Elastic Compute Fabric Using Virtual Machine Templates

• US 20150178107A1
• Filed: 12/20/2013
• Published: 06/25/2015
• Est. Priority Date: 12/20/2013
• Status: Active Grant

• Current Assignee: Vmware LLC (Broadcom, Inc.)
• Original Assignee: VMware, Inc. (Broadcom, Inc.)
• Inventors: Gummaraju, Jayanth, Tarasuk-Levin, Gabriel
• Granted Patent: US 10,977,063 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 2009/45562 Creating, deleting, cloning virtual machine instances
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 2009/45575 Starting, stopping, suspending or resuming virtual machine instances
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects

Abstract

Embodiments include an infrastructure shared among cloud services that supports fast provisioning of virtual machines (VMs). A set of powered-on parent VM templates and a set of powered-off child VMs are maintained by the infrastructure in a hierarchy. The child VMs are instantiated from the parent VM templates, and pre-registered to a cloud operating system in some embodiments. In response to requests from the cloud services for the child VMs, where the requests specify child VM configurations, child VMs from the set of powered-off child VMs are selected and customized based on the child VM configurations, and then deployed for use by the cloud services. In some embodiments, the fast provisioning of VMs is supported by forking operations in the infrastructure.

Claims

1. A system comprising:

a shared compute fabric cloud service communicating with a plurality of cloud services, the shared compute fabric cloud service having a plurality of virtual machines (VMs);

a memory associated with the shared compute fabric cloud service, the memory storing a plurality of powered-on parent VM templates;

storage including a plurality of powered-off child VMs instantiated from the plurality of parent VM templates; and

a processor associated with the shared compute fabric cloud service, the processor programmed to;

receive a request from one of the plurality of cloud services for at least one of the plurality of child VMs, the request including child VM properties;

in response to the received request, customize the at least one of the plurality of child VMs based on the child VM properties in the received request; and

power-on the customized at least one of the plurality of child VMs.

2. The system of claim 1, wherein the memory stores the plurality of parent VM templates as a tree hierarchy, and wherein each of the plurality of child VMs is pre-registered to an operating system associated with the shared compute fabric cloud service.

3. The system of claim 1, wherein the child VM properties include at least one of:

hostname, Internet Protocol (IP) address, media access control (MAC) address, processor size, or memory size.

4. The system of claim 1, wherein the processor is programmed to customize the at least one of the plurality of child VMs by configuring the at least one of the plurality of child VMs to have the child VM properties from the received request.

5. The system of claim 1, wherein the plurality of parent VM templates comprise derived VM templates and standalone VM templates, each of the derived VM templates sharing one or more disk blocks with a corresponding one of the plurality of parent VM templates.

6. The system of claim 5, wherein the standalone VM templates lack any disk block inherited from the corresponding one of the plurality of parent VM templates.

7. The system of claim 1, wherein the processor is programmed to receive the request, customize the at least one of the plurality of child VMs, and power-on the customized at least one of the plurality of child VMs, without any hot spare VMs being stored.

8. The system of claim 1, further comprising means for maintaining the plurality of powered-on parent VM templates and the plurality of powered-off child VMs.

9. A method comprising:

maintaining, by a computing device, a set of powered-on parent VM templates and a set of powered-off child VMs instantiated from the powered-on parent VM templates, each of the child VMs sharing memory and storage of one of the parent VM templates, wherein sharing memory comprises copy-on-write (COW) sharing of memory pages;

receiving a request from a cloud service for at least one of the child VMs, the request identifying a child VM configuration;

applying, by the computing device in response to the received request, the child VM configuration to the at least one of the child VMs in the set of child VMs; and

deploying the at least one of the child VMs with the applied child VM configuration.

10. The method of claim 9, wherein deploying the at least one of the child VMs occurs without registering, in response to the received request, the at least one of the plurality of child VMs with a cloud operating system.

11. The method of claim 9, further comprising notifying the cloud service of the deployed at least one of the child VMs.

12. The method of claim 9, wherein maintaining the set of powered-on parent VM templates comprises powering-on each of the parent VM templates.

13. The method of claim 9, wherein maintaining the set of powered-on parent VM templates comprises pre-registering each of the child VMs with a cloud operating system.

14. The method of claim 9, wherein maintaining the set of powered-on parent VM templates comprises creating at least one of the powered-on parent VM templates in response to receiving a request from the cloud service to create said at least one of the powered-on parent VM templates.

15. The method of claim 9, wherein maintaining the set of powered-on parent VM templates comprises automatically creating at least one of the powered-on parent VM templates in response to receiving a plurality of requests for a same type of child VM.

16. One or more computer-readable storage media including computer-executable instructions that, when executed, cause at least one processor to dynamically scale a cloud service by increasing a quantity of virtual machines (VMs) available thereto by:

creating a hierarchy of powered-on parent VM templates and powered-off child VMs instantiated from the powered-on parent VM templates;

receiving a request from the cloud service for at least one of the child VMs from the created hierarchy, the request including child VM identity data;

in response to the received request, applying the child VM identity data to the at least one of the child VMs in the created hierarchy; and

providing, to the cloud service, the at least one of the child VMs with the applied child VM identity data.

17. The computer storage media of claim 16, wherein the computer-executable instructions further cause the processor to:

receive a request from the cloud service for a parent VM template not in the hierarchy; and

dynamically create the requested parent VM template.

18. The computer storage media of claim 16, wherein the computer-executable instructions further cause the process to:

receive a request from the cloud service to destroy the provided at least one of the child VMs; and

in response to the received request, destroy the provided at least one of the child VMs.

19. The computer storage media of claim 18, wherein the computer-executable instructions further cause the processor to:

receive a request from the cloud service to re-create the destroyed child VM; and

re-create the destroyed child VM by re-performing said applying and said providing.

20. The computer storage media of claim 16, wherein the computer-executable instructions cause the processor to perform said applying and said providing without using a hot spare VM.