Evaluation of Mixed-Criticality Scheduling Algorithms using a Fair Taskset Generator

[Sophie Quinton]

Title: Evaluation of Mixed-Criticality Scheduling Algorithms using a Fair Taskset Generator

Authors:
Saravanan Ramanathan, Arvind Easwaran (Nanyang Technological University, Singapore)

Abstract:
The problem of scheduling mixed-criticality (MC) task systems is known to be NP-Hard, and as a consequence the performance of MC scheduling algorithms is frequently assessed using experimental evaluations based on randomly generated tasksets. It is therefore important to have a thorough understanding of all the parameters that impact the algorithms and a taskset generation procedure that is fair with respect to those parameters. Although there are a few popular taskset generators, there is no evaluation of the fairness properties of those generators. In fact, there is no existing study on identifying all the parameters that are relevant in the evaluation of MC scheduling algorithms. We address this shortcoming in this paper, and present a set of essential fairness properties for MC taskset generators. We also develop a new taskset generator and show that it satisfies those fairness properties. Finally, we evaluate the performance of multi-core MC scheduling algorithms using the generator, and provide new insights on the performance of those
algorithms with respect to several taskset parameters.

Attached paper:

WATERS_2016_MC-FairGen.pdf

(990.08 KiB) Downloaded 724 times

[saravananr]

Here is the presentation slides.

[saravananr]

Here is the cleaned version of the task set generator used.