Linux, Hadoop and Amazon Web Services: Crunching Big Data in the Cloud

The BoF session will cover how to utilize Hadoop on Amazon EC2, including storage options: localdisk, EBS, S3, etc. price/performance of EC2, and will demonstrate how to get started fast with Hadoop on EC2 - from registering an Amazon Web Services account to launching an EC2 Hadoop cluster and using such tools as Apache Pig and HIVE to analyze your data. As an example, we will walk you through the analysis of real Tivoli log data, from the business question you want to ask through answering it with amazon web services and Hadoop, to arrive at a more informed provisioning and purchasing decision.

No pre-existing knowledge of Amazon web services or Hadoop is required to participate, although an understanding of basic Linux bash commands will be helpful. Participants are encouraged to follow along with their notebook computers and amazon web services accounts.

We are Cloud Stenography. The session will be led by Russell Jurney and John Willis.