Heuristic Based Task Scheduling In Grid Kamali Gupta 1 , Manpreet Singh 2 1Department of Computer Engineering, GIMT, Kanipala, Kurukshetra, Haryana,, India kamaligupta@gimtkkr.com 2Department of Computer Engineering, M.M. University, Mullana, Ambala, Haryana,, India drmanpreetsinghin@gmail.com Abstract— Grid computing is concerned with coordinated resource sharing and problem solving in dynamic, multi-institutional virtual organizations. Efficient scheduling of complex applications in a grid environment reveals several challenges due to its high heterogeneity, dynamic behavior and space shared utilization. Objectives of scheduling algorithms are increase in system throughput, efficiency and reduction in task completion time. The main focus of this paper is to highlight the merits of resource and task selection technique based on certain heuristics. Keyword- Grid Computing, Task Scheduling, Min-Min, Max-Min, Suffrage, Makespan. I. INTRODUCTION The term grid [1] is increasingly appearing in computer literature, generally referring to some form of system framework into which hardware or software components can be plugged and which permits easy configuration and creation of new functionality from existing components. Grids enable the sharing, selection and aggregation of a wide variety of resources including supercomputers, storage systems, data sources and specialized devices that are geographically distributed and owned by different organizations for solving large- scale computational and data intensive problems in science, engineering and commerce [2]. The computing power of grid is aggregated by that of various organizational or individual computing resources and grid users need only to submit computational tasks to it. There are still some difficult issues impeding the development of grid, among which is the issue of grid task scheduling [3][4]. In order to efficiently utilize available grid resources and promptly complete tasks assigned to the grid, providing a suitable task scheduling strategy for the grid computing is necessary [5][6]. The objective of this research work is to make a comparison among various heuristic based scheduling algorithms under different resource/task mapping environments. In Min-Min algorithm [7], the smaller tasks are chosen first, making use of resources with high computational power. As a result, the schedule prepared by Min- Min is not optimal when number of smaller tasks exceeds the larger one. Max-Min algorithm [9] schedules larger tasks first. But in some cases, the makespan may increase due to the execution of larger tasks first. The rationale behind Suffrage [10] is that a task should be assigned to a certain resource and if it does not go to that resource, it will suffer the most. For each task, its suffrage value is defined as the difference between its best Minimum Completion Time (MCT) and its second-best MCT. Tasks with high suffrage value take precedence during scheduling. II HEURISTIC BASED SCHEDULING ALGORITHMS The resource selection process is used to choose one or more resources from the list of candidates for a given resource requirement. Since all resources in the list could meet the minimum requirements imposed by the task, so an algorithm is needed that can choose the best resource for executing the task. Min-Min Algorithm: Min-Min [8] begins with the set MT (Meta Task) of all unassigned tasks and has two phases. In the first phase, the set of minimum expected completion time for each task in MT is found. In the second phase, the task with the overall minimum expected completion time from MT is chosen and assigned to the corresponding macine. Then this task is removed from MT and the process is repeated until all tasks in the MT are mapped as shown in Fig. 1. However, the Min- Min algorithm is unable to balance the load well as it usually does the scheduling of small tasks initially. BEGIN 1. While (J != Null) // J is set of jobs 2. For each job j i £ J For each machine m j Kamali Gupta et al. / International Journal of Engineering and Technology (IJET) ISSN : 0975-4024 Vol 4 No 4 Aug-Sep 2012 254