Adding robustness in dynamic preemptive scheduling

In this paper we introduce a robust earliest deadline scheduling algorithm for deal ing with hard aperiodic tasks under overloads in a dynamic realtime environment The algorithm synergistically combines many features including dynamic guarantees graceful degradation in overloads deadline tolerance resource reclaiming and dy namic reguarantees A necessary and sucient schedulability test is presented and an ecient On guarantee algorithm is proposed The new algorithm is evaluated via simulation and compared to several baseline algorithms The experimental results show excellent performance of the new algorithm in normal and overload conditions Static realtime systems are designed for worst case situations Assuming that all the assumptions made in the design and analysis are correct we can say that the level of guarantee for these systems is absolute and all tasks will make their deadlines Unfortunately static systems are not always possible becaus