Virtual machine placement

• US 10,365,943 B2
• Filed: 01/27/2015
• Issued: 07/30/2019
• Est. Priority Date: 01/27/2015
• Status: Active Grant

• Current Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Original Assignee: Hewlett Packard Enterprise Development LP (Hewlett-Packard Enterprise Company)
• Inventors: Voigt, Douglas L., Grumm, Scott
• Primary Examiner(s): Swift, Charles M
• Application Number:
  US15/507,651
• Publication Number:
  US 20170286146A1
• Time in Patent Office: 1,645 Days
• CPC Class Codes: G06F 1/266 Arrangements to supply power to external peripherals either directly from the computer or under computer control, e.g. supply of power through the communication port, computer controlled power-strips
• CPC Class Codes: G06F 2009/45562 Creating, deleting, cloning virtual machine instances
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 2009/45575 Starting, stopping, suspending or resuming virtual machine instances
• CPC Class Codes: G06F 2009/45583 Memory management, e.g. access or allocation
• CPC Class Codes: G06F 2009/45591 Monitoring or debugging support
• CPC Class Codes: G06F 2009/45595 Network integration; Enabling network access in virtual machine instances
• CPC Class Codes: G06F 9/455 Emulation; Interpretation; Software simulation, e.g. virtualisation or emulation of application or operating system execution engines
• CPC Class Codes: G06F 9/45533 Hypervisors; Virtual machine monitors
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: G06F 9/48 Program initiating; Program switching, e.g. by interrupt
• CPC Class Codes: G06F 9/4806 Task transfer initiation or dispatching
• CPC Class Codes: G06F 9/4843 by program, e.g. task dispatcher, supervisor, operating system
• CPC Class Codes: G06F 9/485 Task life-cycle, e.g. stopping, restarting, resuming execution G06F9/4881 takes precedence
• CPC Class Codes: G06F 9/4856 resumption being on a different machine, e.g. task migration, virtual machine migration G06F9/5088 takes precedence
• CPC Class Codes: G06F 9/4881 Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
• CPC Class Codes: G06F 9/50 Allocation of resources, e.g. of the central processing unit [CPU]
• CPC Class Codes: G06F 9/5005 to service a request
• CPC Class Codes: G06F 9/5027 the resource being a machine, e.g. CPUs, Servers, Terminals
• CPC Class Codes: G06F 9/505 considering the load
• 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
• CPC Class Codes: G06F 9/5083 : Techniques for rebalancing the load in a distributed system
• CPC Class Codes: G06F 9/5088 : involving task migration

Abstract

Example implementations relate to defining a first placement plan to place virtual storage appliance virtual machines on servers and defining a second placement plan to place an application virtual machine on the servers. The first placement plan can place each virtual storage appliance virtual machine on a server that is connected to a storage asset used by a respective VSA virtual machine.

Claims

1. A method comprising:

defining a first placement plan by placing each virtual storage appliance (VSA) virtual machine of a plurality of VSA virtual machines on a server of a plurality of servers that is connected to a storage asset used by the each VSA virtual machine to support a storage cluster, placing VSA virtual machines supporting a same storage cluster on different servers of the plurality of servers, and placing the plurality of VSA virtual machines on servers with virtual machines before servers without virtual machines;

defining a second placement plan by placing an application virtual machine on a server of the plurality of servers that has available utilization capacity for the application virtual machine and has virtual machines in preference over servers without virtual machines; and

deploying the plurality of VSA virtual machines and the application virtual machine according to the first placement plan and the second placement plan, respectively.

2. The method of claim 1, wherein the defining the first placement plan is performed prior to the defining the second placement plan.

3. The method of claim 1, further comprising reducing a power usage of a first subset of the plurality of servers,

wherein the deploying includes migrating at least some of the plurality of VSA virtual machines or the application virtual machine from the first subset of the plurality of servers to a second subset of the plurality of servers.

4. The method of claim 1, further comprising:

determining a server utilization of each VSA virtual machines;

determining a server utilization of the application virtual machine; and

determining a maximum utilization capacity of each server of the plurality of servers.

5. The method of claim 4, wherein the defining the first placement plan and the defining the second placement plan each include a rule that limits a total server utilization of each server to less than or equal to a maximum utilization capacity of the each server.

6. The method of claim 1, wherein each server of the plurality of servers has a maximum storage cluster utilization,

the server utilization of each of the VSA virtual machines supporting the same storage cluster varies inversely with a number of the VSA virtual machines supporting the same storage cluster, and

the number of the VSA virtual machines supporting the same storage cluster is adjusted between a minimum for fault tolerance and a maximum by the defining the first placement plan so that a respective maximum storage cluster utilization is satisfied for at least one server of the plurality of servers.

7. The method of claim 1, wherein the defining the first placement plan places a VSA virtual machine with a single server placement option prior to placing a VSA virtual machine with a multiple server placement options, wherein the VSA virtual machine with the single server placement option uses a storage asset connected to a single server and the VSA virtual machine with multiple server placement options uses a storage asset connected to multiple servers.

