kernel/sched/fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
Running n CPU-bound tasks on an n CPUs platform:
- with asymmetric CPU capacity
- not being a DynamIq system (i.e. having a PKG level sched domain
without the SD_SHARE_PKG_RESOURCES flag set)
might result in a task placement where two tasks run on a big CPU
and none on a little CPU. This placement could be more optimal by
using all CPUs.
Testing platform:
Juno-r2:
- 2 big CPUs (1-2), maximum capacity of 1024
- 4 little CPUs (0,3-5), maximum capacity of 383
Testing workload ([1]):
Spawn 6 CPU-bound tasks. During the first 100ms (step 1), each tasks
is affine to a CPU, except for:
- one little CPU which is left idle.
- one big CPU which has 2 tasks affine.
After the 100ms (step 2), remove the cpumask affinity.
Before patch:
During step 2, the load balancer running from the idle CPU tags sched
domains as:
- little CPUs: 'group_has_spare'. Cf. group_has_capacity() and
group_is_overloaded(), 3 CPU-bound tasks run on a 4 CPUs
sched-domain, and the idle CPU provides enough spare capacity
regarding the imbalance_pct
- big CPUs: 'group_overloaded'. Indeed, 3 tasks run on a 2 CPUs
sched-domain, so the following path is used:
group_is_overloaded()
\-if (sgs->sum_nr_running <= sgs->group_weight) return true;
The following path which would change the migration type to
'migrate_task' is not taken:
calculate_imbalance()
\-if (env->idle != CPU_NOT_IDLE && env->imbalance == 0)
as the local group has some spare capacity, so the imbalance
is not 0.
The migration type requested is 'migrate_util' and the busiest
runqueue is the big CPU's runqueue having 2 tasks (each having a
utilization of 512). The idle little CPU cannot pull one of these
task as its capacity is too small for the task. The following path
is used:
detach_tasks()
\-case migrate_util:
\-if (util > env->imbalance) goto next;
After patch:
As the number of failed balancing attempts grows (with
'nr_balance_failed'), progressively make it easier to migrate
a big task to the idling little CPU. A similar mechanism is
used for the 'migrate_load' migration type.
Improvement:
Running the testing workload [1] with the step 2 representing
a ~10s load for a big CPU:
Before patch: ~19.3s
After patch: ~18s (-6.7%)
Similar issue reported at:
https://lore.kernel.org/lkml/20230716014125.139577-1-qyousef@layalina.io/
v1:
https://lore.kernel.org/all/20231110125902.2152380-1-pierre.gondois@arm.com/
v2:
https://lore.kernel.org/all/20231124153323.3202444-1-pierre.gondois@arm.com/
Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Pierre Gondois <pierre.gondois@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
---
Notes:
v2:
- Used Vincent's approach.
v3:
- Updated commit message.
- Added Reviewed-by tags
kernel/sched/fair.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d7a3c63a2171..9481b8cff31b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9060,7 +9060,7 @@ static int detach_tasks(struct lb_env *env)
case migrate_util:
util = task_util_est(p);
- if (util > env->imbalance)
+ if (shr_bound(util, env->sd->nr_balance_failed) > env->imbalance)
goto next;
env->imbalance -= util;
--
2.25.1Hello stable folk,
This patch was merged as:
commit 3af7524b1419 ("sched/fair: Use all little CPUs for CPU-bound workloads")
into 6.7, improving the following:
commit 0b0695f2b34a ("sched/fair: Rework load_balance()")
Would it be possible to port it to the 6.1 stable branch ?
The patch should apply cleanly by cherry-picking onto v6.1.94,
Regards,
Pierre
On 12/6/23 10:00, Pierre Gondois wrote:
> Running n CPU-bound tasks on an n CPUs platform:
> - with asymmetric CPU capacity
> - not being a DynamIq system (i.e. having a PKG level sched domain
> without the SD_SHARE_PKG_RESOURCES flag set)
> might result in a task placement where two tasks run on a big CPU
> and none on a little CPU. This placement could be more optimal by
> using all CPUs.
>
> Testing platform:
> Juno-r2:
> - 2 big CPUs (1-2), maximum capacity of 1024
> - 4 little CPUs (0,3-5), maximum capacity of 383
>
> Testing workload ([1]):
> Spawn 6 CPU-bound tasks. During the first 100ms (step 1), each tasks
> is affine to a CPU, except for:
> - one little CPU which is left idle.
> - one big CPU which has 2 tasks affine.
> After the 100ms (step 2), remove the cpumask affinity.
