Cache for File-Based Dispersed Storage Network

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional data storage systems face challenges with data integrity and security due to the failure of memory devices, particularly those using physical movement technologies, which can lead to data loss and increased maintenance demands, and RAID systems face inefficiencies and security risks with multiple copies of data.

Innovation Solution

A dispersed storage network (DSN) system that uses error-coded data slices distributed across multiple geographically diverse storage units, allowing for reliable and secure data storage and retrieval, with a storage integrity processing unit for verification and rebuilding of corrupted slices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If data is stored in multiple copies using RAID systems, then data redundancy and reliability are improved, but device complexity and security risks increase

Engineering Contradiction:
Improvedata redundancyVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments data into multiple slices and distributes them across different storage units in a dispersed storage network. Each slice is encoded using error correction codes, allowing the system to tolerate failures without requiring complete redundancy. This segmentation approach achieves reliability without the complexity of traditional RAID systems.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates encoded copies of data slices that are distributed across multiple storage units. Rather than storing identical full copies as in RAID, the system stores encoded portions that can be reconstructed through decoding operations, reducing the overhead and complexity associated with managing multiple complete copies.

Inventive Principle:
Principle #26Copying

2Quantity of substance

If memory devices using physical movement technologies are used, then storage capacity is improved, but data integrity and reliability deteriorate due to failure risks

Engineering Contradiction:
Improvestorage capacityVSAvoiddata integrity
Core Design Contradiction:
Quantity of substanceVSReliability

Solution Approach 1:

The patent implements error correction coding on data slices before storage, creating a protective buffer against potential failures of physical storage devices. This beforehand cushioning ensures that even if physical movement technologies fail, the data can be recovered through the encoded information, maintaining data integrity while using high-capacity storage devices.

Inventive Principle:
Principle #11Beforehand cushioning (Prior cushioning)

3Reliability

If data is distributed across multiple geographically diverse storage units, then security and reliability are improved, but device complexity and maintenance demands increase

Engineering Contradiction:
Improvedata securityVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The dispersed storage network implements automated error detection, correction, and data reconstruction capabilities. The system self-manages the complexity of distributed storage through built-in error correction codes and automated recovery mechanisms, reducing the need for manual intervention and simplifying maintenance despite the geographically distributed architecture.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS9811405B2Cache for file-based dispersed storage
Publication Date: 2017.11.07 PURE STORAGE INC
  • US9811405B2 patent drawing
  • US9811405B2 patent drawing
  • US9811405B2 patent drawing

AI summary

A method obtains at least part of a file from a dispersed storage network (DSN) memory, and stores it in a data object cache. When the file is changed, a determination is made about where to store the changed file portions: in the data object cache or in the DSN. The changed file portions, for example a new copy of the part of the file obtained from the DSN, are encoded utilizing an error coding dispersal storage function, and stored in either the data object cache, or in the DSN memory.