Off-campus WSU users: To download campus access dissertations, please use the following link to log into our proxy server with your WSU access ID and password, then click the "Off-campus Download" button below.
Non-WSU users: Please talk to your librarian about requesting this dissertation through interlibrary loan.
Date of Award
Large scale data storage systems have been widely distributed with the ever-increasing amount of data. Over the years, erasure codes have been proven effective and adopted in various data storage systems to provide data protection in large scale data storage systems. On the other hand, data compression has been essentially implemented in computing storage services and network transactions. For the past decade, with the emergence of new storage technologies, the performance of erasure codes and data compression algorithms may soon become a potential bottleneck in the whole system. This dissertation evaluates the performance of some popular erasure codes and proposes a new decoding algorithm for XOR-based erasure codes, with which CPU cache can be utilized more efficiently. With experiments conducted, the proposed new decoding algorithm is proven to improve the decoding performance. Also, two new data compression algorithms, namely SnappyR and LZ4r, are designed to optimize the compression ratio with practically competitive speed.
Chen, Rui, "Practical Algorithms For High-Performance Data Storage Systems" (2021). Wayne State University Dissertations. 3534.