SSD Read Disturb Detection Using Aggressor-Victim Error Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for handling Read Disturb errors in solid state drives (SSDs) are inefficient, as they either relocate entire blocks without considering error rates or require lengthy background media scanning, leading to potential data loss due to uncorrectable errors.
Innovation Solution
A method that determines Read Disturb errors by comparing the error levels of aggressor and victim pages, relocating only affected pages when the victim page's error level exceeds the aggressor's by a predefined factor, thereby reducing unnecessary data relocation and preventing data loss.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If periodic Background Media Scanning is performed to detect Read Disturb errors, then error detection capability is improved, but time delay increases and data loss risk increases
Solution Approach 1:
The patent applies preliminary action by proactively detecting Read Disturb errors through periodic scanning and comparing error rates between aggressor and victim pages before data becomes uncorrectable. This early detection mechanism identifies potential issues while they are still manageable, preventing later data loss and avoiding the need for lengthy RAID recoveries that would occur with traditional periodic scanning approaches.
2Reliability
If entire block relocation is performed when read threshold is reached, then data protection is improved, but operational efficiency deteriorates
Solution Approach 1:
The patent applies segmentation by dividing the memory block into individual pages and selectively relocating only the victim pages that are actually affected by Read Disturb errors, rather than relocating the entire block. This is achieved by comparing error rates between aggressor pages (frequently read) and victim pages (adjacent pages), and only relocating victims that exceed error thresholds, thereby maintaining data protection while significantly improving operational efficiency.
Solution Approach 2:
The patent applies local quality by implementing targeted error handling where different pages within the same block receive different treatments based on their actual error conditions. Victim pages with high error rates are relocated, while other pages remain in place, allowing the system to provide localized data protection exactly where needed rather than applying uniform block-level relocation.
3Reliability
If read count monitoring is performed for every block, then error prevention is improved, but system complexity increases
Solution Approach 1:
The patent applies partial action by monitoring error rates only for specific victim pages that are adjacent to aggressor pages with high read counts, rather than monitoring every block uniformly. This selective monitoring approach reduces the overall system complexity while maintaining effective error prevention, as it focuses resources only on the pages most susceptible to Read Disturb errors.
Data Source
AI summary
Aspects of the disclosure provide methods and apparatus for handling Read Disturb and block errors in a non-volatile memory (NVM) device. An error level of both an aggressor page that causes Read Disturb errors and an error level of adjacent victim pages are obtained. The error level of the victim page is compared against a predetermined threshold error level to determine if the victim page is experiencing a high level of bit errors. If so, then the error level of the aggressor page is compared to the error level of the victim page to determine whether Read Disturb errors are actually occurring due to host reads of the aggressor page. By looking at both the aggressor and victim error levels, a more accurate determination of Read Disturb errors may be obtained, resulting in less unnecessary relocations of pages and blocks within an NVM for mitigating Read Disturb effects.