<div dir="ltr"><br><div class="gmail_extra"><br><br><div class="gmail_quote">On Thu, Jan 30, 2014 at 9:06 AM, Jeremy Tourville <span dir="ltr"><<a href="mailto:organ_dr@hotmail.com" target="_blank">organ_dr@hotmail.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div><div>Hello, I followed your excellent instructions here -<br><a href="http://www.bufferbloat.net/projects/cerowrt/wiki/Setting_up_SQM_for_CeroWrt_310" target="_blank">http://www.bufferbloat.net/projects/cerowrt/wiki/Setting_up_SQM_for_CeroWrt_310</a><br>
<br>I am using build 3.10.24-8<br> <br>I am using a DSL line rated at 6 Mbps down and 512kbps up. My real throughput without SQM enabled is 5.7Mbps down and 450kbps up.<br> <br></div></div></blockquote><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div><div dir="ltr">After enabling SQM my throughput has dropped to approximately 4.5Mbps down and 350 kbps up. Does this seem like an amount that is expected? (within norms?)<br></div></div></blockquote><div><br></div><div>
I recommend tuning, using reasonable benchmarks, like rrul. <br><br>Generally you can get pretty close to your provider's provided bandwidth, but repeated tuning is something we try really hard to avoid. We know 85% always works. :)<br>
<br>Hopefully we'll come up with a tool or approach that works dynamically one day, but we're not there yet.<br><br></div><div>So create a setting, run a benchmark, change a knob, run the benchmark, until you get something satisfying<br>
<br>example:<br><br><a href="http://snapon.lab.bufferbloat.net/~cero2/jimreisert/results.html">http://snapon.lab.bufferbloat.net/~cero2/jimreisert/results.html</a><br></div><div><br></div><div>notes:<br><br></div><div>At the moment nfq_codel is a mildly bigger win than fq_codel is at bandwidths below 1mbit.<br>
<br></div><div>there was a change to sqm in releases after this ( I think ). It used to allocate a fairly large<br>amount of bandwidth for priority traffic (64kbit I recall), now it does 12 or so. rrul exercises all queues.<br>
</div><div><br></div><div>you might want to fiddle with target a little (target 20ms)<br> <br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div><div dir="ltr">It would seem reasonable that I should expect some performance loss at the expense of better bufferbloat management based on setting 85-95% of actual download/upload speeds. Please correct me if I am wrong. :-) But my question is, how much is too much? The setting of SQM does fix the bufferbloat issue as evidenced by ping testing and times for packets. With SQM on all packets were 100ms or less. With SQM off the times jumped to over 500ms or more during the speed testing. <br>
<br>For reference I have set the parameters as indicated in the screenshots. I have changed only two variables and tested after each change as indicated in the grid below.<br> <br><table style="width:506pt;border-collapse:collapse" width="674" border="0" cellpadding="0" cellspacing="0">
<colgroup><col style="width:82pt" span="2" width="109">
<col style="width:102pt" width="136">
<col style="width:129pt" width="172">
<col style="width:111pt" width="148">
</colgroup><tbody><tr style="height:15pt" height="20">
<td style="border:0.5pt solid windowtext;width:82pt;height:15pt;background-color:transparent" width="109" height="20"></td>
<td style="border-width:0.5pt 0.5pt 0.5pt 0px;border-style:solid solid solid none;border-color:windowtext windowtext windowtext black;width:82pt;background-color:transparent" width="109">Que setup script</td>
<td style="border-width:0.5pt 0.5pt 0.5pt 0px;border-style:solid solid solid none;border-color:windowtext windowtext windowtext black;width:102pt;background-color:transparent" width="136">Per packet
overhead</td>
<td style="border-width:0.5pt 0.5pt 0.5pt 0px;border-style:solid solid solid none;border-color:windowtext windowtext windowtext black;width:240pt;background-color:transparent" colspan="2" width="320">test
results</td>
</tr>
<tr style="height:15pt" height="20">
<td style="border-width:0px 0.5pt 0.5pt;border-style:none solid solid;border-color:black windowtext windowtext;height:15pt;background-color:transparent" height="20">Test #1</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent">simple.qos</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent" align="right">40</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent">no buffer, less
throughput</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent"><100ms, 4.5mbps
down</td>
</tr>
<tr style="height:15pt" height="20">
<td style="border-width:0px 0.5pt 0.5pt;border-style:none solid solid;border-color:black windowtext windowtext;height:15pt;background-color:transparent" height="20">Test #2<span> </span></td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent">simple.qos</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent" align="right">44</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent">no buffer, less
throughput</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent"><100ms, 4.5mbps
down</td>
</tr>
<tr style="height:15pt" height="20">
<td style="border-width:0px 0.5pt 0.5pt;border-style:none solid solid;border-color:black windowtext windowtext;height:15pt;background-color:transparent" height="20">Test #3</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent">simplest.qos</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent" align="right">40</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent">no buffer, less
throughput</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent"><100ms, 4.5mbps
down</td>
</tr>
<tr style="height:15pt" height="20">
<td style="border-width:0px 0.5pt 0.5pt;border-style:none solid solid;border-color:black windowtext windowtext;height:15pt;background-color:transparent" height="20">Test #4</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent">simplest.qos</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent" align="right">44</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent">no buffer, less
throughput</td>
<td style="border-width:0px 0.5pt 0.5pt 0px;border-style:none solid solid none;border-color:black windowtext windowtext black;background-color:transparent"><100ms, 4.5mbps
down<br></td>
</tr>
</tbody></table> <br></div></div></blockquote><div><br></div><div>whether overhead of 44 or 40 is correct for your provider...<br> <br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
<div><div dir="ltr">I also read your statement- <br>>>>"The CeroWrt development team has been working to nail down a no-brainer set of instructions for eliminating bufferbloat - the lag/latency that kills voice & video chat, gaming, and overall network responsiveness. The hard part is that optimal configuration of the Smart Queue Management (SQM) link is difficult - there are tons of options an ISP can set. Although CeroWrt can adapt to any of them, it's difficult to find out the exact characteristics of the link you have."<br>
<br>What info do I need to get from my ISP to best optimize my connection?</div></div></blockquote><div><br></div><div dir="ltr">Ask 'em to do their own benchmarking with cero & rrul, adopt fq_codel on their dslams and (especially) rate-limiters, and publish their results for each tier they sell?<br>
<br>>I also recognize that this could be an issue that requires multiple changes at once. I am curious to know from the experts what your thoughts are on this. Many thanks in advance!<span class=""><font color="#888888"><br>
</font></span></div><div><br></div><div>I think you can get closer than you got. <br> <br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div>
<div dir="ltr"><span class=""><font color="#888888"> <br>-Jeremy<br> </font></span></div></div>
<br>_______________________________________________<br>
Cerowrt-users mailing list<br>
<a href="mailto:Cerowrt-users@lists.bufferbloat.net">Cerowrt-users@lists.bufferbloat.net</a><br>
<a href="https://lists.bufferbloat.net/listinfo/cerowrt-users" target="_blank">https://lists.bufferbloat.net/listinfo/cerowrt-users</a><br>
<br></blockquote></div><br><br clear="all"><br>-- <br>Dave Täht<br><br>Fixing bufferbloat with cerowrt: <a href="http://www.teklibre.com/cerowrt/subscribe.html" target="_blank">http://www.teklibre.com/cerowrt/subscribe.html</a>
</div></div>