Encoded Data Slice Transfer on Flash Memory Shutdown
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data storage systems face challenges with memory device failures, particularly in commercial-grade devices using technologies that require physical movement, leading to bit-level corruption and complete failure, and redundant array of independent discs (RAID) solutions suffer from increased maintenance demands, security risks, and efficiency issues as data grows.
Innovation Solution
A distributed storage network (DSN) system that disperses data across geographically diverse locations using error-correcting codes, ensuring data integrity and security through error-coded data slices stored in multiple devices, with a DS processing unit managing distribution and retrieval.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If RAID solutions are used to protect against memory device failures, then data reliability is improved, but maintenance complexity and security risks increase
Solution Approach 1:
The patent segments data into multiple slices and disperses them across different storage locations (flash memory and remote storage). This segmentation allows the system to achieve RAID-like reliability without the complexity of traditional RAID arrays, as each slice can be independently managed and recovered
Solution Approach 2:
The patent introduces an intermediary error-correcting code layer between the data and storage media. This intermediary mechanism provides automatic error correction and data recovery capabilities, eliminating the need for complex RAID management and reducing maintenance complexity while maintaining high data reliability
2Reliability
If data is dispersed across multiple locations with error-correcting codes, then fault tolerance is improved, but storage overhead increases
Solution Approach 1:
The patent dynamically adjusts the dispersal parameter based on the utilization level of flash memory. When flash memory is highly utilized, more slices are stored remotely with additional error-correcting codes, increasing storage overhead but maintaining fault tolerance. When utilization is low, the system optimizes by storing more slices locally, reducing storage overhead while maintaining the same level of fault tolerance
Data Source
AI summary
A method for execution by a computing device of a storage network includes detecting a shutdown associated with a local flash memory of the storage network, where a plurality of data segments are dispersed storage error encoded in accordance with distributed data storage parameters to produce pluralities of sets of encoded data slices, and the pluralities of sets of encoded data slices include encoded data slices stored in the local flash memory. The method further includes determining at least one storage location for transferring storage of a group of the encoded data slices. The method further includes transferring the group of the encoded data slices to the at least one storage location.