Performance Measurement of Distributed Storage on Edge Devices

Edge computing and storage have been proposed as an alternative to current cloud computing infrastructures to address the latter's limitations. However, edge computing services and support for applications based on edge infrastructures are still in the incipient stages. There are numerous storage services for efficient data storage in the cloud. In contrast, few such services exist at the edge. We look at the performance of a cloud storage service Cassandra when deployed on an edge network. In this paper, we analyze Cassandra's performance in three different networks. We vary Cassandra's attributes and the overall conditions in each network to simulate a real-world scenario and study the effect on the total time taken for a particular request. We (a) establish trends for different configurations, (b) discuss the reasoning behind them, and (c) suggest optimal configurations for the networks used, which are important for deploying Cassandra in an edge setting.