SOA as Panacea

To deliver effective solutions the IT landscape needs to cover a lot of ground: enterprise integration, user experience, application architecture, "stacks", languages (Java isn't the only one, even now), data standards, and so on. In 1996 most IT trade magazines seemed to forget about everything but the web and the thin layer of technologies that it was implemented on. Today the Department of Defense sort of feels sort of that way as all discussion of anything other than SOA has been drowned out. SOA is the panacea of the moment. "We won't build applications anymore, we'll just have services out in the cloud and people, machines, and whatever will discover them and consume them."

Naturally, I don't think that statement makes sense as the real world is more complex and nuanced than that. If you don't believe me, just tell your users they don't need applications and that they can just go to your UDDI repository, find services, and start mentally de-serializing SOAP envelopes.

But that isn't really what triggered this post. This article about the complexity of enterprise software that Nick Carr discussed today did. It is a sceptical (if dour) take on SOA as rescuer from complexity. If it wasn't enough that SOA alone just doesn't cover all the basis, it may just be that SOA adds as much complexity as it attempts to contain.

Comments

[Kit]

Yeh, I saw Rettig's article a few days ago...and couldn't help but think: "man, can she pack anymore more buzzwords in to this thing?" - but, I guess that's what it takes to get noticed.

It really is a shame that so much gets lost in between the boon of buzz-tech (ala the current Master: Web2.0) and logical understanding of how things work. I really have no sympathy for the IT fools who get locked in to savior solutions from Gorilla-Vendors (read IBM et al (read SCA)) and then wonder why they never realize their grand ROI. At the same time I have no sympathy for the small boutique businesses who shrivel up because they had no idea that "connectivity" was so difficult.

To continue with the "dour" note - just consider the differences between orchestration and choreography, and how the latter arrives back at the notion of an "application". Then, realize that SOA has arrived at choreography.

This (http://www.se-radio.net/index.php?post_id=160206) podcast does more for adding to the SOA intellectual landscape - than any MIT-centric writing will ever do.

Kit

[Jim S]

Hey Kit, I'll check out that podcast.

If's funny,.. I think I reacted to the Rettig article very differently than you. It left me with a "well, so what do we do?" sense at the end; but that aside, the message that all these huge enterprise efforts aren't paying off resonated with me. I think the web demonstrates an interesting model for how complex systems can co-evolve whereas "enterprise software" seems to me like the IT equivilent of a centrally planned economy.

[Kit]

There is something to be said for the "organics" of technology. I'm really surprised that we aren't very close to SAP killer from the OSS community.

I, too, wonder "what do we do?" though. Even as irritated as I get by jargonistas, it is impossible to deny that the IT world is struggling. The bottom line is the need for Open standards, that can promote proprietary solutions (remembering our capitalist nature). Standards can help break down the complexity, and promote innovation of interoperability - something that is ruining IT shop's effectiveness.

Anyway...sorry to drag your blog into the mud. ; }