TCPS: A Task and Cache-aware Partitioned Scheduler for Hard Real-time Multi-core Systems

Shared caches in multi-core processors seriously complicate the timing verification of real-time software tasks due to the task interference occurring in the shared caches. Explicitly calculating the amount of cache interference among tasks and cache partitioning are two major approaches to enhance the schedulability performance in the context of multi-core processors with shared caches. The former approach suffers from pessimistic cache interference estimations that subsequently result in suboptimal schedulability performance, whereas the latter approach may increase the execution time of tasks due to a lower cache usage, also degrading the schedulability performance.

In this paper, we propose a heuristic partitioned scheduler, called TCPS, for real-time non-preemptive multi-core systems with partitioned caches. To achieve a high degree of schedulability, TCPS combines the benefits of partitioned scheduling, relieving the computing resources from contention, and cache partitioning, mitigating cache interference, in conjunction with exploiting task characteristics. A series of comprehensive experiments were performed to evaluate the schedulability performance of TCPS and compare it against a variety of global and partitioned scheduling approaches. Our results show that TCPS outperforms all of these scheduling techniques in terms of schedulability, and yields a more effective cache usage and more stable load balancing.