Deepak Majeti explains why the separation of compute and storage has become critical to maximizing the benefits of cloud economics. Advances in database technology, specifically in Vertica’s architecture, now allow users to tap into the economically friendly AWS S3 as a storage location. The distinction between storing data on-premises, in HDFS (with Parquet and Orc), or in the cloud is becoming less and less of a factor in achieving high-performance big data analytics. Rapid elastic scaling of the Vertica cluster delivers just-in-time workload-based provisioning, which also keeps costs low when you don’t have major workloads being processed. This separation of the compute engine and storage resources keeps the hot data hot and the cold data cold for the best results and cost.
This session is sponsored by Micro Focus Security and Big Data Analytics.
Deepak Majeti is a systems software engineer at Vertica. He is also a committer and an active contributor to Hadoop’s two most popular file formats: ORC and Parquet. His interests lie in getting the best from HPC and big data and building scalable, high-performance, and energy-efficient data analytics tools for modern computer architectures. Deepak holds a PhD in the high-performance computing (HPC) domain from Rice University.
©2017, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • email@example.com