Run and Be Safe: Mixed-Criticality Scheduling with Temporary Processor Speedup

Mixed-Criticality systems are arising due to the push from several major industries including avionics and automotive, where functionalities with different safety criticality levels are integrated into a modern computing platform to reduce size, weight and energy. The state-of-the-art research has focused on protecting critical tasks under the threat of task overrun, which is achieved by killing less critical tasks or degrading their services to free system resources to guarantee critical tasks. We take in this paper a different approach to protecting critial tasks by embracing rich features of modern computing platforms. In particular, we explore dynamic processor speedup to aid the scheduling of mixed-criticality systems. We show that speedup in situation of overrun can not only help to protect the timeliness of critical tasks, but also to improve the degraded services for less critical tasks. Furthermore, we show that speedup is even more attractive as it can help the system to recover faster to normal operation. Thus, speedup could only be temporarily required and incur low cost. The proposed techniques are validated by both theoretical analysis and experimental results with an industrial flight management system and extensive simulations.