No abstract

Most of the existing research on multiprocessor mixed-criticality scheduling has focused on ensuring schedulability of the task set when the criticality level of the system increases. Furthermore, upon increasing the criticality level, most of these scheduling approaches suspend the execution of the lower criticality tasks in order to guarantee the schedulability of the higher criticality tasks. Although there exists a couple of approaches to facilitate the execution of some of the lower criticality tasks using the available slack in the system, to the best of our knowledge, there is no efficient mechanism that allows for eventually decreasing the criticality level of the system in order to resume the execution of the suspended lower criticality tasks. We refer to the problem of deciding when and how to lower the criticality level of the system as the "Safe Criticality Reduction" (SCR) problem. In this work, we design two solutions that are independent of the number of criticality levels and the number of processors and prove their correctness. The first protocol can be applied to any fixed task priority scheduler, and an upper-bound on the suspension delay suffered by the lower criticality tasks is presented. The second protocol can be applied to any fixed job priority scheduler and hence dominates the first protocol albeit with a higher run-time overhead. To the best of our knowledge, these are the first solutions for the SCR problem on multiprocessor platforms.