From a35b6466aabb051568b844e8c63f87a356d3d129 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Wed, 8 Aug 2012 21:46:40 +0200
Subject: [PATCH] sched, cgroup: Reduce rq->lock hold times for large cgroup
hierarchies
Peter Portante reported that for large cgroup hierarchies (and or on
large CPU counts) we get immense lock contention on rq->lock and stuff
stops working properly.
His workload was a ton of processes, each in their own cgroup,
everybody idling except for a sporadic wakeup once every so often.
It was found that:
schedule()
idle_balance()
load_balance()
local_irq_save()
double_rq_lock()
update_h_load()
walk_tg_tree(tg_load_down)
tg_load_down()
Results in an entire cgroup hierarchy walk under rq->lock for every
new-idle balance and since new-idle balance isn't throttled this
results in a lot of work while holding the rq->lock.
This patch does two things, it removes the work from under rq->lock
based on the good principle of race and pray which is widely employed
in the load-balancer as a whole. And secondly it throttles the
update_h_load() calculation to max once per jiffy.
I considered excluding update_h_load() for new-idle balance
all-together, but purely relying on regular balance passes to update
this data might not work out under some rare circumstances where the
new-idle busiest isn't the regular busiest for a while (unlikely, but
a nightmare to debug if someone hits it and suffers).
Cc: pjt@google.com
Cc: Larry Woodman <lwoodman@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Reported-by: Peter Portante <pportant@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-aaarrzfpnaam7pqrekofu8a6@git.kernel.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
kernel/sched/fair.c | 11 +++++++++--
kernel/sched/sched.h | 6 +++++-
2 files changed, 14 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d0cc03b3e70b9..c219bf8d704c5 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3387,6 +3387,14 @@ static int tg_load_down(struct task_group *tg, void *data)
static void update_h_load(long cpu)
{
+ struct rq *rq = cpu_rq(cpu);
+ unsigned long now = jiffies;
+
+ if (rq->h_load_throttle == now)
+ return;
+
+ rq->h_load_throttle = now;
+
rcu_read_lock();
walk_tg_tree(tg_load_down, tg_nop, (void *)cpu);
rcu_read_unlock();
@@ -4293,11 +4301,10 @@ static int load_balance(int this_cpu, struct rq *this_rq,
env.src_rq = busiest;
env.loop_max = min(sysctl_sched_nr_migrate, busiest->nr_running);
+ update_h_load(env.src_cpu);
more_balance:
local_irq_save(flags);
double_rq_lock(this_rq, busiest);
- if (!env.loop)
- update_h_load(env.src_cpu);
/*
* cur_ld_moved - load moved in current iteration
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c35a1a7dd4d67..531411b1044e8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -374,7 +374,11 @@ struct rq {
#ifdef CONFIG_FAIR_GROUP_SCHED
/* list of leaf cfs_rq on this cpu: */
struct list_head leaf_cfs_rq_list;
-#endif
+#ifdef CONFIG_SMP
+ unsigned long h_load_throttle;
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
#ifdef CONFIG_RT_GROUP_SCHED
struct list_head leaf_rt_rq_list;
#endif
--
GitLab