Adjusting guest memory allocation in virtual non-uniform memory architecture (NUMA) nodes of a virtual machine

Patent metadata

Field	Value
Publication number	US-10705879-B2
Application number	US-201615355754-A
Country	US
Kind code	B2
Filing date	Nov 18, 2016
Priority date	Mar 26, 2009
Publication date	Jul 7, 2020
Grant date	Jul 7, 2020

Abstract

Techniques for effectuating a virtual Non-Uniform Memory Architecture (NUMA) for virtual machines and adjusting memory in virtual NUMA nodes are described. The virtual NUMA node topology may include a plurality of virtual NUMA nodes. The memory may be adjusted based on pressure in a specific virtual NUMA node of the plurality and an amount of guest memory assigned to the specific virtual NUMA node.

First claim

What is claimed:

1. A method, comprising:
receiving a request to instantiate a virtual machine;
selecting a virtual non-uniform memory architecture (NUMA) node topology for the virtual machine, the virtual NUMA node topology including a plurality of virtual NUMA nodes;
instantiating the virtual machine on a computer system, the virtual machine including the plurality of virtual NUMA nodes; and
adjusting an amount of guest memory assigned to a specific virtual NUMA node by a second amount of guest memory, wherein the adjusting comprises exchanging the second amount of guest memory between the specific virtual NUMA node and a second virtual NUMA node of the plurality of virtual NUMA nodes.

2. The method of claim 1 , wherein adjusting an amount of guest memory assigned to the specific virtual NUMA node is based at least in part on memory pressure in the second virtual NUMA node.

3. The method of claim 1 , further comprising:
sending a message to a guest operating system running on the specific virtual NUMA node, wherein the message indicates that at least one memory block of guest memory has been added to the specific virtual NUMA node.

4. The method of claim 1 , further comprising:
associating at least one memory block of guest memory with system memory prior to adding, during runtime execution of the virtual machine, guest memory to the specific virtual NUMA node.

5. The method of claim 1 , further comprising:
removing, during runtime execution of the virtual machine, guest memory from the specific virtual NUMA node.

6. The method of claim 5 , wherein removing, during runtime execution of the virtual machine, guest memory from the specific virtual NUMA node is based at least in part on memory pressure of the specific virtual NUMA node.

7. The method of claim 5 , wherein the removing, during runtime execution of the virtual machine, guest memory from the specific virtual NUMA node, further comprises:
disassociating at least one memory block of guest memory of the specific virtual NUMA node from system memory.

8. A computer system, comprising:
circuitry for receiving a request to instantiate a virtual machine;
circuitry for selecting a virtual non-uniform memory architecture (NUMA) node topology for the virtual machine, the virtual NUMA node topology including a plurality of virtual NUMA nodes;
circuitry for instantiating the virtual machine on a computer system, the virtual machine including the plurality of virtual NUMA nodes; and
circuitry for adjusting an amount of guest memory assigned to a specific virtual NUMA node by a second amount of guest memory, wherein the adjusting comprises exchanging the second amount of guest memory between the specific virtual NUMA node and a second virtual NUMA node of the plurality of virtual NUMA nodes.

9. The computer system of claim 8 , wherein the amount of guest memory assigned to the specific virtual NUMA node is based at least in part on memory pressure in the second virtual NUMA node.

10. The computer system of claim 8 , further comprising:
circuitry for sending a message to a guest operating system running on the specific virtual NUMA node, wherein the message indicates that at least one memory block of guest memory has been added to the specific virtual NUMA node.

11. The computer system of claim 8 , further comprising:
circuitry for associating at least one memory block of guest memory with system memory prior to adding, during runtime execution of the virtual machine, guest memory to the specific NUMA node.

12. The computer system of claim 8 , further comprising:
circuitry for removing, during runtime execution of the virtual machine, guest memory from the specific virtual NUMA node.

13. The computer system of claim 12 , wherein the removing, during runtime execution of the virtual machine, guest memory from the specific virtual NUMA node is based at least in part on memory pressure of the specific virtual NUMA node.

14. The computer system of claim 12 , wherein the circuitry for removing, during runtime execution of the virtual machine, guest memory from the specific virtual NUMA node, further comprises:
circuitry for disassociating at least one memory block of guest memory of the specific virtual NUMA node from system memory.

15. A non-transitory computer readable medium including processor-executable instructions, comprising:
instructions for receiving a request to instantiate a virtual machine;
instructions for selecting a virtual non-uniform memory architecture (NUMA) node topology for the virtual machine, the virtual NUMA node topology including a plurality of virtual NUMA nodes;
instructions for instantiating the virtual machine on a computer system, the virtual machine including the plurality of virtual NUMA nodes; and
instructions for adjusting an amount of guest memory assigned to a specific virtual NUMA node by a second amount of guest memory, the second amount of guest memory being exchanged between the specific virtual NUMA node and a second virtual NUMA node of the plurality of virtual NUMA nodes.

16. The non-transitory computer readable medium of claim 15 , wherein the amount of guest memory assigned to the specific virtual NUMA node is based at least in part on memory pressure in the second virtual NUMA node.

17. The non-transitory computer readable medium of claim 15 , further comprising:
instructions for associating at least one memory block of guest memory with system memory prior to adding, during runtime execution of the virtual machine, guest memory to the specific virtual NUMA node.

18. The non-transitory computer readable medium of claim 15 , further comprising:
instructions for removing, during runtime execution of the virtual machine, guest memory from the specific virtual NUMA node.

19. The non-transitory computer readable medium of claim 18 , wherein the removing, during runtime execution of the virtual machine, guest memory from the specific virtual NUMA node is based at least in part on memory pressure of the specific virtual NUMA node.

20. The non-transitory computer readable medium of claim 18 , wherein the instructions for removing, during runtime execution of the virtual machine, guest memory from the specific virtual NUMA node, further comprise:
instructions for disassociating at least one memory block of guest memory of the specific virtual NUMA node from system memory.

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Oshins Jacob

Classifications

• G06F12/0284 Primary

  Multiple user address space allocation, e.g. using different base addresses (interprocessor communication G06F15/163) · CPC title

• G06F2212/1041

  Resource optimization · CPC title

• G06F9/5016

  the resource being the memory · CPC title

• G06F15/161

  Computing infrastructure, e.g. computer clusters, blade chassis or hardware partitioning (casings, cabinets, racks or drawers for data centers H05K5/00) · CPC title

• G06F9/455

  Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines · CPC title