Using eBPF for Database Workload Tracing: An Explorative Study
Authors: 
Jörg Domaschka, Simon Volpert, Kevin Maier, Georg Eisenhart, Daniel SeyboldAuthors Info & Claims
Pages 311 - 317
Abstract
Database management systems~(DBMS) are crucial architectural components of any modern distributed software system. Yet, ensuring a smooth, high-performant operation of a DBMS is a black art that requires tweaking many knobs and is heavily dependent on the experienced workload. Misconfigurations at production systems have an heavy impact on the overall delivered service quality and hence, should be avoided at all costs. Replaying production workload on test and staging systems to estimate the ideal configuration are a valid approach. Yet, this requires traces from the production systems.
While many DBMS's have built-in support to capture such traces these have a non-negligible impact on performance. eBPF is a Linux kernel feature claiming to enable low-overhead observability and application tracing. In this paper, we evaluate different eBPF-based approaches to DBMS workload tracing for PostgreSQL and MySQL. The results show that using eBPF causes lower overhead than the built-in mechanisms. Hence, eBPF can be a viable baseline for building a generic tracing framework. Yet, our current results also show that additional optimisation and fine-tuning is needed to further lower the performance overhead.
References
[1]
Marcelo Amaral, Tatsuhiro Chiba, Scott Trent, Takeshi Yoshimura, and Sunyanan Choochotkaew. 2022. MicroLens: A Performance Analysis Framework for Microservices Using Hidden Metrics With BPF. In 2022 IEEE 15th International Conference on Cloud Computing (CLOUD). 2022 IEEE 15th International Conference on Cloud Computing (CLOUD). (July 2022), 230--240.
[2]
Brian F. Cooper, Adam Silberstein, Erwin Tam, Raghu Ramakrishnan, and Russell Sears. 2010. Benchmarking cloud serving systems with ycsb. In Proceedings of the 1st ACM Symposium on Cloud Computing (SoCC '10). Association for Computing Machinery, Indianapolis, Indiana, USA, 143--154. isbn: 9781450300360.
[3]
Shaleen Deep, Anja Gruenheid, Kruthi Nagaraj, Hiro Naito, Jeff Naughton, and Stratis Viglas. 2021. DIAMetrics: Benchmarking Query Engines at Scale. ACM SIGMOD Record, 50, 1, (June 17, 2021), 24--31.
[4]
Jörg Domaschka, Mark Leznik, Daniel Seybold, Simon Eismann, Johannes Grohmann, and Samuel Kounev. 2021. Buzzy: Towards Realistic DBMS Benchmarking via Tailored, Representative, Synthetic Workloads: Vision Paper. In Companion of the ACM/SPEC International Conference on Performance Engineering (ICPE '21). Association for Computing Machinery, New York, NY, USA, (Apr. 19, 2021), 175--178. isbn: 978--1--4503--8331--8.
[5]
Jörg Domaschka, Simon Volpert, and Daniel Seybold. 2020. Hathi: An MCDMbased Approach to Capacity Planning for Cloud-hosted DBMS. In 2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC). 2020 IEEE/ACM 13th International Conference on Utility and Cloud Computing (UCC). (Dec. 2020), 143--154.
[6]
Srikar Dronamraju. 2022. Uprobe-tracer: Uprobe-based Event Tracing - The Linux Kernel documentation. Accessed: 2023-02--27. Retrieved Feb. 27, 2023 from https://docs.kernel.org/trace/uprobetracer.html.
[7]
Mohamad Gebai and Michel R. Dagenais. 2018. Survey and Analysis of Kernel and Userspace Tracers on Linux: Design, Implementation, and Overhead. ACM Computing Surveys, 51, 2, (Mar. 12, 2018), 26:1--26:33.
[8]
Brendan Gregg. 2022. Linux eBPF Tracing Tools. Retrieved Sept. 9, 2022 from https://www.brendangregg.com/ebpf.html.
[9]
Brendan Gregg. 2020. Systems Performance: Enterprise and the Cloud. (Second ed.). Addison-Wesley Professional Computing Series.Addison-Wesley, Boston. isbn: 978-0--13--682015--4.
[10]
Johannes Grohmann, Daniel Seybold, Simon Eismann, Mark Leznik, Samuel Kounev, and Jörg Domaschka. 2020. Baloo: measuring and modeling the performance configurations of distributed DBMS. In 28th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems, MASCOTS 2020, Nice, France, November 17--19, 2020. IEEE, 1--8.
[11]
Masami Hiramatsu. [n. d.] Kprobe-based Event Tracing - The Linux Kernel documentation. Accessed: 2023-02--27. (). Retrieved Feb. 27, 2023 from https://docs.kernel.org/trace/kprobetrace.html.
[12]
Jim Keniston, Ananth Mavinakayanahalli, Vara Prasad, and Prasanna Panchamukhi. 2007. Ptrace, Utrace, Uprobes: Lightweight, Dynamic Tracing of User Apps. In Proceedings of the 2007 Linux Symposium.
[13]
Robert Krahn, Donald Dragoti, Franz Gregor, Do Le Quoc, Valerio Schiavoni, Pascal Felber, Clenimar Souza, Andrey Brito, and Christof Fetzer. 2020. TEEMon: A continuous performance monitoring framework for TEEs. In Proceedings of the 21st International Middleware Conference. Middleware '20: 21st International Middleware Conference. ACM, Delft Netherlands, (Dec. 7, 2020), 178--192. isbn: 978--1--4503--8153--6.
