System and method for dynamic allocation of virtual machines in a virtual server environment

• US 8,261,268 B1
• Filed: 08/05/2009
• Issued: 09/04/2012
• Est. Priority Date: 08/05/2009
• Status: Active Grant

• Current Assignee: NetApp, Inc.
• Original Assignee: NetApp, Inc.
• Inventors: Forgette, Eric P.
• Primary Examiner(s): PETRANEK, JACOB ANDREW
• Application Number:
  US12/535,993
• Time in Patent Office: 1,126 Days
• Field of Search: None
• US Class Current: 718/1
• 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 system and method for dynamically producing virtual machines (VMs) across a plurality of servers in the virtual server environment is provided. A single VM request queue is produced comprising VM requests for producing the plurality of VMs. A processing thread is produced and assigned for each server and retrieves VM requests from the VM request queue and produces VMs only on the assigned server according to the retrieved VM requests. Each processing thread may be configured for retrieving VM requests and producing VMs without any programmed delays, whereby the rate at which a processing thread produces VMs on its assigned server is a function of the performance capabilities of the assigned server. This dynamic allocation of VMs based on such a “natural selection” technique may provide an appropriately balanced allocation of VMs based on the performance capabilities of each server in the virtual server environment.

Claims

1. A system for dynamically producing virtual machines (VMs) on a plurality of servers, the system comprising:

a VM manager engine configured for;

receiving VM parameters specifying a plurality of VMs to be produced across the plurality of servers, wherein the VM parameters do not specify that a VM be produced on a specific server in the plurality of servers;

producing a single VM request queue for the plurality of servers, the VM request queue being accessible by a plurality of threads and comprising a plurality of VM requests for producing the plurality of VMs, each VM request specifying a VM for producing on the plurality of servers and not specifying the VM for producing on a specific server in the plurality of servers; and

producing a plurality of processing threads for the plurality of servers, each processing thread assigned to a server, each processing thread configured to access and retrieve VM requests from the single VM request queue and process a retrieved VM request for producing a VM only on the assigned server, wherein each VM request is configured for processing by any processing thread in the plurality of processing threads for producing a VM on any server in the plurality of servers depending on which processing thread retrieves the VM request from the VM request queue.

2. The system of claim 1, wherein the VM parameters further specify a total number of VMs to be produced across the plurality of servers, wherein the VM parameters do not specify a number of VMs to be produced on a specific server.

3. The system of claim 1, wherein:

each server comprises a server operating system; and

each VM produced on a server comprises a separate instance of a separate operating system and one or more applications that execute on the server.

4. The system of claim 1, further comprising:

a storage system connected with each server in the plurality of servers for storing client data; and

a plurality of client systems, each client system connected with a server and interfacing with a VM on a server to access client data of the storage system.

5. The system of claim 1, wherein each processing thread executes on its assigned server as rapidly as possibly allowed by the performance capabilities of its assigned server without any programmed delays for retrieving and processing VM requests.

6. The system of claim 1, wherein:

each processing thread executes on its assigned server; and

a number of VMs produced on an assigned server by a processing thread is dependent on the performance capabilities of the assigned server.

7. The system of claim 6, wherein more VMs are produced on a server having relatively faster performance capabilities than on a server having relatively slower performance capabilities.

8. The system of claim 1, wherein:

each processing thread executes on its assigned server; and

a number of VMs produced on a server by the assigned processing thread is dependent on the rate the server executes the assigned processing thread to retrieve and process VM requests.

9. The system of claim 1, wherein:

each server executes a VM monitor engine for producing and managing VMs on the server;

a processing thread assigned to a server submits VM requests to the VM monitor engine residing on the assigned server for producing VMs on the assigned server; and

a number of VMs produced on a server is dependent on the rate that the server can execute its VM monitor engine to produce VMs.

10. A method for dynamically producing virtual machines (VMs) on a plurality of servers, the method comprising:

receiving, at a VM manager engine, VM parameters specifying a plurality of VMs to be produced across the plurality of servers, wherein the VM parameters do not specify that a VM be produced on a specific server in the plurality of servers;

producing, using the VM manager engine, a single VM request queue for the plurality of servers, the VM request queue being accessible by a plurality of threads and comprising a plurality of VM requests for producing the plurality of VMs, each VM request specifying a VM for producing on the plurality of servers and not specifying the VM for producing on a specific server in the plurality of servers; and

producing, using the VM manager engine, a plurality of processing threads for the plurality of servers, each processing thread assigned to a server, each processing thread configured to access and retrieve VM requests from the single VM request queue and process a retrieved VM request for producing a VM only on the assigned server, wherein each VM request is configured for processing by any processing thread in the plurality of processing threads for producing a VM on any server in the plurality of servers depending on which processing thread retrieves the VM request from the VM request queue.

