隨著對大容量高效能RAID系統的需求增加，其可靠度也因此而越來越重要。 高可靠度的RAID等級如RAID 5或RAID 6通常需要使用專屬的硬體加速器；而低成本的軟體RAID又往往伴隨著不佳的效能，使其在業界未曾真正的被重視。 在這篇論文中，我們試著提出一個方法，可以運用多核心架構以及常見的Reed Solomon編碼來達到可接受的軟體RAID效能。 我們對提出的方法做了模擬，在處理器核心數目未少於資料磁碟個數的狀況下，結果顯示出不錯的線性度以及效能增進。 接著我們使用Linux 2.6版核心的系統來實作我們的方法，所測得的真實效能也相當合理。 即使我們是在Linux上做效能評估、分析及實作，我們提出的方法不會受限於某一硬體平台或作業系統，而能夠應用到任何其他的環境上。

With the demand of larger capacity and higher performance for RAID system increased, the reliability of it becomes more and more important. While we usually need to use a dedicated hardware accelerator for high availability RAID level such as RAID 5 and RAID 6, Software RAID never became feasible in the industry because of its low performance despite of its lower cost. In this paper, we try to propose a scheme, which could take advantage of the Multi-core architecture along with the popular Reed Solomon code to achieve acceptable Software RAID performance. We have the simulation result for the proposed scheme; it shows a good scalability and performance improvement if number of the processor cores isn’t less than the number of data disks. And then we use Linux kernel 2.6 based system to implement, and the real world result is also reasonable. The proposed scheme should be independent of hardware platform and operation system, even though the performance evaluation, profiling and the experiment are done in Linux, the scheme could be applied to any other environments.

[1] D.A. Patterson, G. Gibson, and R.H. Katz, “A Case for Redundant Arrays of Inexpensive Disks (RAID),” Proc. ACM SIGMOD, pp. 109-116, Jun. 1988.
[2] P.M. Chen et al., “RAID: High-Performance, Reliable Secondary Storage,” ACM Computing Surveys, Vol. 26, No. 2, pp. 145-188, Jun. 1994.
[3] G.R. Ganger et al., “Disk Arrays: High-Performance High-Reliability Storage Subsystems,” Computer, Vol. 27, No. 3, pp. 30-36, Mar. 1994.
[4] Qin Xin; Miller, E.L.; Schwarz, T.; Long, D.D.E.; Brandt, S.A.; Litwin, W. “Reliability mechanisms for very large storage systems”, Mass Storage Systems and Technologies, 2003. (MSST 2003). Proceedings 20th IEEE/11th NASA Goddard Conference, 7-10, pp.146-156, April 2003.
[5] Jack Y.B. Lee and John C.S. Lui, “Automatic Recovery from Disk Failure in Continuous-Media Servers,” IEEE Transactions on Parallel and Distributed System, Vol. 13, No.5, May 2002
[6] D.A. Patterson, G. Gibson, and R.H. Katz, “Disk System Architectures for High Performance Computing” Proceedings of the IEEE, VOL. 77, NO. 12, pp. 1842-1858, Dec 1989.
[7] J. Menon and D. Mattson, “Performance of Disk Arrays in Transaction Processing Environments,” Proc. 12th Int’l Conf. Distributed Computing Systems, pp. 302-309, June 1992.
[8] Jenwei Hsieh, Christopher Stanton, Rizwan Ali, “Performance Evaluation of Software RAID vs. Hardware RAID for Parallel Virtual File System,” Ninth International Conference on Parallel and Distributed Systems (ICPADS'02), pp. 307, Dec 2002.
[9] Telemetry Channel Coding, Recommendation for Space Data Systems Standards, CCSDS 101.0-B-3, Blue Book, Issue 3, May 1992.
[10] Irving S. Reed, Xuemin Chen, “Error-Control Coding For Data Networks”, Kluwer Academic Publishers, 1999
[11] Intel Inc.,” RAID-6 P+Q Basic Theory“, Sep 2004.
[12] M. Blaum, H. Hao, R. Mattson, and J. Menon, “A Coding Technique for Double Disk Failures in Disk Arrays,” US Patent 5,271,012, Dec. 1993.
[13] M. Blaum, J. Bradt, J. Bruck, and J. Menon, “EVEN-ODD: An Efficient Scheme for Toleranting Double Disk Failures in RAID Architectures,” IEEE Trans. Computers, vol. 44, no. 2, pp. 192-202, Feb. 1995.
[14] L. Xu and J. Bruck, “X-Code: MDS Array Codes with Optimal Encoding,” IEEE Trans. Information Theory, pp. 272-276, Jan. 1999.
[15] L. Xu, V. Bohossian, J. Bruck, and D.G. Wagner, “Low-Density MDS Codes and Factors of Complete Graphs,” IEEE Trans. Information Theory, pp. 1817-1826, Sept. 1999.
[16] M. Blaum, J. Bradt, J. Bruck, J. Menon, and A. Vardy, “The EVENODD Code and Its Generalization: An Efficient Scheme for Tolerating Multiple Disk Failures in RAID Architectures,” High Performance Mass Storage and Parallel I/O, chapter 14, 2002
[17] J.S. Plank. “A tutorial on Reed-Solomon coding for fault-tolerance in RAID-like systems,” Software – Practice& Experience, pp. 995–1012, Sep 1997.
[18] J.S. Plank. “Correction to the 1997 Tutorial on Reed-Solomon Coding,” Technical Report UT-CS-03-504, University of Tennessee, April, 2003.
[19] T.K. Truong, J.H. Jeng, T.C. Cheng, “A New Decoding Algorithm for Correcting Both Erasures and Errors of Reed-Solomon Codes,” IEEE Transactions on Communications, pp.381-388, March 2003.
[20] Ping-Hsun Hsieh, Ing-Yi Chen, Yu-Ting Lin, Sy-Yen Kuo, “An XOR Based Reed-Solomon Algorithm for Advanced RAID Systems,” 19th IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems (DFT'04), pp. 165-172, Oct 2004.
[21] Min-An Song, I-Feng Lan, Sy-Yen Kuo, “An Area-Efficient Architecture of Reed-Solomon Codec for Advanced RAID Systems,”11th International Conference on Parallel and Distributed Systems (ICPADS'05), pp. 620-626, Jul 2005.
[22] Gui-Liang Feng , Robert H. Deng , Feng Bao , Jia-Chen Shen, “New Efficient MDS Array Codes for RAID Part I: Reed-Solomon-Like Codes for Tolerating Three Disk Failures,” IEEE Transactions on Computers, Vol. 54, No. 9, pp. 1071-1080, Sep 2005.
[23] Alessandro Di Marco, Giuseppe Ciaccios, “Efficient Many-to-One Communication for a Distributed RAID,” Sixth IEEE International Symposium on Cluster Computing and the Grid (CCGRID'06), pp. 438-445, May 2006.