
Reducing Fragmentation for In-line Deduplication Backup Storage via Exploiting Backup History and Cache Knowledge
Abstract
We propose Reducing Fragmentation for In-line Deduplication Backup Storage via Exploiting Backup History and Cache Knowledge. HAR exploits historical information in backup systems to accurately identify and reduce sparse containers, and CAF exploits restore cache knowledge to identify out – of-order containers that hurt performance restore. In datasets where out – of-order containers are dominant, CAF efficiently complements HAR.
System Configuration
Platform : cloud computing
Conclusion
Hybrid cloud storage is useful to further improve performance in datasets where out – of-charge containers are dominant. To avoid a significant decrease in the hybrid scheme’s deduplication ratio, we develop a two-algorithm such as container marker algorithm and history-conscious rewriting algorithm to exploit backup history and cache knowledge. With the help of CMA, the hybrid scheme significantly improves the deduplication ratio without reducing restore performance.