check_load --- divide by number of cpus?
Hugo van der Kooij
hvdkooij at vanderkooij.org
Sat May 10 09:31:29 CEST 2008
-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Terry wrote:
| I am sitting here racking my brain on this one. Is dividing the load
| average by the number of CPUs a smart thing to do? the 'uptime'
| command on a box does not do this. So, if I have an 8 core box
| sitting with a load average of 8, its the same as a single core box
| sitting with a load average of 1? I'll see the same type of server
| response? Thoughts?
The load value is the least understood value of a unix system. Most
people simple do not know how to handle it.
I have created situations with a load of just 1 and a CPU usage of 100%
where a second session becomes sluggish. And I have also created
situation where the same system had a load of around 12 and I could
happely hack away on the system at the same time.
By itself the load factor is not very usefull. Take into account the CPU
usage and I/O actions and you start to get a proper picture.
If you are to do any maths on the load factor you should not divide it
by the number of CPU's. Doing a substraction would give a slightly less
distorted figure if you start to mangle with the numbers.
Say you use the following value for a single core CPU:
define service{
~ use local-service ; Name of
service template to use
~ host_name balin.waakhond.net
~ service_description Current Load
~ check_command
check_local_load!5.0,4.0,3.0!10.0,6.0,4.0
~ }
Then basically I would add 7 to all these counters for a 8 core system.
Hugo.
- --
hvdkooij at vanderkooij.org http://hugo.vanderkooij.org/
PGP/GPG? Use: http://hugo.vanderkooij.org/0x58F19981.asc
A: Yes.
>Q: Are you sure?
>>A: Because it reverses the logical flow of conversation.
>>>Q: Why is top posting frowned upon?
Bored? Click on http://spamornot.org/ and rate those images.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.7 (GNU/Linux)
iD8DBQFIJU9PBvzDRVjxmYERAuuiAKClbDiwmk6cDqpdBZG555sriS/IxgCfUvVJ
JC1bD7qpZ9M0f2YRgTnx6VA=
=TNia
-----END PGP SIGNATURE-----
-------------------------------------------------------------------------
This SF.net email is sponsored by the 2008 JavaOne(SM) Conference
Don't miss this year's exciting event. There's still time to save $100.
Use priority code J8TL2D2.
http://ad.doubleclick.net/clk;198757673;13503038;p?http://java.sun.com/javaone
_______________________________________________
Nagios-users mailing list
Nagios-users at lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/nagios-users
::: Please include Nagios version, plugin version (-v) and OS when reporting any issue.
::: Messages without supporting info will risk being sent to /dev/null
More information about the Users
mailing list