Most IT pros I know think cloud computing is a joke. There are some good reasons for that. But lately I've noticed the laughter is ringing a little hollow, as if tempered by a secret fear: Is it possible the business side might go behind my back and replace chunks of IT at lower cost? Or maybe get some big projects done faster than I can?
It's true. Cloud services -- generally divided into software-as-a-service applications, on-demand infrastructure, and Web-based dev platforms -- may soon form the greatest threat to IT since offshoring. Businesses are increasingly frustrated at the cost and pace of internal IT operations even as fluffy cloud options multiply like rabbits. The buzz is overwhelming. Last week I went to the GigaOm Structure '09 event in San Francisco, subtitled "put cloud computing to work," and it was packed even in this awful economy.
[ For more on this topic, read whurley's classic blog post, "IT needs to get over its cloud denial, or management will get over IT." ]
You may be philosophically opposed to cloud computing, but the last thing you want is for the business side to adopt cloud services without involving IT. Left to their own devices, the business guys will inevitably pick an unwieldy cloud service or jettison an internal system of unique value.
So point one: Engage with management on this topic preemptively and create your own hierarchical list of applications, environments, and/or infrastructure that could be replaced by commodity cloud services with the least pain and risk and the greatest cost savings. Point two: Sketch out an architecture that would allow you to get the maximum benefit from those services.
On that latter point, Miko Matsumura, vice president and chief strategist at Software AG, offered some interesting advice when we spoke at Structure '09. "The critical skill in the cloud age is the ability to integrate and combine on- and off-premise infrastructure and applications," he said. "This skill is supported by a service-oriented architecture."
Those of you familiar with SOA (service-oriented architecture) know that a registry/repository is the best way to expose and govern internally provisioned services. But, says Miko, a registry/repository can also be used to take externally procured cloud services and make them accessible via standard protocols across an organization, leveraging them beyond point solutions while maintaining control. Conversely, IT can use a registry/repository to expose its own native services to the cloud for B-to-B integration or even for a revenue-generating project or two.
CentraSite ActiveSOA, Software AG's new registry/repository, is the heart of the company's recent webMethods 8 release (IBM, Oracle, HP, SOA Software, and others offer their own as well). Miko claims that registry/repositories based on XML databases (like his and HP Systinet) are the most conducive to cloud-SOA synergy. In a sweet piece of irony, the Tamino XML database upon which the new ActiveSOA registry/repository is based derives from the first commercially available DBMS, ADABAS, developed in 1970 by Software AG.
So once again, a solution from the mainframe past vaults into the present like a "crashed UFO" (a favorite Miko phrase). If SOA never got off the ground in your organization, then a registry/repository may not help you. But if you're already on an SOA track, then some extra dev time to expose and govern cloud services may put you on the cutting edge of the biggest trend in IT -- and prevent you from being tagged as an obstacle to progress.