lkml.org 
[lkml]   [2009]   [May]   [15]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
SubjectRe: kernel softlocks
From
Frederik,

Thanks. The user process also seems to lock during this run and turns
the job unkillable. Though it's hard to say whether that behavior is
the result of this softlock or the threading in the application.

The system does have a large amount of ram, its an hp superdome.

On Fri, May 15, 2009 at 8:44 AM, Frederik Deweerdt
<frederik.deweerdt@xprog.eu> wrote:
> Hi Michael,
>
> The behaviour of the soft lockup has been modified since 2.6.18 to match
> the increasing RAM found on systems (flushing large amounts of RAM to
> disk tend to keep the CPUs busy).
>
> On recent kernels, the soft lockup threshold is set to 60s whereas 2.6.18
> used a 10s threshold, IIRC.
>
> So if you do have large amounts of RAM, you can safely ignore this
> warning if you don't observe any other weird behaviour.
>
> Regards,
> Frederik
>
> On Fri, May 15, 2009 at 08:15:13AM -0400, Michael Di Domenico wrote:
>> I have a user application that seems to be soft locking the linux
>> kernel, in this case 2.6.18
>>
>> Can anyone narrow down whether this is a bug in the linux kernel (and
>> perhaps if so, whether is was fixed in a later version) or not?
>>
>> Or what this user application might have done to create this issue if
>> its not a bug?
>>
>> thanks
>> - Michael
>>
>>
>>
>>
>> BUG: soft lockup detected on CPU#33!
>>
>> Call Trace:
>> [<a000000100013b20>] show_stack+0x40/0xa0
>> sp=e00000ff000b73d0 bsp=e00000ff000b1818
>> [<a000000100013bb0>] dump_stack+0x30/0x60
>> sp=e00000ff000b75a0 bsp=e00000ff000b1800
>> [<a0000001000e5fe0>] softlockup_tick+0x240/0x280
>> sp=e00000ff000b75a0 bsp=e00000ff000b17b8
>> [<a000000100092df0>] run_local_timers+0x30/0x60
>> sp=e00000ff000b75b0 bsp=e00000ff000b17a0
>> [<a000000100092ea0>] update_process_times+0x80/0x100
>> sp=e00000ff000b75b0 bsp=e00000ff000b1770
>> [<a000000100037220>] timer_interrupt+0x180/0x360
>> sp=e00000ff000b75b0 bsp=e00000ff000b1730
>> [<a0000001000e6650>] handle_IRQ_event+0x90/0x120
>> sp=e00000ff000b75b0 bsp=e00000ff000b16f0
>> [<a0000001000e6810>] __do_IRQ+0x130/0x420
>> sp=e00000ff000b75b0 bsp=e00000ff000b16a8
>> [<a000000100011630>] ia64_handle_irq+0xf0/0x1a0
>> sp=e00000ff000b75b0 bsp=e00000ff000b1678
>> [<a00000010000c020>] __ia64_leave_kernel+0x0/0x280
>> sp=e00000ff000b75b0 bsp=e00000ff000b1678
>> [<a000000100626b90>] _spin_unlock_irqrestore+0x30/0x60
>> sp=e00000ff000b7780 bsp=e00000ff000b1660
>> [<a0000001000989d0>] force_sig_info+0x130/0x160
>> sp=e00000ff000b7780 bsp=e00000ff000b1620
>> [<a00000010003c620>] ia64_handle_unaligned+0x2d00/0x2d20
>> sp=e00000ff000b7780 bsp=e00000ff000b1580
>> [<a00000010000c630>] ia64_prepare_handle_unaligned+0x30/0x60
>> sp=e00000ff000b7970 bsp=e00000ff000b1580
>> [<a00000010000c020>] __ia64_leave_kernel+0x0/0x280
>> sp=e00000ff000b7b80 bsp=e00000ff000b1580
>> [<a0000001000b9150>] exit_robust_list+0x250/0x2e0
>> sp=e00000ff000b7d50 bsp=e00000ff000b1518
>> [<a000000100081690>] do_exit+0x510/0x14a0
>> sp=e00000ff000b7d60 bsp=e00000ff000b14c0
>> [<a000000100082770>] do_group_exit+0x150/0x160
>> sp=e00000ff000b7d80 bsp=e00000ff000b1488
>> [<a000000100099a00>] get_signal_to_deliver+0x740/0x7c0
>> sp=e00000ff000b7d80 bsp=e00000ff000b1438
>> [<a0000001000341d0>] ia64_do_signal+0x90/0xde0
>> sp=e00000ff000b7d80 bsp=e00000ff000b1350
>> [<a0000001000139a0>] do_notify_resume_user+0x100/0x160
>> sp=e00000ff000b7e20 bsp=e00000ff000b1320
>> [<a00000010000c500>] notify_resume_user+0x40/0x60
>> sp=e00000ff000b7e20 bsp=e00000ff000b12d0
>> [<a00000010000c430>] skip_rbs_switch+0xe0/0x110
>> sp=e00000ff000b7e30 bsp=e00000ff000b12d0
>>
>> BUG: soft lockup detected on CPU#72!
>>
>> Call Trace:
>> [<a000000100013b20>] show_stack+0x40/0xa0
>> sp=e00000fbe5e3f3d0 bsp=e00000fbe5e39830
>> [<a000000100013bb0>] dump_stack+0x30/0x60
