Real-time Schedule Algorithm with Temporal and Spatial Isolation Feature for Mixed Criticality System
Zubin Hu, Jianchao Luo, Xiyu Fang, Kun Xiao, Bitao Hu, Lirong Chen · 2021
With the continuous development of science and information technology, mixed criticality system(MCS) is more widely used in the embedded devices such as autonomous driving vehicles. The number and variety of programs with different importance in the system are increasing. Previous mixed criticality systems placed applications with different critical levels on different hardware platforms, which was a spatial isolation technique. However, this approach creates additional problems, such as high power consumption and complex hardware design. To reduce the design complexity and cost of mixed criticality systems, embedded operating systems should satisfy the demand that applications with different critical levels would run simultaneously on unique hardware platform such as system on chip(soc). In this paper, we propose a mixed criticality system model and a scheduling strategy with low overhead, high performance, and real-time features for embedded operating system. We implement and experiment them on our own microkernel operating system named Mginkgo. The test results show that our design comes with minimal overhead, and supports temporal-isolated and spatial-isolated.