lkml.org 
[lkml]   [2011]   [Sep]   [28]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
SubjectRe: [PATCH v1] sched: fix nohz idle load balancer issues
From
Date
On Tue, 2011-09-27 at 21:15 -0700, Srivatsa Vaddagiri wrote:
> * Suresh Siddha <suresh.b.siddha@intel.com> [2011-09-27 16:49:36]:
>
> > I will post this patch mostly tomorrow. That patch will not use the
> > idle_at_tick check in the nohz_idle_balance(). So that should address
> > your issue in some cases if not most.
>
> Ok ..would be glad to test your change ..

Vatsa, Here is the promised patch. I haven't completely made up my mind
about this patch. Specially the change that I am doing now in
scheduler_ipi().

Initially I was planning to use resched_cpu() to trigger the
nohz_idle_balance() as part of the idle_balance(). But preemption is
disabled during idle_balance() and I don't want to do more work in
idle_balance. Thomas/PeterZ may not like that. And also the idle cpu
would have done tick_nohz_restart_sched_tick() unnecessarily etc.

So ended up with using kick_process() and the scheduler_ipi() context to
trigger the SCHED_SOFTIRQ instead of using smp call function vector
sequence (which has a deadlock scenario in the context of heavy
interrupts which I can explain in detail when I send the complete
changelog). And also I am explicitly requesting for idle balance to
address the stale idle_at_tick condition.

Anyways, this appended patch is just for your quick experiment. I will
think a bit more tomorrow morning before sending the patch with complete
changelog. Thanks.
---

Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
---
kernel/sched.c | 10 +++++++---
kernel/sched_fair.c | 25 +++----------------------
2 files changed, 10 insertions(+), 25 deletions(-)

diff --git a/kernel/sched.c b/kernel/sched.c
index c5cf15e..482b9d2 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -644,7 +644,7 @@ struct rq {

unsigned long cpu_power;

- unsigned char idle_at_tick;
+ unsigned char idle_balance;
/* For active balancing */
int post_schedule;
int active_balance;
@@ -2733,6 +2733,11 @@ void scheduler_ipi(void)
struct rq *rq = this_rq();
struct task_struct *list = xchg(&rq->wake_list, NULL);

+ if (unlikely((rq->idle == current) && rq->nohz_balance_kick)) {
+ rq->idle_balance = 1;
+ raise_softirq_irqoff(SCHED_SOFTIRQ);
+ }
+
if (!list)
return;

@@ -4257,7 +4262,7 @@ void scheduler_tick(void)
perf_event_task_tick();

#ifdef CONFIG_SMP
- rq->idle_at_tick = idle_cpu(cpu);
+ rq->idle_balance = idle_cpu(cpu);
trigger_load_balance(rq, cpu);
#endif
}
@@ -8303,7 +8308,6 @@ void __init sched_init(void)
rq_attach_root(rq, &def_root_domain);
#ifdef CONFIG_NO_HZ
rq->nohz_balance_kick = 0;
- init_sched_softirq_csd(&per_cpu(remote_sched_softirq_cb, i));
#endif
#endif
init_rq_hrtick(rq);
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index fef0bfd..bcefcb8 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -4269,22 +4269,6 @@ out_unlock:
}

#ifdef CONFIG_NO_HZ
-
-static DEFINE_PER_CPU(struct call_single_data, remote_sched_softirq_cb);
-
-static void trigger_sched_softirq(void *data)
-{
- raise_softirq_irqoff(SCHED_SOFTIRQ);
-}
-
-static inline void init_sched_softirq_csd(struct call_single_data *csd)
-{
- csd->func = trigger_sched_softirq;
- csd->info = NULL;
- csd->flags = 0;
- csd->priv = 0;
-}
-
/*
* idle load balancing details
* - One of the idle CPUs nominates itself as idle load_balancer, while
@@ -4450,11 +4434,8 @@ static void nohz_balancer_kick(int cpu)
}

if (!cpu_rq(ilb_cpu)->nohz_balance_kick) {
- struct call_single_data *cp;
-
cpu_rq(ilb_cpu)->nohz_balance_kick = 1;
- cp = &per_cpu(remote_sched_softirq_cb, cpu);
- __smp_call_function_single(ilb_cpu, cp, 0);
+ kick_process(idle_task(ilb_cpu));
}
return;
}
@@ -4687,7 +4668,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
if (time_before(now, nohz.next_balance))
return 0;

- if (rq->idle_at_tick)
+ if (idle_cpu(cpu))
return 0;

first_pick_cpu = atomic_read(&nohz.first_pick_cpu);
@@ -4723,7 +4704,7 @@ static void run_rebalance_domains(struct softirq_action *h)
{
int this_cpu = smp_processor_id();
struct rq *this_rq = cpu_rq(this_cpu);
- enum cpu_idle_type idle = this_rq->idle_at_tick ?
+ enum cpu_idle_type idle = this_rq->idle_balance ?
CPU_IDLE : CPU_NOT_IDLE;

rebalance_domains(this_cpu, idle);



\
 
 \ /
  Last update: 2011-09-29 02:49    [W:0.076 / U:0.388 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site