Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 18 October 2016 at 11:07, Peter Zijlstra wrote: > On Mon, Oct 17, 2016 at 11:52:39PM +0100, Dietmar Eggemann wrote: >> >> Something looks weird related to the use of for_each_possible_cpu(i) in >> online_fair_sched_group() on my i5-3320M CPU (4 logical cpus). >> >> In

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 13 October 2016 at 23:34, Vincent Guittot <vincent.guit...@linaro.org> wrote: > On 13 October 2016 at 20:49, Dietmar Eggemann <dietmar.eggem...@arm.com> > wrote: >> On 13/10/16 17:48, Vincent Guittot wrote: >>> On 13 October 2016 at 17:52, Joseph Salisbury &g

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

Le Friday 14 Oct 2016 à 14:10:07 (+0100), Dietmar Eggemann a écrit : > On 14/10/16 09:24, Vincent Guittot wrote: > > On 13 October 2016 at 23:34, Vincent Guittot <vincent.guit...@linaro.org> > > wrote: > >> On 13 October 2016 at 20:49, Dietmar Eggemann <diet

[PATCH 4/6 v5] sched: propagate load during synchronous attach/detach

is greater than its share so it will contribute the same load of a task of equal weight. Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- kernel/sched/fair.c | 200 ++- kernel/sched/sched.h | 1 + 2 files changed, 200 insertions

[PATCH 6/6 v5] sched: fix task group initialization

The moves of tasks are now propagated down to root and the utilization of cfs_rq reflects reality so it doesn't need to be estimated at init. Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff

[PATCH 5/6 v5] sched: propagate asynchrous detach

any pending changes.The propagation relies on patch "sched: fix hierarchical order in rq->leaf_cfs_rq_list", which orders children and parents, to ensure that it's done in one pass. Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- kernel/sched/fair.c | 6 ++

[PATCH 2/6 v5] sched: fix hierarchical order in rq->leaf_cfs_rq_list

s before, and after any potential parents that are already in the list. The easiest way is to put the cfs_rq just after the last inserted one and to keep track of it untl the branch is fully added. Signed-off-by: Vincent Guittot <vincent.guit..

[PATCH 1/6 v5] sched: factorize attach entity

Factorize post_init_entity_util_avg and part of attach_task_cfs_rq in one function attach_entity_cfs_rq Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- kernel/sched/fair.c | 24 +--- 1 file changed, 13 insertions(+), 11 deletions(-) diff --git a/kernel

[PATCH 3/6 v5] sched: factorize PELT update

sched_entity and cfs_rq metrics to now. Use update_load_avg everytime we have to update and sync cfs_rq and sched_entity before changing the state of a sched_enity Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- kernel/sched/fair.

[PATCH 0/6 v5] sched: reflect sched_entity move into task_group's load

sent them as a single patchset because the fix is independent of this one - Merge some functions that are always used together - During update of blocked load, ensure that the sched_entity is synced with the cfs_rq applying changes - Fix an issue when task changes its cpu affinity Vincent Guittot (

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

Le Friday 14 Oct 2016 à 12:04:02 (-0400), Joseph Salisbury a écrit : > On 10/14/2016 11:18 AM, Vincent Guittot wrote: > > Le Friday 14 Oct 2016 à 14:10:07 (+0100), Dietmar Eggemann a écrit : > >> On 14/10/16 09:24, Vincent Guittot wrote: > >>> On 13 October

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

Le Tuesday 18 Oct 2016 à 12:34:12 (+0200), Peter Zijlstra a écrit : > On Tue, Oct 18, 2016 at 11:45:48AM +0200, Vincent Guittot wrote: > > On 18 October 2016 at 11:07, Peter Zijlstra <pet...@infradead.org> wrote: > > > So aside from funny BIOSes, this should al

Re: [PATCH] sched/fair: Do not decay new task load on first enqueue

On 18 October 2016 at 13:09, Peter Zijlstra <pet...@infradead.org> wrote: > On Wed, Oct 12, 2016 at 09:41:36AM +0200, Vincent Guittot wrote: > >> ok. In fact, I have noticed another regression with tip/sched/core and >> hackbench while looking at yours. >> I have bis

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 19 October 2016 at 11:46, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: > On 18/10/16 12:56, Vincent Guittot wrote: >> Le Tuesday 18 Oct 2016 à 12:34:12 (+0200), Peter Zijlstra a écrit : >>> On Tue, Oct 18, 2016 at 11:45:48AM +0200, Vincent Guittot wrote: >>

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 19 October 2016 at 13:33, Peter Zijlstra <pet...@infradead.org> wrote: > On Tue, Oct 18, 2016 at 01:56:51PM +0200, Vincent Guittot wrote: > >> --- >> kernel/sched/fair.c | 9 - >> 1 file changed, 8 insertions(+), 1 deletion(-) >> >> diff

