Re: [LKP] [mm] 9bc8039e71: will-it-scale.per_thread_ops -64.1% regression

From: Waiman Long
Date: Wed Jan 30 2019 - 21:54:22 EST


On 01/30/2019 07:06 PM, Tim Chen wrote:
> On 12/27/18 6:55 PM, Waiman Long wrote:
>> On 12/27/2018 08:31 PM, Wang, Kemi wrote:
>>> Hi, Waiman
>>> Did you post that patch? Let's see if it helps.
>> I did post the patch a while ago. I will need to rebase it to a new
>> baseline. Will do that in a week or 2.
>>
>> -Longman
>>
> Waiman,
>
> In a large scale OLTP benchmark, we are also seeing a 1% loss in performance
> from patch 9bc8039e71. We'll be interested to try out your patch to
> restore some optimistic spinning on reader held sem.
>
> Thanks.
>
> Tim

I am reworking the rwsem code and reader-optimistic spinning code isn't
ready with the reworked code yet. I need a bit more time to work on that
and certainly keep you posted once it is ready for review.

Cheers,
Longman