Cloud Placement Module for VM Affinity and Anti-Affinity Constraints

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In distributed computer systems, effectively placing resource-consuming clients like virtual machines (VMs) while satisfying conflicting constraints such as affinity and anti-affinity requirements is challenging, as it requires balancing resource utilization and communication overhead.

Innovation Solution

A cloud management server employs a cloud placement module to select affinity and anti-affinity clusters by filtering out incompatible clusters, ensuring that VMs with affinity constraints are placed together and those with anti-affinity constraints are separated across different clusters, using a cloud placement engine that executes program instructions to optimize placement based on resource utilization metrics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of energy

If VMs are placed together on a cluster to reduce communication overhead, then communication efficiency is improved, but resource availability and system reliability deteriorate due to lack of separation

Engineering Contradiction:

Improvecommunication overheadVSAvoidresource availability

Core Design Contradiction:

Loss of energyVSReliability

Solution Approach 1:

The system segments VMs into different placement groups based on their constraint requirements. Affinity-constrained VMs are placed together in the same cluster to reduce communication overhead, while anti-affinity-constrained VMs are placed in different clusters to ensure resource availability and reliability. This segmentation allows simultaneous optimization of both communication efficiency and system reliability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system changes the placement parameter (cluster assignment) based on the type of constraint. For affinity constraints, the parameter change groups VMs together; for anti-affinity constraints, the parameter change separates VMs across clusters. This dynamic parameter adjustment resolves the contradiction by adapting placement strategy to specific constraint requirements.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If VMs are separated onto different clusters to increase resource availability, then reliability is improved, but communication overhead increases due to distributed placement

Engineering Contradiction:

Improveresource availabilityVSAvoidcommunication overhead

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

Inventive Principle:

Principle #1Segmentation

3Loss of energy

If placement strategy prioritizes affinity constraints, then communication efficiency is improved, but ability to satisfy anti-affinity constraints deteriorates

Engineering Contradiction:

Improvecommunication overheadVSAvoidconstraint satisfaction capability

Core Design Contradiction:

Loss of energyVSAdaptability or versatility

Solution Approach 1:

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system uses feedback from constraint analysis to adjust placement decisions. By evaluating both affinity and anti-affinity constraints during the placement process, the system can make informed decisions that satisfy multiple constraints simultaneously, improving overall adaptability while maintaining communication efficiency where applicable.

Inventive Principle:

Principle #23Feedback

4Reliability

If placement strategy prioritizes anti-affinity constraints, then resource availability is improved, but communication efficiency deteriorates due to separated placement

Engineering Contradiction:

Improveresource availabilityVSAvoidcommunication overhead

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

Inventive Principle:

Principle #35Parameter changes

5Ease of operation

If automated placement algorithm is simplified, then ease of operation is improved, but ability to satisfy multiple conflicting constraints deteriorates

Engineering Contradiction:

Improveplacement automationVSAvoidconstraint satisfaction capability

Core Design Contradiction:

Ease of operationVSAdaptability or versatility

Solution Approach 1:

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11595260B2Automatic placement of clients in a distributed computer system satisfying constraints

Publication Date: 2023.02.28 VMWARE INC

AI summary

A cloud management server and method for performing automatic placement of clients in a distributed computer system uses a list of compatible clusters to select an affinity cluster to place the clients associated with an affinity constraint. As part of the placement method, a cluster that cannot satisfy any anti-affinity constraint associated with the clients and the affinity constrain is removed from the list of compatible clusters. After the affinity cluster has been selected, at least one cluster in the distributed computer system is also selected to place clients associated with an anti-affinity constraint.