<div dir="ltr">Don't you want to accuse the size of the buffer, rather than the latency?<div><br></div><div>For example, say someone has some hardware and their line is fairly slow.</div><div>it might be RED on the graph because the buffer is quite big relative to the</div><div>bandwidth delay product of the line. A test is telling them they have</div><div>bloated buffers.</div><div><br></div><div>Then they upgrade their product speed to a much faster product, and suddenly</div><div>that buffer is fairly small, the incremental latency is low, and no longer shows</div><div>RED on a test.</div><div><br></div><div>What changed? the hardware didn't change. Just the speed changed. So the</div><div>test is saying that for your particular speed, the buffers are too big. But for a</div><div>higher speed, they may be quite ok.</div><div><br></div><div>If you add 100ms to a 1gigabit product the buffer has to be what, ~10mb?</div><div>but adding 100ms to my feeble line is quite easy, the billion router can have </div><div>a buffer of just 100kb and it is too high. But that same billion in front of a</div><div>gigabit modem is only going to add at most 1ms to latency and nobody</div><div>would complain.</div><div><br></div><div>Ok I think I talked myself around in a complete circle: a buffer is only bad IF</div><div>it increases latency under load. Not because of its size. It might explain why</div><div>these fiber connection tests don't show much latency change, because </div><div>their buffers are really inconsequential at those higher speeds?</div><div><br></div></div><div class="gmail_extra"><br><div class="gmail_quote">On Fri, Apr 24, 2015 at 7:02 PM, Toke Høiland-Jørgensen <span dir="ltr"><<a href="mailto:toke@toke.dk" target="_blank">toke@toke.dk</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><span class="">Sebastian Moeller <<a href="mailto:moeller0@gmx.de">moeller0@gmx.de</a>> writes:<br>
<br>
> Oh, I can get behind that easily, I just thought basing the<br>
> limits on externally relevant total latency thresholds would directly<br>
> tell the user which applications might run well on his link. Sure this<br>
> means that people on a satellite link most likely will miss out the<br>
> acceptable voip threshold by their base-latency alone, but guess what<br>
> telephony via satellite leaves something to be desired. That said if<br>
> the alternative is no telephony I would take 1 second one-way delay<br>
> any day ;).<br>
<br>
</span>Well I agree that this is relevant information in relation to the total<br>
link latency. But keeping the issues separate has value, I think,<br>
because you can potentially fix your bufferbloat, but increasing the<br>
speed of light to get better base latency on your satellite link is<br>
probably out of scope for now (or at least for a couple of hundred more<br>
years: <a href="http://theinfosphere.org/Speed_of_light" target="_blank">http://theinfosphere.org/Speed_of_light</a>).<br>
<span class=""><br>
> What I liked about fixed thresholds is that the test would give<br>
> a good indication what kind of uses are going to work well on the link<br>
> under load, given that during load both base and induced latency come<br>
> into play. I agree that 300ms as first threshold is rather unambiguous<br>
> though (and I am certain that remote X11 will require a massively<br>
> lower RTT unless one likes to think of remote desktop as an oil tanker<br>
> simulator ;) )<br>
<br>
</span>Oh, I'm all for fixed thresholds! As I said, the goal should be (close<br>
to) zero added latency...<br>
<span class=""><br>
> Okay so this would turn into:<br>
><br>
> base latency to base latency + 30 ms: green<br>
> base latency + 31 ms to base latency + 100 ms: yellow<br>
> base latency + 101 ms to base latency + 200 ms: orange?<br>
> base latency + 201 ms to base latency + 500 ms: red<br>
> base latency + 501 ms to base latency + 1000 ms: fire<br>
> base latency + 1001 ms to infinity: fire & brimstone<br>
><br>
> correct?<br>
<br>
</span>Yup, something like that :)<br>
<span class="HOEnZb"><font color="#888888"><br>
-Toke<br>
</font></span></blockquote></div><br></div>