Threshold-Based Chunk Allocation for Distributed Storage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Distributed storage systems face capacity exhaustion issues due to uncontrolled allocation of storage chunks, leading to a situation where no new chunks can be allocated, as both deleting user data and reclaiming unused capacity require allocating new chunks, resulting in a lack of free storage space.
Innovation Solution
Implementing threshold-based mechanisms to limit storage capacity by disabling chunk allocation when used capacity exceeds predetermined thresholds, allowing different users to share capacity while prioritizing critical system tasks, and using hysteresis to prevent frequent switching between accepting and rejecting new data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If storage chunk allocation is allowed without controls to maximize storage utilization, then storage capacity usage increases, but storage capacity exhaustion occurs when no free space remains
Solution Approach 1:
The patent introduces a configurable threshold parameter (default 80% of total storage capacity) that dynamically controls chunk allocation. When usage exceeds this threshold, the system transitions from allowing allocations to rejecting them, preventing exhaustion while maximizing utilization within safe limits
Solution Approach 2:
The system continuously monitors storage capacity usage and provides feedback through the threshold mechanism. When usage approaches the threshold, allocation decisions change, creating a self-regulating feedback loop that prevents capacity exhaustion while maintaining high utilization
2Quantity of substance
If user data deletion is performed to free storage space, then available capacity increases, but new chunk allocation is still required for the deletion process itself
Solution Approach 1:
The patent establishes the threshold mechanism in advance before capacity exhaustion occurs. This preliminary control structure is already in place when deletion operations are needed, allowing smooth continuation of deletion processes without requiring complex real-time decision-making about whether to permit the necessary chunk allocations
3Reliability
If strict capacity limits are enforced to prevent exhaustion, then storage capacity exhaustion is avoided, but storage resource utilization decreases
Solution Approach 1:
The patent allows storage usage to exceed 50% (partial action) and even approach 80% or higher (excessive action relative to safe limits) before enforcement kicks in. This staged approach maximizes utilization while still preventing complete exhaustion, balancing productivity and reliability
4Adaptability or versatility
If dynamic threshold adjustment is implemented to adapt to different system conditions, then system adaptability improves, but control mechanism complexity increases
Solution Approach 1:
The patent segments the storage system into chunk groups that can have different thresholds assigned. This segmentation allows different adaptability rules for different storage categories while keeping each individual control rule simple and manageable
Solution Approach 2:
The threshold mechanism serves multiple functions: it prevents capacity exhaustion, controls resource allocation, enables adaptability through configuration, and simplifies operational decisions. This multi-functionality justifies the control mechanism while delivering broad adaptability benefits
Data Source
AI summary
Systems and processes to prevent storage capacity exhaustion within distributed storage systems using chunk-based storage. The systems and processes control capacity by classifying various types of storage chunks into groups and impose used capacity thresholds on chunk groups.