DBJoules: An Energy Measurement Tool for Database Management Systems

November 15, 2023 · Entered Twilight · 🏛 arXiv.org

"No code URL or promise found in abstract"
"Derived repo from GitHub Pages (backfill)"

Evidence collected by the PWNC Scanner

Repo contents: Experiments, README.md, Tracker, __pycache__, data, docs, emission.csv, hardware, logfiles, main_app.py, queries.py, results, setup.py, static, stop_background_processes.py, templates, tests, uploads

Authors Hemasri Sai Lella, Kurra Manasa, Rajrupa Chattaraj, Sridhar Chimalakonda arXiv ID 2311.08961 Category cs.SE: Software Engineering Citations 1 Venue arXiv.org Repository https://github.com/rishalab/DBJoules ⭐ 1 Last Checked 3 months ago

Abstract

In the rapidly evolving landscape of modern data-driven technologies, software relies on large datasets and constant data center operations using various database systems to support computation-intensive tasks. As energy consumption in software systems becomes a growing concern, selecting the right database from energy-efficiency perspective is also critical. To address this, we introduce \textbf{\textit{DBJoules}}, a tool that measures the energy consumption of activities in database systems. \textit{DBJoules} supports energy measurement of CRUD operations for four popular databases. Through evaluations on two widely-used datasets, we identify disparities of 7\% to 38\% in the energy consumption of these databases. Hence, the goal is to raise developer awareness about the effect of running queries in different databases from an energy consumption perspective, enabling them to select appropriate database for sustainable usage. The tool's demonstration is available at \url{https://youtu.be/D1MTZum0jok} and related artifacts at \url{https://rishalab.github.io/DBJoules/}.