An architecture for automatic scaling of replicated services
An architecture for automatic scaling of replicated services
Replicated services that allow to scale dynamically can adapt to requests load. Choosing the right number of replicas is fundamental to avoid performance worsening when input spikes occur and to save resources when the load is low. Current mechanisms for automatic scaling are mostly based on fixed thresholds on CPU and memory usage, which are not sufficiently accurate and often entail late countermeasures. We propose Make Your Service Elastic (MYSE), an architecture for automatic scaling of generic replicated services based on queuing models for accurate response time estimation. Requests and service times patterns are analyzed to learn and predict over time their distribution so as to allow for early scaling. A novel heuristic is proposed to avoid the flipping phenomenon. We carried out simulations that show promising results for what concerns the effectiveness of our approach.
Aniello, Leonardo
9846e2e4-1303-4b8b-9092-5d8e9bb514c3
Bonomi, Silvia
7d0e385d-e494-47aa-8589-a804a7a50fe0
Lombardi, Federico
78e41297-64c9-4c1e-9515-8eb59334a795
Zelli, Alessandro
8de735da-72e6-48e3-ba56-324132372095
Baldoni, Roberto
4265db45-a184-45c4-a56d-b5829b6f6f1f
Aniello, Leonardo
9846e2e4-1303-4b8b-9092-5d8e9bb514c3
Bonomi, Silvia
7d0e385d-e494-47aa-8589-a804a7a50fe0
Lombardi, Federico
78e41297-64c9-4c1e-9515-8eb59334a795
Zelli, Alessandro
8de735da-72e6-48e3-ba56-324132372095
Baldoni, Roberto
4265db45-a184-45c4-a56d-b5829b6f6f1f
Aniello, Leonardo, Bonomi, Silvia, Lombardi, Federico, Zelli, Alessandro and Baldoni, Roberto
(2014)
An architecture for automatic scaling of replicated services.
In Network Systems NETYS 2014.
Springer.
122 pp
.
(doi:10.1007/978-3-319-09581-3_9).
Record type:
Conference or Workshop Item
(Paper)
Abstract
Replicated services that allow to scale dynamically can adapt to requests load. Choosing the right number of replicas is fundamental to avoid performance worsening when input spikes occur and to save resources when the load is low. Current mechanisms for automatic scaling are mostly based on fixed thresholds on CPU and memory usage, which are not sufficiently accurate and often entail late countermeasures. We propose Make Your Service Elastic (MYSE), an architecture for automatic scaling of generic replicated services based on queuing models for accurate response time estimation. Requests and service times patterns are analyzed to learn and predict over time their distribution so as to allow for early scaling. A novel heuristic is proposed to avoid the flipping phenomenon. We carried out simulations that show promising results for what concerns the effectiveness of our approach.
Text
AnArchitectureForAutomaticScalingOfReplicatedServices_
- Accepted Manuscript
More information
Accepted/In Press date: 2 February 2014
e-pub ahead of print date: 3 August 2014
Venue - Dates:
NETYS 2014, , Marrekech, Morocco, 2014-05-15 - 2014-05-17
Identifiers
Local EPrints ID: 419692
URI: http://eprints.soton.ac.uk/id/eprint/419692
PURE UUID: ee18a51b-d45c-4ff6-af60-aee1344090b4
Catalogue record
Date deposited: 19 Apr 2018 16:30
Last modified: 16 Mar 2024 04:32
Export record
Altmetrics
Contributors
Author:
Leonardo Aniello
Author:
Silvia Bonomi
Author:
Federico Lombardi
Author:
Alessandro Zelli
Author:
Roberto Baldoni
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics