An EDF Interrupt Handling Scheme for Real-Time Kernel: Design and Task Simulation

Authors:
Peng Liu;Ming Cai;Tingting Fu;Jinxiang Dong
Affiliations:
Institute of Artificial Intelligence, Zhejiang University, Hangzhou, 310027, PRC;Institute of Artificial Intelligence, Zhejiang University, Hangzhou, 310027, PRC;Institute of Graphics and Image, Hangzhou Dianzi University, Hangzhou, 310018, PRC;Institute of Artificial Intelligence, Zhejiang University, Hangzhou, 310027, PRC
Venue:
ICCS '07 Proceedings of the 7th international conference on Computational Science, Part IV: ICCS 2007
Year:
2007

Citing 6
Cited 0

Interrupts as threads

ACM SIGOPS Operating Systems Review
Distributed Fault-Tolerant Real-Time Systems: The Mars Approach

IEEE Micro
Handling Interrupts with Static Scheduling in an Automotive Vehicle Control System

RTCSA '98 Proceedings of the 5th International Conference on Real-Time Computing Systems and Applications
Non-Preemptive Interrupt Scheduling for Safe Reuse of Legacy Drivers in Real-Time Systems

ECRTS '05 Proceedings of the 17th Euromicro Conference on Real-Time Systems
Predictable Interrupt Management for Real Time Kernels over conventional PC Hardware

RTAS '06 Proceedings of the 12th IEEE Real-Time and Embedded Technology and Applications Symposium
In-Line Interrupt Handling and Lock-Up Free Translation Lookaside Buffers (TLBs)

IEEE Transactions on Computers

Quantified Score

Hi-index	0.00

Visualization

Abstract

Traditional model of interrupt managemnent has been used for several decades. But it is often incapacity to incorporate reliability and temporal predictability demanded on real-time systems. Many solutions have been proposed to improve efficiency of interrupt handling such as In-line Interrupt Handling and Predictable Interrupt Management In this paper we propose a model that schedules interrupts in terms of their deadlines. Hard priorities of IRQs are still left to hardware. We only manager interrupts that can enter the kernel space so that hard real-time can be assured. Each interrupt will be scheduled only before its first execution according to their arrival time and deadlines so that the scheme is very simple and easy to be implemented. The scheme tries to make as many as possible ISRs finish their work within the time limit. Finally we do some experiments, which prove there is a big decrease of nested overtime interrupts, by means of task simulation on VxWorks.