Incorporation of optimal timeouts into distributed real-time load sharing

Abstract

Consideration is given to the problem of designing and incorporating a timeout mechanism into load sharing (LS) with state-region change broadcasts in the presence of node failures in a distributed real-time system. Failure of a node is diagnosed by the other nodes through communication timeouts, and the timeout period used to diagnose whether a node is faulty or not usually depends on the dynamic changes in system load, the task attributes at the node, and the state the node was initially in. We formulate the problem of determining the best timeout period T/sub out//sup (i)/ for node i as a hypothesis testing problem, and maximize the probability of detecting node failures subject to a pre-specified probability of falsely diagnosing a healthy node as faulty. The parameters needed for the calculation of T/sub out//sup (i)/ are estimated online by node i using the Bayesian technique and are piggy-backed in its region-change broadcasts. The broadcast information is then used to determine T/sub out//sup (i)/. If node n has not heard from node i for T/sub out//sup (i)/ since its receipt of the latest broadcast from node i, it will consider node i failed, and will not consider any task transfer to node i until it receives a broadcast message from node i again. On the other hand, to further reduce the probability of incorrect diagnosis, each node n also determines its own timeout period T/sub out//sup (n)/, and broadcasts its state not only at the time of state-region changes but also when it has remained within a broadcast interval throughout T/sub out//sup (n)/. >