VIRTUALIZED CLUSTER COMMUNICATION SYSTEM

• US 20120144229A1
• Filed: 12/03/2010
• Published: 06/07/2012
• Est. Priority Date: 12/03/2010
• Status: Active Grant

• Current Assignee: Avago Technologies International Sales Pte Limited (Broadcom, Inc.)
• Original Assignee: LSI Corporation (Broadcom, Inc.)
• Inventors: NADOLSKI, EDMUND
• Granted Patent: US 8,707,083 B2
• Time in Patent Office: Days
• US Class Current: 714/4.2
• CPC Class Codes: G06F 11/1484 involving virtual machines
• CPC Class Codes: G06F 11/2028 eliminating a faulty processor or activating a spare
• CPC Class Codes: G06F 11/2035 without idle spare hardware
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects

Abstract

A method includes executing, in each of a number of nodes of a cluster communication system, a specialized instance of an operating system privileged to control a corresponding hypervisor configured to consolidate one or more VM(s) on a system hardware. The one or more VM(s) is configured to be associated with a non-privileged operating system. The method also includes providing a cluster stack associated with the specialized instance of the operating system on the each of the number of nodes to enable communication between peers thereof in different nodes, and controlling the one or more VM(s) as a cluster resource through the cluster stack.

Claims

1. A method comprising:

executing, in each of a plurality of nodes of a cluster communication system, a specialized instance of an operating system privileged to control a corresponding hypervisor configured to consolidate at least one virtual machine (VM) on a system hardware, the at least one VM being configured to be associated with a non-privileged operating system;

providing a cluster stack associated with the specialized instance of the operating system on the each of the plurality of nodes to enable communication between peers thereof in different nodes; and

controlling the at least one VM as a cluster resource through the cluster stack.

2. The method of claim 1, further comprising executing the specialized instance of the privileged operating system on a control VM on the system hardware associated with the at least one VM consolidated thereon through the corresponding hypervisor.

3. The method of claim 1, further comprising:

electing a node of the plurality of nodes as a designated controller of a cluster formed by the plurality of nodes, the designated controller being configured to be a decision maker of the cluster; and

electing another node of the plurality of nodes as the designated controller upon a failure thereof.

4. The method of claim 1, wherein the cluster stack includes a Cluster Resource Manager (CRM) stack configured to enable controlling the at least one VM as the cluster resource through deploying a resource control script to enable at least one of:

starting the at least one VM, stopping the at least one VM and monitoring the at least one VM.

5. The method of claim 1,

wherein the plurality of nodes is configured to communicate with one another through a computer network, and

wherein the system hardware is associated with one of a host server and a controller board.

6. The method of claim 3, further comprising detecting the failure of the node elected as the designated controller through the CRM stack,

wherein the CRM stack is configured to reinstantiate an instance of at least one of an application and an application program associated with the at least one VM on the another node of the plurality of nodes.

7. The method of claim 4, wherein the cluster stack further comprises a Cluster Infrastructure Services (CIS) stack configured to expose a set of cluster resource management Application Programming Interfaces (APIs) to the CRM stack to enable an independence thereof from an underlying cluster infrastructure.

8. A method comprising:

executing, in each of a plurality of nodes of a cluster communication system, a specialized instance of an operating system privileged to control a corresponding hypervisor configured to consolidate at least one VM on a system hardware, the at least one VM being configured to be associated with a non-privileged operating system;

controlling the at least one VM as a cluster resource through a cluster stack associated with the specialized instance of the operating system, the cluster stack being provided on the each of the plurality of nodes to enable communication between peers thereof in different nodes;

electing a node of the plurality of nodes as a designated controller of a cluster formed by the plurality of nodes, the designated controller being configured to be a decision maker of the cluster; and

reinstantiating the at least one VM on another node of the plurality of nodes through the cluster stack upon detection of a failure of the node elected as the designated controller.

9. The method of claim 8, further comprising executing the specialized instance of the privileged operating system on a control VM on the system hardware associated with the at least one VM consolidated thereon through the corresponding hypervisor.

10. The method of claim 8, further comprising:

electing the another node of the plurality of nodes as the designated controller upon a failure thereof.

11. The method of claim 8, wherein the cluster stack includes a CRM stack configured to enable controlling the at least one VM as the cluster resource through deploying a resource control script to enable at least one of:

starting the at least one VM, stopping the at least one VM and monitoring the at least one VM.

12. The method of claim 8,

wherein the plurality of nodes is configured to communicate with one another through a computer network, and

wherein the system hardware is associated with one of a host server and a controller board.

13. The method of claim 8, further comprising detecting the failure of the node elected as the designated controller through the CRM stack,

wherein the CRM stack is configured to reinstantiate an instance of at least one of an application and an application program associated with the at least one VM on the another node of the plurality of nodes.

14. The method of claim 11, wherein the cluster stack further comprises a CIS stack configured to expose a set of cluster resource management APIs to the CRM stack to enable an independence thereof from an underlying cluster infrastructure.

15. A virtualized cluster communication system comprising:

a plurality of nodes, each node comprising a system hardware configured to have at least one VM consolidated thereon through a corresponding hypervisor, the hypervisor being configured to be controlled by a specialized instance of a privileged operating system associated with a control VM also consolidated on the system hardware, the at least one VM being configured to be associated with a non-privileged operating system, and the each node further comprising a cluster stack associated with the specialized instance of the privileged operating system to enable communication between peers thereof in different nodes,

wherein the cluster stack is configured to control the at least one VM as a cluster resource.

16. The virtualized cluster communication system of claim 15, wherein the cluster stack is further configured to enable:

electing a node of the plurality of nodes as a designated controller of a cluster formed by the plurality of nodes, the designated controller being configured to be a decision maker of the cluster, and

electing another node of the plurality of nodes as the designated controller upon a failure thereof.

17. The virtualized cluster communication system of claim 16, further comprising a computer network configured to enable communication between the each node of the plurality of nodes and the another node of the plurality of nodes,

wherein the system hardware is associated with one of a host server and a controller board.

18. The virtualized cluster communication system of claim 16, wherein the cluster stack includes a CRM stack configured to enable controlling the at least one VM as the cluster resource through deploying a resource control script to enable at least one of:

starting the at least one VM, stopping the at least one VM and monitoring the at least one VM.

19. The virtualized cluster communication system of claim 18,

wherein the CRM stack is configured to detect the failure of the node elected as the designated controller, and

wherein the CRM stack is further configured to reinstantiate an instance of at least one of an application and an application program associated with the at least one VM on the another node of the plurality of nodes.

20. The virtualized cluster communication system of claim 18, wherein the cluster stack further comprises a CIS stack configured to expose a set of cluster resource management APIs to the CRM stack to enable an independence thereof from an underlying cluster infrastructure.