Performance Prediction Based Resource Selection in Grid Environments

Deploying Grid technologies by distributing an application over several machines has been widely used for scientific simulations, which have large requirements for computational resources. The Grid Configuration Manager (GCM) is a tool developed to ease the management of scientific applications in distributed environments and to hide some of the complexities of Grids from the end-user. In this paper we present an extension to the Grid Configuration Manager in order to incorporate a performance based resource brokering mechanism. Given a pool of machines and a trace file containing information about the runtime characteristics of the according application, GCM is able to select the combination of machines leading to the lowest execution time of the application, taking machine parameters as well as the network interconnect between the machines into account. The estimate of the execution time is based on the performance prediction tool Dimemas. The correctness of the decisions taken by GCM is evaluated in different scenarios.

[1]  Andrew S. Grimshaw,et al.  Grid resource management in legion , 2004 .

[2]  Ramin Yahyapour,et al.  A Proposal for a Generic Grid Scheduling Architecture , 2007 .

[3]  Rajkumar Buyya,et al.  A Grid service broker for scheduling e-Science applications on global data Grids: Research Articles , 2006 .

[4]  Jarek Nabrzyski,et al.  Grid resource management: state of the art and future trends , 2004 .

[5]  Kenichi Miura,et al.  Overview of Japanese science Grid project NAREGI , 2006 .

[6]  Michael M. Resch,et al.  Towards Efficient Execution of MPI Applications on the Grid: Porting and Optimization Issues , 2003, Journal of Grid Computing.

[7]  Ian T. Foster,et al.  The Globus project: a status report , 1998, Proceedings Seventh Heterogeneous Computing Workshop (HCW'98).

[8]  Message Passing Interface Forum MPI: A message - passing interface standard , 1994 .

[9]  Rajkumar Buyya,et al.  A Grid service broker for scheduling e‐Science applications on global data Grids , 2006, Concurr. Comput. Pract. Exp..

[10]  H. Martin Bücker,et al.  A Parallel Version of the Quasi-Minimal Residual Method, Based on Coupled Two-Term Recurrences , 1996, PARA.

[11]  Michael M. Resch,et al.  GCM: a grid configuration manager for heterogeneous grid environments , 2005, Int. J. Grid Util. Comput..

[12]  Michael M. Resch,et al.  Software Development in the Grid: The DAMIEN Tool-Set , 2003, International Conference on Computational Science.

[13]  John Darlington,et al.  Scheduling Architecture and Algorithms within the ICENI Grid Middleware , 2003 .

[14]  Jack Dongarra,et al.  Computational Science — ICCS 2003 , 2003, Lecture Notes in Computer Science.

[15]  Jiulong Shan,et al.  Web Services Agreement Based Resource Negotiation in UNICORE , 2005, PDPTA.