Understanding load averages and stretch factors
What is the real meaning of those little “load average” values in the output of shell commands like procinfo and uptime, and what can you do with these numbers?
Most Linux system administrators are familiar with those three little numbers that appear in shell commands like procinfo, uptime, top, and remote host ruptime. Uptime, for example, emits:
9:40am up 9 days, load average: 0.02, 0.01, 0.00
The load average metrics are always included within the output of commands like uptime. While the load average is well known to Linux system administrators, its meaning is often poorly understood. The man page for uptime states that these values represent
a one line display of ... the system load averages for the past 1, 5, and 15 minutes.
which explains why there are three numbers, but it does not explain what the word load means or how to use these figures to forecast and troubleshoot system performance. This article takes a close look at the load average metrics and how to use them.