A New (k+2, k) Hadamard Minimum Storage Regenerating Code

ZHANG Sina; TANG Xiaohu; LI Jie

doi:10.3969/j.issn.0258-2724.2016.01.026

Volume 29 Issue 1

Jan. 2016

Turn off MathJax

Article Contents

Abstract

References

Journal of Southwest Jiaotong University > 2016 > 29(1): 188-192,200.

TIAN Mingxing, LI Jin, Gao Yuan, LIU Yibin, MIN Yongzhi. Decoupling Operation Mode of Controllable Reactor of Transformer Type[J]. Journal of Southwest Jiaotong University, 2018, 53(3): 620-627. doi: 10.3969/j.issn.0258-2724.2018.03.025

Citation:

ZHANG Sina, TANG Xiaohu, LI Jie. A New (k+2, k) Hadamard Minimum Storage Regenerating Code[J]. Journal of Southwest Jiaotong University, 2016, 29(1): 188-192,200. doi: 10.3969/j.issn.0258-2724.2016.01.026

Citation:

PDF( 0 KB)

A New (k+2, k) Hadamard Minimum Storage Regenerating Code

doi: 10.3969/j.issn.0258-2724.2016.01.026

Received Date: 01 Feb 2015
Publish Date: 25 Jan 2016

Abstract

Abstract

To reduce the storage capacity of nodes in distributed storage systems, a new (k+2, k) Hadamard Minimum Storage Regenerating (MSR) code was constructed. Each coding matrix is related to two values, from which the diagonal elements of this coding matrix are selected. These two values appear in the coding matrix in a repeating pattern, but with different repeating cycles for different matrices. Based on the structure of the coding matrix, a repair strategy was constructed. The repair strategy divides symbols in the failed node into /2 groups with two symbols in each group, then the two symbols are recovered by downloading one symbol from each of the other k+1 nodes. If the two values related to each coding matrix are unequal, the new Hadamard MSR code can optimally repair systematic nodes. If the sum of two values related to each coding matrix is nonzero and the k values are the same, the new Hadamard MSR code can optimally repair the first parity node. If the sum of the inverse of two values related to each coding matrix is one, the new Hadamard MSR code can optimally repair the second parity node. The new code reduces the storage capacity to the bond for Hadamard MSR code. Further, it can optimally repair all systematic nodes and one parity node.
- distributed,
- storage,
- regenerating code,
- MSR code,
- high code-rate,
- optimal,
- repair

FullText(HTML)

致谢: 本文的研究工作得到兰州交通大学优秀科研团队项目(201701)的资助.

References(16)

References

RHEA S, WELLS C, EATON P, et al. Maintenance-free global data storage[J]. IEEE Internet Computing, 2001, 5(5): 40-49.

BHAGWAN R, TATI K, CHENG Y C, et al. Total recall: System support for automated availability management[C]//Symposium Networked Systems Design and Implementation. San Francisco: ACM, 2004: 25-25.

DABEK F, LI Jinyang, SIT E, et al. Designing a DHT for low latency and high throughput[C]//Symposium Networked Systems Design and Implementation (NSDI). San Francisco: ACM, 2004: 85-98

HUANG Cheng, SIMITCI H, XU Yi, et al. Erasure coding in windows azure storage[C]//Usenix annual Technical Conference. Boston: ACM, 2012: 15-26.

DIMAKIS A G, GODFREY P B, WU Yunnan, et al. Network coding for distributed storage systems[J]. IEEE Transactions on Information Theory, 2010, 56(9): 4539-4551.

范文礼,刘志刚. 基于传输效率矩阵的复杂网络节点重要度排序方法[J]. 西南交通大学学报,2014,49(2): 337-342. FAN Wenli, LIU Zhigang. Ranking method for node importance based on efficiency matrix[J]. Journal of Southwest Jiaotong University, 2014, 49(2): 337-342.

DIMAKIS A G, RAMCHANDRAN K, WU Yunnan, et al. A survey on network codes for distributed storage[J]. Proceedings of the IEEE, 2011, 99(3): 476-489.

郝杰,逯彦博,刘鑫吉,等. 分布式存储中的再生码综述[J]. 重庆邮电大学学报:自然科学版,2013,25(1): 30-38. HAO Jie, LU Yanbo, LIU Xinji, et al. Survey for regenerating codes for distributed storage[J]. Journal of Chongqing University of Posts and Telecommunications: Natural Science Edition, 2013, 25(1): 30-38.

PAPAILIOPOULOS D S, DIMAKIS A G, CADAMBE V R. Repair optimal erasure codes through hadamard designs[J]. IEEE Transactions on Information Theory, 2013, 59(5): 3021-3037.

TAMO I, WANG Zhiying, BRUCK J. Zigzag codes: MDS array codes with optimal rebuilding[J]. IEEE Transactions on Information Theory, 2013, 59(3): 1597-1616.

WANG Zhiying, TAMO I, BRUCK J. Long MDS codes for optimal repair bandwidth[C]//Proceedings of IEEE International Symposium on Information Theory. Cambridge: IEEE, 2012: 1182-1186.

TAMO I, WANG Zhiying, BRUCK J. MDS array codes with optimal rebuilding[C]//Proceedings of IEEE International Symposium on Information Theory. St. Petersburg: IEEE, 2011: 1240-1244.

CADAMBE V R, JAFAR S A, MALEKI H, et al. Asymptotic interference alignment for optimal repair of MDS codes in distributed storage[J]. IEEE Transactions on Information Theory, 2013, 59(5): 2974-2987.

CADAMBE V R, HUANG Cheng, LI Jin, et al. Polynomial length MDS codes with optimal repair in distributed storage[C]//The 45th Asilomar Conference on Signals, Systems and Computers (ASILOMAR).Pacific Grove: IEEE, 2011: 1850-1854.

CADAMBE V R, HUANG Cheng, LI Jin. Permutation code: Optimal exact-repair of a single failed node in MDS code based distributed storage systems[C]//Proceedings of IEEE International Symposium on Information Theory Proceedings (ISIT).St. Petersburg: IEEE, 2011: 1225-1229.

TAMO I, WANG Zhiying, BRUCK J. Access versus bandwidth in codes for storage[J]. IEEE Transactions on Information Theory, 2014, 60(4): 2028-2037.

Relative Articles

Supplements(0)

Cited By

Cited by

Periodical cited type(5)

1.	肖鹤玲，郭网媚，王静. 基于再生码的区块链分布式编码方案. 吉林大学学报(工学版). 2022(11): 2685-2697 .
2.	李琛，李琦，高军萍，岳红翠，万梦华. 基于Hadamard向量的新型(k+2, k)MSR码. 河北工业大学学报. 2018(02): 9-13 .
3.	曹凯，文捷. 基于(k+2, k)MSR的多容错低修复带宽编码. 计算机工程. 2018(02): 84-87+91 .
4.	王小红. 网格空间应急信息资源高效调度算法仿真. 计算机仿真. 2017(09): 292-295 .
5.	叶其革，张岚，樊冬梅. 智能变电站多层数据交换调度优化方法研究. 自动化与仪器仪表. 2017(08): 115-117 .

Other cited types(2)

Proportional views

Proportional views

通讯作者: 陈斌, bchen63@163.com

1.
沈阳化工大学材料科学与工程学院沈阳 110142

Get Citation

PDF

XML

Article views(895) PDF downloads(273)

A New (k+2, k) Hadamard Minimum Storage Regenerating Code

doi: 10.3969/j.issn.0258-2724.2016.01.026