LinuxQuestions.org - How to determine load on CPU is high

- Linux - Newbie (https://www.linuxquestions.org/questions/linux-newbie-8/)

- - How to determine load on CPU is high (https://www.linuxquestions.org/questions/linux-newbie-8/how-to-determine-load-on-cpu-is-high-947380/)

How to determine load on CPU is high

Hi all,

There is a linux server with 4 CPU cores and is having the load average's in the range greater than 7. I am wondering if this should be considered as a high load on CPU ?
What is the rule of thumb to determine this ?

Code:

]# grep cores /proc/cpuinfo

cpu cores      : 1

cpu cores      : 1

cpu cores      : 1

cpu cores      : 1

Code:

09:48:26 up 225 days, 20:32, 1 user, load average: 7.70, 7.52, 7.34

Thanks in advance!

not sure... but heres mine for comparison:

Code:

[schneidz@hyper ~]$ egrep "(processor|name|core id)" /proc/cpuinfo

processor        : 0

model name        : Intel(R) Atom(TM) CPU  230  @ 1.60GHz

core id                : 0

processor        : 1

model name        : Intel(R) Atom(TM) CPU  230  @ 1.60GHz

core id                : 0

[schneidz@hyper ~]$ w

 11:14:14 up 7 days,  2:17,  3 users,  load average: 0.00, 0.02, 0.05

Well, one way to get a bit more info is to run 'top', then hit '1' which should display separate figures for each core.

Code:

 top

top - 09:22:33 up 506 days,  1:11,  2 users,  load average: 0.34, 0.33, 0.36

Tasks: 160 total,  1 running, 159 sleeping,  0 stopped,  0 zombie

Cpu0  :  0.2%us,  0.1%sy,  0.0%ni, 99.7%id,  0.1%wa,  0.0%hi,  0.0%si,  0.0%st

Cpu1  :  0.3%us,  0.4%sy,  0.0%ni, 99.0%id,  0.4%wa,  0.0%hi,  0.0%si,  0.0%st

Cpu2  :  0.0%us,  0.3%sy,  0.0%ni, 99.4%id,  0.1%wa,  0.1%hi,  0.1%si,  0.0%st

Cpu3  :  0.3%us,  0.3%sy,  0.0%ni, 99.2%id,  0.1%wa,  0.0%hi,  0.0%si,  0.0%st

Cpu4  :  0.0%us,  0.1%sy,  0.0%ni, 99.7%id,  0.1%wa,  0.0%hi,  0.0%si,  0.0%st

Cpu5  :  0.3%us,  0.4%sy,  0.0%ni, 99.2%id,  0.1%wa,  0.0%hi,  0.0%si,  0.0%st

Cpu6  :  0.0%us,  0.1%sy,  0.0%ni, 99.8%id,  0.1%wa,  0.0%hi,  0.0%si,  0.0%st

Cpu7  :  0.3%us,  0.3%sy,  0.0%ni, 99.1%id,  0.2%wa,  0.0%hi,  0.0%si,  0.0%st

Mem:  3368188k total,  3278892k used,    89296k free,  122800k buffers

Swap:  2097144k total,      116k used,  2097028k free,  3006816k cached

My general rules of thumb are:
1. load < 0.1 -> just OS
2. load < 1 ignore
3. load < 5 -> busy but nothing to worry about
4. load < 10 -> busy and users may notice
5. load >= 10 definitely an issue

BUT this all depends on what is normal/what response times are reqd by the users. Some people just can't afford a fast box and always run at eg load = 10.

In Linux, CPU busy percentage has only an indirect influence on loadavg. It is not the same concept.
Read this - it's a little dated, but the concepts expounded are still relevant.