Matthias Scheler <tron@zhadum.de> writes:
  <about ping as a network speed test method>
> This test method is bad. If you test the fxp driver with "ttcp" in
> UDP mode it gets good results, too. But if you use TCP mode or try
> to copy files via NFS/UDP you will not even get full 10MB/Sec
> ethernet speed.

...

> I suggest you try running "ttcp -r -s" on one and "ttcp -t -s
> first-machine" on the other machine and post the results. I would
> really like to see your numbers.

dogbert(68)ttcp -r -s
ttcp-r: buflen=8192, nbuf=2048, align=16384/0, port=5001  tcp
ttcp-r: socket
ttcp-r: accept from 129.16.227.166
ttcp-r: 16777216 bytes in 1.92 real seconds = 8512.14 KB/sec +++
ttcp-r: 11287 I/O calls, msec/call = 0.17, calls/sec = 5864.05
ttcp-r: 0.0user 0.3sys 0:01real 15% 0i+0d 0maxrss 0+2pf 11081+88csw

butthead(94)ttcp -t -s dogbert
ttcp-t: buflen=8192, nbuf=2048, align=16384/0, port=5001  tcp  -> dogbert
ttcp-t: socket
ttcp-t: connect
ttcp-t: 16777216 bytes in 1.89 real seconds = 8668.57 KB/sec +++
ttcp-t: 2048 I/O calls, msec/call = 0.95, calls/sec = 1083.57
ttcp-t: 0.0user 0.4sys 0:01real 23% 0i+0d 0maxrss 0+2pf 1872+3csw

dogbert(69)dmesg | grep fxp0
fxp0 at pci0 dev 13 function 0: Intel EtherExpress Pro 10+/100B Ethernet
fxp0: interrupting at irq 5
fxp0: Ethernet address 00:10:5c:ab:02:fb
inphy0 at fxp0 phy 1: i82555 10/100 media interface, rev. 0

butthead(99)dmesg | grep de0
de0 at pci0 dev 11 function 0
de0: interrupting at irq 11
de0: 21140A [10-100Mb/s] pass 2.0
de0: address 00:a0:cc:6a:0c:a4
de0: enabling 10baseT port
de0: enabling 100baseTX port

dogbert is a 450Mhz PII with 512MB (BX) and butthead is a 266MHz PII
with 128MB (LX), both running NetBSD almost-current.

Almost 9MB/s seems pretty OK with me.

/Jan Sparud