Pattern-Based Workload Migration via Discovery and Residual Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current workload migration across computer systems is labor-intensive and costly, primarily based on lifting and shifting code images, making it expensive and a major hurdle for adopting cloud computing, regardless of whether the target environment is on-premise or off-premise.
Innovation Solution
A pattern-based migration approach that uses a discovery engine to identify metadata, a decision system to determine the suitability of pattern-based deployment, and a residual migration system to deploy undiscovered components via image-based migration, reducing costs and complexity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If image-based workload migration is used, then workload can be migrated from source to target, but the process becomes labor-intensive and expensive
Solution Approach 1:
The patent replaces manual image-based migration processes with an automated pattern recognition and matching system. The discovery engine automatically analyzes source workload components and their relationships, the pattern catalog provides pre-defined deployment patterns, and the decision system automatically determines migration strategies, substituting manual mechanical processes with automated intelligent systems.
Solution Approach 2:
The patent transforms the migration approach by changing key parameters: from treating workloads as monolithic images to decomposing them into individual components with attributes; from direct copying to pattern-based reconstruction; from manual execution to automated decision-making based on component analysis and pattern matching.
2Productivity
If pattern-based migration is implemented, then time and labor are saved, but the system complexity increases due to multiple components
Solution Approach 1:
The patent segments the migration system into distinct functional modules: a discovery engine that analyzes source workloads, a pattern catalog that stores deployment patterns, a decision system that selects migration strategies, and a residual migration system that handles remaining components. This segmentation enables parallel processing and specialized optimization of each component, improving overall migration speed despite the increased number of system elements.
3Measurement precision
If complete component discovery is performed, then migration accuracy improves, but the discovery process becomes more time-consuming
Solution Approach 1:
The patent implements a two-phase discovery approach: the primary discovery engine performs comprehensive analysis of critical workload components to ensure high accuracy, while the residual migration system performs a secondary pass to handle any remaining undiscovered components. This partial repetition ensures complete accuracy without requiring the entire system to operate at maximum detail level simultaneously, balancing precision with time efficiency.
Data Source
AI summary
Apparatus for pattern-based migration of a source workload to a target workload at a target deployment which includes a discovery engine, a decision system, a deployment manager, a pattern deployment engine and a residual migration and remediation system. The discovery engine takes the source deployment as an input and discovers metadata associated with the deployed components of the source workload and the IT topology. The deployment manager in cooperation with the pattern deployment engine at the target determines a closest starting-point template to be used for pattern-based target workload deployment. The decision system receives the metadata from the discovery engine and in cooperation with the deployment manager makes a go or no-go decision whether to trigger pattern-based target workload. The residual migration and remediation system finds any undiscovered source workload components and deploys the undiscovered workload components to the target deployment by an image-based migration.