De-duplication is an approach to avoid storing data blocks with identical content. It has effectively reduced the disk space for storing large content files. However, it remains challenging to deploy deduplication in a real system, such as a cloud platform setup. We proposed VDFS, a live de-duplication file system that enables de-duplication storage in VM. VM is an open-source cloud environment that is deployed under low-cost commodity hardware settings with limited memory footprints. We will deploy our VDFS prototype as a storage layer in a cloud platform based on Open Stack, and conduct extensive experiments. When compared to an ordinary file system without deduplication, we show that VDFS can save at least 40% of space for storage in cloud environment. We also achieve reasonable performance in importing and retrieving files. In existing process collision may occur due to dual hashing algorithm and time latency while use of large data. Our work justifies the feasibility of deploying VDFS in an open-source cloud. This scheme not only reduces the cloud storage capacity, but also improves the speed of data de-duplication and concentrates on security to data‟s. Furthermore, the signature is computed for every file for verifying the integrity of files.
展开▼
