Chunk Index Structure for Storage Defragmentation Overhead Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing defragmentation techniques for storage devices suffer from partial defragmentation, discontinuous data blocks, high computation overhead, and high communication overhead due to frequent interactions with the storage device.
Innovation Solution
A defragmentation method that involves acquiring chunk information upon writing requests, updating fragmentation degrees in a chunk index structure, determining the most fragmented chunk, and transmitting relevant information to the storage device for defragmentation, thereby reducing overhead and improving efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional defragmentation techniques are used, then file data can be defragmented, but computation overhead and communication overhead increase due to frequent interactions with the storage device
Solution Approach 1:
The system performs preliminary actions by maintaining a chunk index structure that tracks fragmentation degrees of all chunks before actual defragmentation is needed. This advance preparation allows the system to identify fragmented chunks and their locations without requiring frequent storage device interactions during runtime, thereby reducing computation and communication overhead while maintaining defragmentation effectiveness
Solution Approach 2:
The patent introduces an intermediary chunk index structure that acts as a mediator between the storage device and the defragmentation process. This index structure stores metadata about chunk fragmentation degrees and locations, allowing the system to make defragmentation decisions based on pre-collected information rather than frequent direct queries to the storage device, thus reducing communication overhead
2Productivity
If data is written continuously to the storage device, then data storage capacity is utilized, but file data becomes scattered and fragmented in different spaces
Solution Approach 1:
The system implements feedback by continuously updating the chunk index structure with fragmentation degree information as data is written to the storage device. This real-time feedback mechanism allows the system to monitor data continuity degradation and trigger defragmentation operations when fragmentation thresholds are exceeded, balancing storage capacity utilization with data continuity maintenance
Solution Approach 2:
The patent applies dynamics by making the chunk index structure adaptive and dynamic, automatically updating fragmentation degrees and reorganizing chunk information as data is written, read, or deleted. This dynamic structure enables the system to respond to changing data patterns and maintain optimal data organization without requiring static pre-allocation schemes
Data Source
AI summary
A defragmentation method may include: acquiring at least one chunk information of data in response to a writing request for the data, wherein the at least one chunk information may include an identification of at least one chunk and a stream identification assigned to data of the at least one chunk; updating a fragmentation degree of each of the at least one chunk and a stream to which the each of the at least one chunk belongs in a chunk index structure to obtain an updated chunk index structure, based on the at least one chunk information, wherein the chunk index structure may include identifications of a plurality of chunks, stream identifications corresponding to the plurality of chunks, and fragmentation degrees of the plurality of chunks; and determining a first chunk to be defragmented, based on the fragmentation degrees of the plurality of chunks in the updated chunk index structure.