Re: [RFC/RFT][PATCH 1/2] cpufreq: schedutil: Use policy-dependent latency multupliers

Hi Rafael, On Mon, Apr 10 2017 at 00:10, Rafael J. Wysocki wrote: > From: Rafael J. Wysocki > > Make the schedutil governor compute the initial (default) value of > the rate_limit_us sysfs attribute by multiplying the transition > latency by a multiplier depending on

Re: [RFC/RFT][PATCH 1/2] cpufreq: schedutil: Use policy-dependent transition delays

Hi Rafael, On Fri, Apr 14 2017 at 22:51, Rafael J. Wysocki wrote: > On Tuesday, April 11, 2017 12:20:41 AM Rafael J. Wysocki wrote: >> From: Rafael J. Wysocki >> >> Make the schedutil governor take the initial (default) value of the >> rate_limit_us sysfs attribute

Re: [PATCH] sched/fair: Sync task util before slow-path wakeup

On Wed, Aug 02 2017 at 13:24, Peter Zijlstra wrote: > On Wed, Aug 02, 2017 at 02:10:02PM +0100, Brendan Jackman wrote: >> We use task_util in find_idlest_group via capacity_spare_wake. This >> task_util is updated in wake_cap. However wake_cap is not the only >>

Re: wake_wide mechanism clarification

Hi, On Fri, Jun 30 2017 at 17:55, Josef Bacik wrote: > On Fri, Jun 30, 2017 at 07:02:20PM +0200, Mike Galbraith wrote: >> On Fri, 2017-06-30 at 10:28 -0400, Josef Bacik wrote: >> > On Thu, Jun 29, 2017 at 08:04:59PM -0700, Joel Fernandes wrote: >> > >> > > That makes sense that we multiply

Re: wake_wide mechanism clarification

On Thu, Aug 03 2017 at 13:15, Josef Bacik wrote: > On Thu, Aug 03, 2017 at 11:53:19AM +0100, Brendan Jackman wrote: >> >> Hi, >> >> On Fri, Jun 30 2017 at 17:55, Josef Bacik wrote: >> > On Fri, Jun 30, 2017 at 07:02:20PM +0200, Mike Galbraith wrote: >> &

[RFC] sched/fair: Use wake_q length as a hint for wake_wide

have relatively few CPUs, which suggests the trade-off makes sense here. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Ingo Molnar <mi...@redhat.com> Cc: Peter Zijlstra <pet...@infradead.org> Cc: Josef Bacik <jo...@toxicpanda.com> Cc: Joel Fernandes

Re: wake_wide mechanism clarification

On Wed, Aug 09 2017 at 21:22, Atish Patra wrote: > On 08/03/2017 10:05 AM, Brendan Jackman wrote: >> >> On Thu, Aug 03 2017 at 13:15, Josef Bacik wrote: >>> On Thu, Aug 03, 2017 at 11:53:19AM +0100, Brendan Jackman wrote: >>>> >>>> Hi, >>&

[PATCH] sched/fair: Sync task util before slow-path wakeup

cing, we won't need the task_util and we'd just clobber the last_update_time, which is supposed to be 0. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit...@linaro.org> Cc: Josef Bacik <jo...

Re: [PATCH 7/7] sched/fair: don't wake affine recently load balanced tasks

Hi Josef, I happened to be thinking about something like this while investigating a totally different issue with ARM big.LITTLE. Comment below... On Fri, Jul 14 2017 at 13:21, Josef Bacik wrote: > From: Josef Bacik > > The wake affinity logic will move tasks between two cpu's

[PATCH v2] sched/fair: Sync task util before slow-path wakeup

cing, we won't need the task_util and we'd just clobber the last_update_time, which is supposed to be 0. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit...@linaro.org> Cc: Josef Bacik <jo...

