<font size=2 face="sans-serif">Thanks a lot Rick and Andrew.</font>
<br>
<br><font size=2 face="sans-serif">The CPU seems to be the bottleneck (single
core 333MHz). I get better results when I connect 2 Freescale boards together
(see results below). </font>
<br>
<br><font size=2 face="sans-serif">I tried the sendfile test with a 10MB
file of random data, but I still see the cpu saturated and lower throughput
(see last test below). Is this 10MB big enough?</font>
<br>
<br><font size=2 face="sans-serif">Thanks again,</font>
<br>
<br><font size=2 face="sans-serif">Dominic</font>
<br>
<br><font size=2 face="Courier New">---------- 10Mbit hub ----------</font>
<br><font size=2 face="Courier New">PHY: e0024520:04 - Link is Up - 10/Half</font>
<br><font size=2 face="Courier New">~ # ./netperf -H 10.42.43.2 -c -C --
-s 128K -S 128K</font>
<br><font size=2 face="Courier New">TCP STREAM TEST from 0.0.0.0 (0.0.0.0)
port 0 AF_INET to 10.42.43.2 (10.42.43.2) port 0 AF_INET</font>
<br><font size=2 face="Courier New">Recv Send Send
Utilization Service Demand</font>
<br><font size=2 face="Courier New">Socket Socket Message Elapsed
Send Recv
Send Recv</font>
<br><font size=2 face="Courier New">Size Size Size
Time Throughput local remote
local remote</font>
<br><font size=2 face="Courier New">bytes bytes bytes
secs. 10^6bits/s % S % S
us/KB us/KB</font>
<br>
<br><font size=2 face="Courier New">217088 217088 217088 10.12
7.67 3.45 6.14
36.846 65.596</font>
<br>
<br><font size=2 face="Courier New">---------- 10/100Mbit hub ----------</font>
<br><font size=2 face="Courier New">PHY: e0024520:04 - Link is Up - 100/Half</font>
<br><font size=2 face="Courier New">~ # ./netperf -H 10.42.43.2 -c -C --
-s 128K -S 128K</font>
<br><font size=2 face="Courier New">TCP STREAM TEST from 0.0.0.0 (0.0.0.0)
port 0 AF_INET to 10.42.43.2 (10.42.43.2) port 0 AF_INET</font>
<br><font size=2 face="Courier New">Recv Send Send
Utilization Service Demand</font>
<br><font size=2 face="Courier New">Socket Socket Message Elapsed
Send Recv
Send Recv</font>
<br><font size=2 face="Courier New">Size Size Size
Time Throughput local remote
local remote</font>
<br><font size=2 face="Courier New">bytes bytes bytes
secs. 10^6bits/s % S % S
us/KB us/KB</font>
<br>
<br><font size=2 face="Courier New">217088 217088 217088 10.02
79.87 29.32 67.95
30.072 69.699</font>
<br>
<br><font size=2 face="Courier New">---------- 10/100Mbit switch ----------</font>
<br><font size=2 face="Courier New">PHY: e0024520:04 - Link is Up - 100/Full</font>
<br><font size=2 face="Courier New">~ # ./netperf -H 10.42.43.2 -c -C --
-s 128K -S 128K</font>
<br><font size=2 face="Courier New">TCP STREAM TEST from 0.0.0.0 (0.0.0.0)
port 0 AF_INET to 10.42.43.2 (10.42.43.2) port 0 AF_INET</font>
<br><font size=2 face="Courier New">Recv Send Send
Utilization Service Demand</font>
<br><font size=2 face="Courier New">Socket Socket Message Elapsed
Send Recv
Send Recv</font>
<br><font size=2 face="Courier New">Size Size Size
Time Throughput local remote
local remote</font>
<br><font size=2 face="Courier New">bytes bytes bytes
secs. 10^6bits/s % S % S
us/KB us/KB</font>
<br>
<br><font size=2 face="Courier New">217088 217088 217088 10.02
94.11 45.09 83.53
39.252 72.709</font>
<br>
<br><font size=2 face="Courier New">---------- Two Freescale boards with
