Chamulteon: Coordinated auto-scaling of micro-services

Andre Bauer; Veronika Lesch; Laurens Versluis; Alexey Ilyushkin; Nikolas Herbst; Samuel Kounev

doi:10.1109/ICDCS.2019.00199

Chamulteon: Coordinated auto-scaling of micro-services

Andre Bauer
, Veronika Lesch
, Laurens Versluis
, Alexey Ilyushkin
, Nikolas Herbst
, Samuel Kounev

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Nowadays, in order to keep track of the fast changing requirements of Internet applications, auto-scaling is used as an essential mechanism for adapting the number of provisioned resources to the resource demand. The straightforward approach is to deploy a set of common and opensource single-service auto-scalers for each service independently. However, this deployment leads to problems such as bottleneck-shifting and increased oscillations. Existing auto-scalers that scale applications consisting of multiple services are kept closed-source. To face these challenges, we first survey existing auto-scalers and highlight current challenges. Then, we introduce Chamulteon, a redesign of our previously introduced mechanism, which can scale applications consisting of multiple services in a coordinated manner. We evaluate Chamulteon against four different well-cited auto-scalers in four sets of measurement-based experiments where we use diverse environments (VM vs. Docker), real-world traces, and vary the scale of the demanded resources. Overall, Chamulteon achieves the best auto-scaling performance based on established user-oriented and endorsed elasticity metrics.

Original language	English
Title of host publication	2019 39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2015-2025
Number of pages	11
ISBN (Electronic)	9781728125190
DOIs	https://doi.org/10.1109/ICDCS.2019.00199
Publication status	Published - 31 Oct 2019
Event	39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019 - Richardson, United States Duration: 7 Jul 2019 → 9 Jul 2019

Publication series

Name	Proceedings - International Conference on Distributed Computing Systems
Volume	2019-July

Conference

Conference	39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019
Country/Territory	United States
City	Richardson
Period	7/07/19 → 9/07/19

Funding

ACKNOWLEDGEMENTS This work was funded by the German Research Foundation (DFG) under grant No. KO 3445/11-1. This research has been supported by the SPEC Research Group8 of the Standard Performance Evaluation Corporation (SPEC).

Keywords

Auto-Scaling
Benchmarking
Cloud Computing
Container
Elasticity
Metrics
Service Demand Estimation
Workload Forecasting

Access to Document

10.1109/ICDCS.2019.00199

Persistent URL (handle)

Persistent link

Cite this

Bauer, A., Lesch, V., Versluis, L., Ilyushkin, A., Herbst, N., & Kounev, S. (2019). Chamulteon: Coordinated auto-scaling of micro-services. In 2019 39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019 (pp. 2015-2025). Article 8885153 (Proceedings - International Conference on Distributed Computing Systems; Vol. 2019-July). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDCS.2019.00199

@inproceedings{cb261b840e80403fa9c68bc7ddf9295d,

title = "Chamulteon: Coordinated auto-scaling of micro-services",

abstract = "Nowadays, in order to keep track of the fast changing requirements of Internet applications, auto-scaling is used as an essential mechanism for adapting the number of provisioned resources to the resource demand. The straightforward approach is to deploy a set of common and opensource single-service auto-scalers for each service independently. However, this deployment leads to problems such as bottleneck-shifting and increased oscillations. Existing auto-scalers that scale applications consisting of multiple services are kept closed-source. To face these challenges, we first survey existing auto-scalers and highlight current challenges. Then, we introduce Chamulteon, a redesign of our previously introduced mechanism, which can scale applications consisting of multiple services in a coordinated manner. We evaluate Chamulteon against four different well-cited auto-scalers in four sets of measurement-based experiments where we use diverse environments (VM vs. Docker), real-world traces, and vary the scale of the demanded resources. Overall, Chamulteon achieves the best auto-scaling performance based on established user-oriented and endorsed elasticity metrics.",

keywords = "Auto-Scaling, Benchmarking, Cloud Computing, Container, Elasticity, Metrics, Service Demand Estimation, Workload Forecasting",

author = "Andre Bauer and Veronika Lesch and Laurens Versluis and Alexey Ilyushkin and Nikolas Herbst and Samuel Kounev",

year = "2019",

month = oct,

day = "31",

doi = "10.1109/ICDCS.2019.00199",

language = "English",

series = "Proceedings - International Conference on Distributed Computing Systems",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "2015--2025",

booktitle = "2019 39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019",

address = "United States",

note = "39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019 ; Conference date: 07-07-2019 Through 09-07-2019",

