New Logo for EMC: The Jolly Green Giant
You would think that was the case from the press around EMC’s new product functionality, announced yesterday at the kickoff of EMC World. Plus, they even have an analyst saying so.
Charles King, Pund-IT Research, was impressed with a number of the announcements and EMC’s continuing focus on issues troubling the storage industry, including green computing, solid state drive usage and simplifying storage management. He noted that EMC continues to set the bar for many of these issues and other vendors are either just getting involved, or waiting.
“Nobody has taken the end-to-end way to green storage that EMC has,” said King. He believes the new spin-down technology is one of the only such energy-efficiency initiatives around.
My take about EMC’s announcements of their new de-dupe, drive spin down, hybrid drive stuff: it’s all about the green, not about Green.
Blood is in the water and the sharks have started circling. This image may well come to mind when you read the flood of articles that have been filling the technology trade press since “Green IT” became the rage a little over a year ago.
Green IT is only one dimension of green technology activism, which spans issues ranging from technology product manufacturing and tech product recycling. Green IT refers specifically to electrical power consumption and ways to contain its growth in contemporary data centers with the ultimate goal of reducing carbon gas emissions and slowing global warming.
Green IT is good, everyone agrees, whether their motives are pure and environmental or pragmatic and focused on cutting the IT facility power bill. However, the discussion over ways to get to green nirvana has become the stuff of marketecture rather than architecture.
Initial focus has been placed on servers, thanks largely to the Koomey Study – produced by Jonathan G. Koomey, Ph.D., Staff Scientist at Lawrence Berkeley National Laboratory and Consulting Professor at Stanford University. Flawed though his study might be, given its myopic attention to servers (ignoring storage and network equipment), its use of IDC projections on new deployments (2000 through 2005), and its use of vendor-provided power consumption labels on equipment (usually understated), it became the darling of the Green IT movement. Based on Koomey, servers were immediately cast as the villain in the Green IT story: the power they consume and the heat they generate amounts to significant electrical load.
However, other evidence supplied by IT datacenter operators such as Dell Computers suggested that, by the time Koomey released his data, storage equipment (disk arrays, switches, appliances, etc.) were already outpacing servers as the biggest power pigs in the data center. Partly this was due to server consolidation efforts and the advent of multicore x86 chipsets, but mostly the change could be attributed to an explosion of data under storage.
Note that the term “under storage” is substituted for “under management.” Truth be told, data management in distributed computing environments is extraordinarily lax. The best analogy for distributed storage is a huge and growing junk drawer. This point is underscored by data collated by Sun Microsystems after performing nearly 10,000 storage assessments at client facilities. Per Sun’s statistics, for every hard disk deployed by a company, roughly 30 percent of its capacity contains useful data accessed regularly as part of day to day operations. Another 40 percent must be retained for reasons of historical value, regulatory or legal compliance, or because it is intellectual property. Rarely referenced, this data belongs in an archive, preferably tape or optical because they consume far less kilowatt hours than do disk-based systems.
The balance of the space on each hard disk, some 30 percent of total disk capacity, comprises orphan data (whose owner of record no longer exists at the company), contraband data (collections of MP3 files, videos or pictures downloaded from the Internet), and good old fashioned wasted space that has been reserved by an application or file system, but never used. This capacity could be freed up through a combination of data hygiene and good storage resource monitoring and management. If that were done, and archiving was implemented, companies could return up to 70 percent of the capacity of every spindle they own today, deferring the need to invest in more storage and exacerbating the storage acquisition trend that IDC projects will total 300 percent by 2011.
This point is never brought up in the articles you read in the trades. Instead, vendors posit a number of hardware and software value-add solutions as silver bullets for Green IT. Virtualization, de-duplication, compression, re-driving arrays with larger disk drives, leveraging MAID (massive arrays of independent disk, a portion of which spin down when not in use), and thin provisioning are just a few of the green panaceas that are being discussed. Most involve plugging additional hardware into the wall, which is hardly an intelligent way to reduce power consumption.
All of these techniques deliver tactical value at best: unmanaged data will continue to grow over time and eliminate whatever short term power reductions that the new technologies deliver. They are simply re-arranging deck chairs on the Titanic. Getting to green in IT ultimately and strategically comes down to managing data better. It costs a company virtually nothing to sort out their data junk drawer, to apply processes for classifying data so that it can be migrated over time into an archive, and to deploy storage resource management tools to spot wasted space, ownerless files and junk data in their repositories.
This is the path to strategic green. Once done, IT managers can selectively and intelligently apply cool new features that have the vendors clamoring to help with their capacity allocation efficiency objectives.
By the way, improving data management returns its investment of sweat equity and software in droves. It addresses the C-4 objectives that are being discussed in every boardroom and front office of every company we visit today: cost-containment, compliance, continuity and carbon footprint reduction. Managed data defers storage spending and reduces power consumption. It also enables the proper selection of data for compliance and continuity planning. And it enables users to more productive. That hits all sides of the business value case: cost-savings, risk reduction and top line growth.
One last thing: Charles King is now on my pay-per-view analyst watch list.

May 20th, 2008 at 8:39 am
It occurs to me, after reading the article again, that there is zero mention of tape or optical in the EMC green initiative. Aren’t these the least carbon utilizing storage media of them all? In a traditional tiered storage architecture (mainframe, that is), tape had about three roles to play.
Big Green, I mean EMC, is saying that its dedupe solution is greener than tape. Per this extract from the proceedings:
“The EMC Avamar Data Store Gen 2 and EMC Avamar 4.0 can use up to 43% less energy per terabyte backed up and reduce total cost of ownership by up to 25% compared to the first generation product, and 75% less than tape.”
75 percent less energy consumed by de-duped disk than by tape. Hmm. Wonder who came up with those numbers?
May 22nd, 2008 at 9:16 am
EMC isnt doing anything innovative here - many companies are already doing the same
May 23rd, 2008 at 5:14 am
Interesting article - do you have any links/references to the Dell/Sun stats that you quote though?
May 23rd, 2008 at 7:56 am
Thanks, Spang.
The Dell article is here. The Sun data was collected by Tom Neeley at Sun and is cited by Randy Chalfant, a Sun CTO, in our blook at MakingITMatter.com.