Dispersed Storage Network Vault Memory Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional data storage systems face challenges with memory device failures, particularly in commercial-grade systems using physical movement technologies, leading to data loss and security issues due to the need for redundant arrays like RAID, which increase maintenance demands and risk of unauthorized access.
Innovation Solution
A dispersed storage network system that distributes data across multiple geographically diverse locations using error coding dispersal storage, where data is partitioned into segments, encoded, and stored on multiple units, allowing for secure and reliable retrieval even in the event of device failures, with a management system for resource allocation and integrity verification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If RAID is used to protect against disc drive failure, then data reliability is improved, but device complexity and maintenance demands increase
Solution Approach 1:
The patent divides data into multiple segments and disperses them across different storage locations. Each segment is independently stored with its own error correction code, eliminating the need for complex RAID arrays. This segmentation approach provides reliability through distribution rather than through complex redundant array structures.
Solution Approach 2:
The patent introduces an intermediary error correction code that is dispersed along with data segments. This intermediary mechanism enables recovery from disc failures without requiring complex RAID controllers or multiple redundant arrays, simplifying the overall system while maintaining reliability.
2Reliability
If multiple copies of data are stored for redundancy, then data reliability is improved, but security risk increases due to unauthorized access
Solution Approach 1:
The patent segments data into multiple pieces and disperses them across different locations. To reconstruct the original data, a threshold number of segments must be collected, providing both redundancy and security. This segmentation eliminates the security vulnerability of storing complete copies while maintaining reliability through distributed storage.
Solution Approach 2:
The patent applies different local qualities to different data segments by storing them in geographically diverse locations with varying security characteristics. This allows the system to leverage the security strengths of different locations while maintaining overall data reliability, rather than requiring all copies to have uniform high security.
3Quantity of substance
If disc drive capacity is increased to store more data, then storage capacity is improved, but probability of disc failure increases
Solution Approach 1:
The patent divides large storage capacity into multiple smaller segments distributed across different discs and locations. This segmentation reduces the probability of complete data loss because failure of any single disc only affects a portion of the data, not the entire dataset. The system can recover by collecting segments from remaining functional discs.
Solution Approach 2:
The patent transitions from storing data in a single dimension (one large disc) to multiple dimensions (multiple discs across multiple locations). This dimensional expansion provides both increased storage capacity and improved reliability, as data survival depends on the intersection of multiple independent failure modes rather than a single point of failure.
4Ease of manufacture
If manual replacement of failed discs is delayed, then maintenance cost is reduced, but risk of data loss increases
Solution Approach 1:
The patent performs preliminary error correction coding and data segmentation before storage, enabling automatic recovery when discs fail. This preliminary action eliminates the need for immediate manual intervention, as the system can autonomously reconstruct data from remaining segments, reducing both maintenance costs and data loss risk.
Solution Approach 2:
The patent implements a self-service error correction mechanism where the distributed error correction codes automatically detect and correct failures without human intervention. The system monitors its own health and performs recovery operations autonomously, reducing maintenance burden while maintaining high reliability through continuous self-healing.
Data Source
AI summary
A method includes determining virtual memory use of a vault based on virtual memory use of one dispersed storage (DS) unit of a set of DS units that services the vault within the DSN, where data is dispersed storage error encoded in accordance with dispersed data storage parameters to produce a plurality of sets of error coded (EC) data slices that are stored in the vault. The method continues by comparing the virtual memory use of the vault to one or more vault thresholds. When the virtual memory use of the vault is less than or equal to a first vault threshold of the one or more vault thresholds, the method continues by instructing a memory state of the vault to be in a normal state, wherein when the vault is in the normal state, a write mode is activated allowing write requests of EC data slices to the vault.