The Design and Implementation of Multi-Cloud Based Distributed Storage Platform with Random Linear Coding

Nowadays, distributed storage systems have been widely used in the world, e.g, Google Drive, OneDrive, DropBox, Baidu PCS, etc.. Although these cloud storage services significantly facilitate the file storage for users, the performance of them varies widely when using in different countries. For example, Google Drive has high upload/download speed in America while it has very low upload/download speed in China. Therefore, to enhance the reliability and security of the cloud storage, in this paper, we firstly design a multi-cloud based distributed storage platform, named as, Normal Drive, by utilizing random linear coding and APIs provided by multiple cloud disks. We then implement the Normal Drive and conduct extensive evaluation from different aspects in five different locations around the world to test the performance of it. The experimental results show that the proposed Normal Drive can significantly improve the transmission performance and enhance the reliability of file storage when comparing with single-cloud based distributed storage system.