From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-oa0-x22a.google.com (mail-oa0-x22a.google.com [IPv6:2607:f8b0:4003:c02::22a]) (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 E54A321F7FD; Fri, 15 Aug 2014 13:33:17 -0700 (PDT) Received: by mail-oa0-f42.google.com with SMTP id n16so2435093oag.29 for ; Fri, 15 Aug 2014 13:33:17 -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=x9OVyyGgAQ/y7Z2nAgbhLTTJOhNzvLLwZyZiuEJQaJs=; b=hvC7aL4+bvh8C7Yl29hUGY9ymfTTWVgpCjWkb6UqaWfUammA1MWOvIm4Nhrsrrymfm w7eMBWQNkK4wTI4AOJRIE2wtIpd2kVhDnKczk9KEjt7Xo2c4ZBUHLXaM0dkObveQN5lP NUlGVoOr0Xedpc0e92iSrsrYsvTvZ3nkOKIZ+sNKc9Kb5N8/VJIU9WbjI2MY+P1W6QvU /YwGZmOYbyRUBwct8wJ1NyF6WfYOcFqEGV4oCPzkv9agnvo34TkJ57oJ8IkvCyT3aVKX FWEqjGejtWvqxtg0N1FbecbMcRUe6gUQD4T2w783ichpW3lYCdM0Y6HxcVfe5tXaliDC 7mKg== MIME-Version: 1.0 X-Received: by 10.182.186.73 with SMTP id fi9mr23007647obc.0.1408134796953; Fri, 15 Aug 2014 13:33:16 -0700 (PDT) Received: by 10.202.93.69 with HTTP; Fri, 15 Aug 2014 13:33:16 -0700 (PDT) Date: Fri, 15 Aug 2014 13:33:16 -0700 Message-ID: From: Dave Taht To: bloat , "cerowrt-devel@lists.bufferbloat.net" Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable Subject: [Bloat] still trying to find hardware for the next generation worth hacking on X-BeenThere: bloat@lists.bufferbloat.net X-Mailman-Version: 2.1.13 Precedence: list List-Id: General list for discussing Bufferbloat List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Fri, 15 Aug 2014 20:33:18 -0000 I figure everyone has already seen this: http://burntchrome.blogspot.com/2014/05/fixing-bufferbloat-on-comcasts-blas= t.html But this is the best we can do. Above 50mbit, cero's current hardware (cpu designed in 1989) peaks out. We've done some testing on the slightly higher end edgerouter lite, and it can't keep up, either, above about 70mbit. The edgerouter pro does considerably better but costs considerably more. ivy bridge x86 boxes "just work" up to well past 300mbits... As cerowrt 3.10 is basically baked, it's time (finally!) to find a new chipset that everyone can work with, and move on to higher gateway bandwidths, and 802.11ac. For 2+ years now, we've been looking for better hardware than this... and I'd like to at least find something sooner that could run the SQM system at 105Mbit... I know we could just switch future development to intel hardware, and there are some promising arm based designs now out, and there have been a few suggestions here and on cerowrt-devel... At the moment, I'm thinking that instead of searching for a chipset, and board, that merely issuing an RFP with the requirements of this project and others associated with it, might find us a vendor willing to help, with something new coming off the line... would anyone be interested in helping write that? --=20 Dave T=C3=A4ht