Video on demand digital server load balancing

• US 7,680,938 B2
• Filed: 08/30/2006
• Issued: 03/16/2010
• Est. Priority Date: 06/27/2003
• Status: Active Grant

• Current Assignee: Xylon LLC (Intellectual Ventures LLC)
• Original Assignee: Beach Unlimited LLC (Intellectual Ventures LLC)
• Inventors: Oesterreicher, Richard T., Murphy, Craig
• Primary Examiner(s): Bruckart; Benjamin R.
• Application Number:
  US11/468,613
• Publication Number:
  US 20070124476A1
• Time in Patent Office: 1,294 Days
• Field of Search: 709217-219, 709227-229, 709/226
• US Class Current: 709/226
• 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 67/1012 based on compliance of requirements or conditions with available server resources

Abstract

A system and method for load balancing a plurality of servers is disclosed. In a preferred embodiment, a plurality of servers in a video-on-demand or other multi-server system are divided into one or more load-balancing groups. Each server preferably maintains state information concerning other servers in its load-balancing group including information concerning content maintained and served by each server in the group. Changes in a server'"'"'s content status or other state information are preferably proactively delivered to other servers in the group. When a content request is received by any server in a load-balancing group, it evaluates the request in accordance with a specified algorithm to determine whether it should deliver the requested content itself or redirect the request to another server in its group. In a preferred embodiment, this determination is a function of information in the server'"'"'s state table.

Claims

1. A method comprising:

designating a director server from among a plurality of servers configured to service requests for assets and configured to function as a director server if designated, each of the plurality of servers further configured with a storage system and an adaptable cache configured to proactively cache assets;

receiving a first request and a second request for an asset at a network interface of the designated director server;

forwarding the first request and the second request to a host processor of the designated director server over a bus;

determining whether or not the asset is present on the designated director server;

if the asset is present on the designated director server, servicing the first request and the second request from the designated director server by;

monitoring the bus by a designated director server'"'"'s adaptable cache,

detecting the first request and the second request on the bus at the designated director server'"'"'s adaptable cache,

generating, at the designated director server'"'"'s adaptable cache, a list of pairs of requests for the asset comprising a first pair of requests comprising the first request and the second request,

determining that the first pair of requests has the shortest interval between start times from among pairs of requests identified in the list of pairs of requests,

responsive to the first request, streaming the asset from a designated director server'"'"'s storage system and storing the asset on the designated director server'"'"'s adaptable cache as it is being streamed from the designated director server'"'"'s storage system, and

responsive to the second request, streaming the asset from the designated director server'"'"'s adaptable cache and transmitting an instruction from the designated director server'"'"'s adaptable cache to the designated director server'"'"'s storage system directing the designated director server'"'"'s storage system not to respond to the second request; and

if the asset is not present on the designated director server, selecting, by the designated director server based on a designated director server'"'"'s state table, a first server in said plurality of servers to service the first request and the second request, said designated director server'"'"'s state table comprising state information for said first server indicating that the asset is present on the first server.

2. The method of claim 1, wherein servicing the first request and the second request from the designated director server comprises updating a designated director'"'"'s state table based on the servicing of the first request and the second request, and transmitting changes to the designated director'"'"'s state table to each server in said plurality of servers.

3. The method of claim 1, wherein said designated director'"'"'s state table comprises parametric information for servers in said plurality of servers, and wherein selecting, by the designated director server, the first server in said plurality of servers to service the first request and the second request comprises the designated director server selecting the first server using the designated director'"'"'s state table, wherein said parametric information comprises information identifying assets maintained on each server in said plurality of servers.

4. The method of claim 3, wherein said parametric information further comprises information indicative of the functional state and current load of each server in said plurality of servers.

5. The method of claim 3, wherein said parametric information further comprises information indicative of whether each server in said plurality of servers comprises extended memory.

6. The method of claim 3, wherein said parametric information further comprises information indicative of whether an asset is a new release.

7. The method of claim 1, further comprising rejecting the request for an asset if the requested video is not present in said plurality of servers.

8. The method of claim 1, further comprising forwarding the first request and the second request to the first server.

9. The method of claim 1, further comprising redirecting the first request and the second request to the first server.

10. The method of claim 1, wherein selecting the first server comprises:

calculating a load factor for servers in said plurality of servers having the asset;

determining that no servers in said plurality of servers have parameters that are below threshold limits; and

selecting a server having the lowest load factor from the servers in said plurality of servers having the asset.

