Exploratory Performance Testing Using Reinforcement Learning

EasyChair Preprint 2746

Abstract

Performance bottlenecks in software systems resulting in high response times and low throughput can ruin the reputation of the companies that rely on them. Almost two-thirds of performance bottlenecks are triggered on specific input values. However, finding the input values for performance test cases that can identify performance bottlenecks in a large-scale complex system within a reasonable amount of time is a cumbersome, cost-intensive and time-consuming task. The reason is that there can be numerous combinations of test input values to explore. This paper presents PerfXRL, a novel approach for finding the combinations of input values which can reveal performance bottlenecks in the system under test. Our approach uses reinforcement learning to explore a large input space comprising combinations of input values and learn to focus on those areas of the input space which reveal performance bottlenecks. The results show that PerfxRL intelligently explores a huge space of combinations of input values and finds 50% of the performance bottlenecks by only exploring the 25% of the input space.

Keyphrases: Deep Neural Network, Deep Reinforcement Learning, Reinforcement Learning, data generation problem, machine learning, performance bottleneck, performance testing

@booklet{EasyChair:2746,
  author    = {Tanwir Ahmad and Adnan Ashraf and Dragos Truscan and Ivan Porres},
  title     = {Exploratory Performance Testing Using Reinforcement Learning},
  howpublished = {EasyChair Preprint 2746},
  year      = {EasyChair, 2020}}