A Weakly Hard Real-Time Tasks on Global Scheduling of Multiprocessor Systems

Real-time tasks can be classified into three categories, based on the "seriousness" of deadline misses - hard, soft and weakly hard real-time tasks. The consequences of a deadline miss of a hard real-time task cannot be accepted whereas soft real-time tasks tolerate "some" deadline misses. While, in a weakly hard real-time task, the distribution of its met and missed deadlines is stated and specified precisely. Due to the complexity and significantly increased functionality in system computation, attention has been given to multiprocessor scheduling, comprised of several processors. Due to the fact that in multiprocessor, there have more than one processor, algorithms which can cater higher computational complexity for task allocation and for task migration are highly required. Thus, the sufficient and efficient scheduling algorithm supported by accurate schedulability analysis technique is presented to provide weakly hard real-time guarantees. In this paper, a schedulability analysis to schedule weakly hard real-time tasks has been proposed by using the global multiprocessor scheduling technique, called multiprocessor response time analysis combining with the exact analysis, named hyperperiod analysis and deadline models; weakly hard constraints and mu-pattern under static priority scheduling. Then, the Matlab simulation tool is used in order to validate the result of analysis. From the performance evaluation results, it proved that the proposed approach is satisfied the tasks deadlines with less number of misses.