Cisco Data Center Initiative, A View From the Network

Got a tip from another reader on a blog post, Enterprise Cloud Computing - Build your own with Cisco VFrame .

Enterprise Cloud Computing - Build Your Own With Cisco VFrame - Why Wait ?

21 August, 2008 by Greg Ferro

I can see some value in external Cloud Computing, but why not just build your own with Cisco ? Take a bunch of leftover machines, that old storage system and get a demo version and make your own.
It seems clear to me that Cloud Computing is going to go down two quite different paths. The first is the path that Amazon / Google / Joyent represent. Enough said on those technologies.

But why not build a Cloud Infrastructure in your own Data Centre ?

And says Cisco has the solution

Cisco already makes a cloud solution

Sometimes there are so many products in the Cisco catalog that some of them get lost. But one product I have been researching over the last six months is Cisco VFrame.

Now VFrame is software toolset that automatically provisions VMware ESX servers, Cisco Catalyst switches, ACE Application Delivery Controllers1 , FWSM modules, Storage Arrays and Storage Switches and so on. In simple terms, it is programming environment that allows to ‘orchestrate’ the configuration of many separate technologies into a single process.

Let me ay that last bit again ” ‘orchestrate’ the configuration of many separate technologies into a single process.” Thats is the first part of Cloud Computing right there.

What does VFrame do?

So if I have Cisco VFrame, a software tool that automates the following tasks:

  • allocate and create a storage capacity and storage network from my existing storage system
  • allocate and create CPU / RAM resources in the form of a VMWare ESX hypervisor
  • creates the network modifications for firewalling and application acceleration

then that smells lot like Cloud Computing to me.

I am going to forward this entry to a few people i know and get their opinions on using VFrame for building a Cloud Computing environment.

Read more

What is Motivating Ken Brill to Criticize PUE? Maybe, another Uptime Seminar

TechHermit has a post on

Ken Brill continues to use his bully pulpit to slow down Data Center Energy Efficiency measurement adoption

August 29, 2008

I am really quite flabbergasted at Ken Brill.  I am really beginning to think he is going crazy.   On Monday, Mr. Brill posted a comment on his blog at Forbes essentially going after the gaming and potential mis-use of metrics. 

TechHermit then details Ken's bully pulpit behavior.

  1. Electricity is only one of a number of data center energy sources. Others include natural gas, steam, chilled water, diesel, free-cooling and one-pass cooling. So, if electricity alone is counted as an energy source, some sites will appear to be better than they really are.
  2. I also find it humorous that he mentions his ludicrously non-adopted Site Infrastructure Energy Overhead metric.   This metric is essentially PUE.  I guess this wonderful metric could not be gamed either.   Or that it somehow incorporates the energy calculation of cooling the earths air for free-cooling. 
  3. Given the amount of times he mentions PUE in negative connotations, I cannot but help think this a thinly veiled attempt to associate PUE with “Bad Marketeering” and “Green Washing”.

And, then TechHermit closes with

Having been involved in my local political scene I can tell you its a standard strategy.   That’s exactly what this smells of….politics.

Out of curiosity I went to the Forbes article ,and saw the overall rating was 5 stars, I clicked one star, and it dropped to 3 stars. Did someone at Uptime click on a 5 star rating, and my click on one star, averaged it to 3?

image 

I have nothing personal against Ken, but I do agree with TechHermit's point.

In my opinion he is doing nothing more than creating significantly more mis-information and hesitance for companies to even begin measurement in the first place.

I've been sitting on this post for 5 days, not feeling I had enough information to post it.  But, 5 minutes ago I got the other piece of the puzzle in email, an Uptime Seminar promoting Four Metrics.

Last Chance to Register for Tomorrow's How to Apply the Four Metrics to Achieve Data Center GreennessOnline Seminar

In this two-hour, live online seminar, Institute Executive Director Ken Brill helps you holistically model the total energy use of your data center. Direct benefits of the course include a framework you can employ to understand the growing energy use in your data center as well as in the industry, a usable model of data center energy consumption upon which to base strategic planning, concrete examples of how best practices can curb your data center's energy consumption, and a set of metrics that you can apply to plan and better control energy use in your data center.

