Browse Prior Art Database

Method to Optimize Standby Virtual Image Utilization with Balanced Workload Popularity and Priority

IP.com Disclosure Number: IPCOM000213908D
Publication Date: 2012-Jan-05
Document File: 3 page(s) / 36K

Publishing Venue

The IP.com Prior Art Database

Abstract

Disclosed is a novel process to solve the problem of maintaining standby virtual image diversity vs. cloud resource conservation. The approach enables the cloud resource to be efficiently managed while improving deployment (i.e., new, scaling and recovery) times for the largest number of user workload deployments.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 51% of the total text.

Page 01 of 3

Method to Optimize Standby Virtual Image Utilization with Balanced Workload Popularity and Priority

Deployment of a virtual image can be optimized if the cloud management platform maintains a group of "hot standby" images. Since users have different requirements when requesting cloud resources, care must be taken to ensure the contents match user needs. Taking full advantage of hot standby images requires a diverse group of base virtual images (e.g., virtual image resource size, operating system type, products on virtual image) to match diverse user requirements. The greater number of distinct types of images, the higher the probability a user will request a matching image.

On the other hand, it is important to conserve resources (e.g., memory, Central Processing Unit (CPU), bandwidth, storage, etc.) in the cloud. The standby virtual images consume valuable cloud resources specifically to speed up deployments (i.e., new, scaling, and recovery) time, so there is a need to only insert images that are most likely to be requested by the user. While it is costly to maintain these standby images, if they are not diverse enough they might not improve the deployment times for the popular and priority workloads.

There is a need to establish a balance between the amount of resources used by the standby virtual images and providing a diverse enough group to optimize the deployment time of popular and priority workloads.

This invention defines a novel process to solve the problem of maintaining standby virtual image diversity vs. cloud resource conservation. The cloud management platform's unique knowledge of user workload activity is leveraged to predict future deployment requests. The virtual image mixture is a design based on the current deployment information and modeled solutions to increase the probability for popular and priority deployments to match the base virtual images. This approach enables...