Research of Process Migration Mechanism Based on Checkpoint in Computational Grid

Abstract

Checkpoint mechanism is very important for long-running and large-scale scientific project computing tasks. So it just meet the requirements of fault-tolerant in grid system. This paper imports GridCPR into Grid Environment. When a job was failed, it can be started from the latest checkpoint instead of the begin to provide with the function of fault tolerance in grid platform and enhance the efficiency of computing tasks.