[PATCH] sched/fair: Force balancing on nohz balance if local group has capacity

the force_balance case means there's an upper bound on the time before we can attempt to solve the underutilization: after DIE's sd->balance_interval has passed the next nohz balance kick will help us out. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Ingo Molnar <mi...@re

Re: [PATCH] cpufreq: dt: Set default policy->transition_delay_ns

Hi Viresh, On Mon, May 22 2017 at 05:10, Viresh Kumar wrote: > The rate_limit_us for the schedutil governor is getting set to 500 ms by > default for the ARM64 hikey board. And its way too much, even for the > default value. Lets set the default transition_delay_ns to something > more realistic

Re: [RFC] sched/fair: Use wake_q length as a hint for wake_wide

On Mon, Sep 18 2017 at 22:15, Joel Fernandes wrote: > Hi Brendan, Hi Joel, Thanks for taking a look :) > On Fri, Aug 11, 2017 at 2:45 AM, Brendan Jackman > <brendan.jack...@arm.com> wrote: >> This patch adds a parameter to select_task_rq, sibling_count_hint >> allowi

Re: [RFC] sched/fair: Use wake_q length as a hint for wake_wide

On Wed, Sep 20 2017 at 05:06, Joel Fernandes wrote: >> On Tue, Sep 19, 2017 at 3:05 AM, Brendan Jackman >> <brendan.jack...@arm.com> wrote: >>> On Mon, Sep 18 2017 at 22:15, Joel Fernandes wrote: > [..] >>>>> IIUC, if wake_affine() behaves correctly

Re: [RFC] sched/fair: Use wake_q length as a hint for wake_wide

Hi Joel, Sorry I didn't see your comments on the code before, I think it's orthoganal to the other thread about the overall design so I'll just respond here. On Tue, Sep 19 2017 at 05:15, Joel Fernandes wrote: > Hi Brendan, > > On Fri, Aug 11, 2017 at 2:45 AM, Brendan Jackman [snip] &

Re: [PATCH] sched/fair: Force balancing on nohz balance if local group has capacity

Hi Peter, Josef, Do you have any thoughts on this one? On Mon, Aug 07 2017 at 16:39, Brendan Jackman wrote: > The "goto force_balance" here is intended to mitigate the fact that > avg_load calculations can result in bad placement decisions when > priority is asymmetrical

Re: [PATCH v2] sched/fair: Sync task util before slow-path wakeup

Hi Peter, Ping. Log of previous discussion: https://patchwork.kernel.org/patch/9876769/ Cheers, Brendan On Tue, Aug 08 2017 at 09:55, Brendan Jackman wrote: > We use task_util in find_idlest_group via capacity_spare_wake. This > task_util is updated in wake_cap. However wa

[PATCH RESEND v2] sched/fair: Sync task util before slow-path wakeup

cing, we won't need the task_util and we'd just clobber the last_update_time, which is supposed to be 0. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit...@linaro.org> Cc: Josef Bacik <jo...

[PATCH RESEND] sched/fair: Force balancing on nohz balance if local group has capacity

the force_balance case means there's an upper bound on the time before we can attempt to solve the underutilization: after DIE's sd->balance_interval has passed the next nohz balance kick will help us out. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Ingo Molnar <mi...@re

[PATCH RESEND v3 0/5]

just initialise @new_cpu to @cpu instead of @prev_cpu (which is what PeterZ suggested in v1 review). In that case, some extra code could be removed in & around find_idlest_group_cpu. Brendan Jackman (5): sched/fair: Move select_task_rq_fair slow-path into its own function sched/fair

[PATCH RESEND v3 1/5] sched/fair: Move select_task_rq_fair slow-path into its own function

is added as a variable in the new function, with the same initial value as the @new_cpu in select_task_rq_fair. Suggested-by: Peter Zijlstra <pet...@infradead.org> Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> C

[PATCH RESEND v3 5/5] sched/fair: Fix use of find_idlest_group when local group is idlest

and we return @prev_cpu from select_task_rq_fair. This is fixed by initialising @new_cpu to @cpu instead of @prev_cpu. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit...@linaro.org> C

[PATCH RESEND v3 2/5] sched/fair: Remove unnecessary comparison with -1

Since commit 83a0a96a5f26 ("sched/fair: Leverage the idle state info when choosing the "idlest" cpu") find_idlest_grou_cpu (formerly find_idlest_cpu) no longer returns -1. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...

[PATCH RESEND v3 3/5] sched/fair: Fix find_idlest_group when local group is not allowed

in that case. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit...@linaro.org> Cc: Josef Bacik <jo...@toxicpanda.com> Cc: Ingo Molnar <mi...@redhat.com> Cc: Morten Rasmussen <morten.rasm

[PATCH RESEND v3 4/5] sched/fair: Fix use of find_idlest_group when no groups are allowed

for this case, and a comment to find_idlest_group. Now when find_idlest_group returns NULL, it always means that the local group is allowed and idlest. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot &

Re: [PATCH v2 5/5] sched/fair: Fix use of find_idlest_group when local group is idlest.

