Encoded Data Slice Recovery for Fault-Tolerant Chunk Access

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing dispersed storage networks face challenges in efficiently encoding and decoding data across multiple storage units, particularly in ensuring data integrity and availability in the presence of storage unit failures.

Innovation Solution

The implementation of a dispersed storage network that utilizes Cauchy Reed-Solomon encoding to divide data into fixed-sized segments, which are then encoded into a set of encoded data slices. This encoding process includes creating slice names for each encoded data slice and using a decoding function to recover the original data segments from a decode threshold number of encoded data slices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If data is divided into segments and encoded into multiple slices for distributed storage, then data availability and fault tolerance are improved, but system complexity increases due to encoding and decoding operations

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

Solution Approach 1:

The patent divides data into multiple segments and encodes them into distributed slices using Cauchy Reed-Solomon encoding. Each slice can be independently stored and retrieved, enabling fault tolerance while maintaining manageable system complexity through modular processing

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent employs Cauchy Reed-Solomon encoding which transforms data segments into encoded slices with specific mathematical properties. This parameter-based transformation enables efficient encoding and decoding operations that balance reliability improvements with computational complexity

Inventive Principle:
Principle #35Parameter changes

2Productivity

If a decode threshold is implemented to recover data from a portion of encoded slices, then storage efficiency is improved, but data integrity verification becomes more difficult

Engineering Contradiction:
Improvestorage efficiencyVSAvoiddata integrity verification
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent implements integrity verification mechanisms that provide feedback on the quality and validity of retrieved encoded slices. This feedback system enables the decode threshold mechanism to operate efficiently while maintaining data integrity through continuous verification of slice validity

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent performs preliminary encoding with built-in verification capabilities before distribution. This preliminary action embeds integrity information within the encoded slices, enabling efficient verification during the decoding process without compromising storage efficiency

Inventive Principle:
Principle #10Preliminary action

3Adaptability or versatility

If random access to data chunks is enabled in dispersed storage, then operational flexibility is improved, but the number of required encoded slices increases

Engineering Contradiction:
Improverandom access capabilityVSAvoidnumber of encoded slices
Core Design Contradiction:
Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

The patent segments data into fixed-sized chunks that can be independently accessed. Each chunk is encoded into a specific number of slices based on the decode threshold, enabling random access to individual chunks without requiring all slices to be stored or retrieved

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent enables retrieval of data chunks using only the minimum required number of encoded slices (decode threshold) rather than requiring all slices. This partial action approach reduces the effective number of slices needed for each access operation while maintaining random access flexibility

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12212623B2Recovering a data chunk from a portion of a set of encoded data slices
Publication Date: 2025.01.28 PURE STORAGE INC
  • US12212623B2 patent drawing
  • US12212623B2 patent drawing
  • US12212623B2 patent drawing

AI summary

A method for execution by a computing device of a storage network includes obtaining at least a “T” number of encoded data slices of a set of encoded data slices, where a plurality of data chunks are all-or-nothing encoded in accordance with distributed data storage parameters to produce the set of encoded data slices. The method further includes decoding a first section of the at least the “T” number of encoded data slices to recover a first data chunk of a plurality of data chunks. The method further includes decoding a second section of the at least the “T” number of encoded data slices to recover a second data chunk of the plurality of data chunks.