From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-lb0-x232.google.com (mail-lb0-x232.google.com [IPv6:2a00:1450:4010:c04::232]) (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 1A5BD21F415; Thu, 26 Mar 2015 22:05:52 -0700 (PDT) Received: by lbbug6 with SMTP id ug6so55939181lbb.3; Thu, 26 Mar 2015 22:05:50 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20120113; h=content-type:mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=OtSEjNCElLVenm/XYe8LZoIfZmeoXlbvsy6+LZViqxQ=; b=bL8DbucUiywnY7EhSGacFqVSAs8Jv2nenb6Sn5iQLvWzCJNMeHhCJRjtKlUpxKn1Uk f+7uQx3MKPE2Ybv2ouDD8hjph3Jp7UUry1bnYOkgEX1/xNoAdpMd2wcDxPLtjYGGr386 KemTObuYIMXJ9MXrJL9mKxfG87SlK34DROlvkj/v399OMBhDRRQ7WQG6/78JY9Y64pyx cyCl0Gzc6BBzwoY2uZVGZAf06ltJjRQv9yN3hapB34sBGAfhy+fOazbYPvqyNxlo+4d8 IRqmRkGvlaYoCWkPBSMzjbgu0XqEONT/bTRQ1FveuagSxgGyuOEz7NIJMNdD5D7mWnFI JA1w== X-Received: by 10.112.160.227 with SMTP id xn3mr2569477lbb.112.1427432750551; Thu, 26 Mar 2015 22:05:50 -0700 (PDT) Received: from bass.home.chromatix.fi (37-33-89-117.bb.dnainternet.fi. [37.33.89.117]) by mx.google.com with ESMTPSA id rz10sm132584lbb.46.2015.03.26.22.05.48 (version=TLSv1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Thu, 26 Mar 2015 22:05:49 -0700 (PDT) Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 8.2 \(2070.6\)) From: Jonathan Morton In-Reply-To: Date: Fri, 27 Mar 2015 07:05:44 +0200 Content-Transfer-Encoding: quoted-printable Message-Id: <13C8415C-F90D-4D4B-962A-AAF945D20F2E@gmail.com> References: To: Dave Taht X-Mailer: Apple Mail (2.2070.6) Cc: Andrew McGregor , Jesper Dangaard Brouer , "cerowrt-devel@lists.bufferbloat.net" , bloat , Lorenzo Colitti , Felix Fietkau Subject: Re: [Cerowrt-devel] [Bloat] some notes on the archer c7v2's suitability for make-wifi-fast X-BeenThere: cerowrt-devel@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: Development issues regarding the cerowrt test router project List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 27 Mar 2015 05:06:21 -0000 > On 27 Mar, 2015, at 04:10, Dave Taht wrote: >=20 > I think cake can be improved quite a bit more and we really need to do = some profiling to find other bottlenecks. I=E2=80=99ve got far enough with the improved Diffserv logic to see = that, at the very least, cake3 will need to do less work to figure out = that it=E2=80=99s throttled. That=E2=80=99s because the hard shaper is = now global rather than class-local, so I can hoist it before any of the = class-specific work. If it gets past that, it can be confident that = it=E2=80=99s got a packet to deliver. This is important, because cake_dequeue() often gets called twice per = packet - once just after cake_enqueue(), when it might be too soon to = transmit, and again when the watchdog timer fires to denote the correct = transmit time. The class selection loop is also smaller and simpler (fewer edge cases = to cope with), and I worked out a shortcut to put in further down, so it = doesn=E2=80=99t have to re-run the class selection if a flow happens to = be in deficit. That=E2=80=99s another likely win. So those might turn out to be significant efficiency improvements, = altogether. Of course, if the real overhead is elsewhere, the = improvements in throughput might turn out to be small, but for the = moment I=E2=80=99m actually focusing on behaviour rather than = throughput. On that note, I=E2=80=99ve added a four-class Diffserv mapping alongside = the existing eight-class one. This new mapping is: Latency Sensitive (CS7, CS6, EF, VA, CS5, CS4) Streaming Media (AF4x, AF3x, CS3, AF2x, TOS4, CS2, TOS1) Best Effort (CS0, AF1x, TOS2, and all not otherwise = specified) Background Traffic (CS1) > So I saw fairly long delays (7ms or more) when running at these speeds = through the router. TBH, it=E2=80=99s a sign of how far we=E2=80=99ve come that we now = consider 7ms to be painful. :-) - Jonathan Morton