Performance analysis of parallel file system for I/O load balancing in distributed applications

被引:0
|
作者
Deepalakshmi, S [1 ]
Baswaraj, K [1 ]
Rao, SSSP [1 ]
Jagdish, BS [1 ]
Sonavane, DD [1 ]
Dhekne, PS [1 ]
Kaura, HK [1 ]
机构
[1] Indian Inst Technol, Dept Comp Sci & Engn, Bombay 400076, Maharashtra, India
关键词
I/O load balancing; parallel file system; cluster computing; performance analysis; performance issues;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Cluster environment these days is gaining recognition in equivalence to complex parallel machines. This provides environment to utilize distributed resources in an efficient way. Complex applications can be run on clusters and at the same time have advantage of the power of high-end machines due to the availability of resources in multiples across the cluster. In order to provide transparency in data location we need some kind of interface, which would provide access to data that has been distributed across the nodes. Parallel File System for Intel Networked Work-stations (PFSNIW) is one such parallel file system that has been developed by a team in Indian Institute of Technology, Bombay. In this paper we are discussing the effect of different network parameters on the performance of PFSNIW. We also discuss the results of the experiments that have been conducted to get optimal values for different parameters that influence the performance of the file system.
引用
收藏
页码:713 / 720
页数:8
相关论文
共 50 条
  • [31] UFCR: An efficient I/O method for parallel file system
    Huo, Yanmei
    Ju, Jiubin
    Hu, Liang
    [J]. SEVENTH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED COMPUTING, APPLICATIONS AND TECHNOLOGIES, PROCEEDINGS, 2006, : 223 - +
  • [32] Performance Analysis of Hadoop Distributed File System Writing File Process
    Xie, Yunyue
    Farhan, Abobaker Mohammed Qasem
    Zhou, Meihua
    [J]. 2018 INTERNATIONAL CONFERENCE ON INTELLIGENT AUTONOMOUS SYSTEMS (ICOIAS), 2018, : 116 - 120
  • [33] Evaluating ParFiSys: A high-performance parallel and distributed file system
    Perez, F
    Carretero, J
    Garcia, F
    DeMiguel, P
    Alonso, L
    [J]. JOURNAL OF SYSTEMS ARCHITECTURE, 1997, 43 (08) : 533 - 542
  • [34] Enabling dynamic file I/O path selection at runtime for parallel file system
    Xiuqiao Li
    Limin Xiao
    Meikang Qiu
    Bin Dong
    Li Ruan
    [J]. The Journal of Supercomputing, 2014, 68 : 996 - 1021
  • [35] Enabling dynamic file I/O path selection at runtime for parallel file system
    Li, Xiuqiao
    Xiao, Limin
    Qiu, Meikang
    Dong, Bin
    Ruan, Li
    [J]. JOURNAL OF SUPERCOMPUTING, 2014, 68 (02): : 996 - 1021
  • [36] A Parallel Fuzzy Load Balancing Algorithm for Distributed Nodes Over a Cloud System
    Hamdani, Mostefa
    Aklouf, Youcef
    Bouarara, Hadj Ahmed
    [J]. INTERNATIONAL JOURNAL OF GRID AND HIGH PERFORMANCE COMPUTING, 2022, 14 (01)
  • [37] A New Approach to Double I/O performance for Ceph Distributed File System in Cloud Computing
    Zhang, Xiao
    Wang, Yanqiu
    Wang, Qing
    Zhao, Xiaonan
    [J]. 2019 2ND INTERNATIONAL CONFERENCE ON DATA INTELLIGENCE AND SECURITY (ICDIS 2019), 2019, : 68 - 75
  • [38] Task Partitioning and Load Balancing Strategy for Matrix Applications on Distributed System
    Bashir, Adeela }
    Madani, Sajjad A.
    Kazmi, Jawad Haider
    Qureshi, Kalim
    [J]. JOURNAL OF COMPUTERS, 2013, 8 (03) : 576 - 584
  • [39] FILE CONCEPTS FOR PARALLEL I/O
    CROCKETT, TW
    [J]. PROCEEDINGS : SUPERCOMPUTING 89, 1989, : 574 - 579
  • [40] Quantification and analysis of performance fluctuation in distributed file system
    Zhang, Yuchen
    Zhang, Xiao
    Yu, Jinyang
    Shi, Yulong
    Su, Linxuan
    [J]. CLUSTER COMPUTING-THE JOURNAL OF NETWORKS SOFTWARE TOOLS AND APPLICATIONS, 2024, 27 (03): : 3149 - 3162