Caching, clustering and aggregating server

• US 7,337,214 B2
• Filed: 09/26/2003
• Issued: 02/26/2008
• Est. Priority Date: 09/26/2002
• Status: Active Grant

• Current Assignee: YHC Corporation
• Original Assignee: YHC Corporation
• Inventors: Henigin, Edward, Swarin, Douglas, Douglass, Michael, Yokubaitis, Jonah
• Primary Examiner(s): Jean; Frantz B.
• Application Number:
  US10/672,189
• Publication Number:
  US 20040122910A1
• Time in Patent Office: 1,614 Days
• Field of Search: 709/203, 709/214, 709/217, 709/249, 709/247, 709/231, 709/219
• US Class Current: 709/214
• CPC Class Codes: G06F 16/9574 of access to content, e.g. by caching
• CPC Class Codes: H04L 67/288 Distributed intermediate devices, i.e. intermediate devices for interaction with other intermediate devices on the same level
• CPC Class Codes: H04L 67/56 Provisioning of proxy services store-and-forward switching systems in data switching networks H04L12/54
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching

Abstract

A cluster of data caching servers that provide UseNet service to customers. The cluster of data caching servers cache articles and data requested by customers after retrieving the articles and data from a backend server/server farm. The cluster of data caching servers are adapted to share their cache memories with the other clustered servers in the cluster such that, if an article is requested by a client and the article has already been stored in one of the clustered server'"'"'s cache memories, there is no requirement to retrieve all the requested article from the backend server.

Claims

1. A server system comprising:

a backend server;

a first communication link connected to the backend server;

a cluster of servers connected to the first communication link;

wherein each server in the cluster of servers is in communication with the other servers in the cluster of servers and

wherein at least one of the servers in said the cluster of servers stores retrieved articles from the backend server when the articles are requested by a customer;

a second communication link;

wherein the second communication link provides article requests from at least a first customer to the cluster of servers and provides at least one of the retrieved articles to the at least one customer; and

wherein the server system retrieves stored articles from the at least one server in the cluster of servers when a first requested article has been previously requested by a second customer and is stored in the at least one server in the cluster of servers.

2. The server system of claim 1, wherein a second server of the cluster of servers is retrieves the first requested article from the at least one of the servers in the cluster of servers when the customer requested article has already been requested from the backend servers due to a previous customer request for the first requested article.

3. The server system of claim 1, wherein the retrieved articles stored in the at least one server in the cluster of servers are each stored for a period of time until more storage space is required.

4. The server system of claim 1, wherein:

the retrieved articles stored in the at least one server in the cluster of servers are stored in a memory device divided into smaller sized data storage units; and

each data storage unit is dynamically assigned a time interval such that only articles originally posted within the dynamically assigned time interval are stored in each the storage unit.

5. The server system of claim 1, wherein the customer requests for articles can be fulfilled by retrieving the requested articles from the at least one server in the cluster of servers for about 20 to 90 percent of the customer requests for articles.

6. The server system of claim 1, wherein the first communications link is a TCP/IP communication session.

7. The server system of claim 1, wherein the communications link uses a Network News Transfer Protocol (NNTP).

8. The server system of claim 1, wherein each the server in the cluster of servers is adapted to be in communication with the other servers in the cluster of servers via a network connection.

9. The server system of claim 8, wherein the network connection comprises at least one of an wired connection, a wireless connection, an optical connection, and a satellite connection or link.

10. The server system of claim 1, wherein the second communications link is a TCP/IP session.

11. The server system of claim 1, wherein the second communications link uses a Network News Transfer Protocol (NNTP).

12. The server system of claim 1, wherein each server in the cluster of servers is a commodity server.

13. The server system of claim 1, wherein the backend server and the cluster of servers are geographically distant from each other.

14. A storage and retrieval system comprising:

a plurality of servers forming a server cluster,

each server of the plurality of servers having storage space for storing articles and data;

a communication network allowing each one of the plurality of servers to communicate with each other;

a backend server comprising storage space for storing articles,

the backend server being in communication with the server cluster via a first communication link;

wherein a first server of the plurality of servers accepts a request for a first article from a customer;

wherein the first server, via the communication network, queries the plurality of servers for the first article;

wherein if the first article is found in one of the plurality of servers storage space, the first article is provided to the first server for delivery to the customer; and

wherein the first article is not found in one of the plurality of server the first server requests the first article from the backend server.

15. The system of claim 14, wherein:

the backend server provides the first article to the first server for delivery to the customer; and

the first server stores the first article in the first server'"'"'s storage space.

16. The system of claim 14, wherein the storage space of each one of the plurality of servers combined provides less article retention then the storage space of the backend server.

17. The system of claim 14, wherein when the first server queries the plurality of servers for the first article, the first article is found in one of the plurality of servers at least 20 percent of the time.

18. The system of claim 14, wherein the communication network comprises at least one of a wired connection, a wireless connection, an optical connection, and a satellite connection or link.

19. The system of claim 14, wherein the first communication link is a TCP/IP session.

20. The system of claim 14, wherein the backend server is geographically separated from the plurality of servers.

21. The system of claim 14, wherein the memory space of each the server of the plurality of servers is logically divided in smaller sized storage units such that each storage space is assigned a time interval for storing articles originally posted within the time interval.

22. The system of claim 21, wherein the backend server provides the first article to the first server for delivery to the customer and the first server stores the first article in a first storage space that is assigned a time interval that includes a date of the first article.

23. The system of claim 21, wherein the backend server provides the first article to the first server for delivery to the customer and wherein the first server attempts to store the first article in a first storage space such that, if there are only time interval storage spaces having time intervals newer than a date of the first article, then the first article is not stored in the first server.

24. The system of claim 21, wherein the backend server provides the first article to the first server for delivery to the customer and wherein the first server attempts to store the first article in a first storage space such that, if there are only time interval storage spaces having time intervals older than a date of the first article, then storage space having the oldest time interval is reassigned a time interval that includes the date of the first article and the first article is stored therein.

25. A method for providing news services comprising:

providing a local network cluster of news servers;

caching data and metadata related to news services with the news servers in the local network cluster;

receiving a request for news services from a client associated with the local network cluster;

determining whether the requested news services are available from the news servers in the local network cluster;

if so, retrieving the requested news services from the news servers in the local network cluster and providing the requested news services to the client directly from the local network cluster; and

if not, creating a session to one of at least one backend server(s) to retrieve the requested news services.

26. The method of claim 25, wherein the requested news services are retrieved from the one backend server in a compressed format.

27. The method of claim 25, further comprising:

storing the retrieved requested news service;

providing the retrieved requested news service to the client; and

storing the retrieved requested news service in at least one of the news servers.