Application-directed memory de-duplication

• US 9,355,039 B2
• Filed: 08/12/2013
• Issued: 05/31/2016
• Est. Priority Date: 05/02/2013
• Status: Active Grant

• Current Assignee: GlobalFoundries, Inc.
• Original Assignee: GlobalFoundries, Inc.
• Inventors: Dawson, Michael H., Iyengar, Arun K., Johnson, Graeme
• Primary Examiner(s): Peugh, Brian
• Assistant Examiner(s): Bone, Dustin
• Application Number:
  US13/964,689
• Publication Number:
  US 20140331017A1
• Time in Patent Office: 1,023 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06F 12/08 in hierarchically structured memory systems, e.g. virtual memory systems
• CPC Class Codes: G06F 12/10 Address translation
• CPC Class Codes: G06F 2009/45583 Memory management, e.g. access or allocation
• CPC Class Codes: G06F 2212/1016 Performance improvement
• CPC Class Codes: G06F 2212/1044 Space efficiency improvement
• CPC Class Codes: G06F 2212/152 Virtualized environment, e.g. logically partitioned system
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects

Abstract

In a computing system including an application executing on top of a virtualization control layer, wherein the virtualization control layer maps portions of a virtual memory to portions of a physical memory, an apparatus for managing memory configured to: identify, by the application, a range of virtual memory whose probability of being replicated in the virtual memory exceeds a given threshold; obtain, by the application, at least one memory address corresponding to the range of virtual memory; and pass, from the application to the virtualization control layer, an identifier for the range of virtual memory and the memory address corresponding to the range of virtual memory, wherein the identifier is useable by the virtualization control layer to identify similar ranges within the virtual memory.

Claims

1. In a computing system comprised of an application executing on top of a virtualization control layer, wherein the virtualization control layer maps portions of a virtual memory to portions of a physical memory, an apparatus for managing memory comprising:

a memory; and

a processor coupled to the memory and configured to;

identify, by the application, a range of the virtual memory whose probability of being replicated in the virtual memory exceeds a given threshold;

obtain, by the application, at least one memory address corresponding to the range of virtual memory;

pass, from the application to the virtualization control layer, an identifier for the range of virtual memory and the memory address corresponding to the range of virtual memory, wherein the identifier is useable by the virtualization control layer to identify similar ranges within the virtual memory; and

provide an application programming interface configured to allow the identifier and the range of virtual memory to be passed down from the application to a guest operating system, and from the guest operating system to the virtualization control layer at runtime;

wherein the application executes on the guest operating system, and the guest operating system executes on the virtualization control layer; and

wherein the processor is further configured to use at the virtualization control layer, based at least in part upon the identifier, delta encoding to reduce redundant information in the physical memory.

2. The apparatus of claim 1, wherein the range of virtual memory is used to store one of:

at least one file read into memory; and

at least one read only program artifact.

3. The apparatus of claim 1, wherein the virtualization control layer comprises a hypervisor.

4. The apparatus of claim 1, wherein the virtualization control layer comprises an operating system.

11. The apparatus of claim 1, wherein the identifier is useable by the virtualization control layer to limit comparison of memory pages to each other to particular memory pages.

12. The apparatus of claim 1, wherein the identifier is useable by the virtualization control layer to determine that the similar ranges within the virtual memory are likely to occur.

13. The apparatus of claim 1, wherein the processor is further configured to use at the virtualization control layer, based at least in part upon the identifier and the memory address corresponding to the range of virtual memory, delta encoding to reduce redundant information in the physical memory.

14. The apparatus of claim 1, wherein the delta encoding operates using an offset that represents a difference from a base memory page.

15. The apparatus of claim 14, wherein redundant information is reduced by de-duplicating a plurality of base memory pages.

16. The apparatus of claim 1, wherein the identifier passed by the application is selected by the application such that the identifier is the same as an identifier from another process in the guest operating system.

17. The apparatus of claim 1, wherein the processor is further configured to change a page size of a portion of the physical memory that backs the identified range of virtual memory.

18. The apparatus of claim 17, wherein the page size of the portion of the physical memory that backs the identified range of virtual memory is reduced.

5. A computer program product comprising a non-transitory processor-readable storage medium having encoded therein executable code of one or more software programs, wherein the one or more software programs when executed by the at least one processor implement the steps of:

identifying, by the application, a range of the virtual memory whose probability of being replicated in the virtual memory exceeds a given threshold;

obtaining, by the application, at least one memory address corresponding to the range of virtual memory;

passing, from the application to the virtualization control layer, an identifier for the range of virtual memory and the memory address corresponding to the range of virtual memory, wherein the identifier is useable by the virtualization control layer to identify similar ranges within the virtual memory; and

providing an application programming interface configured to allow the identifier and the range of virtual memory to be passed down from the application to a guest operating system, and from the guest operating system to the virtualization control layer at runtime;

wherein the application executes on the guest operating system, and the guest operating system executes on the virtualization control layer; and

wherein the one or more software programs when executed by the at least one processor implement at the virtualization control layer, based at least in part upon the identifier, delta encoding to reduce redundant information in the physical memory.

6. In a computing system comprised of an application executing on top of a virtualization control layer, wherein the virtualization control layer maps portions of a virtual memory to portions of a physical memory, an apparatus for managing memory comprising:

a memory; and

a processor coupled to the memory and configured to;

receive, at the virtualization control layer from the application, an identifier for a range of virtual memory whose probability of being replicated in the virtual memory exceeds a given threshold and at least one memory address corresponding to the range of virtual memory; and

use, by the virtualization control layer, the identifier to identify similar ranges within the virtual memory; and

provide an application application programming interface configured to allow the identifier and the range of virtual memory to be passed down from the application to a guest operating system, and from the guest operating m to the virtualization control layer at runtime;

wherein the application executes on the guest operating system, and the guest operating system executes on the virtualization control layer; and

wherein the processor is further configured to use at the virtualization control layer, based at least in part upon the identifier, delta encoding to reduce redundant information in the physical memory.

7. The apparatus of claim 6, wherein the range of virtual memory is used to store one of:

at least one file read into memory; and

at least one read only program artifact.

8. The apparatus of claim 6, wherein the virtualization control layer comprises a hypervisor.

9. The apparatus of claim 6, wherein the virtualization control layer comprises an operating system.

10. A computer program product comprising a non-transitory processor-readable storage medium having encoded therein executable code of one or more software programs, wherein the one or more software programs when executed by the at least one processor implement the steps of:

receiving, at the virtualization control layer from the application, an identifier for a range of virtual memory whose probability of being replicated in the virtual memory exceeds a given threshold and at least one memory address corresponding to the range of virtual memory;

using, by the virtualization control layer, the identifier to identify similar ranges within the virtual memory; and

providing an application programming interface configured to allow the identifier and the range of virtual memory to be passed down from the application to a guest operating system, and from the guest operating system to the virtualization control layer at runtime; and

wherein the application executes on the guest operating system, and the guest operating system executes on the virtualization control layer; and

wherein the one or more software programs when executed by the at least one processor implement at the virtualization control layer, based at least in part upon the identifier, delta encoding to reduce redundant information in the physical memory.