Merits of a probabilistic approach to properties in process group systems
- 120 Downloads
Distributed computing systems have traditionally been designed using either a purely asynchronous methodology, in which no use is made of time, or a purely synchronous one, in which all delays are bounded and clocks are assumed to be synchronized. We argue in favor of an intermediate approach, in which delay states would be systematically removed from an asynchronous system, resulting in a high probability of predictably good performance. Preliminary and very informal analysis suggests that this would yield systems with predictably high performance, and yet that are as likely to achieve this performance as would a real-time system based upon a traditional synchronous design. Such thinking leads to a paradox. On the one hand, we conclude that asynchronous systems may be able to offer real-time properties with high probability. On the other, it fosters concern that all properties of distributed systems might better be viewed as probabilistic.
KeywordsClock Synchronization Distribute Computing System Asynchronous System Asynchronous Model Synchronous Approach
Unable to display preview. Download preview PDF.
- [A92]Y. Amir, et. al. Transis: A communication subsystem for high availability. In Proceedings of the 22nd International Symposium on Fault-Tolerant Computing, pages 76–84, Boston MA (July 1992). IEEE.Google Scholar
- [B94]K.P. Birman and R. Van Renesse, eds. Reliable Distributed Computing with the Isis Toolkit. IEEE Computer Society Press (1994).Google Scholar
- [C85]F. Cristian, H. Aghili, R. Strong and D. Dolev. Atomic broadcast: From simple message diffusion to Byzantine agreement. Proceedings of the 15th International Symposium on Fault-Tolerant Computing, Ann Arbor, Michigan (June 1985). IEEE.Google Scholar
- [C86]F. Cristian, H. Aghili, R. Strong. Approximate clock synchronization despite omission and performance faults and processor joins. Proceedings of the 16th International Symposium on Fault-Tolerant Computing, Vienna, Austria (July 1986). IEEE.Google Scholar
- [F85]M.J. Fischer, N.A. Lynch and M.S. Patterson. Impossibility of distributed consensus with one faulty process. Journal of the ACM, 32: 2, 374–382 (April 1985).Google Scholar
- [M94]L.E. Moser and MP.M. Melliar-Smith. Probablistic bounds on message delivery for the Totem single-ring protocol. Proceedings of the Real-Time Systems Symposium, San Juan Puerto Rico (Dec. 1994). IEEE.Google Scholar
- [M94]Dalia Malki, Ken Birman, Aleta Ricciardi, Andre Schiper. Uniform actions in asynchronous distributed systems. Dept. of Computer Science, Cornell University. TR 94-1447 (Sept. 1994).Google Scholar
- [R95]R. Van Renesse, et. al. Horus: A Flexible Group Communications System. Forthcoming, Dept. of Computer Science, Cornell University (March 1995).Google Scholar
- [S87]T. K. Srikanth, S. Toueg. Optimal clock synchronization. Journal of the ACM, 34: 3, 626–645 (July 1987).Google Scholar