Divide et Impera: Partitioning Unstructured Peer-to-Peer Systems to Improve Resource Location

  • Harris Papadakis
  • Paraskevi Fragopoulou
  • Evangelos P. Markatos
  • Marios Dikaiakos
  • Alexandros Labrinidis


Unstructured P2P systems exhibit a great deal of robustness and self-healing at the cost of reduced scalability. Resource location is performed using a broadcast-like process called flooding. The work presented in this paper comprises an effort to reduce the overwhelming volume of traffic generated by flooding, thus increasing the scalability of unstructured P2P systems. Using a simple hash-based content categorization method the Ultrapeer overlay network is partitioned into a relatively small number of distinct subnetworks. By employing a novel index splitting technique each leaf peer is effectively connected to each different subnetwork. The search space of each individual flooding is restricted to a single partition, and is thus considerably limited. This reduces significantly the volume of traffic produced by flooding without affecting at all the accuracy of the search method. Experimental results demonstrate the efficiency of the proposed method.


Peer-to-peer resource location flooding overlay network network partition 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    Gnutella 0.6 protocol specification. Scholar
  2. [2]
    Limewire Inc. http://www.limewire.comGoogle Scholar
  3. [3]
    B.H. Bloom. Space/time trade-offs in hash coding with allowable errors. Communications of the ACM, 13(7):422–426, 1970.zbMATHCrossRefGoogle Scholar
  4. [4]
    Y. Chawathe, S. Ratnasamy, L. Breslau, N. Lanham, and S. Shenker. Making Gnutella-like P2P Systems Scalable. Proc. ACM SIGCOMM 2003 Conf. on Applications, Technologies, Architectures, and Protocols for Computer Communication, pp. 407-418, 2003.Google Scholar
  5. [5]
    V. Cholvi P. Felber, and E. Biersack. Efficient search in unstructured peer-to-peer networks. Proc. 16th ACM Symposium on Parallelism in Algorithms and Architectures, 2004.Google Scholar
  6. [6]
    A. Crespo and H. Garcia-Molina. Semantic overlay networks for p2p systems. Technical report, 2002.Google Scholar
  7. [7]
    C. Gkantsidis, M. Mihail, and A. Saberi. Hybrid search schemes for unstructured peer-to-peer networks. Proc. of INFOCOM, 2005.Google Scholar
  8. [8]
    C. Papadakis P. Fragopoulou E. Athanasopoulos M. Dikaiakos, A. Labrinidis, and E. Markatos. A feedback-based approach to reduce duplicate messages in unstructured peer-to-peer networks. Proc. of the CoreGRID Integration Workshop, 2005.Google Scholar
  9. [9]
    R. Rejaie, Shanyu Zhao, and D. Stutzbach. Characterizing files in the modern Gnutella network: A measurement study. Proc. SPIE/ACM Multimedia Computing and Networking, 2006.Google Scholar
  10. [10]
    K. Sripanidkulchai, B. Maggs, and H. Zhang. Efficient content location using interest-based locality in peer-to-peer systems. Proc. of INFOCOM, 2003. Google Scholar
  11. [11]
    D. Stutzbach and R. Rejaie. Characterizing the two-tier gnutella topology. Proc. of the ACM SIGMETRICS, Poster Session, 2005.Google Scholar
  12. [12]
    B. Yang and H. Garcia-Molina. Improving search in peer-to-peer networks. Proc. of the 22nd International Conference on Distributed Computing Systems (ICDCS02), 2002.Google Scholar
  13. [13]
    B. Yang and H. Garcia-Molina. Designing a Super-Peer Network. Proc. Int. Conference on Data Engineering (ICDE 2003), pp. 49-60, 2003.Google Scholar
  14. [14]
    Fisk, A. Gnutella Ultrapeer Query Routing, v. 0.1. LimeWire Inc. 2003Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2008

Authors and Affiliations

  • Harris Papadakis
    • 1
  • Paraskevi Fragopoulou
    • 1
  • Evangelos P. Markatos
    • 1
  • Marios Dikaiakos
    • 2
  • Alexandros Labrinidis
    • 3
  1. 1.Institute of Computer ScienceFoundation for Research and Technology-HellasGreece
  2. 2.Department of Computer ScienceUniversity of CyprusCyprus
  3. 3.Department of Computer ScienceUniversity of PittsburghPittsburghUSA

Personalised recommendations