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 19 October 2016 at 16:49, Joseph Salisbury <joseph.salisb...@canonical.com> wrote: > On 10/18/2016 07:56 AM, Vincent Guittot wrote: >> Le Tuesday 18 Oct 2016 à 12:34:12 (+0200), Peter Zijlstra a écrit : >>> On Tue, Oct 18, 2016 at 11:45:48AM +0200, Vincent Guittot wrote:

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 19 October 2016 at 15:30, Morten Rasmussen <morten.rasmus...@arm.com> wrote: > On Tue, Oct 18, 2016 at 01:56:51PM +0200, Vincent Guittot wrote: >> Le Tuesday 18 Oct 2016 à 12:34:12 (+0200), Peter Zijlstra a écrit : >> > On Tue, Oct 18, 2016 at 11:45:48AM +020

[PATCH] sched: fix wrong task group's load_avg

ed to something else than 0 because their load will increase when entity will be attached. Fixes: 3d30544f0212 ("sched/fair: Apply more PELT fixes) Reported-by: Joseph Salisbury <joseph.salisb...@canonical.com> Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org>

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 19 October 2016 at 17:33, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: > On 19/10/16 12:25, Vincent Guittot wrote: >> On 19 October 2016 at 11:46, Dietmar Eggemann <dietmar.eggem...@arm.com> >> wrote: >>> On 18/10/16 12:56, Vincent Guittot wrote: &g

[PATCH 1/2 v2] sched: fix find_idlest_group for fork

ched_domain_span(sd), target, wrap) { Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- kernel/sched/fair.c | 6 ++ 1 file changed, 6 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index aa47589..820a787 100644 --- a/kernel/sched/fair.c +++ b/kernel/sc

[PATCH 2/2 v2] sched: use load_avg for selecting idlest group

057 0.057(0%) 0.057(0%) 0,055(+5%) max0.066 0.068 0.070 0,063 stdev +/-9% +/-9% +/-8% +/-9% Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- Changes since v2: - Rebase on latest sched/core - Get same results with the rebase an

[PATCH 0/2 v2] sched: improve spread of tasks during fork

/2016/10/18/206 Vincent Guittot (2): sched: fix find_idlest_group for fork sched: use load_avg for selecting idlest group kernel/sched/fair.c | 54 +++-- 1 file changed, 44 insertions(+), 10 deletions(-) -- 2.7.4

Re: [PATCH 1/2] PM / Domains: Introduce domain-performance-state binding

On 23 November 2016 at 16:51, Kevin Hilman <khil...@baylibre.com> wrote: > Vincent Guittot <vincent.guit...@linaro.org> writes: > >> On 22 November 2016 at 19:12, Kevin Hilman <khil...@baylibre.com> wrote: >>> Viresh Kumar <viresh.ku...@linaro.org> wri

Re: [PATCH 0/6 v6] sched: reflect sched_entity move into task_group's load

> > >> > [1] http://www.96boards.org/product/hikey >> > [2] https://play.google.com/store/apps/details?id=com.quicinc.vellamo >> > >> > >> >> From: Vincent Guittot <vincent.guit...@linaro.org> >> >> Date: Tue, Nov 8, 2016 at 12:26 AM

Re: [PATCH] cpufreq: schedutil: add up/down frequency transition rate limits

On 21 November 2016 at 15:37, Juri Lelli wrote: > On 21/11/16 15:17, Peter Zijlstra wrote: >> On Mon, Nov 21, 2016 at 01:53:08PM +, Juri Lelli wrote: >> > On 21/11/16 13:26, Peter Zijlstra wrote: >> >> > > So the limited decay would be the dominant factor in ramp-up time,

Re: [PATCH 1/2 v2] sched: fix find_idlest_group for fork

On 28 November 2016 at 18:01, Matt Fleming <m...@codeblueprint.co.uk> wrote: > On Fri, 25 Nov, at 04:34:32PM, Vincent Guittot wrote: >> >> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c >> index aa47589..820a787 100644 >> --- a/kernel/sched/fa

Re: [PATCH 0/2 v2] sched: improve spread of tasks during fork

On 28 November 2016 at 18:02, Matt Fleming <m...@codeblueprint.co.uk> wrote: > On Fri, 25 Nov, at 04:34:31PM, Vincent Guittot wrote: >> This patchset was originally 1 patch but a perf regression happened during >> the rebase. >> The patch 01 fixes the perf regression d

Re: [PATCH 1/2] PM / Domains: Introduce domain-performance-state binding

On 22 November 2016 at 19:12, Kevin Hilman wrote: > Viresh Kumar writes: > >> On 21-11-16, 09:07, Rob Herring wrote: >>> On Fri, Nov 18, 2016 at 02:53:12PM +0530, Viresh Kumar wrote: >>> > Some platforms have the capability to configure the

