A new grid resource management mechanism with resource-aware policy administrator for SLA-constrained applications

被引:11
作者
Han, Youngjoo [1 ]
Youn, Chan-Hyun [1 ]
机构
[1] Informat & Commun Univ, Sch Engn, Taejon, South Korea
来源
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE | 2009年 / 25卷 / 07期
关键词
Grid resource management; Service level agreement; Deadline scheduling; Profit policy; Divisible load scheduling; SELECTION;
D O I
10.1016/j.future.2008.11.005
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
Due to the dynamic nature and an uncertainty of Grid computing, system behavior in terms of Quality of Service (QoS) depends crucially Oil the selection of appropriate subset of the available resources. Thus, a well-organized system architecture that provides high system availability using a scheduling mechanism for Grid applications is required. In this paper, we design an efficient architecture referred to as Resource-Aware Policy Administrator (RAPA) with Service Level Agreement (SLA) and real-time attributes in Grid resources and propose a new Grid resource management mechanism with an admission control scheme to make an optimal resource allocation policy for both satisfying QoS requirements in terms of deadline as well as profit and accepting more jobs. Also, we demonstrate detailed workings of the proposed schemes with the RAPA via a simulation study by using real-life parameters. The simulation results show that the proposed schemes have an effect oil accepting more jobs with satisfying the deadline of jobs and increasing service profits and Call guarantee high system availability in terms of system performance. (C) 2008 Elsevier B.V. All rights reserved.
引用
收藏
页码:768 / 778
页数:11
相关论文
共 34 条
[1]   GridICE: a monitoring service for Grid systems [J].
Andreozzi, S ;
De Bortoli, N ;
Fantinel, S ;
Ghiselli, A ;
Rubini, GL ;
Tortone, G ;
Vistoli, MC .
FUTURE GENERATION COMPUTER SYSTEMS, 2005, 21 (04) :559-571
[2]  
BATTRE D, 2007, P WORKSH UK PLANN SC
[3]   Divisible Load Theory: A New Paradigm for Load Scheduling in Distributed Systems [J].
Veeravalli Bharadwaj ;
Debasish Ghose ;
Thomas G. Robertazzi .
Cluster Computing, 2003, 6 (1) :7-17
[4]   The Grid economy [J].
Buyya, R ;
Abramson, D ;
Venugopal, S .
PROCEEDINGS OF THE IEEE, 2005, 93 (03) :698-714
[5]  
CAPANNINI G, 2007, P 2007 ACM IEEE C SU
[6]   Adjusted fair scheduling and non-linear workload prediction for QoS guarantees in grid computing [J].
Doulamis, Nikolaos ;
Doulamis, Anastasios ;
Litke, Antonios ;
Panagakis, Athanasios ;
Varvarigou, Theodora ;
Varvarigos, Emmanuel .
COMPUTER COMMUNICATIONS, 2007, 30 (03) :499-515
[7]   Grid resource brokering algorithms enabling advance reservations and resource selection based on performance predictions [J].
Elmroth, Erik ;
Tordsson, Johan .
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2008, 24 (06) :585-593
[8]  
FOSTER I, 2003, GRID 2 BLUEPRINT NEW, P159
[9]   Condor-G: A Computation Management Agent for Multi-Institutional Grids [J].
James Frey ;
Todd Tannenbaum ;
Miron Livny ;
Ian Foster ;
Steven Tuecke .
Cluster Computing, 2002, 5 (3) :237-246
[10]  
HAN YJ, 2006, P INT C GRID COMP AP, P25