<div dir="ltr">Hi,<div>at CERN we have 3 regions regions with a total of 75 cells (>8000 compute nodes).</div><div><br></div><div>In the past we had a cell with almost 2000 compute nodes. </div><div>Now, we try to not have more than 200 compute nodes per cell.</div><div>We prefer to manage more but smaller cells. </div><div><br></div><div>Belmiro</div><div>CERN</div><div> </div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Thu, Jan 28, 2021 at 2:29 PM Thierry Carrez <<a href="mailto:thierry@openstack.org">thierry@openstack.org</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left-width:1px;border-left-style:solid;border-left-color:rgb(204,204,204);padding-left:1ex">Hi everyone,<br>
<br>
As part of the Large Scale SIG[1] activities, I'd like to quickly poll <br>
our community on the following question:<br>
<br>
How many compute nodes do you feel comfortable fitting in a <br>
single-cluster deployment of OpenStack, before you need to scale it out <br>
to multiple regions/cells/.. ?<br>
<br>
Obviously this depends on a lot of deployment-dependent factors (type of <br>
activity, choice of networking...) so don't overthink it: a rough number <br>
is fine :)<br>
<br>
[1] <a href="https://wiki.openstack.org/wiki/Large_Scale_SIG" rel="noreferrer" target="_blank">https://wiki.openstack.org/wiki/Large_Scale_SIG</a><br>
<br>
Thanks in advance,<br>
<br>
-- <br>
Thierry Carrez (ttx)<br>
<br>
</blockquote></div>