Re: [PATCH v3 01/10] sched/fair: clean up asym packing

2019-09-27 Thread Rik van Riel
On Thu, 2019-09-19 at 09:33 +0200, Vincent Guittot wrote:
> Clean up asym packing to follow the default load balance behavior:
> - classify the group by creating a group_asym_packing field.
> - calculate the imbalance in calculate_imbalance() instead of
> bypassing it.
> 
> We don't need to test twice same conditions anymore to detect asym
> packing
> and we consolidate the calculation of imbalance in
> calculate_imbalance().
> 
> There is no functional changes.
> 
> Signed-off-by: Vincent Guittot 

Acked-by: Rik van Riel 

-- 
All Rights Reversed.


signature.asc
Description: This is a digitally signed message part


[PATCH v3 01/10] sched/fair: clean up asym packing

2019-09-19 Thread Vincent Guittot
Clean up asym packing to follow the default load balance behavior:
- classify the group by creating a group_asym_packing field.
- calculate the imbalance in calculate_imbalance() instead of bypassing it.

We don't need to test twice same conditions anymore to detect asym packing
and we consolidate the calculation of imbalance in calculate_imbalance().

There is no functional changes.

Signed-off-by: Vincent Guittot 
---
 kernel/sched/fair.c | 63 ++---
 1 file changed, 16 insertions(+), 47 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1054d2c..3175fea 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7685,6 +7685,7 @@ struct sg_lb_stats {
unsigned int group_weight;
enum group_type group_type;
int group_no_capacity;
+   unsigned int group_asym_packing; /* Tasks should be moved to preferred 
CPU */
unsigned long group_misfit_task_load; /* A CPU has a task too big for 
its capacity */
 #ifdef CONFIG_NUMA_BALANCING
unsigned int nr_numa_running;
@@ -8139,9 +8140,17 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 * ASYM_PACKING needs to move all the work to the highest
 * prority CPUs in the group, therefore mark all groups
 * of lower priority than ourself as busy.
+*
+* This is primarily intended to used at the sibling level.  Some
+* cores like POWER7 prefer to use lower numbered SMT threads.  In the
+* case of POWER7, it can move to lower SMT modes only when higher
+* threads are idle.  When in lower SMT modes, the threads will
+* perform better since they share less core resources.  Hence when we
+* have idle threads, we want them to be the higher ones.
 */
if (sgs->sum_nr_running &&
sched_asym_prefer(env->dst_cpu, sg->asym_prefer_cpu)) {
+   sgs->group_asym_packing = 1;
if (!sds->busiest)
return true;
 
@@ -8283,51 +8292,6 @@ static inline void update_sd_lb_stats(struct lb_env 
*env, struct sd_lb_stats *sd
 }
 
 /**
- * check_asym_packing - Check to see if the group is packed into the
- * sched domain.
- *
- * This is primarily intended to used at the sibling level.  Some
- * cores like POWER7 prefer to use lower numbered SMT threads.  In the
- * case of POWER7, it can move to lower SMT modes only when higher
- * threads are idle.  When in lower SMT modes, the threads will
- * perform better since they share less core resources.  Hence when we
- * have idle threads, we want them to be the higher ones.
- *
- * This packing function is run on idle threads.  It checks to see if
- * the busiest CPU in this domain (core in the P7 case) has a higher
- * CPU number than the packing function is being run on.  Here we are
- * assuming lower CPU number will be equivalent to lower a SMT thread
- * number.
- *
- * Return: 1 when packing is required and a task should be moved to
- * this CPU.  The amount of the imbalance is returned in env->imbalance.
- *
- * @env: The load balancing environment.
- * @sds: Statistics of the sched_domain which is to be packed
- */
-static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
-{
-   int busiest_cpu;
-
-   if (!(env->sd->flags & SD_ASYM_PACKING))
-   return 0;
-
-   if (env->idle == CPU_NOT_IDLE)
-   return 0;
-
-   if (!sds->busiest)
-   return 0;
-
-   busiest_cpu = sds->busiest->asym_prefer_cpu;
-   if (sched_asym_prefer(busiest_cpu, env->dst_cpu))
-   return 0;
-
-   env->imbalance = sds->busiest_stat.group_load;
-
-   return 1;
-}
-
-/**
  * fix_small_imbalance - Calculate the minor imbalance that exists
  * amongst the groups of a sched_domain, during
  * load balancing.
@@ -8411,6 +8375,11 @@ static inline void calculate_imbalance(struct lb_env 
*env, struct sd_lb_stats *s
local = >local_stat;
busiest = >busiest_stat;
 
+   if (busiest->group_asym_packing) {
+   env->imbalance = busiest->group_load;
+   return;
+   }
+
if (busiest->group_type == group_imbalanced) {
/*
 * In the group_imb case we cannot rely on group-wide averages
@@ -8515,8 +8484,8 @@ static struct sched_group *find_busiest_group(struct 
lb_env *env)
busiest = _stat;
 
/* ASYM feature bypasses nice load balance check */
-   if (check_asym_packing(env, ))
-   return sds.busiest;
+   if (busiest->group_asym_packing)
+   goto force_balance;
 
/* There is no busy sibling group to pull tasks from */
if (!sds.busiest || busiest->sum_nr_running == 0)
-- 
2.7.4