Augmented allocation of virtual machines for application

• US 9,600,316 B2
• Filed: 10/17/2012
• Issued: 03/21/2017
• Est. Priority Date: 10/17/2012
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Dournov, Pavel A., Samoylov, Denis, Ingle, Anil
• Primary Examiner(s): Bullock, Jr., Lewis A
• Assistant Examiner(s): KEPNANG, GILLES R
• Application Number:
  US13/654,062
• Publication Number:
  US 20140109088A1
• Time in Patent Office: 1,616 Days
• Field of Search: 718/1, 718/102, 718/104
• US Class Current: 1/1
• 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 8/61 Installation
• CPC Class Codes: G06F 9/44505 Configuring for program initiating, e.g. using registry, configuration files
• CPC Class Codes: G06F 9/45533 Hypervisors; Virtual machine monitors
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects

Abstract

The starting up of an application involving multiple virtual machines by overallocating virtual machines. In response to a request to allocate a certain number of virtual machines corresponding to the application, an augmented number of virtual machines is determined to be allocated in response to the request. The augmented number includes both the initially requested number of virtual machines in addition to a surplus number of virtual machines. The virtual machines are then initiated to start up if they are not already started up. Before all of the virtual machines are started up, code is bound to the virtual machines. Thus, because more virtual machines were initiated startup than are required for the application, the code may be bound to some of the virtual machines in the application before all of the virtual machine have started up.

Claims

1. A computer system, comprising:

one or more processors; and

one or more computer-readable hardware storage devices having stored thereon computer-executable instructions that are executable by the one or more processors to cause the computing system to start a plurality of virtual machines corresponding to an application, the computer-executable instructions including instructions that are executable to cause the computing system to perform at least the following;

access a request to allocate a requested number of virtual machines to an application, for executing a plurality of code portions of the application across the requested virtual machines;

determine that different sets of virtual machines are to be bound to different code portions of the application corresponding to different roles in the applications, including at least a first role having a first, higher, level of criticality to application functioning, and a second role having a second, lower, level of criticality to application functioning;

in response to the request, determine a number of virtual machines to allocate to the application, while taking into account the different roles, the number including the sum of;

a first requested number of virtual machines for the first role, plus a first additional number of virtual machines for the first role, wherein the first additional number is determined based on applying a first, higher, ratio identified based on the first, higher, level of criticality and;

a second requested number of virtual machines for the second role, plus a second additional number of virtual machines for the second role, wherein the second additional number is determined based on applying a second, lower, ratio identified based on the second, lower, level of criticality;

in response to the request, and prior to binding any code of the application to any of the requested virtual machines, allocate the determined number of virtual machines to the application, including causing a particular number of virtual machines to initiate start up across a set of one or more host computing systems, such that a sum of the particular number of virtual machines and any already started up virtual machines at the set of one or more host computing systems that are available for allocation to the application equals the determined number of virtual machines; and

after causing the particular number of virtual machines to initiate start up, and before all of the particular number of virtual machines have completed starting up, bind at least one of the one or more code portions to one or more of the allocated virtual machines that have completed starting up.

2. The computer system in accordance with claim 1, wherein the binding of code is performed by a binding engine that prioritizes binding of code to virtual machines according to which role that each virtual machine is to perform in the application.

3. The computer system in accordance with claim 1, wherein the binding of code comprises:

binding a first code portion to the first set of one or more virtual machines, to cause each of the virtual machines in the first set to perform the first role in the application; and

binding a second code portion to the second set of one or more virtual machines, to cause each of the virtual machines in the second set to perform the second role in the application.

4. The computer system in accordance with claim 3, wherein the binding of the first code portion and the binding of the second code portion are prioritized based on the first level of criticality and the second level of criticality.

5. The computer system in accordance with claim 1, wherein the requested number of virtual machines for the application includes a requested number of virtual machines of a first type and a requested number of virtual machines of a second type, and wherein the computer-executable instructions also include instructions that are executable to cause the computing system to perform at least the following:

determine a number of virtual machines of the second type to allocate in response to the request, the number of virtual machines of the second type including a sum of the requested number of virtual machines of the second type in addition to an additional number of virtual machines of the second type;

cause the number of virtual machines of the second type to initiate start up across the set of one or more host computing systems; and

after causing the number of virtual machines of the second type to initiate start up, and before all of the number of virtual machines of the second type are started up, bind code to started up virtual machines of the second type equal to the requested number of virtual machines of the second type.

6. The computer system in accordance with claim 5, wherein the binding of code to started up virtual machines of the second type is completed at a different time for at least one of the virtual machines of the second type than the binding of code to started up virtual machines of the first type for at least one of the virtual machines of the first type.

7. The computer system in accordance with claim 5, wherein the computer-executable instructions also include instructions that are executable to cause the computing system to perform at least the following:

determine a number of virtual machines of a third type to allocate in response to the request, the number of virtual machines of the third type including a sum of the requested number of virtual machines of the third type in addition to an additional number of virtual machines of the third type;

cause the augmented number of virtual machines of the third type to initiate start up across the set of one or more host computing systems; and

after causing the augmented number of virtual machines of the third type to initiate start up, and before all of the augmented number of virtual machines of the third type are started up, bind code to started up virtual machines of the third type equal to the requested number of virtual machines of the third type.

