This article outlines the process of installing the Apache Hadoop and Spark Bigtop v1.1.0 bundle on an IBM® SoftLayer® POWER8® bare metal server running Ubuntu 14.04. Apache Zeppelin notebook is included in the bundled installation script to run an initial benchmark suite.
PDF (648 KB) |
(email@example.com), Big Data Solution Developer, IBM
Amir Sanjar has many years of experience in big data software and solution development at companies including IBM and Canonical. He holds several patents in areas of enterprise solution automation, wireless, and cell technology. Currently at IBM, he leads big data ecosystem and ISVs IBM Power enablement.
(firstname.lastname@example.org), ISST Open Source Offerings Test Lead, IBM
Donna has been with IBM for over 15 years, the majority of her time spent as a Test Lead on various IBM System programs such as FAStT, RSSM, and FLEX iLAB. Two years ago, she moved to lead the IBM PowerKVM Customer Test Environment project, researching and implementing analytic and cloud solutions with Linux on Power architecture. She is currently the Integrated Software Systems Test Open Source Offerings Test Lead.
(email@example.com), Software Performance Analyst, IBM
Bill started work as an IBM DB2® kernel developer, and then after 8 years moved to the System and Software Performance group. There, he tests the performance of a wide range of products, Including Hadoop and Spark on SoftLayer, creating price and performance reports.
(firstname.lastname@example.org), ISST Power SW Solutions Test Architect, IBM
Maria Ward is the Power Software and Solutions Test Architect for the IBM Systems Client Advocacy and System Assurance organization. Her current focus is on IBM Power solutions and integrating OpenPOWER and open source technologies, such as Hadoop and Spark, into the IBM Power Systems test strategy to help provide a green path to deploying customer solutions on IBM Power servers.
01 June 2016
- Table of contents
- 2. Getting started on SoftLayer
- 3. Preparing the system for Bigtop installation
- 4. Installing Bigtop Hadoop
- 5. Installing and running the Hadoop test script
- 6. Installing and running the Spark test script
- 8. Zeppelin sample stock intraday workload