Hi Dietmar,
On Thu, Apr 14, 2016 at 01:52:43PM +0100, Dietmar Eggemann wrote:
> On 13/04/16 19:44, Yuyang Du wrote:
> > On Wed, Apr 13, 2016 at 05:28:18PM +0200, Vincent Guittot wrote:
>
> [...]
>
> > By "bailing out", you mean return without update because the delta is less
> > than 1ms?
>
>
Hi Dietmar,
On Thu, Apr 14, 2016 at 01:52:43PM +0100, Dietmar Eggemann wrote:
> On 13/04/16 19:44, Yuyang Du wrote:
> > On Wed, Apr 13, 2016 at 05:28:18PM +0200, Vincent Guittot wrote:
>
> [...]
>
> > By "bailing out", you mean return without update because the delta is less
> > than 1ms?
>
>
On 13/04/16 19:44, Yuyang Du wrote:
> On Wed, Apr 13, 2016 at 05:28:18PM +0200, Vincent Guittot wrote:
[...]
> By "bailing out", you mean return without update because the delta is less
> than 1ms?
yes.
>
>>> Examples of 1 periodic task pinned to a cpu on an ARM64 system, HZ=250
>>> in steady
On 13/04/16 19:44, Yuyang Du wrote:
> On Wed, Apr 13, 2016 at 05:28:18PM +0200, Vincent Guittot wrote:
[...]
> By "bailing out", you mean return without update because the delta is less
> than 1ms?
yes.
>
>>> Examples of 1 periodic task pinned to a cpu on an ARM64 system, HZ=250
>>> in steady
On Wed, Apr 13, 2016 at 05:28:18PM +0200, Vincent Guittot wrote:
> > For a periodic task, the signals really get much more unstable. Even for
> > a steady state (load/util related) periodic task there is a meander
> > pattern which depends on if we for instance hit a dequeue (decay +
> > accrue)
On Wed, Apr 13, 2016 at 05:28:18PM +0200, Vincent Guittot wrote:
> > For a periodic task, the signals really get much more unstable. Even for
> > a steady state (load/util related) periodic task there is a meander
> > pattern which depends on if we for instance hit a dequeue (decay +
> > accrue)
On 13 April 2016 at 17:28, Vincent Guittot wrote:
> On 13 April 2016 at 17:13, Dietmar Eggemann wrote:
>> On 10/04/16 23:36, Yuyang Du wrote:
>>> In __update_load_avg(), the current period is never complete. This
>>> basically leads to a
On 13 April 2016 at 17:28, Vincent Guittot wrote:
> On 13 April 2016 at 17:13, Dietmar Eggemann wrote:
>> On 10/04/16 23:36, Yuyang Du wrote:
>>> In __update_load_avg(), the current period is never complete. This
>>> basically leads to a slightly over-decayed average, say on average we
>>> have
On 13 April 2016 at 17:13, Dietmar Eggemann wrote:
> On 10/04/16 23:36, Yuyang Du wrote:
>> In __update_load_avg(), the current period is never complete. This
>> basically leads to a slightly over-decayed average, say on average we
>> have 50% current period, then we
On 13 April 2016 at 17:13, Dietmar Eggemann wrote:
> On 10/04/16 23:36, Yuyang Du wrote:
>> In __update_load_avg(), the current period is never complete. This
>> basically leads to a slightly over-decayed average, say on average we
>> have 50% current period, then we will lose
On 10/04/16 23:36, Yuyang Du wrote:
> In __update_load_avg(), the current period is never complete. This
> basically leads to a slightly over-decayed average, say on average we
> have 50% current period, then we will lose 1.08%(=(1-0.5^(1/64)) of
> past avg. More importantly, the incomplete
On 10/04/16 23:36, Yuyang Du wrote:
> In __update_load_avg(), the current period is never complete. This
> basically leads to a slightly over-decayed average, say on average we
> have 50% current period, then we will lose 1.08%(=(1-0.5^(1/64)) of
> past avg. More importantly, the incomplete
On 12 April 2016 at 23:09, Yuyang Du wrote:
>
> Hi Vincent,
>
> On Tue, Apr 12, 2016 at 01:56:45PM +0200, Vincent Guittot wrote:
> > Le Tuesday 12 Apr 2016 à 03:41:41 (+0800), Yuyang Du a écrit :
> > > Hi Vincent,
> > >
> > > On Mon, Apr 11, 2016 at 11:08:04AM +0200, Vincent
On 12 April 2016 at 23:09, Yuyang Du wrote:
>
> Hi Vincent,
>
> On Tue, Apr 12, 2016 at 01:56:45PM +0200, Vincent Guittot wrote:
> > Le Tuesday 12 Apr 2016 à 03:41:41 (+0800), Yuyang Du a écrit :
> > > Hi Vincent,
> > >
> > > On Mon, Apr 11, 2016 at 11:08:04AM +0200, Vincent Guittot wrote:
> > >
On Wed, Apr 13, 2016 at 04:14:48AM +0800, Yuyang Du wrote:
> On Tue, Apr 12, 2016 at 01:02:58PM +0100, Dietmar Eggemann wrote:
> > On 10/04/16 23:36, Yuyang Du wrote:
> >
> > [...]
> >
> > > @@ -2704,11 +2694,14 @@ static __always_inline int
> > > __update_load_avg(u64 now, int cpu, struct
On Wed, Apr 13, 2016 at 04:14:48AM +0800, Yuyang Du wrote:
> On Tue, Apr 12, 2016 at 01:02:58PM +0100, Dietmar Eggemann wrote:
> > On 10/04/16 23:36, Yuyang Du wrote:
> >
> > [...]
