<div dir="ltr">Not powersave of any component in my control. Powersave of the CMTS? I'd expect high latency for idle pings in that case too.<div><br><div><br><div class="gmail_extra"><br><div class="gmail_quote">On 16 January 2018 at 20:52, Dave Taht <span dir="ltr"><<a href="mailto:dave.taht@gmail.com" target="_blank">dave.taht@gmail.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Power save?<br>
<div><div class="h5"><br>
On Tue, Jan 16, 2018 at 11:36 AM, Arie <<a href="mailto:nospam@ariekanarie.nl">nospam@ariekanarie.nl</a>> wrote:<br>
> Recently I accidentally discovered something quite odd about my home DOCSIS<br>
> connection (shaped with cake) while running a flent rrul test.<br>
> During the flent rrul test, another machine in my home had started a Steam<br>
> game update, this opened somewhere between 8-12 connections and saturated my<br>
> downstream.<br>
><br>
> The interesting part was the resulting rrul graph, showing perfect latency<br>
> control during the test, but 100-150ms of bufferbloat at the very start and<br>
> end of the rrul graph (when rrul is idle, just pinging).<br>
><br>
> Instead of a Steam download I started an iperf3 client on a remote machine<br>
> that opened 16 connections to a LAN machine. Same behavior as the Steam<br>
> download.<br>
><br>
> At first I thought this was a bug with cake, but no matter how I tuned cake<br>
> (limiting my 400/40 connection to 50/20 for example), the behavior was<br>
> similar.<br>
> I tried fq_codel+htb, and got similar results to cake, high latency before<br>
> the rrul test kicked off, great latency while rrul was doing its up and<br>
> downloads.<br>
><br>
> So I swapped out my self-compile LEDE router with an Edgerouter ER-X with<br>
> both stock and LEDE firmware, both with fq_codel and cake (on both stock and<br>
> LEDE firmware). Same results.<br>
> Even without any SQM active, the rrul test still improved the latency of my<br>
> connection when it's also downloading from 8+ connections at the same time.<br>
><br>
> I managed to take the flent rrul test out of the equation by starting a<br>
> hping3 "flood" to the hop next of my cable modem.<br>
><br>
>> hping3 -2 -d 0 -s 10080 -k -p 80 -i u100<br>
>> first-hop-or-ISP-gateway-goes-<wbr>here<br>
><br>
><br>
> This also fixed the latency while many downloads were running by sending<br>
> about 300KB/s of empty UDP packets to some unresponsive port on my ISPs<br>
> local gateway.<br>
><br>
> I'm puzzled by this result, somehow sending 300KB/s of empty packets<br>
> upstream drastically improves the latency of my connection when it's<br>
> receiving many downloads.<br>
><br>
> Equipment used:<br>
> Cisco EPC3212 cable modem (8x4 EuroDOCSIS 3.0)<br>
> Linksys WRT1900ACS router with LEDE<br>
> Ubiquiti Edgerouter ER-X with both EdgeOS (stock) and LEDE<br>
><br>
><br>
><br>
><br>
</div></div>> ______________________________<wbr>_________________<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" rel="noreferrer" target="_blank">https://lists.bufferbloat.net/<wbr>listinfo/bloat</a><br>
><br>
<span class="HOEnZb"><font color="#888888"><br>
<br>
<br>
--<br>
<br>
Dave Täht<br>
CEO, TekLibre, LLC<br>
<a href="http://www.teklibre.com" rel="noreferrer" target="_blank">http://www.teklibre.com</a><br>
Tel: <a href="tel:1-669-226-2619" value="+16692262619">1-669-226-2619</a><br>
</font></span></blockquote></div><br></div></div></div></div>