Lauca: Generating Application-Oriented Synthetic Workloads

TL;DR

Lauca is a novel workload duplicator that generates highly application-specific synthetic workloads for database performance evaluation, ensuring high fidelity and more accurate benchmarking results.

Contribution

Lauca is the first application-oriented transactional workload generator that models key OLTP characteristics for synthetic workload creation.

Findings

Lauca produces synthetic workloads with similar performance metrics to real applications.

Experimental results show high fidelity of generated workloads across different databases.

Lauca outperforms existing generic workload generators in accuracy and relevance.

Abstract

The synthetic workload is essential and critical to the performance evaluation of database systems. When evaluating the database performance for a specific application, the similarity between synthetic workload and real application workload determines the credibility of evaluation results. However, the workload currently used for performance evaluation is difficult to have the same workload characteristics as the target application, which leads to inaccurate evaluation results. To address this problem, we propose a workload duplicator (Lauca) that can generate synthetic workloads with highly similar performance metrics for specific applications. To the best of our knowledge, Lauca is the first application-oriented transactional workload generator. By carefully studying the application-oriented synthetic workload generation problem, we present the key workload characteristics (transaction logic and data access distribution) of online transaction processing (OLTP) applications, and propose novel workload characterization and generation algorithms, which guarantee the high fidelity of synthetic workloads. We conduct extensive experiments using workloads from TPC-C, SmallBank and micro benchmarks on both MySQL and PostgreSQL databases, and experimental results show that Lauca consistently generates high-quality synthetic workloads.