M. Chakraborty, S. Roy, and N. Mukherjee (India)
Grid, parallel execution, task dependence, communication overhead, agglomeration.
Scheduling dependent tasks onto Grid resources is an important area in Grid computing research. One major objective of the problem is to allocate tasks to make efficient use of the computational resources by combining the benefits of parallelisms available among those tasks. Identification of the communication requirements among the tasks and grouping them in order to reduce communication overhead are the major issues related to task scheduling problem. This paper proposes a scheme for task scheduling and identifies the different kinds of task dependencies. A novel technique is introduced which works with a metric called performance ratio and checks the possibilities of parallel execution of a set of dependent tasks, so that the dependent tasks with heavy communication overhead can be scheduled on the same Grid resource provider and communication overhead is reduced.
Important Links:
Go Back
