From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-oi0-x22e.google.com (mail-oi0-x22e.google.com [IPv6:2607:f8b0:4003:c06::22e]) (using TLSv1 with cipher RC4-SHA (128/128 bits)) (Client CN "smtp.gmail.com", Issuer "Google Internet Authority G2" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id 909B421FBE2 for ; Fri, 14 Aug 2015 07:23:00 -0700 (PDT) Received: by oiev193 with SMTP id v193so44490103oie.3 for ; Fri, 14 Aug 2015 07:22:59 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=mime-version:date:message-id:subject:from:to:content-type :content-transfer-encoding; bh=XNbWG6n2DEEex73QI2PLCG33h4SmlDbElJmEPSSUcdk=; b=C360gzN2XSCl8YoxBXHIp6TdZ98WAcaCAF2MJphgo4E5ksjbd40tyqmr2p0El36SkJ BaaXqET49vFbLzXoGTH/uxmHcOklcHYWNuHlWcXf9wHY3co5XiTipu3GvjRUA/NnU2rG R+V6Q8YFTYEbLN5Ak2Yjdy6rTfwKaubOw2y7jH8qVZgmbsoM6K7HAI4AfKfT0s89+53g sxy3TzpqT1eIJRoaapJKJAG0yFmYkCwZg1K+nND3Ln+m3aK7eSdL5SBL/cWoCs47QaCI uaNwigLtOhXQxM1jMPsFB4bNNsBCFWycFtG0d07PFdqwKK0+PW9cm88aAAzivgdSZ5io itJg== MIME-Version: 1.0 X-Received: by 10.202.179.87 with SMTP id c84mr38309385oif.110.1439562179407; Fri, 14 Aug 2015 07:22:59 -0700 (PDT) Received: by 10.202.108.12 with HTTP; Fri, 14 Aug 2015 07:22:59 -0700 (PDT) Date: Fri, 14 Aug 2015 07:22:59 -0700 Message-ID: From: Dave Taht To: cake@lists.bufferbloat.net Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Subject: [Cake] making peeling more aggressive? X-BeenThere: cake@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Cake - FQ_codel the next generation List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 14 Aug 2015 14:23:23 -0000 I have been running this in production. http://snapon.lab.bufferbloat.net/~d/0001-make-peeling-more-aggressive.patc= h It is hard to discern differences between these two variants, but I am a big believer in trying to get the peeling threshold down below what can be effectively scheduled by the cpu, which is less than 250us on many platforms. Also for those trying to make this work on current kernels, a quick and dirty patch to get it basically running is below. If someone can grok the new kernel hashing API enough to make it usable for cake, I'd love it. On Fri, Aug 14, 2015 at 7:16 AM, Dave Taht wrote: > damn me, I did this patch back in early june. > > http://snapon.lab.bufferbloat.net/~d/0001-hacked-to-more-or-less-support-= netnext-4.2-change-in.patch > > On Fri, Aug 14, 2015 at 7:09 AM, Toke H=C3=B8iland-J=C3=B8rgensen wrote: >> Dave Taht writes: >> >>> want a patch >>> I guess you >> >> Yes, please :) >> >> -Toke > > > > -- > Dave T=C3=A4ht > worldwide bufferbloat report: > http://www.dslreports.com/speedtest/results/bufferbloat > And: > What will it take to vastly improve wifi for everyone? > https://plus.google.com/u/0/explore/makewififast --=20 Dave T=C3=A4ht worldwide bufferbloat report: http://www.dslreports.com/speedtest/results/bufferbloat And: What will it take to vastly improve wifi for everyone? https://plus.google.com/u/0/explore/makewififast