请教easy stalll on CPU的问题

来源：蜘蛛抓取(WebSpider) 时间：2017-06-16 12:37 标签： sybil stallon
Access denied |
used Cloudflare to restrict access
Please enable cookies.
What happened?
The owner of this website () has banned your access based on your browser's signature (38a24a42b16511d1-ua98).匿名用户不能发表回复！|
每天回帖即可获得10分可用分！小技巧：
你还可以输入10000个字符
(Ctrl+Enter)
请遵守CSDN，不得违反国家法律法规。
转载文章请注明出自“CSDN（www.csdn.net）”。如是商业用途请联系原作者。总数：189，共4页
最后更新时间
最后更新时间
总数：189，共4页rcu_preempt self-detected stall on CPU from 4.4-rc4, since 3.17
[][][][][][]
Subject: rcu_preempt self-detected stall on CPU from 4.4-rc4, since 3.17
From: Ross Green &&
Date: Fri, 11 Dec :33 +1100
I have been getting these stalls in kernels going back to 3.17.
This stall occurs usually under light load but often requires several
days to show itself. I have not found any simple way to trigger the
stall. Indeed heavy workloads seems not to show the fault.
Anyone have any thoughts here?
The recent patch by peterz with kernel/sched/wait.c I thought might
help the situation, but alas after a few days of running 4.4-rc4 the
following turned up.
[570] INFO: rcu_preempt self-detected stall on CPU
[178] INFO: rcu_preempt detected stalls on CPUs/tasks:
0-...: (1 ticks this GP) idle=a91/1/0
softirq=6733 fqs=0
[209] (detected by 1, t=8775 jiffies, g=576439, c=576438, q=102)
[209] Task dump for CPU 0:
[209] swapper/0
[209] Backtrace:
[239] Backtrace aborted due to bad frame pointer &c0907f54&
[239] rcu_preempt kthread starved for 8775 jiffies! g576439
cx0 s3 -&state=0x1
0-...: (1 ticks this GP) idle=a91/1/0
softirq=6733 fqs=0
(t=8775 jiffies g=576439 c=576438 q=102)
[913] rcu_preempt kthread starved for 8775 jiffies! g576439
cx2 s3 -&state=0x100
[587] Task dump for CPU 0:
[097] swapper/0
[292] Backtrace:
[313] [&c0013ea8&] (dump_backtrace) from [&c00140a4&]
(show_stack+0x18/0x1c)
r7:c:::c090aca8
[809] [&c001408c&] (show_stack) from [&c005a858&]
(sched_show_task+0xbc/0x110)
[049] [&c005a79c&] (sched_show_task) from [&c005ccd4&]
(dump_cpu_task+0x40/0x44)
[042] [&c005cc94&] (dump_cpu_task) from [&c0082268&]
(rcu_dump_cpu_stacks+0x9c/0xdc)
[157] [&c00821cc&] (rcu_dump_cpu_stacks) from [&c008637c&]
(rcu_check_callbacks+0x504/0x8e4)
r9:c:c::2eeab000
r5:c:ef7af300
[499] [&c0085e78&] (rcu_check_callbacks) from [&c00895d0&]
(update_process_times+0x40/0x6c)
r10:c009a584 r9::ef7abc4c r7:
r6:4ec3391c r5:
r4:c090aca8
[708] [&c0089590&] (update_process_times) from [&c009a580&]
(tick_sched_handle+0x50/0x54)
r5:c:ef7abe40
[983] [&c009a530&] (tick_sched_handle) from [&c009a5d4&]
(tick_sched_timer+0x50/0x94)
[895] [&c009a584&] (tick_sched_timer) from [&c0089fe4&]
(__hrtimer_run_queues+0x110/0x1a0)
r7::ef7abc40 r5:ef7abe40 r4:ef7abc00
[428] [&c0089ed4&] (__hrtimer_run_queues) from [&c008a674&]
(hrtimer_interrupt+0xac/0x1f8)
r10:ef7abc78 r9:ef7abc98 r8:ef7abc14 r7:ef7abcb8
r6:ffffffff r5:
r4:ef7abc00
[220] [&c008a5c8&] (hrtimer_interrupt) from [&c00170ec&]
(twd_handler+0x38/0x48)
r10:c:fa::ef028780
r6:c092574c r5:ef005cc0
[110] [&c00170b4&] (twd_handler) from [&c007c8f8&]
(handle_percpu_devid_irq+0x74/0x8c)
r5:ef005cc0 r4:ef7b1740
[683] [&c007c884&] (handle_percpu_devid_irq) from
[&c0078454&] (generic_handle_irq+0x2c/0x3c)
r9:fa:ef::
r5::c09013e8
[985] [&c0078428&] (generic_handle_irq) from [&c007872c&]
(__handle_domain_irq+0x64/0xbc)
[842] [&c00786c8&] (__handle_domain_irq) from [&c00094c0&]
(gic_handle_irq+0x50/0x90)
r9:fa:fa:c:fa24010c
r5:c:c0925748
[216] [&c0009470&] (gic_handle_irq) from [&c0014bd4&]
(__irq_svc+0x54/0x90)
[000] Exception stack(0xc0907f10 to 0xc0907f58)
[542] 7f00:
ef7ab390 fe00000
[542] 7f20: c0849c caf80
c084e8 c0907f6c
[029] 7f40: c0907f4c c287ac c80113 ffffffff
r9:c:c:c:ffffffff
r5::c0010ba8
[116] [&c0010b80&] (arch_cpu_idle) from [&c006f034&]
(default_idle_call+0x28/0x34)
[926] [&c006f00c&] (default_idle_call) from [&c006f154&]
(cpu_startup_entry+0x114/0x18c)
[926] [&c006f040&] (cpu_startup_entry) from [&c069fc6c&]
(rest_init+0x90/0x94)
r7:ffffffff r4:
[463] [&c069fbdc&] (rest_init) from [&c08bbcec&]
(start_kernel+0x370/0x37c)
[421] [&c08bb97c&] (start_kernel) from [&8000807c&] (0x8000807c)
To unsubscribe from this list: send the line &unsubscribe linux-kernel& in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at
Please read the FAQ at
Follow-Ups:
From: Ross Green
From: Peter Zijlstra
Prev by Date:
Next by Date:
Previous by thread:
Next by thread:
Index(es):

我要回帖

更多关于 sybil stallon 的文章

 

随机推荐