<html><body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;"><div class="">Hi Dave,</div><div class=""><br class=""></div><div class="">when I use tcp_12down instead of tcp_ndown I end up with something looking sane (see attached image?)</div><div class=""><br class=""></div><div class="">Also:</div><div class="">Summary of tcp_12down test run at 2016-11-20 20:16:54.350770:<br class=""><br class=""> avg / median # data pts<br class=""> Ping (ms) ICMP : 54.08 / 53.75 ms 351<br class=""> TCP download avg : 3.52 / 3.57 Mbits/s 301<br class=""> TCP download sum : 42.24 / 42.79 Mbits/s 301<br class=""> TCP download::1 : 3.50 / 3.63 Mbits/s 301<br class=""> TCP download::10 : 3.55 / 3.61 Mbits/s 301<br class=""> TCP download::11 : 3.57 / 3.62 Mbits/s 301<br class=""> TCP download::12 : 3.54 / 3.66 Mbits/s 300<br class=""> TCP download::2 : 3.51 / 3.61 Mbits/s 300<br class=""> TCP download::3 : 3.55 / 3.61 Mbits/s 301<br class=""> TCP download::4 : 3.59 / 3.67 Mbits/s 300<br class=""> TCP download::5 : 3.46 / 3.55 Mbits/s 300<br class=""> TCP download::6 : 3.49 / 3.60 Mbits/s 301<br class=""> TCP download::7 : 3.50 / 3.59 Mbits/s 300<br class=""> TCP download::8 : 3.48 / 3.57 Mbits/s 301<br class=""> TCP download::9 : 3.50 / 3.58 Mbits/s 300<br class=""><br class=""></div><div class=""><br class=""></div><div class="">looks fine. But maybe tcp_12down is not exactly doing the same as tcp_ndown… I tested from a laptop attached to one of the omnia’s lan ports (omnia’s wan is connected to the lan port of a LEDE r2222 wndr3700v2 with double NAT).</div><div class=""><br class=""></div><div class="">Best Regards</div><div class=""><span class="Apple-tab-span" style="white-space:pre"> </span>Sebastian</div><img height="240" width="320" apple-width="yes" apple-height="yes" apple-inline="yes" id="CA78E901-7DA4-4E27-96E0-3DE7D89144B4" src="cid:15A59BBF-804A-4B05-9FD7-E87D2AC3ADF4@lan" class=""><br class=""><blockquote type="cite" class="">On Nov 20, 2016, at 20:30, Dave Taht <<a href="mailto:dave.taht@gmail.com" class="">dave.taht@gmail.com</a>> wrote:<br class=""><br class="">Has the omnia got this problem?<br class=""><br class="">On Sun, Nov 20, 2016 at 11:29 AM, Dave Taht <<a href="mailto:dave.taht@gmail.com" class="">dave.taht@gmail.com</a>> wrote:<br class=""><blockquote type="cite" class="">so, in a flood of optimism, I reflashed my linksys 1200ac with lede head.<br class=""><br class="">If you hit it with more than one download flow in netperf(flent), all<br class="">successor flows still starve.<br class=""><br class=""><a href="http://www.taht.net/~d/linksys1200aclockout.png" class="">http://www.taht.net/~d/linksys1200aclockout.png</a><br class=""><br class="">I was under the impression a fix (also adding BQL) had arrived for<br class="">this problem in mainline.<br class=""><br class="">filed a bug on it just now, I should have done so long ago.<br class=""><br class="">https://bugs.lede-project.org/index.php?do=details&task_id=294<br class=""><br class="">--<br class="">Dave Täht<br class="">Let's go make home routers and wifi faster! With better software!<br class="">http://blog.cerowrt.org<br class=""></blockquote><br class=""><br class=""><br class="">-- <br class="">Dave Täht<br class="">Let's go make home routers and wifi faster! With better software!<br class=""><a href="http://blog.cerowrt.org" class="">http://blog.cerowrt.org</a><br class="">_______________________________________________<br class="">Cerowrt-devel mailing list<br class="">Cerowrt-devel@lists.bufferbloat.net<br class="">https://lists.bufferbloat.net/listinfo/cerowrt-devel<br class=""></blockquote><br class=""></body></html>