Data Center

It’s Not About the Network (Unless it’s Slow….or Down)

by asardell on ‎10-03-2016 10:52 AM - last edited on ‎11-01-2016 04:32 PM by Community Manager (895 Views)

Jay Etchings has a key mission as director of research operations at Arizona State University – make sure his customers don’t know about the network.  

 

“From a researcher’s point of view—a computational biologist or a genomicist—the network is not important unless it ceases to function,” say Mr. Etchings in this video detailing ASU’s use of this technology.

 

With an SDN-based solution featuring Brocade Flow Optimizer and MLXe routers, ASU has put itself squarely at the cutting edge of computing research.

 

Open-source OpenDaylight applications are very popular among customers in the research and education space, who often require high-performance security applications, such as a Science DMZ (Figure 1).

 

ASU NW.png

 

Figure 1: Brocade Solution for ASU’s Research Network and Science DMZ

 

This solution uses MLXe routers, the Brocade SDN Controller and of course the Brocade Flow Optimizer.  Providing high availability and resiliency, and supporting IPv4, IPv6 and OpenFlow 1.3, the network serves as a scalable, high-performance solution with a Layer 2 firewall bypass.  

 

In particular, the high-speed interfaces (100GE) into the DMZ are ideal for the cutting-edge research that ASU supports. Etchings notes that this performance allows ASU to pursue and support the most impactful global research: “Unlike competing institutions that are focused on papers and theoretical components, we’re actually doing these things, and Brocade is instrumental in helping us do them.”

 

“Cybersecurity is one of the leading disciplines these days, so I can identify new problems and new ideas almost every day,” notes Dr. Gail J Ahn, Ph.D., CISSP and professor of computer science and engineering.  Sometimes these problems may be security related, and other times they may just be poor performance.

 

But with the new network, Etchings said his team can “take some development that Dr. Ahn put into production, observe the latency, and if necessary remove that flow.” In the past, he notes, the department would have had to put that flow into production without examining it, and it would have been more difficult to back out.

 

The new process results in less maintenance and less downtime—exactly the way to keep a happy team of researchers, who are always too busy to think about the network. 

 

Related Links

 

For more detail, see the written success story on this network.