On Mon, Nov 24, 2014 at 02:04:15PM +0000, Vincent Guittot wrote:

On 21 November 2014 at 13:34, Morten Rasmussen [off-list ref] wrote:

quoted

Should the subject mention that the patch adds utilization tracking?
Maybe: 'sched: Add utilization tracking' ?


On Mon, Nov 03, 2014 at 04:54:38PM +0000, Vincent Guittot wrote:

quoted

Add new statistics which reflect the average time a task is running on the CPU
and the sum of these running time of the tasks on a runqueue. The latter is
named utilization_load_avg.

This patch is based on the usage metric that was proposed in the 1st
versions of the per-entity load tracking patchset by Paul Turner

Should we do ourselves and anybody else who feels like going through the
pain of understanding the load-tracking code a favor and drop the use of
the term 'usage' and use 'utilization' everywhere instead? 'usage' isn't
clearly defined anywhere.

Referring to 'usage' here in the reference to original patch is fine,
but I suggest that we remove it from the code and comment on subsequent
patches unless there is a very good reason to keep it.

As discussed with Peter, we use usage when the task's utilization has
been scaled by the capacity.

IIRC from one of our discussion, dietmar should prepare a patchset to
rename and aligned variables and field.

I read this as we stick with usage while utilization is scaled by
capacity and potentially drop it again when adding uarch invariance so
the scaling goes away. Or rename it before if we find a better name for
it.