3rd International IEEE/Create-Net Workshop on Networks for Grid Applications

Research Article

The Design and Demonstration of the Ultralight Testbed

  • @INPROCEEDINGS{10.1109/BROADNETS.2006.4374312,
        author={Harvey Newman and Dimitri Bourilkov and Julian Bunn and Richard Cavanaugh and Iosif Legrand and Steven Low and Shawn McKee and Dan Nae and Sylvain Ravot and Conrad Steenberg and Xun Su and Michael Thomas and Frank van  Lingen and Yang  Xia},
        title={The Design and Demonstration of the Ultralight Testbed},
        proceedings={3rd International IEEE/Create-Net Workshop on Networks for Grid Applications},
  • Harvey Newman
    Dimitri Bourilkov
    Julian Bunn
    Richard Cavanaugh
    Iosif Legrand
    Steven Low
    Shawn McKee
    Dan Nae
    Sylvain Ravot
    Conrad Steenberg
    Xun Su
    Michael Thomas
    Frank van Lingen
    Yang Xia
    Year: 2006
    The Design and Demonstration of the Ultralight Testbed
    DOI: 10.1109/BROADNETS.2006.4374312
Harvey Newman1,*, Dimitri Bourilkov2,*, Julian Bunn1,*, Richard Cavanaugh2,*, Iosif Legrand1,*, Steven Low1,*, Shawn McKee3,*, Dan Nae1,*, Sylvain Ravot1,*, Conrad Steenberg1,*, Xun Su1,*, Michael Thomas1,*, Frank van Lingen1,*, Yang Xia1,*
  • 1: California Institute of Technology, United States
  • 2: University of Florida
  • 3: University of Michigan
*Contact email: newman@hep.caltech.edu , bourilkov@phys.ufl.edu, julian.bunn@caltech.edu , cavanaug@phys.ufl.edu , iosif.legrand@cern.ch , slowc@altech.edu , smckee@umich.edu , dan.nae@cern.ch , sylvain.ravot@cern.ch , conrad@hep.caltech.edu, xsu@hep.caltech.edu, thomas@hep.caltech.edu, fvlingen@caltech.edu, yxia@caltech.edu


In this paper we present the motivation, the design, and a recent demonstration of the UltraLight testbed at SC|05. The goal of the Ultralight testbed is to help meet the data-intensive computing challenges of the next generation of particle physics experiments with a comprehensive, network- focused approach. UltraLight adopts a new approach to networking: instead of treating it traditionally, as a static, unchanging and unmanaged set of inter-computer links, we are developing and using it as a dynamic, configurable, and closely monitored resource that is managed from end-to-end. To achieve its goal we are constructing a next-generation global system that is able to meet the data processing, distribution, access and analysis needs of the particle physics community. In this paper we will first present early results in the various working areas of the project. We then describe our experiences of the network architecture, kernel setup, application tuning and configuration used during the bandwidth challenge event at SC|05. During this Challenge, we achieved a record-breaking aggregate data rate in excess of 150 Gbps while moving physics datasets between many Grid computing sites.