RAID Disk Degradation Detection via Z-Score Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining disk performance degradation in RAID systems are resource-intensive and often result in false positives due to the complexity of analyzing numerous statistics, leading to inefficient identification of disks that need replacement.
Innovation Solution
A management system analyzes disk performance statistics, including usage observations and byte-counts, to calculate Z-scores and determine population means and standard deviations, discarding predictions if workload imbalances are detected and ensuring high Z-scores are sustained over consecutive time periods to minimize false positives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional methods analyze a large number of disk statistics (SMART data, log pages), then disk performance monitoring is comprehensive, but resource consumption increases and false positives increase
Solution Approach 1:
The patent extracts only the most critical performance indicators from the vast array of available disk statistics. Instead of analyzing all SMART attributes and log pages, the system selectively monitors key metrics such as read/write throughput, latency, and error rates that directly indicate performance degradation, thereby reducing computational resources while maintaining monitoring effectiveness
Solution Approach 2:
The monitoring approach is segmented into multiple stages: initial baseline establishment, anomaly detection using simplified metrics, and detailed analysis only when anomalies are detected. This hierarchical segmentation allows the system to spend minimal resources on routine monitoring while allocating full analytical power only when necessary, reducing overall resource consumption
2Measurement precision
If conventional methods analyze a large number of disk statistics, then performance degradation detection is thorough, but false positives increase
Solution Approach 1:
The system performs preliminary baseline characterization of each disk's normal performance patterns before attempting to detect degradation. By establishing expected performance ranges and patterns in advance, the system can later compare actual performance against these baselines to distinguish true degradation from normal variations, thereby reducing false positives
Solution Approach 2:
The monitoring system incorporates feedback loops where detection results are continuously refined. When potential degradation is detected, the system adjusts monitoring parameters and applies additional validation checks specific to the detected anomaly type, improving accuracy while reducing false alarms through iterative learning from actual system behavior
3Use of energy by moving object
If simple monitoring mechanisms are used, then resource consumption is low, but detection accuracy decreases
Solution Approach 1:
The monitoring system dynamically adapts its complexity based on system conditions. During normal operation, simple threshold-based monitoring is used to consume minimal resources. When anomalies are detected or during critical periods, the system automatically increases monitoring frequency and analytical depth, ensuring high detection accuracy is available when needed while maintaining low resource consumption during stable periods
Data Source
AI summary
Exemplary methods for determining performance degradation of one or more disks at a storage system include analyzing disk performance statistics of a target storage system periodically collected during a storage of data from a source storage system to the target storage system, wherein the target storage system is a redundant array of inexpensive disks (RAID) storage system comprising of one or more arrays, each array comprising of a plurality of disks. The methods further include creating a predictive model based on the analysis of the collected performance statistics, and predicting, using the predictive model, that one or more disks of an array of the one or more arrays of the RAID storage system has degraded in performance.