Re: [PATCH 0/6 v7] sched: reflect sched_entity move into task_group's load

On 10 November 2016 at 18:04, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: > On 08/11/16 09:53, Vincent Guittot wrote: >> Ensure that the move of a sched_entity will be reflected in load and >> utilization of the task_group hierarchy. >> >> When a sched_en

Re: [PATCH v2 2/2] arm64: dts: hi6220: add resets property into dwmmc nodes

Hi, My hikey board failed to detect and mount sdcard with v4.9-rc1 and i have bisected the issue to this patch. Once reverted, the sdcard is detected again. Regards, Vincent On 25 August 2016 at 05:00, Guodong Xu wrote: > Add resets property into dwmmc_0, dwmmc_1 and

Re: [PATCH 4/6 v5] sched: propagate load during synchronous attach/detach

On 21 October 2016 at 14:19, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: > > On 10/17/2016 10:14 AM, Vincent Guittot wrote: >> >> When a task moves from/to a cfs_rq, we set a flag which is then used to >> propagate the change at parent level (sched_entity and

Re: [PATCH 4/6 v5] sched: propagate load during synchronous attach/detach

On 26 October 2016 at 13:16, Peter Zijlstra <pet...@infradead.org> wrote: > On Wed, Oct 26, 2016 at 09:05:49AM +0200, Vincent Guittot wrote: >> > >> > The 'detach across' and 'attach across' in detach_task_cfs_rq() and >> > attach_entity_cfs_rq() do

Re: [PATCH 3/6 v5] sched: factorize PELT update

On 26 October 2016 at 13:41, Peter Zijlstra <pet...@infradead.org> wrote: > On Mon, Oct 17, 2016 at 11:14:10AM +0200, Vincent Guittot wrote: >> @@ -3110,11 +3116,12 @@ static inline void update_load_avg(struct >> sched_entity *se, int update_tg) >>* Track tas

Re: [PATCH 4/6 v5] sched: propagate load during synchronous attach/detach

On 26 October 2016 at 12:54, Peter Zijlstra <pet...@infradead.org> wrote: > On Mon, Oct 17, 2016 at 11:14:11AM +0200, Vincent Guittot wrote: >> /* >> + * Signed add and clamp on underflow. >> + * >> + * Explicitly do a load-store to ensure the intermedia

Re: [PATCH] sched/fair: Do not decay new task load on first enqueue

On 11 October 2016 at 12:24, Matt Fleming <m...@codeblueprint.co.uk> wrote: > On Mon, 10 Oct, at 07:34:40PM, Vincent Guittot wrote: >> >> Subject: [PATCH] sched: use load_avg for selecting idlest group >> >> select_busiest_group only compares the runnable_load_a

Re: [PATCH 1/7 v4] sched: factorize attach entity

On 7 October 2016 at 01:11, Vincent Guittot <vincent.guit...@linaro.org> wrote: > > On 5 October 2016 at 11:38, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: > > On 09/26/2016 01:19 PM, Vincent Guittot wrote: > >> > >> Factorize post_init_enti

Re: [PATCH] sched/fair: Do not decay new task load on first enqueue

On 11 October 2016 at 20:57, Matt Fleming <m...@codeblueprint.co.uk> wrote: > On Tue, 11 Oct, at 03:14:47PM, Vincent Guittot wrote: >> > >> > I see a regression, >> > >> > baseline: 2.41228 >> > patched : 2.64528 (-9.7%) >>

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 13 October 2016 at 17:52, Joseph Salisbury <joseph.salisb...@canonical.com> wrote: > On 10/13/2016 06:58 AM, Vincent Guittot wrote: >> Hi, >> >> On 12 October 2016 at 18:21, Joseph Salisbury >> <joseph.salisb...@canonical.com> wrote: >>> On 10/12

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 13 October 2016 at 20:49, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: > On 13/10/16 17:48, Vincent Guittot wrote: >> On 13 October 2016 at 17:52, Joseph Salisbury >> <joseph.salisb...@canonical.com> wrote: >>> On 10/13/2016 06:58 AM, Vincent Gui

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 8 October 2016 at 13:49, Mike Galbraith <efa...@gmx.de> wrote: > On Sat, 2016-10-08 at 13:37 +0200, Vincent Guittot wrote: >> On 8 October 2016 at 10:39, Ingo Molnar <mi...@kernel.org> wrote: >> > >> > * Peter Zijlstra <pet...@infradead.org> wrote: &

