With a great diversity of real-time embedded systems, developers often utilize a real-time operating system (RTOS) to efficiently build the systems. However, in exchange for the usefulness, execution of RTOS codes brings runtime overhead, which can influence the system schedulability. In this paper, we propose techniques for guaranteeing schedulability including RTOS runtime overhead. In the proposed techniques, we introduce two servers with planned capacity: periodic management server for invoking periodic tasks and aperiodic management server for aperiodic events such as task completion. Then, we provide the schedulability test considering the servers' utilization. In addition, we show techniques for slack reclaiming to improve the aperiodic application tasks' responsiveness by utilizing capacity (or slack) of the servers which is left unused. The evaluation shows that average response times for aperiodic application tasks can be improved by up to 31.6% while guaranteeing schedulability of periodic tasks, and that larger RTOS overhead leads to more effectiveness of the slack reclaiming.
展开▼
