Storage Device Dynamic Throttling via Workload Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional storage devices perform throttling operations based on fixed target performances, leading to performance fluctuations and potential losses due to variations in operating environments, as they do not adapt to actual performance levels.
Innovation Solution
A storage device with a controller that includes a throttling predefined table (PDT) and a PDT updating module, which monitors workload characteristics and updates the PDT based on actual performance to dynamically adjust throttling operations, ensuring optimal performance without fixed target constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If fixed target performance throttling operations are used, then device complexity is reduced and ease of operation is improved, but performance consistency deteriorates due to variations in operating environments
Solution Approach 1:
The patent implements dynamic throttling operations that automatically adjust performance targets based on monitored workload characteristics and actual performance metrics. The system transitions from static fixed targets to dynamic adaptive targets that respond to changing operating conditions, thereby maintaining performance consistency across varying environments while preserving ease of operation through automated adjustment.
Solution Approach 2:
The patent establishes a feedback mechanism that continuously monitors workload characteristics and actual performance, then uses this information to adjust throttling targets. The system measures performance metrics, compares them against targets, and dynamically modifies future targets based on the observed performance patterns, creating a closed-loop control system that ensures consistent performance without requiring manual intervention.
2Device complexity
If fixed target performance throttling operations are used, then device complexity is reduced, but adaptability to actual performance levels deteriorates
Solution Approach 1:
The system implements dynamic adaptability by automatically adjusting throttling targets based on monitored performance characteristics. Rather than using fixed targets, the system adapts its performance targets in real-time based on workload patterns and actual performance metrics, thereby achieving high adaptability while maintaining relatively simple device architecture through automated adjustment logic.
Solution Approach 2:
The patent enables the storage device to self-adjust its throttling performance targets without external intervention. The system autonomously monitors its own performance, analyzes workload characteristics, and dynamically modifies its operating parameters to achieve optimal performance, thereby achieving high adaptability while keeping the control mechanism relatively simple and self-contained.
3Reliability
If dynamic throttling adjustments based on monitored performance are implemented, then performance consistency is improved, but device complexity increases
Solution Approach 1:
The patent implements a feedback-based performance adjustment mechanism that monitors workload characteristics and actual performance metrics, then dynamically adjusts throttling targets to maintain consistent performance. The system uses performance measurement and comparison logic to automatically modify future performance targets, achieving reliable consistent performance through a relatively streamlined feedback loop that avoids excessive complexity.
Solution Approach 2:
The storage device performs self-adjustment of throttling parameters based on its own monitored performance data. The system autonomously measures its performance, analyzes the results, and modifies its operating parameters without requiring complex external control systems, thereby achieving performance consistency while keeping the overall device complexity manageable through self-contained adjustment logic.
4Adaptability or versatility
If performance monitoring and PDT updates are performed, then adaptability to workload changes is improved, but loss of time increases due to monitoring and calculation overhead
Solution Approach 1:
The patent implements selective monitoring and update mechanisms that focus on critical performance metrics and workload characteristics rather than comprehensively monitoring all possible parameters. The system performs partial monitoring of key indicators and updates throttling targets based on significant changes, thereby achieving adequate adaptability while minimizing the time overhead associated with continuous comprehensive monitoring and calculation.
Data Source
AI summary
An method of a storage device configured to communicate with an external device through an interface channel includes: storing a throttling predefined table (PDT) including a relationship between target performances and workload characteristics; detecting that a first workload characteristic has changed; determining whether to update the PDT; when it is determined to update the PDT, monitoring a performance of the storage device; updating the PDT to include at least one new value for the workload characteristics and an additional target throttling performance value, based on a calculated monitored performance and the changed value of the first workload characteristic; controlling an operation parameter based on the updated PDT such that the interface channel has a first throttling performance corresponding to the additional target throttling performance value; receiving a first request through the interface channel from the external device; and processing the first I/O request through the interface channel.