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

Hi, On 12 October 2016 at 18:21, Joseph Salisbury <joseph.salisb...@canonical.com> wrote: > On 10/12/2016 08:20 AM, Vincent Guittot wrote: >> On 8 October 2016 at 13:49, Mike Galbraith <efa...@gmx.de> wrote: >>> On Sat, 2016-10-08 at 13:37 +0200, Vincent Guittot

Re: [PATCH 5/7 v4] sched: propagate asynchrous detach

On 12 October 2016 at 17:03, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: > On 26/09/16 13:19, Vincent Guittot wrote: >> A task can be asynchronously detached from cfs_rq when migrating >> between CPUs. The load of the migrated task is then removed from >> so

Re: [v4.8-rc1 Regression] sched/fair: Apply more PELT fixes

On 17 October 2016 at 15:19, Peter Zijlstra wrote: > On Mon, Oct 17, 2016 at 12:49:55PM +0100, Dietmar Eggemann wrote: > >> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c >> > index 8b03fb5..8926685 100644 >> > --- a/kernel/sched/fair.c >> > +++

Re: [PATCH 2/2 v2] sched: use load_avg for selecting idlest group

On 8 December 2016 at 15:09, Matt Fleming <m...@codeblueprint.co.uk> wrote: > On Mon, 05 Dec, at 01:35:46PM, Matt Fleming wrote: >> On Mon, 05 Dec, at 10:27:36AM, Vincent Guittot wrote: >> > >> > Hi Matt, >> > >> > Thanks for the results. &

[PATCH 0/2 v3] sched: improve spread of tasks during fork

comparing runnable_load [1] https://lkml.org/lkml/2016/10/18/206 [2] https://lkml.org/lkml/2016/12/8/260 [3] https://lkml.org/lkml/2016/12/8/260 Vincent Guittot (2): sched: fix find_idlest_group for fork sched: use load_avg for selecting idlest group kernel/sched/fair.c | 54

[PATCH 2/2 v3] sched: use load_avg for selecting idlest group

/-9% +/-9% +/-8% +/-9% Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- kernel/sched/fair.c | 48 ++-- 1 file changed, 38 insertions(+), 10 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c inde

[PATCH 1/2 v3] sched: fix find_idlest_group for fork

d_domain_span(sd), target, wrap) { Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> Acked-by: Morten Rasmussen <morten.rasmus...@arm.com> --- kernel/sched/fair.c | 6 ++ 1 file changed, 6 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 92cb50d.

Re: [PATCH 2/2 v3] sched: use load_avg for selecting idlest group

On 9 December 2016 at 16:22, Peter Zijlstra <pet...@infradead.org> wrote: > On Thu, Dec 08, 2016 at 05:56:54PM +0100, Vincent Guittot wrote: >> @@ -5449,14 +5456,32 @@ find_idlest_group(struct sched_domain *sd, struct >> task_struct *p, >> } >> >&

Re: [PATCH] sched: fix group_entity's share update

Gentle ping ... Vincent On 1 December 2016 at 17:38, Vincent Guittot <vincent.guit...@linaro.org> wrote: > The update of the share of a cfs_rq is done when its load_avg is updated > but before the group_entity's load_avg has been updated for the past time > slot. This generates

Re: [PATCH] sched: fix group_entity's share update

On 15 December 2016 at 22:42, Peter Zijlstra <pet...@infradead.org> wrote: > > On Thu, Dec 01, 2016 at 05:38:53PM +0100, Vincent Guittot wrote: > > The update of the share of a cfs_rq is done when its load_avg is updated > > but before the group_entity's load_avg has been u

Re: [lkp-developer] [sched/fair] 4e5160766f: +149% ftq.noise.50% regression

Hi Ying, On 12 December 2016 at 06:43, kernel test robot wrote: > Greeting, > > FYI, we noticed a 149% regression of ftq.noise.50% due to commit: > > > commit: 4e5160766fcc9f41bbd38bac11f92dce993644aa ("sched/fair: Propagate > asynchrous detach") >

[PATCH] sched: fix group_entity's share update

ntity is updated only once its load_avg has been synced with current time. Cc: <sta...@vger.kernel.org> Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- I have seen the problem on tip/sched/core, v4.8 and v4.7. Previous versions might also have the problem but I haven'

Re: [PATCH 1/2 v2] sched: fix find_idlest_group for fork

On 29 November 2016 at 11:57, Morten Rasmussen <morten.rasmus...@arm.com> wrote: > On Fri, Nov 25, 2016 at 04:34:32PM +0100, Vincent Guittot wrote: >> During fork, the utilization of a task is init once the rq has been >> selected because the current utilization level of

Re: [PATCH 1/2 v2] sched: fix find_idlest_group for fork

On 29 November 2016 at 15:50, Morten Rasmussen <morten.rasmus...@arm.com> wrote: > On Tue, Nov 29, 2016 at 02:04:27PM +0100, Vincent Guittot wrote: >> On 29 November 2016 at 11:57, Morten Rasmussen <morten.rasmus...@arm.com> >> wrote: >> > On Fri, Nov 25, 2016