[14]
Hsuan-Chi Kuo, Kai-Hsun Chen, Yicheng Lu, Dan Williams, Sibin Mohan, and Tianyin Xu. 2022. Verified programs can party: optimizing kernel extensions via post-verification merging. In Proceedings of the Seventeenth European Conference on Computer Systems. EuroSys '22: Seventeenth European Conference on Computer Systems. ACM, Rennes France, (Mar. 28, 2022), 283--299. isbn: 978--1--4503--9162--7.
[15]
Joshua Levin. 2020. ViperProbe: Using eBPF Metrics to Improve Microservice Observability. Honors Thesis. (2020). https://cs.brown.edu/research/pubs/theses/ugrad/2020/levin.joshua.pdf.
[16]
Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new architecture for user-level packet capture. In Proceedings of the USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993 Conference Proceedings (USENIX'93). USENIX Association, USA, (Jan. 25, 1993), 2.
[17]
Andy Nisbet, Nuno Miguel Nobre, Graham Riley, and Mikel Luján. 2019. Profiling and Tracing Support for Java Applications. In Proceedings of the 2019 ACM/SPEC International Conference on Performance Engineering. ICPE '19: Tenth ACM/SPEC International Conference on Performance Engineering. ACM, Mumbai India, (Apr. 4, 2019), 119--126. isbn: 978--1--4503--6239--9.
[18]
Rasha Osman and William J. Knottenbelt. 2012. Database system performance evaluation models: A survey. Performance Evaluation, 69, 10, (Oct. 1, 2012), 471--493.
[19]
Vincent Reniers, Dimitri Van Landuyt, Ansar Rafique, andWouter Joosen. 2017. On the State of NoSQL Benchmarks. In Proceedings of the 8th ACM/SPEC on International Conference on Performance Engineering Companion. ICPE '17: ACM/SPEC International Conference on Performance Engineering. ACM, L'Aquila Italy, (Apr. 18, 2017), 107--112. isbn: 978--1--4503--4899--7.
[20]
Joel Scheuner and Philipp Leitner. 2018. Estimating cloud application performance based on micro-benchmark profiling. In 2018 IEEE 11th International Conference on Cloud Computing (CLOUD), 90--97.
[21]
Daniel Seybold. 2021. An Automation-Based Approach for Reproducible Evaluations of Distributed DBMS on Elastic Infrastructures. Ph.D. Dissertation. Universität Ulm, (May 14, 2021). isbn: 9781757899956.
[22]
Daniel Seybold and Jörg Domaschka. 2021. Benchmarking-as-a-service for cloud-hosted dbms. In Proceedings of the 22nd International Middleware Conference: Demos and Posters (Middleware '21). Association for Computing Machinery, Virtual Event, Canada, 12--13. isbn: 9781450391542.
[23]
Theodore Ts'o. 2022. Event Tracing - The Linux Kernel documentation. Accessed: 2023-02--27. Retrieved Feb. 27, 2023 from https://docs.kernel.org/trace/events.html.
Index Terms
- Using eBPF for Database Workload Tracing: An Explorative Study
Recommendations
Exemplary Determination of Cgroups-Based QoS Isolation for a Database Workload
ICPE '24 Companion: Companion of the 15th ACM/SPEC International Conference on Performance EngineeringAn effective isolation among workloads within a shared and possibly contended compute environment is a crucial aspect for industry and academia alike to ensure optimal performance and resource utilization. Modern ecosystems offer a wide range of ...
Eliminating eBPF Tracing Overhead on Untraced Processes
eBPF '24: Proceedings of the ACM SIGCOMM 2024 Workshop on eBPF and Kernel ExtensionsCurrent eBPF-based kernel extensions affect entire systems, and are coarse-grained. For some use cases, like tracing, operators are more interested in tracing a subset of processes (e.g., belonging to a container) rather than all processes. While ...
μBPF: Using eBPF for Microcontroller Compartmentalization
eBPF '24: Proceedings of the ACM SIGCOMM 2024 Workshop on eBPF and Kernel ExtensionsAlthough eBPF (Extended Berkeley Packet Filter) started as a virtualization technology used in the Linux kernel to allow for executing user code inside the kernel in a safe way, it is a general purpose software fault isolation technology. The ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
April 2023
421 pages
ISBN:9798400700729
DOI:10.1145/3578245
- General Chairs:
- Marco Vieira,
- Valeria Cardellini,
- Program Chairs:
- Antinisca Di Marco,
- Petr Tuma
Copyright © 2023 Owner/Author.
This work is licensed under a Creative Commons Attribution-ShareAlike International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 15 April 2023
Check for updates
Author Tags
Qualifiers
- Research-article
Funding Sources
- German Federal Ministry for Economic Affairs and Climate Action
Conference
ICPE '23
Sponsor:
ICPE '23: ACM/SPEC International Conference on Performance Engineering
April 15 - 19, 2023
Coimbra, Portugal
Acceptance Rates
Overall Acceptance Rate 252 of 851 submissions, 30%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 1,108Total Downloads
- Downloads (Last 12 months)809
- Downloads (Last 6 weeks)80
Reflects downloads up to 20 Dec 2024
Other Metrics
Citations
Cited By
View allView Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in