Timestamp-Based Flash Block Selection for Garbage Collection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accuracy of attribute information for data stored in storage devices deteriorates over time, affecting the write performance and lifetime of the storage device.
Innovation Solution
A storage device that includes a controller capable of receiving a timestamp from an external device to calibrate time information, determining the retention time of memory blocks, and selecting victim memory blocks for operations like garbage collection or wear leveling based on this timestamp.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If attribute information is received from external device, then data management is enabled, but accuracy of attribute information deteriorates over time
Solution Approach 1:
The storage device establishes a feedback mechanism by continuously monitoring the passage of time and comparing it with the received attribute information. When a predetermined time period elapses, the system triggers an update process to refresh the attribute information from the external device, ensuring accuracy is maintained despite the natural deterioration over time.
Solution Approach 2:
The system performs preliminary actions by proactively updating attribute information before complete deterioration occurs. By monitoring time passage and triggering updates at predetermined intervals, the system prevents accuracy loss rather than reacting after deterioration has significantly impacted performance.
2Quantity of substance
If garbage collection operations are performed frequently, then free space is recovered, but write performance deteriorates
Solution Approach 1:
The system dynamically changes the parameter of garbage collection frequency based on multiple factors including the age of attribute information, current storage utilization, and workload characteristics. By adjusting this parameter adaptively rather than using fixed intervals, the system optimizes the balance between recovering free space and maintaining write performance.
Solution Approach 2:
The garbage collection operation transitions from a static, periodic task to a dynamic process that adjusts its execution frequency and intensity based on real-time system conditions. The controller monitors various parameters and modulates garbage collection activity accordingly, making the system adaptable to changing workload demands and storage states.
3Duration of action of stationary object
If wear leveling operations are performed, then memory block lifetime is extended, but write performance deteriorates
Solution Approach 1:
The system dynamically adjusts wear leveling operation parameters based on the age of attribute information and current memory block usage patterns. By changing the frequency and intensity of wear leveling tasks adaptively, the system extends memory block lifetime while minimizing impact on write performance during high-demand periods.
Solution Approach 2:
Wear leveling transitions from a static, uniform distribution approach to a dynamic process that considers real-time factors such as attribute information freshness, memory block health status, and current workload. This enables the system to optimize the balance between extending component lifetime and maintaining operational performance.
Data Source
AI summary
A storage device may get a timestamp when a timestamp getting condition is satisfied, may determine a retention time of a target super memory block according to time information calibrated on the basis of the timestamp, and may determine whether to select the target super memory block as a victim memory block for a target operation, on the basis of the determined retention time.