Re: [PATCH 1/2 v2] sched: fix find_idlest_group for fork

On 4 December 2016 at 00:25, Matt Fleming <m...@codeblueprint.co.uk> wrote: > On Fri, 25 Nov, at 04:34:32PM, Vincent Guittot wrote: >> During fork, the utilization of a task is init once the rq has been >> selected because the current utilization level of the rq is used to s

Re: [PATCH 2/2 v2] sched: use load_avg for selecting idlest group

Le Saturday 03 Dec 2016 à 21:47:07 (+), Matt Fleming a écrit : > On Fri, 02 Dec, at 07:31:04PM, Brendan Gregg wrote: > > > > For background, is this from the "A decade of wasted cores" paper's > > patches? > > No, this patch fixes an issue I originally reported here, > >

Re: [PATCH 2/2 v2] sched: use load_avg for selecting idlest group

On 30 November 2016 at 13:49, Morten Rasmussen <morten.rasmus...@arm.com> wrote: > On Fri, Nov 25, 2016 at 04:34:33PM +0100, Vincent Guittot wrote: >> find_idlest_group() only compares the runnable_load_avg when looking for >> the least loaded group. But on fork intensive us

Re: [PATCH 2/2 v2] sched: use load_avg for selecting idlest group

On 30 November 2016 at 14:49, Vincent Guittot <vincent.guit...@linaro.org> wrote: > On 30 November 2016 at 13:49, Morten Rasmussen <morten.rasmus...@arm.com> > wrote: >> On Fri, Nov 25, 2016 at 04:34:33PM +0100, Vincent Guittot wrote: >>> find_idlest_group() on

Re: [PATCH 2/2 v2] sched: use load_avg for selecting idlest group

On 30 November 2016 at 15:24, Morten Rasmussen <morten.rasmus...@arm.com> wrote: > On Wed, Nov 30, 2016 at 02:54:00PM +0100, Vincent Guittot wrote: >> On 30 November 2016 at 14:49, Vincent Guittot >> <vincent.guit...@linaro.org> wrote: >> > On 30 Nove

Re: [LKP] [lkp-developer] [sched/fair] 4e5160766f: +149% ftq.noise.50% regression

Hi Dietmar and Ying, Le Tuesday 03 Jan 2017 à 11:38:39 (+0100), Dietmar Eggemann a écrit : > Hi Vincent and Ying, > > On 01/02/2017 04:42 PM, Vincent Guittot wrote: > >Hi Ying, > > > >On 28 December 2016 at 09:17, Huang, Ying <ying.hu...@intel.com> wrote:

Re: [lkp-developer] [sched/core] 6b94780e45: unixbench.score -4.5% regression

ong...@intel.com> wrote: > On 01/02, Vincent Guittot wrote: >>Hi Xiaolong, >> >>Le Monday 19 Dec 2016 ŕ 08:14:53 (+0800), kernel test robot a écrit : >>> >>> Greeting, >>> >>> FYI, we noticed a -4.5% regression of unixbench.score due to comm

Re: [LKP] [lkp-developer] [sched/fair] 4e5160766f: +149% ftq.noise.50% regression

On 4 January 2017 at 04:08, Huang, Ying <ying.hu...@intel.com> wrote: > Vincent Guittot <vincent.guit...@linaro.org> writes: > >>> >>> Vincent, like we discussed in September last year, the proper fix would >>> probably be a cfs-rq->nr_attached

Re: [LKP] [lkp-developer] [sched/fair] 4e5160766f: +149% ftq.noise.50% regression

Hi Ying, On 28 December 2016 at 09:17, Huang, Ying <ying.hu...@intel.com> wrote: > Vincent Guittot <vincent.guit...@linaro.org> writes: > >> Le Tuesday 13 Dec 2016 . 09:47:30 (+0800), Huang, Ying a .crit : >>> Hi, Vincent, >>> >>> Vincent Guitto

Re: [lkp-developer] [sched/core] 6b94780e45: unixbench.score -4.5% regression

Hi Xiaolong, Le Monday 19 Dec 2016 à 08:14:53 (+0800), kernel test robot a écrit : > > Greeting, > > FYI, we noticed a -4.5% regression of unixbench.score due to commit: I have been able to restore performance on my platform with the patch below. Could you test it ? --- kernel/sched/core.c |

Re: [PATCH v2] sched: fix group_entity's share update

On 4 January 2017 at 18:20, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: > On 21/12/16 15:50, Vincent Guittot wrote: > > IMHO, the overall idea makes sense to me. Just a couple of small > questions ... > >> The update of the share of a cfs_rq is done w