cross-over cable (1000Mbit, full-duplex) ----------</font>
<br><font size=2 face="Courier New">PHY: e0024520:04 - Link is Up - 1000/Full</font>
<br><font size=2 face="Courier New">~ # ./netperf -H 10.42.43.2 -c -C --
-s 128K -S 128K</font>
<br><font size=2 face="Courier New">TCP STREAM TEST from 0.0.0.0 (0.0.0.0)
port 0 AF_INET to 10.42.43.2 (10.42.43.2) port 0 AF_INET</font>
<br><font size=2 face="Courier New">Recv Send Send
Utilization Service Demand</font>
<br><font size=2 face="Courier New">Socket Socket Message Elapsed
Send Recv
Send Recv</font>
<br><font size=2 face="Courier New">Size Size Size
Time Throughput local remote
local remote</font>
<br><font size=2 face="Courier New">bytes bytes bytes
secs. 10^6bits/s % S % S
us/KB us/KB</font>
<br>
<br><font size=2 face="Courier New">217088 217088 217088 10.01
191.72 99.90 92.01 42.686
39.313</font>
<br>
<br><font size=2 face="Courier New">---------- Sendfile test ----------</font>
<br><font size=2 face="Courier New">~ # ./netperf -H 10.42.43.2 -c -C -tTCP_SENDFILE
-F /dev/shm/10meg.bin</font>
<br><font size=2 face="Courier New">TCP SENDFILE TEST from 0.0.0.0 (0.0.0.0)
port 0 AF_INET to 10.42.43.2 (10.42.43.2) port 0 AF_INET</font>
<br><font size=2 face="Courier New">Recv Send Send
Utilization Service Demand</font>
<br><font size=2 face="Courier New">Socket Socket Message Elapsed
Send Recv
Send Recv</font>
<br><font size=2 face="Courier New">Size Size Size
Time Throughput local remote
local remote</font>
<br><font size=2 face="Courier New">bytes bytes bytes
secs. 10^6bits/s % S % S
us/KB us/KB</font>
<br>
<br><font size=2 face="Courier New"> 87380 16384 16384
10.00 150.21 99.90 96.50
54.481 52.628</font>
<br>
<br>
<br>
<table width=100%>
<tr valign=top>
<td>
<td><font size=1 face="sans-serif"><b>Andrew Gallatin <gallatin@cs.duke.edu></b></font>
<p><font size=1 face="sans-serif">2010/05/05 01:08 PM</font>
<td><font size=1 face="Arial"> </font>
<br><font size=1 face="sans-serif"> To:
Dominic Lemire <DominicLemire@vtech.ca></font>
<br><font size=1 face="sans-serif"> cc:
netperf-talk@netperf.org</font>
<br><font size=1 face="sans-serif"> Subject:
Re: [netperf-talk] Testing on Freescale
MPC8313ERDB</font></table>
<br>
<br>
<br><tt><font size=2>Rick Jones wrote:<br>
> Dominic Lemire wrote:<br>
<br>
> and make certain your CPU is not saturated. If there is any
question <br>
> whatsoever the remote CPU might be bottlenecking, you should check
there <br>
> too - add a "-C" after the "-c"<br>
<br>
And if the CPU is saturated on the sender, try using the sendfile<br>
test:<br>
<br>
./netperf -H 192.168.1.1 -c -C -tTCP_SENDFILE -F /path/to/a/big/file<br>
<br>
This eliminates the copy on the transmit side.<br>
<br>
Are there multiple CPUS (cores?) on this system, if yes<br>
and your CPU is still saturated, then try using the -T CPU binding<br>
options and multiple copies of netperf. Assuming 2 quad-cores<br>
<br>
netperf -H 192.168.1.1 -T0,0 -P 0 -l 120 &<br>
netperf -H 192.168.1.1 -T1,1 -P 0 -l 120 &<br>
netperf -H 192.168.1.1 -T2,2 -P 0 -l 120 &<br>
netperf -H 192.168.1.1 -T3,3 -P 0 -l 120 &<br>
<br>
Note the "-l 120", which is intended to run a longer<br>
test, and minimize the percent of time when not all<br>
4 are running at once. To really do a multithreaded<br>
test, you need netperf4, uperf, or even iperf.<br>
<br>
Drew<br>
</font></tt>
<br>