Model-driven technique for virtual network function rehoming for service chains

1. An apparatus comprising:

a processor; and

a memory coupled with the processor, the memory comprising executable instructions stored thereon that when executed by the processor cause the processor to effectuate operations comprising:

determining whether a trigger has occurred within a cloud infrastructure;

in response to determining that the trigger has occurred, extracting characteristics from one or more virtual network functions (VNFs) of a service chain within the cloud infrastructure;

in response to extracting characteristics from the one or more VNFs of the service chain, determining rehoming actions for each of the one or more VNFs of the service chain based on a feasibility of whether or not each rehoming action of the rehoming actions can be performed by the one or more VNFs of the service chain, wherein the feasibility is one of an impact analysis of the rehoming actions, contention analysis of the rehoming actions, or a state of VNFs associated with the rehoming actions;

in response to determining rehoming actions, predicting a rehoming delay or a connectivity downtime for each of the rehoming actions for each of the one or more VNFs of the service chain;

determining an optimal rehoming action from the rehoming actions for at least one of the one or more VNFs of the service chain using the rehoming delay or the connectivity downtime for each rehoming action of the rehoming actions; and

performing the optimal rehoming action for the at least one of one or more VNFs of the service chain.

2. The apparatus of claim 1 , wherein the processor effectuates further operations comprising inputting the optimal rehoming action for each of the one or more VNFs in the service chain into a Model-driven Rehoming Technique (MERIT) application.

3. The apparatus of claim 2 , wherein the processor effectuates further operations comprising refining analysis and modeling of rehoming actions performed by the MERIT application.

4. The apparatus of claim 1 , wherein the rehoming delay is a time to perform a rehoming action.

5. The apparatus of claim 1 , wherein the connectivity downtime is a time until an end-to-end connectivity of the service chain is restored.

6. The apparatus of claim 1 , wherein the trigger is one of: a hotspot, a virtual machine (VM) workload shift, a network failure, and a network upgrade.

7. The apparatus of claim 1 , wherein the rehoming actions are one of: a live migration, a cold migration, and a rebuild.

8. The apparatus of claim 1 , wherein the predicting the rehoming delay or a chain downtime for each of the rehoming actions for each of the one or more VNFs of the service chain accounts for network contention due to simultaneous rehoming of each of the one or more VNFs of the service chain.

9. A system comprising:

a processor;

a memory coupled with the processor; and

an analytics application within a cloud infrastructure and stored in the memory, the analytics application comprising executable instructions that when executed by the processor cause the processor to effectuate operations comprising;

determining whether a trigger has occurred within the cloud infrastructure;

in response to determining that the trigger has occurred, extracting characteristics from one or more virtual network functions (VNFs) of a service chain within the cloud infrastructure;

in response to extracting characteristics from the one or more VNFs of the service chain, determining rehoming actions for each of the one or more VNFs of the service chain based on a feasibility of whether or not each rehoming action of the rehoming actions can be performed by the one or more VNFs of the service chain, wherein the feasibility is one of an impact analysis of the rehoming actions, contention analysis of the rehoming actions, or a state of VNFs associated with the rehoming actions;

in response to determining rehoming actions, predicting a rehoming delay or a connectivity downtime for each of the rehoming actions for each of the one or more VNFs of the service chain;

determining an optimal rehoming action from the rehoming actions for at least one of the one or more VNFs of the service chain using the rehoming delay or the connectivity downtime for each rehoming action of the rehoming actions; and

performing the optimal rehoming action for the at least one of one or more VNFs of the service chain.

10. The system of claim 9 wherein the system further comprises: a client virtual machine (VM), a switch within the cloud infrastructure, and a server VM.

11. The system of claim 9 wherein the service chain is one of: a firewall service chain, an intrusion detection system service chain, and a web caching service chain.

12. The system of claim 9 , wherein the processor effectuates further operations comprising inputting the optimal rehoming action for each of the one or more VNFs of the service chain into an analytics application.

13. The system of claim 9 , wherein the rehoming delay is a time to perform a rehoming action.

14. The system of claim 9 , wherein the connectivity downtime is a time until an end-to-end connectivity of the service chain is restored.

15. The system of claim 9 , wherein the trigger is one of: a hotspot, a virtual machine (VM) workload shift, a network failure, and a network upgrade.

16. The system of claim 9 , wherein the rehoming actions are one of: a live migration, a cold migration and a rebuild.

17. The system of claim 9 , wherein the predicting a rehoming delay or a chain downtime for each of the rehoming actions for each of the one or more VNFs of the service chain accounts for network contention due to simultaneous rehoming of each of the one or more VNFs of the service chain.

18. A computer readable storage medium storing computer executable instructions that when executed by a computing device cause said computing device to effectuate operations comprising:

determining whether a trigger has occurred within a cloud infrastructure;

in response to determining that the trigger has occurred, extracting characteristics from one or more virtual network functions (VNFs) of a service chain within the cloud infrastructure;

in response to extracting characteristics from the one or more VNFs of the service chain, determining rehoming actions for each of the one or more VNFs of the service chain based on a feasibility of whether or not each rehoming action of the rehoming actions can be performed by the one or more VNFs of the service chain, wherein the feasibility is one of an impact analysis of the rehoming actions, contention analysis of the rehoming actions, or a state of VNFs associated with the rehoming actions;

in response to determining the rehoming actions, predicting a rehoming delay or a connectivity downtime for each of the rehoming actions for each of the one or more VNFs of the service chain;

determining an optimal rehoming action from the rehoming actions for at least one of the one or more VNFs of the service chain using the rehoming delay or the connectivity downtime for each rehoming action of the rehoming actions; and

performing the optimal rehoming action for the at least one of one or more VNFs of the service chain.

19. The computer readable storage medium of claim 18 , wherein the rehoming delay is a time to perform a rehoming action and the connectivity downtime is a time until an end-to-end connectivity of the service chain is restored.

20. The computer readable storage medium of claim 18 , wherein the predicting a rehoming delay or a chain downtime for each of the rehoming actions for each of the one or more VNFs of the service chain accounts for network contention due to simultaneous rehoming of each of the one or more VNFs of the service chain.