A Multicast Protocol Based on a Single Logical Ring Using a Virtual Token and Logical Clocks

A novel and efficient protocol based on a single logical ring for multicast communication among a group of processes is presented. The senders and receivers are merged in the same group and this peer group reflects a cooperative (mirror) group of information servers. The protocol maintains consistency in the group by using two strategies. First, by placing a total sequence number in each of the multicast messages, it guarantees total ordering of message delivery for each member. Second, in contrast to other ring protocols which are based on real token passing, it uses a virtual token and achieves message atomicity by using up to n point-to-point control messages. Since no real token passing messages are rotating on the ring, the position of the token holder is calculated by using a logical clock located in each of the processes. The protocol can tolerate communication faults, process crash failures and network partitioning. The protocol has been implemented and experimental results show that the protocol achieves satisfactory performance.

[1]  Andrew S. Tanenbaum,et al.  An evaluation of the Amoeba group communication system , 1996, Proceedings of 16th International Conference on Distributed Computing Systems.

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

[3]  Jo-Mei Chang,et al.  Reliable broadcast protocols , 1984, TOCS.

[4]  Leslie Lamport,et al.  Time, clocks, and the ordering of events in a distributed system , 1978, CACM.

[5]  Hector Garcia-Molina,et al.  Ordered and reliable multicast communication , 1991, TOCS.

[6]  Matti A. Hiltunen,et al.  An approach to constructing modular fault-tolerant protocols , 1993, Proceedings of 1993 IEEE 12th Symposium on Reliable Distributed Systems.

[7]  Virgil D. Gligor,et al.  A Fault-Tolerant Protocol for Atomic Broadcast , 1990, IEEE Trans. Parallel Distributed Syst..

[8]  Paulo Veríssimo,et al.  AMp: a highly parallel atomic multicast protocol , 1989, SIGCOMM 1989.

[9]  Andrew S. Tanenbaum,et al.  Group communication in the Amoeba distributed operating system , 1991, [1991] Proceedings. 11th International Conference on Distributed Computing Systems.

[10]  Weijia Jia,et al.  RMP: fault-tolerant group communication , 1996, IEEE Micro.

[11]  Philip K. McKinley,et al.  A token-based protocol for reliable, ordered multicast communication , 1989, Proceedings of the Eighth Symposium on Reliable Distributed Systems.

[12]  Louise E. Moser,et al.  The Totem system , 1995, Twenty-Fifth International Symposium on Fault-Tolerant Computing. Digest of Papers.

[13]  Richard D. Schlichting,et al.  Preserving and using context information in interprocess communication , 1989, TOCS.

[14]  Robbert van Renesse,et al.  Horus: a flexible group communication system , 1996, CACM.

[15]  Sam Toueg,et al.  Fault-tolerant broadcasts and related problems , 1993 .

[16]  Hermann Kopetz,et al.  Distributed fault-tolerant real-time systems: the Mars approach , 1989, IEEE Micro.

[17]  Nancy A. Lynch,et al.  Impossibility of distributed consensus with one faulty process , 1985, JACM.

[18]  Weijia Jia,et al.  An efficient and reliable group multicast protocol , 1995, Proceedings ISADS 95. Second International Symposium on Autonomous Decentralized Systems.

[19]  Edgar Nett,et al.  Generic Action Support for Distributed, Cooperative Applications , 1993, HPTS.

[20]  Yair Amir,et al.  Membership Algorithms for Multicast Communication Groups , 1992, WDAG.

[21]  Shivakant Mishra,et al.  Experience with modularity in consul , 1993, Softw. Pract. Exp..

[22]  Weijia Jia,et al.  Implementation of Reliable Multicast Protocol , 1997, Softw. Pract. Exp..