Memory Block Reuse for Soft-Failure Task Allocation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory sub-systems inefficiently handle bad blocks by assuming permanent retirement based on initial defects, leading to overprovisioning and reduced system performance.
Innovation Solution
A dynamic block-retirement strategy that evaluates block failures over time, distinguishing between hard and soft failures, allowing reuse of soft failure blocks for non-critical tasks and maintaining system performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional memory sub-systems retire blocks based on initial defects, then reliability is improved, but productivity deteriorates due to overprovisioning
Solution Approach 1:
The patent implements a dynamic block retirement strategy that transitions from static initial defect-based retirement to continuous monitoring over time. Blocks are evaluated periodically to distinguish between temporary soft failures and permanent hard failures, allowing the system to adaptively adjust which blocks remain in service based on their actual performance history rather than initial status alone.
Solution Approach 2:
The system changes the evaluation parameter from a single-point-in-time defect check to a time-based reliability metric. By monitoring block performance across multiple time points and operational cycles, the system uses parameter changes in reliability assessment to identify blocks that can safely continue service, thereby improving productivity without compromising reliability.
2Reliability
If more blocks are retired to ensure reliability, then reliability is improved, but loss of substance worsens due to reduced available storage capacity
Solution Approach 1:
The patent implements a feedback mechanism where block performance data is continuously collected and analyzed over time. This feedback loop allows the system to distinguish between blocks with temporary issues (soft failures) and those with permanent defects (hard failures), providing accurate information for retirement decisions that prevents unnecessary retirement of reliable blocks.
Solution Approach 2:
The system performs preliminary monitoring and evaluation of block performance before making retirement decisions. By establishing a time-based observation period and collecting reliability data in advance, the system can make informed decisions about which blocks to retire, avoiding premature retirement of blocks that would have continued to function reliably.
3Ease of operation
If initial defect detection is used for block retirement, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent implements continuous monitoring of block performance over time rather than relying on a single initial detection event. This continuous evaluation maintains ease of operation through automated processes while significantly improving measurement precision by accumulating reliability data across multiple operational cycles to accurately distinguish between soft and hard failures.
Data Source
AI summary
A failure of a block among a set of blocks of a memory device of a memory sub-system is detected. Based on detecting the failure of the block, the block is evaluated for reuse. The block is designated for reuse based on a result of the evaluating of the block. The block is allocated to a task based on the block being designated for reuse.