The World's Largest Data Warehouse

By Jackie Davis and Jens Langer, NetApp


According to Gartner and other research institutions, Big Data will grow explosively over the next few years. The average company’s annual IT spending for Big Data will grow ten-fold from 2012 to 2016. In 2020 Big Data, will eventually be built into enterprise systems as a default functionality. What's called Big Data today will just be called data by then.


To stay ahead of the trend, SAP, BMMsoft, HP, NetApp and Red Hat, worked together to get ready for this shift in future data. Based on SAP HANA, SAP IQ 16 and BMMsoft EDMT running on HP DL980 servers under Red Hat Enterprise Linux with multiple petabytes of NetApp E5460 storage systems, connected through fibre switches, the World’s Largest Data Warehouse, with a size greater than 12PB, was created culminating in a Guinness Book of World Records setting entry.


The results were audited by InforSizing, an independent Transaction Processing Council, and forwarded to the Guinness World Record to claim the category of “World's Largest Data Warehouse”, and verified according to accepted industry practices. The previous record for a 3PB data warehouse was set in 2012 by IBM DB2.  Thus, achieving this new Guinness Book record as the World’s Largest Data Warehouse is clearly a milestone for SAP, BMMsoft, RedHat, HP and NetApp.


NetApp E5460 storage systems, part of the NetApp E-Series product line designed for delivering leading bandwidth performance for data-intensive applications, was chosen as the preferred storage platform for its ability to handle large data volumes, enormous throughput requirements, a load speed of 34.3TB/hour, maintain high speed during data refresh and bulk delete operation, and support high availability at the same time. Twenty E-Series E5460 storage arrays with dual controllers, dual 8 Gbps Fibre Channel each, and 10 disk expansions were deployed in this world record test. In total 1,800 3TB SATA drives equivalent to 5,400 TB raw storage capacity were used. Dynamic Disk Pools (DDP) provided strong data protection and ease of management while still resulting in extremely high throughput.


In this world record test, running the NetApp E-Series storage arrays proved to be the top performance enterprise storage systems for SAP deployments, ready for Big Data and customers’ future external storage requirements.

on ‎2014-03-20 03:11 AM

Now that's a lot of Storage, haha.