Real-time semi-partitioned scheduling of fork-join tasks using work-stealing

Abstract

This paper extends the work presented in Maia et al. (Semi-partitioned scheduling of fork-join tasks using work-stealing, 2015) where we address the semi-partitioned scheduling of real-time fork-join tasks on multicore platforms. The proposed approach consists of two phases: an offline phase where we adopt a multi-frame task model to perform the task-to-core mapping so as to improve the schedulability and the performance of the system and an online phase where we use the work-stealing algorithm to exploit tasks' parallelism among cores with the aim of improving the system responsiveness. The objective of this work is twofold: (1) to provide an alternative scheduling technique that takes advantage of the semi-partitioned properties to accommodate fork-join tasks that cannot be scheduled in any pure partitioned environment and (2) to reduce the migration overheads which has been shown to be a traditional major source of non-determinism for global scheduling approaches. In this paper, we consider different allocation heuristics and we evaluate the behavior of two of them when they are integrated within our approach. The simulation results show an improvement up to 15% of the proposed heuristic over the state-of-the-art in terms of the average response time per task set.

Reducing the Interprocessors Migrations of the EKG Algorithm

“…To overcome the problem of the partitioned approach and increase the utilization rate of the system, recent works [6,7,8,9,10] have introduced the semi-partitioning scheduling in which most of tasks are assigned to particular processors as the partitioned scheduling, but the remaining tasks (unasigned tasks) are allowed to migrate between processors. In other words, each remaining task is splitted into a set of sub-tasks and each one of them is affected to a processor.…”