• Subscribe

iSGTW Feature - The GridSims: real tools for simulated parallel and distributed computing


Feature - The GridSims: real tools for simulated parallel and distributed computing


Grid developers can now test and evaluate their algorithms in a controlled, simulated grid environment.
Screenshot © Electronic Arts Inc.

How can you test new grid algorithms and management tools without tying up the resources of the grid you're trying to manage? The GridSim toolkit may well be your answer.

An open-source software platform that lets users simulate grid resources and networks with a variety of configurations, GridSim allows researchers to perform repeatable experiments and studies otherwise impossible in a real, dynamic grid environment.

Checking reality

To evaluate the performance of grid resource management and application scheduling algorithms, researchers need to conduct many rounds of repeatable and controlled experiments: somewhat difficult given the inherent heterogeneity and dynamic nature of grids.

Additionally, grid testbeds are limited, and creating an adequately-sized testbed is expensive and time consuming. Moreover, since resources are autonomous and owned by different organisations, creating a testbed requires the handling of different administration policies at each resource. Simulation is thus a much easier means of studying complex scenarios.

All roads lead to grid. Rajkumar Buyya, a developer of the GridSim technology, poses next to an Australian roadsign that shows what lies ahead.
Image courtesy of the Gridbus Project

GridSim is of great value to both students and experienced researchers who want to study grids, or test new algorithms and strategies in a controlled parallel and distributed computing environment.

GridSim supports the simulation of various types of resources with different capabilities and configurations and can easily create and integrate various allocation or scheduling policies by extending them from one of the classes. Its infrastructure and framework support advance reservation as well as auction and data grid functionalities, and it can read workload traces taken from supercomputers for simulating a realistic grid environments. This functionality is useful for testing resource scheduling problems.

The program also incorporates a background network traffic functionality, based on a probabilistic distribution. This function is useful when conducting simulations over congested public networks.

International adoption

GridSim was developed by the Grids Lab at the Unversity of Melbourne in Australia and in the last five years has been continuously extended to include many new capabilities, also receiving contributions from external collaborators.

In particular, the National University of Singapore has contributed a QoS-based network module, the University of Ljubljana (Slovenia) has carried out a DataGrid module, and Universidad de Castilla La Mancha (Spain) has worked together on a resource failure module. Academic and industrial users of GridSim include the University of Manchester (UK), IBM Research, Unisys, HP, University of Southern California (USA), France Telecom, Indian Institute of Technology, Tsinghua University (China), and Sweden's Umeå University.

International collaborators include Gokul Poduval and Chen-Khong Tham, National University of Singapore; Uros Cibej and Borut Robic, The University of Ljubljana, Slovenia; Agustin Caminero, Blanca Caminero; and Carmen Carrion, Universidad de Castilla La Mancha, Spain.

- Anthony Sulistio and Rajkumar Buyya, Department of Computer Science and Software Engineering, the University of Melbourne, Australia

Join the conversation

Do you have story ideas or something to contribute? Let us know!

Copyright © 2021 Science Node ™  |  Privacy Notice  |  Sitemap

Disclaimer: While Science Node ™ does its best to provide complete and up-to-date information, it does not warrant that the information is error-free and disclaims all liability with respect to results from the use of the information.

Republish

We encourage you to republish this article online and in print, it’s free under our creative commons attribution license, but please follow some simple guidelines:
  1. You have to credit our authors.
  2. You have to credit ScienceNode.org — where possible include our logo with a link back to the original article.
  3. You can simply run the first few lines of the article and then add: “Read the full article on ScienceNode.org” containing a link back to the original article.
  4. The easiest way to get the article on your site is to embed the code below.