期刊文献+

FastQueue:一种高性能的磁盘队列存储管理机制 被引量:1

FastQueue:A High Performance Disk Queue Storage Management Mechanism
下载PDF
导出
摘要 1.引言 随着消息通信(如消息、短消息)的爆炸式增长,消息传递系统的性能面临严峻的挑战.消息通信的首要特点是高可靠性,在发送人确认消息收到之前必须将消息保存到磁盘上. High reliability is the primary requirement for messaging system. Messaging system always utilizes disk queue to temporarily store message to be delivered. Experiments show that Disk queue I/O is the primary performance bottleneck in the messaging system. In this paper we present a high performance disk queue storage management mechanism-FastQueue. The FastQueue utilizes a large file to serve as disk queue to reduce file manage overhead, in which adjacent messages are stored in adjacent disk block. Several messages are written to disk queue in a one large write by Lazy Gathering Write. Several adjacent messages are read into buffer in a one read by Sequential Grouping Prefetch. The Lazy Gathering Write and Sequential Grouping Prefetch policies take full advantage of the disk bandwidth. Experiment shows that performance of the FastQueue is more than an order of magnitude higher than that of traditional disk queue.
出处 《计算机科学》 CSCD 北大核心 2003年第10期81-83,88,共4页 Computer Science
基金 国家95重点攻关项目支持
关键词 磁盘队列存储管理机制 FastQueue 磁盘带宽 文件系统 UNIX 操作系统 Messaging system,Disk queue,Lazy gathering write,Sequential grouping prefetch
  • 相关文献

参考文献5

  • 1John M R, Ousterhout K. The Design and Implementation of a Log-Structured File System. ACM Transaction on Computer Systems,Feb. 1992. 10~22.
  • 2Matthew McCormick Jonathan Ledlie. A Fast File System for Caching Web Objects, First Annual Symposium on Operating Systems Design, Implementation, and Evaluation (OS-DIE 1).
  • 3Gregory R,Ganger M,Kaashoek F. Embedded Inodes and Explicit Grouping: Exploiting Disk BandWidth for Small Files. Annual USENIX Technical Conference (Anaheim, CA), Jan. 1997. 1~17.
  • 4Kathy C M, Richardson J. Reducing the Disk I/O of Web Proxy Server Caches, USENIX Annual Technical Conference Monterey,California, USA, June. 1999.
  • 5Evangelos P, Markatos Manolis G, Pnevrnatikaos H K D.Secondary Storage Management for Web Proxies, 2nd USENIX Symposium on Internet Technologies & Systems Boulder,Colorado, USA,Oct. 1999.

同被引文献12

  • 1熊建刚,冯丹.高可用的磁盘阵列Cache的设计和实现[J].计算机工程与科学,2006,28(8):119-121. 被引量:5
  • 2Peacock J K. The counterpoint fast file system [C]// Proceedings of the USENIX Winter Confer- ence. Dallas, Texas, USA: USENIX Association, 1988.
  • 3McVoy L W, Kleiman S R. Extent-like performance from a UNIX file system[C]// Proceedings of the USENIX Winter Conference. Dallas, Texas, USA: USENIX Association, 1991.
  • 4Sweeney A, Doucette D, Hu W, et al. Scalability in the XFS file system[C]// Proceedings of the USENIX 1996 Annual Technical Conference. San Diego, CA: USENIX Association, 1996.
  • 5Ruemmler C, Wilkes J. An introduction to disk drive modeling[C]. Comput, 1994, 27(3): 17.
  • 6Mckusick MK, JoyWN, LefflerSJ, etal. A fast file system for UNIX[J]. ACM Trans on Sys, 1984, 2(3): 181.
  • 7Ganger G R, Kaashoek M F. Embedded inodes and explicit grouping: exploiting disk bandwidth for small files[C]//Annual USENIX Technical Confer- ence. Anaheim, CA: USENIX Association, 1997.
  • 8Rosenblum M, Ousterhout J K. The design and im- plementation of a log-structured file system [J ]. ACM Transactions on Computer Systems, 1992,10 (1):26.
  • 9Zawodny J D, Balling D J. High performance MySQL [M]. USA: O'Reilly Media, Inc, 2004.
  • 10郭丹,卢正添,陈文,林汉翮.一种数据表实时备份系统的高速缓存方法[J].四川大学学报(自然科学版),2010,47(5):998-1002. 被引量:2

引证文献1

二级引证文献9

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部