Fault-tolerant scheduling in distributed real-time systems

Abstract

In distributed systems, a real-time task has several subtasks which need to be executed at different nodes. Some of these subtasks can be executed in parallel on different nodes without violating their precedence relationships, if any, among them. To better exploit the parallelism, it becomes necessary to assign separate deadlines to subtasks and schedule them independently. We use three subtask deadline assignment policies which we have introduced earlier [4], [7] to develop a bidding-based fault-tolerant scheduling algorithm for distributed real-time systems. A local scheduler which resides on each node, tries to determine a schedule for each subtask according to the primary-backup approach. In this paper we discuss the algorithm and present the results of simulation studies conducted to establish the efficacy of our algorithm.