diff mbox series

[v2,2/6] sched/topology: Record number of cores in sched group

Message ID a8acc91631a1c044ee16081bc80c1b044827c7b2.1686263351.git.tim.c.chen@linux.intel.com
State New
Headers
Series Enable Cluster Scheduling for x86 Hybrid CPUs |

Commit Message

Tim Chen June 8, 2023, 10:32 p.m. UTC 
  From: Tim C Chen <tim.c.chen@linux.intel.com>

When balancing sibling domains that have different number of cores,
tasks in respective sibling domain should be proportional to the number
of cores in each domain. In preparation of implementing such a policy,
record the number of tasks in a scheduling group.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
---
 kernel/sched/sched.h    |  1 +
 kernel/sched/topology.c | 10 +++++++++-
 2 files changed, 10 insertions(+), 1 deletion(-)

Comments

Peter Zijlstra June 12, 2023, 11:29 a.m. UTC | #1 
On Thu, Jun 08, 2023 at 03:32:28PM -0700, Tim Chen wrote:
> From: Tim C Chen <tim.c.chen@linux.intel.com>
> 
> When balancing sibling domains that have different number of cores,
> tasks in respective sibling domain should be proportional to the number
> of cores in each domain. In preparation of implementing such a policy,
> record the number of tasks in a scheduling group.
> 
> Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
> ---
>  kernel/sched/sched.h    |  1 +
>  kernel/sched/topology.c | 10 +++++++++-
>  2 files changed, 10 insertions(+), 1 deletion(-)
> 
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 3d0eb36350d2..5f7f36e45b87 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -1860,6 +1860,7 @@ struct sched_group {
>  	atomic_t		ref;
>  
>  	unsigned int		group_weight;
> +	unsigned int		cores;
>  	struct sched_group_capacity *sgc;
>  	int			asym_prefer_cpu;	/* CPU of highest priority in group */
>  	int			flags;
> diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
> index 6d5628fcebcf..6b099dbdfb39 100644
> --- a/kernel/sched/topology.c
> +++ b/kernel/sched/topology.c
> @@ -1275,14 +1275,22 @@ build_sched_groups(struct sched_domain *sd, int cpu)
>  static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
>  {
>  	struct sched_group *sg = sd->groups;
> +	struct cpumask *mask = sched_domains_tmpmask2;
>  
>  	WARN_ON(!sg);
>  
>  	do {
> -		int cpu, max_cpu = -1;
> +		int cpu, cores = 0, max_cpu = -1;
>  
>  		sg->group_weight = cpumask_weight(sched_group_span(sg));
>  
> +		cpumask_copy(mask, sched_group_span(sg));
> +		for_each_cpu(cpu, mask) {
> +			cores++;
> +			cpumask_andnot(mask, mask, cpu_smt_mask(cpu));
> +		}
> +		sg->cores = cores;
> +
>  		if (!(sd->flags & SD_ASYM_PACKING))
>  			goto next;

Just a note; not sure we want or can do anything about this, but
consider someone doing partitions like:

	[0,1] [2,3] [3,6]
	[------] [------]

That is, 3 SMT cores, and 2 partitions splitting an SMT core in two.

Then the domain trees will see either 2 or 3 but not the fully core.

I'm perfectly fine with saying: don't do that then.
Tim Chen June 12, 2023, 8:16 p.m. UTC | #2 
On Mon, 2023-06-12 at 13:29 +0200, Peter Zijlstra wrote:
> On Thu, Jun 08, 2023 at 03:32:28PM -0700, Tim Chen wrote:
> > 
> >  		sg->group_weight = cpumask_weight(sched_group_span(sg));
> >  
> > +		cpumask_copy(mask, sched_group_span(sg));
> > +		for_each_cpu(cpu, mask) {
> > +			cores++;
> > +			cpumask_andnot(mask, mask, cpu_smt_mask(cpu));
> > +		}
> > +		sg->cores = cores;
> > +
> >  		if (!(sd->flags & SD_ASYM_PACKING))
> >  			goto next;
> 
> Just a note; not sure we want or can do anything about this, but
> consider someone doing partitions like:
> 
> 	[0,1] [2,3] [3,6]
> 	[------] [------]
> 
> That is, 3 SMT cores, and 2 partitions splitting an SMT core in two.
> 
> Then the domain trees will see either 2 or 3 but not the fully core.
> 
> I'm perfectly fine with saying: don't do that then.

I also can't see a reason to split SMT between two domains.

Tim
diff mbox series

Patch

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 3d0eb36350d2..5f7f36e45b87 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1860,6 +1860,7 @@  struct sched_group {
 	atomic_t		ref;
 
 	unsigned int		group_weight;
+	unsigned int		cores;
 	struct sched_group_capacity *sgc;
 	int			asym_prefer_cpu;	/* CPU of highest priority in group */
 	int			flags;
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 6d5628fcebcf..6b099dbdfb39 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1275,14 +1275,22 @@  build_sched_groups(struct sched_domain *sd, int cpu)
 static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
 {
 	struct sched_group *sg = sd->groups;
+	struct cpumask *mask = sched_domains_tmpmask2;
 
 	WARN_ON(!sg);
 
 	do {
-		int cpu, max_cpu = -1;
+		int cpu, cores = 0, max_cpu = -1;
 
 		sg->group_weight = cpumask_weight(sched_group_span(sg));
 
+		cpumask_copy(mask, sched_group_span(sg));
+		for_each_cpu(cpu, mask) {
+			cores++;
+			cpumask_andnot(mask, mask, cpu_smt_mask(cpu));
+		}
+		sg->cores = cores;
+
 		if (!(sd->flags & SD_ASYM_PACKING))
 			goto next;