Utilizing Multi-Level Data Fault Tolerance to Converse Energy on Software-Defined Storage

摘要

In the era of digitalization, people store their data digitally on local or remote storage. To prevent data loss due to disk failures, data fault tolerance mechanisms have been widely deployed to provide different levels of reliability. However, applying data fault tolerance mechanisms incurs extra cost on storage space and energy consumption. Therefore, data with different importance should be stored on storage that provides different levels of fault tolerance to lower the cost. Software-defined storage (SDS) become a viable option since it includes a centralized controller to process data requirements. However, there is little discussion on how to enable multilevel data fault tolerance on single SDS disk group to satisfy different levels of fault tolerance requirement with energy-efficient considerations. %In addition, applying two or more data fault tolerance mechanisms directly on the same disk group could be problematic and not energy efficient. To address this issue, this study enables an energy-efficient multilevel data fault tolerance design on a single disk group. A series of experiments show that the proposed design could reduce the storage system energy consumption significantly when compared with the original architecture.