“It’s about matching the different dynamic workloads and taking full advantage of the platform,” said Scott Gnau, CTO, Hortonworks, Inc., describing how Hortonworks and HP are partnering to solve Big Data problems for the community.

In an interview at BigDataNYC 2015 in New York City with George Gilbert, cohost of theCUBE, from the SiliconANGLE Media team, Gnau and Joseph George, executive director: Big Data solutions & hyperscale servers at Hewlett-Packard Co., describe how developments in YARN (an architectural center of Hadoop) enable intelligent allocation of workloads to different parts of the cluster, enabling customers to do jobs faster with less data system space and less power.

In a technically detailed discussion, George and Gnau provided many examples to illustrate how, where and when resources are redirected and reallocated. If you run out of space, or run out of power, your Hadoop cluster can’t grow, explained George, but intelligent allocation of resources “lets you take something that was traditionally done in two racks and do it in one rack.”

Watch the full video interview below, and be sure to check out more of SiliconANGLE and theCUBE’s coverage of BigDataNYC 2015.

Photos by SiliconANGLE