Scaling with Your Data: An Introduction to Hadoop

Cloudera will provide a tutorial aimed at producers and users of large volumes of data. Do you deal with TBs on a regular basis? Are traditional databases not doing what you need? Are your challenges related primarily to processing and analyzing data, rather than simply finding it? Hadoop and MapReduce might be just what you need. Google developed an integrated storage and processing framework to scale with the web. After publishing their results, the Apache Software Foundation, along with major contributions from Yahoo!, Facebook and others got the Hadoop project off the ground. Hadoop provides a fully open source implementation of the same system Google uses to perform deep analysis on web scale data.

This half-day tutorial will teach you what you need to know to work more deeply with Hadoop, and help you think about the following questions:

• What must our organization do differently to effectively use large-scale data?
• What tools help us analyze large-scale data and extract meaningful results, and how do we use them?
• How can we reorient our data generation and collection processes to enable more powerful analysis later?

We’ll cover basics around working with large scale data systems and introduce participants to the MapReduce programming model. More importantly, we’ll focus on how to “think in MapReduce.” We’ll go through examples of how to convert common tasks into MapReduce, and provide the foundations which enable you to convert your own specific tasks to this model. We’ll also point you to resources you need to get up and running with Hadoop in your own data center or in the cloud.