On Mon, Aug 28 2017 at 08:56, Vincent Guittot wrote: > On 25 August 2017 at 17:51, Brendan Jackman <brendan.jack...@arm.com> wrote: >> >> On Fri, Aug 25 2017 at 13:38, Vincent Guittot wrote: >>> On 25 August 2017 at 12:16, Brendan Jackman <brendan.jack...@arm.c

Re: [RFC] sched/fair: Use wake_q length as a hint for wake_wide

Hi PeterZ, I just got this in my inbox and noticed I didn't adress it to anyone. I meant to address it to you. On Fri, Sep 29 2017 at 17:05, Brendan Jackman wrote: > There has been a bit of discussion on this RFC, but before I do any > more work I'd really like your input on the basi

Re: [RFC] sched/fair: Use wake_q length as a hint for wake_wide

, Brendan Jackman wrote: > This patch adds a parameter to select_task_rq, sibling_count_hint > allowing the caller, where it has this information, to inform the > sched_class the number of tasks that are being woken up as part of > the same event. > > The wake_q mechanism

[PATCH 1/2] sched/fair: Remove unnecessary comparison with -1

Since 83a0a96a5f26 (sched/fair: Leverage the idle state info when choosing the "idlest" cpu) find_idlest_cpu no longer returns -1. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit

[PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

patch also re-words the check for whether the group in consideration is local, under the assumption that the first group in the sched domain is always the local one. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Ingo Molnar <mi...@redhat.com> Cc: Morten Rasmussen <mor

[PATCH 0/2] sched/fair: Tweaks for select_task_rq_fair slowpath

This patchset optimises away an unused comparison, and fixes some corner cases in the find_idlest_group path of select_task_rq_fair. Brendan Jackman (2): sched/fair: Remove unnecessary comparison with -1 sched/fair: Fix use of NULL with find_idlest_group kernel/sched/fair.c | 36

Re: [PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

On Tue, Aug 22 2017 at 04:34, Joel Fernandes wrote: > Hi Peter, > > On Mon, Aug 21, 2017 at 2:14 PM, Peter Zijlstra <pet...@infradead.org> wrote: >> On Mon, Aug 21, 2017 at 04:21:28PM +0100, Brendan Jackman wrote: >>> The current use of returning NULL from find_idl

Re: [PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

On Tue, Aug 22 2017 at 10:39, Brendan Jackman wrote: > On Tue, Aug 22 2017 at 04:34, Joel Fernandes wrote: >> Hi Peter, >> >> On Mon, Aug 21, 2017 at 2:14 PM, Peter Zijlstra <pet...@infradead.org> wrote: >>> On Mon, Aug 21, 2017 at 04:21:28PM +0100, Brendan

Re: [PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

On Tue, Aug 22 2017 at 07:48, Vincent Guittot wrote: > On 21 August 2017 at 17:21, Brendan Jackman <brendan.jack...@arm.com> wrote: >> The current use of returning NULL from find_idlest_group is broken in > [snip] >> --- >> kernel/sched/fair.c | 34 +++

Re: [PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

On Tue, Aug 22 2017 at 11:03, Peter Zijlstra wrote: > On Tue, Aug 22, 2017 at 11:39:26AM +0100, Brendan Jackman wrote: > >> However the code movement helps - I'll combine it with Vincent's >> suggestions and post a v2. > > Please also split into multiple patches, as

[PATCH v2 1/5] sched/fair: Move select_task_rq_fair slow-path into its own function

is added as a variable in the new function, with the same initial value as the @new_cpu in select_task_rq_fair. Suggested-by: Peter Zijlstra <pet...@infradead.org> Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> C

[PATCH v2 5/5] sched/fair: Fix use of find_idlest_group when local group is idlest.

-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit...@linaro.org> Cc: Josef Bacik <jo...@toxicpanda.com> Cc: Ingo Molnar <mi...@redhat.com> Cc: Morten Rasmussen <morten.rasmus...

