Data Migration Placement Tool for Storage Tiering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data migration to application-defined infrastructure faces challenges due to a lack of knowledge about data access patterns and ideal storage configurations, leading to inefficient data placement and performance optimization.
Innovation Solution
A migration data placement tool that uses analytics to classify data as hot, warm, or cold based on access patterns and migrates it to appropriate storage tiers using a centralized key-value store and event-driven index infrastructure, enabling optimal data tiering and multi-tenant aware migration.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is migrated to application-defined infrastructure without access pattern analysis, then migration can be performed, but data placement efficiency deteriorates
Solution Approach 1:
The system performs preliminary analysis of data access patterns before migration by monitoring events from source storage systems. This preliminary action captures information about which data is frequently accessed (hot), moderately accessed (warm), or rarely accessed (cold), enabling informed placement decisions before the actual migration occurs.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring data access events from storage systems and using this information to dynamically adjust data placement strategies. The analytics engine processes event streams and provides feedback on optimal placement decisions, which are then applied during migration and ongoing data management.
2Reliability
If traditional data migration methods are used, then migration can be completed, but I/O performance optimization deteriorates
Solution Approach 1:
The system applies local quality by placing different types of data in different storage locations based on their specific access characteristics. Hot data is placed in high-performance storage tiers with fast I/O capabilities, while cold data is placed in lower-cost, lower-performance storage. This ensures that each data subset receives the appropriate performance characteristics for its access pattern.
3Ease of operation
If manual data placement strategies are used, then data can be organized, but automation level deteriorates
Solution Approach 1:
The system implements self-service by automatically monitoring data access patterns, analyzing event streams, determining optimal placement strategies, and executing migration decisions without manual intervention. The analytics engine and migration system work autonomously to organize data based on observed access patterns, eliminating the need for manual data organization while maintaining high levels of automation.
Data Source
AI summary
Embodiments for using a migration data placement tool between storage systems based on data access by a processor. Events from a plurality of heterogeneous storage systems may be indexed into a common repository. A migration data placement tool uses analytics to determine data placement of the data in a target storage system according to the data identified as hot data, warm data, or cold data based on the events indexed in the common repository. The data may be placed according to a migration template during migration to the target storage system.