Targeted memory pressure event notifications

• US 9,170,859 B2
• Filed: 10/11/2012
• Issued: 10/27/2015
• Est. Priority Date: 06/07/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Ramesh, Ananthakrishna, Crosby, Daniel E., Magee, James Michael, Desai, Lionel D., Watson, Matthew G., Crane, Neil G.
• Primary Examiner(s): Sough, H S
• Assistant Examiner(s): RONI, SYED A
• Application Number:
  US13/650,083
• Publication Number:
  US 20130332942A1
• Time in Patent Office: 1,111 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 2209/504 Resource capping
• CPC Class Codes: G06F 2209/508 Monitor
• CPC Class Codes: G06F 2209/543 Local
• CPC Class Codes: G06F 9/5016 the resource being the memory
• CPC Class Codes: G06F 9/542 Event management; Broadcasting; Multicasting; Notifications
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

Abstract

Systems, methods, and computer program products for target memory pressure event notifications are disclosed. Processes running on a device can register to receive memory pressure event notifications from a memory management system, which are sent while memory pages are being reclaimed. Active processes running on a device processor can be assigned a priority that ranges from low to high. Responsive to a memory pressure event occurring on the device, the memory management system determines whether less than a threshold number of high priority processes are active on the device. If so, the memory management system sends a memory pressure event notification to the registered process with the lowest priority among the active processes.

Claims

1. A method of managing memory, comprising:

assigning priorities to processes running on a device;

responsive to a memory pressure event on the device exceeding a threshold level, determining that less than a threshold number of high priority processes are active on the device; and

responsive to determining that less than the threshold number of high priority processes are active on the device, sending a memory pressure event notification to an active process with the lowest priority, wherein the memory pressure event notification initiates a memory reclamation event,

where the method is performed by one or more hardware processors.

2. The method of claim 1, wherein the threshold level is a percentage of free memory available to applications.

3. The method of claim 1, further comprising:

registering a process with an operating system or memory management system of the device for receiving memory pressure event notifications.

4. The method of claim 3, where the registration is through an Application Programming Interface (API) of a software framework.

5. The method of claim 3, where the memory pressure event notification includes a code representing a severity level.

6. The method of claim 1, wherein the memory reclamation event comprises terminating the active process with the lowest priority.

7. The method of claim 1, wherein the memory reclamation event comprises dumping contents of a cache memory.

8. The method of claim 1, wherein memory reclamation event comprises:

dumping contents of a cache memory; and

subsequent to dumping contents of the cache memory, terminating the active process with the lowest priority.

9. The method of claim 8, wherein the active process with the lowest priority is terminated an interval of time after the contents of the cache memory is dumped.

10. The method of claim 9, wherein the interval of time is determined based of a severity level of the memory pressure event.

11. A system of managing memory, comprising:

one or more processors;

memory coupled to the one or more processors and having instructions, which, when executed by the one or more processors, causes the one or more processors to perform operations comprising;

assigning priorities to processes running on a device;

responsive to a memory pressure event on the device exceeding a threshold level, determining that less than a threshold number of high priority processes are active on the device; and

responsive to the determining, sending a memory pressure event notification to an active process with the lowest priority, wherein the memory pressure event notification initiates a memory reclamation event.

12. The system of claim 11, wherein the threshold level is a percentage of free memory available to applications.

13. The system of claim 11, where the operations further include:

registering a process with an operating system or memory management system of the device for receiving memory pressure event notifications.

14. The system of claim 13, where the registration is through an Application Programming Interface (API) of a software framework.

15. The system of claim 13, where the memory pressure event notification includes a code representing a severity level.

16. The system of claim 11, wherein the memory reclamation event comprises terminating the active process with the lowest priority.

17. The system of claim 11, wherein the memory reclamation event comprises dumping contents of a cache memory.

18. The system of claim 11, wherein memory reclamation event comprises:

dumping contents of a cache memory; and

subsequent to dumping contents of the cache memory, terminating the active process with the lowest priority.

19. The system of claim 18, wherein the active process with the lowest priority is terminated an interval of time after the contents of the cache memory is dumped.

20. The system of claim 19, wherein the interval of time is determined based of a severity level of the memory pressure event.

21. A non-transitory computer-readable medium including one or more sequences of instructions which, when executed by one or more processes, causes:

assigning priorities to processes running on a device;

responsive to a memory pressure event on the device exceeding a threshold level, determining that less than a threshold number of high priority processes are active on the device; and

responsive to the determining, sending a memory pressure event notification to an active process with the lowest priority, wherein the memory pressure event notification initiates a memory reclamation event.

22. The non-transitory computer-readable medium of claim 21, wherein the threshold level is a percentage of free memory available to applications.

23. The non-transitory computer-readable medium of claim 21, where the operations further include:

registering a process with an operating system or memory management system of the device for receiving memory pressure event notifications.

24. The non-transitory computer-readable medium of claim 23, where the registration is through an Application Programming Interface (API) of a software framework.

25. The non-transitory computer-readable medium of claim 23, where the memory pressure event notification includes a code representing a severity level.

26. The non-transitory computer-readable medium of claim 21, wherein the memory reclamation event comprises terminating the active process with the lowest priority.

27. The non-transitory computer-readable medium of claim 21, wherein the memory reclamation event comprises dumping contents of a cache memory.

28. The non-transitory computer-readable medium of claim 21, wherein memory reclamation event comprises:

dumping contents of a cache memory; and

subsequent to dumping contents of the cache memory, terminating the active process with the lowest priority.

29. The non-transitory computer-readable medium of claim 28, wherein the active process with the lowest priority is terminated an interval of time after the contents of the cache memory is dumped.

30. The non-transitory computer-readable medium of claim 29, wherein the interval of time is determined based of a severity level of the memory pressure event.