>
> Before patch:
> During step 2, the load balancer running from the idle CPU tags sched
> domains as:
> - little CPUs: 'group_has_spare'. Cf. group_has_capacity() and
> group_is_overloaded(), 3 CPU-bound tasks run on a 4 CPUs
> sched-domain, and the idle CPU provides enough spare capacity
> regarding the imbalance_pct
> - big CPUs: 'group_overloaded'. Indeed, 3 tasks run on a 2 CPUs
> sched-domain, so the following path is used:
> group_is_overloaded()
> \-if (sgs->sum_nr_running <= sgs->group_weight) return true;
>
> The following path which would change the migration type to
> 'migrate_task' is not taken:
> calculate_imbalance()
> \-if (env->idle != CPU_NOT_IDLE && env->imbalance == 0)
> as the local group has some spare capacity, so the imbalance
> is not 0.
>
> The migration type requested is 'migrate_util' and the busiest
> runqueue is the big CPU's runqueue having 2 tasks (each having a
> utilization of 512). The idle little CPU cannot pull one of these
> task as its capacity is too small for the task. The following path
> is used:
> detach_tasks()
> \-case migrate_util:
> \-if (util > env->imbalance) goto next;
>
> After patch:
> As the number of failed balancing attempts grows (with
> 'nr_balance_failed'), progressively make it easier to migrate
> a big task to the idling little CPU. A similar mechanism is
> used for the 'migrate_load' migration type.
>
> Improvement:
> Running the testing workload [1] with the step 2 representing
> a ~10s load for a big CPU:
> Before patch: ~19.3s
> After patch: ~18s (-6.7%)
>
> Similar issue reported at:
> https://lore.kernel.org/lkml/20230716014125.139577-1-qyousef@layalina.io/
>
> v1:
> https://lore.kernel.org/all/20231110125902.2152380-1-pierre.gondois@arm.com/
> v2:
> https://lore.kernel.org/all/20231124153323.3202444-1-pierre.gondois@arm.com/
>
> Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
> Signed-off-by: Pierre Gondois <pierre.gondois@arm.com>
> Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
> ---
>
> Notes:
> v2:
> - Used Vincent's approach.
> v3:
> - Updated commit message.
> - Added Reviewed-by tags
>
> kernel/sched/fair.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index d7a3c63a2171..9481b8cff31b 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -9060,7 +9060,7 @@ static int detach_tasks(struct lb_env *env)
> case migrate_util:
> util = task_util_est(p);
>
> - if (util > env->imbalance)
> + if (shr_bound(util, env->sd->nr_balance_failed) > env->imbalance)
> goto next;
>
> env->imbalance -= util;
Hello Sasha,
Would it be possible to pick this patch for the 6.1 stable branch ?
Or is there something I should do for this purpose ?
Regards,
Pierre
On 6/25/24 15:25, Pierre Gondois wrote:
> Hello stable folk,
>
> This patch was merged as:
> commit 3af7524b1419 ("sched/fair: Use all little CPUs for CPU-bound workloads")
> into 6.7, improving the following:
> commit 0b0695f2b34a ("sched/fair: Rework load_balance()")
>
> Would it be possible to port it to the 6.1 stable branch ?
> The patch should apply cleanly by cherry-picking onto v6.1.94,
>
> Regards,
> Pierre
>
>
> On 12/6/23 10:00, Pierre Gondois wrote:
>> Running n CPU-bound tasks on an n CPUs platform:
>> - with asymmetric CPU capacity
>> - not being a DynamIq system (i.e. having a PKG level sched domain
>> without the SD_SHARE_PKG_RESOURCES flag set)
>> might result in a task placement where two tasks run on a big CPU
>> and none on a little CPU. This placement could be more optimal by
>> using all CPUs.
>>
>> Testing platform:
>> Juno-r2:
>> - 2 big CPUs (1-2), maximum capacity of 1024
>> - 4 little CPUs (0,3-5), maximum capacity of 383
>>
>> Testing workload ([1]):
>> Spawn 6 CPU-bound tasks. During the first 100ms (step 1), each tasks
>> is affine to a CPU, except for:
>> - one little CPU which is left idle.
>> - one big CPU which has 2 tasks affine.
>> After the 100ms (step 2), remove the cpumask affinity.
>>
>> Before patch:
>> During step 2, the load balancer running from the idle CPU tags sched
>> domains as:
>> - little CPUs: 'group_has_spare'. Cf. group_has_capacity() and
>> group_is_overloaded(), 3 CPU-bound tasks run on a 4 CPUs
>> sched-domain, and the idle CPU provides enough spare capacity
>> regarding the imbalance_pct
>> - big CPUs: 'group_overloaded'. Indeed, 3 tasks run on a 2 CPUs
>> sched-domain, so the following path is used:
>> group_is_overloaded()
>> \-if (sgs->sum_nr_running <= sgs->group_weight) return true;
>>
>> The following path which would change the migration type to
>> 'migrate_task' is not taken:
>> calculate_imbalance()
>> \-if (env->idle != CPU_NOT_IDLE && env->imbalance == 0)
>> as the local group has some spare capacity, so the imbalance
>> is not 0.
