Slow-dynamic load balancing method and system

• US 20040267930A1
• Filed: 06/16/2004
• Published: 12/30/2004
• Est. Priority Date: 06/26/2003
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Portaluri, Bruno, Rossi, Ricardo, Giulio, Domenico Di
• Granted Patent: US 7,475,108 B2
• Time in Patent Office: Days
• US Class Current: 709/225
• 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
• CPC Class Codes: H04L 67/1021 based on client or server locations

Abstract

A load balancing method and a corresponding system are proposed. The load balancing method is used in environments (e.g., implementing a licensing management application) wherein each client is associated with a preferred server storing specific information for the client. Each client periodically detects a workload and a response time of all the servers. The client selects a subset of nearest servers (according to their response times). The server in that subset with the lowest workload is set as an eligible server. Whenever a ratio between the workload of the preferred server and the workload of the eligible server exceeds a predefined threshold value (e.g., 1.1), the client switches to the eligible server (transferring the corresponding specific information). The method of the invention exhibits a slow dynamic, and tends to reach a steady condition (wherein the specific information of the clients is not continuously moved across the system).

Claims

1. A load balancing method for use in a data processing system with a distributed architecture including a plurality of servers and a plurality of clients, the method comprising for at least one client the steps of:

associating the client with a preferred one of the servers, the preferred server storing specific information for the client;

detecting an indication of a workload and an indication of a response time of each server;

selecting an eligible one of the servers according to the workload and the response time of each server;

calculating at least one comparison parameter indicative of a performance difference between the preferred server and the eligible server; and

switching the preferred server to the eligible server and transferring the specific information to the eligible server in response to the reaching of a predefined threshold by the at least one comparison parameter.

2. The method of claim 1, wherein the performance difference corresponding to the threshold is at least 5%.

3. The method of claim 1, wherein the at least one comparison parameter consists of a ratio between the workload of the preferred server and the workload of the eligible server.

4. The method of claim 1, wherein the step of detecting the indication of the workload and the indication of the response time of each server includes:

sending a request to the server;

receiving a response indicative of the workload from the server;

measuring a time elapsed between the sending of the request and the receiving of the response; and

determining the response time according to at least one of the elapsed times.

5. The method of claim 4, wherein the step of determining the response time includes:

logging a plurality of elapsed times being measured most recently; and

calculating the response time according to an average of the logged elapsed times.

6. The method of claim 1, wherein the step of detecting the indication of the workload and the indication of the response time of each server further includes:

determining the number of clients associated with the server; and

determining the workload according to the number of clients.

7. The method of claim 6, wherein the step of determining the workload according to the number of clients includes dividing the number of clients by a power factor of the server.

8. The method of claim 1, wherein the step of selecting the eligible server includes:

establishing an acceptable range of the response times;

selecting a subset of the servers having the response time within the acceptable range; and

setting the eligible server to a server of the subset having a lowest workload.

9. The method of claim 8, wherein the step of establishing the acceptable range includes:

setting a lower limit of the acceptable range to a lowest response time of the servers; and

setting an upper limit of the acceptable range to the lowest response time multiplied by a predefined factor.

10. The method of claim 1, further comprising the steps of:

providing a list identifying the servers;

distributing the list to the servers; and

distributing the list from each server to the clients associated therewith.

11. The method of claim 1, comprising the enumerated steps for each client.

12. A program storage device readable by a machine, tangibly embodying a program of instructions executable by the machine to perform a load balancing method in a data processing system with a distributed architecture including a plurality of servers and a plurality of clients, the method comprising for at least one client the steps of:

associating the client with a preferred one of the servers, the preferred server storing specific information for the client;

detecting an indication of a workload and an indication of a response time of each server;

selecting an eligible one of the servers according to the workload and the response time of each server;

calculating at least one comparison parameter indicative of a performance difference between the preferred server and the eligible server; and

switching the preferred server to the eligible server and transferring the specific information to the eligible server in response to the reaching of a predefined threshold by the at least one comparison parameter.

13. The program storage device of claim 12, wherein the computer program is directly loadable into a working memory of the data processing system to perform the method when the program is run on the data processing system.

14. The program storage device of claim 12, wherein the computer program is directly loadable into a working memory of a client in the data processing system to perform the method when the program is run on the client.

15. The program storage device of claim 12, wherein the step of switching the preferred server to the eligible server causes the specific information to be transferred to the eligible server.

16. The program storage device of claim 12, wherein the method comprises the enumerated steps for each client.

17. A data processing system with a distributed architecture including a plurality of servers and a plurality of clients for implementing a load balancing application, the system comprising for at least one client:

means for associating the client with a preferred one of the servers;

means for storing specific information for the client on the preferred server;

means for detecting an indication of a workload and an indication of a response time of each server;

means for selecting an eligible one of the servers according to the workload and the response time of each server;

means for calculating at least one comparison parameter indicative of a performance difference between the preferred server and the eligible server; and

means responsive to the reaching of a predefined threshold by the at least one comparison parameter for switching the preferred server to the eligible server and for transferring the specific information to the eligible server.

18. The data processing system of claim 17, comprising the enumerated elements for each client.

19. A data processing system with a distributed architecture including a plurality of servers and a plurality of clients for implementing a load balancing application, the system comprising for at least one client:

a software agent for associating the client with a preferred one of the servers;

a memory structure for storing specific information for the client on the preferred server; and

a load balancing module comprising;

software code for detecting an indication of a workload and an indication of a response time of each server;

software code for selecting an eligible one of the servers according to the workload and the response time of each server;

software code for calculating at least one comparison parameter indicative of a performance difference between the preferred server and the eligible server; and

software code responsive to the reaching of a predefined threshold by the at least one comparison parameter for switching the preferred server to the eligible server and for transferring the specific information to the eligible server.

20. The data processing system of claim 19, comprising the enumerated elements for each client.

21. A client for use in a data processing system with a distributed architecture including a plurality of servers and a plurality of clients for implementing a load balancing application, the client comprising:

means for associating the client with a preferred one of the servers, the preferred server storing specific information for the client;

means for detecting an indication of a workload and an indication of a response time of each server;

means for selecting an eligible one of the servers according to the workload and the response time of each server;

means for calculating at least one comparison parameter indicative of a performance difference between the preferred server and the eligible server; and

means responsive to the reaching of a predefined threshold by the at least one comparison parameter for switching the preferred server to the eligible server, thereby causing the specific information to be transferred to the eligible server.

22. A client for use in a data processing system with a distributed architecture including a plurality of servers and a plurality of clients for implementing a load balancing application, the client comprising:

a software agent for associating the client with a preferred one of the servers, the preferred server storing specific information for the client; and

a load balancing module comprising;

software code for detecting an indication of a workload and an indication of a response time of each server;

software code for selecting an eligible one of the servers according to the workload and the response time of each server;

software code for calculating at least one comparison parameter indicative of a performance difference between the preferred server and the eligible server; and

software code responsive to the reaching of a predefined threshold by the at least one comparison parameter for switching the preferred server to the eligible server, thereby causing the specific information to be transferred to the eligible server.