FONT: A Flexible Polystore Evaluation Platform

Gengyuan Shi, Chaokun Wang, Minghao Zhang, Binbin Wang

Abstract: The concept of polystore has been proposed and studied for heterogeneous data storage and cross-model query processing. Correspondingly, the evaluation of diverse polystores is an essential yet challenging task. However, most current evaluation approaches for polystores only focus on cross-model analytical workloads and provide limited configurations. To address these problems, this paper presents a flexible polystore evaluation platform named FONT. FONT incorporates hybrid single-model and cross-model workloads that combine read and write operations, as well as diagnostic analytical workloads. FONT supports customization of both multi-model dataset generation and workload generation procedures. The proposed platform is the first visual tool for polystore evaluation, providing user-friendly graphical interfaces for user customization and displaying evaluation results.