>>
>> The migration type requested is 'migrate_util' and the busiest
>> runqueue is the big CPU's runqueue having 2 tasks (each having a
>> utilization of 512). The idle little CPU cannot pull one of these
>> task as its capacity is too small for the task. The following path
>> is used:
>> detach_tasks()
>> \-case migrate_util:
>> \-if (util > env->imbalance) goto next;
>>
>> After patch:
>> As the number of failed balancing attempts grows (with
>> 'nr_balance_failed'), progressively make it easier to migrate
>> a big task to the idling little CPU. A similar mechanism is
>> used for the 'migrate_load' migration type.
>>
>> Improvement:
>> Running the testing workload [1] with the step 2 representing
>> a ~10s load for a big CPU:
>> Before patch: ~19.3s
>> After patch: ~18s (-6.7%)
>>
>> Similar issue reported at:
>> https://lore.kernel.org/lkml/20230716014125.139577-1-qyousef@layalina.io/
>>
>> v1:
>> https://lore.kernel.org/all/20231110125902.2152380-1-pierre.gondois@arm.com/
>> v2:
>> https://lore.kernel.org/all/20231124153323.3202444-1-pierre.gondois@arm.com/
>>
>> Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
>> Signed-off-by: Pierre Gondois <pierre.gondois@arm.com>
>> Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
>> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
>> ---
>>
>> Notes:
>> v2:
>> - Used Vincent's approach.
>> v3:
>> - Updated commit message.
>> - Added Reviewed-by tags
>>
>> kernel/sched/fair.c | 2 +-
>> 1 file changed, 1 insertion(+), 1 deletion(-)
>>
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index d7a3c63a2171..9481b8cff31b 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -9060,7 +9060,7 @@ static int detach_tasks(struct lb_env *env)
>> case migrate_util:
>> util = task_util_est(p);
>>
>> - if (util > env->imbalance)
>> + if (shr_bound(util, env->sd->nr_balance_failed) > env->imbalance)
>> goto next;
>>
>> env->imbalance -= util;
>
On Mon, Jul 29, 2024 at 11:50:40AM +0200, Pierre Gondois wrote:
> Hello Sasha,
> Would it be possible to pick this patch for the 6.1 stable branch ?
> Or is there something I should do for this purpose ?
>
> Regards,
> Pierre
>
> On 6/25/24 15:25, Pierre Gondois wrote:
> > Hello stable folk,
> >
> > This patch was merged as:
> > commit 3af7524b1419 ("sched/fair: Use all little CPUs for CPU-bound workloads")
> > into 6.7, improving the following:
> > commit 0b0695f2b34a ("sched/fair: Rework load_balance()")
> >
> > Would it be possible to port it to the 6.1 stable branch ?
> > The patch should apply cleanly by cherry-picking onto v6.1.94,
You also forgot 5.10.y and 5.15.y which need it, I've queued it up for
those as well now, thanks.
greg k-h
On 12/06/23 10:00, Pierre Gondois wrote: > Running n CPU-bound tasks on an n CPUs platform: > - with asymmetric CPU capacity > - not being a DynamIq system (i.e. having a PKG level sched domain > without the SD_SHARE_PKG_RESOURCES flag set) > might result in a task placement where two tasks run on a big CPU > and none on a little CPU. This placement could be more optimal by > using all CPUs. > > Testing platform: > Juno-r2: > - 2 big CPUs (1-2), maximum capacity of 1024 > - 4 little CPUs (0,3-5), maximum capacity of 383 > > Testing workload ([1]): > Spawn 6 CPU-bound tasks. During the first 100ms (step 1), each tasks > is affine to a CPU, except for: > - one little CPU which is left idle. > - one big CPU which has 2 tasks affine. > After the 100ms (step 2), remove the cpumask affinity. > > Before patch: > During step 2, the load balancer running from the idle CPU tags sched > domains as: > - little CPUs: 'group_has_spare'. Cf. group_has_capacity() and > group_is_overloaded(), 3 CPU-bound tasks run on a 4 CPUs > sched-domain, and the idle CPU provides enough spare capacity > regarding the imbalance_pct > - big CPUs: 'group_overloaded'. Indeed, 3 tasks run on a 2 CPUs > sched-domain, so the following path is used: > group_is_overloaded() > \-if (sgs->sum_nr_running <= sgs->group_weight) return true; > > The following path which would change the migration type to > 'migrate_task' is not taken: > calculate_imbalance() > \-if (env->idle != CPU_NOT_IDLE && env->imbalance == 0) > as the local group has some spare capacity, so the imbalance > is not 0. > > The migration type requested is 'migrate_util' and the busiest > runqueue is the big CPU's runqueue having 2 tasks (each having a > utilization of 512). The idle little CPU cannot pull one of these > task as its capacity is too small for the task. The following path > is used: > detach_tasks() > \-case