Investigation of Performance and Configuration of a Selected IoT System—Middleware Deployment Benchmarking and Recommendations

Abstract

Nowadays Internet of Things is gaining more and more focus all over the world. As a concept it gives many opportunities for applications for society and it is expected that the number of software services deployed in this area will still grow fast. Especially important in this context are properties connected with deployment such as portability, scalability and balance between software requirements and hardware capabilities. In this article, we present results of practical tests with multiple clients representing sensors sending notifications to an IoT middleware—DeviceHive. Firstly, we investigate performance using two deployment configurations—containerized and bare-metal showing small overhead of the former under different loads by various numbers of IoT clients. We present scaling of the middleware on the server side using various numbers of cores as well as HyperThreading for all aforementioned configurations. Furthermore, we also investigated how containarization affects performance when the system is scaled with various numbers of nodes each using a predefined number of cores, considering memory usage of various configurations. The latter could be found useful when assigning cores to Docker nodes in cloud environments.