<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="">Interesting, sounds like a good data point for the ECN debate. I wonder if that pathology happens at lower flow counts.<div class=""><br class=""></div><div class="">I’ve been getting into FreeNet’s backhaul. Four of their backhaul links, the orange lines in the following map, are licensed spectrum full-duplex 100Mbit wireless links (not sure what tech, I’ll ask). I’ve so far not witnessed any bloat in these links because they seem to be over-provisioned based on the rates of the CPE connections, although that may change as AC is increasingly deployed.<div class=""><br class=""></div><div class=""><a href="http://mapa.czfree.net/#lat=50.76176199690661&lng=15.06277084350586&zoom=13&autofilter=1&type=satellite&geolocate=98|114|111|117|109|111|118|115|107|97&node=6101&aponly=1&bbonly=1&actlink=1&actnode=1&tilt=0&heading=0&" class="">http://mapa.czfree.net/#lat=50.76176199690661&lng=15.06277084350586&zoom=13&autofilter=1&type=satellite&geolocate=98%7C114%7C111%7C117%7C109%7C111%7C118%7C115%7C107%7C97&node=6101&aponly=1&bbonly=1&actlink=1&actnode=1&tilt=0&heading=0&</a></div><div class=""><br class=""></div><div class="">Active flow counts appear to be in the tens sometimes, probably not hundreds very often, from what I’ve witnessed so far...</div><div class=""><div><br class=""><blockquote type="cite" class=""><div class="">On Aug 30, 2018, at 8:24 PM, 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="">This version does indeed work against net-next. I managed to break<br class="">myself because I'd been fiddling with flows 32 in some cases, and my<br class="">version<br class="">returns ENOTSUPP for that which sqm doesn't catch... and ohhh....<br class="">boy... htb with a 1000 packet fifo buffer fallback... SUCKS! :)<br class=""><br class="">As for profiling, once again I found myself distracted by the ecn<br class="">debate. Fitting ecn 500 flows through a 100mbit bottleneck results in<br class="">1300 packets outstanding<br class="">26 flows that can't start (presumably due to ecn fall back), and<br class="">without ecn, 450 packets outstanding 3 flows that can't start.<br class=""><br class="">On Wed, Aug 29, 2018 at 7:23 AM Dave Taht <<a href="mailto:dave.taht@gmail.com" class="">dave.taht@gmail.com</a>> wrote:<br class=""><blockquote type="cite" class=""><br class="">I'm presently compiling against net-next.<br class="">On Wed, Aug 29, 2018 at 1:12 AM Pete Heist <<a href="mailto:pete@heistp.net" class="">pete@heistp.net</a>> wrote:<br class=""><blockquote type="cite" class=""><br class=""><br class=""><blockquote type="cite" class="">On Aug 29, 2018, at 3:04 AM, Dave Taht <<a href="mailto:dave.taht@gmail.com" class="">dave.taht@gmail.com</a>> wrote:<br class=""><br class="">Anyway, this should be a drop in replacement (presently) for fq_codel,<br class="">that compiles out of tree and rips out almost everything I don't like.<br class=""><br class=""><a href="https://github.com/dtaht/fq_codel_fast" class="">https://github.com/dtaht/fq_codel_fast</a><br class=""></blockquote><br class="">Cool…I’d give it a quick run but it doesn’t compile for me (attached). Kernel version?<br class=""><br class=""><blockquote type="cite" class="">I think the tc filter thing really hurt us in cake.<br class=""></blockquote><br class="">It would be interesting to see how much. Jon also expressed concern and I’d been meaning to try some benchmarks before and after that change…<br class=""><br class=""></blockquote><br class=""><br class="">--<br class=""><br class="">Dave Täht<br class="">CEO, TekLibre, LLC<br class=""><a href="http://www.teklibre.com" class="">http://www.teklibre.com</a><br class="">Tel: 1-669-226-2619<br class=""></blockquote><br class=""><br class=""><br class="">-- <br class=""><br class="">Dave Täht<br class="">CEO, TekLibre, LLC<br class=""><a href="http://www.teklibre.com" class="">http://www.teklibre.com</a><br class="">Tel: 1-669-226-2619<br class=""></div></div></blockquote></div><br class=""></div></div></body></html>