ABSTRACT
Replicating content across a geographically distributed set of servers and redirecting clients to the closest server in terms of latency has emerged as a common paradigm for improving client performance. In this paper, we analyze latencies measured from servers in Google's content distribution network (CDN) to clients all across the Internet to study the effectiveness of latency-based server selection. Our main result is that redirecting every client to the server with least latency does not suffice to optimize client latencies. First, even though most clients are served by a geographically nearby CDN node, a sizeable fraction of experience latencies several tens of milliseconds higher than other in the same region. Second, we find that queueing delays often override the benefits of a client interacting with a nearby server.
To help the administrators of Google's CDN cope with these problems, we have built a system called WhyHigh. First, WhyHigh measures client latencies across all nodes in the CDN and correlates measurements to identify the prefixes affected by inflated latencies. Second, since clients in several thousand prefixes have poor latencies, WhyHigh prioritizes problems based on the impact that solving them would have, e.g., by identifying either an AS path common to several inflated prefixes or a CDN node where path inflation is widespread. Finally, WhyHigh diagnoses the causes for inflated latencies using active measurements such as traceroutes and pings, in combination with datasets such as BGP paths and flow records. Typical causes discovered include lack of peering, routing misconfigurations, and side-effects of traffic engineering. We have used WhyHigh to diagnose several instances of inflated latencies, and our efforts over the course of a year have significantly helped improve the performance offered to clients by Google's CDN.
- Akamai, Inc. home page. http://www.akamai.com.Google Scholar
- D. G. Andersen, H. Balakrishnan, M. F. Kaashoek, and R. Morris. Resilient overlay networks. In SOSP, 2001. Google ScholarDigital Library
- N. Cardwell, S. Savage, and T. Anderson. Modeling TCP latency. In INFOCOM, 2000.Google ScholarCross Ref
- M. Dischinger, A. Haeberlen, K. P. Gummadi, and S. Saroiu. Characterizing residential broadband networks. In IMC, 2007. Google ScholarDigital Library
- A. Feldmann, O. Maennel, Z. M. Mao, A. Berger, and B. Maggs. Locating Internet routing instabilities. In SIGCOMM, 2004. Google ScholarDigital Library
- M. J. Freedman, E. Freudenthal, and D. Mazières. Democratizing content publication with Coral. In NSDI, 2004. Google ScholarDigital Library
- M. J. Freedman, K. Lakshminarayanan, and D. Mazieres. OASIS: Anycast for any service. In NSDI, 2006. Google ScholarDigital Library
- Y. He, M. Faloutsos, S. Krishnamurthy, and B. Huffaker. On routing asymmetry in the Internet. In Autonomic Networks Symposium in Globecom, 2005.Google Scholar
- C. Huang, A. Wang, J. Li, and K. W. Ross. Measuring and evaluating large-scale CDNs. In IMC, 2008. Google Scholar
- E. Katz-Bassett, J. P. John, A. Krishnamurthy, D. Wetherall, T. Anderson, and Y. Chawathe. Towards IP geolocation using delay and topology measurements. In IMC, 2006. Google ScholarDigital Library
- E. Katz-Bassett, H. V. Madhyastha, J. P. John, A. Krishnamurthy, and T. Anderson. Studying black holes in the Internet with Hubble. In NSDI, 2008. Google ScholarDigital Library
- H. V. Madhyastha, T. Isdal, M. Piatek, C. Dixon, T. Anderson, A. Krishnamurthy, and A. Venkataramani. iPlane: An information plane for distributed services. In OSDI, 2006. Google ScholarDigital Library
- H. V. Madhyastha, E. Katz-Bassett, T. Anderson, A. Krishnamurthy, and A. Venkataramani. iPlane Nano: Path prediction for peer-to-peer applications. In NSDI, 2009. Google ScholarDigital Library
- R. Mahajan. Practical and Efficient Internet Routing with Competing Interests. PhD thesis, University of Washington, 2005. Google ScholarDigital Library
- R. Mahajan, M. Zhang, L. Poole, and V. Pai. Uncovering performance differences among backbone ISPs with Netdiff. In NSDI, 2008. Google ScholarDigital Library
- V. Paxson. End-to-end routing behavior in the Internet. ToN, 1997. Google ScholarDigital Library
- Reverse traceroute. http://www.cs.washington.edu/research/networking/astronomy/reverse-traceroute.html.Google Scholar
- S. Savage, T. Anderson, A. Aggarwal, D. Becker, N. Cardwell, A. Collins, E. Hoffman, J. Snell, A. Vahdat, G. Voelker, and J. Zahorjan. Detour: a case for informed Internet routing and transport. IEEE Micro, 1999. Google ScholarDigital Library
- N. Spring, R. Mahajan, and T. Anderson. Quantifying the causes of path inflation. In SIGCOMM, 2003. Google ScholarDigital Library
- N. Spring, R. Mahajan, D. Wetherall, and T. Anderson. Measuring ISP topologies with Rocketfuel. ToN, 2004. Google ScholarDigital Library
- M. Tariq, A. Zeitoun, V. Valancius, N. Feamster, and M. Ammar. Answering what-if deployment and configuration questions with WISE. In SIGCOMM, 2008. Google ScholarDigital Library
- J. Wu, Z. M. Mao, and J. R. J. Wang. Finding a needle in a haystack: Pinpointing significant BGP routing changes in an IP network. In NSDI, 2005. Google ScholarDigital Library
- M. Zhang, C. Zhang, V. Pai, L. Peterson, and R. Wang. PlanetSeer: Internet path failure monitoring and characterization in wide-area services. In OSDI, 2004. Google ScholarDigital Library
- Y. Zhang, Z. M. Mao, and M. Zhang. Effective diagnosis of routing disruptions from end systems. In NSDI, 2008. Google ScholarDigital Library
- Y. Zhang, V. Paxson, and S. Shenker. The stationarity of Internet path properties: Routing, loss, and throughput. Technical report, ACIRI, 2000.Google Scholar
Index Terms
- Moving beyond end-to-end path information to optimize CDN performance
Recommendations
Analyzing the Performance of an Anycast CDN
IMC '15: Proceedings of the 2015 Internet Measurement ConferenceContent delivery networks must balance a number of trade-offs when deciding how to direct a client to a CDN server. Whereas DNS-based redirection requires a complex global traffic manager, anycast depends on BGP to direct a client to a CDN front-end. ...
End-User Mapping: Next Generation Request Routing for Content Delivery
SIGCOMM'15Content Delivery Networks (CDNs) deliver much of the world's web, video, and application content on the Internet today. A key component of a CDN is the mapping system that uses the DNS protocol to route each client's request to a ``proximal'' server ...
End-User Mapping: Next Generation Request Routing for Content Delivery
SIGCOMM '15: Proceedings of the 2015 ACM Conference on Special Interest Group on Data CommunicationContent Delivery Networks (CDNs) deliver much of the world's web, video, and application content on the Internet today. A key component of a CDN is the mapping system that uses the DNS protocol to route each client's request to a ``proximal'' server ...
Comments