Several researches have been proposed and focus on hybrid storage systems, most
of the researches used hard-disk drives (HDDs) as the primary storage devices and solid-state drives (SSDs) as a cache to improve the performance of the storage systems. Some of researches used SSDs as the primary storage devices and HDDs as a write bu er for writing random requests to extend the overall lifetime of the storage systems. However, there are no any previous researches considered
the factor that in state-of-art or near future SSD not only read speed but also
write speed are overwhelming HDD. Most of the managements of these researches
proposed are out-of-date, they do not fully exploiting the read/write performance of SSD. In this paper, we proposed a novel management strategy that we try to use HDD as a bu er for garbage collection of SSD to improve the overall
lifetime of the storage system and meanwhile maintaining the performance of the
storage system at SSD level. The experiment results show that we improved
the overall lifetime of the hybrid storage system by 23% to 409% under di erent
traces. And we proved that the performance of the proposed stragegy is not e ect
by di erent characteristics of workloads. We also used the strategy we designed
that reclaiming data from HDD back to SSD to achieve inter-wear leveling of the
system. The proposed management not only provided lifetime extend by reducing
unnecessary writes but also maintained the performance at SSD level and achieved
great intra/inter-wear leveling of the hybrid storage system.

Several researches have been proposed and focus on hybrid storage systems, most
of the researches used hard-disk drives (HDDs) as the primary storage devices and solid-state drives (SSDs) as a cache to improve the performance of the storage systems. Some of researches used SSDs as the primary storage devices and HDDs as a write bu er for writing random requests to extend the overall lifetime of the storage systems. However, there are no any previous researches considered
the factor that in state-of-art or near future SSD not only read speed but also
write speed are overwhelming HDD. Most of the managements of these researches
proposed are out-of-date, they do not fully exploiting the read/write performance of SSD. In this paper, we proposed a novel management strategy that we try to use HDD as a bu er for garbage collection of SSD to improve the overall
lifetime of the storage system and meanwhile maintaining the performance of the
storage system at SSD level. The experiment results show that we improved
the overall lifetime of the hybrid storage system by 23% to 409% under di erent
traces. And we proved that the performance of the proposed stragegy is not e ect
by di erent characteristics of workloads. We also used the strategy we designed
that reclaiming data from HDD back to SSD to achieve inter-wear leveling of the
system. The proposed management not only provided lifetime extend by reducing
unnecessary writes but also maintained the performance at SSD level and achieved
great intra/inter-wear leveling of the hybrid storage system.

[1] \128gb, 256gb, 512gb async/sync enterprise nand features,"
http://www.micron.com/parts/nand-
ash/enterprise-nand/.
[2] An Introduction to Solid State Drive Performance, Evaluation and Test,
SNIA, 2013.
[3] Dell Drive Characteristics and Metrics, Dell Inc., 2013.
[4] J.-W. Hsieh, H.-Y. Lin, and D.-L. Yang, \Multi-channel architecture-based
ftl for reliable and high-performance ssd," IEEE Transactions on Computers,
vol. 99, no. PrePrints, p. 1, 2013.
[5] E. Gal and S. Toledo, \Algorithms and data structures for
ash memories,"
ACM Comput. Surv., vol. 37, no. 2, pp. 138{163, Jun. 2005.
[6] A. Kawaguchi, S. Nishioka, and H. Motoda, \A
ash-memory based le sys-
tem," in USENIX Winter, 1995, pp. 155{164.
[7] D. Jung, Y.-H. Chae, H. Jo, J.-S. Kim, and J. Lee, \A group-based wear-
leveling algorithm for large-capacity
ash memory storage systems," in Pro-
ceedings of the 2007 International Conference on Compilers, Architecture,
and Synthesis for Embedded Systems, ser. CASES '07. New York, NY, USA:
ACM, 2007, pp. 160{164.
[8] N. Agrawal, V. Prabhakaran, T. Wobber, J. D. Davis, M. Manasse, and
R. Panigrahy, \Design tradeo s for ssd performance," in USENIX 2008 An-
nual Technical Conference on Annual Technical Conference, ser. ATC'08.
Berkeley, CA, USA: USENIX Association, 2008, pp. 57{70.
