Iterative Storage Workload Refinement for QoS Measurement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Evaluating and measuring the Quality of Service (QoS) of storage systems is challenging due to various configurations and combinations of workloads, lacking an efficient and convenient method.
Innovation Solution
An apparatus and method that execute a task set to access the storage system, obtaining performance indicators, adjusting the task set based on execution results, and iteratively refining the task set until predefined conditions are met, including determining task classes and similarity with reference storage systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all possible workloads are tested to evaluate QoS, then measurement completeness is improved, but time consumption and effort increase enormously
Solution Approach 1:
The patent applies partial action by selecting and executing only a subset of representative workloads rather than testing all possible workloads. The system identifies key workload types that sufficiently characterize storage system performance, executing only those necessary tasks to obtain meaningful QoS metrics without exhaustive testing of every possible scenario.
Solution Approach 2:
The patent applies preliminary action by pre-classifying workloads into different types or categories before execution. The system prepares workload classifications in advance, allowing it to systematically select representative tasks from each class rather than randomly testing all workloads, thereby reducing evaluation time while maintaining measurement completeness.
2Measurement precision
If multiple task configurations are executed to cover various scenarios, then measurement comprehensiveness is improved, but system complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the workload into distinct classes or categories based on their characteristics. The system segments tasks into different types (e.g., sequential access, random access, different data sizes) and selects representative tasks from each segment, thereby managing complexity while maintaining comprehensive evaluation coverage.
Solution Approach 2:
The patent applies parameter changes by varying key workload parameters systematically rather than testing all possible parameter combinations. The system identifies critical parameters that most significantly impact storage performance and varies only those parameters across different task configurations, reducing the overall complexity of the task set while preserving measurement comprehensiveness.
Data Source
AI summary
The present disclosure relates to a method and apparatus for measuring performance of a storage system. The method comprises: causing one or more entities to execute a task set comprising multiple tasks, each of the multiple tasks being used for accessing the storage system; obtaining an indicator set of the storage system based on a result of the execution, the indicator set comprising one or more indicators for indicating performance of the storage system; and adjusting the task set based on the indicator set, for subsequent execution by the one or more entities. The method can be executed iteratively. By means of the present invention, workloads for the next round's execution can be intelligently improved according to execution results after each round's execution of workloads, so that performance of the storage system can be obtained more pertinently and efficiently so as to better utilize the storage system.