Fault-Tolerant Scheduling for Real-Time Embedded Control Systems  

作　　者：Chun-HuaYang GeertDeconinck Wei-HuaGui 

机构地区：[1]CollegeofInformationScience&Engineering,CentralSouthUniversity,Changsha410083,P.R.China [2]ElectricalEngineeringDepartment,KatholiekeUniversiteitLeuven,KasteelparkArenberg10,B-3001Leuven-Heverlee,Belgium

出　　处：《Journal of Computer Science & Technology》2004年第2期191-202,共12页计算机科学技术学报（英文版）

摘　　要：With the increasing complexity of industrial application, an embedded control system (ECS) requires processing a number of hard real-time tasks and needs fault-tolerance to assure high reliability. Considering the characteristics of real-time tasks in ECS, an integrated algorithm is proposed to schedule real-time tasks and to guarantee that all real-time tasks are completed before their deadlines even in the presence of faults. Based on the nonpreemptive critical-section protocol (NCSP), this paper analyzes the blocking time introduced by resource conflicts of relevancy tasks in fault-tolerant multiprocessor systems. An extended schedulability condition is presented to check the assignment feasibility of a given task to a processor. A primary/backup approach and on-line replacement of failed processors are used to tolerate processor failures. The analysis reveals that the integrated algorithm bounds the blocking time, requires limited overhead on the number of processors, and still assures good processor utilization. This is also demonstrated by simulation results. Both analysis and simulation show the effectiveness of the proposed algorithm in ECS.With the increasing complexity of industrial application, an embedded control system (ECS) requires processing a number of hard real-time tasks and needs fault-tolerance to assure high reliability. Considering the characteristics of real-time tasks in ECS, an integrated algorithm is proposed to schedule real-time tasks and to guarantee that all real-time tasks are completed before their deadlines even in the presence of faults. Based on the nonpreemptive critical-section protocol (NCSP), this paper analyzes the blocking time introduced by resource conflicts of relevancy tasks in fault-tolerant multiprocessor systems. An extended schedulability condition is presented to check the assignment feasibility of a given task to a processor. A primary/backup approach and on-line replacement of failed processors are used to tolerate processor failures. The analysis reveals that the integrated algorithm bounds the blocking time, requires limited overhead on the number of processors, and still assures good processor utilization. This is also demonstrated by simulation results. Both analysis and simulation show the effectiveness of the proposed algorithm in ECS.

关 键 词：embedded control system real-time task scheduling FAULT-TOLERANCE relevancy task blocking time 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]