LAUSR

Data deduplication is a lossless compression technology that has been widely used in storage systems for space optimization. However, due to the removal of redundant data, the data deduplication has negative influences on data writing, data reading, and data reliability. In this paper, we propose a multi-objective-based performance evaluation framework to analyze the data deduplication performances and evaluate existing well-known deduplication approaches with multiple performance objectives, including compression ratio, data read performance, data write performance, and data reliability. Based on the proposed multi-objective framework and the obtained evaluation results, we further propose a multi-objective-based optimization method. Though our extensive experimental evaluation driven by real-world data sets, it is shown that this method can improve data read/write performance and data reliability while at the cost of little compression ratio.