Semi-Partitioned Hard Real-Time Scheduling with Restricted Migrations upon Identical Multiprocessor Platforms

TL;DR

This paper introduces a semi-partitioned scheduling algorithm with restricted migrations for hard real-time systems on identical multiprocessors, balancing overhead and system utilization.

Contribution

It proposes a novel semi-partitioned scheduling paradigm allowing limited task migrations with a periodic assignment strategy.

Findings

Reduces runtime overhead compared to global scheduling.

Improves schedulability and system utilization over traditional partitioned scheduling.

Provides a new algorithm for restricted migration in semi-partitioned scheduling.

Abstract

Algorithms based on semi-partitioned scheduling have been proposed as a viable alternative between the two extreme ones based on global and partitioned scheduling. In particular, allowing migration to occur only for few tasks which cannot be assigned to any individual processor, while most tasks are assigned to specific processors, considerably reduces the runtime overhead compared to global scheduling on the one hand, and improve both the schedulability and the system utilization factor compared to partitioned scheduling on the other hand. In this paper, we address the preemptive scheduling problem of hard real-time systems composed of sporadic constrained-deadline tasks upon identical multiprocessor platforms. We propose a new algorithm and a scheduling paradigm based on the concept of semi-partitioned scheduling with restricted migrations in which jobs are not allowed to migrate, but two subsequent jobs of a task can be assigned to different processors by following a periodic strategy.