Rating-Based Memory Mapping for Block Retention
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Memory systems face capacity reduction due to premature retirement of blocks containing both low and high performance pages, where poor performance of a subset of pages leads to the entire block being retired, even if other pages within the block are capable of higher performance.
Innovation Solution
Implementing a rating-based mapping system where data is written to pages based on their performance ratings, allowing blocks with low-performance pages to continue being used by assigning low priority data to these pages, thus preserving memory capacity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If blocks are retired based on the performance of individual pages, then the reliability of data storage is improved, but the memory capacity is reduced
Solution Approach 1:
The patent segments the block-level retirement decision into page-level performance evaluation. Instead of retiring entire blocks based on individual page failures, the system evaluates and manages pages independently within blocks, allowing blocks with some low-performance pages to remain operational. This segmentation resolves the contradiction by maintaining reliability through page-level monitoring while preserving capacity through block-level retention.
Solution Approach 2:
The patent applies local quality by differentiating the treatment of individual pages within blocks based on their performance characteristics. Low-performance pages are identified and managed separately from high-performance pages, allowing selective optimization. This enables the system to maintain overall block functionality while addressing specific reliability issues at the page level, thus preserving memory capacity.
2Productivity
If blocks with low-performance pages are retired, then the performance degradation is reduced, but the available memory space is decreased
Solution Approach 1:
The patent implements dynamic management of page performance ratings, where pages are continuously monitored and re-evaluated. The system dynamically adjusts the status of pages based on their performance characteristics, allowing blocks to be retained as long as they contain a sufficient number of functional pages. This dynamic approach resolves the contradiction by maintaining performance through active management while preserving memory space through flexible block retention policies.
3Productivity
If rating-based mapping is implemented, then the efficient use of pages is improved, but the system complexity is increased
Solution Approach 1:
The patent implements self-service through automatic performance evaluation and rating assignment. The system autonomously monitors page performance, assigns ratings, and manages block retention decisions without requiring external intervention. This automated self-service approach resolves the contradiction by improving page utilization efficiency through intelligent management while controlling system complexity through standardized evaluation protocols.
Data Source
AI summary
Methods, systems, and devices for rating-based mapping of data to memory are described. A memory system may determine a first rating for a set of data selected for writing to a memory system. The memory system may select a target page of a block in the memory system for writing the set of data based at least in part on a second rating for the target page. The memory system may write the set of data to the target page based at least in part on the first rating for the set of data corresponding to the second rating for the target page.