Scheduling with Quality of Service and Fairness in Weakly-Hard Real-Time Systems

This paper deals with dynamic scheduling in realtime systems said to be wealkly-hard and which may experience overload. We assume that tasks are periodic and may miss their deadlines, occasionally, as defined by the so-called Skip-Over model. The objective of the scheduler is to provide in line a schedule which provides both Quality of Service and fairness. QoS is a metric of the ratio of periodic task instances which complete before their deadline and fairness is defined in terms of individual success balancing. The work presented here focuses on one skip-over algorithm, namely BWP. The intent of the paper is to show how to improve fairness by combining Earliest Deadline First with two strategies, namely LF ( Last Failure) anf MS ( Minimum Success). An experimental study is reported in order to compare results from these two point of view : fairness and QoS.