8. The method of claim 1, wherein the application virtual machine is one of a plurality of application virtual machines,

the defining the second placement plan places each application virtual machine of the plurality of application virtual machines in turn by decreasing order of server utilizations of the plurality of application virtual machines, and

the defining the second placement plan places each application virtual machine on a server associated with a storage cluster used by the each application virtual machine if the server associated with the storage cluster used by the each application virtual machine has available utilization capacity for the each application virtual machine, or else places the each application virtual machine on a server having a highest utilization capacity among the plurality of servers and has at least one other virtual machine.

9. The method of claim 1, further comprising:

monitoring for changes of the plurality of VSA virtual machines or the application virtual machine,

redefining the first placement plan or the second placement plan based on the changes, and

deploying the plurality of VSA virtual machines and the application virtual machine according to the redefined first placement plan or the redefined second placement plan.

10. An apparatus comprising:

a processing resource;

a non-transitory machine readable medium storing instructions that, when executed, cause the processing resource to;

define a first placement plan that includes placement of;

each virtual storage appliance (VSA) virtual machine of a plurality of VSA virtual machines on a server, of a plurality of servers, that is connected to a storage asset, of a plurality of storage assets, used by the each VSA virtual machine,

VSA virtual machines supporting a same storage cluster on different servers, and

each VSA virtual machine on servers with virtual machines in favor of servers without virtual machines;

define a second placement plan that includes placement of;

each application virtual machine of a plurality of application virtual machines on the plurality of servers, in turn by decreasing order of server utilizations of the application virtual machines, and

each application virtual machine on servers with virtual machines in favor of servers without virtual machines,

apply server utilization rules to the first placement plan and the second placement plan; and

deploy the plurality of VSA virtual machines and the plurality of application virtual machines on the servers according to the first placement plan and the second placement plan, respectively.

11. The apparatus of claim 10, wherein the planner module defines the second placement plan to place each of the application virtual machines on a server associated with a storage cluster used by the each application virtual machine if the server associated with the storage cluster used by the each application virtual machine has available utilization capacity for the each application virtual machine, or else to place the each application virtual machine on a server having a highest utilization capacity among the plurality of servers and has at least one other virtual machine.

12. The apparatus of claim 10, further comprising a utilization determination module to:

determine a server utilization of each VSA virtual machine;

determine a server utilization of each application virtual machine;

determine a maximum utilization capacity of each server of the plurality of servers; and

normalize the maximum utilization capacity of each of the plurality of servers, the server utilization of each of the plurality of VSA virtual machines, and the server utilization of the appliance virtual machine by a lowest maximum utilization capacity of the plurality of servers,

wherein the server utilization rules are based on the normalized maximum utilization capacity of each of the plurality of servers and a maximum storage cluster utilization of each of the plurality of servers.

13. The apparatus of claim 10, further comprising:

a power reduction module to reduce a power usage of a subset of servers; and

a monitor module to;

monitor for a change of the plurality of VSA virtual machines, the plurality of application virtual machines, or the plurality of servers, and

redefine the first placement plan or the second placement plan based on the change.

14. The apparatus of claim 10, wherein at least one server of the plurality of servers has a maximum storage cluster utilization that is a limitation on a sum of server utilizations attributable to VSA virtual machines placed on the at least one server.

15. The apparatus of claim 10, wherein the instructions that cause the processing resource to define the first placement plan includes adjusting a number of VSA virtual machines supporting a particular storage cluster between a minimum number associated with fault tolerance and a maximum number, wherein one of the VSA virtual machines supporting the particular storage cluster is placed on the at least one server and the adjusting causes a server utilization of the one of the VSA virtual machines to comply with the maximum storage cluster utilization of the at least one server.

16. The apparatus of claim 15, wherein the server utilization of the one of the VSA virtual machines varies inversely with the number of VSA virtual machines supporting the particular storage cluster.

17. A non-transitory machine readable medium encoded storing instructions that, when executed by a processor of a processor-based system, cause the processor-based system to:

define one placement plan that places each virtual storage appliance (VSA) virtual machine of a plurality of VSA virtual machines on a server that is connected to a storage asset used by the each VSA virtual machine, that places each VSA virtual machines associated with a same storage cluster on different servers, and that places VSA virtual machines in favor of servers with at least one virtual machine over servers without virtual machines; and

define another placement plan that places each of a plurality of application virtual machines on a server associated with a storage cluster used by the each application virtual machine if the server associated with the storage cluster has available utilization capacity, or else places the application virtual machines in turn by decreasing order of respective server utilizations on a server having available utilization capacity.

18. The non-transitory machine readable medium of claim 17, further comprising instructions that, when executed by the processor, cause the processor-based system to:

deploy the plurality of VSA virtual machines and the plurality of application virtual machines according to the one placement plan and the another placement plan, respectively;

detect changes to the plurality of VSA virtual machines or the plurality of application virtual machines; and

define at least one redefined placement plan in response to the changes.

19. The non-transitory machine readable medium of claim 17, further comprising instructions that, when executed by the processor, cause the processor-based system to:

adjust a number of the VSA virtual machines associated with the same storage cluster between a minimum number associated with fault tolerance and a maximum number to cause a server utilization of each of the VSA virtual machines associated with the same storage cluster to comply with maximum storage cluster utilizations of the different servers, wherein the server utilization of each of the VSA virtual machines associated with the same storage cluster varying inversely with the number of the VSA virtual machines.