Re: [Lse-tech] Re: A common layer for Accounting packages

[Jay Lan <jlan@sgi.com>]

Chris Wright wrote:
> * Jay Lan (jlan@sgi.com) wrote:
> 
>>Andrew Morton wrote:
>>
>>>Kaigai Kohei <kaigai@ak.jp.nec.com> wrote:
>>>
>>>
>>>>In my understanding, what Andrew Morton said is "If target functionality 
>>>>can
>>>>implement in user space only, then we should not modify the kernel-tree".
>>>
>>>
>>>fork, exec and exit upcalls sound pretty good to me.  As long as
>>>
>>>a) they use the same common machinery and
>>>
>>>b) they are next-to-zero cost if something is listening on the netlink
>>>  socket but no accounting daemon is running.
>>>
>>>Question is: is this sufficient for CSA?
>>
>>Yes, fork, exec, and exit upcalls are sufficient for CSA.
> 
> 
> As soon as you want to throttle tasks at the Job level, this would be
> insufficient.  But, IIRC, that's not one of PAGG/Job/CSA's requirements
> right?

PAGG serves more than JOB+CSA.

I am looking into possiblity/feasibility of implementing JOB at
userspace. However, even with JOB as a kernel module, the fork,
exec and exit upcalls would be sufficient to support JOB+CSA.

Thanks,
  - jay

> 
> thanks,
> -chris