[9] X.-Y. Hu, E. Eleftheriou, R. Haas, I. Iliadis, and R. Pletka, \Write ampli -
cation analysis in
ash-based solid state drives," in Proceedings of SYSTOR
2009: The Israeli Experimental Systems Conference, ser. SYSTOR '09. New
York, NY, USA: ACM, 2009, pp. 10:1{10:9.
[10] F. Chen, D. A. Koufaty, and X. Zhang, \Hystor: Making the best use of
solid state drives in high performance storage systems," in Proceedings of the
International Conference on Supercomputing, ser. ICS '11, New York, NY,
USA, 2011, pp. 22{32.
[11] I. Koltsidas and S. D. Viglas, \Flashing up the storage layer," Proc. VLDB
Endow., vol. 1, no. 1, pp. 514{525, Aug. 2008.
[12] H. Jo, Y. Kwon, H. Kim, E. Seo, J. Lee, and S. Maeng, \Ssd-hdd-hybrid
virtual disk in consolidated environments," in Proceedings of the 2009 In-
ternational Conference on Parallel Processing, ser. Euro-Par'09. Berlin,
Heidelberg: Springer-Verlag, 2010, pp. 375{384.
[13] W. Xiao, X. Lei, R. Li, N. Park, and D. J. Lilja, \Pass: A hybrid storage
system for performance-synchronization tradeo s using ssds," in Proceedings
of the 2012 IEEE 10th International Symposium on Parallel and Distributed
Processing with Applications, ser. ISPA '12. Washington, DC, USA: IEEE
Computer Society, 2012, pp. 403{410.
[14] L. Zeng, D. Feng, J. Chen, Q. Wei, B. Veeravalli, and W. Liu, \HRAID6ML:
A hybrid raid6 storage architecture with mirrored logging," in MSST, 2012,
pp. 1{6.
[15] B. Mao, H. Jiang, S. Wu, L. Tian, D. Feng, J. Chen, and L. Zeng, \Hpda:
A hybrid parity-based disk array for enhanced performance and reliability,"
Trans. Storage, vol. 8, no. 1, pp. 4:1{4:20, Feb. 2012.
[16] A. Gupta, Y. Kim, and B. Urgaonkar, \DFTL: a
ash translation layer
employing demand-based selective caching of page-level address mappings,"
SIGPLAN Not., vol. 44, no. 3, pp. 229{240, 2009.
[17] M. Rosenblum and J. K. Ousterhout, \The design and implementation of a
log-structured le system," ACM Trans. Comput. Syst., vol. 10, no. 1, pp.
26{52, 1992.
[18] T.-H. Chen, Y.-Y. Hsiao, Y.-T. Hsing, and C.-W. Wu, \An adaptive-rate
error correction scheme for nand
ash memory," in VTS, 2009, pp. 53{58.
[19] Y.-H. Chang and T.-W. Kuo, \A reliable mtd design for mlc
ash-memory
storage systems," in EMSOFT, 2010, pp. 179{188.
[20] D. J. MacKay and R. M. Neal, \Near shannon limit performance of low
density parity check codes," Electronics Letters, vol. 32, pp. 1645{1646, 1996.
[21] K. Zhao, W. Zhao, H. Sun, X. Zhang, N. Zheng, and T. Zhang,
\Ldpc-in-ssd: Making advanced error correction codes work e ectively
in solid state drives," in Presented as part of the 11th USENIX
Conference on File and Storage Technologies. Berkeley, CA: USENIX, 2013.
[Online]. Available: https://www.usenix.org/conference/fast13/mitigating-
system-response-time-penalty-induced-use-advanced-error-correction
[22] L.-P. Chang, \A hybrid approach to nand-
ash-based solid-state disks," pp.
1337{1349, 2010.
[23] L.-P. Chang and C.-D. Du, \Design and implementation of an e cient wear-
leveling algorithm for solid-state-disk microcontrollers." ACM Trans. Design
Autom. Electr. Syst., vol. 15, 2009.
[24] UMassTraceRepository, \Oltp application i/o,"
http://traces.cs.umass.edu/index.php/Storage/Storage.
[25] J. S. DOMINGO, \Ssd vs. hdd: What's the di erence,"
http://www.pcmag.com/article2/0,2817,2404260,00.asp.