How to determine load on CPU is high

linuxandtsm · 05-29-2012, 09:49 AM

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!

schneidz · 05-29-2012, 11:15 AM

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

chrism01 · 05-29-2012, 07:23 PM

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.

syg00 · 05-29-2012, 09:53 PM

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.