基于软件容错的动态实时调度算法

Dynamic Real-Time Scheduling Algorithm with Software Fault-Tolerance

在硬实时系统中,由于任务超时完成将会导致灾难性后果,因而硬实时系统具有严格的时间及可靠性限制条件.目前实时容错调度算法大多针对硬件的容错,很少考虑软件运行的故障.提出了一种类似EDF的软件容错的动态实时调度算法PKSA(ProbingkstepAlgorithm),本算法在任务执行过程中,通过若干试探性检测步骤,提高了任务可执行性的预测,尽可能地避免了任务早期的失败对后续任务的影响,因此提高了任务的完成率,并同时有效地减少了浪费的CPU时间片.通过实验测试,同目前所知的同类算法相比,具有更佳的调度性能调度成本比.

A hard real-time system was usually subject to stringent reliability and timing constraints due to the fact that failure to produce correct results in a timely manner may lead to a disaster. Almost all fault-tolerant scheduling algorithms at present were designed to deal with hardware faults,less of those take possible software faults into account. This paper presents a new software fault-tolerant real-time scheduling algorithm that is similar to EDF,called PKSA. The most important contribution of this algorithm is probing a certain steps during the execution of tasks in order to prevent early failures in execution from triggering failures in the subsequent job executions. Therefore,our algorithm increases the successful completion percentage of primary tasks,and meanwhile decreases the wasted CPU time slots. The simulation experiments show that this algorithm has a better trade-offs between scheduling costs and scheduling performance than well-known algorithms at present.