Sally Floyd: Questions

• WHERE IS THE CONGESTION IN THE INTERNET?
  What do we know about congested links in the Internet? E.g., where is the congestion in the Internet? On access links to the home or web server? Peering points? Transoceanic links? Wireless and satellite links? Is the congestion on links with high levels of statistical multiplexing, or on links with low levels of statistical multiplexing? How have the congestion points moved around as the Internet has changed over the last ten years? Where do we expect the congestion to be in the future, if anywhere?

  Answers.

• END-TO-END DELAY (HOPS, NUMBER OF ASes) OF PACKETS?
  For packets on a particular link, each packet could be assigned an estimated end-to-end delay (one-way or round-trip), a number of ASes for the end-to-end path, etc, based on the IP source and destination addresses for that packet. For packets on a particular link, what can we say about the distribution of end-to-end delay, or of the number of hops traversed, or the number of ASes traversed, or number of continents traversed, or (this is harder) the number of congested links traversed?

  [Example: For link X, can we say that most packets/bytes stay on that continent? Or that most packets have a minimum end-to-end delay of at least S seconds? Or that most packets on that link during this period of time traverse more than one congested link on their path from source to destination?]

  For round-trip time measurements greater than 500 ms, to what extent is this delay due to queueing delay? to routing problems? to delay at the end-node?

  Answers. Quick summary, so far: A range of more than 10:1 in round-trip times seems common, but with most (85%, in one case) of the connections having round-trip times between 15 and 500 ms.

• PERIODS OF EXTREME CONGESTION AT A ROUTER?
  For those routers in the network that do occationally experience congestion, how can we characterize their rare periods of *extreme* congestion (defining extreme congestion, say, as packet drop rates above 5%)? How frequently to these periods of extreme congestion occur, and how long do they last? What fraction can be attributed to flash crowds? to Denial of Service attacks? to fiber cuts or other routing changes?

• MISBEHAVING FLOWS:
  Does anyone have any measurement data on the presence or behavior of high-bandwidth flows in the Internet that are misbehaving, that is, that are not using conformant end-to-end congestion control?

• SACK TCP DEPLOYMENT:
  What fraction of the bytes/packets/TCP-flows in the Internet are SACK-capable?

  Answers. Quick summary: Deployment is increasing rapidly, both for web browsers and for web servers.
  

• NEW-RENO TCP DEPLOYMENT:
  What fraction of the non-SACK TCP flows in the Internet use NewReno instead of Reno congestion control mechanisms (and thereby avoid unnecessary retransmit timeouts when multiple packets are dropped from a window of data)?

  Answers. Quick summary: There is a significant deployment of NewReno TCP, as compared to Reno or Tahoe TCP.
  

• RED DEPLOYMENT:
  What fraction of the routers in the Internet use some form of active queue management? And what are the reports from operational experiences?

  * The RED Web Page already has pointers to Curtis Villamizar's 1994 paper on "High Performance TCP in ANSNET", and to Sean Doran's web page showing RED turned on at a site at Ebone.
  * WRED is enabled on Cisco GSRs on overloaded links at AS1 (Genuity), to reduce queueing delay. Experience has been positive. (Reported by Derek Fonda of Genuity, October 2000.)

• DIAMETER OF THE INTERNET:
  If anyone is looking for measurements about the "diameter of the Internet", in terms of the minimum acceptable initial TTL for IP, they could contact Richard Wendland <richard@netcraft.com> at Netcraft.

• What was your favorite paper rejected by a conference or journal, so far?