8. The computer system in accordance with claim 5, wherein all of the virtual machines of the first type are the same size.

9. The computer system in accordance with claim 5, wherein all of the virtual machines of the first type are bindable to in a common fault domain.

10. The computer system in accordance with claim 5, wherein all of the virtual machines of the first type are bindable to in a common update domain.

11. A method, implemented at a computer system that includes one or more processors, of starting a plurality of virtual machines corresponding to an application, the method comprising:

accessing a request to allocate a requested number of virtual machines to an application, for executing a plurality of code portions of the application across the requested virtual machines;

determining that different sets of virtual machines are to be bound to different code portions of the application corresponding to different roles of the application, including at least a first role having a first, higher, level of criticality to application functioning, and a second role having a second, lower, level of criticality to make the application functioning;

in response to the request, determining a number of virtual machines to allocate to the application, while taking into account the different roles, the number including the sum of;

a first requested number of virtual machines for the first role, plus a first additional number of virtual machines for the first role, the first additional number being determined based on applying a first, higher, ratio identified based on the first, higher, level of criticality; and

a second requested number of virtual machines for the second role, plus a second additional number of virtual machines for the second role, the second additional number being determined based on applying a second, lower, ratio identified based on the second, lower, level of criticality;

in response to the request, and prior to binding any code of the application to any of the requested virtual machines, allocating the determined number of virtual machines to the application, including causing the augmented number of virtual machines to initiate start up across a set of one or more host computing systems; and

after causing the determined number of virtual machines to initiate start up, and before all of the determined number of virtual machines have competed starting up, binding at least one of the one or more code portions to one or more of the allocated virtual machines that have completed starting up.

12. The method in accordance with claim 11, wherein the method is performed in a cloud computing environment by a service fabric that is connected to a plurality of host computing systems including the set of one or more host computing systems.

13. The method in accordance with claim 11, wherein the binding of code is performed by prioritizing in time the binding of code to virtual machines according to which role that each virtual machine is to perform in the application.

14. The method in accordance with claim 11, wherein the requested number of virtual machines for the application includes a requested number of virtual machines of a first type and a requested number of virtual machines of a second type, the method further comprising:

determining a number of virtual machines of the second type to allocate in response to the request, the number of virtual machines of the second type including a sum of the requested number of virtual machines of the second type in addition to an additional number of virtual machines of the second type;

causing the determined number of virtual machines of the second type to initiate start up across the set of one or more host computing systems; and

after causing the determined number of virtual machines of the second type to initiate start up, and before all of the determined number of virtual machines of the second type are started up, binding code to started up virtual machines of the second type equal to the requested number of virtual machines of the second type.

15. The method in accordance with claim 11, further comprising:

detecting one or more excess virtual machines of the number of virtual machines that are started up beyond the requested number of virtual machines.

16. The method in accordance with claim 15, wherein the request is a first request, and the application is a first application, the method further comprising:

accessing a second request to run a second application; and

using the detected excess one or more virtual machines that were initially started up in response to the first request to instead operate a role in the second application.

17. A computer program product comprising one or more computer-readable hardware storage devices having stored thereon computer-executable instructions that are executable by one or more hardware processors of a computer system to cause the computer system to start a plurality of virtual machines corresponding to an application, the computer-executable instructions including instructions that are executable to cause the computing system to perform at least the following:

receive a request to allocate a requested number of virtual machines to an application, for executing a plurality of code portions of the application across the requested virtual machines;

determine that different sets of virtual machines are to be bound to different code portions of the application corresponding to different roles of the application, including at least a first role having a first, higher, level of criticality to application functioning, and a second role having a second, lower, level of criticality to application functioning;

based on attributes of the application, calculate a number of virtual machines to allocate to the application, while taking into account the first and second roles, the number including the sum of;

a first requested number of virtual machines for the first role, plus a first additional number of virtual machines for the first role, wherein the first additional number is determined based on applying a first, higher, ratio identified based on the first, higher, level of criticality; and

a second requested number of virtual machines for the second role, plus a second additional number of virtual machines for the second role, wherein the second additional number is determined based on applying a second, lower, ratio identified based on the second, lower, level of criticality;

prior to binding any code of the application to any of the requested virtual machines, allocating the calculated number of virtual machines to the application, including causing the calculated number of virtual machines to initiate start up across a set of one or more host computing systems; and

after causing the calculated number of virtual machines to initiate start up, and before all of the calculated number of virtual machines have competed starting up, binding at least one of the one or more code portions to one or more of the allocated virtual machines that have completed starting up.

18. The computer program product in accordance with claim 17, wherein the binding of code is performed by prioritizing in time the binding of code to virtual machines according to which role that each virtual machine is to perform in the application.

19. The computer program product in accordance with claim 18, wherein the binding of code comprises:

binding a first code portion to the first set of one or more virtual machines, to cause each of the virtual machines in the first set to perform the first role in the application; and

binding a second code portion to the second set of one or more virtual machines, to cause each of the virtual machines in the second set to perform the second role in the application.