A New FTL-based Flash Memory Management Scheme with Fast Cleaning Mechanism

Due to the advantages of non-volatility, lightweight, low power consumption, and shock resistance, flash memory has been widely used as the storage of embedded systems and mobile devices. However, unlike hard disk, flash memory does not support update-in-place operation, and each block on flash memory has the limited erasure cycles. Therefore, flash memory needs a different storage management scheme designed specifically for flash memory characteristics. Many researches adopt the log-based approach which needs an efficient cleaning mechanism to reclaim the storage space occupied by obsolete data. In this paper, we have designed and implemented a new flash translation layer for flash memory management and proposed a fast cleaning mechanism for space reclamation. It is based on the DAC technique to separately cluster hot and cold data in flash memory. For the NAND-type flash memory with large capacity, it maintains multiple LRU lists to reduce the time of selecting blocks for erasure in cleaning activity. Moreover, we modify the cost-benefit policy with different weight that considers the attribute of each block on flash memory in selecting a block for cleaning. Simulation results show that our proposed flash memory management scheme with the proposed fast cleaning mechanism could efficiently decrease the number of erase operations, speed up the cleaning activity, and enhance system performance.

[1]  Tei-Wei Kuo,et al.  An efficient management scheme for large-scale flash-memory storage systems , 2004, SAC '04.

[2]  Sang Lyul Min,et al.  A space-efficient flash translation layer for CompactFlash systems , 2002, IEEE Trans. Consumer Electron..

[3]  Tei-Wei Kuo,et al.  Efficient initialization and crash recovery for log-based file systems over flash memory , 2006, SAC.

[4]  Sunhwa Park,et al.  Atomic write FTL for robust flash file system , 2005, Proceedings of the Ninth International Symposium on Consumer Electronics, 2005. (ISCE 2005)..

[5]  Jeffrey Katcher,et al.  PostMark: A New File System Benchmark , 1997 .

[6]  Ruei-Chuan Chang,et al.  Cleaning policies in mobile computers using flash memory , 1999, J. Syst. Softw..

[7]  ChiangMei-Ling,et al.  Using data clustering to improve cleaning performance for plash memory , 1999 .

[8]  Kern Koh,et al.  A fast start-up technique for flash memory based computing systems , 2005, SAC '05.

[9]  Hiroshi Motoda,et al.  A Flash-Memory Based File System , 1995, USENIX.

[10]  Michael Wu,et al.  eNVy: a non-volatile, main memory storage system , 1994, ASPLOS VI.

[11]  TaeHoon Lee,et al.  Design of a Reliable NAND Flash Software for Mobile Device , 2006, The Sixth IEEE International Conference on Computer and Information Technology (CIT'06).

[12]  Tei-Wei Kuo,et al.  An adaptive striping architecture for flash memory storage systems of embedded systems , 2002, Proceedings. Eighth IEEE Real-Time and Embedded Technology and Applications Symposium.

[13]  Sang-goo Lee,et al.  A new flash memory management for flash storage system , 1999, Proceedings. Twenty-Third Annual International Computer Software and Applications Conference (Cat. No.99CB37032).

[14]  Li-Pin Chang,et al.  On efficient wear leveling for large-scale flash-memory storage systems , 2007, SAC '07.

[15]  David Woodhouse,et al.  JFFS : The Journalling Flash File System , 2001 .

[16]  Kyu Ho Park,et al.  An efficient NAND flash file system for flash memory storage , 2006, IEEE Transactions on Computers.

[17]  Jing Chen,et al.  An active space recycling mechanism for flash storage systems in real-time application environment , 2005, 11th IEEE International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA'05).