Virtual cluster as a service (VCIaaS)

• US 9,678,778 B1
• Filed: 05/07/2014
• Issued: 06/13/2017
• Est. Priority Date: 05/07/2014
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Youseff, Lamia
• Primary Examiner(s): Nguyen, Van
• Application Number:
  US14/271,953
• Time in Patent Office: 1,133 Days
• Field of Search: None
• CPC Class Codes: G06F 2009/45562 Creating, deleting, cloning virtual machine instances
• CPC Class Codes: G06F 2009/45587 Isolation or security of virtual machine instances
• CPC Class Codes: G06F 2009/45595 Network integration; Enabling network access in virtual machine instances
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation

Abstract

Provided are methods and systems for providing users with a cluster of virtual machines (VMs) on-demand, whereby a group of VMs are provisioned together. Virtual Cluster as a Service (VClaaS) relaxes many restrictions on virtualizing VMs and provides performance benefits at the same or similar encapsulations and security measures that Infrastructure as a Service (IaaS) typically provides. The VClaaS system enables users to provision an entire cluster of VMs at a time, and also allows for relaxing the isolation barrier between the machines while maintaining the encapsulation barrier for the cluster as a whole, thereby providing users with improved networking, caching, and scheduling experiences.

Claims

1. A computer-implemented method comprising:

determining, by one or more processors, that a first virtual machine and a second virtual machine are related;

provisioning, by the one or more processors, the first and second virtual machines into a single physical machine together as a group of virtual machines;

encapsulating, by the one or more processors, the group of virtual machines by providing an encapsulation barrier around the group of virtual machines within the single physical machine;

modifying, by the one or more processors, an isolation barrier between the first and second virtual machines in the group by relaxing a restriction on data movement between the first and second virtual machines; and

creating, by the one or more processors, shared memory between the first and second virtual machines in the group, wherein the encapsulation barrier around the group of virtual machines within the single physical machine controls access of the group of virtual machines to the shared memory.

2. The computer-implemented method of claim 1, wherein provisioning the first and second virtual machines includes scheduling computational resources on the first and second virtual machines.

3. The computer-implemented method of claim 1, wherein determining that the first virtual machine and the second virtual machine are related includes:

determining that the first and second virtual machines are associated with the same user;

and receiving an indication that the user intends to combine the first and second virtual machines into a group of virtual machines.

4. The computer-implemented method of claim 3, wherein the determination that the first virtual machine and the second virtual machine are related is based on a determination that the first and second virtual machines are associated with the same user and a determination that the first and second virtual machines are assigned to the same project.

5. The computer-implemented method of claim 1, further comprising provisioning the first and second virtual machines using different settings and/or configurations based on indicated performance preferences.

6. A computer-implemented method comprising:

provisioning, by one or more processors, a group of related virtual machines into a single physical machine;

encapsulating, by the one or more processors, the group of virtual machines by providing an encapsulation barrier around the group of virtual machines within the single physical machine;

modifying, by the one or more processors, a restriction on data movement between virtual machines belonging to the group by relaxing a restriction on data movement between the first and second virtual machines; and

creating, by the one or more processors, shared memory between the virtual machines belonging to the group, wherein the encapsulation barrier around the group of virtual machines within the single physical machine controls access of the group of virtual machines to the shared memory.

7. The computer-implemented method of claim 6, wherein provisioning the group of virtual machines includes scheduling computational resources on the virtual machines belonging to the group.

8. The computer-implemented method of claim 6, further comprising determining that the virtual machines belonging to the group are related based on the virtual machines being associated with the same user.

9. The computer-implemented method of claim 6, further comprising determining that the virtual machines belonging to the group are related based on the virtual machines being assigned to the same workload.

10. The computer-implemented method of claim 6, further comprising provisioning a first virtual machine belonging to the group using first settings and/or configurations and a second virtual machine belonging to the group using second settings and/or configurations, wherein the first and second settings and/or configurations are different.

11. The computer-implemented method of claim 10, wherein the first and second settings and/or configurations are each based on indicated performance preferences.

12. A system for provisioning a group of virtual machines, the system comprising:

one or more computing devices;

a memory storing instructions, which when executed by the one or more computing devices, cause the one or more computing devices to;

determine that a group of virtual machines are related;

provision the group of virtual machines into a physical machine;

provide an encapsulation barrier around the group of virtual machines;

modify isolation barriers between virtual machines belonging to the group by relaxing a restriction on data movement between the virtual machines belonging to the group;

configure the memory to be shared between the virtual machines belonging to the group; and

control access of the group of virtual machines to the shared memory.

13. The system of claim 12, further configured to:

schedule computational resources on the virtual machines belonging to the group.

14. The system of claim 12, further configured to:

determine that the virtual machines belonging to the group are related based on a determination that the group of virtual machines is associated with the same user and an indication that the user intends to combine the virtual machines into a group of virtual machines.

15. The system of claim 12, further configured to:

determine that the virtual machines belonging to the group are related based on a determination that the group of virtual machines is associated with the same user and a determination that the group of virtual machines is assigned to the same project.

16. The system of claim 12, further configured to:

provision a first virtual machine belonging to the group using first settings and/or configurations and a second virtual machine belonging to the group using second settings and/or configurations, wherein the first and second settings and/or configurations are different.

17. The system of claim 16, wherein the first and second settings and/or configurations are each based on indicated performance preferences.