Performance management based on resource consumption

• US 9,690,685 B2
• Filed: 05/30/2014
• Issued: 06/27/2017
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Vyas, Amit K., Liu, Albert S., Schmitt, Drew A., Crippes, Karen, Blaine, Russell A., Ramadurai, Anand
• Primary Examiner(s): Zhen, Wei
• Assistant Examiner(s): Lyons, Andrew M
• Application Number:
  US14/292,466
• Publication Number:
  US 20150347262A1
• Time in Patent Office: 1,124 Days
• Field of Search: 718104
• CPC Class Codes: G06F 11/3003 Monitoring arrangements specially adapted to the computing system or computing system component being monitored
• CPC Class Codes: G06F 11/3013 where the computing system is an embedded system, i.e. a combination of hardware and software dedicated to perform a certain function in mobile devices, printers, automotive or aircraft systems testing or monitoring of control systems or parts thereof G05B23/02
• CPC Class Codes: G06F 11/302 where the computing system component is a software system
• CPC Class Codes: G06F 11/3024 where the computing system component is a central processing unit [CPU]
• CPC Class Codes: G06F 11/3409 for performance assessment
• CPC Class Codes: G06F 2201/81 Threshold
• CPC Class Codes: G06F 2201/865 Monitoring of software
• CPC Class Codes: G06F 2209/5022 Workload threshold
• CPC Class Codes: G06F 9/5011 the resources being hardware resources other than CPUs, Servers and Terminals
• CPC Class Codes: G06F 9/5022 Mechanisms to release resources
• CPC Class Codes: G06F 9/505 considering the load
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

A method and apparatus of a device for performance management by terminating application programs that consume an excessive amount of system resources is described. The device receives a resource consumption threshold and a detection period. The device further monitors a resource usage of an application program. The device determines whether the resource usage of the application program exceeds the resource consumption threshold for the detection period. The device further terminates the application program when the resource usage exceeds the resource consumption threshold for the detection period.

Claims

1. A computer-implemented method for performance management of a data processing system, the method comprising:

selecting a first application program having a first application program type for resource usage monitoring, wherein the first application program is running in a background state while the first application program is executing one or more first application tasks or one or more system tasks and is not directly interacting with the user or directly viewable by a user of the data processing system, and the first application program is not a daemon;

determining a resource consumption threshold and a detection period for the first application program having the first application program type, wherein the resource consumption threshold and the detection period for the first application program are based at least in part on the first application program type;

monitoring a resource usage of the first application program, in response to selecting the first application program for resource usage monitoring and determining the resource consumption threshold and detection period for the first application program;

determining whether the monitored resource usage of the first application program exceeds the resource consumption threshold over the duration of the detection period;

terminating the first application program when the resource usage exceeds the resource consumption threshold over the duration of the detection period;

receiving statistics characterizing one or more previous terminations of a plurality of application programs having the first application program type;

dynamically adjusting the detection period of the first application program type based on the statistics.

2. The method of claim 1 further comprising:

terminating monitoring of resource usage of the first application program in response to determining that the first application program is no longer in the background state.

3. The method of claim 1, wherein the determining that the resource consumption of the first application program exceeds the resource consumption threshold comprises determining that the average resource consumption over the duration of the detection period for the first application program exceeds the resource consumption threshold.

4. The method of claim 1, further comprising terminating monitoring of resource usage of the first application program in response to determining that the first application program is running in the foreground.

5. The method of claim 1, wherein the determining of whether the resource usage of the first application program exceeds the resource consumption threshold over the detection period comprises determining whether resource usage exceeds the resource consumption threshold for a time period that is at least as long as the detection period.

6. The method of claim 1, wherein the resource consumption threshold comprises a CPU consumption threshold.

7. The method of claim 1, wherein the resource consumption threshold comprises one of a networking usage threshold, a radio communication usage threshold, or a storage access threshold.

8. The method of claim 1, wherein the resource consumption threshold and the detection period are based on an analysis of resource usage by different application programs.

9. The method of claim 1, wherein dynamically adjusting comprises:

increasing at least one of the detection period or the resource consumption threshold for applications having the first application program type, in response to the statistics indicating that fewer applications of the first application program type should be terminated, or

decreasing at least one of the detection period or the resource consumption threshold for applications having the first application program type, in response to the statistics indicating that more applications of the first application program type should be terminated.

10. The method of claim 9, wherein a second application program has a second type having at least one of a different detection period or a different resource consumption threshold than the first application program type.

22. The method of claim 1, wherein the detection period is at least one minute.

23. The method of claim 1, wherein the resource usage fluctuates during the detection period, and monitoring resource usage comprises taking an average of a plurality of sampling points over the detection period, and determining that the first application program exceeds the resource consumption threshold comprises determining that a majority of the sample points over the interval exceed the resource consumption threshold.

