Please wait a minute...
浙江大学学报(工学版)
J4  2014, Vol. 48 Issue (1): 92-99    DOI: 10.3785/j.issn.1008-973X.2014.01.014
计算机技术﹑电信技术     
基于日志结构的闪存均衡回收策略
陈钊,余锋,陈婷婷
浙江大学 仪器科学与工程学系,浙江 杭州 310027
Log-structured even recycle strategy for flash storage
CHEN Zhao, YU Feng, CHEN Ting-ting
Department of Instrumentation Science and Engineering, Zhejiang University, Hangzhou 310027, China
 全文: PDF(1324 KB)  
摘要：

针对闪存存储的异址更新和有限擦除等特点以及由此引起的使用寿命优化问题,提出基于日志结构的资深块优先回收（SBFR）策略.为了有效地提高使用寿命,闪存存储管理必须在减少垃圾回收开销的同时实现闪存的均衡擦除,并尽量避免两者的冲突.SBFR采用回收和聚集分散的冷数据的方法,选择块利用率和资历等级作为标准来判定冷数据和筛选回收块,高效集成了一种强制均衡策略.实验结果表明,SBFR能够减少回收开销和实现理想的均衡效果,有效地提高闪存存储的使用寿命.
关键词： 闪存管理;  存储系统;  日志结构;  垃圾回收;  擦除均衡    
Abstract:

Some factors, like out-of-place write and limited erasure lifecycles, pose reliability challenge for flash storage. A novel recycle scheme, called senior-block-first recycle method (SBFR), was proposed for log-structured flash management in order to mitigate the problem. In order to extend the functional life-time, the flash management must utilize blocks evenly and lower space-reclamation overhead at the same time, and has to avoid the confliction of these two objectives. SBFR tended to collect and assemble scattered cold data. Utilization-ratio and seniority-degree were taken as the selection criterions for block recycle. A forced wear-leveling mechanism was incorporated into the recycle method with little overhead. Experimental results indicate that SBFR method can effectively prolong flash’s functional life-time by leveling erase counts of all blocks evenly with small recycle overhead．
Key words: flash management    storage system    log-structure    garbage collection    wear leveling
出版日期: 2014-02-21
:     
通讯作者: 余锋，男，教授.     E-mail: osfengyu@zju.edu.cn
作者简介: 陈钊（1985-），男，博士生，从事光纤通道网络和存储技术研究.E-mail：zjucnz@gmail.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

陈钊,余锋,陈婷婷. 基于日志结构的闪存均衡回收策略[J]. J4, 2014, 48(1): 92-99.

CHEN Zhao, YU Feng, CHEN Ting-ting. Log-structured even recycle strategy for flash storage. J4, 2014, 48(1): 92-99.

链接本文:

http://www.zjujournals.com/xueshu/eng/CN/10.3785/j.issn.1008-973X.2014.01.014    或    http://www.zjujournals.com/xueshu/eng/CN/Y2014/V48/I1/92

［1］ GAL E, TOLEDO S. Algorithms and data structures for flash memories ［J］. ACM Computing Surveys, 2005, 37 (2): 138-163．
［2］ DENG Yu-hui, ZHOU Ji-peng. Architecture and optimization methods of flash memory based storage systems ［J］. Journal of Systems Architecture, 2011, 57(2): 214-227．
［3］ LIU Zhan-zhan, YUE Li-hua, WEI Peng, et al. An adaptive block-set based management for large-scale flash memory ［C］∥ Proceedings of the 2009 ACM Symposium on Applied Computing. Honolulu: ACM, 2009: 1621-1625．
［4］ BEN-AROYA A, TOLEDO S. Competitive analysis of flash-memory algorithms ［G］∥ Lecture Notes in Computer Science. Heidelberg: Springer, 2006, 4168: 100-111.
［5］ ROSENBLUM M, OUSTERHOUT J K. The design and implementation of a log-structured file system ［J］. ACM Transactions on Computer Systems, 1992, 10(1): 26-52．
［6］ KIM H J, LEE S G. An effective flash memory manager for reliable flash memory space management ［J］. IEICE Transactions on Information and Systems, 2002, E85-D (6): 950-964．
［7］ HU Xiao-yu, HAAS R, EVANGELOS E. Container marking: combining data placement, garbage collection and wear leveling for flash ［C］∥ Proceedings of the 19th IEEE International Symposium on Modeling, Analysis and Simulation of Computer and Telecommunication Systems. ［S.l.］: IEEE, 2011: 237-247．
［8］ CHANG Y H, HSIEH J W, KUO T W. Endurance enhancement of flash-memory storage systems: an efficient static wear leveling design ［C］∥ Proceedings of the 44th ACM/IEEE Design Automation Conference. San Diego: ACM, 2007: 212-217．
［9］ JUNG D, CHAE Y H, JO H, et al. A group-based wear-leveling algorithm for large-capacity flash memory storage systems ［C］∥ Proceedings of the 2007 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems. Salzburg: ACM, 2007: 160-164．
［10］ PARK S, LEE Y, KIM S. A high performance NAND array file system based on multiple NAND flash memories ［J］. The Journal of Supercomputing, 2011: 1-15．
［11］ KIM S Y, JUNG S I. A log-based flash translation layer for large NAND flash memory ［C］∥ Proceedings of the 8th International Conference on Advanced Communication Technology.Phoenix Park:IEEE,2006: 1641-1644．
［12］ CHANG Li-pin. On efficient wear leveling for large-scale flash-memory storage systems ［C］∥ Proceedings of the 2007 ACM Symposium on Applied Computing. Seoul: ACM, 2007: 1126-1130．
［13］ CHIANG M L, CHANG R C. Cleaning policies in mobile computers using flash memory ［J］. Journal of Systems and Software, 1999, 48 (3): 213-231．
［14］ KAWAGUCHI A, NISHIOKA S, MOTODA H. A flash-memory based file system ［C］∥ Proceedings of the USENIX Technical Conference. New Orleans:USENIX,1995:13-22．
［15］ WU M, ZWAENEPOEL W. eNVy: a non-volatile, main memory storage system ［C］∥ Proceedings of the 6th International Conference on Architectural Support for Programming Languages and Operating Systems. San Jose: ACM, 1994: 86-97．
［16］ CHANG Li-pin, KUO T W. An adaptive striping architecture for flash memory storage systems of embedded systems ［C］∥ Proceedings of the 8th IEEE Symposium on Real-Time and Embedded Technology and Applications. San Jose:IEEE, 2002: 187-196.
［17］ NARAYANAN D, DONNELLY A, ROWSTRON A. Write off-loading: practical power management for enterprise storage ［J］. ACM Transactions on Storage, 2008, 4 (3): 1-23．
[1] 张启飞, 张尉东, 李文娟, 潘雪增, 沈雁. 基于对等网络的面向小文件的云存储系统[J]. J4, 2013, 47(1): 8-14.
[2] 余利华, 陈刚, 王伟, 陈柯, 董金祥. 一种基于容器的自组织存储模型[J]. J4, 2010, 44(5): 915-922.