Load average is not solely CPU usage. It also encompasses disk I/O and network-bound processes. It is not just an average it is a time-based damped average. In short, a load average of 0 means you have a completely idle system (not unheard of, but rare). A load average of 1 means that your CPU is handling things fine there is a 1:1 ratio of instructions in the run queue to the CPU processing them. Less than 1 means that you have more headroom to spare, and more than 1 means that the system could benefit from a more powerful single processor, or multi-core processors to handle the load. It is situation-dependent, and will mean different things depending on the use of the system:
A machine acting solely as a database server even under heavy use will have a completely different load average pattern than a file server or a shell server.
So, while somewhat confusing, load average is certainly not a useless metric. Watch it, and learn the patterns from your system or systems. Following load average is CPU usage. Don’t panic when the CPU load rises. It’s the job of Mac OS X to make sure that the CPU is getting used. There is no sense in having a CPU if you’re not going to put it to work. The values displayed in the example show CPU usage segmented into user processes, system use, and percent idle.
You’re likely to see these numbers jumping about as the CPU does its job. Even though you may run a basic user space program such as, say, iTunes, the kernel still has to work keeping track of all the resources used by the application. These values are affected by everything the CPU needs to handle running applications, processing interrupts (think video cards, network interfaces, and so on), moving memory around, and more.
Once again, you need to learn the patterns of the system that you’re monitoring. In conjunction with the load average metric, you can get a good idea if processes are suffering or flourishing with the CPU usage statistics.