25. The method of claim 1, wherein the application program types comprises one of an email application, a game application, a web browser application or a media playing application.

27. The method of claim 1, further comprising:

dynamically adjusting the resource consumption threshold of the first application program type based on the statistics.

11. A non-transitory machine-readable medium having executable instructions to cause one or more processing units to perform a method of performance management of a data processing system, the method comprising:

selecting a first application program for resource usage monitoring, wherein the first application program is running in a background state while the first application program is executing one or more first application tasks or one or more system tasks and is not directly interacting with the user or directly viewable by a user of the data processing system, and the first application program is not a daemon;

determining a resource consumption threshold and a detection period for the first application program having a first application program type, wherein the resource consumption threshold and the detection period for the first application program are based at least in part on the first application program type;

monitoring resource usage of the first application program, in response to selecting the first application program for resource usage monitoring and determining the resource consumption threshold and detection period for the first application program;

determining whether the monitored resource usage of the first application program exceeds the resource consumption threshold over the duration of the detection period;

terminating the first application program when the resource usage exceeds the resource consumption threshold over the duration of the detection period;

receiving statistics characterizing one or more previous terminations of a plurality of application programs having the first application program type;

dynamically adjusting the detection period of the first application program type based on the statistics.

12. The non-transitory machine-readable medium of claim 11, wherein the determining of whether the resource usage of the first application program exceeds the resource consumption threshold over the detection period comprises determining whether resource usage exceeds the resource consumption threshold for a time period that is at least as long as the detection period.

13. The non-transitory machine-readable medium of claim 11, wherein the resource consumption threshold comprises a CPU consumption threshold.

14. The non-transitory machine-readable medium of claim 11, wherein the method further comprises:

terminating monitoring of resource usage of the first application program in response to determining that the first application program is no longer in the background state.

15. The non-transitory machine-readable medium of claim 11, wherein the determining that the first application program exceeds the resource consumption threshold comprises determining that the average resource consumption over the duration of the detection period for the first application program exceeds the resource consumption threshold.

16. The non-transitory machine-readable medium of claim 15, wherein the first application program performs one or more of the following operations while in the background state:

(a) outputting audio;

(b) providing a location service;

(c) providing functions relative to a Bluetooth connection;

or

(d) performing network communications functions by sending or receiving data through one or more networks.

17. The non-transitory machine-readable medium of claim 11, further comprising terminating monitoring of resource usage of the first application program in response to determining that the first application program is running in the foreground.

24. The non-transitory machine-readable medium of claim 11, wherein dynamically adjusting comprises:

increasing at least one of the detection period or the resource consumption threshold for applications having the first application program type, in response to the statistics indicating that fewer applications of the first application program type should be terminated, or

decreasing at least one of the detection period or the resource consumption threshold for applications having the first application program type, in response to the statistics indicating that more applications of the first application program type should be terminated.

18. A device to perform performance management, the device comprising:

a processing system;

a memory coupled to the processing system through a bus; and

a process executed from the memory by the processing system causes the processing system to;

select a first application program for resource usage monitoring, wherein the first application program is running in a background state while the first application program is executing one or more first application tasks or one or more system tasks and is not directly interacting with the user or directly viewable by a user of the data processing system, and the first application program is not a daemon;

determine a resource consumption threshold and a detection period for the first application program having a first application program type, wherein the resource consumption threshold and the detection period for the first application program are based at least in part on the first application program type;

monitor a resource usage of the first application program, in response to selecting the first application program for resource usage monitoring and determining the resource consumption threshold and detection period for the first application program;

determine whether the monitored resource usage of the first application program exceeds the resource consumption threshold over the duration of the detection period;

terminate the first application program when the resource usage exceeds the resource consumption threshold over the duration of the detection period;

receive statistics characterizing one or more previous terminations of a plurality of application programs having the first application program type; and

dynamically adjust the detection period of the first application program type based on the statistics.

19. The device of claim 18, wherein the resource usage of the first application program exceeds the resource consumption threshold over the detection period when resource usage exceeds the resource consumption threshold for a period of time that is at least as long as the detection period.

20. The device of claim 18, wherein the resource consumption threshold comprises a CPU consumption threshold.

21. The device of claim 18, wherein the resource consumption threshold and the detection period are determined based on an analysis of resource usage by the first application program.

26. The device of claim 18, wherein dynamically adjusting comprises:

increasing at least one of the detection period or the resource consumption threshold for applications having the first application program type, in response to the statistics indicating that fewer applications of the first application program type should be terminated, or

decreasing at least one of the detection period or the resource consumption threshold for applications having the first application program type, in response to the statistics indicating that more applications of the first application program type should be terminated.