Will Cisco position the upcoming Nexus 9000 as the foundation for its proprietary Application Centric Infrastructure (ACI) fabric? Or as a cost-effective 40G platform for OpenFlow software-defined networks?
It could go either way. And both ways.
[SAVE THE DATE: Cisco to launch Insieme Nov. 6]
As previously reported, the Nexus 9000 switches will include both modular spine and fixed-configuration leaf devices that run in either standalone mode - vanilla Layer2/3 based on Broadcom's Trident II silicon -- or ACI mode based on Insieme ASICs with proprietary extensions to the VXLAN spec. The switches will also run a stripped-down version of NX-OS with standalone and ACI fabric images: standalone will include OpenFlow, onePK after first customer ship, and an OpenStack Quantum plug-in; ACI will feature "centralized" programmability that does not include onePK or OpenFlow.
The switches will also feature an Insieme-developed 40G transceiver designed to bring 40G pricing down to just 30% above 10G pricing. In 2012, the average selling price of 10G ports was $1,229 for modular and $335 for purpose built (aka, top-of-rack), according to Dell'Oro Group.
With 40G Ethernet costing only 30% more than 10G, the Nexus 9000 will make 40G networking attractive to both constituencies - OpenFlow and ACI. Cloud providers and webscale hosting companies that currently go the low cost OpenFlow/open source/bare metal hardware route might now be inclined to consider the standalone version of the Nexus 9000 for those applications.
Cloud providers and enterprises looking for all of the application centrism Insieme wedged into the VXLAN header for ACI fabric mode - and already heavily invested in Cisco-specific networking -- will go the ACI route.
Our bet is that Cisco will emphasize the benefits of going all ACI mode. But the Nexus 9000 allows it to play in both worlds at 40G price points that are competitive with the OpenFlow SDN/low-cost hardware crowd.
Those price points might also be a major selling point of ACI's vs. VMware's NSX network virtualization platform. Insieme has previously said that it's a waste of money to pay for network virtualization on a per VM basis. Our sources say that Insieme is telling people that, even on the cheapest hardware, paying for NSX on a per virtual port per month basis could cost more than ACI.
This is in addition to Insieme claims that NSX and other software-intensive network virtualization and SDN techniques lack visibility into the physical network infrastructure for QoS, policing, monitoring, etc. - that bandwidth is the answer to most traffic issues. Insieme has also said that NSX and its ilk lack scalability and are hypervisor-dependent.
VMware counters by saying that the convergence NSX enables actually improves visibility:
Convergence of network and compute is made possible by a platform ideally positioned at the first point in the architecture where these different yet closely related services can reliably coexist. A less obvious yet significant consequence of this is that convergence inherently provides more visibility, for the simple reason that a single platform now offers a consolidated and synchronous view into multiple services and how they relate to each other in real-time. This combined visibility can bring about more sophisticated applications and operational tools than previously thought possible.
Fight fire with fire, but in Insieme's case fight software with hardware.
More from Cisco Subnet:
The Cisco Subnet blog is written by Network World managing editor Jim Duffy Visit the Cisco Subnet home page daily and while you are there, subscribe to the Cisco Alert e-mail newsletter, which includes news and views generated by the Cisco Subnet community as well as Cisco-related stories on Network World and elsewhere on the Web.
Follow Jim Duffy on Twitter