LOAD BALANCING USING IMPROVED COMPONENT CAPACITY ESTIMATION

• US 20160224392A1
• Filed: 01/30/2015
• Published: 08/04/2016
• Est. Priority Date: 01/30/2015
• Status: Active Grant

• Current Assignee: CA, Inc. (d/b/a CA Technologies) (Broadcom, Inc.)
• Original Assignee: CA, Inc. (d/b/a CA Technologies) (Broadcom, Inc.)
• Inventors: Clarke, Allan D., Neuse, Douglas M.
• Granted Patent: US 9,575,810 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 2209/5019 Workload prediction
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: G06F 9/5083 Techniques for rebalancing the load in a distributed system
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A method includes receiving, at a load balancer for a plurality of computing components, a workload request. The method also includes accessing a database including a respective non-linear scalability model for each of the plurality of computing components. The method further includes determining a particular computing component from the plurality of computing components based on each respective non-linear scalability model; and scheduling the workload request for execution by the particular computing component.

Claims

1. A method, comprising:

receiving, at a load balancer for a plurality of computing components, a workload request;

accessing a database comprising a respective non-linear scalability model for each of the plurality of computing components;

determining a particular computing component from the plurality of computing components based on each respective non-linear scalability model; and

scheduling the workload request for execution by the particular computing component.

2. The method of claim 1, further comprising:

determining a normalized estimated capacity of each of the plurality of computing components based on each respective non-linear scalability model, wherein determining the particular computing component is further based on each of the normalized estimated capacities.

3. The method of claim 2, wherein the particular computing component is determined so as to maximize the normalized estimated capacity of each of the plurality of computing components.

4. The method of claim 1, further comprising:

determining a normalized estimated size of the workload request, wherein determining the particular computing component is further based on the normalized estimated size of the workload request.

5. The method of claim 4, further comprising:

determining an estimated workload request completion time for each of the plurality of computing components based on each respective non-linear scalability model and the normalized estimated size of the workload request, wherein determining the particular computing component is further based on each workload request completion time, and wherein the particular computing component is determined so as to minimize the estimated workload request completion time.

6. The method of claim 1, further comprising:

determining an estimated workload queue completion time for each of the plurality of computing components based on;

a respective plurality of jobs in a workload queue for each of the plurality of computing components, and

each respective non-linear scalability model, wherein determining the particular computing component is further based on each estimated workload queue completion time.

7. The method of claim 1 further comprising:

determining a workload completion rate for each of the plurality of computing components based on;

a respective plurality of jobs in a workload queue for each of the plurality of computing components, and

each respective non-linear scalability model, wherein determining the particular computing component is further based on each workload completion rate.

8. A computer configured to access a storage device, the computer comprising:

a processor; and

a non-transitory, computer-readable storage medium storing computer-readable instructions that when executed by the processor cause the computer to perform;

receiving, at a load balancer for a plurality of computing components, a workload request;

accessing a database comprising a respective non-linear scalability model for each of the plurality of computing components;

determining a particular computing component from the plurality of computing components based on each respective non-linear scalability model; and

scheduling the workload request for execution by the particular computing component.

9. The computer of claim 8, wherein the computer-readable instructions further cause the computer to perform:

determining a normalized estimated capacity of each of the plurality of computing components based on each respective non-linear scalability model, wherein determining the particular computing component is further based on each of the normalized estimated capacities.

10. The computer of claim 9, wherein the particular computing component is determined so as to maximize the normalized estimated capacity of each of the plurality of computing components.

11. The computer of claim 8, wherein the computer-readable instructions further cause the computer to perform:

determining a normalized estimated size of the workload request, wherein determining the particular computing component is further based on the normalized estimated size of the workload request.

12. The computer of claim 11, wherein the computer-readable instructions further cause the computer to perform:

determining an estimated workload request completion time for each of the plurality of computing components based on each respective non-linear scalability model and the normalized estimated size of the workload request, wherein determining the particular computing component is further based on each workload request completion time, and wherein the particular computing component is determined so as to minimize the estimated workload request completion time.

13. The computer of claim 8, wherein the computer-readable instructions further cause the computer to perform:

determining an estimated workload queue completion time for each of the plurality of computing components based on;

a respective plurality of jobs in a workload queue for each of the plurality of computing components, and

each respective non-linear scalability model, wherein determining the particular computing component is further based on each estimated workload queue completion time.

14. The computer of claim 8, wherein the computer-readable instructions further cause the computer to perform:

determining a workload completion rate for each of the plurality of computing components based on;

a respective plurality of jobs in a workload queue for each of the plurality of computing components, and

each respective non-linear scalability model, wherein determining the particular computing component is further based on each workload completion rate.

15. A computer program product comprising:

a computer-readable storage medium having computer-readable program code embodied therewith, the computer-readable program code comprising;

computer-readable program code configured to receive, at a load balancer for a plurality of computing components, a workload request;

computer-readable program code configured to access a database comprising a respective non-linear scalability model for each of the plurality of computing components;

computer-readable program code configured to determine a particular computing component from the plurality of computing components based on each respective non-linear scalability model; and

computer-readable program code configured to schedule the workload request for execution by the particular computing component.

16. The computer program product of claim 15, wherein the computer-readable program code further comprises:

computer-readable program code configured to determine a normalized estimated capacity of each of the plurality of computing components based on each respective non-linear scalability model, wherein determining the particular computing component is further based on each of the normalized estimated capacities.

17. The computer program product of claim 16, wherein the particular computing component is determined so as to maximize the normalized estimated capacity of each of the plurality of computing components.

18. The computer program product of claim 15, wherein the computer-readable program code further comprises:

determining a normalized estimated size of the workload request, wherein determining the particular computing component is further based on the normalized estimated size of the workload request.

19. The computer program product of claim 18, wherein the computer-readable program code further comprises:

computer-readable program code configured to determine an estimated workload request completion time for each of the plurality of computing components based on each respective non-linear scalability model and the normalized estimated size of the workload request, wherein determining the particular computing component is further based on each workload request completion time, and wherein the particular computing component is determined so as to minimize the estimated workload request completion time.

20. The computer program product of claim 15, wherein the computer-readable program code further comprises:

computer-readable program code configured to determine an estimated workload queue completion time for each of the plurality of computing components based on;

a respective plurality of jobs in a workload queue for each of the plurality of computing components, and

each respective non-linear scalability model, wherein determining the particular computing component is further based on each estimated workload queue completion time.