Compressed Data Packing Across Disk Blocks to Reduce Space Waste

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional techniques for storing, garbage collecting, and repacking compressed data segments in fixed size disk blocks are inefficient, leading to significant waste of disk space due to partially filled blocks.

Innovation Solution

Implement a sequential packing technique that stores compressed data segments from multiple segments in a single disk block, followed by identifying and repacking garbage collectible compressed data extents (CDEs) to optimize storage efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If compressed data segments are stored one per disk block, then data integrity is maintained, but disk space is wasted due to partially filled blocks

Engineering Contradiction:

Improvedata integrityVSAvoiddisk space waste

Core Design Contradiction:

ReliabilityVSLoss of substance

Solution Approach 1:

The patent combines multiple compressed data segments into a single disk block when they are garbage collectible, thereby reducing disk space waste while maintaining data integrity through proper tracking of segment references and block associations

Inventive Principle:

Principle #5Merging (Combining)

2Productivity

If sequential packing of compressed data segments is implemented, then storage efficiency is improved, but complexity of garbage collection increases

Engineering Contradiction:

Improvestorage efficiencyVSAvoidgarbage collection complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent segments the tracking of compressed data by introducing separate data structures (compressed data extent structure and mapping structure) that divide the garbage collection task into manageable parts, reducing overall complexity while enabling sequential packing

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces mapping structures as intermediaries between disk blocks and compressed data segments, which simplify garbage collection by providing a clear reference trail without increasing operational complexity

Inventive Principle:

Principle #24Intermediary (Mediator)

3Loss of substance

If multiple compressed data segments are stored in a single disk block, then disk space utilization is improved, but difficulty of managing and tracking data increases

Engineering Contradiction:

Improvedisk space utilizationVSAvoiddata management difficulty

Core Design Contradiction:

Loss of substanceVSDifficulty of detecting and measuring

Solution Approach 1:

The patent implements feedback mechanisms through reference counting and mapping structures that automatically track which compressed data segments are referenced and their locations, simplifying management and tracking of multiple segments per block

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS20250335090A1Methods and Systems for Managing Compressed Data in Disk Blocks

Publication Date: 2025.10.30 NETAPP INC

AI summary

Methods and systems involve sequentially storing compressed data segments received at a storage system in disk blocks such that at least one of the disk blocks includes compressed data from at least two of the compressed data segments.