sched/numa: Use effective_load() to balance NUMA loads

When CONFIG_FAIR_GROUP_SCHED is enabled, the load that a task places
on a CPU is determined by the group the task is in. The active groups
on the source and destination CPU can be different, resulting in a
different load contribution by the same task at its source and at its
destination. As a result, the load needs to be calculated separately
for each CPU, instead of estimated once with task_h_load().

Getting this calculation right allows some workloads to converge,
where previously the last thread could get stuck on another node,
without being able to migrate to its final destination.

Signed-off-by: Rik van Riel <riel@redhat.com>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1403538378-31571-3-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f287d0b4007ad3e4cf3c066cfd90e041bbd7af5a..d6526d2cf1732499182877074c701c9f94c7c4b2 100644 (file)
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1151,6 +1151,7 @@ static void task_numa_compare(struct task_numa_env *env,
        struct rq *src_rq = cpu_rq(env->src_cpu);
        struct rq *dst_rq = cpu_rq(env->dst_cpu);
        struct task_struct *cur;
+       struct task_group *tg;
        long src_load, dst_load;
        long load;
        long imp = (groupimp > 0) ? groupimp : taskimp;
@@ -1225,14 +1226,21 @@ static void task_numa_compare(struct task_numa_env *env,
         * In the overloaded case, try and keep the load balanced.
         */
 balance:
-       load = task_h_load(env->p);
-       dst_load = env->dst_stats.load + load;
-       src_load = env->src_stats.load - load;
+       src_load = env->src_stats.load;
+       dst_load = env->dst_stats.load;
+
+       /* Calculate the effect of moving env->p from src to dst. */
+       load = env->p->se.load.weight;
+       tg = task_group(env->p);
+       src_load += effective_load(tg, env->src_cpu, -load, -load);
+       dst_load += effective_load(tg, env->dst_cpu, load, load);
 
        if (cur) {
-               load = task_h_load(cur);
-               dst_load -= load;
-               src_load += load;
+               /* Cur moves in the opposite direction. */
+               load = cur->se.load.weight;
+               tg = task_group(cur);
+               src_load += effective_load(tg, env->src_cpu, load, load);
+               dst_load += effective_load(tg, env->dst_cpu, -load, -load);
        }
 
        if (load_too_imbalanced(src_load, dst_load, env))