Partition and Scheduling of the Mixed-Criticality Tasks Based on Probability

Abstract

In the mixed-criticality (MC) system, it is important to achieve better execution quality for the tasks with low criticality (LO tasks) while guaranteeing the completion of tasks with high criticality (HI tasks). To improve the execution of LO tasks, this paper studies the partition and scheduling for dualcriticality tasks on the homogeneous multiprocessor platform. First, we propose a probability MC (PMC) task model that adds a parameter of overload probability for HI tasks to the classic MC model. Second, we optimize the Earliest Deadline First with Virtual Deadline (EDF-VD) algorithm by switching the criticality of the HI tasks in sequence. Third, we analyze the possible cases in an execution period and calculate the expectation of different criticality stages based on the probability theory. Finally, we propose a partitioning algorithm based on probability (PPDC) for tasks with the PMC model. The experiments confirm the effectiveness of our calculations and show that our algorithm has better performance than the existing partition schemes.

Towards Fully Jitterless Applications: Periodic Scheduling in Multiprocessor MCSs Using a Table-Driven Approach

“…A task consists of a series of jobs, with each job inheriting the set of parameters of the task, (T i , D i , L i ), to which it adds its own parameters [27]. Thus, the kth job of task τ i is characterized as…”