Hi Peter,
So this is my sample implementation of the concept of matching the CPU's
avg_idle
with the maximum time we ever spend in a new idle load balance for each domain.
This is based on our previous patch which compares avg_idle with sd->avg_cost,
but I replaced sd->avg_cost with sd->max_cost.
Since we are comparing avg_idle with sd->max_cost, the existing avg_idle would
not be accurate since it is limited based on migration_cost, so I increased the
max avg_idle to 25*sched_migration_cost. Additionally, I updated avg_idle by
calling update_avg() first. Then if the avg_idle exceeds the max, the avg_idle
is set to the max. This is to prevent avg_idle from being set to the maximum
after 1 long idle.
Since I have found idle balance to be beneficial when it is not failing to move
tasks, I was thinking we can also not skip newidle balance (regardless of what
avg_idle and max_cost are) if the previous attempt on the rq or domain
succeeded in moving tasks. I was also wondering if we should periodically reset
the max cost. Both would require an extra field to be added to either the
rq or domain structure though.
Signed-off-by: Jason Low <jason.l...@hp.com>
---
arch/metag/include/asm/topology.h | 1 +
include/linux/sched.h | 1 +
include/linux/topology.h | 3 +++
kernel/sched/core.c | 9 +++++----
kernel/sched/fair.c | 16 ++++++++++++++++
5 files changed, 26 insertions(+), 4 deletions(-)
diff --git a/arch/metag/include/asm/topology.h
b/arch/metag/include/asm/topology.h
index 23f5118..be400ad 100644
--- a/arch/metag/include/asm/topology.h
+++ b/arch/metag/include/asm/topology.h
@@ -26,6 +26,7 @@
.last_balance = jiffies, \
.balance_interval = 1, \
.nr_balance_failed = 0, \
+ .max_idle_balance_cost = 0, \
}
#define cpu_to_node(cpu) ((void)(cpu), 0)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d722490..6e89421 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -818,6 +818,7 @@ struct sched_domain {
unsigned int nr_balance_failed; /* initialise to 0 */
u64 last_update;
+ u64 max_idle_balance_cost;
#ifdef CONFIG_SCHEDSTATS
/* load_balance() stats */
diff --git a/include/linux/topology.h b/include/linux/topology.h
index d3cf0d6..e3cfe88 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -106,6 +106,7 @@ int arch_update_cpu_topology(void);
.last_balance = jiffies, \
.balance_interval = 1, \
.smt_gain = 1178, /* 15% */ \
+ .max_idle_balance_cost = 0, \
}
#endif
#endif /* CONFIG_SCHED_SMT */
@@ -135,6 +136,7 @@ int arch_update_cpu_topology(void);
, \
.last_balance = jiffies, \
.balance_interval = 1, \
+ .max_idle_balance_cost = 0, \
}
#endif
#endif /* CONFIG_SCHED_MC */
@@ -166,6 +168,7 @@ int arch_update_cpu_topology(void);
, \
.last_balance = jiffies, \
.balance_interval = 1, \
+ .max_idle_balance_cost = 0, \
}
#endif
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b7c32cb..204e02c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1343,12 +1343,13 @@ ttwu_do_wakeup(struct rq *rq, struct task_struct *p,
int wake_flags)
if (rq->idle_stamp) {
u64 delta = rq_clock(rq) - rq->idle_stamp;
- u64 max = 2*sysctl_sched_migration_cost;
+ u64 max = 25*sysctl_sched_migration_cost;
- if (delta > max)
+ update_avg(&rq->avg_idle, delta);
+
+ if (rq->avg_idle > max)
rq->avg_idle = max;
- else
- update_avg(&rq->avg_idle, delta);
+
rq->idle_stamp = 0;
}
#endif
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 9565645..1b76933 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5277,6 +5277,7 @@ void idle_balance(int this_cpu, struct rq *this_rq)
struct sched_domain *sd;
int pulled_task = 0;
unsigned long next_balance = jiffies + HZ;
+ u64 cost = 0;
this_rq->idle_stamp = rq_clock(this_rq);
@@ -5293,14 +5294,29 @@ void idle_balance(int this_cpu, struct rq *this_rq)
for_each_domain(this_cpu, sd) {
unsigned long interval;
int balance = 1;
+ u64 this_domain_balance_cost = 0;
+ u64 start_time;
if (!(sd->flags & SD_LOAD_BALANCE))
continue;
+ if (this_rq->avg_idle < sd->max_idle_balance_cost + cost)
+ break;
+
if (sd->flags & SD_BALANCE_NEWIDLE) {
+ start_time = sched_clock_cpu(smp_processor_id());
+
/* If we've pulled tasks over stop searching: */
pulled_task = load_balance(this_cpu, this_rq,
sd, CPU_NEWLY_IDLE,
&balance);
+
+ this_domain_balance_cost =
sched_clock_cpu(smp_processor_id()) - start_time;
+
+ /* Update the max idle balance cost stats for this sd */
+ if (this_domain_balance_cost >
sd->max_idle_balance_cost)
+ sd->max_idle_balance_cost =
this_domain_balance_cost;
+
+ cost += this_domain_balance_cost;
}
interval = msecs_to_jiffies(sd->balance_interval);
--
1.7.1
--
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/
