We discussed the differences between load balancing and high availability in Chapter 4, “High Availability. HA! No Downtime?!,” so we will pursue that topic by seeking a better understanding of load balancing.

First, let’s reflect on the term load balancing. Although it is obvious what it means—to balance a load—it is often misunderstood to mean balance the system load. System load is defined as the average length of the run queue (processes in a runnable state waiting for the system processor) over the last 1 minute, 5 minutes, and 15 minutes; typically updated on 5-second intervals.

When you type uptime on your Unix or Linux system, you should see something like what I see on one of our production web servers:

The numbers seen at the end are the 1-, 5-, and 15-minute load averages, respectively. So, what is wrong with thinking of load balancing as an attempt to even the load average of the machines in a cluster? In short, everything.