From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mout.gmx.net (mout.gmx.net [212.227.15.19]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "mout.gmx.net", Issuer "TeleSec ServerPass DE-1" (verified OK)) by huchra.bufferbloat.net (Postfix) with ESMTPS id CF05E21F0BA for ; Mon, 23 Mar 2015 17:07:46 -0700 (PDT) Received: from hms-beagle.home.lan ([87.164.165.7]) by mail.gmx.com (mrgmx002) with ESMTPSA (Nemesis) id 0LsTDk-1ZbslM06eW-0122yK; Tue, 24 Mar 2015 01:07:44 +0100 Content-Type: text/plain; charset=windows-1252 Mime-Version: 1.0 (Mac OS X Mail 7.3 \(1878.6\)) From: Sebastian Moeller In-Reply-To: Date: Tue, 24 Mar 2015 01:07:41 +0100 Content-Transfer-Encoding: quoted-printable Message-Id: <0D932070-8516-4EBD-A793-F11DFE4A2C57@gmx.de> References: <08BAF198-87C5-42B8-8899-53F34E47156E@gmail.com> <896FAE61-B45A-4F34-9449-5ADB82194DD9@gmx.de> <48350C2E-C33A-4534-84BC-5D56F4AAF0EA@gmail.com> <8AC58249-8199-405B-997A-E8F7285A34FB@gmx.de> To: =?windows-1252?Q?Dave_T=E4ht?= X-Mailer: Apple Mail (2.1878.6) X-Provags-ID: V03:K0:6q1GEaHIP2z3BwL6WElr08YkL/XskxXbHIOzfBtA1JhnCo9MH21 g9CaXugkEHazjxMIBaPCM6HEjapcIhXsm9SG5VJBW7+fL8UywTOdEcKmHLVBCzVIj81+m1W J09FMc3mqPTWn3j8aWBuCI0+gOwbvz0kE3Orm+EsPVpaARRUClf/IISdYowdwod1VruExDH RIM4Z6QdGsasoXuPzSOHA== X-UI-Out-Filterresults: notjunk:1; Cc: Jonathan Morton , "cerowrt-devel@lists.bufferbloat.net" Subject: Re: [Cerowrt-devel] archer c7 v2, policing, hostapd, test openwrt build 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: Tue, 24 Mar 2015 00:08:15 -0000 Hi Dave, On Mar 24, 2015, at 01:05 , Dave Taht wrote: > this is with cero or last weekend's build? Oops, forgot to mention, this is with cerowrt 3.10.50-1, I only = have one router and have not dared to switch to the new shiny = (unstable?) thing yet. The test was going over se00 from a machine that = should be able to deliver >=3D 100Mbps symmetric. Best Regards Sebastian >=20 > On Mon, Mar 23, 2015 at 5:00 PM, Sebastian Moeller = wrote: >> Hi Jonathan, hi List, >>=20 >>=20 >> So I got around to a bit of rrul testing of the dual egress idea to = asses the cost of IFB, but the results are complicated (so most likely I = screwed up). On an wndr3700v2 on a 100Mbps/40Mbps link I get the = following (excuse the two images either the plot is intelligble or the = legend...): >>=20 >>=20 >>=20 >> Only in case of shaping the total bandwidth to the ~70Mbps this = router can barely do can I see an effect of the dual egress instead of = the IFB based ingress shaper. So column 7 (ipv4) and column 8 (ipv6) are = larger than columns 9 (ipv4) and 10 (ipv6) showing that dual egress = instead of egress and ingress effective upload increases by < 10 Mbps = (while download and latency stay unaffected). That is not bad, but also = does not look like the IFB is the cost driver in sqm-scripts, or does = it? Also as a corollary of the data I would say, my old interpretation = that we hit a limit at ~70Mbps combined traffic might not be correct in = that ingress and egress might carry slightly different costs, but then = thins difference is not going to make a wndr punch way above its weight=85= >>=20 >> Best Regards >> Sebastian >>=20 >>=20 >>=20 >>=20 >> On Mar 23, 2015, at 17:09 , Sebastian Moeller = wrote: >>=20 >>> Hi Jonathan, >>>=20 >>> On Mar 23, 2015, at 14:43 , Jonathan Morton = wrote: >>>=20 >>>>=20 >>>>> On 23 Mar, 2015, at 08:09, Sebastian Moeller = wrote: >>>>>=20 >>>>> It obviously degrade local performance of se00 and hence be not a = true solution unless one is happy to fully dedicate a box as shaper ;) >>>>=20 >>>> Dedicating a box as a router/shaper isn=92t so much of a problem, = but shaping traffic between wired and wireless - and sharing the = incoming WAN bandwidth between them, too - is. outer >>>=20 >>> Exactly the sentiment I had, but less terse and actually = understandable ;) >>>=20 >>>> It=92s a valid test, though, for this particular purpose. >>>=20 >>> Once I get around to test it, I should b able to share some = numbers=85 >>>=20 >>> Best Regards >>> Sebastian >>>=20 >>>>=20 >>>> - Jonathan Morton >>>>=20 >>>=20 >>> _______________________________________________ >>> Cerowrt-devel mailing list >>> Cerowrt-devel@lists.bufferbloat.net >>> https://lists.bufferbloat.net/listinfo/cerowrt-devel >>=20 >>=20 >> _______________________________________________ >> Cerowrt-devel mailing list >> Cerowrt-devel@lists.bufferbloat.net >> https://lists.bufferbloat.net/listinfo/cerowrt-devel >>=20 >=20 >=20 >=20 > --=20 > Dave T=E4ht > Let's make wifi fast, less jittery and reliable again! >=20 > https://plus.google.com/u/0/107942175615993706558/posts/TVX3o84jjmb