Mixed Granularity Redundancy for Non-Volatile Memory Error Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current SSD technologies face challenges in maintaining reliable operation and efficiency due to uncertainties in data storage and retrieval from NAND flash memory, particularly as manufacturing scales down and storage capacity increases, leading to higher probabilities of data corruption and failure.
Innovation Solution
Implementing mixed-granularity higher-level redundancy techniques, including dynamic mode management with Redundant Array of Silicon Independent Elements (RASIE) and adaptive error correction, to transition between different redundancy modes based on changing reliability and error rates, ensuring continued operation even with failing flash memory elements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If storage capacity is increased by scaling down manufacturing, then storage density is improved, but data corruption probability increases
Solution Approach 1:
The patent segments redundancy management into multiple granularity levels (read unit level, page level, block level) allowing different redundancy strategies to be applied to different portions of storage based on their reliability characteristics, enabling fine-grained error handling that scales with capacity while maintaining reliability
Solution Approach 2:
The patent implements dynamic redundancy mode management that transitions between different redundancy modes (first mode with higher redundancy, second mode with lower redundancy) based on observed error rates and element reliability, allowing the system to adapt to changing conditions as storage capacity scales
2Reliability
If higher-level redundancy is increased to improve error recovery, then reliability is improved, but redundancy information overhead increases
Solution Approach 1:
The patent applies different redundancy levels to different granularities of data (read units, pages, blocks) based on their specific reliability needs, rather than applying uniform redundancy across all data, thereby reducing overall redundancy overhead while maintaining error recovery capability where most needed
Solution Approach 2:
The patent implements partial redundancy by selectively applying higher-level redundancy only to data portions that require it based on error rates and reliability metrics, rather than applying full redundancy to all data, thus reducing information overhead while maintaining adequate error recovery
3Adaptability or versatility
If dynamic mode transition is implemented to adapt to changing error rates, then adaptability is improved, but system complexity increases
Solution Approach 1:
The patent merges multiple redundancy management functions into a unified higher-level redundancy system that operates across different granularities simultaneously, consolidating what would otherwise be separate complexity-prone systems into a coordinated framework
Data Source
AI summary
Mixed-granularity higher-level redundancy for NVM provides improved higher-level redundancy operation with better error recovery and/or reduced redundancy information overhead. For example, pages of the NVM that are less reliable, such as relatively more prone to errors, are operated in higher-level redundancy modes having relatively more error protection, at a cost of relatively more redundancy information. Concurrently, blocks of the NVM that are more reliable are operated in higher-level redundancy modes having relatively less error protection, at a cost of relatively less redundancy information. Compared to techniques that operate the entirety of the NVM in the higher-level redundancy modes having relatively less error protection, techniques described herein provide better error recovery. Compared to techniques that operate the entirety of the NVM in the higher-level redundancy modes having relatively more error protection, the techniques described herein provide reduced redundancy information overhead.