Description of problem: We need to add to our limitation document[1] that we recommend not scaling past 300 compute nodes per-region with our monolithic controller configuration. Additionally, I would like to see a "OpenStack Director Limitation and Recommendations" section. Initially, I would like to see us add a recommendation to not deploy > 32 nodes at a time. This will ensure more successful deployments and scale-out situations. Things I would like to add later: How many nodes can we deploy of Ceph (based on OSD count?), Numbers of HCI nodes we support, etc... [1] https://access.redhat.com/articles/1436373
Closing this as a scaling guide has been published now for OSP 10 https://access.redhat.com/documentation/en-us/red_hat_openstack_platform/10/html/recommendations_for_large_deployments/index