Implementing adaptive time-triggered co-operative scheduling framework for highly-predictable embedded systems

摘要

For many real-time embedded systems, Time-Triggered Co-operative (TTC) scheduling algorithms provide simple and reliable solution at low cost. Previous work in this area has focused on the development of a wide range of TTC implementations for various purposes (e.g. for achieving low-jitter characteristics, reducing CPU power consumption or dealing with task-overruns). Despite the great deal of work in this area, it can be said that each previous scheduler implementation was created to address only one particular problem in TTC algorithm. For applications which require extremely high degree of reliability, a combinational TTC architecture - that incorporates multiple features - can be an appropriate solution. This paper describes the implementation of an adaptive, highly-predictable TTC scheduler that addresses both jitter and task-overrun problems simultaneously. Furthermore, the presented scheduler incorporates an online technique for measuring the practical "worst-case execution time" for each task during system runtime. The behavior of the proposed scheduler is compared with a set of previously developed schedulers in terms of timing jitter, task-overrun handling capability and resource requirements for practical real-time implementations.