[PATCH v2 2/5] sched/fair: Remove unnecessary comparison with -1

Since commit 83a0a96a5f26 ("sched/fair: Leverage the idle state info when choosing the "idlest" cpu") find_idlest_grou_cpu (formerly find_idlest_cpu) no longer returns -1. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...

[PATCH v2 3/5] sched/fair: Fix find_idlest_group when local group is not allowed

in that case. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit...@linaro.org> Cc: Josef Bacik <jo...@toxicpanda.com> Cc: Ingo Molnar <mi...@redhat.com> Cc: Morten Rasmussen <morten.rasm

[PATCH v2 4/5] sched/fair: Fix use of find_idlest_group when no groups are allowed

for this case, and a comment to find_idlest_group. Now when find_idlest_group returns NULL, it always means that the local group is allowed and idlest. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot &

[PATCH v2 0/5] sched/fair: Tweaks for select_task_rq_fair slowpath

erZ suggested in v1 review). In that case, some extra code could be removed in & around find_idlest_group_cpu. Brendan Jackman (5): sched/fair: Move select_task_rq_fair slow-path into its own function sched/fair: Remove unnecessary comparison with -1 sched/fair: Fix find_idlest_group

Re: [PATCH v2 5/5] sched/fair: Fix use of find_idlest_group when local group is idlest.

On Fri, Aug 25 2017 at 13:38, Vincent Guittot wrote: > On 25 August 2017 at 12:16, Brendan Jackman <brendan.jack...@arm.com> wrote: >> find_idlest_group currently returns NULL when the local group is >> idlest. The caller then continues the find_idlest_group searc

Re: [PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

Hi Josef, Thanks for taking a look. On Mon, Aug 21 2017 at 17:26, Josef Bacik wrote: > On Mon, Aug 21, 2017 at 04:21:28PM +0100, Brendan Jackman wrote: [...] >> -local_group = cpumask_test_cpu(this_cpu, >> - sched_g

[PATCH v3 5/5] sched/fair: Fix use of find_idlest_group when local group is idlest

and we return @prev_cpu from select_task_rq_fair. This is fixed by initialising @new_cpu to @cpu instead of @prev_cpu. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit...@linaro.org> C

[PATCH v3 1/5] sched/fair: Move select_task_rq_fair slow-path into its own function

is added as a variable in the new function, with the same initial value as the @new_cpu in select_task_rq_fair. Suggested-by: Peter Zijlstra <pet...@infradead.org> Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> C

[PATCH v3 4/5] sched/fair: Fix use of find_idlest_group when no groups are allowed

for this case, and a comment to find_idlest_group. Now when find_idlest_group returns NULL, it always means that the local group is allowed and idlest. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot &

[PATCH v3 3/5] sched/fair: Fix find_idlest_group when local group is not allowed

in that case. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit...@linaro.org> Cc: Josef Bacik <jo...@toxicpanda.com> Cc: Ingo Molnar <mi...@redhat.com> Cc: Morten Rasmussen <morten.rasm

[PATCH v3 0/5] sched/fair: Tweaks for select_task_rq_fair slowpath

just initialise @new_cpu to @cpu instead of @prev_cpu (which is what PeterZ suggested in v1 review). In that case, some extra code could be removed in & around find_idlest_group_cpu. Brendan Jackman (5): sched/fair: Move select_task_rq_fair slow-path into its own function sched/fair

[PATCH v3 2/5] sched/fair: Remove unnecessary comparison with -1

Since commit 83a0a96a5f26 ("sched/fair: Leverage the idle state info when choosing the "idlest" cpu") find_idlest_grou_cpu (formerly find_idlest_cpu) no longer returns -1. Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> Cc: Dietmar Eggemann <dietmar.eggem...

[PATCH 0/2] sched/fair: remote load updates for idle CPUs

into the future. This field is used to determine the need for triggering the newly-added NOHZ kick. So if such newly-idle balances are happening often enough, no additional CPU wakeups are required to keep all the CPUs' loads updated. Brendan Jackman (1): sched/fair: Update blocked load

[PATCH 1/2] sched: force update of blocked load of idle cpus

edhat.com> Cc: Morten Rasmussen <morten.rasmus...@arm.com> Cc: Peter Zijlstra <pet...@infradead.org> Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> [Switched remote update interval to use PELT half life] [Moved update_blocked_averges call outside rebalance_domains

