Transfer Learning with Bellwethers to find Good Configurations

TL;DR

This paper introduces BEETLE, a transfer learning approach using bellwethers to efficiently find near-optimal software configurations, significantly reducing measurement costs while maintaining or improving performance.

Contribution

The paper proposes BEETLE, a novel bellwether-based transfer learning scheme that outperforms existing methods in configuration optimization with lower data collection costs.

Findings

BEETLE outperforms state-of-the-art methods in 61 scenarios.

BEETLE requires only 1/7th of the evaluations compared to existing approaches.

BEETLE consistently finds configurations as good or better than previous methods.

Abstract

As software systems grow in complexity, the space of possible configurations grows exponentially. Within this increasing complexity, developers, maintainers, and users cannot keep track of the interactions between all the various configuration options. Finding the optimally performing configuration of a software system for a given setting is challenging. Recent approaches address this challenge by learning performance models based on a sample set of configurations. However, collecting enough data on enough sample configurations can be very expensive since each such sample requires configuring, compiling and executing the entire system against a complex test suite. The central insight of this paper is that choosing a suitable source (a.k.a. "bellwether") to learn from, plus a simple transfer learning scheme will often outperform much more complex transfer learning methods. Using this insight, this paper proposes BEETLE, a novel bellwether based transfer learning scheme, which can identify a suitable source and use it to find near-optimal configurations of a software system. BEETLE significantly reduces the cost (in terms of the number of measurements of sample configuration) to build performance models. We evaluate our approach with 61 scenarios based on 5 software systems and demonstrate that BEETLE is beneficial in all cases. This approach offers a new highwater mark in configuring software systems. Specifically, BEETLE can find configurations that are as good or better as those found by anything else while requiring only 1/7th of the evaluations needed by the state-of-the-art.