R&D: Sector Error-Oriented Durability-Aware Fast Repair in Erasure-Coded Cloud Storage

Springer Nature has published, in International Conference on Data Mining and Big Data proceedings, an article written by Yifei Xiao, Shijie Zhou, Linpeng Zhong, School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China, and Zhao Zhang, School of Public Affairs and Administration, University of Electronic Science and Technology of China, Chengdu, China.

Abstract: “There is a variety of erasure-coded data placement schemes that make a great contribution to data repair. To repair data, the operator should replace the failed node with a new node first. However, almost all these schemes assume the node replacement process (NRP) is done quickly, which is not true. Generally, NRP includes failure detection and failure repair, which may take hours or even days. Long delay of replacement may cause the recovered data lost again due to the lack of durability. To improve data durability, we propose a novel scheme called Sector Error-Oriented Durability-Aware Fast Repair (SEDRepair), which carefully couples data migration and data reconstruction in parallel for data repair. We conduct mathematical analysis and compute the optimal repair in our model. The results show that, compared to the traditional erasure coding methods, SEDRepair saves the repair time by up to 60% in most cases and improves data durability while keeping minimal storage.“