Storage Grid Data Survivability via Cluster Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional storage systems, including solid-state drives and hard disk drives, are vulnerable to disasters such as multiple component failures, system power loss, data theft, and physical theft, as they often rely on architectures that do not fully utilize the unique characteristics of solid-state memory and expose data in case of physical theft.
Innovation Solution
A storage grid architecture is implemented, comprising multiple clusters with distributed data copies, using erasure coding and redundant metadata to ensure data survivability and security. Each cluster stores a full or partial copy of the data, allowing any two clusters to recover all data in case of failure, and employs mechanisms like shared secrets for encryption and redundancy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If data is stored in a single storage cluster for simplicity, then device complexity is reduced, but data survivability and reliability deteriorate due to vulnerability to disasters and component failures
Solution Approach 1:
The patent divides data into multiple segments and distributes them across three separate storage clusters. Each cluster stores a portion of the segmented data, so that no single cluster holds the complete dataset. This segmentation approach reduces the reliability impact of any single cluster failure while maintaining manageable complexity through systematic data distribution.
Solution Approach 2:
The patent implements different data storage configurations in different clusters - one cluster stores a first segment of data, another cluster stores a second segment, and a third cluster stores both first and second segments. This local quality differentiation allows each cluster to have specialized storage roles, improving overall data survivability while maintaining clear functional distinctions that simplify management.
2Reliability
If full data copies are stored in multiple clusters for high reliability, then data survivability improves, but storage space requirements and device complexity increase
Solution Approach 1:
The patent segments data into distinct portions (first segment and second segment) and distributes them across clusters. Instead of storing complete copies of all data in every cluster, each cluster stores only the segments it needs, reducing total storage space requirements while maintaining the ability to recover all data through segment combination.
Solution Approach 2:
The patent combines segmented data from multiple clusters to reconstruct complete datasets. Cluster 3 stores both first and second segments, allowing it to independently provide complete data, while clusters 1 and 2 can combine their respective segments to achieve the same result. This merging approach reduces redundant storage compared to full replication.
3Ease of operation
If data is concentrated in fewer clusters for easier management, then ease of operation improves, but vulnerability to data theft and physical theft increases
Solution Approach 1:
The patent segments data across multiple clusters so that no single cluster contains the complete dataset. This segmentation provides inherent security against data theft - even if one cluster is compromised, the attacker only obtains partial data segments that are useless without the other segments from additional clusters.
Solution Approach 2:
Different clusters have different data segment configurations, creating local quality differences that enhance security. Cluster 1 has only first segments, Cluster 2 has only second segments, while Cluster 3 has both. This differentiation ensures that data theft from any single cluster results in incomplete information, reducing the harmful impact of security breaches.
Data Source
AI summary
A storage grid is provided. The storage grid includes a first cluster, a second cluster, and a third cluster. Each of the first cluster, the second cluster and the third cluster is configured to store an amount of data ranging from a portion of a copy of the data to a full copy of the data. The first cluster has a full copy of data written to the first cluster and at least a partial copy of data written to the second and third cluster. The second cluster has a full copy of data written to the second cluster, and at least a partial copy of the data written to the first and third cluster. The third cluster has a full copy of data written to the third cluster and at least a partial copy of the data written to the first and second cluster. A method of storing data is also provided.