Delegate-Based Index Node Updates in Dispersed Storage Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current cloud storage systems face challenges in securely storing data across distributed networks, particularly in maintaining data integrity and security while tolerating storage unit failures without the need for redundant copies.
Innovation Solution
A dispersed storage network (DSN) utilizing Cauchy Reed-Solomon error encoding and decoding, where data is segmented into encoded slices stored across multiple geographically dispersed units, allowing for secure and fault-tolerant storage without redundant copies, with a managing unit for vault creation, security, and integrity processing for rebuilding 'bad' or missing slices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is stored using traditional redundant copy methods in cloud storage systems, then data reliability is improved, but storage efficiency deteriorates due to duplicate data occupying additional space
Solution Approach 1:
The patent segments data into multiple slices and disperses them across different storage units using Cauchy Reed-Solomon error encoding. Instead of creating full redundant copies, the system divides data into N slices where any K slices can reconstruct the original data, achieving fault tolerance with reduced storage overhead.
Solution Approach 2:
The patent changes the storage parameter from traditional redundant copying to dispersed storage with error encoding. By using Cauchy Reed-Solomon codes with configurable (N, K) parameters, the system can adjust the balance between reliability and storage efficiency based on specific requirements.
2Quantity of substance
If data is dispersed across multiple storage units without error encoding, then storage efficiency is improved, but data integrity deteriorates when storage units fail
Solution Approach 1:
The patent applies Cauchy Reed-Solomon error encoding to data slices before dispersing them across storage units. This preliminary encoding action ensures that even if some storage units fail, the original data can be reconstructed from the remaining slices, maintaining data integrity without requiring full redundancy.
3Ease of operation
If index structures are updated centrally in cloud storage systems, then data organization is improved, but system complexity increases and update performance deteriorates
Solution Approach 1:
The patent segments the index structure into multiple index nodes that are dispersed across different storage units. Each index node can be independently updated by identifying delegate storage units, distributing the update workload and reducing centralization complexity while maintaining organized data access.
Solution Approach 2:
The patent introduces an optional index update module as an intermediary that coordinates index node updates. This module manages the complexity of distributed index maintenance by selectively engaging delegate storage units for updates, balancing organization needs with system complexity reduction.
4Reliability
If traditional RAID systems are used for cloud storage, then data security is improved through redundancy, but the ability to tolerate storage unit failures without redundant copies deteriorates
Solution Approach 1:
The patent transitions from fixed RAID redundancy configurations to flexible dispersed storage with Cauchy Reed-Solomon encoding. The (N, K) parameters allow the system to adapt to different failure scenarios and storage capacities, providing both security and versatile failure tolerance without requiring fixed redundant copies.
Data Source
AI summary
A method includes identifying, by a computing device of a dispersed storage network (DSN), a delegate device of a plurality of delegate devices of the DSN for processing a change to a node of a plurality of nodes of a hierarchical index structure. The method further includes sending, by the computing device, a change type specific request to the delegate device regarding the change to the node. The method further includes determining, by the delegate device, whether the delegate device is responsible for executing the change type specific request. When the delegate device is responsible for executing the change type specific request, the method further includes sending, by the delegate device, a response message to the computing device indicating that the delegate device is responsible for executing the change type specific request. The method further includes executing, by the delegate device, the change type specific request.