From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-qk0-x236.google.com (mail-qk0-x236.google.com [IPv6:2607:f8b0:400d:c09::236]) (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 A47753B2B6 for ; Tue, 16 Feb 2016 14:27:19 -0500 (EST) Received: by mail-qk0-x236.google.com with SMTP id s68so70910380qkh.3 for ; Tue, 16 Feb 2016 11:27:19 -0800 (PST) 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=xYiiW2eC2iVJrHVD+XNXTDluNAF5GsP6erkF2Jq0T3Y=; b=Dfk031h+FcG9sec6ZaW+cKlKvl86CYuiGhffvqe/qslkNUhGH5TkCSsTHoqmo6VyVr JmRD7r1+J/i3ai9IDUKT4X1/p9IXzpaPiWMU1oM+08EAL1/DzyjTGmxMXWQ32duel0wO iBRlN/Axk08JfcjBUI+ONVud+I7FlfToZv2y696GzSg31KenB7EfRKKdyVcpENPJv8nx t19Jmb9zDL0fPrI3OQuEwFNAjBXF4aHNkGyK/MMqSY/dR6pL+3HQTwc83EHER5g38Z80 MlAj9r8ow3t9ndNGzvDtP9s0tEXGxaUioc4DWq+dbhj0ZsAIkJL0Eq3SjtXI8GiApBX3 DqGA== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:content-type:mime-version:subject:from :in-reply-to:date:cc:content-transfer-encoding:message-id:references :to; bh=xYiiW2eC2iVJrHVD+XNXTDluNAF5GsP6erkF2Jq0T3Y=; b=LN36UNNnQtCUvZ7wgsipA24ZxQf+aVUaqDDtpCyouAiNvtDgI1aJO7THsnGSupRCIg gLNJF09MJ3qrm8lVMqxv1sMVbJ1ESPYFYlx/SvZmCLBVNOM8Wp53eDACbtMbj6sEmFpI GeZ9cKDu1ndKGBesjQJmB8xO1RDAOU4tDWmDovmmHxpemsX4IakFHbXZR5684b/ucRJp p3L4yuiJsUMQwHI23/V5RjAmt63F9+mgk7OBD2n2GeEhUSlEH2KP0zTgCdiaq42ZPxWQ FrNMSRSoj5E/aUU6hg0R8nD2G/8GHIesaz6/fLGSjZOGbV0/wLFc7oZvBDljtZJLhmjg 7XVQ== X-Gm-Message-State: AG10YORJS5RYZrQxAuArvu8+nqhHvXICSW6fVh9mdPCx3r8pie0gRs3gRLcbVv1PmmHg/w== X-Received: by 10.55.74.209 with SMTP id x200mr29324387qka.106.1455650839220; Tue, 16 Feb 2016 11:27:19 -0800 (PST) Received: from [10.248.145.211] (mobile-166-171-057-019.mycingular.net. [166.171.57.19]) by smtp.gmail.com with ESMTPSA id g6sm13804539qgd.5.2016.02.16.11.27.18 (version=TLSv1/SSLv3 cipher=OTHER); Tue, 16 Feb 2016 11:27:18 -0800 (PST) Content-Type: text/plain; charset=us-ascii Mime-Version: 1.0 (1.0) From: John Klimek X-Mailer: iPad Mail (13C75) In-Reply-To: Date: Tue, 16 Feb 2016 14:27:18 -0500 Cc: bloat Content-Transfer-Encoding: quoted-printable Message-Id: References: <86929A3A-5095-4506-8897-03EA5DABAF90@gmail.com> To: Dave Taht Subject: Re: [Bloat] fq_codel settings for 25/3 connection? X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.20 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Tue, 16 Feb 2016 19:27:19 -0000 Thanks very much for the information! (I've been reading 20+ page threads o= n Ubiquity's forum looking for messages that you've posted) I'm going to be testing an EdgeRouter X which doesn't support hardware accel= eration so I don't think I have to worry about TCP offload (?). (I'd like t= o use my existing x86 hardware but I can't find a solid router OS that I lik= e) I'll also go ahead and enable fq_codel on my downstream and hope for the bes= t. Thanks again, John > On Feb 16, 2016, at 2:19 PM, Dave Taht wrote: >=20 >> On Tue, Feb 16, 2016 at 10:06 AM, John Klimek wrote: >> Does anybody have any suggested quantum/target values for a cable modem c= onnection of 25/3? (25 Mbps down, 3 Mbps up) >=20 > I would use a quantum 300 for the up. There is no need to fiddle with > the target values below 2.5mbits. >=20 > The edgerouter has issues with tcp offloads enabled. If you are not > using the other ports as routed ports, you can disable gro offloads on > all ports for lower latency at a huge cost in local bandwidth (this is > something that cake will fix if we can get ubnt to ship it one day. > http://www.bufferbloat.net/projects/codel/wiki/CakeTechnical ) >=20 >=20 >>=20 >> It looks like the defaults for Ubiquity EdgeRouter should work but I'm no= t sure if I can achieve better performance by tuning anything? >=20 > Make a change, measure with a good benchmark like flent's rrul test. >=20 >> Also, should I enable fq_codel on my downstream or only my upstream? >=20 > Both are severely overbuffered on cablemodems and CMTSes running at this s= peed. >=20 > http://burntchrome.blogspot.com/2014/05/fixing-bufferbloat-on-comcasts-bla= st.html >=20 > https://wiki.openwrt.org/doc/howto/sqm >=20 >=20 >> Thanks! >>=20 >> - John >> _______________________________________________ >> Bloat mailing list >> Bloat@lists.bufferbloat.net >> https://lists.bufferbloat.net/listinfo/bloat