Toward a Practical Regularity-based Model

Most Hierarchical Real-time Scheduling (HiRTS) techniques have focused on temporal resource partitions in which time units are periodically distributed. Although such periodic partitions could provide great flexibility for the resource-level scheduling, engineers face significant obstacles when trying to determine the schedulability of real-time tasks running on them. The main reason is that periodic partitions fail to effectively bound the difference between the ideal and the actual resource allocation. To solve this problem, some researchers introduced the Regular Partition, a type of temporal resource partition that is almost evenly distributed. Recent research has shown that it achieves maximal transparency for task scheduling—some classical real-time scheduling problems on a regular partition can be easily transformed into equivalent problems on a dedicated single resource. However, the resource partitioning problem for regular partitions is much more complicated than the one for periodic partitions. Based on a practical two-layer HiRTS platform, this article introduces MulZ (Multiple Z-seqences), which is the first to solve this problem with a partitioned scheduling strategy. By using a more complicated approximation methodology, our experimental results show that MulZ outperforms the current best global scheduling algorithm on this problem. After that, it compares the overall performance of the periodic partition and the regular partition. We conclude that the regular partition is a better choice for the integration of real-time applications.