Adaptive Real-Time Scheduling of Dynamic Multiple-Criticality Applications on Heterogeneous Distributed Computing Systems

Abstract

In this paper, we first propose laxity-based strategy that prioritizes applications based on the laxity of meeting their deadlines. Application with the least laxity will have the highest scheduling priority. Calculating the application laxity will consume some computation time, which may not be practicable for the online implementation. To overcome this problem, we further propose transferring the application deadline to its inside tasks, which makes the laxity calculation easier. We also apply the laxity-based scheduling algorithm to schedule applications with multiple criticalities. Towards the challenge of reconciling timing requirements from different criticality applications, system mode-switch scheme and virtual deadlines are adopted to preferentially guarantee high-critical applications when system is overloaded. Experimental results demonstrate that on the one hand our proposed algorithms can greatly reduce the deadline misses, and on the other hand timing requirements of high-critical applications can be more stringently guaranteed compared with low-critical applications.