What's in Dell's move to Quincy, WA? Competing with IBM and HP?

Wenatchee World has the story on Dell coming to Quincy, WA for a data center.

Secret's out? Dell headed here

Blog: Everyday Business

    By Mike Irwin

    November 2, 2010

    Dell, the world's third-largest computer company, has purchased property in Quincy that could become the site of the Columbia Basin town's newest data center, the Seattle Daily Journal of Commerce reported this morning.
    Underway for months, the top-secret purchase — known as Project Roosevelt — would add the computer manufacturer to Quincy's list of tech industry standouts, such as Microsoft and Yahoo.

    DataCenterKnowledge has more details.

    Officials with the Port of Quincy have confirmed that the deal is related to Project Roosevelt, the code name for a data center that could include grow to 250,000 square feet over time. The initial specifications call for 7 megawatts of power, ramping up to 30 megawatts over time. The search also considered sites in Douglas County.

    Why is Dell building 7 MW with growth for 25 MW?  Perot systems is the competitor of HP/EDS and IBM services. Perot systems doesn't have the data center inventory that HP and IBM has.

    Converged infrastructure is a hot topic, and it is much easier to sell a converged infrastructure solution when you have the data center contract.  The Dell data center is most likely a cost effective solution for hosting, gives a low carbon data center alternative, and becomes a showcase for Dell/Perot.

    Dell announced today the acquisition of Cloud Solution SaaS company Boomi.

    Dell to Acquire Boomi; Adds Industry’s No. 1 Integration Cloud™ Solution to SaaS Capabilities

    Date : 11/2/2010

    Round Rock, Texas

    Dell today announced it has agreed to acquire Software-as-a-Service (SaaS) integration leader Boomi to help businesses reap the full value of cloud computing. Powered by its revolutionary AtomSphere technology, Boomi offers the industry’s only pure SaaS application integration platform that takes the cost and complexity out of integrating applications by allowing easy transfer of data between cloud-based and on-premise applications with no appliances, no software and no coding required.

     

    image

    Read more

    Do you have an Elephant and Pig in your data center? Hadoop momentum continues

    I am sure most of your have heard of Hadoop.

    I've started studying Hadoop and its adoption in data centers.  Google started the effort with its MapReduce and Google File System.

    Apache Hadoop is a software framework that supports data-intensive distributed applications under a free license.[1] It enables applications to work with thousands of nodes and petabytes of data. Hadoop was inspired by Google's MapReduce and Google File System (GFS) papers.

    Why should you care about Hadoop? Look at who the users are - Amazon Web Services, Adobe, AOL, Baidu, eBay, Facebook, Google, Hulu, IBM, LinkedIn, Quantcast, Rackspace, Twitter, and Yahoo.

    Yahoo! is proud of being the largest Hadoop user.  Here is their 2009 #'s 25,000 nodes.

    image

    And, 2010 38,000 servers for 170 PB of storage

    image

    Apache Pig is a platform for analyzing the large data set.

    Pig

    Apache Pig is a platform for analyzing large data sets that consists of a high-level language for expressing data analysis programs, coupled with infrastructure for evaluating these programs. The salient property of Pig programs is that their structure is amenable to substantial parallelization, which in turns enables them to handle very large data sets.

    At the present time, Pig's infrastructure layer consists of a compiler that produces sequences of Map-Reduce programs, for which large-scale parallel implementations already exist (e.g., the Hadoop subproject). Pig's language layer currently consists of a textual language called Pig Latin, which has the following key properties:

    Read more

    IT Professionals predict Mobile and Cloud Technologies will dominate by 2015, but where will IT professionals be?

    IBM has research that supports the view the future is Mobile and Cloud Computing.

    IBM Survey: IT Professionals Predict Mobile and Cloud Technologies Will Dominate Enterprise Computing By 2015

    Trends Signal Shift in Skills Necessary for Businesses to Drive Growth

    ARMONK, N.Y. - 08 Oct 2010: Information technology professionals predict that mobile and cloud computing will emerge as the most in-demand platforms for software application development and IT delivery over the next five years, according to a new IBM (NYSE: IBM) survey released today.

    The 2010 IBM Tech Trends Survey, conducted online by IBM developerWorks, provides insight into the most significant enterprise technology and industry trends based on responses from 2,000 IT developers and specialists across 87 countries.  
    IBM Survey: IT Professionals Predict Mobile and Cloud Technologies Will Dominate Enterprise Computing By 2015
    According to the survey, more than half of all IT professionals – 55 percent -- expect mobile software application development for devices such as iPhone and Android, and even tablet PCs like iPad and PlayBook, will surpass application development on all other traditional computing platforms by 2015.

