sched/core: Disable SD_PREFER_SIBLING on asymmetric CPU capacity domains

The 'prefer sibling' sched_domain flag is intended to encourage
spreading tasks to sibling sched_domain to take advantage of more caches
and core for SMT systems. It has recently been changed to be on all
non-NUMA topology level. However, spreading across domains with CPU
capacity asymmetry isn't desirable, e.g. spreading from high capacity to
low capacity CPUs even if high capacity CPUs aren't overutilized might
give access to more cache but the CPU will be slower and possibly lead
to worse overall throughput.

To prevent this, we need to remove SD_PREFER_SIBLING on the sched_domain
level immediately below SD_ASYM_CPUCAPACITY.

Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dietmar.eggemann@arm.com
Cc: gaku.inami.xh@renesas.com
Cc: valentin.schneider@arm.com
Cc: vincent.guittot@linaro.org
Link: http://lkml.kernel.org/r/1530699470-29808-13-git-send-email-morten.rasmussen@arm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 2536e1b938f9b046ac870b235542f72aac7715fd..7ffad0d3a4ebb9b0dcd9d14b912f50e46c6347e7 100644 (file)
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1126,7 +1126,7 @@ sd_init(struct sched_domain_topology_level *tl,
                                        | 0*SD_SHARE_CPUCAPACITY
                                        | 0*SD_SHARE_PKG_RESOURCES
                                        | 0*SD_SERIALIZE
-                                       | 0*SD_PREFER_SIBLING
+                                       | 1*SD_PREFER_SIBLING
                                        | 0*SD_NUMA
                                        | sd_flags
                                        ,
@@ -1152,17 +1152,21 @@ sd_init(struct sched_domain_topology_level *tl,
        if (sd->flags & SD_ASYM_CPUCAPACITY) {
                struct sched_domain *t = sd;
 
+               /*
+                * Don't attempt to spread across CPUs of different capacities.
+                */
+               if (sd->child)
+                       sd->child->flags &= ~SD_PREFER_SIBLING;
+
                for_each_lower_domain(t)
                        t->flags |= SD_BALANCE_WAKE;
        }
 
        if (sd->flags & SD_SHARE_CPUCAPACITY) {
-               sd->flags |= SD_PREFER_SIBLING;
                sd->imbalance_pct = 110;
                sd->smt_gain = 1178; /* ~15% */
 
        } else if (sd->flags & SD_SHARE_PKG_RESOURCES) {
-               sd->flags |= SD_PREFER_SIBLING;
                sd->imbalance_pct = 117;
                sd->cache_nice_tries = 1;
                sd->busy_idx = 2;
@@ -1173,6 +1177,7 @@ sd_init(struct sched_domain_topology_level *tl,
                sd->busy_idx = 3;
                sd->idle_idx = 2;
 
+               sd->flags &= ~SD_PREFER_SIBLING;
                sd->flags |= SD_SERIALIZE;
                if (sched_domains_numa_distance[tl->numa_level] > RECLAIM_DISTANCE) {
                        sd->flags &= ~(SD_BALANCE_EXEC |
@@ -1182,7 +1187,6 @@ sd_init(struct sched_domain_topology_level *tl,
 
 #endif
        } else {
-               sd->flags |= SD_PREFER_SIBLING;
                sd->cache_nice_tries = 1;
                sd->busy_idx = 2;
                sd->idle_idx = 1;