Most of the focus of software-defined networks (SDNs) has been on how it impacts the layer 2/3 switch vendors. The industry seems to have moved off of this notion that it commoditizes the underlying infrastructure, but recently another question has come up. Big Switch recently launched the company and related products, one of which is called “Big Tap,” that provide traffic visibility functionality similar to what one might get from vendors such as Gigamon and VSS. This has raised a question: are SDNs a death knell to the traffic visibility vendors?
I looked at this and then talked to a number of customers, including Big Switch, and I believe the information that one can get out of an SDN-led product to be very much complementary to the traffic visibility market, not competitive. Think of “Big Tap” as being traffic visibility light where they provide a very basic level of information. The level of information that one gets from the dedicated vendors is much richer and more granular than what one would get from Big Tap.
Gigamon’s recent news and definition of the “Engaged Fabric” highlights the higher-value functions of a dedicated solution to provide extended features such as the following:
- Ability to remove duplicate traffic, improving the effectiveness of the solution as well as the products that sit above it (NetScout, Riverbed, etc).
- Packet slicing to reduce the packet size to increase processing and monitoring throughput. This allows lower-speed tools to manage high-speed networks. This is a huge requirement as companies look to migrate to 10 Gig and 40 Gig.
- Time stamping to accurately record the time of traffic for latency analysis and troubleshooting. This makes the products like the previously mentioned Netscout and Riverbed/Cascade work more efficiently.
In fact, customers should look at solutions like Engaged Fabric as a way of being the “enabler” network evolution as it can enable legacy tools that only understand the physical world to bridge to a virtual, software-defined world. A traffic visibility fabric can provide a higher-level abstraction layer to allow network owners to move to an SDN without losing visibility, management and control.
One of my concerns with SDNs has been that the radically new approach to networking can create a number of blind spots that legacy tools just can’t see. This is similar to the problem server managers faced in the early days of server virtualization. Eventually, the tools were developed to help manage large-scale virtual environments. However, because of the criticality of the network, I don’t believe the industry can go through this kind of “blindness” when it comes to SDNs and network virtualization.
I strongly recommend deploying organizations look at something like Big Tap, but to be sure to complement it with a solution like Gigamon’s to remove those nasty blind spots.