Please wait a minute...
浙江大学学报(工学版)
J4  2013, Vol. 47 Issue (10): 1731-1740    DOI: 10.3785/j.issn.1008-973X.2013.10.005
自动化技术、电信技术     
延长闪存寿命的数据库数据复制协议
李伟, 王新根, 周波, 李善平
浙江大学 计算机科学与技术学院,浙江 杭州 310027
Data replication protocol for extending flash memory lifetime in database system
LI Wei, WANG Xin-gen, ZHOU Bo, LI Shan-ping
College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
 全文: PDF  HTML
摘要：

针对传统数据库系统中数据复制协议未充分考虑取决于数据块擦写次数的闪存寿命问题的不足,提出基于上下文的数据复制协议(CBRP).CBRP分析在一定时间窗口内数据复制写操作之间的上下文关系,以闪存数据块大小为基准合并针对相同表的同类操作,以每个操作数据集之间的覆盖或回滚关系为依据消除不必要的操作,在处理结果递交到其他线程进行并行提交后,即刻开始新一轮的处理过程.基于完整实现CBRP的MySQL数据库系统的实验结果表明,在不同的工作负载下,CBRP与经典数据复制协议相比,在从节点上降低了20%～50%的块写操作数,数据复制性能有20%～40%的提升.证明CBRP是对延长闪存寿命行之有效的数据库数据复制协议.
Abstract:

The traditional data replication protocol in the database system did not consider the flash erasing time saving. The CBRP - a context based data replication protocol was proposed in order to solve the problem. The CBRP analyzed the context between write operations in a time window, then merged the same type writes on the same table to the block size and eliminated the unneeded writes based on the overwrite or rollback relations. A new CBRP process restarted after the processed result was passed to another thread for the concurrent committing. The experiments based on the CBRP enhanced MySQL show that under different workloads the CBRP can reduce 20%～50% blocks written to the flash memory on the slave node and replication performance is improved by 20%～40% compared with the classic data replication protocol. Results indicate that the CBRP is a practical data replication protocol that will help extend the flash memory lifetime in the database system.
出版日期: 2013-10-01
:  TP 333.8  
基金资助:

李伟(1983—), 男, 博士生,从事基于闪存的数据库优化研究.E-mail: wli@zju.edu.cn
通讯作者: 李善平, 男, 教授, 博导.     E-mail: shan@zju.edu.cn
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:

李伟, 王新根, 周波, 李善平. 延长闪存寿命的数据库数据复制协议[J]. J4, 2013, 47(10): 1731-1740.

LI Wei, WANG Xin-gen, ZHOU Bo, LI Shan-ping. Data replication protocol for extending flash memory lifetime in database system. J4, 2013, 47(10): 1731-1740.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2013.10.005    或    http://www.zjujournals.com/eng/CN/Y2013/V47/I10/1731

［1］ METZ C. Flash drives replace disks at Amazon, Facebook, Dropbox ［EB/OL］. ［2012-06-13］. http:∥www.wired.com/wiredenterprise/2012/06/flash-data-centers/.

［2］ GRAY J, HELLAND P, O’NEIL P, et al. The dangers of replication and a solution ［C］∥ Proceedings of the 1996 ACM SIGMOD international conference on Management of data. Montreal, Canada: ACM, 1996: 173-182.

［3］ SAITO Y, SHAPIRO M. Optimistic replication ［J］. ACM Computing Surveys, 2005, 37(1): 42-81.

［4］ PARK S, JUNG D, KANG J, et al. CFLRU: a replacement algorithm for flash memory ［C］∥ CASES ′06 Proceedings of the 2006 International Conference on Compilers, Architecture and Synthesis for Embedded Systems. Seoul: ACM, 2006: 234-241.

［5］ KIM H, AHN S. BPLRU: a buffer management scheme for improving random writes in flash storage ［C］∥ FAST′08 Proceedings of the 6th USENIX Conference on File and Storage Technologies. San Jose, California: USENIX, 2008: 1-14.

［6］ SOUNDARARAJAN G, PRABHAKARAN V, BALAKRISHNAN M, et al. Extending SSD lifetimes with disk-based write caches ［C］∥ FAST′10 Proceedings of the 8th USENIX Conference on File and Storage Technologies. San Jose, California: USENIX, 2010: 8.

［7］ SUN Guang-yu, JOO Y, CHEN Yi-bo, et al. A hybrid solid-state storage architecture for the performance, energy consumption, and lifetime improvement ［C］∥ 2010 IEEE 16th International Symposium on High Performance Computer Architecture (HPCA). Bangalore, India: IEEE, 2010: 1-12.

［8］ WIKIPEDIA. Phase-change memory. ［EB/OL］. ［2012-04-12］.http:∥en.wikipedia.org/wiki/Phase_change_ram

［9］ AGRAWAL D, GANESAN D, SITARAMAN R, et al. Lazy-adaptive tree: an optimized index structure for flash devices ［J］. Proceeding of the VLDB Endowment， 2009, 2(1): 361-372.

