Several excellent researches have been proposed to improve the performance of
solid state drives (SSDs) by exploiting I/O parallelism of multi-channel architecture. However, these researches do not fully explore the internal parallelism and do not take wear leveling into consideration. In this paper, I/O performance is further improved by interleaving request in channel level and striping request in plane level. A wear-leveling-aware distributed garbage collector is proposed to improve SSD lifetime and reclamation efficiency. To balance the utilization of user space among all channels, data migration is performed implicitly during channel selection and explicitly during garbage collection. To the best of our knowledge, this is the first paper on the design of distributed garbage collector for multi-channel flash-memory storage system. The experimental results showed that the proposed scheme can achieve perfect wear leveling and improve the overall performance by 25% for the Windows workload, 23% for the Linux workload, and 42% for the multimedia workload, compared with the related work.

Several excellent researches have been proposed to improve the performance of
solid state drives (SSDs) by exploiting I/O parallelism of multi-channel architecture. However, these researches do not fully explore the internal parallelism and do not take wear leveling into consideration. In this paper, I/O performance is further improved by interleaving request in channel level and striping request in plane level. A wear-leveling-aware distributed garbage collector is proposed to improve SSD lifetime and reclamation efficiency. To balance the utilization of user space among all channels, data migration is performed implicitly during channel selection and explicitly during garbage collection. To the best of our knowledge, this is the first paper on the design of distributed garbage collector for multi-channel flash-memory storage system. The experimental results showed that the proposed scheme can achieve perfect wear leveling and improve the overall performance by 25% for the Windows workload, 23% for the Linux workload, and 42% for the multimedia workload, compared with the related work.

[1] Li-Pin Chang. A Hybrid Approach to NAND-Flash-Based Solid-State Disks.
IEEE Transactions on Computers, 59(10):1337–1349, October 2010.
[2] Li-Pin Chang and Chun-Da Du. Design and Implementation of an Effi-
cient Wear-Leveling Algorithm for Solid-State-Disk Micro-Controllers. ACM
Transactions on Design Automation for Electronic Systems, 15(1):1–36, Dec
2009.
[3] Feng Chen, Tian Luo, and Xiaodong Zhang. CAFTL: A Content-Aware Flash
Translation Layer Enhancing the Lifespan of Flash Memory Based Solid State
Drives. In Proceedings of the 9th USENIX Conference on File and Stroage
Technologies, FAST’11, pages 77–90, 2011.
[4] Feng Chen, Tian Luo, and Xiaodong Zhang. Essential Roles of Exploiting In-
ternal Parallelism of Flash Memory based Solid State Drives in High-Speed
Data Processing. In IEEE 17th International Symposium on High Perfor-
mance Computer Architecture (HPCA), pages 266–277, Feb 2011.
[5] Yang Hu, Hong Jiang, Dan Feng, Lei Tian, Hao Luo, and Chao Ren. Ex-
ploring and Exploiting the Multi-level Parallelism Inside SSDs for Improved
Performance and Endurance. IEEE Transactions on Computers, 58(12):1,
Mar 2012.
[6] Jeong-Uk Kang, Jin-Soo Kim, Chanik Park, Hyoungjun Park, and Joon-
won Lee. A Multi-Channel Architecture for High-Performance NAND Flash-
Based Storage System. Journal of Systems Architecture, 53:644–658, Septem-
ber 2007.
[7] Micron. NAND Flash Memory MT29F4G08AAA, MT29F8G08BAA,
MT29F8G08DAA, MT29F16G08FAA. Technical report, Micron, 2006.
[8] Micron. TN-29-25: Improving Performance Using Two-Plane Commands
Introduction. Technical report, Micron, 2007.
[9] Micron. 16Gb, 32Gb, 64Gb, 128Gb Asynchronous/Synchronous NAND Fea-
tures. Technical report, Micron, 2009.
[10] MIRA. 3.3V 16Gb MLC NAND Flash Memory Specification and Technical
Notes. Technical report, MIRA, 2011.
[11] Sang-Hoon Park, Seung-Hwan Ha, Kwanhu Bang, and Eui-Young Chung.
Design and Analysis of Flash Translation Layers for Multi-Channel NAND
Flash-based Storage Devices. IEEE Transaction on Consumer Electronics,
55(3):1392–1400, August 2009.
[12] Sung Kyu Park, Youngwoo Park, Gyudong Shim, and Kyu Ho Park. CAVE:
Channel-Aware Buffer Management Scheme for Solid State Disk. In ACM
Symposium on Applied Computing, pages 346–353, 2011.
[13] Samsung. K9GAG08B0M (2G x 8 Bit NAND Flash Memory) Datasheet.
Technical report, Samsung, 2006.
[14] Samsung. NAND Flash Memory K9GAG08B0M, K9GAG08U0M,
K9LBG08U1M. Technical report, Samsung, 2007.
[15] Gyudong Shim, Youngwoo Park, and Kyu Ho Park. A hybrid flash translation
layer with adaptive merge for ssds. ACM Transactions on Storage, 6(4):15,
May 2011.
[16] Seon yeong Park, Euiseong Seo, Ji-Yong Shin, Seungryoul Maeng, and Joon-
won Lee. Exploiting Internal Parallelism of Flash-based SSDs. IEEE Com-
puter Architecture Letters, 9(1):9–12, Jan 2010.