Installation Guide

Big data Cumulus-Linux installation guide

Issue link:

Contents of this Issue


Page 6 of 26

B I G D AT A W I T H C U MU L U S L I NU X 7 As you approach the limit for the number of spine switches, you can increase scale by adding additional tiers as shown in Figure 5. Figure 5. Adding Tiers Converged Administration Because Cumulus Linux is Linux and not simply a Linux-based network operating system, you also have the ability to leverage existing server automation tools for managing your switches. While big data users typically install open source solutions like Zookeeper and Ambari to deploy Hadoop clusters, you can also leverage open source and automation/orchestration tools of DevOps' choice such as: Ansible, Chef, Puppet, Salt, or CFEngine. These same tools are already used by many organizations to simplify server deployments, and modifying them to provision entire racks of Hadoop clusters, including both servers and network switches, becomes a simple task of converged administration. Cumulus Linux also integrates with many open source monitoring tools available for both servers, such as OpenTSDB, Nagios, Ganglia, and Splunk. Converged administration can show both sever and switch data in a similar manner and make correlation easier. The ability to use these common tools unifies your data center operations and can lower operational expenses. The open source nature of Cumulus Linux and the inclusion of programming languages like Python, Perl, Ruby and Bash make it very extensible and easy to modify if desired. Several innovations such as networking plug-ins with Ambari APIs can also be easily built in the future. Intended Audience for Network Design and Build The intended audience for the rest of this white paper is a data center architect or administrator experienced with big data Hadoop clusters and familiar with Layer 3 networking for large-scale designs. The network architecture and build steps provided in this document can be used as a reference for planning and implementing big data analytics with Cumulus Linux in your environment. In addition to knowledge of Apache Hadoop configuration, a basic understanding of Linux commands is assumed, such as accessing a Linux installation, navigating the file system, and editing files. If you are using this guide to help you set up your Cumulus Linux environment to support your big data implementation, we assume you have Cumulus Linux binaries, licenses, and switches from the Cumulus Linux Hardware Compatibility List (HCL) at Additional information on Cumulus Linux software, licensing, and supported hardware may be found on or by contacting

Articles in this issue

Links on this page

view archives of Installation Guide - Big data Cumulus-Linux installation guide