2020-11-30 14:46:56

by Mel Gorman

Subject: [PATCH] sched/fair: Clear SMT siblings after determining the core is not idle

The clearing of SMT siblings from the SIS mask before checking for an idle
core is a small but unnecessary cost. Defer the clearing of the siblings
until the scan moves to the next potential target. The cost of this was
not measured as it is borderline noise but it should be self-evident.

Signed-off-by: Mel Gorman <[email protected]>
---
kernel/sched/fair.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 0d54d69ba1a5..d9acd55d309b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6087,10 +6087,11 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
break;
}
}
- cpumask_andnot(cpus, cpus, cpu_smt_mask(core));

if (idle)
return core;
+
+ cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
}

/*

2020-11-30 14:51:58

by Vincent Guittot

Subject: Re: [PATCH] sched/fair: Clear SMT siblings after determining the core is not idle

On Mon, 30 Nov 2020 at 15:40, Mel Gorman <[email protected]> wrote:
>
> The clearing of SMT siblings from the SIS mask before checking for an idle
> core is a small but unnecessary cost. Defer the clearing of the siblings
> until the scan moves to the next potential target. The cost of this was
> not measured as it is borderline noise but it should be self-evident.

Good point

>
> Signed-off-by: Mel Gorman <[email protected]>

Reviewed-by: Vincent Guittot <[email protected]>

> ---
> kernel/sched/fair.c | 3 ++-
> 1 file changed, 2 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 0d54d69ba1a5..d9acd55d309b 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6087,10 +6087,11 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
> break;
> }
> }
> - cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
>
> if (idle)
> return core;
> +
> + cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
> }
>
> /*

2020-12-01 02:42:04

by Li, Aubrey

Subject: Re: [PATCH] sched/fair: Clear SMT siblings after determining the core is not idle

On 2020/11/30 22:47, Vincent Guittot wrote:
> On Mon, 30 Nov 2020 at 15:40, Mel Gorman <[email protected]> wrote:
>>
>> The clearing of SMT siblings from the SIS mask before checking for an idle
>> core is a small but unnecessary cost. Defer the clearing of the siblings
>> until the scan moves to the next potential target. The cost of this was
>> not measured as it is borderline noise but it should be self-evident.
>
> Good point

This is more reasonable, thanks Mel.

>
>>
>> Signed-off-by: Mel Gorman <[email protected]>
>
> Reviewed-by: Vincent Guittot <[email protected]>
>
>> ---
>> kernel/sched/fair.c | 3 ++-
>> 1 file changed, 2 insertions(+), 1 deletion(-)
>>
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index 0d54d69ba1a5..d9acd55d309b 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -6087,10 +6087,11 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
>> break;
>> }
>> }
>> - cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
>>
>> if (idle)
>> return core;
>> +
>> + cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
>> }
>>
>> /*

2020-12-01 11:06:33

by Peter Zijlstra

Subject: Re: [PATCH] sched/fair: Clear SMT siblings after determining the core is not idle

On Mon, Nov 30, 2020 at 03:47:01PM +0100, Vincent Guittot wrote:
> On Mon, 30 Nov 2020 at 15:40, Mel Gorman <[email protected]> wrote:
> >
> > The clearing of SMT siblings from the SIS mask before checking for an idle
> > core is a small but unnecessary cost. Defer the clearing of the siblings
> > until the scan moves to the next potential target. The cost of this was
> > not measured as it is borderline noise but it should be self-evident.
>
> Good point
>
> >
> > Signed-off-by: Mel Gorman <[email protected]>
>
> Reviewed-by: Vincent Guittot <[email protected]>

Thanks!

2020-12-03 09:15:51

by tip-bot2 for Alexey Makhalov

Subject: [tip: sched/core] sched/fair: Clear SMT siblings after determining the core is not idle

The following commit has been merged into the sched/core branch of tip:

Commit-ID: 82b738de57d571cd366d89e75b5fd60f3060852b
Gitweb: https://git.kernel.org/tip/82b738de57d571cd366d89e75b5fd60f3060852b
Author: Mel Gorman <[email protected]>
AuthorDate: Mon, 30 Nov 2020 14:40:20
Committer: Peter Zijlstra <[email protected]>
CommitterDate: Thu, 03 Dec 2020 10:00:36 +01:00

sched/fair: Clear SMT siblings after determining the core is not idle

The clearing of SMT siblings from the SIS mask before checking for an idle
core is a small but unnecessary cost. Defer the clearing of the siblings
until the scan moves to the next potential target. The cost of this was
not measured as it is borderline noise but it should be self-evident.

Signed-off-by: Mel Gorman <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Vincent Guittot <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
---
kernel/sched/fair.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f5dceda..efac224 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6086,10 +6086,11 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
break;
}
}
- cpumask_andnot(cpus, cpus, cpu_smt_mask(core));

if (idle)
return core;
+
+ cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
}

/*

2020-12-12 10:49:51

by tip-bot2 for Alexey Makhalov

Subject: [tip: sched/core] sched/fair: Clear SMT siblings after determining the core is not idle

The following commit has been merged into the sched/core branch of tip:

Commit-ID: 13d5a5e9f9b8515da3c04305ae1bb03ab91be7a7
Gitweb: https://git.kernel.org/tip/13d5a5e9f9b8515da3c04305ae1bb03ab91be7a7
Author: Mel Gorman <[email protected]>
AuthorDate: Mon, 30 Nov 2020 14:40:20
Committer: Ingo Molnar <[email protected]>
CommitterDate: Fri, 11 Dec 2020 10:30:38 +01:00

sched/fair: Clear SMT siblings after determining the core is not idle

The clearing of SMT siblings from the SIS mask before checking for an idle
core is a small but unnecessary cost. Defer the clearing of the siblings
until the scan moves to the next potential target. The cost of this was
not measured as it is borderline noise but it should be self-evident.

Signed-off-by: Mel Gorman <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Vincent Guittot <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]
---
kernel/sched/fair.c | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f5dceda..efac224 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6086,10 +6086,11 @@ static int select_idle_core(struct task_struct *p, struct sched_domain *sd, int
break;
}
}
- cpumask_andnot(cpus, cpus, cpu_smt_mask(core));

if (idle)
return core;
+
+ cpumask_andnot(cpus, cpus, cpu_smt_mask(core));
}

/*