> >
> > > @@ -2704,11 +2694,14 @@ static __always_inline int
> > > __update_load_avg(u64 now, int cpu, struct
Hi Vincent,
On Tue, Apr 12, 2016 at 01:56:45PM +0200, Vincent Guittot wrote:
> Le Tuesday 12 Apr 2016 à 03:41:41 (+0800), Yuyang Du a écrit :
> > Hi Vincent,
> >
> > On Mon, Apr 11, 2016 at 11:08:04AM +0200, Vincent Guittot wrote:
> > > > @@ -2704,11 +2694,14 @@ static __always_inline int
> > >
Hi Vincent,
On Tue, Apr 12, 2016 at 01:56:45PM +0200, Vincent Guittot wrote:
> Le Tuesday 12 Apr 2016 à 03:41:41 (+0800), Yuyang Du a écrit :
> > Hi Vincent,
> >
> > On Mon, Apr 11, 2016 at 11:08:04AM +0200, Vincent Guittot wrote:
> > > > @@ -2704,11 +2694,14 @@ static __always_inline int
> > >
On Wed, 2016-04-13 at 04:14 +0800, Yuyang Du wrote:
> On Tue, Apr 12, 2016 at 01:02:58PM +0100, Dietmar Eggemann wrote:
> > On 10/04/16 23:36, Yuyang Du wrote:
> > [...]
> > > @@ -2704,11 +2694,14 @@ static __always_inline int
> > > __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
> > >
On Wed, 2016-04-13 at 04:14 +0800, Yuyang Du wrote:
> On Tue, Apr 12, 2016 at 01:02:58PM +0100, Dietmar Eggemann wrote:
> > On 10/04/16 23:36, Yuyang Du wrote:
> > [...]
> > > @@ -2704,11 +2694,14 @@ static __always_inline int
> > > __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
> > >
On Tue, Apr 12, 2016 at 01:02:58PM +0100, Dietmar Eggemann wrote:
> On 10/04/16 23:36, Yuyang Du wrote:
>
> [...]
>
> > @@ -2704,11 +2694,14 @@ static __always_inline int
> > __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
> > unsigned long weight, int running, struct
On Tue, Apr 12, 2016 at 01:02:58PM +0100, Dietmar Eggemann wrote:
> On 10/04/16 23:36, Yuyang Du wrote:
>
> [...]
>
> > @@ -2704,11 +2694,14 @@ static __always_inline int
> > __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
> > unsigned long weight, int running, struct
On 10/04/16 23:36, Yuyang Du wrote:
[...]
> @@ -2704,11 +2694,14 @@ static __always_inline int
> __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
> unsigned long weight, int running, struct cfs_rq *cfs_rq)
> {
> - u64 delta, scaled_delta, periods;
> - u32
On 10/04/16 23:36, Yuyang Du wrote:
[...]
> @@ -2704,11 +2694,14 @@ static __always_inline int
> __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
> unsigned long weight, int running, struct cfs_rq *cfs_rq)
> {
> - u64 delta, scaled_delta, periods;
> - u32
Le Tuesday 12 Apr 2016 à 03:41:41 (+0800), Yuyang Du a écrit :
> Hi Vincent,
>
> On Mon, Apr 11, 2016 at 11:08:04AM +0200, Vincent Guittot wrote:
> > > @@ -2704,11 +2694,14 @@ static __always_inline int
> > > __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
> > >
Le Tuesday 12 Apr 2016 à 03:41:41 (+0800), Yuyang Du a écrit :
> Hi Vincent,
>
> On Mon, Apr 11, 2016 at 11:08:04AM +0200, Vincent Guittot wrote:
> > > @@ -2704,11 +2694,14 @@ static __always_inline int
> > > __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
> > >
Hi Vincent,
On Mon, Apr 11, 2016 at 11:08:04AM +0200, Vincent Guittot wrote:
> > @@ -2704,11 +2694,14 @@ static __always_inline int
> > __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
> > unsigned long weight, int running, struct cfs_rq *cfs_rq)
> > {
> > - u64
Hi Vincent,
On Mon, Apr 11, 2016 at 11:08:04AM +0200, Vincent Guittot wrote:
> > @@ -2704,11 +2694,14 @@ static __always_inline int
> > __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
> > unsigned long weight, int running, struct cfs_rq *cfs_rq)
> > {
> > - u64
Hi Yuyang
On 11 April 2016 at 00:36, Yuyang Du wrote:
> In __update_load_avg(), the current period is never complete. This
> basically leads to a slightly over-decayed average, say on average we
yes, that also explains why we almost never reach the max value
> have 50%
Hi Yuyang
On 11 April 2016 at 00:36, Yuyang Du wrote:
> In __update_load_avg(), the current period is never complete. This
> basically leads to a slightly over-decayed average, say on average we
yes, that also explains why we almost never reach the max value
> have 50% current period, then we
In __update_load_avg(), the current period is never complete. This
basically leads to a slightly over-decayed average, say on average we
have 50% current period, then we will lose 1.08%(=(1-0.5^(1/64)) of
past avg. More importantly, the incomplete current period significantly
complicates the avg
In __update_load_avg(), the current period is never complete. This
basically leads to a slightly over-decayed average, say on average we
have 50% current period, then we will lose 1.08%(=(1-0.5^(1/64)) of
past avg. More importantly, the incomplete current period significantly
complicates the avg
32 matches
Mail list logo