Change search
ReferencesLink to record
Permanent link

Direct link
Control-based load-balancing techniques: Analysis and performance evaluation via a randomized optimization approach
Lund University, Sweden.ORCID iD: 0000-0002-1364-8127
Umeå University, Faculty of Science and Technology, Department of Computing Science. (DS)ORCID iD: 0000-0003-0106-3049
Lund University.ORCID iD: 0000-0002-1143-1127
Lund University, Sweden.
Show others and affiliations
2016 (English)In: Control Engineering Practice, ISSN 0967-0661, E-ISSN 1873-6939, Vol. 52, 24-34 p.Article in journal (Refereed) Published
Abstract [en]

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.

Place, publisher, year, edition, pages
Elsevier, 2016. Vol. 52, 24-34 p.
Keyword [en]
Load-balancing, Randomized optimization, Cloud control
National Category
Computer Science
Research subject
Computer Science
URN: urn:nbn:se:umu:diva-119368DOI: 10.1016/j.conengprac.2016.03.020ISI: 000377740300003OAI: diva2:920654
Swedish Research Council, Cloud ControlSwedish Research Council, Power and temperature control for large-scale computing infrastructureseLLIIT - The Linköping‐Lund Initiative on IT and Mobile Communications
Available from: 2016-04-18 Created: 2016-04-18 Last updated: 2016-09-14Bibliographically approved

Open Access in DiVA

The full text will be freely available from 2018-07-31 11:07
Available from 2018-07-31 11:07

Other links

Publisher's full textURL

Search in DiVA

By author/editor
Papadopoulos, Alessandro VittorioKlein, CristianMaggio, MartinaHernández-Rodriguez, FranciscoElmroth, Erik
By organisation
Department of Computing Science
In the same journal
Control Engineering Practice
Computer Science

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Altmetric score

Total: 54 hits
ReferencesLink to record
Permanent link

Direct link