Implementing Adaptive Clustered Scheduling in LITMUSRT

In this paper, we develop an adaptive scheduling algorithm for changing the processor shares of tasks on realtime multiprocessor systems where tasks are assigned to clusters of processors. Additionally, we implement this adaptive algorithm as a LITMUS plugin. Our focus is on adaptive systems that are deployed in environments in which tasks may frequently require significant share changes. Prior work on enabling real-time adaptivity on multiprocessors has focused primarily on systems where tasks are scheduled from a global priority queue. The algorithm proposed in this paper use feedback and optimization techniques to determine at runtime which adaptations are needed.