and 53 ms of latency. Results show that up to 97% efficiency of such high bandwidth high latency network is possible, achieving 80-90 Gbps in most test cases with a peak transfer rate of 100 Gbps.
Grid computing has enabled scientific communities to effectively share computing resources distributed over many independent sites. Several such communities, or Virtual Organizations (VO), in the Open Science Grid and the European Grid Infrastructure use the GlideinWMS system to run complex application work-flows. GlideinWMS is a pilot-based workload… (More)
In 2005, the DZero Data Reconstruction project processed 250 tera-bytes of data on the Grid, using 1,600 CPU-years of computing cycles in 6 months. The large computational task required a high-level of refinement of the SAM-Grid system, the integrated data, job, and information management infrastructure of the RunII experiments at Fermilab. The success of… (More)
The SAM-Grid job management component does not currently regulate the flow of jobs to the execution sites. When multiple jobs are submitted to the same execution site, they all enter the gateway node more or less at the same time. Because job preparation at the gateway is a CPU intensive activity, we have observed high value of load (20) at the gateway… (More)
Collaborate with the Open Science Grid (OSG) Network Area for the deployment of PerfSONAR at 100 OSG facilities Aggregate and display data through the OSG Dashboard for end-to-end hop-by-hop paths across network domains R&D on 100G for production use by CMS & FNAL high-capacity high-throughput Storage facility Ensure that the stack of software and… (More)
The SciDAC Center for Enabling Distributed Petascale Science (CEDPS) seeks to accelerate DOE research by eliminating barriers to reliable and performant wide area data movement. A major focus of CEDPS R&D has been the development of Globus Online, a hosted data movement service to which users can hand off responsibility for a range of data movement tasks.… (More)
The Open Science Grid (OSG) offers access to around hundred Compute elements (CE) and storage elements (SE) via standard Grid interfaces. The Resource Selection Service (ReSS) is a push-based workload management system that is integrated with the OSG information systems and resources. ReSS integrates standard Grid tools such as Condor, as a brokering… (More)