Scalable distributed storage and delivery

• US 7,844,691 B2
• Filed: 12/23/2005
• Issued: 11/30/2010
• Est. Priority Date: 12/30/2004
• Status: Expired due to Fees

• Current Assignee: XStor Systems, Inc.
• Original Assignee: XStor Systems, Inc.
• Inventors: Gopalakrishnan, Shivakumar
• Primary Examiner(s): Jacobs; Lashonda T
• Application Number:
  US11/319,293
• Publication Number:
  US 20070198710A1
• Time in Patent Office: 1,803 Days
• Field of Search: 709/201, 709/203, 709/217, 709/223, 709/224, 718/105, 725/93, 725/25
• US Class Current: 709/223
• CPC Class Codes: H04L 67/06 specially adapted for file transfer, e.g. file transfer protocol [FTP]
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/1008 based on parameters of servers, e.g. available memory or workload monitoring of computer activity G06F11/30
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer
• CPC Class Codes: H04L 67/1034 Reaction to server failures by a load balancer

Abstract

Embodiments describe scalable distributed storage delivery method that can utilize commodity storage devices, thus there is little, if any, modification of the existing storage hardware or storage clients. According to an aspect is a system that can include a plurality of primary servers and application servers to deliver data to the storage client. The client can request information from the primary server, which can in some embodiments, authenticate the client. The primary server can determine a set of application servers that can deliver the information. The information data can be served to the client transparently from the application servers. The application servers can read the information content from a local cache or directly from storage devices.

Claims

1. A scalable distributed delivery system, comprising:

a first management component that receives a user information request and optimizes the request for efficient delivery;

at least a second management component that is a replicate of the first management component wherein the first management component and the second management component share a single virtual IP address;

a network switch that detects failure in the first management component and dynamically switches to the second management component to which the single virtual IP address is directed; and

at least one application component that retrieves the requested information and delivers the information to the user.

2. The system of claim 1, the first management component relinquishes control of the information request to the at least one application component during information retrieval.

3. The system of claim 1, the at least one application component is selectively distributed to eliminate data congestion.

4. The system of claim 1, the at least one application component is installed on a data center machine that utilized unused server resources.

5. The system of claim 1, the at least one application component is installed near a network edge.

6. The system of claim 1, further comprising a second application component that retrieves a portion of the requested information.

7. The system of claim 1, the at least one application component retrieves the requested information from a storage server.

8. The system of claim 1, the delivery of information to the user is sent through a spoofing technique.

9. A method for scalable data delivery, comprising:

receiving a client request for information from a client;

directing the client request to one of a plurality of management components that share a virtual IP address to optimize the client request for delivery;

identifying when a management component that is optimizing the client request goes offline;

dynamically switching to a second management component to continue optimizing the client request for delivery; and

selecting a plurality of application servers to retrieve the requested information and deliver the requested information to the client.

10. The method of claim 9, further comprising:

releasing control of the requested information to at least one application server.

11. The method of claim 9, further comprising:

selectively distributing the at least one application server to eliminate data congestion.

12. The method of claim 9, further comprising:

selecting the at least one application server that is installed on a data center machine that utilizes unused server resources.

13. The method of claim 9, further comprising:

retrieving a portion of the requested information with a second application server.

14. The method of claim 9, further comprising:

retrieving the requested information from a storage server.

15. The method of claim 9, further comprising:

delivering the information to the client using a spoofing technique.

16. A scalable distributed storage system, comprising:

means for receiving a client request for information;

means for selecting a first management component to optimize the client request for delivery;

means for detecting when the first management component selected by the means for selecting fails and for dynamically switching to a second management component that is a mirror of functionality of the first management component; and

means for delivering the information to the client using at least one application component.

17. The system of claim 16, further comprising:

means for retrieving a portion of the information with a second application component.

18. The system of claim 16, further comprising:

means for surrendering control of the client request for the information to the at least one application component during information retrieval.

19. The system of claim 16, further comprising:

means for reducing data congestion by selectively distributing the at least one application component.

20. The system of claim 16, further comprising:

means for retrieving the information from a storage server.