Auto-Scaling of Containers: The Impact of Relative and Absolute Metrics

Today, The cloud industry is adopting the container technology both for internal usage and as commercial offering. The use of containers as base technology for large-scale systems opens many challenges in the area of resource management at run-time. This paper addresses the problem of selecting the more appropriate performance metrics to activate auto-scaling actions. Specifically, we investigate the use of relative and absolute metrics. Results demonstrate that, for CPU intense workload, the use of absolute metrics enables more accurate scaling decisions. We propose and evaluate the performance of a new autoscaling algorithm that could reduce the response time of a factor between 0.66 and 0.5 compared to the actual Kubernetes' horizontal auto-scaling algorithm.

[1]  Miika Komu,et al.  Hypervisors vs. Lightweight Virtualization: A Performance Comparison , 2015, 2015 IEEE International Conference on Cloud Engineering.

[2]  Eric W. Biederman,et al.  Multiple Instances of the Global Linux Namespaces , 2010 .

[3]  Maya Gokhale,et al.  A Container-Based Approach to OS Specialization for Exascale Computing , 2015, 2015 IEEE International Conference on Cloud Engineering.

[4]  Richard O. Sinnott,et al.  A performance comparison of container-based technologies for the Cloud , 2017, Future Gener. Comput. Syst..

[5]  Dirk Merkel,et al.  Docker: lightweight Linux containers for consistent development and deployment , 2014 .

[6]  David Bernstein,et al.  Containers and Cloud: From LXC to Docker to Kubernetes , 2014, IEEE Cloud Computing.

[7]  Eui-nam Huh,et al.  An Index Scheme for Similarity Search on Cloud Computing using MapReduce over Docker Container , 2016, IMCOM.

[8]  Emiliano Casalicchio.  Autonomic Orchestration of Containers: Problem Definition and Research Challenges , 2016, VALUETOOLS.

[9]  Wouter Joosen,et al.  Towards a container-based architecture for multi-tenant SaaS applications , 2016, ARM@Middleware.

[10]  Rui Zhang,et al.  Finding the Big Data Sweet Spot: Towards Automatically Recommending Configurations for Hadoop Clusters on Docker Containers , 2015, 2015 IEEE International Conference on Cloud Engineering.

[11]  Ramakrishnan Rajamony,et al.  An updated performance comparison of virtual machines and Linux containers , 2015, 2015 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS).

[12]  Andreas Wilke,et al.  Skyport - Container-Based Execution Environment Management for Multi-cloud Scientific Workflows , 2014, 2014 5th International Workshop on Data-Intensive Computing in the Clouds.

[13]  Eric A. Brewer,et al.  Borg, Omega, and Kubernetes , 2016, ACM Queue.

[14]  Emiliano Casalicchio,et al.  Measuring Docker Performance: What a Mess!!! , 2017, ICPE Companion.

[15]  Ken Thompson,et al.  The use of name spaces in Plan 9 , 1993, OPSR.

[16]  Christoph Hochreiner,et al.  Elastic Provisioning of Virtual Machines for Container Deployment , 2017, ICPE Companion.

[17]  Giuseppina Cretella,et al.  Advances in Applications Portability and Services Interoperability among Multiple Clouds , 2015, IEEE Cloud Computing.

[18]  Dharmesh Kakadia,et al.  Virtualization vs Containerization to Support PaaS , 2014, 2014 IEEE International Conference on Cloud Engineering.

[19]  Vlado Stankovski,et al.  Implementing time-critical functionalities with a distributed adaptive container architecture , 2016, iiWAS.

[20]  Malgorzata Steinder,et al.  Docker Containers across Multiple Clouds and Data Centers , 2015, 2015 IEEE/ACM 8th International Conference on Utility and Cloud Computing (UCC).

[21]  Ramki Krishnan,et al.  An Analysis of Container-based Platforms for NFV , 2015 .

[22]  Moustafa Ghanem,et al.  Elastic Application Container: A Lightweight Approach for Cloud Resource Provisioning , 2012, 2012 IEEE 26th International Conference on Advanced Information Networking and Applications.