This essential online seminar will be delivered in two one-hour modules on September 3 and 4, October 8 and 9, November 5 and 6, and December 3 and 4. Save your seat by registering now. For a taste of what you can learn, watch Ken Brill's vodcast, What Constitutes Green IT.
Tuition: $295 (Non-Institute Members) / $250 (Institute Members)

And

Revolutionizing Data Center Energy Efficiency Public Seminar

The Institute's newest Public Seminar, Revolutionizing Data Center Energy Efficiency brings together the managerial and strategic approaches of How to Get IT and Facilities Together to Improve Data Center Energy Efficiency with the energy consumption modeling and metrics of How to Apply the Four Metrics to Achieve Data Center Greenness and provides a high-level method for driving energy efficiency from the top. This course is intended for the executive team and focuses on shared language to bridge silo-induced communication gaps, best practices, implementable and sharable metrics, strategic approaches to organizational impediments and more.
Tuition: $1195 (Non-Institute Members) / $995 (Institute Members)

I think this explains Ken's behavior to criticize PUE not as crazy, but a focus on Uptime's (Ken's) seminar revenue.

Read more

Did you Really Turn off the Lights?

DataCenterKnowledge has a post reporting on The Planet's efforts to really turn Lights off in the data center.

The Planet said today that it expects to reduce its annual energy consumption by 1.4 million kilowatt hours, gaining nearly $140,000 in savings, through “more efficient use of lighting.” Translation: they’re strictly enforcing a policy for turning out the lights after hours. That means The Planet’s six data centers will be lit only from 8 a.m. to 5 p.m., with smaller lamps remaining on in main areas for safety and navigation. ”Data-center technicians who work around the clock now turn on lights as needed in computer rooms,” the company said. 

With many bragging about a Lights Out facility, you would think this isn't newsworthy, but many are not really turning off the lights.

“While lighting is a small portion of the total power usage of a datacenter, it can be often be safely reduced through mature, inexpensive technologies and designs,” according to data center energy management best practices from Lawrence Berkeley National Laboratory, which recommends using motion sensors to turn lights off in empty rooms.

Read more

Sun's Energy Efficient Data Center, The Role of Modularity in Datacenter Design

Sun has a pdf on  Energy Efficient Datacenters - The Role of Modularity in Datacenter Design and a wiki post.

Energy Efficient Datacenters: The Role of Modularity in Datacenter Design

by Dean Nelson, Michael Ryan, Serena DeVito, Ramesh KV, Petr Vlasaty, Brett Rucker, and Brian Day
June, 2008

Virtually every Information Technology (IT) organization and the clients that they serve have dramatically different requirements that impact their datacenter designs. Sun is no exception to this rule. As an engineering company, Sun has cross-functional organizations that manage the company's corporate infrastructure portfolio including engineering, services, sales, operations, and IT.

On the surface, the datacenters supporting these different organizations look as different as night and day - one looks like a computer hardware laboratory and another looks like a lights-out server farm. One has employees entering and leaving constantly, and another is accessed remotely and could be anywhere. One may be housed in a building, and another may be housed within an enhanced shipping container. Beneath the surface, however, our datacenters have similar underlying infrastructure including physical design, power, cooling, and connectivity.

At first I thought the document was going to be able Sun's Containers, but as I continued through the document more details were discussed in modular power, cooling, and cabling. The following is from the summary.

The last thing that a datacenter design should do is get in the way of a company’s ability to conduct business. Traditional datacenter designs can do just that. Cooling via raised floors and perimeter CRAC units limit the ability to increase density and achieve energy efficiency. Power distribution units and under-floor whips limit flexibility and require downtime for reconfiguration. Home-run, under-floor cabling makes growth difficult, impacts cooling and raises costs.


Datacenter designs that facilitate — rather than limit — growth, density, flexibility and rapid change can be a company’s competitive weapon. At Sun, our modular, pod-based datacenters can turn on a dime whenever business directions change, from accommodating new equipment in our pods to expanding our rack footprint by deploying additional Sun Modular Datacenters. We can accommodate growth and increases in density because three key datacenter functions — power, cooling, and cabling — are prepared from day one to support an overall doubling in each area.

The document is 58 pages with the following content.

