<div dir="ltr">Hash all pings into one fq_codel bucket reserved for the purpose, so if we're getting DoSed we drop them, otherwise if they stay thin they get prioritised?</div><div class="gmail_extra"><br><div class="gmail_quote">On 2 March 2015 at 14:57, 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">On this thread over here, an otherwise pretty clueful user chose<br>
openwrt's qos-scripts over the sqm-scripts, because sqm-scripts had<br>
*higher ping loss*.<br>
<br>
<br>
<a href="http://forums.dlink.com/index.php?topic=61634.msg251125#msg251125" target="_blank">http://forums.dlink.com/index.php?topic=61634.msg251125#msg251125</a><br>
<br>
(I note that both fq_codel enabled QoS systems outperformed<br>
streamboost by a lot, which I am happy about)<br>
<br>
wow. It never registered to me that users might make a value judgement<br>
based on the amount of ping loss, and in looking back in time, I can<br>
think of multiple people that have said things based on their<br>
perception that losing pings was bad, and that sqm-scripts was "worse<br>
than something else because of it."<br>
<br>
sqm-scripts explicitly *deprioritizes* ping. In particular, this<br>
reduces the impact of ping floods from ipv6 to your entire /64, or to<br>
your whole ipv4, fairly well. And I had made the point that<br>
prioritizing ping was a bad idea here (including some dripping sarcasm<br>
later in the piece).<br>
<br>
<a href="http://www.bufferbloat.net/projects/cerowrt/wiki/Wondershaper_Must_Die" target="_blank">http://www.bufferbloat.net/projects/cerowrt/wiki/Wondershaper_Must_Die</a><br>
<br>
but wow, it never occurred to me - in all these years - that ping was<br>
the next core metric on simple tests. I can be really dumb.<br>
<br>
I use netperf-wrapper and tend to ignore most of the ping data, but<br>
certainly on some benchmarks we have published ping doesn't look as<br>
good as the other stuff, *because it is deprioritized below all the<br>
other traffic*. Not strictly rate limited - as some systems do by<br>
default, including openwrt, which is impossible to get right - just<br>
deprioritized....<br>
<br>
How can we fix this user perception, short of re-prioritizing ping in<br>
sqm-scripts?<br>
<span class="HOEnZb"><font color="#888888"><br>
--<br>
Dave Täht<br>
Let's make wifi fast, less jittery and reliable again!<br>
<br>
<a href="https://plus.google.com/u/0/107942175615993706558/posts/TVX3o84jjmb" target="_blank">https://plus.google.com/u/0/107942175615993706558/posts/TVX3o84jjmb</a><br>
<br>
_______________________________________________<br>
aqm mailing list<br>
<a href="mailto:aqm@ietf.org">aqm@ietf.org</a><br>
<a href="https://www.ietf.org/mailman/listinfo/aqm" target="_blank">https://www.ietf.org/mailman/listinfo/aqm</a><br>
</font></span></blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature"><div dir="ltr"><span style="color:rgb(85,85,85);font-family:sans-serif;font-size:small;line-height:1.5em;border-width:2px 0px 0px;border-style:solid;border-color:rgb(213,15,37);padding-top:2px;margin-top:2px">Andrew McGregor |</span><span style="color:rgb(85,85,85);font-family:sans-serif;font-size:small;line-height:1.5em;border-width:2px 0px 0px;border-style:solid;border-color:rgb(51,105,232);padding-top:2px;margin-top:2px"> SRE |</span><span style="color:rgb(85,85,85);font-family:sans-serif;font-size:small;line-height:1.5em;border-width:2px 0px 0px;border-style:solid;border-color:rgb(0,153,57);padding-top:2px;margin-top:2px"> <a href="mailto:andrewmcgr@google.com" target="_blank">andrewmcgr@google.com</a> |</span><span style="color:rgb(85,85,85);font-family:sans-serif;font-size:small;line-height:1.5em;border-width:2px 0px 0px;border-style:solid;border-color:rgb(238,178,17);padding-top:2px;margin-top:2px"> +61 4 1071 2221</span><br></div></div>
</div>