In an NFV scenario, the VIM platform needs to cooperate with other components under the ETSI-MANO architecture to achieve the same level of reliability assurance as traditional hardware equipments.
NFVI/VIM should detect hardware health status and VNF health status directly or in-directly. It is on demand to integrate all these information to MANO. At the same time the platform needs to be able to receive fault-handling decisions from MANO and take action accordingly.
Faults of the platform components should not have impact on the VMs and business-related processes.
As for fault-handling for hosts VMs and business networks, the platform should be combined with the protection mechanism of the business VMs themselves and ensure the relocated VMs to enjoy the same enhanced features (such as CPU pinning IO-NUMA etc) as before.
The presentation will also analyze the impact of several different types of failure and several solutions according to our test results.
- Common reliability strategy of traditional telecom network elements
- The general HA mechanisms of VIM (openstack) platform for now
- What new requirements are brought to VIM platform in the ETSI-MANO structure for a telecom-level high availability
- The impact of various types of failures on the VMs and business programs. And some fault handling strategies performed by VIM and MANO according to our test results.