Locality Prediction for Oblivious Clients

  • Kevin P. Shanahan
  • Michael J. Freedman
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3640)


To improve performance, large-scale Internet systems require clients to access nearby servers. While centralized systems can leverage static topology maps for rough network distances, fully-decentralized systems have turned to active probing and network coordinate algorithms to scalably predict inter-host latencies. Internet applications seeking immediate adoption, however, must inter-operate with unmodified clients running existing protocols such as HTTP and DNS.

This paper explores a variety of active probing algorithms for locality prediction. Upon receiving an external client request, peers within a decentralized system are able to quickly estimate nearby servers, using a minimum of probes from multiple vantages. We find that, while network coordinates may play an important role in scalably choosing effective vantage points, they are not directly useful for predicting a client’s nearest servers.


Median Error Locality Prediction Predictive Error Network Coordinate Destination Selection 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Akamai Technologies (2004),
  2. 2.
    Costa, M., Castro, M., Rowstron, A., Key, P.: PIC: Practical Internet coordinates for distance estimation. In: Conference on Distributed Systems, Tokyo, Japan (March 2004)Google Scholar
  3. 3.
    Dabek, F., Cox, R., Kaashoek, F., Morris, R.: Vivaldi: A decentralized network coordinate system. In: ACM SIGCOMM, Portland, OR (August 2004)Google Scholar
  4. 4.
    Francis, P., Jamin, S., Jin, C., Jin, Y., Raz, D., Shavitt, Y., Zhang, L.: IDMaps: A global Internet host distance estimation service. IEEE/ACM Trans. on Networking (October 2001)Google Scholar
  5. 5.
    Freedman, M.J., Freudenthal, E., Mazières, D.: Democratizing content publication with Coral. In: USENIX/ACM NSDI, San Francisco, CA (March 2004)Google Scholar
  6. 6.
    Grimm, R., Kravetz, A., Lichtman, G., Michalakis, N., Raza, S., Elliston, A., Miller, J.: OpenEdge: A unified architecture for edge-side content creation, transformation, and caching. Technical report, NYU (February 2005)Google Scholar
  7. 7.
    Karp, B., Ratnasamy, S., Rhea, S., Shenker, S.: Spurring adoption of DHTs with OpenHash, a public DHT service. In: 3rd Intl. Workshop on Peer-to-Peer Systems, San Diego, CA (February 2004)Google Scholar
  8. 8.
    Ng, E., Zhang, H.: Predicting Internet network distance with coordinates-based approaches. In: IEEE INFOCOM, New York, NY (June 2002)Google Scholar
  9. 9.
    Ng, E., Zhang, H.: A network positioning system for the Internet. In: USENIX Conference, Boston, MA (March 2004)Google Scholar
  10. 10.
    Pias, M., Crowcroft, J., Wilbur, S., Bhatti, S., Harris, T.: Lighthouses for scalable distributed location. In: 2nd Intl. Workshop on Peer-to-Peer Systems (February 2003)Google Scholar
  11. 11.
    PlanetLab (2004),
  12. 12.
    Tang, L., Crovella, M.: Virtual landmarks for the Internet. In: Internet Measurement Conference, Miami Beach, FL (October 2003)Google Scholar
  13. 13.
    Walfish, M., Balakrishnan, H., Shenker, S.: Untangling the Web from DNS. In: USENIX/ACM NSDI, San Francisco, CA (March 2004)Google Scholar
  14. 14.
    Walfish, M., Stribling, J., Krohn, M., Balakrishnan, H., Morris, R., Shenker, S.: Middleboxes no longer considered harmful. In: USENIX OSDI, San Francisco, CA (December 2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Kevin P. Shanahan
    • 1
  • Michael J. Freedman
    • 1
  1. 1.New York University 

Personalised recommendations