On Mon, Mar 18, 2019 at 10:14:22AM -0700 bseg...@google.com wrote:
> Phil Auld writes:
>
> > On Fri, Mar 15, 2019 at 05:03:47PM +0100 Peter Zijlstra wrote:
> >> On Fri, Mar 15, 2019 at 11:30:42AM -0400, Phil Auld wrote:
> >>
> >> >> I'll rework the maths in the averaged version and post v2 if
Phil Auld writes:
> On Fri, Mar 15, 2019 at 05:03:47PM +0100 Peter Zijlstra wrote:
>> On Fri, Mar 15, 2019 at 11:30:42AM -0400, Phil Auld wrote:
>>
>> >> I'll rework the maths in the averaged version and post v2 if that makes
>> >> sense.
>> >
>> > It may have the extra timer fetch, although
On Fri, Mar 15, 2019 at 05:03:47PM +0100 Peter Zijlstra wrote:
> On Fri, Mar 15, 2019 at 11:30:42AM -0400, Phil Auld wrote:
>
> >> I'll rework the maths in the averaged version and post v2 if that makes
> >> sense.
> >
> > It may have the extra timer fetch, although maybe I could rework it so
On Fri, Mar 15, 2019 at 09:30:42AM -0400, Phil Auld wrote:
> On Fri, Mar 15, 2019 at 11:11:50AM +0100 Peter Zijlstra wrote:
> > Computers _suck_ at /100. And since you're free to pick the constant,
> > pick a power of two, computers love those.
> >
>
> Fair enough, I was thinking percents. And
On Fri, Mar 15, 2019 at 04:59:33PM +0100 Peter Zijlstra wrote:
> On Fri, Mar 15, 2019 at 09:51:25AM -0400, Phil Auld wrote:
> > On Fri, Mar 15, 2019 at 11:33:57AM +0100 Peter Zijlstra wrote:
> > > On Fri, Mar 15, 2019 at 11:11:50AM +0100, Peter Zijlstra wrote:
> > > > diff --git
On Fri, Mar 15, 2019 at 05:03:47PM +0100 Peter Zijlstra wrote:
> On Fri, Mar 15, 2019 at 11:30:42AM -0400, Phil Auld wrote:
>
> > In my defense here, all the fair.c imbalance pct code also uses 100 :)
>
> Yes, I know, I hate on that too ;-) Just never got around to fixing
> that.
>
>
> > with
On Fri, Mar 15, 2019 at 11:30:42AM -0400, Phil Auld wrote:
> In my defense here, all the fair.c imbalance pct code also uses 100 :)
Yes, I know, I hate on that too ;-) Just never got around to fixing
that.
> with the below:
>
> [ 117.235804] cfs_period_timer[cpu2]: period too short, scaling
On Fri, Mar 15, 2019 at 09:51:25AM -0400, Phil Auld wrote:
> On Fri, Mar 15, 2019 at 11:33:57AM +0100 Peter Zijlstra wrote:
> > On Fri, Mar 15, 2019 at 11:11:50AM +0100, Peter Zijlstra wrote:
> > > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > > index ea74d43924b2..b71557be6b42 100644
On Fri, Mar 15, 2019 at 11:11:50AM +0100 Peter Zijlstra wrote:
> On Wed, Mar 13, 2019 at 11:08:26AM -0400, Phil Auld wrote:
...
> Computers _suck_ at /100. And since you're free to pick the constant,
> pick a power of two, computers love those.
>
> > +
> > + if (new_period >
On Fri, Mar 15, 2019 at 11:33:57AM +0100 Peter Zijlstra wrote:
> On Fri, Mar 15, 2019 at 11:11:50AM +0100, Peter Zijlstra wrote:
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index ea74d43924b2..b71557be6b42 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@
On Fri, Mar 15, 2019 at 11:11:50AM +0100 Peter Zijlstra wrote:
> On Wed, Mar 13, 2019 at 11:08:26AM -0400, Phil Auld wrote:
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index 310d0637fe4b..90cc67bbf592 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@
On Fri, Mar 15, 2019 at 11:11:50AM +0100, Peter Zijlstra wrote:
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index ea74d43924b2..b71557be6b42 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -4885,6 +4885,8 @@ static enum hrtimer_restart
>
On Wed, Mar 13, 2019 at 11:08:26AM -0400, Phil Auld wrote:
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 310d0637fe4b..90cc67bbf592 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -4859,19 +4859,51 @@ static enum hrtimer_restart
>
With extremely short cfs_period_us setting on a parent task group with a large
number of children the for loop in sched_cfs_period_timer can run until the
watchdog fires. There is no guarantee that the call to hrtimer_forward_now()
will ever return 0. The large number of children can make
14 matches
Mail list logo
