Control-Based Load-Balancing Techniques: Analysis and Performance Evaluation via a Randomized Optimization Approach
Papadopoulos, Alessandro Vittorio LU ; Klein, Cristian ; Maggio, Martina LU ; Dürango, Jonas LU ; Dellkrantz, Manfred LU ; Hernandez-Rodriguez, Francisco ; Elmroth, Erik and Årzén, Karl-Erik LU
(2016)
In Control Engineering Practice
52(July).
p.24-34
- Abstract
- Cloud applications are often subject to unexpected events like flashcrowds and hardware failures. Users that expect a predictable behavior may abandon an unresponsive application when these events occur. Researchers and engineers addressed this problem on two separate fronts: first, they introduced replicas - copies of the application with the same functionality - for redundancy and scalability; second, they added a self-adaptive feature called brownout inside cloud applications to bound response times by modulating user experience. The presence of multiple replicas requires a dedicated component to direct incoming traffic: a load-balancer.
Existing load-balancing strategies based on response times interfere with the response time... (More) - Cloud applications are often subject to unexpected events like flashcrowds and hardware failures. Users that expect a predictable behavior may abandon an unresponsive application when these events occur. Researchers and engineers addressed this problem on two separate fronts: first, they introduced replicas - copies of the application with the same functionality - for redundancy and scalability; second, they added a self-adaptive feature called brownout inside cloud applications to bound response times by modulating user experience. The presence of multiple replicas requires a dedicated component to direct incoming traffic: a load-balancer.
Existing load-balancing strategies based on response times interfere with the response time controller developed for brownout-compliant applications. In fact, the brownout approach bounds response times using a control action. Hence, the response time, that was used to aid load-balancing decision, is not a good indicator of how well a replica is performing.
To fix this issue, this paper reviews some proposal for brownout-aware load-balancing and provides a comprehensive experimental evaluation that compares them. To provide formal guarantees on the load-balancing performance, we use a randomized optimization approach and apply the scenario theory. We perform an extensive set of experiments on a real machine, extending the popular lighttpd web server and load-balancer, and obtaining a production-ready implementation. Experimental results show an improvement of the user experience over Shortest Queue First (SQF) - believed to be near-optimal in the non-adaptive case. The improved user experience is obtained preserving the response time predictability. (Less)
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/ccf16d56-2433-430c-83c2-e6b952e82067
- author
- Papadopoulos, Alessandro Vittorio
LU
; Klein, Cristian
; Maggio, Martina
LU
; Dürango, Jonas
LU
; Dellkrantz, Manfred
LU
; Hernandez-Rodriguez, Francisco
; Elmroth, Erik
and Årzén, Karl-Erik
LU
- organization
- publishing date
- 2016-07
- type
- Contribution to journal
- publication status
- published
- subject
- keywords
- load-balancing, randomized optimization, cloud control
- in
- Control Engineering Practice
- volume
- 52
- issue
- July
- pages
- 11 pages
- publisher
- Elsevier
- external identifiers
-
- scopus:84962868608
- wos:000377740300003
- ISSN
- 0967-0661
- DOI
- 10.1016/j.conengprac.2016.03.020
- project
- EIT_VR CLOUD Cloud Control
- language
- English
- LU publication?
- yes
- id
- ccf16d56-2433-430c-83c2-e6b952e82067
- date added to LUP
- 2016-04-13 17:33:01
- date last changed
- 2022-03-31 23:19:58
@article{ccf16d56-2433-430c-83c2-e6b952e82067,
abstract = {{Cloud applications are often subject to unexpected events like flashcrowds and hardware failures. Users that expect a predictable behavior may abandon an unresponsive application when these events occur. Researchers and engineers addressed this problem on two separate fronts: first, they introduced replicas - copies of the application with the same functionality - for redundancy and scalability; second, they added a self-adaptive feature called brownout inside cloud applications to bound response times by modulating user experience. The presence of multiple replicas requires a dedicated component to direct incoming traffic: a load-balancer.<br/><br/>Existing load-balancing strategies based on response times interfere with the response time controller developed for brownout-compliant applications. In fact, the brownout approach bounds response times using a control action. Hence, the response time, that was used to aid load-balancing decision, is not a good indicator of how well a replica is performing.<br/><br/>To fix this issue, this paper reviews some proposal for brownout-aware load-balancing and provides a comprehensive experimental evaluation that compares them. To provide formal guarantees on the load-balancing performance, we use a randomized optimization approach and apply the scenario theory. We perform an extensive set of experiments on a real machine, extending the popular lighttpd web server and load-balancer, and obtaining a production-ready implementation. Experimental results show an improvement of the user experience over Shortest Queue First (SQF) - believed to be near-optimal in the non-adaptive case. The improved user experience is obtained preserving the response time predictability.}},
author = {{Papadopoulos, Alessandro Vittorio and Klein, Cristian and Maggio, Martina and Dürango, Jonas and Dellkrantz, Manfred and Hernandez-Rodriguez, Francisco and Elmroth, Erik and Årzén, Karl-Erik}},
issn = {{0967-0661}},
keywords = {{load-balancing; randomized optimization; cloud control}},
language = {{eng}},
number = {{July}},
pages = {{24--34}},
publisher = {{Elsevier}},
series = {{Control Engineering Practice}},
title = {{Control-Based Load-Balancing Techniques: Analysis and Performance Evaluation via a Randomized Optimization Approach}},
url = {{https://lup.lub.lu.se/search/files/7254320/brownout_cep2014.pdf}},
doi = {{10.1016/j.conengprac.2016.03.020}},
volume = {{52}},
year = {{2016}},
}