On Mon, 2019-09-02 at 09:51 +0200, Vincent Guittot wrote:
> On Fri, 30 Aug 2019 at 17:02, Rik van Riel wrote:
> > I would be more than happy to drop this patch if you
> > prefer. Just let me know.
>
> If i'm not wrong, this change is not mandatory to flatten the
> runqueue and because of the
On Fri, 30 Aug 2019 at 17:02, Rik van Riel wrote:
>
> On Fri, 2019-08-30 at 08:41 +0200, Vincent Guittot wrote:
>
> > > When tasks get their timeslice rounded up, that will increase
> > > the total sched period in a similar way the old code did by
> > > returning a longer period from
On Fri, 2019-08-30 at 08:41 +0200, Vincent Guittot wrote:
> > When tasks get their timeslice rounded up, that will increase
> > the total sched period in a similar way the old code did by
> > returning a longer period from __sched_period.
>
> sched_slice is not a strict value and scheduler will
On Thu, 29 Aug 2019 at 18:00, Rik van Riel wrote:
>
> On Thu, 2019-08-29 at 16:02 +0200, Vincent Guittot wrote:
> > On Thu, 29 Aug 2019 at 01:19, Rik van Riel wrote:
> >
> > > What am I overlooking?
> >
> > My point is more for task that runs several ticks in a row. Their
> > sched_slice will be
On Thu, 2019-08-29 at 16:02 +0200, Vincent Guittot wrote:
> On Thu, 29 Aug 2019 at 01:19, Rik van Riel wrote:
>
> > What am I overlooking?
>
> My point is more for task that runs several ticks in a row. Their
> sched_slice will be shorter in some cases with your changes so they
> can be
On Thu, 29 Aug 2019 at 01:19, Rik van Riel wrote:
>
> On Wed, 2019-08-28 at 19:32 +0200, Vincent Guittot wrote:
> > On Thu, 22 Aug 2019 at 04:18, Rik van Riel wrote:
> > > The idea behind __sched_period makes sense, but the results do not
> > > always.
> > >
> > > When a CPU has one high
On Wed, 2019-08-28 at 19:32 +0200, Vincent Guittot wrote:
> On Thu, 22 Aug 2019 at 04:18, Rik van Riel wrote:
> > The idea behind __sched_period makes sense, but the results do not
> > always.
> >
> > When a CPU has one high priority task and a large number of low
> > priority
> > tasks,
On Thu, 22 Aug 2019 at 04:18, Rik van Riel wrote:
>
> The idea behind __sched_period makes sense, but the results do not always.
>
> When a CPU has one high priority task and a large number of low priority
> tasks, __sched_period will return a value larger than sysctl_sched_latency,
> and the one
The idea behind __sched_period makes sense, but the results do not always.
When a CPU has one high priority task and a large number of low priority
tasks, __sched_period will return a value larger than sysctl_sched_latency,
and the one high priority task may end up getting a timeslice all for
9 matches
Mail list logo