Software-defined data storage systems. Their advantages and features.

Abstract

Every year the amount of generated data grows exponentially which entails an increase in both the number and capacity of data storage systems. The highest capacity is required for data storage systems that are used to store backups and archives, file storages with shared access, testing and development environments, virtual machine storages, corporate or public web services. To solve such tasks, nowadays manufacturers offer three types of storage systems: block and file storages which have already become a standard used for implementing IT infrastructures, and software-defined storage systems. They allow to create data storages on non-specialized equipment, such as a group of x86-64 server nodes managed by general-purpose operating systems. The main feature of software-defined data storages is the transfer of storage functions from the hardware level to the software level where these storage functions are defined not by physical features of the hardware but by the software selected for specific tasks solving. Today there are three main singled out technologies characterized by scalable architecture that allow to increase efficiency and storage volume through adding new nodes to a single pool: Ceph, DELL EMC VxFlex OS, HP StoreVirtual VSA. Software-defined data storages have the following advantages: fault tolerance, efficiency, flexibility and economy. Utilization of software-defined storages allows to increase efficiency of IT infrastructure and reduce its maintenance costs; to build a hybrid infrastructure that would allow to use internal and external cloud resources; to increase efficiency of both services and users by providing reliable connection by using the most convenient devices; to build a portal as a single point of services and resources control.