    But with this paradigm comes an agile, competitive environment.  Which for a risk adverse IT professional can be pretty scary.

    How much of the cloud computing growth is fueled by those business units frustrated by internal IT departments? 

    How many users love the iPad, iPhone, Android phone because there is little IT involvement?

    Blackberry's were top in popularity because IT departments can manage the devices.  How many iPhone and and Android users wish they could go back to their Blackberry?

    Those IT departments who stick to the past and slow down the enterprise will have direct affect on the competitiveness of a company.

    The future will have by 2015 a major company that suffers a catastrophic data center/IT outage that will cripple its business and market cloud just like BP. The nimble companies like Facebook and Foursquare quickly address their outages and are transparent with fixes.

    Foursquare and Facebook Experience Downtime. World Continues to Spin.

    Foursquare? The world found out Monday when the location-based social network went down due to technical difficulties -- not atypical for fast-growing startups, but still concerning at a time when Facebook and other rivals would gladly take its place.
    Total downtime was around 11 hours all told," reports TechCrunch. "That's not good."

    ...

    What's more, "Foursqaure isn't the only one experiencing downtime lately," VentureBeat points out. "Facebook recently had its worst downtime in 4 years when the service was unavailable for 2.5 hours."

    I think the dominant technologies by 2015 are those who can survive outages. 24X7 is much harder in a cloud computing mobile world as people are connecting more than ever.

    Read more

    Verizon’s Cloud Services expand Data Centers WW

    Verizon announced expansion of its Data Centers WW to support its cloud offering.

    Verizon Business Furthers Cloud Strategy Through Global Data Center Expansion

    Expanded Facilities to Accommodate Increased Customer Demand for Public, Private and Hybrid Cloud Services

    September 30, 2010

    BASKING RIDGE, N.J. - To meet the increasing demand for the full range of cloud services, Verizon Business is enhancing its data centers around the globe. Within the next year, Verizon Business will expand its flagship cloud computing services suite - Computing as a Service (CaaS) - into centers in San Jose, Calif.; London; and Canberra, Australia. In addition, CaaS data centers to serve U.S. government customers will come online in Miami and Culpeper, Va., during the first quarter of 2011.

    Here are some of the details on how much expansion Verizon plans.

    As part of this infrastructure enhancement project, more than 5,500 additional server cabinets for enterprise clients also will be added to Verizon Business premium Internet data centers in Paris, Dublin, London, Frankfurt, Belgium, Canberra, Hong Kong and throughout the U.S. The expansion further enables the delivery of private clouds via more than 200 global data centers connected to Verizon's MPLS network, Private IP.

    Verizon Enterprise-Class CaaS Solutions Lead Market in Performance, Security

    Verizon's cloud computing solutions suite, Computing as a Service, offers enterprises on-demand computing resources, including server, network and storage capacity, with high-performance and built-in security that are ideally suited to the complex needs of large enterprises. Enterprises have a choice between Verizon's flagship CaaS offering of its hybrid solution, CaaS enabled VMware vCloud™ Datacenter, which facilitates moving applications from a private to a public cloud setting. Clients can configure their enterprise cloud using Verizon's Private IP network or its global IP network.

    Today, the company has CaaS data centers in Amsterdam and the U.S. A third center in Hong Kong will come online in October.

    Some of the customers are.

    Early adopters of Verizon's cloud services include Modevity, Celstream, iSOFT, ISID and GWR Medical and Intelenet.. Many are using cloud computing to drive further efficiencies within their operations as well as a way to provide corporatewide access to applications while delivering enhanced ease-of-use for end-users.

    And VMware is part of the Verizon partnership.

    Verizon Builds Hybrid Cloud with VMware vCloud Datacenter

    The widgetry won’t be quite as secure as Verizon’s existing Computing as a Service (CaaS) – but pretty close

    Verizon is trusting the solution will get its target accounts up off their collective arse and into the cloud.

    Right now the thing, whose clumsy handle is Computing as a Service (CaaS) enabled by VMware vCloud Datacenter, is in field-test with the big International Hotel Group (IHG), a company whose business inherently sees peaks and troughs, expecting to widen the beta before the stuff goes GA in Q1.

    While the high-end CaaS enterprise is priced à la carte, the Datacenter version will be available on both a utility model and a reservation model.

    The company says it hasn't worked out the numbers yet but that's how it wants to price it; the first for transient trade, the latter for those with predictable workloads that want guaranteed resources.

