%0 Conference Paper %1 domaschka2021buzzy %A Domaschka, Jörg %A Eismann, Simon %A Leznik, Mark %A Grohmann, Johannes %A Kounev, Samuel %A Seybold, Daniel %B Companion of the ACM/SPEC International Conference on Performance Engineering %C New York, NY, USA %D 2021 %I Association for Computing Machinery %K descartes t_visionposition myown %P 175–178 %R 10.1145/3447545.3451175 %T Buzzy: Towards Realistic DBMS Benchmarking via Tailored, Representative, Synthetic Workloads %U https://doi.org/10.1145/3447545.3451175 %V ICPE '21 %X Distributed Database Management Systems (DBMS) are a crucial component of modern IT applications. Understanding their performance and non-functional properties is of paramount importance. Yet, benchmarking distributed DBMS has proven to be difficult in practice. Either, a realistic workload is often mapped to a synthetic workload without knowing if this mapping is correct or available workload traces are replayed. While the latter approach provides more realistic results, real-world traces are hard to obtain and their scope is limited in time scale and variance.We propose collecting real-world traces and then applying data generation techniques to synthesize similar realistic traces based on it. Based in this approach, we can obtain workloads for benchmarking, exhibit variability with respect to different aspects of interest while still being similar to the original traces. Varying generation parameters, we are able to support benchmarking what-if scenarios with hypothetical workloads and introduced anomalies. %@ 9781450383318

@inproceedings{domaschka2021buzzy, abstract = {Distributed Database Management Systems (DBMS) are a crucial component of modern IT applications. Understanding their performance and non-functional properties is of paramount importance. Yet, benchmarking distributed DBMS has proven to be difficult in practice. Either, a realistic workload is often mapped to a synthetic workload without knowing if this mapping is correct or available workload traces are replayed. While the latter approach provides more realistic results, real-world traces are hard to obtain and their scope is limited in time scale and variance.We propose collecting real-world traces and then applying data generation techniques to synthesize similar realistic traces based on it. Based in this approach, we can obtain workloads for benchmarking, exhibit variability with respect to different aspects of interest while still being similar to the original traces. Varying generation parameters, we are able to support benchmarking what-if scenarios with hypothetical workloads and introduced anomalies.}, added-at = {2021-02-25T03:00:25.000+0100}, address = {New York, NY, USA}, author = {Domaschka, Jörg and Eismann, Simon and Leznik, Mark and Grohmann, Johannes and Kounev, Samuel and Seybold, Daniel}, biburl = {https://www.bibsonomy.org/bibtex/2494e3a953825117a9c7d7d226920b619/joh.grohmann}, booktitle = {Companion of the ACM/SPEC International Conference on Performance Engineering}, doi = {10.1145/3447545.3451175}, eventdate = {2021}, interhash = {17545624479f1cb65a5f9e6fca7ada5c}, intrahash = {494e3a953825117a9c7d7d226920b619}, isbn = {9781450383318}, keywords = {descartes t_visionposition myown}, pages = {175–178}, publisher = {Association for Computing Machinery}, timestamp = {2022-11-16T09:10:16.000+0100}, title = {Buzzy: Towards Realistic DBMS Benchmarking via Tailored, Representative, Synthetic Workloads}, url = {https://doi.org/10.1145/3447545.3451175}, venue = {Virtual Event, France}, volume = {ICPE '21}, year = 2021 }