Following my last blog post , I have gotten a number of questions on how we specifically define “fabric” so I thought I’d dig into that a bit more with this post. So, the primarily point is that our definition of fabric it built around a specific set of features and capabilities. It is not tied to specific products or topology. Again, we think it’s important that our customers have choice and not have an arbitrary architecture foisted upon them.
At its most basic level, a fabric is a highly available, high performance shared infrastructure built with integrated, intelligent compute, storage and network nodes that can be rapidly and simply organized around the requirements of a given workload.
We see this fabric as having six specific characteristics:
Open -- based on open standards
Integrated -- breaks down traditional silos with a more holistic approach
Flexible -- allows customers architectural flexibility and choice
Scalability -- easily grows and adapts as the data center evolves
Would you believe you can have yourself a pretty successful business upgrading office buildings with more energy-efficient light bulbs and timers to switch off heating and cooling systems after hours?
I worked as a newspaper reporter for much of the 1990s. I wrote an article in 1993 about how the city of Santa Clarita in Los Angeles County had hired a firm to retrofit its field services office with new lighting, timers and other energy-efficient solutions. The improvements were expected to save about $70,000 per year.
What always intrigued me about the story was that the company that performed the upgrades not only allowed Santa Clarita to incrementally pay for the improvements out of the savings from lowered utility bills but also guaranteed those savings would more than offset the price tag of the improvements in 5 years. If the savings didn’t materialize, the company would pay the shortfall back to the city.
Everyone wins. The company performing the upgrades gets paid for doing the upgrade work, the city saves money on its utility bills for years to come and the environment is better off due to reduced energy consumption and associated carbon emissions.
Now, consider that modern Data Centers can have power densities 50 to 100 times those of conventional office buildings. How much greater green -- both financial and environmental kind - can be had by saving energy in those environments? With that in mind, here is an overview of several strategies being implemented in Data Centers to make them greener.
Sometimes, progress necessitates that we look at things in an entirely new light. To paraphrase Star Trek—if you want to do something groundbreaking, sometimes you have to go boldly where no one has gone before.
Against that backdrop, I wanted to dispel a recent rumor in the marketplace that Cisco has gone (warp drives engaged, presumably) to a place called “Planet Zircon” to sell its industry-first and industry-leading Unified Computing System (UCS).
Leaving aside for a moment that some of our competitors seem to be living in an alternate universe, UCS is actually selling quite well right here on planet Earth. Our architecture for the virtualized data center, whereby via UCS we unify servers, storage access, networks, and virtualization technologies to drive the value of data center infrastructure to an entirely new level, has gained acceptance from a great number of earthly companies.
But since we’re having fun with science fiction metaphors, let’s suppose you were a time traveler who went back to sneak a peek as Cisco first began developing UCS. You might be forgiven for thinking that Cisco had taken leave of its senses. But leaving planet Earth? No, our feet were firmly planted here.
“Fabric computing is a fixture on the radar screen of many IT groups, driven by the increased penetration of virtualization and prospects for cloud computing.As virtualization penetration increases, IT organizations will deploy virtual machine (VM) mobility, which will demand more attention to a fabric-based infrastructure that better integrates server, storage and networking for greater agility and faster time to deploy.” Based on this observation, Gartner George J Reiss and Andrew Butler organized recently a survey to evaluate which vendors are the most credible and ready to address the challenges of virtualization and cloud computing.
Cisco pioneered the vision of Ethernet-based “Unified Fabric” for the data center and has been shipping products to support that vision for over three years. Subsequently it introduced Unified Computing and Unified Network Services, all of which have formed the building blocks for Cisco’s Data Center Fabric. Competitors have validated Cisco’s vision by scrambling to deliver their own versions of the Fabric.
On March 30th starting at 9:00 am PST, Cisco executives and experts , partners and customers will supplement this Fabric vision and showcase its evolution, while bringing multiple proof points to bear. And in a pure Cisco spirit, to enrich a very open conversation, we invited the Senior Analyst Andre Kindnesss from Forrester Research who wrote recently about “The Dark Horse In The Datacenter Fabric Race?” and the Program VP Data Center Network Services Cindy Borovick from IDC to share their vision.
If you want to be among (or amongst) the first to know what’s cooking at Cisco, this is your chance ! This event will be live and we hope to hear from you.
This year’s Cloud Connect was another great success, and thanks to everyone who attended my presentation on Cisco and the Cloud: Within and Beyond the Data Center. I was happy to see that we are beyond the discussion of “Is Cloud a true opportunity?” to “How can we get the most out of the Cloud?” There were many interesting industry topics discussed at Cloud Connect, I wanted to touch on one of them, the benefits of cloud, in more detail.
An interesting discussion came up in a panel on the differences between on-demand virtualization and Cloud. I share the panel’s general consensus that virtualization is a useful first step but not the end of the journey. Businesses of all sizes have achieved major benefits through virtualization (25%+ cost savings), increasing the utilization of servers to reduce hardware requirements and consolidate operations. When you move beyond this crucial first step, you open up the rest of your business Cloud’s benefits: flexibility, agility, scalability, and usability. When a truly dynamic cloud is implemented the benefits for service providers and enterprises are significant - saving 35-80% of the costs of traditional delivery. Let’s look at what drives these benefits:
Flexibility: Implementing a Unified Service Delivery foundation for your Cloud, enables an end-to-end virtualized infrastructure combining both the virtualized data center and the intelligent IP NGN to deliver services/applications from a common pool of compute, network, and storage resources, available on demand and also ensuring the services and applications can be delivered effectively.