［10］ LEE H, PARK S, SONG H, et al. An efficient buffer management scheme for implementing a B-tree on NAND flash memory ［C］∥ Proceedings of the 3rd International Conference on Embedded Software and Systems. Daegu, Korea: Springer-Verlag, 2007: 181-192.

［11］ XU Chang, SHOU Li-dan, CHEN Gang, et al. Update migration: an efficient B+ tree for flash storage ［C］∥ Proceedings of the 15th International Conference on Database Systems for Advanced Applications. Tsukuba, Japan: Springer-Verlag, 2010: 276-290.

［12］ LIANG Zhi-chao, FAN Yu-lei, MENG Xiao-feng. A novel method to extend flash memory lifetime in flash-based DBMS ［C］ ∥Proceedings of the 16th International Conference on Database systems for Advanced Applications. Hong Kong: Springer-Verlag, 2011: 190-201.

［13］ CHEN Feng, LUO Tian, ZHANG Xiao-dong. CAFTL: a content-aware flash translation layer enhancing the lifespan of flash memory based solid state drives ［C］∥ FAST′11 Proceedings of the 9th USENIX Conference on File and Storage Technologies. San Jose, California: USENIX, 2011: 6.

［14］ WU Guan-ying, HE Xu-bin. Delta-FTL: improving SSD lifetime via exploiting content locality ［C］∥ Proceedings of the 7th ACM European conference on Computer Systems. Bern, Switzerland: ACM, 2012: 253-266.

［15］ 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, Korea: ACM, 2007: 1126-1130.

［16］ BOUKHOBZA J, OLIVIER P, RUBINI S. A cache management strategy to replace wear leveling techniques for embedded flash memory ［C］∥ 2011 International Symposium on Performance Evaluation of Computer and Telecommunication Systems (SPECTS). The Hague, Netherlands: IEEE, 2011: 1-8.

［17］ KRISHNAMURTHY S, SANDERS W, CUKIER M. An adaptive framework for tunable consistency and timeliness using replication ［C］∥ Proceedings of the 2002 International Conference on Dependable Systems and Networks. Washington, DC, USA: IEEE, 2002: 17-26.

［18］ PACITTI E, SIMON E, RODIN P. Update propagation strategies to improve freshness of data in Lazy master schemes ［J］. VLDB Journal, 1997, 8: 2000.

［19］ BREITBART Y, KORTH H. Replication and consistency: being lazy helps sometimes ［C］∥ Proceedings of the 16th ACM SIGACT-SIGMOD-SIGART Symposium on Principles of Database Systems. Tucson, Arizona, United States: ACM, 1997: 173-184.

［20］ DAUDJEE K, SALEM K. Lazy database replication with ordering guarantees ［C］∥ Proceedings of the 20th International Conference on Data Engineering. Boston, MA, USA: IEEE, 2004: 424-435.

［21］ AMZA C. Conflict-aware replication for dynamic content web sites ［D］. TX, USA: Rice University Houston, 2003.

［22］ LLOYD W, FREEDMAN M, KAMINSKY M, et al. Don’t settle for eventual: scalable causal consistency for wide-area storage with COPS ［C］∥ Proceedings of the 23rd ACM Symposium on Operating Systems Principles. Cascais, Portugal: ACM, 2011: 401-416.

［23］ AGRAWAL N, PRABHAKARAN V, WOBBER T, et al. Design tradeoffs for SSD performance ［C］∥ USENIX 2008 Annual Technical Conference on Annual Technical Conference. Boston, Massachusetts: USENIX, 2008: 57-60.

［24］ OCZ TECHNOLOGY. OCZ RevoDrive PCI-Express SSD ［EB/OL］. 2012-01-03. http:∥www.ocztechnology.com/ocz-revodrive-pci-express-ssd.html.

［25］ KOPYTOV A. System performance benchmark, Version 0.3.1 ［CP/OL］. ［2004-10-07］. http:∥sysbench.source forge.net/.

［26］ WONG M, WITHAM T. Database Test Suite, Version 0.40 ［CP/OL］. ［2007-02-21］. http:∥sourceforge.net/projects/osdldbt/.

［27］ CAIN T, MARTIN M, HEIL T, et al. TPC-W Java Implementation, Version 1.0 ［CP/OL］. 2012-11-16. https:∥github.com/jopereira/java-tpcw.

［28］ TPC. TPC-C is an on-line transaction processing benchmark ［EB/OL］. ［2009-10-05］. http:∥www.tpc.org /tpcc/.

［29］ WIKIPEDIA. TPC-W ［EB/OL］. 2011-05-24. http:∥en.wikipedia.org/wiki/TPC-W.
No related articles found!