Publication Type:

Conference Paper

Source:

2010 1st International Conference on Parallel, Distributed and Grid Computing, PDGC - 2010, Solan, p.101-106 (2010)

ISBN:

9781424476725

URL:

http://www.scopus.com/inward/record.url?eid=2-s2.0-79551553061&partnerID=40&md5=c3909e6f7493ffb02e60df32bfae8e7f

Keywords:

Computational task, Computing resource, Earliest deadline first, Enhanced performance, Fault tolerance, Fault-tolerant, Fault-tolerant mechanism, Generic features, Grid computing, Hardware and software, Launch vehicles, Launching, Medical equipment, Nuclear power plants, Offline, Onboard computer system, Optimization, Parallel processing systems, Performance metrics, Processor failures, Programming flexibility, Quality assurance, Rate-monotonic, Real time scheduling, Real-time tasks, Redundancy, Response time (computer systems), Safety critical applications, Safety critical systems, Satellite launch vehicles, Scheduling algorithms, System levels, System reliability, System resources, Task allocation

Abstract:

The safety critical systems used in avionics, nuclear power plants and emergency medical equipments have to meet stringent reliability and temporal demands. Such demands are met with fault tolerant mechanisms, such as hardware and software redundancy. In this paper, we consider a safety critical application, the dual redundant onboard computer(OBC) system of the Indian Satellite Launch Vehicle and propose a scheme to optimize the onboard computing resources without detracting from the system reliability requirements. The redundancy is dealt with at the task allocation level and the slack generated, is used for allocation of more computational tasks, making the scheme very attractive in terms of efficient management of resources. The scheme of task allocation combined with real-time scheduling using Rate Monotonic(RM) and Earliest Deadline First(EDF) provide more programming flexibility and efficiently utilize the system resources. The scheme when implemented gives an efficient offline task allocation for fault-free conditions and flexible fault tolerance strategy during processor failure. The proposed scheme is compared with a traditional dual scheme. The implementation is experimented with a simulation and evaluated using performance metrics to illustrate the enhanced performance capability of the approach. This scheme, extended to multiprocessors with generic features can lead to tremendous throughput in terms of performance and costs. The contributions of this work are a system level algorithm for the implementation of real-time task allocation and scheduling. © 2010 IEEE.

Notes:

cited By (since 1996)0; Conference of org.apache.xalan.xsltc.dom.DOMAdapter@7ff8b6d2 ; Conference Date: org.apache.xalan.xsltc.dom.DOMAdapter@21aad6a1 Through org.apache.xalan.xsltc.dom.DOMAdapter@56f0f54b; Conference Code:83696

Cite this Research Publication

Ra Pillay, Chandran, S. Kb, and Punnekkat, Sc, “Optimizing resources in real-time scheduling for fault tolerant processors”, in 2010 1st International Conference on Parallel, Distributed and Grid Computing, PDGC - 2010, Solan, 2010, pp. 101-106.