SSD Block Swapping Based on BER and P/E Cycle Degradation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing SSDs face challenges in managing uncorrectable bit error rates (UBER) due to increasing program/erase (P/E) cycles, leading to reliability degradation and read errors, which impact performance and data integrity.
Innovation Solution
A proactive method is employed to identify blocks with higher P/E cycles and bit error rates (BER) by monitoring metrics, and remediating these blocks through swapping with reserved or overprovisioned blocks, and applying modified trim settings to maintain reliability and reduce UBER.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the SSD continues to operate with increasing P/E cycles, then the storage capacity is maintained, but the reliability decreases and read errors increase
Solution Approach 1:
The system performs preliminary monitoring of BER metrics and proactively identifies physical blocks with high error rates before they cause read failures. By detecting degradation trends early and swapping affected blocks with healthy reserves, the system prevents reliability degradation rather than responding to failures after they occur.
Solution Approach 2:
The system discards (swaps out) physical blocks that have degraded beyond acceptable BER thresholds and recovers storage capacity by replacing them with healthy blocks from the reserved pool. This allows the SSD to maintain reliability by continuously refreshing the active block pool with healthier storage resources.
2Reliability
If the SSD swaps physical blocks frequently to maintain low BER, then reliability is improved, but the complexity of block management increases
Solution Approach 1:
The system implements self-service through automated BER monitoring and threshold-based swap decisions. The controller autonomously identifies degraded blocks, selects replacement blocks from reserves, and performs swaps without host intervention, reducing management complexity while maintaining reliability.
Solution Approach 2:
The system uses feedback from BER measurements to dynamically adjust block management decisions. By continuously monitoring error rates and comparing them against thresholds, the system automatically triggers swaps when degradation is detected, creating a closed-loop control system that maintains reliability without manual intervention.
3Reliability
If the SSD increases program time to reduce BER, then reliability is improved, but the productivity decreases
Solution Approach 1:
The system applies partial action by selectively increasing program time only for specific physical blocks that exhibit high BER, rather than applying slower programming to all blocks. This targeted approach improves reliability for degraded blocks while maintaining normal programming speeds for healthy blocks, thus preserving overall productivity.
Data Source
AI summary
In some implementations, a controller may select a physical block, of a user data virtual block (VB), for a host write operation or a garbage collection operation. The user physical block previously stored user data. The user physical block has previously been programmed in accordance with triple-level cell (TLC) programming. The controller may determine that an average bit error rate (BER) of the user physical block exceeds an average BER of the VB. The controller may, based on determining that the average BER of the physical block exceeds the average BER of the user VB: swap, for the VB, the user physical block with a system physical block that is allocated for storing system data; swap, for the VB, the user physical block with a reserved physical block; or cause a program time, of the user physical block, to be increased.