Overlay Routing under Geographically Correlated Failures in Distributed Event-Based Systems

  • Kyriakos Karenos
  • Dimitrios Pendarakis
  • Vana Kalogeraki
  • Hao Yang
  • Zhen Liu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6427)


In this paper we study the problem of enabling uninterrupted delivery of messages between endpoints, subject to spatially correlated failures in addition to independent failures. We developed a failure model-independent algorithm for computing routing paths based on failure correlations using both a-priory failure statistics together with available real-time monitoring information. The algorithm provides the most cost-efficient message routes that are potentially comprised of multiple simultaneous paths. We also designed and implemented an Internet-based overlay routing service that allows applications to construct and maintain highly resilient end-to-end paths. We have deployed our system over a set of geographically distributed Planetlab nodes. Our experimental results illustrate the feasibility and performance of our approach.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Nedic, D.P., Dobson, I., Kirschen, D.S., Carreras, B.A., Lynch, V.E.: Criticality in a cascading failure blackout model. Int’l. Journal of Electrical Power & Energy Systems 28, 627–633 (2006)CrossRefGoogle Scholar
  2. 2.
    Andersen, D.G., Balakrishnan, H., Kaashoek, M.F., Morris, R.: Resilient overlay networks. In: Proc. 18th ACM SOSP, pp. 131–145 (2001)Google Scholar
  3. 3.
    Andersen, D.G., Snoeren, A.C., Balakrishnan, H.: Best-path vs. multi-path overlay routing. In: Proc. of ACM IMC, pp. 91–100 (2003)Google Scholar
  4. 4.
  5. 5.
    Wang, M., Takada, T.: Macrospatial correlation model of seismic ground motions. Earthquake spectra 21, 1137–1156 (2005)CrossRefGoogle Scholar
  6. 6.
    Haeberlen, A., Mislove, A., Druschel, P.: Glacier: Highly durable, decentralized storage despite massive correlated failures. In: Proc.of NSDI, vol. 75 (2005)Google Scholar
  7. 7.
    Nath, S., Yu, H., Gibbons, P.B., Seshan, S.: Subtleties in tolerating correlated failures in wide-area storage systems. In: Proc. USENIX NSDI, pp. 225–238 (2006)Google Scholar
  8. 8.
    Cui, W., Stoica, I., Katz, R.H.: Backup path allocation based on a correlated link failure probability model in overlay networks. In: IEEE ICNP, p. 236 (2002)Google Scholar
  9. 9.
    Pendarakis, D.E., Shi, S., Verma, D.C., Waldvogel, M.: ALMI: An application level multicast infrastructure. In: Proc. of USENIX USITS, pp. 49–60 (2000)Google Scholar
  10. 10.
    Rowstron, A., Druschel, P.: Pastry: Scalable, decentralized object location and routing for large-scale peer-to-peer systems. In: IFIP/ACM Middleware, pp. 329–350 (2001)Google Scholar
  11. 11.
    Ratnasamy, S., Handley, M., Karp, R.M., Shenker, S.: Topologically-aware overlay construction and server selection. In: INFOCOM (2002)Google Scholar
  12. 12.
    Subramanian, L., Padmanabhan, V.N., Katz, R.H.: Geographic properties of internet routing. In: USENIX Annual Technical Conference, pp. 243–259 (2002)Google Scholar
  13. 13.
    Fan, J., Chang, T., Pendarakis, D., Liu, Z.: Cost-effective configuration of content resiliency services under correlated failures. In: Proc. of DSN, pp. 536–548 (2006)Google Scholar
  14. 14.
    Rowstron, A., Druschel, P., Yalagandula, P., Nath, S., Yu, H., Gibbons, P.B., Sesha, S.: Beyond availability: Towards a deeper understanding of machine failure characteristics in large distributed systems. In: WORLDS (2004)Google Scholar
  15. 15.
    Dennis, S.Z., Geels, D., Stoica, I., Katz, R.H.: On failure detection algorithms in overlay networks. In: IEEE INFOCOM (2003)Google Scholar
  16. 16.
    de Queirós Vieira Martins, E., Marta, M.: A new implementation of yen’s ranking loopless paths algorithm. 4OR-Q J. Oper. Res. 1(2), 121–133 (2003)MathSciNetzbMATHGoogle Scholar
  17. 17.
    Colbourn, J.: The Combinatorics of Network Reliability. Oxford University Press, New York (1987)Google Scholar
  18. 18.
    Gupta, A., Jain, B.N., Tripathi, S.: QoS aware path protection schemes for MPLS networks. In: Proc. of ICCC, pp. 103–118 (2002)Google Scholar
  19. 19.
    Han, S., Shin, K.G.: A primary-backup channel approach to dependable real-time communication in multihop networks. IEEE Trans. Computers 47(1), 46–61 (1998)CrossRefGoogle Scholar
  20. 20.
    Xu, Y.: Understanding the performance and resilience of large-scale multi-hop wireless networks. In: NCSU PhD thesis (2010)Google Scholar
  21. 21.
    Gupta, A., Liskov, B., Rodrigues, R.: Efficient routing for peer-to-peer overlays. In: NSDI, San Francisco, CA (March 2004)Google Scholar
  22. 22.
    Banerjee, S., Lee, S., Bhattacharjee, B., Srinivasan, A.: Resilient multicast using overlays. In: Proc. of SIGMETRICS, pp. 102–113 (2003)Google Scholar
  23. 23.
    Mittra, S.: Lolus: A framework for scalable secure multicasting. In: SIGCOMM, pp. 277–288 (1997)Google Scholar
  24. 24.
    Pappas, V., Zhang, B., Terzis, A., Zhang, L.: Fault-tolerant data delivery for multicast overlay networks. In: Proc. of ICDCS, pp. 670–679 (2004)Google Scholar
  25. 25.
    Mahambre, S., Bellur, U.: Reliable routing of event notifications over p2p overlay routing substrate in event based middleware. In: IPDPS, pp. 1–8 (2007)Google Scholar
  26. 26.
    Campbell, J., Gibbons, P.B., Nath, S., Pillai, P., Seshan, S., Sukthankar, R.: Irisnet: an internet-scale architecture for multimedia sensors. In: Proc. of ACM MULTIMEDIA, pp. 81–88 (2005)Google Scholar
  27. 27.
    Bakkaloglu, M., Wylie, J.J., Wang, C., Ganger, G.R.: Modeling correlated failures in survivable storage systems. In: Proc. of DSN (2002)Google Scholar
  28. 28.
    Kotla, R., Alvisi, L., Dahlin, M.: Safestore: A durable and practical storage system. In: USENIX (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Kyriakos Karenos
    • 1
  • Dimitrios Pendarakis
    • 1
  • Vana Kalogeraki
    • 2
  • Hao Yang
    • 3
  • Zhen Liu
    • 3
  1. 1.IBM, T.J. Watson Research CenterUSA
  2. 2.Athens University of Economics and BusinessGreece
  3. 3.Nokia ResearchUSA

Personalised recommendations