From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from plane.gmane.org (plane.gmane.org [80.91.229.3]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (Client did not present a certificate) by huchra.bufferbloat.net (Postfix) with ESMTPS id C7B4821F3F2 for ; Mon, 18 Aug 2014 12:19:59 -0700 (PDT) Received: from list by plane.gmane.org with local (Exim 4.69) (envelope-from ) id 1XJSTD-0001i7-Rx for cerowrt-devel@lists.bufferbloat.net; Mon, 18 Aug 2014 21:19:55 +0200 Received: from 32.97.110.56 ([32.97.110.56]) by main.gmane.org with esmtp (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Mon, 18 Aug 2014 21:19:55 +0200 Received: from wmf by 32.97.110.56 with local (Gmexim 0.1 (Debian)) id 1AlnuQ-0007hv-00 for ; Mon, 18 Aug 2014 21:19:55 +0200 X-Injected-Via-Gmane: http://gmane.org/ To: cerowrt-devel@lists.bufferbloat.net From: Wes Felter Date: Mon, 18 Aug 2014 14:19:44 -0500 Message-ID: References: <20140815205123.GB30452@thyrsus.com> Mime-Version: 1.0 Content-Type: text/plain; charset=UTF-8; format=flowed Content-Transfer-Encoding: 7bit X-Complaints-To: usenet@ger.gmane.org X-Gmane-NNTP-Posting-Host: 32.97.110.56 User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.9; rv:17.0) Gecko/20130801 Thunderbird/17.0.8 In-Reply-To: Cc: bloat@lists.bufferbloat.net Subject: Re: [Cerowrt-devel] [Bloat] still trying to find hardware for the next generation worth hacking on 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: Mon, 18 Aug 2014 19:20:00 -0000 On 8/15/14, 4:02 PM, Dave Taht wrote: > one promising project is this one: https://www.turris.cz/en/ Huge kudos to the Turris project for designing a modern open router. But... Freescale is in the process of switching from PowerPC to ARM and other vendors are switching from MIPS to ARM. Maybe it's worth waiting a few months for ARM to save the trouble of switching again later. Many people here know this, but if you don't, a word of warning: These chips tend to have various accelerators that don't support CoDel. Turning off acceleration and using software AQM may reduce performance 10x compared to marketing numbers. If the marketing number is over 1 Gbps that may be fine, but as Dave said it's something that should be tested. Intel Avoton/Rangeley looks great but very expensive; boards are around $300 without radios, case or PSU. -- Wes Felter