Analysis of resource mapping strategies for fault tolerant scheduling on grid computing

摘要

Grid environment has significant challenges due to failures encountered during job execution. Grid infrastructure must have mechanisms to deal with faults while also providing efficient and reliable services to its end users. Therefore fault tolerance in such an environment could not be ignored. In this paper, two strategies such as Maximum Mapping Strategy (MMS) and Exact Mapping Strategy (EMS) are proposed for fault tolerant job scheduling in grid. Whenever the scheduler has jobs to schedule, MMS and EMS selects the resources based on the maximum suitable mapping and exact mapping of job requirement value with the resource capable value respectively. If failure occurs during execution, re-schedules the jobs using the last saved state according to the failure rate of the resources. EMS approach is effective in the sense that all resources are busy at the same time so that resources are utilized in better way and Make-span i.e. the time taken by all jobs to be finished processing is also reduced. Failure rate is reduces in EMS because failures due to speed and memory and bandwidth is less as load is distributed almost equally among resources compared to MMS.