Architecting a Software-Defined Storage Platform for Cloud Storage Service

Abstract

The advent of cloud, big data, and mobile creates fast-growing demand of storage. Cloud service providers and data centers are looking for cost-effective storage solution alternative to traditional high-cost embedded-system based storages to meet the need of newly emerging applications, such as messaging, video streaming, data analytics, etc. In particular, they are facing the challenge of lowering cost by accommodating multi-workload on a single instance of storage without compromising workload performance requirements. Software-defined storage (SDS) is a new generation of storage system. Unlike the traditional embedded-system based storages, the SDS uses a software-stack above commodity hardware to provide more valuable and cost-effective features. To meet the challenge the cloud service providers and the data centers are facing, the architecture of a new SDS platform called Federator is proposed in this paper. This paper argues that the architecture of a SDS platform should have three main characteristics: 1. The separation of the control and data path, 2. Self-configuration of storage resources, and 3. Restful APIs for new business extension. A new approach for self-configurable SDS is designed within Federator. This approach includes two types of neural network, which provides optimal storage resource configuration for any type of application. With the clear separation of the control and the data path, the intelligent self-configuration technologies, and the standard Restful API, Federator is expected to better meet the requirements of the new applications in ever-changing computing environments.