[PATCH 2/2] sched/fair: Update blocked load from newly idle balance

the rq lock. Cc: Dietmar Eggemann <dietmar.eggem...@arm.com> Cc: Vincent Guittot <vincent.guit...@linaro.org> Cc: Ingo Molnar <mi...@redhat.com> Cc: Morten Rasmussen <morten.rasmus...@arm.com> Cc: Peter Zijlstra <pet...@infradead.org> Signed-off-by: Brendan Ja

Re: [PATCH 1/2] sched: force update of blocked load of idle cpus

Hi Vincent, On Mon, Nov 20 2017 at 09:04, Vincent Guittot wrote: > On 24 October 2017 at 14:25, Brendan Jackman <brendan.jack...@arm.com> wrote: >> @@ -9062,7 +9109,12 @@ static __latent_entropy void >> run_rebalance_domains(struct softirq_action *h) >> *

[PATCH v2 1/2] sched: force update of blocked load of idle cpus

edhat.com> Cc: Morten Rasmussen <morten.rasmus...@arm.com> Cc: Peter Zijlstra <pet...@infradead.org> Signed-off-by: Vincent Guittot <vincent.guit...@linaro.org> [Switched remote update interval to use PELT half life] [Moved update_blocked_averges call outside rebalance_domains

Re: [PATCH 1/2] sched: force update of blocked load of idle cpus

Hi Todd, On Thu, Nov 09 2017 at 19:56, Todd Kjos wrote: >> @@ -8683,6 +8692,10 @@ static void nohz_balancer_kick(void) >> >> if (test_and_set_bit(NOHZ_BALANCE_KICK, nohz_flags(ilb_cpu))) >> return; >> + >> + if (only_update) >> +

[PATCH] cpu/hotplug: Fix state name in takedown_cpu comment

CPUHP_AP_SCHED_MIGRATE_DYING doesn't exist, it looks like this was supposed to refer to CPUHP_AP_SCHED_STARTING's teardown callback i.e. sched_cpu_dying. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Sebastian Andrzej

[PATCH v2 0/2] sched/fair: remote load updates for idle CPUs

ing CPU B convert the pending/ongoing stats kick to a proper balance by clearing the NOHZ_STATS_KICK bit in nohz_kick_needed. Brendan Jackman (1): sched/fair: Update blocked load from newly idle balance Vincent Guittot (1): sched: force update of blocked load of idle cpus kernel/sc

[PATCH v2 2/2] sched/fair: Update blocked load from newly idle balance

.@infradead.org> Signed-off-by: Brendan Jackman <brendan.jack...@arm.com> --- kernel/sched/core.c | 1 + kernel/sched/fair.c | 44 ++-- kernel/sched/sched.h | 1 + 3 files changed, 40 insertions(+), 6 deletions(-) diff --git a/kernel/sche

Re: [PATCH RFC 5/5] sched/fair: remove impossible condition from find_idlest_group_cpu

edhat.com> > Cc: Peter Zijlstra <pet...@infradead.org> > Cc: Brendan Jackman <brendan.jack...@arm.com> > Cc: Dietmar <dietmar.eggem...@arm.com> > Signed-off-by: Joel Fernandes <joe...@google.com> FWIW: Reviewed-by: Brendan Jackman <brendan.jack...@arm.com>

Re: [PATCH v2 5/5] sched/fair: Fix use of find_idlest_group when local group is idlest.

On Mon, Aug 28 2017 at 08:56, Vincent Guittot wrote: > On 25 August 2017 at 17:51, Brendan Jackman wrote: >> >> On Fri, Aug 25 2017 at 13:38, Vincent Guittot wrote: >>> On 25 August 2017 at 12:16, Brendan Jackman wrote: >>>> find_idlest_group current

[PATCH v3 0/5] sched/fair: Tweaks for select_task_rq_fair slowpath

just initialise @new_cpu to @cpu instead of @prev_cpu (which is what PeterZ suggested in v1 review). In that case, some extra code could be removed in & around find_idlest_group_cpu. Brendan Jackman (5): sched/fair: Move select_task_rq_fair slow-path into its own function sched/fair

[PATCH v3 2/5] sched/fair: Remove unnecessary comparison with -1

Since commit 83a0a96a5f26 ("sched/fair: Leverage the idle state info when choosing the "idlest" cpu") find_idlest_grou_cpu (formerly find_idlest_cpu) no longer returns -1. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ing