>> sp=e00000fbe5e3f5a0 bsp=e00000fbe5e39818
>> [<a0000001000e5fe0>] softlockup_tick+0x240/0x280
>> sp=e00000fbe5e3f5a0 bsp=e00000fbe5e397d0
>> [<a000000100092df0>] run_local_timers+0x30/0x60
>> sp=e00000fbe5e3f5b0 bsp=e00000fbe5e397b8
>> [<a000000100092ea0>] update_process_times+0x80/0x100
>> sp=e00000fbe5e3f5b0 bsp=e00000fbe5e39788
>> [<a000000100037220>] timer_interrupt+0x180/0x360
>> sp=e00000fbe5e3f5b0 bsp=e00000fbe5e39748
>> [<a0000001000e6650>] handle_IRQ_event+0x90/0x120
>> sp=e00000fbe5e3f5b0 bsp=e00000fbe5e39708
>> [<a0000001000e6810>] __do_IRQ+0x130/0x420
>> sp=e00000fbe5e3f5b0 bsp=e00000fbe5e396c0
>> [<a000000100011630>] ia64_handle_irq+0xf0/0x1a0
>> sp=e00000fbe5e3f5b0 bsp=e00000fbe5e39690
>> [<a00000010000c020>] __ia64_leave_kernel+0x0/0x280
>> sp=e00000fbe5e3f5b0 bsp=e00000fbe5e39690
>> [<a000000100009100>] ia64_spinlock_contention+0x20/0x60
>> sp=e00000fbe5e3f780 bsp=e00000fbe5e39690
>> [<a000000100626a20>] _spin_lock_irqsave+0x60/0x80
>> sp=e00000fbe5e3f780 bsp=e00000fbe5e39688
>> [<a0000001000988d0>] force_sig_info+0x30/0x160
>> sp=e00000fbe5e3f780 bsp=e00000fbe5e39648
>> [<a00000010003c620>] ia64_handle_unaligned+0x2d00/0x2d20
>> sp=e00000fbe5e3f780 bsp=e00000fbe5e395a8
>> [<a00000010000c630>] ia64_prepare_handle_unaligned+0x30/0x60
>> sp=e00000fbe5e3f970 bsp=e00000fbe5e395a8
>> [<a00000010000c020>] __ia64_leave_kernel+0x0/0x280
>> sp=e00000fbe5e3fb80 bsp=e00000fbe5e395a8
>> [<a0000001000b4ff0>] handle_futex_death+0x90/0x1a0
>> sp=e00000fbe5e3fd50 bsp=e00000fbe5e39568
>> [<a0000001000b90f0>] exit_robust_list+0x1f0/0x2e0
>> sp=e00000fbe5e3fd50 bsp=e00000fbe5e39518
>> [<a000000100081690>] do_exit+0x510/0x14a0
>> sp=e00000fbe5e3fd60 bsp=e00000fbe5e394c0
>> [<a000000100082770>] do_group_exit+0x150/0x160
>> sp=e00000fbe5e3fd80 bsp=e00000fbe5e39488
>> [<a000000100099a00>] get_signal_to_deliver+0x740/0x7c0
>> sp=e00000fbe5e3fd80 bsp=e00000fbe5e39438
>> [<a0000001000341d0>] ia64_do_signal+0x90/0xde0
>> sp=e00000fbe5e3fd80 bsp=e00000fbe5e39350
>> [<a0000001000139a0>] do_notify_resume_user+0x100/0x160
>> sp=e00000fbe5e3fe20 bsp=e00000fbe5e39320
>> [<a00000010000c500>] notify_resume_user+0x40/0x60
>> sp=e00000fbe5e3fe20 bsp=e00000fbe5e392d0
>> [<a00000010000c430>] skip_rbs_switch+0xe0/0x110
>> sp=e00000fbe5e3fe30 bsp=e00000fbe5e392d0
>>
>> BUG: soft lockup detected on CPU#104!
>>
>> Call Trace:
>> [<a000000100013b20>] show_stack+0x40/0xa0
>> sp=e00000fc4b03f7d0 bsp=e00000fc4b039730
>> [<a000000100013bb0>] dump_stack+0x30/0x60
>> sp=e00000fc4b03f9a0 bsp=e00000fc4b039718
>> [<a0000001000e5fe0>] softlockup_tick+0x240/0x280
>> sp=e00000fc4b03f9a0 bsp=e00000fc4b0396d8
>> [<a000000100092df0>] run_local_timers+0x30/0x60
>> sp=e00000fc4b03f9b0 bsp=e00000fc4b0396c0
>> [<a000000100092ea0>] update_process_times+0x80/0x100
>> sp=e00000fc4b03f9b0 bsp=e00000fc4b039690
>> [<a000000100037220>] timer_interrupt+0x180/0x360
>> sp=e00000fc4b03f9b0 bsp=e00000fc4b039650
>> [<a0000001000e6650>] handle_IRQ_event+0x90/0x120
>> sp=e00000fc4b03f9b0 bsp=e00000fc4b039610
>> [<a0000001000e6810>] __do_IRQ+0x130/0x420
>> sp=e00000fc4b03f9b0 bsp=e00000fc4b0395c0
>> [<a000000100011630>] ia64_handle_irq+0xf0/0x1a0
>> sp=e00000fc4b03f9b0 bsp=e00000fc4b039590
>> [<a00000010000c020>] __ia64_leave_kernel+0x0/0x280
>> sp=e00000fc4b03f9b0 bsp=e00000fc4b039590
>> [<a000000100004ac0>] dispatch_unaligned_handler+0x2a0/0x400
>> sp=e00000fc4b03fb80 bsp=e00000fc4b039580
>> [<a0000001000b90f0>] exit_robust_list+0x1f0/0x2e0
>> sp=e00000fc4b03fb80 bsp=e00000fc4b039530
>> --
>> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
>> the body of a message to majordomo@vger.kernel.org
>> More majordomo info at http://vger.kernel.org/majordomo-info.html
>> Please read the FAQ at http://www.tux.org/lkml/
>


\
 
 \ /
  Last update: 2009-05-15 14:57    [W:0.037 / U:0.064 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site