<p dir="ltr">In summary, the new Codel behaviour works better on egress but worse on ingress. That's reasonable - on ingress the queue always appears to build slowly, so the new scheme always triggers late, and is more likely to return aggressively to a lower signalling rate. I think we're going to need a special mode for ingress.</p>
<p dir="ltr">However, I think a good deal of your poor results are due to not properly matching the actual link bandwidth any more. I would suspect trouble in the cable rather than the modem, given the symptoms.</p>
<p dir="ltr"> - Jonathan Morton<br>
</p>
<div class="gmail_quote">On 4 Jun 2015 21:11, "Dave Taht" <<a href="mailto:dave.taht@gmail.com">dave.taht@gmail.com</a>> wrote:<br type="attribution"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">not very well controlled dataset at:<br>
<a href="http://snapon.lab.bufferbloat.net/~d/fishcake/" target="_blank">http://snapon.lab.bufferbloat.net/~d/fishcake/</a><br>
<br>
On Thu, Jun 4, 2015 at 11:10 AM, Dave Taht <<a href="mailto:dave.taht@gmail.com">dave.taht@gmail.com</a>> wrote:<br>
> I did a bit of setup on my connection to give me a decent rrul result.<br>
> (I was not rate limiting inbound enough) The duration of the initial<br>
> load spike is much less pronounced than the fq_codel result. I note<br>
> that I have offloads still on, so I imagine fq_codel is getting<br>
> tweaked by that....<br>
><br>
> but ingress gets way out of hand later on in this test. I can make an<br>
> argument for decay (count/2) being far too aggressive. In fact, even<br>
> count - 2 seemed too much in older testing I had done with other<br>
> variants. I would certainly like to get a feel for when and where the<br>
> three parts of codel are kicking in in various workloads.<br>
><br>
> <a href="http://www.dslreports.com/speedtest/613646" target="_blank">http://www.dslreports.com/speedtest/613646</a><br>
><br>
> I really need to get to where I can quickly get to a blog entry on<br>
> this stuff, and back to comprehensive, controlled testing.<br>
><br>
><br>
><br>
><br>
><br>
> On Thu, Jun 4, 2015 at 10:11 AM, Dave Taht <<a href="mailto:dave.taht@gmail.com">dave.taht@gmail.com</a>> wrote:<br>
>> My network here is in flux (new modem, signal strength problems, cable<br>
>> problems) and toke's testbed is presently doing wifi work, so I did a<br>
>> quick mod to fishcake to make it do linux 4.0 (note I am not sure if<br>
>> this was a 4.1 or a 4.0 change) - attached. (and we lose a few cake<br>
>> options due to me not grokking the new API)<br>
>><br>
>> Cake did well on this, but the behavior at the tail end of the test<br>
>> was disturbing:<br>
>><br>
>> <a href="http://www.dslreports.com/speedtest/611312" target="_blank">http://www.dslreports.com/speedtest/611312</a><br>
>><br>
>> Need to do some work to emulate the dslreports tests.<br>
>><br>
>> And it dropped LOT more packets than fq_codel did. fq_codel marked 33<br>
>> packets for it's result, cake marked 600 and dropped 200, for its.<br>
>><br>
>> I did some rrul testing as well, but was fighting with a modem that<br>
>> used to get 140Mbits, and now only gets 70mbits, and behaves very<br>
>> differently overall with pfifo_fast than i had ever seen before. And<br>
>> along the way snapon got upgraded a bit too... sigh...<br>
>><br>
>> --<br>
>> Dave Täht<br>
>> What will it take to vastly improve wifi for everyone?<br>
>> <a href="https://plus.google.com/u/0/explore/makewififast" target="_blank">https://plus.google.com/u/0/explore/makewififast</a><br>
><br>
><br>
><br>
> --<br>
> Dave Täht<br>
> What will it take to vastly improve wifi for everyone?<br>
> <a href="https://plus.google.com/u/0/explore/makewififast" target="_blank">https://plus.google.com/u/0/explore/makewififast</a><br>
<br>
<br>
<br>
--<br>
Dave Täht<br>
What will it take to vastly improve wifi for everyone?<br>
<a href="https://plus.google.com/u/0/explore/makewififast" target="_blank">https://plus.google.com/u/0/explore/makewififast</a><br>
_______________________________________________<br>
Cake mailing list<br>
<a href="mailto:Cake@lists.bufferbloat.net">Cake@lists.bufferbloat.net</a><br>
<a href="https://lists.bufferbloat.net/listinfo/cake" target="_blank">https://lists.bufferbloat.net/listinfo/cake</a><br>
</blockquote></div>