Automatic scaling of at least one user application to external clouds

Patent metadata

Field	Value
Publication number	US-9871745-B2
Application number	US-201414539543-A
Country	US
Kind code	B2
Filing date	Nov 12, 2014
Priority date	Nov 12, 2014
Publication date	Jan 16, 2018
Grant date	Jan 16, 2018

Abstract

Embodiments of the invention provide a method, a system and a computer program product configured to automatically auto-scale a user compute instance to multiple cloud providers while considering a multiplicity of user requirements. The method, executed on a digital data processor, includes obtaining information, via a user interface, that is descriptive of user cloud computing related preferences, including a user cloud computing budgetary preference. The method further includes sensing properties of a plurality of clouds and making decisions, based at least on the obtained information and on the sensed properties, of when to scale up or scale down the user cloud instance, of selecting one of the plurality of clouds as where to scale the user cloud instance, and determining which resource or resources of the selected cloud to add or remove from the selected cloud. The method further includes automatically executing the decisions on the selected cloud.

First claim

What is claimed is:

1. A method executed at least in part by a digital data processor, comprising:
obtaining information, via a user interface, that is descriptive of user cloud computing related preferences, wherein the user cloud computing related preferences comprises at least a user cloud computing budgetary preference, a location preference, a performance preference, and a reliability level preference, and wherein obtaining the information further comprises obtaining indications on whether each of the user cloud computing related preferences is either required or preferred;
sensing properties of a plurality of clouds including at least reliability, cost, security, location, performance and infrastructure properties, wherein the sensed cost and infrastructure properties are obtained directly from a cloud provider via an application program interface of the cloud provider, and wherein the reliability, security, and performance properties are obtained at least in part based on one or more historical records of application deployments in each of the plurality of clouds;
making decisions, based at least on the obtained information and on the sensed properties of the plurality of clouds, of when to scale up or scale down a user cloud instance, of selecting one of the plurality of clouds as where to scale the user cloud instance, and determining which resource or resources of the selected cloud to add or remove from the selected cloud; where
in response to detecting a presence of a trigger to perform a user cloud instance scale up operation, solving a first optimization problem to select where to scale up the user cloud instance by selecting one of the plurality of clouds to add the user cloud instance to and then solving a second optimization problem to select which resource or resources in the selected cloud to add the user cloud instance to, where the selected resource or resources comprise at least one of memory, communication adapters and operating system, wherein selecting one of the plurality of clouds to add comprises generating a requirement satisfaction vector for each of the user cloud computing related preferences comprising binary values indicating whether each of the plurality of clouds satisfy a given one of the user cloud computing related preferences, and selecting the cloud based on both the requirement satisfaction vectors and the obtained indications on whether each of the user cloud computing related preferences is either required or preferred; and
automatically executing the decisions on the selected cloud.

2. The method of claim 1 , where the user's cloud instance is being executed on a private cloud when the decisions are executed, and where the selected cloud is a public cloud.

3. The method of claim 1 , where the obtained information descriptive of user cloud computing related preferences comprises a latency preference, in addition to the user cloud computing budgetary preference, location preference reliability level preference, and performance preference.

4. The method of claim 1 , where the obtained information is further descriptive of a user objective preference as to a certain cloud provider or cloud providers.

5. The method of claim 1 , where the step of making decisions is automatically triggered by at least a change in a user application instance so as to require more cloud resources or less cloud resources.

6. The method of claim 1 , comprising in response to the presence of the trigger initially determining whether the trigger is to scale up or scale down the user cloud instance, where in response to determining that the trigger is to scale up the user cloud instance, determining if there exists a user-defined objective preference and, if the objective preference is determined to exist, then solving the first optimization problem and the second optimization problem.

7. The method of claim 6 , where if it is determined that the user-defined objective preference does not exist, the method further comprises attempting to find a feasible solution by selecting a suitable cloud to add the user cloud instance to and selecting a suitable resource in the selected cloud for adding the user cloud instance to; and
if no feasible solution can be found for selecting either a suitable cloud or a suitable resource in a selected cloud, informing the user.

8. The method of claim 1 , comprising in response to the presence of the trigger initially determining whether the trigger is to scale up or scale down the user cloud instance, where in response to determining that the trigger is to scale down the user cloud instance, determining if there exists a user-defined objective preference and, if the objective preference is determined to exist, then solving a first optimization problem to select where to scale down the user cloud instance by selecting one of the plurality of clouds to remove the user cloud instance from and then solving a second optimization problem to select which resource or resources in the selected cloud to remove the user cloud instance from.

9. The method of claim 8 , where if it is determined that the user-defined objective preference does not exist, the method further comprises attempting to find a feasible solution by selecting a suitable cloud to remove the user cloud instance from and selecting a suitable resource in the selected cloud to remove the user cloud instance from; and
if no feasible solution can be found for selecting either a suitable cloud or a suitable resource in a selected cloud, informing the user.

10. A method executed at least in part by a digital data processor, comprising:
obtaining information, via a user interface, that is descriptive of user cloud computing related preferences, wherein the user cloud computing related preferences comprises at least a user cloud computing budgetary preference, a location preference, a performance preference, and a reliability level preference, and wherein obtaining the information further comprises obtaining indications on whether each of the user cloud computing related preferences is either required or preferred;
sensing properties of a plurality of clouds including at least reliability, cost, security, location, performance, and infrastructure properties, wherein the sensed cost and infrastructure properties are obtained directly from a cloud provider via an application program interface of the cloud provider, and wherein the reliability, security, and performance properties are obtained at least in part based on one or more historical records of application deployments in each of the plurality of clouds;
making decisions, based at least on the obtained information and on the sensed properties of the plurality of clouds, of when to scale up or scale down a user cloud instance, of selecting one of the plurality of clouds as where to scale the user cloud instance, and determining which resource or resources of the selected cloud to add or remove from the selected cloud, wherein selecting one of the plurality of clouds to add comprises generating a requirement satisfaction vector for each of the user cloud computing related preferences comprising binary values indicating whether each of the plurality of clouds satisfy a given one of the user cloud computing related preferences, and selecting the cloud based on both the requirement satisfaction vectors and the obtained indications on whether each of the user cloud computing related preferences is either required or preferred; and
automatically executing the decisions on the selected cloud;
where in response to the presence of a trigger that is automatically generated by at least a change in a user application instance so as to require more cloud resources or less cloud resources, t

Assignees

• IBM

Inventors

• Steinder Malgorzata
• Unuvar Merve

Classifications

• G06Q10/063 Primary

  Operations research, analysis or management · CPC title

• H04L67/16

  Electricity · mapped topic

• H04L67/10

  in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title

• H04L47/783 Primary

  Distributed allocation of resources, e.g. bandwidth brokers · CPC title

• H04L67/51

  Discovery or management thereof, e.g. service location protocol [SLP] or web services · CPC title