lkml.org 
[lkml]   [2012]   [Aug]   [10]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: rcu stalls seen with numasched_v2 patches applied.
> ---
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1539,6 +1539,7 @@ struct task_struct {
> #ifdef CONFIG_SMP
> u64 node_stamp; /* migration stamp */
> unsigned long numa_contrib;
> + struct callback_head numa_work;
> #endif /* CONFIG_SMP */
> #endif /* CONFIG_NUMA */
> struct rcu_head rcu;
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -816,7 +816,7 @@ void task_numa_work(struct callback_head
> struct task_struct *t, *p = current;
> int node = p->node_last;
>
> - WARN_ON_ONCE(p != container_of(work, struct task_struct, rcu));
> + WARN_ON_ONCE(p != container_of(work, struct task_struct, numa_work));
>
> /*
> * Who cares about NUMA placement when they're dying.
> @@ -891,8 +891,8 @@ void task_tick_numa(struct rq *rq, struc
> * yet and exit_task_work() is called before
> * exit_notify().
> */
> - init_task_work(&curr->rcu, task_numa_work);
> - task_work_add(curr, &curr->rcu, true);
> + init_task_work(&curr->numa_work, task_numa_work);
> + task_work_add(curr, &curr->numa_work, true);
> }
> curr->node_last = node;
> }
>

This change worked well on the 2 node machine
but on the 8 node machine it hangs with repeated messages

Pid: 60935, comm: numa01 Tainted: G W 3.5.0-numasched_v2_020812+ #4
Call Trace:
<IRQ> [<ffffffff810d32e2>] ? rcu_check_callback s+0x632/0x650
[<ffffffff81061bb8>] ? update_process_times+0x48/0x90
[<ffffffff810a2a4e>] ? tick_sched_timer+0x6e/0xe0
[<ffffffff81079c85>] ? __run_hrtimer+0x75/0x1a0
[<ffffffff810a29e0>] ? tick_setup_sched_timer+0x100/0x100
[<ffffffff8107a036>] ? hrtimer_interrupt+0xf6/0x250
[<ffffffff814f1379>] ? smp_apic_timer_interrupt+0x69/0x99
[<ffffffff814f034a>] ? apic_timer_interrupt+0x6a/0x70
<EOI> [<ffffffff811082e3>] ? wait_on_page_bit+0x73/0x80
[<ffffffff814e7992>] ? _raw_spin_lock+0x22/0x30
[<ffffffff81131bf3>] ? handle_pte_fault+0x1b3/0xca0
[<ffffffff814e64f7>] ? __schedule+0x2e7/0x710
[<ffffffff8107a9a8>] ? up_read+0x18/0x30
[<ffffffff814eb2be>] ? do_page_fault+0x13e/0x460
[<ffffffff810137ba>] ? __switch_to+0x1aa/0x460
[<ffffffff814e64f7>] ? __schedule+0x2e7/0x710
[<ffffffff814e7de5>] ? page_fault+0x25/0x30
{ 3} (t=62998 jiffies)



\
 
 \ /
  Last update: 2012-08-10 19:01    [W:0.060 / U:0.612 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site