[PATCH v3 3/5] sched/fair: Fix find_idlest_group when local group is not allowed

in that case. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra Reviewed-by: Vincent Guittot --- kernel/sched/fair.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/kernel/sched

[PATCH v3 5/5] sched/fair: Fix use of find_idlest_group when local group is idlest

and we return @prev_cpu from select_task_rq_fair. This is fixed by initialising @new_cpu to @cpu instead of @prev_cpu. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra --- kernel/sched/fair.c | 2

[PATCH v3 4/5] sched/fair: Fix use of find_idlest_group when no groups are allowed

for this case, and a comment to find_idlest_group. Now when find_idlest_group returns NULL, it always means that the local group is allowed and idlest. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter

[PATCH v3 1/5] sched/fair: Move select_task_rq_fair slow-path into its own function

is added as a variable in the new function, with the same initial value as the @new_cpu in select_task_rq_fair. Suggested-by: Peter Zijlstra Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra

[PATCH RESEND v2] sched/fair: Sync task util before slow-path wakeup

cing, we won't need the task_util and we'd just clobber the last_update_time, which is supposed to be 0. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra --- changes v1 -> v2: Just cosmetic

[PATCH RESEND] sched/fair: Force balancing on nohz balance if local group has capacity

the force_balance case means there's an upper bound on the time before we can attempt to solve the underutilization: after DIE's sd->balance_interval has passed the next nohz balance kick will help us out. Signed-off-by: Brendan Jackman Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra

[PATCH RESEND v3 2/5] sched/fair: Remove unnecessary comparison with -1

Since commit 83a0a96a5f26 ("sched/fair: Leverage the idle state info when choosing the "idlest" cpu") find_idlest_grou_cpu (formerly find_idlest_cpu) no longer returns -1. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ing

[PATCH RESEND v3 3/5] sched/fair: Fix find_idlest_group when local group is not allowed

in that case. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra Reviewed-by: Vincent Guittot Reviewed-by: Josef Bacik --- kernel/sched/fair.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions

[PATCH RESEND v3 0/5]

just initialise @new_cpu to @cpu instead of @prev_cpu (which is what PeterZ suggested in v1 review). In that case, some extra code could be removed in & around find_idlest_group_cpu. Brendan Jackman (5): sched/fair: Move select_task_rq_fair slow-path into its own function sched/fair

[PATCH RESEND v3 1/5] sched/fair: Move select_task_rq_fair slow-path into its own function

is added as a variable in the new function, with the same initial value as the @new_cpu in select_task_rq_fair. Suggested-by: Peter Zijlstra Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra

[PATCH RESEND v3 4/5] sched/fair: Fix use of find_idlest_group when no groups are allowed

for this case, and a comment to find_idlest_group. Now when find_idlest_group returns NULL, it always means that the local group is allowed and idlest. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter

[PATCH RESEND v3 5/5] sched/fair: Fix use of find_idlest_group when local group is idlest

and we return @prev_cpu from select_task_rq_fair. This is fixed by initialising @new_cpu to @cpu instead of @prev_cpu. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra Reviewed-by: Josef Bacik

Re: [PATCH 7/7] sched/fair: don't wake affine recently load balanced tasks

Hi Josef, I happened to be thinking about something like this while investigating a totally different issue with ARM big.LITTLE. Comment below... On Fri, Jul 14 2017 at 13:21, Josef Bacik wrote: > From: Josef Bacik > > The wake affinity logic will move tasks between two cpu's that appear to be

Re: [RFC] sched/fair: Use wake_q length as a hint for wake_wide

, Brendan Jackman wrote: > This patch adds a parameter to select_task_rq, sibling_count_hint > allowing the caller, where it has this information, to inform the > sched_class the number of tasks that are being woken up as part of > the same event. > > The wake_q mechanism

Re: [RFC] sched/fair: Use wake_q length as a hint for wake_wide

Hi PeterZ, I just got this in my inbox and noticed I didn't adress it to anyone. I meant to address it to you. On Fri, Sep 29 2017 at 17:05, Brendan Jackman wrote: > There has been a bit of discussion on this RFC, but before I do any > more work I'd really like your input on the basi

