Prerequisites for Introducing All-in-One Computing into Enterprise IT

The "all-in-one" concept is one of the hottest trends in consumer technologies. Just looking at the gadgets and devices that I use on a day-to-day basis in my office, I am hard pressed to find one that does not perform multiple tasks. My office phone supports two lines, has a separate voice message box for each line and tracks all of my incoming and outgoing calls. My printer is not just a printer. It prints, copies, scans and faxes. Then, of course, there is my Blackberry which acts as a cell phone, email client, web browser, calculator, personal organizer (contacts/phone book) and a host of other functions that I have not even had time to figure out yet.

So why is it that this all-in-one concept is slow to catch on in enterprise IT shops? There is any number of reasons. Part of the problem is that these shops are often content to dedicate specific devices to performing specific functions rather than push the boundaries a bit.

However a bigger part of the dilemma is that enterprise IT shops inherently have much more at stake if a device that performs multiple functions fails. When my Blackberry fails, it just inconveniences me. When a device that performs multiple tasks fails in a business, it may disrupt multiple business processes. This can result in missed service level agreements and even incur financial penalties or lost revenue.

Anyone who has ever worked in production IT environments knows that is a sure fire way to get oneself fired. While that alone is not sufficient reason for enterprise IT organizations not to explore enterprise technologies that promise "all-in-one" functionality, it certainly gives IT staff in these organizations pause in implementing them.

Therefore to move all-in-one technologies beyond just consumer-oriented Blackberries into enterprise IT environments requires that these technologies deliver on some key concepts that keep IT managers up at night. These include:

• The ability to sustain multiple, concurrent points of failure. Most computer hardware that is designed for a single purpose, whether it is a storage array, server, or network switch, has redundant everything - power supplies, disk drives, controllers, etc. Yet if two of these items fail at the same time in the unit, the whole unit fails and those who say it can't happen are lying through their teeth as I have seen it happen. Granted, it was always extreme circumstances but the impact was devastating. Now imagine if multiple processes hinge upon the availability of one specific piece of hardware. Companies will want every assurance that device can remain available all of the time.
• Can measure and forecast how much of the hardware resources each function on the device will use. My Blackberry has all of the horsepower, memory and storage I need and, even when it doesn't, I run down to my local Verizon store, buy the item that I need, power my Blackberry off, insert the additional memory or storage and Voila!, I'm ready to go. Enterprise IT shops have no such luxury. They need to forecast, monitor and pro-actively respond with the right amount of memory, processing power or capacity before there is a problem. Then they need to justify why they need what they need, procure the needed equipment, plan the upgrade and non-disruptively upgrade the device so no application outages are incurred. Oh yeah, and then pray to God that they procured the right amount of memory, CPU or storage and that it solves the problem they said it would without causing any new problems.
• Can scale to permit the introduction of the appropriate resources. Knowing what memory, CPU or storage you need to add to correct the problem is only part of the equation. That part of the equation only works if the device can scale to support it. That becomes tricky. If companies overbuy and never use the scalable feature, they find themselves paying for features they never use. Conversely, if they size their hardware too small, they find themselves having to take huge write-offs before the equipment is fully depreciated and needing to buy new hardware that is appropriately sized. Even in circumstances where they can buy the appropriate level of hardware, companies still need the flexibility within the device to dedicate the new hardware resource to the software function that needs it. Otherwise, the performance or capacity enhancement will be negligible.

Meeting any one of these three requirements is a tall order. Meeting all three sounds impossible. However technologies with these types of capabilities are now starting to show up in the enterprise data protection space and specifically in the form of grid storage. In forthcoming blog entries, I'll take a closer look at how the NEC HYDRAstor and its grid storage architecture is giving enterprise IT a realistic chance of bringing devices that provide the all-in-one functionality they want without the typical trade-offs that most other systems at the enterprise level expect.