What is the measured data transmission latency between TeraGrid nodes?

Note: After ten years of service to the national science and engineering community, the TeraGrid project has ended. It is succeeded by a new National Science Foundation (NSF) program, the Extreme Science and Engineering Discovery Environment (XSEDE). You should move any data stored on TeraGrid systems to an alternate storage resource. If you have leftover service units on your TeraGrid allocation, or if your research requires further use of high performance computational, visualization, storage, and network resources, consider applying for an allocation on one or more XSEDE digital services.

The data transmission latency (i.e., network latency or network round trip time) between TeraGrid nodes has been measured at about 80ms, from one US coast to the other. The round trip time (RTT) between nodes at San Diego Supercomputer Center (SDSC) in California and the National Center for Supercomputing Applications (NCSA) in Illinois was measured at 60ms.

The RTT between any two nodes is affected by network and application performance, and the physical distance between the end systems. Applications and remote file system protocols that use many remote procedural calls (RPCs) may not perform well if the RTT between nodes is high.

Note: Due to the speed of light, a data transmission latency of 20ms is unavoidable.

For further examination of network latency, its affect on applications, and methods for bench testing applications, see Applications and the Speed of Light from the Pittsburgh Supercomputing Center (PSC) web site.

Comments/Questions/Corrections