UPDATED 18:29 EDT / JUNE 27 2013

NEWS

Understand Your Own Scale : The First Step in Adopting Hadoop for Enterprise | #hadoopsummit

Karthik Ranganathan, Member of Technical Staff, Nutanix, discussed the advantages of converged infrastructure for Hadoop and their benefits to the enterprise with theCUBE co-hosts John Furrier and Dave Vellante, live at the 2013 Hadoop Summit in San Jose.

Asked about the differences between the hyperscale market and the enterprise, and how Nutanix addressed it, Ranganathan said that “the idea is that’s a device, that encompasses all your performance needs at the ratio you need so that you can configure a distributed cluster,” allowing companies to grow as needed. “The magic sauce is a continuum over time,” he added, “you see new use cases, you adapt, you see more data, you scale out.”

DevOps: Know your own scale

 

John Furrier pointed out that companies look at what Facebook has done with DevOps as a modern way to deploy quickly and scale out and asked what is the mindset of these businesses, and how they should address Hadoop. Ranganathan said that “the most important thing I feel is understanding your own scale. If you’re going to build something that will scale,” scale should be at the core right from the start.

Performance is next, but “as long as the fundamental architecture will scale, that’s the first step,” Ranganathan says. The second step is to make sure you have manageability. Will the system fix itself? What to do when something fails? “Performance is ongoing, but try to build upfront for scalability and manageability.”

Initially, such a way of thinking might be a shock, but slowly,  while working through the mindset and talking to companies, “people usually turn and try and play with the software,” Ranganathan says, then they begin to understand and ask questions. People usually see the benefits of scale out and distributed architectures.

Why converged infrastructure works for Hadoop in the enterprise

 

Asked why converged infrastructure for Hadoop was a good choice, Ranganathan said that in the typical enterprise, there are two potential scenarios – either they are trying to figure out their Big Data needs and how to put it to good use, or they have a bunch of data, and are trying to get some meaning out of it.

The alternative to converged infrastructures would be determining what hardware they need, getting a team to implement and manage it, all becoming a rather complicated and consuming process. With convergence, you don’t give up much performance, “but the big story is the manageability aspect,” says Ranganathan.  When you run Hadooop in a virtual machine, your admins know how to run it, as they are already familiar with virtualization.

Asked why he specifically chose Nutanix after having worked at Facebook, Ranganathan said “they’re bringing all the principles that I was passionate about at Facebook to the enterprise,” the distributed system, the failure management, the scale out.


A message from John Furrier, co-founder of SiliconANGLE:

Your vote of support is important to us and it helps us keep the content FREE.

One click below supports our mission to provide free, deep, and relevant content.  

Join our community on YouTube

Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.

“TheCUBE is an important partner to the industry. You guys really are a part of our events and we really appreciate you coming and I know people appreciate the content you create as well” – Andy Jassy

THANK YOU