From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-oa1-x2a.google.com (mail-oa1-x2a.google.com [IPv6:2001:4860:4864:20::2a]) (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 0D4453CC9C for ; Tue, 7 May 2024 16:06:33 -0400 (EDT) Received: by mail-oa1-x2a.google.com with SMTP id 586e51a60fabf-2401ab56692so830638fac.1 for ; Tue, 07 May 2024 13:06:32 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1715112392; x=1715717192; darn=lists.bufferbloat.net; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:from:to:cc:subject:date:message-id:reply-to; bh=lcAgg9j09xKXzqgPvjupTOUREbEL0ab5J72DgZPKo94=; b=GBHhtc9J+P5QKFFO2S3fobrigrI3p173kveNqQYZeRyxC4CNTAIg8PCGS/SsZejoYK bEW6SyMA43Pqxbx4SY1wu7zaswSojdD2it0nliSNY8DuV3WUILfixggcaKLk5ExenG/3 VMl/10CaqVzXWjqpBot7Rjr+JqNSAiVJoyIrc7hXyKg3qhSzBExyhGOQx/UwVcEYBFR8 Kjuq92A/VVI1D3FAolv51bw+8iYaQM4gQGLDmkhyYu3TAK2Vh1bD0ZmN45Nr9YrIs4Ta zQ+m7LmpVh8/CAxImFCguyWo9Js9/+YQqTBC4mXPxxSX3FV4D9S33CjbijoD014X8WkT mL+Q== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1715112392; x=1715717192; h=cc:to:subject:message-id:date:from:in-reply-to:references :mime-version:x-gm-message-state:from:to:cc:subject:date:message-id :reply-to; bh=lcAgg9j09xKXzqgPvjupTOUREbEL0ab5J72DgZPKo94=; b=XsvAOGgi3s61iBwYysWvhyFX4eIYy4B271ZDwWNV3utcMU65GZozWKbpU7Q5/v73lf xquP4VexVcUpyMo+tMz0xACzSEgVqhh9Yckv5sbM55Jztckq5QJjdbGxmCX8rClNY6dY o7CSl5LanYUKtOB7+YdgoEyhhu1NNJuDG3x6C+gZHGsMKc4GP3nw55Hv0EHkfmI7IYdm pjxUncujT2OcnqwJqU+K1gkQRck3aZB7degydtAHCrpHi4/ew2EjKzLsTT5CCjr0MW4q PJgewNL2QhSATsjekIlJ6EP2VU3ohfXFksMQ+EYxpYiIQztNQBB10wjTOrt544s7gsIV h4ZQ== X-Forwarded-Encrypted: i=1; AJvYcCX1XRaOnljHNNfvzndtjIXEojc741JMA69LrqiRJhAg0eo8ifGlRGKGLJ7cgYsii0yaDgSTcKbD89McEbAUjXbnf6SR/5bkdnCxmyThx6E= X-Gm-Message-State: AOJu0YwACwrKvcYpslywOUWfF+or8Unx8yPT7QLWq0e90PgY0XPkizEu k3XX1k8nPgF7lzgWs86BCpLyxjDLNXrhnOV7Z+BeakiSuUUf63L9grgpvMBzUTjri9OIDM+Y9hc CNNJ0pbpcfalvCZ2USOaQ8/xC3to= X-Google-Smtp-Source: AGHT+IEO9DyWHqMktZAWR3zM5Gf0IlOhoUPIbOjGXHYO8rGBNIbu8+LKqUBsYc0kaIpCx3FBsBrwZHbDoMJ95YRT94U= X-Received: by 2002:a05:6870:d88f:b0:22e:cfee:320c with SMTP id 586e51a60fabf-24098c885afmr678250fac.57.1715112391986; Tue, 07 May 2024 13:06:31 -0700 (PDT) MIME-Version: 1.0 References: <3d6bdccf-e3d1-4f62-a029-25bfd1f458f5@indexexchange.com> <1779481A-0817-4F18-A0D7-A7A5AA0AF9D6@ieee.org> <9C282F48-BA0A-4DF4-B079-A0825453FE44@ieee.org> In-Reply-To: <9C282F48-BA0A-4DF4-B079-A0825453FE44@ieee.org> From: Frantisek Borsik Date: Tue, 7 May 2024 22:05:56 +0200 Message-ID: To: Eugene Y Chang Cc: Dave Taht , Jeremy Austin , Dave Taht via Starlink , Dave Collier-Brown Content-Type: multipart/alternative; boundary="000000000000dfda000617e2b882" Subject: Re: [Starlink] The "reasons" that bufferbloat isn't a problem X-BeenThere: starlink@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: "Starlink has bufferbloat. Bad." