COMPUTING MIGRATION SPHERE OF WORKLOADS IN A NETWORK ENVIRONMENT

• US 20160087910A1
• Filed: 09/22/2014
• Published: 03/24/2016
• Est. Priority Date: 09/22/2014
• Status: Abandoned Application

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Mittal, Shailesh, Krishnamurthy, Raghu
• Application Number:
  US14/492,313
• Publication Number:
  US 20160087910A1
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: H04L 67/1097 for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70

Abstract

An example method for computing migration sphere of workloads in a network environment is provided and includes receiving, at a virtual appliance in a network, network information from a plurality of remote networks, analyzing a service profile associated with a workload to be deployed in one of the remote networks and indicating compute requirements and storage requirements associated with the workload, and generating a migration sphere comprising compute resources in the plurality of networks that meet at least the compute requirements and storage requirements associated with the workload, the workload being successfully deployable on any one of the compute resources in the migration sphere.

Claims

1. A method executing in a virtual appliance in a network, wherein the method comprises:

receiving network information from a plurality of remote networks;

analyzing a service profile associated with a workload to be deployed in one of the remote networks and indicating compute requirements and storage requirements associated with the workload; and

generating a migration sphere comprising compute resources in the plurality of networks that meet at least the compute requirements and storage requirements associated with the workload, the workload being successfully deployable on any one of the compute resources in the migration sphere.

2. The method of claim 1, wherein the network information includes compute resource information, storage resource information and network resource information in the remote networks.

3. The method of claim 1, wherein the network information includes platform specific constraints, power budgeting requirements, network policies, network features, network load, and other network requirements.

4. The method of claim 1, wherein generating the migration sphere comprises:

generating a list of substantially all compute resources across the plurality of remote networks;

analyzing compute, storage and network connectivity of the compute resources based on the network information;

comparing the compute requirements and storage requirements associated with the workload with the compute, storage and network connectivity of the compute resources; and

eliminating compute resources from the list that do not meet at least the compute requirements and storage requirements associated with the workload, wherein the remaining compute resources in the list populate the migration sphere.

5. The method of claim 4, wherein generating the migration sphere further comprises eliminating compute resources that do not meet network policies, network load, and other network requirements.

6. The method of claim 1, wherein the plurality of remote networks includes a first remote network and a second remote network, wherein the migration sphere includes a first compute resource in the first remote network and a second compute resource in the second remote network, wherein the workload is deployed in the first compute resource and migrated from the first compute resource to the second compute resource.

7. The method of claim 1, wherein the migration of the workload causes a change in the network information, wherein the migration sphere is updated with the changed network information.

8. The method of claim 1, wherein the remote networks comprise separate, distinct networks, wherein storage resources in any one remote network cannot be accessed by compute resources in any other remote network.

9. The method of claim 1, wherein each remote network is used by multiple tenants, each tenant using distinct portions of compute resources in each remote network, wherein the service profile is associated with a specific tenant, wherein the migration sphere includes only those compute resources that can be accessed by the specific tenant.

10. The method of claim 1, further comprising associating the migration sphere with the service profile.

11. Non-transitory tangible media that includes instructions for execution, which when executed by a processor associated with a virtual appliance in a network, is operable to perform operations comprising:

receiving network information from a plurality of remote networks;

analyzing a service profile associated with a workload to be deployed in one of the remote networks and indicating compute requirements and storage requirements associated with the workload; and

generating a migration sphere comprising compute resources in the plurality of networks that meet at least the compute requirements and storage requirements associated with the workload, the workload being successfully deployable on any one of the compute resources in the migration sphere.

12. The media of claim 11, wherein the network information includes compute resource information, storage resource information and network resource information in the remote networks.

13. The media of claim 11, wherein generating the migration sphere comprises:

generating a list of substantially all compute resources across the plurality of remote networks;

analyzing compute, storage and network connectivity of the compute resources based on the network information;

comparing the compute requirements and storage requirements associated with the workload with the compute, storage and network connectivity of the compute resources; and

eliminating compute resources from the list that do not meet at least the compute requirements and storage requirements associated with the workload, wherein the remaining compute resources in the list populate the migration sphere.

14. The media of claim 13, wherein generating the migration sphere further comprises eliminating compute resources that do not meet network policies, network load, and other network requirements.

15. The media of claim 11, wherein the plurality of remote networks includes a first remote network and a second remote network, wherein the migration sphere includes a first compute resource in the first remote network and a second compute resource in the second remote network, wherein the workload is deployed in the first compute resource and migrated from the first compute resource to the second compute resource.

16. An apparatus in a first network, comprising:

a virtual appliance;

a memory element for storing data; and

a processor, wherein the processor executes instructions associated with the data, wherein the processor and the memory element cooperate, such that the apparatus is configured for;

receiving network information from a plurality of remote networks;

analyzing a service profile associated with a workload to be deployed in one of the remote networks and indicating compute requirements and storage requirements associated with the workload; and

generating a migration sphere comprising compute resources in the plurality of networks that meet at least the compute requirements and storage requirements associated with the workload, the workload being successfully deployable on any one of the compute resources in the migration sphere.

17. The apparatus of claim 16, wherein the network information includes compute resource information, storage resource information and network resource information in the remote networks.

18. The apparatus of claim 16, wherein generating the migration sphere comprises:

generating a list of substantially all compute resources across the plurality of remote networks;

analyzing compute, storage and network connectivity of the compute resources based on the network information;

comparing the compute requirements and storage requirements associated with the workload with the compute, storage and network connectivity of the compute resources; and

eliminating compute resources from the list that do not meet at least the compute requirements and storage requirements associated with the workload, wherein the remaining compute resources in the list populate the migration sphere.

19. The apparatus of claim 18, wherein generating the migration sphere further comprises eliminating compute resources that do not meet network policies, network load, and other network requirements.

20. The apparatus of claim 16, wherein the plurality of remote networks includes a first remote network and a second remote network, wherein the migration sphere includes a first compute resource in the first remote network and a second compute resource in the second remote network, wherein the workload is deployed in the first compute resource and migrated from the first compute resource to the second compute resource.