Advanced network performance suite to manage collider data
- By William Jackson
- Oct 15, 2008
The U.S. research community that will be working with the Large Hadron Collider (LHC) ' the new particle accelerator near Geneva, Switzerland ' is adopting a new suite of network-performance tools to help manage the terabytes of data that will be produced by the experiments.
This deployment marks the first major implementation in this country of perfSONAR, the product of a global collaboration by educational and research organizations in the United States that includes the Energy Department's ESnet, Internet2, the Fermi National Accelerator Laboratory, the Stanford Linear Accelerator Center and the University of Delaware.
The perfSONAR adopters are members of the U.S. LHC ATLAS community, led by Brookhaven National Laboratory. ATLAS is a particle physics experiment of the LHC at the European Organization for Nuclear Research (CERN). When the particle accelerator goes into full operation next spring, scientists will be transmitting or downloading about two terabytes of data within four-hour windows every few weeks, in addition to the continuous multigigabit flows that will be maintained between LHC sites.
LHC not only is the world's largest collider, it also is the largest distributed scientific project of its kind, relying on the use of advanced networks to support physics analysis carried out by thousands of researchers around the world. Because of these short windows for transferring data, maintaining optimal network performance on the entire network path is critical to completing work on time, which is a challenge when crossing multiple network domains.
'PerfSONAR provides users and network engineers a window into the network to generate near real time performance traffic monitoring and visualization,' said Brian Tierney, computer scientist with DOE's ESnet. 'Its ability to provide global analysis of network performance problems across network domains makes it possible for users to instantly pinpoint choke points and make immediate adjustments to their applications to vastly enhance network performance and facilitate greater network reliability.'
U.S. LHC ATLAS sites will deploy the new Performance Node LiveCD, which allows organizations to install a perfSONAR-enabled node with tools for monitoring passive network metrics and running active performance tests. Internet2 and ESnet are also deploying a number of hosts running perfSONAR services on their respective networks to help monitor LHC data transfers.
Visibility provided by perfSONAR is expected to reduce the burdens of manually troubleshooting networking issues, allowing scientists to focus on their work rather than on network administration.
Development of perfSONAR is being supported in this country by a National Science Foundation grant to the University of Delaware, in collaboration with Internet2 and the Stanford Linear Acceleratory Center. The funding will help make the tools easily deployable by the U.S. research community, as well as enable continued collaboration with the international community. Kevin Thompson, program officer for the NSF Office of Cyberinfrastructure, said the work on perfSONAR "will have the potential to have a lasting impact across all networked scientific applications."
An electrical malfunction discovered during last month's start-up of the LHC is likely to delay ramping up to full operational capability. ATLAS is continuing to tune its detectors using cosmic ray data to minimize disruption caused by delays.
ATLAS originally stood for 'A Toroidal LHC ApparatuS', but today is a stand-alone name, according to CERN. Its detectors will search the results of high-speed, head-on collisions of protons in the collider for new information on the basic forces governing the universe since its creation. Among the areas where it may shed new light are:
- The origins of mass
- Extra dimensions of space
- Microscopic black holes and
- Evidence of dark matter.
William Jackson is a Maryland-based freelance writer.