<div dir="ltr"><div><div>Julien,<br></div><br>Yes, I use the same SQL for Nova and Ceilometer. Thanks for pointing this out. My bad, I didn't take it into account. So if we want to use Ceilometer + MySQL in production (in theory :) ) we need to use separate controllers with Ceilometer's MySQL only. And each controller may run it's own collector which will write data into "local" MySQL. Am I right that only one instance of central-agent may be started (WIP <a href="https://wiki.openstack.org/wiki/Ceilometer/blueprints/tasks-distribution">https://wiki.openstack.org/wiki/Ceilometer/blueprints/tasks-distribution</a>)? Please Julien correct me if I'm wrong. And maybe Ceilometer has recommendations for production deployment and I just missed it? <br>
</div></div><div class="gmail_extra"><br><br><div class="gmail_quote">On Tue, Dec 10, 2013 at 4:25 PM, Boris Pavlovic <span dir="ltr"><<a href="mailto:bpavlovic@mirantis.com" target="_blank">bpavlovic@mirantis.com</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div dir="ltr">Nadya, Julien, <div><br></div><div><br></div><div>We are working around profiling system based on logs. This will allows us to detect bottlenecks.</div>
<div>We should make a couple of small patches in each project to support profiling.</div>
<div><br></div><div>As we are going to be well integrated with OpenStack infrastructure we are going to use Ceilometer as a log collector. </div><div>And we already made patch for this in Ceilometer: <a href="https://review.openstack.org/#/c/60262/" target="_blank">https://review.openstack.org/#/c/60262/</a><br>
</div><div>So it will be nice to get it reviewed/merged. <br></div><div><br></div><div><br></div><div>Thanks. </div><div><br></div><div><br></div><div>Best regards,</div><div>Boris Pavlovic </div><div><br></div><div><br>
</div>
<div><br></div><div><br></div></div><div class="gmail_extra"><br><br><div class="gmail_quote"><div><div class="h5">On Tue, Dec 10, 2013 at 3:19 PM, Julien Danjou <span dir="ltr"><<a href="mailto:julien@danjou.info" target="_blank">julien@danjou.info</a>></span> wrote:<br>
</div></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div><div class="h5">On Tue, Dec 10 2013, Nadya Privalova wrote:<br>
<br>
Hi Nadya,<br>
<div><br>
> Guys, if you have any questions or comments you are welcome! I think that<br>
> 2x difference between avg time in "empty lab" and "5 sec polling" scenario<br>
> is not a bad result. But 100 instances that were being monitored during the<br>
> test is not a real load for the lab. What do you think? Should I repeat the<br>
> test with 1000 instances?<br>
<br>
</div>You didn't mention where you were storing the metrics. If you store them<br>
in the same MySQL DB that's used by Nova for example, it's likely that's<br>
the problem is the load Ceilometer puts on the MySQL cluster slows Nova<br>
down.<br>
<br>
I don't think it's worth running the test with more instances for now.<br>
The results are clear, the next action should be to see why things are<br>
slowed down that much. It shouldn't happen.<br>
<span><font color="#888888"><br>
--<br>
Julien Danjou<br>
# Free Software hacker # independent consultant<br>
# <a href="http://julien.danjou.info" target="_blank">http://julien.danjou.info</a><br>
</font></span><br></div></div>_______________________________________________<br>
OpenStack-dev mailing list<br>
<a href="mailto:OpenStack-dev@lists.openstack.org" target="_blank">OpenStack-dev@lists.openstack.org</a><br>
<a href="http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev" target="_blank">http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev</a><br>
<br></blockquote></div><br></div>
</blockquote></div><br></div>