Cisco Blogs

Can you stick a Data Center in a box?

April 5, 2007 - 4 Comments

A couple of companies have recently come out with the proposal to squeeze Data Centers in a “box” (it’s a box as big as a container, but the concept is no different.) As much as I appreciate the end goal of simplifying DC deployments and management, I am not quite sure that is the right way to go,… yet.My first reaction to Sun’s introduction of the BlackBox project was that it was a nice proof of concept, but not really something an enterprise could use today. But I did not discount Sun’s proposal as Sun is a company that has been historically capable of being a few years ahead of the market. And when I say ahead of the market, I do not just mean ahead of the competition, but also ahead of customers and their ability to understand, purchase and use their products. I was thus very intrigued to see their announcement of Project BlackBox last fall, but I was not really convinced that customers would buy into that so easily.Today, I saw the announcement that Rackable Systems is doing something similar. Of course there are still little information about this, but I am not sure about how a Company that has built their reputation and market presence mostly on low-power server architectures will be able to deliver on something so much bigger as an entire Data Center in a box, where you also have storage, networks, security services, scalability services, application optimization,…This topic was recently discussed on ZDNet with rumors that Microsoft may be an early adopter of portable Data Centers:

Portable data centers: Will Microsoft prime the demand pump? by ZDNet‘s Larry Dignan — Microsoft may be giving the nascent portable data center market a lift. Data Center Knowledge via Slashdot connects a few dots-including a some from ZDNet’s Mary Jo Foley-to conclude that Microsoft may be an early adopter of the portable data centers championed by Sun (right), Rackable and others. These data center in a box concepts have […]

Anyway, my point here is not so much to critique or applaud either Sun or Rackable, but really to ask my fellow bloggers their opinion on whether or not we are ready to put DCs in a box. I think it’s clear that I am personally not convinced, but before telling you why, I will probably wait to see if anybody cares enough about this to even post a comment and then I will tell you more about my thoughts…A wonderful and peaceful Spring break to all of the readers!

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. Before Sun announced Project Blackbox, there were rumblings about Google working on containerized data centers, so it is likely for larger xSP type customers, preconfigured data centers make more sense than buying individual servers.Containerized data centers are really the next step beyond the preconfigured racks of servers which were offered by Sun and Rackable for years.Does it make sense? Probably, to customers who buy servers in blocks of hundreds with the intention of deploying them together (xSP and HPC seem obvious). Also, containerized data centers make sense if new data center construction is required. Already, data centers are built with raised floor construction, which is a forty-year legacy of S/360. If containerized data centers force a rethinking of data center construction, it will be worth it.The biggest drawback preventing customers from implementing containerized data centers is containerized data centers assume a very high IT maturity level. They are lights out data centers. It is a big deal to open one up to physically touch a server. It also assumes the server vendor will install and configure all of the systems. Most customers simply are not ready for that.There can be no doubt it is time to rethink the physical aspects of the data center. It is also time to rethink the physical aspects of the server. Again, if containerized data centers are the stimulous to reconsider discrete rackmout servers as the primary design point, that will be a good start.Containerized data centers offer tremendous market opportunities for Cisco because they require consolidated networking and central software stack provisioning. Containerized data centers beg for tools like VFrame, and align very well with Cisco’s vision of the network as the platform.

  2. I recently had the pleasure of discussing this topic over dinner with several colleagues. It’s a novel concept, and I’d love to explore it further, but I don’t know that it’s quite the panacea some folks are claiming it to be.As a means of delivering high end compute power in unique or ‘impossible’ scenarios this is very interesting. The idea of dropping a container full of compute processing onto the roof of a manufacturing plant, or a remote military outpost (better yet, keep it in flight with satellite uplinks in a C5 Galaxy) intrigues me. But I’m left with 1 question: do I really need that kind of processing power in the middle of my construction site, battlefield, etc?What worries me is that some have taken this to envision a truly mobile data center. In Dallas today, in Austin tomorrow…and I just don’t see the value proposition…let alone the feasibility when one stops to consider little details like maintenance windows the the likelihood of truly taking down the entire ‘data center’ to relocate it.In the end I could envision filling out a root cause analysis with the following:Root Cause of Outage: Forgot to set parking break on the data center.

  3. Today an application relies on data/logic from multiple datacenters. For example, all the mashups like zillow etc. use multiple datacenters to deliver their application. In essence the application is looking at the datacenter as a compute/storage unit and just wants to reason with it using industry standard interfaces. When that starts to happens, the industry needs to climb another layer of abstraction and focus not on building datacenters but simply leasing/buying them. Today’s hardware forces us to use container boxes, but using the Moore’s law to forecast, all that compute power will one day be available in a single rack.

  4. I think overall we are ‘not’ ready. I believe there are only a very few scenarios where this is even remotely feasible.My write-up/thoughts on visiting the touring BlackBox can be found at