NVSM Lifetime Extension via Dynamic Cache Aging Weights
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Data storage systems with non-volatile semiconductor memory (NVSM) face a limited practical usable life due to frequent access and writing, which can lead to premature deterioration, especially in solid-state hybrid drives (SSHDs) where the NVSM's life may expire before a predetermined time period, such as a warranty period.
Innovation Solution
A memory life management process that adjusts the cache update rate using an aging weight to balance the influence of new and old data access patterns, dynamically adjusting the cache composition to prolong the NVSM's life by reducing the frequency of writes to the NVSM.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If the cache memory is accessed and written to at a higher frequency to improve data access performance, then the data access speed is improved, but the practical usable life of the NVSM deteriorates faster
Solution Approach 1:
The patent implements dynamic adjustment of the cache update rate based on the remaining practical usable life of the NVSM. The controller monitors the PEC count and remaining life, then dynamically modifies the cache replacement policy by adjusting the aging weight parameter. When remaining life is sufficient, normal caching operations maintain high performance. When remaining life drops below thresholds, the system reduces write frequency to the NVSM, thereby extending its usable life while gradually transitioning to less frequent updates.
2Reliability
If the cache update rate is increased to maintain up-to-date cache data, then data freshness is improved, but the deterioration rate of the NVSM increases
Solution Approach 1:
The patent changes the parameter of cache update frequency based on the remaining practical usable life of the NVSM. The controller calculates remaining life from the PEC count and rated PEC rating, then adjusts the cache update rate parameter accordingly. When remaining life is above a first threshold, normal update rates maintain data freshness. When remaining life falls below the threshold, the update rate is reduced to decrease write operations, directly addressing the deterioration issue while maintaining acceptable data freshness through the aging weight mechanism.
3Productivity
If the aging weight is increased to prioritize new data access patterns, then cache performance for recent data is improved, but the NVSM life is reduced
Solution Approach 1:
The patent implements a feedback mechanism where the controller continuously monitors the remaining practical usable life of the NVSM and uses this information to adjust the aging weight parameter. The PEC count provides feedback on wear level, which feeds back into the cache replacement algorithm. When remaining life is sufficient, higher aging weights prioritize recent access patterns for optimal performance. When remaining life drops, the feedback triggers reduction of the aging weight, which in turn reduces the priority given to new data patterns, thereby reducing write frequency and preserving NVSM life.
Data Source
AI summary
Memory lifetime extension for a data storage system having a first memory and a second memory includes determining a plurality of age-adjusted access values for a data block stored in the first memory based on access of the data block and at least one aging weight, determining an overall access value for the data block based on the plurality of age-adjusted access values, and determining if at least a portion of the data block should be stored in a cache memory of the second memory based on the overall access value. The at least one aging weight can be dynamically adjusted based on an expected remaining practical usable life of the second memory.