Dispersed Multimedia Storage Using Error-Coded Data Slices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data storage systems face challenges with memory device failures, particularly in commercial-grade devices using physical movement technologies, leading to data loss and security issues, as well as inefficiencies in RAID systems due to increased maintenance demands and unauthorized access risks.
Innovation Solution
A distributed storage network (DSN) system that employs error-coded data slices stored across multiple geographically diverse locations, utilizing a DS processing unit to partition and encode data, and a storage integrity processing unit for verification, ensuring data integrity and security through redundancy and dispersed storage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If redundant disc drives (RAID) are used to protect against data loss, 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 numerous ordinary disc drives rather than using a small array of redundant drives. This segmentation approach allows the system to achieve the same reliability as RAID but with standard commercial-grade drives, reducing device complexity and eliminating RAID controller requirements.
Solution Approach 2:
The system creates multiple copies of data segments and distributes them across different physical locations and drives. This copying strategy ensures data redundancy and reliability without requiring specialized RAID hardware, thereby reducing device complexity while maintaining high reliability.
2Reliability
If multiple copies of data are stored for redundancy, then data reliability is improved, but storage capacity is reduced due to overhead
Solution Approach 1:
The patent changes the redundancy parameter from traditional RAID's fixed parity-based overhead to a more efficient dispersal algorithm that optimizes the balance between redundancy and usable capacity. This allows the system to maintain data reliability while maximizing the quantity of storable data by reducing overhead.
3Object-affected harmful factors
If data is distributed across multiple locations, then security against unauthorized access is improved, but device complexity increases
Solution Approach 1:
The patent segments data and distributes it across multiple geographically dispersed locations, making it difficult for unauthorized access to compromise the entire dataset. This segmentation strategy enhances security without requiring complex specialized hardware, as it can be implemented using standard distributed storage techniques.
4Quantity of substance
If commercial-grade disc drives are used instead of higher-grade drives, then cost is reduced, but reliability deteriorates due to higher failure rates
Solution Approach 1:
The system compensates for the lower reliability of individual commercial-grade drives by creating multiple copies of data segments and distributing them across many drives. This copying strategy ensures that even if some drives fail, the data remains accessible, thereby maintaining reliability while using cost-effective commercial-grade hardware.
Solution Approach 2:
The patent uses homogeneous commercial-grade disc drives throughout the system rather than mixing in higher-grade drives. This homogeneity approach reduces cost while the distributed copying mechanism compensates for the inherently lower reliability of individual drives, achieving the desired balance between cost and reliability.
Data Source
AI summary
A method begins by a processing module determining dispersed storage preferences for streaming multi-media data. The method continues with the processing module transcoding the streaming multi-media data into transcoded data when the dispersed storage preferences include transcoding. In addition, the method continues with the processing module encoding the transcoded data in accordance with an error coding dispersed storage function of the dispersed storage preferences to produce pluralities of error coded data slices. In addition, the method continues with the processing module outputting the pluralities of error coded data slices to a plurality of data storage units for storage therein.