Concurrent processes of CDP in object-based file system

Abstract

An object-based storage system - integrating advantages of both NAS and SAN - can be applied in large-capacity, lowcost and large-scale storage systems built from commodity disk devices. The continuous data protection or CDP is a well-known technique that continuously captures or tracks data modifications and stores changes independent of primary data, enabling data recovery - from any point in the past. An efficient file system optimized for CDP plays an important role in object-based storage systems. In this paper, concurrent processes during data backup and data recovery operations are discussed in details. To fully take the advantage of distributed system architectures, we make the concurrent data operations as far as possible during read, write, and recovery processes. A new backup data object placement strategy is present to work in coordination with a replica strategy in object-based distributed file systems. Backup data object can be placed in other object storage servers (or OSS for short) instead of the OSS where the original data is residing, when the backup data object matches certain conditions. For data recovery, we make the related OSSes to concurrently perform data object movement. All these strategies can efficiently reduce system response times.