分布式容错系统的低冗余重构策略及拓扑结构研究

分布式系统需要采用合理的拓扑结构，才能在低冗余的条件下的实现容错，从而获得高的性能价格比。本文从分析的可靠性与重构策略的关系以及重构策略与系统拓扑系统入手，找出解决这一课题的一种途径，最后介绍了一个低余度高可靠实时重构的分布式容错系统的实现。

The Reconfiguration Policy and Topology of Distributed Computer System with Low-Redundancy

A distributed computer system must be implemented with rational topology, so that fault tolerance can be realized with low redundancy and high performance-cost ratio can be obtained. In this paper, a method to solve this problem is presented. The method is based on the analysis of the relation between the reliability and the policy of reconfiguration as well as the relation between the policy of reconfiguration and the system topology. The implementation of a reconfigurable distributed computer system of high reliability, low redundancy and real-time is also presented as an example.