Overview

“Scaling Hadoop for multi-core and highly threaded systems” is the full title of this presentation from Sun’s Jangwoo Kim and Denis Sheahan.

Here they present the basic architecture of CMT (chip multi-threading) processors, designed by Sun for maximum throughput, and then describe the work the team did using Hadoop and other virtualization technologies to help scale CMT. They also present a case study of a small Washington, DC company they worked with that’s using Hadoop for email discovery.

Quote

Tom White, Cloudera engineer, Hadoop committer, and author of Hadoop the Definitive Guide, from O’Reilly and Yahoo! Press, talks about running Hadoop in EC2.

He opens with a discussion of the Berkeley RAD Lab paper on cloud computing and walks us through a set of definitions to a discussion of the public cloud. He sees a realm of interesting possibilities: an apparently infinite resource; the elimination of user commitment; and the pay-as you go model, which enables elasticity. Tom describes the implementation of Hadoop in this landscape.

Overview

The “Hey, Einstein!” app on My Yahoo! tests your knowledge with an engaging new quiz every day. Developed by LiveScience, you can use this app to compare your results with friends and the rest of the Yahoo community. The app uses PHP, JavaScript, and the Yahoo! PHP SDK. Find out more about the app from LiveScience developer Tim Monaghan

Overview

There are compelling economic reasons to run datacenters with energy efficient software, as UC Berkeley researchers Laura Keys and Yanpei Chen describe in this talk. Typically, datacenters are measured using a Power Utilization Efficiency (PUE) metric– but until now the role of software in the equation has been neglected.

The speakers include energy use as a dimension of software performance alongside productivity and resource consumption metrics, and describe their experiments and findings on changing Hadoop software parameters to improve energy efficiency.

Overview

Amazon Web Services (AWS) evangelist Jinesh Varia presents Amazon’s Elastic MapReduce, a web service that simplifies the complexity of large-scale data processing operations for a growing ecosystem of AWS users. The product utilizes a hosted Hadoop framework running on the infrastructure of Amazon Elastic Compute Cloud (Amazon EC2) and Amazon Simple Storage Service (Amazon S3) and addresses use cases that involve data mining, bio-informatics, financial simulation, file processing, and web indexing.