SCALABLE DISTRIBUTED STORAGE AND DELIVERY

• US 20110072108A1
• Filed: 11/29/2010
• Published: 03/24/2011
• Est. Priority Date: 12/30/2004
• Status: Active Grant

• Current Assignee: XStor Systems, Inc.
• Original Assignee: XStor Systems, Inc.
• Inventors: Gopalakrishnan, Shivakumar
• Granted Patent: US 8,171,125 B2
• Time in Patent Office: Days
• US Class Current: 709/217
• 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 method for scalable data delivery, comprising:

receiving a request for data;

identifying a plurality of application servers to process the request for data;

sending a control message to the plurality of application servers, wherein the control message includes mapping information to allow the plurality of application servers to download directly from a storage device;

temporarily relinquishing control of the request for data to the plurality of application servers at substantially the same time as sending the control message.

2. The method of claim 1, further comprising:

receiving a packet received acknowledgement from a sender of the request for data; and

resuming control of the request for data from the plurality of application servers.

3. The method of claim 1, wherein the identifying is performed autonomously based upon a determination of the plurality of application servers that can perform the request for data.

4. The method of claim 1, further comprising:

determining if a file transfer is complete; and

resuming control of the request for data from the plurality of application servers if the file transfer is complete.

5. The method of claim 1, further comprising:

determining if a file transfer is complete; and

sending a subsequent control message to the plurality of application servers if the file transfer is not complete.

6. The method of claim 1, further comprising:

retrieving at least a portion of the request for data; and

sending the at least the portion of the request for data utilizing a spoofing technique.

7. The method of claim 1, whether the receiving the request for data is at one or more of the plurality of application servers that have the same IP address.

8. The method of claim 1, further comprising:

obtaining control of the request for data, wherein control of the request for data was temporarily relinquished; and

resuming processing of the request for data.

9. The method of claim 1, further comprising:

supporting failover, wherein if a first server fails, a second server takes over functionality of the first server.

10. The method of claim 1, further comprising:

authenticating a sender of the request for data.

11. The method of claim 1, further comprising:

receiving an availably acknowledgement from at least one of the plurality of application servers in response to the control message.

12. A scalable distributed storage system, comprising:

means for receiving a request;

means for identifying at least one application server to process the request;

means for directing the request through at least one symbolic link to a plurality of storage servers;

means for dynamically adding at least one storage server without modification of the at least one symbolic link;

means for processing a portion of the request; and

means for sending the portion in reply to the request.

13. The system of claim 12, further comprising:

means for relinquishing control of the request; and

means for sending a control message to the at least one application server.

14. The system of claim 12, further comprising:

means for utilizing a spoofing technique to disguise a sender of the request.

15. The system of claim 12, further comprising:

means for determining if a response to the request is received by a sender of the request; and

means for resending the request if the response was not received.

16. An apparatus, comprising:

an interface module configured to receive a request for data; and

an optimizer module configured to identify a plurality of application components that can process the request, wherein the apparatus temporarily releases control of processing the request to at least one of the plurality of application components.

17. The apparatus of claim 16, further comprising a confirm module that receives an acknowledgment when the data is provided by the at least one of the plurality of application components.

18. The apparatus of claim 17, wherein the apparatus resumes control of processing the request when the acknowledgment is received.

19. The apparatus of claim 16, wherein the apparatus comprises a single virtual internet protocol address.

20. The apparatus of claim 16, further comprising a mapping module configured to provide information to the at least one of the plurality of applications components, wherein the at least one of the plurality of application components directly accesses a storage component for retrieval of the data.