%0 Conference Paper %1 GrSeEiLeKoDo2020-MASCOTS-DBMSPerformance %A Grohmann, Johannes %A Seybold, Daniel %A Eismann, Simon %A Leznik, Mark %A Kounev, Samuel %A Domaschka, Jörg %B 2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS) %D 2020 %I IEEE %K automated_model_learning descartes myown performance performance_modeling prediction statistical_estimation_and_machine_learning t_full %P 1--8 %R 10.1109/MASCOTS50786.2020.9285960 %T Baloo: Measuring and Modeling the Performance Configurations of Distributed DBMS %U https://doi.org/10.1109/MASCOTS50786.2020.9285960 %X Correctly configuring a distributed database management system (DBMS) deployed in a cloud environment for maximizing performance poses many challenges to operators. Even if the entire configuration spectrum could be measured directly, which is often infeasible due to the multitude of parameters, single measurements are subject to random variations and need to be repeated multiple times. In this work, we propose Baloo, a framework for systematically measuring and modeling different performance-relevant configurations of distributed DBMS in cloud environments. Baloo dynamically estimates the required number of configurations, as well as the number of required measurement repetitions per configuration based on a desired target accuracy. We evaluate Baloo based on a data set consisting of 900 DBMS configuration measurements conducted in our private cloud setup. Our evaluation shows that the highly configurable framework is able to achieve a prediction error of up to 12% while saving 80% of the measurement effort. We also publish all code and the acquired data set to foster future research.

@inproceedings{GrSeEiLeKoDo2020-MASCOTS-DBMSPerformance, abstract = {Correctly configuring a distributed database management system (DBMS) deployed in a cloud environment for maximizing performance poses many challenges to operators. Even if the entire configuration spectrum could be measured directly, which is often infeasible due to the multitude of parameters, single measurements are subject to random variations and need to be repeated multiple times. In this work, we propose Baloo, a framework for systematically measuring and modeling different performance-relevant configurations of distributed DBMS in cloud environments. Baloo dynamically estimates the required number of configurations, as well as the number of required measurement repetitions per configuration based on a desired target accuracy. We evaluate Baloo based on a data set consisting of 900 DBMS configuration measurements conducted in our private cloud setup. Our evaluation shows that the highly configurable framework is able to achieve a prediction error of up to 12% while saving 80% of the measurement effort. We also publish all code and the acquired data set to foster future research.}, added-at = {2020-09-23T10:19:52.000+0200}, author = {Grohmann, Johannes and Seybold, Daniel and Eismann, Simon and Leznik, Mark and Kounev, Samuel and Domaschka, Jörg}, biburl = {https://www.bibsonomy.org/bibtex/271a9507d24d106ee7a1f80e245e67dee/samuel.kounev}, booktitle = {2020 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS)}, doi = {10.1109/MASCOTS50786.2020.9285960}, interhash = {1d922f2bcb9f4d30ace78250dc9be4ab}, intrahash = {71a9507d24d106ee7a1f80e245e67dee}, keywords = {automated_model_learning descartes myown performance performance_modeling prediction statistical_estimation_and_machine_learning t_full}, month = {November}, note = {Acceptance Rate: 27%}, pages = {1--8}, publisher = {IEEE}, series = {MASCOTS '20}, timestamp = {2022-11-16T09:09:50.000+0100}, title = {Baloo: Measuring and Modeling the Performance Configurations of Distributed DBMS}, url = {https://doi.org/10.1109/MASCOTS50786.2020.9285960}, venue = {Nice, France, France}, year = 2020 }