Virtual machine placement in a cloud computing environment based on factors including optimized processor-memory affinity

Abstract

Optimized placement of virtual machines in a cloud environment is based on factors that include processor-memory affinity. A smart migration mechanism (SMM) predicts an optimization score for multiple permutations of placing virtual machines on a target system to create an optimal move list. The optimization score is a theoretical score calculated using dynamic platform optimization (DPO). The SMM may allow the user to set initial parameters and change the parameters to create potential changes lists. The move lists are ranked to allow the user to select the optimal change list to provide the best affinity, quickest fulfillment of requirements and least disruption for a given set of parameters.

Description

BACKGROUND[0001]1. Technical Field[0002]This invention generally relates to cloud computing systems, and more specifically relates to placing virtual machines in a cloud environment based on factors that include optimized processor-memory affinity.[0003]2. Background Art[0004]Cloud computing is a common expression for distributed computing over a network and can also be used with reference to network-based services such as Infrastructure as a Service (IaaS). IaaS is a cloud based service that provides physical processing resources to run virtual machines (VMs) as a guest for different customers. The virtual machine may host a user application or a server.[0005]It is often necessary or desirable to migrate workload in one computer system (a source) to another computer system (a target). Often, workload migration takes the form of migrating one or more virtual machines (sometimes referred to as logical partitions) from the source to the target, the migrated virtual machine's workload ...

AI Technical Summary

Benefits of technology

This patent describes an apparatus and method for optimizing the placement of virtual machines in a cloud computing environment. It uses a smart migration mechanism to predict the best move for multiple virtual machines based on their processor-memory affinity. Users can set initial parameters and change them to create potential changes lists, which are ranked to provide the best option for achieving quickest fulfillment of requirements and least disruption for a given set of parameters. Overall, this patent enables efficient placement of virtual machines in a cloud computing environment for better performance and efficiency.

Problems solved by technology

Physically, many large server systems are designed as systems having a non-uniform memory access in which multiple processors and main memory are physically distributed, so that each processor has some portion of main memory which is in closer physical proximity (and is accessed faster) than other portions of main memory.

Images