Modeling of Request Cloning in Cloud Server Systems using Processor Sharing

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding

Standard

Modeling of Request Cloning in Cloud Server Systems using Processor Sharing. / Nylander, Tommi; Ruuskanen, Johan; Årzén, Karl-Erik; Maggio, Martina.

Proceedings of the 2020 ACM/SPEC International Conference on Performance Engineering (ICPE ’20). 2020.

Forskningsoutput: Kapitel i bok/rapport/Conference proceedingKonferenspaper i proceeding

Harvard

Nylander, T, Ruuskanen, J, Årzén, K-E & Maggio, M 2020, Modeling of Request Cloning in Cloud Server Systems using Processor Sharing. i Proceedings of the 2020 ACM/SPEC International Conference on Performance Engineering (ICPE ’20)., Edmonton, Kanada, 2020/04/20.

APA

Nylander, T., Ruuskanen, J., Årzén, K-E., & Maggio, M. (Accepterad/under tryckning). Modeling of Request Cloning in Cloud Server Systems using Processor Sharing. I Proceedings of the 2020 ACM/SPEC International Conference on Performance Engineering (ICPE ’20)

CBE

Nylander T, Ruuskanen J, Årzén K-E, Maggio M. 2020. Modeling of Request Cloning in Cloud Server Systems using Processor Sharing. I Proceedings of the 2020 ACM/SPEC International Conference on Performance Engineering (ICPE ’20).

MLA

Nylander, Tommi et al. "Modeling of Request Cloning in Cloud Server Systems using Processor Sharing". Proceedings of the 2020 ACM/SPEC International Conference on Performance Engineering (ICPE ’20). 2020.

Vancouver

Nylander T, Ruuskanen J, Årzén K-E, Maggio M. Modeling of Request Cloning in Cloud Server Systems using Processor Sharing. I Proceedings of the 2020 ACM/SPEC International Conference on Performance Engineering (ICPE ’20). 2020

Author

Nylander, Tommi ; Ruuskanen, Johan ; Årzén, Karl-Erik ; Maggio, Martina. / Modeling of Request Cloning in Cloud Server Systems using Processor Sharing. Proceedings of the 2020 ACM/SPEC International Conference on Performance Engineering (ICPE ’20). 2020.

RIS

TY - GEN

T1 - Modeling of Request Cloning in Cloud Server Systems using Processor Sharing

AU - Nylander, Tommi

AU - Ruuskanen, Johan

AU - Årzén, Karl-Erik

AU - Maggio, Martina

PY - 2020

Y1 - 2020

N2 - The interest for studying server systems subject to cloned requests has recently increased. In this paper we present a model that allows us to equivalently represent a system of servers with cloned requests, as a single server. The model is very general, and we show that no assumptions on either inter-arrival or service time distributions are required, allowing for, e.g., both heterogeneity and dependencies. Further, we show that the model holds for any queuing discipline. However, we focus our attention on Processor Sharing, as the discipline has not been studied before in this context.The key requirement that enables us to use the single server G/G/1 model is that the request clones have to receive synchronized service. We show examples of server systems fulfilling this requirement. We also use our G/G/1 model to co-design traditional load-balancing algorithms together with cloning strategies, providing well-performing and provably stable designs.Finally, we also relax the synchronized service requirement and study the effects of non-perfect synchronization. We derive bounds for how common imperfections that occur in practice, such as arrival and cancellation delays, affect the accuracy of our model. We empirically demonstrate that the bounds are tight for small imperfections, and that our co-design method for the popular Join-Shortest-Queue (JSQ) policy can be used even under relaxed synchronization assumptions with small loss in accuracy.

AB - The interest for studying server systems subject to cloned requests has recently increased. In this paper we present a model that allows us to equivalently represent a system of servers with cloned requests, as a single server. The model is very general, and we show that no assumptions on either inter-arrival or service time distributions are required, allowing for, e.g., both heterogeneity and dependencies. Further, we show that the model holds for any queuing discipline. However, we focus our attention on Processor Sharing, as the discipline has not been studied before in this context.The key requirement that enables us to use the single server G/G/1 model is that the request clones have to receive synchronized service. We show examples of server systems fulfilling this requirement. We also use our G/G/1 model to co-design traditional load-balancing algorithms together with cloning strategies, providing well-performing and provably stable designs.Finally, we also relax the synchronized service requirement and study the effects of non-perfect synchronization. We derive bounds for how common imperfections that occur in practice, such as arrival and cancellation delays, affect the accuracy of our model. We empirically demonstrate that the bounds are tight for small imperfections, and that our co-design method for the popular Join-Shortest-Queue (JSQ) policy can be used even under relaxed synchronization assumptions with small loss in accuracy.

KW - Cloning

KW - Cloud computing

KW - Datacenters

M3 - Paper in conference proceeding

BT - Proceedings of the 2020 ACM/SPEC International Conference on Performance Engineering (ICPE ’20)

ER -