Abstract
It is well known that erasure coding can be used in storage systems to efficiently store data while protecting against failures. Conventionally, the design of erasure codes has focused on the tradeoff between redundancy and reliability. Under this criterion, an maximum distance separable(MDS) code has optimal redundancy. In this paper, we address a new class of MDS array codes for tolerating triple node failures by extending the row diagonal parity(RDP) code, named the RDDP(row double diagonal parity) code. The RDDP code takes advantages of good performances of the RDP code with balanced I/O. A specific triple-erasure decoding algorithm to reduce decoding complexity is depicted by geometric graph, and it is easily implemented by software and hardware. The theoretical analysis shows that the comprehensive properties of the RDDP code are optimal, such as encoding and decoding efficiency, update efficiency and I/O balance performance.
Similar content being viewed by others
References
Li G J. The scientific value of big data research [J]. China Computer Federation Communication, 2012, 8(9): 8–15(Ch).
MacWilliams F J, Sloane N J A. The Theory of Error Correcting Codes [M]. New York: Elsevier Science & North Holland Publishing Company, 1977: 32–34.
Wang Yijie, Sun Weidong, Zhou Song, et al. Key technologyies of distributed storage for cloud computing [J]. Journal of Software, 2012, 23(4): 962–986.
Luo Xianghong, Shu Jiwu. Summary of research for erasure code in storage system [J]. Journal of Compute Research and Development, 2012, 49(1): 1–11.
Blaum M, Brady J, Bruck J, et al. EVENODD: An efficient scheme for tolerating double disk failures in RAID architectures [J]. IEEE Transactions Compute, 1995, 44(2): 192–202.
Xu L, Bruck J. X-code: MDS array codes with optimal encoding [J]. IEEE Transactions on Information Theory, 1999, 45(1): 272–276.
Xu L, Bohossian V, Bruck J, et al. Low density MDS codes and factors of complete graphs [J]. IEEE Trans on Information Theory, 1999, 45(6): 1817–1826.
Li Mingqiang, Shu Jiwu. C-Codes: Cyclic lowest-density MDS array codes constructed using starters or RAID 6 [EB/OL]. [2011-10-11]. http://arxiv.org/abs/1104.2547.
Corbett P, English B, Goel A, et al. Row diagonal parity for double disk failure [C]//Proc the Third USENIX Conference on File and Storage Technologies, Berkeley: IEEE Press, 2004: 1–14.
Wu Chentao, Wan Shenggang, He Xubin, et al. H-Code: A hybrid MDS array code to optimize partial stripe writes in RAID-6 [C]//Proc the IEEE Congress on International Parallel & Distributed Processing Symposium. Alaska: IEEE Press, 2011: 782–793.
Wu Chentao, He Xubin, Wu Guanying, et al. HDP code: a horizontal-diagonal parity code to optimize I/O load balancing in RAID-6 [C]//Proc the IEEE/IFIP 41 st International Conference on Dependable Sytem&Network (DSN), Hong Kong: IEEE Press, 2011: 209–220.
Li M, Shu J, Zheng W. GRID codes: Strip-based erasure code with high fault tolerance for storage systems [J]. ACM Transactions on Storage, 2009, 4(4): 1–22.
Hafner J L. HoVer erasure codes for disk arrays [C]//Proc DSN-06: International Conference on Dependable Systems and Networks. Philadelphia: IEEE Press, 2006: 217–226.
Hafner J L. WEAVER codes: Highly fault tolerant erasure codes for storage systems [C]//Proceedings of FAST-2005: 4th Usenix Conference on File and Storage Technologies. San Francisco: IEEE Press, 2005: 211–224.
Blaum M, Bruck J, Vardy A. MDS array codes with independent parity symbols [J]. IEEE Transactions on Information Theory, 1996, 42(2): 529–542.
Sheng L, Gang W, Stones D S, et al. T-code: 3 erasure longest lowest-density MDS codes [J]. IEEE Journal on Selected Areas in Communications, 2010, 28(2): 289–296.
Feng G L, Deng R, Bao F, et al. New efficient MDS array codes for RAID, part I: Reed-Solomon-Like codes for tolerating three disk failures [J]. IEEE Trans Computers, 2005, 54(9): 1071–1080.
Huang C, Xu L. STAR: An efficient coding scheme for correcting triple storage node failures [C]//Proc the 4th USENIX Conference on File and Storage Technologies. Berkeley: IEEE Press, 2005: 197–210.
Wan Wunan, Wu Zheng, et al. RAID-EEOD: The study of data placement based on toleration on triple failures array codes in RAID [J]. Chinese Journal of Compute, 2007, 30(10): 1–10.
Bloemer J M, Kalfane M, Karpinski R, et al. An XOR-Based Erasure-Resilient Coding Scheme [R]. Berkeley: International Computer Science Institute, 1995.
Author information
Authors and Affiliations
Corresponding author
Additional information
Foundation item: Supported by the National Natural Science Foundation of China (60873216) and the Key Project of Sichuan Provincial Department of Education (12ZA223)
Biography: WAN Wunan, female, Professor, Ph.D., research direction: network storage and information security.
Rights and permissions
About this article
Cite this article
Wan, W., Yang, W. & Suo, W. RDDP: An efficient MDS array code on toleration triple node failures in storage system. Wuhan Univ. J. Nat. Sci. 19, 161–168 (2014). https://doi.org/10.1007/s11859-014-0995-3
Received:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11859-014-0995-3
Key words
- maximum distance separable(MDS) array code
- RAID(redundant array of independent disks)
- triple node failures