Implementation of decentralized load sharing in networked workstations using the condor package

被引:9
|
作者
Hou, CJ [1 ]
Shin, KG [1 ]
机构
[1] UNIV MICHIGAN,DEPT ELECT ENGN & COMP SCI,REAL TIME COMP LAB,ANN ARBOR,MI 48109
基金
美国国家科学基金会;
关键词
D O I
10.1006/jpdc.1996.1244
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In recent years a number of load sharing (LS) mechanisms have been proposed or implemented to fully utilize system resources. We have designed and implemented a decentralized real-time LS mechanism based on the Condor package [1, 2]. Two important features of our design are the use of region-change broadcasts in the information policy to provide each workstation with timely state information at minimum communication cost, and the use of preferred lists in the location policy to avoid task collisions. With these two features, we remove the central manager workstation in Condor, configure its functionalities into each participating workstation, transform Condor into a decentralized LS mechanism, and equip Condor with the capability to tolerate single workstation failures. Also discussed are the experiments on the proposed LS mechanism and the off-the-shelf Condor package and our observations of empirical data. (C) 1997 Academic Press.
引用
收藏
页码:173 / 184
页数:12
相关论文
共 50 条
  • [1] Epoch load sharing in a network of workstations
    Karatza, HD
    Hilzer, RC
    34TH ANNUAL SIMULATION SYMPOSIUM, PROCEEDINGS, 2001, : 36 - 42
  • [2] Implementation and performance evaluation of parallel computations by using cluster of networked workstations
    Wang, H
    Prabhu, GM
    Takle, ES
    Shen, J
    PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOLS I-V, 2000, : 2007 - 2013
  • [4] A comparative study of load sharing on networks of workstations
    Piotrowski, A
    Dandamudi, SP
    INTERNATIONAL SOCIETY FOR COMPUTERS AND THEIR APPLICATIONS 10TH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED COMPUTING SYSTEMS, 1997, : 458 - 465
  • [5] Parallel implementation of the boundary element method using PVM and HPF on a collection of networked workstations
    Mushtaq, J
    Davies, AJ
    APPLICATIONS OF HIGH PERFORMANCE COMPUTING IN ENGINEERING V, 1997, 3 : 181 - 188
  • [6] Networked scheduling for decentralized load frequency control
    Peng, Chen
    Yang, Hongchenyu
    INTELLIGENCE & ROBOTICS, 2022, 2 (03):
  • [7] Load balancing for lattice gas and molecular dynamics simulations on networked workstations
    Bubak, M
    Moscinski, J
    Pogoda, M
    Slota, R
    HIGH-PERFORMANCE COMPUTING AND NETWORKING, 1995, 919 : 329 - 334
  • [8] A DISTRIBUTED FACILITY FOR LOAD SHARING AND PARALLEL PROCESSING AMONG WORKSTATIONS
    SHOJA, GC
    JOURNAL OF SYSTEMS AND SOFTWARE, 1991, 14 (03) : 163 - 172
  • [9] A protocol for load sharing among a cluster of heterogeneous Unix workstations
    Gupta, D
    Gupta, A
    Agrawal, SK
    Agarwal, V
    Bepari, P
    FIRST IEEE/ACM INTERNATIONAL SYMPOSIUM ON CLUSTER COMPUTING AND THE GRID, PROCEEDINGS, 2001, : 668 - 673
  • [10] Usefulness of adaptive load sharing for parallel processing on networks of workstations
    Clarke, S
    Dandamudi, SP
    CONCURRENCY-PRACTICE AND EXPERIENCE, 1999, 11 (08): : 387 - 405