Virtual machine management

• US 10,528,376 B2
• Filed: 04/20/2017
• Issued: 01/07/2020
• Est. Priority Date: 04/20/2017
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Devendran, Saravanan, Sainath, Venkatesh
• Primary Examiner(s): Kessler, Gregory A
• Application Number:
  US15/492,829
• Publication Number:
  US 20180307511A1
• Time in Patent Office: 992 Days
• Field of Search: None
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 2009/45583 Memory management, e.g. access or allocation
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: G06F 9/5077 Logical partitioning of resources; Management or configuration of virtualized resources specific details on emulation or internal functioning of virtual machines G06F9/455

Abstract

Disclosed aspects relate to virtual machine management in a shared pool of configurable computing resources. A single multi-node server may be established. The single multi-node server may include a running virtual machine, a set of computing resources that includes a possessed subset of the set of computing resources, a source hypervisor, and a target hypervisor. The possessed subset of the set of computing resources may be assigned to the target hypervisor from the source hypervisor. The running virtual machine may be run using the target hypervisor.

Claims

1. A computer-implemented method for virtual machine management in a shared pool of configurable computing resources, the method comprising:

establishing a single multi-node server that includes;

a running virtual machine,

a set of computing resources that includes a possessed subset of the set of computing resources which is possessed by the running virtual machine,

a source hypervisor which has the running virtual machine with respect to a first temporal period, wherein the source hypervisor is configured to manage the possessed subset of the set of computing resources, and

a target hypervisor to have the running virtual machine with respect to a second temporal period which is subsequent to the first temporal period, wherein the target hypervisor is configured to manage the possessed subset of the set of computing resources;

assigning, to the target hypervisor from the source hypervisor, the possessed subset of the set of computing resources which is possessed by the running virtual machine;

configuring, using a single service processor, both the source and target hypervisors;

communicating, via the single service processor, a set of scheduling-related control information for the running virtual machine from the source hypervisor to the target hypervisor;

running, using the target hypervisor, the running virtual machine;

detecting, with respect to the first temporal period, that the set of computing resources includes both an unreassignable portion and a reassignable portion which relates to the possessed subset of the set of computing resources which is possessed by the running virtual machine;

maintaining, with respect to both the first and second temporal periods, a coupled status of the unreassignable portion and the source hypervisor;

transferring, with respect to the first temporal period, the reassignable portion to a different set of computing resources which is coupled with the source hypervisor;

assigning, to the target hypervisor from the source hypervisor, the reassignable portion; and

running, using the target hypervisor, the running virtual machine using the reassignable portion.

2. The method of claim 1, further comprising:

transferring, to the target hypervisor from the source hypervisor, management of the running virtual machine without copying a set of running virtual machine data from a set of memory regions.

3. The method of claim 1, further comprising:

detecting that the running virtual machine is running across a plurality of nodes of the single multi-node server; and

transferring, to the target hypervisor from the source hypervisor, assignment of the possessed subset of the set of computing resources.

4. The method of claim 1, further comprising:

assembling, with respect to the first temporal period, a set of memory regions of a segment of a node coupled with the source hypervisor;

coupling, with respect to the second temporal period, the target hypervisor with the set of memory regions of the segment of the node; and

decoupling, with respect to the second temporal period, the source hypervisor with the set of memory regions of the segment of the node.

5. The method of claim 1, further comprising:

constructing, by the single service processor, a serial communication between the source and target hypervisors to send the set of scheduling-related control information for the running virtual machine from the source hypervisor to the target hypervisor when transferring the running virtual machine from the source hypervisor to the target hypervisor.

6. The method of claim 1, further comprising:

establishing the single multi-node server that includes;

a different virtual machine,

a first node having the set of computing resources that includes a different subset of the set of computing resources which is possessed by the different virtual machine with respect to the first temporal period, and

the source hypervisor which has the different virtual machine with respect to both the first and second temporal periods;

coupling, with respect to the first temporal period, the first node with the source hypervisor;

transferring, from the first node to a second node which is coupled with the source hypervisor, one or more elements of the different subset of the set of computing resources which is possessed by the different virtual machine; and

coupling, with respect to the second temporal period, the first node with the target hypervisor.

7. The method of claim 1, further comprising:

configuring, with respect to the set of computing resources, a set of floating node boundaries.

8. The method of claim 1, further comprising:

defragmenting, in advance of assigning the possessed subset of the set of computing resources which is possessed by the running virtual machine to the target hypervisor from the source hypervisor, at least a portion of the set of computing resources.

9. The method of claim 1, further comprising:

sensing, with respect to the source hypervisor, a resource transfer threshold; and

copying, to a set of target computing resources coupled with the target hypervisor, a remainder subset of the set of computing resources which is possessed by the running virtual machine.

10. The method of claim 1, further comprising:

sensing, with respect to the target hypervisor, a resource reception threshold; and

copying, to a set of target computing resources coupled with the target hypervisor, a remainder subset of the set of computing resources which is possessed by the running virtual machine.

