[Bloat] WiFi

[Livingood, Jason]

Dropping Starlink as Bloat is the right list. The IEEE 802.11 domain is certainly different than IP, so typical IP CCs don’t apply. In our L4S/NQB trials, we put LL-marked packets into the AC_VI WMM queue in the Wi-Fi network. IMO there is more work in 802.11 to focus on latency – so much focus right now is on throughput over everything else.

From: Starlink <starlink-bounces at lists.bufferbloat.net> on behalf of Rich Brown via Starlink <starlink at lists.bufferbloat.net>
Reply-To: Rich Brown <richb.hanover at gmail.com>
Date: Wednesday, May 8, 2024 at 07:33
To: David Fernández <davidfdzp at gmail.com>
Cc: starlink <starlink at lists.bufferbloat.net>, bloat <bloat at lists.bufferbloat.net>
Subject: Re: [Starlink] [Bloat] L4S

Let's split this thread and use this message to continue the discussion of L4S. Thanks


On May 8, 2024, at 5:31 AM, David Fernández via Starlink <starlink at lists.bufferbloat.net<mailto:starlink at lists.bufferbloat.net>> wrote:

I see that L4S is not really solving everything (I read about issues with Wi-Fi), although it seems to be a step in the right direction, to be improved, let's hope.

At least, Nokia is implementing it in its network gear (for mobile operators), so the bufferbloat problem is somehow acknowledged by industry, at least initially or partially.

I have seen two consecutive RFCs to 9330:
https://www.rfc-editor.org/info/rfc9331<https://urldefense.com/v3/__https:/www.rfc-editor.org/info/rfc9331__;!!CQl3mcHX2A!CGA-mCO2vy_CR16TDfs22u-WM8rcRFi2Ax_22LWAWzLou29azIk9NBy9j65tVl4MM1gfanuytPoVI9c-EGdmsUeJx9ShJwX6Dw$>
https://www.rfc-editor.org/info/rfc9332<https://urldefense.com/v3/__https:/www.rfc-editor.org/info/rfc9332__;!!CQl3mcHX2A!CGA-mCO2vy_CR16TDfs22u-WM8rcRFi2Ax_22LWAWzLou29azIk9NBy9j65tVl4MM1gfanuytPoVI9c-EGdmsUeJx9RJkEV4wA$>

I suspect that optimal results require the bufferbloat to be addressed not only at network layer (IP), but also with some pipelining or cross-layering at link level (Ethernet, Wi-Fi or any other link technology, such as 5G, SATCOM, VHF...)

Regards,

David F.

Date: Tue, 7 May 2024 08:46:03 -0400
From: Dave Collier-Brown <dave.collier-Brown at indexexchange.com<mailto:dave.collier-Brown at indexexchange.com>>
To: starlink at lists.bufferbloat.net<mailto:starlink at lists.bufferbloat.net>
Subject: Re: [Starlink] The "reasons" that bufferbloat isn't a problem
Message-ID: <3d6bdccf-e3d1-4f62-a029-25bfd1f458f5 at indexexchange.com<mailto:3d6bdccf-e3d1-4f62-a029-25bfd1f458f5 at indexexchange.com>>
Content-Type: text/plain; charset="utf-8"; Format="flowed"

It has an RFC at https://datatracker.ietf.org/doc/rfc9330/<https://urldefense.com/v3/__https:/datatracker.ietf.org/doc/rfc9330/__;!!CQl3mcHX2A!CGA-mCO2vy_CR16TDfs22u-WM8rcRFi2Ax_22LWAWzLou29azIk9NBy9j65tVl4MM1gfanuytPoVI9c-EGdmsUeJx9R7SZLUsg$>

I read it as a way to rapidly find the available bandwidth without the TCP "sawtooth". The paper cites fc_codel and research based on it.

I suspect My Smarter Colleagues know more (;-))

--dave



On 2024-05-07 08:13, David Fernández via Starlink wrote:
Is L4S a solution to bufferbloat? I have read that gamers are happy with it.

Sorry, I read it here, in Spanish:
https://www.adslzone.net/noticias/operadores/retardo-videojuegos-nokia-vodafone<https://urldefense.com/v3/__https:/www.adslzone.net/noticias/operadores/retardo-videojuegos-nokia-vodafone__;!!CQl3mcHX2A!CGA-mCO2vy_CR16TDfs22u-WM8rcRFi2Ax_22LWAWzLou29azIk9NBy9j65tVl4MM1gfanuytPoVI9c-EGdmsUeJx9Ro1nvoFA$>

Regards,

David F.
_______________________________________________
Starlink mailing list
Starlink at lists.bufferbloat.net<mailto:Starlink at lists.bufferbloat.net>
https://lists.bufferbloat.net/listinfo/starlink<https://urldefense.com/v3/__https:/lists.bufferbloat.net/listinfo/starlink__;!!CQl3mcHX2A!CGA-mCO2vy_CR16TDfs22u-WM8rcRFi2Ax_22LWAWzLou29azIk9NBy9j65tVl4MM1gfanuytPoVI9c-EGdmsUeJx9QRv1i0VA$>


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.bufferbloat.net/pipermail/bloat/attachments/20240508/f8cdb91e/attachment-0001.html>