proc/locaavg definition

proc/locaavg definition

[David Lang]

from what I have been able to find under /Documentation /proc/loadavg is 
defined as giving three loadaverage numbers, 1 min, 5 min, 15 min.

however as of 2.6.5ish timeframe there are a coupld of additional colums 
that do not appear to be documented

the first is something #/# that could be # of running processes/total # of 
processes, but I can't find a definition of this anywhere

the second new column I don't have any clue what it is.

is there some missing documentation or did I miss something in the 
existing documentation, and if so where should I look?

David Lang

-- 
There are two ways of constructing a software design. One way is to make it so simple that there are obviously no deficiencies. And the other way is to make it so complicated that there are no obvious deficiencies.
  -- C.A.R. Hoare

Re: proc/locaavg definition

[Andrew Morton]

David Lang <david.lang@digitalinsight.com> wrote:
>
> from what I have been able to find under /Documentation /proc/loadavg is 
>  defined as giving three loadaverage numbers, 1 min, 5 min, 15 min.
> 
>  however as of 2.6.5ish timeframe there are a coupld of additional colums 
>  that do not appear to be documented
> 
>  the first is something #/# that could be # of running processes/total # of 
>  processes, but I can't find a definition of this anywhere

	number of currently ready-to-run threads
	/
	total number of threads in the machine
	the pid of the most-recently-created thread.

No idea why the last one is there.

Re: proc/locaavg definition

[David Lang]

On Thu, 3 Mar 2005, Andrew Morton wrote:

> David Lang <david.lang@digitalinsight.com> wrote:
>>
>> from what I have been able to find under /Documentation /proc/loadavg is
>>  defined as giving three loadaverage numbers, 1 min, 5 min, 15 min.
>>
>>  however as of 2.6.5ish timeframe there are a coupld of additional colums
>>  that do not appear to be documented
>>
>>  the first is something #/# that could be # of running processes/total # of
>>  processes, but I can't find a definition of this anywhere
>
> 	number of currently ready-to-run threads
> 	/
> 	total number of threads in the machine
> 	the pid of the most-recently-created thread.
>
> No idea why the last one is there.

Thanks


-- 
There are two ways of constructing a software design. One way is to make it so simple that there are obviously no deficiencies. And the other way is to make it so complicated that there are no obvious deficiencies.
  -- C.A.R. Hoare

Re: proc/locaavg definition

[Coywolf Qi Hunt]

On Thu, 3 Mar 2005 02:36:50 -0800, Andrew Morton <akpm@osdl.org> wrote:
> David Lang <david.lang@digitalinsight.com> wrote:
> >
> > from what I have been able to find under /Documentation /proc/loadavg is
> >  defined as giving three loadaverage numbers, 1 min, 5 min, 15 min.
> >
> >  however as of 2.6.5ish timeframe there are a coupld of additional colums
> >  that do not appear to be documented
> >
> >  the first is something #/# that could be # of running processes/total # of
> >  processes, but I can't find a definition of this anywhere
> 
>         number of currently ready-to-run threads
>         /
>         total number of threads in the machine
>         the pid of the most-recently-created thread.
> 
> No idea why the last one is there.

This refects the forking activity. How `heavy' the load is.


-- 
Coywolf Qi Hunt
Homepage http://sosdg.org/~coywolf/