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.

cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>

Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>

diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 0104e12abf726e5aea628819f7740dd32e5b66c6..8866d486278e5698126b10091560b42cf44108f8 100644 (file)
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1330,7 +1330,7 @@ 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
                                        ,
@@ -1356,17 +1356,21 @@ 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;
@@ -1377,6 +1381,7 @@ 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 |
@@ -1386,7 +1391,6 @@ 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;