Title: Real-time performance analysis of distributed multithreaded applications in a cluster of ARM-based embedded devices

Authors: George K. Adam

Addresses: Computer Systems Laboratory, Department of Digital Systems, University of Thessaly, Larissa, 41500, Greece

Abstract: The challenges in real-time cluster computing, particularly in computing efficiency and reliability, have evolved significantly due to the increase of Internet of Things (IoT), cloud and edge computing applications. Lately, a number of low-power and low-cost clusters have appeared, based upon single board computers, which deploy multithreading techniques to run in parallel thousands of tasks, to support the ever-increasing demand for timely data processing. However, their real-time performance is still under research. This paper proposes a real-time performance analysis approach for evaluating metrics such as thread execution time, response time, parallel efficiency and speedup. The measurements are based upon recursively generated multithreaded applications running in parallel and distributed across multiple cores within a cluster of Raspberry Pi4, running Linux with real-time support and interconnected on a fast gigabit Ethernet. The experimental results validate the efficiency of the proposed approach and show that real-time support enables higher throughput across all workloads, and lower execution times.

Keywords: cluster computing; real-time; performance analysis; multithreaded applications; embedded devices.

DOI: 10.1504/IJHPSA.2022.127772

International Journal of High Performance Systems Architecture, 2022 Vol.11 No.2, pp.105 - 116

Received: 15 Dec 2021
Received in revised form: 14 Jun 2022
Accepted: 15 Jun 2022
Published online: 16 Dec 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article