ORPS

From Ogce

Abstract

Image:ORPS_Architecture.png
Science gateways manage applications on multiple compute resources and manage data on replicated storage resources. These gateways often get overwhelmed with selection of the right combination of data source and compute host to achieve a quick turnaround with lesser queue wait and faster file transfer. Above all, the gateways would like to programmatically detect and avoid submission to resources that have scheduled and unscheduled down times.

The Gateway Optimal Resource Selection and Integrated Information Services Framework marshals: TeraGrid Information Services, INCA resource monitoring, Karnak start time and wait time prediction and Speedpage file transfer prediction services. The following figure illustrates the high level overview of the architecture. The information is exposed through a REST web service and implemented as a flexible and extensible architecture implemented in Java over the Spring framework.

The framework provides application registry capabilities to register the resources and applications used by a gateway. Application performance models can be plugged to update performance data on a specific host. Once registered the gateway can query for real time status information and the framework will provide status determined by ensuring the required File Transfer and Job Management interfaces are healthy. In a first order, resources in maintenance, faulty job managers, overwhelmed gridftp servers are eliminated for scheduling. Further marshaling the karnak and speed page job queue and file transfer information increases gateway job success rates and turn around times.

Web site tools