sched/numa: Use runnable_avg to classify node

Use runnable_avg to classify numa node state similarly to what is done for
normal load balancer. This helps to ensure that numa and normal balancers
use the same view of the state of the system.

Large arm64system: 2 nodes / 224 CPUs:

  hackbench -l (256000/#grp) -g #grp

  grp    tip/sched/core         +patchset              improvement
  1      14,008(+/- 4,99 %)     13,800(+/- 3.88 %)     1,48 %
  4       4,340(+/- 5.35 %)      4.283(+/- 4.85 %)     1,33 %
  16      3,357(+/- 0.55 %)      3.359(+/- 0.54 %)    -0,06 %
  32      3,050(+/- 0.94 %)      3.039(+/- 1,06 %)     0,38 %
  64      2.968(+/- 1,85 %)      3.006(+/- 2.92 %)    -1.27 %
  128     3,290(+/-12.61 %)      3,108(+/- 5.97 %)     5.51 %
  256     3.235(+/- 3.95 %)      3,188(+/- 2.83 %)     1.45 %

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Mel Gorman <mgorman@suse.de>
Link: https://lkml.kernel.org/r/20200921072959.16317-1-vincent.guittot@linaro.org

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 33699db27ed5c6ee941c13a1947e5fa3f8ccda3d..a15deb210a171b70b71dfa21f7df78a1ea992e26 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1504,6 +1504,7 @@ enum numa_type {
 /* Cached statistics for all CPUs within a node */
 struct numa_stats {
        unsigned long load;
+       unsigned long runnable;
        unsigned long util;
        /* Total compute capacity of CPUs on a node */
        unsigned long compute_capacity;
@@ -1547,6 +1548,7 @@ struct task_numa_env {
 };
 
 static unsigned long cpu_load(struct rq *rq);
+static unsigned long cpu_runnable(struct rq *rq);
 static unsigned long cpu_util(int cpu);
 static inline long adjust_numa_imbalance(int imbalance, int src_nr_running);
 
@@ -1555,11 +1557,13 @@ numa_type numa_classify(unsigned int imbalance_pct,
                         struct numa_stats *ns)
 {
        if ((ns->nr_running > ns->weight) &&
-           ((ns->compute_capacity * 100) < (ns->util * imbalance_pct)))
+           (((ns->compute_capacity * 100) < (ns->util * imbalance_pct)) ||
+            ((ns->compute_capacity * imbalance_pct) < (ns->runnable * 100))))
                return node_overloaded;
 
        if ((ns->nr_running < ns->weight) ||
-           ((ns->compute_capacity * 100) > (ns->util * imbalance_pct)))
+           (((ns->compute_capacity * 100) > (ns->util * imbalance_pct)) &&
+            ((ns->compute_capacity * imbalance_pct) > (ns->runnable * 100))))
                return node_has_spare;
 
        return node_fully_busy;
@@ -1610,6 +1614,7 @@ static void update_numa_stats(struct task_numa_env *env,
                struct rq *rq = cpu_rq(cpu);
 
                ns->load += cpu_load(rq);
+               ns->runnable += cpu_runnable(rq);
                ns->util += cpu_util(cpu);
                ns->nr_running += rq->cfs.h_nr_running;
                ns->compute_capacity += capacity_of(cpu);