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 07 May 2024 20:06:33 -0000 --000000000000dfda000617e2b882 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Here is a current view of it, IIRC: https://forum.openwrt.org/t/rfc9330-rfc9331-rfc9332-for-lower-latency/18051= 9/12 All the best, Frank Frantisek (Frank) Borsik https://www.linkedin.com/in/frantisekborsik Signal, Telegram, WhatsApp: +421919416714 iMessage, mobile: +420775230885 Skype: casioa5302ca frantisek.borsik@gmail.com On Tue, May 7, 2024 at 10:03=E2=80=AFPM Eugene Y Chang via Starlink < starlink@lists.bufferbloat.net> wrote: > I thought I saw a reference to an OpenWRT implementation with L4S. How > well does that work? > > > > Gene > ---------------------------------------------- > Eugene Chang > > > > On May 7, 2024, at 9:46 AM, Dave Taht wrote: > > Pete heist, jon morton, and rod grimes published a TON of research as > to where l4s went wrong in these github repos: > > https://github.com/heistp > > The last was: > https://github.com/heistp/l4s-tests?tab=3Dreadme-ov-file#key-findings > > They were ignored. Me, I had taken one look at it 7+ years ago and > said this cannot possibly work with the installed base of wifi > properly and since 97E% of all home connections terminate in that it > was a dead horse which they kept flogging. > > After the L4S RFCs were published they FINALLY took their brands of > wishful thinking to actually exploring what happeed on real wifi > networks, and... I have no idea where that stands today. Yes a custom > wifi7 AP and presumably wifi8 will be able to deal with it, but > everything from the backoff mechanisms in the e2e TCP Prague code and > the proposed implementations on routers just plain does not work > except in a testbed. Fq_codel outperforms it across the board with > perhaps, some increased sensivity to RFC3168 seems needed only. L4S > (all transports actually) benefits a lot from packet pacing, and... > wait for it... fq) > > Slow start and convergence issues are problematic also with l4s. > > Being backward incompatible with fq_codel's deployed treatment of RFC3168 > ECN. > is a huge barrier too. > > The best use case I can think of for l4s is on a tightly controlled > docsis network, pure wires and short RTTs only. The one implementation > for 5G I have heard of was laughable in that they were only aiming for > 200ms of induced latency on that. > > If on the other hand you look at fq (and also how well starlink is > performing nowadays) and ccs like bbr, well... > > I do honestly think there is room for this sort of signalling > somewhere on the internet, and do plan to add what I think will work > to cake at some point in the future. I do wish SCE had won, as it was > backwards compatible. > > > On Tue, May 7, 2024 at 12:15=E2=80=AFPM Jeremy Austin = wrote: > > > > > On Tue, May 7, 2024 at 11:11=E2=80=AFAM Dave Taht via Starlink < > starlink@lists.bufferbloat.net> wrote: > > > The RFC is very plausible but the methods break down in multiple ways, > particularly with wifi. > > > > Dave, can you elaborate more on the failures? Are these being researched > or addressed in the current trials, in your opinion? > > Jeremy > > > > > -- > https://www.youtube.com/watch?v=3DBVFWSyMp3xg&t=3D1098s Waves Podcast > Dave T=C3=A4ht CSO, LibreQos > > > _______________________________________________ > Starlink mailing list > Starlink@lists.bufferbloat.net > https://lists.bufferbloat.net/listinfo/starlink > --000000000000dfda000617e2b882 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable
Here is a current view of it, IIRC:


