Hunter: Using Change Point Detection to Hunt for Performance Regressions

TL;DR

Hunter is an open source tool that leverages a modified change point detection algorithm to automatically identify performance regressions and improvements in software time-series data, improving detection accuracy and determinism.

Contribution

This paper introduces Hunter, a tool with modifications to the E-divisive means algorithm, enhancing change point detection for performance analysis in noisy data environments.

Findings

Hunter outperforms PELT and DYNP in detecting change points.

Modifications to the algorithm improve detection of nearby changes.

Using Student's t-test increases result determinism.

Abstract

Change point detection has recently gained popularity as a method of detecting performance changes in software due to its ability to cope with noisy data. In this paper we present Hunter, an open source tool that automatically detects performance regressions and improvements in time-series data. Hunter uses a modified E-divisive means algorithm to identify statistically significant changes in normally-distributed performance metrics. We describe the changes we made to the E-divisive means algorithm along with their motivation. The main change we adopted was to replace the significance test using randomized permutations with a Student's t-test, as we discovered that the randomized approach did not produce deterministic results, at least not with a reasonable number of iterations. In addition we've made tweaks that allow us to find change points the original algorithm would not, such as two nearby changes. For evaluation, we developed a method to generate real timeseries, but with artificially injected changes in latency. We used these data sets to compare Hunter against two other well known algorithms, PELT and DYNP. Finally, we conclude with lessons we've learned supporting Hunter across teams with individual responsibility for the performance of their project.