An optimal spin-lock priority assignment algorithm for real-time multi-core systems

Support for exclusive access to shared (global) resources is instrumental in the context of embedded real-time multi-core systems, and mechanisms for achieving such access must be deterministic and efficient. There exist two traditional approaches for multiprocessors when a task requests a global resource that is locked by a task on a remote core: a spin-based approach, i.e. non-preemptive busy waiting for the resource to become available, and a suspension-based approach, i.e. the task relinquishes the processor. A suspension-based approach can be viewed as a spin-based approach where the lowest priority on a core is used during spinning, similar to a non-preemptive spin-based approach where the highest priority on a core is used. By taking such a view, we previously provided a general model for spinning, where any arbitrary priority can be used for spinning, i.e. from the lowest to the highest priority on a core. Targeting partitioned fixed-priority preemptive scheduled multiprocessors and spin-based approaches that use a fixed priority for spinning per core for all tasks, we aim at increasing the schedulability of multiprocessor systems by using the spin-lock priority per core as parameter. In this paper, we present (i) a generalization of the traditional worst-case response-time analysis for non-preemptive spin-based approaches addressing an arbitrary but fixed spin-lock priority per core, (ii) an optimal spin-lock priority assignment (OSPA) algorithm per core, i.e. an algorithm that will find a fixed spin-lock priority per core that will make the system schedulable, whenever such an assignment exists and, (iii) comparative evaluations of the OSPA algorithm with the spin-based and suspension-based approaches where OSPA showed up to 38% improvement compared to both approaches.1