Re: [PATCH] sched: fix group_entity's share update

On 16 December 2016 at 09:55, Vincent Guittot <vincent.guit...@linaro.org> wrote: > On 15 December 2016 at 22:42, Peter Zijlstra <pet...@infradead.org> wrote: >> >> On Thu, Dec 01, 2016 at 05:38:53PM +0100, Vincent Guittot wrote: >> > The update of the share o

[PATCH v2] sched: fix group_entity's share update

the cfs_rq and the weight of the group_entity is updated only once its load_avg has been synced with current time. Cc: <sta...@vger.kernel.org> #v4.4+ Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- kernel/sched/fair.c | 53 +++

Re: [LKP] [lkp-developer] [sched/fair] 4e5160766f: +149% ftq.noise.50% regression

Le Tuesday 13 Dec 2016 à 09:47:30 (+0800), Huang, Ying a écrit : > Hi, Vincent, > > Vincent Guittot <vincent.guit...@linaro.org> writes: > > > Hi Ying, > > > > On 12 December 2016 at 06:43, kernel test robot > > <ying.hu...@linux.intel.com> wrote

Re: [RFC][PATCH 2/2] cpufreq: schedutil: Force max frequency on busy CPUs

On 23 March 2017 at 00:56, Joel Fernandes <joe...@google.com> wrote: > On Mon, Mar 20, 2017 at 5:34 AM, Patrick Bellasi > <patrick.bell...@arm.com> wrote: >> On 20-Mar 09:26, Vincent Guittot wrote: >>> On 20 March 2017 at 04:57, Viresh Kumar <viresh.ku...@lina

Re: [PATCH] sched: Prefer sibiling only if local group is under-utilized

gt; more threads, like in Power 8, smt 8 mode. > > Fix this by only allowing local group to pull a task, if the source group > has more number of tasks than the local group. > > Signed-off-by: Srikar Dronamraju <sri...@linux.vnet.ibm.com> Acked-by: Vincent Guittot <vincent.gui

Re: [RFC][PATCH v2 2/2] cpufreq: schedutil: Avoid decreasing frequency of busy CPUs

On 21 March 2017 at 15:58, Peter Zijlstra <pet...@infradead.org> wrote: > > On Tue, Mar 21, 2017 at 03:16:19PM +0100, Vincent Guittot wrote: > > On 21 March 2017 at 15:03, Peter Zijlstra <pet...@infradead.org> wrote: > > > > > On Tue, Mar 21, 2017 at

Re: [PATCH] sched/fair: Fix ftq noise bench regression

On 22 March 2017 at 17:22, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: > On 22/03/17 09:22, Vincent Guittot wrote: >> On 21 March 2017 at 18:46, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: >>> Hi Vincent, >>> >&

Re: [RFC PATCH 0/5] CFS load tracking trace events

On 28 March 2017 at 08:35, Dietmar Eggemann wrote: > This patch-set introduces trace events for load (and utilization) > tracking for the following three cfs scheduler bricks: cfs_rq, > sched_entity and task_group. > > I've decided to sent it out because people are

Re: [RFD PATCH 3/5] sched/cpufreq_schedutil: make worker kthread be SCHED_DEADLINE

On 27 March 2017 at 18:50, Peter Zijlstra wrote: > On Fri, Mar 24, 2017 at 02:08:58PM +, Juri Lelli wrote: >> Worker kthread needs to be able to change frequency for all other >> threads. >> >> Make it special, just under STOP class. > > *yuck* ;-) > > So imagine our

[PATCH] sched/fair: update scale invariance of PELT

tilization, decreases from 223ms with current scale invariance down to 121ms with the new algorithm. For this test, i have enable arch_scale_freq for arm64. Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- include/linux/sched.h | 1 + kernel/sched/fair.c | 49

Re: [RFC][PATCH v3 2/2] cpufreq: schedutil: Avoid reducing frequency of busy CPUs prematurely

On 25 March 2017 at 02:14, Sai Gurrappadi wrote: > Hi Rafael, > > On 03/21/2017 04:08 PM, Rafael J. Wysocki wrote: >> From: Rafael J. Wysocki >> >> The way the schedutil governor uses the PELT metric causes it to >> underestimate the CPU

Re: [RFC][PATCH 2/2] cpufreq: schedutil: Force max frequency on busy CPUs

On 25 March 2017 at 04:48, Joel Fernandes <joe...@google.com> wrote: > Hi Vincent, > > On Thu, Mar 23, 2017 at 3:08 PM, Vincent Guittot > <vincent.guit...@linaro.org> wrote: > [..] >>>> >>>>> So I'm not really aligned with the description of y

