From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qt0-x22e.google.com (mail-qt0-x22e.google.com [IPv6:2607:f8b0:400d:c0d::22e]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by lists.bufferbloat.net (Postfix) with ESMTPS id 8913A3BA8E for ; Thu, 6 Sep 2018 13:22:22 -0400 (EDT) Received: by mail-qt0-x22e.google.com with SMTP id t5-v6so13184933qtn.3 for ; Thu, 06 Sep 2018 10:22:22 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=mime-version:references:in-reply-to:from:date:message-id:subject:to :cc:content-transfer-encoding; bh=dcpGAMg9oNgBnuQcMLXBUMiCjqEd828GeeWXyK/d0DU=; b=UlYumtGih5qGI6WcYQPwHHiCXSRmUdecK11Y7S5uI3o42hGLvjyA6o982FzyRyX/GM AO7wodjpi+XMBl9FwaaOi/srP/ZwiZ7HKMwVRG3/YbGmVyXjmuGcK6cIlUVoqyFL0GHo 2OW4H5STTMscu1T4mOjASEAoCBEVlup3L1BJGbi+CTB9NeeMMtDNNi5rlE2SAVvM4aVb 3PzTGYUFf/yzw3fTRk2lNtmub49jeu0d7yzVg7j3o8tkVfGEcMGHLS8rSeJa8Euw2vXz Le9A7qqxmQ0LQOoRCq3n7jcrfRwNaMg8mui7FKkktW8nbJEYiJGYqUrAnkeH8z7igJDe JJcw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to:cc:content-transfer-encoding; bh=dcpGAMg9oNgBnuQcMLXBUMiCjqEd828GeeWXyK/d0DU=; b=d7/uSbhZcJq0oByedanrLN7MiWNmJTdcvmTw5Nne/qa53Y5uA6gB8KqTSYKOOuyPy3 DNxZFgQoy8nW1Z4+50fApJOvPYwu1IqydSwq/DqHwyphPg3CO1U3BcasTAUhD6IH38Yf UOeKNlsiI1pYO9G6dIZqH0q1+qjwfKubu11B95wV8uNt7C9ntwYFqdo+/Fg0QUSZe52V RKuxC28s06YY0FM4jxeFbVhjOsPoR30IELTDBj3d2z+rGXSkhbOWP4tMWqT5ROwakNGa leDxdF2MFqo+Avv0d9JISi0VHa2JDr3grk4JTu/OVbXZh0DvLvNvVnNBhU4ijGy2oCLH WGyw== X-Gm-Message-State: APzg51Ca/aFPvdP+RZXkDknMaaOz+9xQsYtzETfTEH5DVwl/UnEVJAC5 yPhgxP3CAFvEWOcIZMbqevBjyNiYaphrKKOPjhg= X-Google-Smtp-Source: ANB0VdaB/JV8L9Et/dS+whXoXK41NdO9vJECh7Q555Lr71LMcXE4JlE1Oeb/Gl8/GcPmHKTenlvsdibl+7NIRLEadD0= X-Received: by 2002:a0c:b584:: with SMTP id g4-v6mr2920687qve.94.1536254541910; Thu, 06 Sep 2018 10:22:21 -0700 (PDT) MIME-Version: 1.0 References: <3E647031-D865-41B1-9C3A-6D34DB291005@heistp.net> In-Reply-To: From: Dave Taht Date: Thu, 6 Sep 2018 10:22:10 -0700 Message-ID: To: Pete Heist Cc: Cake List Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable Subject: Re: [Cake] fq_codel_fast X-BeenThere: cake@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: Cake - FQ_codel the next generation List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Thu, 06 Sep 2018 17:22:22 -0000 There was a very good paper or two (I think luca co-authored one) that showed that "active flows" were generally measured in the mid 200s in nearly any scenario. I agreed with that which was in part why I felt we could stick with 1024 queues, a direct mapped hash, and a couple collisions. cake can falsify that conclusion, or not - at least with ecn enabled, it does falsify it. I think. Can't remember the paper's name.... whether or not accepting 3x more delay as in this case is good, well... more measurements await via https://www.bufferbloat.net/projects/ecn-sane/wiki/ and the ecn-sane mailing list is now active. My original cake code dropped ecn on overload. I tended to think a little ecn a good thing. On Thu, Sep 6, 2018 at 10:10 AM Pete Heist wrote: > > Interesting, sounds like a good data point for the ECN debate. I wonder i= f that pathology happens at lower flow counts. > > I=E2=80=99ve been getting into FreeNet=E2=80=99s backhaul. Four of their = backhaul links, the orange lines in the following map, are licensed spectru= m full-duplex 100Mbit wireless links (not sure what tech, I=E2=80=99ll ask)= . I=E2=80=99ve so far not witnessed any bloat in these links because they s= eem to be over-provisioned based on the rates of the CPE connections, altho= ugh that may change as AC is increasingly deployed. > > http://mapa.czfree.net/#lat=3D50.76176199690661&lng=3D15.06277084350586&z= oom=3D13&autofilter=3D1&type=3Dsatellite&geolocate=3D98%7C114%7C111%7C117%7= C109%7C111%7C118%7C115%7C107%7C97&node=3D6101&aponly=3D1&bbonly=3D1&actlink= =3D1&actnode=3D1&tilt=3D0&heading=3D0& > > Active flow counts appear to be in the tens sometimes, probably not hundr= eds very often, from what I=E2=80=99ve witnessed so far... > > On Aug 30, 2018, at 8:24 PM, Dave Taht wrote: > > This version does indeed work against net-next. I managed to break > myself because I'd been fiddling with flows 32 in some cases, and my > version > returns ENOTSUPP for that which sqm doesn't catch... and ohhh.... > boy... htb with a 1000 packet fifo buffer fallback... SUCKS! :) > > As for profiling, once again I found myself distracted by the ecn > debate. Fitting ecn 500 flows through a 100mbit bottleneck results in > 1300 packets outstanding > 26 flows that can't start (presumably due to ecn fall back), and > without ecn, 450 packets outstanding 3 flows that can't start. > > On Wed, Aug 29, 2018 at 7:23 AM Dave Taht wrote: > > > I'm presently compiling against net-next. > On Wed, Aug 29, 2018 at 1:12 AM Pete Heist wrote: > > > > On Aug 29, 2018, at 3:04 AM, Dave Taht wrote: > > Anyway, this should be a drop in replacement (presently) for fq_codel, > that compiles out of tree and rips out almost everything I don't like. > > https://github.com/dtaht/fq_codel_fast > > > Cool=E2=80=A6I=E2=80=99d give it a quick run but it doesn=E2=80=99t compi= le for me (attached). Kernel version? > > I think the tc filter thing really hurt us in cake. > > > It would be interesting to see how much. Jon also expressed concern and I= =E2=80=99d been meaning to try some benchmarks before and after that change= =E2=80=A6 > > > > -- > > Dave T=C3=A4ht > CEO, TekLibre, LLC > http://www.teklibre.com > Tel: 1-669-226-2619 > > > > > -- > > Dave T=C3=A4ht > CEO, TekLibre, LLC > http://www.teklibre.com > Tel: 1-669-226-2619 > > --=20 Dave T=C3=A4ht CEO, TekLibre, LLC http://www.teklibre.com Tel: 1-669-226-2619