Feedback-Controlled Adaptive Multiprocessor Real-Time Systems

Abstract We develop an adaptive feedback-controlled scheduling algorithm for changing,the processor shares of tasksóa process called reweightingóon,real-time multiprocessor,platforms. Our particular focus is reweighting schemes,that are deployed in environments in which tasks may frequently require signicant share changes. Prior work on enabling real-time adaptivity on multiprocessors has focused exclusively on scheduling algorithms that can enact needed adaptations. The algorithm proposed in this paper uses feedback-control techniques to determine at runtime which adaptations are needed.