• Article
  • | |
  • Metrics
  • |
  • Reference [31]
  • |
  • Related [20]
  • | | |
  • Comments
    Abstract:

    With the dramatic increase in the scale of computing, the applications of network storage systems become wider, and the requirements for their I/O performance are also higher. Now with I/O heavy loaded, it becomes meaningful to cache data by using low-speed media in the I/O path between the client and network storage systems. In this paper, a cache system prototype D-Cache is designed and implemented based on disk media at block level for storage system. A two-level structure is adopted to manage disk cache and a corresponding cache management algorithm is provided for it at block level. The algorithm effectively solves the management problem of disk cache brought by the low-speed characteristic of disk media. By the use of bitmap, the cache management algorithm also eliminates the overhead of Copy on Write operations caused by write miss of disk cache. Experimental results show that the prototype can efficiently improve the overall performance for storage system with I/O heavy loaded.

    Reference
    [1] Exterme cluster administration toolkit. 2008. http://xcat.sourceforge.net/
    [2] http://oscar.openclustergroup.org/
    [3] Oliveira F, Patel J. Blutopia: Cluster life-cycle management. Technical Report, RC23784, IBM Research Division Austin Research Laboratory, 2005.
    [4] Hibler M, Storller L, Lepreau J, Ricci R, Barb C. Fast, scalable disk imaging with Frisbee. In: Proc. of the 2003 USENIX Annual Technical Conf. San Antonio, 2003. 283-296. http://www.usenix.org/events/usenix03/tech/full_papers/hibler/hibler_html/
    [5] Sapuntzakis C, Brumley D, Chandra R, Zeldovich N, Chow J, Lam MS, Rosenblum M. Virtual appliances for deploying and maintaining software. In: Proc. of the 17th Large Installation Systems Administration Conf. (LISA 2003). Berkeley, 2003. 181-194. http://www.usenix.org/event/lisa03/tech/full_papers/sapuntzakis/sapuntzakis_html/index.html
    [6] Moore J, Chase J. Cluster on demand. Technical Report, CS-2002-07, Department of Computer Science, Duke University, 2002.
    [7] Liu ZJ, XU L, Yin Y. Blue Whale SonD: A service-on-demand management system. Chinese Journal of Computers, 2005,28(7): 1110-1117 (in Chinese with English abstract).
    [8] Sivathanu G, Zadok E. A versatile persistent caching framework for file systems. Technical Report, FSL-05-05, Stony Brook University, 2005.
    [9] Sandberg R, Goldberg D, Kleiman S, Walsh D, Lyon B. Design and implementation of the Sun network file system. In: Proc. of the Summer 1985 USENIX. Portland, 1985. 119-130.
    [10] Howard JH. An overview of the andrew file system. Technical Report, CMU-ITC-062, CMU Information Technology Center, 1988.
    [11] Satyanarayanan M. Coda: A highly available file system for a distributed workstation environment. IEEE Trans. on Computers, 1990,39(4):447-459.
    [12] Anderson T, Dahlin M, Neefe J, Patterson D, Roselli D, Wang R. Serverless network file systems. ACM SIGOPS Operating Systems Review, 1995,29(5):109-126.
    [13] Vilayannur M, Nath P, Sivasubramaniam A. Providing tunable consistency for a parallel file store. In: Proc. of the 4th USENIX Conf. on File and Storage Technologies. San Francisco, 2005. 17-30. http://www.usenix.org/events/fast05/tech/full_papers/ vilayannur/vilayannur_html/index.html
    [14] http://www.panasas.com
    [15] http://www.sun.com/software/products/lustre/index.xml