[PATCH] cpu/hotplug: Fix state name in takedown_cpu comment

CPUHP_AP_SCHED_MIGRATE_DYING doesn't exist, it looks like this was supposed to refer to CPUHP_AP_SCHED_STARTING's teardown callback i.e. sched_cpu_dying. Cc: Thomas Gleixner Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Sebastian Andrzej Siewior Cc: Boris Ostrovsky Cc: Dietmar Eggemann Cc: Quentin

Re: [PATCH RFC 5/5] sched/fair: remove impossible condition from find_idlest_group_cpu

ch > 'cpu' belongs to is chosen. So we're always guaranteed to call > find_idlest_group_cpu with a group to which cpu is non-local. This makes one > of > the conditions in find_idlest_group_cpu an impossible one, which we can get > rid > off. > > Cc: Ingo Molnar > Cc: Peter Z

Re: [RFC] sched/fair: Use wake_q length as a hint for wake_wide

On Mon, Sep 18 2017 at 22:15, Joel Fernandes wrote: > Hi Brendan, Hi Joel, Thanks for taking a look :) > On Fri, Aug 11, 2017 at 2:45 AM, Brendan Jackman > wrote: >> This patch adds a parameter to select_task_rq, sibling_count_hint >> allowing the caller, where it

Re: [RFC] sched/fair: Use wake_q length as a hint for wake_wide

On Wed, Sep 20 2017 at 05:06, Joel Fernandes wrote: >> On Tue, Sep 19, 2017 at 3:05 AM, Brendan Jackman >> wrote: >>> On Mon, Sep 18 2017 at 22:15, Joel Fernandes wrote: > [..] >>>>> IIUC, if wake_affine() behaves correctly this trick wouldn't be >

Re: [RFC] sched/fair: Use wake_q length as a hint for wake_wide

Hi Joel, Sorry I didn't see your comments on the code before, I think it's orthoganal to the other thread about the overall design so I'll just respond here. On Tue, Sep 19 2017 at 05:15, Joel Fernandes wrote: > Hi Brendan, > > On Fri, Aug 11, 2017 at 2:45 AM, Brendan Jackman [snip] &

Re: [PATCH v2] sched/fair: Sync task util before slow-path wakeup

Hi Peter, Ping. Log of previous discussion: https://patchwork.kernel.org/patch/9876769/ Cheers, Brendan On Tue, Aug 08 2017 at 09:55, Brendan Jackman wrote: > We use task_util in find_idlest_group via capacity_spare_wake. This > task_util is updated in wake_cap. However wa

Re: [PATCH] sched/fair: Force balancing on nohz balance if local group has capacity

Hi Peter, Josef, Do you have any thoughts on this one? On Mon, Aug 07 2017 at 16:39, Brendan Jackman wrote: > The "goto force_balance" here is intended to mitigate the fact that > avg_load calculations can result in bad placement decisions when > priority is asymmetrical

Re: [PATCH 1/2] sched: force update of blocked load of idle cpus

Hi Todd, On Thu, Nov 09 2017 at 19:56, Todd Kjos wrote: >> @@ -8683,6 +8692,10 @@ static void nohz_balancer_kick(void) >> >> if (test_and_set_bit(NOHZ_BALANCE_KICK, nohz_flags(ilb_cpu))) >> return; >> + >> + if (only_update) >> +

Re: wake_wide mechanism clarification

On Wed, Aug 09 2017 at 21:22, Atish Patra wrote: > On 08/03/2017 10:05 AM, Brendan Jackman wrote: >> >> On Thu, Aug 03 2017 at 13:15, Josef Bacik wrote: >>> On Thu, Aug 03, 2017 at 11:53:19AM +0100, Brendan Jackman wrote: >>>> >>>> Hi, >>&

[RFC] sched/fair: Use wake_q length as a hint for wake_wide

have relatively few CPUs, which suggests the trade-off makes sense here. Signed-off-by: Brendan Jackman Cc: Ingo Molnar Cc: Peter Zijlstra Cc: Josef Bacik Cc: Joel Fernandes Cc: Mike Galbraith Cc: Matt Fleming --- include/linux/sched/wake_q.h | 2 ++ kernel/sched/core.c |

[PATCH] sched/fair: Force balancing on nohz balance if local group has capacity

the force_balance case means there's an upper bound on the time before we can attempt to solve the underutilization: after DIE's sd->balance_interval has passed the next nohz balance kick will help us out. Signed-off-by: Brendan Jackman Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra

