<div dir="ltr"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">I know about Chinese operators who will deliberately congest peering ports to influence 3rd party network behaviour.</blockquote><div>How do they deliberately congest peering ports? Do you hear from those Chinese operators or you observe this from the traffic?</div><div><br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><font color="#000000">Most countries in Africa do not implement great big firewalls. Our problems are quite different :-\...</font></blockquote><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Not having great big firewalls tends to help :-).<span class="gmail-im" style="color:rgb(80,0,80)"><br></span></blockquote><div><div class="gmail_signature" data-smartmail="gmail_signature"><br></div><div class="gmail_signature" data-smartmail="gmail_signature">Seems like you also think GFW is part of the cause, however, we don't have direct evidence. Just curious, What is your "problems"? I thought it's congestion.</div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><br></div><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature">Best,<br>Pengxiong Zhu<br>Department of Computer Science and Engineering<br>University of California, Riverside</div></div><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Sun, Mar 15, 2020 at 11:13 PM Mark Tinka <<a href="mailto:mark.tinka@seacom.mu">mark.tinka@seacom.mu</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><br>
<br>
On 15/Mar/20 22:51, Frank Habicht wrote:<br>
<br>
><br>
> thanks for the "quotes", Mark. I agree.<br>
><br>
> <a href="https://www.caida.org/publications/presentations/2018/investigating_causes_congestion_african_afrinic/investigating_causes_congestion_african_afrinic.pdf" rel="noreferrer" target="_blank">https://www.caida.org/publications/presentations/2018/investigating_causes_congestion_african_afrinic/investigating_causes_congestion_african_afrinic.pdf</a><br>
><br>
> page 23:<br>
> Results Overview<br>
> • No evidence of widespread congestion<br>
>    - 2.2% of discovered link showed evidence of congestion at the end of<br>
>      our measurements campaign<br>
><br>
> page 34:<br>
> Conclusions<br>
> • Measured IXPs were congestion-free, which promotes peering in the<br>
>   region<br>
><br>
> <a href="https://conferences.sigcomm.org/imc/2017/papers/imc17-final182.pdf" rel="noreferrer" target="_blank">https://conferences.sigcomm.org/imc/2017/papers/imc17-final182.pdf</a><br>
><br>
> my conclusion: s/congestion/congestion or the lack thereof/g<br>
><br>
> Frank Habicht<br>
><br>
> PS: yes, i could name peers that once had inadequate links into an IXP.<br>
> but for how long did that happen? (yes..., any minute is too long...)<br>
<br>
Indeed.<br>
<br>
There was a time when backhaul links between ISP routers at the exchange<br>
point and their nearest PoP were based on E1's, wireless, e.t.c. But<br>
that could be said of, pretty much, every exchange point that kicked off<br>
inside of the last 2.5 decades.<br>
<br>
Nowadays, such links, if they exist, are the very deep exception, not<br>
the rule.<br>
<br>
Mark.<br>
</blockquote></div>