Powerful and flexible server architecture

• US 6,490,625 B1
• Filed: 11/26/1997
• Issued: 12/03/2002
• Est. Priority Date: 11/26/1997
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Panteleenko, Vsevolod V., Islam, Nayeem, Jaeger, Trent Ray, Liedtke, Jochen
• Primary Examiner(s): Dinh, Dung C.
• Application Number:
  US08/980,074
• Time in Patent Office: 1,833 Days
• Field of Search: 709/229, 709/213, 709/216, 709/201, 709/208, 709/105, 711/138, 364/230, 713/201, 395/187.01
• US Class Current: 709/229
• CPC Class Codes: H04L 67/1001 for accessing one among a plurality of replicated servers
• CPC Class Codes: H04L 67/568 Storing data temporarily at an intermediate stage, e.g. caching

Abstract

A server complex including at least one hit server with item cache, used to process read and write operations relating to cached items from clients, and at least one miss server, serving as a link to other servers (e.g., web servers, file system servers, and databases) for receiving requests relayed from the hit server(s) which relate to non-cached items and for responding to same. The hit server is a general-purpose, generic, component, which is independent of concrete applications and is basically responsible for the performance; while a miss server is a highly-customizable component, which is responsible for flexibility, and is application specific. The inventive architecture provides improved performance whereby a server complex achieves exceptionally high throughput rates for local services (i.e., services using items in the local item cache); flexibility, whereby a server complex can support the enforcement of a variety of application-specific policies for item management, authentication, and item consistency; security, whereby a server complex can enable the verification of the source, integrity, and freshness of communications over untrusted links; and, scalability, whereby a server complex is expandable by adding server components and implementing customized item consistency policies.

Claims

1. A server system comprising:

at least one first server, comprising a generic cache component having at least one cache of items associated therewith, for receiving user requests for performing operations on said items, for determining if user requests relate to items stored at said at least one cache, for determining and executing the item-specific operations for the user requests which relate to said stored items, and for executing default operations for the user requests for items not stored at said at least one cache, said default operations including relaying said user requests to at least one application-specific second server; and

at least one second application-specific miss server in communication with said at least one first server for receiving item-specific operation requests from the at least one first server, for implementing application-specific policies for the distribution of items to clients by executing said item-specific operation requests directly or by linking to one of a plurality of other servers from which non-cached items can be obtained; and

for implementing application-specific policies for managing the at least one cache at said at least one hit server.

2. The server system of claim 1 wherein first and second servers execute on different processors and further comprising a server interconnection system connecting said first and said second servers.

3. The server system of claim 2 wherein said server interconnection system comprises a closed network.

4. The server system of claim 2 wherein said server interconnection system comprises a bus system.

5. The server system of claim 1 further comprising at least one memory location shared by said first and second servers.

6. The server system of claim 1 wherein said first and said second servers execute on a common processor.

7. The server system of claim 2 further comprising at least one memory location shared by said first and second servers.

8. A method for a server system, comprising at least one first server having at least one cache for storing a plurality of items and at least one second server, to respond to user requests comprising the steps of:

receiving a user request at one of said at least one first server;

determining at said one of said at least one first server if said user request relates to an item stored at said at least one cache;

determining the item-specific operations for the user request at said one of said at least one first server;

executing said item-specific operations on said item stored at said at least one cache;

relaying an item-specific operation request relating to said user request from said at least one first server to at least one of said at least one application-specific second server if said user request does not relate to an item stored at said at least one cache;

responding to said relayed item-specific operation request by implementing application-specific policies for the distribution of items to clients by executing item-specific operations at one of said at least one application-specific second server; and

said at least one application-specific second server implementing application specific policies for managing the at least one cache at said at least one hit server.

9. The method of claim 8 further comprising generating and relaying an item-specific operation request relating to said user request when the estimated processing time for executing the item-specific operation at said one of said at least one first server exceeds a threshold time.

10. The method of claim 8 wherein said relaying said user request from one of said at least one first server to at least one of said at least one second server comprises broadcasting said user request to all of said at least one second server.

11. The method of claim 8 wherein said relaying said user request from one of said at least one first server to at least one of said at least one second server comprises transmitting said user request to less than all of said at least one second server.

12. The method of claim 8 wherein said responding to said user request comprises operating on less than all of said cached item.

13. The method of claim 8 wHerein said responding to said relayed user request comprises operating on less than all of a non- cached item.

14. The method of claim 8 wherein at least one item-specific operation is stored with said at least one item in said at least one cache and wherein responding to said user request comprises the steps of:

accessing said item-specific operation from said at least one cache; and

responding to said user request by applying said item-specific operation to said item.

15. The method of claim 12 wherein at least one item-specific operation is stored with said at least one item in said at least one cache and wherein responding to said user request comprises the steps of:

accessing said item-specific operation from said at least one cache; and

responding to said user request by applying said item-specific operation to less than all of said item.

16. The method of claim 8 further comprising the step of verifying user access to said server.

17. The method of claim 8 further comprising the step of verifying user access to said at least one item.

18. The method of claim 8 further comprising the step of encrypting communications between said server and said user.

19. The method of claim 8 further comprising performing coherency operations for items operated upon.

20. The method of claim 14, wherein said item-specific operations include coherency operations, further comprising the steps of:

accessing said item-specific coherency operations; and

performing said item-specific coherency operations for said items.

21. The method of claim 8 further comprising generating and relaying an item-specific operation request relating to said user request when the item-specific operation is preempted at said one of the at least one first server by higher priority item-specific operations for at least one other user request.