The Online Optimization Strategy And Simulation Of Preemption Overhead In Hard Real-time Scheduling

The embedded system has been widely applied to people's lives and production areas. In the hard real-time embedded systems, the preemptions of tasks not only lead to the context-switching time spending of the operating system, and other resources to reduce bandwidth and waste energy consumption. How to guarantee the real-time character of system, optimize the preemption overhead of hard real-time task scheduling and improve the system performance are the main issue in this paper.In this paper, under the universal periodic task model of real-time systems, the author analyzes the timing relationship of fixed priority and dynamic priority scheduling and the preemption relationship among tasks. While respectively doing the quantitative analysis to the suspending time of the RM and EDF scheduling preemption action, export the blocked task set obstructed by low priority tasks and the determinant condition to avoid the preemption in the arbitrary preemption moment by postponing high-priority tasks in hard real-time system.This paper presents an online optimization strategy of hard real-time task scheduling preemption spending. By the TORSCHE toolbox of Matlab, the author build a simulation test environment and conduct the simulation test to the Optimization Strategies. And the data compared with the simulation data of the standard RM, EDF scheduling model and the preemption threshold model.The Simulation experimental results show that, the hard real-time task scheduling seizing the online optimization strategy presented by this paper can effectively reduce the number of preemptions in the system operation. While to ensure the task scheduling, effectively reduce the number of task preemptions in the different scheduling algorithms and the preemption overhead.