Block Storage Volume Tier Tuning via Usage Simulation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Cloud infrastructure environments face challenges in providing flexible and scalable data storage solutions that balance cost and performance, as on-premise storage area networks are constrained to rack-level operations, while cloud providers offer disjoint capabilities with friction when moving data between storage options.

Innovation Solution

A data storage service that automatically adjusts data storage across performance tiers, such as SSD/NVMe and HDD or object storage, based on usage characteristics, to dynamically tune block volume performance without manual input, optimizing for cost and performance by simulating caching policies and adjusting storage types.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If cloud providers offer multiple storage options with different performance characteristics, then storage performance can be optimized for specific workloads, but data movement between storage options creates friction and operational complexity

Engineering Contradiction:
Improvestorage performanceVSAvoiddata movement operations
Core Design Contradiction:
ReliabilityVSEase of operation

Solution Approach 1:

The patent merges multiple storage options (block storage and object storage) into a unified storage service. The system automatically manages data placement between different storage types based on usage patterns, eliminating the need for manual data movement operations while maintaining performance optimization. The block volume serves as a unified interface that can dynamically leverage both high-performance block storage and cost-effective object storage.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The storage system performs self-service by automatically monitoring usage patterns and dynamically adjusting data placement between storage types without user intervention. The system autonomously determines when to use block storage versus object storage based on access patterns, eliminating operational friction while maintaining performance optimization.

Inventive Principle:
Principle #25Self-service

2Reliability

If high-performance block storage is used for all data, then performance requirements are met, but storage costs increase significantly

Engineering Contradiction:
Improvestorage performanceVSAvoidstorage costs
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The patent applies local quality by providing different storage performance characteristics to different data based on its access patterns. Frequently accessed data is automatically served from high-performance block storage, while infrequently accessed data is automatically moved to cost-effective object storage. This creates localized performance optimization without uniformly applying high-performance storage to all data.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system dynamically changes storage parameters (performance tier, storage type) based on monitored usage patterns. When usage patterns indicate lower performance requirements, the system automatically transitions data to lower-cost storage options, thereby reducing costs while maintaining adequate performance. The block volume performance tier can be automatically adjusted based on simulated and actual usage characteristics.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If manual tuning of storage performance is implemented, then performance can be optimized, but operational complexity and user burden increase

Engineering Contradiction:
Improvestorage performanceVSAvoidstorage configuration
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The storage system performs self-service by automatically monitoring usage patterns and dynamically adjusting data placement between storage types without user intervention. The system autonomously determines when to use block storage versus object storage based on access patterns, eliminating operational friction while maintaining performance optimization.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system implements feedback mechanisms by continuously monitoring usage patterns and performance metrics, then automatically adjusting storage configuration in response. The block volume service uses simulated usage characteristics and actual usage data to dynamically tune performance settings, eliminating the need for manual configuration while maintaining optimization.

Inventive Principle:
Principle #23Feedback

4Productivity

If cloud storage operates at regional level with high scalability, then availability and capacity are improved, but data movement between storage options creates friction

Engineering Contradiction:
Improvestorage scalabilityVSAvoiddata movement operations
Core Design Contradiction:
ProductivityVSEase of operation

Solution Approach 1:

The patent merges multiple storage options (block storage and object storage) into a unified storage service. The system automatically manages data placement between different storage types based on usage patterns, eliminating the need for manual data movement operations while maintaining performance optimization. The block volume serves as a unified interface that can dynamically leverage both high-performance block storage and cost-effective object storage.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentUS12323489B2System and method for automatic block storage volume tier tuning
Publication Date: 2025.06.03 ORACLE INT CORP
  • US12323489B2 patent drawing
  • US12323489B2 patent drawing
  • US12323489B2 patent drawing

AI summary

In accordance with an embodiment, described herein are systems and methods for automatic block storage volume tuning by simulating usage characteristics for data/block volumes. The block storage performance associated with usage by a cloud instance of a block volume can be simulated, and the manner in which data is stored or cached, for example within a combination of SSD/NVMe block storage and/or HDD object storage, can be automatically adjusted, for example to associate the block volume with a particular volume performance tier. The described approach allows the system to tune block volume performance in a dynamic manner, without further manual input from a user—the volume performance can be automatically increased when the user needs it, and otherwise reduced down to save costs (both for the user and the cloud provider). A user can enable tuning on a particular block volume, and thereafter automatically receive appropriate price/performance characteristics.