Container Migration Using Vitality Metrics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Migrating applications from one node cluster to another is time-consuming and resource-intensive, often resulting in unnecessary instances being migrated, leading to inefficiencies and potential catastrophic failures during scaling down, which can cause downtime and waste resources.

Innovation Solution

Monitoring vitality metrics to determine the optimal number of application instances, disabling horizontal scaling during migration, and scaling down applications until they reach a dead state before migrating them to a new cluster, where they are then scaled up and optimized for the new hardware architecture.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If applications are migrated from one node cluster to another, then applications can be reallocated to update hardware or meet workload demands, but migration is time-consuming and resource-intensive

Engineering Contradiction:

Improveability to reallocate resources and update hardwareVSAvoidmigration time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The system performs preliminary scaling down of applications to the minimum necessary instances before migration begins. By using vitality metrics to determine the optimal reduced scale, the system prepares applications in advance so that fewer instances need to be migrated, thereby reducing migration time and resource consumption while still maintaining adequate service capacity.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If applications are scaled down during migration, then resource utilization improves, but scaling down can cause downtime and catastrophic failures

Engineering Contradiction:

Improveresource utilization efficiencyVSAvoidapplication availability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system continuously monitors vitality metrics during the scaling down process to provide feedback on application health and performance. This feedback mechanism allows the system to detect when scaling down is approaching unsafe thresholds, enabling corrective actions to be taken before catastrophic failures occur, thus maintaining reliability while improving resource utilization.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary scaling down to a carefully calculated minimum number of instances that maintains application stability. By using vitality metrics to determine this optimal point in advance, the system reduces resource consumption while preventing the application from being scaled down too far, which would cause downtime or failures.

Inventive Principle:

Principle #10Preliminary action

3Reliability

If all application instances are migrated to the new cluster, then complete application functionality is maintained, but unnecessary instances are migrated wasting resources

Engineering Contradiction:

Improveapplication functionalityVSAvoidmigration resource consumption

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system extracts and removes unnecessary application instances from the migration process by determining the minimum number of instances required to maintain application functionality. Using vitality metrics, the system identifies and eliminates redundant instances before migration, so only the essential instances are migrated to the new cluster, reducing resource consumption while maintaining complete application functionality.

Inventive Principle:

Principle #2Taking out (Extraction)

4Adaptability or versatility

If horizontal scaling is enabled during migration, then applications can automatically adapt to workload changes, but scaling operations during migration can cause instability

Engineering Contradiction:

Improveautomatic workload adaptationVSAvoidmigration stability

Core Design Contradiction:

Adaptability or versatilityVSStability of the object's composition

Solution Approach 1:

The system performs preliminary scaling operations and determines the optimal instance count before migration begins. By establishing the target scale in advance using vitality metrics, the system prevents automatic scaling operations from occurring during the actual migration process, thereby maintaining migration stability while still allowing applications to adapt to workload changes after migration is complete.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11579935B2Merging scaled-down container clusters using vitality metrics

Publication Date: 2023.02.14 RED HAT LLC

AI summary

A system for container migration includes containers running instances of an application running on a cluster, an orchestrator with a controller, a memory, and a processor in communication with the memory. The processor executes to monitor a vitality metric of the application. The vitality metric indicates that the application is in either a live state or a dead state. Additionally, horizontal scaling for the application is disabled and the application is scaled-down until the vitality metric indicates that the application is in the dead state. Responsive to the vitality metric indicating that the application is in the dead state, the application is scaled-up until the vitality metric indicates that the application is in the live state. Also, responsive to the vitality metric indication transitioning from the dead state to the live state, the application is migrated to a different cluster while the horizontal scaling of the application is disabled.