<html>
<head>
<meta content="text/html; charset=utf-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<div class="moz-cite-prefix">On 21/05/2015 17:21, Jonathan Morton
wrote:<br>
</div>
<blockquote
cite="mid:3BDE8792-3B33-4DD6-B662-C18B2CECD183@gmail.com"
type="cite">
<pre wrap="">
</pre>
<blockquote type="cite">
<pre wrap="">On 19 May, 2015, at 22:17, Dave Taht <a class="moz-txt-link-rfc2396E" href="mailto:dave.taht@gmail.com"><dave.taht@gmail.com></a> wrote:
So I finished writing up my thoughts on bobbie,
<a class="moz-txt-link-freetext" href="http://www.bufferbloat.net/projects/codel/wiki/Bobbie">http://www.bufferbloat.net/projects/codel/wiki/Bobbie</a>
which might work better than anything on the table in the face of huge
bursts like these, when the rate differential is so small.
</pre>
</blockquote>
<pre wrap="">
I wonder if there’s any profit in making fq_codel and cake behave more like a policer on ingress; that would be halfway to bobbie without writing a lot of new code.
A reasonable test would be to try configuring fq_codel with interval = target = 5ms. If that works better, I could add similar functionality to cake.
- Jonathan Morton
_______________________________________________
Bloat mailing list
<a class="moz-txt-link-abbreviated" href="mailto:Bloat@lists.bufferbloat.net">Bloat@lists.bufferbloat.net</a>
<a class="moz-txt-link-freetext" href="https://lists.bufferbloat.net/listinfo/bloat">https://lists.bufferbloat.net/listinfo/bloat</a>
</pre>
</blockquote>
<br>
Up for a challenge I tried it. Line rate is 40000 down, 10000 up -
Sky broadband UK VDSL2 PTM (manual overhead of 8 for VLAN tagging on
WAN & VDSL2 flags)<br>
note that I also use ECN everywhere. From the dslreports site, with
a new layout I note - nice! Numbers at end of each line are<br>
reported latency for idle (minimum), up (average), down (average) in
ms.<br>
<font face="Courier New, Courier, monospace"><br>
Baseline:<br>
fq_codel 37500 9700 interval 100ms
<a class="moz-txt-link-freetext" href="http://www.dslreports.com/speedtest/526382">http://www.dslreports.com/speedtest/526382</a> - 109 114 112<br>
fq_codel 37500 9700 interval 5ms
<a class="moz-txt-link-freetext" href="http://www.dslreports.com/speedtest/526367">http://www.dslreports.com/speedtest/526367</a> - 106 119 111<br>
<br>
<br>
fq_codel 38500 9700 interval 100ms
<a class="moz-txt-link-freetext" href="http://www.dslreports.com/speedtest/526318">http://www.dslreports.com/speedtest/526318</a> - 106 120 110 standing
q but managed slightly better than....<br>
fq_codel 38500 9700 interval 5ms
<a class="moz-txt-link-freetext" href="http://www.dslreports.com/speedtest/526305">http://www.dslreports.com/speedtest/526305</a> - 116 142 118 standing
q<br>
<br>
<br>
fq_codel 39000 9700 interval 100ms
<a class="moz-txt-link-freetext" href="http://www.dslreports.com/speedtest/526335">http://www.dslreports.com/speedtest/526335</a> - 110 153 113 spikey
spaced<br>
fq_codel 39000 9700 interval 5ms
<a class="moz-txt-link-freetext" href="http://www.dslreports.com/speedtest/526308">http://www.dslreports.com/speedtest/526308</a> - 109 194 112 spikey
closer<br>
<br>
<br>
fq_codel 40000 9700 interval 100ms
<a class="moz-txt-link-freetext" href="http://www.dslreports.com/speedtest/526347">http://www.dslreports.com/speedtest/526347</a> - 116 191 118 spikey <br>
fq_codel 40000 9700 interval 5ms
<a class="moz-txt-link-freetext" href="http://www.dslreports.com/speedtest/526353">http://www.dslreports.com/speedtest/526353</a> - 109 172 112 spikey<br>
<br>
</font>I don't think tweaking intervals has given the hoped for
result in my case. If anything It looks like it increases standing
latency though some of graph<br>
scaling makes that difficult to see. The final test looks like it's
heading in a better direction but it still has 420+ms spikes.<br>
<br>
<br>
<pre class="moz-signature" cols="0">--
Thanks,
<a class="moz-txt-link-abbreviated" href="mailto:Kevin@Darbyshire-Bryant.me.uk">Kevin@Darbyshire-Bryant.me.uk</a>
</pre>
</body>
</html>