On Mon, 20 Sep 2004 11:45:42 -0500, James Kuhns <[EMAIL PROTECTED]> wrote: > I benchmarked the "raw" speed using ttcp and a windows port of ttcp called > wsttcp before I benchmarked the file transfers (I didn't post those > results). I used the -s option in ttcp to take the drives out of the > equation as much as possible. Throughput averaged ~11.4MB/s over 100Mb and > ~60.4MB/s over 1000Mb (no matter which direction). > > I purposely added the overhead of the transfer protocols and I/O into the > benchmark stats because I wanted a more realistic picture of what kind of > improvement 1000Mb gave me when transfering files (the primary reason I went > to 1000Mb). >
Just to give you guys an idea of TCP overhead, I benchmarked about $100k of network gear today. Using Sun Blade 1500s and nttcp, on UDP I can saturate the gigE ports (I get right at 1000 mbit), but the Sun is at about 97-99 % CPU. The same test but with TCP puts the CPU pegged, and I only get about 650 Mbit/sec.
