summaryrefslogtreecommitdiffstats
path: root/kernel/sched
diff options
context:
space:
mode:
authorRik van Riel <riel@redhat.com>2014-06-23 11:46:14 -0400
committerIngo Molnar <mingo@kernel.org>2014-07-05 11:17:35 +0200
commit6dc1a672ab15604947361dcd02e459effa09bad5 (patch)
tree1489a94ff9417433749d4adc181ed6952cb807c1 /kernel/sched
parent28a21745190a0ca613cab817bfe3dc65373158bf (diff)
downloadop-kernel-dev-6dc1a672ab15604947361dcd02e459effa09bad5.zip
op-kernel-dev-6dc1a672ab15604947361dcd02e459effa09bad5.tar.gz
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>
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/fair.c20
1 files changed, 14 insertions, 6 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f287d0b..d6526d2 100644
--- 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))
OpenPOWER on IntegriCloud