Add ecu support for nova based on Cgroup on kvm hypervisor
Currently nova supports cpu qos with vcpu pin and qouta/period, it is not so intelligent, and the cloud user usually doesn't know how to set the 'quota/period' of all instances and could still keeps fair and performance of them.
We should add an intelligent(non or very few manually interactive), fair, consistency performance way to implement the ecu concept like amazon ec2, we also need to treat ecu as an extra_spec of flavor, the instances which has the same ecus should have consistency performance even if they are running on several heterogeneous servers.
We also need to treat ecu as a resource like vcpu, it need has qouta management, resource tracking, scheduler filter.
Whiteboard
Gerrit topic: https:/
Addressed by: https:/
Add ecu support for nova
Addressed by: https:/
Add ecus quota support
Addressed by: https:/
Add ECU setting for libvirt
How would you implement this? How would you automatically figure out how many ECUs a machine has? All I see is https:/
Yes, jogo is right. https:/
discussion: http://
Gerrit topic: https:/
Addressed by: https:/
Add ecu support for nova
Addressed by: https:/
Add ecus quota support
Addressed by: https:/
Add ECU setting for libvirt
How would you implement this? How would you automatically figure out how many ECUs a machine has? All I see is https:/
Yes, jogo is right. https:/
discussion: http://
If you are still working on this, please re-submit via nova-specs. If not, please mark as obsolete, and add a quick comment to describe why. --johnthetubaguy (20th April 2014)