FSCK Space Reservation Using ML-Based Storage Consumption Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current storage systems lack a method to accurately determine the physical storage space consumption during metadata repair processes, leading to insufficient reservation of space for successful file system check (FSCK) tool operations.
Innovation Solution
A method utilizing a machine learning model, specifically a linear regression or neural network model, to predict space consumption based on a first feature set that includes the size of logical space and other storage system parameters, allowing adjustment of reserved physical storage space to ensure successful metadata repair.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a fixed reserved value of physical storage space is allocated for FSCK tool operations, then the storage system can perform metadata repair, but the reserved space may be insufficient when the storage system scales up, leading to failed repair operations
Solution Approach 1:
The patent applies dynamics by transitioning from a fixed reserved space value to a dynamic prediction mechanism. The machine learning model continuously predicts space consumption based on current storage system features (logical space size, data growth rate, metadata complexity), allowing the reserved space to adapt automatically as the storage system scales, ensuring sufficient space is always allocated for successful metadata repair operations
Solution Approach 2:
The patent changes the parameter of reserved space from a static configuration value to a dynamically determined value based on multiple storage system parameters. The machine learning model analyzes features such as logical space size, data growth rate, and metadata complexity to predict the required physical storage space, transforming the reserved space allocation into a parameter-driven adaptive system that responds to changing storage conditions
2Reliability
If more physical storage space is reserved for the FSCK tool, then metadata repair can be performed more reliably, but storage capacity available for actual data is reduced
Solution Approach 1:
The patent optimizes the balance between repair reliability and storage utilization by using machine learning to predict the minimum necessary reserved space. Instead of allocating excessive fixed space, the model predicts the precise amount needed based on current storage system characteristics, ensuring sufficient space for repair while maximizing available capacity for actual data storage
Solution Approach 2:
The system performs self-service by automatically predicting and adjusting its own space requirements. The machine learning model continuously monitors storage system features and autonomously determines the optimal reserved space allocation, eliminating the need for manual configuration and ensuring that the reserved space is neither excessive nor insufficient
3Ease of manufacture
If traditional fixed reserved space allocation is used, then configuration is simple, but accurate prediction of space consumption during metadata repair is not achieved
Solution Approach 1:
The system implements self-service by automatically performing space consumption prediction without requiring manual configuration. The machine learning model autonomously analyzes storage system features and predicts the required reserved space, eliminating complex manual setup while achieving accurate predictions through automated feature extraction and model inference
Data Source
AI summary
Techniques for determining space consumption involve acquiring a first feature set of a storage system, wherein the first feature set comprises at least a size of logical space of the storage system. Such techniques further involve determining space consumption for file system checks of the storage system by a machine learning model based on the first feature set. Such techniques further involve adjusting a reserved value of physical storage space of the storage system in response to the determined space consumption meeting a predetermined condition. In this way, it is possible to predict a total amount of space to be consumed by a file system checking tool based on collection of data of the storage system, and to adjust a reserved value of physical storage space of the storage system based on the predicted value, so as to ensure metadata repair of the storage system.