All the best,

Frank

F= rantisek (Frank) Borsik

=C2=A0

https://www.linkedin.com= /in/frantisekborsik

Signal, Telegram, WhatsApp: +421919416714=C2=A0

iMessage, mob= ile: +420775230885

Skype: casioa5302ca

frantisek.borsik@gmail.com=

<= /div>


On Tue, May 7, 2024 at 10:03=E2=80=AFPM Eugene Y Chang= via Starlink <starlin= k@lists.bufferbloat.net> wrote:
I thought I saw a reference to an OpenWRT= implementation with L4S. How well does that work?


<= /div>
<= div dir=3D"auto" style=3D"color:rgb(0,0,0);letter-spacing:normal;text-align= :start;text-indent:0px;text-transform:none;white-space:normal;word-spacing:= 0px;text-decoration:none;line-break:after-white-space">

Gene
----------------------------------------------
Eugene Cha= ng


<= /div>

On May 7, 2024, at 9:46 AM, Dave Ta= ht <dave.taht@g= mail.com> wrote:

Pete heist, jon morton, and rod = grimes published a TON of research as
to where l4s went wrong in these g= ithub repos:

https://github.com/heistp

The last was: https://github.com/heistp/l4s-tests?tab=3Dreadme-ov-file#key-findings=

They were ignored. Me, I had taken one look at it 7+ years ago and<= br>said this cannot possibly work with the installed base of wifi
proper= ly and since 97E% of all home connections terminate in that it
was a dea= d horse which they kept flogging.

After the L4S RFCs were published = they FINALLY took their brands of
wishful thinking to actually exploring= what happeed on real wifi
networks, and... I have no idea where that st= ands today. Yes a custom
wifi7 AP and presumably wifi8 will be able to d= eal with it, but
everything from the backoff mechanisms in the e2e TCP P= rague code and
the proposed implementations on routers just plain does n= ot work
except in a testbed. Fq_codel outperforms it across the board wi= th
perhaps, some increased sensivity to RFC3168 seems needed only. L4S(all transports actually) benefits a lot from packet pacing, and...
wa= it for it... fq)

Slow start and convergence issues are problematic a= lso with l4s.

Being backward incompatible with fq_codel's deploy= ed treatment of RFC3168 ECN.
is a huge barrier too.

The best use= case I can think of for l4s is on a tightly controlled
docsis network, = pure wires and short RTTs only. The one implementation
for 5G I have hea= rd of was laughable in that they were only aiming for
200ms of induced l= atency on that.

If on the other hand you look at fq (and also how we= ll starlink is
performing nowadays) and ccs like bbr, well...

I d= o honestly think there is room for this sort of signalling
somewhere on = the internet, and do plan to add what I think will work
to cake at some = point in the future. I do wish SCE had won, as it was
backwards compatib= le.


On Tue, May 7, 2024 at 12:15=E2=80=AFPM Jeremy Austin <jeremy@aterlo.com&= gt; wrote:



On Tue, May 7, 2024 at = 11:11=E2=80=AFAM Dave Taht via Starlink <starlink@lists.bufferbloat.net>= wrote:

The RFC is very plausible but the = methods break down in multiple ways,
particularly with wifi.


Dave, can you elaborate more on the failures? Are these being = researched or addressed in the current trials, in your opinion?

Jere= my



--
https://www.youtube.com= /watch?v=3DBVFWSyMp3xg&t=3D1098s Waves Podcast
Dave T=C3=A4ht CS= O, LibreQos

_____________= __________________________________
Starlink mailing list
Starlin= k@lists.bufferbloat.net
https://lists.bufferbloat.net/listinfo/starlink
--000000000000dfda000617e2b882--