System and method for caching server images in a hosting system

• US 8,473,587 B1
• Filed: 07/21/2010
• Issued: 06/25/2013
• Est. Priority Date: 05/20/2010
• Status: Expired due to Fees

• Current Assignee: Open Invention Network LLC
• Original Assignee: GoGrid LLC (Apollo Global Management, Inc.)
• Inventors: Keagy, John M., Lappas, Paul, Kitagawa, Justin
• Primary Examiner(s): HIGA, BRENDAN Y
• Application Number:
  US12/841,158
• Time in Patent Office: 1,070 Days
• Field of Search: 709212-216, 709220-222, 718/1, 717174-178
• US Class Current: 709/220
• CPC Class Codes: G06F 2009/45562 Creating, deleting, cloning virtual machine instances
• CPC Class Codes: G06F 3/0619 in relation to data integrity, e.g. data losses, bit errors
• CPC Class Codes: G06F 3/065 Replication mechanisms
• CPC Class Codes: G06F 3/067 Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455

Abstract

Some embodiments provide a method that, at a caching network of a hosting and storage system that includes several nodes for hosting virtual machines for users, receives a request for an image of a particular computer system configuration for deployment as a virtual machine on a particular node of the hosting system. The method determines whether the requested image is presently stored on the caching network. When the image is present on the caching network, the method streams the image to the particular node of the hosting system for deployment as a virtual machine on the particular node. When the image is not presently stored on the caching network, the method retrieves a copy of the image from a permanent storage network and then streams the image to the particular node of the hosting system for deployment as a virtual machine on the particular node.

Claims

1. A method comprising:

at a caching network of a hosting and storage system that comprises a plurality of nodes for hosting virtual machines for users, receiving a request for an image of a particular computer system configuration for deployment as a virtual machine on a particular node of the hosting system;

determining whether the requested image is presently stored on the caching network;

when the image is present on the caching network, streaming the image to the particular node of the hosting system for deployment as a virtual machine on the particular node; and

when the image is not presently stored on the caching network, retrieving a copy of the image from a permanent storage network and then streaming the image to the particular node of the hosting system for deployment as a virtual machine on the particular node.

2. The method of claim 1, wherein the request is received from the particular node.

3. The method of claim 1, wherein the request is received from a utility management module operating on the particular node, the utility management module for deploying the particular computer system configuration as a virtual machine on the particular node using the image.

4. The method of claim 1, wherein the caching network comprises a single cache server.

5. The method of claim 1, wherein the caching network comprises a plurality of cache servers.

6. The method of claim 5, wherein the cache servers are Squid servers.

7. The method of claim 5, wherein determining whether the requested image is presently stored on the caching network comprises searching through the plurality of cache servers for the image.

8. The method of claim 7, wherein searching through the plurality of cache servers comprises:

selecting a first cache server based on a set of scores computed for each of the plurality of cache servers;

determining whether the image is on the first cache server; and

when the image is not on the first cache server, selecting a second cache server based on the set of scores.

9. The method of claim 5, wherein each cache server comprises a queue of images of computer system configurations.

10. The method of claim 9 further comprising, when the requested image is present in the queue of a particular cache server, moving the requested image to an entry point of the queue of the particular cache server.

11. The method of claim 9 further comprising, when the requested image is not presently stored on the caching network, loading the retrieved image onto a particular cache server at an entry point of the queue of the particular cache server.

12. The method of claim 11, wherein the retrieved image is loaded onto the particular cache server based on a set of scores computed for each of the plurality of cache servers.

13. The method of claim 1, wherein the image is streamed to the particular node in equally sized sections.

14. The method of claim 13, wherein each section is 256 Mb.

15. A method comprising:

at a caching network of a hosting and storage system that comprises a plurality of nodes for hosting virtual machines for users, the caching network comprising a plurality of cache servers, receiving a request for an image of a particular computer system configuration for deployment as a virtual machine on a particular node of the hosting system;

for each cache server in the caching network, calculating a score for the requested image; and

searching through the cache servers for the requested image in an order determined by the calculated scores.

16. The method of claim 15, wherein the calculated score for the requested image for a particular cache server is based on a name of the requested image and a name of the particular cache server.

17. The method of claim 15, wherein calculating the score for the requested image for a particular cache server comprises calculating a hash function using a name of the requested image and a name of the particular cache server.

18. The method of claim 15, wherein searching through the cache servers comprises:

identifying a first cache server having a highest calculated score for the requested image;

determining whether the image is in a memory of the first cache server; and

when the image is not in a memory of the first cache server, identifying a second cache server having a next highest calculated score for the requested image.

19. The method of claim 18, wherein searching through the cache servers further comprises iteratively identifying a cache server with a next highest calculated score and determining whether the image is in a memory of the identified cache server until the image is found in a particular cache server.

20. The method of claim 19 further comprising streaming the image to the particular node from the particular cache server.

21. A non-transitory computer readable medium storing a computer program for execution by at least one processor, the computer program comprising sets of instructions for:

at a caching network of a hosting and storage system that comprises a plurality of nodes for hosting virtual machines for users, receiving a request for an image of a particular computer system configuration for deployment as a virtual machine on a particular node of the hosting system;

determining whether the requested image is presently stored on the caching network;

when the image is present on the caching network, streaming the image to the particular node of the hosting system for deployment as a virtual machine on the particular node; and

when the image is not presently stored on the caching network, retrieving a copy of the image from a permanent storage network and then streaming the image to the particular node of the hosting system for deployment as a virtual machine on the particular node.

22. The non-transitory computer readable medium of claim 21, wherein the caching network comprises a plurality of cache servers.

23. The non-transitory computer readable medium of claim 22, wherein the set of instructions for determining whether the requested image is presently stored on the caching network comprises a set of instructions for searching through the plurality of cache servers for the image.

24. The non-transitory computer readable medium of claim 23, wherein the set of instructions for searching through the plurality of cache servers comprises sets of instructions for:

selecting a first cache server based on a set of scores computed for each of the plurality of cache servers;

determining whether the image is on the first cache server; and

when the image is not on the first cache server, selecting a second cache server based on the set of scores.

25. A non-transitory computer readable medium storing a computer program for execution by at least one processor, the computer program comprising sets of instructions for:

at a caching network of a hosting and storage system that comprises a plurality of nodes for hosting virtual machines for users, the caching network comprising a plurality of cache servers, receiving a request for an image of a particular computer system configuration for deployment as a virtual machine on a particular node of the hosting system;

for each cache server in the caching network, calculating a score for the requested image; and

searching through the cache servers for the requested image in an order determined by the calculated scores.

26. The non-transitory computer readable medium of claim 25, wherein the calculated score for the requested image for a particular cache server is based on a name of the requested image and a name of the particular cache server.

27. The non-transitory computer readable medium of claim 25, wherein the set of instructions for calculating the score for the requested image for a particular cache server comprises a set of instructions for calculating a hash function using a name of the requested image and a name of the particular cache server.

28. The non-transitory computer readable medium of claim 25, wherein the set of instructions for searching through the cache servers comprises sets of instructions for:

identifying a first cache server having a highest calculated score for the requested image;

determining whether the image is in a memory of the first cache server; and

when the image is not in a memory of the first cache server, identifying a second cache server having a next highest calculated score for the requested image.