<br><br><div class="gmail_quote">On Sun, May 29, 2011 at 10:24 PM, George B. <span dir="ltr"><<a href="mailto:georgeb@gmail.com">georgeb@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
Ok, say I have a network with no over subscription in my net. </blockquote><div><br>I'd love to see one of those. Can I get on it?<br> <br></div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
I have<br>
10G to the internet but am only using about 2G of that. This is the<br>
server side of a network talking to millions of clients. The clients<br>
in this case are on "lossy" wireless networks where packet loss is not<br>
an indication of congestion so much as it is an indication that the<br>
client moved 15 feet behind a pole and had poor network connectivity<br>
for a few minutes.<br>
<br></blockquote><div>Or is using multicast.<br> <br></div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
The idea being that in today's internet, packet loss is not a good<br>
indication of congestion. Often it just means that the radio signal<br>
has been briefly interrupted. What I need is something that can tell<br>
the difference between real congestion and radio loss. ECN seems to<br>
be the way forward in that respect.<br>
<br></blockquote><div>Yes. When it works. Which is rarely.<br> <br></div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
But assuming my network, as a server of content is not over<br>
subscribed, what would you suggest as the best qdisc for such a<br>
traffic profile? In other words, I am looking at this from the server<br>
aspect rather than from the client aspect.<br>
<br></blockquote><div><br>Ah, ok. This was discussed in this loooong thread:<br><br><a href="https://lists.bufferbloat.net/pipermail/bloat/2011-March/000272.html">https://lists.bufferbloat.net/pipermail/bloat/2011-March/000272.html</a><br>
<br>Some form of fair queuing distributes the load to the ultimate end nodes better.<br><br>As for which packet scheduler to choose for that? Don't know, I'm just trying to get to where we can actually test stuff on the edge gateways at this point.<br>
<br></div><blockquote class="gmail_quote" style="margin: 0pt 0pt 0pt 0.8ex; border-left: 1px solid rgb(204, 204, 204); padding-left: 1ex;">
g<br>
_______________________________________________<br>
Bloat mailing list<br>
<a href="mailto:Bloat@lists.bufferbloat.net">Bloat@lists.bufferbloat.net</a><br>
<a href="https://lists.bufferbloat.net/listinfo/bloat" target="_blank">https://lists.bufferbloat.net/listinfo/bloat</a><br>
</blockquote></div><br><br clear="all"><br>-- <br>Dave Täht<br>SKYPE: davetaht<br>US Tel: 1-239-829-5608<br><a href="http://the-edge.blogspot.com" target="_blank">http://the-edge.blogspot.com</a> <br>