Method to effectively collect data from systems that consists of dynamic sub-systems

• US 20060168194A1
• Filed: 12/06/2004
• Published: 07/27/2006
• Est. Priority Date: 12/06/2004
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Rangaswamy, Srinivasan K., Vignola, Christopher Paul, Lake, John Michael, Qiao, Wenjian
• Granted Patent: US 8,990,377 B2
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06F 11/3495 for systems
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: H04L 67/55 Push-based network services
• CPC Class Codes: H04L 67/62 Establishing a time schedule for servicing the requests

Abstract

A method, apparatus and computer instructions are provided to improve the push/pull workload management model with intelligent routing to effectively collect data from systems that consist of dynamic sub-systems. The invention improves the push/pull model of the referenced invention with intelligent request routing to solve the above problem. An API is exposed in the workload manager enabling its request router to decline requests to route to idle sub-systems. This allows the monitoring agent to avoid sending a pull request to an idle sub-system. Each sub-system will push the data to the agent as it enters the idle state. The agent caches the data it receives from idle sub-systems and combines it with data it pulls from active and stopped sub-systems.

Claims

1. A method in a data processing system for improving workload management, the method comprising:

receiving a status of at least one sub-system;

in response to the sub-system status, retrieving latest performance data for the at least one sub-system; and

determining an overall state of a system based on the latest performance data for the at least one sub-system.

2. The method of claim 1, wherein the status of the at least one sub-system is one of active, idle, stopping or stopped.

3. The method of claim 2, wherein retrieving the latest performance data for an active sub-system includes:

sending a pull request to the active sub-system;

receiving the latest performance data from the active sub-system; and

passing the latest performance data to an aggregator.

4. The method of claim 2, wherein retrieving the latest performance data for an idle sub-system includes:

determining if the status of the idle sub-system has changed;

in response to no status change, retrieving the latest performance data for the idle sub-system from a buffer; and

passing the latest performance data to an aggregator.

5. The method of claim 4, in response to a status change, notifying a monitoring agent of the status change.

6. The method of claim 2, wherein retrieving the latest performance data for a stopping or stopped sub-system includes:

retrieving the latest performance data for the stopping or stopped sub-system from a buffer; and

passing the latest performance data to an aggregator.

7. The method of claim 1, wherein determining the overall state of the system includes:

calculating the overall state of the system by adding the latest performance data from each of the at least one sub-system together.

8. A data processing system comprising:

a bus system;

a communications system connected to the bus system;

a memory connected to the bus system, wherein the memory includes a set of instructions; and

a processing unit connected to the bus system, wherein the processing unit executes the set of instructions to receive a status of at least one sub-system;

in response to the sub-system status, retrieve latest performance data for the at least one sub-system; and

determine an overall state of a system based on the latest performance data for the at least one sub-system.

9. The data processing system of claim 8, wherein the status of the at least one sub-system is one of active, idle, stopping or stopped.

10. The method of claim 9, wherein retrieving the latest performance data for an active sub-system includes a set of instructions to send a pull request to the active sub-system;

receive the latest performance data from the active sub-system; and

pass the latest performance data to an aggregator.

11. The data processing system of claim 9, wherein retrieving the latest performance data for an idle sub-system includes a set of instructions to determine if the status of the idle sub-system has changed;

in response to no status change, retrieve the latest performance data for the idle sub-system from a buffer; and

pass the latest performance data to an aggregator.

12. The data processing system of claim 11, in response to a status change a set of instructions to notify a monitoring agent of the status change.

13. The data processing system of claim 9, wherein retrieving the latest performance data for a stopping or stopped sub-system includes a set of instructions to retrieve the latest performance data for the stopping or stopped sub-system from a buffer;

and pass the latest performance data to an aggregator.

14. The data processing system of claim 8, wherein determining the overall state of the system includes a set of instructions to calculate the overall state of the system by adding the latest performance data from each of the at least one sub-system together.

15. A computer program product in a computer readable medium for improving workload management, the computer program product comprising:

instructions for receiving a status of at least one sub-system;

in response to the sub-system status, instructions for retrieving latest performance data for the at least one sub-system; and

instructions for determining an overall state of a system based on the latest performance data for the at least one sub-system.

16. The computer program product of claim 15, wherein the status of the at least one sub-system is one of active, idle, stopping or stopped.

17. The computer program product of claim 16, wherein the instructions for retrieving the latest performance data for an active sub-system includes:

instructions for sending a pull request to the active sub-system;

instructions for receiving the latest performance data from the active sub-system; and

instructions for passing the latest performance data to an aggregator

18. The computer program product of claim 16, wherein the instructions for retrieving the latest performance data for an idle sub-system includes:

instructions for determining if the status of the idle sub-system has changed;

in response to no status change, instructions for retrieving the latest performance data for the idle sub-system from a buffer; and

instructions for passing the latest performance data to an aggregator

19. The computer program product of claim 18, in response to a status change, instructions for notifying a monitoring agent of the status change

20. The computer program product of claim 16, wherein the instructions for retrieving the latest performance data for a stopping or stopped sub-system includes:

instructions for retrieving the latest performance data for the stopping or stopped sub-system from a buffer; and

instructions for passing the latest performance data to an aggregator.

21. The computer program product of claim 15, wherein the instructions for determining the overall state of the system includes:

instructions for calculating the overall state of the system by adding the latest performance data from each of the at least one sub-system together.

22. An apparatus for improving workload management, the method comprising:

receiving means for receiving a status of at least one sub-system;

in response to the sub-system status, retrieving means for retrieving latest performance data for the at least one sub-system; and

determining means for determining an overall state of a system based on the latest performance data for the at least one sub-system.