Why IT projects fail

Friday 26 September 2008

The past years, many companies complained about IT projects. In general, IT projects tend to be late, over budget, and not fulfilling expectations. What is the reason for these complaints?

I think most projects fail because expectations are not aligned between stakeholders and projects.

All projects have several stakeholders. These stakeholders are (among others):

• Business process owners
• End users
• The financial department
• The system administrators (functional and technical)
• etc.

Who decides if a project is a success?

If the expectations of a project meet the financial departments expectations and the end users expectations, but not the expectations of the system administrators, some stakeholders feel the project is a success, and others don’t. I think a project is only a success if all stakeholders are happy in the end.

All stakeholders all have expectations about the project. Sometimes these expectations are written requirements, but many expectations are implicit. Implicit requirements that are obvious to one or more stakeholders might not be so obvious to the project team.

An example can be the availability of the system. If the requirements say 99% availability (where the actual expectations are that the system is always up), the system administrators can use the 14 minutes per day (which 99% availability implies) to make a snapshot of a SAN for backup reasons. The business probably did not meant this, and thinks the project made a mistake.

Another example is the assumption that an web-enabled system works with older browsers (or with Firefox), where the developers used technology only available in Internet Explorer 6 and higher. The helpdesk probably will feel the project failed, where the only problem was a lack of communications of requirements.

Another issue is the expectation of the project planning. Sometimes the planning of a project is not based on realistic prognoses by experienced people, but on business requirements. The business timelines can be very important, but to make a project a success, the amount of work that can be done in a certain timeframe is limited. Either the scope of the project should become smaller, or the quality (and the success) of the project will be too low.

So, if the project has no knowledge of all the requirements and expectations, and if the project is faced with an impossible planning, it will certainly fail, no matter how hard the project staff is working.

Power and cooling

Friday 12 September 2008

Lately, the most discussed subject in datacenters is Power and Cooling. Why is this such a big issue all of a sudden?

Power bill

Usually a system administrator or a datacenter operator knows what a typical server cost. How many of them know what a kilowatt-hour (kWh) of energy costs? Do YOU know? And who pays that bill? The IT departyment?

The typical power consumption of a full-blown datacenter, including air-conditioning today is in the order of several megawatts. With a power price of 6 dollar cents per kWh (which is typically what large customers pay), the power bill of one megawatt is $1440 per day and $525,600 per megawatt per year!

In 1999, the price of a barrel oil was 11 dollar. Now, the price is 120 dollar. This means that the price of energy is rising at an incredible speed, and there is no end in sight. Therefore, the power bill will go up the coming years, and more attention should be paid to reducing the power consumption in datacenters.

It becomes now viable to place new datacenters in the neighborhood of “green” power plants, like water dams (the water can also be used to cool the datacenter). The cost of moving data through a fibre optics cable is much less than the cost of moving energy from a energy plant to a datacenter.

Lower consumption

For every dollar spent on servers, the same amount is spent on power. Not only the kWh´s of the server itself must be paid, but also on cooling the system, the cost of expanding the air-conditioning system and the uninterruptable power supply (UPS).

Therefore it is a good financial investment to try to keep the power consumption of servers low. A typical Intel CPU in 2005 used ten times more power than the same CPU capacity today. This brought the energy bill down considerably. Therefore, the focus for Intel these days is not to increase the speed of a CPU, but to lower the power consumption. The money saved in power, UPS systems and cooling could be invested in more (low power) CPU’s.

Virtualization is another method to decrease power consumption. Not only can resources be better utilized, and CPU’s used as efficiently as possible, but also the possibility to move running virtual machines to other physical machines (using for instance vMotion from VMware) can reduce hot spots in the datacenter.