<div dir="ltr">One other thought I've had with this, is that the apu2 is multi-core, and the i210 is multi-queue.<div><br></div><div>Cake/htb aren't, iirc, setup to run on multiple cores (as the rate limiters then don't talk to each other). But with the correct tuple hashing in the i210, I _should_ be able to split things and do two cores at 500Mbps each (with lots of compute left over). </div><div><br></div><div>Obviously, that puts a limit on single-connection rates, but as the number of connections climb, they should more or less even out (I remember Dave Taht showing the oddities that happen with say 4 streams and 2 cores, where it's common to end up with 3 streams on the same core). But assuming that the hashing function results in even sharing of streams, it should be fairly balanced (after plotting some binomial distributions with higher "n" values). Still not perfect, especially since streams aren't likely to all be elephants.</div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Wed, Mar 25, 2020 at 4:03 AM Toke Høiland-Jørgensen <<a href="mailto:toke@toke.dk">toke@toke.dk</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-style:solid;border-left-color:rgb(204,204,204);padding-left:1ex">Sebastian Moeller <<a href="mailto:moeller0@gmx.de" target="_blank">moeller0@gmx.de</a>> writes:<br>
<br>
> Hi Toke,<br>
><br>
><br>
>> On Mar 25, 2020, at 09:58, Toke Høiland-Jørgensen <<a href="mailto:toke@toke.dk" target="_blank">toke@toke.dk</a>> wrote:<br>
>> <br>
>> Aaron Wood <<a href="mailto:woody77@gmail.com" target="_blank">woody77@gmail.com</a>> writes:<br>
>> <br>
>>> I recently upgraded service from 150up, 10dn Mbps to xfinity's gigabit<br>
>>> (with 35Mbps up) tier, and picked up a DOCSIS 3.1 modem to go with it.<br>
>>> <br>
>>> Flent test results are here:<br>
>>> <a href="https://burntchrome.blogspot.com/2020/03/bufferbloat-with-comcast-gigabit-with.html" rel="noreferrer" target="_blank">https://burntchrome.blogspot.com/2020/03/bufferbloat-with-comcast-gigabit-with.html</a><br>
>>> <br>
>>> tl/dr; 1000ms of upstream bufferbloat<br>
>>> <br>
>>> But it's DOCSIS 3.1, so why isn't PIE working? Theory: It's in DOCSIS 3.0<br>
>>> upstream mode based on the status LEDs. Hopefully it will go away if I can<br>
>>> convince it to run in DOCSIS 3.1 mode.<br>
>> <br>
>> I think that while PIE is "mandatory to implement" in DOCSIS 3.1, the<br>
>> ISP still has to turn it on? So maybe yelling at them will work? (ha!)<br>
>> <br>
>>> At the moment, however, my WRT1900AC isn't up to the task of dealing with<br>
>>> these sorts of downstream rates.<br>
>>> <br>
>>> So I'm looking at the apu2, which from this post:<br>
>>> <a href="https://forum.openwrt.org/t/comparative-throughput-testing-including-nat-sqm-wireguard-and-openvpn/44724" rel="noreferrer" target="_blank">https://forum.openwrt.org/t/comparative-throughput-testing-including-nat-sqm-wireguard-and-openvpn/44724</a><br>
>>> <br>
>>> Will certainly get most of the way there.<br>
>> <br>
>> My Turris Omnia is doing fine on my 1Gbps connection (although that<br>
>> hardly suffers from bloat, so I'm not doing any shaping; did try it<br>
>> though, and it has no problem with running CAKE at 1Gbps).<br>
><br>
> Well, doing local network flent RRUL stress tests indicated that<br>
> my omnia (at that time with TOS4/Openwrt18) only allowed up to<br>
> 500/500 Mbps shaping with bi directionally saturating traffic<br>
> with full MTU-sized packets. So I undirectional CAKE at 1Gbps<br>
> can work, but under full load, I did not manage that, what did I<br>
> wrong?<br>
<br>
Hmm, not sure I've actually done full bidirectional shaping. And trying<br>
it now, it does seem to be struggling...<br>
<br>
-Toke<br>
</blockquote></div>