Storage Device Performance Monitoring via Threshold-Based Data Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining storage device performance in a longer time period are either computationally intensive or result in inaccurate and delayed performance calculations due to issues with message reception and timestamp synchronization.
Innovation Solution
A method where a server maintains a status record of received indicator values and updates it based on incoming messages, determining storage device performance only when the threshold number of values is reached, allowing for quick and accurate performance assessment while reducing resource consumption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods are used to determine storage device performance in a longer time period, then performance data is collected, but computational resources are excessively consumed and accuracy is reduced due to message reception issues
Solution Approach 1:
The patent segments the performance determination process into two distinct phases: (1) a data collection phase where indicator values and timestamps are accumulated without intensive processing, and (2) a calculation phase that is triggered only when sufficient data is available. This segmentation avoids continuous computational resource consumption while maintaining data collection, directly resolving the contradiction between measurement precision and energy usage.
Solution Approach 2:
The system performs preliminary data collection and validation before initiating performance calculations. By pre-collecting indicator values and timestamps, and pre-validating their consistency, the system ensures that when calculation does occur, it is based on verified data, improving accuracy while avoiding wasteful re-calculations and reducing overall computational resource usage.
2Speed
If performance is determined continuously, then real-time monitoring is achieved, but computational overhead increases significantly
Solution Approach 1:
The patent implements periodic performance determination based on data availability rather than continuous calculation. The system periodically checks whether sufficient indicator values have been collected and validates timestamp consistency before triggering performance calculations. This periodic approach maintains responsive performance monitoring while dramatically reducing computational overhead compared to continuous determination, directly addressing the contradiction between speed and resource efficiency.
3Reliability
If all received indicator values are used for calculation, then comprehensive performance assessment is achieved, but errors from missed or delayed messages reduce accuracy
Solution Approach 1:
The patent employs feedback mechanisms through timestamp validation to detect and handle message reception issues. The system checks whether received indicator values have corresponding timestamps within expected time ranges, providing feedback on data quality. When timestamps indicate missed or delayed messages, the system can identify and exclude problematic data points, maintaining reliable performance assessment despite incomplete message reception, thus resolving the contradiction between reliability and information loss.
Data Source
AI summary
A data processing method includes receiving a message related to performance of a storage device, the message including an indicator value regarding the performance in a first time period, and a timestamp associated with the first time period. A status record of the storage device, including the number of received indicator values in a second time period including the first time period, is determined based on the timestamp, wherein the number of the received indicator values is less than a threshold number and can be updated based on the indicator value. The performance in the second time period can be determined based on the indicator value and the received indicator values in response to determining that the updated number of the received indicator values reaches the threshold number. Thus, the performance of the storage device can be quickly and accurately determined, and the consumption of computing resources is reduced.