Cisco Blogs

So Google is building a 10GbE switch?

- November 20, 2007 - 3 Comments

Today I ran across an article about Google building its own 10GbE switch:’s no secret that Google has been building its own servers for their data centers for some time and is now one of AMD’s top customers. It probably makes a lot of sense for Google to extend this to the network infrastructure and start building it’s own 10GbE switches for server access. With as many servers as Google is installing, anything it can do to take cost out of its infrastructure and improve efficiencies in space and power will certainly help it scale.Now server design is fairly straightforward and understood and most of the components have been commoditized. But can the same be said for network switches?Cisco and other network equipment vendors have built up years of experience in network switch design and optimized the architecture for performance and reliability. With Google entering this space, there are several questions that could be asked.Can Google hope to replicate this design expertise in just a few years?If Google is succesful and building a low-cost, high-performance 10GbE switch, what effect will it have on the networking industry?Should networking engineers start looking at Google for new and exciting opportunities in switch design?What other technologies should Google look to invest in?Will this buy vs. build argument sway other companies into considering this approach?What is certain is that Google, because of its size and cash warchest, can move into any industry at will and potentially become a disruptive force to an incumbent player.

In an effort to keep conversations fresh, Cisco Blogs closes comments after 60 days. Please visit the Cisco Blogs hub page for the latest content.


  1. Any chance this 48port 10G switch is the Google"" switch?"

  2. You forgot the question mark in the summary -- So?"". Google is an aberration and as fascinating as a lot of what they're doing is, very little of it is directly applicable until you're anywhere close to their scale in workload, NIH attitude, technology investment, and staffing.This is the same as Sun's (and several others') past attempts at ""building"" a switch -- taking a white-box Broadcom design and wrapping their sheet metal around it. Despite product marketing, from a hardware perspective Cisco did much the same with ISR's; however ignoring on-board components, there's a world of difference between a 3825 and a BCM1125.It would be naive to assume that building equivalent speeds'n'feeds for internal use (which is all I've seen discussed) is anything remotely close to bringing a product to market. If they can ramp this up with a support organization, documentation, long-term roadmap, compelling feature-set, and sufficient scale to meet demand, and do so while remaining cost competitive with well-established competition then and only then are they ready to start building a sales organization around it.There's some risk to mainstream vendors from Google's internal initiatives to reduce vendor dependence. The most apparent place this can be seen is in their campus cafeterias -- clearly they've had enough traction in that operation that they've been able to successfully market their KoolAid far and wide."

  3. Google has enough cash to do everything at will. Almost all the experts can be hired at a certain price. So lack of experiences in this field could possiblely be overcomed in few years. But I think the time a company to do everything by itself, the time it is getting on downside road.