摘要： 提出了一个在实时分布式系统中有失败结点情况下容错的、动态的、带区域状态变化信息广播的负载共享算法。如果结点 n自从最后一次收到结点i的广播信息以后T(i)out还没有收到结点i的广播信息，就认为结点i 失败，然后调整各正常的结点的优先列表，以保证每个结点被一个也只能是一个结点选作自己的第k个优先结点，以减少任务的失败率。该文主要确定最佳的超时值及时检测一个结点的失败；调整结点的优先列表以处理结点的失败。

关键词: 负载共享, 超时, 假设检验

Abstract: This paper addresses a fault-tolerant, dynamic load sharing (LS) with state-region change broadcasts in the presence of node failures for a distributed real-time system. If node n has not heard from node i for T(i)out since its receipt of the latest broadcast from node i, it will consider node i failed, then modify the preferred list in such a way that each node will be selected as the kth preferred node of one and only one other node. This paper, mainly determines the "best" timeout period though which failure of a node is diagnosed by the other nodes and proposes an algorithm to modify the preferred list in such a way that node failures are tolerated.

中图分类号: 

• TP338.8