Re: [RFD PATCH 4/5] sched/cpufreq_schedutil: always consider all CPUs when deciding next freq

On 30 March 2017 at 10:58, Juri Lelli wrote: > Hi, > > On 30/03/17 00:41, Rafael J. Wysocki wrote: >> On Friday, March 24, 2017 02:08:59 PM Juri Lelli wrote: >> > No assumption can be made upon the rate at which frequency updates get >> > triggered, as there are scheduling

Re: [PATCH v3 3/9] arm: fix return value of parse_cpu_capacity

On 27 March 2017 at 15:18, Juri Lelli wrote: > parse_cpu_capacity() has to return 0 on failure, but it currently returns > 1 instead if raw_capacity kcalloc failed. > > Fix it by removing the negation of the return value. > > Cc: Russell King >

Re: [PATCH v3 4/9] arm: remove wrong CONFIG_PROC_SYSCTL ifdef

ested-by: Sudeep Holla <sudeep.ho...@arm.com> > Fixes: 7e5930aaef5d ('ARM: 8622/3: add sysfs cpu_capacity attribute') > Signed-off-by: Juri Lelli <juri.le...@arm.com> Acked-by: Vincent Guittot <vincent.guit...@linaro.org> > --- > arch/arm/kernel/topology.c | 2 -- >

Re: [PATCH] sched/fair: update scale invariance of PELT

On 28 March 2017 at 17:35, Vincent Guittot <vincent.guit...@linaro.org> wrote: > The current implementation of load tracking invariance scales the contribution > with current frequency and uarch performance (only for utilization) of the > CPU. One main result of this formula is t

Re: [RFC][PATCH 2/2] cpufreq: schedutil: Force max frequency on busy CPUs

On 20 March 2017 at 04:57, Viresh Kumar wrote: > On 19-03-17, 14:34, Rafael J. Wysocki wrote: >> From: Rafael J. Wysocki >> >> The PELT metric used by the schedutil governor underestimates the >> CPU utilization in some cases. The reason for

Re: [RFC][PATCH v2 2/2] cpufreq: schedutil: Avoid decreasing frequency of busy CPUs

On 20 March 2017 at 22:46, Rafael J. Wysocki wrote: > From: Rafael J. Wysocki > > The way the schedutil governor uses the PELT metric causes it to > underestimate the CPU utilization in some cases. > > That can be easily demonstrated by running

Re: [RFC][PATCH v2 2/2] cpufreq: schedutil: Avoid decreasing frequency of busy CPUs

On 21 March 2017 at 14:22, Peter Zijlstra <pet...@infradead.org> wrote: > On Tue, Mar 21, 2017 at 09:50:28AM +0100, Vincent Guittot wrote: >> On 20 March 2017 at 22:46, Rafael J. Wysocki <r...@rjwysocki.net> wrote: > >> > To work around this issue use the observat

Re: [RFC][PATCH 2/2] cpufreq: schedutil: Force max frequency on busy CPUs

On 20 March 2017 at 13:59, Rafael J. Wysocki <r...@rjwysocki.net> wrote: > On Monday, March 20, 2017 09:26:34 AM Vincent Guittot wrote: >> On 20 March 2017 at 04:57, Viresh Kumar <viresh.ku...@linaro.org> wrote: >> > On 19-03-17, 14:34, Rafael J. Wysocki wrote:

[PATCH] sched/fair: Fix ftq noise bench regression

agressive optimization has been tried but has shown worse score. Reported-by: ying.hu...@linux.intel.com Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> Fixes: 4e5160766fcc ("sched/fair: Propagate asynchrous detach") --- kernel/sched/fair.c | 39 +

Re: [RFC][PATCH v2 2/2] cpufreq: schedutil: Avoid decreasing frequency of busy CPUs

On 21 March 2017 at 15:03, Peter Zijlstra <pet...@infradead.org> wrote: > On Tue, Mar 21, 2017 at 02:37:08PM +0100, Vincent Guittot wrote: >> On 21 March 2017 at 14:22, Peter Zijlstra <pet...@infradead.org> wrote: > >> For the not overloaded case, it makes sense t

Re: [PATCH] sched/fair: Fix ftq noise bench regression

On 21 March 2017 at 18:46, Dietmar Eggemann <dietmar.eggem...@arm.com> wrote: > Hi Vincent, > > On 17/03/17 13:47, Vincent Guittot wrote: > > [...] > >> Reported-by: ying.hu...@linux.intel.com >> Signed-off-by: Vincent Guittot <vincent.guit...@linaro.o

Re: [PATCH v2] sched/fair: update scale invariance of PELT

Le Wednesday 12 Apr 2017 à 13:28:58 (+0200), Peter Zijlstra a écrit : > On Tue, Apr 11, 2017 at 03:09:20PM +0200, Vincent Guittot wrote: > > Le Tuesday 11 Apr 2017 à 12:49:49 (+0200), Peter Zijlstra a écrit : > > > > > > Lets go back to the unscaled version: >

