Dispersed Storage Unit Mapping for Secure Failure-Tolerant Data Slices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional RAID systems face issues with effectiveness, efficiency, and security, particularly as the number of disks increases, leading to higher maintenance costs and risks of data loss due to disk failures, and the duplication of data raises security concerns and vulnerability to natural disasters.
Innovation Solution
A dispersed storage network (DSN) that uses dispersed storage units located at different geographical sites, employing error encoding and decoding techniques like Cauchy Reed-Solomon to distribute data across multiple storage units, ensuring data integrity and security without the need for redundant copies, and allowing for secure and efficient data storage and retrieval.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is duplicated across multiple RAID devices to reduce data loss risk, then reliability improves, but security deteriorates due to increased unauthorized access vulnerability
Solution Approach 1:
The patent segments data into multiple encoded slices distributed across different storage units. Instead of creating redundant copies, the system divides data into N slices where any K slices can reconstruct the original data. This segmentation approach provides reliability through distribution while maintaining security since no single slice contains complete data.
Solution Approach 2:
The patent changes the parameter of data representation from redundant copies to encoded slices using error correction codes. By transforming data into a different parameter space (encoded form), the system achieves both reliability (through error correction capability) and security (since decoded data requires combining multiple slices).
2Productivity
If more disks are added to RAID array to increase storage capacity, then productivity improves, but reliability deteriorates due to higher disk failure probability
Solution Approach 1:
The patent applies segmentation by dividing data into slices distributed across multiple storage units. This allows the system to scale storage capacity by adding more units while maintaining reliability through the error correction code structure, where the system can tolerate up to (N-K) failures regardless of array size.
Solution Approach 2:
The patent creates a universal error correction structure that works regardless of the number of storage units. The same encoding scheme provides both storage expansion capability and failure tolerance, making the system scalable without proportionally increasing vulnerability to failures.
3Ease of operation
If RAID devices are co-located for ease of access, then ease of operation improves, but reliability deteriorates due to natural disaster risk
Solution Approach 1:
The patent introduces a spatial distribution dimension by placing storage units at geographically separated locations. This dimensional change allows the system to maintain data accessibility (through networked distributed storage) while achieving natural disaster resistance through physical separation, resolving the contradiction between operational convenience and disaster resilience.
4Device complexity
If manual disk replacement is required to maintain RAID systems, then device complexity reduces, but loss of time increases due to maintenance interruptions
Solution Approach 1:
The patent implements self-service through automated error correction and data reconstruction. When storage units fail, the system automatically detects the failure, retrieves data slices from remaining units, and reconstructs lost data without manual intervention. This eliminates maintenance downtime while keeping the system conceptually simple.
Data Source
AI summary
Methods for assigning data storage resources are disclosed. The methods includes obtaining memory resource availability information for a plurality of physical memory devices of a dispersed storage network, determining a number of logical storage units for the dispersed storage network, determining a memory capacity level for each of the logical storage units, determining a mapping in accordance with a mapping approach of at least some of the plurality of physical memory devices to achieve a corresponding memory capacity level, and when accessing encoded data slices associated with the logical storage unit by an accessing entity, communicating slice access messages with a dispersed storage unit associated with the logical storage unit. A dispersed storage managing unit and dispersed storage network are also disclosed.