Mechanism for enabling multiple processes to share physical memory

• US 8,255,922 B1
• Filed: 01/09/2006
• Issued: 08/28/2012
• Est. Priority Date: 01/09/2006
• Status: Active Grant

• Current Assignee: Oracle America, Inc. (Oracle Corporation)
• Original Assignee: Oracle America, Inc. (Oracle Corporation)
• Inventors: Fresko, Nedim, Zhou, Jiangli, Long, Dean R. E.
• Primary Examiner(s): Puente, Emerson
• Assistant Examiner(s): Labud, Jonathan R
• Application Number:
  US11/328,965
• Time in Patent Office: 2,423 Days
• Field of Search: None
• US Class Current: 719/312
• CPC Class Codes: G06F 9/45516 Runtime code conversion or optimisation
• CPC Class Codes: G06F 9/544 Buffers; Shared memory; Pipes

Abstract

A mechanism is disclosed for enabling multiple processes to share the same portion of physical memory. The first time an instance of a process is executed, a list of common components is compiled. The compiled code is then written into a newly created mappable data structure, which is stored into persistent storage. The next time an instance of that process is executed, the mappable data structure is mapped into a portion of the process instance'"'"'s virtual memory space. This enables the process instance to invoke the compiled code for the common components. Multiple instances of the process may have their virtual memory spaces mapped to the same mappable data structure in this way. Thereafter, it is up to the operating system to load the contents of the mappable data structure into a portion of physical memory, and to ensure that all of the process instances share that physical memory portion.

Claims

1. A method implemented by a computer, wherein a first process is executing on the computer, the method comprising:

initializing, in response to executing a first virtual machine (VM) instance on the computer, a first code cache associated with the first VM instance, wherein the computer comprises a persistent storage, a first virtual memory space, and a physical memory;

assigning the first virtual memory space to the first code cache;

obtaining, from the first VM instance, a persistent storage location;

determining that a mappable data structure does not exist at the persistent storage location;

obtaining, in response to the determining that the mappable data structure does not exist, a first component associated with the first VM instance and a second component associated with the first VM instance;

compiling the first component to obtain first compiled code stored in the first virtual memory space;

compiling the second component to obtain second compiled code stored in the first virtual memory space;

creating, at the persistent storage location, the mappable data structure;

storing the first compiled code and the second compiled code in the mappable data structure;

initializing, in response to executing a second virtual machine (VM) instance on the computer, a second code cache associated with the second VM instance, wherein the computer further comprises a second virtual memory space;

assigning the second virtual memory space to the second code cache;

obtaining, from the second VM instance, the persistent storage location;

determining that the mappable data structure exists at the persistent storage location;

determining that the mappable data structure is compatible with the second VM instance; and

mapping, in response to the determining that the mappable data structure is compatible with the second VM instance, the mappable data structure into the second virtual memory space.

2. The method of claim 1, wherein determining that the mappable data structure is compatible with the second VM instance comprises:

obtaining a first set of information associated with the mappable data structure;

obtaining a second set of information associated with the second VM instance; and

comparing the first set of information to the second set of information to obtain an indication that the mappable data structure is compatible with the second VM instance.

3. The method of claim 1, wherein storing the mappable data structure comprises:

obtaining a set of information associated with the first VM instance; and

storing the set of information with the mappable data structure.

4. The method of claim 1, further comprising:

providing component reference information to the second VM instance to enable the second VM instance to invoke the first compiled code, wherein the component reference information includes information identifying the first component, and a reference to the first compiled code.

5. The method of claim 4, further comprising:

processing the mappable data structure to derive the component reference information therefrom.

6. The method of claim 1, wherein the first VM instance is a Java virtual machine (JVM), and wherein the component-is a Java method.

7. The method of claim 1, wherein the first VM instance and second VM instance are created by executing the same set of code.

