Irregular flat XOR codes for reducing repair bandwidth of multi-point distributed storage systems

To ensure the reliability of distributed storage systems, we studied network bandwidth-aware multiple fault tolerant erasure codes. A flat XOR code is one of the sparse graph codes designed for distributed storage systems. It encodes and decodes data by exclusive OR (XOR) operation with low complexity. However, conventional construction methods of flat XOR codes are not optimal in terms of repair bandwidth. In this paper, we propose two novel constructions of irregular flat XOR code that can remarkably reduce repair bandwidth compared to conventional flat XOR codes and Reed-Solomon codes. Our irregular flat XOR codes also reduce repair bandwidth compared to flat XOR codes designed by the Monte-Carlo method.

[1]  Jason K. Resch,et al.  Reliability Models for Highly Fault-tolerant Storage Systems , 2013, ArXiv.

[2]  Xiaozhou Li,et al.  Flat XOR-based erasure codes in storage systems: Constructions, efficient recovery, and tradeoffs , 2010, 2010 IEEE 26th Symposium on Mass Storage Systems and Technologies (MSST).

[3]  Alexandros G. Dimakis,et al.  Network Coding for Distributed Storage Systems , 2007, IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications.

[4]  John Kubiatowicz,et al.  Erasure Coding Vs. Replication: A Quantitative Comparison , 2002, IPTPS.

[5]  Minghua Chen,et al.  Pyramid Codes: Flexible Schemes to Trade Space for Access Efficiency in Reliable Data Storage Systems , 2007, Sixth IEEE International Symposium on Network Computing and Applications (NCA 2007).

[6]  Radford M. Neal,et al.  Near Shannon limit performance of low density parity check codes , 1996 .