Storage QoS Violation Detection via Interval-Based Aggregation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing scale of computer systems leads to a significant increase in the amount of information that needs to be monitored for detecting Quality of Service (QoS) violations in storage devices, resulting in high analysis costs and increased operating costs, especially when using cloud-based management systems on a pay-as-you-go platform.
Innovation Solution
A management system that collects performance information from storage devices at a first time interval and detects QoS violations at a second time interval longer than the first, reducing the frequency of data collection and analysis, thereby lowering the analysis cost by generating statistical information over a longer period to detect long-term performance trends rather than momentary deviations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If performance information is collected at a short time interval to reliably detect QoS violations, then detection reliability is improved, but analysis cost and processing load increase
Solution Approach 1:
The patent combines multiple performance measurements taken at short time intervals into aggregated statistical information (such as average values, maximum values, or trend indicators) that is then analyzed at a longer time interval. This merging approach preserves the reliability benefits of frequent monitoring while reducing the processing burden by analyzing consolidated data rather than every individual measurement point.
2Measurement precision
If performance information is collected at a short time interval to detect QoS violations, then detection precision is improved, but processing load increases
Solution Approach 1:
The system performs preliminary aggregation and preprocessing of performance data at short time intervals before the actual QoS violation detection analysis. By pre-processing the data into summarized statistical forms, the system maintains precise measurement capabilities while significantly reducing the computational workload during the detection phase, thereby improving overall processing efficiency.
3Reliability
If performance information is collected frequently to detect QoS violations, then detection accuracy is improved, but data storage requirements increase
Solution Approach 1:
The patent extracts only the essential features and statistical summaries from the frequently collected performance data, storing these condensed representations rather than the complete raw dataset. This extraction approach maintains the accuracy needed for reliable QoS violation detection while dramatically reducing the storage capacity required, as only key metrics and trends are retained rather than every individual measurement.
Data Source
AI summary
It is possible to reduce analysis cost of a management system.The management system includes a CPU and manages one or more storage devices that provide, to a higher-level device, one or more volumes for inputting and outputting data. The CPU is configured to collect performance information of the volume from the storage device at a predetermined first time interval and detect a QoS violation of the performance information of the volume at a second time interval longer than the first time interval.