Design, Implementation and Performance Evaluation of a High Performance CORBA Group Membership Protocol

This paper describes the design, implementation, and performance evaluation of a CORBA group membership protocol. Using CORBA to implement a group membership protocol enables that protocol to operate in a heterogeneous, distributed computing environment. To evaluate the effect of CORBA on the performance of a group membership protocol, this paper provides a detailed comparison of the performance measured from three implementations of a group membership protocol. One implementation uses UDP sockets, while the other two use CORBA for interprocess communication. The main conclusion is that CORBA can be used to implement high performance group membership protocols. There is some performance degradation due to CORBA, but this degradation can be reduced by carefully choosing an appropriate design.

[1]  Shivakant Mishra,et al.  Design, implementation and performance evaluation of a CORBA group communication service , 1999, Digest of Papers. Twenty-Ninth Annual International Symposium on Fault-Tolerant Computing (Cat. No.99CB36352).

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

[3]  Priya Narasimhan,et al.  Consistent Object Replication in the external System , 1998, Theory Pract. Object Syst..

[4]  Raghu V. Hudli,et al.  CORBA fundamentals and programming , 1996 .

[5]  Louise E. Moser,et al.  The Totem single-ring ordering and membership protocol , 1995, TOCS.

[6]  William H. Sanders,et al.  AQuA: an adaptive architecture that provides dependable distributed objects , 1998, Proceedings Seventeenth IEEE Symposium on Reliable Distributed Systems (Cat. No.98CB36281).

[7]  Shivakant Mishra,et al.  Consul: a communication substrate for fault-tolerant distributed programs , 1993, Distributed Syst. Eng..

[8]  Rachid Guerraoui,et al.  The design of a CORBA group communication service , 1996, Proceedings 15th Symposium on Reliable Distributed Systems.