<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">I thought I saw a reference to an OpenWRT implementation with L4S. How well does that work?<div class=""><br class=""></div><div class=""><br class=""></div><div class=""><div class="">
<meta charset="UTF-8" class=""><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div dir="auto" style="caret-color: rgb(0, 0, 0); color: rgb(0, 0, 0); letter-spacing: normal; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; word-spacing: 0px; -webkit-text-stroke-width: 0px; text-decoration: none; word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div><br class="">Gene<br class="">----------------------------------------------<br class="">Eugene Chang</div><div><br class=""></div><div><br class=""></div></div></div></div></div></div></div></div></div>
</div>
<div><br class=""><blockquote type="cite" class=""><div class="">On May 7, 2024, at 9:46 AM, Dave Taht <<a href="mailto:dave.taht@gmail.com" class="">dave.taht@gmail.com</a>> wrote:</div><br class="Apple-interchange-newline"><div class=""><div class="">Pete heist, jon morton, and rod grimes published a TON of research as<br class="">to where l4s went wrong in these github repos:<br class=""><br class=""><a href="https://github.com/heistp" class="">https://github.com/heistp</a><br class=""><br class="">The last was: https://github.com/heistp/l4s-tests?tab=readme-ov-file#key-findings<br class=""><br class="">They were ignored. Me, I had taken one look at it 7+ years ago and<br class="">said this cannot possibly work with the installed base of wifi<br class="">properly and since 97E% of all home connections terminate in that it<br class="">was a dead horse which they kept flogging.<br class=""><br class="">After the L4S RFCs were published they FINALLY took their brands of<br class="">wishful thinking to actually exploring what happeed on real wifi<br class="">networks, and... I have no idea where that stands today. Yes a custom<br class="">wifi7 AP and presumably wifi8 will be able to deal with it, but<br class="">everything from the backoff mechanisms in the e2e TCP Prague code and<br class="">the proposed implementations on routers just plain does not work<br class="">except in a testbed. Fq_codel outperforms it across the board with<br class="">perhaps, some increased sensivity to RFC3168 seems needed only. L4S<br class="">(all transports actually) benefits a lot from packet pacing, and...<br class="">wait for it... fq)<br class=""><br class="">Slow start and convergence issues are problematic also with l4s.<br class=""><br class="">Being backward incompatible with fq_codel's deployed treatment of RFC3168 ECN.<br class=""> is a huge barrier too.<br class=""><br class="">The best use case I can think of for l4s is on a tightly controlled<br class="">docsis network, pure wires and short RTTs only. The one implementation<br class="">for 5G I have heard of was laughable in that they were only aiming for<br class="">200ms of induced latency on that.<br class=""><br class="">If on the other hand you look at fq (and also how well starlink is<br class="">performing nowadays) and ccs like bbr, well...<br class=""><br class="">I do honestly think there is room for this sort of signalling<br class="">somewhere on the internet, and do plan to add what I think will work<br class="">to cake at some point in the future. I do wish SCE had won, as it was<br class="">backwards compatible.<br class=""><br class=""><br class="">On Tue, May 7, 2024 at 12:15 PM Jeremy Austin <jeremy@aterlo.com> wrote:<br class=""><blockquote type="cite" class=""><br class=""><br class=""><br class="">On Tue, May 7, 2024 at 11:11 AM Dave Taht via Starlink <starlink@lists.bufferbloat.net> wrote:<br class=""><blockquote type="cite" class=""><br class="">The RFC is very plausible but the methods break down in multiple ways,<br class="">particularly with wifi.<br class=""></blockquote><br class=""><br class="">Dave, can you elaborate more on the failures? Are these being researched or addressed in the current trials, in your opinion?<br class=""><br class="">Jeremy<br class=""></blockquote><br class=""><br class=""><br class="">--<br class="">https://www.youtube.com/watch?v=BVFWSyMp3xg&t=1098s Waves Podcast<br class="">Dave Täht CSO, LibreQos<br class=""></div></div></blockquote></div><br class=""></div></body></html>