Issue No. 09 - September (2000 vol. 49)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/12.869322
<p><b>Abstract</b>—Real-time systems are being increasingly used in several applications which are time-critical in nature. Fault tolerance is an essential requirement of such systems, due to the catastrophic consequences of not tolerating faults. In this paper, we study a scheme that guarantees the timely recovery from multiple faults within hard real-time constraints in uniprocessor systems. Assuming earliest-deadline-first scheduling (EDF) for aperiodic preemptive tasks, we develop a necessary and sufficient feasibility-check algorithm for fault-tolerant scheduling with complexity <tmath>$O(n^2 \cdot k)$</tmath>, where <tmath>$n$</tmath> is the number of tasks to be scheduled and <tmath>$k$</tmath> is the maximum number of faults to be tolerated.</p>
Real-time scheduling, earliest-deadline first, fault-tolerant schedules, fault recovery.
Frank Liberato, Rami Melhem, Daniel Mossé, "Tolerance to Multiple Transient Faults for Aperiodic Tasks in Hard Real-Time Systems", IEEE Transactions on Computers, vol. 49, no. , pp. 906-914, September 2000, doi:10.1109/12.869322