QoS-based Scheduling of Workflow Applications on Grids

L.M. Khanli and M. Analoui (Iran)

Keywords

Workflow management, grid computing, active database, GridJQA, QoS

Abstract

With the advent of Grid and application technologies, scientists and engineers are building more and more complex applications to manage and process large data sets, and execute scientific experiments on distributed resources. Such application scenarios require means for composing and executing complex workflows. Therefore, many efforts have been made towards the development of workflow management systems for Grid computing. In this paper, we propose a QoS-based workflow management system and scheduling algorithm that find the best match between workflow applications and resources while meeting QoS requests. The infrastructure is based on the event condition action (ECA) rules in active database. In none of reported works, the ECA rules haven’t been used so far. We also attempt to solve the fault tolerance problem by duplicating delayed tasks using proper rules. Some rules are used for QoS monitoring. We implement the ECA rules in Grid-JQA [1, 2] in order to show that using the rules in the grid environment have better performance. The results of a simulation are provided to evaluate the main idea of the paper.

Important Links:



Go Back