Piotr Kołaczkowski discusses how they integrated Spark with Cassandra, how it was done, how it works in practice and why it is better than using a Hadoop intermediate layer.
The authors present an approach for automatic translation of sequential, imperative code into a parallel MapReduce framework using Mold, translating Java code to run on Apache Spark.
Colin Mower discusses the challenges met using together Cloud, Big Data, Mobile and Security and how these can work together to achieve business value.
Sean Owen introduces Spark, Scala and random decision forests, and demonstrates the process of analyzing a real-world data set with them.
John Davies shows a Spring work-flow consuming 7.4kB XML messages, binding them to 25kB Java but storing them in just 450 bytes each, 10 million derivative contracts in-memory on a laptop.
Lin Qiao discusses the architecture of Gobblin, LinkedIn’s framework for addressing the need of high quality and high velocity data ingestion.
Eugene Mandel discusses challenges of conforming data sources and compares processing stacks: Hadoop+Redshift vs Spark, showing how the technology drives the way the problem is modeled.
Sharan Kalwani presents the history of HPC and the technologies and trends which have contributed to creating the world of big data, covering applications of HPC resulting in big data technologies.
John Leach explains using HBase co-processors to support a full ANSI SQL RDBMS without modifying the core HBase source, showing how Hadoop/HBase can replace traditional RDBMS solutions.
Roman Shaposhnik discusses more advanced features of HDFS, in addition to how YARN has enabled businesses to massively scale their systems beyond what was previously possible.
Yann Yu discusses how Solr and Hadoop complement each other, and how to use Solr as a real-time, analytical, full-text search front-end to data stored in Hadoop.
Mike Keane presents how Conversant migrated to Flume, managing 1000 agents across 4 data centers, processing over 50B log lines per day with peak hourly averages of over 1.5 million log lines/sec.