Allocation Unit Bitmap for Storage Rebuild Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In storage systems, when a drive fails or goes offline, unnecessary rebuilds are triggered even if no data modifications occurred during the degraded state, leading to excessive I/O load and potential data corruption.

Innovation Solution

A method that identifies an in-memory bit for an allocation unit to determine if data was modified during the degraded state, executing a rebuild only when the bit indicates modifications, and skipping the rebuild if no changes were made, thereby clearing related metadata and synchronizing the bit between nodes to avoid data corruption.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a rebuild is triggered when a drive fails or goes offline, then data consistency is ensured, but unnecessary rebuilds occur even when no data modifications happened during degraded state, leading to excessive I/O load

Engineering Contradiction:
Improvedata consistencyVSAvoidsystem I/O load
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system performs a preliminary check using a bitmap to determine whether data modifications occurred during the degraded state before initiating a rebuild. This preliminary action prevents unnecessary rebuild operations while ensuring data consistency when modifications are detected.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The bitmap mechanism automatically tracks data modification status during degraded states, enabling the system to self-determine whether a rebuild is necessary without external intervention or complex verification processes.

Inventive Principle:
Principle #25Self-service

2Reliability

If a rebuild is executed to ensure data consistency after drive failure, then reliability is improved, but system performance degrades due to excessive I/O operations

Engineering Contradiction:
Improvedata consistencyVSAvoidsystem performance
Core Design Contradiction:
ReliabilityVSPower

Solution Approach 1:

The bitmap provides preliminary information about data modification status before rebuild initiation, allowing the system to avoid unnecessary I/O-intensive rebuild operations and maintain system performance while ensuring reliability when needed.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If rebuild operations are performed frequently to maintain data consistency, then reliability is improved, but the risk of data corruption increases due to multiple rebuild attempts

Engineering Contradiction:
Improvedata consistencyVSAvoiddata corruption risk
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The bitmap automatically tracks whether data modifications occurred during degraded states, enabling the system to make accurate, automated decisions about rebuild necessity and reduce the risk of data corruption from unnecessary or incorrect rebuild operations.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS11269738B2System and method for fast rebuild of metadata tier
Publication Date: 2022.03.08 EMC IP HLDG CO LLC
  • US11269738B2 patent drawing
  • US11269738B2 patent drawing
  • US11269738B2 patent drawing

AI summary

A method, computer program product, and computer system for identifying a bit for an allocation unit. It may be determined if data has been modified on the allocation unit while degraded. A rebuild of the allocation unit may be executed when the bit is a first value. The rebuild of the allocation unit may be skipped when the bit is a second value.