EOS: Automatic In-vivo Evolution of Kernel Policies for Better Performance

TL;DR

EOS automatically evolves kernel policies and parameters in vivo on real workloads, bridging the gap between kernel developers and users to improve system performance without requiring user domain knowledge.

Contribution

It introduces a system that enables automatic, in-vivo tuning of kernel policies and parameters through a simple API, policy cache, and hierarchical search engine.

Findings

EOS improves performance across four Linux subsystems.

It is easy to use for kernel developers and users.

Effective in tuning policies for real-world workloads.

Abstract

Today's monolithic kernels often implement a small, fixed set of policies such as disk I/O scheduling policies, while exposing many parameters to let users select a policy or adjust the specific setting of the policy. Ideally, the parameters exposed should be flexible enough for users to tune for good performance, but in practice, users lack domain knowledge of the parameters and are often stuck with bad, default parameter settings. We present EOS, a system that bridges the knowledge gap between kernel developers and users by automatically evolving the policies and parameters in vivo on users' real, production workloads. It provides a simple policy specification API for kernel developers to programmatically describe how the policies and parameters should be tuned, a policy cache to make in-vivo tuning easy and fast by memorizing good parameter settings for past workloads, and a hierarchical search engine to effectively search the parameter space. Evaluation of EOS on four main Linux subsystems shows that it is easy to use and effectively improves each subsystem's performance.