Heat Score File Tiering for Balanced Storage Utilization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing data storage systems face inefficiencies in re-tiering files between storage tiers due to reliance on unreliable access timestamps, resource-intensive sampling processes, and changes in tier utilization levels, requiring laborious administrator oversight.

Innovation Solution

A system that maintains a 'heat score' for each file based on activity data, using exponential or linear decay to adjust scores over time, and employs machine learning to predict access patterns, enabling automatic and efficient re-tiering without frequent administrator intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of manufacture

If access timestamps are used to determine file re-tiering, then the re-tiering process is simple to implement, but the accuracy of access pattern prediction deteriorates

Engineering Contradiction:

Improveease of implementationVSAvoidaccess pattern prediction accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent changes the parameter used for re-tiering decisions from simple access timestamps to a composite heat score that incorporates multiple factors including access frequency, access recency, file size, and storage tier characteristics. This parameter transformation resolves the contradiction by providing both implementation feasibility and improved prediction accuracy through multi-dimensional file activity assessment.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If file sampling is performed to assess access patterns, then re-tiering decisions can be data-driven, but system resource consumption and processing time increase

Engineering Contradiction:

Improvere-tiering decision accuracyVSAvoidsystem resource consumption

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent implements partial sampling rather than comprehensive file assessment. It selectively samples files based on criteria such as file age, size thresholds, and tier-specific parameters, processing only a subset of files that are most likely to benefit from re-tiering. This approach maintains reliable decision-making while significantly reducing system resource consumption compared to full-file-system scanning.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent divides the file system into multiple segments or zones with different sampling strategies. Hot tier files, warm tier files, and cold tier files are assessed using different sampling rates and methodologies. This segmentation allows the system to apply intensive analysis only where necessary while using lighter-weight assessment methods elsewhere, balancing reliability with resource efficiency.

Inventive Principle:

Principle #1Segmentation

3Productivity

If files are moved between storage tiers, then storage optimization is achieved, but tier utilization levels may become unbalanced

Engineering Contradiction:

Improvestorage optimizationVSAvoidtier utilization balance

Core Design Contradiction:

ProductivityVSStability of the object's composition

Solution Approach 1:

The patent implements a feedback mechanism that continuously monitors tier utilization levels and adjusts re-tiering operations accordingly. When a tier approaches capacity thresholds or utilization becomes unbalanced, the system modifies its file selection criteria to prevent further imbalance. This feedback loop ensures that storage optimization goals are pursued while maintaining stable, balanced tier utilization across the storage hierarchy.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent performs preliminary assessment of tier capacity and utilization before executing re-tiering operations. It calculates the expected impact of proposed file moves on tier balance and prevents moves that would create significant imbalance. This preliminary anti-action approach proactively avoids utilization instability before it occurs, maintaining both optimization and balance.

Inventive Principle:

Principle #9Preliminary anti-action

Data Source

PatentUS12360960B2Heat score-based tiering of data between different storage tiers of a file system

Publication Date: 2025.07.15 DELL PROD LP

AI summary

The described technology is generally directed towards maintaining a heat score per file based on a file's access/activity level, and using the heat score to re-tier files from faster to slower storage and vice-versa. Files on a slower tier that have more activity are thereby moved (“up-tiered”) to a faster access storage tier, while the files that have less activity on the faster access storage tier are moved (“down-tiered”) to a slower access storage tier. The heat score for a file is increased based on more input-output operation activity, and decayed over time. The decaying can be based on a relative importance value (e.g., business value) assigned to the file or a domain that includes the file. Ordering the files based on their respective heat scores allows only a fraction of the files to be considered for re-tiering before the re-tiering moves are performed.