Storage Array Response Time Prediction via IO Workload Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Businesses face challenges in ensuring that their storage arrays can efficiently handle anticipated input/output workloads, as existing methods lack effective prediction and configuration optimization to meet performance requirements defined by service level objectives.
Innovation Solution
A method and system that generate a storage array configuration based on array-configuration-related parameters, record IO workload metrics, predict response times, and adjust configurations to meet performance requirements by analyzing IO workloads, determining IOPS, and using inverse distance weighting interpolation to optimize storage array performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If storage array configuration is optimized to handle anticipated IO workloads, then performance and reliability are improved, but device complexity and computational overhead increase
Solution Approach 1:
The system performs preliminary actions by generating multiple storage array configurations and predicting their response times before actual workload execution. This allows the identification of optimal configurations in advance, ensuring performance reliability when workloads are executed without requiring complex real-time adjustments.
Solution Approach 2:
The system creates virtual copies of storage array configurations to simulate and predict performance without affecting the actual physical storage array. These virtual configurations allow for comprehensive testing and optimization while maintaining the simplicity of the actual deployed system.
2Productivity
If response time prediction is performed for multiple storage array configurations, then performance optimization is improved, but computational time and resources increase
Solution Approach 1:
The system performs response time predictions for multiple configurations in advance, before actual workload execution. This preliminary analysis allows for selecting the optimal configuration without time-consuming adjustments during runtime, thus improving productivity while managing computational time efficiently.
Solution Approach 2:
The system replaces physical trial-and-error configuration testing with computational modeling and prediction algorithms. This substitution allows for rapid evaluation of multiple configurations without the time cost of actual hardware testing, significantly reducing computational time while maintaining optimization accuracy.
3Measurement precision
If IO workload metrics are recorded and analyzed in detail, then measurement precision is improved, but device complexity and processing overhead increase
Solution Approach 1:
The system extracts only the essential IO workload metrics needed for accurate response time prediction, separating these from unnecessary monitoring data. This extraction maintains measurement precision for critical parameters while reducing the complexity of the monitoring system by eliminating redundant measurement and analysis components.
Data Source
AI summary
One or more aspects of the present disclosure relate to predicting one or more performance metrics of a storage array configuration. In embodiments, a storage array configuration can be generated based on one or more array-configuration related parameters. In addition, IO workload metrics corresponding to an IO workload received by an array corresponding to the storage array configuration can be recorded. Further, at least one response time (RT) prediction can be generated based on the IO workload metrics. Accordingly, another storage array configuration can be generated based on the RT predictions and according to performance requirements defined by a service level objective (SLO).