ABSTRACT
We introduce and demonstrate the utility of a method to localize and quantify inter-domain congestion in the Internet. Our Time Sequence Latency Probes (TSLP) method depends on two facts: Internet traffic patterns are typically diurnal, and queues increase packet delay through a router during periods of adjacent link congestion. Repeated round trip delay measurements from a single test point to the two edges of a congested link will show sustained increased latency to the far (but not to the near) side of the link, a delay pattern that differs from the typical diurnal pattern of an uncongested link. We describe our technique and its surprising potential,carefully analyze the biggest challenge with the methodology (interdomain router-level topology inference), describe other less severe challenges, and present initial results that are sufficiently promising to motivate further attention to overcoming the challenges.
- R. Andrews and S. Higginbotham. YouTube sucks on French ISP Free, and French regulators want to know why. GigaOm, 2013.Google Scholar
- S. Bauer, D. Clark, and W. Lehr. Understanding Broadband Speed Measurements. In TPRC, 2010.Google Scholar
- J. Brodkin. Time Warner, net neutrality foes cry foul over Netflix Super HD demands, 2013.Google Scholar
- J. Brodkin. Why YouTube buffers: The secret deals that make-and break-online video. Ars Technica, July 2013.Google Scholar
- S. Buckley. Cogent and Orange France fight over interconnection issues. Fierce Telecom, 2011.Google Scholar
- S. Buckley. France Telecom and Google entangled in peering fight. Fierce Telecom, 2013.Google Scholar
- K. L. Calvert, W. K. Edwards, N. Feamster, R. E. Grinter, Y. Deng, and X. Zhou. Instrumenting home networks. ACM SIGCOMM CCR, 41(1), Jan. 2011. Google ScholarDigital Library
- K. Chen, D. R. Choffnes, R. Potharaju, Y. Chen, F. E. Bustamante, D. Pei, and Y. Zhao. Where the sidewalk ends: Extending the Internet AS graph using traceroutes from P2P users. In ACM CoNEXT, Dec. 2009. Google ScholarDigital Library
- Y. Chen, S. Jain, V. K. Adhikari, and Z.-L. Zhang. Characterizing roles of front-end servers in end-to-end performance of dynamic content distribution. In ACM SIGCOMM IMC, Nov. 2011. Google ScholarDigital Library
- S. Cowley. ISP spat blacks out Net connections. InfoWorld, 2005.Google Scholar
- L. DiCioccio, R. Teixeira, M. May, and C. Kreibich. Probe and Pray: Using UPnP for Home Network Measurements. In PAM, pages 96--105, 2012. Google ScholarDigital Library
- M. Dischinger, A. Haeberlen, K. P. Gummadi, and S. Saroiu. Characterizing residential broadband networks. In ACM SIGCOMM IMC, Oct. 2007. Google ScholarDigital Library
- J. Engebretson. Level 3/Comcast dispute revives eyeball vs. content debate, Nov. 2010.Google Scholar
- J. Engebretson. Behind the Level 3-Comcast peering settlement, July 2013. http://www.telecompetitor.com/behind-the-level-3-comcast-peering-settlement/.Google Scholar
- P. Faratin, D. Clark, S. Bauer, W. Lehr, P. Gilmore, and A. Berger. The growing complexity of Internet interconnection. Communications and Strategies, (72):51--71, 2008.Google Scholar
- FCC. Measuring Broadband America, 2011. http://www.fcc.gov/measuring-broadband-america.Google Scholar
- S. Floyd and V. Jacobson. Random early detection (RED) gateways for congestion avoidance. IEEE/ACM Transactions on Networking, 1(4):397--413, 1993. Google ScholarDigital Library
- D. Genin and J. Splett. Where in the Internet is congestion?, 2013. http://arxiv.org/abs/1307.3696.Google Scholar
- B. Huffaker, A. Dhamdhere, M. Fomenkov, and kc claffy. Toward topology dualism: Improving the accuracy of AS annotations for routers. In PAM, Apr. 2010. Google ScholarDigital Library
- Y. Hyun, B. Huffaker, D. Andersen, M. Luckie, and K. C. Claffy. The IPv4 Routed /24 Topology Dataset, 2014. http://www.caida.org/data/active/ipv4_routed_24_topology_dataset.xml.Google Scholar
- M. Jain and C. Dovrolis. End-to-end available bandwidth: Measurement methodology, dynamics, and relation with TCP throughput. IEEE/ACM Transactions on Networking, 11(4):537--549, 2003. Google ScholarDigital Library
