NAND Data Striping Across Planes for Power-Failure Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing NAND devices face challenges in efficiently handling data loss and power failure scenarios, particularly in ensuring data integrity and system reliability, particularly in ensuring data integrity and system reliability, particularly in ensuring data integrity and system reliability, particularly in ensuring data integrity and system reliability, particularly in ensuring data integrity and system reliability, particularly in ensuring data integrity and system robustness, especially in the context of NAND memory devices.
Innovation Solution
Implementing an improved NAND data placement schema that stripes data portions across different page lines and planes, coupled with parity information and system reliability, particularly in ensuring data integrity and system robustness, specifically in enhancing data protection and system reliability, particularly in ensuring data protection and system reliability, particularly in enhancing data integrity and system reliability, particularly in ensuring data integrity and system robustness, especially in the context of NAND memory devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is stored in traditional NAND architecture without distributed placement, then device complexity is reduced, but data integrity and reliability deteriorate due to vulnerability to power failures and programming errors
Solution Approach 1:
The patent divides data into multiple portions and distributes them across different page lines and planes within the NAND device. This segmentation ensures that a power failure or programming error affecting one page line or plane does not corrupt the entire data set, as other portions remain intact and can be used for recovery through parity information.
Solution Approach 2:
The patent extends data distribution from a single-plane architecture to multi-plane architecture, utilizing the plane dimension to further separate data portions. By distributing data across multiple planes in addition to multiple page lines, the system creates redundant spatial distribution that enhances fault tolerance without requiring multiple physical devices.
2Reliability
If data portions are distributed across multiple page lines and planes, then reliability improves through fault tolerance, but device complexity increases due to enhanced data placement schema
Solution Approach 1:
The patent divides data into multiple portions and distributes them across different page lines and planes within the NAND device. This segmentation ensures that a power failure or programming error affecting one page line or plane does not corrupt the entire data set, as other portions remain intact and can be used for recovery through parity information.
Solution Approach 2:
The patent creates a data placement schema that serves multiple functions simultaneously: it enables normal data storage operations, provides fault tolerance against power failures, protects against programming errors, and facilitates data recovery through parity information. This multi-functional approach consolidates what would otherwise require separate mechanisms into a unified system.
3Reliability
If traditional NAND storage is used without distributed data placement, then ease of operation is maintained, but data protection capability deteriorates
Solution Approach 1:
The patent implements automatic data distribution across multiple page lines and planes through the controller, which handles the complexity of placement and recovery operations transparently. The system self-manages the distribution of data portions and parity information, and automatically performs recovery operations when errors are detected, eliminating the need for user intervention in these complex processes.
Solution Approach 2:
The controller acts as an intermediary between the host system and the NAND memory array, managing the complex data distribution and recovery operations. It translates simple host write commands into distributed data placement across multiple page lines and planes, and handles recovery operations when errors occur, shielding the user from the underlying complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Disclosed in some examples are improvements to data placement architectures in NAND that provide additional data protection through an improved NAND data placement schema that allows for recovery from certain failure scenarios. The present disclosure stripes data diagonally across page lines and planes to enhance the data protection. Parity bits are stored in SLC blocks for extra protection until the block is finished writing and then the parity bits may be deleted.