Storage Controller Hash Comparison Reduces Memory Wear
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Nonvolatile memory devices experience reliability degradation due to increased wear from frequent data writing, leading to reduced lifespan and potential data loss, as existing technologies lack effective methods to prevent redundant writes and maintain data integrity.
Innovation Solution
A storage device with a controller that generates hash values from data and signatures to determine similarity, skipping redundant writes and maintaining data integrity by using these hash values to manage write operations and mapping information, thereby extending the lifespan of the nonvolatile memory.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data are frequently written in memory cells to maintain data availability, then data accessibility is improved, but memory cell reliability decreases due to wear
Solution Approach 1:
The controller performs preliminary hash value comparison before executing write operations to memory cells. By generating a hash value from incoming data and comparing it with hash values of previously written data, the controller identifies redundant writes in advance and prevents them, thereby reducing unnecessary wear on memory cells while maintaining data availability when needed.
2Reliability
If redundant write operations are performed to ensure data integrity, then data reliability is improved, but memory cell wear increases
Solution Approach 1:
The controller creates a hash value copy of the incoming data and compares it with stored hash values representing previously written data. This copying approach allows the controller to verify data redundancy without performing full write operations, thereby ensuring data integrity through comparison while avoiding unnecessary physical writes that would increase memory cell wear and extend device lifespan.
3Duration of action of stationary object
If hash value comparison is performed for every write operation to prevent redundant writes, then memory wear is reduced, but processing time increases
Solution Approach 1:
The controller replaces the mechanical process of actual data writing with a computational hash value comparison process. By substituting the physical write operation with a lightweight hash comparison, the system determines whether a write is redundant before committing resources, thereby reducing overall memory wear while the computational overhead of hash generation and comparison is minimal compared to full write operations.
Data Source
AI summary
A storage device includes a nonvolatile memory device, and a controller that receives a write command, data, and a signature associated with the data from an external device, generates a first hash value from the data, generates a second hash value from the signature, generates an output hash value based on the first hash value and the second hash, and detects whether the data received from the external device are previously written in the nonvolatile memory device, by using the output hash value.