[PATCH v2] sched/fair: update scale invariance of PELT

tilization, decreases from 223ms with current scale invariance down to 121ms with the new algorithm. For this test, i have enable arch_scale_freq for arm64. Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> --- Update since v1: - rebase on latest tip/sched/core which includes "Opt

Re: [PATCH v2] sched/fair: update scale invariance of PELT

Le Monday 10 Apr 2017 à 19:38:02 (+0200), Peter Zijlstra a écrit : > > Thanks for the rebase. > > On Mon, Apr 10, 2017 at 11:18:29AM +0200, Vincent Guittot wrote: > > Ok, so let me try and paraphrase what this patch does. > > So consider a task that runs 1

Re: [PATCH v2] sched/fair: update scale invariance of PELT

On 11 April 2017 at 11:12, Peter Zijlstra <pet...@infradead.org> wrote: > On Tue, Apr 11, 2017 at 09:52:21AM +0200, Vincent Guittot wrote: > >> > > + } else if (!weight) { >> > > + if (sa->util_sum < (LOAD_AVG_MAX * 1000)) { >> > &

Re: [PATCH v2] sched/fair: update scale invariance of PELT

Le Tuesday 11 Apr 2017 à 12:41:36 (+0200), Peter Zijlstra a écrit : > On Tue, Apr 11, 2017 at 11:40:21AM +0200, Vincent Guittot wrote: > > Le Tuesday 11 Apr 2017 à 10:53:05 (+0200), Peter Zijlstra a écrit : > > > On Tue, Apr 11, 2017 at 09:52:21AM +0200, Vincent Guittot wrote: &g

Re: [PATCH v2] sched/fair: update scale invariance of PELT

Le Tuesday 11 Apr 2017 à 10:53:05 (+0200), Peter Zijlstra a écrit : > On Tue, Apr 11, 2017 at 09:52:21AM +0200, Vincent Guittot wrote: > > Le Monday 10 Apr 2017 à 19:38:02 (+0200), Peter Zijlstra a écrit : > > > > > > Thanks for the rebase. > > > > >

Re: [PATCH v2] sched/fair: update scale invariance of PELT

Le Tuesday 11 Apr 2017 à 12:49:49 (+0200), Peter Zijlstra a écrit : > > Lets go back to the unscaled version: > > running idle >|*|-| > > With the current code, that would effectively end up like (again > assuming 50%): > > running idle >

Re: [PATCH v2] sched/fair: update scale invariance of PELT

On 12 April 2017 at 17:44, Peter Zijlstra <pet...@infradead.org> wrote: > On Wed, Apr 12, 2017 at 04:50:47PM +0200, Vincent Guittot wrote: >> Le Wednesday 12 Apr 2017 à 13:28:58 (+0200), Peter Zijlstra a écrit : > >> > >> > |

Re: [PATCH v2] sched/fair: update scale invariance of PELT

On 13 April 2017 at 20:06, Peter Zijlstra <pet...@infradead.org> wrote: > On Thu, Apr 13, 2017 at 04:59:15PM +0200, Vincent Guittot wrote: >> On 13 April 2017 at 15:32, Peter Zijlstra <pet...@infradead.org> wrote: >> > On Wed, Apr 12, 2017 at 01:28:58PM +0200, Pete

Re: [PATCH v2] sched/fair: update scale invariance of PELT

On 13 April 2017 at 18:13, Peter Zijlstra <pet...@infradead.org> wrote: > On Thu, Apr 13, 2017 at 05:16:20PM +0200, Vincent Guittot wrote: >> On 13 April 2017 at 15:39, Peter Zijlstra <pet...@infradead.org> wrote: > >> > OK, so the reason util_avg varies is b

Re: [PATCH v2] sched/fair: update scale invariance of PELT

On 13 April 2017 at 15:32, Peter Zijlstra wrote: > On Wed, Apr 12, 2017 at 01:28:58PM +0200, Peter Zijlstra wrote: > >> I still wonder about the whole !running vs !weight thing., > > Ah, since we use this for both util _and_ load, we need !running && > !weight, and it so

Re: [PATCH v2] sched/fair: update scale invariance of PELT

On 13 April 2017 at 15:39, Peter Zijlstra <pet...@infradead.org> wrote: > On Tue, Apr 11, 2017 at 09:52:21AM +0200, Vincent Guittot wrote: > >> > Secondly, what's up with the util_sum < LOAD_AVG_MAX * 1000 thing? >> >> The lost idle time makes sense only if

<    5   6   7   8   9   10   11   12   13   14   >