NNSquad - Network Neutrality Squad
[ NNSquad ] Re: Routers deal with IP information
Dr. Reed, I don't believe I have ever spoke to you in a nasty or disrespectful manner, so such a personal attack is uncalled for. Let's keep this civilized. You seem to be making contradictory statements here because on the one hand you make a statement that maybe routers (yes that does include those boxes with NAT support because surely you recognize that nearly all routers support NAT) do avoid dropping UDP packets but you categorically state that it is "utterly" false. Now which is it? Is it maybe or utterly false? As for streaming video on the Internet, the bulk of it is transmitted using HTTP TCP. If you need confirmation, just put a sniffer on YouTube. Still, it's unclear what point you're trying to make saying that RTP streams are "designed" to handle packet drops and how that's relevant to the discussion of whether UDP is dropped less than TCP by routers in general. The way to settle this scientifically is to verify whether routers with congested links will drop UDP as much as TCP or whether it will favor dropping TCP packets. Run 8 Mbps of fixed UDP traffic over a 100 Mbps FastEthernet link to a router with a 10 Mbps Ethernet link on the other end (9 mbps effective throughput) and then try to run a single-flow TCP file transfer over the same bottle neck and see if the TCP stream will go faster than 1 or 2 Mbps and force UDP packets to drop. Then measure if all of the UDP traffic arrived on the other end of if it simply kept charging forward at 8 Mbps despite losing packets. If I have time over the Christmas holiday, I'll try to run this test. If anyone else is up for the challenge, go for it. George Ou -----Original Message----- From: nnsquad-bounces+george_ou=lanarchitect.net@nnsquad.org [mailto:nnsquad-bounces+george_ou=lanarchitect.net@nnsquad.org] On Behalf Of David P. Reed Sent: Tuesday, December 02, 2008 6:43 PM To: nnsquad@nnsquad.org Subject: [ NNSquad ] Routers deal with IP information One more correction of a complete boner by "expert" George Ou: > > Because UDP end-points don't respond to dropped packets the way TCP > end-points do, most routers leave the UDP traffic alone when there is > congestion and they only drop TCP packets which respond by cutting their > flow rate in half. This is UTTERLY false. Perhaps if Mr. Ou worked for a router company instead of making up fantasies in his own mind, he'd understand this. (it may be that "NAT boxes" do such things, and are often called "home routers", but routers do not - the generality of the statement is awesome in its ignorance). > Besides, there's no point in forcing a 30 kbps gaming > UDP data stream to slow down because it's already very slow and it's only > fair to ask the bursty applications that have no bandwidth limit operating > at 100 to 500 times faster to take a hit on bandwidth. > Like most people who are not on solid ground, he has to give details of "why" his fantasy must be true. > Now here comes BitTorrent with their well-meaning but problematic change to > take a bulk file transfer protocol and stick it on UDP. So instead of tiny > 30-80 Kbps VoIP and online gaming UDP streams, we're now looking at multiple > UDP streams operating at 15,000 Kbps per user. Now we're forcing the > network operator to change their routers inside the Internet to start > managing UDP flows by dropping UDP packets whenever a link is congested. > > > RTP streams such as streaming video are *designed* to handle dropped packets. That's the one of the main reasons we invented UDP - in particular, Danny Cohen, who created the field of packetized speech over the Internet pretty much from the whole cloth, taught me why. Ou is close to impeaching his credibility here.