• DocumentCode
    3600024
  • Title

    Data Center Multicast with High Stability

  • Author

    Ye Shen ; Jing Feng ; Zhanfeng Wang ; Weijun Ma ; Min Yin ; Lei Jiang

  • Author_Institution
    Inst. of Meteorol. & Oceanogr., PLA Univ. of Sci. & Technol., Nanjing, China
  • fYear
    2014
  • Firstpage
    168
  • Lastpage
    173
  • Abstract
    Multicast benefits data center group communication in both saving network traffic and improving application throughput. The SLA (Service Level Agreement) of cloud service requires the computation correctness of distributed applications, translating to the requirement of reliable Multicast delivery. In this paper we present INICE, a high stable Multicast approach for data center network. The key idea of INICE is to minimize the impact of end host instability on the Multicast performance, by computing the link weight with node stability. A Multicast tree-aware backup overlay is purposely built on hierarchical clustering of stable nodes. INICE proposes feasible and highly efficient node clustering algorithm, and guarantees the out-degree of node being a constant. The backup overlay multicast tree is organized in such a way that it causes little multicast tree rebuilding. We extensively evaluate the INICE algorithm by theoretical analysis and experiments.
  • Keywords
    computer centres; computer networks; multicast protocols; overlay networks; pattern clustering; INICE algorithm; data center multicast; data center network; end host instability; hierarchical clustering; multicast protocol; multicast tree rebuilding; multicast tree-aware backup overlay; node clustering algorithm; node stability; Clustering algorithms; Network topology; Partitioning algorithms; Peer-to-peer computing; Stability analysis; Throughput; Topology; data center multicast; hierarchical arrangement; node clustering; node stability;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Advanced Cloud and Big Data (CBD), 2014 Second International Conference on
  • Print_ISBN
    978-1-4799-8086-4
  • Type

    conf

  • DOI
    10.1109/CBD.2014.28
  • Filename
    7176088