    Read more

    HP introduces Butterfly Flexible Data Center design, reducing CAPex by 50%

    OK, my Microsoft past haunts me.  HP introduces a "butterfly" data center design and I think of the MSN butterfly.

    HP's butterfly looks different than MSN's, and I doubt we'll see an HP data center staff in a butterfly outfit, but the building does look like a butterfly.

    HP Flexible DC “butterfly” design

    HP Flexible DC is based on a “butterfly” design featuring four prefabricated quadrants, or modules, that stem off a central administrative section. The offering uses industrial components to improve cost efficiencies as well as a streamlined building process with a variety of options for power and cooling distribution.

    image

    Joking aside I was able to talk to Kfir Godrich, CTO of HP critical infrastructure.

    “Clients, such as financial service providers, government entities, and cloud and colocation hosts, will find the scalable and modular nature of HP Flexible DC a compelling option,” said Kfir Godrich, chief technology officer, Technology Services, HP. “HP can help clients innovate the way they build and operate a greenfield data center for greater savings over its life span.”

    I am writing this blog post before the official release, and I will update this blog with the press release link.

    HP Flexible Data Center Reduces Clients’ Upfront Capital Investment Requirements by Half, Optimizes Resource Use

    Design delivers flexibility, lowers carbon footprint

    PALO ALTO, Calif., July 27, 2010

    HP today introduced a new way for clients to cut capital investment requirements for the design and build of data centers in half while significantly decreasing their carbon footprint.(1)

    The patent-pending HP Flexible Data Center (HP Flexible DC) offers a standardized, modular approach to designing and building data centers that allows clients to replace traditional data center designs with a flexible solution that can be expanded as needed while conserving resources.

    Some facts that data center folks will care about are:

    • 3.2 MW is the overall capability of the total butterfly building.
    • Each of the modules is 800 kW which you can deploy in a partial deployment, supporting 800, 1600, 2400, and 3200 kW increments.
    • The central core is shared building support space for the four modules.
    • You can use multiple 3.2 MW deployments for a campus approach like below

    image

    • PUE is in the 1.2 - 1.25 range.
    • The design is modular to support multiple power and cooling systems, using multiple vendors while maintaining a high degree of integration across the systems.
    • Total square footage for a 3.2 MW configuration is 25,000.
    • Removing complexity in the system increases availability, efficiency, and cost effectiveness.

    Here are images from the official presentation.

    The one slide I would add if I was creating the presentation is "Why a new Data Center design?" where HP explained problems it sees customers having and then how Flexible DC creates a new approach to DC design.

    image

    Modularity and of the system to support 800kW increments.  BTW, Kfir said you could deploy a 400 kW configuration instead of 800kW.

    image

    To support a low PUE, hot air is exhausted through the roof.  Although in the images HP provided you can't see the roof system which lead me to think HP has a patent in process for the roof.  Note Yahoo patented its Chicken Coop design.  Kfir also made it clear the  design with 4 cooling methods can support deployments anywhere in the world, and where trade-offs can be made for when water is an expensive resource. 

    image

    Don't ask what Tier the design is.  It is designed for availability, energy and cost efficiency, not to meet a Tier standard.

    image

    I've been spending more time thinking about how you present data center issues to the CFO and so has HP.

    image

    There were six things that impressed me

    1. The amount of topics Kfir and I could cover in 25 minutes.
    2. The quality of the presentation and information that HP has in the Flexible Data Center Solution.  They can use this same presentation for CxO and data center geeks.  Although I would add a Why change data center design slide.  On the other hand criticizing decisions people have made in the past could upset some the audience and make them defensive, so being on the safe side I can see HP's choice for not calling out what is wrong with data center design.
    3. A focus on the supply chain.  If you are going to use HP's approach you could efficiently add data center capacity every year or more often.  This approach like a Just In Time manufacturing approach reduces the data center building inventory now that you could add additional space in as little as 3 months.  The current approach of building for 5 years of data center needs now turns into what do you need in 3 - 6 months.
    4. This is going to get a lot of people thinking about how they approach data center capacity.  How many were trying to save 10% in data center construction, and HP says hey you can save 50%?
    5. Building in smaller increments allows management to see data center building costs on a regular basis.
    6. The Butterfly Flexible DC design is a good alternative for Cloud Computing.

    image

    As HP's Flexible DC hits the market it will be interesting to watch the media coverage and customer interest.  I've already talked to my friends to tell them HP's Butterfly Flexible Data Center is something they should look at.

    Five years ago who would have thought HP would have Data Center PODs and Flexible Data Centers?

    image

    Read more