Re: [PATCH RT 00/12] [ANNOUNCE] 3.0.36-rt58-rc1 stable review

[Steven Rostedt]

On Thu, 2012-07-19 at 06:00 +0200, Mike Galbraith wrote:
> On Wed, 2012-07-18 at 18:39 -0400, Steven Rostedt wrote:
> 
> > Please test the patches too.
> 
> Your hotplug stress test script made x3550 M3 box fall over.  It took a
> bit, but down she went.  64 core test box fell over quickly, but that's
> very far from virgin source.. seems to be the same though.

Thanks for the report. I know a few areas in the hotplug code that can
still deadlock (but are hard to hit). But there's no easy fix for them.
Basically, the only thing we can do is redesign cpu hotplug (I think
someone is already trying to do that ;-).

But these patches do fix the main issues of cpu hotplug (albeit, making
the code even uglier).

The panic below isn't telling much. We really need to know what the
other CPUs were up to. This call trace is just telling us that one of
the CPUs is waiting for other CPUs to stop or to finish something up.

-- Steve


> 
> [  255.016043] CPU 1 MCA<0>Kernel panic - not syncing: Watchdog detected hard LOCKUP on cpu 7
> Pid: 9914, comm: migration/7 Not tainted 3.0.36-rt57 #49
> Call Trace:
>  <NMI>  [<ffffffff814a0f7b>] panic+0x9b/0x1b0
>  [<ffffffff810b0627>] watchdog_overflow_callback+0xd7/0xe0
>  [<ffffffff810c3dad>] __perf_event_overflow+0x9d/0x240
>  [<ffffffff810c066b>] ? perf_event_update_userpage+0x9b/0xe0
>  [<ffffffff810c41a4>] perf_event_overflow+0x14/0x20
>  [<ffffffff81015707>] intel_pmu_handle_irq+0x177/0x230
>  [<ffffffff814a5549>] perf_event_nmi_handler+0x39/0xc0
>  [<ffffffff814a727d>] notifier_call_chain+0x4d/0x70
>  [<ffffffff814a72e3>] __atomic_notifier_call_chain+0x43/0x60
>  [<ffffffff814a7311>] atomic_notifier_call_chain+0x11/0x20
>  [<ffffffff814a734e>] notify_die+0x2e/0x30
>  [<ffffffff814a4699>] default_do_nmi+0x39/0x200
>  [<ffffffff814a4a48>] do_nmi+0x78/0x80
>  [<ffffffff814a44d0>] nmi+0x20/0x30
>  [<ffffffff810a461a>] ? stop_machine_cpu_stop+0x6a/0xe0
>  <<EOE>>  [<ffffffff810a47f4>] cpu_stopper_thread+0xf4/0x1d0
>  [<ffffffff810a45b0>] ? wait_for_stop_done+0xa0/0xa0
>  [<ffffffff814a1397>] ? __schedule+0x2c7/0x630
>  [<ffffffff810a4700>] ? cpu_stop_queue_work+0x70/0x70
>  [<ffffffff810a4700>] ? cpu_stop_queue_work+0x70/0x70
>  [<ffffffff810702c6>] kthread+0xa6/0xb0
>  [<ffffffff81056328>] ? do_exit+0x278/0x450
>  [<ffffffff810016b2>] ? __switch_to+0xf2/0x370
>  [<ffffffff81040f15>] ? finish_task_switch+0x55/0xd0
>  [<ffffffff814aa6e4>] kernel_thread_helper+0x4/0x10
>  [<ffffffff81070220>] ? __init_kthread_worker+0x50/0x50
>  [<ffffffff814aa6e0>] ? gs_change+0x13/0x13
> 


--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/