Date:   Tue, 14 Mar 2023 16:54:03 -0700
From:   Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
To:     Tim Chen <tim.c.chen@linux.intel.com>
Cc:     "Peter Zijlstra (Intel)" <peterz@infradead.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Ricardo Neri <ricardo.neri@intel.com>,
        "Ravi V. Shankar" <ravi.v.shankar@intel.com>,
        Ben Segall <bsegall@google.com>,
        Daniel Bristot de Oliveira <bristot@redhat.com>,
        Dietmar Eggemann <dietmar.eggemann@arm.com>,
        Len Brown <len.brown@intel.com>, Mel Gorman <mgorman@suse.de>,
        "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>,
        Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
        Steven Rostedt <rostedt@goodmis.org>,
        Valentin Schneider <vschneid@redhat.com>,
        Ionela Voinescu <ionela.voinescu@arm.com>, x86@kernel.org,
        linux-kernel@vger.kernel.org, "Tim C . Chen" <tim.c.chen@intel.com>
Subject: Re: [PATCH v3 04/10] sched/fair: Let low-priority cores help
 high-priority busy SMT cores
Message-ID: <20230314235403.GB30287@ranerica-svr.sc.intel.com>
References: <20230207045838.11243-1-ricardo.neri-calderon@linux.intel.com>
 <20230207045838.11243-5-ricardo.neri-calderon@linux.intel.com>
 <9f3688d2d44ae766069487858bd28b5d49c19575.camel@linux.intel.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=iso-8859-1
Content-Disposition: inline
Content-Transfer-Encoding: 8bit
In-Reply-To: <9f3688d2d44ae766069487858bd28b5d49c19575.camel@linux.intel.com>
User-Agent: Mutt/1.9.4 (2018-02-28)
Precedence: bulk

On Thu, Mar 09, 2023 at 04:51:35PM -0800, Tim Chen wrote:
> On Mon, 2023-02-06 at 20:58 -0800, Ricardo Neri wrote:
> > Using asym_packing priorities within an SMT core is straightforward.
> > Just
> > follow the priorities that hardware indicates.
> > 
> > When balancing load from an SMT core, also consider the idle of its
> > siblings. Priorities do not reflect that an SMT core divides its
> > throughput
> > among all its busy siblings. They only makes sense when exactly one
> > sibling
> > is busy.
> > 
> > Indicate that active balance is needed if the destination CPU has
> > lower
> > priority than the source CPU but the latter has busy SMT siblings.
> > 
> > Make find_busiest_queue() not skip higher-priority SMT cores with
> > more than
> > busy sibling.
> > 
> > Cc: Ben Segall <bsegall@google.com>
> > Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
> > Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
> > Cc: Len Brown <len.brown@intel.com>
> > Cc: Mel Gorman <mgorman@suse.de>
> > Cc: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
> > Cc: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
> > Cc: Steven Rostedt <rostedt@goodmis.org>
> > Cc: Tim C. Chen <tim.c.chen@intel.com>
> > Cc: Valentin Schneider <vschneid@redhat.com>
> > Cc: x86@kernel.org
> > Cc: linux-kernel@vger.kernel.org
> > Suggested-by: Valentin Schneider <vschneid@redhat.com>
> > Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
> > ---
> > Changes since v2:
> > ?* Introduced this patch.
> > 
> > Changes since v1:
> > ?* N/A
> > ---
> > ?kernel/sched/fair.c | 31 ++++++++++++++++++++++++++-----
> > ?1 file changed, 26 insertions(+), 5 deletions(-)
> > 
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index 80c86462c6f6..c9d0ddfd11f2 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -10436,11 +10436,20 @@ static struct rq *find_busiest_queue(struct
> > lb_env *env,
> > ??????????????????? nr_running == 1)
> > ????????????????????????continue;
> > ?
> > -???????????????/* Make sure we only pull tasks from a CPU of lower
> > priority */
> > +???????????????/*
> > +??????????????? * Make sure we only pull tasks from a CPU of lower
> > priority
> > +??????????????? * when balancing between SMT siblings.
> > +??????????????? *
> > +??????????????? * If balancing between cores, let lower priority
> > CPUs help
> > +??????????????? * SMT cores with more than one busy sibling.
> > +??????????????? */
> > ????????????????if ((env->sd->flags & SD_ASYM_PACKING) &&
> > ??????????????????? sched_asym_prefer(i, env->dst_cpu) &&
> > -?????????????????? nr_running == 1)
> > -???????????????????????continue;
> > +?????????????????? nr_running == 1) {
> > +???????????????????????if (env->sd->flags & SD_SHARE_CPUCAPACITY ||
> > +?????????????????????????? (!(env->sd->flags & SD_SHARE_CPUCAPACITY)
> > && is_core_idle(i)))
> > +???????????????????????????????continue;
> > +???????????????}
> > ?
> > ????????????????switch (env->migration_type) {
> > ????????????????case migrate_load:
> > @@ -10530,8 +10539,20 @@ asym_active_balance(struct lb_env *env)
> > ???????? * lower priority CPUs in order to pack all tasks in the
> > ???????? * highest priority CPUs.
> > ???????? */
> > -???????return env->idle != CPU_NOT_IDLE && (env->sd->flags &
> > SD_ASYM_PACKING) &&
> > -????????????? sched_asym_prefer(env->dst_cpu, env->src_cpu);
> > +???????if (env->idle != CPU_NOT_IDLE && (env->sd->flags &
> > SD_ASYM_PACKING)) {
> > +???????????????/* Always obey priorities between SMT siblings. */
> > +???????????????if (env->sd->flags & SD_SHARE_CPUCAPACITY)
> > +???????????????????????return sched_asym_prefer(env->dst_cpu, env-
> > >src_cpu);
> > +
> > +???????????????/*
> > +??????????????? * A lower priority CPU can help an SMT core with
> > more than one
> > +??????????????? * busy sibling.
> > +??????????????? */
> > +???????????????return sched_asym_prefer(env->dst_cpu, env->src_cpu)
> > ||
> > +????????????????????? !is_core_idle(env->src_cpu);
> > +???????}
> 
> Suppose we have the Atom cores in a sched group (e.g. a cluster),
> this will pull the tasks from those core to a SMT thread even if
> its sibling thread is busy.  Suggest this change
> 
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index da1afa99cd55..b671cb0d7ab3 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -10473,9 +10473,11 @@ asym_active_balance(struct lb_env *env)
>                 /*
>                  * A lower priority CPU can help an SMT core with more than one
>                  * busy sibling.
> +                * Pull only if no SMT sibling busy.
>                  */
> -               return sched_asym_prefer(env->dst_cpu, env->src_cpu) ||
> -                      !is_core_idle(env->src_cpu);
> +               if (is_core_idle(env->dst_cpu))
> +                       return sched_asym_prefer(env->dst_cpu, env->src_cpu) ||
> +                              !is_core_idle(env->src_cpu);

Thank you Tim! Patch 3 does this check for asym_packing, but we could land
from other types of idle load balancing.

I wil integrate this change to the series.

Thanks and BR,
Ricardo