- E. Katz-Bassett, H. V. Madhyastha, V. K. Adhikari, C. Scott, J. Sherry, P. vas Wesep, T. Anderson, and A. Krishnamurthy. Reverse traceroute. In USENIX NSDI, Apr. 2010. Google ScholarDigital Library
- C. Kreibich, N. Weaver, B. Nechaev, and V. Paxson. Netalyzr: Illuminating the Edge Network. In ACM SIGCOMM IMC, 2010. Google ScholarDigital Library
- J. Liu and M. Crovella. Using loss pairs to discover network properties. In ACM SIGCOMM IMW, Nov. 2001. Google ScholarDigital Library
- M. Luckie, B. Huffaker, A. Dhamdhere, V. Giotsas, and k claffy. AS relationships, customer cones, and validation. In ACM SIGCOMM IMC, 2013. Google ScholarDigital Library
- M. Luckie and kc claffy. A second look at detecting third-party addresses in traceroute traces with the IP timestamp option. In PAM, 2014.Google Scholar
- R. Mahajan, N. Spring, D. Wetherall, and T. Anderson. User-level Internet path diagnosis. In ACM SOSP, Oct. 2003. Google ScholarDigital Library
- A. A. Mahimkar, H. H. Song, Z. Ge, A. Shaikh, J. Wang, J. Yates, Y. Zhang, and J. Emmons. Detecting the performance impact of upgrades in large operational networks. In ACM SIGCOMM, Aug. 2010. Google ScholarDigital Library
- Z. M. Mao, D. Johnson, J. Rexford, J. Wang, and R. Katz. Scalable and accurate identification of AS-Level forwarding paths. In IEEE INFOCOM, Mar. 2004.Google Scholar
- M. Mathis. Model Based Bulk Performance Metrics. http://datatracker.ietf.org/doc/draft-ietf-ippm-model-based-metrics/, Oct 2013.Google Scholar
- K. Nichols and V. Jacobson. Controlling queue delay. ACM Queue, 10(5), May 2012. Google ScholarDigital Library
- M. Ricknas. Sprint-Cogent dispute puts small rip in fabric of Internet. PCWorld, Oct. 2008.Google Scholar
- J. Sherry, E. Katz-Bassett, M. Pimenova, H. V. Madhyastha, T. Anderson, and A. Krishnamurthy. Resolving IP aliases with prespecified timestamps. In ACM SIGCOMM IMC, Nov. 2010. Google ScholarDigital Library
- S. Sundaresan, W. de Donato, N. Feamster, R. Teixeira, S. Crawford, and A. Pescapè. Broadband Internet performance: A view from the gateway. In ACM SIGCOMM, 2011. Google ScholarDigital Library
- M. Taylor. Observations of an Internet Middleman, May 2014. http://blog.level3.com/global-connectivity/observations-internet-middleman/.Google Scholar
- W. A. Taylor. Change-point analysis: A powerful new tool for detecting changes, 2000. http://www.variation.com/cpa/tech/changepoint.html.Google Scholar
- Verizon. Unbalanced peering, and the real story behind the Verizon/Cogent dispute, June 2013. http://publicpolicy.verizon.com/blog/.Google Scholar
- B. Zhang, J. Bi, Y. Wang, Y. Zhang, and J. Wu. Refining IP-to-AS mappings for AS-level traceroute. In IEEE ICCCN, July 2013.Google ScholarCross Ref
- Y. Zhang, R. Oliveira, H. Zhang, and L. Zhang. Quantifying the pitfalls of traceroute in AS connectivity inference. In PAM, 2010. Google ScholarDigital Library
Index Terms
- Challenges in Inferring Internet Interdomain Congestion
Recommendations
Challenges in inferring internet congestion using throughput measurements
IMC '17: Proceedings of the 2017 Internet Measurement ConferenceWe revisit the use of crowdsourced throughput measurements to infer and localize congestion on end-to-end paths, with particular focus on points of interconnections between ISPs. We analyze three challenges with this approach. First, accurately ...
Inferring persistent interdomain congestion
SIGCOMM '18: Proceedings of the 2018 Conference of the ACM Special Interest Group on Data CommunicationThere is significant interest in the technical and policy communities regarding the extent, scope, and consumer harm of persistent interdomain congestion. We provide empirical grounding for discussions of interdomain congestion by developing a system ...
Avoiding congestion collapse on the internet using TCP Tunnels
This paper discusses the application of TCP tunnels on the Internet and how Internet traffic can benefit from the congestion control mechanism of the tunnels. Primarily, we show the TCP tunnels offer TCP-friendly flows protection from TCP-unfriendly ...
Comments