topology, offered loa= d, >> and client mix=2E If those measurements do not improve relative to base= line, >> the architectural claim of Fi-Wi fails=2E We won't know until Fi-Wi is >> designed, built, deployed and measured at many different locations=2E T= he >> theoretical case is strong=2E Centralized scheduling, joint optimizati= on, >> and observability all argue for it=2E The design and measurements are t= he >> next steps=2E Then we'll see based on evidence=2E >> >> Bob >> >> Technically, Betamax was superior to VHS, and yet=2E=2E=2E >> >> If we would be talking about FiWi pre-jump from Wi-Fi 5 to Wi-Fi6/E/7, = I >> would even try to do my best and ignore https://fastgood=2Echeap=2E >> But we are not there, for better or for worse=2E >> >> ISPs like Dan that use Wi-Fi 6 (with mesh, especially based on batman-a= dv >> and FQ-CoDel / CAKE) and above at customer premises and Quality of >> Experience middle-box on their last-mile, while providing good, persona= l >> customer service (not some crappy outsourcing of it to India or "AI") w= ill >> be hard to beat, even for a big telco/ISP offering cheaper price=2E Yes= , some >> people will leave but the most of them will be coming back=2E >> >> This is, believe it or not, not a high bar to jump over, even though no= t >> many ISPs are getting it already=2E We all know that more or less: "Ban= dwidth >> is a lie, Bandwidth is dead," so it's coming=2E They will be throwing m= ore >> bandwidth on it for some time, but we will be getting from "innovators"= to >> "early adopters" soon and then, all we need is just that "crossing the >> chasm=2E" >> >> Despite all the difficulties, it will be faster and cheaper - also "goo= d >> enough," than FiWi=2E Or rather, it's here already, it's just not evenl= y >> distributed=2E >> There might be some good niche use case for FiWi, though, once it will >> mature and get there=2E >> >> All the best, >> >> >> Frank >> >> >> >> Frantisek (Frank) Borsik >> >> >> >> *In loving memory of Dave T=C3=A4ht: *1965-2025 >> >> https://libreqos=2Eio/2025/04/01/in-loving-memory-of-dave/ >> >> >> >> https://www=2Elinkedin=2Ecom/in/frantisekborsik >> >> Signal, Telegram, WhatsApp: +421919416714 >> >> iMessage, mobile: +420775230885 >> >> Skype: casioa5302ca >> >> frantisek=2Eborsik@gmail=2Ecom >> >> On Sun, May 24, 2026 at 2:12=E2=80=AFAM dan wro= te: >> >> >> >> On Sat, May 23, 2026 at 10:36=E2=80=AFAM wrote: >> >> > I don't have arguments on the technical bits of your reply=2E >> >> The industry hasn't provided open source tools to analyze 802=2E11 prop= erly=2E >> The proprietary ones are tightly coupled to chip firmware, owned by 802= =2E11 >> vendors, and not for sale=2E >> >> You've built solid networks, especially given how little 802=2E11 MAC-l= ayer >> and MCS observability current tooling exposes=2E I hope to make open so= urce >> 802=2E11 MAC telemetry tools available sooner rather than later=2E Thes= e will >> run on both an ESP32-C5 and an RPi5=2E The inexpensive ESP32 allows mon= itors >> to be placed throughout a venue at low cost=2E >> >> A key issue is what's being measured=2E Your deployment data is a capac= ity >> analysis=2E Once baseline capacity is adequate, user experience is driv= en by >> tail latency and service-time variance rather than throughput=2E A netw= ork >> can saturate aggregate throughput while still showing large service-tim= e >> variance and long per-flow tails under contention=2E These are differen= t >> measurements=2E >> >> And CODEL and CAKE are IP-layer mechanisms=2E They don't operate on 802= =2E11 >> TXOPs or airtime sojourn, which is where the contention and service-tim= e >> variance actually live=2E AQL is closer=2E It operates on airtime at th= e >> driver/firmware boundary, but it's still per-AP=2E There's no coordinat= ion >> across APs and no MAC telemetry exposed upward=2E >> >> Slide 6 of my DPDK Summit Stockholm talk lays out the layering: >> https://www=2Eumbernetworks=2Ecom/DPDK_WiFi_Stockholm_Pres=2Ehtml >> >> Check out iperf2's advanced features around --bounceback, --trip-times, >> and --histograms=2E These are available as open source=2E Man page: >> https://iperf2=2Esourceforge=2Eio/iperf-manpage=2Ehtml >> >> I'll try to respond with some metrics soon=2E My rig is down at the mom= ent, >> so give me a few days=2E >> >> Bob >> >> >> I agree=2E However, I'm not actually just measuring throughput, but ru= nning >> latency sensitive applications without issues=2E Frank might attest to= my >> efforts to reduce latency and I routinely share data on lqos (and anoth= er >> QoE product's) TCP measurements for latency and among QoE users, I beli= eve >> my network is top 1% in latency and jitter and in the WISP space=2E >> Obviously I'm not going to compete with XGSPON operators=2E=2E (though = I'm only >> measuring TCP because that's the 'easiest' to measure passively >> practically)=2E While this is not an engineering adequate benchmark, i= f my >> VoIP handsets work over wireless then the wireless is good is a very >> reasonable latency, jitter, loss argument=2E And I run a few brands of= WiFi >> based VoIP phones (Fanvill Wxxx series, Yealink Wxx and AXxx series)=2E >> Similarly, if the sonos works and is in sync, the wifi is good=2E >> >> As a service company and as a user, I don't really care so much where t= he >> goodness is in the system, mac layer or IP having cake work it's magic= =2E >> Basically running an AP on OFMDA (as much as possible) and well under t= he >> 'red line' capacity delivers great results on WiFi7 radios (and some Wi= Fi6 >> radios)=2E I have no doubt that FiWi could get more of the theoretical >> throughput delivered at the mac layer=2E >> >> Deliverables are all that matter to me and I think to buyers and users= =2E >> Benchmarks test deliverables which is great and I'm a routing iperf* us= er=2E >> It's engineering's problem to develop the next tech *AND* solicit fundi= ng >> to do so=2E >> >> >> >_______________________________________________ >Codel mailing list -- codel@lists=2Ebufferbloat=2Enet >To unsubscribe send an email to codel-leave@lists=2Ebufferbloat=2Enet --=20 Sent from my Android device with K-9 Mail=2E Please excuse my brevity=2E