SCIENCE

Live Testbed to Provide Wide Area OpenFlow Network For Innovative Research Projects

SC11 has announced a reminder for its call for SCinet Research Sandbox (SRS) proposals which are due on June 5, 2011. The SRS is designed to allow researchers to experimentally test and demonstrate their ideas on innovative network architectures, applications and protocols in the unique live environment of the SCinet network. This year, the SRS will provide researchers with access to over 100 Gigabits per second of capacity and the flexibility of a software-programmable testbed network on the SCinet infrastructure.   

To do so, the SC11 SRS will feature for the first time a 10 Gigabit per second (Gbps), multi-vendor OpenFlow network testbed connected from the Washington State Convention Center in Seattle to potentially several national research networks to provide wide area OpenFlow capabilities. OpenFlow allows the implementation of software-defined network policy.  While originally conceived to allow researchers to implement new protocols without entirely new hardware, OpenFlow has begun to allow innovation and optimization with current protocols. Researchers can experiment with new protocols and techniques for high-throughput data movement, and also use the OpenFlow protocol to program the network to “steer” data flows in real time based on a number of flow characteristics

“OpenFlow is featured prominently this year as part of the SRS because of its promise to revolutionize the networking environment and in turn its ability to support HPC applications. OpenFlow allows an HPC data center to easily reconfigure the network on the fly, separating bulk data flows from other flows, for example. Openflow will also provide virtualization of the data center network to support cloud environments, allowing resource allocation to individual virtual machines, or providing multiple clouds from the same infrastructure,” said Brian Tierney, co-chair of the SRS and group lead for the Advanced Network Technologies Group, ESnet. “The SRS provides a perfect testbed environment to showcase the emerging work in this space directly to potential stakeholders in the HPC community.”

Built each year to support the SC conference, SCinet represents one of the most powerful and advanced networks in the world. SCinet brings to life a highly sophisticated, very high capacity networking infrastructure that supports the revolutionary application demonstrations that have become the trademark of SC. In 2011, it is anticipated that SCinet will have nearly .5 Tbps of capacity and be built using emerging 100 Gigabit Ethernet.

“In addition to supporting the extreme demands of the HPC-based demonstrations that have become the trademark of the conference, SCinet also seeks to foster and highlight developments in network research – which is critical infrastructure for connecting high-performance, distributed computing resources,” said Jeff Boote, SCinet chair for SC11 and Internet2 assistant director for R&D Architecture and Performance. “The SRS has been established to provide a formal venue to showcase network innovations in their infancy to demonstrate the value of these innovations to the HPC community”

Unique in 2011, submissions to the Disruptive Technologies (DT) program can also demonstrate their research as part of the SRS.  Complementary to the mission of the SRS, Disruptive Technologies, which has taken place as part of the SC technical program since 2006, examines new computing and networking architectures and interfaces that will significantly impact the high-performance computing field throughout the next five to 15 years, but have not yet emerged in current systems.Submissions to Disruptive Technologies should indicate their interest in demonstrating their research as part of SRS where indicated in the DT online submissions form.

“The Disruptive Technology program at SC is aimed at showcasing technologies and innovations that have the potential to transform high-performance computing. The ability to ‘program the network’ stands to be one of the most disruptive innovations in high performance computing, an arena that depends on, and pushes, the capabilities of network infrastructure.  Virtualization and customization of the network is missing piece of the cloud computing ecosystem, and this stands to finally make it viable for HPC. For this reason, we have coupled the DT program with the SRS this year to allow researchers the unique ability to demonstrate the possibilities of this disruptive innovation in HPC,” said Martin Swany, co-chair of the SRS, chair of Disruptive Technologies, and associate professor at the University of Delaware.

SRS submissions should describe the nature of the experiments, desired outcomes, the relevance to the HPC community, as well as a description of the network requirements and vendor collaborations (if appropriate). Submissions do not have to utilize OpenFlow to be considered for SRS. Submissions may be up to 3 pages long, and must address the approach and what will be learned or demonstrated by the effort. Those whose submissions are accepted will be able to present their experiment in a technical panel session, and submissions will be included in the SC11 proceedings. In addition, accepted projects are expected to write up the results obtained during SC11, and all SRS write-ups will be assembled for journal submission. SCinet may provide additional fiber to a booth to support an SRS experiment as well. Submissions are due by June 5, 2011.  To submit to the SRS, visit:  https://submissions.supercomputing.org/