How does Docker affect energy consumption? Evaluating workloads in and out of Docker containers

@article{Santos2018HowDD,
  title={How does Docker affect energy consumption? Evaluating workloads in and out of Docker containers},
  author={Eddie Antonio Santos and Carson McLean and Christopher Solinas and Abram Hindle},
  journal={J. Syst. Softw.},
  year={2018},
  volume={146},
  pages={14-25}
}
Power Budgeting of Big Data Applications in Container-based Clusters
TLDR
A platform that manages a power budget to cap the energy consumed from users to applications and down to individual instances is presented, showing that it is possible to distribute and enforce a powerudget among users and applications.
Evaluating Energy Consumption in a Different Virtualization within a Cloud System
TLDR
This work provides information on the impact of workload into Cloud computing services by measuring the energy usage of three different virtualization technologies namely Virtual Machine, Docker and Kubernete in an Openstack system, Opensource Cloud computing environment.
WattsApp: Power-Aware Container Scheduling
TLDR
The results highlight that power estimation has negligible overheads - nearly 90% of all data samples can be estimated with less than a 10% error, and the Mean Absolute Percentage Error (MAPE) is less than 6%.
An Analysis of the Energy Consumption Behavior of Scaled, Containerized Web Apps
TLDR
How the energy consumption behavior of single containerized web services/web apps changes while creating replicas of the service in order to scale and balance the web service is shown.
Containers in Software Development: A Systematic Mapping Study
TLDR
Containers are most often discussed in the context of cloud computing, performance and DevOps, and it is found that what is currently missing is more deeply focused research.
Erlang Based Server Selection Scheme Using Software Defined Networking in Datacenter for Energy Conservation
TLDR
An Erlang based approach to control server allocation in Software Defined Networking (SDN) based datacenters is implemented using proactive use of Erlang distribution of services along with centralized control plane architecture of SDN, thus maximizing energy efficiency, and ensuring optimal performance of services.
Energy Consumption Analysis of Edge Orchestrated Virtualized Wireless Multimedia Sensor Networks
TLDR
This paper investigates how much energy overhead is generated by Docker-based virtualization on battery powered camera sensor nodes and finds that starting and closing of containers in the Docker platform adds-up roughly 13 percent power consumption overhead during the boot-up and shutdown of the camera nodes.
Here, There, Anywhere: Profiling-Driven Services to Tame the Heterogeneity of Edge Applications
TLDR
This paper presents a profiling-based methodology that effectively matches edge computational tasks with the available devices to best satisfy programmer-defined non-functional requirements and evaluates μHTA, whose service-oriented architecture manages the heterogeneity of edge environments and optimally executes microservices on the available mobile devices.
Taming Energy Consumption Variations In Systems Benchmarking
TLDR
An empirical study of multiple controllable parameters that one can easily tune to tame the energy consumption variations when benchmarking software systems and argues that the guidelines delivered are the minimal requirements to be considered prior to any energy efficiency evaluation.
Parsimonious Edge Computing to Reduce Microservice Resource Usage
TLDR
This work designs a scaling strategy aimed to instantiate, parsimoniously, a number of microservices sufficient to guarantee a certain Quality of Service (QoS) target in a Kubernetes/Docker environment, based on a simple Proportional-Integrative-Derivative (PID) controller.
...
...

References

SHOWING 1-10 OF 20 REFERENCES
An updated performance comparison of virtual machines and Linux containers
TLDR
This paper explores the performance of traditional virtual machine (VM) deployments, and contrast them with the use of Linux containers, using KVM as a representative hypervisor and Docker as a container manager.
Power consumption of virtual machines with network transactions: Measurement and improvements
TLDR
It is found that both Hardware Virtualization and Paravirtualization add considerable energy overhead, affecting both sending and receiving, and a busy virtualized web-server may consume 40% more energy than its non-virtualized counterparts.
Energy Efficiency of Cloud Virtual Machines: From Traffic Pattern and CPU Affinity Perspectives
TLDR
Through real-world measurement on both Xen- and KVM-based platforms, it is shown that these state-of-the-art virtualization designs noticeably increase the demand of CPU resources when handling network transactions, generating excessive interrupt requests with ceaseless context switching, which increases energy consumption.
Power Consumption of Virtualization Technologies: An Empirical Investigation
  • R. Morabito
  • Computer Science
    2015 IEEE/ACM 8th International Conference on Utility and Cloud Computing (UCC)
  • 2015
TLDR
The initial results show how, despite of the number of virtual entities running, both kinds of virtualization alternatives behave similarly in idle state and in CPU/Memory stress test, and the results on network performance show differences between the two technologies.
Making cluster applications energy-aware
TLDR
This paper proposes, implements, and evaluates modifications for the Hadoop Distributed File System and the MapReduce clone that make them capable of operating efficiently under limited power budgets.
Power Efficiency of Hypervisor-based Virtualization versus Container-based Virtualization February 11 , 2016
TLDR
This research project investigates whether the power efficiency significantly differs on Xen, which is based on hypervisor virtualization, and Docker, which are based on container-based virtualization.
Haskell in Green Land: Analyzing the Energy Behavior of a Purely Functional Language
TLDR
This paper has conducted two empirical studies to analyze the energy efficiency of Haskell programs from two different perspectives: strictness and concurrency and extended two existing performance analysis tools to also collect and present data about energy consumption.
Detecting Energy Patterns in Software Development
TLDR
This paper describes several approaches for describing power con- sumption and detecting anomalous energy patterns and describes prediction models to estimate the overall energy consumption based on usage of individual modules for the Windows Phone platform.
Green mining: A methodology of relating software change to power consumption
  • Abram Hindle
  • Computer Science
    2012 9th IEEE Working Conference on Mining Software Repositories (MSR)
  • 2012
TLDR
It is demonstrated that software change can effect power consumption using the Firefox web-browser and the Azureus/Vuze BitTorrent client and there is evidence of a potential relationship between some software metrics and power consumption.
GreenOracle: Estimating Software Energy Consumption with Energy Measurement Corpora
  • S. Chowdhury, Abram Hindle
  • Computer Science
    2016 IEEE/ACM 13th Working Conference on Mining Software Repositories (MSR)
  • 2016
TLDR
This paper presents a model that can estimate software energy consumption mostly within 10% error (in joules) and does not require the developer to train on energy measurements of their own applications and applies the model to estimate any foreign application’s energy consumption for a test run.
...
...