摘要: 提出一种基于Lebesgue采样方法和弹性调度算法的动态反馈实时调度模型。通过调整实时任务的执行速率,使软实时系统的系统负载始终保持在参考值以下。利用硬件看门狗技术在系统过载时产生中断,实现基于事件的Lebesgue采样。在实时操作系统RTAI中实现该调度模型,并对模型的暂态性能和稳态性能进行分析验证。实验结果表明,该模型不仅保持了系统的稳定性,还能显著降低调度算法的系统开销。
关键词:
动态反馈调,
Lebesgue采样,
弹性调度算法
Abstract: This paper presents a dynamic feedback real-time scheduling model based on Lebesgue sampling and elastic scheduling algorithm. The workload of soft real-time system can be held below the reference value by adjusting the task rate. An interrupt can be triggered while system is overload, and the scheduling model can be regarded as an event-based system. The mechanism is realized by a watch dog. The scheduling model is realized in the RTAI real-time system, and the model’s dynamic characteristics and steady state characteristics are tested. Experimental results of test show the model can reduce the workload of task scheduling, while the system is steady.
Key words:
dynamic feedback scheduling,
Lebesgue sampling,
elastic scheduling algorithm
中图分类号:
秦承刚, 于东, 吴文江, 丁万夫, 胡毅. 基于Lebesgue采样的动态反馈实时调度模型[J]. 计算机工程, 2010, 36(19): 1-4.
QIN Cheng-Gang, XU Dong, TUN Wen-Jiang, DING Mo-Fu, HU Yi. Dynamic Feedback Real-time Scheduling Model Based on Lebesgue Sampling[J]. Computer Engineering, 2010, 36(19): 1-4.