优先级有限时的单处理器静态优先级调度

Uniprocessor Static Priority Scheduling with Limited Priority Levels

静态优先级调度在实际应用中经常受到系统支持的优先级个数的影响,当任务个数多于系统优先级个数时,需要将几个任务优先级映射成一个系统优先级.这可能引起优先级映射问题,使映射前可调度的系统(任务集合)在映射后变得不可调度.解决这一问题需要减少时间复杂度的映射算法和判定映射后任务可调度性的充分必要条件主要存在3种映射算法:(1)按照任务优先级递减顺序进行映射的DPA(decreasingpriorityassignment)算法;(2)按照优先级递增顺序进行映射的IPA(Increasingpriorityassignment)算法;(3)阈值段间映射法(thresholdsegmentmapping,简称TSM).描述了3种算法的实现和判定条件,论述并证明了算法特性,分析并通过仿真实验比较了算法的性能,最后总结了3种算法各自的适用场合.比较结果和结论对实时嵌入式系统的设计和实现具有一定的参考价值.

In practice, the schedulability of static priority scheduling may be reduced when priority levels of the system are insufficient. If a task set requires more priority levels than the system can support, several tasks must be assigned the same priority level. This causes the priority mapping problem. To solve it, a priority mapping algorithm and necessary and sufficient conditions for analyzing the schedulability of a task after priority mapping are needed. There are three kinds of priority mapping algorithms： decreasing priority assignment algorithm, increasing priority assignment algorithm, and threshold segment mapping algorithm. This paper presents implementation and analyzing conditions of algorithms. Properties of the algorithms are also described and showed. Performance of the algorithms is compared through simulations. Simulation results and conclusions are useful for designing and implementing real-time embedded systems.