11. The method of claim 10, wherein the VM parameters further specify a total number of VMs to be produced across the plurality of servers, wherein the VM parameters do not specify a number of VMs to be produced on a specific server.

12. The method of claim 10, wherein:

each server comprises a server operating system; and

each VM produced on a server comprises a separate instance of a separate operating system and one or more applications that execute on the server.

13. The method of claim 10, further comprising:

accessing a storage system connected with each server in the plurality of servers for storing client data; and

interfacing with a plurality of client systems, each client system connected with a server and interfacing with a VM on a server to access client data of the storage system.

14. The method of claim 10, wherein each processing thread executes on its assigned server as rapidly as possibly allowed by the performance capabilities of its assigned server without any programmed delays for retrieving and processing VM requests.

15. The method of claim 10, wherein:

each processing thread executes on its assigned server; and

a number of VMs produced on an assigned server by a processing thread is dependent on the performance capabilities of the assigned server.

16. The method of claim 15, wherein more VMs are produced on a server having relatively faster performance capabilities than on a server having relatively slower performance capabilities.

17. The method of claim 10, wherein:

each processing thread executes on its assigned server; and

a number of VMs produced on a server by the assigned processing thread is dependent on the rate that the server executes the assigned processing thread to retrieve and process VM requests.

18. The method of claim 10, wherein:

each server executes a VM monitor engine for producing and managing VMs on the server;

a processing thread assigned to a server submits VM requests to the VM monitor engine residing on the assigned server for producing VMs on the assigned server; and

a number of VMs produced on a server is dependent on the rate that the server can execute its VM monitor engine to produce VMs.

19. A system for dynamically producing virtual machines (VMs) on a plurality of servers, the system comprising:

a VM manager engine configured for;

receiving VM parameters specifying a plurality of VMs to be produced across the plurality of servers, wherein the VM parameters do not specify that a VM be produced on a specific server in the plurality of servers;

producing a single VM request queue for the plurality of servers, the VM request queue being accessible by a plurality of threads and comprising a plurality of VM requests for producing the plurality of VMs, each VM request specifying a VM for producing on the plurality of servers and not specifying the VM for producing on a specific server in the plurality of servers; and

producing a plurality of processing threads for the plurality of servers, each processing thread assigned to a server, each processing thread configured to access and retrieve VM requests from the single VM request queue and process a retrieved VM request for producing a VM only on the assigned server, wherein each processing thread is configured for retrieving VM requests and producing VMs without any programmed delays, whereby the rate at which a processing thread produces VMs on its assigned server is a function of the performance capabilities of the assigned server.

20. The system of claim 19, wherein more VMs are produced on a server having relatively faster performance capabilities than on a server having relatively slower performance capabilities.

21. A method for dynamically producing virtual machines (VMs) on a plurality of servers, the method comprising:

receiving, at a VM manager engine, VM parameters specifying a plurality of VMs to be produced across the plurality of servers, wherein the VM parameters do not specify that a VM be produced on a specific server in the plurality of servers;

producing, using the VM manager engine, a single VM request queue for the plurality of servers, the VM request queue being accessible by a plurality of threads and comprising a plurality of VM requests for producing the plurality of VMs, each VM request specifying a VM for producing on the plurality of servers and not specifying the VM for producing on a specific server in the plurality of servers; and

producing, using the VM manager engine, a plurality of processing threads for the plurality of servers, each processing thread assigned to a server, each processing thread configured to access and retrieve VM requests from the single VM request queue and process a retrieved VM request for producing a VM only on the assigned server, wherein each processing thread is configured for retrieving VM requests and producing VMs without any programmed delays, whereby the rate at which a processing thread produces VMs on its assigned server is a function of the performance capabilities of the assigned server.

22. The method of claim 21, wherein more VMs are produced on a server having relatively faster performance capabilities than on a server having relatively slower performance capabilities.