Storage Metadata Checksum Segmentation for I/O Efficiency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing storage systems face performance degradation and increased I/O operations when handling large quantities of IO requests due to the need to validate data using checksums, which are typically stored alongside the data, leading to inefficiencies and potential misdirected writes.

Innovation Solution

Storing checksum information separately from the data in mapping metadata, allowing for efficient validation and error detection without additional I/O operations, and enabling the storage system to handle misdirected writes by maintaining updated checksums in metadata.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If checksum information is stored alongside the data on the storage device, then data validation can be performed, but additional I/O operations are required to read the checksum, degrading performance

Engineering Contradiction:
Improvedata validationVSAvoidI/O performance
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent segments the storage system into two distinct components: data storage area and metadata storage area. The checksum information is separated from the actual data and stored in the metadata area, allowing independent access to checksums without reading the entire data block. This segmentation enables the system to retrieve only the necessary validation information, improving I/O performance while maintaining data validation capability.

Inventive Principle:
Principle #1Segmentation

2Productivity

If checksum information is stored in mapping metadata separately from data, then I/O operations are reduced, but the complexity of managing mapping metadata increases

Engineering Contradiction:
ImproveI/O efficiencyVSAvoidmetadata management
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent merges the checksum information with the mapping metadata structure, combining multiple functions (data location tracking, data validation, and mapping information) into a single integrated metadata system. This consolidation allows the storage system to manage checksums alongside existing metadata without requiring separate storage mechanisms, thereby improving I/O efficiency while controlling the increase in complexity through unified management.

Inventive Principle:
Principle #5Merging (Combining)

3Reliability

If checksum validation is performed by reading checksum from storage device, then data integrity can be verified, but storage system efficiency decreases due to additional read operations

Engineering Contradiction:
Improvedata integrity verificationVSAvoidstorage system efficiency
Core Design Contradiction:
ReliabilityVSLoss of energy

Solution Approach 1:

The patent performs preliminary action by pre-computing and pre-storing checksum values in the mapping metadata when data is written to the storage device. This allows the system to perform data integrity verification by simply reading the pre-computed checksum from metadata without requiring additional read operations from the storage device, thereby maintaining reliable verification while improving storage system efficiency and reducing energy consumption.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10120797B1Managing mapping metadata in storage systems
Publication Date: 2018.11.06 EMC IP HLDG CO LLC
  • US10120797B1 patent drawing
  • US10120797B1 patent drawing
  • US10120797B1 patent drawing

AI summary

A method is used in managing mapping metadata in storage systems. A request is received to access data organized on a storage device of a storage system. Checksum information is used for validating the data. The checksum information is stored on the storage system separate from a location at which the data has been stored.