Magnetic Disk Device Dual Refresh Threshold Strategy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Magnetic disk devices face challenges in executing track ECC processing due to random overwrite issues and side erase effects, which hinder error correction and data integrity, especially when the number of writes exceeds a certain threshold, leading to uncorrectable sectors and reduced track per inch (TPI) performance.
Innovation Solution
The magnetic disk device employs a dual refresh threshold strategy, setting a high threshold for correctable areas and a low threshold for uncorrectable areas, and adjusts the refresh frequency accordingly, allowing for read modify write operations to maintain data integrity and improve TPI by differentiating the rewrite frequencies of sectors based on their error correction capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If track ECC processing is executed to correct errors using parity sectors, then data reliability is improved, but the system cannot handle random overwrites that occur in conventional magnetic recording formats
Solution Approach 1:
The track is divided into multiple sectors, with specific sectors designated as parity sectors and others as data sectors. This segmentation allows the system to maintain error correction capability while accommodating random overwrites of data sectors without affecting the integrity of parity sectors needed for ECC processing.
Solution Approach 2:
Different sectors are assigned different functions: data sectors for storage and parity sectors for error correction. This local differentiation enables the system to tolerate random overwrites in data sectors while preserving the error correction functionality provided by dedicated parity sectors.
2Reliability
If refresh operations are performed frequently to prevent side erase and maintain data integrity, then data reliability is improved, but write performance deteriorates due to increased rewrite operations
Solution Approach 1:
The refresh threshold is dynamically adjusted based on the correctability status of sectors. Correctable sectors use a higher refresh threshold (reducing refresh frequency), while uncorrectable sectors use a lower threshold (increasing refresh frequency). This dynamic adaptation optimizes the balance between data integrity and write performance.
Solution Approach 2:
The system changes the refresh threshold parameter based on sector error correction status. By adjusting this critical parameter, the system adapts refresh frequency to actual data conditions, preventing unnecessary refresh operations on healthy data while intensifying refresh on degraded sectors.
3Device complexity
If a single refresh threshold is used for all sectors, then system complexity is reduced, but the system cannot optimize performance for sectors with different error correction capabilities
Solution Approach 1:
Different refresh thresholds are applied to different sectors based on their error correction status. This local customization allows optimization of refresh operations for each sector's specific conditions, improving overall TPI performance without requiring complex global management mechanisms.
Solution Approach 2:
The system preliminarily determines the correctability status of sectors and sets appropriate refresh thresholds in advance. This preliminary classification enables subsequent refresh operations to be efficiently performed with predetermined thresholds, avoiding complex real-time decision-making while optimizing performance.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances data reliability by maintaining higher refresh frequencies for correctable areas and lower frequencies for uncorrectable areas, thereby improving areal density capability and maintaining performance across multiple heads, even when writes exceed the threshold, thus addressing the limitations of conventional magnetic recording formats.
Implementation Method 1
a head writing data to the disk and reading data from the disk
Implementation Method 2
a head writing data to the disk and reading data from the disk
Implementation Method 3
side erase that the data is erased may occur due to the influence of magnetic flux leakage from the head or the like (adjacent track interference: ATI)
Data Source
AI summary
According to one embodiment, a magnetic disk device includes a disk, a head, and a controller setting a rewrite threshold value for executing a rewrite process of different tracks in a first sector group including at least one first sector continuous from a first parity sector in which error correction processing in units of tracks is executable based on the first parity sector and including the first parity sector, and a second sector group including at least one second sector continuous in which the error correction processing in units of tracks is unexecutable, and rewriting the first sector group and the second sector group with different frequencies.