Exploiting laxity for heterogeneous multiprocessor real-time scheduling
Hamid Tabatabaee, Narges Khatib-Astaneh, Vahid Salmani, Mahdi Salmani, Amin Milani Fard · 2008
In this paper a new laxity-based algorithm for scheduling real-time tasks on heterogeneous uniform multiprocessors is presented. In the proposed algorithm we have made use of laxity in two ways: Calculating the dynamic priority of tasks, and performing feasibility check. Besides, we have applied processor affinity to reduce the overhead in terms of task migration. The performance of this algorithm is then compared with that of EDF and LLF algorithms. It is shown that our proposed approach not only demonstrates a performance close to that of EDF in non-overloaded conditions but also has supremacy over EDF in overloaded situations in many aspects. Furthermore, it imposes much less overhead on the system.