RAID-6 Triple Disk Failure Recovery Parity Scheme

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current RAID systems face challenges in efficiently recovering data after multiple disk failures, particularly due to bottlenecks and high overhead in updating and rebuilding processes, especially when dealing with single and double disk failures, which can lead to data loss and prolonged recovery times.

Innovation Solution

The implementation of a RAID-6 system with a triple redundancy scheme that includes parity blocks stored by rows and diagonals, allowing for the recovery of data from three failed disks by using a combination of row and diagonal parity blocks to distribute parity information across multiple disks, reducing bottlenecks and overhead in data recovery operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If RAID-1 mirroring is used to protect against disk failure, then data reliability is improved, but capacity utilization deteriorates (50% loss)

Engineering Contradiction:

Improvedata reliabilityVSAvoidcapacity utilization

Core Design Contradiction:

ReliabilityVSQuantity of substance

Solution Approach 1:

The patent changes the redundancy parameter from full mirroring (RAID-1) to partial parity-based redundancy (RAID-4/5/6), where only the necessary parity information is stored rather than complete data copies. This allows achieving the same reliability goal with significantly improved capacity utilization (90% in RAID-4, 91.67% in RAID-5, 95.24% in RAID-6).

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

Instead of uniformly duplicating all data across disks (global mirroring), the patent applies local parity calculation where each disk stores parity information only for specific data blocks. This localized approach reduces overall redundancy overhead while maintaining data recovery capability for failed disks.

Inventive Principle:

Principle #3Local quality

2Quantity of substance

If RAID-4 with dedicated parity disk is used to improve capacity utilization, then capacity utilization is improved (90%), but system bottleneck deteriorates (parity disk becomes bottleneck)

Engineering Contradiction:

Improvecapacity utilizationVSAvoidsystem throughput

Core Design Contradiction:

Quantity of substanceVSProductivity

Solution Approach 1:

The patent segments the parity storage function from a single dedicated disk (RAID-4) and distributes it across multiple disks (RAID-5). Each disk in the array contributes to storing parity information, eliminating the single-point bottleneck and allowing parallel access during write operations.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent transitions from a centralized parity architecture (single parity disk in RAID-4) to a distributed parity architecture (multiple parity disks in RAID-5). This dimensional change in the storage topology allows simultaneous read/write operations across multiple disks without contending for a single parity disk resource.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Productivity

If RAID-5 distributed parity is used to eliminate bottleneck, then system throughput is improved, but reliability deteriorates (cannot tolerate double disk failure)

Engineering Contradiction:

Improvesystem throughputVSAvoidfault tolerance

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The patent adds an extra layer of redundancy (sixth disk) that serves as a cushion against double disk failures. This additional disk provides backup parity information that can compensate for the loss of two data disks, extending fault tolerance from single-disk (RAID-5) to double-disk failure scenarios.

Inventive Principle:

Principle #11Beforehand cushioning (Prior cushioning)

Solution Approach 2:

The patent creates a composite storage system (RAID-6) that combines the distributed parity structure of RAID-5 with an additional redundancy layer. This composite architecture integrates multiple protection mechanisms, achieving both high throughput (from distributed parity) and enhanced reliability (from double-failure tolerance).

Inventive Principle:

Principle #40Composite materials

4Reliability

If more redundancy disks are added to tolerate more failures, then reliability is improved, but device complexity deteriorates

Engineering Contradiction:

Improvefault toleranceVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent implements dynamic recovery strategies where the system adapts its reconstruction approach based on the specific failure scenario. For single-disk failures, it uses efficient single-parity reconstruction; for double-disk failures, it activates the second parity layer. This dynamic behavior optimizes the balance between reliability and complexity by only engaging additional redundancy when needed.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS9063910B1Data recovery after triple disk failure

Publication Date: 2015.06.23 EMC IP HLDG CO LLC

AI summary

In one aspect, a redundant array of independent disk (RAID) memory storage system includes a plurality of data storage disks comprising data blocks, a first redundancy storage disk comprising parity blocks that are a parity by row of the data blocks in the data storage disks, a second redundancy storage disk comprising parity blocks storing parities of diagonals of the data blocks in the data storage disks, a third redundancy storage disk comprising parity blocks storing parities of diagonals of the data blocks in the data storage disks and circuitry configured to recover data from three failed storage disks.