Partial Recall Deduplication Mechanism for Storage Latency

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Data deduplication systems face latency and resource consumption issues due to full file recall, especially when dealing with large files, which affects throughput and introduces significant I/O overload.

Innovation Solution

Implementing a partial deduplication mechanism that allows only relevant chunks of a file to be recalled, with tracking information maintained to differentiate between recalled and deduplicated data, enabling efficient management and re-deduplication by scanning only recalled file ranges.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If full file recall is implemented, then data access is enabled, but latency increases and I/O overload occurs

Engineering Contradiction:
Improvedata accessVSAvoidlatency
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The patent segments the file into multiple chunks and selectively recalls only the necessary chunks rather than the entire file. This segmentation allows the system to divide the recall operation into smaller, more manageable units that can be processed in parallel and reduce overall latency.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent extracts and recalls only the specific chunks that are needed for the current operation, leaving the rest of the file data in the deduplicated storage. This selective extraction minimizes the amount of data that needs to be transferred and processed, thereby reducing latency and I/O overhead.

Inventive Principle:
Principle #2Taking out (Extraction)

2Reliability

If full file recall is implemented, then data access is enabled, but resource consumption increases

Engineering Contradiction:
Improvedata accessVSAvoidresource consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The patent segments the file into multiple chunks and selectively recalls only the necessary chunks rather than the entire file. This segmentation allows the system to divide the recall operation into smaller, more manageable units that can be processed in parallel and reduce overall latency.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by recalling only the minimum necessary chunks required for the current operation rather than the entire file. This partial recall approach reduces resource consumption by avoiding the overhead of transferring and processing unnecessary data while still enabling the required data access functionality.

Inventive Principle:
Principle #16Partial or excessive action

3Reliability

If full file recall is implemented, then data access is enabled, but deduplication throughput decreases

Engineering Contradiction:
Improvedata accessVSAvoiddeduplication throughput
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent segments the file into multiple chunks and selectively recalls only the necessary chunks rather than the entire file. This segmentation allows the system to divide the recall operation into smaller, more manageable units that can be processed in parallel and reduce overall latency.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies partial action by recalling only the minimum necessary chunks required for the current operation rather than the entire file. This partial recall approach reduces resource consumption by avoiding the overhead of transferring and processing unnecessary data while still enabling the required data access functionality.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP2652622B1Partial recall of deduplicated files
Publication Date: 2020.11.18 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP2652622B1 patent drawingFigure 1
  • EP2652622B1 patent drawingFigure 2~4
  • EP2652622B1 patent drawingFigure 5

AI summary

The subject disclosure is directed towards changing a file from a fully deduplicated state to a partially deduplicated state in which some of the file data is deduplicated in a chunk store, and some is recalled into the file, that is, in the file's storage volume. A partial recall mechanism such as in a file system filter tracks (e.g., via a bitmap in a file reparse point) whether file data is maintained in the chunk store or has been recalled to the file. Data is recalled from the chunk store as needed, and committed (e.g., flushed) to the file. Also described is efficiently returning the file to a fully deduplicated state by using the tracking information to determine which parts of the file are already deduplicated into the chunk store so as to avoid their further deduplication processing.