SSD DRAM Patrol Read Failure Buffer ECC
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The reliability of dynamic random access memory (DRAM) in solid-state drives (SSDs) is compromised due to failure issues, leading to potential CPU exceptions and impaired SSD operations, necessitating effective management and error correction mechanisms.
Innovation Solution
A method and storage device that periodically perform patrol read operations to collect failure information, store it in a buffer memory, and use this information for subsequent error correction operations to enhance DRAM reliability, including ECC decoding using erasure symbols inferred from failure history.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If process refinement is applied to DRAM to increase storage capacity, then storage density is improved, but cell reliability deteriorates
Solution Approach 1:
The system performs patrol read operations periodically to detect potential failures before they cause data corruption. Failure information is collected and stored in advance, allowing the ECC decoder to use this pre-acquired information during subsequent error correction operations, thereby preventing unrecoverable errors.
Solution Approach 2:
The system accumulates failure information from patrol reads and stores it in a buffer memory, creating a protective cushion of diagnostic data. This pre-collected failure information serves as a buffer that enables more effective error correction when actual errors occur, compensating for the reduced cell reliability caused by process refinement.
2Speed
If traditional ECC operations are performed without failure information, then operation speed is maintained, but error correction capability deteriorates
Solution Approach 1:
Failure information is collected and stored in advance through periodic patrol read operations. When a read operation requires error correction, this pre-collected failure information is immediately available to enhance the ECC decoding process, providing improved error correction capability without adding significant processing delay.
Solution Approach 2:
The patrol read operations continue periodically in the background, continuously gathering failure information without interrupting normal read operations. This ensures that the error correction capability is continuously enhanced by the most recent failure information while maintaining operational throughput.
3Reliability
If patrol read operations are performed periodically to collect failure information, then reliability is improved, but processing overhead increases
Solution Approach 1:
Patrol read operations are performed periodically rather than continuously, collecting failure information at intervals. This periodic approach provides sufficient failure data to enhance error correction while minimizing the processing overhead and avoiding continuous interference with normal read operations.
Solution Approach 2:
A buffer memory is introduced as an intermediary component to store failure information. This buffer decouples the patrol read operations from the main read path, allowing failure information to be accumulated without blocking normal data flow and reducing processing overhead in the critical data path.
4Reliability
If uncorrectable errors occur in DRAM, then data integrity is compromised, but with failure information loading, error correction capability is restored
Solution Approach 1:
The system uses failure information from patrol reads as feedback to enhance the ECC decoding process. When an uncorrectable error is detected, the feedback mechanism loads relevant failure information from the buffer and uses it to guide a second error correction operation, thereby restoring error correction capability and preventing data integrity loss.
Data Source
AI summary
A method of operating a storage device includes: periodically performing a patrol read operation on a memory device; storing failure information according to the patrol read operation in a buffer memory; generating an uncorrectable error as a result of a first error correction operation performed on read data of the memory device; loading the failure information from the buffer memory; and performing a second error correction operation on the read data by using the failure information.