PRAM Mapping Table Redundancy for Power Loss Data Integrity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory devices like PRAM face challenges in managing data states and maintaining data integrity during power supply interruptions, particularly when transitioning between valid and invalid states, leading to potential data loss and mapping table corruption.
Innovation Solution
A data management method and mapping table update method are implemented in PRAM, utilizing two mapping tables (one active and one backup) with specific mark data (0x0000 for valid and 0xFFFF for invalid states) to ensure data validity and integrity, even during power outages, by updating physical addresses corresponding to logical addresses and selecting the appropriate table for writing based on state validity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single mapping table is used to manage data in non-volatile memory, then the device complexity is reduced, but data integrity and reliability deteriorate during power supply interruptions
Solution Approach 1:
The mapping table is segmented into multiple copies (first mapping table and second mapping table) stored in different physical locations. Each mapping table contains the same logical-to-physical address mappings, allowing the system to switch between copies if one becomes corrupted or inaccessible during power interruptions.
Solution Approach 2:
Different regions of the non-volatile memory are assigned different qualities or states (valid/invalid) to indicate their reliability. The system selectively reads from or writes to specific mapping table copies based on their validity status, ensuring data integrity by preferring reliable copies while managing complexity through localized quality indicators.
2Speed
If mapping table updates are performed in-place without backup, then the write operation speed is improved, but the risk of data loss during power interruptions increases
Solution Approach 1:
Before performing an in-place update of the mapping table, the system preliminarily validates the target mapping table copy and ensures it is in a valid state. This preliminary check prevents corrupted data from being written, maintaining reliability while allowing fast in-place updates to proceed when conditions are safe.
Solution Approach 2:
The mapping table information is copied across multiple physical locations (first and second mapping tables). When updating, the system can copy valid mappings from one location to another, ensuring that even if one copy is corrupted during a power interruption, the data remains valid and recoverable from the other copy.
3Reliability
If the system continuously validates mapping table states to prevent corruption, then data reliability is improved, but the processing time and energy consumption increase
Solution Approach 1:
The validity state information is extracted as a separate metadata element (valid/invalid flag) from the mapping table data itself. This separation allows the system to quickly check validity status without validating the entire mapping table content, reducing processing time while maintaining reliability through efficient state tracking.
Solution Approach 2:
The mapping table structure includes self-validating features where the valid/invalid state is automatically updated and tracked by the system. This self-service mechanism reduces the need for continuous external validation, minimizing processing overhead while ensuring data reliability through automatic state management.
4Reliability
If multiple mapping tables are maintained with validity states, then data integrity during power interruptions is improved, but the device complexity and memory overhead increase
Solution Approach 1:
Multiple mapping table copies are merged in the sense that they contain identical logical-to-physical address mappings, but are stored in different physical locations with validity flags. This merging approach provides redundancy for reliability while the shared mapping logic reduces the overall complexity of managing multiple independent structures.
Solution Approach 2:
The system discards or invalidates mapping table copies that become corrupted or outdated, and recovers by switching to valid copies or regenerating mappings from valid data. This discard-and-recover mechanism simplifies management by allowing the system to forget invalid states and rely on valid ones, reducing complexity through selective memory management.
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 ensures data validity and integrity by maintaining valid states during power interruptions and allowing for secure data management, preventing data loss and corruption, even when power is abruptly cut off or re-applied.
Implementation Method 1
PRAM uses a phase change material, e.g., germanium (Ge), antimony (Sb) and tellurium (Te), to obtain signal changes of 0 and 1 for information processing. The two states include a crystalline state and an amorphous state.
Implementation Method 2
For the phase change material to enter the amorphous state, it is heated to its melting point, e.g., through a resistance heat
Data Source
AI summary
A data management method of a non-volatile memory device includes writing data and representing a state of the data. The state includes one of multiple possible states. A state of the multiple possible states corresponding to a final operation is determined as a valid state of the data.