A resource selection strategy and check pointing to minimize computational time in case of grid resource failure

Grid provides us a huge amount of computational resources in a distributed manner, using which we can perform our tasks over these grid environments. The main bottleneck of the grid environment is resource failure. When a resource fails, the grid scheduler reschedules that job on the new resource from its last saved checkpoint information. In this paper, we propose the following algorithm: if a resource fails, then it tries to minimize the completion time of a job running on two different resources with different characteristics by comparing highest check point information between these two concurrent resources.