Performance Analysis of Object Store Systems in a Fog and Edge Computing Infrastructure


Authors: Bastien Confais, Adrien Lebre, and Benoit Parrein

Volume 33 (2017)

Abstract


Fog and Edge computing infrastructures have been proposed as an alternative to the current Cloud Computing facilities to address the latency issue for some applications. The main idea is to deploy smaller data-centers at the edge of the backbone in order to bring Cloud Computing resources closer to the end-usages. While a couple of works illustrated the advantages of such infrastructures in particular for Internet of Things (IoT) applications, the way of designing elementary services that can take advantage of such massively distributed infrastructures has not been yet discussed. In this paper, we propose to deal with such a question from the storage point of view. First, we propose a list of properties a storage system should meet in this context. Second, we evaluate through performance analysis three \o -the-shelf" object store solutions, namely Rados, Cassandra and InterPlanetary File System (IPFS). In particular, we focus (i) on access times to push and get objects under different scenarios and (ii) on the amount of network traffic that is exchanged between the different geographical sites during such operations. We also evaluate how the network latencies influence the access times. Experiments are conducted using the Yahoo Cloud System Benchmark (YCSB) on top of the Grid'5000 testbed. Finally, we show that adding a Scale- Out NAS system on each site improves the access times of IPFS and reduces the amount of traffic between the sites when objects are read locally by reducing the costly DHT access. The simultaneous observation of different Fog sites also constitutes the originality of this work.