An Efficient Optimistic Atomic Broadcast Algorithm

Atomic broadcast is a fundamental building block in the construction of fault tolerant distributed applications. Although a number of algorithms have been published, the implementation of such a primitive is still considered costly in terms of communication latency. To solve this problem, some algorithms based on optimistic assumptions are proposed. When the optimistic assumption holds, those algorithms are more efficient than conservative algorithms. However, if the assumption does not hold, the efficiency of those algorithms deteriorates. In this paper, we propose a novel optimistic algorithm which exploits the optimistic assumption in a way that never leads to high latency. Simulation experiments have been performed to evaluate the algorithm and the results show it achieves satisfactory performance

[1]  André Schiper,et al.  Optimistic atomic broadcast: a pragmatic viewpoint , 2003, Theor. Comput. Sci..

[2]  Idit Keidar,et al.  Group communication specifications: a comprehensive study , 2001, CSUR.

[3]  Sam Toueg,et al.  Unreliable failure detectors for reliable distributed systems , 1996, JACM.

[4]  Xavier Défago,et al.  Time vs. space in fault-tolerant distributed systems , 2001, Proceedings Sixth International Workshop on Object-Oriented Real-Time Dependable Systems.

[5]  A. Schiper,et al.  Contention-aware metrics for distributed algorithms: comparison of atomic broadcast algorithms , 2000, Proceedings Ninth International Conference on Computer Communications and Networks (Cat.No.00EX440).

[6]  Steve Harrison,et al.  Boosting system performance with optimistic distributed protocols , 2001 .

[7]  Achour Mostéfaoui,et al.  Low cost consensus-based Atomic Broadcast , 2000, Proceedings. 2000 Pacific Rim International Symposium on Dependable Computing.

[8]  A. Fleischmann Distributed Systems , 1994, Springer Berlin Heidelberg.

[9]  Sape Mullender,et al.  Distributed systems , 1989 .

[10]  Nancy A. Lynch,et al.  Impossibility of distributed consensus with one faulty process , 1983, PODS '83.

[11]  Fred B. Schneider,et al.  Implementing fault-tolerant services using the state machine approach: a tutorial , 1990, CSUR.

[12]  Danny Dolev,et al.  Evaluating Total Order Algorithms in WAN , 2003 .

[13]  Gustavo Alonso,et al.  Using Optimistic Atomic Broadcast in Transaction Processing Systems , 2003, IEEE Trans. Knowl. Data Eng..

[14]  Idit Keidar,et al.  On the Cost of Fault-Tolerant Consensus When There Are No Faults - A Tutorial , 2003, LADC.

[15]  André Schiper,et al.  Lightweight causal and atomic group multicast , 1991, TOCS.

[16]  Francisco Moura,et al.  Optimistic total order in wide area networks , 2002, 21st IEEE Symposium on Reliable Distributed Systems, 2002. Proceedings..

[17]  Paul D. Ezhilchelvan,et al.  An optimal atomic broadcast protocol and an implementation framework , 2003, Proceedings of the Eighth International Workshop on Object-Oriented Real-Time Dependable Systems, 2003. (WORDS 2003)..