Can you provide some more information?<br><br>Actual timings, and a tcpdump fragment?<br><br><div><span class="gmail_quote">On 2/14/06, <b class="gmail_sendername">Laurent Lagrange</b> <<a href="mailto:lagrange@fr.oleane.com">
lagrange@fr.oleane.com</a>> wrote:</span><blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;">
<div><span><font color="#0000ff" face="Arial" size="2">Hi
Pantelis,</font></span></div>
<div><span><font color="#0000ff" face="Arial" size="2"></font></span> </div>
<div><span><font color="#0000ff" face="Arial" size="2">Thanks
for the express reply.</font></span></div>
<div><span><font color="#0000ff" face="Arial" size="2"></font></span> </div>
<div><span><font color="#0000ff" face="Arial" size="2">I know
that what I say seems incredible. </font></span><span><font color="#0000ff" face="Arial" size="2">But I don't
understand what NAPI does.</font></span></div>
<div><span><font color="#0000ff" face="Arial" size="2">My
measure is very simple. I display a message </font></span><span><font color="#0000ff" face="Arial" size="2">on the client
when 1000 exchanges are done.</font></span></div>
<div><span><font color="#0000ff" face="Arial" size="2">I
already check the ifconfig stats on the board after some
seconds.</font></span></div>
<div><span><font color="#0000ff" face="Arial" size="2">The
measures seems the same with or without NAPI.</font></span></div>
<div><span><font color="#0000ff" face="Arial" size="2"></font></span> </div>
<div><span><font color="#0000ff" face="Arial" size="2">More
details ?</font></span></div>
<div><span><font color="#0000ff" face="Arial" size="2">Thanks
again</font></span></div>
<div><span><font color="#0000ff" face="Arial" size="2">Laurent</font></span></div>
<div><span><font color="#0000ff" face="Arial" size="2"></font></span> </div>
<div><span><font color="#0000ff" face="Arial" size="2"></font></span> </div>
<blockquote style="border-left: 2px solid rgb(0, 0, 255); padding-left: 5px; margin-left: 5px;">
<div dir="ltr" align="left"><font face="Tahoma" size="2">-----Message d'origine-----<br><b>De :</b> Pantelis Antoniou
[mailto:<a href="mailto:pantelis.antoniou@gmail.com" target="_blank" onclick="return top.js.OpenExtLink(window,event,this)">pantelis.antoniou@gmail.com</a>]<br><b>Envoyé :</b> mar. 14 février
2006 16:29<br><b>À :</b> Laurent Lagrange<br><b>Cc :</b>
<a href="mailto:linuxppc-embedded@ozlabs.org" target="_blank" onclick="return top.js.OpenExtLink(window,event,this)">linuxppc-embedded@ozlabs.org</a><br><b>Objet :</b> Re: Gianfar is slower than
fcc_enet on MPC8541 ???<br><br></font></div><div><span class="e" id="q_1096952d8b1af181_1">Hi Laurent,<br><br>I found that
pretty hard to believe.<br><br>What are you measuring exactly?<br><br>Speed of
replies? If so it's explainable since the TSECs
use<br>NAPI.<br><br>Regards<br><br>Pantelis<br><br>
<div><span class="gmail_quote">On 2/14/06, <b class="gmail_sendername">Laurent
Lagrange</b> <<a href="mailto:lagrange@fr.oleane.com" target="_blank" onclick="return top.js.OpenExtLink(window,event,this)">lagrange@fr.oleane.com</a>>
wrote:</span>
<blockquote class="gmail_quote" style="border-left: 1px solid rgb(204, 204, 204); margin: 0pt 0pt 0pt 0.8ex; padding-left: 1ex;"><br>Hello,<br><br>I
work on a cutom MPC8541 board with Linux 2.6.9.<br>The kernel activates the
L1 cache (instructions and data)<br>and the L2 cache (entirely used as cache
and not as sram).<br><br>I configure<br>1 FCC (FCC1), <br>2 TSECs with or
without NAPI (no effect) but without stashing in L2 sram.<br>All PHYs are
automatically configured in 100MB full
duplex.<br><br> eth0: Gianfar
Ethernet Controller Version 1.1,
00:10:cd:48:48:e0<br> eth0:
Running with NAPI
disabled<br> eth0: 64/64
RX/TX BD ring size<br> eth1:
Gianfar Ethernet Controller Version 1.1,
00:10:cd:48:48:e1<br> eth1:
Running with NAPI
disabled<br> eth1: 64/64
RX/TX BD ring size <br> eth2:
FCC ENET Version custom, 00:10:cd:48:48:e2<br><br>Then I launch 3 simple TCP
servers, one on each ports.<br><br>From remote machines I runs 3 TCP
clients.<br>The client sends messages of 1000 bytes,<br>The server receives
and echoes the message <br>The client receives the echoed message, check the
content<br>and sends a new message again.<br><br>The result is that the 2
TSECs are 2 times slower than the FCC.<br><br>If I run a "top" application
on the board, I use less than 10% of the CPU <br>Each port consumes about
1/3 of the CPU.<br><br>Any idea on how to configure the gianfar driver
?<br><br>Thanks<br>Laurent<br><br><br>_______________________________________________<br>Linuxppc-embedded
mailing list<br><a href="mailto:Linuxppc-embedded@ozlabs.org" target="_blank" onclick="return top.js.OpenExtLink(window,event,this)">Linuxppc-embedded@ozlabs.org</a><br><a href="https://ozlabs.org/mailman/listinfo/linuxppc-embedded" target="_blank" onclick="return top.js.OpenExtLink(window,event,this)">
https://ozlabs.org/mailman/listinfo/linuxppc-embedded</a><br></blockquote></div><br></span></div></blockquote>
</blockquote></div><br>