Re: [PATCH v5 1/9] sched: Extend scheduler's asym packing
From: Tim Chen
Date: Mon Oct 03 2016 - 12:49:17 EST
On Sat, Oct 01, 2016 at 11:38:04AM -0500, Nilay Vaish wrote:
> On 1 October 2016 at 06:45, Srinivas Pandruvada
> <srinivas.pandruvada@xxxxxxxxxxxxxxx> wrote:
> > diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> > index e86c4a5..08135ca 100644
> > --- a/kernel/sched/core.c
> > +++ b/kernel/sched/core.c
> > @@ -6237,7 +6237,25 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
> > WARN_ON(!sg);
> >
> > do {
> > + int cpu, max_cpu = -1, prev_cpu = -1;
> > +
> > sg->group_weight = cpumask_weight(sched_group_cpus(sg));
> > +
> > + if (!(sd->flags & SD_ASYM_PACKING))
> > + goto next;
> > +
> > + for_each_cpu(cpu, sched_group_cpus(sg)) {
> > + if (prev_cpu < 0) {
> > + prev_cpu = cpu;
> > + max_cpu = cpu;
>
> It seems that you can drop prev_cpu and put the check on max_cpu instead.
>
The usage of prev_cpu was an artifact of the evolution of this patch.
It can indeed be dropped and I've updated this change in the patch below.
Thanks.
Tim
--->8---
commit 90955f87f228ee2fe7eeffcab851eb3141a783b4
Author: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Subject: [PATCH v5 1/9 update] sched: Extend scheduler's asym packing
sched: Extend scheduler's asym packing
We generalize the scheduler's asym packing to provide an ordering
of the cpu beyond just the cpu number. This allows the use of the
ASYM_PACKING scheduler machinery to move loads to preferred CPU in a
sched domain. The preference is defined with the cpu priority
given by arch_asym_cpu_priority(cpu).
We also record the most preferred cpu in a sched group when
we build the cpu's capacity for fast lookup of preferred cpu
during load balancing.
Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@xxxxxxxxxxxxxxx>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 62c68e5..aeea288 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1052,6 +1052,8 @@ static inline int cpu_numa_flags(void)
}
#endif
+int arch_asym_cpu_priority(int cpu);
+
struct sched_domain_attr {
int relax_domain_level;
};
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e86c4a5..b2e22de 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6237,7 +6237,22 @@ static void init_sched_groups_capacity(int cpu, struct sched_domain *sd)
WARN_ON(!sg);
do {
+ int cpu, max_cpu = -1;
+
sg->group_weight = cpumask_weight(sched_group_cpus(sg));
+
+ if (!(sd->flags & SD_ASYM_PACKING))
+ goto next;
+
+ for_each_cpu(cpu, sched_group_cpus(sg)) {
+ if (max_cpu < 0)
+ max_cpu = cpu;
+ else if (sched_asym_prefer(cpu, max_cpu))
+ max_cpu = cpu;
+ }
+ sg->asym_prefer_cpu = max_cpu;
+
+next:
sg = sg->next;
} while (sg != sd->groups);
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 039de34..8e2a078 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -100,6 +100,16 @@ const_debug unsigned int sysctl_sched_migration_cost = 500000UL;
*/
unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
+#ifdef CONFIG_SMP
+/*
+ * For asym packing, by default the lower numbered cpu has higher priority.
+ */
+int __weak arch_asym_cpu_priority(int cpu)
+{
+ return -cpu;
+}
+#endif
+
#ifdef CONFIG_CFS_BANDWIDTH
/*
* Amount of runtime to allocate from global (tg) to local (per-cfs_rq) pool
@@ -6862,16 +6872,18 @@ static bool update_sd_pick_busiest(struct lb_env *env,
if (env->idle == CPU_NOT_IDLE)
return true;
/*
- * ASYM_PACKING needs to move all the work to the lowest
- * numbered CPUs in the group, therefore mark all groups
- * higher than ourself as busy.
+ * 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.
*/
- if (sgs->sum_nr_running && env->dst_cpu < group_first_cpu(sg)) {
+ if (sgs->sum_nr_running &&
+ sched_asym_prefer(env->dst_cpu, sg->asym_prefer_cpu)) {
if (!sds->busiest)
return true;
- /* Prefer to move from highest possible cpu's work */
- if (group_first_cpu(sds->busiest) < group_first_cpu(sg))
+ /* Prefer to move from lowest priority cpu's work */
+ if (sched_asym_prefer(sds->busiest->asym_prefer_cpu,
+ sg->asym_prefer_cpu))
return true;
}
@@ -7023,8 +7035,8 @@ static int check_asym_packing(struct lb_env *env, struct sd_lb_stats *sds)
if (!sds->busiest)
return 0;
- busiest_cpu = group_first_cpu(sds->busiest);
- if (env->dst_cpu > busiest_cpu)
+ busiest_cpu = sds->busiest->asym_prefer_cpu;
+ if (sched_asym_prefer(busiest_cpu, env->dst_cpu))
return 0;
env->imbalance = DIV_ROUND_CLOSEST(
@@ -7365,10 +7377,11 @@ static int need_active_balance(struct lb_env *env)
/*
* ASYM_PACKING needs to force migrate tasks from busy but
- * higher numbered CPUs in order to pack all tasks in the
- * lowest numbered CPUs.
+ * lower priority CPUs in order to pack all tasks in the
+ * highest priority CPUs.
*/
- if ((sd->flags & SD_ASYM_PACKING) && env->src_cpu > env->dst_cpu)
+ if ((sd->flags & SD_ASYM_PACKING) &&
+ sched_asym_prefer(env->dst_cpu, env->src_cpu))
return 1;
}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c64fc51..b6f449d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -532,6 +532,11 @@ struct dl_rq {
#ifdef CONFIG_SMP
+static inline bool sched_asym_prefer(int a, int b)
+{
+ return arch_asym_cpu_priority(a) > arch_asym_cpu_priority(b);
+}
+
/*
* We add the notion of a root-domain which will be used to define per-domain
* variables. Each exclusive cpuset essentially defines an island domain by
@@ -884,6 +889,7 @@ struct sched_group {
unsigned int group_weight;
struct sched_group_capacity *sgc;
+ int asym_prefer_cpu; /* cpu of highest priority in group */
/*
* The CPUs this group covers.