INDUSTRY

The Measurement and Network Analysis group of the National Laboratory for Applied Network Research (NLANR/MNA) has successfully begun a cooperative effort with the Computer Network Information Center (CNIC) of the Chinese Academy of Science in Beijing China, in which researchers of the two nations are using advanced technology to measure traffic on high-speed international computer networks. “CNIC Director Baoping Yan and I are delighted to announce that an NLANR AMP device has been installed in Beijing and is acquiring statistical data for traffic on the international link,” said Ronn Ritke, Co-Principal Investigator of NLANR/MNA. “This not only is an important step in scientific cooperation, it literally will assist in the exchange of information between our two countries.” Based at the San Diego Supercomputer Center (SDSC), the National Science Foundation-funded NLANR/MNA group has created a network analysis infrastructure to conduct their own research and to support the efforts of outside researchers, systems administrators, and students. The work began on high-performance networks operating in the United States, but within the past three years network researchers and system administrators in other countries have been enthusiastically collaborating with NLANR/MNA researchers, hosting NLANR devices on their networks and even setting up measurement and analysis research projects of their own. The NLANR/MNA research infrastructure now extends to five continents, and when the GLORIAD ring network connecting the U.S., China, and Russia becomes fully operational, it will circle the world. Contacts between the American and Chinese network researchers took off in late 2001, when CNIC Director Yan visited SDSC. The dialog continued over the subsequent two years and was reinforced at the sixth international workshop Pacific Rim Applications and Grid Middleware Assembly (PRAGMA). Held at CNIC in Beijing in May 2004, PRAGMA 6 was attended by 150 representatives from 39 institutions in more than a dozen Pacific Rim countries. PRAGMA was founded in March 2002 at SDSC as an open international initiative to establish collaborations and advance the use of computational grids among the leading research institutions of the Pacific Rim; CNIC was a founding member. PRAGMA 6 was chaired by Director Yan, and she and Ritke used the meeting as an opportunity to finalize the placement of an AMP device at CNIC. Ritke also established close working relationships with the other network measurement researchers at CNIC during the PRAGMA meeting. “Installation of the AMP machine at CNIC is a critical step for us to understand network efficiency between the U.S. and China, and can improve network operation for scientific cooperation between the two nations. I commend Ronn Ritke’s tireless efforts to make this a reality,” said Bill Chang, Senior Program Manager at the NSF’s Office of International Science and Engineering. Network measurements are essential for identifying and locating problems -- malfunctions, bottlenecks, inefficiencies, incompatibilities, etc. -- in ultrafast research networks and in high-speed international links. The NLANR/MNA researchers assess the performance of next-generation computer networks by measuring the flow of message traffic and analyzing performance issues. The group makes all of the data, analyses and tools available to the worldwide network engineering and research community to ensure that American and international networks can be tuned for maximum end-to-end performance. The Active Measurement Project (AMP) performs site-to-site active measurements and analyses, which enable network researchers and engineers to track problems and changes in network performance, by inserting test messages into the networks it studies and observing their progress through the systems. The measurement devices for the AMP project are rack-mounted PCs with high-speed network cards, installed in the network equipment racks of universities and research institutions that participate in this project. More than 160 AMP monitors are deployed on high-speed research networks in the United States and in other countries. The monitors exchange messages with other monitors on the network, tracking the messages to determine the routing pathways, round-trip times, and packet loss between sites. In addition to gathering data, the AMP project also analyzes long-term, large-scale trends in message flow patterns. All participation is voluntary, and both NLANR/MNA and participating sites are meticulous about maintaining the privacy of network users. “We collect statistics of the message traffic, but we don’t read the content of any messages,” said Tony McGregor, AMP Project Manager. “If we were working with the Post Office instead of high-speed networks, our devices would be sending post cards to each other and reading postmarks -- but they would completely ignore all of the other mail being handled.” Trust in NLANR/MNA’s integrity was one of the key elements in obtaining the approval of the Chinese government for the research project. There were some initial concerns over what sorts of information the AMP devices would be able to acquire, and what raw data and analyses would be published on the Internet for anyone and everyone to see. The senior staff of CNIC and NLANR resolved all of the questions in the spirit of open scientific inquiry. The mission of the San Diego Supercomputer Center (SDSC) is to innovate, develop, and deploy technology to advance science. SDSC is involved in an extensive set of collaborations and activities at the intersection of technology and science whose purpose is to enable and facilitate the next generation of scientific advances. Founded in 1985 and primarily funded by the National Science Foundation, SDSC is an organized research unit of the University of California, San Diego. With a staff of more than 400 scientists, software developers, and support personnel, SDSC is an international leader in data management, network research, grid and cluster computing, biosciences, geosciences, and visualization. For more information on SDSC, visit http://www.sdsc.edu/. For information about the NLANR Measurement and Network Analysis group, see http://mna.nlanr.net/. This material is based upon work supported by the National Science Foundation under cooperative agreement no. ANI-0129677 (2002).