Asymmetric Data Striping for NAND Defect Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current data striping methods in NAND storage devices face inefficiencies due to the randomness of defect locations, leading to variations in available blocks across slices, resulting in either insufficient or excessive blocks per slice, which can fail to meet the target volume size and lead to resource wastage and high yield issues.
Innovation Solution
Implementing an asymmetric data striping approach where the number of mapped and skipped DLBAs varies across slices based on their defect ratios, using a skip map to dynamically distribute data across slices, ensuring each slice's volume size can differ while maintaining the overall target volume size, thereby optimizing block utilization and reducing resource wastage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If data striping is implemented with fixed equal distribution across slices, then the system is simple to manage, but it cannot accommodate varying defect ratios across slices leading to insufficient or excessive blocks per slice
Solution Approach 1:
The patent applies asymmetric data striping where each slice is assigned a different number of blocks based on its defect ratio. Slices with lower defect ratios receive more blocks while slices with higher defect ratios receive fewer blocks. This asymmetric distribution allows each slice to have an appropriate number of available blocks for its specific defect characteristics, resolving the contradiction between adaptability to defect distribution and management complexity.
Solution Approach 2:
The patent implements local quality by tailoring the block allocation to each individual slice's defect characteristics. Instead of uniform treatment, each slice receives customized block assignment based on its specific defect ratio, allowing optimal utilization of available blocks in each local region while maintaining overall system functionality.
2Loss of energy
If symmetric data striping is used with equal blocks per slice, then resource allocation is simple, but it causes resource wastage when some slices have excessive blocks due to random defect locations
Solution Approach 1:
The asymmetric block distribution strategy allocates fewer blocks to slices with higher defect ratios and more blocks to slices with lower defect ratios. This prevents resource wastage by ensuring each slice receives only the necessary number of blocks for its actual capacity, eliminating the inefficiency of symmetric allocation where all slices receive equal blocks regardless of their defect characteristics.
Solution Approach 2:
The patent changes the allocation parameter from fixed equal distribution to variable distribution based on defect ratios. By dynamically adjusting the number of blocks per slice according to its defect characteristics, the system optimizes resource utilization and reduces wastage while maintaining manageable complexity through parameter-based control.
3Productivity
If fixed volume size is enforced for all slices, then consistency is maintained, but it prevents optimization of block utilization based on actual defect ratios
Solution Approach 1:
The patent introduces asymmetric volume sizes for different slices based on their defect ratios. Slices with lower defect ratios can achieve higher volume sizes while slices with higher defect ratios have reduced volumes. This asymmetric approach optimizes block utilization efficiency by allowing each slice to operate at its optimal capacity rather than being constrained by a fixed uniform volume limit.
Solution Approach 2:
The system transitions from static fixed volume assignment to dynamic volume adjustment based on defect ratios. The volume size of each slice is determined dynamically according to its actual defect characteristics, enabling optimal block utilization while maintaining overall system consistency through controlled variability in slice volumes.
Data Source
AI summary
A storage device implements striping logic with respect to a plurality of slices, each slice including one or more storage media, such as NAND flash dies. Data operations are distributed among the slice in an unequal manner such that the frequency of selection of a slice decreases with number of defects in the NAND dies of that slice. For example, data operations may be distributed in a round-robin fashion with some slices being skipped periodically. In some embodiments, a skip map may be used that maps host addresses (HLBA) to a particular slice and device address (DLBA) in that slice, the skip map implementing the skipping of slices. The skip map may be smaller than the size of the storage device such that each HLBA is mapped to a zone of the storage device and a slice and offset within that zone are determined according to the skip map.