An Analysis of Open-Source HTAP Platforms: Towards a Standardized Benchmarking Suite

Investigating what an HTAP benchmark needs
Students: Jeppe Koch Schwensen
Supervisors: Pınar Tözün
Level: MSc, Semesters: Spring 2019
Tags: HTAP, benchmarking


The rising demand for large-scale real-time analytics applications emphasize the need for distributed data management systems that can handle fast transactions and analytics concurrently. Efficient processing of transactional and analytical requests, however, require different optimizations and architectural decisions in the system.

Data systems targeting concurrent processing of transactional and analytical workloads fall under the term Hybrid Transactional and Analytical Processing (HTAP). HTAP data systems are subject to rapid development and many solutions are emerging both from the industry and academia. Due to the rapidly changing HTAP environment, there is no industry-accepted standard across the platforms in terms of their ability to handle different applications and analytics within transactions.

The goal of the project is to analyse and benchmark a set of database systems and extend the benchmark to include queries that are widely needed in HTAP-applications, but are not represented in existing benchmarks.