IMDEA Networks Institute Publications Repository

When Less is More: Core-Restricted Container Provisioning for Serverless Computing

Gaetano, Somma and Ayimba, Constantine and Paolo, Casari and Simon Pietro , Romano and Mancuso, Vincenzo (2020) When Less is More: Core-Restricted Container Provisioning for Serverless Computing. In: The 3rd International Workshop on Network Intelligence (NI 2020): Learning and Optimizing Future Networks, 6 July 2020, Toronto, Canada.

[img] PDF
Download (585Kb)

Abstract

Cloud applications are exposed to workloads whose intensity can change unpredictably over time. Hence, the ability to quickly scale the amount of computing resources provisioned to applications is essential to minimize costs while providing reliable services. In this context,containers are deemed to be a promising technology to enable fast elasticity in resource allocation schemes.In this paper, we propose and experimentally test an efficient container-based cloud computing provisioning system. First, we address the container deployment problem and discuss how to manage container provisioning and scaling. Second, we devise are source management mechanism leveraging on both admission control and auto-scaling techniques. We propose to drive auto-scaling decisions through a Q-Learning algorithm, which is agnostic to the specific computing environment, and proceeds based only on the load of the physical processors assigned to a container. We evaluate our solution in two experimental setups,and show that it yields significant advantages when compared to popular container managers such as Kubernetes.

Item Type: Conference or Workshop Papers (Paper)
Uncontrolled Keywords: Autoscaling, Provisioning, Q-Learning, Container, Docker, Kubernetes
Subjects: UNSPECIFIED
Divisions: UNSPECIFIED
Depositing User: Constantine Ayimba
Date Deposited: 13 Apr 2020 08:33
Last Modified: 13 Apr 2020 08:33
URI: http://eprints.networks.imdea.org/id/eprint/2125

Actions (login required)

View Item View Item