}

Bauer, A, Lesch, V, Versluis, L, Ilyushkin, A, Herbst, N & Kounev, S 2019, Chamulteon: Coordinated auto-scaling of micro-services. in 2019 39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019., 8885153, Proceedings - International Conference on Distributed Computing Systems, vol. 2019-July, Institute of Electrical and Electronics Engineers Inc., pp. 2015-2025, 39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019, Richardson, United States, 7/07/19. https://doi.org/10.1109/ICDCS.2019.00199

Chamulteon: Coordinated auto-scaling of micro-services. / Bauer, Andre; Lesch, Veronika; Versluis, Laurens et al.
2019 39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. p. 2015-2025 8885153 (Proceedings - International Conference on Distributed Computing Systems; Vol. 2019-July).

Research output: Chapter in Book / Report / Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Chamulteon

T2 - 39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019

AU - Bauer, Andre

AU - Lesch, Veronika

AU - Versluis, Laurens

AU - Ilyushkin, Alexey

AU - Herbst, Nikolas

AU - Kounev, Samuel

PY - 2019/10/31

Y1 - 2019/10/31

N2 - Nowadays, in order to keep track of the fast changing requirements of Internet applications, auto-scaling is used as an essential mechanism for adapting the number of provisioned resources to the resource demand. The straightforward approach is to deploy a set of common and opensource single-service auto-scalers for each service independently. However, this deployment leads to problems such as bottleneck-shifting and increased oscillations. Existing auto-scalers that scale applications consisting of multiple services are kept closed-source. To face these challenges, we first survey existing auto-scalers and highlight current challenges. Then, we introduce Chamulteon, a redesign of our previously introduced mechanism, which can scale applications consisting of multiple services in a coordinated manner. We evaluate Chamulteon against four different well-cited auto-scalers in four sets of measurement-based experiments where we use diverse environments (VM vs. Docker), real-world traces, and vary the scale of the demanded resources. Overall, Chamulteon achieves the best auto-scaling performance based on established user-oriented and endorsed elasticity metrics.

AB - Nowadays, in order to keep track of the fast changing requirements of Internet applications, auto-scaling is used as an essential mechanism for adapting the number of provisioned resources to the resource demand. The straightforward approach is to deploy a set of common and opensource single-service auto-scalers for each service independently. However, this deployment leads to problems such as bottleneck-shifting and increased oscillations. Existing auto-scalers that scale applications consisting of multiple services are kept closed-source. To face these challenges, we first survey existing auto-scalers and highlight current challenges. Then, we introduce Chamulteon, a redesign of our previously introduced mechanism, which can scale applications consisting of multiple services in a coordinated manner. We evaluate Chamulteon against four different well-cited auto-scalers in four sets of measurement-based experiments where we use diverse environments (VM vs. Docker), real-world traces, and vary the scale of the demanded resources. Overall, Chamulteon achieves the best auto-scaling performance based on established user-oriented and endorsed elasticity metrics.

KW - Auto-Scaling

KW - Benchmarking

KW - Cloud Computing

KW - Container

KW - Elasticity

KW - Metrics

KW - Service Demand Estimation

KW - Workload Forecasting

UR - https://www.scopus.com/pages/publications/85074866400

UR - https://www.scopus.com/pages/publications/85074866400#tab=citedBy

U2 - 10.1109/ICDCS.2019.00199

DO - 10.1109/ICDCS.2019.00199

M3 - Conference contribution

AN - SCOPUS:85074866400

T3 - Proceedings - International Conference on Distributed Computing Systems

SP - 2015

EP - 2025

BT - 2019 39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019

PB - Institute of Electrical and Electronics Engineers Inc.

Y2 - 7 July 2019 through 9 July 2019

ER -

Bauer A, Lesch V, Versluis L, Ilyushkin A, Herbst N, Kounev S. Chamulteon: Coordinated auto-scaling of micro-services. In 2019 39th IEEE International Conference on Distributed Computing Systems, ICDCS 2019. Institute of Electrical and Electronics Engineers Inc. 2019. p. 2015-2025. 8885153. (Proceedings - International Conference on Distributed Computing Systems). doi: 10.1109/ICDCS.2019.00199

Chamulteon: Coordinated auto-scaling of micro-services

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Persistent URL (handle)

Other files and links

Fingerprint

Cite this