IR-RBT Codes: A New Scheme of Regenerating Codes for Tolerating Node and Intra-node Failures in Distributed Storage Systems
Jianchao Bian, Shoushan Luo, Wei Li, Yaxing Zha, Yixian Yang · KSII Transactions on Internet and Information Systems · 2019
Traditional regenerating codes are designed to tolerate node failures with optimal bandwidth overhead.However, there are many types of partial failures inside the node, such as latent sector failures.Recently, proposed regenerating codes can also repair intra-node failures with node-level redundancy but incur significant bandwidth and I/O overhead.In this paper, we construct a new scheme of regenerating codes, called IR-RBT codes, which employs intra-node redundancy to tolerate intra-node failures and serve as the help data for other nodes during the repair operation.We propose 2 algorithms for assigning the intra-node redundancy and RBT-Helpers according to the failure probability of each node, which can flexibly adjust the helping relationship between nodes to address changes in the actual situation.We demonstrate that the IR-RBT codes improve the bandwidth and I/O efficiency during intra-node failure repair over traditional regenerating codes but sacrifice the storage efficiency.