    [16] Megiddo N, Modha D. ARC: A self-tuning, low overhead replacement cache. In: Proc. of the 2nd USENIX Conf. on File and Storage Technologies (FAST 2003). San Francisco, 2003. 115-130. http://www.usenix.org/events/fast03/tech/megiddo.html
    [17] Jiang S, Zhang X. LIRS: An efficient low interreference recency set replacement policy to improve buffer cache performance. In: Proc. of the 2002 ACM SIGMETRICS. Marina Del Rey: ACM, 2002. 31-42.
    [18] http://nbd.sourceforge.net
    [19] Hensbergen EV, Zhao M. Dynamic policy disk caching for storage networking. Technical Report, RC24123, IBM Research Division Austin Research Laboratory, 2006.
    [20] Johnson T, Shasha D. 2Q: A low overhead high performance buffer management replacement algorithm. In: Proc. of the 20th Int’l Conf. on VLDB. Santiago de Chile: Morgan Kaufmann Publishers, 1994. 439-450. http://www.vldb.org/conf/1994/P439.PDF
    [21] He X, Zhang M, Yang Q. STICS: SCSI-to-IP cache for storage area networks. Journal of Parallel and Distributed Computing, 2004, 64(9):1069-1085.
    [22] Hu Y, Yang Q. DCD—Disk caching disk: A new approach for boosting I/O performance. In: Proc. of the 23rd Annual Int’l Symp. on Computer Architecture. Pennsylvania: ACM, 1996. 169-178. http://www.ele.uri.edu/Research/hpcl/DCD/DCD.html
    [23] Hu Y, Yang Q, Nightingale T. RAPID-Cache—A reliable and inexpensive write cache for disk I/O systems. In: Proc. of the 5th Int’l Symp. on High Performance Computer Architecture. Orlando, 1999. 204-213 http://www.ele.uri.edu/Research/hpcl/RAPID/ RAPID.html
    [24] Luo YF, Shu JW, Yu B, Wen DC. A cache system hosted on the iSCSI target in an IP SAN. In: Proc. of the 5th Int’l Conf. on Grid and Cooperative Computing-Workshops. Changsha: IEEE, 2006. 412-417. http://portal.acm.org/citation.cfm?id=1170685
    [25] Xiong JG, Feng D. Design and implementation of a high availability RAID cache. Computer Engineering and Science, 2006,28(8): 119-124 (in Chinese with English abstract).
    [26] Feng D, Xiong JG. Study and implementation of consistency of RAID-based NVRAM cache. Journal of Huazhong University of Science and Technology (Nature Science), 2005,33(10):70-72 (in Chinese with English abstract).
    [27] Chandra R, Zeldovich N, Sapuntzakis C, Lam MS. The collective: A cache-based system management architecture. In: Proc. of the 2nd Symp. on Networked Systems Design and Implementation (NSDI 2005). Boston, 2005. 259-272. http://www.usenix.org/ events/nsdi05/tech/full_papers/chandra/chandra_html/index.html
    [28] Tang S, Chen Y, Zhang Z. Machine bank: Own your virtual personal computer. In: Proc. of the 21st Int’l Parallel and Distributed Processing Symp. Long Beach, 2007. http://research.microsoft.com/apps/pubs/default.aspx?id=69423
    附中文参考文献: [7] 刘振军,许鲁,尹洋.蓝鲸SonD服务部署系统.计算机学报,2005,28(7):1110-1117.
    [25] 熊建刚,冯丹.高可用的磁盘阵列Cache的设计和实现.计算机工程与科学,2006,28(8):119-124.
    [26] 冯丹,熊建刚.磁盘阵列cache数据一致性的研究与实现.华中科技大学学报(自然科学版),2005,33(10):70-72.
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

尹 洋,刘振军,许 鲁.一种基于磁盘介质的网络存储系统缓存.软件学报,2009,20(10):2752-2765

Copy
Share
Article Metrics
  • Abstract:4809
  • PDF: 7916
  • HTML: 0
  • Cited by: 0
History
  • Received:January 09,2008
  • Revised:August 11,2008
You are the first2034788Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address:4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code:100190
Phone:010-62562563 Fax:010-62562533 Email:jos@iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063