# Lynceus: Cost-efficient Tuning and Provisioning of Data Analytic Jobs

## TL;DR

Lynceus is a cost-efficient method for tuning cloud data analytic jobs by jointly optimizing cloud and application parameters, significantly reducing costs and improving optimization efficiency.

## Contribution

It introduces a novel joint optimization approach that outperforms existing methods by reducing configuration costs and optimization time through innovative mechanisms.

## Key findings

- Up to 3.7x cost reduction in configurations at the 90th percentile.
- Up to 11x reduction in optimization process costs.
- Effective use of timeout and long-sighted techniques for better exploration.

## Abstract

Modern data analytic and machine learning jobs find in the cloud a natural deployment platform to satisfy their notoriously large resource requirements. Yet, to achieve cost efficiency, it is crucial to identify a deployment configuration that satisfies user-defined QoS constraints (e.g., on execution time), while avoiding unnecessary over-provisioning. This paper introduces Lynceus, a new approach for the optimization of cloud based data analytic jobs that improves overstate-of-the-art approaches by enabling significant cost savings both in terms of the final recommended configuration and of the optimization process used to recommend configurations. Unlike existing solutions, Lynceus optimizes in a joint fashion both the cloud-related and the application-level parameters. This allows for a reduction of the cost of recommended configurations by up to 3.7x at the 90-th percentile with respect to existing approaches, which treat the optimization of cloud-related and application-level parameters as two independent problems. Further, Lynceus reduces the cost of the optimization process (i.e., the cloud cost incurred for testing configurations) by up to 11x. Such an improvement is achieved thanks to two mechanisms: i) a timeout approach which allows to abort the exploration of configurations that are deemed suboptimal, while still extracting useful information to guide future explorations and to improve its predictive model - differently from recent works, which either incur the full cost for testing suboptimal configurations or are unable to extract any knowledge from aborted runs; ii) a long-sighted and budget-aware technique that determines which configurations to test by predicting the long-term impact of each exploration - unlike state-of-the-art approaches for the optimization of cloud jobs, which adopt greedy optimization methods.