I continue to think about the role and structure of the IT function and how it needs to change as the landscape evolves around us and here are some of my more random thoughts.
It is important to stop thinking about the scale; scale needs to become completely meaningless; if you think about it, you will terrify yourself and fall into the traps of applying old paradigms. Forget about scale but always account for how to scale. Whatever you do today, you will need to do more of tomorrow.
I think we need to review how operational support, implementation and architectural teams interact. I hesitate to suggest that these all need to become a single function due to the health impact on some of my regular readers. But I think the divorcing of these functions has caused many of the problems that we keep hitting and will continue to do so. In order for management of environments at scale, the feedback loop needs to be closed; this means platform teams who are able manage both the infrastructure from end-to-end but also the infrastructure life-cycle from cradle-to-grave. At the very least, there needs to be regular and open end-to-end reviews involving all the players.
Too often I have seen extremely complex designs created and implemented by people who are not going to run them on a day-to-day basis slowly decay into a morass because the architectural decisions have not taken into account operational procedures, business growth and all those things which the operational teams have to deal with.
How quickly people forget the support issues and operational headaches caused when they become no longer their problem. How quickly people forget the broken nights caused by overly complex designs which are a nightmare to scale and manage. How quickly people forget cursing the implementation team who have not created basic automation for monitoring and restart scripts.
I can point to some extremely complex storage implementations and layouts which have caused no end of headaches because no account has been made as to how to add more space.
However even as we consider IT as a service; we also need to review the vertical services that we provide and how best to service our businesses. My favourite example is email and all the related services around email. Email is now so ubiquitous that we know what is required from it but when was the last time anyone did a requirements review of email? I hear lots of talk about Exchange 2010 upgrade projects but little about what the business wants from the service, I suspect that we have stopped asking.
As we separate services into verticals; this does bring us into conflict at times with horizontal services such as back-up and archiving. Do you use a single back-up and archiving tool or do you encapsulate the backup and archive function into the vertical. Does this breed a multitude of products and does it increase complexity? It could do but if you are charging the business for the provision of the service and they are willing to pay the cost, this may not be important. However as you enter a service-oriented world, you might be competing with external providers. Keeping things as simple as possible would probably make sense but at times a vertical stack might make more sense than a horizontal slice.
We need to consider how we measure our success as an IT service provider and provide business relevant metrics designed to demonstrate value and not to make the IT department look good. For example, I regularly see change metrics demonstrating the number of changes undertaken successfully but what does that mean to the business. Did all those changes actually need to happen? Why are there so many changes? How many of those changes actually needed to happen because of mistakes made in prior changes? What value did those changes generate as opposed to the risk that those changes introduced?
As we define service metrics with the business; there needs to be a mature discussion about how things like growth are handled. As IT departments, we cannot expect blank cheques but we cannot continue to provide IT services as a pure all you can eat buffet; yes, there is an always open buffet but every visit may attract a cost.
Every IT spend above a certain threshold needs to have a worked business case and every business case should be up for a spot audit to demonstrate that it actually delivered the business benefit stated; this should not be used to beat people up but should be used to build an understanding as to what actually works and getting better at delivering business benefits.
Yours,
A Random Bod