8. A machine readable storage medium comprising a set of instructions which, when executed by one or more processors, causes the one or more processors to perform the following operations:

initializing, in response to executing a first virtual machine (VM) instance on the computer, a first code cache associated with the first VM instance, wherein the computer comprises a persistent storage, a first virtual memory space, and a physical memory;

assigning the first virtual memory space to the first code cache;

obtaining, from the first VM instance, a persistent storage location;

determining that a mappable data structure does not exist at the persistent storage location;

obtaining, in response to the determining that the mappable data structure does not exist, a first component associated with the first VM instance and a second component associated with the first VM instance;

compiling the first component to obtain first compiled code stored in the first virtual memory space;

compiling the second component to obtain second compiled code stored in the first virtual memory space;

creating, at the persistent storage location, the mappable data structure;

storing the first compiled code and the second compiled code in the mappable data structure;

initializing, in response to executing a second virtual machine (VM) instance on the computer, a second code cache associated with the second VM instance, wherein the computer further comprises a second virtual memory space;

assigning the second virtual memory space to the second code cache;

obtaining, from the second VM instance, the persistent storage location;

determining that the mappable data structure exists at the persistent storage location;

determining that the mappable data structure is compatible with the second VM instance; and

mapping, in response to the determining that the mappable data structure is compatible with the second VM instance, the mappable data structure into the second virtual memory space.

9. The machine readable storage medium of claim 8, wherein determining that the mappable data structure is compatible with the second VM instance comprises:

obtaining a first set of information associated with the mappable data structure;

obtaining a second set of information associated with the second VM instance; and

comparing the first set of information to the second set of information to obtain an indication that the mappable data structure is compatible with the second VM instance.

10. The machine readable storage medium of claim 8, wherein storing the mappable data structure comprises:

obtaining a set of information associated with the first VM instance; and

storing the set of information with the mappable data structure.

11. The machine readable storage medium of claim 8, wherein the set of instructions causes the one or more processors to further perform the following operation:

providing component reference information to the second VM instance to enable the second VM instance to invoke the first compiled code, wherein the component reference information includes information identifying the first component, and a reference to the first compiled code.

12. The machine readable storage medium of claim 11, wherein the set of instructions causes the one or more processors to further perform the following operation:

processing the mappable data structure to derive the component reference information therefrom.

13. The machine readable storage medium of claim 8, wherein the first VM instance is a Java virtual machine (JVM), and wherein the component-is a Java method.

14. An apparatus, comprising:

a persistent storage;

one or more processors;

a first virtual memory space;

a second virtual memory space;

a physical memory; and

a set of instructions, which when executed by the one or more processors, causes the one or more processors to perform the following operations;

initializing, in response to executing a first virtual machine (VM) instance on the apparatus, a first code cache associated with the first VM instance;

assigning the first virtual memory space to the first code cache;

obtaining, from the first VM instance, a persistent storage location;

determining that a mappable data structure does not exist at the persistent storage location;

obtaining, in response to the determining that the mappable data structure does not exist, a first component associated with the first VM instance and a second component associated with the first VM instance;

compiling the first component to obtain first compiled code stored in the first virtual memory space;

compiling the second component to obtain second compiled code stored in the first virtual memory space;

creating, at the persistent storage location, the mappable data structure;

storing the first compiled code and the second compiled code in the mappable data structure;

initializing, in response to executing a second virtual machine (VM) instance on the apparatus, a second code cache associated with the second VM instance;

assigning the second virtual memory space to the second code cache;

obtaining, from the second VM instance, the persistent storage location;

determining that the mappable data structure exists at the persistent storage location;

determining that the mappable data structure is compatible with the second VM instance; and

mapping, in response to the determining that the mappable data structure is compatible with the second VM instance, the mappable data structure into the second virtual memory space.

15. The apparatus of claim 14, determining that the mappable data structure is compatible with the second VM instance comprises:

obtaining a first set of information associated with the mappable data structure;

obtaining a second set of information associated with the second VM instance; and

comparing the first set of information to the second set of information to obtain an indication that the mappable data structure is compatible with the second VM instance.

16. The apparatus of claim 14, wherein storing the mappable data structure comprises:

obtaining a set of information associated with the first VM instance; and

storing the set of information with the mappable data structure.

17. The apparatus of claim 14, wherein the set of instructions caused the one or more processors to further perform the following operation:

providing component reference information to the second VM instance to enable the second VM instance to invoke the first compiled code, wherein the component reference information includes information identifying the first component, and a reference to the first compiled code.

18. The apparatus of claim 17, wherein the set of instructions causes the one or more processors to further perform the following operation:

processing the mappable data structure to derive the component reference information therefrom.

19. The apparatus of claim 14, wherein the first VM instance is a Java virtual machine (JVM), and wherein the component-is a Java method.