RESOURCE MANAGEMENT BASED ON DEVICE-SPECIFIC OR USER-SPECIFIC RESOURCE USAGE PROFILES

• US 20150256476A1
• Filed: 04/29/2014
• Published: 09/10/2015
• Est. Priority Date: 03/10/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Whitechapel, David A., Gbadegesin, Abolade, Trufinescu, Adina M., Kaza, Akhilesh, Clinick, Andrew, Kurtzman, Timothy M., Robinson, Jeremy P., Shah, Samarth H.
• Granted Patent: US 9,871,741 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 2209/5019 Workload prediction
• CPC Class Codes: G06F 9/5011 the resources being hardware resources other than CPUs, Servers and Terminals
• CPC Class Codes: G06F 9/5016 the resource being the memory
• CPC Class Codes: G06F 9/5022 Mechanisms to release resources
• CPC Class Codes: H04L 47/70 Admission control; Resource allocation
• CPC Class Codes: H04L 47/83 based on usage prediction
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Resources used by a foreground process associated with an application as well as one or more background tasks associated with the application that are running as separate processes on the computing device are tracked. Historical data relating to resource usage by the application is utilized to predict a resource usage amount for the application which is then stored. A subsequent launch of the application can be conditioned upon whether the predicted resource usage amount is available. If the predicted resource usage amount is available, it can be allocated to the application and the application can be launched. If the application then exceeds the predicted resource usage amount, other processes executing concurrently therewith may be terminated to free up the resource. Regardless of how the application performs, new resource usage data is obtained for the application, which is then used to adjust the predicted resource usage amount.

Claims

1. A method implemented by a computing device for managing a resource thereof, comprising:

determining a first amount of the resource that is used by a first instance of an application while being executed by the computing device, the determining including determining an amount of the resource that is used by a foreground process associated with the first instance of the application and one or more background tasks associated with the first instance of the application;

calculating a first predicted resource usage amount for the application based at least on the first amount;

storing the first predicted resource usage amount in a data store;

determining a second amount of the resource to be allocated to a second instance of the application to be executed by the computing device based at least on the first predicted resource usage amount stored in the data store.

2. The method of claim 1, wherein the resource comprises at least one of:

a volatile or non-volatile memory resource;

a central processing unit (CPU) resource;

an input/output (I/O) resource;

a network resource;

a power resource; and

a sensor resource.

3. The method of claim 1, wherein calculating the first predicted resource usage amount for the application based on at least the first amount comprises:

obtaining a maximum resource usage amount for the application by comparing the first amount to one or more previously-determined amounts associated with one or more previously-executed instances of the application; and

calculating the first predicted resource usage amount based on the maximum resource usage amount.

4. The method of claim 1, wherein calculating the first predicted resource usage amount for the application based on at least the first amount comprises:

obtaining an average resource usage amount for the application based on the first amount and one or more previously-determined amounts associated with previously-executed instances of the application; and

calculating the first predicted resource usage amount based on the average resource usage amount.

5. The method of claim 4, wherein obtaining the average resource usage amount for the application based on the first amount and the one or more previously-determined amounts associated with previously-executed instances of the application comprises:

multiplying the first amount by a first weighting factor to obtain a first product;

multiplying a running average amount obtained based on at least the one or more previously-determined amounts by a second weighting factor to obtain a second product; and

summing the first product and the second product.

6. The method of claim 5, wherein the first weighting factor is larger than the second weighting factor.

7. The method of claim 1, further comprising:

in response to determining that an amount of the resource used by the second instance of the application while being executed by the computing device exceeds the second amount, terminating one or more processes that are concurrently executing on the computing device.

8. The method of claim 1, further comprising:

in response to determining that the second amount of the resource is not currently available, preventing execution of the second instance of the application.

9. The method of claim 1, further comprising:

in response to determining that the second amount of the resource is not currently available, terminating one or more processes that are currently executing on the computing device.

10. The method of claim 1, wherein the determining, calculating and storing steps comprise:

determining the first amount of the resource that is used by the first instance of the application while being executed by the computing device on behalf of a first user;

calculating the first predicted resource usage amount for the application and the first user based at least on the first amount;

storing the first predicted resource usage amount in the data store; and

determining the second amount of the resource to be allocated to the second instance of the application to be executed by the computing device on behalf of the first user based at least on the first predicted resource usage amount stored in the data store;

the method further comprising;

determining a third amount of the resource that is used by a third instance of the application while being executed by the computing device on behalf of a second user;

calculating a second predicted resource usage amount for the application and the second user based at least on the third amount;

storing the second predicted resource usage amount in the data store; and

determining a fourth amount of the resource to be allocated to a fourth instance of the application to be executed by the computing device on behalf of the second user based at least on the second predicted resource usage amount stored in the data store.

11. A computer program product comprising a computer-readable memory having computer program logic recorded thereon that when executed by at least one processor of a computing device causes the at least one processor to perform operations, the operations comprising:

receiving a request to launch an application;

obtaining a predicted resource usage amount for the application, the predicted resource usage amount being based on a monitored usage of a resource of the computing device by a foreground process associated with the application and one or more background tasks associated with the application during one or more prior executions of the application;

determining whether a sufficient amount of a resource is available by comparing the predicted resource usage amount to an amount of the resource that is currently available; and

allowing the application to launch in response to at least determining that a sufficient amount of the resource is available.

12. The computer program product of claim 11, wherein the resource comprises one of:

a volatile or non-volatile memory resource;

a central processing unit (CPU) resource;

an input/output (I/O) resource;

a network resource;

a power resource; and

a sensor resource.

13. The computer program product of claim 11, wherein the operations further comprise:

not allowing the application to launch in response to at least determining that a sufficient amount of the resource is not available.

14. The computer program product of claim 11, wherein the operations further comprise:

causing one or more processes to be terminated in response to at least determining that a sufficient amount of the resource is not available.

15. The computer program product of claim 11, wherein the operations further comprise:

in response to determining that an amount of the resource used by the application after being launched exceeds the predicted resource usage amount, terminating one or more processes that are concurrently executing on the computing device.

16. The computer program product of claim 11, wherein the receiving step comprises receiving the request to launch the application on behalf of a first user and wherein the obtaining step comprises obtaining a predicted resource usage amount for the application and the first user.

17. A system implemented on a computing device, comprising:

at least one processor; and

memory that is accessible by the at least one processor, the memory storing components for execution by the at least one processor, the components including;

a resource manager operable to monitor a pattern of usage of at least one resource of the computing device by one or more of an application and a user, to store information associated with the pattern of usage, and to use the stored information to predictively allocate at least a portion of the resource to at least one process prior to execution thereof by the at least one processor.

18. The system of claim 17, wherein the at least one resource comprises:

a volatile or non-volatile memory resource;

a central processing unit (CPU) resource;

an input/output (I/O) resource;

a network resource;

a power resource; and

a sensor resource.

19. The system of claim 17, wherein the resource manager is operable to predictively allocate the at least a portion of the resource to an application prior to launching of the application by any entity.

20. The system of claim 17, wherein the at least one resource comprises memory and wherein the resource manager is further operable to load at least a portion of an application or data associated with an application into the predictively-allocated memory prior to launching of the application by any entity.