Global Data Reduction Across Virtual Storage Systems

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing storage systems face inefficiencies in data management and reliability due to unnecessary write operations and lack of centralized control over storage processes, leading to reduced reliability and increased wear on storage devices.

Innovation Solution

Implementing a direct-mapped flash storage system where higher-level processes, such as the operating system, manage data allocation and storage operations directly across flash drives without intermediate storage controllers, thereby reducing redundant writes and enhancing reliability.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If intermediate storage controllers are used to manage data allocation and storage operations, then device complexity is reduced and ease of operation is improved, but unnecessary write operations increase and reliability decreases

Engineering Contradiction:
ImprovereliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent removes intermediate storage controllers from the data path, allowing the operating system to directly manage flash drives. This extraction of the controller layer eliminates redundant write operations that controllers perform for wear leveling and data management, thereby improving reliability while accepting increased complexity at the OS level.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The flash drives are designed to be directly managed by higher-level processes without intermediary controllers. The OS performs data allocation and storage operations directly on the flash drives, making the system self-sufficient without requiring additional controller hardware to manage wear and data integrity.

Inventive Principle:
Principle #25Self-service

2Duration of action of stationary object

If intermediate storage controllers are used to manage storage operations, then ease of operation is improved, but device wear increases and lifespan is reduced

Engineering Contradiction:
ImprovelifespanVSAvoidease of operation
Core Design Contradiction:
Duration of action of stationary objectVSEase of operation

Solution Approach 1:

By removing intermediate storage controllers that perform wear-leveling operations, the patent allows the OS to directly manage flash drive operations. This eliminates redundant write cycles through controllers, reducing overall device wear and extending lifespan, though it requires the OS to handle storage management directly.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The flash drives operate without intermediary controllers that would otherwise manage wear and data allocation. The OS directly performs storage operations, eliminating the extra write cycles that occur when data passes through controllers, thereby extending device lifespan.

Inventive Principle:
Principle #25Self-service

3Reliability

If centralized control over storage processes is implemented, then reliability is improved, but device complexity increases

Engineering Contradiction:
ImprovereliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent extracts centralized control from intermediate storage controllers and relocates it to the operating system. This eliminates the reliability issues caused by controller-mediated write operations while accepting that the OS must directly manage storage complexity.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS20250355803A1Similarity-based global data reduction across virtual storage systems
Publication Date: 2025.11.20 PURE STORAGE INC
  • US20250355803A1 patent drawing
  • US20250355803A1 patent drawing
  • US20250355803A1 patent drawing

AI summary

Data reduction across different cloud-based storage systems, including: performing one or more global data reduction processes on the data using one or more global databases that represent the data associated with the plurality of cloud-based virtual storage systems.