Quantifying the Impact of Replication on the Quality-of-Service in Cloud Databases

Título traducido de la contribución: Cuantificación del impacto de la replicación en la calidad del servicio en bases de datos en la nube

Rasha Osman, Juan F. Perez, Giuliano Casale

Resultado de la investigación: Contribución a libro /Tipo informe o reporteContribución en conferencia

Resumen

Las bases de datos en nube logran una alta disponibilidad al replicar automáticamente los datos en múltiples nodos. Sin embargo, la sobrecarga causada por el proceso de replicación puede llevar a un aumento de la media y la varianza de los tiempos de respuesta de las transacciones, causando impactos imprevistos en la calidad de servicio ofrecida (QoS). En este documento, proponemos una metodología basada en la medición para predecir el impacto de la replicación en los entornos de Base de Datos como Servicio (DBaaaS). Nuestra metodología utiliza datos operativos para parametrizar un modelo de red de colas cerradas del cluster de la base de datos junto con un modelo de Markov que abstrae el proceso de replicación dinámica. Los experimentos con Amazon RDS muestran que nuestra metodología predice tiempos de respuesta medios y percentiles con errores de sólo 1% y 15% respectivamente, y bajo condiciones operativas significativamente diferentes a las utilizadas para la parametrización del modelo. Demostramos que nuestro enfoque de modelado supera los métodos de modelado estándar e ilustra la aplicabilidad de nuestra metodología para el aprovisionamiento automatizado de DBaaaS.
Idioma originalEnglish (US)
Título de la publicación alojadaProceedings - 2016 IEEE International Conference on Software Quality, Reliability and Security, QRS 2016
EditorialInstitute of Electrical and Electronics Engineers Inc.
Páginas286-297
Número de páginas12
ISBN (versión digital)9781509041275
DOI
EstadoPublished - oct 12 2016
Publicado de forma externa
Evento2nd IEEE International Conference on Software Quality, Reliability and Security, QRS 2016 - Vienna
Duración: ago 1 2016ago 3 2016

Conference

Conference2nd IEEE International Conference on Software Quality, Reliability and Security, QRS 2016
PaísAustria
CiudadVienna
Período8/1/168/3/16

Huella dactilar

Quality of service
Queueing networks
Parameterization
Availability
Experiments

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Software
  • Safety, Risk, Reliability and Quality

Citar esto

Osman, R., Perez, J. F., & Casale, G. (2016). Quantifying the Impact of Replication on the Quality-of-Service in Cloud Databases. En Proceedings - 2016 IEEE International Conference on Software Quality, Reliability and Security, QRS 2016 (pp. 286-297). [7589808] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/QRS.2016.40
Osman, Rasha ; Perez, Juan F. ; Casale, Giuliano. / Quantifying the Impact of Replication on the Quality-of-Service in Cloud Databases. Proceedings - 2016 IEEE International Conference on Software Quality, Reliability and Security, QRS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 286-297
@inproceedings{12ad6e48715f405898f29d992d1fd052,
title = "Quantifying the Impact of Replication on the Quality-of-Service in Cloud Databases",
abstract = "Cloud databases achieve high availability by automatically replicating data on multiple nodes. However, the overhead caused by the replication process can lead to an increase in the mean and variance of transaction response times, causing unforeseen impacts on the offered quality-of-service (QoS). In this paper, we propose a measurement-driven methodology to predict the impact of replication on Database-As-A-Service (DBaaS) environments. Our methodology uses operational data to parameterize a closed queueing network model of the database cluster together with a Markov model that abstracts the dynamic replication process. Experiments on Amazon RDS show that our methodology predicts response time mean and percentiles with errors of just 1{\%} and 15{\%} respectively, and under operational conditions that are significantly different from the ones used for model parameterization. We show that our modeling approach surpasses standard modeling methods and illustrate the applicability of our methodology for automated DBaaS provisioning.",
author = "Rasha Osman and Perez, {Juan F.} and Giuliano Casale",
year = "2016",
month = "10",
day = "12",
doi = "10.1109/QRS.2016.40",
language = "English (US)",
pages = "286--297",
booktitle = "Proceedings - 2016 IEEE International Conference on Software Quality, Reliability and Security, QRS 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Osman, R, Perez, JF & Casale, G 2016, Quantifying the Impact of Replication on the Quality-of-Service in Cloud Databases. En Proceedings - 2016 IEEE International Conference on Software Quality, Reliability and Security, QRS 2016., 7589808, Institute of Electrical and Electronics Engineers Inc., pp. 286-297, Vienna, 8/1/16. https://doi.org/10.1109/QRS.2016.40

Quantifying the Impact of Replication on the Quality-of-Service in Cloud Databases. / Osman, Rasha; Perez, Juan F.; Casale, Giuliano.

Proceedings - 2016 IEEE International Conference on Software Quality, Reliability and Security, QRS 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 286-297 7589808.

Resultado de la investigación: Contribución a libro /Tipo informe o reporteContribución en conferencia

TY - GEN

T1 - Quantifying the Impact of Replication on the Quality-of-Service in Cloud Databases

AU - Osman, Rasha

AU - Perez, Juan F.

AU - Casale, Giuliano

PY - 2016/10/12

Y1 - 2016/10/12

N2 - Cloud databases achieve high availability by automatically replicating data on multiple nodes. However, the overhead caused by the replication process can lead to an increase in the mean and variance of transaction response times, causing unforeseen impacts on the offered quality-of-service (QoS). In this paper, we propose a measurement-driven methodology to predict the impact of replication on Database-As-A-Service (DBaaS) environments. Our methodology uses operational data to parameterize a closed queueing network model of the database cluster together with a Markov model that abstracts the dynamic replication process. Experiments on Amazon RDS show that our methodology predicts response time mean and percentiles with errors of just 1% and 15% respectively, and under operational conditions that are significantly different from the ones used for model parameterization. We show that our modeling approach surpasses standard modeling methods and illustrate the applicability of our methodology for automated DBaaS provisioning.

AB - Cloud databases achieve high availability by automatically replicating data on multiple nodes. However, the overhead caused by the replication process can lead to an increase in the mean and variance of transaction response times, causing unforeseen impacts on the offered quality-of-service (QoS). In this paper, we propose a measurement-driven methodology to predict the impact of replication on Database-As-A-Service (DBaaS) environments. Our methodology uses operational data to parameterize a closed queueing network model of the database cluster together with a Markov model that abstracts the dynamic replication process. Experiments on Amazon RDS show that our methodology predicts response time mean and percentiles with errors of just 1% and 15% respectively, and under operational conditions that are significantly different from the ones used for model parameterization. We show that our modeling approach surpasses standard modeling methods and illustrate the applicability of our methodology for automated DBaaS provisioning.

UR - http://www.scopus.com/inward/record.url?scp=84995403894&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84995403894&partnerID=8YFLogxK

U2 - 10.1109/QRS.2016.40

DO - 10.1109/QRS.2016.40

M3 - Conference contribution

SP - 286

EP - 297

BT - Proceedings - 2016 IEEE International Conference on Software Quality, Reliability and Security, QRS 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Osman R, Perez JF, Casale G. Quantifying the Impact of Replication on the Quality-of-Service in Cloud Databases. En Proceedings - 2016 IEEE International Conference on Software Quality, Reliability and Security, QRS 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 286-297. 7589808 https://doi.org/10.1109/QRS.2016.40