Peer-to-Peer Networking and Applications

, Volume 9, Issue 2, pp 313–327 | Cite as

Evaluation of alternatives for the broadcast operation in Kademlia under churn

  • Antonio Delgado PerisEmail author
  • José M. Hernández
  • Eduardo Huedo


During recent years, considerable effort has been devoted to the enhancement of Distributed Hash Table (DHT) systems with broadcasting capabilities. Such systems typically provide individual node routing but a broadcast primitive is required for functionalities such as information dissemination or data aggregation. Broadcasting can also be used as the basis for partial keyword searches. Little work has however specifically addressed Kademlia, a well known DHT, used in real applications. Our work exposes the particularities of this system, notably its XOR-based distance metrics, and analytically studies what broadcasting techniques can be applied to it. A model that estimates node coverage as a function of the probability that individual messages reach their destination has been also developed. For validation, several broadcasting algorithms have been implemented and comprehensively evaluated, considering node coverage, messages to nodes ratio, latency and imbalance factor. Moreover, several techniques are proposed to enhance the bare protocols when adverse circumstances such as churn and failure rate conditions are present. These include redundancy, resubmissions or flooding, and also combinations of those. All have been implemented and fully tested. An analysis of the strengths and weaknesses of algorithms and additional techniques, and a discussion on the choices and compromises to make, depending on system characteristics or application priorities, is finally presented.


DHT Kademlia Broadcast P2P Distributed computing 



We acknowledge the funding support provided by the Spanish funding agency SEIDI, through the grant FPA2010-21638-C02-02.


  1. 1.
    Balakrishnan H, Kaashoek M, Karger D, Morris R, Stoica I (2003) Looking up data in P2P systems. Commun ACM 46(2):43–48CrossRefGoogle Scholar
  2. 2.
    Crosby S, Wallach D (2007) An analysis of BitTorrent’s two Kademlia-based DHTs. Tech. rep., Technical Report TR07-04 Rice UniversityGoogle Scholar
  3. 3.
    Czirkos Z, Hosszú G (2013) Solution for the broadcasting in the Kademlia peer-to-peer overlay. Comput Networks 57(8): 1853–1862. doi: 10.1016/j.comnet.2013.02.021 CrossRefGoogle Scholar
  4. 4.
    Delgado Peris A, Hernández JM, Huedo E (2012) Evaluation of the broadcast operation in Kademlia. In: Min G, Hu J, Liu LC, Yang LT, Seelam S, Lefevre L (eds) IEEE 14th International Conference on High Performance Computing and Communication & IEEE 9th Intl. Conf. on Embedded Software and Systems (HPCC-ICESS). IEEE Computer Society, pp 756–763Google Scholar
  5. 5.
    Delgado Peris A, Hernández JM, Huedo E (2014) Distributed scheduling and data sharing in late-binding overlays, International Conference on High Performance Computing Simulation (HPCS), 2014 , pp 129–136Google Scholar
  6. 6.
    El-Ansary S, Alima L, Brand P, Haridi S (2003) Efficient broadcast in structured P2P networks 2nd International Workshop On Peer-To-Peer Systems (IPTPS’03). Springer, pp 304–314Google Scholar
  7. 7.
    Ghodsi A, Onana Alima L, El-Ansary S, Brand P, Haridi S (2003) Self-correcting broadcast in distributed hash tables 15th IASTED International Conference, Parallel and Distributed Computing and Systems (PDCS). ACTA PressGoogle Scholar
  8. 8.
    Hasham K, Delgado Peris A et al (2011) CMS workflow execution using intelligent job scheduling and data access strategies. Nuclear Science. IEEE Trans 58(3):1221–1232Google Scholar
  9. 9.
    Huang K, Zhang D (2010) Dht-based lightweight broadcast algorithms in large-scale computing infrastructures. Future Gen Comput Sys 26(3):291–303CrossRefGoogle Scholar
  10. 10.
    Li J, Sollins K, Lim D (2005) Implementing aggregation and broadcast over distributed hash tables. ACM SIGCOMM Comput Commun Rev 35(1):81–92CrossRefGoogle Scholar
  11. 11.
    Li W, Chen S, Zhou P, Li X, Li Y (2007) An efficient broadcast algorithm in distributed hash table under churn International Conference on Wireless Communications, Networking and Mobile Computing (WiCom), 2007, pp 1929–1932. IEEEGoogle Scholar
  12. 12.
    Lin F, Henricsson C, Abbas S, Sandkuhl K (2009) Hypercircle: An efficient broadcast protocol for super-peer P2P networks International Conference on Computational Science and Engineering (CSE), 2009, vol 2, pp 426–433. IEEEGoogle Scholar
  13. 13.
    Maymounkov P, Mazieres D (2002) Kademlia: A peer-to-peer information system based on the XOR metric Revised Papers from the First International Workshop on Peer-to-Peer Systems (IPTPS ’01). Springer-Verlag, London, pp 53–65Google Scholar
  14. 14.
    Merz P, Gorunova K (2005) Efficient broadcast in P2P grids, IEEE International Symposium on Cluster Computing and the Grid (CCGrid), 2005, vol 1, IEEEGoogle Scholar
  15. 15.
    Ratnasamy S, Francis P, Handley M, Karp R, Shenker S (2001) A scalable content-addressable network. ACM SIGCOMM Comput Commun Rev 31(4):161–172CrossRefGoogle Scholar
  16. 16.
    Rowstron A, Druschel P (2001) Pastry: Scalable, decentralized object location, and routing for large-scale peer-to-peer systems Middleware 2001Google Scholar
  17. 17.
    Stoica I, Morris R, Karger D, Kaashoek M, Balakrishnan H. (2001) Chord: A scalable peer-to-peer lookup service for internet applications. ACM SIGCOMM Comput Commun Rev 31(4):149–160CrossRefGoogle Scholar
  18. 18.
    Wahlisch M, Schmidt T, Wittenburg G (2009) Broadcasting in prefix space: P2P data dissemination with predictable performance Fourth International Conference on Internet and Web Applications and Services (ICIW’09), IEEEGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  • Antonio Delgado Peris
    • 1
    Email author
  • José M. Hernández
    • 1
  • Eduardo Huedo
    • 2
  1. 1.MadridSpain
  2. 2.Facultad de InformáticaUniversidad Complutense de Madrid (UCM)MadridSpain

Personalised recommendations