<div>Hello!</div>
<div> </div>
<div>Yes, it is IronCore, not Jet</div>
<div> </div>
<div>/Alexey<br><br></div>
<div class="gmail_quote">2009/3/7 Peter Olsen <span dir="ltr"><<a href="mailto:Peter.Olsen@globalconnect.dk">Peter.Olsen@globalconnect.dk</a>></span><br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">
<div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2">Is it IronCore mgmt module ?</font></span></div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2"></font></span> </div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2">If yes, it is properly even worse.</font></span></div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2"></font></span> </div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2">We discussed this in legth with foundry. To my opinion it is a design bug: stating wire speed packet forward performance and then having limitations like this.</font></span></div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2">I don't know if there is a fix for you. But we gave up in the end, and as we for other reasons as well needed bigger boxes we have replaced nearly all JetCore with XMR/MLX</font></span></div>
<div> </div>
<div>
<p align="left"><font face="Arial" size="2"></font></p>
<p><b><span style="FONT-SIZE: 10pt; COLOR: black; FONT-FAMILY: Arial">Med venlig hilsen/Best regards<br><br></span></b><b><span style="FONT-SIZE: 14pt; COLOR: #005a5a; FONT-FAMILY: Arial">Peter Olsen<br></span></b><b><span style="FONT-SIZE: 8pt; COLOR: gray; FONT-FAMILY: Arial">CTO<br>
</span></b><b><span style="FONT-SIZE: 8pt; COLOR: gray; FONT-FAMILY: Arial">D: +45 7730 3122<br></span></b><b><span style="FONT-SIZE: 8pt; COLOR: gray; FONT-FAMILY: Arial">M: +45 2726 3122<br></span></b><span style="FONT-SIZE: 8pt; FONT-FAMILY: Arial"></span></p>
</div>
<div> </div><br>
<div lang="en-us" dir="ltr" align="left">
<hr>
<font face="Tahoma" size="2"><b>From:</b> Alexey Kouznetsov [mailto:<a href="mailto:foundry-list@kouznetsov.com" target="_blank">foundry-list@kouznetsov.com</a>] <br><b>Sent:</b> 7. marts 2009 14:58<br><b>To:</b> Peter Olsen
<div class="im"><br><b>Subject:</b> Re: [f-nsp] Multicast causing high CPU<br></div></font><br></div>
<div>
<div></div>
<div class="h5">
<div></div>
<div>Thank you, for your replay Peter!</div>
<div> </div>
<div>This is no Jet core... AFAIK Jet core will be J-<font color="#465584">BxGMR4 </font>and CPU protection is not available in our version. As far as I can see it takes 100%CPU at less 10kpps, not 200k<br></div>
<div>Active management module:<br> 466 MHz Power PC processor 750 (version 8/8302) 66 MHz bus<br> 512 KB boot flash memory<br> 8192 KB code flash memory<br> 256 KB SRAM<br> 256 MB DRAM<br></div>
<div>So, As far as I can see only hardware upgrade is the possible solution ?</div>
<div> </div>
<div>/Alexey</div>
<div> </div>
<div class="gmail_quote">2009/3/7 Peter Olsen <span dir="ltr"><<a href="mailto:Peter.Olsen@globalconnect.dk" target="_blank">Peter.Olsen@globalconnect.dk</a>></span><br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">
<div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2">JetCore FPGA can handle around 200.000pps broadcast/multicast before you have ~80-100% CPU load as far as L2 is concerned</font></span></div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2">All packets is handled by CPU by default.</font></span></div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2">You can play around with the CPU protection features but to my experience it have limited impact (and limited success as far as CPU load is concerned)</font></span></div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2">I guess this is kind of architecture limitation in JetCore.</font></span></div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2"></font></span> </div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2">It is even worse if you have the same mac adress arriving from two different directions, e.g. hitting two port at the same time. (will happen if you have a L2 loop), then 99% CPU load will happen at very load pps. In this case it is caused by the mac learning process eating all CPU resources. This behaviour makes JetCore L2 very sensitive to layer2 loops.</font></span></div>
<div><font face="Tahoma" color="#800000" size="2">
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2"></font></span> </div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2">For us it was first efficiently fixed going to MLX/XMR where CPU-protection feature is very efficient and you can force all braodcast/multicast packets to stay in hardware for forwarding. XMR/MLX can also handle much more than 200.000pps in CPU</font></span></div>
<div dir="ltr" align="left"><span><font face="Tahoma" color="#800000" size="2"></font></span> </div></font></div>
<div><span><font face="Tahoma" color="#800000" size="2">br,</font></span></div>
<div><span><font face="Tahoma" color="#800000" size="2">Peter</font></span></div>
<div> </div></div></blockquote></div></div></div></div></blockquote></div><br>