Dynamic Data Classification for Tiered Storage Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Tiered storage systems face challenges in balancing the cost of storing and accessing data due to the need to constantly move data between storage mediums with different access speeds and costs, leading to inefficient bandwidth usage and increased operational costs.
Innovation Solution
Implementing a dynamic data classification system that modifies the classification of data based on its priority rather than physically moving it to different storage mediums, allowing for optimized resource allocation and bandwidth management without relocating the data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is constantly moved between storage mediums in a tiered storage system, then data access efficiency is improved, but bandwidth usage increases and operational costs increase
Solution Approach 1:
The patent implements dynamic data classification that adjusts data priority levels based on changing access patterns and business needs, allowing the system to optimize resource allocation without physically moving data between storage tiers. This dynamic reclassification enables the same storage medium to serve different priority levels over time, reducing unnecessary data movement and bandwidth consumption while maintaining efficient access to high-priority data.
2Quantity of substance
If data is moved to lower storage tiers with slower access time, then storage cost is reduced, but data access speed decreases
Solution Approach 1:
The patent changes the parameter of data priority classification without changing the physical location of data. By dynamically adjusting classification parameters based on access patterns, business criticality, and storage policies, the system can allocate appropriate access resources to different data sets regardless of their physical storage location, thereby maintaining fast access speeds for high-priority data while storing it on cost-effective media.
3Speed
If data is kept on expensive high-speed storage mediums, then data access speed is improved, but storage cost increases
Solution Approach 1:
The patent applies local quality by providing differentiated resource allocation and access prioritization based on data classification rather than uniform treatment of all data. High-priority data receives preferential treatment in terms of access resource allocation, caching strategies, and bandwidth allocation, while low-priority data uses standard access paths. This enables cost-effective storage of all data while ensuring fast access to only the high-priority subset that actually requires it.
4Productivity
If data is frequently moved between storage tiers, then optimal storage utilization is achieved, but operational complexity increases
Solution Approach 1:
The patent extracts the data classification and priority determination logic from the physical data movement process. Instead of coupling storage tier selection with data priority, the system separates these functions by maintaining dynamic classification metadata that independently tracks data priority. This extracted classification system then guides resource allocation and access prioritization without requiring physical data movement, thereby achieving optimal storage utilization while reducing operational complexity.
Data Source
AI summary
The classification of data stored on a storage medium is dynamically modified without the data being relocated to another storage medium. Data stored on a plurality of storage mediums is classified independent of the physical location at which the data resides. Rather than moving data to storage media that possess different classifications, the data itself receives a classification apart from the storage medium. Data which is considered high priority would be afforded maximum use of the storage medium resources and bandwidth availability. Data that is of lower interest is classified with a lower classification resulting in differing levels of resources authorized to access that data. Throughout this reclassification process the data remains resident on the same storage medium.