One of the key components of any grid architecture is managing compute and storage resources and optimizing their utilization.SAM has implemented features that allow it to exercise a "fair share" and "prioritized" policy among many groups of users.The goals are as follows:1)implement th experiments policies for resource usage by research group and by data access mode,and 2) optimize the resource usage to maximize the overall throughput defined in terms of real data processing activity,At the lowest level of SAM architecture,called the station,the SAM system integrates the data delivery and cache management with the job control and scheduling of the batch system.At the site-level,for example at Fermilab,requests for data from on-site stations are managed to optimize Mass Storage System resources and network throughput,Management of resources at a various geographic levels are discussed.
展开▼
