If you look at various businesses across the world, you’ll see that they are facing some similar strategic challenges – such as globalization, innovation, new business models, evolving customer transactions to interactions, environmental sustainability, new partnerships, and the need to reduce costs. To address these challenges, companies are adding rich communication, information and collaboration services and these services are increasingly being delivered by a data center. So, what are Data Centers? Data centers are buildings that house IT resources such as server, storage systems and networking equipment. These data centers typically host a large number of business and consumer applications and data, each running on a dedicated or shared hardware infrastructure. In today’s connected global marketplace, where customers and users expect to purchase products and access services 24×7, datacenters are playing an increasingly important role for successful experience.
In my work in the Cisco Data Center Advanced Services Product Management team, I’ve watched as Data centers have undergone transformation over the past few years to achieve significant savings in time, capital, and energy while increasing flexibility, efficiency, and comprehensive disaster recovery. At the same time, in both Cisco and our customers, I’ve observed how the demand on the next generation Data Center are always increasing and the push for IT organizations to deliver IT services to their customers faster and cheaper has never been stronger. The challenge to optimize how network, storage and compute resources deliver business services has become increasingly complex.
Since we announced FabricPath at CiscoLive!, the most common questions I have gotten are “how do I get it?” and “when should I use it?”
So, the first question is pretty easy to answer. While we launched the Fabric Switching System (FSS) as part of the announcement as a pre-built option, the reality is that all you need is one or more of the new F-series IO modules to able to deploy FabricPath. This would be an example of the forward investment protection we talked about when we first introduced the Nexus 7000–customers have an simple way to add FabricPath support to their existing N7K chassis in a incremental fashion. Availability is calendar Q3 of this year.
The “when should I use it” question is a little bit more interesting because there is no hard and fast answer.
So, normally I have some fun with our competitors in this space, but today, I am actually going to go ask you to go read a post on a competitor’s website (then come back!). Why? Because some things are really more important then who has the zoomiest new widget today…go on, go read it…I’ll still be here….
Back? Good….so I have been going to CiscoLive!/Networkers for more than a decade and I gotta tell you, if the audience there is a representative of IT as a whole, then we moving the needle at a glacial pace.
So, considering the fact that our entire industry is about being forward thinking and redefining what’s possible, why is this so tough?
Yes, my implicit opinion is that this is an issue with tangible/practical impact for folks running data centers. When meeting with IT management one of the top concerns I consistently hear is not technology based, it is around finding enough smart people to design, build and run the next generation of IT infrastructure. If our industry routinely makes IT an inhospitable place for half the population (my wife would argue the smarter half of the population) then its everyone’s problem–or everyone’s opportunity–this report makes some interesting points.
So, dear readers, what do you think and what can we be doing better? What are the experiences of other folks out there? Is networking particularly behind the curve and other parts of IT are more hospitable? Is this even an issue–should I go back to writing about who has the zoomiest new widget?
Recently I met the CIO of a large pharmaceutical company and had the opportunity to discuss virtualization and evolution of network protocols as related to his data center environments. Like most enterprise customers, this CIO is also looking for ways to improve efficiency and maximize asset utilization while gaining operational efficiency.
The evolution of virtualization now encompassing servers, storage and networks along with the need to support multiple protocols (FC, iSCSI, FCoE, 10G/100G) introduced new challenges in his DC environments, most notably, how to tie the new virtual environment into his legacy environment and how to manage end- to- end to get operational efficiency. His company is looking for ways to reduce ‘time to service’ for application deployment while keeping cost at a minimum.
The real question he has is: “how do I support a multiprotocol virtualized environment to improve efficiency, maximize utilization and increase operational cost?”
According to Rick Vilars, VP of Storage Strategy at IDC, “what enterprise is looking for is simpler networks to do more complex things with all their IT assets”. Your competitiveness in the market place depends on how well your DC scales and grows in this new world, and the first step to surmount these complex problems is to build a common hardware foundation with common OS across entire DC, i.e, LAN to SAN to WAN to DC Interconnect, all on a common platform.
Watch this video to hear IDC’s perspective of multiprotocol SAN evolution and how it can solve the problems faced by our pharmaceutical CIO and other customers in his situation.
So, a couple of weeks ago, I had an interesting conversation going with a fellow blogger Steve Duplessie about our prospects versus a certain vendor of IT gear and office supplies. Steve’s contention was that our competition’s ability to push the “commodity envelope” would give them a strategic advantage.
At the time, I argued that pushing the commodity envelope (i.e. making things cheaper) only gets you so far. You start running up against diminishing marginal utility–at some point customers stop looking for cheaper mousetraps and start looking for better mousetraps. At some point you need to innovate as a way to create competitive or operational advantage, or you better figure out how to run your business on commodity margins.
This week, our FabricPath announcement served as a great reinforcement of that point. Simply, new challenges require new thinking. The challenges put forth by broad scale virtualization and federated server application environments needed a fresh approach. In this case, FabricPath gives you new functional benefits that map quite nicely to the demands of these emerging DC environments, while still reducing both CapEx and OpEx. Simply taking existing technology and making it cheaper doesn’t buy you anything in his case. I don’t care if you can deliver 10GbE ports for $10 a pop, they are still not going to solve these emerging challenges–in the end, there is no substitute for vision, expertise and R&D follow-through.