From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mout.gmx.net (mout.gmx.net [212.227.17.21]) (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 036343CB38; Wed, 4 Aug 2021 09:03:12 -0400 (EDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=gmx.net; s=badeba3b8450; t=1628082188; bh=lXncxlZNLJK5NBmytCxqSOxeCPRmZfKl/t8+QUo4q18=; h=X-UI-Sender-Class:Date:From:To:CC:Subject:In-Reply-To:References; b=Q89uhgheXUxmWU7su3B70O5snVTQZ/06c6cznsmSNV5M1dJS+70ZHqVFNgmjbg8kJ goTjOFtEoJwwxdRXplL4rJtzu/d7uP02ngp6e4pi3U7CMij9QWxPFIWBhPJ63YPOsi SFu0m/4BXw8nH+of76mwRKd4Kps42XP+u32h+h00= X-UI-Sender-Class: 01bb95c1-4bf8-414a-932a-4f6e2808ef9c Received: from [127.0.0.1] ([77.0.38.27]) by mail.gmx.net (mrgmx105 [212.227.17.168]) with ESMTPSA (Nemesis) id 1Mk0NU-1mqyA80nrE-00kOc3; Wed, 04 Aug 2021 15:03:08 +0200 Date: Wed, 04 Aug 2021 15:03:08 +0200 From: Sebastian Moeller To: Mikael Abrahamsson , Mikael Abrahamsson via Bloat , Jonathan Morton CC: starlink@lists.bufferbloat.net, dickroy@alum.mit.edu, bloat User-Agent: K-9 Mail for Android In-Reply-To: References: <058681B8-89EB-42ED-8E82-4048BA3C9504@cable.comcast.com> <649DC4B024D74B8BA6926ABFCD52DC79@SRA6> Message-ID: <5C65BC6E-1ABD-4432-B2CE-AC8BACDA363D@gmx.de> MIME-Version: 1.0 Content-Type: multipart/alternative; boundary=----96XJKT4NOZ8LAIJFBQJ3YQAUR8ZIFJ Content-Transfer-Encoding: 7bit X-Provags-ID: V03:K1:8Zql/3SUa/tFTeiy53FEkJA95nCwkWdqcB4tfoNu46l/5Q8d2tG q0rwyrBhiuO1zhUSd8mfupnTL7gg5WoNXo6YG1q4AhhLbgTuY8GgCgKkA3P9VeA+P7Yj+PW 9PJESDBAKCKr4Q+dLFSCO4fjzqX8cHXlPzY4l6WwtwH5CsUkwKmR3Qgg3GaNy1yO1s4fIsG Pf0loZw13SSFMntIr3pFw== X-Spam-Flag: NO X-UI-Out-Filterresults: notjunk:1;V03:K0:sKhdeBhzhYM=:7MvW3onH93OES4EyvabfGo ei3ywpzuUjV4iO6ozcJFI5pAfeqVsOApYtnLDH8YN7w76Vo0ke7Dr4iPja8k2YqJ10jRcZZG/ 5XDq9xmkRkLFyl0l50b86GBLxERvkPQRkl+9O0IAqk+Y2PwNvPoK8rSSCzlLacqrM1KKX0m+k KQsP7Zgyjw6CZ27Ejb2LrP8U1D1G6ZTkWyKwCFklFHsFrhiVnbPB3Wg8rgnxo+DyHnWoIvI7g XnO1CnR7iAl5qkS6tbspSNctIed/jb6vjKv28ddQn5L84+fCyNlBXsgJvh4ZAv7Cr7TBD7cAi VASVobFaVNNUUgzYjHIj0Z88ps6xPiJZWG3tWQWBVrT9L0RTvVxE1cH+PveKjFm+gT+gidTDZ OR542IOK1s+VKstSr8xAEZskE9wuSGvPUyk8MUyUHSD+gwnmclYvOkfS2sko+MJEf5QYA/Awj Xh4VBm7nMswLp3Abf2dnEvEJzpatFwBYFpfp2DfPrmoeLihwQO2iP1n9WtHXIM5ffCc895eoI 0FlfUBsvkFDxXy93g007bhQFAqLc2S/mQiMrEgGeUpjZUxXOZVqplByExxUIzgMSeYB3e4RJK VrwUPpEQQ+juvTx39A00T3Q/zxvrW46yHmEodVub4rZ1mJ99az2cZ6wbO9OXNITjg55EZPfCJ Wl2+7hJOHuVqYJeN24KaVSwmzPcmyoXE2cWPMubzM1P8OaMNqBDUjVKF/exkudrRCt+rHQbpJ 6gPMVdD0vUlkKCug5DYgLAOT7DKjm3AZbndaBpxiAWcBgUpLDjmXbaUGYSKegNHL1JwW5bTCb pVf5fGqMLrzKHBmAEUc75kZOQgtevLwV7iVpOd+PmvwKmYWWhHWtmtypeoDq/FdPTS3kz6N7X pTv6dJzhgPYr8QjVugQNZrz5LL8bzBkRb4A5Iz7EuMLScZ4iHYlwQkj+16E/coipPX8oXTW19 wr3KtXuMFiqBEtu/LiX9AO8UyqaU+mCMfr9COC5M8H/BbqhJDIypEOqf7tL6x34xl8ISRtiY1 4plS8WI12jzz+ObPJN7AKhyZ1Z6U3RpB9TE2FmajJZuyIdGFrZJTYB1HLreFH/a04snvIFydY 3LDZ7f97AZFH+D+pVBHodXdlNLCgH7LGOYlQDJlzD9d6AC/TK9LkuxIrg== Subject: Re: [Bloat] [Starlink] Of interest: Comcast AQM Paper 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: Wed, 04 Aug 2021 13:03:13 -0000 ------96XJKT4NOZ8LAIJFBQJ3YQAUR8ZIFJ Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: quoted-printable I guess the point is AQM is not really that expensive, even FQ AQM, traffic= shaping however is expensive=2E But for wifi shaping is not required so AQ= M became feasible=2E Regards Sebastian On 4 August 2021 14:46:30 CEST, Mikael Abrahamsson via Bloat wrote: >On Wed, 4 Aug 2021, Jonathan Morton wrote: > >> Linux-based CPE devices have AQM functionality integrated into the Wifi= =20 >> stack=2E The AQM itself operates at layer 3, but the Linux Wifi stack= =20 >> implementation uses information from layers 2 and 4 to improve=20 >> scheduling decisions, eg=2E airtime-fairness and flow-isolation (FQ)=2E= This=20 >> works best on soft-MAC Wifi hardware, such as ath9k/10k and MT76, where= =20 >> this information is most readily available to software=2E In principle= it=20 >> could also be implemented in the MAC, but I don't know of any vendor=20 >> that's done that yet=2E > >Does this work also with flowoffload enabled, or is that not accelerated= =20 >on for instance MT76? I'm surprised since MT76 can barely do 100 meg/s of= =20 >large packets using only CPU? > >--=20 >Mikael Abrahamsson email: swmike@swm=2Epp=2Ese >_______________________________________________ >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 ------96XJKT4NOZ8LAIJFBQJ3YQAUR8ZIFJ Content-Type: text/html; charset=utf-8 Content-Transfer-Encoding: quoted-printable I guess the point is AQM is not really that expens= ive, even FQ AQM, traffic shaping however is expensive=2E But for wifi shap= ing is not required so AQM became feasible=2E