11. A method comprising:

responsive to an asset being copied onto a first server in a load balancing group, modifying, by said first server, said first server'"'"'s state information table by placing an identifier for the asset in said first server'"'"'s state information table, wherein said first server'"'"'s state information table comprises state information for servers in said load balancing group, wherein said state information comprises a plurality of parameters concerning said servers in said load balancing group, and wherein the plurality of parameters comprise asset identifiers;

pushing, by said first server, said identifier for the asset to all servers in said load balancing group;

modifying, by each server in said load balancing group, its respective state information table, by placing said identifier for the asset in its respective state information table;

receiving by said load balancing group a designation by a management system of a director server from among servers in said load balancing group, wherein each server in said load balancing group is configured to function as a director server if designated, and wherein each server in said load balancing group is further configured with a storage system and an adaptable cache configured to proactively cache assets;

receiving at a director server'"'"'s network interface a first request and a second request for an asset,

forwarding the first request and the second request to a director server'"'"'s host processor over a bus;

determining whether or not the asset is present on the director server;

if the asset is present on the director server, servicing the request for the video asset by;

monitoring the bus by a director server'"'"'s adaptable cache,

detecting the first request and the second request on the bus at the director server'"'"'s adaptable cache,

generating, at the director server'"'"'s adaptable cache, a list of pairs of requests for the asset comprising a first pair of requests comprising the first request and the second request,

determining that the first pair of requests has the shortest interval between start times from among pairs of requests associated with the list of pairs of requests,

responsive to the first request, streaming the asset from a director server'"'"'s storage system and storing the asset on the director server'"'"'s adaptable cache as it is being streamed from the designated director server'"'"'s storage system, and

responsive to the second request, streaming the asset from the director server'"'"'s adaptable cache and transmitting an instruction from the director server'"'"'s adaptable cache to the director server'"'"'s storage system directing the director server'"'"'s storage system not to respond to the second request; and

if the asset is not present on the director server, servicing the first request and the second request by;

determining by said director server that the identifier for the asset in a director server'"'"'s state information table is associated with a selected server in said load balancing group;

transmitting an instruction from the director server to the selected server to stream the asset to a requesting client; and

streaming by said selected server the asset to the requesting client.

12. The method of claim 11, wherein selecting by said director server the selected server in said load balancing group comprises selecting the selected server based on information in said director server'"'"'s state information table indicating that the selected server has the asset stored in a selected server'"'"'s adaptable cache.

13. The method of claim 11, further comprising updating a selected server'"'"'s state table based on the streaming of the requested asset and transmitting changes to said selected server'"'"'s state table from said selected server to each server in said load balancing group.

14. The method of claim 11, wherein said management system designates servers in said load balancing group as director server on the basis of lowest load.

15. The method of claim 11, wherein said plurality of parameters concerning said servers in said load balancing group comprise parameters that indicate whether one or more of assets maintained on said servers in the load balancing group are stored on an adaptable cache of each of the servers in the load balancing group.

16. A method comprising:

designating, by a management system, a director server from among a plurality of servers configured to service requests for assets and configured to function as the director server if designated, each of the plurality of servers further configured with a storage system and an adaptable cache configured to proactively cache video assets;

receiving a first request and a second request for a first asset at a network interface of the designated director server;

forwarding the first request and the second request to a host processor of the designated director server over a bus;

determining that the first asset is present on the designated director server;

servicing the first request and the second request from the designated director server by;

monitoring the bus by a designated director server'"'"'s adaptable cache,

detecting the first request and the second request on the bus at the designated director server'"'"'s adaptable cache,

generating, at the designated director server'"'"'s adaptable cache, a list of pairs of requests for the first asset comprising a first pair of requests comprising the first request and the second request,

determining that the first pair of requests has the shortest interval between start times from among pairs of requests associated with the list of pairs of requests,

responsive to the first request, streaming the first asset from a designated director server'"'"'s storage system and storing the first asset on the designated director server'"'"'s adaptable cache as it is being streamed from the designated director server'"'"'s storage system, and

responsive to the second request, streaming the first asset from the designated director server'"'"'s adaptable cache and transmitting an instruction from the designated director server'"'"'s adaptable cache to the designated director'"'"'s storage system directing the designated director'"'"'s storage system not to respond to the second request;

receiving a third request for a second asset at the designated director server;

determining that the second asset is not present on the designated director server; and

selecting, by the designated director server based on a designated director server'"'"'s state table, a first server in said plurality of servers to service the third request, said designated director server'"'"'s state table comprising state information for said first server indicating that the second asset is present on the first server.

17. The method of claim 16, wherein servicing the first request and the second request from the designated director server comprises updating the designated director'"'"'s state table based upon the servicing of the first request and the second request and transmitting changes to the designated director'"'"'s state table to each server in said plurality of servers.

18. The method of claim 16, wherein said designated director'"'"'s state table comprises parametric information for servers in said plurality of servers, and wherein selecting, by the designated director server, the first server in said plurality of servers to service the third request comprises the designated director server selecting the first server using the designated director'"'"'s state table, wherein said parametric information comprises information identifying assets maintained on said plurality of servers.

19. The method of claim 18, wherein said parametric information further comprises information indicative of the functional state and current load of each server in said plurality of servers.

20. The method of claim 18, wherein said parametric information further comprises information indicative of whether each server in said plurality of servers comprises extended memory.

21. The method of claim 18, wherein said parametric information further comprises information indicative of whether an asset is a new release.

22. The method of claim 16, further comprising rejecting the third request if the second asset is not present in said plurality of servers.

23. The method of claim 16, further comprising forwarding the third request to the first server.

24. The method of claim 16, further comprising redirecting the third request to the first server.

25. The method of claim 16, wherein selecting the first server comprises:

calculating a load factor for servers in said plurality of servers having the second asset;

determining as available servers one or more servers in said plurality of servers whose parameters are below threshold limits; and

selecting the first server from the available servers having a lowest load factor.