From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from bifrost.lang.hm (mail.lang.hm [64.81.33.126]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client did not present a certificate) by huchra.bufferbloat.net (Postfix) with ESMTPS id 836DA21F616; Fri, 25 Jul 2014 16:30:30 -0700 (PDT) Received: from asgard.lang.hm (asgard.lang.hm [10.0.0.100]) by bifrost.lang.hm (8.13.4/8.13.4/Debian-3) with ESMTP id s6PNUT3D006434; Fri, 25 Jul 2014 16:30:29 -0700 Date: Fri, 25 Jul 2014 16:30:29 -0700 (PDT) From: David Lang X-X-Sender: dlang@asgard.lang.hm To: Valdis.Kletnieks@vt.edu In-Reply-To: <25037.1406327367@turing-police.cc.vt.edu> Message-ID: References: <03292B76-5273-4912-BB18-90E95C16A9F5@pnsol.com> <66FF8435-C8A5-4596-B43A-EC12D537D49E@gmx.de> <25037.1406327367@turing-police.cc.vt.edu> User-Agent: Alpine 2.02 (DEB 1266 2009-07-14) MIME-Version: 1.0 Content-Type: TEXT/PLAIN; charset=US-ASCII; format=flowed Cc: Neil Davies , cerowrt-devel , bloat Subject: Re: [Cerowrt-devel] [Bloat] Check out www.speedof.me - no Flash 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, 25 Jul 2014 23:30:30 -0000 On Fri, 25 Jul 2014, Valdis.Kletnieks@vt.edu wrote: > On Fri, 25 Jul 2014 14:20:53 -0700, David Lang said: > >> cost of bandwidth for this is just something to get someone to pay for (ideally >> someone with tons of bandwidth already who won't notice this sort of test, even >> if there are a few going on at once.) > > Ask U of Wisconsin how that worked out for them when Netgear shipped some > new boxes.... > > http://en.wikipedia.org/wiki/NTP_server_misuse_and_abuse#NETGEAR_and_the_University_of_Wisconsin.E2.80.93Madison > > It's one thing to come up with a solution that works for the 300 (total wild guess) people > on this list. But to be useful for field deployable, it really needs to be able > to handle a "every Comcast customer in a major metro area", because we *do* > want this stuff to work well when this makes it into the CPE that Comcast > gives every new customer, right? :) the key thing here is to stagger the work. Don't have every device do the test immediatly at startup. As you noted, that will collapse as they all start up at once. Have them operate from their saved stats and test at (largish) random offsets. ideally, have this test be against an ANYCAST address, so that the ISP can run a copy internally without having to reconfigure the clients. David Lang