Re: [PATCH 4/4] locking/osq_lock: The numa-aware lock memory prepare, assign and cleanup.

[Waiman Long]

On 9/19/24 05:41, yongli-os wrote:
> BTW, your patch series lacks performance data to justify the addition of
>
> > quite a lot of complexity to the core locking code. We are unlikely to
> > take this without sufficient justification.
> In the cover letter,  these is performance test result for AMD EPYC 
> 7551 and
>
> Zhaoxin KH40000. I listed the perf epoll, locktorture mutex, unixbench 
> and fxmark.
>
> What test do you think is important for the Lock performance?
>
> I will do more test in next submission.

Ah, I was not sent to/cc on the cover-letter. I only got your patches 
1-4. Yes, you did sent out a cover letter with some performance numbers 
after checking the LKML list. I will take a closer look at these 
performance numbers later as I am attending the LPC conference this week.

Cheers,
Longman