Redundant Array of Independent Disks (RAID) system, especially RAID-6, are widely used in enterprise to provide high performance and reliable data accesses. As the age of big data is emerging, it is indispensable to scale a storage system on demand to meet the requirements of increasing storage capacity or improving I/O performance. In recent years, more and more RAID systems adopt solid- state drives (SSD’s) as major storage media to boost I/O performance. However, most existing RAID-6 scaling schemes are designed for hard-disk drives (HDD’s). Due to the characteristics of flash memory, HDD-based scaling schemes cannot be directly applied to SSD-based RAID-6 since these schemes usually incur a large amount of data-migration overheads. In this paper, we propose an efficient scaling scheme, Scale-RAID, for SSD-based RAID-6 storage system. To fit the scaling requirements, we propose the Scale-EVENODD algorithm for the generation of parity data. Taking flash-memory characteristics into consideration, Scale-RAID avoids data migration to minimize the scaling overheads. With the notion of virtual devices, Scale-RAID need not always trigger the scaling procedure whenever new devices are added. We conduct a trace-driven simulation to compare the performance of the proposed Scale-RAID with Scale-RS and RS6. The experiment results showed that the proposed strategy can reduce 75.7%-90.0% write operations and decrease 47.2%-52.3% scaling time. The I/O latency can also be reduced by 47.2%-52.3%.

[1] M. Blaum, J. Brady, J. Bruck, and J. Menon, “Evenodd: an optimal scheme for tolerating double disk failures in raid architectures,” in Computer Archi- tecture, 1994., Proceedings the 21st Annual International Symposium on, Apr 1994, pp. 245–254.
[2] J. S. Plank, “A tutorial on reed-solomon coding for fault-tolerance in raid-like systems,” Softw. Pract. Exper., vol. 27, no. 9, pp. 995–1012, Sep. 1997. [Online]. Available: http://dx.doi.org/10.1002/(SICI)1097- 024X(199709)27:9¡995::AID-SPE111¿3.3.CO;2-Y
[3] P. Corbett, B. English, A. Goel, T. Grcanac, S. Kleiman, J. Leong, and S. Sankar, “Row-diagonal parity for double disk failure correction,” in Proceedings of the 3rd USENIX Conference on File and Storage Technologies, ser. FAST’04. Berkeley, CA, USA: USENIX Association, 2004, pp. 1–1. [Online]. Available: http://dl.acm.org/citation.cfm?id=1973374.1973375
[4] L. Xu and J. Bruck, “X-code: Mds array codes with optimal encoding,” IEEE Transactions on Information Theory, vol. 45, no. 1, pp. 272–276, Jan 1999.
[5] M. Blaum and R. M. Roth, “On lowest density mds codes,” IEEE Transac- tions on Information Theory, vol. 45, no. 1, pp. 46–59, Jan 1999.
[6] A. Goel, C. Shahabi, S. Y. D. Yao, and R. Zimmermann, “Scaddar: an efficient randomized technique to reorganize continuous media blocks,” in Data Engineering, 2002. Proceedings. 18th International Conference on, 2002, pp. 473–482.
[7] W. Zheng and G. Zhang, “Fastscale: Accelerate raid scaling by minimizing data migration,” in Proceedings of the 9th USENIX Conference on File and Stroage Technologies, ser. FAST’11. Berkeley, CA, USA: USENIX Association, 2011, pp. 11–11. [Online]. Available: http://dl.acm.org/citation.cfm?id=1960475.1960486
[8] S. Im, S. Im, S. Im, S. Im, D. Shin, D. Shin, D. Shin, and D. Shin, “Flash- aware raid techniques for dependable and high-performance flash memory ssd,” IEEE Transactions on Computers, vol. 60, no. 1, pp. 80–92, Jan 2011.
[9] J. Huang, X. Liang, X. Qin, P. Xie, and C. Xie, “Scale-rs: An efficient scaling scheme for rs-coded storage clusters,” IEEE Transactions on Parallel and Distributed Systems, vol. 26, no. 6, pp. 1704–1717, June 2015.
[10] G. Zhang, K. Li, J. Wang, and W. Zheng, “Accelerate rdp raid-6 scaling by reducing disk i/os and xor operations,” IEEE Transactions on Computers, vol. 64, no. 1, pp. 32–44, Jan 2015.
[11] “Micronl84128gb,256gb,512gbasync/syncenterprisenandfeatures.” [Online]. Available: http://www.micron.com/parts/nand-flash/enterprise-nand/
[12] L.-P. Chang and C.-D. Du, “Design and implementation of an efficient wear- leveling algorithm for solid-state-disk microcontrollers,” ACM Trans. Design Autom. Electr. Syst., vol. 15, no. 6, December 2009.
[13] L.-P. Chang, “A hybrid approach to nand-flash-based solid-state disks,” Com- puters, IEEE Transactions on, vol. 59, no. 10, pp. 1337 – 1349, October 2010.
[14] UMassTraceRepository, “Oltp applications of two financial institutions.” [Online]. Available: http://traces.cs.umass.edu/index.php/Storage/Storage