Linux: Maximum CPU Load

My Linux server is reporting 1.2 as its CPU Load.   How can I find out what the maximum number for the CPU load would be?
LVL 16
hankknightAsked:
Who is Participating?
I wear a lot of hats...

"The solutions and answers provided on Experts Exchange have been extremely helpful to me over the last few years. I wear a lot of hats - Developer, Database Administrator, Help Desk, etc., so I know a lot of things but not a lot about one thing. Experts Exchange gives me answers from people who do know a lot about one thing, in a easy to use platform." -Todd S.

farzanjCommented:
You need to understand what the load is.
Here's a good link
http://blog.scoutapp.com/articles/2009/07/31/understanding-load-averages

Also remember that if your system have more CPU's and/or cores, the load number totally depends on it.

So if you have multiple cores/ CPUs, you are completely fine with 1.25 load average.

Generally it is 1 per core or CPU.
Duncan RoeSoftware DeveloperCommented:
You can make the load average arbitrarily large by starting a process that runs enough simultaneous threads. E.g. make -j7 in the Linux source directory will ramp the load average up to 7. As long as %id in top is nonzero, you still have CPU power to spare. Watch %wa (wait) - this is the time when no work can be done because of waiting for a disk transfer to finish.
Most important: is response time acceptable?
mohansahuCommented:
Hi,

Please find the below link for CPU load and utilization

http://www.cyberciti.biz/tips/how-do-i-find-out-linux-cpu-utilization.html

MS
Get Blueprints for Increased Customer Retention

The IT Service Excellence Tool Kit has best practices to keep your clients happy and business booming. Inside, you’ll find everything you need to increase client satisfaction and retention, become more competitive, and increase your overall success.

hankknightAuthor Commented:
How can I find out the total number of available processors and cores?  This should be the maximum CPU Load.   Is there a way from the Linux command line to detect the number of available processors and cores so I can know what the highest potential CPU load could be?
farzanjCommented:
You can issue command
top

Open in new window


And then hit key '1'

Or use command

dmidecode processor

Open in new window


Or
cat /proc/cpuinfo

Open in new window

mohansahuCommented:
1 . To find the number of physical CPUs:
$ cat /proc/cpuinfo | grep "^physical id" | sort | uniq | wc -l

2.To find the number of cores per CPU:
cat /proc/cpuinfo | grep "^cpu cores" | uniq

3.To find the total number of processors:

cat /proc/cpuinfo | grep "^processor" | wc -l

MS
comfortjeaniusCommented:
The nproc command shows the number of processing units available:
nproc

Open in new window


lscpu gathers CPU architecture information :
lscpu

Open in new window


or you could use this....
dmidecode -t 4 | grep CPU

Open in new window


Information in the /proc/cpuinfo
cat /proc/cpuinfo  | grep processor

Open in new window


cat /proc/cpuinfo | grep "physical id" | sort | uniq | wc -l

Open in new window

Experts Exchange Solution brought to you by

Your issues matter to us.

Facing a tech roadblock? Get the help and guidance you need from experienced professionals who care. Ask your question anytime, anywhere, with no hassle.

Start your 7-day free trial
Duncan RoeSoftware DeveloperCommented:
The load average can go way over the number of CPUs or cores with no ill effects. I've looked into precisely what it means at some length in the past, but not come to any useful conclusion (except that you can make it as high as you like as per http:#a39763344).
Mainly it just scares people. Ignore it and concentrate on real measures like time to accomplish work.
serialbandCommented:
The load average can go way over the number of CPUs or cores with no ill effects.

That hasn't been my experience.   If the load average is too far above the number of CPU cores the system does slow down and becomes quite unresponsive.  If it's a short one minute spike, it's not a big deal.  If you run parallel compute clusters that run for hours and days, you can't really run it above the number of CPUs.  It can go a little bit above the number of CPU cores or threads, but then processes slow down.

Load averages are ballpark figures, but I kept them equal to the number of CPU for optimal compute speeds on the parallel compute clusters I ran.
It's more than this solution.Get answers and train to solve all your tech problems - anytime, anywhere.Try it for free Edge Out The Competitionfor your dream job with proven skills and certifications.Get started today Stand Outas the employee with proven skills.Start learning today for free Move Your Career Forwardwith certification training in the latest technologies.Start your trial today
Linux

From novice to tech pro — start learning today.