• DocumentCode
    3145801
  • Title

    Solving k-Set Agreement with Stable Skeleton Graphs

  • Author

    Biely, Martin ; Robinson, Peter ; Schmid, Ulrich

  • Author_Institution
    EPFL, Lausanne, Switzerland
  • fYear
    2011
  • fDate
    16-20 May 2011
  • Firstpage
    1488
  • Lastpage
    1495
  • Abstract
    In this paper we consider the k-set agreement problem in distributed message-passing systems using a round-based approach: Both synchrony of communication and failures are captured just by means of the messages that arrive within a round, resulting in round-by-round communication graphs that can be characterized by simple communication predicates. We introduce the weak communication predicate Psrcs(k) and show that it is tight for k-set agreement, in the following sense: We (i) prove that there is no algorithm for solving (k-1)-set agreement in systems characterized by Psrcs(k), and (ii) present a novel distributed algorithm that achieves k-set agreement in runs where Psrcs(k) holds. Our algorithm uses local approximations of the stable skeleton graph, which reflects the underlying perpetual synchrony of a run. We prove that this approximation is correct in all runs, regardless of the communication predicate, and show that graph-theoretic properties of the stable skeleton graph can be used to solve k-set agreement if Psrcs(k) holds.
  • Keywords
    distributed algorithms; graph theory; message passing; set theory; Psrcs; communication predicates; communication synchrony; distributed algorithm; distributed message-passing systems; graph-theoretic property; k-set agreement; local approximations; round-based approach; round-by-round communication graphs; stable skeleton graphs; underlying perpetual synchrony; Approximation algorithms; Approximation methods; Computational modeling; Computer crashes; Erbium; Proposals; Skeleton;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW), 2011 IEEE International Symposium on
  • Conference_Location
    Shanghai
  • ISSN
    1530-2075
  • Print_ISBN
    978-1-61284-425-1
  • Electronic_ISBN
    1530-2075
  • Type

    conf

  • DOI
    10.1109/IPDPS.2011.301
  • Filename
    6009006