migrate_util: > \-if (util > env->imbalance) goto next; > > After patch: > As the number of failed balancing attempts grows (with > 'nr_balance_failed'), progressively make it easier to migrate > a big task to the idling little CPU. A similar mechanism is > used for the 'migrate_load' migration type. > > Improvement: > Running the testing workload [1] with the step 2 representing > a ~10s load for a big CPU: > Before patch: ~19.3s > After patch: ~18s (-6.7%) > > Similar issue reported at: > https://lore.kernel.org/lkml/20230716014125.139577-1-qyousef@layalina.io/ > > v1: > https://lore.kernel.org/all/20231110125902.2152380-1-pierre.gondois@arm.com/ > v2: > https://lore.kernel.org/all/20231124153323.3202444-1-pierre.gondois@arm.com/ > > Suggested-by: Vincent Guittot <vincent.guittot@linaro.org> > Signed-off-by: Pierre Gondois <pierre.gondois@arm.com> > Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org> > Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> > --- Thanks Pierre! I think this is a good candidate to stable. It is likely to help some folks shipping with phantom domains on impacted stable kernels. Cheers -- Qais Yousef
The following commit has been merged into the sched/core branch of tip:
Commit-ID: 3af7524b14198f5159a86692d57a9f28ec9375ce
Gitweb: https://git.kernel.org/tip/3af7524b14198f5159a86692d57a9f28ec9375ce
Author: Pierre Gondois <pierre.gondois@arm.com>
AuthorDate: Wed, 06 Dec 2023 10:00:43 +01:00
Committer: Ingo Molnar <mingo@kernel.org>
CommitterDate: Sat, 23 Dec 2023 16:06:36 +01:00
sched/fair: Use all little CPUs for CPU-bound workloads
Running N CPU-bound tasks on an N CPUs platform:
- with asymmetric CPU capacity
- not being a DynamIq system (i.e. having a PKG level sched domain
without the SD_SHARE_PKG_RESOURCES flag set)
.. might result in a task placement where two tasks run on a big CPU
and none on a little CPU. This placement could be more optimal by
using all CPUs.
Testing platform:
Juno-r2:
- 2 big CPUs (1-2), maximum capacity of 1024
- 4 little CPUs (0,3-5), maximum capacity of 383
Testing workload ([1]):
Spawn 6 CPU-bound tasks. During the first 100ms (step 1), each tasks
is affine to a CPU, except for:
- one little CPU which is left idle.
- one big CPU which has 2 tasks affine.
After the 100ms (step 2), remove the cpumask affinity.
Behavior before the patch:
During step 2, the load balancer running from the idle CPU tags sched
domains as:
- little CPUs: 'group_has_spare'. Cf. group_has_capacity() and
group_is_overloaded(), 3 CPU-bound tasks run on a 4 CPUs
sched-domain, and the idle CPU provides enough spare capacity
regarding the imbalance_pct
- big CPUs: 'group_overloaded'. Indeed, 3 tasks run on a 2 CPUs
sched-domain, so the following path is used:
group_is_overloaded()
\-if (sgs->sum_nr_running <= sgs->group_weight) return true;
The following path which would change the migration type to
'migrate_task' is not taken:
calculate_imbalance()
\-if (env->idle != CPU_NOT_IDLE && env->imbalance == 0)
as the local group has some spare capacity, so the imbalance
is not 0.
The migration type requested is 'migrate_util' and the busiest
runqueue is the big CPU's runqueue having 2 tasks (each having a
utilization of 512). The idle little CPU cannot pull one of these
task as its capacity is too small for the task. The following path
is used:
detach_tasks()
\-case migrate_util:
\-if (util > env->imbalance) goto next;
After the patch:
As the number of failed balancing attempts grows (with
'nr_balance_failed'), progressively make it easier to migrate
a big task to the idling little CPU. A similar mechanism is
used for the 'migrate_load' migration type.
Improvement:
Running the testing workload [1] with the step 2 representing
a ~10s load for a big CPU:
Before patch: ~19.3s
After patch: ~18s (-6.7%)
Similar issue reported at:
https://lore.kernel.org/lkml/20230716014125.139577-1-qyousef@layalina.io/
Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Pierre Gondois <pierre.gondois@arm.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Qais Yousef <qyousef@layalina.io>
Link: https://lore.kernel.org/r/20231206090043.634697-1-pierre.gondois@arm.com
---
kernel/sched/fair.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 823dd76..1d561b5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9071,7 +9071,7 @@ static int detach_tasks(struct lb_env *env)
case migrate_util:
util = task_util_est(p);
- if (util > env->imbalance)
+ if (shr_bound(util, env->sd->nr_balance_failed) > env->imbalance)
goto next;
env->imbalance -= util;© 2016 - 2025 Red Hat, Inc.