Supporting Programmable Autoscaling Rules for Containers and Virtual Machines on Clouds

Research output: Article

1 Citation (Scopus)

Abstract

With the increasing utilization of cloud computing and container technologies, orchestration is becoming an important area on both cloud and container levels. Beyond resource allocation, deployment and configuration, scaling is a key functionality in orchestration in terms of policy, description and flexibility. This paper presents an approach where the aim is to provide a high degree of flexibility in terms of available monitoring metrics and in terms of the definition of elasticity rules to implement practically any possible business logic for a given application. The aim is to provide a general interface for supporting programmable scaling policies utilizing monitoring metrics originating from infrastructure, application or any external components. The paper introduces a component, called Policy Keeper performing the auto-scaling based on user-defined rules, details how this component is operating in the auto-scaling framework, called MiCADO and demonstrates a deadline-based scaling use case.

Original languageEnglish
Pages (from-to)813-829
Number of pages17
JournalJournal of Grid Computing
Volume17
Issue number4
DOIs
Publication statusPublished - dec. 1 2019

ASJC Scopus subject areas

  • Software
  • Information Systems
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Supporting Programmable Autoscaling Rules for Containers and Virtual Machines on Clouds'. Together they form a unique fingerprint.

  • Cite this