Re: [LKP] Re: [mm] 10befea91b: hackbench.throughput -62.4% regression

[Rongwei Wang]

Hi, Roman

We also found the same regression of hackbench.throughput in our 
kernel-5.10, likes described in [1].

It seems that the mail thread in [2] doesn't show the last solution. So 
I wonder whether the upstream already has fix patch or solution can help 
us to solve this regression.

Thanks!

[1] 
https://lore.kernel.org/lkml/20210114025151.GA22932@xsang-OptiPlex-9020/.
[2] 
https://lore.kernel.org/lkml/YCcp7pwzlQy15v5H@xxxxxxxxxxxxxxxxxxxxxxxxxxx/#R