11. The method of claim 1, further comprising:

copying, to a set of target computing resources coupled with the target hypervisor, less than one-hundred percent of a memory feature of the running virtual machine.

12. The method of claim 1, further comprising:

consolidating a plurality of virtual machines across a set of physical servers below a threshold number.

13. The method of claim 1, further comprising:

performing, in a dynamic fashion to streamline virtual machine management in the shared pool of configurable computing resources, each of;

the establishing, the assigning, and the running.

14. The method of claim 1, further comprising:

performing, in an automated fashion without user intervention, each of;

the establishing, the assigning, and the running.

15. The method of claim 1, further comprising:

transferring, to the target hypervisor from the source hypervisor, management of the running virtual machine without copying a set of running virtual machine data from a first set of memory regions;

detecting that the running virtual machine is running across a plurality of nodes of the single multi-node server;

transferring, to the target hypervisor from the source hypervisor, assignment of the possessed subset of the set of computing resources;

assembling, with respect to the first temporal period, a second set of memory regions of a segment of a node coupled with the source hypervisor;

coupling, with respect to the second temporal period, the target hypervisor with the second set of memory regions of the segment of the node;

decoupling, with respect to the second temporal period, the source hypervisor with the second set of memory regions of the segment of the node;

configuring, using a single service processor, both the source and target hypervisors;

communicating, via the single service processor, a set of scheduling-related control information for the running virtual machine from the source hypervisor to the target hypervisor;

constructing, by the single service processor, a serial communication between the source and target hypervisors to send the set of scheduling-related control information for the running virtual machine from the source hypervisor to the target hypervisor when transferring the running virtual machine from the source hypervisor to the target hypervisor.

16. A system for virtual machine management with respect to a shared pool of configurable computing resources, the system comprising:

a memory having a set of computer-readable computer instructions, and

a processor for executing the set of computer-readable instructions, the set of computer-readable instructions including;

establishing a single multi-node server that includes;

a running virtual machine,

a set of computing resources that includes a possessed subset of the set of computing resources which is possessed by the running virtual machine,

a source hypervisor which has the running virtual machine with respect to a first temporal period, wherein the source hypervisor is configured to manage the possessed subset of the set of computing resources, and

a target hypervisor to have the running virtual machine with respect to a second temporal period which is subsequent to the first temporal period, wherein the target hypervisor is configured to manage the possessed subset of the set of computing resources;

assigning, to the target hypervisor from the source hypervisor, the possessed subset of the set of computing resources which is possessed by the running virtual machine;

configuring, using a single service processor, both the source and target hypervisors;

communicating, via the single service processor, a set of scheduling-related control information for the running virtual machine from the source hypervisor to the target hypervisor; and

running, using the target hypervisor, the running virtual machine;

detecting, with respect to the first temporal period, that the set of computing resources includes both an unreassignable portion and a reassignable portion which relates to the possessed subset of the set of computing resources which is possessed by the running virtual machine;

maintaining, with respect to both the first and second temporal periods, a coupled status of the unreassignable portion and the source hypervisor;

transferring, with respect to the first temporal period, the reassignable portion to a different set of computing resources which is coupled with the source hypervisor;

assigning, to the target hypervisor from the source hypervisor, the reassignable portion; and

running, using the target hypervisor, the running virtual machine using the reassignable portion.

17. A computer program product for virtual machine management with respect to a shared pool of configurable computing resources, the computer program product comprising a computer-readable storage medium having program instructions embodied therewith, wherein the computer-readable storage medium is not a transitory signal per se, the program instructions executable by a processor to cause the processor to perform a method comprising:

establishing a single multi-node server that includes;

a running virtual machine,

a set of computing resources that includes a possessed subset of the set of computing resources which is possessed by the running virtual machine,

a source hypervisor which has the running virtual machine with respect to a first temporal period, wherein the source hypervisor is configured to manage the possessed subset of the set of computing resources, and

a target hypervisor to have the running virtual machine with respect to a second temporal period which is subsequent to the first temporal period, wherein the target hypervisor is configured to manage the possessed subset of the set of computing resources;

assigning, to the target hypervisor from the source hypervisor, the possessed subset of the set of computing resources which is possessed by the running virtual machine;

configuring, using a single service processor, both the source and target hypervisors;

communicating, via the single service processor, a set of scheduling-related control information for the running virtual machine from the source hypervisor to the target hypervisor; and

running, using the target hypervisor, the running virtual machine;

detecting, with respect to the first temporal period, that the set of computing resources includes both an unreassignable portion and a reassignable portion which relates to the possessed subset of the set of computing resources which is possessed by the running virtual machine;

maintaining, with respect to both the first and second temporal periods, a coupled status of the unreassignable portion and the source hypervisor;

transferring, with respect to the first temporal period, the reassignable portion to a different set of computing resources which is coupled with the source hypervisor;

assigning, to the target hypervisor from the source hypervisor, the reassignable portion; and

running, using the target hypervisor, the running virtual machine using the reassignable portion.