Memory Array Error-Code Switching for Data Integrity Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face challenges in ensuring data integrity across different types of storage devices, as error control codes suitable for one type of device may not be compatible with others, leading to issues in error detection and correction.
Innovation Solution
The implementation of a system that uses a combination of error control codes such as Reed Solomon and Hamming codes, or even/odd parity techniques, to distribute data records across multiple memory devices, allowing for error detection and correction even if one device experiences degradation, and dynamically switches error control techniques based on the need for error correction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single type of error control code is used for all memory devices, then the system is simple to implement, but data integrity cannot be maintained across devices with different error characteristics
Solution Approach 1:
The patent applies local quality by selecting different error control codes based on the specific characteristics of each memory device or data region. The system identifies devices with higher error rates and applies more robust error control codes (such as Reed-Solomon) to those specific devices, while using simpler codes (such as Hamming or parity) for devices with lower error rates. This localized approach ensures data integrity is maintained where needed without unnecessarily complicating the overall system.
Solution Approach 2:
The patent implements parameter changes by dynamically selecting error control codes based on measured error rates and device characteristics. The system monitors device performance and adjusts the error control parameters (code type, code strength) accordingly. This allows the system to adapt to changing device conditions and maintain optimal data integrity while minimizing complexity by using simpler codes when conditions permit.
2Reliability
If robust error control codes are applied to all devices, then data integrity is improved, but the number of error control bits increases reducing storage efficiency
Solution Approach 1:
The patent applies local quality by concentrating robust error control mechanisms only on memory devices or data regions that exhibit higher error rates. Instead of uniformly applying strong error control codes to all devices, the system identifies problematic devices and applies enhanced error control (such as Reed-Solomon with more correction bits) only to those specific locations. This localized application maintains data integrity for vulnerable data while preserving storage capacity in regions that require less protection.
Solution Approach 2:
The patent implements partial action by applying error control codes at different strengths to different portions of the data storage system. Rather than using maximum-strength error control uniformly, the system applies just enough error control capability to each device based on its actual error characteristics. This partial application of error control ensures adequate protection where needed while minimizing the overhead of error control bits in regions where simpler protection suffices, thereby optimizing the balance between reliability and storage capacity.
Data Source
AI summary
A method includes detecting that a first device in a memory array has degraded, the first device storing a portion of a data record, wherein the data record is encoded using a first error control technique. The method continues with recovering the data record using portions of the data record stored in devices other than the first device in the memory array and encoding the data record using a second error control technique. The method also includes storing the data record in the devices of the memory array other than the first device.