If many tasks sleep long time, their runnable load are zero. And if they
are waked up bursty, too light runnable load causes big imbalance among
CPU. So such benchmark, like aim9 drop 5~7%.
With this patch the losing is covered, and even is slight better.
Signed-off-by: Alex Shi <alex....@intel.com>
---
kernel/sched/fair.c | 18 ++++++++++++++++--
1 file changed, 16 insertions(+), 2 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fdb88de..c2f6e4e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3103,12 +3103,26 @@ static int wake_affine(struct sched_domain *sd, struct
task_struct *p, int sync)
unsigned long weight;
int balanced;
int runnable_avg;
+ int burst_prev = 0, burst_this = 0;
idx = sd->wake_idx;
this_cpu = smp_processor_id();
prev_cpu = task_cpu(p);
- load = source_load(prev_cpu, idx);
- this_load = target_load(this_cpu, idx);
+
+ if (cpu_rq(this_cpu)->avg_idle < sysctl_sched_migration_cost)
+ burst_this = 1;
+ if (cpu_rq(prev_cpu)->avg_idle < sysctl_sched_migration_cost)
+ burst_prev = 1;
+
+ /* use instant load on bursty waking up cpu */
+ if (!burst_prev)
+ load = source_load(prev_cpu, idx);
+ else
+ load = cpu_rq(prev_cpu)->load.weight;
+ if (!burst_this)
+ this_load = target_load(this_cpu, idx);
+ else
+ this_load = cpu_rq(this_cpu)->load.weight;
/*
* If sync wakeup then subtract the (maximum possible)
--
1.7.12
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
