<div dir="ltr">thanks Dan and Jay, we don't need add new scheduler for that :-), <br>what about provide cpu frequency to api /os-hypervisors, that means we can<br>report this value automatically, the value can be used in high level mange tools.<br></div><div class="gmail_extra"><br><div class="gmail_quote">2015-07-01 2:58 GMT+08:00 Jay Pipes <span dir="ltr"><<a href="mailto:jaypipes@gmail.com" target="_blank">jaypipes@gmail.com</a>></span>:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div class="HOEnZb"><div class="h5">On 06/30/2015 02:42 AM, ChangBo Guo wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
CPU frequency is an import performance parameter, currently nova<br>
drivers just report cpu_info without frequency. we stored the compute<br>
node cpu_info in database with colum compute_nodes.cpu_info, we can add<br>
the frequency easily.<br>
<br>
The usage of cpu frequency I can think is used to schedule to meet<br>
applications which need high frequency. add a frequency based filter ?<br>
if we need this , I would like to propose a spec for this .<br>
<br>
<br>
There are two steps to leverage cpu frequency:<br>
1. report cpu frequency and record the value, nova hypervisor-show<br>
will include the value .<br>
<br>
2. filter compute nodes based cpu frequency.<br>
add a new scheduler filter to do that<br>
<br>
before I start to do these stuff. I would like to your input .<br>
<br>
Do we need leverage CPU frequency in Nova ?<br>
if yes, do we need a new filter or leverage existing filter to use<br>
frequency ?<br>
</blockquote>
<br></div></div>
Like Dan B, I question whether CPU frequency really is a useful metric for scheduling decisions.<br>
<br>
That said, it is already possible to use CPU frequency in the MetricsWeigher scheduler weigher. The compute monitor plugin system is currently being overhauled [1], but the functionality to monitor CPU-related metrics already exists in Nova and can be enabled by doing the following in your nova-compute nova.conf:<br>
<br>
compute_monitors = ComputeDriverCPUMonitor<br>
<br>
Note that with the refactoring of the monitoring plugin interface, the above option will change due to using stevedore to load monitor extensions:<br>
<br>
compute_monitors = nova.compute.monitors.cpu.virt_driver:Monitor<br>
<br>
In your Nova scheduler nova.conf, you will need to add the following in the [metrics] section of the file:<br>
<br>
weights_setting = cpu.frequency=10.0<br>
<br>
Again, I'm not saying that the above will result in any appreciable enhancement to the scheduler's decision-making, but it will do what you're trying to accomplish :)<br>
<br>
Best,<br>
-jay<br>
<br>
[1] <a href="https://review.openstack.org/#/q/status:open+project:openstack/nova+branch:master+topic:bug/1468012,n,z" rel="noreferrer" target="_blank">https://review.openstack.org/#/q/status:open+project:openstack/nova+branch:master+topic:bug/1468012,n,z</a><div class="HOEnZb"><div class="h5"><br>
<br>
__________________________________________________________________________<br>
OpenStack Development Mailing List (not for usage questions)<br>
Unsubscribe: <a href="http://OpenStack-dev-request@lists.openstack.org?subject:unsubscribe" rel="noreferrer" target="_blank">OpenStack-dev-request@lists.openstack.org?subject:unsubscribe</a><br>
<a href="http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev" rel="noreferrer" target="_blank">http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-dev</a><br>
</div></div></blockquote></div><br><br clear="all"><br>-- <br><div class="gmail_signature"><div dir="ltr"><div>ChangBo Guo(gcb)</div></div></div>
</div>