Anyone doing Big Data on z?


#1

Curious if there is anyone using Spark or Hadoop with their mainframes. Want to see what the common use cases are.


#2

Hi, just to share my curiosity upon this matter as well. Sounds quite interesting.


#3

An email to Mythili Venkatakrishnan (mythili@us.ibm.com) would answer this. We have around 15 Spark PoCs with clients and while we can’t disclose the details, we can disclose the general use-cases.


#4

We want to set it up for education purposes. I will inform about our progress as soon was we are started!


#5

@wolfram Interesting. Keep us up to date on this - keen to see how it works for you.


#6

We should have him chime in on this thread - can you forward this to him?


#7

Hey @jmertic,

I’m new to Open Mainframe project and I’m willing to contribute in project based on Docker, ML and Blockchain.
We’re using Spark for our DynaML project.

I submitted my proposal for Open Mainframe Project and submitting another one soon.

Please let me know the ways to get involved in Open Mainframe Project.

Cheers,
Amit Kumar Jaiswal


#8

That’s great to hear! Excited for your contributions to the project.

Thanks!

John Mertic
Director of Program Management - Linux Foundation - ODPi and Open Mainframe
Project
jmertic@linuxfoundation.org
+1 234-738-4571


#9

I created spark/spark-ui/zeppelin containers for Linux on z. Hadoop is part of this. See:
https://hub.docker.com/u/sinenomine/dashboard/ which holds 60+ containers for use on z, and Getting Started with OpenShift on z in which a chapter describes how to use the spark/zeppelin containers.

Neale


#10

Great to hear! Do you commercially support these containers?