An ordered and reliable broadcast protocol for distributed systems

The purpose of a reliable broadcast protocol is to allow groups of nodes on unreliable broadcast networks to reliably broadcast messages. A reliable broadcast protocol must guarantee two properties: (1) all of the receivers in a group receive the broadcast messages, and (2) each of the receivers orders the messages in the same sequence. In an optimistic approach to reliable broadcast protocol, a batch acknowledgement is employed for a sequence of broadcast messages, instead of one or more acknowledgements per broadcast message used in the pessimistic approach. In this paper, based on the optimistic approach, we have proposed a counter-based reliable broadcast protocol. In this protocol, the unique token ownership is circulated among all the nodes in an order specified by a token-passing-list. The system state which records related information about messages broadcast by each node is included in the token message. By appropriately updating the counter information recorded in the system state included in the token message, instead of using explicit acknowledgement messages, the proposed protocol needs fewer control messages to commit a broadcast message than other protocols, no matter whether the rate of transmission errors is high or low. Moreover, we show how to handle the flow control problem and describe the token update technique.

[1]  Henri E. Bal,et al.  An efficient reliable broadcast protocol , 1989, OPSR.

[2]  Hector Garcia-Molina,et al.  Message ordering in a multicast environment , 1989, [1989] Proceedings. The 9th International Conference on Distributed Computing Systems.

[3]  Amr El Abbadi,et al.  Maintaining availability in partitioned replicated databases , 1987, ACM Trans. Database Syst..

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

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

[6]  P.M. Melliar-Smith,et al.  Fault-tolerant distributed systems based on broadcast communication , 1989, [1989] Proceedings. The 9th International Conference on Distributed Computing Systems.

[7]  Xiaohua Jia,et al.  A multicast mechanism with ordering on overlapping groups , 1993, 1993 International Conference on Network Protocols.

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

[9]  Adrian Segall,et al.  A Failsafe Distributed Routing Protocol , 1979, IEEE Trans. Commun..

[10]  Samuel T. Chanson,et al.  Reliable group communication in distributed systems , 1988, [1988] Proceedings. The 8th International Conference on Distributed.

[11]  Jo-Mei Chang.  Simplifying distributed database systems design by using a broadcast network , 1984, SIGMOD '84.

[12]  Jane W.-S. Liu,et al.  A Reliable Token-Driven Process Synchronization Algorithm , 1986, ICDCS.

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

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

[15]  Baruch Awerbuch,et al.  "A reliable broadcast protocol" , 1982, 1982 21st IEEE Conference on Decision and Control.

[16]  R. Newman-Wolfe,et al.  An efficient broadcast protocol in networks with changing topologies , 1990, [1990] Proceedings. Second IEEE Workshop on Future Trends of Distributed Computing Systems.

[17]  Hector Garcia-Molina,et al.  An implementation of reliable broadcast using an unreliable multicast facility , 1988, Proceedings [1988] Seventh Symposium on Reliable Distributed Systems.

[18]  Kenneth P. Birman,et al.  Reliable communication in the presence of failures , 1987, TOCS.

[19]  Philip A. Bernstein,et al.  Categories and Subject Descriptors: H.2.4 [Database Management]: Systems. , 2022 .

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

[21]  Samuel T. Chanson,et al.  Process groups and group communications: classifications and requirements , 1990, Computer.

[22]  Jane W.-S. Liu,et al.  Optimistic Token-Driven Reliable Sequenced Broadcast Protocols , 1990, International Conference on Parallel Processing.

[23]  Kenneth P. Birman,et al.  Low cost management of replicated data in fault-tolerant distributed systems , 1986, TOCS.

[24]  Louise E. Moser,et al.  Broadcast Protocols for Distributed Systems , 1990, IEEE Trans. Parallel Distributed Syst..

[25]  Louise E. Moser,et al.  Membership algorithms for asynchronous distributed systems , 1991, [1991] Proceedings. 11th International Conference on Distributed Computing Systems.