Dispersed Storage Mapping for Fault-Tolerant Data Object Retrieval

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies face challenges in efficiently storing and processing large volumes of data across distributed networks while ensuring data integrity and security, particularly in the presence of failures and potential hacking attempts.

Innovation Solution

A distributed computing system that employs dispersed storage and task processing units, utilizing error encoding and decoding techniques to securely store and process data across geographically diverse locations, allowing for fault tolerance and secure retrieval without redundant copies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If data is stored in a distributed network across multiple locations, then fault tolerance and security are improved, but system complexity and coordination overhead increase

Engineering Contradiction:
Improvefault toleranceVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments data into multiple data objects that are distributed across different storage locations in the network. Each data object can be independently stored, managed, and retrieved, which reduces the complexity of managing large datasets as a single unit while improving fault tolerance through geographic distribution

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The storage network is designed to handle multiple types of data objects (images, videos, audio, text, etc.) using a unified storage and retrieval mechanism. This multi-functional approach simplifies the system architecture by providing a universal interface for diverse data types rather than requiring separate specialized systems for each data type

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Quantity of substance

If data objects are concatenated and stored together, then storage efficiency is improved, but retrieval time and processing complexity increase

Engineering Contradiction:
Improvestorage efficiencyVSAvoidretrieval time
Core Design Contradiction:
Quantity of substanceVSLoss of time

Solution Approach 1:

The patent concatenates multiple data objects into a single stored object with internal segmentation markers that divide the concatenated data into identifiable segments. This allows the system to store multiple data objects efficiently in a single location while enabling rapid retrieval of individual segments by referencing their position markers within the concatenated structure

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system performs preliminary organization of data objects into concatenated groups with pre-established segment markers during the storage phase. This preliminary action enables faster retrieval operations because the segmentation structure is already in place, eliminating the need for time-consuming processing during retrieval

Inventive Principle:
Principle #10Preliminary action

3Reliability

If error encoding is applied to protect data integrity, then data security is improved, but processing overhead and computational resources increase

Engineering Contradiction:
Improvedata integrityVSAvoidcomputational resources
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent applies error encoding selectively to critical portions of data objects rather than encoding entire datasets uniformly. This partial application of error encoding protects the most important data integrity requirements while reducing the overall computational overhead compared to full-system encoding

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12585539B2Storage network for storage of data object sets with a common trait
Publication Date: 2026.03.24 PURE STORAGE INC
  • US12585539B2 patent drawing
  • US12585539B2 patent drawing
  • US12585539B2 patent drawing

AI summary

A storage network is operable to identify a set of data objects having a common trait from a plurality of data objects for storage via the storage network. The set of data objects are combined to produce a concatenated data object. The concatenated data object is encoded in accordance with a dispersed encoding function to produce a set of encoded data blocks. A mapping of the set of data objects to the set of encoded data blocks is generated. The mapping facilitates retrieval from the storage network of individual data objects of the set of data objects.