Dynamic Allocation Unit Size Selection for File Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing file systems face inefficiencies due to fixed allocation unit (AU) sizes, leading to wasted storage space and performance degradation when AU sizes do not match with input/output (IO) operations, requiring costly system migration to adjust AU sizes.
Innovation Solution
A method for dynamically determining a candidate AU size based on statistical analysis of IO requests, allowing for adaptive AU size selection that optimizes storage usage and performance by matching AU sizes with specific IO patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a fixed AU size is used in the file system, then the system structure is simple and stable, but storage space is wasted and performance degrades when AU size does not match IO operations
Solution Approach 1:
The patent implements dynamic AU size selection by introducing a statistic module that collects IO request data and an AU size determination module that selects optimal AU sizes based on statistical analysis. This transforms the static, fixed AU size system into a dynamic one that adapts to actual IO patterns, resolving the contradiction between system stability and storage efficiency.
Solution Approach 2:
The patent changes the parameter of AU size from a fixed value to a dynamically determined value based on IO statistics. By collecting IO request data, analyzing patterns, and selecting AU sizes that best match actual usage, the system optimizes storage efficiency while maintaining operational stability through evidence-based parameter adjustment.
2Productivity
If the AU size is changed to optimize storage space, then storage efficiency improves, but system migration cost increases
Solution Approach 1:
The patent performs preliminary action by collecting IO statistics and determining optimal AU sizes before actual file storage operations. This advance planning allows the system to configure appropriate AU sizes proactively, avoiding the need for costly system migrations later while achieving storage optimization.
Solution Approach 2:
The system performs self-service by automatically collecting IO statistics, analyzing patterns, and determining optimal AU sizes without requiring external intervention or system migration. The file system autonomously optimizes its own configuration, eliminating migration costs while improving storage efficiency.
3Adaptability or versatility
If statistical analysis is performed on IO requests to determine AU size, then AU size matching with IO operations improves, but system complexity increases
Solution Approach 1:
The patent segments the AU size determination process into distinct functional modules: an IO request collection module, a statistic module for analyzing IO patterns, and an AU size determination module. This segmentation makes the complex statistical analysis manageable and maintainable while achieving adaptive AU size matching.
Solution Approach 2:
The patent introduces intermediary modules (statistic module and AU size determination module) that mediate between raw IO requests and the final AU size selection. These intermediaries process and analyze IO data, transforming complex raw information into actionable AU size recommendations, thereby managing system complexity while improving adaptability.
4Ease of operation
If a default AU size is used for all files, then the file system operation is simple and fast, but performance degrades for files with different IO patterns
Solution Approach 1:
The patent applies local quality by determining AU sizes specifically for each file based on its own IO patterns rather than using a universal default. The statistic module collects IO data for individual files, and the AU size determination module selects optimal sizes tailored to each file's characteristics, improving performance while maintaining operational simplicity through automated per-file optimization.
Data Source
AI summary
Techniques perform file storage. Such techniques involve determining a candidate allocation unit (AU) size for storing data based on a statistic of an AU size matching with a write request during a statistic period, and storing a new file using the determined candidate AU size to store the new file. Accordingly, storage space is saved and reading and writing performance are improved.