A log buffer-based flash translation layer using fully-associative sector translation

被引:406
作者
Lee, Sang-Won [1 ]
Park, Dong-Joo [2 ]
Chung, Tae-Sun [3 ]
Lee, Dong-Ho [4 ]
Park, Sangwon [5 ]
Song, Ha-Joo [6 ]
机构
[1] Sungkyunkwan Univ, Sch Informat & Communicat Engn, Suwon 440746, South Korea
[2] Soongsil Univ, Sch Comp, Seoul 156743, South Korea
[3] Ajou Univ, Coll Informat Technol, Suwon 443749, South Korea
[4] Hanyang Univ, Dept Comp Sci & Engn, Ansan 426791, South Korea
[5] Hankuk Univ Foreign Studies, Yongin 449791, South Korea
[6] Pukyong Natl Univ, Div Elect Comp & Telecommun, Pusan 608737, South Korea
关键词
algorithms; performance; flash memory; FTL; address translation; log blocks; associative mapping;
D O I
10.1145/1275986.1275990
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Flash memory is being rapidly deployed as data storage for mobile devices such as PDAs, MP3 players, mobile phones, and digital cameras, mainly because of its low electronic power, nonvolatile storage, high performance, physical stability, and portability. One disadvantage of flash memory is that prewritten data cannot be dynamically overwritten. Before overwriting prewritten data, a time-consuming erase operation on the used blocks must precede, which significantly degrades the overall write performance of flash memory. In order to solve this "erase-before-write" problem, the flash memory controller can be integrated with a software module, called "flash translation layer (FTL)." Among many FTL schemes available, the log block buffer scheme is considered to be optimum. With this scheme, a small number of log blocks, a kind of write buffer, can improve the performance of write operations by reducing the number of erase operations. However, this scheme can suffer from low space utilization of log blocks. In this paper, we show that there is much room for performance improvement in the log buffer block scheme, and propose an enhanced log block buffer scheme, called FAST (full associative sector translation). Our FAST scheme improves the space utilization of log blocks using fully-associative sector translations for the log block sectors. We also show empirically that our FAST scheme outperforms the pure log block buffer scheme.
引用
收藏
页数:27
相关论文
共 12 条
[1]  
Ban Amir, 1995, United States Patent, Patent No. [5,404,485, 5404485]
[2]  
Chung Tae-Sun, 2006, P 2006 IFIP INT C EM
[3]  
Douglis F., 1994, Proceedings of the First USENIX Symposium on Operating Systems Design and Implementation (OSDI), P25
[4]  
Estakhri P., 1999, United States Patent, Patent No. [5,930,815, 5930815]
[5]   Algorithms and data structures for flash memories [J].
Gal, E ;
Toledo, S .
ACM COMPUTING SURVEYS, 2005, 37 (02) :138-163
[6]  
Hennessy John L., 2003, COMPUTER ARCHITECTUR
[7]  
Kim B. S., 2002, United States Patent, Patent No. [6,381,176, 6381176]
[8]  
Kim J, 2002, IEEE T CONSUM ELECTR, V48, P366
[9]   Improved flash memory grows in popularity [J].
Lawton, G .
COMPUTER, 2006, 39 (01) :16-18
[10]  
PAULSON LD, 2005, IEEE COMPUT, V38, P14, DOI [10.1109/MC.2005.330., DOI 10.1109/MC.2005.330]