From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from tuna.sandelman.ca (unknown [IPv6:2607:f0b0:f:3:216:3eff:fe7c:d1f3]) by huchra.bufferbloat.net (Postfix) with ESMTP id D7AAF21F17B; Mon, 26 Nov 2012 07:38:59 -0800 (PST) Received: from obiwan.sandelman.ca (unknown [IPv6:2607:f0b0:f:2::247]) by tuna.sandelman.ca (Postfix) with ESMTP id CFCD72016D; Mon, 26 Nov 2012 10:40:43 -0500 (EST) Received: by obiwan.sandelman.ca (Postfix, from userid 179) id 3353F63A8E; Mon, 26 Nov 2012 10:38:33 -0500 (EST) Received: from obiwan.sandelman.ca (localhost [127.0.0.1]) by obiwan.sandelman.ca (Postfix) with ESMTP id 25DED63A8C; Mon, 26 Nov 2012 10:38:33 -0500 (EST) From: Michael Richardson To: dpreed@reed.com In-Reply-To: <1353942251.571510886@apps.rackspace.com> References: <20121125232034.GF24680@merlins.org> <31933.1353939756@obiwan.sandelman.ca> <1353942251.571510886@apps.rackspace.com> X-Mailer: MH-E 8.3; nmh 1.3-dev; XEmacs 21.4 (patch 22) X-Face: $\n1pF)h^`}$H>Hk{L"x@)JS7<%Az}5RyS@k9X%29-lHB$Ti.V>2bi.~ehC0; <'$9xN5Ub# z!G,p`nR&p7Fz@^UXIn156S8.~^@MJ*mMsD7=QFeq%AL4m Sender: mcr@obiwan.sandelman.ca Cc: cerowrt-users@lists.bufferbloat.net, cerowrt-devel@lists.bufferbloat.net Subject: Re: [Cerowrt-devel] [Cerowrt-users] QOS settings vs speedboost and random bandwidth 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, 26 Nov 2012 15:39:00 -0000 --=-=-= Content-Transfer-Encoding: quoted-printable >>>>> "dpreed" =3D=3D dpreed writes: dpreed> You can use a small fraction of the capacity of the cable dpreed> uplink path to measure its queueing delay dynamically, and dpreed> when it gets longer than latency*"expected bitrate", reduce dpreed> "expected bitrate".=20 =20 dpreed> You want to do this *as quickly as possible*, so what you do dpreed> is insert a "link monitor" task in the driver that sends dpreed> tiny probe packets addressed to the nearest "loopback point" dpreed> you can find/create on the other side, and measure the RTT. dpreed> You can use, for example, the technique used by traceroute, dpreed> which is to set the hop count to the smallest number that dpreed> causes a return ICMP packet to be sent, and send one of dpreed> those periodically.=20 As I understand it, you can do this with 802.1ag http://en.wikipedia.org/wiki/IEEE_802.1ag,=20 with the Loop-back frames as well. Whether or not any of this is enabled on typical broadband networks, I have no idea. dpreed> I used this specific technique to cause my uplink queue to dpreed> move back into my router, where I could manage it. You can dpreed> also use it for the downlink queue measurement, but it dpreed> doesn't move the queue into the router smoothly, instead you dpreed> have to drop/ECN-mark the IP frames coming in.=20 dpreed> This can all be done between the IP layer and layer 2. dpreed> Since it exploits speedboost better, it might be worth dpreed> adding as an option to cerowrt, so you don't have to set a dpreed> speed limit explicitly when you have a single connection to dpreed> the public Internet.=20 wow, this would be awesome... code?? =2D-=20 ] He who is tired of Weird Al is tired of life! | firewall= s [ ] Michael Richardson, Sandelman Software Works, Ottawa, ON |net archit= ect[ ] mcr@sandelman.ottawa.on.ca http://www.sandelman.ottawa.on.ca/ |device dri= ver[ Kyoto Plus: watch the video then sign the petition.=20 --=-=-= Content-Type: application/pgp-signature -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.12 (GNU/Linux) iQCVAwUAULOM+YqHRg3pndX9AQLPugQA7ZBMqRx10NC9UEsdbJDcT/6ZURc+8eOU jnjvNuyIhfyyUuTAflUDrIafzi0zjXHR1nLPSrOvWIPJ2xQktMsX4zyhE9Y4i+UF DkgUATNJ2vABLaGSIWofru2y3jiNrGuHWVRdCB8VyHO5YkwnKQf2kM1H1j7uIY5P jDwpYlzDJCA= =pSkg -----END PGP SIGNATURE----- --=-=-=--