<div dir="ltr"><div class="gmail_extra">RPS didn't change. Throughput didn't change. Our prod load is 200-700 RPS per server (changes during the day) and my load test load was constant 470 RPS.</div><div class="gmail_extra"><br></div><div class="gmail_extra">Clients didn't change. Doesn't matter if they use HTTP 1.1 or 1.0, because the only thing which changed is squid version. And as I figured out, it's not actually about 2.7 to 3.5 update, it's all about difference between 3.5.20 and 3.5.21.</div><div class="gmail_extra"><br></div><div class="gmail_extra">I'm sorry but anything you say about throughput doesn't make any sense. Load pattern didn't change. Squid still handles the same amount of requests.</div><div class="gmail_extra"><br></div><div class="gmail_extra">I think I'm going to load test every patch applied to 3.5.21 from this page: <a href="http://www.squid-cache.org/Versions/v3/3.5/changesets/SQUID_3_5_21.html">http://www.squid-cache.org/Versions/v3/3.5/changesets/SQUID_3_5_21.html</a> so I'll be able to point to exact change which introduced this behavior. I'll try to do it during the weekend or may be on Monday.</div><div class="gmail_extra"><br><div class="gmail_quote">On Sat, Jul 8, 2017 at 5:46 AM, Amos Jeffries <span dir="ltr"><<a href="mailto:squid3@treenet.co.nz" target="_blank">squid3@treenet.co.nz</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"><span class="gmail-">On 08/07/17 02:06, Ivan Larionov wrote:<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
Thank you for the fast reply.<br>
<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
On Jul 7, 2017, at 01:10, Amos Jeffries <<a href="mailto:squid3@treenet.co.nz" target="_blank">squid3@treenet.co.nz</a>> wrote:<br>
<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
On 07/07/17 13:55, Ivan Larionov wrote:<br>
</blockquote></blockquote></blockquote>
>>><br>
</span><span class="gmail-"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
However I assumed that this is a bug and that I can find older version which worked fine. I started testing from 3.1.x all the way to 3.5.26 and this is what I found:<br>
* All versions until 3.5.21 work fine. There no issues with huge amount of TIME_WAIT connections under load.<br>
* 3.5.20 is the latest stable version.<br>
* 3.5.21 is the first broken version.<br>
* 3.5.23, 3.5.25, 3.5.26 are broken as well.<br>
This effectively means that bug is somewhere in between 3.5.20 and 3.5.21.<br>
I hope this helps and I hope you'll be able to find an issue. If you can create a bug report based on this information and post it here it would be awesome.<br>
</blockquote>
<br>
The changes in 3.5.21 were fixes to some common crashes and better caching behaviour. So I expect at least some of the change is due to higher traffic throughput on proxies previously restricted by those problems.<br>
<br>
</blockquote>
<br>
I can't imagine how throughput increase could result in 500 times more TIME_WAIT connections count.<br>
<br>
</blockquote>
<br></span>
More requests per second generally means more TCP connections churning.<br>
<br>
Also when going from Squid-2 to Squid-3 there is a change from HTTP/1.0 to HTTP/1.1 and the accompanying switch from MISS to near-HIT revalidations. Revalidations usually only have headers without payload so the same bytes/sec can contain orders more magnitude of those than MISS - which is the point of having them.<span class="gmail-"><br>
<br>
<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
In our prod environment when we updated from 2.7.x to 3.5.25 we saw increase from 100 to 10000. This is 100x.<br>
<br>
</blockquote>
<br></span>
Compared to what RPS change? Given the above traffic change this may be reasonable for a v2 to v3 jump. Or own very rough tests on old hardware lab tests have shown rates for Squid-2 at ~900 RPS and Squid-3 at around 1900 RPS.<span class="gmail-"><br>
<br>
<br>
<blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">
When I was load testing different versions yesterday I was always sending the same amount of RPS to them. Update from 3.5.20 to 3.5.21 resulted in jump from 20 to 10000 TIME_WAIT count. This is 500x.<br>
<br>
I know that time_wait is fine in general. Until you have too many of them.<br>
<br>
</blockquote>
<br></span>
At this point I'd check that your testing software supports HTTP/1.1 pipelines. It may be giving you worst-case results with per-message TCP churn rather than what will occur normally (pipelines of N requests per TCP connection).<br>
Though seeing such a jump between Squid-3 releases is worrying.<span class="gmail-HOEnZb"><font color="#888888"><br>
<br>
Amos<br>
</font></span></blockquote></div><br><br clear="all"><div><br></div>-- <br><div class="gmail_signature">With best regards, Ivan Larionov.</div>
</div></div>