<div dir="ltr"><div class="gmail_default" style="font-family:monospace">It is not surprising that BBR comes from Van who's also designed and implemented pathchar.</div><div class="gmail_default" style="font-family:monospace"><br></div><div class="gmail_default" style="font-family:monospace">I liked reading the paper when it was published and it has the merit to be simple to read</div><div class="gmail_default" style="font-family:monospace">for a large audience.</div><div class="gmail_default" style="font-family:monospace"><br></div><div class="gmail_default" style="font-family:monospace">I agree very much on the title as bang-bang congestion control (not only AIMD) could be</div><div class="gmail_default" style="font-family:monospace">deprecated entirely by measurement based approaches like BBR. </div><div class="gmail_default" style="font-family:monospace"><br></div><div class="gmail_default" style="font-family:monospace">In bang-bang cc the sending rate is obtained by a root-finding algorithm (gradient based) that</div><div class="gmail_default" style="font-family:monospace">is fed by measurements of congestion (queue, loss, latency), whereas in BBR the sending rate is</div><div class="gmail_default" style="font-family:monospace">an (almost?) explicit function of the measured quantities. </div><div class="gmail_default" style="font-family:monospace"><br></div><div class="gmail_default" style="font-family:monospace">In theory both approaches work, but for the former we have seen a proliferation of root-finding algorithms</div><div class="gmail_default" style="font-family:monospace">for wireless, large BDP networks, small BDP network, satellite, cellular, shared-media, non-shared media and more.</div><div class="gmail_default" style="font-family:monospace">Selection of the right one is a question of tuning, which is extremely complex and static.</div><div class="gmail_default" style="font-family:monospace"><br></div><div class="gmail_default" style="font-family:monospace">If BBR can fix that by having a unique model for all these cases that would make deprecation, as intended in the paper,</div><div class="gmail_default" style="font-family:monospace">likely to happen.</div><div class="gmail_default" style="font-family:monospace"><br></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Fri, Dec 13, 2019 at 10:25 PM Dave Taht <<a href="mailto:dave.taht@gmail.com">dave.taht@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">and everything we know about the tcp macroscopic model, is obsolete,<br>
according to a provocative paper by matt mathis and Jamshid Mahdavi<br>
in sigcomm.<br>
<br>
<a href="https://ccronline.sigcomm.org/wp-content/uploads/2019/10/acmdl19-323.pdf" rel="noreferrer" target="_blank">https://ccronline.sigcomm.org/wp-content/uploads/2019/10/acmdl19-323.pdf</a><br>
<br>
<br>
<br>
<br>
On Fri, Dec 13, 2019 at 1:05 PM Carlo Augusto Grazia<br>
<<a href="mailto:carloaugusto.grazia@unimore.it" target="_blank">carloaugusto.grazia@unimore.it</a>> wrote:<br>
><br>
> Hi Dave,<br>
> thank you for your email!<br>
> Toke told me about AQL a couple of weeks ago, I definitely want to test it ASAP.<br>
> BBR struggles a lot on Wi-Fi interfaces (ones with aggregation) with kernel 4.14 & 4.19.<br>
> Anyway, it seems that with BBRv2 on new kernels this problem does not exist anymore.<br>
><br>
> Best regards<br>
> Carlo<br>
><br>
> Il giorno ven 13 dic 2019 alle 20:54 Dave Taht <<a href="mailto:dave.taht@gmail.com" target="_blank">dave.taht@gmail.com</a>> ha scritto:<br>
>><br>
>> <a href="https://sci-hub.tw/10.1109/WiMOB.2019.8923418" rel="noreferrer" target="_blank">https://sci-hub.tw/10.1109/WiMOB.2019.8923418</a><br>
>><br>
>> It predates the aql work, but the bbr result is puzzling.<br>
>><br>
>><br>
>> --<br>
>> Make Music, Not War<br>
>><br>
>> Dave Täht<br>
>> CTO, TekLibre, LLC<br>
>> <a href="http://www.teklibre.com" rel="noreferrer" target="_blank">http://www.teklibre.com</a><br>
>> Tel: 1-831-435-0729<br>
><br>
> --<br>
> --------------------------------------------------------------------<br>
> Carlo Augusto Grazia, Ph. D.<br>
> Assistant Professor<br>
> --------------------------------------------------------------------<br>
> Dept. of Engineering "Enzo Ferrari"<br>
> University of Modena and Reggio Emilia<br>
> Via Pietro Vivarelli, 10/1 - 41125 - Modena - Italy<br>
> Building 26, floor 2, room 28<br>
> Tel.: +39-059-2056323<br>
> email: <a href="mailto:carloaugusto.grazia@unimore.it" target="_blank">carloaugusto.grazia@unimore.it</a><br>
> Link to my personal home page here<br>
> --------------------------------------------------------------------<br>
<br>
<br>
<br>
-- <br>
Make Music, Not War<br>
<br>
Dave Täht<br>
CTO, TekLibre, LLC<br>
<a href="http://www.teklibre.com" rel="noreferrer" target="_blank">http://www.teklibre.com</a><br>
Tel: 1-831-435-0729<br>
_______________________________________________<br>
Make-wifi-fast mailing list<br>
<a href="mailto:Make-wifi-fast@lists.bufferbloat.net" target="_blank">Make-wifi-fast@lists.bufferbloat.net</a><br>
<a href="https://lists.bufferbloat.net/listinfo/make-wifi-fast" rel="noreferrer" target="_blank">https://lists.bufferbloat.net/listinfo/make-wifi-fast</a></blockquote></div>