In linux, load average determines the server load

We may know how to view resources used by cpu and memory in minutes using top, but how much we know about the load average. Let's take a look at it.

Top command: top



Shown as follows:



The three values after load average are 1 minute, 5 minutes, and 15 minutes respectively. The data checks the number of active processes every five seconds, and then calculates the number based on this value. If this number is divided by the number of CPUs, the system is overloaded when the result is greater than 5.

Query the number of cpu cores: cat/proc/cpuinfo


Obviously, the load average: 185.87, 149.43, 489.26

It can be seen that 185.87/4 is far greater than 5 in a minute. At this time, the server is overloaded, and it must be very slow. (Normally, load average: 1.59, 1.57, 1.70 as shown in the first figure)