[PATCH 0/2] sched/fair: Tweaks for select_task_rq_fair slowpath

This patchset optimises away an unused comparison, and fixes some corner cases in the find_idlest_group path of select_task_rq_fair. Brendan Jackman (2): sched/fair: Remove unnecessary comparison with -1 sched/fair: Fix use of NULL with find_idlest_group kernel/sched/fair.c | 36

[PATCH 1/2] sched/fair: Remove unnecessary comparison with -1

Since 83a0a96a5f26 (sched/fair: Leverage the idle state info when choosing the "idlest" cpu) find_idlest_cpu no longer returns -1. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra -

[PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

patch also re-words the check for whether the group in consideration is local, under the assumption that the first group in the sched domain is always the local one. Signed-off-by: Brendan Jackman Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra Cc: Dietmar Eggemann Cc: Vince

Re: [PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

Hi Josef, Thanks for taking a look. On Mon, Aug 21 2017 at 17:26, Josef Bacik wrote: > On Mon, Aug 21, 2017 at 04:21:28PM +0100, Brendan Jackman wrote: [...] >> -local_group = cpumask_test_cpu(this_cpu, >> - sched_g

Re: [PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

On Tue, Aug 22 2017 at 04:34, Joel Fernandes wrote: > Hi Peter, > > On Mon, Aug 21, 2017 at 2:14 PM, Peter Zijlstra wrote: >> On Mon, Aug 21, 2017 at 04:21:28PM +0100, Brendan Jackman wrote: >>> The current use of returning NULL from find_idlest_group is broken in &

Re: [PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

On Tue, Aug 22 2017 at 07:48, Vincent Guittot wrote: > On 21 August 2017 at 17:21, Brendan Jackman wrote: >> The current use of returning NULL from find_idlest_group is broken in > [snip] >> --- >> kernel/sched/fair.c | 34 +++--- >>

Re: [PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

On Tue, Aug 22 2017 at 10:39, Brendan Jackman wrote: > On Tue, Aug 22 2017 at 04:34, Joel Fernandes wrote: >> Hi Peter, >> >> On Mon, Aug 21, 2017 at 2:14 PM, Peter Zijlstra wrote: >>> On Mon, Aug 21, 2017 at 04:21:28PM +0100, Brendan Jackman wrote: >>>&

Re: [PATCH 2/2] sched/fair: Fix use of NULL with find_idlest_group

On Tue, Aug 22 2017 at 11:03, Peter Zijlstra wrote: > On Tue, Aug 22, 2017 at 11:39:26AM +0100, Brendan Jackman wrote: > >> However the code movement helps - I'll combine it with Vincent's >> suggestions and post a v2. > > Please also split into multiple patches, as

Re: [PATCH v2 5/5] sched/fair: Fix use of find_idlest_group when local group is idlest.

On Fri, Aug 25 2017 at 13:38, Vincent Guittot wrote: > On 25 August 2017 at 12:16, Brendan Jackman wrote: >> find_idlest_group currently returns NULL when the local group is >> idlest. The caller then continues the find_idlest_group search at a >> lower level of the curre

[PATCH v2] sched/fair: Sync task util before slow-path wakeup

cing, we won't need the task_util and we'd just clobber the last_update_time, which is supposed to be 0. Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra --- changes v1 -> v2: Just cosmetic

[PATCH v2 0/5] sched/fair: Tweaks for select_task_rq_fair slowpath

erZ suggested in v1 review). In that case, some extra code could be removed in & around find_idlest_group_cpu. Brendan Jackman (5): sched/fair: Move select_task_rq_fair slow-path into its own function sched/fair: Remove unnecessary comparison with -1 sched/fair: Fix find_idlest_group

[PATCH v2 1/5] sched/fair: Move select_task_rq_fair slow-path into its own function

is added as a variable in the new function, with the same initial value as the @new_cpu in select_task_rq_fair. Suggested-by: Peter Zijlstra Signed-off-by: Brendan Jackman Cc: Dietmar Eggemann Cc: Vincent Guittot Cc: Josef Bacik Cc: Ingo Molnar Cc: Morten Rasmussen Cc: Peter Zijlstra

  1   2   3   >