Re: sched: hang in migrate_swap

From: Kirill Tkhai
Date: Fri Apr 11 2014 - 11:24:02 EST


11.04.2014, 18:33, "Sasha Levin" <sasha.levin@xxxxxxxxxx>:
> On 04/10/2014 09:38 AM, Kirill Tkhai wrote:
>
>>  10.04.2014, 11:00, "Michael wang" <wangyun@xxxxxxxxxxxxxxxxxx>:
>>>>  On 04/10/2014 11:31 AM, Sasha Levin wrote:
>>>>  [snip]
>>>>>>   I'd like to re-open this issue. It seems that something broke and I'm
>>>>>>   now seeing the same issues that have gone away 2 months with this patch
>>>>>>   again.
>>>>  A new mechanism has been designed to move the priority checking inside
>>>>  idle_balance(), including Kirill who is the designer ;-)
>>  Not sure, it's connected with my patch. But looks like, we forgot
>>  exactly stop class. Maybe this will help?
>>
>>  [PATCH] sched: Checking for stop task appearance when balancing happens
>>
>>  Just do it, like we do for other higher priority classes...
>>
>>  Signed-off-by: Kirill Tkhai <tkhai@xxxxxxxxx>
>
> I've been running with this patch for the last two days and the hang
> seems to be gone.
>
> I'll leave it running on the weekend and will update again on Monday.

Thanks for testing.

Sorry for I killed your linuxes by this lost need_resched().

>
> Thanks,
> Sasha
--
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/