QAAS: quick accurate auto-scaling for streaming processing

Abstract

In recent years, the demand for real-time data processing has been increasing, and various stream processing systems have emerged. When the amount of data input to the stream processing system fluctuates, the computing resources required by the stream processing job will also change. The resources used by stream processing jobs need to be adjusted according to load changes, avoiding the waste of computing resources. At present, existing works adjust stream processing jobs based on the assumption that there is a linear relationship between the operator parallelism and operator resource consumption (e.g., throughput), which makes a significant deviation when the operator parallelism increases. This paper proposes a nonlinear model to represent operator performance. We divide the operator performance into three stages, the Non-competition stage, the Non-full competition stage, and the Full competition stage. Using our proposed performance model, given the parallelism of the operator, we can accurately predict the CPU utilization and operator throughput. Evaluated with actual experiments, the prediction error of our model is below 5%. We also propose a quick accurate auto-scaling (QAAS) method that uses the operator performance model to implement the auto-scaling of the operator parallelism of the Flink job. Compared to previous work, QAAS is able to maintain stable job performance under load changes, minimizing the number of job adjustments and reducing data backlogs by 50%.

Graphical abstract

Keywords

stream processing / performance model / auto-scaling

Shiyuan Liu is a master student in School of Computer Science and Engineering, Beihang University, China. He is currently working on big data processing optimization. His research interests include data streaming systems

Yunchun Li is a professor in School of Computer Science and Engineering, Beihang University, China. He received the PhD degree in Computer Science from Beihang University, China. He went to University of Illinois at Urbana-Champaign (UIUC), USA as a visiting scholar in 2010. His research interests include big data, cloud computing, and parallel computing

Hailong Yang is an associate professor in School of Computer Science and Engineering, Beihang University, China. He received the PhD degree in the School of Computer Science and Engineering, Beihang University, China in 2014. His research interests include parallel and distributed computing, HPC, performance optimization and energy efficiency

Ming Dun is a master student in School of Cyber Science and Technology, Beihang University, China. She is currently working on performance optimization for large scale applications. Her research interests include parallel computing and HPC

Chen Chen is studying for PhD degree in School of Cyber Science and Technology, Beihang University, China. His current research interests include Web security, machine learning, cloud computing, and attack detection

Huaitao Zhang is an undergraduate student in School of Computer Science and Technology, Xi’an Jiaotong University, China. His research interest is high performance computing

Wei Li is an associate professor with the School of Computer Science and Engineering, Beihang University, China. She received the PhD degree in computer science from Beihang University, China. Her research interests include network measurement, network virtualization, and cloud computing

References

[1] Vastardis N, Yang K. Mobile social networks: architectures, social properties, and key research challenges. IEEE Communications Surveys & Tutorials, 2013, 15( 3): 1355–1371

[2] Chen H, Chiang R H L, Storey V C. Business intelligence and analytics: from big data to big impact. MIS Quarterly, 2012, 36( 4): 1165–1188

[3] Carbone P, Katsifodimos A, Ewen S, Markl V, Haridi S, Tzoumas K. Apache flink^TM: stream and batch processing in a single engine. IEEE Data Engineering Bulletin, 2015, 38( 4): 28–38

[4] Kulkarni S, Bhagat N, Fu M, Kedigehalli V, Kellogg C, Mittal S, Patel J M, Ramasamy K, Taneja S. Twitter heron: stream processing at scale. In: Proceedings of 2015 ACM SIGMOD International Conference on Management of Data. 2015, 239−250

[5] Toshniwal A, Taneja S, Shukla A, Ramasamy K, Patel J M, Kulkarni S, Jackson J, Gade K, Fu M, Donham J, Bhagat N, Mittal S, Ryaboy D. Storm@twitter. In: Proceedings of 2014 ACM SIGMOD International Conference on Management of Data. 2014, 147−156

[6] Song Y, Li Y, Yang H, Xu J, Luan Z, Li W. Adaptive watermark generation mechanism based on time series prediction for stream processing. Frontiers of Computer Science, 2021, 15( 6): 156213

[7] Kahveci B, Gedik B. Joker: elastic stream processing with organic adaptation. Journal of Parallel and Distributed Computing, 2020, 137: 205–223

[8] Kalim F, Cooper T, Wu H, Li Y, Wang N, Lu N, Fu M, Qian X, Luo H, Cheng D, Wang Y, Dai F, Ghosh M, Wang B. Caladrius: a performance modelling service for distributed stream processing systems. In: Proceedings of the 35th IEEE International Conference on Data Engineering (ICDE). 2019, 1886−1897

[9] Kalavri V, Liagouris J, Hoffmann M, Dimitrova D C, Forshaw M, Roscoe T. Three steps is all you need: fast, accurate, automatic scaling decisions for distributed streaming dataflows. In: Proceedings of the 13th USENIX Symposium on Operating Systems Design and Implementation. 2018, 783−798

[10] Mei Y, Cheng L, Talwar V, Levin M Y, Jacques-Silva G, Simha N, Banerjee A, Smith B, Williamson T, Yilmaz S, Chen W, Chen G J. Turbine: Facebook’s service management platform for stream processing. In: Proceedings of the 36th IEEE International Conference on Data Engineering (ICDE). 2020, 1591−1602

[11] Kreps J, Narkhede N, Rao J. Kafka: a distributed messaging system for log processing. In: Proceedings of the NetDB. 2011, 1−7

[12] Burns B, Grant B, Oppenheimer D, Brewer E, Wilkes J. Borg, omega, and kubernetes. Communications of the ACM, 2016, 59( 5): 50–57

[13] Vavilapalli V K, Murthy A C, Douglas C, Agarwal S, Konar M, Evans R, Graves T, Lowe J, Shah H, Seth S, Saha B, Curino C, O’Malley O, Radia S, Reed B, Baldeschwieler E. Apache hadoop YARN: yet another resource negotiator. In: Proceedings of the 4th Annual Symposium on Cloud Computing. 2013, 5

[14] Röger H, Mayer R. A comprehensive survey on parallelization and elasticity in stream processing. ACM Computing Surveys, 2020, 52( 2): 36

[15] Floratou A, Agrawal A, Graham B, Rao S, Ramasamy K. Dhalion: self-regulating stream processing in heron. Proceedings of the VLDB Endowment, 2017, 10( 12): 1825–1836

[16] Marangozova-Martin V, de Palma N, El Rheddane A. Multi-level elasticity for data stream processing. IEEE Transactions on Parallel and Distributed Systems, 2019, 30( 10): 2326–2337

[17] Arkian H, Pierre G, Tordsson J, Elmroth E. An experiment-driven performance model of stream processing operators in fog computing environments. In: Proceedings of the 35th Annual ACM Symposium on Applied Computing. 2020, 1763−1771

Acknowledgements

This work was supported by the National Key Research and Development Program of China (2020YFB1506703), the National Natural Science Foundation of China (Grant No. 62072018), the State Key Laboratory of Software Development Environment (SKLSDE-2021ZX-06), and the Fundamental Research Funds for the Central Universities.

RIGHTS & PERMISSIONS

2024 Higher Education Press