Non-Volatile Memory Disturb Inspection Mechanism
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory devices face increased bit error rates due to disturb effects such as read and program disturbances, which can lead to unrecoverable data loss, especially in Multi-Level Cell (MLC) flash memory devices with high storage density.
Innovation Solution
An inspection mechanism is implemented to detect disturb effects by reading selected states of storage elements, using an inspection engine that initiates a selected state read operation to determine error counts and schedule remedial actions, such as data moves or refresh operations, to mitigate these errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If increasing the number of bits per cell and reducing device feature dimensions is done to increase storage density, then storage density is improved, but bit error rate increases
Solution Approach 1:
The inspection mechanism performs preliminary reading of selected states (including states more susceptible to disturb effects) before actual data operations. This allows the system to detect disturb effects proactively and schedule remedial actions in advance, preventing bit errors before they occur during normal operations.
Solution Approach 2:
The system implements a feedback loop where data read from selected states is decoded to determine error counts, and this information is used to schedule remedial actions. The inspection mechanism continuously monitors storage element states and adjusts operations based on detected disturb effects, creating a closed-loop error prevention system.
2Reliability
If more parity bits are used to increase error correction capacity, then error correction capability is improved, but number of bits required to store encoded data increases
Solution Approach 1:
By performing preliminary inspection of selected states and detecting disturb effects before they cause data errors, the system can schedule remedial actions that prevent errors from occurring in the first place. This reduces the need for extensive error correction coding, thereby minimizing the storage space required for parity bits.
Solution Approach 2:
The inspection mechanism enables the memory system to self-diagnose and self-correct by detecting disturb effects and automatically scheduling remedial actions. This self-service capability reduces reliance on heavy ECC coding schemes, allowing the system to maintain high reliability with minimal overhead.
3Reliability
If reading data from all states is performed to ensure complete data retrieval, then data completeness is improved, but inspection time and energy consumption increase
Solution Approach 1:
The inspection mechanism segments the storage elements into selected states and non-selected states. By focusing inspection only on selected states (which are more susceptible to disturb effects), the system achieves adequate error detection without the time and energy cost of inspecting all states, thereby reducing inspection time while maintaining data reliability.
Solution Approach 2:
The system applies different inspection strategies to different states based on their susceptibility to disturb effects. Selected states receive intensive inspection while non-selected states are read during normal operations, optimizing the balance between inspection thoroughness and time/energy consumption.
Data Source
AI summary
A method performed in a data storage device including a non-volatile memory includes reading a representation of data, the representation corresponding to one or more selected states of storage elements of a group of storage elements of the non-volatile memory. The method includes, in response to a count of errors in the representation of the data exceeding a threshold, scheduling a remedial action to be performed on the group of storage elements.