This Big Data Networked Storage Solution for Hadoop Redpaper  provides a reference architecture, based on Apache Hadoop, to help businesses gain control over their data, meet tight service level agreements (SLAs) around their data applications, and turn data-driven insight into effective action.

I was in Las Vegas during Edge2013 and had a chance to talk to the IBM Product Manager of Storage for Big Data Analytics and HPC.  I had printed a hardcopy of this Redpaper to give to him and just as I handed it to him someone walked up and shouted, "Where can I get a copy of that Hadoop Redpaper? That is hot stuff!" We introduced ourselves and it turns out he is the president  of a technology services company in Chicago and has a group of clients very interested in Hadoop. 

I explained that the Redpaper was just published the prior week and the copy  we were holding was the only hardcopy in Vegas.   We went ahead and  gave it to him and he invited the product manager to visit and present to his clients.   Definitely a positive experience having been involved in producing a Redpaper with such a positive and timely reaction. 

 The redpaper describes several Hadoop test case scenarios.  Figure 1 from the Redpaper  shows that MapReduce is the Hadoop framework for parallel processing and the Hadoop Distributed File System (HDFS) is the distributed file system that provides petabyte-size storage and data management can be integrated with IBM Systems and Storage. 

As enterprises begin to move Hadoop deployments out of the lab and into production, they typically expect a certain degree of scalability and efficiency. IBM Open Solution for Hadoop uniquely complements the IBM feature-rich BigInsights software suite to create an end-to-end solution that focuses on functionality, efficiency, and quality that are so critical.

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

 

Figure 1.  IBM Integration with Hadoop