Storage Controller Reliability Scheduling by Block Degradation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Flash memory devices experience data errors that exceed the correction capability of error correction means, leading to unreliability and potential data loss, due to their physical characteristics and ambient factors.
Innovation Solution
A storage controller operation method that includes initiating reliability operations based on degradation levels, setting skip reference values, and selectively skipping or performing operations based on error information to maintain data reliability and performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If reliability operations are performed frequently on memory blocks, then data reliability is improved, but performance degradation occurs due to excessive operations
Solution Approach 1:
The patent applies local quality by differentiating reliability operation strategies based on memory block degradation levels. Memory blocks are classified into multiple degradation levels (e.g., first level, second level, third level), and skip reference values are selectively applied according to each block's specific degradation state. This allows intensive reliability operations on highly degraded blocks while reducing operations on less degraded blocks, thereby maintaining data reliability where needed while preserving overall performance.
Solution Approach 2:
The patent implements dynamics by making the reliability operation frequency adaptive rather than static. The skip reference value is dynamically adjusted based on the degradation level of each memory block and the number of consecutive skipped instances. As blocks degrade over time, the system automatically modifies the operation frequency, increasing reliability checks for severely degraded blocks while maintaining lower operation rates for healthier blocks, thus balancing reliability and performance dynamically.
2Reliability
If reliability operations are performed on all memory blocks, then data reliability is improved, but unnecessary operations increase workload
Solution Approach 1:
The patent applies local quality by customizing reliability operation intensity according to the specific degradation level of each memory block. Instead of uniform treatment, each block receives a tailored operation frequency based on its degradation characteristics. Blocks with lower degradation levels experience reduced or skipped operations, while blocks with higher degradation levels receive more frequent reliability operations, thereby reducing unnecessary workload across the system while maintaining reliability where it is most needed.
Solution Approach 2:
The patent implements partial action by selectively applying reliability operations only where necessary rather than uniformly across all memory blocks. The skip reference value mechanism allows the system to partially execute reliability operations on some blocks while completely skipping them on others, based on degradation levels. This partial application of reliability operations reduces overall system workload while maintaining adequate reliability protection for critical degraded blocks.
3Reliability
If skip reference values are set low, then reliability operations are performed more often improving reliability, but performance degradation increases
Solution Approach 1:
The patent implements dynamics by making skip reference values adaptive rather than fixed. The system dynamically adjusts skip reference values based on the degradation level of each memory block and monitors the number of consecutive skipped instances. This dynamic adjustment allows the system to automatically increase reliability operation frequency (lower skip values) when blocks are severely degraded, while maintaining higher skip values (lower operation frequency) when blocks are in better condition, thus balancing reliability and performance based on real-time block states.
Solution Approach 2:
The patent applies parameter changes by modifying the skip reference value parameter according to degradation level. Different degradation levels correspond to different skip reference value parameters (e.g., first skip reference value for first degradation level, second skip reference value for second degradation level). This parameter variation allows the system to optimize the balance between reliability and performance by selecting appropriate skip reference values matched to the actual degradation state of each memory block.
4Productivity
If reliability operations are skipped frequently, then performance is maintained, but data reliability may be compromised
Solution Approach 1:
The patent implements dynamics by making the skip decision process adaptive rather than static. The system continuously monitors the number of consecutive skipped instances and compares it against the degradation level and skip reference value. This dynamic monitoring ensures that skips are maintained only as long as reliability thresholds are met, and automatically terminates skipping when reliability concerns arise, thus preserving performance while protecting against reliability degradation through real-time adaptive control.
Solution Approach 2:
The patent applies feedback by using the count of consecutive skipped instances as a feedback parameter to control future skip decisions. The system feeds back information about how many times operations have been consecutively skipped and uses this feedback to determine whether to continue skipping or to resume operations. This feedback mechanism ensures that skipping does not exceed safe limits and automatically triggers reliability operations when the skip count approaches or exceeds the skip reference value, thereby maintaining reliability while optimizing performance.
Data Source
AI summary
An operation method for controlling a nonvolatile memory device includes initiating a first instance of a respective reliability operation for a respective memory block included in the nonvolatile memory device. The respective reliability operation includes detecting a degradation level of the respective memory block and setting a respective skip reference value based on the detected degradation level. The operation method also includes determining whether a respective number of consecutively skipped instances of the respective reliability operation is less than the respective skip reference value. The operation method further includes selectively skipping or performing a next instance of the respective reliability operation based on the determination result.