Re: [PATCH v3 5/6] sched/fair: Consider SMT in ASYM_PACKING load balance

From: Peter Zijlstra <peterz@infradead.org>
To: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
Cc: Ingo Molnar <mingo@kernel.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
	Len Brown <len.brown@intel.com>,
	Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
	Tim Chen <tim.c.chen@linux.intel.com>,
	Aubrey Li <aubrey.li@linux.intel.com>,
	"Ravi V. Shankar" <ravi.v.shankar@intel.com>,
	Ricardo Neri <ricardo.neri@intel.com>,
	Quentin Perret <qperret@google.com>,
	"Joel Fernandes (Google)" <joel@joelfernandes.org>,
	linux-kernel@vger.kernel.org, Aubrey Li <aubrey.li@intel.com>,
	Daniel Bristot de Oliveira <bristot@redhat.com>
Subject: Re: [PATCH v3 5/6] sched/fair: Consider SMT in ASYM_PACKING load balance
Date: Fri, 14 May 2021 11:47:45 +0200	[thread overview]
Message-ID: <YJ5HQR943rSFsLxw@hirez.programming.kicks-ass.net> (raw)
In-Reply-To: <20210513154909.6385-6-ricardo.neri-calderon@linux.intel.com>

On Thu, May 13, 2021 at 08:49:08AM -0700, Ricardo Neri wrote:
>  include/linux/sched/topology.h |   1 +
>  kernel/sched/fair.c            | 101 +++++++++++++++++++++++++++++++++
>  2 files changed, 102 insertions(+)
> 
> diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
> index 8f0f778b7c91..43bdb8b1e1df 100644
> --- a/include/linux/sched/topology.h
> +++ b/include/linux/sched/topology.h
> @@ -57,6 +57,7 @@ static inline int cpu_numa_flags(void)
>  #endif
>  
>  extern int arch_asym_cpu_priority(int cpu);
> +extern bool arch_asym_check_smt_siblings(void);
>  
>  struct sched_domain_attr {
>  	int relax_domain_level;
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index c8b66a5d593e..3d6cc027e6e6 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -106,6 +106,15 @@ int __weak arch_asym_cpu_priority(int cpu)
>  	return -cpu;
>  }
>  
> +/*
> + * For asym packing, first check the state of SMT siblings before deciding to
> + * pull tasks.
> + */
> +bool __weak arch_asym_check_smt_siblings(void)
> +{
> +	return false;
> +}
> +
>  /*
>   * The margin used when comparing utilization with CPU capacity.
>   *

> @@ -8458,6 +8550,9 @@ sched_asym(struct lb_env *env, struct sd_lb_stats *sds,  struct sg_lb_stats *sgs
>  	if (group == sds->local)
>  		return false;
>  
> +	if (arch_asym_check_smt_siblings())
> +		return asym_can_pull_tasks(env->dst_cpu, sds, sgs, group);
> +
>  	return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu);
>  }

So I'm thinking that this is a property of having ASYM_PACKING at a core
level, rather than some arch special. Wouldn't something like this be
more appropriate?

---

--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -57,7 +57,6 @@ static inline int cpu_numa_flags(void)
 #endif
 
 extern int arch_asym_cpu_priority(int cpu);
-extern bool arch_asym_check_smt_siblings(void);
 
 struct sched_domain_attr {
 	int relax_domain_level;
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -107,15 +107,6 @@ int __weak arch_asym_cpu_priority(int cp
 }
 
 /*
- * For asym packing, first check the state of SMT siblings before deciding to
- * pull tasks.
- */
-bool __weak arch_asym_check_smt_siblings(void)
-{
-	return false;
-}
-
-/*
  * The margin used when comparing utilization with CPU capacity.
  *
  * (default: ~20%)
@@ -8550,7 +8541,8 @@ sched_asym(struct lb_env *env, struct sd
 	if (group == sds->local)
 		return false;
 
-	if (arch_asym_check_smt_siblings())
+	if ((sds->local->flags & SD_SHARE_CPUCAPACITY) ||
+	    (group->flags & SD_SHARE_CPUCAPACITY))
 		return asym_can_pull_tasks(env->dst_cpu, sds, sgs, group);
 
 	return sched_asym_prefer(env->dst_cpu, group->asym_prefer_cpu);
