Improve the performance of web service by parallel I/O system

被引:0
|
作者
Zeng, JY [1 ]
Zhen, C [1 ]
Li, BF [1 ]
机构
[1] Sichuan Univ, Dept Comp Sci, Chengdu 610064, Sichuan Prov, Peoples R China
来源
WAVELET ANALYSIS AND ITS APPLICATIONS, AND ACTIVE MEDIA TECHNOLOGY, VOLS 1 AND 2 | 2004年
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Over years, a lot of people have devoted themselves to the research of parallel I/O. In some applications, Parallel I/O, whose goal is to improve the performance of a system by enhancing its throughput capacity and accomplished by reducing bottlenecks in I/O path: no single I/O device, no single I/O bus, and no single network path, has been used. Nowadays, various web services have very high requirement of throughput. In this paper, we discuss a parallel I/O architecture and describe how to improve the performance of web service with the parallel I/O system which is at the back of database sever in the 3-tiers architecture and provides transparent data access. To provide parallel I/O, three software requirements have to be satisfied: application interface, underlying high performance data storage mechanism, and tools for file manipulation. And as the parallel I/O system is used in web applications, parallel I/O will interact with database server.
引用
收藏
页码:646 / 651
页数:6
相关论文
共 50 条
  • [31] Addressing Web Service Performance by Replication at the Operating System Level
    Stantchev, Vladimir
    Malek, Miroslaw
    2008 3RD INTERNATIONAL CONFERENCE ON INTERNET AND WEB APPLICATIONS AND SERVICES (ICIW 2008), 2008, : 696 - +
  • [32] Distributed parallel file system for I/O intensive parallel computing on clusters
    Domínguez-Domínguez, S
    Buenabad-Chávez, J
    2004 1st International Conference on Electrical and Electronics Engineering (ICEEE), 2004, : 194 - 199
  • [33] Commodity network based parallel I/O system for massively parallel processors
    Matsubara, M
    Numa, H
    Boku, T
    INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-V, PROCEEDINGS, 1999, : 2424 - 2429
  • [35] Performance of parallel I/O scheduling strategies on a network of workstations
    Chen, FY
    Majumdar, S
    PROCEEDINGS OF THE EIGHTH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS, 2001, : 157 - 164
  • [36] Performance characterization and optimization of parallel I/O on the Cray XT
    Yu, Weikuan
    Vetter, Jeffrey S.
    Oral, H. Sarp
    2008 IEEE INTERNATIONAL SYMPOSIUM ON PARALLEL & DISTRIBUTED PROCESSING, VOLS 1-8, 2008, : 1468 - 1478
  • [37] Impact of spatial layout of jobs on parallel I/O performance
    Lewis & Clark Coll, Portland, OR, United States
    Proc Annu Workshop I/O Parall Distrib Syst, (45-56):
  • [38] Parallel I/O performance of fine grained data distributions
    Cho, Y
    Winslett, M
    Chen, Y
    Kuo, SW
    SEVENTH INTERNATIONAL SYMPOSIUM ON HIGH PERFORMANCE DISTRIBUTED COMPUTING - PROCEEDINGS, 1998, : 163 - 170
  • [39] Performance model of I/O-intensive parallel applications
    Chen, Yongran
    Qi, Xingyun
    Dou, Wenhua
    Jisuanji Yanjiu yu Fazhan/Computer Research and Development, 2007, 44 (04): : 707 - 713
  • [40] Observing Parallel Phase and I/O Performance Using TAU
    Shende, Sameer
    Malony, Allen
    Morris, Alan
    Cronk, David
    PROCEEDINGS OF THE HPCMP USERS GROUP CONFERENCE 2008, 2008, : 431 - +