RAID DMA DIF Checking for Silent Data Corruption Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In RAID systems, data corruption during transfer can lead to silent data corruption, negating the redundancy benefits, and existing methods for data integrity verification are CPU-intensive and inefficient.

Innovation Solution

A DMA controller performs Data Integrity Field (DIF) checking concurrently with data transfers, offloading CPU cycles and enhancing data integrity verification efficiency by using a combination of RAID operations and DIF checking, which includes generating and verifying DIFs and syndrome blocks within the DMA controller.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If DIF checking is implemented during data transfers, then data integrity verification is enhanced, but CPU cycles are consumed

Engineering Contradiction:

Improvedata integrityVSAvoidCPU cycles

Core Design Contradiction:

ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent extracts the DIF checking function from the CPU and implements it in the DMA controller. This separation allows data integrity verification to be performed independently of the CPU, eliminating the trade-off between reliability enhancement and CPU cycle consumption.

Inventive Principle:

Principle #2Taking out (Extraction)

2Productivity

If RAID operations are performed without DIF checking, then CPU cycles are conserved, but data corruption goes undetected

Engineering Contradiction:

ImproveCPU efficiencyVSAvoiddata integrity

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The DMA controller serves as an intermediary that performs DIF checking on data transfers between memory and storage devices. This intermediary function enables RAID operations to maintain data integrity without requiring CPU intervention, thus preserving CPU efficiency while enhancing reliability.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Reliability

If manual DIF verification is performed by the processor, then data integrity can be checked, but I/O performance is reduced

Engineering Contradiction:

Improvedata integrity verificationVSAvoidI/O performance

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The DMA controller performs DIF checking autonomously during data transfers without requiring processor intervention. This self-service capability allows data integrity verification to occur in parallel with data movement, eliminating the performance penalty associated with manual verification and maintaining high I/O throughput.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS8583984B2Method and apparatus for increasing data reliability for raid operations

Publication Date: 2013.11.12 SK HYNIX NAND PRODUCT SOLUTIONS CORP

AI summary

A method and apparatus to enable data integrity checking of a block of data while the block of data is being transferred from a volatile memory to a non-volatile storage device is provided. The data integrity checking is performed in conjunction with Direct Memory Access operations and Redundant Array of Independent Disk (RAID) operations. In addition, data integrity checking of syndrome blocks in the RAID is performed during transfers to/from the storage devices in the RAID system and during RAID update and RAID data reconstruction operations.