Re: [PATCH 2/2] sched: Rewrite per entity runnable load average tracking

[Yuyang Du]

On Wed, Jul 09, 2014 at 10:08:42AM -0700, bsegall@xxxxxxxxxx wrote:

> > That I believe is not a problem. It is a matter of when cfs_rq->load.weight
> > changes and when we look at it to contribute to the cfs_rq's load_avg.
> > Fortunately, we will not miss any change of cfs_rq->load.weight, always
> > contributing to the load_avg the right amount. Put another way, we always
> > use the right cfs_rq->load.weight.
> 
> You always call __update_load_avg with every needed load.weight, but if
> now - sa->last_update_time < 1024, then it will not do anything with
> that weight, and the next actual update may be with a different weight.
 
Oh, yes, I finally understand, :) You are right. That is the matter of 1ms period.
Within period boundary, everything will be lost.

Thanks,
Yuyang
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/