  • The Role of Modularity in Datacenter Design
    • Choosing Modularity
    • Defining Modular, Energy-Efficient Building Blocks
    • Buildings Versus Containers
    • Cost Savings
    • About This Article
  • The Range of Datacenter Requirements
    • Power and Cooling Requirements
      • Using Racks, Not Square Feet, as the Key Metric
      • Temporal Power and Cooling Requirements
      • Equipment-Dictated Power and Cooling Requirements
    • Connectivity Requirements
    • Equipment Access Requirements
    • Choosing Between Buildings and Containers
    • Living Within a Space, Power, and Cooling Envelope
      • Space
      • Power
      • Cooling
    • Calculating Sun's Santa Clara Datacenters
      • Efficiency in Sun's Santa Clara Software Datacenter
  • Sun's Pod-Based Design
    • Modular Components
    • Pod Examples
      • Hot-Aisle Containment and In-Row Cooling
      • Overhead Cooling for High Spot Loads
      • A Self-Contained Pod - the Sun Modular Datacenter
  • Modular Design Elements
    • Physical Design Issues
      • Sun Modular Datacenter Requirements
      • Structural Requirements
      • Raised Floor or Slab
      • Racks
      • Future Proofing
    • Modular Power Distribution
      • The Problem with PDUs
      • The Benefits of Modular Busway
    • Modular Spot Cooling
      • Self-Contained, Closely Coupled Cooling
      • In-Row Cooling with Hot-Aisle Containment
      • Overhead Spot Cooling
      • The Future of Datacenter Cooling
    • Modular Cabling Design
      • Cabling Best Practices
  • The Modular Pod Design at Work
    • Santa Clara Software Organization Datacenter
    • Santa Clara Services Organization Datacenter
    • Sun Solution Center
    • Guillemont Park Campus, UK
    • Prague, Czech Republic
    • Bangalore, India
    • Louisville, Colorado: Sun Modular Datacenter
  • Summary
    • Looking Toward the Future
    • Read more

    Bunch of Cloud Computing News

    Cloud Computing continues to get lots of news.  Here are a few to get you thinking about the impact.

    Nicholas Carr discusses Google’s Chrome browser and how it is the client side browser for Cloud Computing.

    The cloud's Chrome lining

    September 02, 2008

    Google's release today of a test version of its new open-source web browser, Chrome, marks an important moment in the ongoing shift of personal computing from the PC hard drive to the Internet "cloud." I distinctly remember when, back in 1988, Apple Computer added MultiFinder to its Macintosh operating system, allowing my beloved Mac Plus to run more than one application at a time. That was, for us Mac users, anyway, a very big deal. Chrome - if we can trust the comic book - promises a similar leap in the capacity of the cloud to run applications speedily, securely, and simultaneously. Indeed, it is the first browser built from the ground up with the idea of running applications rather than displaying pages. It takes the browser's file-tab metaphor, a metaphor reflecting the old idea of the web as a collection of pages, and repurposes it for application multitasking. Chrome is the first cloud browser.

    GigaOm discusses the move to a hosted Desktop in the cloud model.

    Broadband service providers are looking to add higher-value services to their offerings, services that could soon include a virtual desktop for consumers. Indeed, the idea of a service provider offering a PC as a Service (PCaaS), essentially a PC in the cloud, may be coming to your broadband connection sooner than you might think. Here is how a virtual desktop would work: You’d have an access device at your location, called a thin client, which would connect your keyboard, video screen and mouse (KVM) to the service provider’s broadband network. (For more detail on thin clients, see Stacey’s recent post.)

    Cassatt’s CEO Bill Coleman writes on Cloud Computing moving in the Enterprise.

    Cloud computing is gaining attention among technologists and the wider public, yet its definition remains a bit, well, cloudy. If you wouldn't mind one more cloud computing definition, I rather like mine.

    In cloud computing, you care deeply about access to computing, storage, and network resources. You could not care less about where the servers carrying out these processes are located (as long as you keep in mind a few compliance requirements), nor how they are implemented. With cloud computing, what you don't see is what you get, and as long as you get that resource availability for an affordable price, there really is not much need to ask what is going on behind the scenes.
    This "traditional" concept of cloud computing has some big stumbling blocks at the moment. My belief, however, is that many of these issues can be addressed by doing something intriguing with the cloud computing idea: bringing it inside your own datacenter.

    Gear6’s VP of Marketing, Gary Orenstein, positions his product in a changing infrastructure for Cloud Computing.

    The emergence of cloud computing as a way to build and deliver always-on, pay-by-the-drink IT services has emerged as one of the hottest topics this year. Major players -- including Amazon, EMC, Google and IBM -- have promoted offerings that proclaim near infinite-scale computing, storage, database and related Web services that can be easily leveraged by talented developers with a browser.

    This paper will specifically focus on how Web-scale and commercial enterprises can benefit from current cloud computing technology trends to build a new class of datacenters that are more autonomous and dynamic than traditional implementations. It also will examine how new cloud computing models enable the rapid scaling and reallocation of resources to a wide variety of customers, delivering core cost and agility benefits to purveyors of cloud computing services. And, specifically, we will explore how the change in application workloads is driving a need for accelerated file services to maintain optimized performance.

    Initially, I blew off the Google Chrome browser, but after looking at the comic book description of the product I am going to give it a try as my most common reboot is caused by Internet Explorer.  I don’t know which is more frustrating Outlook or IE.

    Read more