Regards
Seb= astian

On 4 August 2021 14:46:30 CEST, Mi= kael Abrahamsson via Bloat <bloat@lists=2Ebufferbloat=2Enet> wrote: 
On Wed, 4 Aug 2021, Jonathan Morton wro=
te:

Linux-based CPE=
 devices have AQM functionality integrated into the Wifi 
stack=2E  The =
AQM itself operates at layer 3, but the Linux Wifi stack 
implementation=
 uses information from layers 2 and 4 to improve 
scheduling decisions, =
eg=2E airtime-fairness and flow-isolation (FQ)=2E This 
works best on so=
ft-MAC Wifi hardware, such as ath9k/10k and MT76, where 
this informatio=
n is most readily available to software=2E  In principle it 
could also =
be implemented in the MAC, but I don't know of any vendor 
that's done t=
hat yet=2E

Does this work also with flowoffload enabled=
, or is that not accelerated 
on for instance MT76? I'm surprised since =
MT76 can barely do 100 meg/s of 
large packets using only CPU?

-- 
Mikael Abrahamsson    email: swmike@sw=
m=2Epp=2Ese
Bloat mailing list
Bloat@lists=2Ebufferbloat=2Enet
https://lists=2Eb=
ufferbloat=2Enet/listinfo/bloat
--
Sent= from my Android device with K-9 Mail=2E Please excuse my brevity=2E
<= /div> ------96XJKT4NOZ8LAIJFBQJ3YQAUR8ZIFJ--