摘要：The computational resources need by the scientific community to solve problems is beyond the current available infrastructure. Performance requirements are needed due constant research progress, new problems studies or detail increase of the current ones. Users create new wide distributed systems such as computational Grids to achieve desired performance goals. Grid systems are generally built on top of available computational resources as cluster, parallel machines or storage devices distributed within different organizations and those resources are interconnected by a network. Application tuning on Grid environment is a hard task due system characteristics like multi-cluster job distribution among different local schedulers and dynamic network bandwidth behavior. We had a Monitoring, Analysis and Tuning Environment (MATE) that allows dynamic performance tuning applications within a cluster. Due to the many software layers present on the grid, similar job submission may execute on different places. To tune application jobs, our tool needs to locate and follow the jobs execution within the system. We call this a process tracking problem. This paper presents MATE integration to the Grid and the two process tracking approaches implemented in order to solve the process tracking problem within Grid systems
