Dynamic Garbage Threshold Adjustment for Block Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing block storage systems face challenges in efficiently reclaiming storage space due to fixed garbage thresholds, which require manual intervention and monitoring, leading to inefficiencies and potential storage space wastage.
Innovation Solution
A system that dynamically adjusts the garbage threshold based on various parameters such as storage space, ingestion rate, reclamation speed, and amount of unreclaimable garbage, using predictive models to automatically optimize storage capacity without manual intervention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If a fixed garbage threshold is used in block storage systems, then the system is simple to operate, but storage space is wasted due to inefficient reclamation
Solution Approach 1:
The patent implements dynamic garbage threshold adjustment by continuously monitoring storage metrics (garbage size, storage capacity, ingestion rate, reclamation speed) and automatically modifying the threshold value. This transforms the static fixed threshold into a dynamic parameter that adapts to changing system conditions, maximizing storage reclamation efficiency without requiring manual intervention.
Solution Approach 2:
The system establishes a feedback loop where storage metrics are continuously measured, correlated with garbage threshold values, and used to adjust future threshold decisions. The correlation between garbage size and threshold is determined based on historical data, creating a self-learning mechanism that improves storage efficiency over time while maintaining system simplicity.
2Productivity
If manual monitoring and intervention are used to adjust garbage thresholds, then the system requires less computational resources, but storage reclamation efficiency is reduced
Solution Approach 1:
The patent enables the storage system to automatically monitor its own metrics, correlate data to determine optimal thresholds, and adjust garbage collection parameters without external intervention. The system serves itself by using its own operational data to make intelligent decisions about storage reclamation, eliminating the need for manual monitoring while maximizing reclamation efficiency.
Solution Approach 2:
The system dynamically changes operational parameters (garbage threshold, reclamation timing) based on correlated analysis of multiple metrics. By transforming static parameters into dynamic variables that respond to system conditions, the patent achieves high reclamation efficiency through automated parameter optimization rather than manual adjustment.
3Quantity of substance
If aggressive garbage collection is performed to maximize storage reclamation, then storage capacity increases, but resource usage increases
Solution Approach 1:
The patent applies partial action by selectively performing garbage collection only when metrics indicate it is beneficial. Rather than continuously aggressive collection, the system uses correlation analysis to determine the optimal threshold and timing, applying reclamation effort only when it will effectively increase storage capacity without wasting resources on unnecessary operations.
Solution Approach 2:
The system dynamically adjusts the garbage collection threshold parameter based on correlated metrics including current storage capacity, ingestion rate, and reclamation speed. This parameter adaptation allows the system to balance reclamation aggressiveness with resource conservation, increasing storage capacity only when the cost of collection is justified by the available resources and expected benefit.
Data Source
AI summary
A system can determine a first correlation between respective percentages of stored garbage and respective amounts of garbage of a block storage system based on determining the respective amounts of garbage among first blocks of the respective blocks that satisfy respective criterions of the respective percentages of stored garbage. The system can, based on the first correlation, determine a second correlation between an estimated throughput applicable to reclaiming garbage in the block storage system and the respective amounts of garbage of the block storage system. The system can, based on the first correlation and the second correlation and for a specified target reclamation throughput, determine a corresponding first percentage of stored garbage of the respective percentages of stored garbage. The system can perform copy-forward garbage collection on second blocks of the block storage system that satisfy a criterion defined with respect to the first percentage of stored garbage.