CERN Accelerating science

Evaluation of Apache Mesos for Data Analytics

Date published: 
Tuesday, 1 September, 2015
Document type: 
Summer student report
S. Amrouche
Apache Mesos is a popular open source cluster manager for data centers and cloud environments, aimed at providing efficient resource isolation and sharing across distributed applications. Apache Mesos is used in multiple domains as it provides frameworks to run distributed applications for Big Data processing such as Hadoop, Spark and Storm, for batch scheduling like Chronos, data storage, PaaS and more. This report is about the evaluation of Apache Mesos in the context of data analytics and distributed applications. The evaluation consists mainly of the installation and configuration of an Apache Mesos cluster as well as the analysis of the performance and management of resources in a data analytics context.