<https://access.redhat.com/documentation/en-us/red_hat_openstack_platform/16.2/html/recommendations_for_large_deployments/index, Section 2.2 (table 2.2),Regarding the Disk recommandations for controller nodes, don't we need dedicated disks for glance images caching ?

According to the glance documentation, here https://access.redhat.com/documentation/en-us/red_hat_openstack_platform/17.1/html/creating_and_managing_images/assembly_image-service_osp#proc_improving-scalability-with-image-service-caching_glance, it is recommended to configure glance caching in glance APIs to improve scalability.>