Re: [PATCH 2/2 v2] sched/wait: Introduce lock breaker in wake_up_page_bit

[Tim Chen]

On 08/29/2017 09:01 AM, Linus Torvalds wrote:
> On Tue, Aug 29, 2017 at 5:57 AM, Liang, Kan <kan.liang@xxxxxxxxx> wrote:
>>>
>>> Attached is an ALMOST COMPLETELY UNTESTED forward-port of those two
>>> patches, now without that nasty WQ_FLAG_ARRIVALS logic, because we now
>>> always put the new entries at the end of the waitqueue.
>>
>> The patches fix the long wait issue.
>>
>> Tested-by: Kan Liang <kan.liang@xxxxxxxxx>
> 
> Ok. I'm not 100% comfortable applying them at rc7, so let me think
> about it. There's only one known load triggering this, and by "known"
> I mean "not really known" since we don't even know what the heck it
> does outside of intel and whoever your customer is.
> 
> So I suspect I'll apply the patches next merge window, and we can
> maybe mark them for stable if this actually ends up mattering.
> 
> Can you tell if the problem is actually hitting _production_ use or
> was some kind of benchmark stress-test?
> 
> 

It is affecting not a production use, but the customer's acceptance
test for their systems.  So I suspect it is a stress test.

Tim