Hardware resources contention-aware scheduling of hard real-time multiprocessor systems

Abstract

In hard real-time embedded systems, switching to multicores is a step that most application domains delay as much as possible. This is mainly due to the number of sources of indeterminism, which mainly involve shared hardware resources, such as buses, caches, and memories. In this paper, a new task model that considers the interference that task execution causes in other tasks running on other cores due to memory contention is proposed. We propose a scheduling algorithm that calculates the exact interference. We also analyse and compare existing partitioning algorithms and propose three strategies to allocate tasks to cores to schedule as many tasks as possible and minimise total interference. • Definition of a task model that considers interference delays due to contention of shared hardware resources. • Proposal of a new scheduling algorithm that copes with the new task model. This scheduling algorithm is formulated to be included in any priority-based scheduling algorithm for monocores. • Proposal of three allocation algorithms and comparison with existing ones in terms of schedulability and total utilisation of the system.