diff mbox series

[v4,09/24] sched/fair: Use IPCC stats to break ties between fully_busy SMT groups

Message ID 20230613042422.5344-10-ricardo.neri-calderon@linux.intel.com
State New
Headers show
Series sched: Introduce classes of tasks for load balance | expand

Commit Message

Ricardo Neri June 13, 2023, 4:24 a.m. UTC 
IPCC statistics are used during idle load balancing. After balancing one
of the siblings of an SMT core becomes idle. The remaining busy siblings
experience increased throughput. The IPCC statistics provide a measure of
the increased throughput. Use them to select the busiest group between
otherwise identical fully_busy scheduling groups. (The avg_load is not
computed in this case and is zero for both groups).

IPCC scores are not needed to break ties with non-SMT fully_busy sched
groups. SMT sched groups always need more help.

Add a stub sched_asym_ipcc_prefer() to handle !CONFIG_IPC_CLASSES.

Cc: Ben Segall <bsegall@google.com>
Cc: Daniel Bristot de Oliveira <bristot@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Ionela Voinescu <ionela.voinescu@arm.com>
Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
Cc: Len Brown <len.brown@intel.com>
Cc: Lukasz Luba <lukasz.luba@arm.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Perry Yuan <Perry.Yuan@amd.com>
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: Zhao Liu <zhao1.liu@linux.intel.com>
Cc: x86@kernel.org
Cc: linux-pm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ricardo Neri <ricardo.neri-calderon@linux.intel.com>
---
Changes since v3:
 * None

Changes since v2:
 * Introduced this patch.

Changes since v1:
 * N/A
---
 kernel/sched/fair.c | 23 ++++++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)
diff mbox series

Patch

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fb3d793fe9ad..fcec791ede4f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9580,6 +9580,12 @@  static void update_sg_lb_stats_scores(struct sg_lb_stats *sgs,
 {
 }
 
+static bool sched_asym_ipcc_prefer(struct sg_lb_stats *a,
+				   struct sg_lb_stats *b)
+{
+	return false;
+}
+
 static bool sched_asym_ipcc_pick(struct sched_group *a,
 				 struct sched_group *b,
 				 struct sg_lb_stats *a_stats,
@@ -9861,10 +9867,21 @@  static bool update_sd_pick_busiest(struct lb_env *env,
 		if (sgs->avg_load == busiest->avg_load) {
 			/*
 			 * SMT sched groups need more help than non-SMT groups.
-			 * If @sg happens to also be SMT, either choice is good.
 			 */
-			if (sds->busiest->flags & SD_SHARE_CPUCAPACITY)
-				return false;
+			if (sds->busiest->flags & SD_SHARE_CPUCAPACITY) {
+				if (!(sg->flags & SD_SHARE_CPUCAPACITY))
+					return false;
+
+				/*
+				 * Between two SMT groups, use IPCC scores to pick the
+				 * one that would improve throughput the most (only
+				 * asym_packing uses IPCC scores for now).
+				 */
+				if (sched_ipcc_enabled() &&
+				    env->sd->flags & SD_ASYM_PACKING &&
+				    sched_asym_ipcc_prefer(busiest, sgs))
+					return false;
+			}
 		}
 
 		break;