Driven by applications such as autonomous vehicles, spacecrafts, robotics, and industrial automation, real-time systems are required to implement ever more complex functionalities with high performance, while maintaining the conventional timing predictability, reliability, and cost efficiency. Necessarily, large-scale resource sharing on multiprocessor architectures have to be deployed. Unfortunately, existing protocols that manage shared resources and bound blocking delay have not considered reliability, i.e., how to handle faults. Contention over the shared resources may be seriously aggravated by re-executions that are deployed for satisfying the reliability requirement. Hence, there exists a significant barrier to apply resource sharing in the mission-critical sectors. This talk fills the gap between reliability and resource sharing. Focusing on mixed-criticality systems (MCS), which widely exist in practice and make the problem more challenging, we propose the first fault-tolerant solution in the presence of shared resources. Our aim is to minimize blocking time while satisfying the reliability requirement. A schedulability analysis is reported to provide timing bounds. Compared to the state-of-the-art method, which was developed for fault-tolerant MCS, we improve the system schedulability by an average of 64.5% in stable modes and 50.6% during the mode switch.

常万里教授2020年入选国家海外高层次人才引进计划，任湖南大学正教授，华为高级专家顾问，ACM嵌入式系统专委会秘书长。此前任英国约克大学终身教职，实时系统国家实验室副主任，Bosch专家顾问。博士毕业于德国慕尼黑工大，获最佳博士论文奖，本科新加坡南洋理工大学。近两年发表CCF A类论文18篇，多次获得CCF B类以上会议最佳论文提名。常教授在嵌入式与实时系统领域三大顶级学术会议首次创立工业论文并任主席，任CCF A类会议DAC自动系统领域主席，CCF A类会议RTSS论文评奖委员会委员，英国计算机学会杰出论文奖评审专家。