Performance Model for Application Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Application testing requires significant resources and it is challenging to predict how proposed changes or new applications will perform before investing in performance tests, making it difficult to determine if resources will be wasted or if performance standards will be met.
Innovation Solution
A system and method that use a performance model generated from software, workload, and hardware models to simulate application performance before actual testing, allowing for assessment of proposed changes or new applications, incorporating updates for changes in workload and hardware, and enabling rapid evaluation of different scenarios without committing resources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If performance testing is conducted to accurately assess application performance, then measurement precision is improved, but loss of time and loss of energy increase due to resource consumption
Solution Approach 1:
The system performs preliminary static analysis of application code to generate performance predictions before actual performance testing is conducted. This allows stakeholders to assess whether the application is likely to meet performance requirements without investing time in full-scale performance tests, thereby resolving the contradiction between measurement precision and time loss.
Solution Approach 2:
The system creates a computational model (copy) of the application's performance characteristics through static analysis, rather than requiring physical execution of performance tests. This model can be used to predict performance under various conditions without consuming the time and resources of actual testing, thus improving measurement precision while reducing time loss.
2Measurement precision
If performance testing is conducted to accurately predict application behavior, then measurement precision is improved, but loss of energy increases due to computing resource consumption
Solution Approach 1:
The system performs preliminary static analysis to predict application behavior before committing energy-intensive performance testing resources. By analyzing code structure, algorithms, and complexity metrics in advance, the system can identify applications that are unlikely to meet performance requirements, avoiding waste of computing energy on futile testing efforts.
Solution Approach 2:
The system creates a computational model of application performance characteristics through static analysis, serving as an energy-efficient copy that predicts behavior without requiring actual execution. This model allows stakeholders to assess performance likelihood with minimal energy consumption, resolving the contradiction between measurement precision and energy use.
3Reliability
If comprehensive performance testing is performed to assess application performance, then reliability is improved, but device complexity increases due to coordination of multiple resources
Solution Approach 1:
The system extracts the essential performance assessment function from complex coordinated testing resources and implements it through automated static analysis. By taking out the core predictive capability and encoding it in algorithms that analyze code metrics, the system maintains reliability of performance assessment while eliminating the need to coordinate multiple human and computational resources, thus reducing device complexity.
Solution Approach 2:
The system enables the application code itself to provide performance predictions through automated static analysis, without requiring external coordination of testing resources. The code's structure, algorithms, and metrics serve as self-describing information that the system processes automatically, maintaining reliability while reducing the complexity of resource coordination to minimal system configuration.
Data Source
AI summary
The system, method, and device for simulating application performance prior to conducting performance testing is disclosed. The illustrative method includes obtaining results of a preliminary simulation, and processing the obtained results from the preliminary simulation, with a profiling tool, and generate a software model based on an output of the profiling tool. A workload model and a hardware model are configured to account for a desired scenario. A performance model is defined using the software model, the workload model, and the hardware model, and prior to testing the application, the performance model is used to simulate performance of the application in the desired scenario.