Tiered Storage Data Distribution via Randomness Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Tiered storage systems face challenges in efficiently managing the distribution of data between high-cost, high-performance storage and lower-cost, lower-performance storage tiers, leading to suboptimal data placement and access times.
Innovation Solution
A system controller with a tier manager and classification module determines relative randomness values for data pages based on seek distance, operation rate, and elapsed time, then assigns and relocates pages to optimize placement across storage tiers, ensuring higher randomness and performance in the first tier compared to the second tier.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If data is placed on high-speed storage devices, then access performance is improved, but storage cost increases
Solution Approach 1:
The patent applies local quality by differentiating data placement strategies based on access patterns. Frequently accessed data (high randomness value) is placed on high-speed storage devices, while less frequently accessed data is placed on slower, cheaper storage. This creates a localized optimization where each storage tier serves data with appropriate access characteristics, resolving the contradiction between performance and cost.
Solution Approach 2:
The patent implements dynamic data placement by continuously monitoring access patterns and recalculating randomness values. Data pages are dynamically relocated between storage tiers based on changing access characteristics. This dynamic adaptation allows the system to maintain optimal performance-cost balance as data usage patterns evolve over time.
2Loss of time
If frequently accessed data is stored on high-speed storage, then access time is reduced, but system complexity increases
Solution Approach 1:
The patent implements self-service by enabling data pages to effectively 'self-classify' through the randomness calculation mechanism. The system automatically monitors access patterns, calculates randomness values, and relocates data without manual intervention. This self-managing approach reduces operational complexity while maintaining performance benefits.
Solution Approach 2:
The patent employs feedback mechanisms by continuously monitoring access patterns and using this information to adjust data placement. The randomness calculation incorporates access frequency and recency, creating a feedback loop that automatically optimizes data distribution. This feedback-driven approach simplifies management compared to static classification methods.
3Quantity of substance
If data is distributed across multiple storage tiers, then storage cost is optimized, but data placement efficiency decreases
Solution Approach 1:
The patent uses parameter changes by calculating a randomness value that synthesizes multiple access pattern dimensions (frequency, recency, sequence). This composite parameter enables efficient single-metric decision-making for data placement, avoiding the complexity of multi-parameter optimization while maintaining effective data distribution across storage tiers.
Data Source
AI summary
A method for assigning data in a plurality of physical storage resources for an information handling system is disclosed. The plurality of physical storage resources includes a first tier and a second tier with a lower performance and cost relative to capacity than the first tier. A tier manager hosted on the information handling system and in electronic communication with the plurality of physical storage resources is configured to: determine a seek distance value, operation rate, operation size value, and elapsed time value for each page; and calculate a relative randomness value for each page using the seek distance value, operation rate, operation size value, and elapsed time value determined for each page. A classification module may assign a physical location for each page such that the relative randomness value for each page in the first tier is greater than the relative randomness value for each page in the second tier.