Re: [PATCH 4/5] sched: don't consider upper se in sched_slice()

[Joonsoo Kim <iamjoonsoo.kim@lge.com>]

Hello, Preeti.

On Tue, Apr 02, 2013 at 11:02:43PM +0530, Preeti U Murthy wrote:
> Hi Joonsoo,
> 
> 
> >>> I think that it is real problem that sysctl_sched_min_granularity is not
> >>> guaranteed for each task.
> >>> Instead of this patch, how about considering low bound?
> >>>
> >>> if (slice < sysctl_sched_min_granularity)
> >>> 	slice = sysctl_sched_min_granularity;
> >>
> >> Consider the below scenario.
> >>
> >> A runqueue has two task groups,each with 10 tasks.
> >>
> >> With the current implementation,each of these tasks get a sched_slice of
> >> 2ms.Hence in a matter of (10*2) + (10*2) = 40 ms, all tasks( all tasks
> >> of both the task groups) will get the chance to run.
> >>
> >> But what is the scheduling period in this scenario? Is it 40ms (extended
> >> sysctl_sched_latency), which is the scheduling period for each of the
> >> runqueues with 10 tasks in it?
> >> Or is it 80ms which is the total of the scheduling periods of each of
> >> the run queues with 10 tasks.Either way all tasks seem to get scheduled
> >> atleast once within the scheduling period.So we appear to be safe.
> >> Although the sched_slice < sched_min_granularity.
> >>
> >> With your above lower bound of sysctl_sched_min_granularity, each task
> >> of each tg gets 4ms as its sched_slice.So in a matter of
> >> (10*4) + (10*4) = 80ms,all tasks get to run. With the above question
> >> being put forth here as well, we don't appear to be safe if the
> >> scheduling_period is considered to be 40ms, otherwise it appears fine to
> >> me, because it ensures the sched_slice is atleast sched_min_granularity
> >> no matter what.
> > 
> > So, you mean that we should guarantee to schedule each task atleast once
> > in sysctl_sched_latency? 
> 
> I would rather say all tasks get to run atleast once in a sched_period,
> which could be just sysctl_sched_latency or more depending on the number
> of tasks in the current implementation.
> 
> But this is not guaranteed in current code,
> > this is why I made this patch. Please refer a patch description.
> 
> Ok,take the example of a runqueue with 2 task groups,each with 10
> tasks.Same as your previous example. Can you explain how your patch
> ensures that all 20 tasks get to run atleast once in a sched_period?

My patch doesn't ensure that :)
I just want to say a problem of current implementation which can't
ensure to run atleast once in sched_period through my patch description.

So, how about extending a sched_period with rq->nr_running, instead of
cfs_rq->nr_running? It is my quick thought and I think that we can ensure
to run atleast once in this extending sched_period.

And, do we leave a problem if we cannot guaranteed atleast once property?

Thanks.

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