A Fault Tolerance Scheduling Algorithm for Parallel Terrain Analysis

In recent years, due to the increasing calculation demands for the massive spatial data analysis, the parallel computing based on high-performance computers has become an inevitable trend of Digital Terrain Analysis (DTA in short). A key problem is to design fault-tolerant software to enhance the stability and robustness of scientific application. This paper presents an approach of failure recovery solution in distributed parallel computing environment. This approach to schedule the failing task is built by dividing all the failing data into several partitions according the calculating scale of failure. By means of the Fault-Tolerant Granularity Model, the scheduling algorithm can assign the failing task dynamically. Finally, two experiments focusing data size and failure size are discussed.