SSD Data-Digest Mapping for Silent Corruption Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing SSDs face silent corruption issues due to soft errors, which can lead to incorrect data retrieval without detection by error correction techniques, especially in large data sets, increasing resource burden and power consumption.
Innovation Solution
Storing data and its integrity digest in separate memory locations with distinct mapping table entries to prevent silent corruption, ensuring data integrity without additional storage or processing overhead.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If redundant sets of data are created and stored to detect silent corruption, then data integrity is improved, but memory resources and processing resources are significantly increased
Solution Approach 1:
The patent segments the data storage system into two distinct components: the original data and its corresponding digest (integrity verification data). Each is stored in separate memory locations with separate mapping table entries, allowing independent management and verification without requiring redundant copies of the entire data set.
Solution Approach 2:
Instead of creating redundant copies of the actual data, the patent creates a compact digest (hash or checksum) that serves as a lightweight copy for verification purposes. This digest is stored separately and used to verify data integrity without requiring substantial additional memory resources.
2Reliability
If redundant sets of data are created and stored to detect silent corruption, then data integrity is improved, but processing resources and bandwidth are significantly increased
Solution Approach 1:
The patent replaces resource-intensive redundant data copies with a compact digest representation. This digest requires minimal processing power to generate and verify, dramatically reducing the computational burden compared to creating, storing, and comparing multiple full data sets.
Solution Approach 2:
The patent transforms the data verification approach by changing from comparing entire data sets to comparing compact digests (hash values or checksums). This parameter change from full-data comparison to digest comparison significantly reduces processing resources and bandwidth requirements while maintaining detection capability.
3Reliability
If separate mapping table entries are used for data and digest, then silent corruption detection is improved, but device complexity is increased
Solution Approach 1:
The patent segments the mapping table functionality into separate entries for data and digest, allowing independent addressing and verification. This segmentation enables the system to track and verify data integrity without requiring complex cross-referencing or interdependent data structures.
Data Source
AI summary
Encoded information, including first data and second data that was derived using the first data, is received. The second data can be used to determine the accuracy of the first data. The first data is stored in a first memory location that has a first address, and the second data is stored in a second memory location that has a second address. First information that is useful for determining the first address is stored, and second information that is useful for determining the second address is stored. Accessing the first data using the first information also causes the second data to be accessed using the second information.